Spaces:
Running on CPU Upgrade
Running on CPU Upgrade
Deploy AIOS web (React glide grid + FastAPI slice)
Browse filesThis view is limited to 50 files because it contains too many changes. Β See raw diff
- RELEASES.json +19 -1
- VERSION +1 -1
- api/ai_enrich.py +550 -0
- api/ai_review.py +314 -9
- api/automation_engine.py +0 -0
- api/deps.py +421 -1
- api/main.py +183 -14
- api/odoo_relational.py +233 -15
- api/routes_admin.py +224 -12
- api/routes_alerts.py +137 -6
- api/routes_automation.py +648 -21
- api/routes_brand.py +140 -0
- api/routes_changes.py +85 -1
- api/routes_connectors.py +42 -13
- api/routes_customers.py +11 -0
- api/routes_feedback.py +180 -0
- api/routes_grid.py +123 -1
- api/routes_keychain.py +212 -4
- api/routes_nav.py +212 -10
- api/routes_odoo_tables.py +12 -1
- api/routes_publish.py +917 -0
- api/routes_query.py +0 -0
- api/routes_records.py +59 -12
- api/routes_shares.py +9 -1
- api/routes_slack.py +756 -0
- api/routes_starred.py +828 -0
- api/routes_statements.py +104 -3
- api/routes_tables.py +307 -44
- api/routes_usage.py +51 -0
- api/usage_ledger.py +281 -0
- api/web_agent.py +41 -23
- jobs/web_agent_job.py +117 -2
- platform/aios_grid.py +41 -1
- platform/aios_grid_fields.json +70 -0
- platform/core/alerts.py +21 -2
- platform/core/data_binding.py +270 -0
- platform/core/grid_events.py +113 -10
- platform/core/keychain.py +46 -0
- platform/core/perm_scope.py +130 -0
- platform/core/perms.py +110 -0
- platform/core/registry.py +141 -20
- platform/core/shared_overlay.py +38 -0
- platform/core/shares.py +26 -4
- platform/core/store.py +448 -57
- platform/core/user_tables.py +428 -5
- platform/core/users.py +45 -25
- platform/harness/datastore.py +23 -2
- platform/harness/tools.py +38 -9
- platform/model/topics/odoo_accounts.yml +60 -0
- platform/model/topics/odoo_agents.yml +59 -0
RELEASES.json
CHANGED
|
@@ -1,6 +1,24 @@
|
|
| 1 |
{
|
| 2 |
-
"current": "
|
| 3 |
"releases": [
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
{
|
| 5 |
"version": "v25",
|
| 6 |
"sha": "bc24829",
|
|
|
|
| 1 |
{
|
| 2 |
+
"current": "v29 (55ced50)",
|
| 3 |
"releases": [
|
| 4 |
+
{
|
| 5 |
+
"version": "v29",
|
| 6 |
+
"sha": "55ced50",
|
| 7 |
+
"date": "2026-08-18",
|
| 8 |
+
"subject": "v29: the build staging has been running since 2026-08-18 (55ced50)."
|
| 9 |
+
},
|
| 10 |
+
{
|
| 11 |
+
"version": "v28",
|
| 12 |
+
"sha": "2793e4b",
|
| 13 |
+
"date": "2026-08-18",
|
| 14 |
+
"subject": "release v28"
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"version": "v27",
|
| 18 |
+
"sha": "c05a794",
|
| 19 |
+
"date": "2026-08-18",
|
| 20 |
+
"subject": "release v27"
|
| 21 |
+
},
|
| 22 |
{
|
| 23 |
"version": "v25",
|
| 24 |
"sha": "bc24829",
|
VERSION
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
|
|
|
|
| 1 |
+
v29 (55ced50)
|
api/ai_enrich.py
ADDED
|
@@ -0,0 +1,550 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"""ai_enrich.py -- the AI ENRICHMENT column (wave 34, owner ruling R13).
|
| 2 |
+
|
| 3 |
+
R13: *"A field kind called AI enrichment: a prompt per row that populates text. Detailed
|
| 4 |
+
configuration in the field's own config, including a token-usage limit."*
|
| 5 |
+
|
| 6 |
+
WHERE THE HALVES LIVE, and why the line is drawn here rather than anywhere else:
|
| 7 |
+
|
| 8 |
+
core/user_tables.py the CONTRACT and the STORAGE -- `UT_FIELD_TYPES`, `_clean_ai_enrich`,
|
| 9 |
+
the per-cell provenance stratum, and the law about what an automatic
|
| 10 |
+
run may overwrite. It owns the store document, so it owns the marks.
|
| 11 |
+
api/ai_enrich.py THIS file: the PROMPT vocabulary, the run PLAN, and the token ceiling's
|
| 12 |
+
own report. `core` may not import upward, so anything that needs to
|
| 13 |
+
reach a vendor or an HTTP session lives here.
|
| 14 |
+
|
| 15 |
+
Everything in this module is a PURE FUNCTION of data it is handed. That is deliberate: it is the
|
| 16 |
+
half a gate can exercise without a network, a store, or a running server, which is what makes
|
| 17 |
+
`api_ai_enrich` a real gate rather than a mount check.
|
| 18 |
+
|
| 19 |
+
TOKEN ACCOUNTING, and the hole it is filling. `api/ai_review.py::decide` -- the product's only
|
| 20 |
+
other LLM entry -- has no token accounting of ANY kind: `max_tokens: 300` per call, one 20 s
|
| 21 |
+
timeout, no retry, and nothing anywhere counts what a run spent. R13 asks for a usage limit, so
|
| 22 |
+
there was nothing to build on and the ledger starts here. The two measured community complaints
|
| 23 |
+
about this feature elsewhere are both REPORTING gaps rather than capability gaps (a preview said
|
| 24 |
+
15 credits and the run spent 360; a finished run gave no completion signal), which is why
|
| 25 |
+
`ceiling_report` exists beside the ceiling itself.
|
| 26 |
+
"""
|
| 27 |
+
from __future__ import annotations
|
| 28 |
+
|
| 29 |
+
import os
|
| 30 |
+
import re
|
| 31 |
+
|
| 32 |
+
import requests
|
| 33 |
+
|
| 34 |
+
#: A prompt names other columns the way a formula does, so a user who has written one already
|
| 35 |
+
#: knows this syntax. β ONE parser, exported, because `user_tables.ai_enrich_input_hash` fingerprints
|
| 36 |
+
#: the referenced cells and a second copy of this pattern would disagree with it the first time the
|
| 37 |
+
#: token syntax gained a form ([[one-question-two-normalizers]]).
|
| 38 |
+
_REF = re.compile(r'\{([a-zA-Z0-9_]{1,60})\}')
|
| 39 |
+
|
| 40 |
+
#: What a cell can say about where its value came from. Mirrors
|
| 41 |
+
#: `user_tables.AI_ENRICH_STATES` plus the two states that are DERIVED rather than stored:
|
| 42 |
+
#: `stale` (the inputs moved since the value was written) and `empty` (nothing has run).
|
| 43 |
+
#: β Re-exported rather than re-declared: the stored vocabulary has exactly one owner.
|
| 44 |
+
CELL_STATES = ('empty', 'agent', 'human', 'stale', 'error')
|
| 45 |
+
|
| 46 |
+
#: β THERE IS DELIBERATELY NO PROVIDER LIST IN THIS FILE. The product already has TWO opinions
|
| 47 |
+
#: about provider order (`harness/analyst.PROVIDERS` says groq-first, `routes_query.
|
| 48 |
+
#: QUERY_PROVIDER_ORDER` says cerebras-first) and `W34-T37` exists to reconcile them. Declaring a
|
| 49 |
+
#: third here would make that ticket harder and this feature wrong in a new way, so the catalogue
|
| 50 |
+
#: is BORROWED from `ai_review` (`PROVIDERS` + `ladder()` + the key names + the cheap-first order
|
| 51 |
+
#: owner ruling R14 set). β The CALL is ours because the requirements differ: `ai_review` hardcodes
|
| 52 |
+
#: `max_tokens: 300` and reads no `usage`, and R13 needs a per-column ceiling and a real ledger.
|
| 53 |
+
#: One provider catalogue, two call shapes, and the reason is written down rather than inferred.
|
| 54 |
+
|
| 55 |
+
#: The run's per-cell wall clock. Separate from `ai_review.TIMEOUT_SECONDS` because a review is
|
| 56 |
+
#: one classification a person is waiting on and this is a loop over rows.
|
| 57 |
+
TIMEOUT_SECONDS = float(os.environ.get('AIOS_AI_ENRICH_TIMEOUT') or 30)
|
| 58 |
+
#: How many failing rows carry their error into the report before it is summarised. A report that
|
| 59 |
+
#: lists 900 identical `429`s is a report nobody reads.
|
| 60 |
+
MAX_REPORTED_ERRORS = 10
|
| 61 |
+
#: Bound on what one row hands the model, mirroring `ai_review`'s own two caps: a table can hold a
|
| 62 |
+
#: 32 KB JSON cell per row and no prompt needs it.
|
| 63 |
+
MAX_CELL_CHARS = 400
|
| 64 |
+
|
| 65 |
+
|
| 66 |
+
def prompt_refs(prompt):
|
| 67 |
+
"""The column keys a prompt names, in first-appearance order, de-duplicated.
|
| 68 |
+
|
| 69 |
+
`"Summarise {name} for {segment}"` -> `['name', 'segment']`.
|
| 70 |
+
"""
|
| 71 |
+
seen, out = set(), []
|
| 72 |
+
for key in _REF.findall(str(prompt or '')):
|
| 73 |
+
if key not in seen:
|
| 74 |
+
seen.add(key)
|
| 75 |
+
out.append(key)
|
| 76 |
+
return out
|
| 77 |
+
|
| 78 |
+
|
| 79 |
+
def render_prompt(prompt, row, field_keys=()):
|
| 80 |
+
"""`(text, unresolved)` -- the prompt with `{token}` replaced by this row's cells.
|
| 81 |
+
|
| 82 |
+
β AN UNKNOWN TOKEN IS REPORTED, NOT SILENTLY BLANKED. A prompt naming a column that does not
|
| 83 |
+
exist is a prompt that will quietly ask a different question on every row, and the resulting
|
| 84 |
+
text looks exactly like a correct answer. `unresolved` is what the caller shows the user;
|
| 85 |
+
R6's standing rule is the same sentence one layer up (a limit that cannot be removed must be
|
| 86 |
+
reported with its cause).
|
| 87 |
+
|
| 88 |
+
β A token naming a real column whose CELL is empty is NOT unresolved: an empty cell is data.
|
| 89 |
+
"""
|
| 90 |
+
known = set(field_keys or ())
|
| 91 |
+
unresolved = []
|
| 92 |
+
|
| 93 |
+
def _sub(match):
|
| 94 |
+
key = match.group(1)
|
| 95 |
+
if known and key not in known:
|
| 96 |
+
unresolved.append(key)
|
| 97 |
+
return match.group(0)
|
| 98 |
+
return str((row or {}).get(key, ''))
|
| 99 |
+
|
| 100 |
+
return _REF.sub(_sub, str(prompt or '')), sorted(set(unresolved))
|
| 101 |
+
|
| 102 |
+
|
| 103 |
+
def ceiling_report(spent, ceiling, rows_done, rows_total):
|
| 104 |
+
"""R6's second sentence as DATA, or None while the run is still inside its budget.
|
| 105 |
+
|
| 106 |
+
`{subject, limit, spent, effect, cause, recommendation}` -- the same shape
|
| 107 |
+
`user_tables.limit_report` returns, so the client renders one vocabulary for every limit the
|
| 108 |
+
product enforces rather than a second one for this feature.
|
| 109 |
+
|
| 110 |
+
β `effect` is `stopped`, never `truncated`. A run that quietly stopped filling cells leaves a
|
| 111 |
+
column that looks complete and is not, which is the failure the whole reporting rule is
|
| 112 |
+
arranged against. The caller STOPS and says so.
|
| 113 |
+
"""
|
| 114 |
+
if ceiling is None or spent < ceiling:
|
| 115 |
+
return None
|
| 116 |
+
left = max(0, int(rows_total or 0) - int(rows_done or 0))
|
| 117 |
+
rest = f'{left:,} rows' if left != 1 else '1 row'
|
| 118 |
+
return {
|
| 119 |
+
'subject': 'tokens',
|
| 120 |
+
'limit': int(ceiling),
|
| 121 |
+
'spent': int(spent),
|
| 122 |
+
'effect': 'stopped',
|
| 123 |
+
'cause': f'this run reached its token ceiling of {int(ceiling):,} after filling '
|
| 124 |
+
f'{int(rows_done or 0):,} of {int(rows_total or 0):,} rows',
|
| 125 |
+
'recommendation': f'raise the column\'s token limit, shorten its prompt, or run the '
|
| 126 |
+
f'remaining {rest} again. Nothing was truncated and no cell holds a '
|
| 127 |
+
f'partial answer',
|
| 128 |
+
}
|
| 129 |
+
|
| 130 |
+
|
| 131 |
+
def plan_rows(rows, col_id, config, marks, cost_of=None):
|
| 132 |
+
"""Which rows an automatic run should fill, and why the others were left alone.
|
| 133 |
+
|
| 134 |
+
Returns `{'run': [row_id, ...], 'skipped': {reason: count}, 'estimate': int}`.
|
| 135 |
+
|
| 136 |
+
β THE SELECTION IS SEPARATE FROM THE RUN ON PURPOSE. It is pure, so a gate can prove the
|
| 137 |
+
never-overwrite-a-human-edit law without a vendor, and so the client can PREVIEW a run
|
| 138 |
+
honestly before it spends anything -- which is exactly the complaint R13 cites (a preview
|
| 139 |
+
that said 15 credits against a run that spent 360).
|
| 140 |
+
|
| 141 |
+
`cost_of(row)` estimates one row's tokens; absent, the column's own ceiling is used per row,
|
| 142 |
+
which is the pessimistic direction and the right one for a preview.
|
| 143 |
+
"""
|
| 144 |
+
import core.user_tables as ut
|
| 145 |
+
|
| 146 |
+
cfg = config if isinstance(config, dict) else {}
|
| 147 |
+
prompt = str(cfg.get('prompt') or '')
|
| 148 |
+
policy = str(cfg.get('overwrite') or 'blank')
|
| 149 |
+
refs = prompt_refs(prompt)
|
| 150 |
+
per_row = int(cfg.get('maxTokens') or 0)
|
| 151 |
+
run, skipped, estimate = [], {}, 0
|
| 152 |
+
for row_id, row in (rows or {}).items():
|
| 153 |
+
row = row if isinstance(row, dict) else {}
|
| 154 |
+
mark = (marks or {}).get(str(row_id)) or {}
|
| 155 |
+
fresh = ut.ai_enrich_input_hash(prompt, row, refs)
|
| 156 |
+
has_value = bool(str(row.get(str(col_id)) or '').strip())
|
| 157 |
+
if ut.ai_enrich_may_write(mark, policy, fresh, has_value=has_value):
|
| 158 |
+
run.append(str(row_id))
|
| 159 |
+
estimate += int(cost_of(row)) if callable(cost_of) else per_row
|
| 160 |
+
else:
|
| 161 |
+
# The same predicate again, so the count a preview shows and the cells a run leaves
|
| 162 |
+
# alone can never be two different sets.
|
| 163 |
+
reason = ('human_edited' if ut.ai_enrich_human_authored(mark, has_value)
|
| 164 |
+
else 'unchanged' if has_value else 'skipped')
|
| 165 |
+
skipped[reason] = skipped.get(reason, 0) + 1
|
| 166 |
+
return {'run': run, 'skipped': skipped, 'estimate': estimate}
|
| 167 |
+
|
| 168 |
+
|
| 169 |
+
def cell_state(mark, config, row, col_id):
|
| 170 |
+
"""What ONE cell should say about itself: one of `CELL_STATES`.
|
| 171 |
+
|
| 172 |
+
β `stale` and `empty` are computed here and never stored -- see the stratum's own note in
|
| 173 |
+
`core/user_tables.py`. A stored staleness flag needs a sweep to stay true, and a sweep nobody
|
| 174 |
+
runs is a flag shipped without its writer.
|
| 175 |
+
"""
|
| 176 |
+
import core.user_tables as ut
|
| 177 |
+
|
| 178 |
+
mark = mark if isinstance(mark, dict) else {}
|
| 179 |
+
has_value = bool(str((row or {}).get(str(col_id)) or '').strip())
|
| 180 |
+
if str(mark.get('state') or '') == 'error':
|
| 181 |
+
return 'error'
|
| 182 |
+
# β THE SAME PREDICATE THE RUNNER OBEYS, called rather than restated. A cell this reports as
|
| 183 |
+
# the human's while `ai_enrich_may_write` would overwrite it is the worst of both answers.
|
| 184 |
+
if ut.ai_enrich_human_authored(mark, has_value):
|
| 185 |
+
return 'human'
|
| 186 |
+
if str(mark.get('state') or '') != 'agent':
|
| 187 |
+
return 'empty'
|
| 188 |
+
cfg = config if isinstance(config, dict) else {}
|
| 189 |
+
prompt = str(cfg.get('prompt') or '')
|
| 190 |
+
fresh = ut.ai_enrich_input_hash(prompt, row or {}, prompt_refs(prompt))
|
| 191 |
+
return 'stale' if ut.ai_enrich_is_stale(mark, fresh) else 'agent'
|
| 192 |
+
|
| 193 |
+
|
| 194 |
+
# ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ THE RUN
|
| 195 |
+
# οΏ½οΏ½οΏ½β THE LEDGER IS THE POINT OF THIS HALF. `ai_review.decide` (the product's only other LLM entry)
|
| 196 |
+
# counts nothing: it sends `max_tokens: 300` and never reads `usage` off the response, so no run in
|
| 197 |
+
# this product has ever been able to say what it cost. R13 asks for a token-usage limit, so the
|
| 198 |
+
# accounting starts here, and every leg below reads `usage` even where it is not needed, because a
|
| 199 |
+
# ledger with one blind provider is not a ledger.
|
| 200 |
+
|
| 201 |
+
|
| 202 |
+
def _usage_tokens(body):
|
| 203 |
+
"""Total tokens for one call, from whichever shape the provider answered in.
|
| 204 |
+
|
| 205 |
+
β RETURNS None WHEN THE PROVIDER DID NOT SAY, and the caller treats that as a real unknown
|
| 206 |
+
rather than as zero. A ledger that silently books an unmeasured call at 0 reports a cheaper
|
| 207 |
+
run than happened, which is exactly the cost-surprise complaint R13 cites.
|
| 208 |
+
|
| 209 |
+
ββ W35-T41 / C7 β THE READER MOVED AND THIS IS NOW ONE LINE OVER IT. `usage_ledger.total_from`
|
| 210 |
+
is the same logic, in the module that owns the meter; the alternative was a second reader in a
|
| 211 |
+
second file answering the same question about the same key, which is the shape this repo pays
|
| 212 |
+
for most often ([[one-question-two-normalizers]]). β The NAME and the None-semantics stay
|
| 213 |
+
exactly as wave 34 wrote them, because `run_field`'s ceiling arithmetic reads this and a gate
|
| 214 |
+
injects against its shape β lifting the body, not the signature.
|
| 215 |
+
"""
|
| 216 |
+
import usage_ledger
|
| 217 |
+
return usage_ledger.total_from(body)
|
| 218 |
+
|
| 219 |
+
|
| 220 |
+
#: R6's subject: the em dash (U+2014) and the en dash (U+2013), as a regex character class.
|
| 221 |
+
#: β BUILT FROM CODE POINTS, NOT TYPED, AND THIS IS NOT COSMETIC. `web_prose` reads a Python
|
| 222 |
+
#: string's VALUE off the AST, so a class written `'[<em><en>]'` is reported as two findings in
|
| 223 |
+
#: the one function whose entire job is to REMOVE those characters. That is a false positive, and
|
| 224 |
+
#: the wrong fix would be to silence the gate or to weaken the pattern. `chr()` keeps the value
|
| 225 |
+
#: byte-identical while putting no dash in a literal, so the gate sees what it should see and the
|
| 226 |
+
#: normalizer keeps working. β Lane D hit the same wall in `routes_query` (note D-13).
|
| 227 |
+
_DASH = '[' + chr(0x2014) + chr(0x2013) + ']'
|
| 228 |
+
|
| 229 |
+
|
| 230 |
+
def no_dashes(text):
|
| 231 |
+
"""R6 applied to MODEL-AUTHORED text, before it is stored.
|
| 232 |
+
|
| 233 |
+
ββ A PROMPT INSTRUCTION DOES NOT ENFORCE THIS, AND THE MEASUREMENT IS LANE D'S, NOT A GUESS
|
| 234 |
+
(mailbox note D-4, 2026-08-16): a system prompt ending *"Never use an em dash or an en dash"*
|
| 235 |
+
was answered on the very next live turn with *"Which view type would you like-grid, chart,
|
| 236 |
+
list, or another?"* carrying U+2014 (cerebras). `web_prose` scans SOURCE, so it is
|
| 237 |
+
structurally blind to a dash that arrives at runtime.
|
| 238 |
+
β AND THIS COLUMN IS THE WORST CASE IN THE WAVE, which is why D routed the note here: chat
|
| 239 |
+
prose is read once, but an enrichment value is WRITTEN INTO A CELL, then re-read and
|
| 240 |
+
re-rendered forever. Normalising after the write would never reach the rows already stored.
|
| 241 |
+
|
| 242 |
+
β A DIGIT RANGE IS A DIFFERENT SENTENCE and gets the first rule: "10-20" means "10 to 20", and
|
| 243 |
+
rewriting it as "10, 20" states two numbers where the model stated a span. That is a wrong
|
| 244 |
+
value, not a punctuation fix.
|
| 245 |
+
|
| 246 |
+
ββ THIS IS THE SECOND IMPLEMENTATION IN THE PRODUCT and that is a known cost, taken
|
| 247 |
+
deliberately rather than by drift. The first is `routes_query._no_dashes` (lane D's, shipped
|
| 248 |
+
first). Importing it would point a LIBRARY module at a ROUTE module, which is backwards, and
|
| 249 |
+
lane D's file is not in this lane's fence to move it. So the two are held in step by a PARITY
|
| 250 |
+
CHECK instead of by hope: `verify_ai_enrich` section 10 imports D's function and asserts both
|
| 251 |
+
agree over a corpus including every shape either docstring names. One shared home is owed and
|
| 252 |
+
is booked as a PENDING line, not left implicit ([[one-question-two-normalizers]]).
|
| 253 |
+
"""
|
| 254 |
+
text = str(text or '')
|
| 255 |
+
text = re.sub(rf'(?<=\d)\s*{_DASH}\s*(?=\d)', ' to ', text)
|
| 256 |
+
text = re.sub(rf'\s*{_DASH}\s*(?=[,.;:!?])', '', text) # abutting punctuation: it just goes
|
| 257 |
+
text = re.sub(rf'(?<=[,;:])\s*{_DASH}\s*', ' ', text) # already punctuated: one space
|
| 258 |
+
return re.sub(rf'\s*{_DASH}\s*', ', ', text)
|
| 259 |
+
|
| 260 |
+
|
| 261 |
+
#: What the model is told about its job. It fills ONE cell, so anything conversational it adds is
|
| 262 |
+
#: a defect in the column rather than a nicety. `UNKNOWN` is the honest out: a row the data cannot
|
| 263 |
+
#: answer is recorded as an error against that row, never as an invented value.
|
| 264 |
+
#: β The dash sentence is here for the same reason lane D kept theirs: it costs nothing and it
|
| 265 |
+
#: reduces how often `no_dashes` has to act. It is NOT the enforcement; `no_dashes` is.
|
| 266 |
+
_SYSTEM = ('You fill in ONE cell of a spreadsheet. Answer with the value only: no preamble, no '
|
| 267 |
+
'quotes, no markdown, no explanation. Never use an em dash or an en dash; use a comma, '
|
| 268 |
+
'a colon or a full stop. If the information given does not let you answer, reply with '
|
| 269 |
+
'exactly: UNKNOWN')
|
| 270 |
+
|
| 271 |
+
|
| 272 |
+
def _ask(provider, model, prompt, max_tokens, timeout):
|
| 273 |
+
"""One cell's answer. `(text, tokens_or_None, problem)`; a truthy `problem` means no text.
|
| 274 |
+
|
| 275 |
+
β Both request shapes are `ai_review`'s, changed in exactly two ways: they carry the COLUMN's
|
| 276 |
+
ceiling instead of a hardcoded 300, and they read `usage` back.
|
| 277 |
+
"""
|
| 278 |
+
key = (os.environ.get(provider['env']) or '').strip()
|
| 279 |
+
if not key:
|
| 280 |
+
return '', None, f"{provider['name']} has no key on this deployment"
|
| 281 |
+
try:
|
| 282 |
+
if provider['shape'] == 'anthropic':
|
| 283 |
+
r = requests.post(
|
| 284 |
+
provider['url'], timeout=timeout,
|
| 285 |
+
headers={'x-api-key': key, 'anthropic-version': '2023-06-01',
|
| 286 |
+
'content-type': 'application/json'},
|
| 287 |
+
json={'model': model, 'max_tokens': max_tokens, 'system': _SYSTEM,
|
| 288 |
+
'messages': [{'role': 'user', 'content': prompt}]})
|
| 289 |
+
if r.status_code >= 400:
|
| 290 |
+
return '', None, f"{provider['name']} answered {r.status_code}"
|
| 291 |
+
body = r.json()
|
| 292 |
+
# β stop_reason FIRST. A safety refusal is a 200 with an EMPTY content list, so
|
| 293 |
+
# reading content[0] before this turns a refusal into an IndexError inside the loop.
|
| 294 |
+
if body.get('stop_reason') == 'refusal':
|
| 295 |
+
return '', _usage_tokens(body), f"{provider['name']} declined this row"
|
| 296 |
+
parts = [b.get('text') or '' for b in (body.get('content') or [])
|
| 297 |
+
if isinstance(b, dict) and b.get('type') == 'text']
|
| 298 |
+
return ''.join(parts).strip(), _usage_tokens(body), ''
|
| 299 |
+
r = requests.post(
|
| 300 |
+
provider['url'], timeout=timeout,
|
| 301 |
+
headers={'Authorization': f"Bearer {key}", 'Content-Type': 'application/json'},
|
| 302 |
+
json={'model': model, 'max_tokens': max_tokens, 'temperature': 0,
|
| 303 |
+
'messages': [{'role': 'system', 'content': _SYSTEM},
|
| 304 |
+
{'role': 'user', 'content': prompt}]})
|
| 305 |
+
if r.status_code >= 400:
|
| 306 |
+
return '', None, f"{provider['name']} answered {r.status_code}"
|
| 307 |
+
body = r.json()
|
| 308 |
+
choices = body.get('choices') or []
|
| 309 |
+
if not choices:
|
| 310 |
+
return '', _usage_tokens(body), f"{provider['name']} returned no choices"
|
| 311 |
+
text = ((choices[0] or {}).get('message') or {}).get('content') or ''
|
| 312 |
+
return str(text).strip(), _usage_tokens(body), ''
|
| 313 |
+
except Exception as exc: # noqa: BLE001
|
| 314 |
+
return '', None, f"{provider['name']} failed: {type(exc).__name__}"
|
| 315 |
+
|
| 316 |
+
|
| 317 |
+
def on_change_fields(defn, changed_keys):
|
| 318 |
+
"""Which `ai_enrich` columns in this table want a run because one of their inputs moved.
|
| 319 |
+
|
| 320 |
+
A column qualifies when its trigger is `on_change` AND its prompt names at least one of the
|
| 321 |
+
columns that just changed. β A column that names NOTHING (a prompt with no `{token}`) never
|
| 322 |
+
fires on change, whatever its trigger says: it would re-ask the same question of the same row
|
| 323 |
+
forever, once per unrelated edit, and bill for every one.
|
| 324 |
+
|
| 325 |
+
β PURE, AND HANDED THE DEFINITION IT SHOULD USE. `automation_engine.grid_hook` calls
|
| 326 |
+
`all_definitions(st)` once PER EVENT, which turns a 20,000-row import into 20,000 whole
|
| 327 |
+
document reads (`D-134`); this function reads no store at all, so the caller can do one read
|
| 328 |
+
for a whole batch. Rebuilding that shape here was the one thing T54's ticket said not to do.
|
| 329 |
+
"""
|
| 330 |
+
import core.user_tables as ut
|
| 331 |
+
|
| 332 |
+
touched = {str(k) for k in (changed_keys or ())}
|
| 333 |
+
if not touched:
|
| 334 |
+
return []
|
| 335 |
+
out = []
|
| 336 |
+
for field in ut.ai_enrich_fields(defn):
|
| 337 |
+
cfg = field.get('aiEnrich') or {}
|
| 338 |
+
if (cfg.get('trigger') or {}).get('mode') != 'on_change':
|
| 339 |
+
continue
|
| 340 |
+
refs = set(prompt_refs(cfg.get('prompt')))
|
| 341 |
+
# β A column never fires on a change to ITSELF. Its own value moving is either the run
|
| 342 |
+
# that just wrote it or a person typing over it, and both would loop.
|
| 343 |
+
refs.discard(str(field.get('key') or ''))
|
| 344 |
+
if refs & touched:
|
| 345 |
+
out.append(field)
|
| 346 |
+
return out
|
| 347 |
+
|
| 348 |
+
|
| 349 |
+
def scheduled_fields(defn):
|
| 350 |
+
"""`[(field, cron)]` for every enrichment column that runs on a cadence.
|
| 351 |
+
|
| 352 |
+
β IT DOES NOT PARSE THE CRON AND MUST NOT. `core.user_tables` stores that string opaque
|
| 353 |
+
precisely so the cadence vocabulary has ONE owner, and the owner is the scheduler
|
| 354 |
+
(`automation_engine`), not the field layer. A second parser here would be a door that starts
|
| 355 |
+
refusing a cadence the other one accepts, which is exactly the divergence the whole field
|
| 356 |
+
contract keeps paying for ([[one-question-two-normalizers]]).
|
| 357 |
+
|
| 358 |
+
β SO THIS IS HALF A FEATURE ON PURPOSE, and the other half is a cross-fence ask: something has
|
| 359 |
+
to TICK. Nothing in lane F's fence runs on a timer.
|
| 360 |
+
"""
|
| 361 |
+
import core.user_tables as ut
|
| 362 |
+
|
| 363 |
+
out = []
|
| 364 |
+
for field in ut.ai_enrich_fields(defn):
|
| 365 |
+
trigger = ((field.get('aiEnrich') or {}).get('trigger') or {})
|
| 366 |
+
if trigger.get('mode') == 'schedule' and str(trigger.get('cron') or '').strip():
|
| 367 |
+
out.append((field, str(trigger['cron'])))
|
| 368 |
+
return out
|
| 369 |
+
|
| 370 |
+
|
| 371 |
+
def run_field(table_key, col_id, *, st, rows=None, manual=False, policy=None, budget=None,
|
| 372 |
+
timeout=None, ask=None, user=''):
|
| 373 |
+
"""Fill one `ai_enrich` column over the rows an automatic run is allowed to touch.
|
| 374 |
+
|
| 375 |
+
Returns a REPORT and never raises for a vendor problem:
|
| 376 |
+
`{planned, filled, failed, skipped{reason: count}, tokens, provider, model,
|
| 377 |
+
limit: <ceiling_report or None>, errors[], problem}`
|
| 378 |
+
|
| 379 |
+
β THE RUN BUDGET IS DERIVED FROM THE COLUMN'S OWN CEILING, and the arithmetic is the point:
|
| 380 |
+
`budget = maxTokens * planned`. `maxTokens` bounds the OUTPUT of one call while spend counts
|
| 381 |
+
INPUT tokens too, so a real run crosses this before it finishes every row. That is intended:
|
| 382 |
+
R13 asked for a token-usage limit and a ceiling that can never bite is not one. A caller may
|
| 383 |
+
pass a TIGHTER `budget`; nothing may pass a looser one.
|
| 384 |
+
|
| 385 |
+
β TWO STORE WRITES FOR THE WHOLE RUN, not two per row: one `patch_many_cells` for the values
|
| 386 |
+
and one `stamp_ai_enrich` for the marks. Each is a read-modify-write of the whole tenant
|
| 387 |
+
document, which is why `patch_cells` in a loop was never an option (D-134's shape).
|
| 388 |
+
|
| 389 |
+
β `ask` is injectable so a gate can exercise the ledger, the ceiling and every failure path
|
| 390 |
+
with no network and no vendor bill. It defaults to the real `_ask`.
|
| 391 |
+
|
| 392 |
+
ββ W35-T41 / C7 β ONE USAGE-LEDGER LINE PER RUN, NOT PER ROW, and the arithmetic is the reason:
|
| 393 |
+
this loop makes one LLM call per row, so a ledger write per call would be hundreds of store
|
| 394 |
+
writes for one click. The run already accumulates `report['tokens']`; `calls` and `unmeasured`
|
| 395 |
+
join it so the meter can say "40 calls, 12,000 tokens, 3 of them unmeasured" instead of a total
|
| 396 |
+
with an unknown shortfall. `user` is the ledger's attribution and is passed by this file's own
|
| 397 |
+
callers in `routes_tables`.
|
| 398 |
+
"""
|
| 399 |
+
import ai_review
|
| 400 |
+
import core.user_tables as ut
|
| 401 |
+
import usage_ledger
|
| 402 |
+
|
| 403 |
+
defn = ut.get(table_key, st=st) or {}
|
| 404 |
+
field = next((f for f in ut.ai_enrich_fields(defn) if f.get('key') == str(col_id)), None)
|
| 405 |
+
if field is None:
|
| 406 |
+
return {'problem': f'{col_id!r} is not an AI enrichment column on this database',
|
| 407 |
+
'planned': 0, 'filled': 0, 'failed': 0, 'skipped': {}, 'tokens': 0,
|
| 408 |
+
'errors': [], 'limit': None, 'provider': '', 'model': ''}
|
| 409 |
+
cfg = field.get('aiEnrich') or {}
|
| 410 |
+
# β THE BULK MENU'S TWO CHOICES ARE THIS ONE OVERRIDE (`W34-T54`): "Rows never filled" is
|
| 411 |
+
# `blank` and "All rows" is `always`. β It overrides the column's SAVED POLICY for one run and
|
| 412 |
+
# NOTHING ELSE: `ai_enrich_may_write` still refuses a human-edited cell under every value, so
|
| 413 |
+
# "All rows" means every row the AGENT wrote, which is exactly what the menu label says.
|
| 414 |
+
# β An unrecognised value falls back to the column's own setting rather than to a default: a
|
| 415 |
+
# typo'd override must not quietly widen what a run touches.
|
| 416 |
+
if policy in ut.AI_ENRICH_OVERWRITE:
|
| 417 |
+
cfg = {**cfg, 'overwrite': policy}
|
| 418 |
+
all_rows = defn.get('rows') or {}
|
| 419 |
+
marks = ut.ai_enrich_marks(table_key, col_id, st=st)
|
| 420 |
+
# ββ `rows` NARROWS; `manual` DECIDES WHETHER THE POLICY APPLIES. They are two questions and
|
| 421 |
+
# an early draft of this function conflated them, which would have let an ON-CHANGE fire (an
|
| 422 |
+
# automatic act, scoped to one row) overwrite a cell a person had typed into. That is the one
|
| 423 |
+
# law this whole feature is arranged around, broken by a parameter name.
|
| 424 |
+
# rows=None -> the automatic plan over every row
|
| 425 |
+
# rows=[...], manual=False -> the automatic plan, INTERSECTED with those rows (on_change)
|
| 426 |
+
# rows=[...], manual=True -> exactly those rows, policy skipped
|
| 427 |
+
# `manual` is skippable because a person clicking "run this cell" has asked, in front of the
|
| 428 |
+
# value being replaced; refusing them would be the product overruling an explicit act with a
|
| 429 |
+
# rule written for an implicit one. `ai_enrich_may_write`'s own docstring says exactly this.
|
| 430 |
+
# β A named row is always INTERSECTED with the table's own row set, so a stale caller cannot
|
| 431 |
+
# name a record that has since been deleted.
|
| 432 |
+
named = None if rows is None else [str(r) for r in rows if str(r) in all_rows]
|
| 433 |
+
if named is not None and manual:
|
| 434 |
+
plan = {'run': named, 'skipped': {},
|
| 435 |
+
'estimate': int(cfg.get('maxTokens') or 0) * len(named)}
|
| 436 |
+
else:
|
| 437 |
+
plan = plan_rows(all_rows, col_id, cfg, marks)
|
| 438 |
+
if named is not None:
|
| 439 |
+
keep = set(named)
|
| 440 |
+
dropped = [r for r in plan['run'] if r not in keep]
|
| 441 |
+
plan = {**plan, 'run': [r for r in plan['run'] if r in keep]}
|
| 442 |
+
if dropped:
|
| 443 |
+
plan['skipped'] = {**plan['skipped'], 'not_in_this_run': len(dropped)}
|
| 444 |
+
rows = all_rows
|
| 445 |
+
keys = [f.get('key') for f in (defn.get('fields') or []) if f.get('key')]
|
| 446 |
+
report = {'planned': len(plan['run']), 'filled': 0, 'failed': 0,
|
| 447 |
+
'skipped': dict(plan['skipped']), 'tokens': 0, 'errors': [], 'limit': None,
|
| 448 |
+
'provider': '', 'model': '', 'problem': '',
|
| 449 |
+
# β C7's two counters. `calls` is what the meter bills; `unmeasured` is how many of
|
| 450 |
+
# them the provider declined to report tokens for, so a total is never presented as
|
| 451 |
+
# complete when it is a floor.
|
| 452 |
+
'calls': 0, 'unmeasured': 0}
|
| 453 |
+
if not plan['run']:
|
| 454 |
+
return report
|
| 455 |
+
|
| 456 |
+
caller = ask or _ask
|
| 457 |
+
ceiling = int(cfg.get('maxTokens') or 0) * len(plan['run'])
|
| 458 |
+
if isinstance(budget, int) and not isinstance(budget, bool):
|
| 459 |
+
ceiling = min(ceiling, max(0, budget))
|
| 460 |
+
live = ai_review.ladder()
|
| 461 |
+
if not live and ask is None:
|
| 462 |
+
# β FAIL CLOSED AND SAY SO. A run that quietly filled nothing looks identical to a run
|
| 463 |
+
# with nothing to do; `planned` above is the number that distinguishes them.
|
| 464 |
+
report['problem'] = 'no AI provider is configured on this deployment'
|
| 465 |
+
return report
|
| 466 |
+
provider = (live or [{'name': 'injected', 'model': 'injected', 'env': '',
|
| 467 |
+
'shape': 'openai', 'url': ''}])[0]
|
| 468 |
+
model = str(cfg.get('model') or provider['model'])
|
| 469 |
+
report['provider'], report['model'] = provider['name'], model
|
| 470 |
+
tmo = float(timeout or TIMEOUT_SECONDS)
|
| 471 |
+
|
| 472 |
+
values, stamps = {}, {}
|
| 473 |
+
for row_id in plan['run']:
|
| 474 |
+
if ceiling and report['tokens'] >= ceiling:
|
| 475 |
+
# β STOP AND REPORT (R6's second sentence). Cells already written STAY written and
|
| 476 |
+
# carry honest marks; nothing is truncated and no cell holds half an answer.
|
| 477 |
+
report['limit'] = ceiling_report(report['tokens'], ceiling,
|
| 478 |
+
report['filled'], report['planned'])
|
| 479 |
+
left = report['planned'] - report['filled'] - report['failed']
|
| 480 |
+
if left > 0:
|
| 481 |
+
report['skipped']['over_budget'] = left
|
| 482 |
+
break
|
| 483 |
+
row = rows.get(row_id) or {}
|
| 484 |
+
text, unresolved = render_prompt(cfg.get('prompt'), row, keys)
|
| 485 |
+
if unresolved:
|
| 486 |
+
# Reported per row rather than refused up front: the prompt is valid for the column,
|
| 487 |
+
# and naming the missing token is what lets somebody fix it.
|
| 488 |
+
why = ('the prompt names ' + ', '.join(unresolved)
|
| 489 |
+
+ ', which is not a column on this database')
|
| 490 |
+
report['failed'] += 1
|
| 491 |
+
stamps[row_id] = {'state': 'error', 'error': why}
|
| 492 |
+
if len(report['errors']) < MAX_REPORTED_ERRORS:
|
| 493 |
+
report['errors'].append({'row': row_id, 'error': why})
|
| 494 |
+
continue
|
| 495 |
+
answer, tokens, problem = caller(provider, model, text[:MAX_CELL_CHARS * 8],
|
| 496 |
+
int(cfg.get('maxTokens') or 300), tmo)
|
| 497 |
+
# β COUNTED HERE, ON EVERY OUTCOME β before the `problem` branch below, because a call that
|
| 498 |
+
# errored or answered UNKNOWN still reached the vendor and is still billed. A meter that
|
| 499 |
+
# counts only filled cells reports a cheap run for one that spent its whole budget failing.
|
| 500 |
+
report['calls'] += 1
|
| 501 |
+
if isinstance(tokens, int) and not isinstance(tokens, bool):
|
| 502 |
+
report['tokens'] += tokens
|
| 503 |
+
else:
|
| 504 |
+
report['unmeasured'] += 1
|
| 505 |
+
if problem or not answer or answer.strip().upper() == 'UNKNOWN':
|
| 506 |
+
# β THE CELL IS LEFT ALONE. An errored row keeps whatever it held; only the MARK
|
| 507 |
+
# changes, so a failed run never destroys a value it could not replace.
|
| 508 |
+
why = problem or ('the model had nothing to answer from' if not answer
|
| 509 |
+
else 'the model answered UNKNOWN for this row')
|
| 510 |
+
report['failed'] += 1
|
| 511 |
+
stamps[row_id] = {'state': 'error', 'error': why, 'model': model}
|
| 512 |
+
if len(report['errors']) < MAX_REPORTED_ERRORS:
|
| 513 |
+
report['errors'].append({'row': row_id, 'error': why})
|
| 514 |
+
continue
|
| 515 |
+
# β NORMALISED BEFORE THE WRITE, NOT AFTER (note D-6). This is the ONE line where model
|
| 516 |
+
# prose becomes stored product data; a cell fixed after the fact leaves every row already
|
| 517 |
+
# written carrying the dash, and `web_prose` can never see it because it scans source.
|
| 518 |
+
values[row_id] = no_dashes(answer)[:MAX_CELL_CHARS]
|
| 519 |
+
stamps[row_id] = {'state': 'agent', 'model': model,
|
| 520 |
+
'hash': ut.ai_enrich_input_hash(cfg.get('prompt'), row,
|
| 521 |
+
prompt_refs(cfg.get('prompt'))),
|
| 522 |
+
'tokens': tokens if isinstance(tokens, int) else 0}
|
| 523 |
+
report['filled'] += 1
|
| 524 |
+
|
| 525 |
+
if values:
|
| 526 |
+
ut.patch_many_cells(table_key, {r: {str(col_id): v} for r, v in values.items()}, st=st)
|
| 527 |
+
if stamps:
|
| 528 |
+
ut.stamp_ai_enrich(table_key, col_id, stamps, st=st)
|
| 529 |
+
# β The ceiling is re-asked AFTER the loop too: a run whose LAST row crossed the budget spent
|
| 530 |
+
# over it without re-entering the guard, and staying silent there would under-report the one
|
| 531 |
+
# run most likely to surprise somebody.
|
| 532 |
+
if report['limit'] is None and ceiling and report['tokens'] >= ceiling:
|
| 533 |
+
report['limit'] = ceiling_report(report['tokens'], ceiling,
|
| 534 |
+
report['filled'], report['planned'])
|
| 535 |
+
# ββ C7's LEDGER LINE β one per run, after both store writes, and only when the run actually
|
| 536 |
+
# called something. `total=` rather than a split: `_ask`'s contract returns a total and a gate
|
| 537 |
+
# injects against that shape, so splitting it here would mean inventing two numbers from one.
|
| 538 |
+
#
|
| 539 |
+
# β TWO LINES WHEN A RUN HAS BOTH KINDS, and it is not tidiness. `record` marks a line
|
| 540 |
+
# `unmeasured` only when its total is None, so ONE line carrying 40 calls and a partial total
|
| 541 |
+
# would book all forty as measured and lose the shortfall β a total presented as complete when
|
| 542 |
+
# it is a floor, which is the exact failure `_usage_tokens`' None-semantics exists to prevent.
|
| 543 |
+
_measured = report['calls'] - report['unmeasured']
|
| 544 |
+
if _measured > 0:
|
| 545 |
+
usage_ledger.record('field_agent', report['provider'], report['model'],
|
| 546 |
+
total=report['tokens'], calls=_measured, st=st, user=user)
|
| 547 |
+
if report['unmeasured'] > 0:
|
| 548 |
+
usage_ledger.record('field_agent', report['provider'], report['model'],
|
| 549 |
+
total=None, calls=report['unmeasured'], st=st, user=user)
|
| 550 |
+
return report
|
api/ai_review.py
CHANGED
|
@@ -130,6 +130,17 @@ def _parse(text, options):
|
|
| 130 |
return "", reason
|
| 131 |
|
| 132 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 133 |
def _call_openai(p, model, system, user, timeout):
|
| 134 |
r = requests.post(p["url"], timeout=timeout,
|
| 135 |
headers={"Authorization": f"Bearer {os.environ[p['env']].strip()}",
|
|
@@ -138,12 +149,14 @@ def _call_openai(p, model, system, user, timeout):
|
|
| 138 |
"messages": [{"role": "system", "content": system},
|
| 139 |
{"role": "user", "content": user}]})
|
| 140 |
if r.status_code >= 400:
|
| 141 |
-
|
|
|
|
|
|
|
| 142 |
body = r.json()
|
| 143 |
choices = body.get("choices") or []
|
| 144 |
if not choices:
|
| 145 |
-
return "", f"{p['name']} returned no choices"
|
| 146 |
-
return str(((choices[0] or {}).get("message") or {}).get("content") or ""), ""
|
| 147 |
|
| 148 |
|
| 149 |
def _call_anthropic(p, model, system, user, timeout):
|
|
@@ -154,25 +167,34 @@ def _call_anthropic(p, model, system, user, timeout):
|
|
| 154 |
json={"model": model, "max_tokens": 300, "system": system,
|
| 155 |
"messages": [{"role": "user", "content": user}]})
|
| 156 |
if r.status_code >= 400:
|
| 157 |
-
return "", f"anthropic answered {r.status_code}"
|
| 158 |
body = r.json()
|
| 159 |
# β stop_reason FIRST. A safety refusal is a successful 200 with an EMPTY content list, so
|
| 160 |
# reading content[0] before this check turns a refusal into an IndexError inside a run.
|
|
|
|
| 161 |
if body.get("stop_reason") == "refusal":
|
| 162 |
-
return "", "anthropic declined to answer this record"
|
| 163 |
parts = [b.get("text") or "" for b in (body.get("content") or [])
|
| 164 |
if isinstance(b, dict) and b.get("type") == "text"]
|
| 165 |
if not parts:
|
| 166 |
-
return "", "anthropic returned no text"
|
| 167 |
-
return "".join(parts), ""
|
| 168 |
|
| 169 |
|
| 170 |
-
def decide(*, prompt, options, row, fields=(), label="Review", timeout=None):
|
| 171 |
"""Pick this record's next stage. Returns `(choice, meta)`.
|
| 172 |
|
| 173 |
`choice` is "" whenever a person should decide β which is every failure mode there is.
|
| 174 |
`meta` carries `provider`, `model`, `reason` on success, and `problem` on refusal to answer.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 175 |
"""
|
|
|
|
| 176 |
opts = [str(o) for o in (options or []) if str(o).strip()]
|
| 177 |
if not opts:
|
| 178 |
return "", {"problem": "the review offers no next stages"}
|
|
@@ -188,11 +210,22 @@ def decide(*, prompt, options, row, fields=(), label="Review", timeout=None):
|
|
| 188 |
problems = []
|
| 189 |
for p in live:
|
| 190 |
model = override or p["model"]
|
|
|
|
| 191 |
try:
|
| 192 |
-
text, err = (_call_anthropic if p["shape"] == "anthropic" else _call_openai)(
|
| 193 |
p, model, system, user, tmo)
|
| 194 |
except Exception as e: # noqa: BLE001
|
| 195 |
text, err = "", f"{p['name']} failed: {type(e).__name__}"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 196 |
if err:
|
| 197 |
problems.append(err)
|
| 198 |
continue # ladder: a dead provider degrades to the next one
|
|
@@ -205,3 +238,275 @@ def decide(*, prompt, options, row, fields=(), label="Review", timeout=None):
|
|
| 205 |
"problem": reason or "the model did not choose one of the stages"}
|
| 206 |
return choice, {"provider": p["name"], "model": model, "reason": reason}
|
| 207 |
return "", {"problem": "; ".join(problems)[:300] or "no provider answered"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 130 |
return "", reason
|
| 131 |
|
| 132 |
|
| 133 |
+
# ββ WAVE 35 Β· W35-T41 / C7 β THE TWO TRANSPORTS RETURN THE RESPONSE BODY'S `usage`.
|
| 134 |
+
#
|
| 135 |
+
# β THIS FILE'S OWN HEADER USED TO BE THE PRODUCT'S CONFESSION THAT NOTHING COUNTED: `ai_enrich`'s
|
| 136 |
+
# docstring says *"`ai_review.decide` -- the product's only other LLM entry -- has no token
|
| 137 |
+
# accounting of ANY kind"*. R9 asks for ONE meter for every AI surface, so the counting has to reach
|
| 138 |
+
# this transport rather than be bolted onto its caller β the caller never sees the body.
|
| 139 |
+
#
|
| 140 |
+
# β A THIRD RETURN VALUE, NOT A MUTATED ARGUMENT, and both call sites are in `decide` below. The
|
| 141 |
+
# tuple grew from `(text, err)` to `(text, err, usage)`; `usage` is the raw `usage` OBJECT (or None),
|
| 142 |
+
# because reading it is `usage_ledger`'s job and a second reader here would be the two-normalizers
|
| 143 |
+
# shape this repo keeps paying for.
|
| 144 |
def _call_openai(p, model, system, user, timeout):
|
| 145 |
r = requests.post(p["url"], timeout=timeout,
|
| 146 |
headers={"Authorization": f"Bearer {os.environ[p['env']].strip()}",
|
|
|
|
| 149 |
"messages": [{"role": "system", "content": system},
|
| 150 |
{"role": "user", "content": user}]})
|
| 151 |
if r.status_code >= 400:
|
| 152 |
+
# β NO BODY ON A 4xx/5xx: an error envelope carries no usage, and a provider that refused
|
| 153 |
+
# before running the model has nothing to bill. The call is still COUNTED by `decide`.
|
| 154 |
+
return "", f"{p['name']} answered {r.status_code}", None
|
| 155 |
body = r.json()
|
| 156 |
choices = body.get("choices") or []
|
| 157 |
if not choices:
|
| 158 |
+
return "", f"{p['name']} returned no choices", body
|
| 159 |
+
return str(((choices[0] or {}).get("message") or {}).get("content") or ""), "", body
|
| 160 |
|
| 161 |
|
| 162 |
def _call_anthropic(p, model, system, user, timeout):
|
|
|
|
| 167 |
json={"model": model, "max_tokens": 300, "system": system,
|
| 168 |
"messages": [{"role": "user", "content": user}]})
|
| 169 |
if r.status_code >= 400:
|
| 170 |
+
return "", f"anthropic answered {r.status_code}", None
|
| 171 |
body = r.json()
|
| 172 |
# β stop_reason FIRST. A safety refusal is a successful 200 with an EMPTY content list, so
|
| 173 |
# reading content[0] before this check turns a refusal into an IndexError inside a run.
|
| 174 |
+
# β A refusal IS billed and its body carries `usage`, so the body rides back on this branch too.
|
| 175 |
if body.get("stop_reason") == "refusal":
|
| 176 |
+
return "", "anthropic declined to answer this record", body
|
| 177 |
parts = [b.get("text") or "" for b in (body.get("content") or [])
|
| 178 |
if isinstance(b, dict) and b.get("type") == "text"]
|
| 179 |
if not parts:
|
| 180 |
+
return "", "anthropic returned no text", body
|
| 181 |
+
return "".join(parts), "", body
|
| 182 |
|
| 183 |
|
| 184 |
+
def decide(*, prompt, options, row, fields=(), label="Review", timeout=None, st=None, user=""):
|
| 185 |
"""Pick this record's next stage. Returns `(choice, meta)`.
|
| 186 |
|
| 187 |
`choice` is "" whenever a person should decide β which is every failure mode there is.
|
| 188 |
`meta` carries `provider`, `model`, `reason` on success, and `problem` on refusal to answer.
|
| 189 |
+
|
| 190 |
+
β W35-T41 / C7 β `st` and `user` are the USAGE LEDGER's target. Both default to absent because
|
| 191 |
+
this function's caller is `automation_engine.ai_decide(rt, ...)`, in another lane's fence: it
|
| 192 |
+
HAS the runtime and does not pass it yet, so until it does, a review's tokens are counted as
|
| 193 |
+
unattributed and REPORTED by `GET /usage` rather than dropped. See `usage_ledger`'s header for
|
| 194 |
+
why they cannot be resolved implicitly (measured: a contextvar does not survive a FastAPI
|
| 195 |
+
dependency).
|
| 196 |
"""
|
| 197 |
+
import usage_ledger # noqa: PLC0415
|
| 198 |
opts = [str(o) for o in (options or []) if str(o).strip()]
|
| 199 |
if not opts:
|
| 200 |
return "", {"problem": "the review offers no next stages"}
|
|
|
|
| 210 |
problems = []
|
| 211 |
for p in live:
|
| 212 |
model = override or p["model"]
|
| 213 |
+
body = None
|
| 214 |
try:
|
| 215 |
+
text, err, body = (_call_anthropic if p["shape"] == "anthropic" else _call_openai)(
|
| 216 |
p, model, system, user, tmo)
|
| 217 |
except Exception as e: # noqa: BLE001
|
| 218 |
text, err = "", f"{p['name']} failed: {type(e).__name__}"
|
| 219 |
+
# ββ C7 β THE LEDGER LINE, BEFORE ANY BRANCH BELOW READS THE ANSWER.
|
| 220 |
+
# β IT IS WRITTEN ON EVERY OUTCOME THAT REACHED A PROVIDER, including a refusal and an
|
| 221 |
+
# unusable answer. A meter that books only successes reports a cheap week for a run that
|
| 222 |
+
# spent its budget being declined β and a declined call is billed. The only path that does
|
| 223 |
+
# NOT record is a transport that never reached the vendor (`body is None`), which spent
|
| 224 |
+
# nothing.
|
| 225 |
+
if body is not None:
|
| 226 |
+
ins, outs = usage_ledger.tokens_from(body)
|
| 227 |
+
usage_ledger.record("ai_review", p["name"], model, ins, outs,
|
| 228 |
+
total=usage_ledger.total_from(body), st=st, user=user)
|
| 229 |
if err:
|
| 230 |
problems.append(err)
|
| 231 |
continue # ladder: a dead provider degrades to the next one
|
|
|
|
| 238 |
"problem": reason or "the model did not choose one of the stages"}
|
| 239 |
return choice, {"provider": p["name"], "model": model, "reason": reason}
|
| 240 |
return "", {"problem": "; ".join(problems)[:300] or "no provider answered"}
|
| 241 |
+
|
| 242 |
+
|
| 243 |
+
# ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ the FLOW WRITER
|
| 244 |
+
# ββ WAVE 33 Β· W33-T54/T55 (owner item 7, ruling R3) β A PROMPT BECOMES A DRAFT AUTOMATION.
|
| 245 |
+
#
|
| 246 |
+
# Owner, verbatim: *"lay out the foundation with custom tools we provide"* β and the tools are the
|
| 247 |
+
# action catalog, which has been machine-readable since wave 23. So this writes no new vocabulary:
|
| 248 |
+
# it hands the model the SAME `ACTION_CATALOG` the menu paints, the SAME `ACTION_REQUIRED` the
|
| 249 |
+
# runner blocks on, and the SAME trigger keys `clean_trigger` accepts, and asks for one JSON object
|
| 250 |
+
# in that vocabulary.
|
| 251 |
+
#
|
| 252 |
+
# β WHY IT LIVES IN `ai_review.py` RATHER THAN A NEW FILE. Two reasons, both about ownership. This
|
| 253 |
+
# is the one module in the API package that already holds an LLM ladder and its credentials, so a
|
| 254 |
+
# second one would be a second place a rotated key has to be noticed; and a new `routes_*.py` needs
|
| 255 |
+
# a `main.py` line from another lane (contract C2) to be reachable at all, which is how wave 23
|
| 256 |
+
# shipped three finished routers 404-dead behind green gates. The DOOR is a route on
|
| 257 |
+
# `routes_automation.py`, which is already mounted.
|
| 258 |
+
#
|
| 259 |
+
# ββ CONTRACT C7 IS THE DESIGN, NOT A CHECK AT THE END: *"the flow writer may emit only kinds
|
| 260 |
+
# present in `ACTION_CATALOG`, and its output must pass `clean_actions` unchanged."* Both halves are
|
| 261 |
+
# enforced mechanically rather than asked for politely β the kind list is an `enum` in the schema
|
| 262 |
+
# the model fills, and the caller runs `clean_actions` and DIFFS the result. That diff matters
|
| 263 |
+
# because `clean_actions` has no disclosure channel (D-75): it drops a key it does not recognise
|
| 264 |
+
# and answers 200, so a draft accepted without the diff would show a person a flow that is not the
|
| 265 |
+
# flow the model described, with nothing anywhere saying so.
|
| 266 |
+
#
|
| 267 |
+
# β `chat` IS INJECTABLE, exactly as `routes_query._call_model`'s is, and it is the reason this door
|
| 268 |
+
# can be proven end to end with no API key and no spend. A gate that can only run where a
|
| 269 |
+
# credential exists is a gate that never runs.
|
| 270 |
+
|
| 271 |
+
#: Cerebras first, NOT the cheap-first order `ladder()` uses. Same reason `routes_query` inverts it:
|
| 272 |
+
#: this contract includes a REFUSAL, and refusing honestly ("I cannot build that from the steps you
|
| 273 |
+
#: have") is a model property. A cheaper rung answers an impossible request with a plausible flow,
|
| 274 |
+
#: which is worse than no flow. Override with `AIOS_FLOW_PROVIDER`.
|
| 275 |
+
FLOW_PROVIDER_ORDER = ("cerebras", "groq", "openrouter", "anthropic")
|
| 276 |
+
MAX_DRAFT_ACTIONS = 12 # a draft a person reads in one screen; the engine's own cap is 25
|
| 277 |
+
MAX_PROMPT_CHARS = 2000
|
| 278 |
+
|
| 279 |
+
|
| 280 |
+
def flow_providers():
|
| 281 |
+
"""The rungs usable here, in THIS module's refusal-first order. Empty = the feature is off."""
|
| 282 |
+
pin = (os.environ.get("AIOS_FLOW_PROVIDER") or "").strip().lower()
|
| 283 |
+
by_name = {p["name"]: p for p in PROVIDERS}
|
| 284 |
+
order = [pin] if pin else list(FLOW_PROVIDER_ORDER)
|
| 285 |
+
return [by_name[n] for n in order
|
| 286 |
+
if n in by_name and (os.environ.get(by_name[n]["env"]) or "").strip()]
|
| 287 |
+
|
| 288 |
+
|
| 289 |
+
def flow_schema(kinds, trigger_keys, table_keys):
|
| 290 |
+
"""The tool schema the model fills β the catalog's OWN key lists as enums.
|
| 291 |
+
|
| 292 |
+
β `kind` AND `trigger` ARE ENUMS, not free strings, and that is C7's first half enforced by the
|
| 293 |
+
transport rather than by a check afterwards. A model asked for "any action name" invents
|
| 294 |
+
`send_slack_message` on a deployment that has no such kind, and the failure then surfaces as a
|
| 295 |
+
400 from `clean_actions` carrying a sentence about a word the person never typed.
|
| 296 |
+
β `required` IS `["kind"]` ALONE, deliberately: a REFUSAL carries no name and no actions, and a
|
| 297 |
+
schema demanding them turns an honest refusal into a provider-side 400 that reads exactly like a
|
| 298 |
+
transport failure (`routes_query._spec_schema` carries the same note, for the same measured
|
| 299 |
+
reason).
|
| 300 |
+
"""
|
| 301 |
+
return {
|
| 302 |
+
"type": "object",
|
| 303 |
+
"properties": {
|
| 304 |
+
"kind": {"type": "string", "enum": ["flow", "refused"],
|
| 305 |
+
"description": "refused = this cannot be built from the steps available"},
|
| 306 |
+
"refusal": {"type": "string",
|
| 307 |
+
"description": "when kind=refused: ONE plain sentence naming what is "
|
| 308 |
+
"missing, in the words a non-technical person would use"},
|
| 309 |
+
"name": {"type": "string", "description": "a short title for the automation"},
|
| 310 |
+
"trigger": {"type": "string", "enum": sorted(trigger_keys),
|
| 311 |
+
"description": "what starts this automation"},
|
| 312 |
+
"table": {"type": "string", "enum": sorted(table_keys),
|
| 313 |
+
"description": "the database whose records this flow walks, if any"},
|
| 314 |
+
"actions": {
|
| 315 |
+
"type": "array",
|
| 316 |
+
"maxItems": MAX_DRAFT_ACTIONS,
|
| 317 |
+
"items": {
|
| 318 |
+
"type": "object",
|
| 319 |
+
"properties": {
|
| 320 |
+
"kind": {"type": "string", "enum": sorted(kinds)},
|
| 321 |
+
"why": {"type": "string",
|
| 322 |
+
"description": "one short sentence: why this step is here"},
|
| 323 |
+
"config": {"type": "object", "additionalProperties": True,
|
| 324 |
+
"description": "the step's settings, using ONLY the keys named "
|
| 325 |
+
"for that kind in the system message"},
|
| 326 |
+
},
|
| 327 |
+
"required": ["kind"],
|
| 328 |
+
},
|
| 329 |
+
},
|
| 330 |
+
},
|
| 331 |
+
"required": ["kind"],
|
| 332 |
+
}
|
| 333 |
+
|
| 334 |
+
|
| 335 |
+
def flow_system_prompt(catalog, required, triggers, tables):
|
| 336 |
+
"""What the model is told it may build with β DERIVED, never written down twice.
|
| 337 |
+
|
| 338 |
+
Every list here is the server's own: the catalog rows the menu paints, the required-key table
|
| 339 |
+
the runner blocks on, the trigger keys `clean_trigger` accepts, and this tenant's real databases
|
| 340 |
+
with their real columns. Nothing about the vocabulary is restated by hand, so a kind added to
|
| 341 |
+
the catalog is offered here on the same deploy and a kind removed stops being offered.
|
| 342 |
+
"""
|
| 343 |
+
lines = ["You build small automations for a business tool. You are given the EXACT set of "
|
| 344 |
+
"steps this tool can perform. You may use nothing else.",
|
| 345 |
+
"", "THE STEPS YOU MAY USE:"]
|
| 346 |
+
# β BOTH HALVES, `key (phrase)`. The KEY is what the model must write into `config` and the
|
| 347 |
+
# PHRASE is the only human wording of that requirement anywhere β the one the runner's own
|
| 348 |
+
# refusal sentence is built from. Keys alone leave the model guessing what `field` means on a
|
| 349 |
+
# `web_read` (it is a column to write into, not a form field); phrases alone leave it guessing
|
| 350 |
+
# what to call the setting. Handing it one and hoping is how a draft comes back configured
|
| 351 |
+
# against a key the validator drops.
|
| 352 |
+
req = {str(k): [f"{key} ({phrase})" for phrase, key in v] for k, v in (required or {}).items()}
|
| 353 |
+
for row in catalog or []:
|
| 354 |
+
if not row.get("ready"):
|
| 355 |
+
continue
|
| 356 |
+
kind = str(row.get("kind") or "")
|
| 357 |
+
need = req.get(kind) or []
|
| 358 |
+
lines.append(f"- {kind}: {row.get('label')} - {row.get('detail') or ''}"
|
| 359 |
+
+ (f" REQUIRED settings: {', '.join(need)}" if need else ""))
|
| 360 |
+
lines += ["", "WHAT CAN START AN AUTOMATION:"]
|
| 361 |
+
for t in triggers or []:
|
| 362 |
+
if t.get("planned") or not t.get("ready", True):
|
| 363 |
+
continue
|
| 364 |
+
lines.append(f"- {t.get('key')}: {t.get('label')}")
|
| 365 |
+
lines += ["", "THE DATABASES THIS PERSON HAS:"]
|
| 366 |
+
for t in (tables or [])[:40]:
|
| 367 |
+
cols = ", ".join(str(f.get("key")) for f in (t.get("fields") or [])[:25])
|
| 368 |
+
lines.append(f"- {t.get('key')} ({t.get('label')}): {cols or 'no columns yet'}")
|
| 369 |
+
if not tables:
|
| 370 |
+
lines.append("- (none - do not name a database)")
|
| 371 |
+
lines += [
|
| 372 |
+
"",
|
| 373 |
+
"RULES:",
|
| 374 |
+
"1. Use ONLY the step kinds listed above. If what is asked needs a step that is not there, "
|
| 375 |
+
"answer kind=refused and say plainly which capability is missing.",
|
| 376 |
+
"2. Fill in every REQUIRED setting you can from what the person told you. Leave one blank "
|
| 377 |
+
"rather than inventing a web address, a CSS selector or a column name.",
|
| 378 |
+
"3. A web address must start with http:// or https://.",
|
| 379 |
+
"4. To use a value from the record the flow is walking, write it as {{Column name}}.",
|
| 380 |
+
"5. Name a database only from the list above, by its key.",
|
| 381 |
+
"6. Keep it short. Fewer steps that work beat more steps that guess.",
|
| 382 |
+
]
|
| 383 |
+
return "\n".join(lines)
|
| 384 |
+
|
| 385 |
+
|
| 386 |
+
def _flow_from_tool_call(obj):
|
| 387 |
+
"""The model's tool arguments -> `(draft, refusal)`. A shape error is a refusal, never a crash."""
|
| 388 |
+
if not isinstance(obj, dict):
|
| 389 |
+
return None, "the assistant's answer could not be read"
|
| 390 |
+
if str(obj.get("kind") or "") == "refused":
|
| 391 |
+
return None, (str(obj.get("refusal") or "").strip()
|
| 392 |
+
or "the assistant could not build this from the steps available")
|
| 393 |
+
acts = obj.get("actions")
|
| 394 |
+
if not isinstance(acts, list) or not acts:
|
| 395 |
+
return None, ("the assistant did not produce any steps - try describing what should "
|
| 396 |
+
"happen, one action at a time")
|
| 397 |
+
out = []
|
| 398 |
+
for a in acts[:MAX_DRAFT_ACTIONS]:
|
| 399 |
+
if not isinstance(a, dict) or not str(a.get("kind") or "").strip():
|
| 400 |
+
continue
|
| 401 |
+
cfg = a.get("config")
|
| 402 |
+
out.append({"kind": str(a["kind"]).strip(),
|
| 403 |
+
"config": cfg if isinstance(cfg, dict) else {},
|
| 404 |
+
"why": str(a.get("why") or "").strip()[:200]})
|
| 405 |
+
if not out:
|
| 406 |
+
return None, "the assistant's steps could not be read"
|
| 407 |
+
return {"name": str(obj.get("name") or "").strip()[:80] or "New automation",
|
| 408 |
+
"trigger": str(obj.get("trigger") or "").strip(),
|
| 409 |
+
"table": str(obj.get("table") or "").strip(),
|
| 410 |
+
# ββ THE TRUNCATION IS REPORTED, and it is a STANDING RULE that it must be (owner,
|
| 411 |
+
# 2026-08-12, W30/R6 second sentence): *"if there is lag or it can't be done, you need
|
| 412 |
+
# to explicitly tell me why and recommend a fix"* β **a silent truncation IS the
|
| 413 |
+
# violation, not the limit.** `acts[:MAX_DRAFT_ACTIONS]` above dropped everything past
|
| 414 |
+
# the twelfth and said nothing, so a model that answered with a twenty-step journey had
|
| 415 |
+
# eight steps deleted between the answer and the screen, with no key anywhere in the
|
| 416 |
+
# response naming them. `MAX_ACTIONS` is 20, so those steps were STORABLE β this
|
| 417 |
+
# ceiling is the draft door's own, which makes reporting it the whole obligation.
|
| 418 |
+
# β Found by the verifier that checked this ticket, not by a gate.
|
| 419 |
+
"asked": len([a for a in acts if isinstance(a, dict)]),
|
| 420 |
+
"actions": out}, ""
|
| 421 |
+
|
| 422 |
+
|
| 423 |
+
def draft_flow(*, prompt, catalog, required, triggers, tables, chat=None, timeout=None,
|
| 424 |
+
st=None, user=""):
|
| 425 |
+
"""A sentence -> `(draft, refusal_sentence, provider)`. β NOTHING IS SAVED HERE.
|
| 426 |
+
|
| 427 |
+
Exactly one of `draft` and `refusal_sentence` is truthy β the same contract
|
| 428 |
+
`web_agent.run_step` keeps, so a caller has no third case to get wrong.
|
| 429 |
+
|
| 430 |
+
β W35-T41 / C7 β `st`/`user` are the usage ledger's target, exactly as on `decide` above and for
|
| 431 |
+
the same reason: both of this function's callers (`automation_engine._ai_agent_plan` and
|
| 432 |
+
`routes_automation`'s draft door) are in lane D's fence. C7 says E adds the ledger line here and
|
| 433 |
+
D asserts it; the two keywords are what D has to pass for the line to be attributable.
|
| 434 |
+
"""
|
| 435 |
+
import usage_ledger # noqa: PLC0415
|
| 436 |
+
text = str(prompt or "").strip()[:MAX_PROMPT_CHARS]
|
| 437 |
+
if not text:
|
| 438 |
+
return None, "type what you want the automation to do", None
|
| 439 |
+
kinds = sorted({str(r.get("kind")) for r in (catalog or []) if r.get("ready")})
|
| 440 |
+
if not kinds:
|
| 441 |
+
return None, "this deployment offers no automation steps to build with", None
|
| 442 |
+
trigger_keys = sorted({str(t.get("key")) for t in (triggers or [])
|
| 443 |
+
if t.get("key") and not t.get("planned")}) or ["manual"]
|
| 444 |
+
table_keys = sorted({str(t.get("key")) for t in (tables or []) if t.get("key")}) or [""]
|
| 445 |
+
tools = [{"type": "function", "function": {
|
| 446 |
+
"name": "build_automation",
|
| 447 |
+
"description": "Emit the automation, or refuse.",
|
| 448 |
+
"parameters": flow_schema(kinds, trigger_keys, table_keys)}}]
|
| 449 |
+
messages = [{"role": "system",
|
| 450 |
+
"content": flow_system_prompt(catalog, required, triggers, tables)},
|
| 451 |
+
{"role": "user", "content": text}]
|
| 452 |
+
|
| 453 |
+
if chat is not None:
|
| 454 |
+
# β THE INJECTED PATH IS THE PROVEN PATH. It runs the SAME parse and the SAME refusal
|
| 455 |
+
# branches as a live call; only the transport is replaced.
|
| 456 |
+
draft, refusal = _flow_from_tool_call(chat(messages, tools))
|
| 457 |
+
return draft, refusal, "injected"
|
| 458 |
+
|
| 459 |
+
provs = flow_providers()
|
| 460 |
+
if not provs:
|
| 461 |
+
# β SAY SO. An AI feature that silently does nothing is indistinguishable from one that was
|
| 462 |
+
# never built [[flag-shipped-without-its-writer]].
|
| 463 |
+
return None, ("the assistant is not configured on this deployment, so an automation cannot "
|
| 464 |
+
"be drafted from a description yet"), None
|
| 465 |
+
tmo = float(timeout or TIMEOUT_SECONDS)
|
| 466 |
+
problems = []
|
| 467 |
+
for p in provs:
|
| 468 |
+
if p["shape"] != "openai":
|
| 469 |
+
# Anthropic's tool transport differs; it stays on the ladder for `decide()` and is
|
| 470 |
+
# SKIPPED here rather than half-supported. Named in `problems` so it is not invisible.
|
| 471 |
+
problems.append(f"{p['name']}: tool calls are not wired for this shape")
|
| 472 |
+
continue
|
| 473 |
+
try:
|
| 474 |
+
r = requests.post(p["url"], timeout=tmo,
|
| 475 |
+
headers={"Authorization": f"Bearer {os.environ[p['env']].strip()}",
|
| 476 |
+
"Content-Type": "application/json"},
|
| 477 |
+
json={"model": p["model"], "messages": messages, "tools": tools,
|
| 478 |
+
"tool_choice": "required", "temperature": 0.1,
|
| 479 |
+
"max_tokens": 1500})
|
| 480 |
+
except Exception as e: # noqa: BLE001
|
| 481 |
+
problems.append(f"{p['name']}: {type(e).__name__}")
|
| 482 |
+
continue
|
| 483 |
+
if r.status_code != 200:
|
| 484 |
+
problems.append(f"{p['name']}: HTTP {r.status_code}")
|
| 485 |
+
continue
|
| 486 |
+
try:
|
| 487 |
+
body = r.json()
|
| 488 |
+
calls = (((body.get("choices") or [{}])[0].get("message") or {})
|
| 489 |
+
.get("tool_calls") or [])
|
| 490 |
+
args = json.loads(calls[0]["function"]["arguments"]) if calls else None
|
| 491 |
+
except Exception as e: # noqa: BLE001
|
| 492 |
+
problems.append(f"{p['name']}: unreadable answer ({type(e).__name__})")
|
| 493 |
+
continue
|
| 494 |
+
# ββ C7 β THE LEDGER LINE. Placed after the parse rather than before it so an UNREADABLE
|
| 495 |
+
# answer is not double-counted by the `continue` above... β which means an unreadable answer
|
| 496 |
+
# is NOT counted at all, and that is a deliberate, disclosed loss: a body this code cannot
|
| 497 |
+
# parse is a body whose `usage` it also cannot trust, and `body` is out of scope in that
|
| 498 |
+
# branch by construction. The 200-with-junk case is rare and named here rather than
|
| 499 |
+
# silently rounded to zero.
|
| 500 |
+
ins, outs = usage_ledger.tokens_from(body)
|
| 501 |
+
usage_ledger.record("automation_draft", p["name"], p["model"], ins, outs,
|
| 502 |
+
total=usage_ledger.total_from(body), st=st, user=user)
|
| 503 |
+
draft, refusal = _flow_from_tool_call(args)
|
| 504 |
+
if draft is None and isinstance(args, dict) and str(args.get("kind")) == "refused":
|
| 505 |
+
# β A REFUSAL IS AN ANSWER, NOT A FAULT, so it does NOT fall through to a more
|
| 506 |
+
# expensive rung β the model has just said this cannot be built. `decide()` takes the
|
| 507 |
+
# same posture for the same reason.
|
| 508 |
+
return None, refusal, p["name"]
|
| 509 |
+
if draft is not None:
|
| 510 |
+
return draft, "", p["name"]
|
| 511 |
+
problems.append(f"{p['name']}: {refusal}")
|
| 512 |
+
return None, ("; ".join(problems)[:300] or "no provider answered"), None
|
api/automation_engine.py
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
api/deps.py
CHANGED
|
@@ -10,6 +10,7 @@ epoch-revoked, or naming an unknown tenant β **401**. Authenticated but not gr
|
|
| 10 |
**403**. Never an empty 200: an empty list is a legitimate answer meaning "no rows", and using it
|
| 11 |
to mean "you are not allowed" is how a permission bug becomes invisible.
|
| 12 |
"""
|
|
|
|
| 13 |
import os
|
| 14 |
import sys
|
| 15 |
import time
|
|
@@ -68,6 +69,418 @@ class Session:
|
|
| 68 |
f"this workspace does not include {module_key}")
|
| 69 |
|
| 70 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 71 |
def _user_for(claims):
|
| 72 |
"""The account named by a verified cookie, or None β with the epoch check that makes a
|
| 73 |
stateless cookie revocable.
|
|
@@ -110,7 +523,14 @@ def _user_for(claims):
|
|
| 110 |
# (login validated the slug's existence, never the membership) β with
|
| 111 |
# AIOS_ENABLE_QA_TENANT=1 that was a working cross-tenant session. A signature proves
|
| 112 |
# the cookie is ours; THIS proves the account belongs where the cookie says it does.
|
| 113 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 114 |
return None
|
| 115 |
return pub
|
| 116 |
if (uname == "admin" and os.environ.get("APP_PASSWORD", "")
|
|
|
|
| 10 |
**403**. Never an empty 200: an empty list is a legitimate answer meaning "no rows", and using it
|
| 11 |
to mean "you are not allowed" is how a permission bug becomes invisible.
|
| 12 |
"""
|
| 13 |
+
import copy
|
| 14 |
import os
|
| 15 |
import sys
|
| 16 |
import time
|
|
|
|
| 69 |
f"this workspace does not include {module_key}")
|
| 70 |
|
| 71 |
|
| 72 |
+
# ββ Assistant: app-stored, permissioned snapshot boundary (W33-T71 / C8) βββββββββββββββββββββββ
|
| 73 |
+
#
|
| 74 |
+
# This is deliberately an ordinary function rather than a route. E owns the Assistant's tool
|
| 75 |
+
# routes and model/provider choices; every one of those tools must come through this one boundary
|
| 76 |
+
# before it can see a database. Keeping it here gives the reader the already-verified Session and
|
| 77 |
+
# prevents Query's schema-only `_target` helper from becoming an accidental data authority.
|
| 78 |
+
#
|
| 79 |
+
# The important absence is as much part of the contract as the code below: this module never calls
|
| 80 |
+
# the Customer/Product pool builders, connector routes, provider routes, Odoo, or an environment
|
| 81 |
+
# lookup from this boundary. A cache miss is a named refusal, never permission to refresh from the
|
| 82 |
+
# source of truth. That is what "data the app already stores or serves" means in executable form.
|
| 83 |
+
_ASSISTANT_BUILT_INS = {
|
| 84 |
+
"customer_data": {"label": "Odoo customers", "cache_prefix": "pool"},
|
| 85 |
+
"product_data": {"label": "Odoo products", "cache_prefix": "product_pool"},
|
| 86 |
+
}
|
| 87 |
+
|
| 88 |
+
|
| 89 |
+
def _assistant_refuse(status, code, message):
|
| 90 |
+
"""Raise the public error shape without exposing a source implementation detail."""
|
| 91 |
+
raise err(status, code, message)
|
| 92 |
+
|
| 93 |
+
|
| 94 |
+
def _assistant_tenant_allows(session: Session, database: str) -> bool:
|
| 95 |
+
"""Read the served tenant catalogue without reusing the legacy account gate."""
|
| 96 |
+
tenant = getattr(getattr(session, "runtime", None), "tenant", None)
|
| 97 |
+
config = getattr(tenant, "config", None) or {}
|
| 98 |
+
modules = config.get("modules", "all") if isinstance(config, dict) else "all"
|
| 99 |
+
return modules == "all" or str(database) in {str(key) for key in (modules or ())}
|
| 100 |
+
|
| 101 |
+
|
| 102 |
+
def _assistant_preflight_request(session: Session, database: str, canonical_fields,
|
| 103 |
+
requested_fields, filters, *, require_explicit_grant: bool):
|
| 104 |
+
"""Refuse an unresolved grant, field or filter before a stored record is touched."""
|
| 105 |
+
import core.perm_scope as perm_scope
|
| 106 |
+
|
| 107 |
+
grant = perm_scope.assistant_entry(session.user, database)
|
| 108 |
+
if require_explicit_grant and grant is None:
|
| 109 |
+
_assistant_refuse(403, "assistant_forbidden",
|
| 110 |
+
"your current permissions do not allow this database")
|
| 111 |
+
visible = (perm_scope.assistant_visible_fields(canonical_fields, session.user, database)
|
| 112 |
+
if grant is not None else list(canonical_fields or ()))
|
| 113 |
+
try:
|
| 114 |
+
perm_scope.validate_assistant_filter((grant or {}).get("filter"), canonical_fields)
|
| 115 |
+
_assistant_requested_fields(requested_fields, visible)
|
| 116 |
+
perm_scope.validate_assistant_filter(filters, visible)
|
| 117 |
+
except ValueError as exc:
|
| 118 |
+
_assistant_refuse(400, "assistant_bad_filter", str(exc))
|
| 119 |
+
return grant, visible
|
| 120 |
+
|
| 121 |
+
|
| 122 |
+
def _assistant_cached_builtin(session: Session, database: str, requested_fields=None, filters=None):
|
| 123 |
+
"""The exact in-process snapshot for one built-in database, or a loud cache-miss refusal.
|
| 124 |
+
|
| 125 |
+
This intentionally reads `runtime.pool_cache` directly. Calling either route's `_pool_for`
|
| 126 |
+
would make a first Assistant request call Odoo; calling a cache helper would make a stale entry
|
| 127 |
+
refresh. Neither is data already stored/served by this process.
|
| 128 |
+
"""
|
| 129 |
+
import core.perm_scope as perm_scope
|
| 130 |
+
|
| 131 |
+
# Unlike an interactive grid, the Assistant has no legacy-grant compatibility path: the
|
| 132 |
+
# caller needs a declared, migrated database grant. `may_access` retains the old wall for
|
| 133 |
+
# the grid rollout, so it is necessary but not sufficient at this boundary.
|
| 134 |
+
declared_access = perm_scope.assistant_entry(session.user, database) is not None
|
| 135 |
+
if not _assistant_tenant_allows(session, database) or not declared_access:
|
| 136 |
+
_assistant_refuse(403, "assistant_forbidden",
|
| 137 |
+
"your current permissions do not allow this database")
|
| 138 |
+
|
| 139 |
+
# These are static field contracts, not the route assemblies: route assemblies can add
|
| 140 |
+
# per-user workspace state and can call a source builder. The Assistant begins with the
|
| 141 |
+
# already-stored base rows only; resolve their grant/field/filter contract *before* the cache
|
| 142 |
+
# read so a denied field or malformed operand cannot touch a stored record.
|
| 143 |
+
import aios_grid
|
| 144 |
+
fields = aios_grid.FIELDS if database == "customer_data" else aios_grid.product_fields()
|
| 145 |
+
_assistant_preflight_request(session, database, fields, requested_fields, filters,
|
| 146 |
+
require_explicit_grant=True)
|
| 147 |
+
|
| 148 |
+
team_id, agent = perm_scope.derive_pool_scope(session.user, database)
|
| 149 |
+
cache_key = (("pool", team_id, agent) if database == "customer_data"
|
| 150 |
+
else ("product_pool", team_id))
|
| 151 |
+
cache = getattr(session.runtime, "pool_cache", None)
|
| 152 |
+
entry = cache.get(cache_key) if isinstance(cache, dict) else None
|
| 153 |
+
if (not isinstance(entry, tuple) or len(entry) < 2
|
| 154 |
+
or not isinstance(entry[1], (list, tuple))
|
| 155 |
+
or any(not isinstance(row, dict) for row in entry[1])):
|
| 156 |
+
_assistant_refuse(409, "assistant_snapshot_unavailable",
|
| 157 |
+
"this database has no app-stored snapshot for your current scope")
|
| 158 |
+
return list(entry[1]), [dict(field) for field in fields if isinstance(field, dict)], entry[0]
|
| 159 |
+
|
| 160 |
+
|
| 161 |
+
def _assistant_user_table(session: Session, database: str, requested_fields=None, filters=None):
|
| 162 |
+
"""Read a materialised user-table document after a rows-free database grant check."""
|
| 163 |
+
from core import user_tables
|
| 164 |
+
|
| 165 |
+
# A guessed `ut_*` key must never make `user_tables.get()` copy the tenant's rows before the
|
| 166 |
+
# table resolver refuses it. `all_defs` can fall back to a whole-document read for older
|
| 167 |
+
# stores, so use the runtime's projection primitive directly and fail closed if it is absent.
|
| 168 |
+
# The existing `may_open` remains THE resolver; it is lent this rows-dropped document.
|
| 169 |
+
try:
|
| 170 |
+
definitions = session.runtime.get_projection('user_tables', drop=('rows',))
|
| 171 |
+
except Exception:
|
| 172 |
+
_assistant_refuse(409, "assistant_snapshot_unavailable",
|
| 173 |
+
"this database has no readable definition snapshot")
|
| 174 |
+
if not isinstance(definitions, dict):
|
| 175 |
+
_assistant_refuse(409, "assistant_snapshot_unavailable",
|
| 176 |
+
"this database has no readable definition snapshot")
|
| 177 |
+
definition = definitions.get(database)
|
| 178 |
+
if not isinstance(definition, dict):
|
| 179 |
+
_assistant_refuse(404, "assistant_unknown_database", "that database is not available")
|
| 180 |
+
definition_runtime = user_tables.lend(session.runtime, user_tables=definitions)
|
| 181 |
+
if not user_tables.may_open(database, session.uname, session.admin, st=definition_runtime):
|
| 182 |
+
# Deliberately no label/owner in this response: knowing a key must not become an oracle
|
| 183 |
+
# for somebody else's database.
|
| 184 |
+
_assistant_refuse(403, "assistant_forbidden",
|
| 185 |
+
"your current permissions do not allow this database")
|
| 186 |
+
|
| 187 |
+
fields = [dict(field) for field in (definition.get("fields") or [])
|
| 188 |
+
if isinstance(field, dict) and field.get("key")]
|
| 189 |
+
_assistant_preflight_request(session, database, fields, requested_fields, filters,
|
| 190 |
+
require_explicit_grant=False)
|
| 191 |
+
|
| 192 |
+
# Only an admitted table may now cross the app-stored record seam. This call still has no
|
| 193 |
+
# upstream fallback: it is the tenant's materialised document already held by the runtime.
|
| 194 |
+
table = user_tables.get(database, st=session.runtime)
|
| 195 |
+
if not isinstance(table, dict):
|
| 196 |
+
_assistant_refuse(409, "assistant_snapshot_unavailable",
|
| 197 |
+
"this database changed before its stored snapshot could be read")
|
| 198 |
+
if not user_tables.materialises(database, st=session.runtime, defn=table):
|
| 199 |
+
# Read-through rows belong to the app's DuckDB mirror, but this fence does not own its
|
| 200 |
+
# tenant-checked query binding. Returning an empty table would be a false answer; E must
|
| 201 |
+
# consume the mirror through its own `runtime.mirror_cursor`-guarded seam.
|
| 202 |
+
_assistant_refuse(409, "assistant_snapshot_unavailable",
|
| 203 |
+
"this database is mirror-served and needs its materialised reader")
|
| 204 |
+
|
| 205 |
+
# A table's field contract was authorized from the rows-free definition. If it changed while
|
| 206 |
+
# the materialised document was fetched, fail rather than projecting a schema that was never
|
| 207 |
+
# checked.
|
| 208 |
+
actual_fields = [dict(field) for field in (table.get("fields") or [])
|
| 209 |
+
if isinstance(field, dict) and field.get("key")]
|
| 210 |
+
if actual_fields != fields:
|
| 211 |
+
_assistant_refuse(409, "assistant_snapshot_unavailable",
|
| 212 |
+
"this database changed before its stored snapshot could be read")
|
| 213 |
+
raw_rows = table.get("rows") or {}
|
| 214 |
+
if not isinstance(raw_rows, dict):
|
| 215 |
+
_assistant_refuse(409, "assistant_snapshot_unavailable",
|
| 216 |
+
"this database does not have a readable stored snapshot")
|
| 217 |
+
keys = {field["key"] for field in fields}
|
| 218 |
+
rows = []
|
| 219 |
+
for record_id, raw in raw_rows.items():
|
| 220 |
+
if not str(record_id).isdigit() or not isinstance(raw, dict):
|
| 221 |
+
continue
|
| 222 |
+
# Matches `routes_tables.scoped_pool`: user-table permission is table-level, and only
|
| 223 |
+
# declared fields cross this boundary. `pid` is the opaque record identity required to
|
| 224 |
+
# bind a returned record to a single-source Query artefact; it is not a selectable field.
|
| 225 |
+
rows.append({"pid": int(record_id),
|
| 226 |
+
**{key: raw.get(key) for key in keys if key in raw}})
|
| 227 |
+
rows.sort(key=lambda row: row["pid"])
|
| 228 |
+
return rows, fields, (table.get("updated") or table.get("created")), table.get("label") or database
|
| 229 |
+
|
| 230 |
+
|
| 231 |
+
def _assistant_requested_fields(fields, visible_fields):
|
| 232 |
+
"""Resolve an explicit field selection without turning an unknown key into an omission."""
|
| 233 |
+
by_key = {str(field.get("key")): field for field in visible_fields
|
| 234 |
+
if isinstance(field, dict) and field.get("key")}
|
| 235 |
+
if fields is None:
|
| 236 |
+
return list(by_key)
|
| 237 |
+
if not isinstance(fields, (list, tuple)):
|
| 238 |
+
_assistant_refuse(400, "assistant_bad_fields", "fields must be a list of field keys")
|
| 239 |
+
out = []
|
| 240 |
+
for raw in fields:
|
| 241 |
+
key = raw.strip() if isinstance(raw, str) else ""
|
| 242 |
+
if not key or key not in by_key or key in out:
|
| 243 |
+
_assistant_refuse(400, "assistant_unknown_field",
|
| 244 |
+
"every requested field must be visible in this database")
|
| 245 |
+
out.append(key)
|
| 246 |
+
return out
|
| 247 |
+
|
| 248 |
+
|
| 249 |
+
def assistant_read_scope(session: Session, database, fields=None, filters=None):
|
| 250 |
+
"""Return a detached, permissioned snapshot for one Assistant tool call.
|
| 251 |
+
|
| 252 |
+
Signature (the C8 contract for E):
|
| 253 |
+
assistant_read_scope(session, database, fields, filters) -> {
|
| 254 |
+
database, label, source_kind, source_version, retrieved_at,
|
| 255 |
+
permission_scope_applied, fields, filters, records
|
| 256 |
+
}
|
| 257 |
+
|
| 258 |
+
`database` is exactly one source. `fields` is an explicit list of visible field keys (or
|
| 259 |
+
``None`` for every visible field). `filters` is ``None`` or the strict tree accepted by
|
| 260 |
+
`core.perm_scope.validate_assistant_filter`; it rejects unknown, hidden, inactive and
|
| 261 |
+
unsupported operands before a row is read. The returned dictionaries are deep copies, never
|
| 262 |
+
a live cache/store object, cursor, connector, route, provider, or credential.
|
| 263 |
+
"""
|
| 264 |
+
import core.perm_scope as perm_scope
|
| 265 |
+
from harness import filter_eval
|
| 266 |
+
|
| 267 |
+
key = str(database or "").strip()
|
| 268 |
+
if key in _ASSISTANT_BUILT_INS:
|
| 269 |
+
rows, canonical_fields, source_version = _assistant_cached_builtin(session, key, fields, filters)
|
| 270 |
+
label = _ASSISTANT_BUILT_INS[key]["label"]
|
| 271 |
+
source_kind = "runtime_cache"
|
| 272 |
+
elif key.startswith("ut_"):
|
| 273 |
+
rows, canonical_fields, source_version, label = _assistant_user_table(session, key, fields, filters)
|
| 274 |
+
source_kind = "materialised_user_table"
|
| 275 |
+
else:
|
| 276 |
+
_assistant_refuse(404, "assistant_unknown_database", "that database is not available")
|
| 277 |
+
|
| 278 |
+
# Permanent permissions run against the full source contract. A permission filter may name
|
| 279 |
+
# a field that is intentionally hidden from the returned schema; resolving it after the field
|
| 280 |
+
# projection would make that filter unanswerable and (depending on the evaluator) could widen.
|
| 281 |
+
# Validate even that grant before evaluating it: `permits` would deny an unknown operand row
|
| 282 |
+
# by row, but the Assistant contract requires an explicit refusal for unresolved grants.
|
| 283 |
+
grant = perm_scope.assistant_entry(session.user, key)
|
| 284 |
+
if source_kind != "materialised_user_table" and grant is None:
|
| 285 |
+
# `_assistant_cached_builtin` already made this decision before touching its cache. Keep
|
| 286 |
+
# this guard adjacent to the field/row projection so a future source cannot forget it.
|
| 287 |
+
_assistant_refuse(403, "assistant_forbidden",
|
| 288 |
+
"your current permissions do not allow this database")
|
| 289 |
+
try:
|
| 290 |
+
perm_scope.validate_assistant_filter((grant or {}).get("filter"), canonical_fields)
|
| 291 |
+
except ValueError as exc:
|
| 292 |
+
_assistant_refuse(400, "assistant_bad_filter", str(exc))
|
| 293 |
+
permitted_rows = (perm_scope.assistant_apply_row_scope(rows, session.user, key, canonical_fields)
|
| 294 |
+
if grant is not None else list(rows or ()))
|
| 295 |
+
visible = (perm_scope.assistant_visible_fields(canonical_fields, session.user, key)
|
| 296 |
+
if grant is not None else list(canonical_fields))
|
| 297 |
+
selected_keys = _assistant_requested_fields(fields, visible)
|
| 298 |
+
try:
|
| 299 |
+
requested_filter = perm_scope.validate_assistant_filter(filters, visible)
|
| 300 |
+
except ValueError as exc:
|
| 301 |
+
_assistant_refuse(400, "assistant_bad_filter", str(exc))
|
| 302 |
+
if requested_filter is not None:
|
| 303 |
+
permitted_rows = [row for row in permitted_rows
|
| 304 |
+
if filter_eval.permits(requested_filter, row, visible)]
|
| 305 |
+
|
| 306 |
+
records = []
|
| 307 |
+
for row in permitted_rows:
|
| 308 |
+
if not isinstance(row, dict) or row.get("pid") is None:
|
| 309 |
+
continue
|
| 310 |
+
records.append({"pid": copy.deepcopy(row["pid"]),
|
| 311 |
+
**{field: copy.deepcopy(row.get(field)) for field in selected_keys}})
|
| 312 |
+
|
| 313 |
+
return {
|
| 314 |
+
"database": key,
|
| 315 |
+
"label": str(label),
|
| 316 |
+
"source_kind": source_kind,
|
| 317 |
+
"source_version": copy.deepcopy(source_version),
|
| 318 |
+
"retrieved_at": time.strftime("%Y-%m-%dT%H:%M:%SZ", time.gmtime()),
|
| 319 |
+
"permission_scope_applied": True,
|
| 320 |
+
"fields": [copy.deepcopy(field) for field in visible
|
| 321 |
+
if field.get("key") in selected_keys],
|
| 322 |
+
"filters": copy.deepcopy(requested_filter),
|
| 323 |
+
"records": records,
|
| 324 |
+
}
|
| 325 |
+
|
| 326 |
+
|
| 327 |
+
def assistant_permitted_sources(session: Session, databases):
|
| 328 |
+
"""Which of `databases` the caller may still read β WITHOUT reading one record.
|
| 329 |
+
|
| 330 |
+
β THIS EXISTS BECAUSE `GET /query` LISTS ARTEFACTS, AND AN ARTEFACT IS NOT A READ.
|
| 331 |
+
`routes_query._public_state` has to drop every saved view whose source the caller has since
|
| 332 |
+
lost. The obvious way to ask that question is `assistant_read_scope(..., fields=[])` β and it
|
| 333 |
+
is the wrong one: for a `ut_*` source that call runs `user_tables.get()`, i.e. a WHOLE-DOCUMENT
|
| 334 |
+
read of the tenant store (measured at **28.6 MB / 703 ms warm on tenant #0**, and 99.9% of those
|
| 335 |
+
bytes are `rows` this question does not look at), then projects every row down to its `pid` and
|
| 336 |
+
throws the result away. Once per saved view, up to `MAX_ARTIFACTS = 200` of them, on a route
|
| 337 |
+
that BOTH the Assistant and Query call on mount. That is `/nav`'s old 1+N whole-document read
|
| 338 |
+
(D-175, an 11.0 s median) rebuilt inside a new route, and every fixture with two artefacts
|
| 339 |
+
passes it [[measure-the-real-call]].
|
| 340 |
+
|
| 341 |
+
So this asks the permission question and ONLY the permission question:
|
| 342 |
+
* the rows-free `user_tables` projection is read at most ONCE for the whole batch, and lent
|
| 343 |
+
to `may_open` exactly as `_assistant_user_table` lends it;
|
| 344 |
+
* a built-in resolves from the tenant catalogue and the declared grant, with no `pool_cache`
|
| 345 |
+
read β a cache MISS is a data-availability fact, not a permission one, and refusing to list
|
| 346 |
+
an artefact because its snapshot is cold would silently delete the user's history from the
|
| 347 |
+
rail every time the process restarted [[empty-answer-vs-unfinished-answer]].
|
| 348 |
+
|
| 349 |
+
β It is deliberately NOT a second permission wall. Every predicate here is the same call
|
| 350 |
+
`assistant_read_scope` makes for the same source; nothing may be admitted here that the read
|
| 351 |
+
boundary would refuse, which is what `verify_query.py` asserts in both directions.
|
| 352 |
+
"""
|
| 353 |
+
return {key for key, row in assistant_source_status(session, databases).items()
|
| 354 |
+
if row["permitted"]}
|
| 355 |
+
|
| 356 |
+
|
| 357 |
+
def assistant_source_status(session: Session, databases=None):
|
| 358 |
+
"""`{key: {permitted, answerable, reason}}` β WITHOUT reading one record.
|
| 359 |
+
|
| 360 |
+
ββ `answerable` EXISTS BECAUSE `permitted` IS NOT THE QUESTION THE READER IS ASKING.
|
| 361 |
+
Measured on tenant #0, signed in, 2026-08-15: the Assistant offered **twelve** source chips
|
| 362 |
+
and could answer for **two**. The other ten are the `ut_odoo_*` grids, and
|
| 363 |
+
`_assistant_user_table` refuses every one of them β *"this database is mirror-served and needs
|
| 364 |
+
its materialised reader"* β because their rows live UNCAPPED in the DuckDB mirror and are read
|
| 365 |
+
through it (W30/R6 is exactly why). The refusal is correct, named and fail-closed. The defect
|
| 366 |
+
is that it arrives one spent prompt at a time: a picker that offers ten doors which cannot
|
| 367 |
+
open is the same shape as the rail that painted two rows differently from five.
|
| 368 |
+
β It is R6's SECOND SENTENCE, in the family that rule was written for β a limit that cannot be
|
| 369 |
+
removed must be REPORTED with its cause, never silently enforced.
|
| 370 |
+
|
| 371 |
+
β AND IT COSTS NOTHING, WHICH IS WHY IT IS HERE RATHER THAN IN THE REGISTER.
|
| 372 |
+
`user_tables.materialises()` reads the `readThrough` flag off the DEFINITION, and the
|
| 373 |
+
rows-free projection this function already reads carries it. So the batch that answers
|
| 374 |
+
"may they?" answers "can it?" in the same pass, with no extra store read.
|
| 375 |
+
|
| 376 |
+
β `databases=None` enumerates every source this tenant HAS (the two built-ins plus every
|
| 377 |
+
`ut_*` in the projection) rather than taking a caller-supplied list. A client list would make
|
| 378 |
+
the answer depend on what the caller thought to ask about, and the nav has already told them
|
| 379 |
+
what they hold.
|
| 380 |
+
"""
|
| 381 |
+
import core.perm_scope as perm_scope
|
| 382 |
+
from core import user_tables
|
| 383 |
+
|
| 384 |
+
definitions = None
|
| 385 |
+
read_definitions = False
|
| 386 |
+
|
| 387 |
+
def _definitions():
|
| 388 |
+
nonlocal definitions, read_definitions
|
| 389 |
+
if not read_definitions:
|
| 390 |
+
read_definitions = True
|
| 391 |
+
try:
|
| 392 |
+
candidate = session.runtime.get_projection('user_tables', drop=('rows',))
|
| 393 |
+
except Exception:
|
| 394 |
+
candidate = None
|
| 395 |
+
definitions = candidate if isinstance(candidate, dict) else None
|
| 396 |
+
return definitions
|
| 397 |
+
|
| 398 |
+
if databases is None:
|
| 399 |
+
wanted = list(_ASSISTANT_BUILT_INS) + [
|
| 400 |
+
key for key in sorted((_definitions() or {}))
|
| 401 |
+
if isinstance(key, str) and key.startswith("ut_")
|
| 402 |
+
]
|
| 403 |
+
else:
|
| 404 |
+
wanted = [str(key or "").strip() for key in (databases or ())]
|
| 405 |
+
wanted = list(dict.fromkeys(key for key in wanted if key))
|
| 406 |
+
|
| 407 |
+
out = {}
|
| 408 |
+
for key in wanted:
|
| 409 |
+
# `visible` = "the caller can open this database elsewhere in the product". D-276 uses it
|
| 410 |
+
# to decide whether an unusable source is REPORTED or stays absent; default False, so a
|
| 411 |
+
# branch that never sets it keeps today's silence rather than inheriting a disclosure.
|
| 412 |
+
row = {"permitted": False, "answerable": False, "reason": "", "visible": False}
|
| 413 |
+
out[key] = row
|
| 414 |
+
if key in _ASSISTANT_BUILT_INS:
|
| 415 |
+
# ββ D-276 (2026-08-15) β AN OMISSION MUST STATE ITS CAUSE, and this branch used to
|
| 416 |
+
# `continue` in silence. MEASURED on tenant #0, both `admin` and `leadership`:
|
| 417 |
+
# `GET /query` listed nine sources and `product_data` was not among them, while
|
| 418 |
+
# `POST /query/chat {database:"product_data"}` answered 403 `assistant_forbidden` β
|
| 419 |
+
# for a database the SAME account opens from the nav, holds saved views on, and can
|
| 420 |
+
# see in the Database flyout. The two mirror-served grids are also un-askable and they
|
| 421 |
+
# ARE listed, with their cause in the chip; this one said nothing at all.
|
| 422 |
+
# β THE ASYMMETRY IS THE DEFECT, NOT THE REFUSAL. R6's second sentence: a limit that
|
| 423 |
+
# cannot be removed must be REPORTED with its cause, never silently enforced.
|
| 424 |
+
# β `visible` IS WHAT KEEPS THIS FROM BEING A DISCLOSURE. A source the caller cannot
|
| 425 |
+
# open ANYWHERE stays absent β naming it would tell them a database exists that they
|
| 426 |
+
# were never allowed to know about. `visible` is true only when the ordinary product
|
| 427 |
+
# wall already lets them open it, i.e. when the silence was incoherent rather than
|
| 428 |
+
# protective. `permitted` is untouched: it gates which stored artefacts survive, and
|
| 429 |
+
# widening it here would resurrect views the read boundary refuses.
|
| 430 |
+
if not _assistant_tenant_allows(session, key):
|
| 431 |
+
row["visible"] = bool(perm_scope.may_access(session.user, key))
|
| 432 |
+
row["reason"] = ("this workspace's catalogue does not list it as an assistant "
|
| 433 |
+
"source β an administrator can add it")
|
| 434 |
+
continue
|
| 435 |
+
if perm_scope.assistant_entry(session.user, key) is None:
|
| 436 |
+
row["visible"] = bool(perm_scope.may_access(session.user, key))
|
| 437 |
+
# ββ THIS SENTENCE DELIBERATELY PROMISES NO REMEDY, AND THAT IS A CORRECTION.
|
| 438 |
+
# Its first version said *"an administrator can re-save them"*. MEASURED on the
|
| 439 |
+
# deployed build the same hour: re-saving `leadership`'s permissions through
|
| 440 |
+
# `PUT /admin/users/{u}/perms` returned 200 with the block byte-identical and
|
| 441 |
+
# `perms_v` unchanged at 1 β and the source stayed refused. So the advice was
|
| 442 |
+
# wrong, and a refusal that hands the reader a fix which does not work is worse
|
| 443 |
+
# than one that admits it does not know: they spend the trip and land back here.
|
| 444 |
+
# β The cause is still open (D-276). `assistant_entry` reads only `entry`,
|
| 445 |
+
# `is_migrated` and `may_access`, and `product_data` carries the SAME grant as
|
| 446 |
+
# `customer_data` under one record β so the divergence is not visible in the perms
|
| 447 |
+
# document and guessing at it once already produced a wrong answer.
|
| 448 |
+
row["reason"] = ("the assistant cannot resolve a data grant for it yet β this is a "
|
| 449 |
+
"known gap (D-276), not something you have set wrongly")
|
| 450 |
+
continue
|
| 451 |
+
row["permitted"] = True
|
| 452 |
+
# β A CACHE MISS IS A DATA-AVAILABILITY FACT, NOT A PERMISSION ONE, and it must not
|
| 453 |
+
# drop the source from the list β an artefact already built on it stays listed. It is
|
| 454 |
+
# reported as not-yet-answerable, with the action that fixes it. MEASURED: the pool is
|
| 455 |
+
# filled by a grid REQUEST, not by `AIOS_PREWARM` β a fresh process refuses until
|
| 456 |
+
# somebody opens the database once.
|
| 457 |
+
team_id, agent = perm_scope.derive_pool_scope(session.user, key)
|
| 458 |
+
cache_key = (("pool", team_id, agent) if key == "customer_data"
|
| 459 |
+
else ("product_pool", team_id))
|
| 460 |
+
cache = getattr(session.runtime, "pool_cache", None)
|
| 461 |
+
entry = cache.get(cache_key) if isinstance(cache, dict) else None
|
| 462 |
+
if isinstance(entry, tuple) and len(entry) >= 2 and isinstance(entry[1], (list, tuple)):
|
| 463 |
+
row["answerable"] = True
|
| 464 |
+
else:
|
| 465 |
+
row["reason"] = "no snapshot loaded yet β open this database once, then ask"
|
| 466 |
+
continue
|
| 467 |
+
if not key.startswith("ut_"):
|
| 468 |
+
continue
|
| 469 |
+
defs = _definitions()
|
| 470 |
+
definition = (defs or {}).get(key)
|
| 471 |
+
if not isinstance(definition, dict):
|
| 472 |
+
continue
|
| 473 |
+
lent = user_tables.lend(session.runtime, user_tables=defs)
|
| 474 |
+
if not user_tables.may_open(key, session.uname, session.admin, st=lent):
|
| 475 |
+
continue
|
| 476 |
+
row["permitted"] = True
|
| 477 |
+
if user_tables.materialises(key, st=lent, defn=definition):
|
| 478 |
+
row["answerable"] = True
|
| 479 |
+
else:
|
| 480 |
+
row["reason"] = "served live from its connector mirror β the assistant cannot read it yet"
|
| 481 |
+
return out
|
| 482 |
+
|
| 483 |
+
|
| 484 |
def _user_for(claims):
|
| 485 |
"""The account named by a verified cookie, or None β with the epoch check that makes a
|
| 486 |
stateless cookie revocable.
|
|
|
|
| 523 |
# (login validated the slug's existence, never the membership) β with
|
| 524 |
# AIOS_ENABLE_QA_TENANT=1 that was a working cross-tenant session. A signature proves
|
| 525 |
# the cookie is ours; THIS proves the account belongs where the cookie says it does.
|
| 526 |
+
# β WAVE 33 (W33-T37) β the default was DELETED, not changed. It read
|
| 527 |
+
# `pub.get("tenant", "royal-imports")` and could never fire: `users._public` normalises a
|
| 528 |
+
# missing tenant to `royal-imports` before this line ever sees it. A dead default that
|
| 529 |
+
# names a real tenant reads like a live fallback, and the cross-tenant audit spent a row
|
| 530 |
+
# proving it was not one. Bare `.get` is also the safer shape if that ever stops being
|
| 531 |
+
# true: `None != claim_tenant` denies, where the old default would have ADMITTED a
|
| 532 |
+
# tenant-less record into tenant #0's session.
|
| 533 |
+
if claim_tenant != pub.get("tenant"):
|
| 534 |
return None
|
| 535 |
return pub
|
| 536 |
if (uname == "admin" and os.environ.get("APP_PASSWORD", "")
|
api/main.py
CHANGED
|
@@ -79,7 +79,18 @@ import routes_odoo_tables # noqa: E402 (wave 27 item 17 β Odoo relational; S
|
|
| 79 |
import routes_connected_tables # noqa: E402 (wave 31 T49/C4 β the source-neutral grid door; D's)
|
| 80 |
import routes_web_agent # noqa: E402 (wave 31 R10/C5 β the web-browsing agent; E's router, A's line)
|
| 81 |
import routes_query # noqa: E402 (wave 32 R1/C5 β the Query module; E's router, A's line)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 82 |
from core import grid_events # noqa: E402
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 83 |
from deps import Session, module_gate # noqa: E402
|
| 84 |
|
| 85 |
_WEB_DIST = _HERE.parents[1] / "web" / "dist"
|
|
@@ -164,7 +175,49 @@ def _store_unavailable(request: Request, exc: grid_events.StoreUnavailable):
|
|
| 164 |
"""
|
| 165 |
return JSONResponse(
|
| 166 |
{"error": {"code": "store_unavailable",
|
| 167 |
-
"message": "the tenant store is unavailable
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 168 |
status_code=503)
|
| 169 |
|
| 170 |
|
|
@@ -269,6 +322,60 @@ app.include_router(routes_web_agent.router) # R10 / C5 β E's router, A's lin
|
|
| 269 |
# β `verify_api` asserts `/api/v1/query` in `app.openapi()["paths"]` β NEVER `{r.path for r in
|
| 270 |
# app.routes}`, which finds nothing in this app because FastAPI wraps included routers (W31).
|
| 271 |
app.include_router(routes_query.router) # R1 / C5 β E's router, A's line
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 272 |
|
| 273 |
|
| 274 |
# --- DEPRECATED ALIASES (removed when S2's shell flips; kept so the current bundle keeps working)
|
|
@@ -302,18 +409,18 @@ def _assert_contract_floor():
|
|
| 302 |
if [f["key"] for f in base] != [f["key"] for f in FIELDS]:
|
| 303 |
raise RuntimeError(
|
| 304 |
"AIOS web API: the canonical field contract and aios_grid.fields_from_workspace({}) "
|
| 305 |
-
"disagree on the base field set
|
| 306 |
"Run aios-web/verify_fields_contract.py.")
|
| 307 |
|
| 308 |
|
| 309 |
def _startup_notes():
|
| 310 |
"""Say the two things an operator must know, once, at import β never in a response body."""
|
| 311 |
if aios_session.EPHEMERAL_SECRET:
|
| 312 |
-
print("[aios-api] AIOS_SESSION_SECRET is not set
|
| 313 |
"key. Sessions will not survive a restart and will not work across workers. "
|
| 314 |
"Set it in production.")
|
| 315 |
if os.environ.get("AIOS_INSECURE_SSL") == "1":
|
| 316 |
-
print("[aios-api] AIOS_INSECURE_SSL=1
|
| 317 |
"requests. Local development only; never in a deployed environment.")
|
| 318 |
|
| 319 |
|
|
@@ -431,6 +538,12 @@ def _seed_and_sync_store():
|
|
| 431 |
# is D-107's own hypothesis 3: a partial population trips `MAX_SHRINK` and the rebuild
|
| 432 |
# refuses β correctly, but for a reason that reads like a data loss scare.
|
| 433 |
# β Same thread on purpose: it is already a daemon and nothing serves requests behind it.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 434 |
_pull_meta("boot")
|
| 435 |
_rebuild_odoo_relational("boot")
|
| 436 |
# ββ W32-T07 β owner items 13 and 15, DELIVERED. See `_sweep_automation_schemas`.
|
|
@@ -442,6 +555,35 @@ def _seed_and_sync_store():
|
|
| 442 |
print(f"[aios-api] datastore seed/sync skipped: {e}")
|
| 443 |
|
| 444 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 445 |
def _pull_meta(why):
|
| 446 |
"""Pull Meta Ads into THIS container's mirror, before the relational rebuild reads it.
|
| 447 |
|
|
@@ -546,18 +688,18 @@ def _sweep_automation_schemas(why):
|
|
| 546 |
import automation_engine as _eng
|
| 547 |
from harness import runtime as _runtime
|
| 548 |
except Exception as e: # noqa: BLE001
|
| 549 |
-
print(f"[aios-api] schema sweep ({why}) SKIPPED
|
| 550 |
return
|
| 551 |
try:
|
| 552 |
schemas = _eng.platform_schemas()
|
| 553 |
except Exception as e: # noqa: BLE001
|
| 554 |
-
print(f"[aios-api] schema sweep ({why}) SKIPPED
|
| 555 |
return
|
| 556 |
tenants = []
|
| 557 |
try:
|
| 558 |
tenants = _runtime.known_tenants()
|
| 559 |
except Exception as e: # noqa: BLE001
|
| 560 |
-
print(f"[aios-api] schema sweep ({why}) SKIPPED
|
| 561 |
return
|
| 562 |
for slug in tenants:
|
| 563 |
try:
|
|
@@ -599,7 +741,7 @@ def _sweep_automation_schemas(why):
|
|
| 599 |
# which is how the previous behaviour survived review in the first place.
|
| 600 |
print(f"[aios-api] schema sweep ({why}) {slug}: {len(skipped)} child table(s) not "
|
| 601 |
f"present in this tenant, so nothing was created for them "
|
| 602 |
-
f"({', '.join(sorted(skipped))})
|
| 603 |
f"needs them, never by this sweep")
|
| 604 |
# β THE RETRACTION (D's `retract_foreign_presets`, D-152), AFTER the children loop.
|
| 605 |
# β THE SWEEP ABOVE MAKES COLUMNS **ARRIVE** AND CANNOT MAKE STALE ONES **LEAVE**, and
|
|
@@ -714,11 +856,31 @@ def _store_resync_loop():
|
|
| 714 |
# next cycle rather than at the next container restart, which is what makes it a setting.
|
| 715 |
# β FAIL-SAFE TO 1800 β an unreadable config must not become a tight loop. The floor is
|
| 716 |
# enforced in `sync_seconds` as well as at the write door, for the same reason.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 717 |
_every = 1800
|
|
|
|
| 718 |
try:
|
| 719 |
import odoo_relational as _rel_cad
|
| 720 |
from harness import runtime as _rt_cad
|
|
|
|
|
|
|
|
|
|
|
|
|
| 721 |
_secs = _rel_cad.sync_seconds(_rt_cad.get_runtime("royal-imports"))
|
|
|
|
| 722 |
_every = 1800 if _secs is None else max(int(_secs), 60)
|
| 723 |
except Exception: # noqa: BLE001
|
| 724 |
pass
|
|
@@ -731,12 +893,19 @@ def _store_resync_loop():
|
|
| 731 |
_odoo._tlocal.client = _odoo.OdooClient()
|
| 732 |
except Exception:
|
| 733 |
pass
|
| 734 |
-
|
| 735 |
-
#
|
| 736 |
-
#
|
| 737 |
-
#
|
| 738 |
-
if
|
| 739 |
-
_ds.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 740 |
except Exception as e: # noqa: BLE001
|
| 741 |
print(f"[aios-api] store resync failed: {e}")
|
| 742 |
# β WAVE 27 item 17 (E's ASK ->A, resolved): the Odoo RELATIONAL tables are rebuilt
|
|
|
|
| 79 |
import routes_connected_tables # noqa: E402 (wave 31 T49/C4 β the source-neutral grid door; D's)
|
| 80 |
import routes_web_agent # noqa: E402 (wave 31 R10/C5 β the web-browsing agent; E's router, A's line)
|
| 81 |
import routes_query # noqa: E402 (wave 32 R1/C5 β the Query module; E's router, A's line)
|
| 82 |
+
import routes_publish # noqa: E402 (wave 33 R5/C2 β the publish door; C's router, A's line)
|
| 83 |
+
import routes_brand # noqa: E402 (wave 33 R4/C2/C6 β connector brand marks; G's router, A's line)
|
| 84 |
+
import routes_slack # noqa: E402 (wave 33 R4/C2 β Manage agent + the Slack door; D's router, A's line)
|
| 85 |
+
import routes_starred # noqa: E402 (wave 35 R4/C2/C3/C5 β the star; E's router, E's line)
|
| 86 |
+
import routes_usage # noqa: E402 (wave 35 R9/C7 β the AI usage meter; E's router, E's line)
|
| 87 |
+
import routes_feedback # noqa: E402 (wave 35 R8/C6 β feedback to the operator plane; E's router)
|
| 88 |
from core import grid_events # noqa: E402
|
| 89 |
+
# D-315 / D-305 (2026-08-18) β the two store REFUSALS get their own app-level handlers below.
|
| 90 |
+
# β Neither is a `StoreUnavailable` subclass, on purpose: routes that degrade a store outage into a
|
| 91 |
+
# session fallback must NOT degrade a refusal, or the user is told a change was saved that was not.
|
| 92 |
+
from core import data_binding # noqa: E402
|
| 93 |
+
from core import store # noqa: E402
|
| 94 |
from deps import Session, module_gate # noqa: E402
|
| 95 |
|
| 96 |
_WEB_DIST = _HERE.parents[1] / "web" / "dist"
|
|
|
|
| 175 |
"""
|
| 176 |
return JSONResponse(
|
| 177 |
{"error": {"code": "store_unavailable",
|
| 178 |
+
"message": "the tenant store is unavailable. No change was saved"}},
|
| 179 |
+
status_code=503)
|
| 180 |
+
|
| 181 |
+
|
| 182 |
+
@app.exception_handler(data_binding.StoreWriteRefused)
|
| 183 |
+
def _store_write_refused(request: Request, exc: data_binding.StoreWriteRefused):
|
| 184 |
+
"""D-315 β this deployment may not write that store. 503, with the REASON.
|
| 185 |
+
|
| 186 |
+
β IT ECHOES THE EXCEPTION'S OWN MESSAGE, WHERE ITS NEIGHBOUR ABOVE USES A FIXED SENTENCE, and
|
| 187 |
+
the difference is the point. "The store is unavailable" is the whole truth about an outage; a
|
| 188 |
+
refusal has a cause the operator cannot otherwise discover, because per D-160 the Space
|
| 189 |
+
environment cannot be read from outside. A refusal that said only "unavailable" would send
|
| 190 |
+
somebody hunting for a network fault that does not exist ([[report-the-cause-before-you-fix-it]]).
|
| 191 |
+
The message names the deployment, the store and the fix, and carries no customer data.
|
| 192 |
+
|
| 193 |
+
β AND IT IS ITS OWN HANDLER RATHER THAN A SUBCLASS OF `StoreUnavailable`. Several routes carry
|
| 194 |
+
`except StoreUnavailable:` blocks that DEGRADE to a session-scoped fallback workspace β correct
|
| 195 |
+
for an outage, catastrophic here, because the user would be told the change was saved. A
|
| 196 |
+
distinct type falls through every one of them to this handler.
|
| 197 |
+
"""
|
| 198 |
+
return JSONResponse(
|
| 199 |
+
{"error": {"code": "store_write_refused",
|
| 200 |
+
"message": f"this deployment may not write the tenant store. No change was "
|
| 201 |
+
f"saved. {exc}"}},
|
| 202 |
+
status_code=503)
|
| 203 |
+
|
| 204 |
+
|
| 205 |
+
@app.exception_handler(store.StoreConflict)
|
| 206 |
+
def _store_conflict(request: Request, exc: store.StoreConflict):
|
| 207 |
+
"""D-305 β the document moved under this write more times than it could be rebased. 503.
|
| 208 |
+
|
| 209 |
+
β 503 RATHER THAN 409, DELIBERATELY. A 409 invites the client to resolve a conflict, and there
|
| 210 |
+
is nothing here for it to resolve: the store already re-read and re-applied this change up to
|
| 211 |
+
`_MAX_REBASE` times before giving up. What the caller needs to know is that the write did not
|
| 212 |
+
land and nothing was damaged, which is the same contract as the outage above and the same
|
| 213 |
+
retry-later shape. β The one answer this must never be is 200: reaching this handler means the
|
| 214 |
+
only way to have "succeeded" was to overwrite somebody else's work.
|
| 215 |
+
"""
|
| 216 |
+
return JSONResponse(
|
| 217 |
+
{"error": {"code": "store_conflict",
|
| 218 |
+
"message": f"somebody else changed this database while your change was being "
|
| 219 |
+
f"saved, and it could not be merged. Nothing was saved or "
|
| 220 |
+
f"overwritten. Try again. {exc}"}},
|
| 221 |
status_code=503)
|
| 222 |
|
| 223 |
|
|
|
|
| 322 |
# β `verify_api` asserts `/api/v1/query` in `app.openapi()["paths"]` β NEVER `{r.path for r in
|
| 323 |
# app.routes}`, which finds nothing in this app because FastAPI wraps included routers (W31).
|
| 324 |
app.include_router(routes_query.router) # R1 / C5 β E's router, A's line
|
| 325 |
+
# ββ WAVE 33 (C2) β THE SIXTH CONSECUTIVE WAVE IN WHICH THIS BLOCK IS THE THING THE PROTOCOL LOSES.
|
| 326 |
+
# Contract C2 is written for exactly that: a lane creating a `routes_*.py` posts an ASK, and the
|
| 327 |
+
# INTEGRATOR adds the line in the SAME wave. Both of these arrived that way (C's `ASK C-1`, G's
|
| 328 |
+
# `ASK G-1`), and `verify_api::section_w23_mounts` asserts each path in `app.openapi()["paths"]`
|
| 329 |
+
# with an NC that comments a mount out and goes RED.
|
| 330 |
+
# β Same placement rule as the line above β ABOVE the `app.mount("/", _AppStatic(...), html=True)`
|
| 331 |
+
# at the end of the file, never after it.
|
| 332 |
+
# ββ THE PUBLISH DOOR IS MOUNTED AGAIN (2026-08-15). It was withheld for the wave-33 deploy
|
| 333 |
+
# because QA reproduced three HIGH defects that are armed ONLY by mounting it. All three are fixed
|
| 334 |
+
# in `routes_publish.py`, each at its cause rather than at its symptom:
|
| 335 |
+
# 1. W33-T68 β `form` LEFT `PUBLISHABLE_MODES`. A form view's rows ARE the submissions people
|
| 336 |
+
# sent it, so publishing one served other people's answers to anyone holding the link. A form
|
| 337 |
+
# still has its own public door (`#/form/<token>`) which serves the BLANK form and never rows.
|
| 338 |
+
# 2. W33-T69 β `_visible_keys` returns `[]` when a view STORED a `visible` list and none of its
|
| 339 |
+
# keys survive, instead of falling back to the table default. The fallback still applies to a
|
| 340 |
+
# view that never stored one, which is what it was written for.
|
| 341 |
+
# 3. W33-T70 β three separate leaks closed: the rate limit no longer keys on the caller-supplied
|
| 342 |
+
# `x-forwarded-for` (it keys on the socket peer and counts FAILURES only, so a shared proxy
|
| 343 |
+
# peer cannot become one global bucket); every failing path now spends the same PBKDF2 the
|
| 344 |
+
# success path spends, closing the 206x timing gap; and an unknown token on the sibling GET
|
| 345 |
+
# answers the LOCKED shape rather than a 403, so that route stops sorting real tokens from
|
| 346 |
+
# fake ones for free.
|
| 347 |
+
# β `verify_api::section_w23_mounts` asserts this path in `app.openapi()["paths"]`, so its four
|
| 348 |
+
# EXPECTED reds should now go GREEN. A red here after this line means the mount broke, not the gate.
|
| 349 |
+
app.include_router(routes_publish.router) # R5 / C2 β C's router, A's line (the publish door)
|
| 350 |
+
# β NOT BEHIND `module_gate("product_data")`, WHICH IS THE WHOLE REASON IT IS A SECOND ASSET DOOR.
|
| 351 |
+
# `routes_assets.py` gates EVERY one of its routes on that module, so a connector logo served from
|
| 352 |
+
# there would 403 for any account without the product-data grant β i.e. the Connectors directory
|
| 353 |
+
# would lose its logos for exactly the accounts most likely to be setting a connector up (C6).
|
| 354 |
+
app.include_router(routes_brand.router) # R4 / C2 / C6 β G's router, A's line (brand marks)
|
| 355 |
+
# β TWO OF ITS SIX PATHS ARE UNAUTHENTICATED BY DESIGN (`/slack/events`, `/slack/interact`) and
|
| 356 |
+
# that is the DOOR, not an omission β Slack posts to them with no session and could not carry one.
|
| 357 |
+
# They are built on `routes_forms`' proven public shape: signing-secret verification, a sliding-window
|
| 358 |
+
# rate limit, a body cap and ONE non-oracle 403, so a bad signature cannot distinguish "no such
|
| 359 |
+
# workspace" from "not yours". β There is no auth middleware and no exempt-path allow-list in this
|
| 360 |
+
# file to register them in: "public" here IS the absence of `Depends(require_session)`, which is why
|
| 361 |
+
# `verify_api` asserts the absence rather than an entry in a list that does not exist.
|
| 362 |
+
app.include_router(routes_slack.router) # R4 / C2 β D's router, A's line (Manage agent + Slack)
|
| 363 |
+
# ββ WAVE 35 (R4/R5/R7, contracts C2/C3/C5) β THE STAR. Mounted in the SAME change that created
|
| 364 |
+
# `routes_starred.py`, which is the seventh consecutive wave in which this block is the artefact the
|
| 365 |
+
# protocol nearly loses β and the first in which the router's own lane also owns `main.py`, so there
|
| 366 |
+
# is no ask/mount pair to drop. `W35-T46` asserts every one of this wave's paths in
|
| 367 |
+
# `app.openapi()["paths"]` and CALLS one route from each.
|
| 368 |
+
# β Same placement rule as every line above: ABOVE `app.mount("/", _AppStatic(...), html=True)`, or
|
| 369 |
+
# the router answers 404 on GET and 405 on POST while every one of its own tests passes.
|
| 370 |
+
app.include_router(routes_starred.router) # R4 / C2 β the star, counts, and record stars
|
| 371 |
+
# β R9 SAYS THIS ROUTE REPORTS AND NEVER ENFORCES, so mounting it cannot cut anybody off β there is
|
| 372 |
+
# no ceiling anywhere behind it (`usage_ledger` has no refusal in it). The one AI limit the product
|
| 373 |
+
# enforces is per COLUMN and is unchanged (`ai_enrich.ceiling_report`).
|
| 374 |
+
app.include_router(routes_usage.router) # R9 / C7 β GET /usage, the one AI meter
|
| 375 |
+
# β ITS TWO DOORS CARRY DIFFERENT WALLS ON PURPOSE (R8, and D-221 is the booked precedent): the
|
| 376 |
+
# POST is any authenticated session's own act, the GET is `is_platform_admin` only. Mounting it does
|
| 377 |
+
# not widen anything a tenant admin can reach β `verify_api` proves that by having one try.
|
| 378 |
+
app.include_router(routes_feedback.router) # R8 / C6 β feedback to the operator plane
|
| 379 |
|
| 380 |
|
| 381 |
# --- DEPRECATED ALIASES (removed when S2's shell flips; kept so the current bundle keeps working)
|
|
|
|
| 409 |
if [f["key"] for f in base] != [f["key"] for f in FIELDS]:
|
| 410 |
raise RuntimeError(
|
| 411 |
"AIOS web API: the canonical field contract and aios_grid.fields_from_workspace({}) "
|
| 412 |
+
"disagree on the base field set. Embed and standalone would serve different schemas. "
|
| 413 |
"Run aios-web/verify_fields_contract.py.")
|
| 414 |
|
| 415 |
|
| 416 |
def _startup_notes():
|
| 417 |
"""Say the two things an operator must know, once, at import β never in a response body."""
|
| 418 |
if aios_session.EPHEMERAL_SECRET:
|
| 419 |
+
print("[aios-api] AIOS_SESSION_SECRET is not set. Signing with a random per-process "
|
| 420 |
"key. Sessions will not survive a restart and will not work across workers. "
|
| 421 |
"Set it in production.")
|
| 422 |
if os.environ.get("AIOS_INSECURE_SSL") == "1":
|
| 423 |
+
print("[aios-api] AIOS_INSECURE_SSL=1. TLS verification is DISABLED for outbound "
|
| 424 |
"requests. Local development only; never in a deployed environment.")
|
| 425 |
|
| 426 |
|
|
|
|
| 538 |
# is D-107's own hypothesis 3: a partial population trips `MAX_SHRINK` and the rebuild
|
| 539 |
# refuses β correctly, but for a reason that reads like a data loss scare.
|
| 540 |
# β Same thread on purpose: it is already a daemon and nothing serves requests behind it.
|
| 541 |
+
# ββ W35-T45 / R11 β TENANT #0'S ODOO CREDENTIAL MOVES ONTO ITS KEYCHAIN, IN THE CONTAINER.
|
| 542 |
+
# β BEFORE the relational rebuild, deliberately: the rebuild resolves its connector through
|
| 543 |
+
# `rt.odoo_source()`, so running the migration first means the very next read already goes
|
| 544 |
+
# through the keychain branch and a broken migration is visible in THIS boot's log rather
|
| 545 |
+
# than in tomorrow's. It is idempotent, so every later boot is one `list_entries` read.
|
| 546 |
+
_migrate_env_odoo("boot")
|
| 547 |
_pull_meta("boot")
|
| 548 |
_rebuild_odoo_relational("boot")
|
| 549 |
# ββ W32-T07 β owner items 13 and 15, DELIVERED. See `_sweep_automation_schemas`.
|
|
|
|
| 555 |
print(f"[aios-api] datastore seed/sync skipped: {e}")
|
| 556 |
|
| 557 |
|
| 558 |
+
def _migrate_env_odoo(why):
|
| 559 |
+
"""ββ W35-T45 / R11 β move tenant #0's environment Odoo credential onto its keychain.
|
| 560 |
+
|
| 561 |
+
ββ IN THE CONTAINER, WHICH IS THE WHOLE REASON THIS IS A BOOT LINE AND NOT A SCRIPT. D-195,
|
| 562 |
+
measured three times: a developer's CLI write to the tenant store is reverted by the running
|
| 563 |
+
Space within a minute (download-modify-upload, last-write-wins) β and the write REPORTS SUCCESS
|
| 564 |
+
every time, then a fresh read confirms it, and it is gone by the next poll. A CLI migration would
|
| 565 |
+
be a dry run that lies, and what it would lie about here is a credential.
|
| 566 |
+
|
| 567 |
+
β IDEMPOTENT AND SCOPED TO TENANT #0 by `routes_keychain.env_odoo_available`, so on every other
|
| 568 |
+
tenant and on every later boot this is one `list_entries` read and a line.
|
| 569 |
+
β FAIL-QUIET: this must never take a boot down. But it is never SILENT β a skip prints its reason,
|
| 570 |
+
because "already migrated", "no keychain key on this deployment" and "the env is incomplete" are
|
| 571 |
+
three different operator actions and a blank Keychain page cannot tell them apart.
|
| 572 |
+
"""
|
| 573 |
+
try:
|
| 574 |
+
import routes_keychain as _kc_routes
|
| 575 |
+
from harness import runtime as _runtime
|
| 576 |
+
rep = _kc_routes.migrate_env_odoo(_runtime.get_runtime("royal-imports"))
|
| 577 |
+
if rep.get("done"):
|
| 578 |
+
print(f"[aios-api] odoo credential migrated onto the keychain ({why}): "
|
| 579 |
+
f"entry={rep['entry']} carried_pause={rep['carried_pause']}"
|
| 580 |
+
+ (f" PROBLEM: {rep['why']}" if rep.get("why") else ""))
|
| 581 |
+
else:
|
| 582 |
+
print(f"[aios-api] odoo keychain migration skipped ({why}): {rep.get('why')}")
|
| 583 |
+
except Exception as e: # noqa: BLE001
|
| 584 |
+
print(f"[aios-api] odoo keychain migration FAILED ({why}): {type(e).__name__}: {e}")
|
| 585 |
+
|
| 586 |
+
|
| 587 |
def _pull_meta(why):
|
| 588 |
"""Pull Meta Ads into THIS container's mirror, before the relational rebuild reads it.
|
| 589 |
|
|
|
|
| 688 |
import automation_engine as _eng
|
| 689 |
from harness import runtime as _runtime
|
| 690 |
except Exception as e: # noqa: BLE001
|
| 691 |
+
print(f"[aios-api] schema sweep ({why}) SKIPPED. Import failed: {e}")
|
| 692 |
return
|
| 693 |
try:
|
| 694 |
schemas = _eng.platform_schemas()
|
| 695 |
except Exception as e: # noqa: BLE001
|
| 696 |
+
print(f"[aios-api] schema sweep ({why}) SKIPPED. No declarations: {e}")
|
| 697 |
return
|
| 698 |
tenants = []
|
| 699 |
try:
|
| 700 |
tenants = _runtime.known_tenants()
|
| 701 |
except Exception as e: # noqa: BLE001
|
| 702 |
+
print(f"[aios-api] schema sweep ({why}) SKIPPED. Tenant list unreadable: {e}")
|
| 703 |
return
|
| 704 |
for slug in tenants:
|
| 705 |
try:
|
|
|
|
| 741 |
# which is how the previous behaviour survived review in the first place.
|
| 742 |
print(f"[aios-api] schema sweep ({why}) {slug}: {len(skipped)} child table(s) not "
|
| 743 |
f"present in this tenant, so nothing was created for them "
|
| 744 |
+
f"({', '.join(sorted(skipped))}). They are spawned by an automation that "
|
| 745 |
f"needs them, never by this sweep")
|
| 746 |
# β THE RETRACTION (D's `retract_foreign_presets`, D-152), AFTER the children loop.
|
| 747 |
# β THE SWEEP ABOVE MAKES COLUMNS **ARRIVE** AND CANNOT MAKE STALE ONES **LEAVE**, and
|
|
|
|
| 856 |
# next cycle rather than at the next container restart, which is what makes it a setting.
|
| 857 |
# β FAIL-SAFE TO 1800 β an unreadable config must not become a tight loop. The floor is
|
| 858 |
# enforced in `sync_seconds` as well as at the write door, for the same reason.
|
| 859 |
+
# ββ WAVE 34 Β· W34-T46 / D-246 β THE PARAGRAPH ABOVE DESCRIBED A BRANCH THAT DID NOT
|
| 860 |
+
# EXIST, AND THAT IS WHY NOBODY LOOKED. It said `manual` "parks at the default cadence
|
| 861 |
+
# instead and simply DOES NO WORK". The first half was true; the second half was not
|
| 862 |
+
# implemented anywhere: `_secs is None` set the sleep to 1800 and then fell into an
|
| 863 |
+
# UNCONDITIONAL `sync_all()`. So a tenant who chose "manual" was synced every thirty
|
| 864 |
+
# minutes exactly like everyone else, with the setting stored, displayed, clamped and
|
| 865 |
+
# obeyed by nothing β the identical failure this block's own W32/R11 note is about, one
|
| 866 |
+
# layer further in. A comment asserting a fix is why the second reader stops reading.
|
| 867 |
+
# β FIXED, AND THE FIX IS NARROW ON PURPOSE. `manual` is an ODOO connector setting, so it
|
| 868 |
+
# skips the Odoo mirror sync and its reconcile and NOTHING ELSE: the Meta pull and the
|
| 869 |
+
# relational rebuild below still run, because a tenant asking not to have Odoo polled has
|
| 870 |
+
# not asked for the other connector to stop.
|
| 871 |
+
# β AND IT STILL SLEEPS AND STILL LOOPS. The config is re-read every pass, so switching
|
| 872 |
+
# back off `manual` takes effect on the next cycle rather than at the next restart.
|
| 873 |
_every = 1800
|
| 874 |
+
_manual = False
|
| 875 |
try:
|
| 876 |
import odoo_relational as _rel_cad
|
| 877 |
from harness import runtime as _rt_cad
|
| 878 |
+
# β D-245, KNOWN AND NOT FIXED HERE: the slug is hardcoded, so this reads TENANT #0's
|
| 879 |
+
# cadence and applies it to a loop that syncs the shared mirror. Correct while one
|
| 880 |
+
# tenant has Odoo; wrong the moment a second one does. Out of this ticket's scope and
|
| 881 |
+
# named rather than silently inherited.
|
| 882 |
_secs = _rel_cad.sync_seconds(_rt_cad.get_runtime("royal-imports"))
|
| 883 |
+
_manual = _secs is None
|
| 884 |
_every = 1800 if _secs is None else max(int(_secs), 60)
|
| 885 |
except Exception: # noqa: BLE001
|
| 886 |
pass
|
|
|
|
| 893 |
_odoo._tlocal.client = _odoo.OdooClient()
|
| 894 |
except Exception:
|
| 895 |
pass
|
| 896 |
+
# β A PLAIN BRANCH, NOT AN EARLY EXIT AND NOT AN EXCEPTION. A `raise` here would be
|
| 897 |
+
# caught by this block's own `except` and printed as "store resync failed", turning a
|
| 898 |
+
# setting a person chose into a recurring error in the log; a `continue` would skip
|
| 899 |
+
# the Meta pull and the relational rebuild below, which `manual` says nothing about.
|
| 900 |
+
if not _manual:
|
| 901 |
+
_ds.sync_all(log=lambda *a, **k: None)
|
| 902 |
+
# Wave 21 β every 4th pass (~2h): purge hard-deleted rows the cursor sync cannot
|
| 903 |
+
# see (the boot pass's comment has the measured case). Cheap id-sweep per entity;
|
| 904 |
+
# without it deleted Odoo lines inflate every sum on the mirror FOREVER.
|
| 905 |
+
# β INSIDE the branch: a reconcile is a pass over the mirror this loop was just
|
| 906 |
+
# told not to advance.
|
| 907 |
+
if passes % 4 == 0:
|
| 908 |
+
_ds.reconcile_deletes(log=lambda *a, **k: None)
|
| 909 |
except Exception as e: # noqa: BLE001
|
| 910 |
print(f"[aios-api] store resync failed: {e}")
|
| 911 |
# β WAVE 27 item 17 (E's ASK ->A, resolved): the Odoo RELATIONAL tables are rebuilt
|
api/odoo_relational.py
CHANGED
|
@@ -117,6 +117,13 @@ def _ut():
|
|
| 117 |
return user_tables
|
| 118 |
|
| 119 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 120 |
def _iso_today():
|
| 121 |
return _dt.date.today().strftime("%Y-%m-%d")
|
| 122 |
|
|
@@ -180,9 +187,14 @@ def agent_fields():
|
|
| 180 |
"source": "overlay", "default": True},
|
| 181 |
# β THE INVERSE HALF: the customers whose `agent_id` names this agent. MEASURED: 2,093
|
| 182 |
# customers carry one and ALL 2,093 resolve to a row in this table (zero dangling).
|
| 183 |
-
|
| 184 |
-
|
| 185 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 186 |
_refreshed_field(),
|
| 187 |
)]
|
| 188 |
|
|
@@ -237,8 +249,34 @@ def vendor_fields():
|
|
| 237 |
"default": False, "description": "The `res.partner` id. Also this row's id."},
|
| 238 |
{"key": VENDOR_JOIN_KEY, "label": "Odoo vendor id", "type": "int", "source": "overlay",
|
| 239 |
"default": False},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 240 |
{"key": "country", "label": "Country", "type": "text", "source": "overlay",
|
| 241 |
"default": True},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 242 |
{"key": "bills", "label": "Bills", "type": "link", "source": "overlay", "default": True,
|
| 243 |
"link": {"table": BILLS_KEY, "on": VENDOR_JOIN_KEY, "from": VENDOR_JOIN_KEY}},
|
| 244 |
_refreshed_field(),
|
|
@@ -316,9 +354,21 @@ def invoice_fields():
|
|
| 316 |
_scope_field(),
|
| 317 |
# β THE RECIPROCAL HALF (owner item 2, 2026-08-09). DERIVED (`on` declared), exactly like
|
| 318 |
# its twin, so the engine owns the cell and no human can edit a relation Odoo decided.
|
| 319 |
-
|
| 320 |
-
|
| 321 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 322 |
# β DEBT D-88, closed 2026-08-09. `invoice_origin` carries the ORDER NAME an invoice was
|
| 323 |
# raised from, and the mirror did not sync it until this wave β so order->invoice was a
|
| 324 |
# two-hop join through 963,783 `account_move_line` rows and wave 27 shipped no link at all.
|
|
@@ -358,9 +408,9 @@ def order_fields():
|
|
| 358 |
{"key": "invoice_status", "label": "Invoice status", "type": "select", "source": "overlay",
|
| 359 |
"default": True, "options": ["invoiced", "to invoice", "upselling", "no"]},
|
| 360 |
_scope_field(),
|
| 361 |
-
|
| 362 |
-
|
| 363 |
-
|
| 364 |
# The reciprocal of the invoice's `order_link` (D-88): the invoices raised from THIS
|
| 365 |
# order, matched on the order's own name.
|
| 366 |
{"key": "invoices", "label": "Invoices", "type": "link", "source": "overlay",
|
|
@@ -1071,18 +1121,44 @@ def read_vendors(cur):
|
|
| 1071 |
have = columns(cur, "res_partner")
|
| 1072 |
if not have or not columns(cur, "account_move"):
|
| 1073 |
return []
|
| 1074 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1075 |
"FROM res_partner p WHERE p.id IN "
|
| 1076 |
f" (SELECT partner_id FROM account_move WHERE {_VENDOR_DOCS} "
|
| 1077 |
" AND partner_id IS NOT NULL)")
|
| 1078 |
out = []
|
| 1079 |
-
for (pid, name, country
|
|
|
|
| 1080 |
out.append({
|
| 1081 |
"_id": str(pid),
|
| 1082 |
"vendor": str(name or ""),
|
| 1083 |
"odoo_id": int(pid),
|
| 1084 |
VENDOR_JOIN_KEY: int(pid),
|
| 1085 |
"country": str(country or ""),
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1086 |
})
|
| 1087 |
return out
|
| 1088 |
|
|
@@ -1118,8 +1194,14 @@ class Refused(Exception):
|
|
| 1118 |
#: point: adding an Odoo entity is a spec row plus a reader, not a fifth copy of the spawn code.
|
| 1119 |
#: β ORDER MATTERS ONLY FOR THE REFUSAL MESSAGE; `plan` checks every cap before anything commits.
|
| 1120 |
TABLES = (
|
| 1121 |
-
|
| 1122 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1123 |
("invoices", INVOICES_KEY, "Odoo invoices", invoice_fields),
|
| 1124 |
("orders", ORDERS_KEY, "Odoo orders", order_fields),
|
| 1125 |
# β WAVE 28 / R1. Measured populations: 19 / 192 / 6,538 / 393 β every one of them two orders
|
|
@@ -1139,6 +1221,66 @@ TABLES = (
|
|
| 1139 |
("gl_lines", GL_LINES_KEY, "Odoo GL lines", gl_line_fields),
|
| 1140 |
)
|
| 1141 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1142 |
#: The bucket -> reader map. β ITS ABSENCES ARE LOAD-BEARING: a bucket with no reader has no
|
| 1143 |
#: python row builder ANYWHERE, which is what makes "never materialised" structural rather than a
|
| 1144 |
#: policy `plan()` could forget. The two line grains are absent for that reason and no other.
|
|
@@ -1412,7 +1554,7 @@ def plan(cur, rt=None):
|
|
| 1412 |
return built
|
| 1413 |
|
| 1414 |
|
| 1415 |
-
def apply_plan(rt, built, username="automation", today=None):
|
| 1416 |
"""Create-or-merge every table in `built` and its rows. Idempotent by construction.
|
| 1417 |
|
| 1418 |
Row ids ARE the Odoo ids, so a re-run updates in place and never appends a second copy of the
|
|
@@ -1425,6 +1567,9 @@ def apply_plan(rt, built, username="automation", today=None):
|
|
| 1425 |
raise Refused("; ".join(built["problems"]))
|
| 1426 |
stamp = today or _iso_today()
|
| 1427 |
written = {}
|
|
|
|
|
|
|
|
|
|
| 1428 |
plans = [(key, label, fields(), built[bucket])
|
| 1429 |
for bucket, key, label, fields in TABLES if bucket in built]
|
| 1430 |
|
|
@@ -1442,11 +1587,29 @@ def apply_plan(rt, built, username="automation", today=None):
|
|
| 1442 |
# create. Inside one updater, a raise aborts before anything is persisted.
|
| 1443 |
def _apply_all(cur):
|
| 1444 |
cur = cur if isinstance(cur, dict) else {}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1445 |
for key, label, fields, rows in plans:
|
| 1446 |
written[key] = _ensure_table_inplace(cur, key, label, fields, rows, username, stamp)
|
| 1447 |
return cur
|
| 1448 |
|
| 1449 |
rt.update(_ut().STORE_KEY, _apply_all, flush="sync")
|
|
|
|
|
|
|
| 1450 |
return written
|
| 1451 |
|
| 1452 |
|
|
@@ -1478,12 +1641,37 @@ def _ensure_table_inplace(cur, key, label, fields, rows, username, stamp):
|
|
| 1478 |
for row in wanted.values():
|
| 1479 |
row["refreshed"] = stamp
|
| 1480 |
counts = {"added": 0, "updated": 0, "removed": 0, "rows": len(wanted)}
|
|
|
|
| 1481 |
table = cur.get(key)
|
| 1482 |
if table is None:
|
| 1483 |
if len(cur) >= ut.MAX_TABLES:
|
| 1484 |
# β `ut_ensure` returns silently at this cap; a silent no-op here would report a
|
| 1485 |
# successful refresh over a table that does not exist.
|
| 1486 |
raise Refused(f"{key}: tenant is at MAX_TABLES={ut.MAX_TABLES}; nothing created")
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1487 |
table = cur[key] = {
|
| 1488 |
"key": key, "label": label, "source": ut.AUTOMATION_SOURCE,
|
| 1489 |
"createdBy": username, "created": stamp, "fields": [], "rows": {},
|
|
@@ -1499,8 +1687,33 @@ def _ensure_table_inplace(cur, key, label, fields, rows, username, stamp):
|
|
| 1499 |
# an empty grid.
|
| 1500 |
if key in READ_THROUGH_KEYS:
|
| 1501 |
table["readThrough"] = True
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1502 |
have = {str(f.get("key")): f for f in (table.get("fields") or [])}
|
| 1503 |
for field in fields:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1504 |
fkey = str(field.get("key"))
|
| 1505 |
if fkey not in have:
|
| 1506 |
table.setdefault("fields", []).append(dict(field))
|
|
@@ -1599,8 +1812,13 @@ def refresh(rt, tenant, username="automation", cur=None, today=None):
|
|
| 1599 |
built.pop(bucket, None)
|
| 1600 |
else:
|
| 1601 |
skipped = []
|
| 1602 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1603 |
return {"tables": written,
|
|
|
|
| 1604 |
# R6's second sentence: a set that was deliberately not built SAYS SO, with the keys.
|
| 1605 |
**({"skipped": skipped} if skipped else {}),
|
| 1606 |
**{bucket: len(built[bucket]) for bucket, _k, _l, _f in TABLES if bucket in built}}
|
|
|
|
| 117 |
return user_tables
|
| 118 |
|
| 119 |
|
| 120 |
+
def _registry():
|
| 121 |
+
"""`core.registry`, imported the same lazy way `_ut` is β this module is imported by the
|
| 122 |
+
route layer before `platform/` is necessarily on the path."""
|
| 123 |
+
import core.registry as registry
|
| 124 |
+
return registry
|
| 125 |
+
|
| 126 |
+
|
| 127 |
def _iso_today():
|
| 128 |
return _dt.date.today().strftime("%Y-%m-%d")
|
| 129 |
|
|
|
|
| 187 |
"source": "overlay", "default": True},
|
| 188 |
# β THE INVERSE HALF: the customers whose `agent_id` names this agent. MEASURED: 2,093
|
| 189 |
# customers carry one and ALL 2,093 resolve to a row in this table (zero dangling).
|
| 190 |
+
# β W33-T43 / AMENDMENT A2 β the `customers` REVERSE link DELETED. See `invoice_fields`
|
| 191 |
+
# for the ruling. β This one costs more than the other two and the difference is worth
|
| 192 |
+
# recording: those were a click-through to a record whose id stays on the row, while this
|
| 193 |
+
# was an agent's BOOK β the list of customers assigned to them. The id side survives
|
| 194 |
+
# (`agent_id` here, and `agent_id` on `customer_data`), so the relationship is intact in
|
| 195 |
+
# the data and only the rendered list is gone; the same question is answerable on the
|
| 196 |
+
# customer grid by filtering `agent_id`, and at analytical grain via the `agent` dim on
|
| 197 |
+
# `sales_lines` / `sales_orders`.
|
| 198 |
_refreshed_field(),
|
| 199 |
)]
|
| 200 |
|
|
|
|
| 249 |
"default": False, "description": "The `res.partner` id. Also this row's id."},
|
| 250 |
{"key": VENDOR_JOIN_KEY, "label": "Odoo vendor id", "type": "int", "source": "overlay",
|
| 251 |
"default": False},
|
| 252 |
+
# ββ W33-T48 / owner item 13 β the columns the census proved are there and were not shown.
|
| 253 |
+
# β `default` is deliberately split: the ones a vendor list is READ for (contact + tax id)
|
| 254 |
+
# arrive visible; the postal lines arrive HIDDEN, because four address columns turned on by
|
| 255 |
+
# default would push the useful ones off the first screen, and DESIGN.md's "never
|
| 256 |
+
# over-explain" applies to columns as much as to prose. Every one is one click away in the
|
| 257 |
+
# field picker, and a locked database still allows fields (item 4's vocabulary).
|
| 258 |
{"key": "country", "label": "Country", "type": "text", "source": "overlay",
|
| 259 |
"default": True},
|
| 260 |
+
{"key": "email", "label": "Email", "type": "text", "source": "overlay", "default": True},
|
| 261 |
+
{"key": "phone", "label": "Phone", "type": "text", "source": "overlay", "default": True},
|
| 262 |
+
{"key": "mobile", "label": "Mobile", "type": "text", "source": "overlay",
|
| 263 |
+
"default": False},
|
| 264 |
+
{"key": "vat", "label": "Tax ID", "type": "text", "source": "overlay", "default": True,
|
| 265 |
+
"description": "Odoo `vat` β the vendor's tax/VAT registration number."},
|
| 266 |
+
# β `vendor_ref`, not `ref`: `ref` is Odoo's own name for it, and the bills grid already
|
| 267 |
+
# uses `ref` for the VENDOR'S INVOICE NUMBER on a document. Two different facts, and a
|
| 268 |
+
# shared spelling across two linked grids is how a rollup ends up summing the wrong column.
|
| 269 |
+
{"key": "vendor_ref", "label": "Vendor reference", "type": "text", "source": "overlay",
|
| 270 |
+
"default": False,
|
| 271 |
+
"description": "Odoo `res.partner.ref` β our internal reference for this vendor."},
|
| 272 |
+
{"key": "website", "label": "Website", "type": "url", "source": "overlay",
|
| 273 |
+
"default": False},
|
| 274 |
+
{"key": "street", "label": "Street", "type": "text", "source": "overlay",
|
| 275 |
+
"default": False},
|
| 276 |
+
{"key": "street2", "label": "Street 2", "type": "text", "source": "overlay",
|
| 277 |
+
"default": False},
|
| 278 |
+
{"key": "city", "label": "City", "type": "text", "source": "overlay", "default": False},
|
| 279 |
+
{"key": "zip", "label": "ZIP", "type": "text", "source": "overlay", "default": False},
|
| 280 |
{"key": "bills", "label": "Bills", "type": "link", "source": "overlay", "default": True,
|
| 281 |
"link": {"table": BILLS_KEY, "on": VENDOR_JOIN_KEY, "from": VENDOR_JOIN_KEY}},
|
| 282 |
_refreshed_field(),
|
|
|
|
| 354 |
_scope_field(),
|
| 355 |
# β THE RECIPROCAL HALF (owner item 2, 2026-08-09). DERIVED (`on` declared), exactly like
|
| 356 |
# its twin, so the engine owns the cell and no human can edit a relation Odoo decided.
|
| 357 |
+
# ββ W33-T43 / AMENDMENT A2 β `customer_link` DELETED, and the loss is stated here rather
|
| 358 |
+
# than left to be inferred from a green gate.
|
| 359 |
+
#
|
| 360 |
+
# It pointed at `ut_odoo_customers`, which W33-T44 retires (R2: one identity per subject).
|
| 361 |
+
# A2 ruled OPTION 2 β retire both twins, DROP the three link columns, keep every data
|
| 362 |
+
# column β so this grid loses the CLICK-THROUGH to a customer record and NOTHING else:
|
| 363 |
+
# `customer` (the name) and `partner_id` (the Odoo id) are plain columns on this same row,
|
| 364 |
+
# and `customer_data` now carries `partner_id` too, so both ends of the join still exist.
|
| 365 |
+
#
|
| 366 |
+
# β THE ALTERNATIVE WAS REFUSED IN WRITING, and the reason belongs beside the deletion:
|
| 367 |
+
# re-pointing this bag at `customer_data` needs `core/user_tables.py::_clean_link`'s `ut_`
|
| 368 |
+
# prefix test relaxed β which makes EVERY GATE GREEN while
|
| 369 |
+
# `automation_engine::compute_relation_cells` still resolves out of the `user_tables`
|
| 370 |
+
# document alone and returns `{}`. Empty cells, blank rollups, nothing red. A2 forbids
|
| 371 |
+
# touching that line this wave for exactly that reason.
|
| 372 |
# β DEBT D-88, closed 2026-08-09. `invoice_origin` carries the ORDER NAME an invoice was
|
| 373 |
# raised from, and the mirror did not sync it until this wave β so order->invoice was a
|
| 374 |
# two-hop join through 963,783 `account_move_line` rows and wave 27 shipped no link at all.
|
|
|
|
| 408 |
{"key": "invoice_status", "label": "Invoice status", "type": "select", "source": "overlay",
|
| 409 |
"default": True, "options": ["invoiced", "to invoice", "upselling", "no"]},
|
| 410 |
_scope_field(),
|
| 411 |
+
# β W33-T43 / AMENDMENT A2 β `customer_link` DELETED here too; see the note on the same
|
| 412 |
+
# column in `invoice_fields` above for the ruling and the refused alternative. This row
|
| 413 |
+
# keeps `customer` and `partner_id`, so only the click-through is gone.
|
| 414 |
# The reciprocal of the invoice's `order_link` (D-88): the invoices raised from THIS
|
| 415 |
# order, matched on the order's own name.
|
| 416 |
{"key": "invoices", "label": "Invoices", "type": "link", "source": "overlay",
|
|
|
|
| 1121 |
have = columns(cur, "res_partner")
|
| 1122 |
if not have or not columns(cur, "account_move"):
|
| 1123 |
return []
|
| 1124 |
+
# ββ W33-T48 (owner item 13). The grid served FIVE columns off a partner the census measured
|
| 1125 |
+
# at SEVENTY-SIX populated fields. The nine added here are the ones a buyer actually asks a
|
| 1126 |
+
# vendor record for β how to reach them, who they are for tax, and where they are.
|
| 1127 |
+
# β EVERY ONE GOES THROUGH `_col`, which substitutes a literal when the mirror lacks the
|
| 1128 |
+
# column. That is not defensive habit: this projection has to keep working against a mirror
|
| 1129 |
+
# that has not been re-synced since the widening, and the alternative is a reader that raises
|
| 1130 |
+
# on the exact box the widening was meant to help. The columns arrive when the backfill runs;
|
| 1131 |
+
# until then these read blank rather than failing.
|
| 1132 |
+
blank = chr(39) + chr(39)
|
| 1133 |
+
sql = ("SELECT p.id, p.name, "
|
| 1134 |
+
f"{_col(have, 'p.country_name', blank)}, {_col(have, 'p.email', blank)}, "
|
| 1135 |
+
f"{_col(have, 'p.phone', blank)}, {_col(have, 'p.mobile', blank)}, "
|
| 1136 |
+
f"{_col(have, 'p.website', blank)}, {_col(have, 'p.vat', blank)}, "
|
| 1137 |
+
f"{_col(have, 'p.ref', blank)}, {_col(have, 'p.street', blank)}, "
|
| 1138 |
+
f"{_col(have, 'p.street2', blank)}, {_col(have, 'p.city', blank)}, "
|
| 1139 |
+
f"{_col(have, 'p.zip', blank)} "
|
| 1140 |
"FROM res_partner p WHERE p.id IN "
|
| 1141 |
f" (SELECT partner_id FROM account_move WHERE {_VENDOR_DOCS} "
|
| 1142 |
" AND partner_id IS NOT NULL)")
|
| 1143 |
out = []
|
| 1144 |
+
for (pid, name, country, email, phone, mobile, website, vat, ref,
|
| 1145 |
+
street, street2, city, zipc) in cur.execute(sql).fetchall():
|
| 1146 |
out.append({
|
| 1147 |
"_id": str(pid),
|
| 1148 |
"vendor": str(name or ""),
|
| 1149 |
"odoo_id": int(pid),
|
| 1150 |
VENDOR_JOIN_KEY: int(pid),
|
| 1151 |
"country": str(country or ""),
|
| 1152 |
+
"email": str(email or ""),
|
| 1153 |
+
"phone": str(phone or ""),
|
| 1154 |
+
"mobile": str(mobile or ""),
|
| 1155 |
+
"website": str(website or ""),
|
| 1156 |
+
"vat": str(vat or ""),
|
| 1157 |
+
"vendor_ref": str(ref or ""),
|
| 1158 |
+
"street": str(street or ""),
|
| 1159 |
+
"street2": str(street2 or ""),
|
| 1160 |
+
"city": str(city or ""),
|
| 1161 |
+
"zip": str(zipc or ""),
|
| 1162 |
})
|
| 1163 |
return out
|
| 1164 |
|
|
|
|
| 1194 |
#: point: adding an Odoo entity is a spec row plus a reader, not a fifth copy of the spawn code.
|
| 1195 |
#: β ORDER MATTERS ONLY FOR THE REFUSAL MESSAGE; `plan` checks every cap before anything commits.
|
| 1196 |
TABLES = (
|
| 1197 |
+
# ββ `customers` AND `products` ARE GONE FROM THIS TUPLE β W33-T44 / owner item 12 /
|
| 1198 |
+
# AMENDMENT A2. They presented the same SUBJECTS as the compiled registry modules
|
| 1199 |
+
# `customer_data` and `product_data` ("why do we have 'Odoo products' already with the current
|
| 1200 |
+
# Products database? The Unique ID is redundant"), and R2 ruled the LEGACY key survives: it
|
| 1201 |
+
# keeps its store bucket, so no saved view, grant, cohort or formula moves, and it now carries
|
| 1202 |
+
# the twins' join keys (`partner_id`; `product_id` pending the ask in `mailbox/E.md`).
|
| 1203 |
+
# Dropping the row here is what stops them being planned, built or re-created;
|
| 1204 |
+
# `RETIRED_KEYS` below is what removes the rows a tenant already has.
|
| 1205 |
("invoices", INVOICES_KEY, "Odoo invoices", invoice_fields),
|
| 1206 |
("orders", ORDERS_KEY, "Odoo orders", order_fields),
|
| 1207 |
# β WAVE 28 / R1. Measured populations: 19 / 192 / 6,538 / 393 β every one of them two orders
|
|
|
|
| 1221 |
("gl_lines", GL_LINES_KEY, "Odoo GL lines", gl_line_fields),
|
| 1222 |
)
|
| 1223 |
|
| 1224 |
+
#: store key -> the REAL-WORLD POPULATION that table presents (`core.registry`'s `subject`
|
| 1225 |
+
#: vocabulary, same strings, one namespace). β W33-T41 / item 12a.
|
| 1226 |
+
#:
|
| 1227 |
+
#: β A SEPARATE MAP RATHER THAN A FIFTH ELEMENT ON EACH `TABLES` ROW, and that is not tidiness:
|
| 1228 |
+
#: six sites in this file and two in the gate unpack `for bucket, key, _l, _f in TABLES`, so
|
| 1229 |
+
#: widening the tuple is eight edits that all fail loudly at once and one β in a gate β that
|
| 1230 |
+
#: would fail QUIETLY, having already been rewritten to match. The subject is a fact ABOUT the
|
| 1231 |
+
#: key, and this is the shape that says so.
|
| 1232 |
+
#:
|
| 1233 |
+
#: β THE THREE res.partner SUBSETS ARE THREE SUBJECTS, NOT ONE. Customers, agents and vendors all
|
| 1234 |
+
#: read `res_partner`, and they are different POPULATIONS of it β the claim is over who is in the
|
| 1235 |
+
#: database, never over which Odoo model was queried. Same for `account_move`, which is the
|
| 1236 |
+
#: customer-invoice book under one WHERE and the vendor-bill book under another.
|
| 1237 |
+
TABLE_SUBJECTS = {
|
| 1238 |
+
# β `CUSTOMERS_KEY` and `PRODUCTS_KEY` are absent β W33-T44 retired them, and their subjects
|
| 1239 |
+
# (`odoo:res.partner`, `odoo:product.product`) are claimed by `core.registry`'s `customer_data`
|
| 1240 |
+
# and `product_data` rows, which is now the ONLY claim on each. That is item 12 satisfied: one
|
| 1241 |
+
# subject, one database, and `subject_conflict` would REFUSE either of these keys if a future
|
| 1242 |
+
# spec row tried to bring it back.
|
| 1243 |
+
INVOICES_KEY: "odoo:account.move.customer",
|
| 1244 |
+
ORDERS_KEY: "odoo:sale.order",
|
| 1245 |
+
AGENTS_KEY: "odoo:res.partner.agent",
|
| 1246 |
+
ACCOUNTS_KEY: "odoo:account.account",
|
| 1247 |
+
VENDORS_KEY: "odoo:res.partner.vendor",
|
| 1248 |
+
BILLS_KEY: "odoo:account.move.vendor",
|
| 1249 |
+
ORDER_LINES_KEY: "odoo:sale.order.line",
|
| 1250 |
+
GL_LINES_KEY: "odoo:account.move.line",
|
| 1251 |
+
}
|
| 1252 |
+
|
| 1253 |
+
#: ββ THE TWO RETIRED KEYS β W33-T44 / AMENDMENT A2. The rows a tenant ALREADY HAS.
|
| 1254 |
+
#:
|
| 1255 |
+
#: Dropping the `TABLES` rows above stops these being planned or re-created; it does NOT remove the
|
| 1256 |
+
#: definitions and rows already sitting in a tenant's `user_tables` document, which is what the
|
| 1257 |
+
#: owner actually sees in the nav. This set is what removes them, and it is applied inside
|
| 1258 |
+
#: `apply_plan`'s single atomic updater β i.e. BY THE CONTAINER, on the boot rebuild and every
|
| 1259 |
+
#: resync.
|
| 1260 |
+
#:
|
| 1261 |
+
#: β IT MUST BE THE CONTAINER AND NOT A CLI, AND THIS IS MEASURED, NOT CAUTIOUS (D-195): a
|
| 1262 |
+
#: developer's script CAN write the tenant store, the write returns clean, a fresh read confirms
|
| 1263 |
+
#: it β and the running Space reverts it within a minute, because the container holds the document
|
| 1264 |
+
#: and re-uploads its own copy (download-modify-upload, last write wins). A removal shipped as a
|
| 1265 |
+
#: script is a dry run that reports success.
|
| 1266 |
+
#:
|
| 1267 |
+
#: β AND A SWEEP THAT DELIVERS MUST NOT CREATE. Wave 32's `ut_ensure` was handed a merge-only job
|
| 1268 |
+
#: and minted 8 empty databases in every tenant, because the door it used creates when absent. This
|
| 1269 |
+
#: is a `pop`, it runs only over keys already present, and the gate asserts BOTH halves β removed,
|
| 1270 |
+
#: AND not re-created on the next pass. Gating only the removal would pass on a tree that deletes
|
| 1271 |
+
#: and re-adds the table every 30 minutes.
|
| 1272 |
+
RETIRED_KEYS = (CUSTOMERS_KEY, PRODUCTS_KEY)
|
| 1273 |
+
|
| 1274 |
+
#: β THE GRANDFATHER LIST IS DELETED β W33-T44 did what it was written to force.
|
| 1275 |
+
#:
|
| 1276 |
+
#: It existed for exactly one wave, to keep the product runnable between W33-T41 (the uniqueness
|
| 1277 |
+
#: check) and W33-T44 (the retirement): the check is CORRECT and the collision it forbids was
|
| 1278 |
+
#: LIVE, so without a named exemption the spawn refused on any fresh document and tenant #0 wrote
|
| 1279 |
+
#: nothing at all. The exemption was ratcheted BOTH ways β a collision outside it was a new
|
| 1280 |
+
#: duplicate, a member that stopped colliding was a stale exemption β so retiring the twins turned
|
| 1281 |
+
#: the gate RED until this constant went with them. It did, and that is the ratchet working.
|
| 1282 |
+
#: `verify_odoo_relational::_prove_subject_uniqueness` now asserts the collision set is EMPTY.
|
| 1283 |
+
|
| 1284 |
#: The bucket -> reader map. β ITS ABSENCES ARE LOAD-BEARING: a bucket with no reader has no
|
| 1285 |
#: python row builder ANYWHERE, which is what makes "never materialised" structural rather than a
|
| 1286 |
#: policy `plan()` could forget. The two line grains are absent for that reason and no other.
|
|
|
|
| 1554 |
return built
|
| 1555 |
|
| 1556 |
|
| 1557 |
+
def apply_plan(rt, built, username="automation", today=None, report=None):
|
| 1558 |
"""Create-or-merge every table in `built` and its rows. Idempotent by construction.
|
| 1559 |
|
| 1560 |
Row ids ARE the Odoo ids, so a re-run updates in place and never appends a second copy of the
|
|
|
|
| 1567 |
raise Refused("; ".join(built["problems"]))
|
| 1568 |
stamp = today or _iso_today()
|
| 1569 |
written = {}
|
| 1570 |
+
# β An OPTIONAL out-parameter, not a return-shape change: `written` has one value shape and
|
| 1571 |
+
# keeps it. A caller that wants to SAY what was retired passes a dict; `refresh` does.
|
| 1572 |
+
retired = []
|
| 1573 |
plans = [(key, label, fields(), built[bucket])
|
| 1574 |
for bucket, key, label, fields in TABLES if bucket in built]
|
| 1575 |
|
|
|
|
| 1587 |
# create. Inside one updater, a raise aborts before anything is persisted.
|
| 1588 |
def _apply_all(cur):
|
| 1589 |
cur = cur if isinstance(cur, dict) else {}
|
| 1590 |
+
# ββ W33-T44 β THE RETIREMENT, INSIDE THE SAME ATOMIC WRITE. This updater is the ONE
|
| 1591 |
+
# sync write the whole spawn makes, and it runs in the CONTAINER (boot rebuild + every
|
| 1592 |
+
# resync), which is the only place a change to the tenant document survives (D-195: the
|
| 1593 |
+
# same edit from a CLI reports success and is reverted within a minute).
|
| 1594 |
+
# β It POPS and never creates: `RETIRED_KEYS` are absent from `TABLES`, so `plans` cannot
|
| 1595 |
+
# contain them, and there is no door here that could re-add one. `removed` is reported so
|
| 1596 |
+
# a caller can SAY what happened rather than infer it from a table going missing.
|
| 1597 |
+
# β THE REMOVED KEYS DO **NOT** GO INTO `written`, and the first cut of this put them
|
| 1598 |
+
# there. `written` maps table key -> a COUNTS dict, and every consumer iterates its
|
| 1599 |
+
# `.values()` expecting `c["added"]`; a list under `"_retired"` made the very next leg die
|
| 1600 |
+
# with `TypeError: list indices must be integers`. One dict, two value shapes, is a
|
| 1601 |
+
# sentinel in a result set [[sentinel-in-a-sort-key]] β so the retirement reports through
|
| 1602 |
+
# its OWN channel and the return type stays exactly what it was.
|
| 1603 |
+
for key in RETIRED_KEYS:
|
| 1604 |
+
if cur.pop(key, None) is not None:
|
| 1605 |
+
retired.append(key)
|
| 1606 |
for key, label, fields, rows in plans:
|
| 1607 |
written[key] = _ensure_table_inplace(cur, key, label, fields, rows, username, stamp)
|
| 1608 |
return cur
|
| 1609 |
|
| 1610 |
rt.update(_ut().STORE_KEY, _apply_all, flush="sync")
|
| 1611 |
+
if report is not None and retired:
|
| 1612 |
+
report["retired"] = sorted(retired)
|
| 1613 |
return written
|
| 1614 |
|
| 1615 |
|
|
|
|
| 1641 |
for row in wanted.values():
|
| 1642 |
row["refreshed"] = stamp
|
| 1643 |
counts = {"added": 0, "updated": 0, "removed": 0, "rows": len(wanted)}
|
| 1644 |
+
subject = TABLE_SUBJECTS.get(key)
|
| 1645 |
table = cur.get(key)
|
| 1646 |
if table is None:
|
| 1647 |
if len(cur) >= ut.MAX_TABLES:
|
| 1648 |
# β `ut_ensure` returns silently at this cap; a silent no-op here would report a
|
| 1649 |
# successful refresh over a table that does not exist.
|
| 1650 |
raise Refused(f"{key}: tenant is at MAX_TABLES={ut.MAX_TABLES}; nothing created")
|
| 1651 |
+
# ββ W33-T41 / item 12a β THE UNIQUENESS CHECK, ON THE LINE THAT MINTED THE DUPLICATE.
|
| 1652 |
+
#
|
| 1653 |
+
# β IT GUARDS **CREATION ONLY**, AND THAT IS THE WHOLE DESIGN, NOT A WEAKENING. This
|
| 1654 |
+
# function is the boot rebuild and the 1800 s resync; it adopts an existing table by key
|
| 1655 |
+
# on every pass. A claim test outside this `if` refuses the table it created last boot,
|
| 1656 |
+
# `_apply_all` raises inside the updater, and tenant #0 spawns NOTHING β the check would
|
| 1657 |
+
# take the product down to prevent a duplicate that already exists. Refusing the SECOND
|
| 1658 |
+
# birth is what "make sure this never happens" asks for; the FIRST one is T44's job to
|
| 1659 |
+
# remove, and it is removed by dropping its `TABLES` row, not by a guard here.
|
| 1660 |
+
#
|
| 1661 |
+
# β Claims are gathered from THIS TENANT'S document (`cur`) plus the compiled registry.
|
| 1662 |
+
# Never a module-level cache: one Space process serves every tenant, and two tenants both
|
| 1663 |
+
# holding an "Odoo customers" is correct (that is D-169's shape, and it is not repeated
|
| 1664 |
+
# here). A stored definition with no `subject` claims nothing.
|
| 1665 |
+
held = {t["subject"]: k for k, t in cur.items()
|
| 1666 |
+
if isinstance(t, dict) and t.get("subject")}
|
| 1667 |
+
# β NO EXEMPTION ANY MORE. The grandfather list is deleted with the two tables it covered
|
| 1668 |
+
# (W33-T44), so this is now the plain rule the owner asked for: one subject, one database.
|
| 1669 |
+
other = _registry().subject_conflict(subject, key, claimed=held)
|
| 1670 |
+
if other:
|
| 1671 |
+
raise Refused(
|
| 1672 |
+
f"{key}: refusing to create a second database for {subject!r} β {other!r} "
|
| 1673 |
+
f"already presents it. One subject, one database (item 12a); if this table is "
|
| 1674 |
+
f"meant to replace {other!r}, retire {other!r} first rather than shipping both")
|
| 1675 |
table = cur[key] = {
|
| 1676 |
"key": key, "label": label, "source": ut.AUTOMATION_SOURCE,
|
| 1677 |
"createdBy": username, "created": stamp, "fields": [], "rows": {},
|
|
|
|
| 1687 |
# an empty grid.
|
| 1688 |
if key in READ_THROUGH_KEYS:
|
| 1689 |
table["readThrough"] = True
|
| 1690 |
+
# W33-T41 β the claim, made DURABLE on the definition. Written on every pass for the same
|
| 1691 |
+
# reason `readThrough` is: it is derived from this module's own structure, so the code is what
|
| 1692 |
+
# it has to agree with, and a definition that lost the stamp should regain it rather than go
|
| 1693 |
+
# on being invisible to the next table's claim test. β It is also the ONLY way the check sees
|
| 1694 |
+
# a `ut_*` table at all β those are per-tenant DATA, never compiled registry rows, so a cold
|
| 1695 |
+
# process reading a fresh document has nothing else to read the claim off.
|
| 1696 |
+
if subject:
|
| 1697 |
+
table["subject"] = subject
|
| 1698 |
have = {str(f.get("key")): f for f in (table.get("fields") or [])}
|
| 1699 |
for field in fields:
|
| 1700 |
+
# ββ THE ONE DOOR THAT BYPASSES THE FIELD VALIDATOR, HARDENED WHERE IT BYPASSES IT.
|
| 1701 |
+
#
|
| 1702 |
+
# `user_tables._clean_field` stamps `source: 'overlay'` unconditionally on create AND
|
| 1703 |
+
# patch, so every field that goes through the normal door has one. This function does NOT
|
| 1704 |
+
# go through that door β it writes definitions straight into the document β and
|
| 1705 |
+
# `aios_grid.rows_from_pool` reads `field["source"]` as a HARD KEY, so a contract that
|
| 1706 |
+
# ever omitted it would 500 the entire rows route rather than degrade one column. Measured
|
| 1707 |
+
# today across 9 automation-owned tables and 173 fields: zero are missing it, so this is
|
| 1708 |
+
# LATENT, not live (A's PENDING row, raised as D-9 and corrected by D-23 β the crash that
|
| 1709 |
+
# prompted it came from a hand-written test fixture, not from production).
|
| 1710 |
+
#
|
| 1711 |
+
# β Fixed HERE rather than by softening `rows_from_pool` to `.get`, deliberately: a
|
| 1712 |
+
# missing `source` means the definition does not say which stratum owns the column, and
|
| 1713 |
+
# rendering it as blank would bury that. The default matches what the validator would
|
| 1714 |
+
# have stamped, so the bypass stops being a hole without inventing a second rule.
|
| 1715 |
+
if isinstance(field, dict) and not field.get("source"):
|
| 1716 |
+
field = {**field, "source": "overlay"}
|
| 1717 |
fkey = str(field.get("key"))
|
| 1718 |
if fkey not in have:
|
| 1719 |
table.setdefault("fields", []).append(dict(field))
|
|
|
|
| 1812 |
built.pop(bucket, None)
|
| 1813 |
else:
|
| 1814 |
skipped = []
|
| 1815 |
+
# β W33-T44: a table this pass REMOVED is reported, not inferred from a grid going missing.
|
| 1816 |
+
# Same rule as `skipped` below β R6's second sentence: what was deliberately not built (or no
|
| 1817 |
+
# longer built) SAYS SO, with the keys.
|
| 1818 |
+
plan_report = {}
|
| 1819 |
+
written = apply_plan(rt, built, username=username, today=today, report=plan_report)
|
| 1820 |
return {"tables": written,
|
| 1821 |
+
**({"retired": plan_report["retired"]} if plan_report.get("retired") else {}),
|
| 1822 |
# R6's second sentence: a set that was deliberately not built SAYS SO, with the keys.
|
| 1823 |
**({"skipped": skipped} if skipped else {}),
|
| 1824 |
**{bucket: len(built[bucket]) for bucket, _k, _l, _f in TABLES if bucket in built}}
|
api/routes_admin.py
CHANGED
|
@@ -356,7 +356,78 @@ def set_password(username: str, body: dict = Body(default=None),
|
|
| 356 |
#: so a migrated account would be locked out of Product with no control anywhere to grant it:
|
| 357 |
#: fail-closed, but unadministrable. The editor grows its section with zero client edits
|
| 358 |
#: (S3 built it off this route's `modules` + `fields_by_module`).
|
| 359 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 360 |
|
| 361 |
|
| 362 |
def _module_fields(key):
|
|
@@ -374,23 +445,98 @@ def _module_fields(key):
|
|
| 374 |
a filter naming a field the product rows lack would DENY every row via `permits()`.
|
| 375 |
The product contract is served CONSOLIDATED (every column) on purpose: a BU-scoped reader
|
| 376 |
is served fewer columns, but the ADMIN is choosing what may ever be hidden.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 377 |
"""
|
| 378 |
import aios_grid
|
| 379 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 380 |
out = []
|
| 381 |
for f in src:
|
| 382 |
if not isinstance(f, dict) or not f.get("key"):
|
| 383 |
continue
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 384 |
out.append({"key": f["key"], "label": f.get("label") or f["key"],
|
| 385 |
"type": f.get("type") or "text",
|
| 386 |
-
**({"options":
|
| 387 |
**({"pinned": True} if f.get("pinned") else {})})
|
| 388 |
return out
|
| 389 |
|
| 390 |
|
| 391 |
-
def
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 392 |
"""Validate a whole `perms` block. FAIL-CLOSED, and LOUD rather than lenient.
|
| 393 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 394 |
β WHY THIS REFUSES WHERE `clean_filter_tree` DROPS. The view sanitiser is deliberately
|
| 395 |
drop-per-node: one bad rule must never cost a user their whole saved view. A PERMISSION
|
| 396 |
filter is the opposite situation β an admin types "agent is Tara", a leaf is silently
|
|
@@ -409,11 +555,21 @@ def _clean_perms(v):
|
|
| 409 |
return None
|
| 410 |
if not isinstance(v, dict):
|
| 411 |
raise err(400, "bad_perms", "perms must be an object keyed by module")
|
| 412 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 413 |
if unknown:
|
| 414 |
raise err(400, "bad_perms",
|
| 415 |
-
f"unknown module keys: {unknown} β
|
| 416 |
-
f"{
|
| 417 |
out = {}
|
| 418 |
for key, raw in v.items():
|
| 419 |
if not isinstance(raw, dict):
|
|
@@ -730,8 +886,16 @@ def get_perms(username: str, session: Session = Depends(admin_gate)):
|
|
| 730 |
# omitted from `perms` would become an explicit DENY the moment anyone pressed Save. The
|
| 731 |
# default sent is the EFFECTIVE one (`may_access`), so an un-migrated record shows the
|
| 732 |
# access its legacy grant currently gives rather than a guess in either direction.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 733 |
perms_out = {}
|
| 734 |
-
for k in
|
| 735 |
e = stored.get(k)
|
| 736 |
perms_out[k] = e if isinstance(e, dict) else {
|
| 737 |
"access": bool(perm_scope.may_access(rec, k)), "filter": None, "hiddenFields": []}
|
|
@@ -744,11 +908,20 @@ def get_perms(username: str, session: Session = Depends(admin_gate)):
|
|
| 744 |
# `role == 'admin'` bypasses perms entirely (amendment 4) β sent so the editor can
|
| 745 |
# say "Everything (admin)" instead of rendering stored rules that do not apply.
|
| 746 |
"is_admin": perms.is_admin(rec),
|
| 747 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 748 |
# S3 ask 1 β CANONICAL SHAPE: a BARE ARRAY of fields per module key. Not the nav
|
| 749 |
# schema envelope; the editor needs the field list and nothing else, and one shape
|
| 750 |
# beats two readings of a sentence.
|
| 751 |
-
|
|
|
|
|
|
|
|
|
|
| 752 |
|
| 753 |
|
| 754 |
@router.put("/admin/users/{username}/perms")
|
|
@@ -781,7 +954,10 @@ def put_perms(username: str, body: dict = Body(default=None),
|
|
| 781 |
raise err(400, "self_perms",
|
| 782 |
"you cannot set permissions on your own account β ask another admin")
|
| 783 |
|
| 784 |
-
|
|
|
|
|
|
|
|
|
|
| 785 |
cleaned = _fold_legacy_scope(reg[uname], cleaned)
|
| 786 |
_guard_bu_widening(reg[uname], cleaned, bool(body.get("confirm_widen")))
|
| 787 |
users.set_access(uname, perms=cleaned)
|
|
@@ -796,7 +972,29 @@ def put_perms(username: str, body: dict = Body(default=None),
|
|
| 796 |
"perms_v": int(rec.get("perms_v") or 0)}
|
| 797 |
|
| 798 |
|
| 799 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 800 |
|
| 801 |
|
| 802 |
@router.get("/settings")
|
|
@@ -827,6 +1025,20 @@ def settings(session: Session = Depends(require_session)):
|
|
| 827 |
},
|
| 828 |
"tenant": {"key": session.tenant, "name": getattr(session.runtime, "name",
|
| 829 |
session.tenant)},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 830 |
# CHROME ONLY. Every /admin route re-checks the role server-side; this exists so the client
|
| 831 |
# does not paint a "Manage users" button that 403s.
|
| 832 |
"admin": perms.is_admin(session.user),
|
|
|
|
| 356 |
#: so a migrated account would be locked out of Product with no control anywhere to grant it:
|
| 357 |
#: fail-closed, but unadministrable. The editor grows its section with zero client edits
|
| 358 |
#: (S3 built it off this route's `modules` + `fields_by_module`).
|
| 359 |
+
#:
|
| 360 |
+
#: ββ WAVE 33 (owner item 11, W33-T33) β **THIS IS A CATALOGUE, NOT AN ANSWER.** It used to be
|
| 361 |
+
#: both, and that was the defect the owner flagged four times: `get_perms` served this tuple
|
| 362 |
+
#: verbatim and never touched `session.runtime`, so EVERY tenant was handed tenant #0's two grid
|
| 363 |
+
#: modules. What this names now is a fact about THIS FILE β the registry topics `_module_fields`
|
| 364 |
+
#: below has a field-schema arm for β and the answer a tenant receives is `_perm_modules(session)`,
|
| 365 |
+
#: which filters this by the tenant's own provisioning and merges the tenant's own `ut_*`
|
| 366 |
+
#: databases. β Serving this list directly again re-opens item 11; `verify_perm_scope`'s
|
| 367 |
+
#: `section_tenant_derived` NC does exactly that and reds.
|
| 368 |
+
#: β CONTRACT C3, CONSUMED (lane E's `W33-T46`, answered as `E-3`). The topic list is DERIVED from
|
| 369 |
+
#: `registry.governable_modules()` β `{topic: {'key','label','subject'}}` over every non-archived,
|
| 370 |
+
#: non-group_only registry row that declares a `topic`. What stays hand-written is
|
| 371 |
+
#: `_FIELD_PROVIDER_KEYS` below, and that is CODE, not policy: each name has its own `aios_grid`
|
| 372 |
+
#: contract behind it in `_module_fields`, and a topic with no arm cannot be governed by this
|
| 373 |
+
#: editor at all. The intersection is the honest answer to "what can this module build pickers for".
|
| 374 |
+
#:
|
| 375 |
+
#: β KEPT AS A SYMBOL RATHER THAN DELETED, deliberately. `verify_api`'s W30a reads
|
| 376 |
+
#: `routes_admin._PERM_MODULES` to assert `perm_scope.BU_FILTERABLE_MODULES` names exactly the
|
| 377 |
+
#: governed topics whose contract carries `dba`. Deleting the name would make that gate raise
|
| 378 |
+
#: `AttributeError` β a CRASH, which scores as "the gate is broken" rather than as a red
|
| 379 |
+
#: [[gate-must-go-red-not-crash]] β and `verify_api.py` is lane A's fence. Derived-and-kept gives
|
| 380 |
+
#: that assertion a truer subject than the literal ever did, and costs nobody a cross-fence edit.
|
| 381 |
+
_FIELD_PROVIDER_KEYS = frozenset({"customer_data", "product_data"})
|
| 382 |
+
|
| 383 |
+
|
| 384 |
+
def _governable_catalogue():
|
| 385 |
+
"""The REGISTRY topics this module can govern: `[{key, label}]`, in registry order.
|
| 386 |
+
|
| 387 |
+
β No tenant filtering here β that is `perms.tenant_governable_modules`' job, and E's map is
|
| 388 |
+
tenant-blind by design. Two filters in two files answering one question is how the perms route
|
| 389 |
+
and `routes_nav` came apart in the first place.
|
| 390 |
+
"""
|
| 391 |
+
import core.registry as registry
|
| 392 |
+
return [{"key": v["key"], "label": v["label"]}
|
| 393 |
+
for v in registry.governable_modules().values()
|
| 394 |
+
if v.get("key") in _FIELD_PROVIDER_KEYS]
|
| 395 |
+
|
| 396 |
+
|
| 397 |
+
_PERM_MODULES = tuple(m["key"] for m in _governable_catalogue())
|
| 398 |
+
|
| 399 |
+
|
| 400 |
+
def _perm_modules(session):
|
| 401 |
+
"""The databases THIS tenant's permission editor governs: `[{key, label, enforced}]`.
|
| 402 |
+
|
| 403 |
+
Three inputs, none of them a literal: the topic catalogue above, the tenant's provisioned
|
| 404 |
+
module set (`tenant.config['modules']`, exactly the rule `routes_nav.py::nav` applies), and
|
| 405 |
+
the tenant's own `ut_*` databases read through the DEFINITIONS projection.
|
| 406 |
+
|
| 407 |
+
β `user_tables.nav_entries` rather than a fresh listing, deliberately: it is already the ONE
|
| 408 |
+
resolver for "which databases may this account see", it is `may_open`-filtered, and it reads
|
| 409 |
+
the projected document (`all_defs`) so this costs definitions, never the 28.6 MB of rows.
|
| 410 |
+
The caller is admin-gated, so the filter admits the whole tenant β but asking the resolver
|
| 411 |
+
instead of assuming that is what keeps this from becoming the SECOND idea of who may see a
|
| 412 |
+
table (`user_tables.may_open`'s own docstring is the record of the first time that happened).
|
| 413 |
+
"""
|
| 414 |
+
import core.perms as _perms
|
| 415 |
+
import core.user_tables as user_tables
|
| 416 |
+
try:
|
| 417 |
+
ut = user_tables.nav_entries(viewer=session.uname, is_admin=True,
|
| 418 |
+
st=session.runtime)
|
| 419 |
+
except Exception:
|
| 420 |
+
# A store that cannot list the tenant's databases must not take the whole editor down β
|
| 421 |
+
# the topic half is still administrable, and an empty `ut_*` half is visibly empty.
|
| 422 |
+
ut = ()
|
| 423 |
+
return _perms.tenant_governable_modules(session.runtime, _governable_catalogue(),
|
| 424 |
+
ut_entries=ut)
|
| 425 |
+
|
| 426 |
+
|
| 427 |
+
def _enforced_keys(session):
|
| 428 |
+
"""The module keys a permission block may actually be STORED against for this tenant."""
|
| 429 |
+
import core.perms as _perms
|
| 430 |
+
return _perms.enforced_module_keys(_perm_modules(session))
|
| 431 |
|
| 432 |
|
| 433 |
def _module_fields(key):
|
|
|
|
| 445 |
a filter naming a field the product rows lack would DENY every row via `permits()`.
|
| 446 |
The product contract is served CONSOLIDATED (every column) on purpose: a BU-scoped reader
|
| 447 |
is served fewer columns, but the ADMIN is choosing what may ever be hidden.
|
| 448 |
+
|
| 449 |
+
ββ WAVE 33 β THE `else` USED TO BE A FALL-THROUGH, AND IT WAS SILENT-WRONG. The body read
|
| 450 |
+
`aios_grid.product_fields() if key == "product_data" else aios_grid.FIELDS`, so ANY key that
|
| 451 |
+
was not `product_data` got the CUSTOMER contract: the moment the governed list stopped being
|
| 452 |
+
a two-element literal, a `ut_*` database or a third topic would have been handed customer
|
| 453 |
+
columns, `_clean_perms` would have validated an admin's `hiddenFields` against them, and the
|
| 454 |
+
stored wall would name columns that module does not have β which `permits()` resolves by
|
| 455 |
+
DENYING every row. No error at any point. So the map is explicit and an unknown key RAISES:
|
| 456 |
+
a topic without a schema arm is a missing arm, never a customer grid in disguise.
|
| 457 |
"""
|
| 458 |
import aios_grid
|
| 459 |
+
providers = {"customer_data": lambda: aios_grid.FIELDS,
|
| 460 |
+
"product_data": aios_grid.product_fields}
|
| 461 |
+
provider = providers.get(str(key or ""))
|
| 462 |
+
if provider is None:
|
| 463 |
+
# Reached only by a caller that skipped `_perm_modules`. Loud, because the alternative
|
| 464 |
+
# (`[]`) is an empty option list read as an ANSWER β wave 26 item 24, `if ([])` is truthy.
|
| 465 |
+
raise err(400, "ungoverned_module",
|
| 466 |
+
f"{key!r} has no permission-editor field schema β the editor governs "
|
| 467 |
+
f"{sorted(providers)}")
|
| 468 |
+
src = provider()
|
| 469 |
+
known = _server_side_vocabularies()
|
| 470 |
out = []
|
| 471 |
for f in src:
|
| 472 |
if not isinstance(f, dict) or not f.get("key"):
|
| 473 |
continue
|
| 474 |
+
opts = f.get("options")
|
| 475 |
+
if not isinstance(opts, list) or not opts:
|
| 476 |
+
# β D-76 / W33-T35 β SUPPLY WHAT THE SERVER ALREADY KNOWS. See
|
| 477 |
+
# `_server_side_vocabularies`.
|
| 478 |
+
opts = known.get(f["key"])
|
| 479 |
out.append({"key": f["key"], "label": f.get("label") or f["key"],
|
| 480 |
"type": f.get("type") or "text",
|
| 481 |
+
**({"options": list(opts)} if isinstance(opts, list) and opts else {}),
|
| 482 |
**({"pinned": True} if f.get("pinned") else {})})
|
| 483 |
return out
|
| 484 |
|
| 485 |
|
| 486 |
+
def _server_side_vocabularies():
|
| 487 |
+
"""`{field key: [choice, β¦]}` for choice columns whose vocabulary is CLOSED and known here,
|
| 488 |
+
but which the grid contract does not declare.
|
| 489 |
+
|
| 490 |
+
β D-76 β WHY THE PERMISSION EDITOR'S DROPDOWNS WERE EMPTY, AND WHY THE FIX IS HERE. The grid
|
| 491 |
+
resolves a choice column through `types.ts::choiceVocabulary`: the DECLARED list when the
|
| 492 |
+
field has one, otherwise the values seen in the loaded ROWS. This editor loads no rows, so
|
| 493 |
+
every column that leans on the second branch renders `Selectβ¦` with nothing in it β the
|
| 494 |
+
identical shape wave 26 item 24 closed on the Product grid, one surface over. β And the fix
|
| 495 |
+
belongs at the CALLER, never in the panel: `FilterBuilderPanel::choicesFor` treats a supplied
|
| 496 |
+
list as authoritative *including when it is empty* ("this column has no values" is an answer),
|
| 497 |
+
which is correct and must not be weakened. So the caller stops handing it nothing.
|
| 498 |
+
|
| 499 |
+
β IMPORTED, NEVER RESTATED. `stock_bucket`'s labels are `modules/inventory.COVERAGE_LABELS`,
|
| 500 |
+
the same constant `_bucket()` mints from β a copy here would be a second vocabulary that
|
| 501 |
+
drifts the first time a band is renamed [[constant-two-features-share]]. The import is lazy
|
| 502 |
+
for the same reason `aios_grid`'s is: this route should not pull the analytics stack at
|
| 503 |
+
module load.
|
| 504 |
+
|
| 505 |
+
β TWO COLUMNS ARE DELIBERATELY ABSENT, and R6's second sentence says to name them rather than
|
| 506 |
+
let them look handled:
|
| 507 |
+
Β· `category` (product) β an OPEN vocabulary read off Odoo's product categories. There is no
|
| 508 |
+
closed list to declare, and discovering it would mean a pool read on an admin route.
|
| 509 |
+
Β· `odoo_status` (customer) β WAS bare for the same reason and is NOT any more: lane E
|
| 510 |
+
answered `ASK D-15` by declaring `options: ['Active','Archived']` on the CONTRACT, which
|
| 511 |
+
is the right home (the grid picks a declared list up for free) and is why this function
|
| 512 |
+
never needed an arm for it. Recorded because the ask, not a guess, is what settled it.
|
| 513 |
+
"""
|
| 514 |
+
try:
|
| 515 |
+
import modules.inventory as inventory
|
| 516 |
+
labels = list(inventory.COVERAGE_LABELS or ())
|
| 517 |
+
except Exception:
|
| 518 |
+
# A missing analytics import must not take the permission editor down; the dropdown
|
| 519 |
+
# degrades to today's empty one rather than the page to a 500.
|
| 520 |
+
return {}
|
| 521 |
+
return {"stock_bucket": labels} if labels else {}
|
| 522 |
+
|
| 523 |
+
|
| 524 |
+
def _clean_perms(v, enforced_keys=None, listed_keys=None):
|
| 525 |
"""Validate a whole `perms` block. FAIL-CLOSED, and LOUD rather than lenient.
|
| 526 |
|
| 527 |
+
β WAVE 33 (W33-T33) β `enforced_keys` IS PER TENANT AND IT IS NOT OPTIONAL IN PRACTICE. It
|
| 528 |
+
used to be `set(_PERM_MODULES)`, a literal, which is the same tenant-blindness owner item 11
|
| 529 |
+
flagged: an admin of a tenant provisioned for neither grid module could still store a wall
|
| 530 |
+
for both. It now comes from `_enforced_keys(session)`, i.e. from the tenant's own catalogue.
|
| 531 |
+
The default is the catalogue itself so a test or a future caller cannot silently widen it.
|
| 532 |
+
|
| 533 |
+
β AND "LISTED" IS NOT "ENFORCED". `listed_keys` is every database the editor SHOWS, which
|
| 534 |
+
includes this tenant's `ut_*` ones. `perm_scope` is never consulted on those (visibility
|
| 535 |
+
there is `user_tables.may_open` β creator, admin, or a `core.shares` grant), so a wall stored
|
| 536 |
+
against one would be INERT: the editor would say DENY and the table routes would keep
|
| 537 |
+
serving. It is refused with a message that says WHICH of the two it is, because
|
| 538 |
+
"unknown module key" for a database the admin can see on screen is the wrong sentence.
|
| 539 |
+
|
| 540 |
β WHY THIS REFUSES WHERE `clean_filter_tree` DROPS. The view sanitiser is deliberately
|
| 541 |
drop-per-node: one bad rule must never cost a user their whole saved view. A PERMISSION
|
| 542 |
filter is the opposite situation β an admin types "agent is Tara", a leaf is silently
|
|
|
|
| 555 |
return None
|
| 556 |
if not isinstance(v, dict):
|
| 557 |
raise err(400, "bad_perms", "perms must be an object keyed by module")
|
| 558 |
+
governed = set(enforced_keys) if enforced_keys is not None else set(_PERM_MODULES)
|
| 559 |
+
shown = set(listed_keys) if listed_keys is not None else governed
|
| 560 |
+
inert = sorted(set(v) & (shown - governed))
|
| 561 |
+
if inert:
|
| 562 |
+
raise err(400, "unenforced_module",
|
| 563 |
+
f"{inert}: this tenant can SEE these databases, but a permission wall stored "
|
| 564 |
+
f"against them would never be applied β `routes_tables` gates a `ut_*` "
|
| 565 |
+
f"database on `user_tables.may_open` (creator, admin, or a share), not on "
|
| 566 |
+
f"`perm_scope`. Saved silently, it would read as a restriction that is not "
|
| 567 |
+
f"there. Share the database instead, or arm `perm_scope` over `ut_*` first.")
|
| 568 |
+
unknown = sorted(set(v) - shown)
|
| 569 |
if unknown:
|
| 570 |
raise err(400, "bad_perms",
|
| 571 |
+
f"unknown module keys: {unknown} β this tenant's permission editor governs "
|
| 572 |
+
f"{sorted(governed)}")
|
| 573 |
out = {}
|
| 574 |
for key, raw in v.items():
|
| 575 |
if not isinstance(raw, dict):
|
|
|
|
| 886 |
# omitted from `perms` would become an explicit DENY the moment anyone pressed Save. The
|
| 887 |
# default sent is the EFFECTIVE one (`may_access`), so an un-migrated record shows the
|
| 888 |
# access its legacy grant currently gives rather than a guess in either direction.
|
| 889 |
+
#
|
| 890 |
+
# ββ WAVE 33 (W33-T33, owner item 11) β THE LIST IS THIS TENANT'S, NOT A LITERAL. Everything
|
| 891 |
+
# below was built from `_PERM_MODULES` and never touched `session.runtime`, which is why a
|
| 892 |
+
# nurilab or gtmlab admin opened Manage user and saw Royal Imports' Customer and Product
|
| 893 |
+
# databases. `_perm_modules` applies the tenant's own provisioning (the rule `routes_nav`
|
| 894 |
+
# has applied since wave 18) and merges the tenant's own `ut_*` databases.
|
| 895 |
+
modules = _perm_modules(session)
|
| 896 |
+
enforced = [m["key"] for m in modules if m.get("enforced")]
|
| 897 |
perms_out = {}
|
| 898 |
+
for k in enforced:
|
| 899 |
e = stored.get(k)
|
| 900 |
perms_out[k] = e if isinstance(e, dict) else {
|
| 901 |
"access": bool(perm_scope.may_access(rec, k)), "filter": None, "hiddenFields": []}
|
|
|
|
| 908 |
# `role == 'admin'` bypasses perms entirely (amendment 4) β sent so the editor can
|
| 909 |
# say "Everything (admin)" instead of rendering stored rules that do not apply.
|
| 910 |
"is_admin": perms.is_admin(rec),
|
| 911 |
+
# β `enforced` rides every row. A `ut_*` database is LISTED because the owner asked to
|
| 912 |
+
# see every database, and declared UNENFORCED because `perm_scope` is not consulted on
|
| 913 |
+
# that path β so the editor can say which it is instead of painting a dead panel
|
| 914 |
+
# (wave 26 item 24: an empty answer that reads as an answer). The LABEL comes from the
|
| 915 |
+
# registry / the table's own definition; `_MODULE_LABELS` was a hardcoded copy of two
|
| 916 |
+
# registry labels and is deleted with this change.
|
| 917 |
+
"modules": modules,
|
| 918 |
# S3 ask 1 β CANONICAL SHAPE: a BARE ARRAY of fields per module key. Not the nav
|
| 919 |
# schema envelope; the editor needs the field list and nothing else, and one shape
|
| 920 |
# beats two readings of a sentence.
|
| 921 |
+
# ENFORCED MODULES ONLY, and that is the honest shape: a picker for a database whose
|
| 922 |
+
# wall is never applied is a control that lies. An unenforced row carries no entry
|
| 923 |
+
# here at all, so a client cannot mistake `[]` for "this database has no fields".
|
| 924 |
+
"fields_by_module": {k: _module_fields(k) for k in enforced}}
|
| 925 |
|
| 926 |
|
| 927 |
@router.put("/admin/users/{username}/perms")
|
|
|
|
| 954 |
raise err(400, "self_perms",
|
| 955 |
"you cannot set permissions on your own account β ask another admin")
|
| 956 |
|
| 957 |
+
_mods = _perm_modules(session)
|
| 958 |
+
cleaned = _clean_perms(body.get("perms"),
|
| 959 |
+
enforced_keys={m["key"] for m in _mods if m.get("enforced")},
|
| 960 |
+
listed_keys={m["key"] for m in _mods}) or {}
|
| 961 |
cleaned = _fold_legacy_scope(reg[uname], cleaned)
|
| 962 |
_guard_bu_widening(reg[uname], cleaned, bool(body.get("confirm_widen")))
|
| 963 |
users.set_access(uname, perms=cleaned)
|
|
|
|
| 972 |
"perms_v": int(rec.get("perms_v") or 0)}
|
| 973 |
|
| 974 |
|
| 975 |
+
def _store_binding(session):
|
| 976 |
+
"""`data_binding.describe()` for the store THIS SESSION's tenant actually writes.
|
| 977 |
+
|
| 978 |
+
β THE TENANT'S STORE, NOT THE PROCESS DEFAULT, AND THAT DISTINCTION IS THE POINT. Tenant #0
|
| 979 |
+
rides `core.store`'s module default, but nurilab/gtmlab/loopable are bound to their OWN dataset
|
| 980 |
+
repos by `harness/runtime.py:470`, straight out of the control-plane record β which is the path
|
| 981 |
+
that carried three tenants' PRODUCTION stores onto staging while `--data-repo` isolated only
|
| 982 |
+
tenant #0. Reporting the process default here would show "staging store, all fine" to exactly
|
| 983 |
+
the tenants that were not fine.
|
| 984 |
+
|
| 985 |
+
β Degrades to a stated `unknown` rather than raising: a settings page that 500s because it
|
| 986 |
+
could not describe the store is worse than one that says it does not know.
|
| 987 |
+
"""
|
| 988 |
+
try:
|
| 989 |
+
import core.data_binding as data_binding # noqa: PLC0415
|
| 990 |
+
import core.store as store # noqa: PLC0415
|
| 991 |
+
bound = getattr(session.runtime, "store_handle", None)
|
| 992 |
+
repo = getattr(bound, "repo", None) or store.REPO
|
| 993 |
+
return data_binding.describe(repo)
|
| 994 |
+
except Exception as e: # noqa: BLE001
|
| 995 |
+
return {"deployment": "unknown", "production": False, "repo": "",
|
| 996 |
+
"writable": False, "refusal": f"could not resolve the store binding: {e}",
|
| 997 |
+
"localOverride": False, "allowlist": [], "observed": {}}
|
| 998 |
|
| 999 |
|
| 1000 |
@router.get("/settings")
|
|
|
|
| 1025 |
},
|
| 1026 |
"tenant": {"key": session.tenant, "name": getattr(session.runtime, "name",
|
| 1027 |
session.tenant)},
|
| 1028 |
+
# ββ D-315 β WHICH STORE THIS CONTAINER IS BOUND TO, AND WHETHER IT MAY WRITE IT.
|
| 1029 |
+
#
|
| 1030 |
+
# β THIS IS NOT DIAGNOSTIC GARNISH; IT IS THE ONLY WAY THE QUESTION CAN BE ANSWERED.
|
| 1031 |
+
# D-160 established that a Space's environment cannot be read from outside, so "is staging
|
| 1032 |
+
# pointed at production data?" is a question only the container can answer β and it went
|
| 1033 |
+
# unanswered for the whole window in which two builds wrote tenant #0's real store.
|
| 1034 |
+
# `verify_live` asserts this field after logging in, which is a check that survives a role
|
| 1035 |
+
# swap in a way that reading a deploy log never did.
|
| 1036 |
+
#
|
| 1037 |
+
# β Session-gated, beside `version`, for `main.py::health`'s reason: a Space id and a
|
| 1038 |
+
# dataset repo id are public names, but a health endpoint is the first URL a scanner finds
|
| 1039 |
+
# and it may not describe the deployment. No customer data is here β only which store, and
|
| 1040 |
+
# yes or no.
|
| 1041 |
+
"store": _store_binding(session),
|
| 1042 |
# CHROME ONLY. Every /admin route re-checks the role server-side; this exists so the client
|
| 1043 |
# does not paint a "Manage users" button that 403s.
|
| 1044 |
"admin": perms.is_admin(session.user),
|
api/routes_alerts.py
CHANGED
|
@@ -172,8 +172,36 @@ def notification_view(item):
|
|
| 172 |
# β `kind` is OVERWRITTEN, not merged. There was one stored value (`automation_review`) and it
|
| 173 |
# is D-101's dead one; leaving it through would give the client two vocabularies for one
|
| 174 |
# question, which is the defect this wave's item 6 is about in a different file.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 175 |
out = {**item, "read": bool(item.get("read")), "kind": kind,
|
| 176 |
-
"subject": subject or "Notification"}
|
| 177 |
if target is not None:
|
| 178 |
out["target"] = target
|
| 179 |
return out
|
|
@@ -191,7 +219,61 @@ def inbox_view(box):
|
|
| 191 |
items = box.get("items")
|
| 192 |
if not isinstance(items, list):
|
| 193 |
return box
|
| 194 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 195 |
|
| 196 |
|
| 197 |
def _topic_or_400(raw):
|
|
@@ -283,7 +365,7 @@ def _evaluate(session: Session, rec: dict, assemblies=None):
|
|
| 283 |
if isinstance(assemblies, dict):
|
| 284 |
assemblies[memo_key] = g
|
| 285 |
|
| 286 |
-
view = (g
|
| 287 |
if not isinstance(view, dict):
|
| 288 |
# Deleted, or un-shared out from under the alert. Say so on the RECORD rather than
|
| 289 |
# deleting the alert: an alert that silently vanishes is indistinguishable from one that
|
|
@@ -293,7 +375,40 @@ def _evaluate(session: Session, rec: dict, assemblies=None):
|
|
| 293 |
# The SAME row build the grid and `/customers` use β `rows_from_pool` is what puts derived
|
| 294 |
# and overlay values on a row. Evaluating a filter against raw pool dicts would silently
|
| 295 |
# never match any condition on a user-created or measure column.
|
| 296 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 297 |
derived=g.get("derived"))
|
| 298 |
config = view.get("config") or view
|
| 299 |
ctx = filter_eval.EvalCtx(
|
|
@@ -391,12 +506,28 @@ def _require_filtered_view(session: Session, topic: str, view_id: str):
|
|
| 391 |
# the one path that reaches this branch is also the one path with nothing to debug from.
|
| 392 |
raise err(503, "unavailable",
|
| 393 |
f"the table could not be read ({type(e).__name__}) β try again in a moment")
|
| 394 |
-
view = (g
|
| 395 |
if not isinstance(view, dict):
|
| 396 |
raise err(404, "no_view", "that view does not exist on this table")
|
| 397 |
nodes, _conj = filter_eval.tree_parts((view.get("config") or view).get("filters") or [])
|
| 398 |
|
| 399 |
-
# ββ WAVE
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 400 |
#
|
| 401 |
# `is_rule_active(rule, columns)` takes TWO parameters (`harness/filter_sql.py`; every other
|
| 402 |
# caller in the repo passes both). This one passed ONE, so the moment the walk reached a LEAF
|
|
|
|
| 172 |
# β `kind` is OVERWRITTEN, not merged. There was one stored value (`automation_review`) and it
|
| 173 |
# is D-101's dead one; leaving it through would give the client two vocabularies for one
|
| 174 |
# question, which is the defect this wave's item 6 is about in a different file.
|
| 175 |
+
# ββ W33-T28 (owner: "the Inbox reads like email") β THE SENDER, WHICH DID NOT EXIST.
|
| 176 |
+
#
|
| 177 |
+
# β A `verifier` reading the finished wave-32 surface found that the row's sender POSITION was
|
| 178 |
+
# occupied by `kindLabel(n.kind)` β the literals "Alert" / "Automation" / "Shared with you" β
|
| 179 |
+
# i.e. a CATEGORY standing where a who belongs, and no sender field anywhere on the wire, in
|
| 180 |
+
# the model or in the markup. Mail has a from. This is it.
|
| 181 |
+
#
|
| 182 |
+
# β IT IS DERIVED HERE, NOT STORED, FOR EVERY KIND BUT ONE β and the exception is the point.
|
| 183 |
+
# An alert firing and an automation landing rows have no person behind them; their honest
|
| 184 |
+
# sender is the machine that did it, named as the thing the reader recognises. A SHARE has a
|
| 185 |
+
# real person, and only the producer knows who: `routes_shares.py` writes it as `actor` and
|
| 186 |
+
# this reads it back. β It is NOT parsed out of the body prose ("<name> shared this with
|
| 187 |
+
# you") β a sender recovered by regexing a sentence breaks the first time the sentence is
|
| 188 |
+
# reworded, and it would break silently, in the header.
|
| 189 |
+
#
|
| 190 |
+
# β FALLS BACK, NEVER BLANK. A share queued BEFORE `actor` existed has none, and a row with an
|
| 191 |
+
# empty from column reads as a broken inbox rather than as an old notification.
|
| 192 |
+
actor = str(item.get("actor") or "").strip()
|
| 193 |
+
if kind == NOTIF_KIND_SHARE:
|
| 194 |
+
sender = actor or "A teammate"
|
| 195 |
+
elif kind == NOTIF_KIND_AUTOMATION:
|
| 196 |
+
# β "Agents", not "Automation" (W34-T40, corrected at QA 2026-08-17). The client's
|
| 197 |
+
# `senderOf` already falls back to `AGENTS_MODULE_LABEL` β but `if (sent) return sent`
|
| 198 |
+
# runs FIRST, so this server literal won and every actor-less automation notification
|
| 199 |
+
# showed the retired module name in the inbox's From column.
|
| 200 |
+
sender = actor or "Agents"
|
| 201 |
+
else:
|
| 202 |
+
sender = actor or "Alerts"
|
| 203 |
out = {**item, "read": bool(item.get("read")), "kind": kind,
|
| 204 |
+
"subject": subject or "Notification", "sender": sender}
|
| 205 |
if target is not None:
|
| 206 |
out["target"] = target
|
| 207 |
return out
|
|
|
|
| 219 |
items = box.get("items")
|
| 220 |
if not isinstance(items, list):
|
| 221 |
return box
|
| 222 |
+
# ββ W33-T28 / D-208 β THE SERVER'S CLOCK RIDES WITH THE PAGE, and it is what lets the client
|
| 223 |
+
# render a mail-shaped stamp ("09:41" today, "Aug 12" beyond) instead of `2026-08-13 09:41`.
|
| 224 |
+
#
|
| 225 |
+
# β THE CLIENT MUST NOT READ ITS OWN CLOCK, which is D-208's exit condition word for word and
|
| 226 |
+
# is why this key exists rather than a `new Date()` in the browser. `at` is sent as UTC WITH
|
| 227 |
+
# its offset (D-18) precisely so every reader sees the same instant; deciding "is this today?"
|
| 228 |
+
# against a browser clock would re-introduce the drift the offset exists to remove β a reader a
|
| 229 |
+
# day ahead being told an event happened tomorrow [[date-window-vocabulary]]. Both operands
|
| 230 |
+
# now come from the same machine.
|
| 231 |
+
# β Same funnel as the enrichment, so the read door and the mark-read door cannot disagree β
|
| 232 |
+
# the note two lines up records what happened last time only one of them was enriched.
|
| 233 |
+
return {**box, "now": alerts._now_iso(),
|
| 234 |
+
"items": [notification_view(n) for n in items]}
|
| 235 |
+
|
| 236 |
+
|
| 237 |
+
def _view_by_id(g, view_id):
|
| 238 |
+
"""One saved view out of an assembly, by id. `None` when there is no such view.
|
| 239 |
+
|
| 240 |
+
ββ W33-T29 (owner: *"Alert me about new records"* answering "Something went wrong") β THIS
|
| 241 |
+
FUNCTION EXISTS BECAUSE TWO CALL SITES BOTH WROTE `(g.get("views") or {}).get(view_id)`, AND
|
| 242 |
+
`g["views"] IS A LIST`. `aios_grid.views_from_defs` returns `[{...}]`, `workspace_wire` passes
|
| 243 |
+
it straight out and both `ut_assembly` and `grid_assembly` return it unchanged β so `.get` on
|
| 244 |
+
it raises `AttributeError`, and `views_from_defs` always returns at least one element, so the
|
| 245 |
+
`or {}` never fires. **It raised on EVERY call, on every topic, since wave 20.**
|
| 246 |
+
|
| 247 |
+
β AND THE TWO SITES FAILED DIFFERENTLY, WHICH IS WHY ONLY ONE WAS EVER REPORTED. In
|
| 248 |
+
`_require_filtered_view` the raise lands ABOVE the handler's own `try`, so it leaves as a bare
|
| 249 |
+
FastAPI 500 and the client's `errorMessage` turns any 5xx into *"Something went wrong on our
|
| 250 |
+
side"* β the exact sentence the owner reported (D-107's shape, again: an attribute error above
|
| 251 |
+
the guard arrives as plain text rather than as our envelope). In `_evaluate` the identical
|
| 252 |
+
line is swallowed by `/notifications`' `except Exception: continue`, so **every stored
|
| 253 |
+
view-alert was silently dropped from the Inbox** and nobody had anything to report at all.
|
| 254 |
+
One expression, one loud symptom and one silent one.
|
| 255 |
+
|
| 256 |
+
β SO IT IS A FUNCTION, NOT TWO FIXED LINES. Two copies of "find the view" is what let one site
|
| 257 |
+
be discussed for three waves while its twin went unnoticed [[one-question-two-normalizers]].
|
| 258 |
+
|
| 259 |
+
β It accepts a dict too, and that is not defensive noise: `verify_alerts`' door fixture was
|
| 260 |
+
keyed `{id: view}` β which is precisely why the gate was green while production raised on
|
| 261 |
+
every call. The fixture is moving to the production shape in this same change, and tolerating
|
| 262 |
+
both here means a caller that legitimately holds one cannot resurrect the bug.
|
| 263 |
+
"""
|
| 264 |
+
want = str(view_id or "")
|
| 265 |
+
if not want:
|
| 266 |
+
return None
|
| 267 |
+
views = (g or {}).get("views")
|
| 268 |
+
if isinstance(views, dict):
|
| 269 |
+
found = views.get(want)
|
| 270 |
+
return found if isinstance(found, dict) else None
|
| 271 |
+
if not isinstance(views, list):
|
| 272 |
+
return None
|
| 273 |
+
for v in views:
|
| 274 |
+
if isinstance(v, dict) and str(v.get("id") or "") == want:
|
| 275 |
+
return v
|
| 276 |
+
return None
|
| 277 |
|
| 278 |
|
| 279 |
def _topic_or_400(raw):
|
|
|
|
| 365 |
if isinstance(assemblies, dict):
|
| 366 |
assemblies[memo_key] = g
|
| 367 |
|
| 368 |
+
view = _view_by_id(g, rec.get("viewId"))
|
| 369 |
if not isinstance(view, dict):
|
| 370 |
# Deleted, or un-shared out from under the alert. Say so on the RECORD rather than
|
| 371 |
# deleting the alert: an alert that silently vanishes is indistinguishable from one that
|
|
|
|
| 375 |
# The SAME row build the grid and `/customers` use β `rows_from_pool` is what puts derived
|
| 376 |
# and overlay values on a row. Evaluating a filter against raw pool dicts would silently
|
| 377 |
# never match any condition on a user-created or measure column.
|
| 378 |
+
#
|
| 379 |
+
# ββ AND "THE SAME ROW BUILD" WAS NOT TRUE, WHICH MADE EVERY ALERT ON A `ut_*` DATABASE BLIND
|
| 380 |
+
# TO IMPORTED DATA. Found by a verifier driving one real assembly through both paths.
|
| 381 |
+
#
|
| 382 |
+
# `routes_tables.table_rows` β the grid the person is looking at β merges the DEFINITION rows
|
| 383 |
+
# underneath the overlay ("base first, overlay wins"; that merge is itself the fix for owner
|
| 384 |
+
# item 3, *"it all got reseted"*). `_evaluate` is a second copy of that read and never got it:
|
| 385 |
+
# it handed `ws['overlays']` to `rows_from_pool` raw, so for a `ut_*` table every base cell
|
| 386 |
+
# evaluated as BLANK. Measured on one assembly, same view, same rows:
|
| 387 |
+
# rows_src state='unpaid' / 'paid'
|
| 388 |
+
# _evaluate saw state='' / '' β every base cell blank
|
| 389 |
+
# the GRID saw state='unpaid' / 'paid'
|
| 390 |
+
# so `state eq unpaid` matched NOTHING while the view showed one row, and `state isEmpty`
|
| 391 |
+
# matched EVERYTHING while the view showed none. **The alert did not merely miss rows β it
|
| 392 |
+
# inverted.** End to end: a row whose value arrived by import, automation, paste or the create
|
| 393 |
+
# door never fired; only a value typed as a hand EDIT did.
|
| 394 |
+
#
|
| 395 |
+
# β Scope, so nobody widens the fix past its cause: materialised `ut_*` tables are hit;
|
| 396 |
+
# `customer`/`product` are not (their fields are `source: "odoo"` and read off `rows_src`);
|
| 397 |
+
# `ut_odoo_*` never reaches here (`with_rows=True` refuses first and returns
|
| 398 |
+
# `skipped: window_required`).
|
| 399 |
+
# β ORDER IS LOAD-BEARING AND IS THE GRID'S: base underneath, overlay ON TOP. Inverting it
|
| 400 |
+
# would let a stale definition value shadow an edit the user has just made β the same defect
|
| 401 |
+
# `table_rows`' own note records, arriving from the other side.
|
| 402 |
+
_ov = (g.get("ws") or {}).get("overlays") or {}
|
| 403 |
+
_merged = {}
|
| 404 |
+
for _r in g["rows_src"]:
|
| 405 |
+
_pid = str(_r.get("pid"))
|
| 406 |
+
_cells = {k: v for k, v in _r.items() if k != "pid"}
|
| 407 |
+
_o = _ov.get(_pid)
|
| 408 |
+
if isinstance(_o, dict):
|
| 409 |
+
_cells.update(_o)
|
| 410 |
+
_merged[_pid] = _cells
|
| 411 |
+
rows = aios_grid.rows_from_pool(g["rows_src"], g["fields"], _merged,
|
| 412 |
derived=g.get("derived"))
|
| 413 |
config = view.get("config") or view
|
| 414 |
ctx = filter_eval.EvalCtx(
|
|
|
|
| 506 |
# the one path that reaches this branch is also the one path with nothing to debug from.
|
| 507 |
raise err(503, "unavailable",
|
| 508 |
f"the table could not be read ({type(e).__name__}) β try again in a moment")
|
| 509 |
+
view = _view_by_id(g, view_id)
|
| 510 |
if not isinstance(view, dict):
|
| 511 |
raise err(404, "no_view", "that view does not exist on this table")
|
| 512 |
nodes, _conj = filter_eval.tree_parts((view.get("config") or view).get("filters") or [])
|
| 513 |
|
| 514 |
+
# ββ WAVE 33 Β· T29 β **CORRECTION: THE BLOCK BELOW IS TRUE ABOUT THE CODE AND FALSE ABOUT
|
| 515 |
+
# PRODUCTION, AND IT MUST BE READ SECOND.** It claims the missing-argument `TypeError` "IS
|
| 516 |
+
# owner item 17" β the owner's *"Something went wrong"*. It was not, and it could not have
|
| 517 |
+
# been: at `cbcf005`, the build the owner was using, the dict-read on `views` sat ~10 lines
|
| 518 |
+
# ABOVE this call and raised `AttributeError` on EVERY request, so the walk never reached the
|
| 519 |
+
# leaf and the arity bug was unreachable. `_view_by_id`'s own header records that fix.
|
| 520 |
+
#
|
| 521 |
+
# β WHY THE STALE PARAGRAPH STAYS RATHER THAN GETTING DELETED: the arity bug was real, the
|
| 522 |
+
# fix was right, and the three reasons it hid are the most transferable thing in this file.
|
| 523 |
+
# What was wrong is only its CLAIM TO BE THE CAUSE. Two comment blocks in one function each
|
| 524 |
+
# naming themselves as the origin of the same screenshot are mutually exclusive, and the next
|
| 525 |
+
# reader believes whichever they meet first β which is why this correction sits above rather
|
| 526 |
+
# than below. Caught by a verifier that read the SHIPPED file at the deployed commit instead
|
| 527 |
+
# of the working tree. [[grep-output-is-not-source]]
|
| 528 |
+
#
|
| 529 |
+
# ββ WAVE 32 Β· T22 β **THE CALL BELOW WAS MISSING AN ARGUMENT** (and wave 32 believed, wrongly,
|
| 530 |
+
# that this was owner item 17 β see the correction directly above).
|
| 531 |
#
|
| 532 |
# `is_rule_active(rule, columns)` takes TWO parameters (`harness/filter_sql.py`; every other
|
| 533 |
# caller in the repo passes both). This one passed ONE, so the moment the walk reached a LEAF
|
api/routes_automation.py
CHANGED
|
@@ -12,10 +12,12 @@ rather than admitting everyone. A "no token configured means no check" default i
|
|
| 12 |
trigger becomes a public one β the same class of mistake as an empty-200 permission answer.
|
| 13 |
"""
|
| 14 |
import os
|
|
|
|
| 15 |
import time
|
| 16 |
|
| 17 |
from fastapi import APIRouter, Body, Depends, Header, Request
|
| 18 |
|
|
|
|
| 19 |
import automation_engine as engine
|
| 20 |
import oauth_connect
|
| 21 |
import routes_oauth
|
|
@@ -27,11 +29,22 @@ router = APIRouter(prefix="/api/v1")
|
|
| 27 |
# C5 (wave 22): the OAuth connector surface rides INSIDE this router β main.py belongs to no
|
| 28 |
# session this wave, and this router is already mounted there. `/api/v1` + `/oauth/...`.
|
| 29 |
router.include_router(routes_oauth.router)
|
| 30 |
-
#
|
| 31 |
-
#
|
| 32 |
-
#
|
| 33 |
-
|
| 34 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 35 |
|
| 36 |
#: The registry key this surface carries (C-AUTONAV β A adds the row; the gate is live now, so
|
| 37 |
#: the day the row lands the wall is already the one that was tested).
|
|
@@ -78,6 +91,27 @@ def _wire(defn, tenant):
|
|
| 78 |
# C3 (wave 22): the trigger config rides whole β the webhook token included, because
|
| 79 |
# the person configuring the external caller has to be shown the URL somewhere, and
|
| 80 |
# this payload is session-gated behind the same wall as everything else here.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 81 |
"trigger": defn.get("trigger") or None,
|
| 82 |
"statusNote": defn.get("statusNote") or "",
|
| 83 |
# The one-sentence summary (airtable-brief rec 7), composed from the definition so it
|
|
@@ -110,6 +144,302 @@ def _wire(defn, tenant):
|
|
| 110 |
}
|
| 111 |
|
| 112 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 113 |
def _triggers_vocab(session):
|
| 114 |
"""C3's server-owned trigger list: `[{key, label, ready, needs, planned}]`, keys EXACTLY
|
| 115 |
`engine.TRIGGER_KEYS` + `engine.TRIGGER_PLANNED`. `ready:false` + `needs` renders as a
|
|
@@ -241,6 +571,13 @@ def _tick_state():
|
|
| 241 |
#: or delete β a new database cannot contain the legacy stage cells this retires.
|
| 242 |
_BOARD_RETIRED = set()
|
| 243 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 244 |
#: ββ WAVE 30 Β· T12 β THE PICKER DEFAULT, MEMOISED. `{tenant: (stamp, table_key)}`, the shape
|
| 245 |
#: `scope_cache` stores.
|
| 246 |
#:
|
|
@@ -393,9 +730,31 @@ def list_automations(session: Session = Depends(_GATE)):
|
|
| 393 |
# Idempotent Board retirement removes only engine-marked stage fields and legacy Board
|
| 394 |
# state. User-created Status/Stage columns remain intact.
|
| 395 |
engine.retire_automation_board_state(session.runtime, tables=tables)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 396 |
defs = engine.all_definitions(session.runtime)
|
| 397 |
items = [_wire(d, session.tenant) for _, d in
|
| 398 |
sorted(defs.items(), key=lambda kv: (kv[1].get("name") or "").lower())]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 399 |
return {"automations": items,
|
| 400 |
# β WAVE 24 β DERIVED from the engine's own `KINDS`, not a hand-written trio. It was
|
| 401 |
# three literals that happened to match, which is a second copy of a server
|
|
@@ -484,7 +843,11 @@ def list_automations(session: Session = Depends(_GATE)):
|
|
| 484 |
# own reason instead of omitting them β the owner asked for Airtable's full menu, and
|
| 485 |
# a shorter list would imply those actions do not exist. `clean_actions` REFUSES an
|
| 486 |
# unready kind, so the faded state is a wall rather than a styling choice.
|
| 487 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 488 |
# The builder's own vocabulary: how deep a condition tree may nest, how deep groups
|
| 489 |
# may nest, and the ceilings. B reads these instead of hard-coding the same numbers
|
| 490 |
# into its "+ Add condition" affordance.
|
|
@@ -505,7 +868,25 @@ def list_automations(session: Session = Depends(_GATE)):
|
|
| 505 |
# The ceiling a group's limit is judged against. `clean_post_groups` bounds a
|
| 506 |
# group by the action's OWN `maxPosts`, not by a constant, so the control can
|
| 507 |
# only warn honestly if it reads the same number the validator uses.
|
| 508 |
-
"maxPostsPerPull": engine.MAX_POSTS_PER_PULL
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 509 |
# Wave 21 C6-A1: {"enabled": bool, "source": "in-process"|"external"|""} β see
|
| 510 |
# `_tick_state` for why one boolean off AIOS_AUTOMATIONS alone would lie.
|
| 511 |
"tick": _tick_state()}
|
|
@@ -714,8 +1095,203 @@ def automation_seed_derive(body: dict = Body(default=None), session: Session = D
|
|
| 714 |
"derived": derived, "basis": basis}
|
| 715 |
|
| 716 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 717 |
@router.get("/automations/{auto_id}")
|
| 718 |
def get_automation(auto_id: str, session: Session = Depends(_GATE)):
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 719 |
defn = engine.all_definitions(session.runtime).get(str(auto_id))
|
| 720 |
if defn is None:
|
| 721 |
raise err(404, "unknown_automation", "no automation with that id")
|
|
@@ -729,33 +1305,84 @@ def create_automation(body: dict = Body(default=None), session: Session = Depend
|
|
| 729 |
answered before the kind. `new` mints the blank database in the same call, so the automation
|
| 730 |
is never saved pointing at a table that does not exist yet."""
|
| 731 |
if not session.runtime.available():
|
| 732 |
-
raise err(503, "store_unavailable", "the tenant store is unavailable
|
| 733 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 734 |
if error:
|
| 735 |
raise err(400, "invalid_automation", error)
|
| 736 |
-
return {"automation": _wire(defn, session.tenant)}
|
| 737 |
|
| 738 |
|
| 739 |
@router.patch("/automations/{auto_id}")
|
| 740 |
def patch_automation(auto_id: str, body: dict = Body(default=None),
|
| 741 |
session: Session = Depends(_GATE)):
|
| 742 |
if not session.runtime.available():
|
| 743 |
-
raise err(503, "store_unavailable", "the tenant store is unavailable
|
| 744 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 745 |
if error:
|
| 746 |
raise err(400 if error != "no such automation" else 404,
|
| 747 |
"invalid_automation" if error != "no such automation" else "unknown_automation",
|
| 748 |
error)
|
| 749 |
-
return {"automation": _wire(defn, session.tenant)}
|
| 750 |
|
| 751 |
|
| 752 |
@router.delete("/automations/{auto_id}")
|
| 753 |
def delete_automation(auto_id: str, session: Session = Depends(_GATE)):
|
| 754 |
"""Delete the DEFINITION. β The database it filled is NOT touched β an automation is the
|
| 755 |
thing that writes rows, not the thing that owns them, and deleting a job must never be a way
|
| 756 |
-
to lose data (the same rule the orphan count encodes).
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 757 |
if engine.running(session.tenant, auto_id):
|
| 758 |
-
raise err(409, "automation_running", "it is running
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 759 |
engine.remove(session.runtime, auto_id)
|
| 760 |
return {"deleted": str(auto_id)}
|
| 761 |
|
|
@@ -773,7 +1400,7 @@ def preview_source(body: dict = Body(default=None), session: Session = Depends(_
|
|
| 773 |
except engine.Refused as e:
|
| 774 |
raise err(400, "refused_url", str(e))
|
| 775 |
except Exception as e: # noqa: BLE001
|
| 776 |
-
raise err(502, "fetch_failed", f"could not read that page
|
| 777 |
f"{str(e)[:160]}")
|
| 778 |
|
| 779 |
|
|
@@ -804,9 +1431,9 @@ def toggle_automation_node(auto_id: str, node_id: str, session: Session = Depend
|
|
| 804 |
nothing: a control that appears to work and does not is worse than one that refuses.
|
| 805 |
"""
|
| 806 |
if not session.runtime.available():
|
| 807 |
-
raise err(503, "store_unavailable", "the tenant store is unavailable
|
| 808 |
if engine.running(session.tenant, auto_id):
|
| 809 |
-
raise err(409, "automation_running", "it is running
|
| 810 |
defn, error = engine.toggle_node(session.runtime, auto_id, node_id)
|
| 811 |
if error:
|
| 812 |
raise err(404 if error == "no such automation" else 400,
|
|
@@ -873,7 +1500,7 @@ def tick(request: Request, x_aios_tick_token: str = Header(default="")):
|
|
| 873 |
want = os.environ.get("AIOS_AUTOMATION_TICK_TOKEN") or ""
|
| 874 |
if not want:
|
| 875 |
raise err(403, "tick_disabled",
|
| 876 |
-
"AIOS_AUTOMATION_TICK_TOKEN is not configured
|
| 877 |
got = x_aios_tick_token or request.headers.get("X-AIOS-TICK-TOKEN") or ""
|
| 878 |
if got != want:
|
| 879 |
raise err(403, "bad_tick_token", "that token is not valid for this deployment")
|
|
@@ -891,7 +1518,7 @@ def purge_ig_subject(body: dict = Body(default=None), session: Session = Depends
|
|
| 891 |
if not session.admin:
|
| 892 |
raise err(403, "admin_only", "erasing a subject is an admin action")
|
| 893 |
if not session.runtime.available():
|
| 894 |
-
raise err(503, "store_unavailable", "the tenant store is unavailable
|
| 895 |
"purged")
|
| 896 |
handle = str((body or {}).get("handle") or "").strip()
|
| 897 |
if not handle:
|
|
@@ -930,7 +1557,7 @@ def metric_drill(table_key: str, field_key: str, row_id: str,
|
|
| 930 |
"measure": bag.get("measure"), "window": bag.get("window"),
|
| 931 |
"value": value, "rows": rows[:200],
|
| 932 |
"note": "" if value is not None else
|
| 933 |
-
"no master data answers this window
|
| 934 |
|
| 935 |
|
| 936 |
@router.get("/automations/{auto_id}/rows")
|
|
|
|
| 12 |
trigger becomes a public one β the same class of mistake as an empty-200 permission answer.
|
| 13 |
"""
|
| 14 |
import os
|
| 15 |
+
import re
|
| 16 |
import time
|
| 17 |
|
| 18 |
from fastapi import APIRouter, Body, Depends, Header, Request
|
| 19 |
|
| 20 |
+
import ai_review
|
| 21 |
import automation_engine as engine
|
| 22 |
import oauth_connect
|
| 23 |
import routes_oauth
|
|
|
|
| 29 |
# C5 (wave 22): the OAuth connector surface rides INSIDE this router β main.py belongs to no
|
| 30 |
# session this wave, and this router is already mounted there. `/api/v1` + `/oauth/...`.
|
| 31 |
router.include_router(routes_oauth.router)
|
| 32 |
+
# ββ D-203 β THE NESTED INCLUDE OF `routes_connectors` IS REMOVED, and the reason it existed is
|
| 33 |
+
# worth keeping because it was a GOOD reason that expired.
|
| 34 |
+
#
|
| 35 |
+
# Wave 23 (C11) mounted the connectors directory here rather than in `main.py`, because this router
|
| 36 |
+
# was already mounted and `main.py` belonged to another session β a sensible way to avoid a
|
| 37 |
+
# cross-fence ask. `main.py:227` includes `routes_connectors` DIRECTLY now, so this line stopped
|
| 38 |
+
# being the only door and became a SECOND one.
|
| 39 |
+
# β AND A ROUTER MOUNTED TWICE DOES NOT SERVE THE SAME PATHS TWICE β it serves the prefix twice.
|
| 40 |
+
# `routes_connectors` carries its own `/api/v1`, so nesting it inside this router's `/api/v1`
|
| 41 |
+
# produced **`/api/v1/api/v1/connectors/directory`**: a live, session-gated, entirely dead path
|
| 42 |
+
# that nothing links to and every route audit has to explain. MEASURED before removal: 123 served
|
| 43 |
+
# paths, exactly 1 of them doubled.
|
| 44 |
+
# β `routes_oauth` above is NOT the same case and stays: `main.py` does not mount it, so this
|
| 45 |
+
# router is genuinely its only door. Deleting it because its neighbour was wrong is how a real
|
| 46 |
+
# route dies for a tidy-up.
|
| 47 |
+
import routes_connectors # noqa: E402,F401
|
| 48 |
|
| 49 |
#: The registry key this surface carries (C-AUTONAV β A adds the row; the gate is live now, so
|
| 50 |
#: the day the row lands the wall is already the one that was tested).
|
|
|
|
| 91 |
# C3 (wave 22): the trigger config rides whole β the webhook token included, because
|
| 92 |
# the person configuring the external caller has to be shown the URL somewhere, and
|
| 93 |
# this payload is session-gated behind the same wall as everything else here.
|
| 94 |
+
# ββ WAVE 35 Β· T36 / R10 β THE PARKED BATCH, SUMMARISED. Without this line the whole
|
| 95 |
+
# ticket would be unreachable: `_wire` is a WHITELIST, so a key the engine parks on the
|
| 96 |
+
# definition simply never arrives, and the detail pane could not know a batch was waiting
|
| 97 |
+
# ([[reachable-is-not-the-same-as-built]] β the exact shape `flow` was caught in above).
|
| 98 |
+
# β COUNT AND NOTES ONLY, NEVER `items`. A 200-statement batch carries 200 rendered HTML
|
| 99 |
+
# mails; this payload rides on the automations LIST, which every rail paint reads.
|
| 100 |
+
# `GET /admin/statements/agent/{id}` serves the detail when somebody opens the batch.
|
| 101 |
+
"pendingStatements": ({
|
| 102 |
+
"count": int((defn.get("pendingStatements") or {}).get("count") or 0),
|
| 103 |
+
"ts": (defn.get("pendingStatements") or {}).get("ts") or "",
|
| 104 |
+
"notes": list((defn.get("pendingStatements") or {}).get("notes") or [])[:25],
|
| 105 |
+
} if isinstance(defn.get("pendingStatements"), dict) else None),
|
| 106 |
+
# ββ WAVE 35 Β· T37 β `system` FOR A **STORED** ROW. Until now only SYNTHETIC rows carried
|
| 107 |
+
# it, stamped by their builders AFTER this function (`_odoo_sync_row`, `_field_agent_rows`),
|
| 108 |
+
# so a stored row with the marker had it enforced on the server (`delete_automation` 409s)
|
| 109 |
+
# and INVISIBLE to the client β which paints a live-looking Delete that answers with a
|
| 110 |
+
# refusal. `AutomationDetail` already reads `automation.system` to disable that button and
|
| 111 |
+
# explain why; this is the line that lets it.
|
| 112 |
+
# β Absent stays absent rather than becoming `""`: every ordinary automation is not-a-system
|
| 113 |
+
# -agent, and an empty string is a value a client could accidentally treat as one.
|
| 114 |
+
**({"system": str(defn.get("system") or "")} if defn.get("system") else {}),
|
| 115 |
"trigger": defn.get("trigger") or None,
|
| 116 |
"statusNote": defn.get("statusNote") or "",
|
| 117 |
# The one-sentence summary (airtable-brief rec 7), composed from the definition so it
|
|
|
|
| 144 |
}
|
| 145 |
|
| 146 |
|
| 147 |
+
#: ββ WAVE 34 Β· CONTRACTS C3 + C4 β WHY A ROW CANNOT BE DELETED, as a slug.
|
| 148 |
+
#:
|
| 149 |
+
#: β ALWAYS A STRING, NEVER A BOOLEAN, and the two contracts disagreed about that (C3 says
|
| 150 |
+
#: `system: true`, C4 says `system: "<slug>"`). Raised as ask `E-13`; built as a slug because one
|
| 151 |
+
#: key with two types is [[one-question-two-normalizers]] before a line is written, and because a
|
| 152 |
+
#: refusal has to be able to NAME the reason. Truthiness is unchanged for any reader that only
|
| 153 |
+
#: asks "is this a system agent".
|
| 154 |
+
SYSTEM_FIELD_AGENT = "field_agent"
|
| 155 |
+
SYSTEM_ODOO_SYNC = "odoo_sync"
|
| 156 |
+
|
| 157 |
+
|
| 158 |
+
def _field_agent_rows(session):
|
| 159 |
+
"""ββ CONTRACT C3 β one synthetic Agent row per `ai_enrich` column in the tenant.
|
| 160 |
+
|
| 161 |
+
R13: *"Every field agent must be VIEWABLE under the Agent module as a simple Trigger whose
|
| 162 |
+
first step is the field enrichment, with the Field and Database shown under Config."*
|
| 163 |
+
|
| 164 |
+
ββ THESE ARE DERIVED, NOT STORED, AND NOTHING HERE MAY WRITE. A field agent's only source of
|
| 165 |
+
truth is the column definition F's `_clean_field` stamps; a copy in the automations bucket
|
| 166 |
+
would be a second one, and the first PATCH through the enrichment editor would silently
|
| 167 |
+
diverge from it. `delete_automation` refuses these ids for the same reason: accepting a delete
|
| 168 |
+
that cannot delete anything is the `view_upsert` failure mode (200 OK, nothing written) in a
|
| 169 |
+
new place.
|
| 170 |
+
|
| 171 |
+
ββ AND IT USES THE ROWS-FREE PROJECTION, WHICH IS THE WHOLE ENGINEERING PROBLEM OF THIS
|
| 172 |
+
TICKET. `GET /automations` is the route W29-T01 and W30-T12 spent two waves taking the
|
| 173 |
+
whole-document read OFF: it reads `user_tables` exactly ONCE PER TENANT PER PROCESS now, and
|
| 174 |
+
this file's own `unconfigured` note says *"a label is not worth putting it back"*. Walking
|
| 175 |
+
every table's fields for `ai_enrich` columns is exactly that read. So this uses
|
| 176 |
+
`user_tables.all_defs` β the same projection `/nav` uses, MEASURED there at 1,750 ms -> 1.4 ms,
|
| 177 |
+
because tenant #0's document is 99.89% rows and a field definition is not a row.
|
| 178 |
+
β `all_defs` RAISES on `rows` rather than answering `{}`. Nothing here wants a row; if that
|
| 179 |
+
ever changes, the error names the projection instead of painting an empty grid.
|
| 180 |
+
|
| 181 |
+
β THE PERMISSION WALL IS CALLED, NEVER RE-IMPLEMENTED. `may_open` decides which databases this
|
| 182 |
+
caller may see, lent the projected document exactly as `/nav` lends it. This route's own
|
| 183 |
+
`automation_tables` carries the scar that makes that non-negotiable: it once re-implemented
|
| 184 |
+
the wall, got it WIDER, and showed people databases they were refused the moment they clicked.
|
| 185 |
+
"""
|
| 186 |
+
import core.user_tables as user_tables
|
| 187 |
+
|
| 188 |
+
try:
|
| 189 |
+
defs = user_tables.all_defs(st=session.runtime) or {}
|
| 190 |
+
lent = user_tables.lend(session.runtime, **{user_tables.STORE_KEY: defs})
|
| 191 |
+
except Exception: # noqa: BLE001
|
| 192 |
+
# A store blip must not take the whole rail down with it. The stored automations are the
|
| 193 |
+
# payload's real subject; field agents are an addition to it.
|
| 194 |
+
return []
|
| 195 |
+
|
| 196 |
+
out = []
|
| 197 |
+
for key, defn in sorted(defs.items(), key=lambda kv: (kv[1].get("label") or "").lower()):
|
| 198 |
+
if not user_tables.may_open(key, session.uname, session.admin, st=lent):
|
| 199 |
+
continue
|
| 200 |
+
table_label = defn.get("label") or key
|
| 201 |
+
for f in user_tables.ai_enrich_fields(defn):
|
| 202 |
+
bag = f.get("automation") if isinstance(f.get("automation"), dict) else {}
|
| 203 |
+
if bag.get("kind") != SYSTEM_FIELD_AGENT:
|
| 204 |
+
continue
|
| 205 |
+
col = str(f.get("key") or "")
|
| 206 |
+
if not col:
|
| 207 |
+
continue
|
| 208 |
+
# β THE ID CARRIES THE TABLE AND THE COLUMN, and `table` is NOT read off the bag:
|
| 209 |
+
# F's `_clean_field` is handed ONE field dict with no table context, so it cannot
|
| 210 |
+
# stamp one (mailbox `F-3`). E holds that key because E is the side that iterates
|
| 211 |
+
# tables. Two sources for one fact was the alternative, and it drifts.
|
| 212 |
+
trig = bag.get("trigger") if isinstance(bag.get("trigger"), dict) else {}
|
| 213 |
+
mode = str(trig.get("mode") or "manual")
|
| 214 |
+
cron = str(trig.get("cron") or "").strip()
|
| 215 |
+
defn_syn = {
|
| 216 |
+
"id": f"field:{key}:{col}",
|
| 217 |
+
"name": f.get("label") or col,
|
| 218 |
+
"kind": SYSTEM_FIELD_AGENT,
|
| 219 |
+
# ββ TWO TRIGGER VOCABULARIES MEET HERE AND THEY ARE NOT THE SAME ONE. A field
|
| 220 |
+
# agent's trigger is the ENRICHMENT vocabulary (`{mode, cron}`, values
|
| 221 |
+
# manual/on_change/schedule); an automation's is the ENGINE's (`{key}` plus a
|
| 222 |
+
# separate `schedule {cron, enabled}`). Handing the engine's shape a `mode` it
|
| 223 |
+
# cannot read is not a type error β it is SILENT: `compose_sentence` fell back to
|
| 224 |
+
# "When you press Run now" for a column scheduled at 06:00, and `graph()` drew a
|
| 225 |
+
# trigger node with no trigger. Measured before this mapping existed, which is the
|
| 226 |
+
# only reason it does.
|
| 227 |
+
# β THE MAP IS EXACT WHERE AN EQUIVALENT EXISTS AND HONEST WHERE IT DOES NOT:
|
| 228 |
+
# `manual` and `schedule` are the engine's own keys, and `on_change` becomes
|
| 229 |
+
# `event_field` ("When a record matches conditions"), the nearest thing the engine
|
| 230 |
+
# has to "a cell this column reads has moved". `mode` is kept verbatim beside it so
|
| 231 |
+
# nothing is lost in translation and the enrichment editor stays the source.
|
| 232 |
+
"trigger": {"key": {"manual": "manual", "schedule": "schedule",
|
| 233 |
+
"on_change": "event_field"}.get(mode, "manual"),
|
| 234 |
+
"mode": mode, **({"cron": cron} if cron else {})},
|
| 235 |
+
**({"schedule": {"cron": cron, "enabled": True}}
|
| 236 |
+
if mode == "schedule" and cron else {}),
|
| 237 |
+
"flow": {"actions": [{"id": "act_1", "kind": "ai_enrich",
|
| 238 |
+
"config": {"table": key, "field": col,
|
| 239 |
+
"tableLabel": table_label}}]},
|
| 240 |
+
}
|
| 241 |
+
# β THROUGH `_wire`, NOT BESIDE IT. A synthetic row hand-built to "look like" a
|
| 242 |
+
# stored one is a second shape that agrees until somebody adds a key to the real one
|
| 243 |
+
# β the exact way `awaitingResults` shipped inert for a whole wave. Passing the
|
| 244 |
+
# synthetic DEFINITION through the same function makes them identical by
|
| 245 |
+
# construction; only `system` is stamped afterwards, because no stored row has it.
|
| 246 |
+
row = _wire(defn_syn, session.tenant)
|
| 247 |
+
row["system"] = SYSTEM_FIELD_AGENT
|
| 248 |
+
out.append(row)
|
| 249 |
+
return out
|
| 250 |
+
|
| 251 |
+
|
| 252 |
+
#: ββ WAVE 34 Β· W34-T47 (mailbox D-5) β R6 APPLIED TO WORDS A MODEL WROTE.
|
| 253 |
+
#:
|
| 254 |
+
#: β `web_prose` READS FILES, so it is structurally blind to a dash that arrives at RUN TIME.
|
| 255 |
+
#: `POST /automations/draft` returns three strings a language model authored (the flow's name,
|
| 256 |
+
#: each step's `why`, and the dropped/notes sentences) and `W34-T42` is what put them on a screen.
|
| 257 |
+
#: Lane D MEASURED that a prompt instruction does not hold: their system prompt ends "Never use an
|
| 258 |
+
#: em dash" and the very next live cerebras turn came back with one. So this is code at the
|
| 259 |
+
#: boundary, not a better prompt.
|
| 260 |
+
#: β A DIGIT RANGE IS A DIFFERENT SENTENCE and gets the first rule: "10-20" means "10 to 20", and
|
| 261 |
+
#: turning it into "10, 20" states two numbers where the model stated a span.
|
| 262 |
+
_DRAFT_DASH = "[" + chr(0x2014) + chr(0x2013) + "]"
|
| 263 |
+
|
| 264 |
+
|
| 265 |
+
def _draft_no_dashes(text):
|
| 266 |
+
"""Model prose with no em or en dash, and no meaning changed on the way."""
|
| 267 |
+
text = str(text or "")
|
| 268 |
+
text = re.sub(rf"(?<=\d)\s*{_DRAFT_DASH}\s*(?=\d)", " to ", text)
|
| 269 |
+
text = re.sub(rf"\s*{_DRAFT_DASH}\s*(?=[,.;:!?])", "", text)
|
| 270 |
+
text = re.sub(rf"(?<=[,;:])\s*{_DRAFT_DASH}\s*", " ", text)
|
| 271 |
+
return re.sub(rf"\s*{_DRAFT_DASH}\s*", ", ", text)
|
| 272 |
+
|
| 273 |
+
|
| 274 |
+
ODOO_SYNC_ID = "system:odoo_sync"
|
| 275 |
+
#: The cadence presets in the words a person reads. β Keyed on `odoo_relational.SYNC_PRESETS`, and
|
| 276 |
+
#: a key with no phrase here falls back to "Every <key>" rather than raising β a missing caption
|
| 277 |
+
#: must degrade to something readable, not take the agents list down.
|
| 278 |
+
ODOO_CADENCE_PHRASE = {"30m": "Every 30 minutes", "1h": "Every hour",
|
| 279 |
+
"4h": "Every 4 hours", "daily": "Every day"}
|
| 280 |
+
|
| 281 |
+
|
| 282 |
+
def _odoo_sync_row(session, detail=False):
|
| 283 |
+
"""ββ CONTRACT C4 (ruling R22) β the Odoo sync, as an agent you can SEE.
|
| 284 |
+
|
| 285 |
+
R22: *"Implicit time-triggered work (Odoo syncing) becomes EXPLICIT: a pre-set agent that
|
| 286 |
+
cannot be deleted, whose Canvas shows Trigger = time and Action = data syncing from Odoo, with
|
| 287 |
+
the keychain/API configuration shown."*
|
| 288 |
+
|
| 289 |
+
ββ DERIVED, NOT STORED, AND C4 SAYS "a stored automation may carry `system:`". THE MECHANISM
|
| 290 |
+
C4 ASKS FOR IS BUILT (`delete_automation` refuses any stored row carrying `system`); this
|
| 291 |
+
particular agent does not use it, for three measured reasons, and the deviation is raised as
|
| 292 |
+
ask `E-15` rather than taken quietly:
|
| 293 |
+
1. NOTHING CAN SEED IT. There is no system-automation seeding path anywhere, and `D-195`
|
| 294 |
+
measured three times that a CLI write to the tenant store while the Space is live REPORTS
|
| 295 |
+
SUCCESS and is reverted within a minute. A stored row would have to be minted by the
|
| 296 |
+
container, i.e. a write-on-read on the busiest list route in the product.
|
| 297 |
+
2. STORED MEANS RUNNABLE BY MACHINERY BUILT FOR USER AUTOMATIONS. If its runs went through
|
| 298 |
+
`_commit_run`, `CONSECUTIVE_FAILURE_PAUSE` would flip `schedule.enabled` off after K bad
|
| 299 |
+
passes β silently disabling the tenant's REAL Odoo cadence, not a cosmetic card.
|
| 300 |
+
3. TWO COPIES OF ONE CADENCE. The loop reads `odoo_relational.sync_seconds`; a stored
|
| 301 |
+
automation would carry its own `schedule.cron`, and C4's own requirement is that the card
|
| 302 |
+
"cannot drift from the running loop". Deriving makes drift impossible instead of
|
| 303 |
+
forbidden.
|
| 304 |
+
|
| 305 |
+
β `detail=False` IS THE LIST PATH AND IT STAYS CHEAP. The keychain label and the last-sync
|
| 306 |
+
stamp each cost their own store read, and `GET /automations` is the route two waves were spent
|
| 307 |
+
taking reads OFF. They are resolved only on the DETAIL fetch, which is one automation and one
|
| 308 |
+
click. Returns `None` when this tenant has no Odoo at all β an agent for a connector nobody
|
| 309 |
+
connected is a card that lies.
|
| 310 |
+
"""
|
| 311 |
+
try:
|
| 312 |
+
import odoo_relational as rel
|
| 313 |
+
except Exception: # noqa: BLE001
|
| 314 |
+
return None
|
| 315 |
+
try:
|
| 316 |
+
cfg = rel.read_config(session.runtime)
|
| 317 |
+
secs = rel.sync_seconds(session.runtime)
|
| 318 |
+
frozen = bool(rel.frozen(session.runtime))
|
| 319 |
+
except Exception: # noqa: BLE001
|
| 320 |
+
return None
|
| 321 |
+
|
| 322 |
+
every = str(cfg.get("syncEvery") or rel.DEFAULT_SYNC)
|
| 323 |
+
manual = secs is None
|
| 324 |
+
defn = {
|
| 325 |
+
"id": ODOO_SYNC_ID,
|
| 326 |
+
"name": "Odoo sync",
|
| 327 |
+
"kind": SYSTEM_ODOO_SYNC,
|
| 328 |
+
# β THE CADENCE IS READ, NEVER STORED HERE. `everySeconds` is what the loop will actually
|
| 329 |
+
# sleep for, so the card cannot claim a schedule the loop is not keeping.
|
| 330 |
+
"trigger": {"key": "manual" if manual else "schedule", "preset": every,
|
| 331 |
+
"everySeconds": secs, "presets": sorted(rel.SYNC_PRESETS)},
|
| 332 |
+
**({} if manual else {"schedule": {"cron": "", "enabled": True}}),
|
| 333 |
+
"flow": {"actions": [{"id": "act_1", "kind": "odoo_sync",
|
| 334 |
+
"config": {"connector": "odoo", "every": every,
|
| 335 |
+
"frozen": frozen}}]},
|
| 336 |
+
}
|
| 337 |
+
row = _wire(defn, session.tenant)
|
| 338 |
+
row["system"] = SYSTEM_ODOO_SYNC
|
| 339 |
+
# β THE SENTENCE IS OVERRIDDEN, AND IT IS A FIX RATHER THAN A PREFERENCE. `compose_sentence`
|
| 340 |
+
# speaks the automation vocabulary β it builds "When <cron phrase>, run N actions" out of
|
| 341 |
+
# `schedule.cron` β and this agent has no cron: its cadence is a PRESET in seconds that the
|
| 342 |
+
# resync loop sleeps on. MEASURED before this line existed, the card read exactly
|
| 343 |
+
# `", run 1 action."`: a leading comma where the trigger phrase should have been. Two
|
| 344 |
+
# vocabularies again, and this one fails in punctuation rather than in behaviour, which is
|
| 345 |
+
# why only reading the output catches it.
|
| 346 |
+
# β AND THE CADENCE IS SPELLED OUT RATHER THAN INTERPOLATED. `f"Every {every}"` produced
|
| 347 |
+
# "Every daily, sync data from Odoo." β the preset KEYS are storage tokens ("30m", "daily"),
|
| 348 |
+
# not English, and a sentence built by pasting one in is only accidentally readable for the
|
| 349 |
+
# three that happen to be durations. Caught by reading the output, not by any assertion.
|
| 350 |
+
row["sentence"] = ("Odoo is disconnected, so nothing syncs." if frozen else
|
| 351 |
+
"Manually, sync data from Odoo." if manual else
|
| 352 |
+
f"{ODOO_CADENCE_PHRASE.get(every, f'Every {every}')}, sync data from Odoo.")
|
| 353 |
+
# β R6's SECOND SENTENCE, WHICH IS THE HALF THAT GETS DROPPED: a limit that cannot be removed
|
| 354 |
+
# must be REPORTED with its cause. Two are reported here rather than left for somebody to
|
| 355 |
+
# discover by watching a mirror not move.
|
| 356 |
+
notes = []
|
| 357 |
+
if frozen:
|
| 358 |
+
notes.append("Odoo is disconnected, so this agent is not syncing. Reconnect it in "
|
| 359 |
+
"Connectors.")
|
| 360 |
+
if manual:
|
| 361 |
+
notes.append("The cadence is set to manual, so nothing syncs on a timer.")
|
| 362 |
+
row["statusNote"] = " ".join(notes)
|
| 363 |
+
if not detail:
|
| 364 |
+
return row
|
| 365 |
+
|
| 366 |
+
# ββ the DETAIL half: two store reads, on a route that fetches one automation ββββββββββββββ
|
| 367 |
+
try:
|
| 368 |
+
import routes_keychain as kc_routes # noqa: PLC0415
|
| 369 |
+
row["flow"]["actions"][0]["config"]["keychain"] = (
|
| 370 |
+
kc_routes.odoo_config(session).get("label") or "Odoo")
|
| 371 |
+
except Exception: # noqa: BLE001
|
| 372 |
+
# A label is a nicety; failing to read one must not make the agent unopenable.
|
| 373 |
+
row["flow"]["actions"][0]["config"]["keychain"] = "Odoo"
|
| 374 |
+
try:
|
| 375 |
+
from harness import datastore as ds # noqa: PLC0415
|
| 376 |
+
# β THE LAST RUN IS THE MIRROR'S OWN `_sync_state`, not a run history we would have to
|
| 377 |
+
# write. That table already carries a real per-entity `updated` stamp, so the card reports
|
| 378 |
+
# what actually happened rather than what this module remembers happening.
|
| 379 |
+
st = ds.status() or {}
|
| 380 |
+
stamps = sorted(str((v or {}).get("updated") or "") for v in st.values() if v)
|
| 381 |
+
last = [s for s in stamps if s]
|
| 382 |
+
if last:
|
| 383 |
+
row["status"] = {**(row.get("status") or {}), "state": "ok", "lastRunAt": last[-1],
|
| 384 |
+
"lastSummary": f"{len(last)} datasets synced"}
|
| 385 |
+
except Exception: # noqa: BLE001
|
| 386 |
+
pass
|
| 387 |
+
return row
|
| 388 |
+
|
| 389 |
+
|
| 390 |
+
def _patch_odoo_sync(session, body):
|
| 391 |
+
"""ββ CONTRACT C4 β THE ONE THING ON THIS CARD THAT IS EDITABLE: how often it runs.
|
| 392 |
+
|
| 393 |
+
C4: *"Its Canvas is READ-ONLY except `trigger.config.everySeconds`, which writes through to the
|
| 394 |
+
same value `odoo_relational.sync_seconds` reads, so the card cannot drift from the running
|
| 395 |
+
loop."*
|
| 396 |
+
|
| 397 |
+
β IT WRITES THE CONNECTOR'S OWN CONFIG KEY, NOT AN AUTOMATION. `rel.CONFIG_KEY` /
|
| 398 |
+
`rel.SYNC_PRESETS` are the same key and the same vocabulary `sync_seconds` reads and
|
| 399 |
+
`_store_resync_loop` sleeps on, so there is one value and the card reads back exactly what the
|
| 400 |
+
loop will use. Storing a cron on a synthetic automation would have been a second copy with a
|
| 401 |
+
guaranteed drift date.
|
| 402 |
+
|
| 403 |
+
β EVERY OTHER FIELD IS REFUSED RATHER THAN IGNORED. A PATCH that silently kept only the part
|
| 404 |
+
it liked would let somebody rename this agent, watch the 200, and find the name gone on reload
|
| 405 |
+
β the failure shape this module has already paid for twice.
|
| 406 |
+
|
| 407 |
+
β AND THE LATENCY IS REPORTED, because it is real and a person would otherwise call it a bug:
|
| 408 |
+
the loop re-reads the cadence at the TOP of its cycle and then sleeps, so a change takes effect
|
| 409 |
+
on the NEXT pass β up to one full OLD interval away (24 hours if it was on `daily`).
|
| 410 |
+
"""
|
| 411 |
+
import odoo_relational as rel # noqa: PLC0415
|
| 412 |
+
|
| 413 |
+
known = {"trigger", "every", "syncEvery"}
|
| 414 |
+
extra = sorted(k for k in body if k not in known)
|
| 415 |
+
if extra:
|
| 416 |
+
raise err(409, "system_agent",
|
| 417 |
+
"this agent is the Odoo connection's own sync. Only how often it runs can be "
|
| 418 |
+
f"changed here; {', '.join(extra)} belongs to the connector in Connectors")
|
| 419 |
+
every = str(body.get("syncEvery") or body.get("every")
|
| 420 |
+
or ((body.get("trigger") or {}) if isinstance(body.get("trigger"), dict) else {})
|
| 421 |
+
.get("preset") or "").strip().lower()
|
| 422 |
+
if every not in rel.SYNC_PRESETS:
|
| 423 |
+
raise err(400, "bad_cadence",
|
| 424 |
+
f"pick one of: {', '.join(sorted(rel.SYNC_PRESETS))}")
|
| 425 |
+
|
| 426 |
+
def _up(cur):
|
| 427 |
+
cur = dict(cur) if isinstance(cur, dict) else {}
|
| 428 |
+
cur["syncEvery"] = every
|
| 429 |
+
return cur
|
| 430 |
+
|
| 431 |
+
session.runtime.update(rel.CONFIG_KEY, _up, flush="sync")
|
| 432 |
+
row = _odoo_sync_row(session, detail=True)
|
| 433 |
+
if row is None:
|
| 434 |
+
raise err(404, "unknown_automation", "no automation with that id")
|
| 435 |
+
secs = row["trigger"].get("everySeconds")
|
| 436 |
+
note = ("It syncs on a timer again from the next cycle." if secs
|
| 437 |
+
else "Nothing will sync on a timer now.")
|
| 438 |
+
return {"automation": row,
|
| 439 |
+
"notes": [f"The Odoo sync is set to {every}. {note} A change takes effect on the "
|
| 440 |
+
f"loop's next pass, so it can be up to one of the OLD intervals away."]}
|
| 441 |
+
|
| 442 |
+
|
| 443 |
def _triggers_vocab(session):
|
| 444 |
"""C3's server-owned trigger list: `[{key, label, ready, needs, planned}]`, keys EXACTLY
|
| 445 |
`engine.TRIGGER_KEYS` + `engine.TRIGGER_PLANNED`. `ready:false` + `needs` renders as a
|
|
|
|
| 571 |
#: or delete β a new database cannot contain the legacy stage cells this retires.
|
| 572 |
_BOARD_RETIRED = set()
|
| 573 |
|
| 574 |
+
#: β WAVE 35 Β· T37 β tenants whose statements agent has been considered THIS PROCESS. Same shape as
|
| 575 |
+
#: `_BOARD_RETIRED` and, like it, purely a cost saver: the DURABLE idempotency is the row's own
|
| 576 |
+
#: existence, which `engine.seed_statements_agent` re-checks inside its own store mutation.
|
| 577 |
+
#: β SO A RESTART RE-CHECKING IS HARMLESS BY CONSTRUCTION, which is the property to preserve. If
|
| 578 |
+
#: this set were ever the only guard, a process restart would mint a second agent.
|
| 579 |
+
_STATEMENTS_SEEDED = set()
|
| 580 |
+
|
| 581 |
#: ββ WAVE 30 Β· T12 β THE PICKER DEFAULT, MEMOISED. `{tenant: (stamp, table_key)}`, the shape
|
| 582 |
#: `scope_cache` stores.
|
| 583 |
#:
|
|
|
|
| 730 |
# Idempotent Board retirement removes only engine-marked stage fields and legacy Board
|
| 731 |
# state. User-created Status/Stage columns remain intact.
|
| 732 |
engine.retire_automation_board_state(session.runtime, tables=tables)
|
| 733 |
+
# ββ WAVE 35 Β· T37 / OWNER RULING R10 β ROYAL IMPORTS' STATEMENTS AGENT EXISTS BEFORE ANYBODY
|
| 734 |
+
# ASKS FOR IT. It is minted ONCE, by the container, SWITCHED OFF; every subsequent call finds
|
| 735 |
+
# it present and returns immediately. See `engine.seed_statements_agent` for why this one is
|
| 736 |
+
# STORED where wave 34's Odoo agent is derived, and why the row's existence is a sufficient
|
| 737 |
+
# idempotency key (it cannot be deleted).
|
| 738 |
+
# β GUARDED SO IT CAN NEVER TAKE THE RAIL DOWN. A tenant with no Odoo, a store mid-outage or a
|
| 739 |
+
# validator change must degrade to "no statements agent", never to a 500 on the one route the
|
| 740 |
+
# whole Agents surface polls. The same posture `_odoo_sync_row` takes for the same reason.
|
| 741 |
+
if session.tenant not in _STATEMENTS_SEEDED:
|
| 742 |
+
try:
|
| 743 |
+
engine.seed_statements_agent(session.runtime, username=session.uname or "system")
|
| 744 |
+
except Exception: # noqa: BLE001
|
| 745 |
+
pass
|
| 746 |
+
_STATEMENTS_SEEDED.add(session.tenant)
|
| 747 |
defs = engine.all_definitions(session.runtime)
|
| 748 |
items = [_wire(d, session.tenant) for _, d in
|
| 749 |
sorted(defs.items(), key=lambda kv: (kv[1].get("name") or "").lower())]
|
| 750 |
+
# ββ WAVE 34 Β· CONTRACT C3 (W34-T48) β field agents join the list as SYNTHETIC rows.
|
| 751 |
+
# β MERGED AND RE-SORTED, not appended in a block at the end. R13 asks for a field agent to be
|
| 752 |
+
# "VIEWABLE under the Agent module", i.e. one list of agents, not a list with a second list
|
| 753 |
+
# stapled to it β and a rail that sorts by name everywhere except its last few rows reads as a
|
| 754 |
+
# rendering bug. `_field_agent_rows` costs no whole-document read; see its docstring.
|
| 755 |
+
_sys_rows = [r for r in (_odoo_sync_row(session),) if r]
|
| 756 |
+
items = sorted(items + _field_agent_rows(session) + _sys_rows,
|
| 757 |
+
key=lambda r: str(r.get("name") or "").lower())
|
| 758 |
return {"automations": items,
|
| 759 |
# β WAVE 24 β DERIVED from the engine's own `KINDS`, not a hand-written trio. It was
|
| 760 |
# three literals that happened to match, which is a second copy of a server
|
|
|
|
| 843 |
# own reason instead of omitting them β the owner asked for Airtable's full menu, and
|
| 844 |
# a shorter list would imply those actions do not exist. `clean_actions` REFUSES an
|
| 845 |
# unready kind, so the faded state is a wall rather than a styling choice.
|
| 846 |
+
# β W35-T35 (C8): `session.runtime` is what withholds a TENANT-GATED row. Passing it
|
| 847 |
+
# here is the whole of "the menu does not offer Send statements to another tenant";
|
| 848 |
+
# the STORE-side wall is `clean_actions(rt=)`, deliberately separate, because a picker
|
| 849 |
+
# is not a security boundary [[opening-a-route-widens-every-field]].
|
| 850 |
+
"actionsCatalog": engine.action_catalog(session.runtime),
|
| 851 |
# The builder's own vocabulary: how deep a condition tree may nest, how deep groups
|
| 852 |
# may nest, and the ceilings. B reads these instead of hard-coding the same numbers
|
| 853 |
# into its "+ Add condition" affordance.
|
|
|
|
| 868 |
# The ceiling a group's limit is judged against. `clean_post_groups` bounds a
|
| 869 |
# group by the action's OWN `maxPosts`, not by a constant, so the control can
|
| 870 |
# only warn honestly if it reads the same number the validator uses.
|
| 871 |
+
"maxPostsPerPull": engine.MAX_POSTS_PER_PULL,
|
| 872 |
+
# ββ W33-T52 (owner item 16) β WHICH CONFIG KEYS A KIND REQUIRES, on the
|
| 873 |
+
# wire, for exactly the reason `postTypes` above is: the panel paints a red
|
| 874 |
+
# `*` beside a required control, and a client-side table of which keys those
|
| 875 |
+
# are would be a SECOND copy of `ACTION_REQUIRED` living in another file. The
|
| 876 |
+
# two would agree on the day they were written and diverge the first time a
|
| 877 |
+
# kind gained a key β the panel would then mark a control optional that the
|
| 878 |
+
# runner blocks on, and the person would read "this is fine" from the one
|
| 879 |
+
# surface that is meant to tell them it is not.
|
| 880 |
+
# β BOTH HALVES RIDE, phrase AND key, because the phrase is the ONLY human
|
| 881 |
+
# wording of that requirement anywhere ("a column to write into"), and the
|
| 882 |
+
# runner's own refusal sentence is built from it. A client that re-worded it
|
| 883 |
+
# would give the same requirement two names.
|
| 884 |
+
# β It is `ACTION_REQUIRED`, not `WEB_REQUIRED`: the table is the one the
|
| 885 |
+
# run refusal and `unconfigured_actions` already read, so a kind added to it
|
| 886 |
+
# later paints its `*` with no client change at all.
|
| 887 |
+
"actionRequired": {kind: [{"phrase": phrase, "key": key}
|
| 888 |
+
for phrase, key in reqs]
|
| 889 |
+
for kind, reqs in engine.ACTION_REQUIRED.items()}},
|
| 890 |
# Wave 21 C6-A1: {"enabled": bool, "source": "in-process"|"external"|""} β see
|
| 891 |
# `_tick_state` for why one boolean off AIOS_AUTOMATIONS alone would lie.
|
| 892 |
"tick": _tick_state()}
|
|
|
|
| 1095 |
"derived": derived, "basis": basis}
|
| 1096 |
|
| 1097 |
|
| 1098 |
+
#: The injected chat transport, for gates only β `None` in every shipped path, so the route takes
|
| 1099 |
+
#: the real ladder. Set by `verify_automation.py` to prove this door end to end with NO API key and
|
| 1100 |
+
#: NO spend (`routes_query._call_model`'s `chat` argument is the same idea and the same reason).
|
| 1101 |
+
_DRAFT_CHAT = [None]
|
| 1102 |
+
|
| 1103 |
+
|
| 1104 |
+
@router.post("/automations/draft")
|
| 1105 |
+
def draft_automation(body: dict = Body(default=None), session: Session = Depends(_GATE)):
|
| 1106 |
+
"""ββ WAVE 33 Β· W33-T54/T55 (owner item 7, ruling R3) β A DESCRIPTION BECOMES A DRAFT FLOW.
|
| 1107 |
+
|
| 1108 |
+
`{prompt}` β `{draft: {name, trigger, table, actions:[{id,kind,config,why}]}, provider,
|
| 1109 |
+
dropped: [...], saved: false}` β or a 400 carrying ONE plain sentence.
|
| 1110 |
+
|
| 1111 |
+
ββ NOTHING IS SAVED HERE, AND THE `saved: false` ON THE WIRE IS NOT DECORATION. T54's
|
| 1112 |
+
`done-when` is *"gets back a DRAFT flow they can see BEFORE anything is saved"*; a door that
|
| 1113 |
+
wrote first and showed second would satisfy every check about the flow's contents and none about
|
| 1114 |
+
the promise. Accepting a draft is the ORDINARY `POST /automations` β R3's *"indistinguishable
|
| 1115 |
+
from a hand-built one"* is achieved by there being no second write path, not by making the
|
| 1116 |
+
second one look similar.
|
| 1117 |
+
|
| 1118 |
+
ββ CONTRACT C7, AND THIS ROUTE IS WHERE IT IS ENFORCED: *"the output must pass `clean_actions`
|
| 1119 |
+
unchanged."* So it is RUN, here, before the person ever sees the draft β and the result is
|
| 1120 |
+
DIFFED against what the model wrote. `clean_actions` has no disclosure channel (D-75): it drops
|
| 1121 |
+
a config key it does not recognise and answers 200. Without this diff a person would accept a
|
| 1122 |
+
flow, open it, and find a step configured differently from the one they were shown, with nothing
|
| 1123 |
+
anywhere having said so. `dropped` is that channel, built here because this is the first caller
|
| 1124 |
+
that needed one.
|
| 1125 |
+
β A draft whose actions `clean_actions` REFUSES outright is a 400, never a partial flow: half a
|
| 1126 |
+
flow presented as a whole one is the one outcome worse than a refusal.
|
| 1127 |
+
|
| 1128 |
+
β DECLARED ABOVE `/automations/{auto_id}`, and that is load-bearing rather than tidy β FastAPI
|
| 1129 |
+
matches in DECLARATION order, so a literal path registered after a sibling path-parameter route
|
| 1130 |
+
is never reached, and `get_automation` would answer *"no automation with that id"* for the id
|
| 1131 |
+
`draft`. The same reason `/automations/tables` and `/automations/presets` sit up here.
|
| 1132 |
+
"""
|
| 1133 |
+
prompt = str((body or {}).get("prompt") or "").strip()
|
| 1134 |
+
if not prompt:
|
| 1135 |
+
raise err(400, "no_prompt", "type what you want the automation to do")
|
| 1136 |
+
# β THE TENANT'S OWN TABLES, THROUGH THE EXISTING WALL. `automation_tables` applies `may_open`
|
| 1137 |
+
# per table, so the model is shown exactly the databases this caller may already see and cannot
|
| 1138 |
+
# name one they were not granted β the permission wall re-used, never a second one built beside
|
| 1139 |
+
# it. (`QueryPage`'s `granted` prop carries the same clause on the client side.)
|
| 1140 |
+
tables = (automation_tables(session) or {}).get("tables") or []
|
| 1141 |
+
# ββ WAVE 34 Β· W34-T42 / R18 β THE DRAFTER IS OFFERED WHAT THE PICKER OFFERS, nothing more.
|
| 1142 |
+
#
|
| 1143 |
+
# R18 collapsed six web actions into one on the menu. The other five stay in the catalog
|
| 1144 |
+
# because the surviving "Web agent" composes its own steps out of them server-side β but a
|
| 1145 |
+
# DRAFT is read and accepted by a PERSON, who then edits it on the Canvas. Handing the model
|
| 1146 |
+
# the unfiltered catalog would let it draft a step kind that is not in the action picker: the
|
| 1147 |
+
# reader could not add a second one, could not reason about where it came from, and the flow
|
| 1148 |
+
# they accepted would not be one they could have built by hand. R3's *"indistinguishable from
|
| 1149 |
+
# a hand-built one"* is a claim about what a person can REACH, not only about the write path.
|
| 1150 |
+
# β This is the ONE place the filter is applied on this route, and it is applied to the
|
| 1151 |
+
# drafter's vocabulary only. `clean_actions` below still validates against the FULL catalog,
|
| 1152 |
+
# so a flow that already holds a hidden kind is unaffected and nothing 400s (D-65).
|
| 1153 |
+
# β AND `required` IS NARROWED WITH IT, which is the half that is easy to miss. `draft_flow`
|
| 1154 |
+
# builds the ENUM from `catalog` and the "settings you must write" prose from `required`, so
|
| 1155 |
+
# filtering one and not the other describes settings for kinds the model cannot choose. That is
|
| 1156 |
+
# not merely untidy: it spends prompt on unreachable options and invites the model to reach for
|
| 1157 |
+
# one. `_ai_agent_plan` already narrows both in exactly this way; this follows it.
|
| 1158 |
+
# W35-T35 (C8): tenant-gated rows are withheld here too, or the DRAFTER would offer a kind
|
| 1159 |
+
# the same tenant's own save door then refuses β a flow the assistant proposes and the product
|
| 1160 |
+
# will not accept.
|
| 1161 |
+
menu_catalog = [r for r in engine.action_catalog(session.runtime) if r.get("menu") is not False]
|
| 1162 |
+
_offered = {r["kind"] for r in menu_catalog}
|
| 1163 |
+
draft, refusal, provider = ai_review.draft_flow(
|
| 1164 |
+
prompt=prompt,
|
| 1165 |
+
catalog=menu_catalog,
|
| 1166 |
+
required={k: v for k, v in engine.ACTION_REQUIRED.items() if k in _offered},
|
| 1167 |
+
triggers=_triggers_vocab(session),
|
| 1168 |
+
tables=tables,
|
| 1169 |
+
# β W35 Β· CONTRACT C7 (`NOTE E-16`) β the spend is ATTRIBUTED. Unlike the two engine call
|
| 1170 |
+
# sites, this one has a real person behind it: somebody typed the sentence, so `user` is
|
| 1171 |
+
# the caller rather than the automation's owner.
|
| 1172 |
+
st=session.runtime, user=getattr(session, "uname", "") or "",
|
| 1173 |
+
chat=_DRAFT_CHAT[0])
|
| 1174 |
+
if refusal or not draft:
|
| 1175 |
+
raise err(400, "draft_refused", refusal or "no automation could be drafted from that")
|
| 1176 |
+
|
| 1177 |
+
# ββ C7: run the real save-door validator and DIFF it ββββββββββββββββββββββββββββββββββ
|
| 1178 |
+
wrote = draft.get("actions") or []
|
| 1179 |
+
# W35-T35 (C8): the SAME `rt` the menu was built with. Without it this validator would refuse
|
| 1180 |
+
# a tenant-gated kind it had just offered the model β the draft door disagreeing with the save
|
| 1181 |
+
# door about one tenant, which reads as "the assistant produced an invalid flow".
|
| 1182 |
+
cleaned, why = engine.clean_actions([{"kind": a.get("kind"), "config": a.get("config") or {}}
|
| 1183 |
+
for a in wrote], rt=session.runtime)
|
| 1184 |
+
if why or cleaned is None:
|
| 1185 |
+
raise err(400, "draft_invalid",
|
| 1186 |
+
f"the assistant produced a flow this deployment will not accept: {why}")
|
| 1187 |
+
dropped = []
|
| 1188 |
+
for before, after in zip(wrote, cleaned):
|
| 1189 |
+
b_cfg = before.get("config") or {}
|
| 1190 |
+
a_cfg = after.get("config") or {}
|
| 1191 |
+
gone = sorted(k for k in b_cfg
|
| 1192 |
+
if k not in a_cfg or str(a_cfg.get(k)) != str(b_cfg.get(k)))
|
| 1193 |
+
if gone:
|
| 1194 |
+
dropped.append({"kind": str(after.get("kind") or ""), "keys": gone})
|
| 1195 |
+
# ββ WHAT IS STILL MISSING FROM EACH STEP, PER STEP β and this is the fix for the sharpest
|
| 1196 |
+
# thing the verifier found. The system prompt TELLS the model *"leave one blank rather than
|
| 1197 |
+
# inventing a web address, a CSS selector or a column name"* (which is right), and the panel
|
| 1198 |
+
# skips empty values (which is also right, on its own). Together they meant a `web_read` with
|
| 1199 |
+
# no selector and no target column painted as a FINISHED step β url, attr, timeout, nothing
|
| 1200 |
+
# else β and the ordinary create door then accepted it. A person approved a step that reads
|
| 1201 |
+
# nothing into nowhere, having been shown no blank at all.
|
| 1202 |
+
# β `engine.action_needs` IS THE PREDICATE, not a second list: the same function the builder's
|
| 1203 |
+
# Configured/Unconfigured label and the run refusal read. Three readers, one answer.
|
| 1204 |
+
_tables_by_key = {str(t.get("key")): t for t in tables}
|
| 1205 |
+
_target_cols = {str(f.get("key")) for f
|
| 1206 |
+
in (_tables_by_key.get(str(draft.get("table") or "")) or {}).get("fields") or []}
|
| 1207 |
+
shown = []
|
| 1208 |
+
for i, after in enumerate(cleaned):
|
| 1209 |
+
row = dict(after, why=str((wrote[i] or {}).get("why") or ""),
|
| 1210 |
+
needs=engine.action_needs(after))
|
| 1211 |
+
# β AND A COLUMN NAME THE DATABASE DOES NOT HAVE. `field` is a free string that nobody
|
| 1212 |
+
# validated at draft, at accept or at store β so a model writing the column's LABEL
|
| 1213 |
+
# ("Price") instead of its key ("price"), which is exactly what a person would say and an
|
| 1214 |
+
# obedient model would echo, stored a write into a column that does not exist. No schema
|
| 1215 |
+
# was violated; the flow was well-formed and did something other than what was asked.
|
| 1216 |
+
_f = str((after.get("config") or {}).get("field") or "")
|
| 1217 |
+
if _f and _target_cols and _f not in _target_cols:
|
| 1218 |
+
row["unknownField"] = _f
|
| 1219 |
+
shown.append(row)
|
| 1220 |
+
# β A TRIGGER THE CREATE DOOR WOULD REFUSE IS CORRECTED HERE, NOT SHOWN AND THEN 400'd. The
|
| 1221 |
+
# enum makes this need a model that ignores its own schema, but the failure mode is ugly: the
|
| 1222 |
+
# draft paints, the person clicks Accept, and the save refuses with a sentence about a word
|
| 1223 |
+
# they never chose. Falling back to `manual` and SAYING SO keeps the draft usable.
|
| 1224 |
+
_trig = str(draft.get("trigger") or "").strip()
|
| 1225 |
+
_notes = []
|
| 1226 |
+
if _trig and _trig not in tuple(engine.TRIGGER_KEYS):
|
| 1227 |
+
_notes.append(f"the assistant asked for a trigger this deployment does not have "
|
| 1228 |
+
f"({_trig}). Set to manual instead")
|
| 1229 |
+
_trig = ""
|
| 1230 |
+
_asked = int(draft.get("asked") or len(wrote))
|
| 1231 |
+
if _asked > len(shown):
|
| 1232 |
+
_notes.append(f"the assistant wrote {_asked} steps and a draft carries at most "
|
| 1233 |
+
f"{ai_review.MAX_DRAFT_ACTIONS}; the last {_asked - len(shown)} were not "
|
| 1234 |
+
f"kept. Describe the job in two automations, or shorten it.")
|
| 1235 |
+
# ββ WAVE 34 Β· W34-T47 (mailbox D-5) β THE MODEL'S OWN WORDS ARE NORMALISED, BECAUSE R6
|
| 1236 |
+
# CANNOT BE ENFORCED BY A SOURCE SCAN.
|
| 1237 |
+
#
|
| 1238 |
+
# β `web_prose` READS FILES. Every string below is written by a language model at run time,
|
| 1239 |
+
# so the gate is structurally blind to it: the sweep every lane did this wave is undone by our
|
| 1240 |
+
# own drafter the first time it answers with an em dash. Lane D MEASURED that a prompt
|
| 1241 |
+
# instruction does not hold (their system prompt says "Never use an em dash" and the very next
|
| 1242 |
+
# cerebras turn came back with one), so this is code, at the boundary, not a nicer prompt.
|
| 1243 |
+
# β THREE STRINGS REACH A SCREEN FROM HERE and all three are covered: the flow's NAME, each
|
| 1244 |
+
# step's `why`, and the `dropped`/`notes` sentences. `W34-T42` is what made them visible.
|
| 1245 |
+
# β A DIGIT RANGE IS A DIFFERENT SENTENCE: "10-20" means "10 to 20", and rewriting it as
|
| 1246 |
+
# "10, 20" states two numbers where the model stated a span. It gets its own rule, first.
|
| 1247 |
+
# Same shape as `routes_query._no_dashes`, deliberately: one behaviour, two doors.
|
| 1248 |
+
# β MODULE-LEVEL, not a closure. A normaliser defined inside this handler is unreachable to
|
| 1249 |
+
# anything that is not an HTTP request, so the only way to test it would be to drive the whole
|
| 1250 |
+
# route and read the answer β which is how a rule ends up asserted by a grep instead of a call.
|
| 1251 |
+
# β `dropped` IS NOT NORMALISED AND THAT IS DELIBERATE: it is `[{kind, keys}]`, an action kind
|
| 1252 |
+
# from OUR catalog and config keys from OUR allowlist, never a model's sentence. The first
|
| 1253 |
+
# version of this block mapped the normaliser over it and turned each dict into the string
|
| 1254 |
+
# `"{'kind': ..., 'keys': [...]}"` β `verify_automation`'s own W33 section caught it with a
|
| 1255 |
+
# `TypeError` on `d["kind"]`. Applying a text rule to a structure is how a channel stops
|
| 1256 |
+
# carrying what its reader expects, and the reader here is a person's list of what changed.
|
| 1257 |
+
shown = [dict(r, why=_draft_no_dashes(r.get("why"))) for r in shown]
|
| 1258 |
+
_notes = [_draft_no_dashes(n) for n in _notes]
|
| 1259 |
+
return {"draft": {"name": _draft_no_dashes(draft.get("name")) or "New automation",
|
| 1260 |
+
"trigger": _trig or "manual",
|
| 1261 |
+
"table": draft.get("table") or "",
|
| 1262 |
+
"actions": shown},
|
| 1263 |
+
"provider": provider, "dropped": dropped, "notes": _notes, "saved": False}
|
| 1264 |
+
|
| 1265 |
+
|
| 1266 |
@router.get("/automations/{auto_id}")
|
| 1267 |
def get_automation(auto_id: str, session: Session = Depends(_GATE)):
|
| 1268 |
+
"""One automation, by id.
|
| 1269 |
+
|
| 1270 |
+
ββ WAVE 34 Β· CONTRACT C3 β A SYNTHETIC ROW MUST BE FETCHABLE BY ID, NOT ONLY LISTABLE, AND
|
| 1271 |
+
THIS IS THE HALF THAT IS EASY TO SHIP BROKEN. `list_automations` and this route are SEPARATE
|
| 1272 |
+
lookups: a row appended only to the list appears in the rail, looks entirely real, and 404s
|
| 1273 |
+
the instant somebody clicks it. `W34-T48`'s `done-when` is *"opening it shows a Trigger and
|
| 1274 |
+
one step"* β i.e. this route, not the list β so the field agents are resolved here too, from
|
| 1275 |
+
the same builder, and a person cannot reach a row the detail route does not know.
|
| 1276 |
+
β THE SAME BUILDER, NOT A SECOND ONE. `_field_agent_rows` is called and the id looked up in
|
| 1277 |
+
its output rather than re-deriving one row from the field: two derivations of one row is how
|
| 1278 |
+
the list and the editor start disagreeing about a name.
|
| 1279 |
+
"""
|
| 1280 |
+
if str(auto_id) == ODOO_SYNC_ID:
|
| 1281 |
+
# β `detail=True` β the keychain label and the last-sync stamp cost a store read each and
|
| 1282 |
+
# are resolved HERE, on a route that fetches one automation, never on the list.
|
| 1283 |
+
row = _odoo_sync_row(session, detail=True)
|
| 1284 |
+
if row is None:
|
| 1285 |
+
raise err(404, "unknown_automation", "no automation with that id")
|
| 1286 |
+
return {"automation": row}
|
| 1287 |
+
if str(auto_id).startswith("field:"):
|
| 1288 |
+
row = next((r for r in _field_agent_rows(session) if r.get("id") == str(auto_id)), None)
|
| 1289 |
+
if row is None:
|
| 1290 |
+
# β The SAME 404 as any other unknown id. A field agent whose column has been deleted
|
| 1291 |
+
# is genuinely gone, and inventing a different error for it would make a normal
|
| 1292 |
+
# outcome look like a fault.
|
| 1293 |
+
raise err(404, "unknown_automation", "no automation with that id")
|
| 1294 |
+
return {"automation": row}
|
| 1295 |
defn = engine.all_definitions(session.runtime).get(str(auto_id))
|
| 1296 |
if defn is None:
|
| 1297 |
raise err(404, "unknown_automation", "no automation with that id")
|
|
|
|
| 1305 |
answered before the kind. `new` mints the blank database in the same call, so the automation
|
| 1306 |
is never saved pointing at a table that does not exist yet."""
|
| 1307 |
if not session.runtime.available():
|
| 1308 |
+
raise err(503, "store_unavailable", "the tenant store is unavailable. Nothing was saved")
|
| 1309 |
+
# ββ D-75 β THE DISCLOSURE CHANNEL, CONSUMED. `clean_actions` silently drops a
|
| 1310 |
+
# `create_record` condition (D-65's law: dropping is recoverable, refusing locks the door) and
|
| 1311 |
+
# any config key an arm's allowlist does not keep. Both are deliberate; what was missing was
|
| 1312 |
+
# anybody being TOLD, so a person saved a flow and got a different one with nothing said.
|
| 1313 |
+
# β It rides the SAVE's own response, beside `unconfigured`, because that is the moment the
|
| 1314 |
+
# person is looking β a note in a log they never open is the same silence with extra steps.
|
| 1315 |
+
_notes = []
|
| 1316 |
+
defn, error = engine.create(session.runtime, body or {}, username=session.uname,
|
| 1317 |
+
notes=_notes)
|
| 1318 |
if error:
|
| 1319 |
raise err(400, "invalid_automation", error)
|
| 1320 |
+
return {"automation": _wire(defn, session.tenant), "notes": _notes}
|
| 1321 |
|
| 1322 |
|
| 1323 |
@router.patch("/automations/{auto_id}")
|
| 1324 |
def patch_automation(auto_id: str, body: dict = Body(default=None),
|
| 1325 |
session: Session = Depends(_GATE)):
|
| 1326 |
if not session.runtime.available():
|
| 1327 |
+
raise err(503, "store_unavailable", "the tenant store is unavailable. Nothing was saved")
|
| 1328 |
+
# ββ WAVE 34 Β· CONTRACT C3 β A SYNTHETIC ROW IS NOT PATCHABLE, AND IT MUST SAY SO. A field
|
| 1329 |
+
# agent is DERIVED from a column definition; there is nothing in the automations bucket to
|
| 1330 |
+
# write. `engine.patch` would answer "no such automation" (a 404 that reads as "your agent
|
| 1331 |
+
# vanished") or, worse for a future id shape, find nothing and report success. The refusal
|
| 1332 |
+
# names where the setting actually lives, because a wall that does not say what to do instead
|
| 1333 |
+
# sends somebody looking for a bug in a decision made on purpose (D-65's own lesson).
|
| 1334 |
+
if str(auto_id).startswith("field:"):
|
| 1335 |
+
raise err(409, "system_agent",
|
| 1336 |
+
"this agent is an AI enrichment column. Change its prompt, model or schedule on "
|
| 1337 |
+
"the column itself and this page follows")
|
| 1338 |
+
if str(auto_id) == ODOO_SYNC_ID:
|
| 1339 |
+
return _patch_odoo_sync(session, body or {})
|
| 1340 |
+
# D-75, same channel as `create` above β an EDIT is where this matters most, because the
|
| 1341 |
+
# person has just typed the thing that gets dropped.
|
| 1342 |
+
_notes = []
|
| 1343 |
+
defn, error = engine.patch(session.runtime, auto_id, body or {}, username=session.uname,
|
| 1344 |
+
notes=_notes)
|
| 1345 |
if error:
|
| 1346 |
raise err(400 if error != "no such automation" else 404,
|
| 1347 |
"invalid_automation" if error != "no such automation" else "unknown_automation",
|
| 1348 |
error)
|
| 1349 |
+
return {"automation": _wire(defn, session.tenant), "notes": _notes}
|
| 1350 |
|
| 1351 |
|
| 1352 |
@router.delete("/automations/{auto_id}")
|
| 1353 |
def delete_automation(auto_id: str, session: Session = Depends(_GATE)):
|
| 1354 |
"""Delete the DEFINITION. β The database it filled is NOT touched β an automation is the
|
| 1355 |
thing that writes rows, not the thing that owns them, and deleting a job must never be a way
|
| 1356 |
+
to lose data (the same rule the orphan count encodes).
|
| 1357 |
+
|
| 1358 |
+
ββ WAVE 34 Β· CONTRACTS C3 + C4 β A SYSTEM AGENT REFUSES, LOUDLY, AND THE REFUSAL SAYS WHERE
|
| 1359 |
+
TO GO INSTEAD. Two families are undeletable and they are undeletable for different reasons, so
|
| 1360 |
+
the sentence names the reason rather than saying "no": a FIELD AGENT is a column (delete the
|
| 1361 |
+
column), and the ODOO SYNC is the connector's own schedule (disconnect the connector).
|
| 1362 |
+
|
| 1363 |
+
β REFUSED, NOT IGNORED, AND THAT IS THE POINT OF THE FIRST BRANCH. A synthetic id is not in
|
| 1364 |
+
the automations bucket, so `engine.remove` would find nothing, do nothing, and this route
|
| 1365 |
+
would answer `200 {"deleted": ...}` β a delete that reports success and changes nothing, which
|
| 1366 |
+
is the `view_upsert` failure mode (200 OK, zero writes) arriving in a new place. The row would
|
| 1367 |
+
then reappear on the next poll and read as a bug in the rail.
|
| 1368 |
+
"""
|
| 1369 |
+
# ββ EVERY SYNTHETIC ID, NOT JUST THE FIELD ONES. The first version of this guard listed
|
| 1370 |
+
# `field:` alone, and `verify_automation`'s own C4 leg caught what that left open: deleting
|
| 1371 |
+
# `system:odoo_sync` fell straight through to `engine.remove`, which popped a key that was
|
| 1372 |
+
# never in the bucket and answered `200 {"deleted": ...}`. A delete that reports success and
|
| 1373 |
+
# changes nothing, on the one row the ruling says must be undeletable β the exact defect the
|
| 1374 |
+
# guard exists for, one id shape away. Both prefixes are refused by the same branch now.
|
| 1375 |
+
if str(auto_id).startswith("field:"):
|
| 1376 |
+
raise err(409, "system_agent", engine.system_agent_refusal(SYSTEM_FIELD_AGENT))
|
| 1377 |
+
if str(auto_id) == ODOO_SYNC_ID:
|
| 1378 |
+
raise err(409, "system_agent", engine.system_agent_refusal(SYSTEM_ODOO_SYNC))
|
| 1379 |
if engine.running(session.tenant, auto_id):
|
| 1380 |
+
raise err(409, "automation_running", "it is running. Wait for it to finish")
|
| 1381 |
+
# β READ BEFORE THE REMOVE, not after: `engine.remove` is the thing being refused.
|
| 1382 |
+
_defn = (engine.all_definitions(session.runtime) or {}).get(str(auto_id)) or {}
|
| 1383 |
+
_sys = str(_defn.get("system") or "").strip()
|
| 1384 |
+
if _sys:
|
| 1385 |
+
raise err(409, "system_agent", engine.system_agent_refusal(_sys))
|
| 1386 |
engine.remove(session.runtime, auto_id)
|
| 1387 |
return {"deleted": str(auto_id)}
|
| 1388 |
|
|
|
|
| 1400 |
except engine.Refused as e:
|
| 1401 |
raise err(400, "refused_url", str(e))
|
| 1402 |
except Exception as e: # noqa: BLE001
|
| 1403 |
+
raise err(502, "fetch_failed", f"could not read that page. {type(e).__name__}: "
|
| 1404 |
f"{str(e)[:160]}")
|
| 1405 |
|
| 1406 |
|
|
|
|
| 1431 |
nothing: a control that appears to work and does not is worse than one that refuses.
|
| 1432 |
"""
|
| 1433 |
if not session.runtime.available():
|
| 1434 |
+
raise err(503, "store_unavailable", "the tenant store is unavailable. Nothing was saved")
|
| 1435 |
if engine.running(session.tenant, auto_id):
|
| 1436 |
+
raise err(409, "automation_running", "it is running. Wait for it to finish")
|
| 1437 |
defn, error = engine.toggle_node(session.runtime, auto_id, node_id)
|
| 1438 |
if error:
|
| 1439 |
raise err(404 if error == "no such automation" else 400,
|
|
|
|
| 1500 |
want = os.environ.get("AIOS_AUTOMATION_TICK_TOKEN") or ""
|
| 1501 |
if not want:
|
| 1502 |
raise err(403, "tick_disabled",
|
| 1503 |
+
"AIOS_AUTOMATION_TICK_TOKEN is not configured. The tick endpoint is closed")
|
| 1504 |
got = x_aios_tick_token or request.headers.get("X-AIOS-TICK-TOKEN") or ""
|
| 1505 |
if got != want:
|
| 1506 |
raise err(403, "bad_tick_token", "that token is not valid for this deployment")
|
|
|
|
| 1518 |
if not session.admin:
|
| 1519 |
raise err(403, "admin_only", "erasing a subject is an admin action")
|
| 1520 |
if not session.runtime.available():
|
| 1521 |
+
raise err(503, "store_unavailable", "the tenant store is unavailable. Nothing was "
|
| 1522 |
"purged")
|
| 1523 |
handle = str((body or {}).get("handle") or "").strip()
|
| 1524 |
if not handle:
|
|
|
|
| 1557 |
"measure": bag.get("measure"), "window": bag.get("window"),
|
| 1558 |
"value": value, "rows": rows[:200],
|
| 1559 |
"note": "" if value is not None else
|
| 1560 |
+
"no master data answers this window. The cell is honestly blank"}
|
| 1561 |
|
| 1562 |
|
| 1563 |
@router.get("/automations/{auto_id}/rows")
|
api/routes_brand.py
ADDED
|
@@ -0,0 +1,140 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"""routes_brand.py β THE CONNECTOR BRAND-ASSET DOOR (wave 33, owner item 6 / ruling R4 / contract C6).
|
| 2 |
+
|
| 3 |
+
β WHAT THE OWNER ASKED FOR, verbatim: *"Do not generate your own logo for Connectors, they look
|
| 4 |
+
really uncanny /browse them the PNG, cut appropriately for our needs, verify visually."* So the marks
|
| 5 |
+
are the VENDORS' OWN artwork, on disk, with their provenance recorded β `web/public/brand/` and its
|
| 6 |
+
`SOURCES.md`. This module is the door R4 asks for and nothing else: it maps a brand KEY to a file,
|
| 7 |
+
serves it, and refuses anything else.
|
| 8 |
+
|
| 9 |
+
β WHY A NEW DOOR AND NOT `routes_assets.py`. That module gates EVERY one of its routes behind
|
| 10 |
+
`module_gate("product_data")` (`routes_assets.py:45`) because it serves product imagery and the grant
|
| 11 |
+
that owns product imagery is the right wall for it. A connector logo is not product data: an account
|
| 12 |
+
with no product grant still opens Connectors, still opens the automation pickers, and would have got
|
| 13 |
+
a 403 where a picture should be. Contract C6 says session-gated, NOT product-gated, and that is the
|
| 14 |
+
whole reason this file exists rather than one more path over there.
|
| 15 |
+
|
| 16 |
+
β SESSION-GATED, AND THAT IS AN HONEST WALL RATHER THAN A SECRET. Public brand artwork is public by
|
| 17 |
+
definition, and the same bytes are ALSO reachable through the static bundle β `web/public/**` is
|
| 18 |
+
copied into `web/dist/**` by `vite build`, which `main.py` mounts unauthenticated at `/`. So the
|
| 19 |
+
session gate here is consistency with every other `/api/v1` route, not a claim that these files are
|
| 20 |
+
confidential. What the door actually buys, and what a raw static path could not:
|
| 21 |
+
|
| 22 |
+
Β· ONE KEY VOCABULARY. The client asks for `instagram`, the same string `BRAND_OF_CONNECTOR` maps
|
| 23 |
+
to β never a filename. The extension is ours to change (a vendor publishing SVG tomorrow moves
|
| 24 |
+
one line here) and no caller learns about it.
|
| 25 |
+
Β· A CLEAN 404 for a key we have no art for, which is what lets the client keep its two-letter tile
|
| 26 |
+
fallback honest instead of painting a broken-image glyph.
|
| 27 |
+
Β· IMMUTABLE CACHING on a response the browser then never re-fetches.
|
| 28 |
+
|
| 29 |
+
β THE FALLBACK IS NOT DEAD CODE AND MUST NOT BE "TIDIED". `ConnectorsPage.tsx:204 tileText` draws two
|
| 30 |
+
letters for any connector with no entry in `BRAND_OF_CONNECTOR` β which is most of the planned list,
|
| 31 |
+
by design, because the directory deliberately lists things we have not built (R8). A 404 from here is
|
| 32 |
+
the *correct* answer for those rows, not a failure.
|
| 33 |
+
"""
|
| 34 |
+
from __future__ import annotations
|
| 35 |
+
|
| 36 |
+
import os
|
| 37 |
+
import re
|
| 38 |
+
from pathlib import Path
|
| 39 |
+
|
| 40 |
+
from fastapi import APIRouter, Depends
|
| 41 |
+
from fastapi.responses import FileResponse
|
| 42 |
+
|
| 43 |
+
from deps import Session, err, require_session
|
| 44 |
+
|
| 45 |
+
router = APIRouter(prefix="/api/v1")
|
| 46 |
+
|
| 47 |
+
#: β CLOSED CHARSET, CHECKED BEFORE THE KEY TOUCHES A PATH β same discipline as
|
| 48 |
+
#: `routes_assets._CODE_RE`. No dot, no slash, no backslash, no colon, so `..` and every absolute
|
| 49 |
+
#: path are refused at the door (400) rather than resolved and then defended against.
|
| 50 |
+
_KEY_RE = re.compile(r"^[a-z][a-z0-9_]{0,31}$")
|
| 51 |
+
|
| 52 |
+
#: A year, immutable. The artwork is versioned by its own key: a NEW mark for a vendor is a new file
|
| 53 |
+
#: with the same name, so a rebrand ships with a deploy and a hard reload, not with a cache bust.
|
| 54 |
+
#: β Deliberately the same string as `routes_assets._IMMUTABLE` β two asset doors telling a browser
|
| 55 |
+
#: two different things about the same class of file would be a defect nobody could see.
|
| 56 |
+
_IMMUTABLE = "public, max-age=31536000, immutable"
|
| 57 |
+
|
| 58 |
+
_MEDIA = {".png": "image/png", ".svg": "image/svg+xml"}
|
| 59 |
+
|
| 60 |
+
#: β THE ROOTS, IN ORDER, AND THE ORDER IS THE POINT.
|
| 61 |
+
#:
|
| 62 |
+
#: `web/dist/brand` FIRST because that is what a container has: `deploy_web.py::_web_source_files`
|
| 63 |
+
#: SKIPS `dist`, so the Space uploads `web/public/**` as source and its own `vite build` produces
|
| 64 |
+
#: `dist/`. `web/public/brand` SECOND because that is what a DEV BOX has before anything is built β
|
| 65 |
+
#: and a door that only works after `npm run build` is a door that fails for the person writing it.
|
| 66 |
+
#: `AIOS_BRAND_DIR` FIRST OF ALL, so an operator can point at either without a redeploy.
|
| 67 |
+
#:
|
| 68 |
+
#: β RESOLVED PER REQUEST, NOT AT IMPORT. A module-level constant computed at import is a fact about
|
| 69 |
+
#: the process's startup, and this one would be wrong for the whole life of any container that built
|
| 70 |
+
#: its bundle after the API module was first imported.
|
| 71 |
+
#:
|
| 72 |
+
#: β THE ONE TRAP THIS ORDER CREATES, AND IT ONLY BITES A DEV BOX. `dist` winning means a mark
|
| 73 |
+
#: replaced in `public/brand/` is NOT served until the next `npm run build` β locally the two can
|
| 74 |
+
#: disagree, and the door will confidently serve yesterday's logo. In the image they cannot: the
|
| 75 |
+
#: Space uploads `public/` (`deploy_web.py::_web_source_files` SKIPS `dist`) and builds `dist/` from
|
| 76 |
+
#: it in the same step. If a local mark looks stale, rebuild before believing the door is wrong.
|
| 77 |
+
_HERE = Path(__file__).resolve().parent
|
| 78 |
+
|
| 79 |
+
|
| 80 |
+
def _roots():
|
| 81 |
+
env = (os.environ.get("AIOS_BRAND_DIR") or "").strip()
|
| 82 |
+
out = [Path(env)] if env else []
|
| 83 |
+
web = _HERE.parent / "web" # _HERE is `aios-web/api`; its parent is `aios-web`
|
| 84 |
+
out.append(web / "dist" / "brand")
|
| 85 |
+
out.append(web / "public" / "brand")
|
| 86 |
+
return out
|
| 87 |
+
|
| 88 |
+
|
| 89 |
+
def brand_path(key):
|
| 90 |
+
"""The file for a brand key, or None. Pure and importable, so the gate answers this question
|
| 91 |
+
without a request β the same shape `routes_connectors.directory` uses for the same reason."""
|
| 92 |
+
k = str(key or "")
|
| 93 |
+
if not _KEY_RE.match(k):
|
| 94 |
+
return None
|
| 95 |
+
for root in _roots():
|
| 96 |
+
for ext in (".png", ".svg"):
|
| 97 |
+
p = root / f"{k}{ext}"
|
| 98 |
+
# β `is_file()` and not `exists()`: a DIRECTORY named `instagram.png` would otherwise
|
| 99 |
+
# resolve and then fail inside FileResponse as a 500.
|
| 100 |
+
if p.is_file():
|
| 101 |
+
return p
|
| 102 |
+
return None
|
| 103 |
+
|
| 104 |
+
|
| 105 |
+
def available():
|
| 106 |
+
"""Every brand key that has artwork on disk, sorted. The directory listing this module can
|
| 107 |
+
answer cheaply β used by `verify_meta` to assert parity against `BRAND_OF_CONNECTOR` rather than
|
| 108 |
+
against a list somebody typed twice."""
|
| 109 |
+
keys = set()
|
| 110 |
+
for root in _roots():
|
| 111 |
+
if not root.is_dir():
|
| 112 |
+
continue
|
| 113 |
+
for p in root.iterdir():
|
| 114 |
+
if p.is_file() and p.suffix in _MEDIA and _KEY_RE.match(p.stem):
|
| 115 |
+
keys.add(p.stem)
|
| 116 |
+
return sorted(keys)
|
| 117 |
+
|
| 118 |
+
|
| 119 |
+
@router.get("/brand/{key}")
|
| 120 |
+
def brand_asset(key: str, session: Session = Depends(require_session)):
|
| 121 |
+
"""R4/C6: one connector's official mark, to any authenticated session.
|
| 122 |
+
|
| 123 |
+
β THREE ANSWERS, AND THE THIRD IS THE ONE THE TICKET ASKS ABOUT: 400 for a key that is not a
|
| 124 |
+
key (it never reaches the filesystem), **404 for a key we simply have no art for**, and the file
|
| 125 |
+
otherwise. A stack trace is not one of the answers β an unknown key is an ordinary, expected
|
| 126 |
+
request from a client whose connector list is longer than our logo set.
|
| 127 |
+
β `session` is required and then unused, which is intentional: the dependency IS the wall, and
|
| 128 |
+
naming it in the signature is what puts it there. Deleting the "unused" parameter would open the
|
| 129 |
+
route to the internet with no other symptom.
|
| 130 |
+
"""
|
| 131 |
+
if not _KEY_RE.match(str(key or "")):
|
| 132 |
+
raise err(400, "bad_brand_key", "that is not a brand key")
|
| 133 |
+
p = brand_path(key)
|
| 134 |
+
if p is None:
|
| 135 |
+
raise err(404, "brand_not_found", f"no brand mark for '{key}'")
|
| 136 |
+
return FileResponse(
|
| 137 |
+
str(p),
|
| 138 |
+
media_type=_MEDIA.get(p.suffix, "application/octet-stream"),
|
| 139 |
+
headers={"Cache-Control": _IMMUTABLE},
|
| 140 |
+
)
|
api/routes_changes.py
CHANGED
|
@@ -55,7 +55,7 @@ So: a valid session, a scope sanitised to a bucket-safe shape, and β for a `ut
|
|
| 55 |
cached verdict that this session may open it.
|
| 56 |
"""
|
| 57 |
import time
|
| 58 |
-
from fastapi import APIRouter, Depends
|
| 59 |
|
| 60 |
import core.shared_overlay as shared_overlay
|
| 61 |
import core.store as store
|
|
@@ -224,3 +224,87 @@ def changes(scope: str = "", session: Session = Depends(require_session)):
|
|
| 224 |
# a token frozen at 0 would promise liveness the backend is not delivering.
|
| 225 |
tokens[label] = rev.get("token") if isinstance(rev, dict) else None
|
| 226 |
return {"scope": _clean_scope(scope), "tokens": tokens, "backend": store.backend()}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 55 |
cached verdict that this session may open it.
|
| 56 |
"""
|
| 57 |
import time
|
| 58 |
+
from fastapi import APIRouter, Depends, Request
|
| 59 |
|
| 60 |
import core.shared_overlay as shared_overlay
|
| 61 |
import core.store as store
|
|
|
|
| 224 |
# a token frozen at 0 would promise liveness the backend is not delivering.
|
| 225 |
tokens[label] = rev.get("token") if isinstance(rev, dict) else None
|
| 226 |
return {"scope": _clean_scope(scope), "tokens": tokens, "backend": store.backend()}
|
| 227 |
+
|
| 228 |
+
|
| 229 |
+
# ββ ββ D-144 (W33-T32) β A CAUGHT RENDER ERROR TELLS SOMEBODY ββββββββββββββββββββββββββββββββ
|
| 230 |
+
#
|
| 231 |
+
# β THE DEBT, in its own words: *"A caught render error tells nobody."* W30-T39 gave the app its
|
| 232 |
+
# first error boundary β measured at the time, `componentDidCatch|getDerivedStateFromError` was
|
| 233 |
+
# **0 hits** across all of `web/src`, so any throw anywhere blanked the whole product. The
|
| 234 |
+
# boundary CONTAINS the failure; it does not REPORT it, so the next user complaint still arrives
|
| 235 |
+
# as a sentence rather than as a stack. That is why owner item 2's crash could not be diagnosed
|
| 236 |
+
# and had to be fixed at both candidate causes.
|
| 237 |
+
#
|
| 238 |
+
# β IT LIVES HERE, IN THE CHANGE-TOKEN ROUTER, AND THE REASON IS WORTH ONE LINE. It is not about
|
| 239 |
+
# change tokens. It is here because this router is already mounted, already in one lane's fence,
|
| 240 |
+
# and a NEW `routes_*.py` costs a cross-fence mount (contract C2) that this wave has already spent
|
| 241 |
+
# three times β and a fourth finished-but-unmounted router is precisely the failure wave 23 shipped
|
| 242 |
+
# three of. Subject purity would have been bought with the exact risk the contract exists to
|
| 243 |
+
# prevent. β It performs no `store.get()`, so this file's zero-deep-copy claim (and
|
| 244 |
+
# `verify_live_workspace`'s count of it) is untouched: `telemetry.log` appends one line to a
|
| 245 |
+
# container-local JSONL.
|
| 246 |
+
#
|
| 247 |
+
# ββ AND IT CARRIES NO ROW DATA, WHICH IS THE DEBT'S OWN HARD CONDITION. The body is rebuilt KEY
|
| 248 |
+
# BY KEY from exactly two strings; there is no `**body` anywhere below. A crash reporter that
|
| 249 |
+
# forwarded props or state would quietly ship a customer's cell values into a log β the one way
|
| 250 |
+
# this feature could do more harm than the silence it replaces.
|
| 251 |
+
_CLIENT_ERR_MAX = 4 * 1024
|
| 252 |
+
_CLIENT_ERR_WINDOW_S = 60
|
| 253 |
+
_CLIENT_ERR_PER_WINDOW = 12
|
| 254 |
+
_CLIENT_ERR_HITS: dict = {}
|
| 255 |
+
|
| 256 |
+
|
| 257 |
+
@router.post("/client-error")
|
| 258 |
+
async def client_error(request: Request, session: Session = Depends(require_session)):
|
| 259 |
+
"""One caught render error, forwarded to telemetry. `{message, componentStack}`.
|
| 260 |
+
|
| 261 |
+
β SESSION-GATED, deliberately. A public crash sink is an unauthenticated append to a log file,
|
| 262 |
+
which is a disk-filling primitive with a URL. Only signed-in accounts can crash this app in a
|
| 263 |
+
way we need to hear about.
|
| 264 |
+
β RATE-LIMITED PER ACCOUNT, because the failure mode is a render LOOP: a boundary that catches,
|
| 265 |
+
resets and re-throws would otherwise post several times a second, for ever, from every open
|
| 266 |
+
tab. Beyond the window the report is DROPPED and the request still answers 200 β the client
|
| 267 |
+
must never learn to retry a report.
|
| 268 |
+
"""
|
| 269 |
+
now = time.time()
|
| 270 |
+
who = session.uname or "?"
|
| 271 |
+
seen = [t for t in _CLIENT_ERR_HITS.get(who, ()) if now - t < _CLIENT_ERR_WINDOW_S]
|
| 272 |
+
seen.append(now)
|
| 273 |
+
_CLIENT_ERR_HITS[who] = seen
|
| 274 |
+
if len(_CLIENT_ERR_HITS) > 2048:
|
| 275 |
+
for k in [k for k, v in _CLIENT_ERR_HITS.items()
|
| 276 |
+
if not v or now - v[-1] > _CLIENT_ERR_WINDOW_S]:
|
| 277 |
+
_CLIENT_ERR_HITS.pop(k, None)
|
| 278 |
+
if len(seen) > _CLIENT_ERR_PER_WINDOW:
|
| 279 |
+
return {"ok": True, "recorded": False}
|
| 280 |
+
|
| 281 |
+
# The body, BOUNDED BY THE STREAM. `Body(...)` would already have been read and parsed before
|
| 282 |
+
# this line ran, and `content-length` is caller-supplied β the same argument `routes_forms`
|
| 283 |
+
# and `routes_publish` both carry.
|
| 284 |
+
size, chunks = 0, []
|
| 285 |
+
async for chunk in request.stream():
|
| 286 |
+
size += len(chunk)
|
| 287 |
+
if size > _CLIENT_ERR_MAX:
|
| 288 |
+
raise err(413, "body_too_large", "that report is too large")
|
| 289 |
+
chunks.append(chunk)
|
| 290 |
+
import json as _json
|
| 291 |
+
try:
|
| 292 |
+
body = _json.loads(b"".join(chunks) or b"{}")
|
| 293 |
+
except ValueError:
|
| 294 |
+
body = {}
|
| 295 |
+
if not isinstance(body, dict):
|
| 296 |
+
body = {}
|
| 297 |
+
|
| 298 |
+
# β TWO KEYS, BOTH TRUNCATED, NOTHING ELSE. See the block note above.
|
| 299 |
+
message = str(body.get("message") or "")[:500]
|
| 300 |
+
stack = str(body.get("componentStack") or "")[:4000]
|
| 301 |
+
if not message and not stack:
|
| 302 |
+
return {"ok": True, "recorded": False}
|
| 303 |
+
try:
|
| 304 |
+
import harness.telemetry as _tel
|
| 305 |
+
_tel.log("client_error", user=session.uname, tenant=session.tenant,
|
| 306 |
+
message=message, componentStack=stack)
|
| 307 |
+
except Exception: # noqa: BLE001
|
| 308 |
+
# Telemetry may never break a request β `deps.py` carries the same rule at its own site.
|
| 309 |
+
return {"ok": True, "recorded": False}
|
| 310 |
+
return {"ok": True, "recorded": True}
|
api/routes_connectors.py
CHANGED
|
@@ -30,7 +30,7 @@ from deps import Session, require_session
|
|
| 30 |
#: one question, and this module used to answer it with an unguarded `os.environ.get("ODOO_URL")`
|
| 31 |
#: while `routes_keychain` answered it correctly. Importing the correct one is the fix; writing a
|
| 32 |
#: second correct one here would leave the same two-copies shape that produced the defect.
|
| 33 |
-
from routes_keychain import env_odoo_available
|
| 34 |
|
| 35 |
# β THE PREFIX IS LOAD-BEARING AND IT WAS MISSING (found at the wave-23 close-out audit).
|
| 36 |
# This router declared a bare `APIRouter()`, so its one path was served at `/connectors/directory`
|
|
@@ -396,15 +396,31 @@ def directory(rt, uname, is_admin=False, incomplete=None):
|
|
| 396 |
# reader. A token connector is the case R4 is really about: a member's own Stripe
|
| 397 |
# key is theirs, and the card must say which kind of connection it is looking at.
|
| 398 |
"scope": scopes.get(t["entry"]) or "business",
|
| 399 |
-
#
|
| 400 |
-
#
|
| 401 |
-
#
|
| 402 |
-
#
|
| 403 |
-
#
|
| 404 |
-
#
|
| 405 |
-
#
|
| 406 |
-
#
|
| 407 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 408 |
# Said once, on the row, rather than in a paragraph somewhere (R13): storing the
|
| 409 |
# key is real and useful, and it is not the same as the data being on screen.
|
| 410 |
"note": "Storing the key connects the account; reading its data lands in a later "
|
|
@@ -566,9 +582,22 @@ def connectors_directory(session: Session = Depends(require_session)):
|
|
| 566 |
"""C11: every connector this platform knows about, with its state for THIS reader.
|
| 567 |
|
| 568 |
Session-gated rather than admin-gated on purpose: a non-admin should be able to see what the
|
| 569 |
-
workspace is connected to
|
| 570 |
-
of R7's per-user slots
|
| 571 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 572 |
"""
|
| 573 |
# β `session.admin`, NOT `is_admin`. A `getattr(session, "is_admin", False)` here reads as
|
| 574 |
# careful and is silently False for every admin on earth β the manage actions would simply
|
|
|
|
| 30 |
#: one question, and this module used to answer it with an unguarded `os.environ.get("ODOO_URL")`
|
| 31 |
#: while `routes_keychain` answered it correctly. Importing the correct one is the fix; writing a
|
| 32 |
#: second correct one here would leave the same two-copies shape that produced the defect.
|
| 33 |
+
from routes_keychain import TENANT_WIDE_TYPES, env_odoo_available
|
| 34 |
|
| 35 |
# β THE PREFIX IS LOAD-BEARING AND IT WAS MISSING (found at the wave-23 close-out audit).
|
| 36 |
# This router declared a bare `APIRouter()`, so its one path was served at `/connectors/directory`
|
|
|
|
| 396 |
# reader. A token connector is the case R4 is really about: a member's own Stripe
|
| 397 |
# key is theirs, and the card must say which kind of connection it is looking at.
|
| 398 |
"scope": scopes.get(t["entry"]) or "business",
|
| 399 |
+
# ββ W33-T66 / D-204 β THE MEMBER'S DOOR, AND IT IS A THIRD WORD RATHER THAN A
|
| 400 |
+
# WIDENED ONE. This route's own docstring has promised since wave 23 that a
|
| 401 |
+
# non-admin may *"connect their OWN per-user accounts"*, and the next sentence
|
| 402 |
+
# then handed them an empty `manage` β a contradiction inside one paragraph, and
|
| 403 |
+
# D-204's subject. W32-T11 opened the ROOM (`admin_gate` is gone from
|
| 404 |
+
# `routes_keychain`; a member may POST `scope: "personal"`), so the only thing
|
| 405 |
+
# still missing was a way to reach it from the map.
|
| 406 |
+
#
|
| 407 |
+
# β `keychain` DOES NOT WIDEN, and that is deliberate rather than timid.
|
| 408 |
+
# `verify_automation`'s NC asserts a non-admin is offered no `manage == "keychain"`
|
| 409 |
+
# row, and its own comment says why in the right words: *"the line is TENANT-WIDE
|
| 410 |
+
# vs PER-USER, not admin vs everyone β¦ what they must never be offered is the
|
| 411 |
+
# KEYCHAIN door, which edits credentials the whole tenant uses."* That assertion
|
| 412 |
+
# is CORRECT and stays green. A member's personal connection is a different door
|
| 413 |
+
# into the same room, so it gets its own word.
|
| 414 |
+
#
|
| 415 |
+
# β THE PREDICATE IS THE CREDENTIAL'S OWN RULE, IMPORTED, NOT RE-STATED HERE.
|
| 416 |
+
# `TENANT_WIDE_TYPES` is what `routes_keychain` REFUSES a personal scope for, so
|
| 417 |
+
# offering a personal door for one of those types would be offering a button that
|
| 418 |
+
# 400s β the exact failure R6 removed from the Google card. Today that means
|
| 419 |
+
# Stripe and Shopify open for a member and Meta Ads does not
|
| 420 |
+
# ([[one-question-two-normalizers]]).
|
| 421 |
+
"manage": ("keychain" if is_admin
|
| 422 |
+
else "" if t["entry"] in TENANT_WIDE_TYPES
|
| 423 |
+
else "keychain_personal"),
|
| 424 |
# Said once, on the row, rather than in a paragraph somewhere (R13): storing the
|
| 425 |
# key is real and useful, and it is not the same as the data being on screen.
|
| 426 |
"note": "Storing the key connects the account; reading its data lands in a later "
|
|
|
|
| 582 |
"""C11: every connector this platform knows about, with its state for THIS reader.
|
| 583 |
|
| 584 |
Session-gated rather than admin-gated on purpose: a non-admin should be able to see what the
|
| 585 |
+
workspace is connected to, and connect their OWN per-user accounts β which is the whole point
|
| 586 |
+
of R7's per-user slots.
|
| 587 |
+
|
| 588 |
+
ββ W33-T66 / D-204 β AND THAT SECOND CLAUSE IS NOW TRUE. This docstring used to promise it and
|
| 589 |
+
then say, one sentence later, that `manage` *"is empty for a non-admin"* β a contradiction
|
| 590 |
+
inside a single paragraph, which is how the promise survived three waves without a door behind
|
| 591 |
+
it. `manage` carries WHICH ROOM, and there are three answers for a keychain-backed row:
|
| 592 |
+
|
| 593 |
+
Β· `keychain` β the tenant-wide credential door. **Admins only**, and it must stay
|
| 594 |
+
that way: it edits the key the whole workspace reads through.
|
| 595 |
+
Β· `keychain_personal` β the same room, for a connection that is this reader's own. Offered
|
| 596 |
+
to a non-admin **only** where a personal credential is actually
|
| 597 |
+
allowed (`routes_keychain.TENANT_WIDE_TYPES` is the refusal list, so
|
| 598 |
+
Odoo and Meta Ads never get it).
|
| 599 |
+
Β· `""` β nothing this reader can do here; the client renders no control
|
| 600 |
+
rather than a door that would 403.
|
| 601 |
"""
|
| 602 |
# β `session.admin`, NOT `is_admin`. A `getattr(session, "is_admin", False)` here reads as
|
| 603 |
# careful and is silently False for every admin on earth β the manage actions would simply
|
api/routes_customers.py
CHANGED
|
@@ -209,6 +209,17 @@ def grid_assembly(session: Session, scope: str = "customer", storage_key: str =
|
|
| 209 |
# The derived channel: cohort membership cells + measure column values, ONE dict β the
|
| 210 |
# same read-only channel the embed host hands to rows_from_pool.
|
| 211 |
derived = aios_grid.cohort_cells(lists)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 212 |
for pid, cells in measure_resolve.column_values(
|
| 213 |
fields, team_id, pids, today, stamp, rt.measure_memo,
|
| 214 |
on_error=_measure_err).items():
|
|
|
|
| 209 |
# The derived channel: cohort membership cells + measure column values, ONE dict β the
|
| 210 |
# same read-only channel the embed host hands to rows_from_pool.
|
| 211 |
derived = aios_grid.cohort_cells(lists)
|
| 212 |
+
# β W33-T43 / owner item 12 ("One unique ID per database always"). The customer grid carried
|
| 213 |
+
# NO Odoo id column at all, while its retiring twin `ut_odoo_customers` carried `partner_id`
|
| 214 |
+
# as its join key β so the merge would have lost the one value every Odoo document joins on.
|
| 215 |
+
#
|
| 216 |
+
# β IT IS DERIVED, NOT A POOL COLUMN, AND THAT IS THE WHOLE POINT: a customer row's `pid` IS
|
| 217 |
+
# the `res.partner` id (`modules/customer_data.pool` mints it that way and the identity is
|
| 218 |
+
# asserted against Odoo in that module). Adding it to the pool would be a SECOND source for
|
| 219 |
+
# one fact, which is the class of defect item 12 is about. This channel exists for exactly
|
| 220 |
+
# this β a value the host knows per render and the pool has no business storing.
|
| 221 |
+
for pid in pids:
|
| 222 |
+
derived.setdefault(pid, {})["partner_id"] = pid
|
| 223 |
for pid, cells in measure_resolve.column_values(
|
| 224 |
fields, team_id, pids, today, stamp, rt.measure_memo,
|
| 225 |
on_error=_measure_err).items():
|
api/routes_feedback.py
ADDED
|
@@ -0,0 +1,180 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"""routes_feedback.py β WAVE 35 (ruling R8, contract C6): FEEDBACK GOES TO THE OPERATOR PLANE.
|
| 2 |
+
|
| 3 |
+
R8: *"Feedback goes to the platform-wide `loopable` operator plane. No tenant sees another's, and
|
| 4 |
+
the submitting tenant cannot edit or delete what it sent."*
|
| 5 |
+
|
| 6 |
+
ββ TWO DOORS, TWO DIFFERENT WALLS, AND THAT ASYMMETRY IS THE WHOLE TICKET. D-221 is already on the
|
| 7 |
+
register for a cross-tenant WRITE gated on `admin_gate` alone, so getting this backwards is a repeat
|
| 8 |
+
rather than a novelty:
|
| 9 |
+
|
| 10 |
+
POST /feedback ANY authenticated session, any tenant. It is the TENANT'S OWN ACT.
|
| 11 |
+
GET /feedback `core.platform_admin.is_platform_admin` ONLY. It is the OPERATOR'S read.
|
| 12 |
+
|
| 13 |
+
A single wall cannot express that. Gating the write on the operator predicate would mean nobody can
|
| 14 |
+
send feedback; gating the read on `admin_gate` would hand every tenant admin every other tenant's
|
| 15 |
+
words. So the walls are declared per route, and `verify_api` drives BOTH from a tenant admin, a
|
| 16 |
+
plain user and a platform admin rather than asserting the source.
|
| 17 |
+
|
| 18 |
+
β THE PROVENANCE IS STAMPED SERVER-SIDE AND NEVER READ FROM THE BODY. `tenant`, `user` and `ts`
|
| 19 |
+
come from the verified session and the clock. A body-supplied tenant would let any account file
|
| 20 |
+
words against another company's name, in a store only the operator reads and therefore only the
|
| 21 |
+
operator could ever be misled by.
|
| 22 |
+
|
| 23 |
+
β NO EDIT AND NO DELETE EXIST AT ALL β not for the tenant (R8 says so) and not for the operator
|
| 24 |
+
either. R8 grants the operator a READ; a delete door is a capability nobody asked for on a store
|
| 25 |
+
whose whole value is that it is append-only. There is nothing here to forget to wall.
|
| 26 |
+
|
| 27 |
+
β ONE STORE, AND WHERE IT PHYSICALLY LIVES IS STATED RATHER THAN IMPLIED. This uses `core.store`
|
| 28 |
+
with a raw key, which is the same thing `routes_platform_admin` does for `runtime.TENANTS_KEY` and
|
| 29 |
+
for the same reason: a platform fact belongs in the default store, not inside any tenant's
|
| 30 |
+
namespace. β That default is currently tenant #0's dataset repo (`OS_DATA_REPO`), so "the platform
|
| 31 |
+
store" and "tenant #0's repo" are the same bucket today. That is pre-existing (the control plane's
|
| 32 |
+
tenant records are already there) and it is a hosting fact, not a permission one β no tenant route
|
| 33 |
+
can read this key, because none of them names it.
|
| 34 |
+
"""
|
| 35 |
+
import time
|
| 36 |
+
|
| 37 |
+
from fastapi import APIRouter, Body, Depends
|
| 38 |
+
|
| 39 |
+
import core.platform_admin as platform_admin
|
| 40 |
+
import core.store as store
|
| 41 |
+
from deps import Session, err, require_session
|
| 42 |
+
|
| 43 |
+
router = APIRouter(prefix="/api/v1")
|
| 44 |
+
|
| 45 |
+
#: The platform-wide bucket. `{"rows": [ {id, tenant, user, category, text, ts} ]}` β newest LAST
|
| 46 |
+
#: in the store, newest FIRST on the wire.
|
| 47 |
+
STORE_KEY = "platform_feedback"
|
| 48 |
+
|
| 49 |
+
#: β THE CATEGORY VOCABULARY IS SERVER-OWNED AND SERVED (B's `ASK B-1 (3)`, agreed). A client
|
| 50 |
+
#: constant beside a server enum drifts, and the drift shows up as a dropdown offering a value the
|
| 51 |
+
#: door refuses. B renders exactly this list; the door accepts exactly these keys.
|
| 52 |
+
CATEGORIES = (
|
| 53 |
+
{"key": "bug", "label": "Something is broken"},
|
| 54 |
+
{"key": "idea", "label": "An idea or a request"},
|
| 55 |
+
{"key": "data", "label": "The numbers look wrong"},
|
| 56 |
+
{"key": "speed", "label": "Something is slow"},
|
| 57 |
+
{"key": "other", "label": "Something else"},
|
| 58 |
+
)
|
| 59 |
+
|
| 60 |
+
MAX_CHARS = 4000
|
| 61 |
+
|
| 62 |
+
#: A ceiling on the whole store. β REPORTED AT BOTH ENDS, never a silent drop: the submitter is
|
| 63 |
+
#: refused with the cause, and the operator's own payload says the store is full so they can act.
|
| 64 |
+
#: Dropping the OLDEST rows instead would delete the operator's earliest feedback to make room for
|
| 65 |
+
#: the newest, which is the one direction this store must never move in.
|
| 66 |
+
MAX_ROWS = 5000
|
| 67 |
+
|
| 68 |
+
|
| 69 |
+
def _rows():
|
| 70 |
+
try:
|
| 71 |
+
raw = store.get(STORE_KEY) or {}
|
| 72 |
+
except Exception:
|
| 73 |
+
return []
|
| 74 |
+
rows = raw.get("rows") if isinstance(raw, dict) else None
|
| 75 |
+
return [r for r in rows if isinstance(r, dict)] if isinstance(rows, list) else []
|
| 76 |
+
|
| 77 |
+
|
| 78 |
+
@router.get("/feedback/form")
|
| 79 |
+
def feedback_form(session: Session = Depends(require_session)):
|
| 80 |
+
"""What the composer renders. Any session β every account may send feedback.
|
| 81 |
+
|
| 82 |
+
β It deliberately returns NO submissions. R8 gives the tenant no read of what it sent, so a
|
| 83 |
+
"your feedback" list would be a second door to a thing the ruling closed. The 201 is the receipt.
|
| 84 |
+
"""
|
| 85 |
+
return {"categories": [dict(c) for c in CATEGORIES], "maxChars": MAX_CHARS}
|
| 86 |
+
|
| 87 |
+
|
| 88 |
+
@router.post("/feedback", status_code=201)
|
| 89 |
+
def submit_feedback(body: dict = Body(default=None),
|
| 90 |
+
session: Session = Depends(require_session)):
|
| 91 |
+
"""Send one piece of feedback to the operator plane. `{"category": key, "text": str}`.
|
| 92 |
+
|
| 93 |
+
β ANY authenticated session, deliberately β see the header. The provenance is stamped from the
|
| 94 |
+
VERIFIED session, never from the body.
|
| 95 |
+
"""
|
| 96 |
+
body = body if isinstance(body, dict) else {}
|
| 97 |
+
category = str(body.get("category") or "").strip()
|
| 98 |
+
text = str(body.get("text") or "").strip()
|
| 99 |
+
if category not in {c["key"] for c in CATEGORIES}:
|
| 100 |
+
# Named, and it names the fix: a client whose dropdown has drifted from this list is a
|
| 101 |
+
# client whose user is about to lose what they typed.
|
| 102 |
+
raise err(400, "unknown_category",
|
| 103 |
+
"that is not one of the feedback categories. Reload the page and try again")
|
| 104 |
+
if not text:
|
| 105 |
+
raise err(400, "bad_request", "type what you want to tell us")
|
| 106 |
+
if len(text) > MAX_CHARS:
|
| 107 |
+
raise err(400, "too_long",
|
| 108 |
+
f"feedback is limited to {MAX_CHARS:,} characters. Yours is {len(text):,}")
|
| 109 |
+
if not store.available():
|
| 110 |
+
raise err(503, "store_unavailable",
|
| 111 |
+
"feedback could not be sent right now. Nothing was saved.")
|
| 112 |
+
if len(_rows()) >= MAX_ROWS:
|
| 113 |
+
raise err(503, "feedback_full",
|
| 114 |
+
"the feedback store is full and we have been told. Nothing was saved, so please "
|
| 115 |
+
"send this again later")
|
| 116 |
+
row = {
|
| 117 |
+
# β EVERY ONE OF THESE FOUR IS SERVER-SIDE. A body-supplied tenant or user would let any
|
| 118 |
+
# account file words against somebody else's name in a store only the operator reads.
|
| 119 |
+
"tenant": str(session.tenant),
|
| 120 |
+
"user": str(session.uname),
|
| 121 |
+
"ts": int(time.time()),
|
| 122 |
+
"category": category,
|
| 123 |
+
"text": text,
|
| 124 |
+
}
|
| 125 |
+
row["id"] = f"fb_{row['ts']}_{abs(hash((row['tenant'], row['user'], text))) % 10**8:08d}"
|
| 126 |
+
|
| 127 |
+
def _up(data):
|
| 128 |
+
data = data if isinstance(data, dict) else {}
|
| 129 |
+
rows = data.get("rows")
|
| 130 |
+
data["rows"] = (rows if isinstance(rows, list) else []) + [row]
|
| 131 |
+
return data
|
| 132 |
+
|
| 133 |
+
try:
|
| 134 |
+
# `flush='sync'`: a person pressed Send and is being told it landed. The coalescing mode is
|
| 135 |
+
# for autosaves nobody is waiting on.
|
| 136 |
+
store.update(STORE_KEY, _up)
|
| 137 |
+
except Exception:
|
| 138 |
+
raise err(503, "store_unavailable",
|
| 139 |
+
"feedback could not be sent right now. Nothing was saved.")
|
| 140 |
+
return {"ok": True, "id": row["id"]}
|
| 141 |
+
|
| 142 |
+
|
| 143 |
+
@router.get("/feedback")
|
| 144 |
+
def list_feedback(tenant: str = "", session: Session = Depends(require_session)):
|
| 145 |
+
"""R8's operator read: every tenant's feedback, newest first. PLATFORM ADMIN ONLY.
|
| 146 |
+
|
| 147 |
+
β THE WALL IS `core.platform_admin.is_platform_admin`, IMPORTED AND CALLED β the double lock
|
| 148 |
+
(the record flag AND the `loopable` tenant), never re-expressed here. A tenant admin is not
|
| 149 |
+
admitted: `role: 'admin'` is one company's authority over its own workspace, and this is every
|
| 150 |
+
company's words in one list.
|
| 151 |
+
β `?tenant=` NARROWS an already-admitted operator's view. It is a convenience, not a wall, and
|
| 152 |
+
it is applied after the gate so it can never be the thing that admits anybody.
|
| 153 |
+
"""
|
| 154 |
+
if not platform_admin.is_platform_admin(session.user):
|
| 155 |
+
raise err(403, "forbidden", "this is a Loopable operator surface")
|
| 156 |
+
rows = _rows()
|
| 157 |
+
if tenant:
|
| 158 |
+
want = str(tenant).strip().lower()
|
| 159 |
+
rows = [r for r in rows if str(r.get("tenant") or "").lower() == want]
|
| 160 |
+
# β THE TIEBREAK IS THE STORE'S OWN ORDER, AND WITHOUT IT "NEWEST FIRST" IS FALSE FOR ANY TWO
|
| 161 |
+
# ROWS FILED IN THE SAME SECOND (wave-35 QA). `ts` is `int(time.time())` β SECOND resolution β
|
| 162 |
+
# and Python's sort is STABLE, so under `reverse=True` a tie keeps INSERTION order, which is
|
| 163 |
+
# oldest-first: the one direction this route promises never to return. It is not hypothetical
|
| 164 |
+
# and it is not a flake: `api_api`'s R8 row failed on it in the close-out battery, in the
|
| 165 |
+
# wave-35 QA battery and in a solo re-run, and the baseline recorded the true count anyway, so
|
| 166 |
+
# a REAL regression would have read as the known-flake line.
|
| 167 |
+
# β ENUMERATE OVER THE ALREADY-FILTERED LIST: `_rows()` appends, so a row's index IS its arrival
|
| 168 |
+
# order (the module docstring's "newest LAST in the store"), and `?tenant=` only drops rows, so
|
| 169 |
+
# the surviving indexes stay monotonic. Raising `ts` to sub-second resolution instead would
|
| 170 |
+
# break every id already minted as `fb_<ts>_β¦`.
|
| 171 |
+
rows = [r for _, r in sorted(enumerate(rows),
|
| 172 |
+
key=lambda p: (int(p[1].get("ts") or 0), p[0]), reverse=True)]
|
| 173 |
+
out = {"rows": [dict(r) for r in rows], "total": len(rows), "capacity": MAX_ROWS,
|
| 174 |
+
"tenants": sorted({str(r.get("tenant") or "") for r in _rows() if r.get("tenant")})}
|
| 175 |
+
if len(_rows()) >= MAX_ROWS:
|
| 176 |
+
# R6's second sentence, aimed at the person who can act: submissions are being REFUSED right
|
| 177 |
+
# now, and the operator is the only one who can see that from here.
|
| 178 |
+
out["note"] = ("the feedback store is at capacity, so new submissions are being refused. "
|
| 179 |
+
"Archive what you have read")
|
| 180 |
+
return out
|
api/routes_grid.py
CHANGED
|
@@ -726,6 +726,111 @@ def grid_calendar_metrics(body: dict = Body(default=None), scope: str = "custome
|
|
| 726 |
return out
|
| 727 |
|
| 728 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 729 |
@router.post("/grid/events")
|
| 730 |
def grid_events_route(body: dict = Body(default=None),
|
| 731 |
session: Session = Depends(require_session)):
|
|
@@ -822,13 +927,30 @@ def grid_events_route(body: dict = Body(default=None),
|
|
| 822 |
try:
|
| 823 |
for one in events:
|
| 824 |
eid = str(one.get("id") or "") if isinstance(one, dict) else ""
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 825 |
rerender = grid_events.handle_one(one, ctx)
|
| 826 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 827 |
except grid_events.StoreUnavailable:
|
| 828 |
raise err(503, "store_unavailable",
|
| 829 |
"the tenant store is unavailable β none of your changes were saved")
|
| 830 |
|
| 831 |
out = {"results": results, "rerender": any(r["rerender"] for r in results)}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 832 |
if ctx.out.doc is not None:
|
| 833 |
# β C4 / W30-T27 β `docPayload` IS THE NAME THE CLIENT ALREADY DECLARES. `types.ts` has
|
| 834 |
# carried `docPayload?: {pid, docId, name, mime, data_b64}` since C5, and `Documents.tsx`
|
|
|
|
| 726 |
return out
|
| 727 |
|
| 728 |
|
| 729 |
+
#: ββ THE BULK CELL DOOR'S OWN CEILING, and it is REPORTED rather than silently enforced. The
|
| 730 |
+
#: standing no-cap rule governs data read from a connected source; this is a WRITE of team-typed
|
| 731 |
+
#: values, so a bound is right β but R6's second sentence still binds, which is why exceeding it
|
| 732 |
+
#: is a 400 naming the number and the count, never a truncation.
|
| 733 |
+
#: Sized against the real job with headroom: the 2027 catalog is 1,397 rows.
|
| 734 |
+
MAX_BULK_ROWS = 10_000
|
| 735 |
+
|
| 736 |
+
|
| 737 |
+
@router.post("/grid/bulk-cells")
|
| 738 |
+
def bulk_cells(body: dict = Body(default=None),
|
| 739 |
+
session: Session = Depends(require_session)):
|
| 740 |
+
"""`{scopeKey, rows: {"<pid>": {key: value}}}` β shared cells on many rows, ONE transaction.
|
| 741 |
+
|
| 742 |
+
ββ WHY THIS EXISTS AT ALL, because "we already have `/grid/events`" is the obvious objection.
|
| 743 |
+
That door is capped at `_MAX_EVENTS = 24` (it is sized for the client's resend window), so a
|
| 744 |
+
1,397-row import is ~59 sequential POSTs against ONE JSON document β and this repo has a
|
| 745 |
+
MEASURED scar for exactly that: 18 writes against one document under the store's coalescing
|
| 746 |
+
single-flight landed **zero** while answering 200 eighteen times. Raising `_MAX_EVENTS` would
|
| 747 |
+
have widened the browser's own resend window to fix a script's problem. One door, one
|
| 748 |
+
transaction, is the honest shape.
|
| 749 |
+
|
| 750 |
+
β TENANT-WIDE KEYS ONLY, AND THAT IS THE POINT RATHER THAN A LIMITATION. It writes through
|
| 751 |
+
`shared_overlay`, which every account in the tenant reads. A per-user bulk write would be a
|
| 752 |
+
contradiction: nobody imports 1,397 rows of the team's work so that one account can see it β
|
| 753 |
+
that is precisely the failure owner ruling R6 was made to avoid. A key that is not declared
|
| 754 |
+
`shared: true` in the canonical contract is REFUSED BY NAME.
|
| 755 |
+
|
| 756 |
+
β ADMIN ONLY. This mutates data every account in the tenant reads, in bulk, in one call.
|
| 757 |
+
D-172 already records that the shared stratum has an asymmetric wall (anyone may create a
|
| 758 |
+
tenant-wide column, only the creator or an admin may delete one); a new door does not get to
|
| 759 |
+
inherit the loose half of an asymmetry somebody already flagged.
|
| 760 |
+
"""
|
| 761 |
+
import core.shared_overlay as shared_overlay
|
| 762 |
+
import modules.product_data as pd
|
| 763 |
+
import core.perm_scope as perm_scope
|
| 764 |
+
from routes_products import MODULE as PRODUCT_MODULE, scoped_pool
|
| 765 |
+
|
| 766 |
+
scope = _scope_or_400((body or {}).get("scopeKey"))
|
| 767 |
+
if scope != "product":
|
| 768 |
+
# Fail-closed with the reason: the shared stratum is a PRODUCT-topic mechanism today.
|
| 769 |
+
raise err(400, "scope_not_bulk_writable",
|
| 770 |
+
f"bulk cell writes are available on the product database; '{scope}' has no "
|
| 771 |
+
f"tenant-wide cell stratum")
|
| 772 |
+
session.require(PRODUCT_MODULE)
|
| 773 |
+
if not session.admin:
|
| 774 |
+
raise err(403, "admin_only",
|
| 775 |
+
"a bulk write changes values every account in this workspace reads")
|
| 776 |
+
|
| 777 |
+
rows = (body or {}).get("rows")
|
| 778 |
+
if not isinstance(rows, dict):
|
| 779 |
+
raise err(400, "bad_rows", "expected {rows: {\"<pid>\": {field: value}}}")
|
| 780 |
+
if len(rows) > MAX_BULK_ROWS:
|
| 781 |
+
raise err(400, "too_many_rows",
|
| 782 |
+
f"at most {MAX_BULK_ROWS} rows per request; this one carried {len(rows)}")
|
| 783 |
+
|
| 784 |
+
pids, _team, _src, fields_base = scoped_pool(session)
|
| 785 |
+
allowed = {int(p) for p in pids}
|
| 786 |
+
shared_keys = set(pd.SHARED_KEYS())
|
| 787 |
+
hidden = perm_scope.hidden_keys(session.user, PRODUCT_MODULE, fields_base)
|
| 788 |
+
|
| 789 |
+
clean, unknown_pid, refused_keys = {}, [], {}
|
| 790 |
+
for raw_pid, values in rows.items():
|
| 791 |
+
try:
|
| 792 |
+
pid = int(raw_pid)
|
| 793 |
+
except (TypeError, ValueError):
|
| 794 |
+
unknown_pid.append(str(raw_pid)[:40])
|
| 795 |
+
continue
|
| 796 |
+
# β THE POOL IS THE WALL. `scoped_pool` is the same predicate the read door uses, so a
|
| 797 |
+
# caller cannot write a row they could not see β including a row in another BU.
|
| 798 |
+
if pid not in allowed:
|
| 799 |
+
unknown_pid.append(str(raw_pid)[:40])
|
| 800 |
+
continue
|
| 801 |
+
keep = {}
|
| 802 |
+
for key, value in dict(values or {}).items():
|
| 803 |
+
key = str(key)
|
| 804 |
+
if key not in shared_keys:
|
| 805 |
+
refused_keys.setdefault("not_shared", set()).add(key)
|
| 806 |
+
continue
|
| 807 |
+
if key in hidden:
|
| 808 |
+
refused_keys.setdefault("hidden_by_permissions", set()).add(key)
|
| 809 |
+
continue
|
| 810 |
+
if not isinstance(value, (str, int, float)) or isinstance(value, bool):
|
| 811 |
+
refused_keys.setdefault("unsupported_value", set()).add(key)
|
| 812 |
+
continue
|
| 813 |
+
keep[key] = value
|
| 814 |
+
if keep:
|
| 815 |
+
clean[pid] = keep
|
| 816 |
+
|
| 817 |
+
written = shared_overlay.put_rows(pd.TABLE_KEY, clean, st=pd.TABLE_OPS.st) if clean else {}
|
| 818 |
+
out = {
|
| 819 |
+
"rows_written": len(written),
|
| 820 |
+
"cells_written": sum(len(v) for v in written.values()),
|
| 821 |
+
"rows_requested": len(rows),
|
| 822 |
+
}
|
| 823 |
+
# β R6's second sentence: what did NOT land, and why. A bulk door that reports only its
|
| 824 |
+
# successes is how 701 unmatched SKUs disappear quietly.
|
| 825 |
+
if unknown_pid:
|
| 826 |
+
out["rows_not_in_your_pool"] = {"count": len(unknown_pid),
|
| 827 |
+
"sample": sorted(unknown_pid)[:10]}
|
| 828 |
+
if refused_keys:
|
| 829 |
+
out["refused_fields"] = {reason: sorted(keys)
|
| 830 |
+
for reason, keys in refused_keys.items()}
|
| 831 |
+
return out
|
| 832 |
+
|
| 833 |
+
|
| 834 |
@router.post("/grid/events")
|
| 835 |
def grid_events_route(body: dict = Body(default=None),
|
| 836 |
session: Session = Depends(require_session)):
|
|
|
|
| 927 |
try:
|
| 928 |
for one in events:
|
| 929 |
eid = str(one.get("id") or "") if isinstance(one, dict) else ""
|
| 930 |
+
# ββ D-291 β WHICH event was refused, not merely THAT something was. The handler
|
| 931 |
+
# appends to a shared list, so the refusals belonging to THIS event are exactly the
|
| 932 |
+
# ones that appeared across THIS call. Reading the list once after the loop would
|
| 933 |
+
# answer "the batch was refused" and leave the caller to guess which member, which is
|
| 934 |
+
# the same class of unfalsifiable answer the channel exists to end.
|
| 935 |
+
_before = len(ctx.out.refusals)
|
| 936 |
rerender = grid_events.handle_one(one, ctx)
|
| 937 |
+
row = {"id": eid, "rerender": bool(rerender)}
|
| 938 |
+
mine = ctx.out.refusals[_before:]
|
| 939 |
+
if mine:
|
| 940 |
+
# `refused` is the SHAPE a caller branches on; the first reason is the one that
|
| 941 |
+
# stopped this write (a handler returns at its first refusal).
|
| 942 |
+
row["refused"] = mine[0]
|
| 943 |
+
results.append(row)
|
| 944 |
except grid_events.StoreUnavailable:
|
| 945 |
raise err(503, "store_unavailable",
|
| 946 |
"the tenant store is unavailable β none of your changes were saved")
|
| 947 |
|
| 948 |
out = {"results": results, "rerender": any(r["rerender"] for r in results)}
|
| 949 |
+
if ctx.out.refusals:
|
| 950 |
+
# β ALSO AT THE TOP LEVEL, because a batch that was wholly refused must not read as a
|
| 951 |
+
# batch that wholly landed. A caller that only checks the envelope still learns something
|
| 952 |
+
# is wrong, and a caller that walks `results` learns exactly which member.
|
| 953 |
+
out["refusals"] = list(ctx.out.refusals)
|
| 954 |
if ctx.out.doc is not None:
|
| 955 |
# β C4 / W30-T27 β `docPayload` IS THE NAME THE CLIENT ALREADY DECLARES. `types.ts` has
|
| 956 |
# carried `docPayload?: {pid, docId, name, mime, data_b64}` since C5, and `Documents.tsx`
|
api/routes_keychain.py
CHANGED
|
@@ -296,6 +296,114 @@ def _rel_reconnect(rt):
|
|
| 296 |
return True
|
| 297 |
|
| 298 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 299 |
def _own_row(session, entry_id):
|
| 300 |
"""The visible row for `entry_id`, or a 404. β A 404 rather than a 403 for an entry the
|
| 301 |
caller cannot see: telling a member that somebody else's personal credential EXISTS is the
|
|
@@ -703,6 +811,31 @@ def odoo_config_put(body: dict = Body(default=None),
|
|
| 703 |
if server_db:
|
| 704 |
notes.append(_rewrite_server_db(session, server_db))
|
| 705 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 706 |
out = odoo_config(session)
|
| 707 |
return {**out, "notes": [n for n in notes if n]}
|
| 708 |
|
|
@@ -783,6 +916,32 @@ def odoo_disconnect(session: Session = Depends(require_session)):
|
|
| 783 |
cur["frozenBy"] = str(session.uname)
|
| 784 |
return cur
|
| 785 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 786 |
# β THE FLAG FIRST, THE CREDENTIAL SECOND. If the flag write fails, nothing has happened and
|
| 787 |
# the connector is still live; if the delete failed AFTER the flag landed, the tenant is
|
| 788 |
# frozen with an unused key, which is recoverable from the Keychains pane. The reverse order
|
|
@@ -791,6 +950,19 @@ def odoo_disconnect(session: Session = Depends(require_session)):
|
|
| 791 |
session.runtime.update(rel.CONFIG_KEY, _up, flush="sync")
|
| 792 |
except Exception:
|
| 793 |
raise err(503, "store_unavailable", "nothing was disconnected β try again")
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 794 |
removed = ""
|
| 795 |
if entry is not None:
|
| 796 |
try:
|
|
@@ -801,10 +973,28 @@ def odoo_disconnect(session: Session = Depends(require_session)):
|
|
| 801 |
raise err(503, "store_unavailable",
|
| 802 |
"the databases are frozen but the stored credential was not removed β "
|
| 803 |
"delete it under Keychains")
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 804 |
return {"frozen": True, "removedEntry": removed,
|
| 805 |
-
|
| 806 |
-
|
| 807 |
-
|
|
|
|
|
|
|
| 808 |
|
| 809 |
|
| 810 |
@router.post("/admin/connectors/odoo/reconnect")
|
|
@@ -820,8 +1010,26 @@ def odoo_reconnect(session: Session = Depends(require_session)):
|
|
| 820 |
_rel_reconnect(session.runtime)
|
| 821 |
except Exception:
|
| 822 |
raise err(503, "store_unavailable", "the change was not saved β try again")
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 823 |
connected = bool(_odoo_entry(session)) or env_odoo_available(session.runtime)
|
| 824 |
-
return {"frozen": False, "connected": connected,
|
| 825 |
"note": ("Odoo is connected again and the databases you already had will refresh in "
|
| 826 |
"place." if connected else
|
| 827 |
"The freeze is lifted, but there is no Odoo credential yet β add one under "
|
|
|
|
| 296 |
return True
|
| 297 |
|
| 298 |
|
| 299 |
+
# ββββββββββββββββββββββββββββββββββββββββββββββββββ W35-T45 / R11: THE ENV -> KEYCHAIN MIGRATION
|
| 300 |
+
#
|
| 301 |
+
# R11: *"Tenant #0's Odoo credential MIGRATES onto the keychain, with the environment kept as
|
| 302 |
+
# fallback."* The owner chose this over a read-only display row WITH THE MIGRATION RISK STATED, so
|
| 303 |
+
# the risk is what this block is mostly about.
|
| 304 |
+
#
|
| 305 |
+
# β WHAT WAS ALREADY TRUE, CHECKED BEFORE ANY OF IT WAS WRITTEN: the keychain-first-then-env
|
| 306 |
+
# RESOLVER has existed since the 2026-08-04 cutover. `harness/runtime.py::odoo_source` is already
|
| 307 |
+
# (1) a keychain `odoo` entry, (2) tenant #0's compiled env connector, (3) None for anybody else,
|
| 308 |
+
# and `visible_entries` already serves a non-admin the row WITHOUT a preview. So R11 is not "build
|
| 309 |
+
# a resolver" β it is "give tenant #0 the ROW", which is the only reason its Keychain page looks
|
| 310 |
+
# empty while its Odoo grids work.
|
| 311 |
+
#
|
| 312 |
+
# ββ AND THE ONE REAL HAZARD IS NOT THE CREDENTIAL, IT IS THE PAUSE FLAG. `odoo_flag_key()` returns
|
| 313 |
+
# the first keychain `odoo` entry id when one exists and `ENV_ODOO_FLAG_KEY` ("odoo-env") otherwise β
|
| 314 |
+
# so CREATING THE ENTRY MOVES THE ADDRESS THE PAUSE FLAG LIVES AT. A tenant #0 that was paused under
|
| 315 |
+
# `odoo-env` would come back UNPAUSED, silently, at the first boot after this ships: the connector
|
| 316 |
+
# resumes pulling live Odoo because a migration changed which key the freeze was stored under. That
|
| 317 |
+
# is D-259's exact shape (a pause written under one key and read under another) and
|
| 318 |
+
# [[a-guard-bound-to-a-role-stops-guarding-when-the-role-moves]]. The flag is carried across in the
|
| 319 |
+
# SAME pass, and the carry is asserted.
|
| 320 |
+
|
| 321 |
+
|
| 322 |
+
def _env_odoo_fields():
|
| 323 |
+
"""The four env values `odoo_client` reads, or `(None, why)` when they are not all present.
|
| 324 |
+
|
| 325 |
+
β ALL FOUR OR NOTHING, and this completeness check is load-bearing rather than defensive.
|
| 326 |
+
Creating the entry makes `odoo_source` resolve through branch 1 INSTEAD of the env β so a
|
| 327 |
+
PARTIAL migration would hand the connector `{url, db}` and no key and take tenant #0's Odoo
|
| 328 |
+
offline, on a deployment where it had been working. The env fallback cannot save it, because the
|
| 329 |
+
entry's existence is what turns the fallback off.
|
| 330 |
+
β The names are `odoo_client.py`'s own (`ODOO_URL`/`ODOO_DB`/`ODOO_USER`/`ODOO_API_KEY`) and the
|
| 331 |
+
field names are `harness/connectors/odoo.py`'s stored shape (`{url, db, user, api_key}`). Two
|
| 332 |
+
vocabularies meet here; nowhere else.
|
| 333 |
+
"""
|
| 334 |
+
want = (("url", "ODOO_URL"), ("db", "ODOO_DB"),
|
| 335 |
+
("user", "ODOO_USER"), ("api_key", "ODOO_API_KEY"))
|
| 336 |
+
got = {field: (os.environ.get(env) or "").strip() for field, env in want}
|
| 337 |
+
missing = sorted(env for field, env in want if not got[field])
|
| 338 |
+
if missing:
|
| 339 |
+
return None, (f"the environment is missing {', '.join(missing)}, and a partial credential "
|
| 340 |
+
f"would take this tenant's Odoo offline rather than migrate it")
|
| 341 |
+
return got, ""
|
| 342 |
+
|
| 343 |
+
|
| 344 |
+
def migrate_env_odoo(rt):
|
| 345 |
+
"""R11 β put tenant #0's environment Odoo credential on its keychain, once. Returns a report.
|
| 346 |
+
|
| 347 |
+
`{"done": bool, "entry": id|"", "carried_pause": bool, "why": str}` β `why` is filled on every
|
| 348 |
+
path including the skips, because "already migrated", "no keychain key on this deployment" and
|
| 349 |
+
"the env is incomplete" are three different operator actions.
|
| 350 |
+
|
| 351 |
+
ββ IT MUST RUN IN THE CONTAINER, WHICH IS WHY `main.py` CALLS IT AND NO SCRIPT DOES. D-195,
|
| 352 |
+
measured three times: a developer's CLI write to the tenant store is reverted by the running
|
| 353 |
+
Space within a minute (download-modify-upload, last-write-wins) β and **the write reports success
|
| 354 |
+
every time**, then a fresh read confirms it, and it is gone by the next poll. A CLI migration here
|
| 355 |
+
would be a dry run that lies, and the thing it would lie about is a credential.
|
| 356 |
+
|
| 357 |
+
β FAIL-QUIET AND IDEMPOTENT. It runs on EVERY boot; the second one must be a no-op and a
|
| 358 |
+
third-party failure must not take the boot down.
|
| 359 |
+
"""
|
| 360 |
+
out = {"done": False, "entry": "", "carried_pause": False, "why": ""}
|
| 361 |
+
if not env_odoo_available(rt):
|
| 362 |
+
# Not tenant #0, or this deployment has no env Odoo at all. Both are normal states.
|
| 363 |
+
out["why"] = "this tenant has no environment Odoo credential to migrate"
|
| 364 |
+
return out
|
| 365 |
+
fields, why = _env_odoo_fields()
|
| 366 |
+
if not fields:
|
| 367 |
+
out["why"] = why
|
| 368 |
+
return out
|
| 369 |
+
# β READ THE PAUSE FLAG BEFORE THE WRITE. After the entry exists, `odoo_flag_key()` answers the
|
| 370 |
+
# NEW key and the old one is unreachable through the resolver β so the only moment this fact can
|
| 371 |
+
# be observed is now. [[undo-capture-before-the-write]] applied to a guard rather than to data.
|
| 372 |
+
try:
|
| 373 |
+
was_paused = bool(((rt.get(_CONNECTOR_FLAGS_KEY) or {})
|
| 374 |
+
.get(_ENV_ODOO_FLAG_KEY) or {}).get("paused"))
|
| 375 |
+
except Exception: # noqa: BLE001
|
| 376 |
+
was_paused = False
|
| 377 |
+
row, why = _kc().ensure_entry_of_type(
|
| 378 |
+
rt, "odoo", "Odoo (migrated from this deployment)", fields, "system")
|
| 379 |
+
if row is None:
|
| 380 |
+
out["why"] = why
|
| 381 |
+
return out
|
| 382 |
+
out["done"], out["entry"] = True, row["id"]
|
| 383 |
+
if was_paused:
|
| 384 |
+
# The freeze followed the credential. Without this the connector silently RESUMES pulling
|
| 385 |
+
# live Odoo at the first boot after the migration.
|
| 386 |
+
def _up(cur):
|
| 387 |
+
cur = cur if isinstance(cur, dict) else {}
|
| 388 |
+
entry = dict(cur.get(row["id"]) or {})
|
| 389 |
+
entry["paused"] = True
|
| 390 |
+
entry["pausedBy"] = "system"
|
| 391 |
+
entry["pausedNote"] = ("carried over from the environment source when the credential "
|
| 392 |
+
"was migrated onto the keychain")
|
| 393 |
+
cur[row["id"]] = entry
|
| 394 |
+
return cur
|
| 395 |
+
|
| 396 |
+
try:
|
| 397 |
+
rt.update(_CONNECTOR_FLAGS_KEY, _up, flush="sync")
|
| 398 |
+
out["carried_pause"] = True
|
| 399 |
+
except Exception as exc: # noqa: BLE001
|
| 400 |
+
# β SAID OUT LOUD. A migration that moved the credential and lost the freeze is worse
|
| 401 |
+
# than one that did not run, so this is the one failure that must never be silent.
|
| 402 |
+
out["why"] = (f"the credential migrated but the PAUSE could not be carried over "
|
| 403 |
+
f"({type(exc).__name__}), so this tenant's Odoo is no longer frozen")
|
| 404 |
+
return out
|
| 405 |
+
|
| 406 |
+
|
| 407 |
def _own_row(session, entry_id):
|
| 408 |
"""The visible row for `entry_id`, or a 404. β A 404 rather than a 403 for an entry the
|
| 409 |
caller cannot see: telling a member that somebody else's personal credential EXISTS is the
|
|
|
|
| 811 |
if server_db:
|
| 812 |
notes.append(_rewrite_server_db(session, server_db))
|
| 813 |
|
| 814 |
+
# ββ W33-T65 / W30-R6's SECOND SENTENCE β THE CADENCE IS SET AND ONLY PARTLY OBEYED, AND THE
|
| 815 |
+
# PERSON SETTING IT IS THE ONE WHO HAS TO BE TOLD. Measured, not guessed:
|
| 816 |
+
# Β· `main.py::_store_resync_loop` reads the interval from `sync_seconds(get_runtime(
|
| 817 |
+
# "royal-imports"))` β a HARDCODED slug β and then sleeps ONCE for the whole process. So
|
| 818 |
+
# for tenant #0 this control moves EVERYBODY's sync, and for every other tenant the value
|
| 819 |
+
# is stored, clamped, displayed and never read.
|
| 820 |
+
# Β· `manual` stores and reads back as `None`, and the loop has no branch on it: it sleeps a
|
| 821 |
+
# default 1800 s and syncs anyway. "Only when I ask" asks all the same.
|
| 822 |
+
# β NEITHER IS FIXABLE FROM THIS FILE β the loop lives in `main.py`, which this lane does not
|
| 823 |
+
# own β and shipping a setting that silently does nothing is the exact failure R6 names. So it
|
| 824 |
+
# is REPORTED here, at the moment of the change, with what it really controls. Delete these
|
| 825 |
+
# notes when the loop becomes per-tenant, not before.
|
| 826 |
+
if clean_every is not None:
|
| 827 |
+
if not rel.is_royal(session.tenant):
|
| 828 |
+
notes.append("this interval is saved, but the sync loop currently reads its schedule "
|
| 829 |
+
"from one workspace for the whole deployment β so it will not change how "
|
| 830 |
+
"often YOUR data refreshes until per-workspace scheduling ships")
|
| 831 |
+
else:
|
| 832 |
+
notes.append("this interval is saved and it is the one the deployment's sync loop "
|
| 833 |
+
"uses β it changes the refresh rate for every workspace on this "
|
| 834 |
+
"deployment, not only this one")
|
| 835 |
+
if clean_every == "manual":
|
| 836 |
+
notes.append("β 'manual' does not yet stop the background sync: the loop has no "
|
| 837 |
+
"manual-only branch, so data still refreshes on the default interval")
|
| 838 |
+
|
| 839 |
out = odoo_config(session)
|
| 840 |
return {**out, "notes": [n for n in notes if n]}
|
| 841 |
|
|
|
|
| 916 |
cur["frozenBy"] = str(session.uname)
|
| 917 |
return cur
|
| 918 |
|
| 919 |
+
# ββ W33-T65 β THE FREEZE HAD A HOLE, AND THE NOTE BELOW WAS THE THING THAT MADE IT A DEFECT
|
| 920 |
+
# RATHER THAN A LIMIT. `rel.frozen` has exactly ONE consumer, `odoo_relational.refresh`, which
|
| 921 |
+
# materialises the EIGHT copied grids. The other two (`ut_odoo_order_lines`,
|
| 922 |
+
# `ut_odoo_gl_lines` β `READ_THROUGH_KEYS`) do not go through `refresh` at all: they read
|
| 923 |
+
# THROUGH the per-tenant DuckDB mirror, and the mirror is advanced by `datastore.sync_all`,
|
| 924 |
+
# which gates on the connector PAUSE flag and has never heard of `frozen`. So a disconnected
|
| 925 |
+
# workspace kept serving LIVE, still-moving rows in its two biggest grids while this route's
|
| 926 |
+
# own sentence promised *"nothing is being refreshed"*.
|
| 927 |
+
#
|
| 928 |
+
# β THE FIX IS TO MAKE THE SENTENCE TRUE, not to soften it. Disconnect now flips the pause
|
| 929 |
+
# flag on the RESOLVED source as well, which is the switch `sync_all` and `reconcile_deletes`
|
| 930 |
+
# actually read β so both halves of "frozen" mean the same thing. Two orderings are borrowed
|
| 931 |
+
# from `pause_connector` because it learned them the hard way:
|
| 932 |
+
# Β· the flag key is resolved BEFORE the credential is deleted β after the delete there is no
|
| 933 |
+
# resolved source left to name, and the flag would land under a key nothing reads (D-10).
|
| 934 |
+
# Β· the snapshot is captured BEFORE the flag flips, so there is a last-successful-sync to
|
| 935 |
+
# serve; a failed capture leaves the connector live rather than paused-with-nothing.
|
| 936 |
+
_, flag_key = _resolved_odoo_key(session.runtime)
|
| 937 |
+
snapshots = 0
|
| 938 |
+
if flag_key:
|
| 939 |
+
try:
|
| 940 |
+
snapshots = save_pool_snapshots(session.runtime, taken_by=session.uname)
|
| 941 |
+
except Exception: # noqa: BLE001
|
| 942 |
+
# A snapshot is a nicety; the freeze is the promise. Reported, never fatal.
|
| 943 |
+
snapshots = 0
|
| 944 |
+
|
| 945 |
# β THE FLAG FIRST, THE CREDENTIAL SECOND. If the flag write fails, nothing has happened and
|
| 946 |
# the connector is still live; if the delete failed AFTER the flag landed, the tenant is
|
| 947 |
# frozen with an unused key, which is recoverable from the Keychains pane. The reverse order
|
|
|
|
| 950 |
session.runtime.update(rel.CONFIG_KEY, _up, flush="sync")
|
| 951 |
except Exception:
|
| 952 |
raise err(503, "store_unavailable", "nothing was disconnected β try again")
|
| 953 |
+
|
| 954 |
+
paused_mirror = False
|
| 955 |
+
if flag_key:
|
| 956 |
+
def _pause(cur):
|
| 957 |
+
cur = cur if isinstance(cur, dict) else {}
|
| 958 |
+
cur[str(flag_key)] = {"paused": True}
|
| 959 |
+
return cur
|
| 960 |
+
try:
|
| 961 |
+
session.runtime.update(_CONNECTOR_FLAGS_KEY, _pause, flush="sync")
|
| 962 |
+
paused_mirror = True
|
| 963 |
+
except Exception: # noqa: BLE001
|
| 964 |
+
paused_mirror = False
|
| 965 |
+
|
| 966 |
removed = ""
|
| 967 |
if entry is not None:
|
| 968 |
try:
|
|
|
|
| 973 |
raise err(503, "store_unavailable",
|
| 974 |
"the databases are frozen but the stored credential was not removed β "
|
| 975 |
"delete it under Keychains")
|
| 976 |
+
|
| 977 |
+
# β THE SENTENCE IS COMPOSED, NOT CONSTANT, because the two sources genuinely differ and the
|
| 978 |
+
# old fixed string was wrong about one of them. A tenant whose Odoo came from the DEPLOYMENT
|
| 979 |
+
# ENVIRONMENT has no credential for this route to remove β `.env` is the container's, not a
|
| 980 |
+
# tenant screen's β so it said "the key back" about a key it never held. R6's second sentence:
|
| 981 |
+
# the limit that cannot be removed is REPORTED, with what to do instead.
|
| 982 |
+
note = ("Your Odoo databases are frozen: every row and every column you had is still there and "
|
| 983 |
+
"still readable, and nothing is being refreshed.")
|
| 984 |
+
if not paused_mirror and flag_key:
|
| 985 |
+
note += (" β The live mirror could not be paused, so the two read-through databases "
|
| 986 |
+
"(order lines and GL lines) may keep advancing β pause the Odoo connector under "
|
| 987 |
+
"Keychains to stop them.")
|
| 988 |
+
note += (" Reconnecting adds the key back and resumes into the same databases." if entry
|
| 989 |
+
else " This workspace's Odoo credential comes from the deployment environment, so "
|
| 990 |
+
"there was no stored key to remove β the databases are frozen and Reconnect "
|
| 991 |
+
"resumes them into the same tables.")
|
| 992 |
return {"frozen": True, "removedEntry": removed,
|
| 993 |
+
# β ON THE WIRE, so the client and a gate can both see which half happened. A boolean
|
| 994 |
+
# nobody returns is a guarantee nobody can check.
|
| 995 |
+
"pausedMirror": paused_mirror, "snapshots": snapshots,
|
| 996 |
+
"source": "keychain" if entry else "env",
|
| 997 |
+
"note": note}
|
| 998 |
|
| 999 |
|
| 1000 |
@router.post("/admin/connectors/odoo/reconnect")
|
|
|
|
| 1010 |
_rel_reconnect(session.runtime)
|
| 1011 |
except Exception:
|
| 1012 |
raise err(503, "store_unavailable", "the change was not saved β try again")
|
| 1013 |
+
# ββ W33-T65 β AND THE PAUSE DISCONNECT SET, or the freeze would be one-way. Clearing only
|
| 1014 |
+
# `frozen` restores the eight materialised grids and leaves the mirror pinned forever, so the
|
| 1015 |
+
# two read-through grids would sit at the disconnect date while the panel said "connected
|
| 1016 |
+
# again" β the same disagreement between the halves of "frozen", pointing the other way.
|
| 1017 |
+
# β Resolved AFTER `_rel_reconnect`: a tenant reconnects by adding the key back FIRST, so the
|
| 1018 |
+
# resolved source only exists again by this point.
|
| 1019 |
+
_, flag_key = _resolved_odoo_key(session.runtime)
|
| 1020 |
+
resumed = False
|
| 1021 |
+
if flag_key:
|
| 1022 |
+
def _unpause(cur):
|
| 1023 |
+
cur = cur if isinstance(cur, dict) else {}
|
| 1024 |
+
cur[str(flag_key)] = {"paused": False}
|
| 1025 |
+
return cur
|
| 1026 |
+
try:
|
| 1027 |
+
session.runtime.update(_CONNECTOR_FLAGS_KEY, _unpause, flush="sync")
|
| 1028 |
+
resumed = True
|
| 1029 |
+
except Exception: # noqa: BLE001
|
| 1030 |
+
resumed = False
|
| 1031 |
connected = bool(_odoo_entry(session)) or env_odoo_available(session.runtime)
|
| 1032 |
+
return {"frozen": False, "connected": connected, "resumedMirror": resumed,
|
| 1033 |
"note": ("Odoo is connected again and the databases you already had will refresh in "
|
| 1034 |
"place." if connected else
|
| 1035 |
"The freeze is lifted, but there is no Odoo credential yet β add one under "
|
api/routes_nav.py
CHANGED
|
@@ -248,6 +248,183 @@ def _read_recents(runtime, uname, allowed):
|
|
| 248 |
return out[:_MAX_RECENTS]
|
| 249 |
|
| 250 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 251 |
@router.get("/nav")
|
| 252 |
def nav(session: Session = Depends(require_session)):
|
| 253 |
"""`{pages: [{key,label,source?,chrome}], landing}`.
|
|
@@ -336,7 +513,7 @@ def nav(session: Session = Depends(require_session)):
|
|
| 336 |
# empty rather than leaving 200-[] ambiguous.
|
| 337 |
return {"pages": [], "landing": None, "empty": "no_databases"}
|
| 338 |
raise err(403, "no_surfaces",
|
| 339 |
-
"your account has no dashboards assigned
|
| 340 |
# WAVE 19 (R8 / C1): the tenant's name + icon overrides, merged LAST β after the registry
|
| 341 |
# rows, after the tenant module filter, after the user tables. Merged HERE rather than
|
| 342 |
# applied by the client for one reason: `label` is what every reader of this payload shows,
|
|
@@ -350,6 +527,21 @@ def nav(session: Session = Depends(require_session)):
|
|
| 350 |
# leak with no symptom until two tenants rename the same registry key. Copy the rows before
|
| 351 |
# merging on the day that invariant changes.
|
| 352 |
meta = _read_nav_meta(session.runtime)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 353 |
# Wave 21 (C3): the definitions, once β `manage`/`canDelete` below answer from `createdBy`.
|
| 354 |
# WAVE 27 (C9): `locked` answers from `recordMode`, off the same one read.
|
| 355 |
# β W31-T10: that read is now the SAME one the merge above did β it used to be a second,
|
|
@@ -398,6 +590,13 @@ def nav(session: Session = Depends(require_session)):
|
|
| 398 |
p["locked"] = True
|
| 399 |
elif session.admin:
|
| 400 |
p["manage"] = True
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 401 |
entry = meta.get(p.get("key")) if meta else None
|
| 402 |
if not entry:
|
| 403 |
continue
|
|
@@ -422,8 +621,11 @@ def nav(session: Session = Depends(require_session)):
|
|
| 422 |
# both doors finally agree on what a placeable key is. This block keeps using the assembled
|
| 423 |
# list because it already holds it: re-enumerating here would be a second store read for an
|
| 424 |
# answer sitting in a local variable.
|
| 425 |
-
|
| 426 |
-
|
|
|
|
|
|
|
|
|
|
| 427 |
# β W31-T11 β TWO KINDS OF ABSENCE, NAMED SEPARATELY, and both keys are ALWAYS PRESENT.
|
| 428 |
# `omitted` β this workspace's catalogue does not include these modules. Deliberate.
|
| 429 |
# `degraded` β a part of this payload could not be read. NOT deliberate, and the shell says
|
|
@@ -460,7 +662,7 @@ def nav_opened(body: dict = Body(default=None),
|
|
| 460 |
raise err(400, "bad_request", "no page was named")
|
| 461 |
if not session.runtime.available():
|
| 462 |
raise err(503, "store_unavailable",
|
| 463 |
-
"the tenant store is unavailable
|
| 464 |
stamp, uname = _now(), session.uname
|
| 465 |
|
| 466 |
def _up(data):
|
|
@@ -484,7 +686,7 @@ def nav_opened(body: dict = Body(default=None),
|
|
| 484 |
session.runtime.update(_NAV_RECENTS_KEY, _up, flush='async')
|
| 485 |
except Exception:
|
| 486 |
raise err(503, "store_unavailable",
|
| 487 |
-
"the tenant store refused the write
|
| 488 |
return {"key": key, "at": stamp}
|
| 489 |
|
| 490 |
|
|
@@ -549,7 +751,7 @@ def save_nav_meta(body: dict = Body(default=None),
|
|
| 549 |
if "name" in body:
|
| 550 |
if not key.startswith("ut_"):
|
| 551 |
raise err(400, "name_not_allowed",
|
| 552 |
-
"only a database you created can be renamed
|
| 553 |
"from the module registry")
|
| 554 |
name = " ".join(str(body.get("name") or "").split())[:_MAX_NAV_NAME]
|
| 555 |
if not name:
|
|
@@ -560,7 +762,7 @@ def save_nav_meta(body: dict = Body(default=None),
|
|
| 560 |
|
| 561 |
if not session.runtime.available():
|
| 562 |
raise err(503, "store_unavailable",
|
| 563 |
-
"the tenant store is unavailable
|
| 564 |
|
| 565 |
def _up(data):
|
| 566 |
data = data if isinstance(data, dict) else {}
|
|
@@ -583,7 +785,7 @@ def save_nav_meta(body: dict = Body(default=None),
|
|
| 583 |
session.runtime.update(_NAV_META_KEY, _up)
|
| 584 |
except Exception:
|
| 585 |
raise err(503, "store_unavailable",
|
| 586 |
-
"the change was not saved
|
| 587 |
return {"key": key, "meta": _read_nav_meta(session.runtime).get(key, {})}
|
| 588 |
|
| 589 |
|
|
@@ -608,7 +810,7 @@ def save_nav_prefs(body: dict = Body(default=None),
|
|
| 608 |
clean = _clean_nav_prefs(body or {}, keys, keep_unknown_ut=not enumerated)
|
| 609 |
if not session.runtime.available():
|
| 610 |
raise err(503, "store_unavailable",
|
| 611 |
-
"the tenant store is unavailable
|
| 612 |
|
| 613 |
def _up(data):
|
| 614 |
data = data if isinstance(data, dict) else {}
|
|
@@ -622,7 +824,7 @@ def save_nav_prefs(body: dict = Body(default=None),
|
|
| 622 |
session.runtime.update(_NAV_PREFS_KEY, _up)
|
| 623 |
except Exception:
|
| 624 |
raise err(503, "store_unavailable",
|
| 625 |
-
"the folder change was not saved
|
| 626 |
return {"prefs": clean}
|
| 627 |
|
| 628 |
|
|
|
|
| 248 |
return out[:_MAX_RECENTS]
|
| 249 |
|
| 250 |
|
| 251 |
+
# ββ VIEW READERS β shared with `routes_starred` (W35-T39/T42) ββββββββββββββββββββββββββββββββ
|
| 252 |
+
#
|
| 253 |
+
# ββ W35-T43 (rulings R4/R7) β THE "MARK IMPORTANT" COUNTS ARE GONE FROM THIS ROUTE, and the
|
| 254 |
+
# block that computed them (`_important_counts`) went with them. It read one store bucket PER
|
| 255 |
+
# DATABASE on the route D-175 spent a whole wave reducing to a single read: MEASURED on a 13-database
|
| 256 |
+
# fixture, `GET /nav` performed **14 per-database view-bucket reads** and stamped `important` on
|
| 257 |
+
# **14** pages. It is **0 and 0** now.
|
| 258 |
+
#
|
| 259 |
+
# Those reads were bounded by a 2.5 s wall clock (`_IMPORTANT_BUDGET_S`) whose own note conceded the
|
| 260 |
+
# cost: twelve buckets are 6.2 ms WARM and **7,331 ms COLD**, so the budget existed to stop a cold
|
| 261 |
+
# container converting a slow success into a manufactured failure against `nav.ts`'s 20 s deadline.
|
| 262 |
+
# A budget that can be exhausted is a number that can be silently short, which is why it also had to
|
| 263 |
+
# publish a `degraded` entry. R7 removes the whole apparatus by moving the question to
|
| 264 |
+
# `GET /starred/counts`, called AFTER the page paints β where a slow answer costs a late badge
|
| 265 |
+
# instead of a late rail. Closes D-288 and D-289.
|
| 266 |
+
#
|
| 267 |
+
# β WHAT SURVIVES AND WHY: `_visible_views`, `_view_record_count` and `_granted_view_ids` are the
|
| 268 |
+
# READERS, and `routes_starred` calls all three. They were never the cost β the per-database store
|
| 269 |
+
# read was β and duplicating them into the new route would have put two answers behind one badge.
|
| 270 |
+
|
| 271 |
+
#: Suffix `core.view_templates.workspace_key` appends. Stripping it is how a page key becomes the
|
| 272 |
+
#: TOPIC key the cohort bucket is named from β `customer_data` -> `customer_table_workspace` ->
|
| 273 |
+
#: `customer` -> `customer_cohorts`. Derived rather than re-listed on purpose: `_WS_KEYS` is
|
| 274 |
+
#: already the one place `customer_data`/`product_data` are mapped to their topic, and a second
|
| 275 |
+
#: copy here would be free to drift from it ([[one-question-two-normalizers]]).
|
| 276 |
+
_WS_SUFFIX = "_table_workspace"
|
| 277 |
+
|
| 278 |
+
|
| 279 |
+
def _visible_views(doc, uname, is_admin, granted_ids):
|
| 280 |
+
"""Every view on ONE database that THIS caller can see, from an already-read workspace doc.
|
| 281 |
+
|
| 282 |
+
β PER-CALLER, NOT TENANT-WIDE, and this is the half a server-side count is most likely to get
|
| 283 |
+
wrong. `<key>_table_workspace` is `{username: {views, fields, overlays}, '__shared__': {...}}`
|
| 284 |
+
β one home per view, never both β so "how many views are marked important here" has a
|
| 285 |
+
DIFFERENT answer for every account. Measured on tenant #0: `leadership` has one marked view and
|
| 286 |
+
`admin` has none, on the same database. A tenant-wide count would put a number in the owner's
|
| 287 |
+
rail that no view sidebar they can open would ever add up to.
|
| 288 |
+
|
| 289 |
+
β `table_store._may_see` is imported rather than re-expressed. It is private, and reaching for
|
| 290 |
+
it is still the right call: the alternative is `TableOps.shared_views`, which re-reads the whole
|
| 291 |
+
bucket per database (the N whole reads this block exists to avoid), and the only other option is
|
| 292 |
+
a second copy of a permission predicate. A wrong copy of `_may_see` widens what a user is told
|
| 293 |
+
exists; a private import cannot.
|
| 294 |
+
"""
|
| 295 |
+
import core.table_store as table_store
|
| 296 |
+
out = {}
|
| 297 |
+
for vid, view in ((doc.get(uname) or {}).get("views") or {}).items():
|
| 298 |
+
if isinstance(view, dict):
|
| 299 |
+
out[str(vid)] = view
|
| 300 |
+
for vid, view in ((doc.get(table_store.SHARED_KEY) or {}).get("views") or {}).items():
|
| 301 |
+
if isinstance(view, dict) and table_store._may_see(view, uname, is_admin):
|
| 302 |
+
out.setdefault(str(vid), view)
|
| 303 |
+
# The wave-21 named-user grants. The ids come from ONE tenant-wide bucket read once for the
|
| 304 |
+
# whole request; the RECORD is already in hand, in whichever stratum its owner keeps it.
|
| 305 |
+
if granted_ids:
|
| 306 |
+
for stratum, blob in doc.items():
|
| 307 |
+
if stratum == uname or not isinstance(blob, dict):
|
| 308 |
+
continue
|
| 309 |
+
for vid, view in (blob.get("views") or {}).items():
|
| 310 |
+
if str(vid) in granted_ids and isinstance(view, dict):
|
| 311 |
+
out.setdefault(str(vid), view)
|
| 312 |
+
return out
|
| 313 |
+
|
| 314 |
+
|
| 315 |
+
def _view_record_count(cfg, cohorts):
|
| 316 |
+
"""How many RECORDS this view resolves to, or None when that cannot be answered for free.
|
| 317 |
+
|
| 318 |
+
β `None` IS AN ANSWER AND IT IS THE IMPORTANT ONE. Two of the three shapes below are exact
|
| 319 |
+
because the view CARRIES its row set; the third β an ordinary filtered view β can only be
|
| 320 |
+
counted by running its filters over the records, and the records are the one thing this route
|
| 321 |
+
must never read (`D-175`/`D-185`: `/nav` is a rows-free projection, and reaching for `rows`
|
| 322 |
+
here raises by that projection's own contract). So a filtered view is reported as UNCOUNTED and
|
| 323 |
+
the database's `partial` flag says so, which is the whole of R6's second sentence applied to a
|
| 324 |
+
badge: a limit that cannot be removed is REPORTED with its cause, never papered over with a
|
| 325 |
+
number that is short by an unknown amount.
|
| 326 |
+
|
| 327 |
+
β THIS IS ALSO WHY THE SERVER DOES NOT SIMPLY MIRROR THE CLIENT. `CustomerGrid::alertCounts`
|
| 328 |
+
counts a filtered view fine and gives up on a SERVER-WINDOWED one (`D-205`'s `Important 0+`);
|
| 329 |
+
this end is the exact inverse β it has no rows at all and no window either. The two are honest
|
| 330 |
+
about different halves, which is why `partial` had to be on the wire rather than derived.
|
| 331 |
+
"""
|
| 332 |
+
if not isinstance(cfg, dict):
|
| 333 |
+
return None
|
| 334 |
+
# A cohort-locked view IS its cohort: the lock and the id are the same fact (`grid_events`
|
| 335 |
+
# re-stamps it on every write), and a cohort's membership is a stored pid LIST, not a query.
|
| 336 |
+
lock = str(cfg.get("cohortLock") or "").strip()
|
| 337 |
+
if lock:
|
| 338 |
+
n = cohorts.get(lock)
|
| 339 |
+
return int(n) if isinstance(n, int) else None
|
| 340 |
+
# A curated row set carries its own count.
|
| 341 |
+
pids = cfg.get("memberPids")
|
| 342 |
+
if isinstance(pids, list) and pids:
|
| 343 |
+
return len(pids)
|
| 344 |
+
return None
|
| 345 |
+
|
| 346 |
+
|
| 347 |
+
def _visible_database_keys(session):
|
| 348 |
+
"""`(keys, enumerated)` β every DATABASE this session may open that HAS a view bucket.
|
| 349 |
+
|
| 350 |
+
β ADDED BY W35-T39 because neither existing enumeration in this file answers this question:
|
| 351 |
+
|
| 352 |
+
Β· `_placeable_top_keys` applies the ACCOUNT grant and `may_open`, and **not the TENANT
|
| 353 |
+
CATALOGUE** β correctly, because a folder placement is cosmetic and pruning one is loss.
|
| 354 |
+
A star scan cannot borrow that: it would open the view bucket of a database this workspace's
|
| 355 |
+
catalogue does not include. `nav()` applies the catalogue filter; that helper never has.
|
| 356 |
+
Β· `nav()`'s own `_page_keys` is assembled from the page DICTS it is building for the wire, so
|
| 357 |
+
it cannot be reached from another route without rebuilding the payload.
|
| 358 |
+
|
| 359 |
+
So this is the KEY-SET question on its own, with the same three walls `nav()` applies in the same
|
| 360 |
+
order: the account grant (`perms.nav_pages`), the TENANT catalogue, and `may_open` for the
|
| 361 |
+
tenant's own databases. `view_templates.workspace_key` is the last filter and it is what makes
|
| 362 |
+
the answer honest for a caller about to read a view bucket: a module surface with no workspace
|
| 363 |
+
(`sales`, `ar`) is not a database and has no views to star.
|
| 364 |
+
|
| 365 |
+
β THE `parent` CLAUSE BELOW IS A NO-OP TODAY AND IS KEPT ONLY TO MIRROR `nav()`. `perms.nav_pages`
|
| 366 |
+
excludes `group_only` rows and therefore **emits no `parent` at all** (its own docstring says so:
|
| 367 |
+
a dangling reference would be worse than a flat list), so `customer_data` arrives here FLAT even
|
| 368 |
+
though the registry gives it `parent: 'customers'`. Stated because the opposite is the obvious
|
| 369 |
+
reading β this ticket's first draft assumed the clause was excluding children and wrote a
|
| 370 |
+
docstring around a defect that does not exist.
|
| 371 |
+
|
| 372 |
+
β `enumerated` is False when the `ut_` listing raised β the caller must not treat the set as
|
| 373 |
+
authoritative for `ut_` keys, exactly as `_placeable_top_keys` requires.
|
| 374 |
+
"""
|
| 375 |
+
import core.view_templates as view_templates
|
| 376 |
+
keys, enumerated = set(), True
|
| 377 |
+
tcfg = getattr(session.runtime.tenant, "config", None) or {}
|
| 378 |
+
tmods = tcfg.get("modules", "all")
|
| 379 |
+
allowed = None if tmods == "all" else {str(k) for k in (tmods or [])}
|
| 380 |
+
for p in (perms.nav_pages(session.user) or []):
|
| 381 |
+
key = str(p.get("key") or "")
|
| 382 |
+
if allowed is not None and key not in allowed \
|
| 383 |
+
and str(p.get("parent") or "") not in allowed:
|
| 384 |
+
continue
|
| 385 |
+
if view_templates.workspace_key(key):
|
| 386 |
+
keys.add(key)
|
| 387 |
+
try:
|
| 388 |
+
import core.user_tables as user_tables
|
| 389 |
+
# The SAME `may_open`-filtered listing `nav()` renders from, over the ROWS-FREE projection
|
| 390 |
+
# (W32-T02) β so this costs ~0.1% of the document rather than a 28.6 MB deep copy.
|
| 391 |
+
for e in user_tables.nav_entries(viewer=session.uname, is_admin=session.admin,
|
| 392 |
+
st=session.runtime):
|
| 393 |
+
k = str(e.get("key") or "")
|
| 394 |
+
if k:
|
| 395 |
+
keys.add(k)
|
| 396 |
+
except Exception:
|
| 397 |
+
enumerated = False
|
| 398 |
+
return keys, enumerated
|
| 399 |
+
|
| 400 |
+
|
| 401 |
+
def _granted_view_ids(session):
|
| 402 |
+
"""Every view id a wave-21 NAMED-USER GRANT lets this caller see. Fail-closed to `set()`.
|
| 403 |
+
|
| 404 |
+
β EXTRACTED (W35-T39) SO THE STAR AND THE COUNT SHARE ONE ANSWER. `_visible_views` above
|
| 405 |
+
takes this set as its third stratum, and it had exactly one caller (`_important_counts`) with
|
| 406 |
+
the derivation inline β which W35-T43 deletes. `routes_starred` needs the identical set to
|
| 407 |
+
answer "which views has this person starred", so the derivation moves here beside the reader
|
| 408 |
+
it feeds rather than being copied into a second file ([[one-evaluator-per-question]]).
|
| 409 |
+
|
| 410 |
+
β THE ROLE FILTER IS NOT BELT-AND-BRACES. `shared_with` answers "is there an entry naming
|
| 411 |
+
me", and `grid_events._granted_views` β the reader whose answer any consumer of this has to
|
| 412 |
+
agree with β then requires `role_for(...) in ('view','edit')`. Dropping that second test
|
| 413 |
+
would admit a view the sidebar does not list. One tenant-wide bucket, read once per call, so
|
| 414 |
+
it costs a dict lookup per id.
|
| 415 |
+
β Fail-closed: no grants is a NARROWER answer, never a wider one.
|
| 416 |
+
"""
|
| 417 |
+
import core.shares as shares
|
| 418 |
+
try:
|
| 419 |
+
return {str(v) for v in
|
| 420 |
+
((shares.shared_with(session.uname, kind="view", st=session.runtime) or {})
|
| 421 |
+
.get("view") or [])
|
| 422 |
+
if shares.role_for("view", str(v), session.uname,
|
| 423 |
+
st=session.runtime) in ("view", "edit")}
|
| 424 |
+
except Exception:
|
| 425 |
+
return set()
|
| 426 |
+
|
| 427 |
+
|
| 428 |
@router.get("/nav")
|
| 429 |
def nav(session: Session = Depends(require_session)):
|
| 430 |
"""`{pages: [{key,label,source?,chrome}], landing}`.
|
|
|
|
| 513 |
# empty rather than leaving 200-[] ambiguous.
|
| 514 |
return {"pages": [], "landing": None, "empty": "no_databases"}
|
| 515 |
raise err(403, "no_surfaces",
|
| 516 |
+
"your account has no dashboards assigned. Ask an administrator.")
|
| 517 |
# WAVE 19 (R8 / C1): the tenant's name + icon overrides, merged LAST β after the registry
|
| 518 |
# rows, after the tenant module filter, after the user tables. Merged HERE rather than
|
| 519 |
# applied by the client for one reason: `label` is what every reader of this payload shows,
|
|
|
|
| 527 |
# leak with no symptom until two tenants rename the same registry key. Copy the rows before
|
| 528 |
# merging on the day that invariant changes.
|
| 529 |
meta = _read_nav_meta(session.runtime)
|
| 530 |
+
# ββ W35-T43 (rulings R4/R7) β THE MARK-IMPORTANT COUNTS ARE NO LONGER COMPUTED HERE.
|
| 531 |
+
#
|
| 532 |
+
# W34-T10 put them on this payload with a 2.5 s budget and a `degraded` entry, spent in RECENTS
|
| 533 |
+
# ORDER so a cold container would reach the databases somebody actually works in first. Every
|
| 534 |
+
# one of those was a correct answer to the wrong question: the block was `N` per-database store
|
| 535 |
+
# reads on the route D-175 spent a wave reducing to ONE, and no ordering makes an N-read block
|
| 536 |
+
# free. MEASURED on a 13-database fixture: **14 view-bucket reads and 14 `important` stamps per
|
| 537 |
+
# `/nav`** before this ticket, **0 and 0** after.
|
| 538 |
+
#
|
| 539 |
+
# R7 moves the question to `GET /starred/counts`, called AFTER the page paints. A slow answer
|
| 540 |
+
# there is a late badge; a slow answer here was a late RAIL. Closes D-288 and D-289.
|
| 541 |
+
# β `recents` STAYS and is still ONE read β it is the Home landing's own payload (C10/R7 of wave
|
| 542 |
+
# 23), and it was only computed this early so the deleted budget could spend itself in its order.
|
| 543 |
+
_page_keys = {str(p.get("key", "")) for p in pages}
|
| 544 |
+
recents = _read_recents(session.runtime, session.uname, _page_keys)
|
| 545 |
# Wave 21 (C3): the definitions, once β `manage`/`canDelete` below answer from `createdBy`.
|
| 546 |
# WAVE 27 (C9): `locked` answers from `recordMode`, off the same one read.
|
| 547 |
# β W31-T10: that read is now the SAME one the merge above did β it used to be a second,
|
|
|
|
| 590 |
p["locked"] = True
|
| 591 |
elif session.admin:
|
| 592 |
p["manage"] = True
|
| 593 |
+
# β W35-T43 β `important` IS NO LONGER STAMPED HERE. W34-T10 emitted it for every database
|
| 594 |
+
# this route could read, including `{marked: 0, counted: 0, partial: false}`, so a consumer
|
| 595 |
+
# never had to test for the key. R4 retires the count from the rail and the flyout entirely
|
| 596 |
+
# (A's W35-T07 is the client half) and R7 moves the numbers to `GET /starred/counts`.
|
| 597 |
+
# β `nav.ts::NavPage` still DECLARES `important` on the client until A's ticket lands; an
|
| 598 |
+
# absent key reads as `undefined` there, which is the same thing the optional field already
|
| 599 |
+
# meant for a non-database row. Flagged to A rather than assumed harmless.
|
| 600 |
entry = meta.get(p.get("key")) if meta else None
|
| 601 |
if not entry:
|
| 602 |
continue
|
|
|
|
| 621 |
# both doors finally agree on what a placeable key is. This block keeps using the assembled
|
| 622 |
# list because it already holds it: re-enumerating here would be a second store read for an
|
| 623 |
# answer sitting in a local variable.
|
| 624 |
+
#
|
| 625 |
+
# β W34-T10 MOVED THE READ, NOT THE RULE. `recents` is now computed ABOVE the enrichment loop,
|
| 626 |
+
# because the important-count block spends its budget in RECENTS ORDER (see there). It is still
|
| 627 |
+
# ONE read of `nav_recents`, still pruned against the assembled page list, and it is used here
|
| 628 |
+
# unchanged β a second `_read_recents` call would be the extra store read this comment forbids.
|
| 629 |
# β W31-T11 β TWO KINDS OF ABSENCE, NAMED SEPARATELY, and both keys are ALWAYS PRESENT.
|
| 630 |
# `omitted` β this workspace's catalogue does not include these modules. Deliberate.
|
| 631 |
# `degraded` β a part of this payload could not be read. NOT deliberate, and the shell says
|
|
|
|
| 662 |
raise err(400, "bad_request", "no page was named")
|
| 663 |
if not session.runtime.available():
|
| 664 |
raise err(503, "store_unavailable",
|
| 665 |
+
"the tenant store is unavailable. Nothing was recorded.")
|
| 666 |
stamp, uname = _now(), session.uname
|
| 667 |
|
| 668 |
def _up(data):
|
|
|
|
| 686 |
session.runtime.update(_NAV_RECENTS_KEY, _up, flush='async')
|
| 687 |
except Exception:
|
| 688 |
raise err(503, "store_unavailable",
|
| 689 |
+
"the tenant store refused the write. Nothing was recorded.")
|
| 690 |
return {"key": key, "at": stamp}
|
| 691 |
|
| 692 |
|
|
|
|
| 751 |
if "name" in body:
|
| 752 |
if not key.startswith("ut_"):
|
| 753 |
raise err(400, "name_not_allowed",
|
| 754 |
+
"only a database you created can be renamed. This one's name comes "
|
| 755 |
"from the module registry")
|
| 756 |
name = " ".join(str(body.get("name") or "").split())[:_MAX_NAV_NAME]
|
| 757 |
if not name:
|
|
|
|
| 762 |
|
| 763 |
if not session.runtime.available():
|
| 764 |
raise err(503, "store_unavailable",
|
| 765 |
+
"the tenant store is unavailable. Nothing was saved.")
|
| 766 |
|
| 767 |
def _up(data):
|
| 768 |
data = data if isinstance(data, dict) else {}
|
|
|
|
| 785 |
session.runtime.update(_NAV_META_KEY, _up)
|
| 786 |
except Exception:
|
| 787 |
raise err(503, "store_unavailable",
|
| 788 |
+
"the change was not saved: the store refused the write.")
|
| 789 |
return {"key": key, "meta": _read_nav_meta(session.runtime).get(key, {})}
|
| 790 |
|
| 791 |
|
|
|
|
| 810 |
clean = _clean_nav_prefs(body or {}, keys, keep_unknown_ut=not enumerated)
|
| 811 |
if not session.runtime.available():
|
| 812 |
raise err(503, "store_unavailable",
|
| 813 |
+
"the tenant store is unavailable. Nothing was saved.")
|
| 814 |
|
| 815 |
def _up(data):
|
| 816 |
data = data if isinstance(data, dict) else {}
|
|
|
|
| 824 |
session.runtime.update(_NAV_PREFS_KEY, _up)
|
| 825 |
except Exception:
|
| 826 |
raise err(503, "store_unavailable",
|
| 827 |
+
"the folder change was not saved: the store refused the write.")
|
| 828 |
return {"prefs": clean}
|
| 829 |
|
| 830 |
|
api/routes_odoo_tables.py
CHANGED
|
@@ -841,7 +841,18 @@ def odoo_table_rows(table_key: str,
|
|
| 841 |
# THE WALL FIRST, and it is the SAME one the materialised path uses β 404 for a key that does
|
| 842 |
# not exist, 403 for one this session may not open. Reused rather than re-stated: a second
|
| 843 |
# idea of "may this session open this database" is a permission bug waiting to happen.
|
| 844 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 845 |
fields = None
|
| 846 |
for _bucket, key, _label, mk_fields in rel.TABLES:
|
| 847 |
if key == table_key:
|
|
|
|
| 841 |
# THE WALL FIRST, and it is the SAME one the materialised path uses β 404 for a key that does
|
| 842 |
# not exist, 403 for one this session may not open. Reused rather than re-stated: a second
|
| 843 |
# idea of "may this session open this database" is a permission bug waiting to happen.
|
| 844 |
+
#
|
| 845 |
+
# ββ W33-T02 / D-213 β `defs_only=True`, AND THIS ROUTE IS THE CLEANEST OPT-IN ON THE BOARD.
|
| 846 |
+
# `defn` is read EXACTLY ONCE below, for `recordMode`; the fields come from `rel.TABLES`'s
|
| 847 |
+
# `mk_fields()` and the rows from `datastore.window`, so nothing here has ever touched
|
| 848 |
+
# `defn["rows"]`. That is what makes it safe by inspection rather than by argument β and it is
|
| 849 |
+
# why the same change must NOT be swept across this file: `odoo_tables_status` a few hundred
|
| 850 |
+
# lines down reads `table["rows"]` and its per-row `refreshed` stamps for the MATERIALISED
|
| 851 |
+
# grids, and a projection there raises `KeyError` on every one of them.
|
| 852 |
+
# β `mirror_stamp`'s bare `except: return ""` would convert exactly that raise into a silently
|
| 853 |
+
# BLANK `refreshed` column rather than a red β which is why the boundary is drawn here, at the
|
| 854 |
+
# one function that provably needs no row, instead of at the file.
|
| 855 |
+
defn = _defn_or_refuse(session, table_key, defs_only=True)
|
| 856 |
fields = None
|
| 857 |
for _bucket, key, _label, mk_fields in rel.TABLES:
|
| 858 |
if key == table_key:
|
api/routes_publish.py
ADDED
|
@@ -0,0 +1,917 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"""routes_publish.py β PUBLISH AN INTERFACE VIEW AS A LINK (wave 33, owner item 8b, ruling R5).
|
| 2 |
+
|
| 3 |
+
The owner, verbatim: *"Have the ability to publish interface, when a user's view is an interface
|
| 4 |
+
(e.g. Map or Catalog), we should have the ability to publish a link that can be either accessed
|
| 5 |
+
publicly or with a password that the user that share it can toggle."*
|
| 6 |
+
|
| 7 |
+
R5, in five clauses, and every one of them is load-bearing:
|
| 8 |
+
* publish = a per-view secret token in a **server-only bucket**;
|
| 9 |
+
* a `public | password` toggle the SHARER owns, with a **hashed** passphrase beside it;
|
| 10 |
+
* an **unauthenticated** read-only route plus a `#/v/<token>` client route;
|
| 11 |
+
* the publish surface **projects only the columns the view shows** β never the whole table;
|
| 12 |
+
* **creator-or-admin** may publish, and **revoke ROTATES** the token.
|
| 13 |
+
|
| 14 |
+
β THIS FILE COPIES `routes_forms.py`'S CONSTRUCTION ON PURPOSE, AND THE TICKET SAID TO. That door
|
| 15 |
+
has been public since wave 23 and carries scar tissue no fresh design would reproduce: ONE refusal
|
| 16 |
+
for every resolution failure (so the route is not an oracle for which tokens are real), a
|
| 17 |
+
constant-time compare, a STREAMING body bound rather than `Body(...)` (FastAPI reads and parses the
|
| 18 |
+
whole body before the handler's first line, and `content-length` is caller-supplied), a sliding
|
| 19 |
+
rate window rather than a fixed bucket, and an index that is a POINTER, never a permission.
|
| 20 |
+
|
| 21 |
+
β WHAT IS DELIBERATELY *NOT* SHARED WITH `routes_forms.py`: the bucket. A form token buys a WRITE
|
| 22 |
+
door into a table; a publish token buys a READ projection of one view. Folding them into one index
|
| 23 |
+
would make a single leaked string ambiguous about which of the two it opens, and would make
|
| 24 |
+
`_resolve` return an object whose capability depends on a field rather than on which door was
|
| 25 |
+
knocked. Two buckets, two resolvers, one shape.
|
| 26 |
+
|
| 27 |
+
β AND NOT SHARED WITH SHARING. **Three systems now answer some version of "who can see this"** and
|
| 28 |
+
they are not the same question (audit S-4): the grant registry drives *Shared with me*,
|
| 29 |
+
`table_store.is_shared` GATES opening a view inside the app, and a published link is a THIRD thing
|
| 30 |
+
β an unauthenticated read of a projection, bound to a secret rather than to an account. A published
|
| 31 |
+
link is NOT a grant: it creates no registry row, appears in nobody's *Shared with me*, and cannot
|
| 32 |
+
be revoked by removing a person, because there is no person.
|
| 33 |
+
|
| 34 |
+
python verify_forms.py # this file's gate; section 6 onward
|
| 35 |
+
"""
|
| 36 |
+
import hashlib
|
| 37 |
+
import hmac
|
| 38 |
+
import os
|
| 39 |
+
import secrets
|
| 40 |
+
import time
|
| 41 |
+
|
| 42 |
+
from fastapi import APIRouter, Depends, Request
|
| 43 |
+
|
| 44 |
+
from deps import Session, err, require_session
|
| 45 |
+
|
| 46 |
+
router = APIRouter(prefix="/api/v1")
|
| 47 |
+
|
| 48 |
+
#: The SERVER-ONLY index: `{token: {table, view, access, pw?, salt?, iter?, createdBy, createdAt}}`.
|
| 49 |
+
#: β IT IS NEVER `display.*`. Contract C1 puts two PRESENTATIONAL flags on the view spec
|
| 50 |
+
#: (`published`, `publishAccess`) precisely so the client has something to render, and the browser
|
| 51 |
+
#: writes that spec on every autosave β so anything secret living there would be echoed back to the
|
| 52 |
+
#: browser by construction. `aios_grid._clean_display`'s allowlist enforces the other half.
|
| 53 |
+
TOKENS_KEY = "publish_tokens"
|
| 54 |
+
TOKEN_BYTES = 24
|
| 55 |
+
|
| 56 |
+
#: Passphrase storage. PBKDF2-HMAC-SHA256 with a per-link salt.
|
| 57 |
+
#: β D-130 IS THE SCAR THIS AVOIDS: a form's "invited addresses" list is IDENTIFICATION β it says
|
| 58 |
+
#: who you claim to be and anyone may claim it. A passphrase is AUTHENTICATION. The difference is
|
| 59 |
+
#: not a stronger string, it is that the secret is never stored, never logged and never echoed.
|
| 60 |
+
PW_ITERATIONS = 240_000
|
| 61 |
+
PW_SALT_BYTES = 16
|
| 62 |
+
MIN_PASSPHRASE = 6
|
| 63 |
+
MAX_PASSPHRASE = 128
|
| 64 |
+
|
| 65 |
+
#: v1 request protections, the same shape and the same numbers as the form door (contract C9), so
|
| 66 |
+
#: the two public routes cannot drift into different postures. β In-process, therefore PER WORKER.
|
| 67 |
+
RATE_WINDOW_S = 60
|
| 68 |
+
RATE_PER_WINDOW = 30
|
| 69 |
+
MAX_BODY_BYTES = 16 * 1024
|
| 70 |
+
|
| 71 |
+
_HITS: dict = {}
|
| 72 |
+
|
| 73 |
+
#: The view kinds that may be published, i.e. R5's "interface".
|
| 74 |
+
#: β THE CLIENT'S SOURCE OF TRUTH IS `customer-grid/iconShapes.ts::MODE_GROUP` (wave 33 item 9
|
| 75 |
+
#: moved `swipe` and `timeseries` into this group). This constant is the SERVER's copy and the two
|
| 76 |
+
#: are held in step by `verify_forms.py`, which parses `MODE_GROUP` and compares β because a
|
| 77 |
+
#: server list that silently drifts from the picker means a mode a user can create and cannot
|
| 78 |
+
#: publish, with nothing anywhere going red. A `grid` or `kanban` view is a re-shaping of a row
|
| 79 |
+
#: set; publishing one would be publishing the table, which is exactly what R5's projection clause
|
| 80 |
+
#: exists to prevent.
|
| 81 |
+
#: ββ W33-T68 β `form` IS DELIBERATELY ABSENT, AND ITS ABSENCE IS THE FIX.
|
| 82 |
+
#: A `form` view's rows ARE the submissions people have sent it. Every other mode here re-shapes a
|
| 83 |
+
#: row set the publisher already curated; a form's row set is other people's answers, gathered under
|
| 84 |
+
#: an implicit promise that they go to the owner. Publishing one turned "share this interface" into
|
| 85 |
+
#: "serve the responses to anyone holding the link" β on the one unauthenticated door in the
|
| 86 |
+
#: product, with no wall between the link and the data.
|
| 87 |
+
#: β AND A FORM ALREADY HAS ITS OWN PUBLIC DOOR: `#/form/<token>` through `routes_forms.py`, which
|
| 88 |
+
#: serves the BLANK form for submitting and never the stored rows. So this is not a capability
|
| 89 |
+
#: removed, it is a second door onto the same object that should never have existed beside the
|
| 90 |
+
#: first. Publishing a form to be filled in still works, at the URL that was always for it.
|
| 91 |
+
#: β `verify_forms.py` holds this list in step with the client's `MODE_GROUP`; the client must not
|
| 92 |
+
#: offer Publish on a form view, or the picker promises what this refuses.
|
| 93 |
+
PUBLISHABLE_MODES = ("map", "catalog", "swipe", "timeseries")
|
| 94 |
+
|
| 95 |
+
|
| 96 |
+
def _refuse():
|
| 97 |
+
"""THE ONE REFUSAL, for every way a published link can fail to resolve.
|
| 98 |
+
|
| 99 |
+
Wrong token, revoked link, deleted view, deleted table, a view that stopped being an
|
| 100 |
+
interface, a wrong passphrase. β Callers must not branch a more specific message out of it:
|
| 101 |
+
the difference between "no such link" and "that link was revoked" tells an enumerator which
|
| 102 |
+
tokens are real, and the difference between "no such link" and "wrong passphrase" tells them
|
| 103 |
+
which links are worth guessing at.
|
| 104 |
+
"""
|
| 105 |
+
return err(403, "bad_publish_token", "that link is not valid")
|
| 106 |
+
|
| 107 |
+
|
| 108 |
+
def _same(a: str, b: str) -> bool:
|
| 109 |
+
"""Constant-time. A `==` leaks a secret's prefix through timing, one character at a time."""
|
| 110 |
+
return hmac.compare_digest(str(a or ""), str(b or ""))
|
| 111 |
+
|
| 112 |
+
|
| 113 |
+
def _client_ip(request: Request) -> str:
|
| 114 |
+
"""ββ W33-T70 β `x-forwarded-for` IS GONE FROM THIS FUNCTION, AND THAT WAS THE WHOLE HOLE.
|
| 115 |
+
|
| 116 |
+
The header is chosen by the caller. Keying a rate limit on it means an enumerator writes a new
|
| 117 |
+
value per request and every request lands in a fresh bucket: MEASURED at **100 of 100 admitted
|
| 118 |
+
through a 30-per-window ceiling**. A limiter with a caller-chosen key is not a limiter, and its
|
| 119 |
+
old docstring said the header was "a rate-limit key and NOTHING else" β which was exactly the
|
| 120 |
+
use it could not support. It is safe as a LOG field and as nothing else.
|
| 121 |
+
|
| 122 |
+
The socket peer is the only thing here the caller cannot choose, so it is the key.
|
| 123 |
+
β AND BEHIND HF'S PROXY EVERY CALLER SHARES ONE PEER, which is why `_rate_ok` counts FAILURES
|
| 124 |
+
ONLY (see there). A per-peer ceiling over ALL traffic would be one global bucket, i.e. an alarm
|
| 125 |
+
that fires for everyone [[alarm-that-fires-for-everyone]] β the honest reading of a shared peer
|
| 126 |
+
is that we cannot separate callers, not that we should throttle them together.
|
| 127 |
+
"""
|
| 128 |
+
return request.client.host if request.client else "?"
|
| 129 |
+
|
| 130 |
+
|
| 131 |
+
def _rate_ok(key: str, now: float) -> bool:
|
| 132 |
+
"""Is this caller UNDER the failure ceiling? Pure check β call `_note_failure` to count.
|
| 133 |
+
|
| 134 |
+
A SLIDING window. A fixed bucket lets a caller spend a whole allowance at 11:59:59 and the
|
| 135 |
+
whole next one at 12:00:00 β i.e. double the limit, back to back, against a door whose entire
|
| 136 |
+
protection is that guessing a 24-byte token is slow.
|
| 137 |
+
|
| 138 |
+
β W33-T70 β IT COUNTS FAILURES, NOT REQUESTS, and the split is what makes a shared proxy peer
|
| 139 |
+
survivable. A legitimate reader opens a link that RESOLVES, so they never touch the counter at
|
| 140 |
+
all; an enumerator produces nothing but misses. Counting every request under one shared peer
|
| 141 |
+
would have denied service to everybody the moment one guesser showed up β trading a token
|
| 142 |
+
oracle for an outage is not a fix.
|
| 143 |
+
"""
|
| 144 |
+
seen = [t for t in _HITS.get(key, ()) if now - t < RATE_WINDOW_S]
|
| 145 |
+
_HITS[key] = seen
|
| 146 |
+
return len(seen) < RATE_PER_WINDOW
|
| 147 |
+
|
| 148 |
+
|
| 149 |
+
def _note_failure(key: str, now: float) -> None:
|
| 150 |
+
"""Record one failed resolution against this peer, and keep the table bounded."""
|
| 151 |
+
seen = [t for t in _HITS.get(key, ()) if now - t < RATE_WINDOW_S]
|
| 152 |
+
seen.append(now)
|
| 153 |
+
_HITS[key] = seen
|
| 154 |
+
if len(_HITS) > 4096:
|
| 155 |
+
for k in [k for k, v in _HITS.items() if not v or now - v[-1] > RATE_WINDOW_S]:
|
| 156 |
+
_HITS.pop(k, None)
|
| 157 |
+
|
| 158 |
+
|
| 159 |
+
#: A salt used ONLY to burn the same PBKDF2 a real verification would, when there is no stored hash
|
| 160 |
+
#: to check against. Its value is irrelevant; its COST is the point.
|
| 161 |
+
_DUMMY_SALT = b"\x00" * 16
|
| 162 |
+
|
| 163 |
+
|
| 164 |
+
def _equalise_pw_cost(entry) -> None:
|
| 165 |
+
"""ββ W33-T70 β SPEND THE PBKDF2 EVEN WHEN THERE IS NOTHING TO VERIFY.
|
| 166 |
+
|
| 167 |
+
MEASURED before this existed: a wrong TOKEN answered in ~0.4 ms and a wrong PASSPHRASE in
|
| 168 |
+
~82 ms β a **206x gap with zero overlap across 24 samples**. So the refusal's careful wording
|
| 169 |
+
("that link is not valid", identical for both) was undone by the clock: anyone could sort real
|
| 170 |
+
tokens from fake ones by timing alone, then spend their guesses only on the real ones. The
|
| 171 |
+
docstring on `_refuse` describes exactly the leak the code then handed over for free.
|
| 172 |
+
|
| 173 |
+
Called on every path that fails BEFORE a passphrase check would have happened, so the cheap
|
| 174 |
+
branch costs what the expensive one costs. `iter` is taken from the entry when there is one, so
|
| 175 |
+
a link minted under a different iteration count stays indistinguishable too.
|
| 176 |
+
"""
|
| 177 |
+
iterations = PW_ITERATIONS
|
| 178 |
+
if isinstance(entry, dict):
|
| 179 |
+
try:
|
| 180 |
+
iterations = int(entry.get("iter") or PW_ITERATIONS)
|
| 181 |
+
except (TypeError, ValueError):
|
| 182 |
+
iterations = PW_ITERATIONS
|
| 183 |
+
_hash_pw("", _DUMMY_SALT, iterations)
|
| 184 |
+
|
| 185 |
+
|
| 186 |
+
def _public_base() -> str:
|
| 187 |
+
return (os.environ.get("AIOS_PUBLIC_BASE") or os.environ.get("APP_BASE_URL") or "").rstrip("/")
|
| 188 |
+
|
| 189 |
+
|
| 190 |
+
def _link_of(token: str) -> str:
|
| 191 |
+
return f"{_public_base()}/#/v/{token}"
|
| 192 |
+
|
| 193 |
+
|
| 194 |
+
def _tokens(rt) -> dict:
|
| 195 |
+
"""This tenant's publish index, always a dict."""
|
| 196 |
+
try:
|
| 197 |
+
found = rt.get(TOKENS_KEY) or {}
|
| 198 |
+
except Exception: # noqa: BLE001
|
| 199 |
+
return {}
|
| 200 |
+
return found if isinstance(found, dict) else {}
|
| 201 |
+
|
| 202 |
+
|
| 203 |
+
def _hash_pw(passphrase: str, salt: bytes, iterations: int = PW_ITERATIONS) -> str:
|
| 204 |
+
return hashlib.pbkdf2_hmac("sha256", str(passphrase).encode("utf-8"),
|
| 205 |
+
salt, int(iterations)).hex()
|
| 206 |
+
|
| 207 |
+
|
| 208 |
+
def _pw_ok(entry: dict, passphrase: str) -> bool:
|
| 209 |
+
"""Constant-time verify against the stored digest.
|
| 210 |
+
|
| 211 |
+
β RETURNS FALSE, NEVER RAISES, and never distinguishes "this link has no passphrase stored"
|
| 212 |
+
from "the passphrase is wrong" β a `password` link whose hash went missing must refuse, not
|
| 213 |
+
fall open. [[default-must-pass-its-own-guard]]
|
| 214 |
+
"""
|
| 215 |
+
stored, salt_hex = str(entry.get("pw") or ""), str(entry.get("salt") or "")
|
| 216 |
+
if not stored or not salt_hex:
|
| 217 |
+
return False
|
| 218 |
+
try:
|
| 219 |
+
salt = bytes.fromhex(salt_hex)
|
| 220 |
+
except ValueError:
|
| 221 |
+
return False
|
| 222 |
+
got = _hash_pw(passphrase, salt, int(entry.get("iter") or PW_ITERATIONS))
|
| 223 |
+
return _same(got, stored)
|
| 224 |
+
|
| 225 |
+
|
| 226 |
+
def _find_view(rt, table_key: str, view_id: str):
|
| 227 |
+
"""`(view, owner_username)` from the table's workspace bucket, or `(None, "")`.
|
| 228 |
+
|
| 229 |
+
The bucket shape is `{username: {views: {id: view}}}` β the same walk `routes_forms._find_view`
|
| 230 |
+
does, and the reason a view is addressable by id ALONE here: the id is unique within the table,
|
| 231 |
+
while the owner is what we are trying to discover.
|
| 232 |
+
"""
|
| 233 |
+
if not table_key or not view_id:
|
| 234 |
+
return None, ""
|
| 235 |
+
try:
|
| 236 |
+
bucket = rt.get(f"{table_key}_table_workspace") or {}
|
| 237 |
+
except Exception: # noqa: BLE001
|
| 238 |
+
return None, ""
|
| 239 |
+
if not isinstance(bucket, dict):
|
| 240 |
+
return None, ""
|
| 241 |
+
for owner, blob in bucket.items():
|
| 242 |
+
views = (blob or {}).get("views") if isinstance(blob, dict) else None
|
| 243 |
+
if isinstance(views, dict) and isinstance(views.get(view_id), dict):
|
| 244 |
+
return views[view_id], str(owner)
|
| 245 |
+
return None, ""
|
| 246 |
+
|
| 247 |
+
|
| 248 |
+
def _mode_of(view: dict) -> str:
|
| 249 |
+
"""The view's display mode. Absent means `grid` β the stored default is "say nothing"."""
|
| 250 |
+
cfg = (view or {}).get("config") if isinstance(view, dict) else None
|
| 251 |
+
disp = (cfg or {}).get("display") if isinstance(cfg, dict) else None
|
| 252 |
+
return str((disp or {}).get("mode") or "grid") if isinstance(disp, dict) else "grid"
|
| 253 |
+
|
| 254 |
+
|
| 255 |
+
def _may_administer_view(session: Session, table_key: str, view_id: str):
|
| 256 |
+
"""`(view, mode)` when this caller may publish THIS view, else raises. R5's creator-or-admin.
|
| 257 |
+
|
| 258 |
+
β `session.uname` / `session.admin`, NOT `username` / `is_admin`. `Session` has no such
|
| 259 |
+
attributes, and reading one raises ABOVE this route's own `try:` β which is how D-107 arrived
|
| 260 |
+
as a bare plain-text 500 rather than as our JSON envelope.
|
| 261 |
+
"""
|
| 262 |
+
import core.table_store as table_store
|
| 263 |
+
|
| 264 |
+
if not table_key.startswith("ut_"):
|
| 265 |
+
# The Odoo/registry grids are read-through mirrors with their own permission wall; a
|
| 266 |
+
# published projection of one would be a second, secret-gated door onto tenant data whose
|
| 267 |
+
# visibility the module gate is supposed to decide.
|
| 268 |
+
raise err(400, "not_a_database", "you can publish views on your own databases only")
|
| 269 |
+
# β A READ-THROUGH DATABASE CANNOT BE PUBLISHED, AND THE REFUSAL SAYS SO RATHER THAN MINTING
|
| 270 |
+
# A LINK THAT WILL NOT OPEN. `startswith("ut_")` admits `ut_odoo_*` and `ut_meta_*`, whose rows
|
| 271 |
+
# do not live in the tenant document at all β they are windowed out of the DuckDB mirror
|
| 272 |
+
# through a Session-bound path (`ut_assembly`, which 409s `window_required` on the big ones,
|
| 273 |
+
# D-174's lineage). An unauthenticated route has no session and therefore no such path, so a
|
| 274 |
+
# token minted here would resolve to a page that could never render.
|
| 275 |
+
# β THIS IS R6's SECOND SENTENCE, WHICH IS THE HALF THAT GETS DROPPED: a limit that genuinely
|
| 276 |
+
# cannot be removed must be REPORTED, with its cause, never silently enforced. Refusing at the
|
| 277 |
+
# MINT β where a person is standing in front of the answer β is the only place that reads as a
|
| 278 |
+
# sentence rather than as an empty page.
|
| 279 |
+
import core.user_tables as user_tables
|
| 280 |
+
|
| 281 |
+
if user_tables.is_connected(table_key, st=session.runtime):
|
| 282 |
+
raise err(400, "connected_source",
|
| 283 |
+
"a database that reads through a connected source (Odoo, Meta Ads) cannot be "
|
| 284 |
+
"published as a public link: its rows are served from the tenant's mirror by a "
|
| 285 |
+
"signed-in request, and a public link has no session to serve them with")
|
| 286 |
+
view, owner = _find_view(session.runtime, table_key, view_id)
|
| 287 |
+
if not isinstance(view, dict):
|
| 288 |
+
raise err(404, "no_such_view", "that view no longer exists")
|
| 289 |
+
if not (owner == session.uname
|
| 290 |
+
or table_store._may_administer(view, session.uname, session.admin)):
|
| 291 |
+
raise err(403, "not_yours", "only this view's creator or an admin can publish it")
|
| 292 |
+
mode = _mode_of(view)
|
| 293 |
+
if mode not in PUBLISHABLE_MODES:
|
| 294 |
+
raise err(400, "not_an_interface",
|
| 295 |
+
"only an interface view (Map, Catalog, Swipe, Time-series, Form) can be "
|
| 296 |
+
"published as a link")
|
| 297 |
+
cfg = view.get("config") or {}
|
| 298 |
+
if cfg.get("cohortLock"):
|
| 299 |
+
raise err(400, "reader_scoped",
|
| 300 |
+
"this view is locked to a cohort, and a cohort's membership is resolved for "
|
| 301 |
+
"the person reading it β a public link has no reader, so the page would show "
|
| 302 |
+
"no rows at all. Publish a copy without the cohort lock.")
|
| 303 |
+
if _needs_a_reader(cfg.get("filters")):
|
| 304 |
+
raise err(400, "reader_scoped",
|
| 305 |
+
"this view filters on a cohort, a measure rule or a top-N slice, and each of "
|
| 306 |
+
"those is resolved for the person reading it β a public link has no reader, so "
|
| 307 |
+
"the page would show no rows at all. Publish a copy filtered on columns.")
|
| 308 |
+
return view, mode
|
| 309 |
+
|
| 310 |
+
|
| 311 |
+
#: How many rows a published page will serve. β R6 (no cap on connected-source data) does not
|
| 312 |
+
#: reach here twice over: a publishable database is `records_mutable`, i.e. the EDITABLE substrate
|
| 313 |
+
#: that keeps its bound (`user_tables.MAX_ROWS`), and a connected one is refused at the mint. What
|
| 314 |
+
#: R6's SECOND sentence does reach here is the reporting duty β a page that serves fewer rows than
|
| 315 |
+
#: the view has must SAY SO on the wire, with the cause, never just stop.
|
| 316 |
+
PUBLIC_ROW_CAP = 5000
|
| 317 |
+
|
| 318 |
+
|
| 319 |
+
def _needs_a_reader(tree) -> bool:
|
| 320 |
+
"""Does this filter tree contain a leaf that only a SIGNED-IN reader could resolve?
|
| 321 |
+
|
| 322 |
+
β COHORTS, MEASURE RULES AND RANK SLICES ARE NOT PROPERTIES OF THE VIEW. Each is a SET the
|
| 323 |
+
host computes for the person asking β `filter_eval.EvalCtx`'s own docstring: *"each is an
|
| 324 |
+
answer a single ROW cannot compute β¦ absent, the condition matches NOTHING rather than
|
| 325 |
+
everything"*. That default is right (it fails closed) and it is unusable here: an anonymous
|
| 326 |
+
page whose every row was silently filtered out is indistinguishable from a broken link, and
|
| 327 |
+
the reader has nobody to ask. Worse, `rank_sets` has NO server-side resolver anywhere in this
|
| 328 |
+
repo β `routes_alerts._evaluate` passes cohort/measure/today and nothing else β so a `topN`
|
| 329 |
+
view would serve zero rows on the server while showing twenty in the browser.
|
| 330 |
+
|
| 331 |
+
β So such a view is refused AT THE MINT, where a person is standing in front of the answer.
|
| 332 |
+
That is R6's second sentence: a limit that genuinely cannot be removed is REPORTED with its
|
| 333 |
+
cause, never silently enforced.
|
| 334 |
+
|
| 335 |
+
β THE PREDICATES ARE `filter_eval`'S OWN. Re-implementing "is this a cohort leaf?" here would
|
| 336 |
+
be a second evaluator that agrees today and drifts the day the leaf shape changes β and it
|
| 337 |
+
would drift SILENTLY, because the two answers only differ on views nobody has published yet.
|
| 338 |
+
[[one-evaluator-per-question]]
|
| 339 |
+
"""
|
| 340 |
+
from harness import filter_eval
|
| 341 |
+
|
| 342 |
+
def walk(node) -> bool:
|
| 343 |
+
if isinstance(node, list):
|
| 344 |
+
return any(walk(n) for n in node)
|
| 345 |
+
if not isinstance(node, dict):
|
| 346 |
+
return False
|
| 347 |
+
if node.get("kind") == "group" or isinstance(node.get("children"), list):
|
| 348 |
+
return any(walk(n) for n in (node.get("children") or []))
|
| 349 |
+
if filter_eval._is_cohort(node) or filter_eval._is_measure(node):
|
| 350 |
+
return True
|
| 351 |
+
return node.get("op") in filter_eval.RANK_OPS
|
| 352 |
+
|
| 353 |
+
return walk(tree)
|
| 354 |
+
|
| 355 |
+
|
| 356 |
+
def _mirror_display(rt, table_key: str, view_id: str, published: bool, access: str = "password"):
|
| 357 |
+
"""Keep contract C1's two PRESENTATIONAL flags on the stored view in step with this bucket.
|
| 358 |
+
|
| 359 |
+
β WHY THIS EXISTS AT ALL, and it was found by a reviewer rather than by a gate: revoking a
|
| 360 |
+
link dropped the token and left `config.display.published: true` on the view, so the grid's
|
| 361 |
+
own UI would go on saying "published" about a link that no longer resolves. Two records of one
|
| 362 |
+
fact, and only one of them moving, is the [[flag-shipped-without-its-writer]] shape β here with
|
| 363 |
+
the writer present and the OTHER half forgotten.
|
| 364 |
+
|
| 365 |
+
β THE BUCKET REMAINS THE TRUTH. These flags exist so the client has something to render
|
| 366 |
+
without asking; they are a MIRROR, never a source, and nothing in this module reads them back
|
| 367 |
+
to decide anything. `read_view_link` deliberately reports both so a drift is visible rather
|
| 368 |
+
than assumed away.
|
| 369 |
+
|
| 370 |
+
β ONLY THE TWO LEGAL KEYS ARE WRITTEN, with E's fail-closed coercion reproduced exactly
|
| 371 |
+
(`aios_grid._clean_display`: `published: True` always carries a `publishAccess`, and anything
|
| 372 |
+
that is not the literal `public` stores as `password`) β so a value written here and a value
|
| 373 |
+
written by the browser cannot disagree.
|
| 374 |
+
"""
|
| 375 |
+
def _set(cur):
|
| 376 |
+
cur = dict(cur or {})
|
| 377 |
+
for owner, blob in list(cur.items()):
|
| 378 |
+
views = (blob or {}).get("views") if isinstance(blob, dict) else None
|
| 379 |
+
view = views.get(view_id) if isinstance(views, dict) else None
|
| 380 |
+
if not isinstance(view, dict):
|
| 381 |
+
continue
|
| 382 |
+
cfg = dict(view.get("config") or {})
|
| 383 |
+
disp = dict(cfg.get("display") or {})
|
| 384 |
+
if not disp.get("mode"):
|
| 385 |
+
# No display block means no interface view; nothing here should invent one.
|
| 386 |
+
continue
|
| 387 |
+
if published:
|
| 388 |
+
disp["published"] = True
|
| 389 |
+
disp["publishAccess"] = "public" if access == "public" else "password"
|
| 390 |
+
else:
|
| 391 |
+
disp.pop("published", None)
|
| 392 |
+
disp.pop("publishAccess", None)
|
| 393 |
+
cfg["display"] = disp
|
| 394 |
+
cur[owner] = {**blob, "views": {**views, view_id: {**view, "config": cfg}}}
|
| 395 |
+
return cur
|
| 396 |
+
|
| 397 |
+
try:
|
| 398 |
+
rt.update(f"{table_key}_table_workspace", _set, flush="sync")
|
| 399 |
+
except Exception: # noqa: BLE001
|
| 400 |
+
# β SWALLOWED, and deliberately: the token bucket is the truth and it has already been
|
| 401 |
+
# written. A mirror that failed to update leaves the UI one refresh out of date, which is
|
| 402 |
+
# strictly better than a 500 on a publish that actually succeeded.
|
| 403 |
+
pass
|
| 404 |
+
|
| 405 |
+
|
| 406 |
+
def _entry_for(rt, table_key: str, view_id: str):
|
| 407 |
+
"""`(token, entry)` for a view's existing link, or `(None, None)`."""
|
| 408 |
+
for token, where in _tokens(rt).items():
|
| 409 |
+
if (isinstance(where, dict) and where.get("table") == table_key
|
| 410 |
+
and where.get("view") == view_id):
|
| 411 |
+
return str(token), where
|
| 412 |
+
return None, None
|
| 413 |
+
|
| 414 |
+
|
| 415 |
+
def _state_of(token, entry) -> dict:
|
| 416 |
+
"""The link's state as the SHARER may see it. Built key by key.
|
| 417 |
+
|
| 418 |
+
β NO `**entry`. The stored blob carries `pw` and `salt`; a spread would put both on the wire
|
| 419 |
+
to the browser, which is the whole failure this file's bucket exists to avoid, and it would do
|
| 420 |
+
it silently the first time somebody added a field.
|
| 421 |
+
"""
|
| 422 |
+
if not token or not isinstance(entry, dict):
|
| 423 |
+
return {"published": False, "access": "password", "token": "", "url": ""}
|
| 424 |
+
return {
|
| 425 |
+
"published": True,
|
| 426 |
+
"access": "public" if entry.get("access") == "public" else "password",
|
| 427 |
+
"token": str(token),
|
| 428 |
+
"url": _link_of(str(token)),
|
| 429 |
+
# A boolean, never the digest and never the salt.
|
| 430 |
+
"hasPassphrase": bool(entry.get("pw")),
|
| 431 |
+
"createdBy": str(entry.get("createdBy") or ""),
|
| 432 |
+
}
|
| 433 |
+
|
| 434 |
+
|
| 435 |
+
def _resolve(token: str):
|
| 436 |
+
"""`(runtime, tenant_slug, table_key, view, entry)` for a token, or None.
|
| 437 |
+
|
| 438 |
+
β THE INDEX IS A POINTER, NEVER A PERMISSION. Holding a token means the sharer minted it for
|
| 439 |
+
THIS view; it does not mean the holder may read anything else, and nothing downstream of here
|
| 440 |
+
may widen the subject beyond the `(table, view)` pair the entry names.
|
| 441 |
+
|
| 442 |
+
β IT WALKS EVERY TENANT, because an unauthenticated request carries no tenant. That is the
|
| 443 |
+
form door's shape too, and the reason `_same` is constant-time: the walk compares the caller's
|
| 444 |
+
string against every stored token in the deployment.
|
| 445 |
+
"""
|
| 446 |
+
from harness import runtime as _rt
|
| 447 |
+
|
| 448 |
+
if not token or len(token) < 16:
|
| 449 |
+
return None
|
| 450 |
+
for slug in _rt.known_tenants():
|
| 451 |
+
try:
|
| 452 |
+
rt = _rt.get_runtime(slug)
|
| 453 |
+
except Exception: # noqa: BLE001
|
| 454 |
+
continue
|
| 455 |
+
for stored, where in _tokens(rt).items():
|
| 456 |
+
if not _same(str(stored), token) or not isinstance(where, dict):
|
| 457 |
+
continue
|
| 458 |
+
table_key = str(where.get("table") or "")
|
| 459 |
+
view, _owner = _find_view(rt, table_key, str(where.get("view") or ""))
|
| 460 |
+
# A view deleted, or re-saved as a grid, since the link was minted. Both answer the
|
| 461 |
+
# ONE refusal β "that link is not valid" β rather than explaining which.
|
| 462 |
+
if not table_key or not isinstance(view, dict):
|
| 463 |
+
return None
|
| 464 |
+
if _mode_of(view) not in PUBLISHABLE_MODES:
|
| 465 |
+
return None
|
| 466 |
+
return rt, slug, table_key, view, where
|
| 467 |
+
return None
|
| 468 |
+
|
| 469 |
+
|
| 470 |
+
def _coord(value, limit: float):
|
| 471 |
+
"""A real coordinate, or `None`. THE WALL that lets a map publish without publishing a column.
|
| 472 |
+
|
| 473 |
+
β A VALUE TEST, NEVER A NAME TEST. A field merely CALLED `lat` proves nothing β a verifier put
|
| 474 |
+
the string `CANARY-LAT-AAA` in one and watched it reach the wire under the first version of
|
| 475 |
+
this code. Anything that is not a finite number inside the earth's range is not a location and
|
| 476 |
+
does not travel.
|
| 477 |
+
β `bool` is rejected explicitly: `isinstance(True, int)` is True in Python, and `float(True)`
|
| 478 |
+
is `1.0` β a checkbox column named `lat` would otherwise publish as a point off the coast of
|
| 479 |
+
Ghana.
|
| 480 |
+
"""
|
| 481 |
+
if value is None or isinstance(value, bool):
|
| 482 |
+
return None
|
| 483 |
+
try:
|
| 484 |
+
n = float(value)
|
| 485 |
+
except (TypeError, ValueError):
|
| 486 |
+
return None
|
| 487 |
+
return n if n == n and abs(n) <= limit else None
|
| 488 |
+
|
| 489 |
+
|
| 490 |
+
def _visible_keys(view: dict, fields: list) -> list:
|
| 491 |
+
"""The columns this view SHOWS, in the view's own order. R5's projection clause, in one place.
|
| 492 |
+
|
| 493 |
+
β `config.order` IS NOT THE ANSWER AND IS THE OBVIOUS WRONG ONE. `aios_grid._default_view_config`
|
| 494 |
+
builds `order` as `shown + hidden`, and `grid_events`' `view_upsert` APPENDS every remaining
|
| 495 |
+
field to it β so `order` is every column the table has, hidden ones included. `visible` is the
|
| 496 |
+
only allowlist that exists; there is no stored "hidden" key to subtract.
|
| 497 |
+
|
| 498 |
+
β AND AN EMPTY `visible` IS NOT "NO COLUMNS". `CustomerGrid` falls back to the table's default
|
| 499 |
+
set when a saved view carries none, so a public page that read `[]` as an empty allowlist would
|
| 500 |
+
render blank β and one that read it as "all fields" would LEAK. The fallback is the same
|
| 501 |
+
predicate the default config uses (`field.default is not False`), taken from `aios_grid` rather
|
| 502 |
+
than restated here.
|
| 503 |
+
"""
|
| 504 |
+
import aios_grid
|
| 505 |
+
|
| 506 |
+
by_key = {str(f.get("key")): f for f in fields if isinstance(f, dict)}
|
| 507 |
+
stored = [str(k) for k in (((view or {}).get("config") or {}).get("visible") or [])]
|
| 508 |
+
keep = [k for k in stored if k in by_key]
|
| 509 |
+
if keep:
|
| 510 |
+
return keep
|
| 511 |
+
# ββ W33-T69 β A STALE `visible` MUST SERVE NOTHING, NOT THE TABLE DEFAULT.
|
| 512 |
+
# `delete_field` never prunes a view's stored `visible`, so a published view whose columns were
|
| 513 |
+
# later deleted and replaced arrives here with a NON-EMPTY `stored` of which nothing survives β
|
| 514 |
+
# and the fallback below then WIDENS the public payload to whatever the table declares by
|
| 515 |
+
# default. The publisher chose five columns; the anonymous reader gets the table's idea of
|
| 516 |
+
# sensible. That is a widening on the one unauthenticated door in the product.
|
| 517 |
+
# β THE DISTINCTION IS `stored` NON-EMPTY, NOT `keep` EMPTY. A view that never stored `visible`
|
| 518 |
+
# at all (a legacy publish, a view saved before the key existed) has no intent to honour and
|
| 519 |
+
# the default IS the right answer for it β that is what the fallback was written for. A view
|
| 520 |
+
# that stored five keys and has none left DID state an intent, and every column it named is
|
| 521 |
+
# gone: the honest answer is no columns, which renders as an empty published view rather than
|
| 522 |
+
# somebody else's data.
|
| 523 |
+
if stored:
|
| 524 |
+
return []
|
| 525 |
+
try:
|
| 526 |
+
default_visible = (aios_grid._default_view_config(fields) or {}).get("visible") or []
|
| 527 |
+
except Exception: # noqa: BLE001
|
| 528 |
+
default_visible = []
|
| 529 |
+
fallback = [str(k) for k in default_visible if str(k) in by_key]
|
| 530 |
+
return fallback or [str(f.get("key")) for f in fields if f.get("default") is not False]
|
| 531 |
+
|
| 532 |
+
|
| 533 |
+
def _public_view(rt, table_key: str, view: dict) -> dict:
|
| 534 |
+
"""The ONLY bytes a valid token buys. Built KEY BY KEY β there is no `**row` in this function.
|
| 535 |
+
|
| 536 |
+
β THE REASON THAT IS A RULE AND NOT A STYLE. `aios_grid.rows_from_pool` puts `pid`, `_created`,
|
| 537 |
+
`lat` and `lon` on EVERY row regardless of what the view shows, and the stored row dict carries
|
| 538 |
+
every column the table has. Serialising a row and deleting the fields we do not want inverts
|
| 539 |
+
the failure: a column added next wave is INCLUDED by default and nobody notices, whereas an
|
| 540 |
+
allowlist that has not learned about it merely omits it. `routes_forms._public_form` is the
|
| 541 |
+
shipped precedent and says the same thing about itself.
|
| 542 |
+
"""
|
| 543 |
+
import core.user_tables as user_tables
|
| 544 |
+
from harness import filter_eval
|
| 545 |
+
|
| 546 |
+
defn = user_tables.get(table_key, st=rt) or {}
|
| 547 |
+
fields = [f for f in (defn.get("fields") or []) if isinstance(f, dict)]
|
| 548 |
+
by_key = {str(f.get("key")): f for f in fields}
|
| 549 |
+
keys = _visible_keys(view, fields)
|
| 550 |
+
cfg = (view or {}).get("config") or {}
|
| 551 |
+
|
| 552 |
+
# The row pool: the table's own rows, narrowed to the fields it declares, exactly as
|
| 553 |
+
# `routes_tables.scoped_pool` builds it for a materialised table. β A read-through table has
|
| 554 |
+
# no rows here and is refused at the MINT, so this branch is the only one that can be reached.
|
| 555 |
+
rows_src = []
|
| 556 |
+
for rid, row in (defn.get("rows") or {}).items():
|
| 557 |
+
if not str(rid).isdigit():
|
| 558 |
+
continue
|
| 559 |
+
r = {k: v for k, v in (row or {}).items() if k in by_key}
|
| 560 |
+
r["pid"] = int(rid)
|
| 561 |
+
rows_src.append(r)
|
| 562 |
+
rows_src.sort(key=lambda r: r["pid"])
|
| 563 |
+
|
| 564 |
+
# The view's own row selection, through the SHARED evaluator. `_needs_a_reader` has already
|
| 565 |
+
# refused anything this context could not answer, so an empty result here means the filter
|
| 566 |
+
# genuinely matches nothing β not that we failed to resolve it.
|
| 567 |
+
ctx = filter_eval.EvalCtx(today=time.strftime("%Y-%m-%d"))
|
| 568 |
+
keep = set(filter_eval.visible_pids(cfg.get("filters"), rows_src, fields, ctx,
|
| 569 |
+
member_pids=cfg.get("memberPids")))
|
| 570 |
+
chosen = [r for r in rows_src if r.get("pid") in keep]
|
| 571 |
+
|
| 572 |
+
# ββ COORDINATES RIDE A MAP WHEN THEY ARE COORDINATES β NOT WHEN THEY ARE VISIBLE, AND NOT
|
| 573 |
+
# BECAUSE OF WHAT A COLUMN IS CALLED. Two verifiers, one from each side, are why this reads
|
| 574 |
+
# the way it does; the first fix I wrote was wrong and the second report proved it.
|
| 575 |
+
#
|
| 576 |
+
# β THE LEAK (verifier #1, driven): a HIDDEN field keyed `lat` holding the string
|
| 577 |
+
# `CANARY-LAT-AAA` came out on the wire, because the pair was emitted before the `keys`
|
| 578 |
+
# projection and the bypass keyed on the FIELD NAME rather than on the value being a
|
| 579 |
+
# coordinate. So a column called `lat` could carry anything β a note, an address β and publish
|
| 580 |
+
# it. That is the real defect.
|
| 581 |
+
#
|
| 582 |
+
# β MY FIRST FIX GATED ON VISIBILITY, AND IT BROKE THE FEATURE (verifier #2): hiding the raw
|
| 583 |
+
# decimals is the NORMAL way somebody builds a Map view β nobody wants `38.7223` in the column
|
| 584 |
+
# list β so gating on `visible` meant an ordinary map published a page with no map, under two
|
| 585 |
+
# messages that contradicted each other ("no rows carry a location" vs "this view hides its
|
| 586 |
+
# location columns").
|
| 587 |
+
#
|
| 588 |
+
# β THE RULE THAT SATISFIES BOTH: publishing a MAP is publishing WHERE THE ROWS ARE β that is
|
| 589 |
+
# what the sharer chose β so a real coordinate rides whether or not its column is shown, and a
|
| 590 |
+
# value that is not a coordinate never rides at all. `_coord` is the whole wall, and it is a
|
| 591 |
+
# VALUE test, so no naming convention can smuggle anything past it.
|
| 592 |
+
# β It mirrors `PublishedView.MapPlot`'s own `coord()` deliberately: the client must not plot
|
| 593 |
+
# what the server would not send, and the server must not send what the client would discard.
|
| 594 |
+
# Two normalizers on one question is a smell [[one-question-two-normalizers]] β kept here
|
| 595 |
+
# because they sit on opposite sides of a trust boundary, where the server's copy is the wall
|
| 596 |
+
# and the client's is display hygiene.
|
| 597 |
+
mode = _mode_of(view)
|
| 598 |
+
plotted = 0
|
| 599 |
+
if mode == "map":
|
| 600 |
+
for r in chosen:
|
| 601 |
+
if _coord(r.get("lat"), 90) is not None and _coord(r.get("lon"), 180) is not None:
|
| 602 |
+
plotted += 1
|
| 603 |
+
|
| 604 |
+
limits = []
|
| 605 |
+
if mode == "map" and chosen and not plotted:
|
| 606 |
+
# R6's second sentence. A map with nothing on it must say WHY β and this says the true
|
| 607 |
+
# why, which is about the DATA, because visibility is no longer part of the answer.
|
| 608 |
+
limits.append({
|
| 609 |
+
"subject": "map", "effect": "not_plotted",
|
| 610 |
+
"detail": f"none of these {len(chosen)} rows carry a usable location",
|
| 611 |
+
"recommendation": "add `lat` and `lon` values to the records, then reload this link",
|
| 612 |
+
})
|
| 613 |
+
if len(chosen) > PUBLIC_ROW_CAP:
|
| 614 |
+
# R6's second sentence. A short page that does not say it is short is the silent
|
| 615 |
+
# truncation the rule is actually about.
|
| 616 |
+
limits.append({
|
| 617 |
+
"subject": "rows", "effect": "windowed",
|
| 618 |
+
"detail": f"this view has {len(chosen)} rows and a published page serves the first "
|
| 619 |
+
f"{PUBLIC_ROW_CAP}",
|
| 620 |
+
"recommendation": "narrow the view's filters, or share it with named people instead "
|
| 621 |
+
"of publishing a link",
|
| 622 |
+
})
|
| 623 |
+
chosen = chosen[:PUBLIC_ROW_CAP]
|
| 624 |
+
|
| 625 |
+
# β THE DISPLAY REFS ARE INTERSECTED WITH `visible`, NOT UNIONED INTO IT. A Map that colours
|
| 626 |
+
# by a column the view HIDES would otherwise put that column's value on every public row β
|
| 627 |
+
# the projection leak, arriving through the renderer rather than through the column list. The
|
| 628 |
+
# fail-closed choice is to drop the ref and render the map without colour; a published page
|
| 629 |
+
# that is slightly plainer beats one that ships a hidden column.
|
| 630 |
+
disp_in = (cfg.get("display") or {})
|
| 631 |
+
display = {"mode": mode}
|
| 632 |
+
for ref in ("dateField", "stackField", "titleField", "colorField", "sizeField"):
|
| 633 |
+
if disp_in.get(ref) in keys:
|
| 634 |
+
display[ref] = disp_in[ref]
|
| 635 |
+
|
| 636 |
+
return {
|
| 637 |
+
"title": str((view or {}).get("name") or "")[:200],
|
| 638 |
+
"mode": display["mode"],
|
| 639 |
+
"display": display,
|
| 640 |
+
"columns": [{"key": k,
|
| 641 |
+
"label": str(by_key[k].get("label") or k),
|
| 642 |
+
"type": str(by_key[k].get("type") or "text"),
|
| 643 |
+
**({"options": [str(o) for o in by_key[k]["options"]][:200]}
|
| 644 |
+
if isinstance(by_key[k].get("options"), list) and by_key[k].get("options")
|
| 645 |
+
else {})}
|
| 646 |
+
for k in keys],
|
| 647 |
+
# KEY BY KEY. `pid` rides because the client needs a stable row identity to render a list;
|
| 648 |
+
# it is a row NUMBER within this table and names nothing outside it.
|
| 649 |
+
# ββ `lat`/`lon` RIDE ONLY ON A MAP **AND ONLY WHEN THE VIEW SHOWS THEM** β and the second
|
| 650 |
+
# half was missing, which was a LEAK. Found by a verifier that drove this route with a
|
| 651 |
+
# hidden field keyed `lat` carrying the string `CANARY-LAT-AAA`, and watched it come out
|
| 652 |
+
# on the wire.
|
| 653 |
+
#
|
| 654 |
+
# The first version emitted the pair BEFORE the `keys` projection, so `_visible_keys` never
|
| 655 |
+
# gated it. On a `ut_*` table coordinates are not magic: `routes_tables.scoped_pool` builds
|
| 656 |
+
# its row as `{k: v for k, v in row.items() if k in field_keys}`, so a value only survives
|
| 657 |
+
# if the table DECLARES a field keyed `lat`/`lon` β i.e. they are ORDINARY COLUMNS, and a
|
| 658 |
+
# view can hide them like any other. Hiding them therefore has to work here, because on a
|
| 659 |
+
# published page **the projection is the only wall there is** (`ut_*` databases have no
|
| 660 |
+
# hidden-field closure behind it, `routes_shares.py`'s docstring).
|
| 661 |
+
#
|
| 662 |
+
# β The bypass was keyed on the FIELD NAME, never on the value being a coordinate, so it
|
| 663 |
+
# forwarded whatever a column called `lat` happened to hold β a string, a note, anything.
|
| 664 |
+
# β And the shipped gate could not see it: it asserted the key NAMES rode on a map and not
|
| 665 |
+
# on a catalog, over a fixture whose rows carried no `lat` key at all β so it pinned the
|
| 666 |
+
# names while both values were `None` [[gate-answers-the-wrong-question]].
|
| 667 |
+
# KEY BY KEY. `pid` rides because the client needs a stable row identity; it is a row
|
| 668 |
+
# NUMBER within this table and names nothing outside it. `lat`/`lon` ride only on a map,
|
| 669 |
+
# and only when they PARSE as coordinates β see the block above for why that is the test.
|
| 670 |
+
"rows": [{"pid": r.get("pid"),
|
| 671 |
+
**({"lat": _coord(r.get("lat"), 90), "lon": _coord(r.get("lon"), 180)}
|
| 672 |
+
if mode == "map"
|
| 673 |
+
and _coord(r.get("lat"), 90) is not None
|
| 674 |
+
and _coord(r.get("lon"), 180) is not None else {}),
|
| 675 |
+
**{k: r.get(k) for k in keys}} for r in chosen],
|
| 676 |
+
"total": len(chosen),
|
| 677 |
+
**({"limits": limits} if limits else {}),
|
| 678 |
+
}
|
| 679 |
+
|
| 680 |
+
|
| 681 |
+
async def _bounded_body(request: Request) -> dict:
|
| 682 |
+
"""The request body, read WITH A BOUND β never `Body(...)`, never `await request.body()`.
|
| 683 |
+
|
| 684 |
+
FastAPI reads and JSON-parses the WHOLE body before the handler's first line runs, so a
|
| 685 |
+
declared model is not a bound at all; `content-length` is caller-supplied, so checking it is
|
| 686 |
+
not one either. Streaming with a running total is the actual bound.
|
| 687 |
+
"""
|
| 688 |
+
size, chunks = 0, []
|
| 689 |
+
async for chunk in request.stream():
|
| 690 |
+
size += len(chunk)
|
| 691 |
+
if size > MAX_BODY_BYTES:
|
| 692 |
+
raise err(413, "body_too_large", "that request is too large")
|
| 693 |
+
chunks.append(chunk)
|
| 694 |
+
import json
|
| 695 |
+
try:
|
| 696 |
+
parsed = json.loads(b"".join(chunks) or b"{}")
|
| 697 |
+
except ValueError:
|
| 698 |
+
raise err(400, "bad_request", "that request could not be read")
|
| 699 |
+
return parsed if isinstance(parsed, dict) else {}
|
| 700 |
+
|
| 701 |
+
|
| 702 |
+
# ββ THE SHARER'S DOOR (authenticated, creator-or-admin) ββββββββββββββββββββββββββββββββββββββ
|
| 703 |
+
#
|
| 704 |
+
# β THE NOUN IS `/view-link`, DELIBERATELY NOT `/views/{...}/publish`, and it mirrors the form
|
| 705 |
+
# door's `/form-link` for the same reason: a literal path segment sitting beside a `/{token}`
|
| 706 |
+
# wildcard is resolved by DECLARATION ORDER, and a noun that cannot collide with a token has no
|
| 707 |
+
# order to get wrong.
|
| 708 |
+
|
| 709 |
+
|
| 710 |
+
@router.get("/view-link")
|
| 711 |
+
def read_view_link(topic: str = "", view: str = "",
|
| 712 |
+
session: Session = Depends(require_session)):
|
| 713 |
+
"""This view's link state. β A GET MUST NOT MINT β opening the panel is not publishing."""
|
| 714 |
+
v, _mode = _may_administer_view(session, str(topic or ""), str(view or ""))
|
| 715 |
+
token, entry = _entry_for(session.runtime, str(topic), str(view))
|
| 716 |
+
out = _state_of(token, entry)
|
| 717 |
+
# The presentational flags contract C1 put on the view spec, echoed back so the client can
|
| 718 |
+
# tell whether the two agree. They are a MIRROR of this bucket, never its source.
|
| 719 |
+
disp = ((v.get("config") or {}).get("display") or {}) if isinstance(v, dict) else {}
|
| 720 |
+
out["displayPublished"] = disp.get("published") is True
|
| 721 |
+
return out
|
| 722 |
+
|
| 723 |
+
|
| 724 |
+
@router.post("/view-link")
|
| 725 |
+
async def mint_view_link(request: Request, session: Session = Depends(require_session)):
|
| 726 |
+
"""Publish this view, or change its access. `{topic, view, access?, passphrase?, rotate?}`.
|
| 727 |
+
|
| 728 |
+
IDEMPOTENT WITHOUT `rotate`: opening the panel twice, or switching publicβpassword, must not
|
| 729 |
+
invalidate a link somebody already sent. `rotate: true` mints a fresh token and the previous
|
| 730 |
+
one dies in the SAME write, so there is never a window where both open the view.
|
| 731 |
+
"""
|
| 732 |
+
body = await _bounded_body(request)
|
| 733 |
+
topic, view = str(body.get("topic") or ""), str(body.get("view") or "")
|
| 734 |
+
_v, _mode = _may_administer_view(session, topic, view)
|
| 735 |
+
|
| 736 |
+
access = "public" if body.get("access") == "public" else "password"
|
| 737 |
+
raw_pw = body.get("passphrase")
|
| 738 |
+
passphrase = "" if raw_pw is None else str(raw_pw)
|
| 739 |
+
if len(passphrase) > MAX_PASSPHRASE:
|
| 740 |
+
raise err(400, "passphrase_too_long",
|
| 741 |
+
f"a passphrase can be at most {MAX_PASSPHRASE} characters")
|
| 742 |
+
|
| 743 |
+
existing_token, existing = _entry_for(session.runtime, topic, view)
|
| 744 |
+
rotate = bool(body.get("rotate"))
|
| 745 |
+
fresh = secrets.token_urlsafe(TOKEN_BYTES)
|
| 746 |
+
|
| 747 |
+
# β A `password` LINK MUST END UP WITH A HASH, and there are exactly two ways to have one:
|
| 748 |
+
# the caller supplied a passphrase now, or one was already stored and is being kept. Anything
|
| 749 |
+
# else is refused HERE rather than stored and refused later β a link that cannot be opened by
|
| 750 |
+
# anybody is not a safe default, it is a broken feature that reads as a permission bug.
|
| 751 |
+
if access == "password":
|
| 752 |
+
if passphrase and len(passphrase) < MIN_PASSPHRASE:
|
| 753 |
+
raise err(400, "passphrase_too_short",
|
| 754 |
+
f"a passphrase needs at least {MIN_PASSPHRASE} characters")
|
| 755 |
+
if not passphrase and not (existing or {}).get("pw"):
|
| 756 |
+
raise err(400, "passphrase_required",
|
| 757 |
+
"a password-protected link needs a passphrase")
|
| 758 |
+
|
| 759 |
+
minted = {"token": existing_token or fresh}
|
| 760 |
+
|
| 761 |
+
def _set(cur):
|
| 762 |
+
cur = dict(cur or {})
|
| 763 |
+
prev = None
|
| 764 |
+
for stored, where in list(cur.items()):
|
| 765 |
+
if (isinstance(where, dict) and where.get("table") == topic
|
| 766 |
+
and where.get("view") == view):
|
| 767 |
+
prev = dict(where)
|
| 768 |
+
cur.pop(stored, None)
|
| 769 |
+
if not rotate:
|
| 770 |
+
minted["token"] = str(stored)
|
| 771 |
+
if rotate or prev is None:
|
| 772 |
+
minted["token"] = fresh
|
| 773 |
+
entry = {"table": topic, "view": view, "access": access,
|
| 774 |
+
"createdBy": str((prev or {}).get("createdBy") or session.uname),
|
| 775 |
+
"createdAt": float((prev or {}).get("createdAt") or time.time())}
|
| 776 |
+
# β THE STORED PASSPHRASE SURVIVES A TRIP THROUGH `public`, and the first version DROPPED
|
| 777 |
+
# it β found by a verifier that traced the toggle rather than the happy path. Publishing
|
| 778 |
+
# as `public` skipped this block entirely, so the hash was destroyed while the TOKEN was
|
| 779 |
+
# kept; switching back to `password` then demanded a new passphrase, silently, while the
|
| 780 |
+
# panel's own sentence promised the opposite ("leave blank to keep the current one").
|
| 781 |
+
# β Carrying it is inert, not lax: `_pw_ok` is consulted ONLY when `access == "password"`
|
| 782 |
+
# (`get_published`/`open_published` both test it first), and `_state_of` exposes a boolean,
|
| 783 |
+
# never the digest. A hash nobody can reach is not a secret in use β but a promise the UI
|
| 784 |
+
# makes and the store breaks is a defect either way, and the honest fix is to keep the
|
| 785 |
+
# promise rather than to reword it.
|
| 786 |
+
if passphrase:
|
| 787 |
+
salt = secrets.token_bytes(PW_SALT_BYTES)
|
| 788 |
+
entry["salt"] = salt.hex()
|
| 789 |
+
entry["iter"] = PW_ITERATIONS
|
| 790 |
+
entry["pw"] = _hash_pw(passphrase, salt)
|
| 791 |
+
elif (prev or {}).get("pw"):
|
| 792 |
+
# Carried key by key, so a future field on the entry is not silently inherited.
|
| 793 |
+
entry["salt"] = str((prev or {}).get("salt") or "")
|
| 794 |
+
entry["iter"] = int((prev or {}).get("iter") or PW_ITERATIONS)
|
| 795 |
+
entry["pw"] = str((prev or {}).get("pw") or "")
|
| 796 |
+
cur[minted["token"]] = entry
|
| 797 |
+
return cur
|
| 798 |
+
|
| 799 |
+
session.runtime.update(TOKENS_KEY, _set, flush="sync")
|
| 800 |
+
_mirror_display(session.runtime, topic, view, True, access)
|
| 801 |
+
token, entry = _entry_for(session.runtime, topic, view)
|
| 802 |
+
# β NO FABRICATED FALLBACK ENTRY HERE. The first version answered
|
| 803 |
+
# `_state_of(token or minted["token"], entry or {"access": access, "pw": "x"})`, and that
|
| 804 |
+
# `"pw": "x"` would have reported `hasPassphrase: true` about a PUBLIC link if the read-back
|
| 805 |
+
# ever came back empty β a lie in the safe-looking direction, which is the kind that survives.
|
| 806 |
+
# If the write cannot be read back, say so; do not describe a state nobody verified.
|
| 807 |
+
if not entry:
|
| 808 |
+
raise err(503, "not_saved",
|
| 809 |
+
"the link was minted but could not be read back β reload and try again")
|
| 810 |
+
return _state_of(token, entry)
|
| 811 |
+
|
| 812 |
+
|
| 813 |
+
@router.delete("/view-link")
|
| 814 |
+
async def revoke_view_link(request: Request, session: Session = Depends(require_session)):
|
| 815 |
+
"""Unpublish. `{topic, view}`.
|
| 816 |
+
|
| 817 |
+
β REVOKE ROTATES β it does not merely unset a flag. The token STRING is dropped from the
|
| 818 |
+
index in this write, so the old link stops resolving immediately; and because a later publish
|
| 819 |
+
mints `secrets.token_urlsafe(24)` afresh, the revoked string can never come back. An
|
| 820 |
+
implementation that kept the token and flipped an `enabled` flag would leave the secret live
|
| 821 |
+
in the store, one bug away from working again, and would make "revoked" a property somebody
|
| 822 |
+
could forget to check on a code path added later.
|
| 823 |
+
"""
|
| 824 |
+
body = await _bounded_body(request)
|
| 825 |
+
topic, view = str(body.get("topic") or ""), str(body.get("view") or "")
|
| 826 |
+
_may_administer_view(session, topic, view)
|
| 827 |
+
|
| 828 |
+
def _drop(cur):
|
| 829 |
+
cur = dict(cur or {})
|
| 830 |
+
for stored, where in list(cur.items()):
|
| 831 |
+
if (isinstance(where, dict) and where.get("table") == topic
|
| 832 |
+
and where.get("view") == view):
|
| 833 |
+
cur.pop(stored, None)
|
| 834 |
+
return cur
|
| 835 |
+
|
| 836 |
+
session.runtime.update(TOKENS_KEY, _drop, flush="sync")
|
| 837 |
+
# β AND THE MIRROR COMES DOWN IN THE SAME BREATH. Without this the grid goes on showing
|
| 838 |
+
# "published" about a link that no longer resolves β the half a reviewer caught.
|
| 839 |
+
_mirror_display(session.runtime, topic, view, False)
|
| 840 |
+
return {"published": False, "access": "password", "token": "", "url": ""}
|
| 841 |
+
|
| 842 |
+
|
| 843 |
+
# ββ THE PUBLIC DOOR (no session β this is the whole feature) βββββββββββββββββββββββββββββββββ
|
| 844 |
+
#
|
| 845 |
+
# β NO `Depends(require_session)` ON EITHER ROUTE BELOW, DELIBERATELY. "Public" in this app is not
|
| 846 |
+
# a flag or an allow-list entry β `main.py` has no auth middleware and no exempt-path table; a
|
| 847 |
+
# route is public exactly by omitting the dependency. Which is why the two are kept together,
|
| 848 |
+
# under one banner, rather than filed beside the sharer's routes they resemble.
|
| 849 |
+
|
| 850 |
+
|
| 851 |
+
@router.get("/published/{token}")
|
| 852 |
+
def get_published(token: str, request: Request):
|
| 853 |
+
"""The published view. Read-only, unauthenticated, projected to the view's own columns."""
|
| 854 |
+
if not _rate_ok(_client_ip(request), time.time()):
|
| 855 |
+
raise err(429, "too_many_requests", "too many requests β wait a moment and try again")
|
| 856 |
+
found = _resolve(token)
|
| 857 |
+
if not found:
|
| 858 |
+
# ββ W33-T70 β AN UNKNOWN TOKEN ANSWERS EXACTLY WHAT A LOCKED ONE ANSWERS.
|
| 859 |
+
# This used to `raise _refuse()`, and that 403 was a free oracle: one unauthenticated GET,
|
| 860 |
+
# no passphrase, no cost, told an enumerator whether a token was REAL. `_refuse`'s own
|
| 861 |
+
# docstring says the difference between "no such link" and "that link was revoked" must
|
| 862 |
+
# never be observable β and the route beside it published that difference in its status
|
| 863 |
+
# code. Sorting real tokens from fake ones is the whole of the work; once it is free, the
|
| 864 |
+
# passphrase is all that is left and it can be attacked offline-cheap.
|
| 865 |
+
# β SO THE UNKNOWN TOKEN GETS THE LOCKED SHAPE: `{"locked": true}` and nothing else β no
|
| 866 |
+
# title, no columns, no count, the same bytes a real password link returns before anyone
|
| 867 |
+
# has tried to open it. The guess then costs a POST with a passphrase, which is rate
|
| 868 |
+
# limited and PBKDF2-priced. A PUBLIC link still opens on this GET, which is what a public
|
| 869 |
+
# link is for; what stops being visible is which PASSWORD tokens exist.
|
| 870 |
+
_note_failure(_client_ip(request), time.time())
|
| 871 |
+
_equalise_pw_cost(None)
|
| 872 |
+
return {"locked": True}
|
| 873 |
+
rt, _slug, table_key, view, entry = found
|
| 874 |
+
if entry.get("access") == "password":
|
| 875 |
+
# β THE SHAPE OF THE PASSWORD ANSWER, and it is not a refusal. A locked link must render
|
| 876 |
+
# a passphrase prompt, so this 200 says "there is something here and it is locked" and
|
| 877 |
+
# NOTHING else β no title, no column names, no row count. A 403 here would be
|
| 878 |
+
# indistinguishable from a bad token, which is right for a WRONG passphrase and wrong for
|
| 879 |
+
# a link the holder has not tried to open yet.
|
| 880 |
+
return {"locked": True}
|
| 881 |
+
return _public_view(rt, table_key, view)
|
| 882 |
+
|
| 883 |
+
|
| 884 |
+
@router.post("/published/{token}")
|
| 885 |
+
async def open_published(token: str, request: Request):
|
| 886 |
+
"""Open a password-protected link. `{passphrase}`.
|
| 887 |
+
|
| 888 |
+
β A WRONG PASSPHRASE AND A WRONG TOKEN ANSWER THE SAME 403, from the same `_refuse`. If they
|
| 889 |
+
differed, the route would confirm which tokens are real to anybody willing to send one guess β
|
| 890 |
+
and a 24-byte token's entire protection is that it cannot be found by guessing.
|
| 891 |
+
β The passphrase is compared against a PBKDF2 digest with `hmac.compare_digest`, and is never
|
| 892 |
+
stored, logged or echoed. D-130's scar: a form's invited-address list is IDENTIFICATION and
|
| 893 |
+
anyone may claim an identity; this is AUTHENTICATION and is treated as one.
|
| 894 |
+
"""
|
| 895 |
+
now = time.time()
|
| 896 |
+
if not _rate_ok(_client_ip(request), now):
|
| 897 |
+
raise err(429, "too_many_requests", "too many requests β wait a moment and try again")
|
| 898 |
+
body = await _bounded_body(request)
|
| 899 |
+
found = _resolve(token)
|
| 900 |
+
if not found:
|
| 901 |
+
# ββ W33-T70 β SPEND THE PBKDF2 ANYWAY. A wrong token skipped the hash entirely and
|
| 902 |
+
# answered in ~0.4 ms while a wrong passphrase paid ~82 ms: a 206x gap, zero overlap in 24
|
| 903 |
+
# samples, and a clean separation of real tokens from fake ones for anyone with a stopwatch.
|
| 904 |
+
# Both arms now cost the same, so the identical 403 above is finally identical in practice
|
| 905 |
+
# rather than only in wording.
|
| 906 |
+
_note_failure(_client_ip(request), now)
|
| 907 |
+
_equalise_pw_cost(None)
|
| 908 |
+
raise _refuse()
|
| 909 |
+
rt, _slug, table_key, view, entry = found
|
| 910 |
+
if entry.get("access") == "password" and not _pw_ok(entry, str(body.get("passphrase") or "")):
|
| 911 |
+
_note_failure(_client_ip(request), now)
|
| 912 |
+
raise _refuse()
|
| 913 |
+
# β A link with NO passphrase must still pay, or "this token is public" is readable from the
|
| 914 |
+
# clock on a route whose whole job is to be uninformative.
|
| 915 |
+
if entry.get("access") != "password":
|
| 916 |
+
_equalise_pw_cost(entry)
|
| 917 |
+
return _public_view(rt, table_key, view)
|
api/routes_query.py
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
api/routes_records.py
CHANGED
|
@@ -15,8 +15,12 @@ one here:
|
|
| 15 |
|
| 16 |
customer / cohort `routes_customers.allowed_pids` behind the `customer_data` grant
|
| 17 |
product `routes_products.scoped_pool` behind the `product_data` grant
|
| 18 |
-
ut_<slug> `routes_tables.
|
| 19 |
-
(404 unknown / 403 not yours β a user table has no module grant)
|
|
|
|
|
|
|
|
|
|
|
|
|
| 20 |
|
| 21 |
β THE PATH KEEPS ITS `/customers/` SEGMENT. It is the shipped URL and `verify_api.py`'s E1a
|
| 22 |
section pins it; the scope now travels beside it explicitly. A nicer noun is not worth churning
|
|
@@ -49,31 +53,74 @@ def _scope_or_400(raw):
|
|
| 49 |
def _pool_or_refuse(session: Session, scope: str):
|
| 50 |
"""The pids this session may attach comments to ON THIS DATABASE β grant wall included.
|
| 51 |
|
| 52 |
-
Returns
|
| 53 |
-
surface never learns anything about the row they asked about.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 54 |
"""
|
| 55 |
if scope == "product":
|
| 56 |
from routes_products import MODULE as PRODUCT_MODULE, scoped_pool
|
| 57 |
|
| 58 |
session.require(PRODUCT_MODULE)
|
| 59 |
pids, _team, _rows, _fields = scoped_pool(session)
|
| 60 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 61 |
if scope.startswith("ut_"):
|
| 62 |
-
# No module grant exists for a user table β `_defn_or_refuse` inside `
|
| 63 |
# the wall (creator or admin, fail-closed), and it answers 404 before 403 exactly as the
|
| 64 |
# rows routes do.
|
| 65 |
-
|
| 66 |
-
|
| 67 |
-
|
| 68 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 69 |
from routes_customers import MODULE as CUSTOMER_MODULE, allowed_pids
|
| 70 |
|
| 71 |
session.require(CUSTOMER_MODULE)
|
| 72 |
-
return frozenset(allowed_pids(session))
|
| 73 |
|
| 74 |
|
| 75 |
def _in_book(pid, session, scope):
|
| 76 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 77 |
# 403, not 404: the record may exist, but this session may not inspect it.
|
| 78 |
raise err(403, "out_of_scope", "that record is not in your book")
|
| 79 |
|
|
|
|
| 15 |
|
| 16 |
customer / cohort `routes_customers.allowed_pids` behind the `customer_data` grant
|
| 17 |
product `routes_products.scoped_pool` behind the `product_data` grant
|
| 18 |
+
ut_<slug> `routes_tables.scoped_pids`, whose `_defn_or_refuse` IS the wall
|
| 19 |
+
(404 unknown / 403 not yours β a user table has no module grant).
|
| 20 |
+
β W33-T03/D-183: `scoped_pIDs`, not `scoped_pOOL` β the pool builds every
|
| 21 |
+
ROW to derive a pid set this module discards, and RAISES 409 on a
|
| 22 |
+
read-through grid past one window, which is why the record drawer painted
|
| 23 |
+
an error page on `ut_odoo_gl_lines`.
|
| 24 |
|
| 25 |
β THE PATH KEEPS ITS `/customers/` SEGMENT. It is the shipped URL and `verify_api.py`'s E1a
|
| 26 |
section pins it; the scope now travels beside it explicitly. A nicer noun is not worth churning
|
|
|
|
| 53 |
def _pool_or_refuse(session: Session, scope: str):
|
| 54 |
"""The pids this session may attach comments to ON THIS DATABASE β grant wall included.
|
| 55 |
|
| 56 |
+
Returns **`(pids, unbounded)`** β a 2-tuple on EVERY branch. Raises the topic's own 403/404/503,
|
| 57 |
+
so a caller who may not open the surface never learns anything about the row they asked about.
|
| 58 |
+
|
| 59 |
+
β `unbounded` is TRUE only when the row set could not be ENUMERATED (a read-through grid past
|
| 60 |
+
one window), never when it is merely EMPTY. Those are opposite answers and `scoped_pids` returns
|
| 61 |
+
`frozenset()` for both β see the branch below.
|
| 62 |
+
β THE SHAPE IS A CONTRACT EVEN THOUGH THIS FUNCTION IS PRIVATE, and it has two consumers that
|
| 63 |
+
do not travel together: `_in_book` here, and a NEGATIVE CONTROL in `aios-web/api/verify_scopes.py`
|
| 64 |
+
that REPLACES this function with its own lambda. A gate's test double is a caller
|
| 65 |
+
([[test-double-patched-by-a-name-list]]); when this signature moved, that double kept returning a
|
| 66 |
+
bare frozenset and the section died on `ValueError: too many values to unpack` β no tally, no
|
| 67 |
+
failing name. Change the shape here and that double changes with it.
|
| 68 |
"""
|
| 69 |
if scope == "product":
|
| 70 |
from routes_products import MODULE as PRODUCT_MODULE, scoped_pool
|
| 71 |
|
| 72 |
session.require(PRODUCT_MODULE)
|
| 73 |
pids, _team, _rows, _fields = scoped_pool(session)
|
| 74 |
+
# β `(pids, unbounded)` on EVERY branch. This one returned a bare frozenset for ten minutes
|
| 75 |
+
# after the `ut_` branch grew its second element, and `_in_book`'s unpack would have raised
|
| 76 |
+
# a `TypeError` β a 500 on every product comment β while both other branches worked. A
|
| 77 |
+
# return shape is a contract even when the function is private.
|
| 78 |
+
return (pids, False)
|
| 79 |
if scope.startswith("ut_"):
|
| 80 |
+
# No module grant exists for a user table β `_defn_or_refuse` inside `scoped_pids` IS
|
| 81 |
# the wall (creator or admin, fail-closed), and it answers 404 before 403 exactly as the
|
| 82 |
# rows routes do.
|
| 83 |
+
#
|
| 84 |
+
# ββ W33-T03 / D-183 β `scoped_pids`, NOT `scoped_pool`, AND THAT ONE WORD IS THE BUG.
|
| 85 |
+
# `scoped_pool` builds every ROW to derive a pid set this function then throws away, and on
|
| 86 |
+
# a read-through grid larger than one window it RAISES `409 window_required`. So opening the
|
| 87 |
+
# record drawer on `ut_odoo_gl_lines` (975,137 rows) painted an error page β for a panel
|
| 88 |
+
# that renders comments about ONE row it already has. `scoped_pids` answers the identical
|
| 89 |
+
# question (its docstring: *"the pid set is IDENTICAL, not merely equivalent"*) and takes
|
| 90 |
+
# W31-T20's `limits` OUT-PARAMETER instead of raising, which is the same shape `/workspace`
|
| 91 |
+
# used to become openable on those two grids.
|
| 92 |
+
from routes_tables import scoped_pids
|
| 93 |
+
|
| 94 |
+
limits = []
|
| 95 |
+
pids, _fields, _defn = scoped_pids(session, scope, limits=limits)
|
| 96 |
+
# β AN EMPTY PID SET AND AN UNRESOLVABLE ONE ARE OPPOSITE ANSWERS, and collapsing them is
|
| 97 |
+
# how a fail-closed default becomes a lie. `scoped_pids` returns `frozenset()` BOTH for a
|
| 98 |
+
# database with no rows and for a read-through grid too big to enumerate β it distinguishes
|
| 99 |
+
# them by APPENDING R6's sentence to `limits`. Without this branch the drawer would move
|
| 100 |
+
# from a 409 error page to a 403 "not in your book" on a row the user is looking at, which
|
| 101 |
+
# is the same defect wearing a politer message ([[empty-answer-vs-unfinished-answer]]).
|
| 102 |
+
# β ADMITTING HERE IS NOT A WIDENING, and the ruling is wave 27 / D-72: on a `ut_*` database
|
| 103 |
+
# THE TENANT IS THE UNIT β `scoped_pool` itself carries "no per-row owner filter; the
|
| 104 |
+
# table-level wall is the WHOLE wall". `_defn_or_refuse` has already run inside
|
| 105 |
+
# `scoped_pids` and answered 404/403. The pid set was only ever an existence check.
|
| 106 |
+
return (pids, bool(limits))
|
| 107 |
from routes_customers import MODULE as CUSTOMER_MODULE, allowed_pids
|
| 108 |
|
| 109 |
session.require(CUSTOMER_MODULE)
|
| 110 |
+
return (frozenset(allowed_pids(session)), False)
|
| 111 |
|
| 112 |
|
| 113 |
def _in_book(pid, session, scope):
|
| 114 |
+
pids, unbounded = _pool_or_refuse(session, scope)
|
| 115 |
+
if unbounded:
|
| 116 |
+
# The table wall passed and the row set is larger than this process will enumerate. Said
|
| 117 |
+
# out loud rather than silently admitting: R6's second sentence is that a limit which
|
| 118 |
+
# cannot be removed gets REPORTED, and this is the one place the report has no envelope to
|
| 119 |
+
# ride in.
|
| 120 |
+
print(f"[records] {scope}: pid membership unresolved (read-through beyond one window) β "
|
| 121 |
+
f"admitting on the table wall alone, per D-72")
|
| 122 |
+
return
|
| 123 |
+
if pid not in pids:
|
| 124 |
# 403, not 404: the record may exist, but this session may not inspect it.
|
| 125 |
raise err(403, "out_of_scope", "that record is not in your book")
|
| 126 |
|
api/routes_shares.py
CHANGED
|
@@ -336,8 +336,16 @@ def _notify_new_grantees(session, kind, oid, before, after):
|
|
| 336 |
# agree or the Inbox row is unclickable: `topic` selects the branch and `key` becomes
|
| 337 |
# `alertId`, which that branch reads as the id to open. Both constants are IMPORTED
|
| 338 |
# from there rather than typed again β one vocabulary, one owner.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 339 |
alerts.notify(user, label, topic=_SHARE_TOPIC, key=route, row_id=view_id,
|
| 340 |
-
detail=f"{sharer} shared this with you",
|
|
|
|
| 341 |
except Exception: # noqa: BLE001
|
| 342 |
return
|
| 343 |
|
|
|
|
| 336 |
# agree or the Inbox row is unclickable: `topic` selects the branch and `key` becomes
|
| 337 |
# `alertId`, which that branch reads as the id to open. Both constants are IMPORTED
|
| 338 |
# from there rather than typed again β one vocabulary, one owner.
|
| 339 |
+
# ββ W33-T28 (`ASK C-14`, answered) β `actor` IS THE SENDER, AND IT IS THE ONLY WAY
|
| 340 |
+
# THE INBOX CAN NAME ONE. An alert and an automation have no person behind them and
|
| 341 |
+
# are honestly named by their machine; a SHARE has a real person, and only this call
|
| 342 |
+
# site knows who. β It is passed as its OWN field rather than recovered from the
|
| 343 |
+
# `detail` prose below: a sender parsed out of "<name> shared this with you" breaks
|
| 344 |
+
# the first time the sentence is reworded, silently, in the header
|
| 345 |
+
# [[grep-output-is-not-source]]. The prose stays as the body; this is the From.
|
| 346 |
alerts.notify(user, label, topic=_SHARE_TOPIC, key=route, row_id=view_id,
|
| 347 |
+
detail=f"{sharer} shared this with you", actor=sharer,
|
| 348 |
+
st=session.runtime)
|
| 349 |
except Exception: # noqa: BLE001
|
| 350 |
return
|
| 351 |
|
api/routes_slack.py
ADDED
|
@@ -0,0 +1,756 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"""routes_slack.py β MANAGE AGENT: a bot per Slack channel, walled by the engine that walls a
|
| 2 |
+
person. (wave 33, owner item 10 Β· `W33-T38` / `W33-T39` / `W33-T67`.)
|
| 3 |
+
|
| 4 |
+
Owner, verbatim (2026-08-14): *"Expand Slack we need to be able to configure an AI bot PER channel
|
| 5 |
+
whose permissions we can toggle based on Fields etc of the databases, exactly like how we toggle
|
| 6 |
+
permissioning per user."*
|
| 7 |
+
|
| 8 |
+
ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
|
| 9 |
+
ββ D-84 SAID THIS WAS "adapted from OpenTag" AND THAT PREMISE IS FALSE (PRD amendment A1).
|
| 10 |
+
|
| 11 |
+
`PENDING.md` D-84 has named OpenTag as the model for per-Slack-channel permissioning since
|
| 12 |
+
2026-08-08. **OpenTag has no permission model to adapt.** `app/runtime-host.ts` is
|
| 13 |
+
`identifyUser: () => OPENTAG_SERVICE_USER` β ONE constant identity for every request β and its own
|
| 14 |
+
`sender-context.ts` says the Slack sender is *"informational only⦠not gating access."* Its
|
| 15 |
+
authorization ceiling is whole-MCP-server, decided once at process boot from env vars. It is a
|
| 16 |
+
live specimen of identity that LOOKS like a permission and is not.
|
| 17 |
+
|
| 18 |
+
`core/perm_scope.py` is already strictly more expressive: per database, per row, per FIELD, per
|
| 19 |
+
principal. So item 10 is OUR engine projected onto a CHANNEL principal β see `agent_principal`
|
| 20 |
+
below, which is the whole projection and is nine lines. Study:
|
| 21 |
+
`.claude/wiki/research/opentag-adoption.md` (licence gate: MIT, PASSED).
|
| 22 |
+
|
| 23 |
+
What OpenTag genuinely contributes is the WRITE-APPROVAL interceptor (`W33-T67`, `approval_card`
|
| 24 |
+
below) and nothing else. Its TRANSPORT is AVOID wholesale β hosted CopilotKit Intelligence, a
|
| 25 |
+
second Node process, a persistent outbound socket and each tenant's Slack credentials held by a
|
| 26 |
+
third party, against ONE process on the HF free tier. The door here is `routes_forms.py`'s proven
|
| 27 |
+
unauthenticated-public shape plus Slack's signing-secret check.
|
| 28 |
+
|
| 29 |
+
ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
|
| 30 |
+
β A CHANNEL IS A PRINCIPAL, NOT A PERSON. The wall binds to the Slack conversation id, so every
|
| 31 |
+
human in that channel reads through the same rules. That is the honest reading of "a bot per
|
| 32 |
+
channel" and the pane says it out loud, because the alternative is an admin assuming per-person
|
| 33 |
+
scoping from a screen that looks exactly like the per-person one.
|
| 34 |
+
|
| 35 |
+
β AND THE IDENTITY IS THE CHANNEL ID, NEVER ITS NAME. A channel can be renamed; its id cannot.
|
| 36 |
+
A wall bound to `#sales` silently re-points the day somebody renames the channel.
|
| 37 |
+
"""
|
| 38 |
+
import hmac
|
| 39 |
+
import json
|
| 40 |
+
import os
|
| 41 |
+
import secrets
|
| 42 |
+
import time
|
| 43 |
+
from datetime import datetime, timezone
|
| 44 |
+
|
| 45 |
+
from fastapi import APIRouter, Body, Depends, Request
|
| 46 |
+
|
| 47 |
+
from deps import Session, err, require_session
|
| 48 |
+
from routes_admin import admin_gate
|
| 49 |
+
|
| 50 |
+
router = APIRouter(prefix="/api/v1")
|
| 51 |
+
|
| 52 |
+
#: The tenant's channel agents: `{id: record}`. A per-tenant bucket, so it rides
|
| 53 |
+
#: `runtime.store_key`'s prefix and never lands in tenant #0's namespace.
|
| 54 |
+
AGENTS_KEY = "slack_agents"
|
| 55 |
+
|
| 56 |
+
#: Pending mutations awaiting a human's click (`W33-T67`). Server-only, per tenant.
|
| 57 |
+
PENDING_KEY = "slack_pending_writes"
|
| 58 |
+
|
| 59 |
+
#: How long an approval card stays clickable. An approval is a statement about the world as it was
|
| 60 |
+
#: when the card was rendered; an hour later the values it names may no longer be the values it
|
| 61 |
+
#: would write. Expiring is the honest behaviour, and an expired card says so rather than 403ing.
|
| 62 |
+
APPROVAL_TTL_S = 15 * 60
|
| 63 |
+
|
| 64 |
+
#: Slack rejects a replayed request older than 5 minutes; so do we, before any signature work.
|
| 65 |
+
SLACK_MAX_SKEW_S = 60 * 5
|
| 66 |
+
|
| 67 |
+
MAX_BODY_BYTES = 64 * 1024
|
| 68 |
+
|
| 69 |
+
#: β ROW-CAPPED BECAUSE AN APPROVER WHO CANNOT READ THE CARD CANNOT APPROVE IT. Copied
|
| 70 |
+
#: deliberately from OpenTag's `agent/write_confirmation.py`, which caps for the same reason:
|
| 71 |
+
#: past a certain length Slack collapses a message behind "Show more", and a human clicking
|
| 72 |
+
#: Approve on a card whose tail they never saw is worse than no card at all.
|
| 73 |
+
APPROVAL_MAX_ROWS = 12
|
| 74 |
+
|
| 75 |
+
|
| 76 |
+
# ββ the tenant's agent records βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
|
| 77 |
+
def _agents(rt):
|
| 78 |
+
"""`{id: record}` for one tenant. `{}` on any failure β an unreadable bucket must degrade to
|
| 79 |
+
"this tenant has no agents", never to a 500 on the settings pane."""
|
| 80 |
+
try:
|
| 81 |
+
found = rt.get(AGENTS_KEY) or {}
|
| 82 |
+
except Exception: # noqa: BLE001
|
| 83 |
+
return {}
|
| 84 |
+
return found if isinstance(found, dict) else {}
|
| 85 |
+
|
| 86 |
+
|
| 87 |
+
def _clean_agent(raw, prior=None):
|
| 88 |
+
"""One stored record, built KEY BY KEY.
|
| 89 |
+
|
| 90 |
+
β Never `dict(raw)` and never `**raw`. This record is the SUBJECT of a permission decision;
|
| 91 |
+
a client-supplied key landing in it is a client-supplied input to `perm_scope`. The same rule
|
| 92 |
+
`routes_forms._public_form` follows on the way out, applied here on the way in.
|
| 93 |
+
"""
|
| 94 |
+
prior = prior if isinstance(prior, dict) else {}
|
| 95 |
+
out = {
|
| 96 |
+
"id": str(prior.get("id") or raw.get("id") or ""),
|
| 97 |
+
"channel": str(raw.get("channel") or prior.get("channel") or "").strip()[:64],
|
| 98 |
+
"channelName": str(raw.get("channelName") or prior.get("channelName") or "").strip()[:80],
|
| 99 |
+
"label": " ".join(str(raw.get("label") or prior.get("label") or "").split())[:80],
|
| 100 |
+
"active": bool(raw.get("active", prior.get("active", True))),
|
| 101 |
+
# β DEFAULT TRUE, AND `is not False` RATHER THAN TRUTHINESS. A record written before this
|
| 102 |
+
# key existed must read as "approval required": the one direction a default here is
|
| 103 |
+
# allowed to be wrong in is the safe one, because an unattended write cannot be undone by
|
| 104 |
+
# revoking the bot afterwards [[default-must-pass-its-own-guard]].
|
| 105 |
+
"writeApproval": raw.get("writeApproval", prior.get("writeApproval", True)) is not False,
|
| 106 |
+
# The permission block. Same shape, same validator, same engine as a user's.
|
| 107 |
+
"perms": prior.get("perms") if isinstance(prior.get("perms"), dict) else {},
|
| 108 |
+
"perms_v": int(prior.get("perms_v") or 0),
|
| 109 |
+
"createdBy": str(prior.get("createdBy") or raw.get("createdBy") or ""),
|
| 110 |
+
"createdAt": str(prior.get("createdAt") or raw.get("createdAt") or ""),
|
| 111 |
+
}
|
| 112 |
+
return out
|
| 113 |
+
|
| 114 |
+
|
| 115 |
+
def _put_agent(session, agent_id, mutate):
|
| 116 |
+
"""Read-modify-write ONE agent under the tenant's bucket, synchronously.
|
| 117 |
+
|
| 118 |
+
`flush="sync"` because the client re-reads the list immediately after every write here, and an
|
| 119 |
+
async flush would let the refetch win the race and paint the pre-write state β the
|
| 120 |
+
[[refetch-eats-its-own-write]] shape.
|
| 121 |
+
"""
|
| 122 |
+
def _set(cur):
|
| 123 |
+
cur = dict(cur or {})
|
| 124 |
+
rec = cur.get(agent_id) if isinstance(cur.get(agent_id), dict) else None
|
| 125 |
+
nxt = mutate(rec)
|
| 126 |
+
if nxt is None:
|
| 127 |
+
cur.pop(agent_id, None)
|
| 128 |
+
else:
|
| 129 |
+
cur[agent_id] = nxt
|
| 130 |
+
return cur
|
| 131 |
+
|
| 132 |
+
session.runtime.update(AGENTS_KEY, _set, flush="sync")
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
# ββ ββ THE PROJECTION β THE WHOLE OF "the same engine that permissions a user" βββββββββββββββ
|
| 136 |
+
def agent_principal(agent):
|
| 137 |
+
"""A channel agent, as a PRINCIPAL `core/perm_scope` already understands.
|
| 138 |
+
|
| 139 |
+
ββ THIS IS THE ENTIRE POINT OF THE TICKET AND IT IS NINE LINES. `perm_scope` takes a user
|
| 140 |
+
RECORD β a plain dict with `perms`, `perms_v` and `role` β not a User object and not a session.
|
| 141 |
+
So a channel agent carrying a `perms` block simply IS such a record, and `may_access`,
|
| 142 |
+
`visible_fields`, `hidden_keys` and `apply_row_scope` work on it unmodified. There is no second
|
| 143 |
+
engine, no parallel vocabulary, and nothing about a channel to keep in step with anything about
|
| 144 |
+
a person. That is what the owner's *"exactly like how we toggle permissioning per user"* means
|
| 145 |
+
when it is true in code rather than in appearance.
|
| 146 |
+
|
| 147 |
+
β `role` IS HARDCODED NON-ADMIN AND MUST STAY SO. `perm_scope.may_access` returns True
|
| 148 |
+
unconditionally for `role == 'admin'` β the break-glass clause that keeps the owner out of a
|
| 149 |
+
locked store. A bot has no such emergency and no hands: an agent record that could carry
|
| 150 |
+
`role: 'admin'` would be one stored key away from bypassing every wall on this page. The key is
|
| 151 |
+
not copied from the record; it is written here, every time.
|
| 152 |
+
|
| 153 |
+
β AND `perms_v` IS FORCED TO THE CURRENT VERSION, which makes an UNDECLARED database DENY
|
| 154 |
+
(C-PERM amendment 4). Without it a fresh agent would fall through to `perms.may_open`'s legacy
|
| 155 |
+
grant wall and read `modules: 'all'`-shaped defaults β i.e. a brand-new bot would start with
|
| 156 |
+
access to everything. Fail-closed from the first byte.
|
| 157 |
+
"""
|
| 158 |
+
import core.perm_scope as perm_scope
|
| 159 |
+
return {
|
| 160 |
+
"username": f"slack:{(agent or {}).get('channel') or '?'}",
|
| 161 |
+
"role": "agent",
|
| 162 |
+
"perms": (agent or {}).get("perms") or {},
|
| 163 |
+
"perms_v": perm_scope.PERMS_VERSION,
|
| 164 |
+
# No `bus`, no `agent`: a channel is not a business unit and not a salesperson. Absent
|
| 165 |
+
# rather than 'all' β `perms.allowed_bu_labels` narrows on absence, which is the direction
|
| 166 |
+
# this must fail in.
|
| 167 |
+
}
|
| 168 |
+
|
| 169 |
+
|
| 170 |
+
def agent_may_read(agent, module):
|
| 171 |
+
"""May this channel open `module` at all?"""
|
| 172 |
+
import core.perm_scope as perm_scope
|
| 173 |
+
if not (agent or {}).get("active", True):
|
| 174 |
+
return False
|
| 175 |
+
return bool(perm_scope.may_access(agent_principal(agent), module))
|
| 176 |
+
|
| 177 |
+
|
| 178 |
+
def agent_visible_fields(agent, fields, module):
|
| 179 |
+
"""`fields` minus this channel's hidden closure β the SAME transitive closure a person gets,
|
| 180 |
+
so a formula over a hidden column cannot leak it back through arithmetic."""
|
| 181 |
+
import core.perm_scope as perm_scope
|
| 182 |
+
return perm_scope.visible_fields(fields, agent_principal(agent), module)
|
| 183 |
+
|
| 184 |
+
|
| 185 |
+
def agent_rows(agent, rows, module, fields, ctx=None):
|
| 186 |
+
"""The rows this channel may receive β `permits()`, so an unanswerable permanent filter DENIES
|
| 187 |
+
rather than being ignored."""
|
| 188 |
+
import core.perm_scope as perm_scope
|
| 189 |
+
p = agent_principal(agent)
|
| 190 |
+
hide = perm_scope.hidden_keys(p, module, fields)
|
| 191 |
+
kept = perm_scope.apply_row_scope(rows, p, module, fields, ctx)
|
| 192 |
+
# Both wires, never one: the field list and the row payload are separate, and stripping only
|
| 193 |
+
# the first leaves the value sitting in the second where anyone can read it.
|
| 194 |
+
return [perm_scope.strip_row(r, hide) for r in kept]
|
| 195 |
+
|
| 196 |
+
|
| 197 |
+
# ββ the credential βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
|
| 198 |
+
def slack_creds(rt):
|
| 199 |
+
"""This TENANT's Slack credentials from its own keychain, or None.
|
| 200 |
+
|
| 201 |
+
β NO ENVIRONMENT FALLBACK, DELIBERATELY, AND THIS IS D-202's LESSON APPLIED BEFORE IT
|
| 202 |
+
HAPPENS AGAIN. Meta Ads shipped loading end-to-end and was still not a connector, because
|
| 203 |
+
`keychain.meta_creds` had no caller and the token came from the owner's `.env` β making it a
|
| 204 |
+
tenant-#0 FACT indistinguishable from a screenshot. `keychain.meta_creds`' own docstring spells
|
| 205 |
+
out the rule: handing the environment's credential to a tenant whose admin has not stored one
|
| 206 |
+
is the leak the resolver exists to prevent. So a tenant with no entry gets None and the pane
|
| 207 |
+
SAYS so.
|
| 208 |
+
|
| 209 |
+
β Reads through `list_entries` + `read_fields` (both public) rather than `keychain._first_creds`
|
| 210 |
+
(private, and in a file outside this lane's fence). Same deterministic rule: entries are
|
| 211 |
+
id-sorted, so "first" is stable across reads rather than dict-order luck.
|
| 212 |
+
"""
|
| 213 |
+
try:
|
| 214 |
+
import core.keychain as keychain
|
| 215 |
+
for row in keychain.list_entries(rt):
|
| 216 |
+
if str(row.get("type") or "") != "slack":
|
| 217 |
+
continue
|
| 218 |
+
fields = keychain.read_fields(rt, row.get("id"))
|
| 219 |
+
if isinstance(fields, dict) and fields.get("signing_secret"):
|
| 220 |
+
return fields
|
| 221 |
+
except Exception: # noqa: BLE001
|
| 222 |
+
# A locked or unreadable keychain reads as "not configured" for the PANE, which is honest;
|
| 223 |
+
# the signature check below fails closed regardless, so this cannot widen anything.
|
| 224 |
+
return None
|
| 225 |
+
return None
|
| 226 |
+
|
| 227 |
+
|
| 228 |
+
# ββ the authenticated doors (the Manage agent surface) βββββββββββββββββββββββββββββββββββββββ
|
| 229 |
+
def _summary(agent, modules):
|
| 230 |
+
"""One sentence per agent for the list row β computed here, because the alternative is one
|
| 231 |
+
round trip per row to fill one cell (the same reason `AdminUser.access` exists)."""
|
| 232 |
+
governed = [m for m in modules if m.get("enforced")]
|
| 233 |
+
perms = agent.get("perms") or {}
|
| 234 |
+
open_n = sum(1 for m in governed if (perms.get(m["key"]) or {}).get("access"))
|
| 235 |
+
if not governed:
|
| 236 |
+
return ""
|
| 237 |
+
if open_n == 0:
|
| 238 |
+
return "No access"
|
| 239 |
+
restricted = sum(1 for m in governed
|
| 240 |
+
if (perms.get(m["key"]) or {}).get("access")
|
| 241 |
+
and ((perms.get(m["key"]) or {}).get("filter")
|
| 242 |
+
or (perms.get(m["key"]) or {}).get("hiddenFields")))
|
| 243 |
+
head = (f"All {open_n} database{'' if open_n == 1 else 's'}" if open_n == len(governed)
|
| 244 |
+
else f"{open_n} of {len(governed)} databases")
|
| 245 |
+
return f"{head}, {restricted} restricted" if restricted else head
|
| 246 |
+
|
| 247 |
+
|
| 248 |
+
@router.get("/agents")
|
| 249 |
+
def list_channel_agents(session: Session = Depends(admin_gate)):
|
| 250 |
+
"""This tenant's channel agents, plus whether Slack is reachable at all."""
|
| 251 |
+
import routes_admin
|
| 252 |
+
modules = routes_admin._perm_modules(session)
|
| 253 |
+
rows = []
|
| 254 |
+
for aid, a in sorted(_agents(session.runtime).items()):
|
| 255 |
+
if not isinstance(a, dict):
|
| 256 |
+
continue
|
| 257 |
+
rows.append({"id": aid, "channel": a.get("channel") or "",
|
| 258 |
+
"channelName": a.get("channelName") or "",
|
| 259 |
+
"label": a.get("label") or "", "active": a.get("active", True) is not False,
|
| 260 |
+
"writeApproval": a.get("writeApproval", True) is not False,
|
| 261 |
+
"summary": _summary(a, modules)})
|
| 262 |
+
return {"agents": rows, "configured": slack_creds(session.runtime) is not None}
|
| 263 |
+
|
| 264 |
+
|
| 265 |
+
@router.post("/agents")
|
| 266 |
+
def create_channel_agent(body: dict = Body(default=None),
|
| 267 |
+
session: Session = Depends(admin_gate)):
|
| 268 |
+
body = body if isinstance(body, dict) else {}
|
| 269 |
+
channel = str(body.get("channel") or "").strip()
|
| 270 |
+
if not channel:
|
| 271 |
+
raise err(400, "no_channel", "a Slack channel ID is required")
|
| 272 |
+
existing = _agents(session.runtime)
|
| 273 |
+
# β ONE AGENT PER CHANNEL. Two records for one conversation would mean two walls, and nothing
|
| 274 |
+
# anywhere decides which one applies β the [[one-question-two-normalizers]] shape, in the one
|
| 275 |
+
# place where the two answers are "may read" and "may not".
|
| 276 |
+
for a in existing.values():
|
| 277 |
+
if isinstance(a, dict) and str(a.get("channel") or "") == channel:
|
| 278 |
+
raise err(409, "channel_taken",
|
| 279 |
+
"that channel already has an agent β edit it instead of adding a second")
|
| 280 |
+
aid = secrets.token_urlsafe(9)
|
| 281 |
+
rec = _clean_agent(dict(body, id=aid, createdBy=session.uname,
|
| 282 |
+
createdAt=datetime.now(timezone.utc).isoformat(timespec="seconds")))
|
| 283 |
+
_put_agent(session, aid, lambda _prior: rec)
|
| 284 |
+
fresh = _agents(session.runtime).get(aid)
|
| 285 |
+
if not isinstance(fresh, dict):
|
| 286 |
+
# The store took the write and did not record it. A 200 here would tell an administrator
|
| 287 |
+
# the agent exists when it does not.
|
| 288 |
+
raise err(503, "store_unavailable", "the agent was NOT created")
|
| 289 |
+
return {"agent": {"id": aid, "channel": rec["channel"], "channelName": rec["channelName"],
|
| 290 |
+
"label": rec["label"], "active": rec["active"],
|
| 291 |
+
"writeApproval": rec["writeApproval"], "summary": "No access"}}
|
| 292 |
+
|
| 293 |
+
|
| 294 |
+
@router.get("/agents/{agent_id}")
|
| 295 |
+
def get_channel_agent(agent_id: str, session: Session = Depends(admin_gate)):
|
| 296 |
+
"""The agent PLUS the permission envelope β the SAME shape `get_perms` answers with.
|
| 297 |
+
|
| 298 |
+
β ONE PAYLOAD SHAPE FOR TWO ROOMS. `permsModel.parsePermsPayload` parses this, and
|
| 299 |
+
`settings/ModulePermsList` renders it, because they are literally the same client code. A
|
| 300 |
+
second envelope here would mean a second parser and a second set of defaults within a wave.
|
| 301 |
+
"""
|
| 302 |
+
import routes_admin
|
| 303 |
+
a = _agents(session.runtime).get(str(agent_id))
|
| 304 |
+
if not isinstance(a, dict):
|
| 305 |
+
raise err(404, "no_such_agent", "no agent with that id")
|
| 306 |
+
modules = routes_admin._perm_modules(session)
|
| 307 |
+
enforced = [m["key"] for m in modules if m.get("enforced")]
|
| 308 |
+
stored = a.get("perms") or {}
|
| 309 |
+
principal = agent_principal(a)
|
| 310 |
+
import core.perm_scope as perm_scope
|
| 311 |
+
perms_out = {}
|
| 312 |
+
for k in enforced:
|
| 313 |
+
e = stored.get(k)
|
| 314 |
+
perms_out[k] = e if isinstance(e, dict) else {
|
| 315 |
+
"access": bool(perm_scope.may_access(principal, k)), "filter": None,
|
| 316 |
+
"hiddenFields": []}
|
| 317 |
+
return {"id": str(agent_id), "channel": a.get("channel") or "",
|
| 318 |
+
"channelName": a.get("channelName") or "", "label": a.get("label") or "",
|
| 319 |
+
"active": a.get("active", True) is not False,
|
| 320 |
+
"writeApproval": a.get("writeApproval", True) is not False,
|
| 321 |
+
"perms": perms_out,
|
| 322 |
+
# β ALWAYS THE CURRENT VERSION, because `agent_principal` forces it: the editor must
|
| 323 |
+
# render "undeclared = denied", not the legacy-grant reading it would show at 0.
|
| 324 |
+
"perms_v": perm_scope.PERMS_VERSION,
|
| 325 |
+
# A bot is NEVER an admin β see `agent_principal`. Sent so the editor never paints
|
| 326 |
+
# the "Everything (admin)" state for a principal that cannot have it.
|
| 327 |
+
"is_admin": False,
|
| 328 |
+
"modules": modules,
|
| 329 |
+
"fields_by_module": {k: routes_admin._module_fields(k) for k in enforced}}
|
| 330 |
+
|
| 331 |
+
|
| 332 |
+
@router.put("/agents/{agent_id}/perms")
|
| 333 |
+
def put_channel_agent_perms(agent_id: str, body: dict = Body(default=None),
|
| 334 |
+
session: Session = Depends(admin_gate)):
|
| 335 |
+
"""Replace this agent's permission block wholesale β the same validator a user's block gets."""
|
| 336 |
+
import routes_admin
|
| 337 |
+
body = body if isinstance(body, dict) else {}
|
| 338 |
+
if not isinstance(_agents(session.runtime).get(str(agent_id)), dict):
|
| 339 |
+
raise err(404, "no_such_agent", "no agent with that id")
|
| 340 |
+
if "perms" not in body:
|
| 341 |
+
raise err(400, "empty_patch", "no perms to save")
|
| 342 |
+
mods = routes_admin._perm_modules(session)
|
| 343 |
+
# β THE SAME `_clean_perms`, NOT A COPY OF IT. It refuses a filter this module cannot
|
| 344 |
+
# evaluate, refuses a hiddenFields key that names nothing, refuses an unenforced `ut_*` key,
|
| 345 |
+
# and refuses a BU condition the pushdown cannot read. Every one of those is exactly as true
|
| 346 |
+
# for a channel as for a person, and a second validator here is a second place for one of
|
| 347 |
+
# them to go missing.
|
| 348 |
+
cleaned = routes_admin._clean_perms(
|
| 349 |
+
body.get("perms"),
|
| 350 |
+
enforced_keys={m["key"] for m in mods if m.get("enforced")},
|
| 351 |
+
listed_keys={m["key"] for m in mods}) or {}
|
| 352 |
+
|
| 353 |
+
import core.perm_scope as perm_scope
|
| 354 |
+
|
| 355 |
+
def _mut(prior):
|
| 356 |
+
if not isinstance(prior, dict):
|
| 357 |
+
return None
|
| 358 |
+
nxt = dict(prior)
|
| 359 |
+
nxt["perms"] = cleaned
|
| 360 |
+
nxt["perms_v"] = perm_scope.PERMS_VERSION
|
| 361 |
+
return nxt
|
| 362 |
+
|
| 363 |
+
_put_agent(session, str(agent_id), _mut)
|
| 364 |
+
fresh = _agents(session.runtime).get(str(agent_id)) or {}
|
| 365 |
+
if (fresh.get("perms") or {}) != cleaned:
|
| 366 |
+
# The one direction this must never fail in: telling an administrator the wall is up when
|
| 367 |
+
# it is not.
|
| 368 |
+
raise err(503, "store_unavailable", "the permissions were not saved β the agent is UNCHANGED")
|
| 369 |
+
return {"id": str(agent_id), "perms": fresh.get("perms") or {},
|
| 370 |
+
"perms_v": int(fresh.get("perms_v") or 0)}
|
| 371 |
+
|
| 372 |
+
|
| 373 |
+
@router.patch("/agents/{agent_id}")
|
| 374 |
+
def patch_channel_agent(agent_id: str, body: dict = Body(default=None),
|
| 375 |
+
session: Session = Depends(admin_gate)):
|
| 376 |
+
body = body if isinstance(body, dict) else {}
|
| 377 |
+
if not isinstance(_agents(session.runtime).get(str(agent_id)), dict):
|
| 378 |
+
raise err(404, "no_such_agent", "no agent with that id")
|
| 379 |
+
#: β `perms` IS NOT PATCHABLE HERE. It has its own door with its own validator; accepting it
|
| 380 |
+
#: on the metadata route would be a second, unvalidated way to write the wall.
|
| 381 |
+
allowed = {k: v for k, v in body.items()
|
| 382 |
+
if k in ("label", "active", "writeApproval", "channelName")}
|
| 383 |
+
if not allowed:
|
| 384 |
+
raise err(400, "empty_patch", "nothing to change")
|
| 385 |
+
|
| 386 |
+
def _mut(prior):
|
| 387 |
+
return _clean_agent(allowed, prior=prior) if isinstance(prior, dict) else None
|
| 388 |
+
|
| 389 |
+
_put_agent(session, str(agent_id), _mut)
|
| 390 |
+
import routes_admin
|
| 391 |
+
a = _agents(session.runtime).get(str(agent_id)) or {}
|
| 392 |
+
return {"agent": {"id": str(agent_id), "channel": a.get("channel") or "",
|
| 393 |
+
"channelName": a.get("channelName") or "", "label": a.get("label") or "",
|
| 394 |
+
"active": a.get("active", True) is not False,
|
| 395 |
+
"writeApproval": a.get("writeApproval", True) is not False,
|
| 396 |
+
"summary": _summary(a, routes_admin._perm_modules(session))}}
|
| 397 |
+
|
| 398 |
+
|
| 399 |
+
@router.delete("/agents/{agent_id}")
|
| 400 |
+
def delete_channel_agent(agent_id: str, session: Session = Depends(admin_gate)):
|
| 401 |
+
if not isinstance(_agents(session.runtime).get(str(agent_id)), dict):
|
| 402 |
+
raise err(404, "no_such_agent", "no agent with that id")
|
| 403 |
+
_put_agent(session, str(agent_id), lambda _prior: None)
|
| 404 |
+
if isinstance(_agents(session.runtime).get(str(agent_id)), dict):
|
| 405 |
+
raise err(503, "store_unavailable", "the agent was NOT removed")
|
| 406 |
+
return {"ok": True}
|
| 407 |
+
|
| 408 |
+
|
| 409 |
+
# ββ β W33-T67: THE WRITE-APPROVAL GATE βββββββββββββββββββββββββββββββββββββββββββββββββββββββ
|
| 410 |
+
def _is_empty(value):
|
| 411 |
+
"""Is this value ABSENT, as opposed to falsy?
|
| 412 |
+
|
| 413 |
+
β COPIED EXACTLY FROM OpenTag's `agent/write_confirmation.py`, and the exactness is the point:
|
| 414 |
+
`0` and `False` are VALUES a human must see on the card. Setting a price to 0 or a flag to
|
| 415 |
+
False is precisely the kind of write somebody needs to approve, and a naive `if not value`
|
| 416 |
+
drops both rows silently β the approver then reads a card that does not describe the write
|
| 417 |
+
they are approving. The MIT licence gate for this borrowing is recorded in
|
| 418 |
+
`.claude/wiki/research/opentag-adoption.md`.
|
| 419 |
+
"""
|
| 420 |
+
return value is None or (isinstance(value, str) and value.strip() == "")
|
| 421 |
+
|
| 422 |
+
|
| 423 |
+
def approval_card(action, values, agent=None):
|
| 424 |
+
"""The card a human reads before a bot writes. `{action, rows, truncated, note}`.
|
| 425 |
+
|
| 426 |
+
β ROW-CAPPED, and the cap is a SAFETY property rather than a layout one: past a certain
|
| 427 |
+
length Slack collapses a message behind "Show more", and **an approver who cannot read the
|
| 428 |
+
card cannot approve it.** When rows are dropped the card SAYS how many β a truncation nobody
|
| 429 |
+
was told about is the violation, not the truncation (wave-30 R6's second sentence).
|
| 430 |
+
"""
|
| 431 |
+
rows = [{"field": str(k), "value": v}
|
| 432 |
+
for k, v in (values or {}).items() if not _is_empty(v)]
|
| 433 |
+
rows.sort(key=lambda r: r["field"])
|
| 434 |
+
shown, dropped = rows[:APPROVAL_MAX_ROWS], max(0, len(rows) - APPROVAL_MAX_ROWS)
|
| 435 |
+
return {
|
| 436 |
+
"action": str(action or "")[:80],
|
| 437 |
+
"rows": shown,
|
| 438 |
+
"truncated": dropped,
|
| 439 |
+
"note": (f"{dropped} more field(s) not shown β open the record to review them before "
|
| 440 |
+
f"approving." if dropped else ""),
|
| 441 |
+
"agent": (agent or {}).get("label") or (agent or {}).get("channel") or "",
|
| 442 |
+
}
|
| 443 |
+
|
| 444 |
+
|
| 445 |
+
def intercept_write(agent, action, values, stash):
|
| 446 |
+
"""THE INTERCEPTOR. Returns `("commit", None)` or `("await_approval", card)`.
|
| 447 |
+
|
| 448 |
+
β The one thing worth taking from OpenTag: a MUTATING tool call is halted, rendered as a card
|
| 449 |
+
naming the action and its values, and committed only on an explicit human accept. Everything
|
| 450 |
+
else in that repo β the transport, the runtime, the identity model β is AVOID (amendment A1).
|
| 451 |
+
|
| 452 |
+
β FAIL-CLOSED ON A MISSING FLAG: `is not False`, so a record written before `writeApproval`
|
| 453 |
+
existed requires approval. The unsafe direction here is not recoverable β revoking a bot does
|
| 454 |
+
not un-write what it wrote.
|
| 455 |
+
"""
|
| 456 |
+
if (agent or {}).get("writeApproval", True) is not False:
|
| 457 |
+
card = approval_card(action, values, agent)
|
| 458 |
+
stash(card)
|
| 459 |
+
return "await_approval", card
|
| 460 |
+
return "commit", None
|
| 461 |
+
|
| 462 |
+
|
| 463 |
+
def _pending(rt):
|
| 464 |
+
try:
|
| 465 |
+
found = rt.get(PENDING_KEY) or {}
|
| 466 |
+
except Exception: # noqa: BLE001
|
| 467 |
+
return {}
|
| 468 |
+
return found if isinstance(found, dict) else {}
|
| 469 |
+
|
| 470 |
+
|
| 471 |
+
def stash_pending(rt, agent, action, values, now=None):
|
| 472 |
+
"""Store one awaiting-approval mutation and return its token.
|
| 473 |
+
|
| 474 |
+
The token is what rides the card's button, so it is `secrets.token_urlsafe` and not the
|
| 475 |
+
action's id: a guessable value on an unauthenticated door is a way to approve somebody else's
|
| 476 |
+
write. Server-only bucket, per tenant, exactly as `routes_forms.TOKENS_KEY` is.
|
| 477 |
+
"""
|
| 478 |
+
token = secrets.token_urlsafe(18)
|
| 479 |
+
row = {"at": float(now if now is not None else time.time()),
|
| 480 |
+
"channel": str((agent or {}).get("channel") or ""),
|
| 481 |
+
"action": str(action or "")[:80],
|
| 482 |
+
"values": values if isinstance(values, dict) else {}}
|
| 483 |
+
rt.update(PENDING_KEY, lambda cur: {**(cur or {}), token: row}, flush="sync")
|
| 484 |
+
return token
|
| 485 |
+
|
| 486 |
+
|
| 487 |
+
#: `{action kind: fn(rt, row) -> None}`. Registered by whatever can actually perform a mutation.
|
| 488 |
+
#:
|
| 489 |
+
#: ββ EMPTY IN PRODUCTION TODAY, AND SAYING SO IS THE POINT. `commit_pending` below is the ONE
|
| 490 |
+
#: place an approved write may be performed, so it is the place a negative control can bite β but
|
| 491 |
+
#: a gate is only as honest as what it guards. Until something registers here, an approved card
|
| 492 |
+
#: performs NOTHING and `commit_pending` returns `no_committer` rather than pretending. That is a
|
| 493 |
+
#: declared absence, not a silent one [[flag-shipped-without-its-writer]].
|
| 494 |
+
_COMMITTERS = {}
|
| 495 |
+
|
| 496 |
+
|
| 497 |
+
def register_committer(kind, fn):
|
| 498 |
+
"""Declare who may perform an approved mutation of `kind`. Idempotent by key."""
|
| 499 |
+
_COMMITTERS[str(kind)] = fn
|
| 500 |
+
|
| 501 |
+
|
| 502 |
+
def commit_pending(rt, token, approved, now=None):
|
| 503 |
+
"""Resolve ONE approval card. Returns one of
|
| 504 |
+
`expired` Β· `unknown` Β· `rejected` Β· `no_committer` Β· `committed` Β· `failed`.
|
| 505 |
+
|
| 506 |
+
ββ THIS IS THE WRITE GATE, AND IT IS A SEPARATE FUNCTION FROM THE ROUTE ON PURPOSE. T67's
|
| 507 |
+
`done-when` asks for an NC proving a REJECTED card writes nothing. A control aimed at the
|
| 508 |
+
route could not bite while the route had no write in it at all β it would stay green with the
|
| 509 |
+
guard deleted, because there would be nothing for the guard to be protecting anything from
|
| 510 |
+
([[gate-can-report-green-on-nothing]], and a verifier caught exactly that on this ticket's
|
| 511 |
+
first draft). Putting the commit behind ONE named seam gives the control a real subject: the
|
| 512 |
+
gate registers a recorder, and `rejected` must leave it untouched while `approve` must call it
|
| 513 |
+
exactly once.
|
| 514 |
+
|
| 515 |
+
β THE TOKEN IS CONSUMED BEFORE EITHER BRANCH, and before any committer runs. A card that
|
| 516 |
+
survives its own click is a replayable write, and "approve twice" must never mean "write
|
| 517 |
+
twice". The delete is `flush="sync"` for the same reason.
|
| 518 |
+
"""
|
| 519 |
+
now = float(now if now is not None else time.time())
|
| 520 |
+
row = _pending(rt).get(str(token))
|
| 521 |
+
if not isinstance(row, dict):
|
| 522 |
+
return "unknown"
|
| 523 |
+
# Consume FIRST β before the TTL verdict, before the approve/reject branch, before any write.
|
| 524 |
+
rt.update(PENDING_KEY,
|
| 525 |
+
lambda cur: {k: v for k, v in (cur or {}).items() if k != str(token)},
|
| 526 |
+
flush="sync")
|
| 527 |
+
if now - float(row.get("at") or 0) > APPROVAL_TTL_S:
|
| 528 |
+
return "expired"
|
| 529 |
+
if not approved:
|
| 530 |
+
# β NOTHING BELOW THIS LINE RUNS FOR A REJECTED CARD. The whole gate is this return.
|
| 531 |
+
return "rejected"
|
| 532 |
+
fn = _COMMITTERS.get(str(row.get("action") or ""))
|
| 533 |
+
if fn is None:
|
| 534 |
+
return "no_committer"
|
| 535 |
+
try:
|
| 536 |
+
fn(rt, row)
|
| 537 |
+
except Exception: # noqa: BLE001
|
| 538 |
+
# A committer that raises must not read as a commit. The card is already consumed, so the
|
| 539 |
+
# honest report is that it failed, and the human asks again.
|
| 540 |
+
return "failed"
|
| 541 |
+
return "committed"
|
| 542 |
+
|
| 543 |
+
|
| 544 |
+
# ββ the UNAUTHENTICATED Slack door βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
|
| 545 |
+
#: Sliding window, keyed on the SLACK TEAM, never the client IP.
|
| 546 |
+
#:
|
| 547 |
+
#: β WHY NOT THE IP, WHICH IS WHAT `routes_forms` DOES. Every Slack event arrives from Slack's own
|
| 548 |
+
#: infrastructure, so an IP window is one shared bucket for every workspace on the platform: one
|
| 549 |
+
#: busy tenant would spend the allowance for all of them, and the symptom would be another
|
| 550 |
+
#: tenant's bot going quiet. The team id is the closest thing to the actual noisy party.
|
| 551 |
+
#: β It is attacker-CONTROLLED before the signature is checked, so the window is applied AFTER
|
| 552 |
+
#: verification, never before β an unsigned request is refused on cost grounds anyway (a signature
|
| 553 |
+
#: check is a single HMAC).
|
| 554 |
+
RATE_WINDOW_S, RATE_PER_WINDOW = 60, 60
|
| 555 |
+
_HITS: dict = {}
|
| 556 |
+
|
| 557 |
+
|
| 558 |
+
def _rate_ok(key, now):
|
| 559 |
+
seen = [t for t in _HITS.get(key, ()) if now - t < RATE_WINDOW_S]
|
| 560 |
+
seen.append(now)
|
| 561 |
+
_HITS[key] = seen
|
| 562 |
+
if len(_HITS) > 4096:
|
| 563 |
+
for k in [k for k, v in _HITS.items() if not v or now - v[-1] > RATE_WINDOW_S]:
|
| 564 |
+
_HITS.pop(k, None)
|
| 565 |
+
return len(seen) <= RATE_PER_WINDOW
|
| 566 |
+
|
| 567 |
+
|
| 568 |
+
async def _raw_body(request):
|
| 569 |
+
"""The body as RAW BYTES, capped.
|
| 570 |
+
|
| 571 |
+
ββ RAW, NOT PARSED, AND THAT IS NOT A STYLE CHOICE. Slack signs the literal string
|
| 572 |
+
`v0:{timestamp}:{body}` byte for byte. `routes_forms._bounded_body` β the function this is
|
| 573 |
+
otherwise copied from β returns only the parsed dict and DISCARDS the bytes, so a verbatim
|
| 574 |
+
copy of it could not verify a Slack signature at all: re-serialising the dict changes
|
| 575 |
+
whitespace and key order and the HMAC no longer matches. The bug would look like "Slack
|
| 576 |
+
signatures are always invalid", which is indistinguishable from a wrong secret.
|
| 577 |
+
|
| 578 |
+
β And it streams rather than calling `request.body()`: FastAPI would otherwise have buffered
|
| 579 |
+
the whole body before the handler's first line, so a content-length check inside the handler
|
| 580 |
+
caps nothing (`routes_forms`' own scar, recorded in its docstring).
|
| 581 |
+
"""
|
| 582 |
+
size, chunks = 0, []
|
| 583 |
+
async for chunk in request.stream():
|
| 584 |
+
size += len(chunk)
|
| 585 |
+
if size > MAX_BODY_BYTES:
|
| 586 |
+
raise err(413, "body_too_large", "that request is too large")
|
| 587 |
+
chunks.append(chunk)
|
| 588 |
+
return b"".join(chunks)
|
| 589 |
+
|
| 590 |
+
|
| 591 |
+
def _refuse():
|
| 592 |
+
"""ONE refusal for every reason. No oracle.
|
| 593 |
+
|
| 594 |
+
A wrong signature, a stale timestamp, an unknown team, an unconfigured tenant and a channel
|
| 595 |
+
with no agent all answer identically β otherwise the door tells an unauthenticated caller
|
| 596 |
+
which tenants exist and which channels are configured, which is the question it was built to
|
| 597 |
+
not answer. `routes_forms._refuse` takes the same posture for the same reason.
|
| 598 |
+
"""
|
| 599 |
+
return err(403, "bad_request", "that request could not be verified")
|
| 600 |
+
|
| 601 |
+
|
| 602 |
+
def _verify(secret, timestamp, raw, signature, now):
|
| 603 |
+
"""Slack's v0 signature, with the replay window checked FIRST."""
|
| 604 |
+
try:
|
| 605 |
+
ts = int(str(timestamp or "0"))
|
| 606 |
+
except ValueError:
|
| 607 |
+
return False
|
| 608 |
+
if abs(now - ts) > SLACK_MAX_SKEW_S:
|
| 609 |
+
return False
|
| 610 |
+
base = b"v0:" + str(ts).encode("ascii") + b":" + (raw or b"")
|
| 611 |
+
import hashlib
|
| 612 |
+
expected = "v0=" + hmac.new(str(secret).encode("utf-8"), base, hashlib.sha256).hexdigest()
|
| 613 |
+
return hmac.compare_digest(expected, str(signature or ""))
|
| 614 |
+
|
| 615 |
+
|
| 616 |
+
def _resolve_tenant(raw, timestamp, signature, now):
|
| 617 |
+
"""`(slug, runtime, creds)` for the tenant whose signing secret verifies this request.
|
| 618 |
+
|
| 619 |
+
β THE TENANT IS DECIDED BY THE SIGNATURE, NEVER BY THE PAYLOAD. A body-supplied `team_id`
|
| 620 |
+
would let an unauthenticated caller name the tenant it wants to be β the exact widening
|
| 621 |
+
`deps._user_for`'s tenant-equality check closes on the authenticated side. So every configured
|
| 622 |
+
tenant's secret is tried and the one that VERIFIES names the tenant.
|
| 623 |
+
|
| 624 |
+
β NO EARLY `break` ON A FAILED CANDIDATE and no per-tenant error: the loop's cost must not
|
| 625 |
+
depend on which tenant matched. `routes_forms._resolve` walks tenants the same way, for the
|
| 626 |
+
same reason β a public door has no session to ask.
|
| 627 |
+
"""
|
| 628 |
+
from harness import runtime as _rt
|
| 629 |
+
hit = None
|
| 630 |
+
try:
|
| 631 |
+
slugs = list(_rt.known_tenants())
|
| 632 |
+
except Exception: # noqa: BLE001
|
| 633 |
+
return None, None, None
|
| 634 |
+
for slug in slugs:
|
| 635 |
+
try:
|
| 636 |
+
rt = _rt.get_runtime(slug)
|
| 637 |
+
except Exception: # noqa: BLE001
|
| 638 |
+
continue
|
| 639 |
+
creds = slack_creds(rt)
|
| 640 |
+
if not creds:
|
| 641 |
+
continue
|
| 642 |
+
if _verify(creds.get("signing_secret"), timestamp, raw, signature, now) and hit is None:
|
| 643 |
+
hit = (slug, rt, creds)
|
| 644 |
+
return hit if hit else (None, None, None)
|
| 645 |
+
|
| 646 |
+
|
| 647 |
+
@router.post("/slack/events")
|
| 648 |
+
async def slack_events(request: Request):
|
| 649 |
+
"""Slack's Events API. UNAUTHENTICATED BY CONSTRUCTION β no `Depends(require_session)`.
|
| 650 |
+
|
| 651 |
+
β Built like `routes_forms.py`'s public door and not like OpenTag's: one process, no vendor,
|
| 652 |
+
no second runtime, no persistent outbound socket, and this tenant's Slack secret never leaves
|
| 653 |
+
this deployment (amendment A1).
|
| 654 |
+
"""
|
| 655 |
+
now = time.time()
|
| 656 |
+
raw = await _raw_body(request)
|
| 657 |
+
ts = request.headers.get("x-slack-request-timestamp")
|
| 658 |
+
sig = request.headers.get("x-slack-signature")
|
| 659 |
+
slug, rt, _creds = _resolve_tenant(raw, ts, sig, now)
|
| 660 |
+
if not rt:
|
| 661 |
+
raise _refuse()
|
| 662 |
+
|
| 663 |
+
try:
|
| 664 |
+
payload = json.loads(raw or b"{}")
|
| 665 |
+
except ValueError:
|
| 666 |
+
raise _refuse()
|
| 667 |
+
if not isinstance(payload, dict):
|
| 668 |
+
raise _refuse()
|
| 669 |
+
|
| 670 |
+
# Slack's one-time endpoint handshake. Answered ONLY after the signature verified β an
|
| 671 |
+
# unsigned challenge echo would confirm the endpoint exists to anyone who probes it.
|
| 672 |
+
if payload.get("type") == "url_verification":
|
| 673 |
+
return {"challenge": str(payload.get("challenge") or "")[:512]}
|
| 674 |
+
|
| 675 |
+
team = str(payload.get("team_id") or slug)
|
| 676 |
+
if not _rate_ok(f"{slug}:{team}", now):
|
| 677 |
+
raise err(429, "too_many_requests", "too many requests β wait a moment and try again")
|
| 678 |
+
|
| 679 |
+
event = payload.get("event") if isinstance(payload.get("event"), dict) else {}
|
| 680 |
+
channel = str(event.get("channel") or "")
|
| 681 |
+
agent = None
|
| 682 |
+
for a in _agents(rt).values():
|
| 683 |
+
if isinstance(a, dict) and str(a.get("channel") or "") == channel:
|
| 684 |
+
agent = a
|
| 685 |
+
break
|
| 686 |
+
# β NO AGENT, OR AN INACTIVE ONE, IS SILENCE β a 200 with no action. Not a 403: Slack retries
|
| 687 |
+
# a non-2xx up to three times, so refusing here would turn "this channel is not configured"
|
| 688 |
+
# into three refusals per message, and the retry storm would be the only visible symptom.
|
| 689 |
+
# β And it must not say WHICH β a distinguishable answer tells an unauthenticated caller which
|
| 690 |
+
# channels this workspace has configured.
|
| 691 |
+
if not isinstance(agent, dict) or agent.get("active", True) is False:
|
| 692 |
+
return {"ok": True}
|
| 693 |
+
|
| 694 |
+
# ββ THE ANSWERING HALF IS NOT BUILT YET, AND SAYING SO IS THE POINT. What ships here is the
|
| 695 |
+
# DOOR and the WALL: a verified request, resolved to a tenant by signature, matched to a
|
| 696 |
+
# channel agent whose `perms` block is a `perm_scope` principal (`agent_principal`). Composing
|
| 697 |
+
# a reply means an LLM call on the cheap-first ladder plus the read path, and a half-built
|
| 698 |
+
# answerer that returns something plausible is worse than one that returns nothing.
|
| 699 |
+
# Booked rather than faked [[flag-shipped-without-its-writer]].
|
| 700 |
+
return {"ok": True}
|
| 701 |
+
|
| 702 |
+
|
| 703 |
+
@router.post("/slack/interact")
|
| 704 |
+
async def slack_interact(request: Request):
|
| 705 |
+
"""The approval card's button (`W33-T67`). UNAUTHENTICATED, signature-verified, same shape."""
|
| 706 |
+
now = time.time()
|
| 707 |
+
raw = await _raw_body(request)
|
| 708 |
+
slug, rt, _creds = _resolve_tenant(raw, request.headers.get("x-slack-request-timestamp"),
|
| 709 |
+
request.headers.get("x-slack-signature"), now)
|
| 710 |
+
if not rt:
|
| 711 |
+
raise _refuse()
|
| 712 |
+
# Slack posts interactions as `application/x-www-form-urlencoded` with a `payload=` field.
|
| 713 |
+
from urllib.parse import parse_qs
|
| 714 |
+
try:
|
| 715 |
+
form = parse_qs(raw.decode("utf-8"))
|
| 716 |
+
payload = json.loads((form.get("payload") or ["{}"])[0])
|
| 717 |
+
except Exception: # noqa: BLE001
|
| 718 |
+
raise _refuse()
|
| 719 |
+
if not isinstance(payload, dict):
|
| 720 |
+
raise _refuse()
|
| 721 |
+
if not _rate_ok(f"{slug}:interact", now):
|
| 722 |
+
raise err(429, "too_many_requests", "too many requests β wait a moment and try again")
|
| 723 |
+
|
| 724 |
+
actions = payload.get("actions") if isinstance(payload.get("actions"), list) else []
|
| 725 |
+
choice = (actions[0] if actions and isinstance(actions[0], dict) else {})
|
| 726 |
+
token = str(choice.get("value") or "")
|
| 727 |
+
# β ANYTHING THAT IS NOT LITERALLY "approve" IS A REJECT. Fail-closed on a malformed,
|
| 728 |
+
# truncated or unknown action id: the direction that can be wrong here without anyone
|
| 729 |
+
# noticing is the one that writes.
|
| 730 |
+
approved = str(choice.get("action_id") or "") == "approve"
|
| 731 |
+
# β THE ROUTE DOES NOT DECIDE β `commit_pending` does, and it is the ONE seam a negative
|
| 732 |
+
# control can aim at. Consumption, the TTL, the reject branch and the committer lookup all
|
| 733 |
+
# live there; this handler only turns its verdict into a sentence.
|
| 734 |
+
verdict = commit_pending(rt, token, approved, now=now)
|
| 735 |
+
return {"text": {
|
| 736 |
+
# An unknown, already-used or expired token is not an error: a person clicking a stale
|
| 737 |
+
# card should be told it is stale, not shown a failure.
|
| 738 |
+
"unknown": "That approval is no longer available. Ask the bot again.",
|
| 739 |
+
"expired": "That approval expired before it was answered. Ask the bot again.",
|
| 740 |
+
"rejected": "Rejected. Nothing was changed.",
|
| 741 |
+
# β HONEST, not reassuring: the answering half that would register a committer is booked,
|
| 742 |
+
# so an approved card today performs nothing and says exactly that rather than "Approved."
|
| 743 |
+
"no_committer": "Approved β but this workspace has nothing configured to carry it out yet.",
|
| 744 |
+
"failed": "That change could not be completed. Nothing was saved; ask the bot again.",
|
| 745 |
+
"committed": "Approved.",
|
| 746 |
+
}.get(verdict, "That approval is no longer available. Ask the bot again.")}
|
| 747 |
+
|
| 748 |
+
|
| 749 |
+
@router.get("/slack/health")
|
| 750 |
+
def slack_health(session: Session = Depends(require_session)):
|
| 751 |
+
"""Is Slack configured for THIS tenant? Session-gated, and it answers about one tenant only β
|
| 752 |
+
enumerating the others would answer a question about our customer list."""
|
| 753 |
+
creds = slack_creds(session.runtime)
|
| 754 |
+
return {"configured": creds is not None,
|
| 755 |
+
"agents": len(_agents(session.runtime)),
|
| 756 |
+
"hasBotToken": bool((creds or {}).get("bot_token"))}
|
api/routes_starred.py
ADDED
|
@@ -0,0 +1,828 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"""routes_starred.py β WAVE 35 (rulings R4/R5/R6/R7, contracts C2/C3/C5): THE STAR.
|
| 2 |
+
|
| 3 |
+
Owner items 8, 9 and 12. **Star and "mark important" are ONE idea and ONE flag** (R4): on screen
|
| 4 |
+
the word is Star, and starring an object lands it on Home and in the new Starred module. Four
|
| 5 |
+
kinds are starrable β `database`, `agent`, `query`, `view` β and RECORDS get their own door
|
| 6 |
+
(C5, `/starred/records`), because a record's identity is `(database, pid)` rather than a bare id.
|
| 7 |
+
|
| 8 |
+
ββ THE ONE DESIGN RULE THAT DECIDES EVERYTHING BELOW: **A VIEW'S STAR IS NOT STORED HERE.**
|
| 9 |
+
C2 is explicit β `kind: "view"` writes the EXISTING `config.important` in that database's own
|
| 10 |
+
`<key>_table_workspace`, and never a second store. R4 says star and mark-important are one flag;
|
| 11 |
+
two stores for one flag is two flags that can disagree, and the badge inside the database and the
|
| 12 |
+
row on Home would then answer differently about the same view. So this file keeps THREE id lists
|
| 13 |
+
(`databases`, `agents`, `queries`) in its own per-user bucket, and for views it is a READER and a
|
| 14 |
+
WRITER of somebody else's bucket rather than an owner of anything.
|
| 15 |
+
|
| 16 |
+
β WHICH IS WHY `GET /starred` IS NOT FREE, AND EVERY CALLER MUST KNOW. Finding the starred views
|
| 17 |
+
means reading each visible database's view bucket β the same N reads `routes_nav._important_counts`
|
| 18 |
+
did before W35-T43 deleted it. Measured on tenant #0 (2026-08-16, recorded on that constant):
|
| 19 |
+
twelve buckets cost **6.2 ms WARM in total** and **7,331 ms of first fetch COLD**. So the scan is
|
| 20 |
+
budgeted, it is spent in the caller's own RECENTS order (a mark lives on a database somebody works
|
| 21 |
+
in), and a database it could not reach is named in `degraded` rather than quietly carrying no star.
|
| 22 |
+
That is R6's second sentence applied to a list: a limit that cannot be removed is REPORTED with its
|
| 23 |
+
cause, never silently enforced. **Call this AFTER first paint.**
|
| 24 |
+
|
| 25 |
+
β NO INDEX, DELIBERATELY. The obvious fix for the scan is a `starred.views` id list written beside
|
| 26 |
+
the three above. That is the second store C2 forbids: the moment the flag and the index can
|
| 27 |
+
disagree β a view deleted, a view unmarked from inside the database, a store write that lands on one
|
| 28 |
+
and not the other β the product has two answers to one question and no way to tell which is right.
|
| 29 |
+
The scan is the price of one flag, and it is paid off the critical path.
|
| 30 |
+
"""
|
| 31 |
+
import time
|
| 32 |
+
|
| 33 |
+
from fastapi import APIRouter, Body, Depends
|
| 34 |
+
|
| 35 |
+
import routes_nav
|
| 36 |
+
from deps import Session, err, require_session
|
| 37 |
+
|
| 38 |
+
router = APIRouter(prefix="/api/v1")
|
| 39 |
+
|
| 40 |
+
#: The per-user bucket holding the three ID-LIST kinds. `{username: {databases, agents, queries}}`
|
| 41 |
+
#:
|
| 42 |
+
#: β PER USER (R6), like `nav_recents` and unlike `nav_meta`: what I care about is not a fact about
|
| 43 |
+
#: the object, so a tenant-wide star would put one person's shortlist on everybody's Home.
|
| 44 |
+
_STARRED_KEY = "starred"
|
| 45 |
+
|
| 46 |
+
#: The four kinds C2 declares. `view` is the odd one out β see the header.
|
| 47 |
+
KINDS = ("database", "agent", "query", "view")
|
| 48 |
+
|
| 49 |
+
#: The three kinds this file's own bucket holds, and the payload key each answers under.
|
| 50 |
+
_LIST_KINDS = {"database": "databases", "agent": "agents", "query": "queries"}
|
| 51 |
+
|
| 52 |
+
#: A bound on each id list. β REPORTED, NEVER SILENT: a POST that would cross it is refused with
|
| 53 |
+
#: the cause and the action (unstar something), rather than being accepted and truncated. A star
|
| 54 |
+
#: silently dropped is a star the user believes they set.
|
| 55 |
+
MAX_PER_KIND = 200
|
| 56 |
+
|
| 57 |
+
#: An id is a store key, a view id or an automation id β all of which are short. Bounded so a
|
| 58 |
+
#: hostile client cannot grow one user's document with one very long string.
|
| 59 |
+
_MAX_ID = 120
|
| 60 |
+
|
| 61 |
+
#: The wall-clock ceiling on the WHOLE view scan, checked between databases β the same number and
|
| 62 |
+
#: the same reason as the `_IMPORTANT_BUDGET_S` this replaces. It bounds the FIRST request after a
|
| 63 |
+
#: container starts; warm it is not reached.
|
| 64 |
+
VIEW_SCAN_BUDGET_S = 2.5
|
| 65 |
+
|
| 66 |
+
|
| 67 |
+
def _clean_id(raw):
|
| 68 |
+
"""One id, or "" β the only shape this file stores."""
|
| 69 |
+
return str(raw or "").strip()[:_MAX_ID]
|
| 70 |
+
|
| 71 |
+
|
| 72 |
+
def _clean_list(raw):
|
| 73 |
+
"""A stored id list, validated on the way OUT as well as in.
|
| 74 |
+
|
| 75 |
+
Re-validating a read is not redundant: the bucket outlives this code and an older build (or a
|
| 76 |
+
hand edit) could have written a shape this one does not accept. Prune, never invent β the
|
| 77 |
+
posture `_clean_nav_prefs` takes one file over.
|
| 78 |
+
"""
|
| 79 |
+
if not isinstance(raw, list):
|
| 80 |
+
return []
|
| 81 |
+
out, seen = [], set()
|
| 82 |
+
for item in raw[:MAX_PER_KIND]:
|
| 83 |
+
got = _clean_id(item)
|
| 84 |
+
if got and got not in seen:
|
| 85 |
+
seen.add(got)
|
| 86 |
+
out.append(got)
|
| 87 |
+
return out
|
| 88 |
+
|
| 89 |
+
|
| 90 |
+
def _read_lists(session):
|
| 91 |
+
"""This caller's three id lists. A store blip answers empty rather than taking the page down."""
|
| 92 |
+
try:
|
| 93 |
+
mine = (session.runtime.get(_STARRED_KEY) or {}).get(session.uname) or {}
|
| 94 |
+
except Exception:
|
| 95 |
+
return {name: [] for name in _LIST_KINDS.values()}
|
| 96 |
+
if not isinstance(mine, dict):
|
| 97 |
+
return {name: [] for name in _LIST_KINDS.values()}
|
| 98 |
+
return {name: _clean_list(mine.get(name)) for name in _LIST_KINDS.values()}
|
| 99 |
+
|
| 100 |
+
|
| 101 |
+
def _database_keys(session):
|
| 102 |
+
"""`(keys, enumerated)` β every database this session may open that has a view bucket.
|
| 103 |
+
|
| 104 |
+
β `routes_nav._visible_database_keys` IS REUSED RATHER THAN RE-DERIVED, and that is not
|
| 105 |
+
tidiness: it merges the compiled registry (behind the account grant AND the tenant catalogue)
|
| 106 |
+
with `user_tables.nav_entries`, the `may_open`-filtered listing over the rows-free projection.
|
| 107 |
+
Writing a second enumeration here is how the folder-drop defect happened (wave 27, item 6): one
|
| 108 |
+
door knew about `ut_*` keys and the other did not, and the disagreeing door answered 200 while
|
| 109 |
+
storing nothing.
|
| 110 |
+
β AND IT IS NOT `_placeable_top_keys`, WHICH NEVER APPLIES THE TENANT CATALOGUE β right for a
|
| 111 |
+
cosmetic folder placement, wrong for a scan that then opens each database's view bucket. See
|
| 112 |
+
that helper's own note for the second difference (module surfaces have no views to star).
|
| 113 |
+
"""
|
| 114 |
+
return routes_nav._visible_database_keys(session)
|
| 115 |
+
|
| 116 |
+
|
| 117 |
+
def _scan_order(session, keys):
|
| 118 |
+
"""`keys`, RECENTS-FIRST β the order the scan budget is spent in.
|
| 119 |
+
|
| 120 |
+
β THE ORDER IS LOAD-BEARING AND W34-T10 LEARNED IT THE EXPENSIVE WAY. A budget spent in
|
| 121 |
+
whatever order the keys happen to arrive is a lottery: measured cold on tenant #0, that block
|
| 122 |
+
spent all of its first draft's budget on ten EMPTY Odoo buckets and was cut off two rows before
|
| 123 |
+
`customer_data`, which holds the only marked view in the tenant. The feature would have been
|
| 124 |
+
correct and shown nothing. A star lives on a database somebody works in, and `nav_recents` is
|
| 125 |
+
exactly that list, newest first.
|
| 126 |
+
"""
|
| 127 |
+
recents = routes_nav._read_recents(session.runtime, session.uname, keys)
|
| 128 |
+
order = [r["key"] for r in recents]
|
| 129 |
+
seen = set(order)
|
| 130 |
+
order += [k for k in sorted(keys) if k not in seen]
|
| 131 |
+
return order
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
def _view_docs(session, order):
|
| 135 |
+
"""`({key: workspace_doc}, unread)` β each database's view bucket, PROJECTED, within budget.
|
| 136 |
+
|
| 137 |
+
β PROJECTED, and the two dropped keys are what makes this affordable: `overlays` is per-record
|
| 138 |
+
cell values and `fields` is the schema stratum, neither of which says anything about a view. On
|
| 139 |
+
`customer_data` they are most of the bucket.
|
| 140 |
+
β `unread` is a store blip OR the budget β reported, never a confident absence.
|
| 141 |
+
"""
|
| 142 |
+
import core.view_templates as view_templates
|
| 143 |
+
docs, unread = {}, []
|
| 144 |
+
started = time.perf_counter()
|
| 145 |
+
for key in order:
|
| 146 |
+
ws_key = view_templates.workspace_key(key)
|
| 147 |
+
if not ws_key:
|
| 148 |
+
continue # a module surface or a folder head, not a table at all
|
| 149 |
+
if time.perf_counter() - started > VIEW_SCAN_BUDGET_S:
|
| 150 |
+
unread.append(key)
|
| 151 |
+
continue
|
| 152 |
+
try:
|
| 153 |
+
docs[key] = session.runtime.get_projection(ws_key,
|
| 154 |
+
drop=("overlays", "fields")) or {}
|
| 155 |
+
except Exception:
|
| 156 |
+
unread.append(key)
|
| 157 |
+
return docs, unread
|
| 158 |
+
|
| 159 |
+
|
| 160 |
+
def _refresh_one(session, cache, key):
|
| 161 |
+
"""Re-read ONE database's bucket inside a cache the caller already holds.
|
| 162 |
+
|
| 163 |
+
β THIS IS WHY A WRITE MAY REUSE A SCAN AT ALL. The star write changes exactly one bucket, so
|
| 164 |
+
every OTHER document in the cache is still true β but the one just written is stale by
|
| 165 |
+
definition, and serving it back would answer the POST with the flag's OLD value. That is a lost
|
| 166 |
+
write wearing the face of a failed read ([[refetch-eats-its-own-write]] in reverse), and it is
|
| 167 |
+
the trap that makes "just reuse the cache" wrong without this function.
|
| 168 |
+
"""
|
| 169 |
+
import core.view_templates as view_templates
|
| 170 |
+
order, docs, unread = cache
|
| 171 |
+
ws_key = view_templates.workspace_key(key)
|
| 172 |
+
if not ws_key:
|
| 173 |
+
return cache
|
| 174 |
+
try:
|
| 175 |
+
docs[key] = session.runtime.get_projection(ws_key, drop=("overlays", "fields")) or {}
|
| 176 |
+
except Exception:
|
| 177 |
+
docs.pop(key, None)
|
| 178 |
+
if key not in unread:
|
| 179 |
+
unread.append(key)
|
| 180 |
+
return (order, docs, unread)
|
| 181 |
+
|
| 182 |
+
|
| 183 |
+
def _scan_starred_views(session, keys=None, cache=None):
|
| 184 |
+
"""`(rows, unread)` β every view this caller has starred, newest-worked database first.
|
| 185 |
+
|
| 186 |
+
A row is `{"id", "database", "name", "config"}`. β `config` is carried so the COUNTS route does
|
| 187 |
+
not have to read every bucket a second time: `_view_docs` is the expensive half of this file
|
| 188 |
+
(7,331 ms cold for twelve buckets) and two consumers asking the same question twice per request
|
| 189 |
+
is the 1+N shape D-175 spent a wave removing from `/nav`. `_starred_views` below drops it for the
|
| 190 |
+
wire.
|
| 191 |
+
|
| 192 |
+
β `cache` IS `(order, docs, unread)` FROM AN EARLIER PASS IN THE SAME REQUEST, and it exists
|
| 193 |
+
because the view-star WRITE otherwise scanned every bucket TWICE: once in `_find_view` to locate
|
| 194 |
+
the view, then again to build the answer. That is the same 1+N shape, in the same file, on the
|
| 195 |
+
same expensive read β introduced an hour after it was removed one function away. A caller that
|
| 196 |
+
has written must `_refresh_one` the database it wrote before passing its cache.
|
| 197 |
+
"""
|
| 198 |
+
if cache is not None:
|
| 199 |
+
order, docs, unread = cache
|
| 200 |
+
else:
|
| 201 |
+
if keys is None:
|
| 202 |
+
keys, _ = _database_keys(session)
|
| 203 |
+
order = _scan_order(session, keys)
|
| 204 |
+
docs, unread = _view_docs(session, order)
|
| 205 |
+
granted = routes_nav._granted_view_ids(session)
|
| 206 |
+
out = []
|
| 207 |
+
for key in order:
|
| 208 |
+
doc = docs.get(key)
|
| 209 |
+
if doc is None:
|
| 210 |
+
continue
|
| 211 |
+
for vid, view in routes_nav._visible_views(doc, session.uname, session.admin,
|
| 212 |
+
granted).items():
|
| 213 |
+
cfg = view.get("config") or {}
|
| 214 |
+
if cfg.get("important") is True:
|
| 215 |
+
out.append({"id": vid, "database": key,
|
| 216 |
+
"name": str(view.get("name") or vid)[:120], "config": cfg})
|
| 217 |
+
return out, unread
|
| 218 |
+
|
| 219 |
+
|
| 220 |
+
def _starred_views(session, keys=None, cache=None):
|
| 221 |
+
"""The C2 wire rows β `{"id", "database", "name"}`, with the config dropped.
|
| 222 |
+
|
| 223 |
+
β `name` is a SUPERSET of C2, published to B as `NOTE E-1`: the scan already holds the record,
|
| 224 |
+
so the name is free, and without it Home would render a starred view as a bare id.
|
| 225 |
+
β THE CONFIG DOES NOT GO ON THE WIRE. It carries `memberPids` (a curated view's whole pid list)
|
| 226 |
+
and every filter leaf, which is somebody's row set travelling to a client that asked for a label.
|
| 227 |
+
"""
|
| 228 |
+
rows, unread = _scan_starred_views(session, keys, cache=cache)
|
| 229 |
+
return ([{"id": r["id"], "database": r["database"], "name": r["name"]} for r in rows],
|
| 230 |
+
unread)
|
| 231 |
+
|
| 232 |
+
|
| 233 |
+
def _query_names(session, qids):
|
| 234 |
+
"""`({qid: name}, resolved)` for the caller's own Query artefacts.
|
| 235 |
+
|
| 236 |
+
β ANSWERS `ASK B-1 (2)`. C2 declares `queries: [qid]` and there is no view/query id -> label map
|
| 237 |
+
anywhere in the client, so Home and Starred would render a starred Query as a bare id. B's only
|
| 238 |
+
alternative was `GET /query`, which drags threads, messages, citations and every saved view
|
| 239 |
+
across the wire to render two strings.
|
| 240 |
+
|
| 241 |
+
β IT READS LANE C's BUCKET AND CALLS LANE C's HELPERS, WITHOUT EDITING LANE C's FILE. Query
|
| 242 |
+
state is ONE small per-user document (`query_user_<hash>`: threads, messages, citations, views β
|
| 243 |
+
no grid rows), and `_namespace_key`/`_state` are pure functions of the session. Re-deriving the
|
| 244 |
+
key here would be a second spelling of a hash, which is the one thing guaranteed to drift.
|
| 245 |
+
|
| 246 |
+
β `resolved` IS FALSE WHEN THE READ FAILED, and the caller must not prune on it β a store blip
|
| 247 |
+
would otherwise delete somebody's whole starred-query list. Same posture as
|
| 248 |
+
`_clean_nav_prefs(keep_unknown_ut=...)`.
|
| 249 |
+
"""
|
| 250 |
+
if not qids:
|
| 251 |
+
return {}, True
|
| 252 |
+
try:
|
| 253 |
+
import routes_query
|
| 254 |
+
views = (routes_query._state(session) or {}).get("views") or {}
|
| 255 |
+
except Exception:
|
| 256 |
+
return {}, False
|
| 257 |
+
out = {}
|
| 258 |
+
for qid in qids:
|
| 259 |
+
row = views.get(qid)
|
| 260 |
+
if isinstance(row, dict):
|
| 261 |
+
out[qid] = str(row.get("name") or qid)[:120]
|
| 262 |
+
return out, True
|
| 263 |
+
|
| 264 |
+
|
| 265 |
+
def _payload(session, keys=None, cache=None):
|
| 266 |
+
"""The C2 answer: the three id lists, the starred views, and what could not be read.
|
| 267 |
+
|
| 268 |
+
β `degraded` SHIPS AS `[]` RATHER THAN BEING OMITTED WHEN EMPTY β the same rule `/nav`'s
|
| 269 |
+
`omitted`/`degraded` follow, for the same reason: a key a consumer has to test for is a key a
|
| 270 |
+
consumer forgets to test for.
|
| 271 |
+
β `cache` is a scan an earlier pass in THIS request already paid for β see `_scan_starred_views`.
|
| 272 |
+
"""
|
| 273 |
+
lists = _read_lists(session)
|
| 274 |
+
if keys is None:
|
| 275 |
+
keys, _ = _database_keys(session)
|
| 276 |
+
# β PRUNED ON READ, NEVER ON WRITE β `_read_recents`' posture, and both halves are deliberate.
|
| 277 |
+
# A database whose grant was revoked must stop being offered without anybody running a
|
| 278 |
+
# migration, and must come back if the grant does. A key that is not visible therefore reaches
|
| 279 |
+
# the store and never reaches a screen.
|
| 280 |
+
# β ONLY `databases` is pruned. An agent id or a query id would each cost another store read to
|
| 281 |
+
# validate, and pruning them here buys nothing: this list is the CALLER'S OWN writes, so it can
|
| 282 |
+
# disclose nothing they did not already know, and B/C render only objects they can already see
|
| 283 |
+
# (the way `groupRecents` drops an unreachable recent). Said out loud rather than left as a gap.
|
| 284 |
+
lists["databases"] = [k for k in lists["databases"] if k in keys]
|
| 285 |
+
# β ASK B-1 (2): the names, and β because the read that answers "what is it called" also answers
|
| 286 |
+
# "does it still exist" β the same prune the databases get. β ONLY WHEN THE READ SUCCEEDED: a
|
| 287 |
+
# store blip that returned no artefacts must not delete the whole starred-query list.
|
| 288 |
+
qnames, qresolved = _query_names(session, lists["queries"])
|
| 289 |
+
if qresolved:
|
| 290 |
+
lists["queries"] = [q for q in lists["queries"] if q in qnames]
|
| 291 |
+
views, unread = _starred_views(session, keys, cache=cache)
|
| 292 |
+
out = {"databases": lists["databases"], "agents": lists["agents"],
|
| 293 |
+
"queries": lists["queries"], "queryNames": qnames,
|
| 294 |
+
"views": views, "degraded": unread}
|
| 295 |
+
if unread:
|
| 296 |
+
# R6's second sentence, in the payload: the CAUSE and what it means, not a bare list.
|
| 297 |
+
out["note"] = (f"{len(unread)} database(s) could not be read in time, so a view you "
|
| 298 |
+
f"starred there is missing from this list. Open one of them once and the "
|
| 299 |
+
f"next load will include it")
|
| 300 |
+
return out
|
| 301 |
+
|
| 302 |
+
|
| 303 |
+
@router.get("/starred")
|
| 304 |
+
def starred(session: Session = Depends(require_session)):
|
| 305 |
+
"""C2 β everything this caller has starred.
|
| 306 |
+
|
| 307 |
+
β NOT ON `/nav`'s PATH, and R7 is the ruling: `/nav` is a rows-free projection whose budget was
|
| 308 |
+
already the subject of D-175/D-185/D-288. This route is called AFTER Home/Starred paint.
|
| 309 |
+
"""
|
| 310 |
+
return _payload(session)
|
| 311 |
+
|
| 312 |
+
|
| 313 |
+
def _find_view(session, vid, database=""):
|
| 314 |
+
"""`(key, ws_key, stratum, view, cache)` for a view this caller can SEE, else None.
|
| 315 |
+
|
| 316 |
+
`stratum` is the username whose block holds it, or `table_store.SHARED_KEY`. `cache` is the
|
| 317 |
+
`(order, docs, unread)` this call paid for β but **only when it scanned everything**. With a
|
| 318 |
+
`database` hint it read ONE bucket, which is not a complete answer for the caller's whole
|
| 319 |
+
starred list, so it hands back None and the caller pays for a full pass. Handing back a partial
|
| 320 |
+
cache would silently drop every starred view on every OTHER database.
|
| 321 |
+
|
| 322 |
+
β `database` IS AN OPTIONAL FAST PATH (a superset of C2, published to B and C): the client
|
| 323 |
+
almost always knows which database the view belongs to, and naming it turns an N-bucket scan
|
| 324 |
+
into one read. Absent, the scan runs β because C2's body carries only `kind`/`id`/`on`, and a
|
| 325 |
+
door that REQUIRED the hint would break the contract two lanes are building against.
|
| 326 |
+
"""
|
| 327 |
+
import core.table_store as table_store
|
| 328 |
+
import core.view_templates as view_templates
|
| 329 |
+
|
| 330 |
+
keys, _ = _database_keys(session)
|
| 331 |
+
if database:
|
| 332 |
+
# An unknown or invisible key must not become a wider scan. It answers "not found", which
|
| 333 |
+
# is the same answer an id nobody holds gets β see the write door's note on why.
|
| 334 |
+
if database not in keys:
|
| 335 |
+
return None
|
| 336 |
+
order, cache = [database], None
|
| 337 |
+
else:
|
| 338 |
+
order = _scan_order(session, keys)
|
| 339 |
+
docs, unread = _view_docs(session, order)
|
| 340 |
+
if not database:
|
| 341 |
+
cache = (order, docs, unread)
|
| 342 |
+
granted = routes_nav._granted_view_ids(session)
|
| 343 |
+
for key in order:
|
| 344 |
+
doc = docs.get(key)
|
| 345 |
+
if doc is None:
|
| 346 |
+
continue
|
| 347 |
+
if str(vid) not in routes_nav._visible_views(doc, session.uname, session.admin, granted):
|
| 348 |
+
continue
|
| 349 |
+
ws_key = view_templates.workspace_key(key)
|
| 350 |
+
# WHICH stratum holds it decides the WALL, so it is resolved here rather than guessed.
|
| 351 |
+
# Personal first: a caller's own block is the common case and needs no grant.
|
| 352 |
+
if isinstance(doc.get(session.uname), dict) and \
|
| 353 |
+
str(vid) in ((doc[session.uname].get("views") or {})):
|
| 354 |
+
return (key, ws_key, session.uname, doc[session.uname]["views"][str(vid)], cache)
|
| 355 |
+
shared = (doc.get(table_store.SHARED_KEY) or {}).get("views") or {}
|
| 356 |
+
if str(vid) in shared:
|
| 357 |
+
return (key, ws_key, table_store.SHARED_KEY, shared[str(vid)], cache)
|
| 358 |
+
for stratum, blob in doc.items():
|
| 359 |
+
if stratum == session.uname or not isinstance(blob, dict):
|
| 360 |
+
continue
|
| 361 |
+
if str(vid) in (blob.get("views") or {}):
|
| 362 |
+
return (key, ws_key, str(stratum), blob["views"][str(vid)], cache)
|
| 363 |
+
return None
|
| 364 |
+
|
| 365 |
+
|
| 366 |
+
def _may_star_view(session, stratum, view):
|
| 367 |
+
"""May this caller WRITE the star on this view? Fail-closed.
|
| 368 |
+
|
| 369 |
+
β A VIEW ID THE CALLER CANNOT WRITE MUST REFUSE **LOUDLY**, and this is a standing scar:
|
| 370 |
+
`view_upsert` answers **200 while writing nothing** when the id belongs to a view the caller
|
| 371 |
+
cannot see, so a pinned id is effectively tenant-scoped and every symptom of it is silent
|
| 372 |
+
([[a-view-id-another-user-holds-refuses-silently]]). This function is the reason the write door
|
| 373 |
+
below raises instead of shrugging.
|
| 374 |
+
|
| 375 |
+
THREE HOMES, THREE WALLS:
|
| 376 |
+
Β· the caller's OWN stratum β theirs, no further question;
|
| 377 |
+
Β· `__shared__` β `table_store._may_edit`, which is the predicate the view door itself uses;
|
| 378 |
+
Β· another user's stratum, reached by a wave-21 grant β the grant must be `edit` or `owner`.
|
| 379 |
+
β A `view` ROLE IS NOT A WRITE GRANT. `_granted_view_ids` admits both roles because it
|
| 380 |
+
answers "can they SEE it"; this answers "may they CHANGE it", and collapsing the two would
|
| 381 |
+
let a read-only grantee mark somebody else's shared view.
|
| 382 |
+
"""
|
| 383 |
+
import core.shares as shares
|
| 384 |
+
import core.table_store as table_store
|
| 385 |
+
if stratum == session.uname:
|
| 386 |
+
return True
|
| 387 |
+
if stratum == table_store.SHARED_KEY:
|
| 388 |
+
return bool(table_store._may_edit(view, session.uname, session.admin))
|
| 389 |
+
return shares.role_for("view", str((view or {}).get("id") or ""), session.uname,
|
| 390 |
+
is_admin=session.admin,
|
| 391 |
+
st=session.runtime) in ("edit", "owner")
|
| 392 |
+
|
| 393 |
+
|
| 394 |
+
def _write_view_star(session, ws_key, stratum, vid, on):
|
| 395 |
+
"""Set `config.important` IN PLACE, in the view's own bucket. Returns True when it landed.
|
| 396 |
+
|
| 397 |
+
ββ IN PLACE, AND **NOT** THROUGH `grid_events.view_upsert` OR `table_store.save_view` β three
|
| 398 |
+
separate reasons, each of which has cost this repo something:
|
| 399 |
+
|
| 400 |
+
1. `view_upsert` REBUILDS `config` from a literal allowlist and filters `memberPids` against
|
| 401 |
+
`allowed_pids` and `cohortLock` against `cohort_ids`. Routing a flag toggle through it
|
| 402 |
+
means a cohort view whose pool this request did not assemble comes back with its curated
|
| 403 |
+
row set pruned β "the 40 accounts we agreed to call" quietly becoming fewer, under the
|
| 404 |
+
same name, with nothing going red.
|
| 405 |
+
2. `table_store.save_view` re-runs `_unique_name` against every view name in the document.
|
| 406 |
+
A star has no business re-allocating a name; a collision would RENAME the starred view.
|
| 407 |
+
3. Both are "write the whole view" doors. This writes one boolean.
|
| 408 |
+
|
| 409 |
+
β SET UNCONDITIONALLY, never "only when True" β `grid_events` records the same rule beside its
|
| 410 |
+
own `important` line: a key written only when present means unstarring is silently a no-op and
|
| 411 |
+
the stored `true` survives, i.e. a mark you can set and never clear.
|
| 412 |
+
β `bool(on)`, so a JSON `"false"` cannot become a star.
|
| 413 |
+
β FLUSH IS THE DEFAULT (sync). This is a deliberate one-at-a-time act like a folder rename, not
|
| 414 |
+
the autosave hot path `table_store` uses `async` for β and a coalesced write is exactly what
|
| 415 |
+
made eighteen 200s land zero rows in wave 33.
|
| 416 |
+
"""
|
| 417 |
+
landed = {"ok": False}
|
| 418 |
+
|
| 419 |
+
def _up(data):
|
| 420 |
+
data = data if isinstance(data, dict) else {}
|
| 421 |
+
block = data.get(stratum)
|
| 422 |
+
if not isinstance(block, dict):
|
| 423 |
+
return data
|
| 424 |
+
views = block.get("views")
|
| 425 |
+
if not isinstance(views, dict) or str(vid) not in views:
|
| 426 |
+
return data
|
| 427 |
+
view = views[str(vid)]
|
| 428 |
+
if not isinstance(view, dict):
|
| 429 |
+
return data
|
| 430 |
+
cfg = view.get("config")
|
| 431 |
+
if not isinstance(cfg, dict):
|
| 432 |
+
cfg = {}
|
| 433 |
+
view["config"] = cfg
|
| 434 |
+
cfg["important"] = bool(on)
|
| 435 |
+
landed["ok"] = True
|
| 436 |
+
return data
|
| 437 |
+
|
| 438 |
+
session.runtime.update(ws_key, _up)
|
| 439 |
+
return landed["ok"]
|
| 440 |
+
|
| 441 |
+
|
| 442 |
+
@router.post("/starred")
|
| 443 |
+
def set_starred(body: dict = Body(default=None),
|
| 444 |
+
session: Session = Depends(require_session)):
|
| 445 |
+
"""C2 β star or unstar ONE object, and answer with the caller's whole new list.
|
| 446 |
+
|
| 447 |
+
Body: `{"kind": "database"|"agent"|"query"|"view", "id": str, "on": bool}`, plus an OPTIONAL
|
| 448 |
+
`"database"` when `kind` is `view` (the fast path β see `_find_view`).
|
| 449 |
+
|
| 450 |
+
β THE WHOLE LIST COMES BACK, not an ack, because the client is optimistic-then-reconciled
|
| 451 |
+
(T15): an ack would leave the browser as the only place that knows what the new state is.
|
| 452 |
+
"""
|
| 453 |
+
body = body if isinstance(body, dict) else {}
|
| 454 |
+
kind = str(body.get("kind") or "").strip()
|
| 455 |
+
oid = _clean_id(body.get("id"))
|
| 456 |
+
if kind not in KINDS:
|
| 457 |
+
raise err(400, "bad_request",
|
| 458 |
+
f"kind must be one of {', '.join(KINDS)}")
|
| 459 |
+
if not oid:
|
| 460 |
+
raise err(400, "bad_request", "no object was named")
|
| 461 |
+
if "on" not in body or not isinstance(body.get("on"), bool):
|
| 462 |
+
# Explicit rather than defaulted: a toggle whose default is "star" turns a malformed
|
| 463 |
+
# unstar into a star, which is the one direction a user cannot undo by repeating it.
|
| 464 |
+
raise err(400, "bad_request", "`on` must be true or false")
|
| 465 |
+
on = bool(body["on"])
|
| 466 |
+
if not session.runtime.available():
|
| 467 |
+
raise err(503, "store_unavailable",
|
| 468 |
+
"the tenant store is unavailable. Nothing was saved.")
|
| 469 |
+
|
| 470 |
+
if kind == "view":
|
| 471 |
+
found = _find_view(session, oid, _clean_id(body.get("database")))
|
| 472 |
+
if not found:
|
| 473 |
+
# β 404 FOR BOTH "no such view" AND "not yours to see", deliberately: a distinct answer
|
| 474 |
+
# would turn this route into an oracle that sorts real view ids from invented ones.
|
| 475 |
+
raise err(404, "unknown_view", "that view is not available")
|
| 476 |
+
db_key, ws_key, stratum, view, cache = found
|
| 477 |
+
if not _may_star_view(session, stratum, view):
|
| 478 |
+
raise err(403, "forbidden",
|
| 479 |
+
"that view belongs to somebody else and you have read access only")
|
| 480 |
+
try:
|
| 481 |
+
landed = _write_view_star(session, ws_key, stratum, oid, on)
|
| 482 |
+
except Exception:
|
| 483 |
+
raise err(503, "store_unavailable",
|
| 484 |
+
"the star was not saved: the store refused the write.")
|
| 485 |
+
if not landed:
|
| 486 |
+
# The view moved between the read and the write (deleted, shared, unshared). Loud,
|
| 487 |
+
# because a 200 over a write that changed nothing is the defect this file's own
|
| 488 |
+
# `_may_star_view` note is about.
|
| 489 |
+
raise err(409, "view_moved",
|
| 490 |
+
"that view changed while the star was being saved. Try again")
|
| 491 |
+
# β REUSE THE SCAN, REFRESH THE ONE BUCKET WE WROTE. Without this the POST scans every view
|
| 492 |
+
# bucket TWICE β once to find the view, once to build the answer β which is the 1+N shape
|
| 493 |
+
# this file removed from `/starred/counts` an hour earlier, reintroduced by the write path.
|
| 494 |
+
# β `_refresh_one` is not optional: the written document is stale by definition and serving
|
| 495 |
+
# it back would answer the POST with the flag's OLD value.
|
| 496 |
+
if cache is not None:
|
| 497 |
+
cache = _refresh_one(session, cache, db_key)
|
| 498 |
+
return _payload(session, cache=cache)
|
| 499 |
+
|
| 500 |
+
field = _LIST_KINDS[kind]
|
| 501 |
+
uname = session.uname
|
| 502 |
+
# β THE CAP IS ENFORCED INSIDE THE TRANSACTION, NOT BY A READ BEFORE IT, AND THAT IS NOT
|
| 503 |
+
# PEDANTRY. A pre-flight `len(current) >= MAX_PER_KIND` check is advisory: two concurrent stars
|
| 504 |
+
# both pass it, both append, and the document ends up at MAX+1 β where `_clean_list`'s
|
| 505 |
+
# `raw[:MAX_PER_KIND]` then drops one **on the next read**. That is a star the user set, saw
|
| 506 |
+
# confirmed, and cannot find, which is exactly the silent truncation R6's second sentence
|
| 507 |
+
# forbids. Refusing inside the read-modify-write makes the ceiling true rather than likely.
|
| 508 |
+
# β IT RECORDS THE REFUSAL RATHER THAN RAISING FROM INSIDE `_up`: an exception thrown through
|
| 509 |
+
# `store.update` would surface as this route's own 503 "the store refused the write", which is a
|
| 510 |
+
# different and wrong story about a limit the caller can act on.
|
| 511 |
+
refused = {"full": False}
|
| 512 |
+
|
| 513 |
+
def _up(data):
|
| 514 |
+
data = data if isinstance(data, dict) else {}
|
| 515 |
+
mine = dict(data.get(uname) or {}) if isinstance(data.get(uname), dict) else {}
|
| 516 |
+
ids = _clean_list(mine.get(field))
|
| 517 |
+
if on:
|
| 518 |
+
if oid not in ids:
|
| 519 |
+
if len(ids) >= MAX_PER_KIND:
|
| 520 |
+
refused["full"] = True
|
| 521 |
+
return data
|
| 522 |
+
ids.append(oid)
|
| 523 |
+
else:
|
| 524 |
+
ids = [i for i in ids if i != oid]
|
| 525 |
+
if ids:
|
| 526 |
+
mine[field] = ids
|
| 527 |
+
else:
|
| 528 |
+
mine.pop(field, None)
|
| 529 |
+
# A user with nothing starred is REMOVED rather than stored empty β a bucket that
|
| 530 |
+
# accumulates `{}` per account is a document that grows forever and says nothing.
|
| 531 |
+
if mine:
|
| 532 |
+
data[uname] = mine
|
| 533 |
+
else:
|
| 534 |
+
data.pop(uname, None)
|
| 535 |
+
return data
|
| 536 |
+
|
| 537 |
+
try:
|
| 538 |
+
session.runtime.update(_STARRED_KEY, _up)
|
| 539 |
+
except Exception:
|
| 540 |
+
raise err(503, "store_unavailable",
|
| 541 |
+
"the star was not saved: the store refused the write.")
|
| 542 |
+
if refused["full"]:
|
| 543 |
+
# R6's second sentence: the cause and the action, never a 200 over a star that was dropped.
|
| 544 |
+
raise err(400, "starred_full",
|
| 545 |
+
f"you have starred the maximum of {MAX_PER_KIND} items of this kind. "
|
| 546 |
+
f"Unstar one to make room")
|
| 547 |
+
return _payload(session)
|
| 548 |
+
|
| 549 |
+
|
| 550 |
+
# ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ STARRED COUNTS (R7, C3)
|
| 551 |
+
#
|
| 552 |
+
# β R7: *"Row counts come from a NEW on-demand endpoint called after Home/Starred paint, never from
|
| 553 |
+
# `/nav`. A view whose count is not free shows the CAUSE, never an invented number."*
|
| 554 |
+
#
|
| 555 |
+
# β SO EVERY VID LANDS IN EXACTLY ONE OF `counts` AND `notes`, AND THAT IS THE CONTRACT (C3). A vid
|
| 556 |
+
# in neither is a client rendering nothing with no idea why; a vid in both is two answers to one
|
| 557 |
+
# question. `notes` is not a fallback for "we did not get round to it" β it is the CAUSE, in a
|
| 558 |
+
# sentence, with what to do about it, which is R6's second sentence applied to a badge.
|
| 559 |
+
|
| 560 |
+
|
| 561 |
+
def _cohort_sizes(session, key, cache):
|
| 562 |
+
"""`{cohort_id: size}` for THIS caller's own cohorts on `key`'s topic. Memoised per request.
|
| 563 |
+
|
| 564 |
+
β THIS CALLER'S OWN COHORTS ONLY, and the consequence is deliberate: a SHARED view locked to a
|
| 565 |
+
cohort somebody else owns finds no id here, so it is reported UNCOUNTED with that cause rather
|
| 566 |
+
than counted out of a stratum this session cannot see. Widening the read would make the number
|
| 567 |
+
disclose the SIZE of another person's private list, which is a leak wearing a bug fix.
|
| 568 |
+
β Read through `session.runtime`, NOT `modules.cohort`'s module-level helpers: those call
|
| 569 |
+
`core.store` directly and carry no tenant namespace. The MODULE is asked for the bucket NAME (it
|
| 570 |
+
owns that rule) and this route does the reading, which is the only tenant-correct combination.
|
| 571 |
+
"""
|
| 572 |
+
import core.view_templates as view_templates
|
| 573 |
+
import modules.cohort as cohort_mod
|
| 574 |
+
ws_key = view_templates.workspace_key(key) or ""
|
| 575 |
+
suffix = "_table_workspace"
|
| 576 |
+
scope = ws_key[:-len(suffix)] if ws_key.endswith(suffix) else key
|
| 577 |
+
if scope in cache:
|
| 578 |
+
return cache[scope]
|
| 579 |
+
try:
|
| 580 |
+
bucket = session.runtime.get(cohort_mod.key_for(scope)) or {}
|
| 581 |
+
mine = bucket.get(session.uname) or {}
|
| 582 |
+
cache[scope] = {str(cid): len(c.get("members") or [])
|
| 583 |
+
for cid, c in mine.items() if isinstance(c, dict)}
|
| 584 |
+
except Exception:
|
| 585 |
+
cache[scope] = {}
|
| 586 |
+
return cache[scope]
|
| 587 |
+
|
| 588 |
+
|
| 589 |
+
def _count_note(cfg, cohorts):
|
| 590 |
+
"""WHY this view's size is not free, as one sentence naming a cause AND a next step.
|
| 591 |
+
|
| 592 |
+
β R6's SECOND SENTENCE IS THE SPEC HERE, and a bare dash is the thing it forbids. D-253 was
|
| 593 |
+
booked once already for a limit whose explanation was hover-only, so this has to be a real
|
| 594 |
+
sentence a client can put in a `title` AND an `aria-label`.
|
| 595 |
+
β THREE DIFFERENT CAUSES, not one generic apology. A view locked to somebody else's list, a
|
| 596 |
+
filtered view and a whole-table view are three different facts, and only one of them is
|
| 597 |
+
something the reader can act on.
|
| 598 |
+
"""
|
| 599 |
+
cfg = cfg if isinstance(cfg, dict) else {}
|
| 600 |
+
lock = str(cfg.get("cohortLock") or "").strip()
|
| 601 |
+
if lock:
|
| 602 |
+
return ("This view is locked to a list owned by somebody else, so its size is not "
|
| 603 |
+
"something your account can read. Ask whoever shared it.")
|
| 604 |
+
if cfg.get("filters"):
|
| 605 |
+
return ("Counting a filtered view means reading every record, which this page does not "
|
| 606 |
+
"do. Open the database and the number is beside the view.")
|
| 607 |
+
return ("This view covers the whole database, so its size is the record count. Open the "
|
| 608 |
+
"database to see it.")
|
| 609 |
+
|
| 610 |
+
|
| 611 |
+
@router.get("/starred/counts")
|
| 612 |
+
def starred_counts(session: Session = Depends(require_session)):
|
| 613 |
+
"""C3 β `{"counts": {vid: int}, "notes": {vid: str}, "degraded": [key]}`.
|
| 614 |
+
|
| 615 |
+
β CALLED AFTER THE PAGE PAINTS, NEVER FROM `/nav` (R7). `/nav` is a rows-free projection whose
|
| 616 |
+
budget was the subject of D-175, D-185, D-288 and D-289; W35-T43 takes the last of that off it,
|
| 617 |
+
and putting a counting pass back on the nav's path would undo the whole point.
|
| 618 |
+
|
| 619 |
+
β THE COUNTER IS `routes_nav._view_record_count`, CALLED β not a second implementation. It is the
|
| 620 |
+
one function that knows which shapes are free (a cohort lock resolves to a stored member list; a
|
| 621 |
+
curated `memberPids` carries its own length) and returns None for everything else. A second
|
| 622 |
+
counter here would be free to disagree with the badge inside the database.
|
| 623 |
+
"""
|
| 624 |
+
rows, unread = _scan_starred_views(session)
|
| 625 |
+
cache, counts, notes = {}, {}, {}
|
| 626 |
+
for row in rows:
|
| 627 |
+
cfg, key, vid = row["config"], row["database"], row["id"]
|
| 628 |
+
sizes = _cohort_sizes(session, key, cache)
|
| 629 |
+
n = routes_nav._view_record_count(cfg, sizes)
|
| 630 |
+
# β EXACTLY ONE OF THE TWO MAPS (C3). The `if/else` is what makes that structural rather
|
| 631 |
+
# than a rule somebody has to remember: there is no path that writes both and none that
|
| 632 |
+
# writes neither.
|
| 633 |
+
if isinstance(n, int):
|
| 634 |
+
counts[vid] = n
|
| 635 |
+
else:
|
| 636 |
+
notes[vid] = _count_note(cfg, sizes)
|
| 637 |
+
return {"counts": counts, "notes": notes, "degraded": unread}
|
| 638 |
+
|
| 639 |
+
|
| 640 |
+
# ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ RECORD STARS (R5/R6, C5)
|
| 641 |
+
#
|
| 642 |
+
# β R5: *"Records get their own star, feeding an undeletable 'Starred records' view beside
|
| 643 |
+
# 'All records' on every database."* R6: *"Record stars are PER USER, in the same per-username
|
| 644 |
+
# stratum views already live in."*
|
| 645 |
+
#
|
| 646 |
+
# ββ THE ID LIST IS ITS OWN KEY IN THAT STRATUM AND IT DOES NOT TRAVEL THROUGH THE VIEW DOOR.
|
| 647 |
+
# D-170, measured: on a read-through grid a VIEW WRITE answers **409 `window_required`** β
|
| 648 |
+
# `/grid/events` -> `routes_tables.ut_write_ctx` -> `scoped_pids` -> `scoped_pool` ->
|
| 649 |
+
# `routes_odoo_tables.whole_pool` raises `TooBigToMaterialise`, because the shared read/write
|
| 650 |
+
# assembly insists on the pid set. `ut_odoo_order_lines` (255,286 rows) and `ut_odoo_gl_lines`
|
| 651 |
+
# (971,034) serve rows through a window correctly and refuse every view-config write. A record star
|
| 652 |
+
# stored inside a view record would therefore be IMPOSSIBLE on exactly the two biggest databases in
|
| 653 |
+
# the tenant. This writes one key in the workspace bucket and touches no pid set, so it answers 200
|
| 654 |
+
# there.
|
| 655 |
+
#
|
| 656 |
+
# β AND FOR THE SAME REASON IT DOES NOT VALIDATE THE ID AGAINST THE ROW SET. Checking that a pid
|
| 657 |
+
# exists means materialising the pool, which is the 409 again. `/nav/opened` takes the identical
|
| 658 |
+
# posture and says why: the WRITE is cheap and unvalidated, the READ is what prunes β a client
|
| 659 |
+
# intersects `memberPids` with the rows it can see, exactly as a cohort already does
|
| 660 |
+
# (`aios_grid.workspace_wire` drops absent members and reports `missing`).
|
| 661 |
+
|
| 662 |
+
#: The per-user key inside `<database>_table_workspace`. BESIDE `views`, never inside one (R6).
|
| 663 |
+
_RECORDS_KEY = "starredRecords"
|
| 664 |
+
|
| 665 |
+
#: The pinned id of the projected view. β C's rail pins this too (W35-T30) β it is a WIRE constant,
|
| 666 |
+
#: so it is exported rather than spelled twice.
|
| 667 |
+
STARRED_VIEW_ID = "starred-records"
|
| 668 |
+
STARRED_VIEW_NAME = "Starred records"
|
| 669 |
+
|
| 670 |
+
#: A bound per (user, database). Reported on overflow, never silently enforced.
|
| 671 |
+
MAX_STARRED_RECORDS = 500
|
| 672 |
+
|
| 673 |
+
|
| 674 |
+
def _record_ids(doc, uname):
|
| 675 |
+
"""This caller's starred record ids on ONE database, validated on the way out.
|
| 676 |
+
|
| 677 |
+
β INTS, AND A NON-DIGIT ID IS NOT STORED. Every record identity in this product is a digit
|
| 678 |
+
string β a pool `pid` is an int and a `ut_*` row key is `str(record_id).isdigit()` β and the
|
| 679 |
+
CLIENT's view engine reads `memberPids` as numbers (a cohort's members are ints). A mixed list
|
| 680 |
+
would make the projection match nothing on the rows it was built for, silently.
|
| 681 |
+
"""
|
| 682 |
+
raw = (doc.get(uname) or {}).get(_RECORDS_KEY) if isinstance(doc.get(uname), dict) else None
|
| 683 |
+
if not isinstance(raw, list):
|
| 684 |
+
return []
|
| 685 |
+
out, seen = [], set()
|
| 686 |
+
for item in raw[:MAX_STARRED_RECORDS]:
|
| 687 |
+
try:
|
| 688 |
+
pid = int(item)
|
| 689 |
+
except (TypeError, ValueError):
|
| 690 |
+
continue
|
| 691 |
+
if pid not in seen:
|
| 692 |
+
seen.add(pid)
|
| 693 |
+
out.append(pid)
|
| 694 |
+
return out
|
| 695 |
+
|
| 696 |
+
|
| 697 |
+
def records_view(ids):
|
| 698 |
+
"""The **"Starred records"** view, as a SavedView β or None when nothing is starred.
|
| 699 |
+
|
| 700 |
+
β THE SERVER HANDS C THE WHOLE OBJECT (C5) rather than a bare id list, so the rail cannot grow
|
| 701 |
+
a second idea of what this view is. `kind: 'system'` and `locked: True` are what make it
|
| 702 |
+
undeletable, the same two facts that protect `all-customers`.
|
| 703 |
+
|
| 704 |
+
β `memberPids` IS THE WHOLE MECHANISM: it makes this a CURATED ROW SET, which is the one shape
|
| 705 |
+
`routes_nav._view_record_count` can count for FREE β no rows read, no filter run. That is why C3
|
| 706 |
+
can put a real number beside it and why R7's counts endpoint costs nothing here.
|
| 707 |
+
β None WHEN EMPTY, not an empty view: a view listing zero records under a name promising some is
|
| 708 |
+
the shape D-229 was booked for. C shows the row only when there is something in it.
|
| 709 |
+
"""
|
| 710 |
+
pids = [int(p) for p in (ids or [])]
|
| 711 |
+
if not pids:
|
| 712 |
+
return None
|
| 713 |
+
return {
|
| 714 |
+
"id": STARRED_VIEW_ID,
|
| 715 |
+
"name": STARRED_VIEW_NAME,
|
| 716 |
+
"kind": "system",
|
| 717 |
+
"locked": True,
|
| 718 |
+
"note": "The records you starred on this database. Only you can see this list.",
|
| 719 |
+
"config": {"filters": [], "filterConj": "and", "sorts": [], "groupBy": None,
|
| 720 |
+
"colorBy": None, "rowHeightMode": "short", "order": [], "visible": [],
|
| 721 |
+
"widths": {}, "memberPids": pids},
|
| 722 |
+
}
|
| 723 |
+
|
| 724 |
+
|
| 725 |
+
def _database_or_refuse(session, key):
|
| 726 |
+
"""The workspace bucket for a database this caller may OPEN, or a refusal.
|
| 727 |
+
|
| 728 |
+
β THE SPLIT IS `routes_nav.nav_schema`'s, COPIED IN SHAPE RATHER THAN INVENTED: a `ut_*`
|
| 729 |
+
database is walled by `user_tables.may_open` (its creator or an admin or a grantee), and a
|
| 730 |
+
built-in module by `session.require`, which would 403 every `ut_` key because a user table is
|
| 731 |
+
deliberately not a module.
|
| 732 |
+
"""
|
| 733 |
+
import core.view_templates as view_templates
|
| 734 |
+
ws_key = view_templates.workspace_key(key)
|
| 735 |
+
if not ws_key:
|
| 736 |
+
raise err(404, "unknown_database", "that database is not available")
|
| 737 |
+
if key.startswith("ut_"):
|
| 738 |
+
import core.user_tables as user_tables
|
| 739 |
+
if not user_tables.may_open(key, session.uname, session.admin, st=session.runtime):
|
| 740 |
+
raise err(403, "forbidden", "that database belongs to another user")
|
| 741 |
+
else:
|
| 742 |
+
session.require(key)
|
| 743 |
+
return ws_key
|
| 744 |
+
|
| 745 |
+
|
| 746 |
+
def _records_payload(session, key, ws_key):
|
| 747 |
+
try:
|
| 748 |
+
doc = session.runtime.get_projection(ws_key, drop=("overlays", "fields")) or {}
|
| 749 |
+
except Exception:
|
| 750 |
+
doc = {}
|
| 751 |
+
ids = _record_ids(doc, session.uname)
|
| 752 |
+
return {"database": key, "ids": ids, "count": len(ids), "view": records_view(ids)}
|
| 753 |
+
|
| 754 |
+
|
| 755 |
+
@router.get("/starred/records")
|
| 756 |
+
def starred_records(database: str = "", session: Session = Depends(require_session)):
|
| 757 |
+
"""C5 β the record ids THIS caller starred on ONE database, plus the view to render.
|
| 758 |
+
|
| 759 |
+
β ONE DATABASE PER CALL, deliberately. Answering "every database" would be the N-bucket scan
|
| 760 |
+
the view half already pays for, on a route a grid calls every time it opens.
|
| 761 |
+
"""
|
| 762 |
+
key = _clean_id(database)
|
| 763 |
+
if not key:
|
| 764 |
+
raise err(400, "bad_request", "no database was named")
|
| 765 |
+
return _records_payload(session, key, _database_or_refuse(session, key))
|
| 766 |
+
|
| 767 |
+
|
| 768 |
+
@router.post("/starred/records")
|
| 769 |
+
def set_starred_record(body: dict = Body(default=None),
|
| 770 |
+
session: Session = Depends(require_session)):
|
| 771 |
+
"""C5 β star or unstar ONE record. Body `{"database": key, "id": str, "on": bool}`.
|
| 772 |
+
|
| 773 |
+
β PER USER, IN THE PER-USERNAME STRATUM, AND IT MUST NEVER FALL BACK TO A TENANT-WIDE LIST
|
| 774 |
+
(R6). One person's stars becoming everyone's is the failure mode a shared column has here β a
|
| 775 |
+
custom field on these grids is written through a per-username stratum anyway, so a "shared"
|
| 776 |
+
answer would be a deliberate widening, not a shortcut.
|
| 777 |
+
"""
|
| 778 |
+
body = body if isinstance(body, dict) else {}
|
| 779 |
+
key = _clean_id(body.get("database"))
|
| 780 |
+
raw_id = _clean_id(body.get("id"))
|
| 781 |
+
if not key:
|
| 782 |
+
raise err(400, "bad_request", "no database was named")
|
| 783 |
+
if not raw_id.isdigit():
|
| 784 |
+
# Named rather than coerced: see `_record_ids` on why a non-numeric id cannot be stored.
|
| 785 |
+
raise err(400, "bad_request", "a record id is a number")
|
| 786 |
+
if "on" not in body or not isinstance(body.get("on"), bool):
|
| 787 |
+
raise err(400, "bad_request", "`on` must be true or false")
|
| 788 |
+
pid, on = int(raw_id), bool(body["on"])
|
| 789 |
+
ws_key = _database_or_refuse(session, key)
|
| 790 |
+
if not session.runtime.available():
|
| 791 |
+
raise err(503, "store_unavailable",
|
| 792 |
+
"the tenant store is unavailable. Nothing was saved.")
|
| 793 |
+
current = _records_payload(session, key, ws_key)["ids"]
|
| 794 |
+
if on and pid not in current and len(current) >= MAX_STARRED_RECORDS:
|
| 795 |
+
raise err(400, "starred_full",
|
| 796 |
+
f"you have starred the maximum of {MAX_STARRED_RECORDS} records on this "
|
| 797 |
+
f"database. Unstar one to make room")
|
| 798 |
+
uname = session.uname
|
| 799 |
+
|
| 800 |
+
def _up(data):
|
| 801 |
+
data = data if isinstance(data, dict) else {}
|
| 802 |
+
block = data.get(uname)
|
| 803 |
+
block = dict(block) if isinstance(block, dict) else {}
|
| 804 |
+
ids = _record_ids({uname: block}, uname)
|
| 805 |
+
if on:
|
| 806 |
+
if pid not in ids:
|
| 807 |
+
ids.append(pid)
|
| 808 |
+
else:
|
| 809 |
+
ids = [i for i in ids if i != pid]
|
| 810 |
+
if ids:
|
| 811 |
+
block[_RECORDS_KEY] = ids
|
| 812 |
+
else:
|
| 813 |
+
block.pop(_RECORDS_KEY, None)
|
| 814 |
+
# β THE STRATUM IS KEPT WHEN IT STILL HOLDS ANYTHING ELSE. Popping a username whose views
|
| 815 |
+
# and overlays live in the same block would delete somebody's whole workspace to clear one
|
| 816 |
+
# star β which is why this writes `block` back rather than replacing it.
|
| 817 |
+
if block:
|
| 818 |
+
data[uname] = block
|
| 819 |
+
else:
|
| 820 |
+
data.pop(uname, None)
|
| 821 |
+
return data
|
| 822 |
+
|
| 823 |
+
try:
|
| 824 |
+
session.runtime.update(ws_key, _up)
|
| 825 |
+
except Exception:
|
| 826 |
+
raise err(503, "store_unavailable",
|
| 827 |
+
"the star was not saved: the store refused the write.")
|
| 828 |
+
return _records_payload(session, key, ws_key)
|
api/routes_statements.py
CHANGED
|
@@ -31,6 +31,10 @@ from fastapi import APIRouter, Body, Depends
|
|
| 31 |
from deps import Session, err
|
| 32 |
from routes_admin import admin_gate
|
| 33 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 34 |
router = APIRouter(prefix="/api/v1")
|
| 35 |
|
| 36 |
#: Cache the Odoo follow-up pull briefly. The Streamlit page used `@st.cache_data(ttl=1800)`; the
|
|
@@ -48,8 +52,17 @@ def _royal_only(session: Session) -> Session:
|
|
| 48 |
"""β See the module docstring, guardrail 3. The send client is env-credentialed, so it is
|
| 49 |
tenant #0's and only tenant #0's. Refuse for anyone else rather than send as the wrong company.
|
| 50 |
|
| 51 |
-
Keyed on the runtime, never on a request field: a tenant is a property of the SESSION.
|
| 52 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 53 |
raise err(404, "not_found", "statements are not configured for this workspace")
|
| 54 |
return session
|
| 55 |
|
|
@@ -91,7 +104,9 @@ def statements(refresh: int = 0, session: Session = Depends(_gate)):
|
|
| 91 |
"replyTo": cs.REPLY_TO, "company": cs.COMPANY},
|
| 92 |
"templates": {"subject": cs.DEFAULT_SUBJECT, "intro": cs.DEFAULT_INTRO,
|
| 93 |
"footer": cs.DEFAULT_FOOTER},
|
| 94 |
-
|
|
|
|
|
|
|
| 95 |
}
|
| 96 |
|
| 97 |
|
|
@@ -166,3 +181,89 @@ def send(body: dict = Body(default=None), session: Session = Depends(_gate)):
|
|
| 166 |
failed.append({"customer": name, "error": str(e)[:200]})
|
| 167 |
return {"sent": sent, "failed": failed, "skipped": skipped,
|
| 168 |
"safeMode": bool(cs.SAFE_MODE), "test": bool(override)}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 31 |
from deps import Session, err
|
| 32 |
from routes_admin import admin_gate
|
| 33 |
|
| 34 |
+
# W35-T35 (C8): the tenant predicate, held once. See `_royal_only` for why the import runs this
|
| 35 |
+
# way round. `main.py` already imports both modules, so this adds no load.
|
| 36 |
+
import automation_engine as engine
|
| 37 |
+
|
| 38 |
router = APIRouter(prefix="/api/v1")
|
| 39 |
|
| 40 |
#: Cache the Odoo follow-up pull briefly. The Streamlit page used `@st.cache_data(ttl=1800)`; the
|
|
|
|
| 52 |
"""β See the module docstring, guardrail 3. The send client is env-credentialed, so it is
|
| 53 |
tenant #0's and only tenant #0's. Refuse for anyone else rather than send as the wrong company.
|
| 54 |
|
| 55 |
+
Keyed on the runtime, never on a request field: a tenant is a property of the SESSION.
|
| 56 |
+
|
| 57 |
+
ββ WAVE 35 Β· T35 / CONTRACT C8 β THE TEST ITSELF NOW LIVES IN ONE PLACE. Statements became an
|
| 58 |
+
agent step this wave, so the automation engine has to answer the same question at two more
|
| 59 |
+
doors (which tenants see the action, which tenants may store it). C8's words are "the predicate
|
| 60 |
+
is imported, never re-expressed", and this is the direction that import can run: the engine
|
| 61 |
+
imports no route module and no FastAPI, so reaching `_royal_only` FROM it would drag `deps` and
|
| 62 |
+
`routes_admin` into a route-free module. The engine holds the boolean; this holds the refusal.
|
| 63 |
+
β WHAT STAYS HERE IS THE HTTP SHAPE, and that is deliberate β a 404 rather than a 403, so the
|
| 64 |
+
surface is invisible rather than forbidden. The engine must not know about status codes."""
|
| 65 |
+
if not engine.is_statement_tenant(session.runtime):
|
| 66 |
raise err(404, "not_found", "statements are not configured for this workspace")
|
| 67 |
return session
|
| 68 |
|
|
|
|
| 104 |
"replyTo": cs.REPLY_TO, "company": cs.COMPANY},
|
| 105 |
"templates": {"subject": cs.DEFAULT_SUBJECT, "intro": cs.DEFAULT_INTRO,
|
| 106 |
"footer": cs.DEFAULT_FOOTER},
|
| 107 |
+
# W35-T35: ONE literal, read from the engine, so the sender's worklist and a statements
|
| 108 |
+
# agent's tier filter cannot come to mean different things.
|
| 109 |
+
"tiers": list(engine.STATEMENT_TIERS),
|
| 110 |
}
|
| 111 |
|
| 112 |
|
|
|
|
| 181 |
failed.append({"customer": name, "error": str(e)[:200]})
|
| 182 |
return {"sent": sent, "failed": failed, "skipped": skipped,
|
| 183 |
"safeMode": bool(cs.SAFE_MODE), "test": bool(override)}
|
| 184 |
+
|
| 185 |
+
|
| 186 |
+
# ---------------------------------------------------------------------------------------------
|
| 187 |
+
# WAVE 35 Β· T36 / CONTRACT C8 / OWNER RULING R10 β THE AGENT'S PARKED BATCH.
|
| 188 |
+
#
|
| 189 |
+
# ββ THE AGENT ASSEMBLES; A PERSON CLICKS SEND. `automation_engine.run_statements` renders a batch
|
| 190 |
+
# and parks it on the automation definition, and it imports no mail path at all. THIS is the only
|
| 191 |
+
# door that releases one, and it is deliberately built out of the parts already here:
|
| 192 |
+
# Β· `_gate` β `admin_gate` THEN `_royal_only`, byte-for-byte the dependency the other three
|
| 193 |
+
# endpoints use. Not a copy of the checks: the same object.
|
| 194 |
+
# Β· `cs.queue_statement` β the same call `send()` above makes, so SAFE_MODE's allow-list refusal
|
| 195 |
+
# happens in the DATA LAYER, where no route, payload or UI can reach around it.
|
| 196 |
+
# β Nothing about the guardrails is re-expressed here, which is what makes "unchanged" checkable.
|
| 197 |
+
#
|
| 198 |
+
# β WHY THE BATCH IS RE-RENDERED FROM THE LIVE WORKLIST RATHER THAN SENT AS STORED. The parked
|
| 199 |
+
# `html` is what a person APPROVED and is what the review screen shows; but a balance can move
|
| 200 |
+
# between the parking and the click, and mailing a figure we know to be stale is worse than mailing
|
| 201 |
+
# a fresh one. So the parked batch decides WHO and WITH WHAT WORDS, and the live row decides the
|
| 202 |
+
# NUMBERS β the same split `preview` already makes. A customer who has left the worklist entirely
|
| 203 |
+
# (they paid) is reported as skipped rather than invoiced.
|
| 204 |
+
|
| 205 |
+
@router.get("/admin/statements/agent/{auto_id}")
|
| 206 |
+
def agent_batch(auto_id: str, session: Session = Depends(_gate)):
|
| 207 |
+
"""What is parked and waiting for a click, for ONE agent. `null` when nothing is."""
|
| 208 |
+
defn = (engine.all_definitions(session.runtime) or {}).get(str(auto_id)) or {}
|
| 209 |
+
pending = defn.get("pendingStatements")
|
| 210 |
+
if not isinstance(pending, dict):
|
| 211 |
+
return {"pending": None}
|
| 212 |
+
# β The rendered `html` is NOT returned in the list β a 200-statement batch of rendered mail is
|
| 213 |
+
# megabytes, and the review screen needs the count and the names to decide. `preview` already
|
| 214 |
+
# renders ONE on demand.
|
| 215 |
+
return {"pending": {
|
| 216 |
+
"ts": pending.get("ts"), "count": int(pending.get("count") or 0),
|
| 217 |
+
"notes": list(pending.get("notes") or []),
|
| 218 |
+
"items": [{k: v for k, v in it.items() if k != "html"}
|
| 219 |
+
for it in (pending.get("items") or [])],
|
| 220 |
+
"safeMode": bool(_cs().SAFE_MODE)}}
|
| 221 |
+
|
| 222 |
+
|
| 223 |
+
@router.post("/admin/statements/agent/{auto_id}/send")
|
| 224 |
+
def agent_send(auto_id: str, body: dict = Body(default=None),
|
| 225 |
+
session: Session = Depends(_gate)):
|
| 226 |
+
"""Release a parked batch. THE CLICK R10 REQUIRES β nothing else in the system calls this.
|
| 227 |
+
|
| 228 |
+
β IT REFUSES AN EMPTY OR MISSING BATCH rather than answering 200 with nothing sent: a send
|
| 229 |
+
that reports success and mails nobody is the `view_upsert` failure mode (200 OK, zero writes)
|
| 230 |
+
arriving on the one route in this system that talks to a mail server.
|
| 231 |
+
"""
|
| 232 |
+
cs = _cs()
|
| 233 |
+
defn = (engine.all_definitions(session.runtime) or {}).get(str(auto_id)) or {}
|
| 234 |
+
pending = defn.get("pendingStatements")
|
| 235 |
+
items = list((pending or {}).get("items") or []) if isinstance(pending, dict) else []
|
| 236 |
+
if not items:
|
| 237 |
+
raise err(404, "no_batch", "there is nothing parked for this agent to send")
|
| 238 |
+
# β An explicit subset is allowed (a person unticking a customer on the review screen) but it
|
| 239 |
+
# may only NARROW the parked batch. A name that was never parked cannot be introduced by the
|
| 240 |
+
# payload, or the review stops being what authorised the send.
|
| 241 |
+
want = {str(n) for n in (body or {}).get("customers") or []}
|
| 242 |
+
if want:
|
| 243 |
+
items = [it for it in items if str(it.get("customer")) in want]
|
| 244 |
+
if not items:
|
| 245 |
+
raise err(400, "bad_request", "none of those customers are in the parked batch")
|
| 246 |
+
rows, _ = _rows()
|
| 247 |
+
sent, failed, skipped = [], [], []
|
| 248 |
+
for it in items:
|
| 249 |
+
name = str(it.get("customer") or "")
|
| 250 |
+
row = _find(rows, name)
|
| 251 |
+
if row is None:
|
| 252 |
+
skipped.append({"customer": name,
|
| 253 |
+
"reason": "no longer on the collection list, so nothing is owed"})
|
| 254 |
+
continue
|
| 255 |
+
try:
|
| 256 |
+
# β THE SAME DATA-LAYER CALL `send()` MAKES. SafeModeBlocked is raised INSIDE
|
| 257 |
+
# `queue_statement`, so the guardrail cannot be argued with from here.
|
| 258 |
+
mid = cs.queue_statement(cs.Odoo(), row,
|
| 259 |
+
str(it.get("subject") or "") or cs.DEFAULT_SUBJECT,
|
| 260 |
+
cs.DEFAULT_INTRO, cs.DEFAULT_FOOTER)
|
| 261 |
+
sent.append({"customer": name, "to": row.get("Email"), "mailId": mid})
|
| 262 |
+
except Exception as e: # noqa: BLE001
|
| 263 |
+
failed.append({"customer": name, "error": str(e)[:200]})
|
| 264 |
+
# β CLEARED ONLY WHEN NOTHING IS LEFT TO RETRY. A batch dropped while some of it failed would
|
| 265 |
+
# lose the list of who still needs a statement, and nobody would know to look.
|
| 266 |
+
if sent and not failed:
|
| 267 |
+
engine.clear_statements(session.runtime, auto_id)
|
| 268 |
+
return {"sent": sent, "failed": failed, "skipped": skipped,
|
| 269 |
+
"safeMode": bool(cs.SAFE_MODE), "cleared": bool(sent and not failed)}
|
api/routes_tables.py
CHANGED
|
@@ -105,7 +105,7 @@ def _refresh_relations(session):
|
|
| 105 |
name=f"rel-refresh:{tenant or 'default'}").start()
|
| 106 |
|
| 107 |
|
| 108 |
-
def _defn_or_refuse(session, table_key, st=None):
|
| 109 |
"""The per-table wall: 404 for a key that does not exist, 403 for one this session may not
|
| 110 |
open. 404-before-403 leaks nothing useful β ut keys are guessable slugs, and 'exists but
|
| 111 |
not yours' is exactly what may_open is for.
|
|
@@ -113,11 +113,30 @@ def _defn_or_refuse(session, table_key, st=None):
|
|
| 113 |
β `st` LETS A CALLER LEND THE SNAPSHOT IT IS ALREADY HOLDING (W31 QA), the same `lend()` the
|
| 114 |
nav and `/tables` use since W31-T10/T12. The WALL is untouched β the same `may_open`, asked
|
| 115 |
about the same table β it is simply not re-reading a 28.5 MB document to ask it.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 116 |
"""
|
| 117 |
ut = _ut()
|
| 118 |
# ββ W31 QA β THE SWEEP, AND IT IS ONE LINE BECAUSE IT IS DONE HERE RATHER THAN PER ROUTE.
|
| 119 |
# Owner: *"this is just one case, I need you to check and apply the fix everywhere too."*
|
| 120 |
-
# This guard has
|
|
|
|
| 121 |
# (`get`, then `may_open`) β on tenant #0 that is 2 x 28.5 MB (D-185) to answer two questions
|
| 122 |
# about ONE table. Lending here fixes every caller at once, including the eight routes the
|
| 123 |
# sweep enumerated (`PATCH /shared/{pid}` Β· `DELETE /shared/fields/{k}` Β· `GET|POST /rows` Β·
|
|
@@ -128,7 +147,8 @@ def _defn_or_refuse(session, table_key, st=None):
|
|
| 128 |
# would hand that stale snapshot to `patch_row`'s and `add_row`'s post-write read-back, which
|
| 129 |
# is [[refetch-eats-its-own-write]] with the sign flipped β a write that reports the value it
|
| 130 |
# replaced. The remaining in-route reads are deliberately untouched and booked instead.
|
| 131 |
-
|
|
|
|
| 132 |
defn = ut.get(table_key, st=st)
|
| 133 |
if not defn:
|
| 134 |
raise err(404, "unknown_table", "that database does not exist")
|
|
@@ -145,7 +165,7 @@ def _records_or_refuse(session, table_key, st=None):
|
|
| 145 |
defn = _defn_or_refuse(session, table_key, st=st)
|
| 146 |
if not _ut().records_mutable(table_key, st=st):
|
| 147 |
raise err(403, "records_read_only",
|
| 148 |
-
"records in this automation-owned database are read-only
|
| 149 |
"handles in a Profile database and let enrichment populate this database")
|
| 150 |
return defn
|
| 151 |
|
|
@@ -234,15 +254,21 @@ _PID_SCOPE_LIMIT = {
|
|
| 234 |
}
|
| 235 |
|
| 236 |
|
| 237 |
-
def scoped_pool(session: Session, table_key: str):
|
| 238 |
"""`(pids, rows_src, fields_base, defn)` β THE USER-TABLE WALL, on its own.
|
| 239 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 240 |
`routes_products.scoped_pool`'s sibling, extracted for the same reason (wave 19, item 12): a
|
| 241 |
caller that only needs "which rows of this database may this session touch" β record comments
|
| 242 |
β must ask through `_defn_or_refuse` (404/403, the whole wall) rather than growing a second
|
| 243 |
idea of what a user table's pool is.
|
| 244 |
"""
|
| 245 |
-
defn = _defn_or_refuse(session, table_key)
|
| 246 |
fields_base = [dict(f) for f in (defn.get("fields") or [])]
|
| 247 |
field_keys = {f["key"] for f in fields_base}
|
| 248 |
# ββ W30-T31 / D-87 β A READ-THROUGH DATABASE HAS NO ROWS HERE, SO THEY COME FROM THE MIRROR.
|
|
@@ -350,7 +376,7 @@ def delete_shared_field(table_key: str, field_key: str,
|
|
| 350 |
owner = str(defn.get("createdBy") or "")
|
| 351 |
if not session.admin and owner != session.uname:
|
| 352 |
raise err(403, "forbidden",
|
| 353 |
-
f"a tenant-wide column can be removed by its creator or an admin
|
| 354 |
f"was added by {owner or 'somebody else'}, and dropping it would delete the "
|
| 355 |
f"value for every account")
|
| 356 |
dropped = shared_overlay.drop_field(table_key, str(field_key), st=session.runtime)
|
|
@@ -375,8 +401,14 @@ def scoped_pids(session: Session, table_key: str, limits=None):
|
|
| 375 |
middle. The row WALL is unchanged β a narrower or wider set here would be a permission
|
| 376 |
change, and this is a performance change.
|
| 377 |
|
| 378 |
-
β It does NOT make the write cheap on its own: `_defn_or_refuse` still costs
|
| 379 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 380 |
|
| 381 |
ββ W31-T20 / D-174 β `limits` IS AN OUT-PARAMETER, AND IT IS THE POINT OF THE TICKET. Pass a
|
| 382 |
list and this function APPENDS R6's sentence to it when the pid set could not be resolved (a
|
|
@@ -386,7 +418,20 @@ def scoped_pids(session: Session, table_key: str, limits=None):
|
|
| 386 |
write is expected to carry the sentence through. Omitting the list means the caller accepts an
|
| 387 |
unannounced empty scope, which is only ever right for a caller that does not use the pids.
|
| 388 |
"""
|
| 389 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 390 |
fields_base = [dict(f) for f in (defn.get("fields") or [])]
|
| 391 |
# β W30-T31: on a read-through database the stored `rows` is `{}` by construction, so the
|
| 392 |
# comprehension below would answer an EMPTY pid set β and the promise this function makes is
|
|
@@ -407,8 +452,25 @@ def scoped_pids(session: Session, table_key: str, limits=None):
|
|
| 407 |
return frozenset(), fields_base, defn
|
| 408 |
except RuntimeError as e:
|
| 409 |
raise err(503, "store_not_ready", str(e))
|
| 410 |
-
|
| 411 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 412 |
|
| 413 |
|
| 414 |
def ut_write_ctx(session: Session, table_key: str):
|
|
@@ -441,7 +503,7 @@ def ut_write_ctx(session: Session, table_key: str):
|
|
| 441 |
|
| 442 |
|
| 443 |
def ut_assembly(session: Session, table_key: str, storage_key: str = "",
|
| 444 |
-
consume_corrections: bool = True, with_rows: bool = True):
|
| 445 |
"""The user-table mirror of `grid_assembly` / `product_assembly` β SAME g-dict keys, so
|
| 446 |
`/workspace` and the events route consume any of the three interchangeably.
|
| 447 |
|
|
@@ -470,7 +532,9 @@ def ut_assembly(session: Session, table_key: str, storage_key: str = "",
|
|
| 470 |
|
| 471 |
limits = []
|
| 472 |
if with_rows:
|
| 473 |
-
|
|
|
|
|
|
|
| 474 |
else:
|
| 475 |
pids, fields_base, defn = scoped_pids(session, table_key, limits=limits)
|
| 476 |
rows_src = []
|
|
@@ -671,17 +735,17 @@ def create_table(body: dict = Body(default=None),
|
|
| 671 |
raise err(400, "bad_label", "give the database a name")
|
| 672 |
if not session.runtime.available():
|
| 673 |
raise err(503, "store_unavailable",
|
| 674 |
-
"the tenant store is unavailable
|
| 675 |
source = body.get("source")
|
| 676 |
try:
|
| 677 |
key = ut.create(label, session.uname, fields=body.get("fields"),
|
| 678 |
source=source, st=session.runtime)
|
| 679 |
except Exception:
|
| 680 |
raise err(503, "store_unavailable",
|
| 681 |
-
"the tenant store refused the write
|
| 682 |
if not key:
|
| 683 |
raise err(400, "refused",
|
| 684 |
-
f"could not create it
|
| 685 |
f"{ut.MAX_TABLES} databases")
|
| 686 |
return {"key": key}
|
| 687 |
|
|
@@ -713,8 +777,11 @@ def table_footprint(table_key: str, session: Session = Depends(require_session))
|
|
| 713 |
|
| 714 |
Counts drill to the SAME buckets `user_tables.delete` cleans; a dialog listing categories
|
| 715 |
without numbers would break [[no-unverifiable-aggregates]] at the scariest moment. Walled
|
| 716 |
-
like the delete itself: only someone who could delete may case the joint.
|
| 717 |
-
|
|
|
|
|
|
|
|
|
|
| 718 |
if not (session.admin or defn.get("createdBy") == session.uname):
|
| 719 |
raise err(403, "forbidden", "only the database's creator or an admin can delete it")
|
| 720 |
s = session.runtime
|
|
@@ -737,7 +804,19 @@ def table_footprint(table_key: str, session: Session = Depends(require_session))
|
|
| 737 |
auto.append({"id": str(aid), "name": d.get("name") or str(aid)})
|
| 738 |
except Exception:
|
| 739 |
pass
|
| 740 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 741 |
"sharedUsers": len(g.get("entries") or []),
|
| 742 |
"automations": sorted(auto, key=lambda a: a["name"].lower())}
|
| 743 |
|
|
@@ -766,7 +845,7 @@ def delete_table(table_key: str, session: Session = Depends(require_session)):
|
|
| 766 |
try:
|
| 767 |
_ut().delete(table_key, st=session.runtime)
|
| 768 |
except Exception:
|
| 769 |
-
raise err(503, "store_unavailable", "the delete did not land
|
| 770 |
return {"ok": True}
|
| 771 |
|
| 772 |
|
|
@@ -856,7 +935,17 @@ def table_rows(table_key: str, session: Session = Depends(require_session)):
|
|
| 856 |
import aios_grid
|
| 857 |
|
| 858 |
_ig_forward(session)
|
| 859 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 860 |
# β THE OVERLAY WAS NEVER ACTUALLY MERGED, and the docstring above has described the merge
|
| 861 |
# this line does not perform since the route was written (owner item 3, 2026-08-09:
|
| 862 |
# *"Using the swipe, fast doesn't register the CHANGE. I went back and it all got reseted"*).
|
|
@@ -904,13 +993,16 @@ def table_rows(table_key: str, session: Session = Depends(require_session)):
|
|
| 904 |
# so a tenant using `json` for a short config sees no change at all.
|
| 905 |
rows = aios_grid.rows_from_pool(
|
| 906 |
g["rows_src"], g["fields"], _thin_json(g["fields"], merged, table_key), derived=g["derived"])
|
|
|
|
|
|
|
|
|
|
| 907 |
# β R6's SECOND SENTENCE, ON THE WIRE (W30-T29). *"if there is lag or it can't be done, you
|
| 908 |
# need to explicitly tell me why and recommend a fix."* A ceiling that still applies to this
|
| 909 |
# database says so here, with its cause and the recommendation, rather than waiting to be
|
| 910 |
# discovered as a refused paste. `None` for a connected source, and an EMPTY LIST is the
|
| 911 |
# honest answer for a table nothing limits β never an absent key, which a client cannot tell
|
| 912 |
# apart from an older server.
|
| 913 |
-
_report = _ut().limit_report(table_key, st=
|
| 914 |
# β C4 / D-138 β THE DOCUMENTS PRODUCER. Absent since EXIT-6 deleted `app.py`, which was the
|
| 915 |
# only thing that ever set this key; the write door never stopped working and every client
|
| 916 |
# half is complete, but all six `onDoc*` handlers read `payload?.docs ? β¦ : undefined`, so a
|
|
@@ -924,7 +1016,49 @@ def table_rows(table_key: str, session: Session = Depends(require_session)):
|
|
| 924 |
"identity": {"pid": "pid"},
|
| 925 |
"scope": {"table": table_key, "rowCount": len(rows)},
|
| 926 |
"limits": [_report] if _report else [],
|
| 927 |
-
"recordsMutable": _ut().records_mutable(table_key, st=
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 928 |
|
| 929 |
|
| 930 |
@router.get("/tables/{table_key}/rows/{pid}/fields/{fkey}")
|
|
@@ -973,7 +1107,7 @@ def add_row(table_key: str, body: dict = Body(default=None),
|
|
| 973 |
rid = ut.add_row(table_key, values, session.uname, st=session.runtime,
|
| 974 |
rid=(body or {}).get("rid"))
|
| 975 |
except Exception:
|
| 976 |
-
raise err(503, "store_unavailable", "the row was not saved
|
| 977 |
if rid is None:
|
| 978 |
# C3 (wave 25): `add_row` also refuses a profile cell that is not a handle, so the cap
|
| 979 |
# sentence alone would misdirect β the reader would go and count rows. Ask the same
|
|
@@ -983,11 +1117,11 @@ def add_row(table_key: str, body: dict = Body(default=None),
|
|
| 983 |
_h, ok = ut.normalize_profile(values[pf["key"]], pf["profile"].get("source"))
|
| 984 |
if not ok:
|
| 985 |
raise err(400, "refused",
|
| 986 |
-
f"{str(values[pf['key']])[:80]!r} is not an Instagram profile
|
| 987 |
f"{pf.get('label') or pf['key']!r} takes a handle (@name) or a "
|
| 988 |
f"profile link (instagram.com/name)")
|
| 989 |
raise err(400, "refused",
|
| 990 |
-
f"row refused
|
| 991 |
_refresh_relations(session)
|
| 992 |
return {"rid": rid, "pid": int(rid)}
|
| 993 |
|
|
@@ -1041,14 +1175,14 @@ def import_rows(table_key: str, body: dict = Body(default=None),
|
|
| 1041 |
for key, value in row.items():
|
| 1042 |
why = ut.cell_type_refusal(by_key[key], value)
|
| 1043 |
if why:
|
| 1044 |
-
raise err(400, "bad_value", f"row {index + 1}: {why}
|
| 1045 |
try:
|
| 1046 |
made = ut.add_rows(table_key, rows_in, session.uname, st=session.runtime)
|
| 1047 |
except Exception:
|
| 1048 |
-
raise err(503, "store_unavailable", "nothing was imported
|
| 1049 |
if made is None:
|
| 1050 |
raise err(400, "refused",
|
| 1051 |
-
f"nothing was imported
|
| 1052 |
f"its {ut.MAX_ROWS}-row cap, or a profile column rejected a value")
|
| 1053 |
_refresh_relations(session)
|
| 1054 |
return {"imported": len(made), "pids": [int(r) for r in made]}
|
|
@@ -1068,12 +1202,18 @@ def import_rows(table_key: str, body: dict = Body(default=None),
|
|
| 1068 |
# as the rename (item 6a): two places to look, and the surfaces disagreed silently.
|
| 1069 |
|
| 1070 |
def _field_or_refuse(session, table_key, fkey=""):
|
| 1071 |
-
"""The schema wall. `_defn_or_refuse` first (404/403 on the table), then the per-field rule.
|
| 1072 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1073 |
ut = _ut()
|
| 1074 |
if not ut.is_user_table(table_key, st=session.runtime):
|
| 1075 |
raise err(400, "not_a_user_table",
|
| 1076 |
-
"only a user-created database has an editable schema
|
| 1077 |
"owns its own columns")
|
| 1078 |
if fkey and not ut.may_edit_field(table_key, fkey, session.uname, session.admin,
|
| 1079 |
st=session.runtime):
|
|
@@ -1126,12 +1266,41 @@ def add_field(table_key: str, body: dict = Body(default=None),
|
|
| 1126 |
# field relational", which is the question that was always meant.
|
| 1127 |
if field.get("type") in ("link", "rollup"):
|
| 1128 |
_refresh_relations(session)
|
| 1129 |
-
return {"field": field}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1130 |
|
| 1131 |
|
| 1132 |
def _refusal_sentence(ut, session, body, table_key="", fkey=""):
|
| 1133 |
"""Why was this column refused? The specific reason when we can name one, the general list
|
| 1134 |
otherwise β never a specific-sounding guess."""
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1135 |
# β C3 (wave 25, R7): the one-profile-per-table refusal NAMES THE EXISTING COLUMN, which is
|
| 1136 |
# what the contract asks for and what makes it actionable β "at most one" sends the reader
|
| 1137 |
# hunting through a 40-column schema for a flag they cannot see from the header.
|
|
@@ -1143,11 +1312,11 @@ def _refusal_sentence(ut, session, body, table_key="", fkey=""):
|
|
| 1143 |
# real mistake was the column type sends them to fix the wrong thing, which is the
|
| 1144 |
# misdirection D-46 closed one door over.
|
| 1145 |
if str((body or {}).get("type") or "text").strip().lower() != "text":
|
| 1146 |
-
return ("a profile column is a flag on an ordinary TEXT column
|
| 1147 |
"is typed into it, which it can only do for text")
|
| 1148 |
existing = ut.profile_field(table_key, st=session.runtime) if table_key else None
|
| 1149 |
if existing and existing.get("key") != str(fkey):
|
| 1150 |
-
return (f"this database already has a profile column
|
| 1151 |
f"{existing.get('label') or existing.get('key')!r}. A database has at most "
|
| 1152 |
f"one, so the automation knows which handle to enrich; edit that column, or "
|
| 1153 |
f"take the flag off it first")
|
|
@@ -1155,16 +1324,16 @@ def _refusal_sentence(ut, session, body, table_key="", fkey=""):
|
|
| 1155 |
if isinstance(bag, dict):
|
| 1156 |
flow = str(bag.get("flowId") or "").strip()
|
| 1157 |
if not flow:
|
| 1158 |
-
return ("an automation column has to name the automation that fills it
|
| 1159 |
"flow, or make this an ordinary column")
|
| 1160 |
if not ut.flow_bound(bag, st=session.runtime):
|
| 1161 |
return (f"this column names automation {flow!r}, which does not exist in this "
|
| 1162 |
-
f"workspace
|
| 1163 |
kind = str((body or {}).get("type") or "").strip()
|
| 1164 |
if kind and kind not in ut.UT_FIELD_TYPES:
|
| 1165 |
return (f"{kind!r} is not a column type here (types: "
|
| 1166 |
f"{', '.join(sorted(ut.UT_FIELD_TYPES))})")
|
| 1167 |
-
return (f"the column was refused
|
| 1168 |
f"{ut.MAX_FIELDS}-column cap (types: {', '.join(sorted(ut.UT_FIELD_TYPES))})")
|
| 1169 |
|
| 1170 |
|
|
@@ -1187,7 +1356,7 @@ def patch_field(table_key: str, fkey: str, body: dict = Body(default=None),
|
|
| 1187 |
try:
|
| 1188 |
migrated = ut.rename_choice_values(table_key, fkey, renames, st=session.runtime)
|
| 1189 |
except Exception:
|
| 1190 |
-
raise err(503, "store_unavailable", "the rename did not land
|
| 1191 |
# The per-user workspace strata and any view filter naming the old value are the OTHER
|
| 1192 |
# half of C-RENAME and belong to `core.table_store`. Called only if it is there: an
|
| 1193 |
# enumerator's mirror waits for its counterpart rather than guessing at its shape, and a
|
|
@@ -1214,7 +1383,85 @@ def patch_field(table_key: str, fkey: str, body: dict = Body(default=None),
|
|
| 1214 |
out = {"field": field}
|
| 1215 |
if migrated is not None:
|
| 1216 |
out["migrated"] = migrated
|
| 1217 |
-
return out
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1218 |
|
| 1219 |
|
| 1220 |
@router.delete("/tables/{table_key}/fields/{fkey}")
|
|
@@ -1222,7 +1469,7 @@ def delete_field(table_key: str, fkey: str, session: Session = Depends(require_s
|
|
| 1222 |
_field_or_refuse(session, table_key, fkey)
|
| 1223 |
if not _ut().delete_field(table_key, fkey, st=session.runtime):
|
| 1224 |
raise err(400, "refused",
|
| 1225 |
-
"that column could not be removed
|
| 1226 |
_refresh_relations(session)
|
| 1227 |
return {"deleted": fkey}
|
| 1228 |
|
|
@@ -1247,7 +1494,7 @@ def delete_row(table_key: str, rid: str, session: Session = Depends(require_sess
|
|
| 1247 |
try:
|
| 1248 |
ok = _ut().delete_row(table_key, rid, st=lent)
|
| 1249 |
except Exception:
|
| 1250 |
-
raise err(503, "store_unavailable", "the delete did not land
|
| 1251 |
if not ok:
|
| 1252 |
raise err(400, "refused", "rows can only be deleted from user-created databases")
|
| 1253 |
_refresh_relations(session)
|
|
@@ -1280,7 +1527,7 @@ def patch_row(table_key: str, pid: int, body: dict = Body(default=None),
|
|
| 1280 |
"pid": pid, "updates": updates}, ctx)
|
| 1281 |
except grid_events.StoreUnavailable:
|
| 1282 |
raise err(503, "store_unavailable",
|
| 1283 |
-
"the tenant store is unavailable
|
| 1284 |
# β THE READ-BACK IS THE DEFINITION ROW, AND ON A `ut_` SCOPE THAT IS THE WHOLE OF IT.
|
| 1285 |
#
|
| 1286 |
# β CORRECTED, wave-29 T22 (owner item 2a): this note used to say "THE READ-BACK SPANS BOTH
|
|
@@ -1319,6 +1566,22 @@ def patch_row(table_key: str, pid: int, body: dict = Body(default=None),
|
|
| 1319 |
return False
|
| 1320 |
|
| 1321 |
refused = sorted(k for k in updates if not _took(k))
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1322 |
out = {"pid": pid, "updates": accepted}
|
| 1323 |
if refused:
|
| 1324 |
out["refused"] = refused
|
|
|
|
| 105 |
name=f"rel-refresh:{tenant or 'default'}").start()
|
| 106 |
|
| 107 |
|
| 108 |
+
def _defn_or_refuse(session, table_key, st=None, defs_only=False):
|
| 109 |
"""The per-table wall: 404 for a key that does not exist, 403 for one this session may not
|
| 110 |
open. 404-before-403 leaks nothing useful β ut keys are guessable slugs, and 'exists but
|
| 111 |
not yours' is exactly what may_open is for.
|
|
|
|
| 113 |
β `st` LETS A CALLER LEND THE SNAPSHOT IT IS ALREADY HOLDING (W31 QA), the same `lend()` the
|
| 114 |
nav and `/tables` use since W31-T10/T12. The WALL is untouched β the same `may_open`, asked
|
| 115 |
about the same table β it is simply not re-reading a 28.5 MB document to ask it.
|
| 116 |
+
|
| 117 |
+
ββ W33-T01 (D-213) β `defs_only=True` MAKES THAT READ A PROJECTION, AND IT IS OPT-IN PER CALL
|
| 118 |
+
SITE ON PURPOSE. This wall asks two questions ("does the key exist", "may this session open
|
| 119 |
+
it") and neither has ever read a row, but three of its ten callers go on to read `rows` OFF THE
|
| 120 |
+
DEFINITION THIS RETURNS β so a blanket swap would turn `scoped_pool`, `scoped_pids` and
|
| 121 |
+
`table_footprint` into `KeyError`s on every materialised table. The flag is therefore the
|
| 122 |
+
CALLER's claim about what it will do next, not a global setting; each opt-in below is annotated
|
| 123 |
+
with why it can make that claim ([[reuse-and-delete-are-hypotheses]]).
|
| 124 |
+
|
| 125 |
+
β **`defs_only` IS FOR READS.** The six write walls (`_records_or_refuse`, `patch_shared_cell`,
|
| 126 |
+
`delete_shared_field`, `patch_table`, `delete_table`, `import_rows`) deliberately do NOT pass
|
| 127 |
+
it: a projected snapshot must never reach a post-write read-back (contract C5), and the
|
| 128 |
+
pre-write lend note below is the same argument one layer down.
|
| 129 |
+
|
| 130 |
+
β **WHAT COMES BACK IS A `store._Projected`, WHICH IS THE EVIDENCE, NOT AN IMPLEMENTATION
|
| 131 |
+
DETAIL.** `all_defs` falls back to the whole read on ANY failure, so "the answer was right"
|
| 132 |
+
proves nothing about which read produced it. `core.store.is_projected(defn)` is how a gate
|
| 133 |
+
asserts the fast path was TAKEN.
|
| 134 |
"""
|
| 135 |
ut = _ut()
|
| 136 |
# ββ W31 QA β THE SWEEP, AND IT IS ONE LINE BECAUSE IT IS DONE HERE RATHER THAN PER ROUTE.
|
| 137 |
# Owner: *"this is just one case, I need you to check and apply the fix everywhere too."*
|
| 138 |
+
# This guard has TEN direct call sites (counted 2026-08-14; the note said FOURTEEN, which was
|
| 139 |
+
# the route count, not the caller count) and cost TWO whole-document deep copies at every one
|
| 140 |
# (`get`, then `may_open`) β on tenant #0 that is 2 x 28.5 MB (D-185) to answer two questions
|
| 141 |
# about ONE table. Lending here fixes every caller at once, including the eight routes the
|
| 142 |
# sweep enumerated (`PATCH /shared/{pid}` Β· `DELETE /shared/fields/{k}` Β· `GET|POST /rows` Β·
|
|
|
|
| 147 |
# would hand that stale snapshot to `patch_row`'s and `add_row`'s post-write read-back, which
|
| 148 |
# is [[refetch-eats-its-own-write]] with the sign flipped β a write that reports the value it
|
| 149 |
# replaced. The remaining in-route reads are deliberately untouched and booked instead.
|
| 150 |
+
if st is None:
|
| 151 |
+
st = ut.lend_defs(session.runtime) if defs_only else ut.lend(session.runtime)
|
| 152 |
defn = ut.get(table_key, st=st)
|
| 153 |
if not defn:
|
| 154 |
raise err(404, "unknown_table", "that database does not exist")
|
|
|
|
| 165 |
defn = _defn_or_refuse(session, table_key, st=st)
|
| 166 |
if not _ut().records_mutable(table_key, st=st):
|
| 167 |
raise err(403, "records_read_only",
|
| 168 |
+
"records in this automation-owned database are read-only. Add Instagram "
|
| 169 |
"handles in a Profile database and let enrichment populate this database")
|
| 170 |
return defn
|
| 171 |
|
|
|
|
| 254 |
}
|
| 255 |
|
| 256 |
|
| 257 |
+
def scoped_pool(session: Session, table_key: str, st=None):
|
| 258 |
"""`(pids, rows_src, fields_base, defn)` β THE USER-TABLE WALL, on its own.
|
| 259 |
|
| 260 |
+
β W33-T03 (D-214) β `st` LETS A CALLER LEND THE DOCUMENT IT IS ALREADY HOLDING, exactly as
|
| 261 |
+
`_defn_or_refuse` has since W31 QA. It is passed straight through to that wall and nowhere
|
| 262 |
+
else, so the permission question is answered by the same code against the same document.
|
| 263 |
+
β READ CALLERS ONLY. A lend is a PRE-WRITE snapshot; handing one to a path that writes and then
|
| 264 |
+
reads back is [[refetch-eats-its-own-write]] with the sign flipped (contract C5).
|
| 265 |
+
|
| 266 |
`routes_products.scoped_pool`'s sibling, extracted for the same reason (wave 19, item 12): a
|
| 267 |
caller that only needs "which rows of this database may this session touch" β record comments
|
| 268 |
β must ask through `_defn_or_refuse` (404/403, the whole wall) rather than growing a second
|
| 269 |
idea of what a user table's pool is.
|
| 270 |
"""
|
| 271 |
+
defn = _defn_or_refuse(session, table_key, st=st)
|
| 272 |
fields_base = [dict(f) for f in (defn.get("fields") or [])]
|
| 273 |
field_keys = {f["key"] for f in fields_base}
|
| 274 |
# ββ W30-T31 / D-87 β A READ-THROUGH DATABASE HAS NO ROWS HERE, SO THEY COME FROM THE MIRROR.
|
|
|
|
| 376 |
owner = str(defn.get("createdBy") or "")
|
| 377 |
if not session.admin and owner != session.uname:
|
| 378 |
raise err(403, "forbidden",
|
| 379 |
+
f"a tenant-wide column can be removed by its creator or an admin. This one "
|
| 380 |
f"was added by {owner or 'somebody else'}, and dropping it would delete the "
|
| 381 |
f"value for every account")
|
| 382 |
dropped = shared_overlay.drop_field(table_key, str(field_key), st=session.runtime)
|
|
|
|
| 401 |
middle. The row WALL is unchanged β a narrower or wider set here would be a permission
|
| 402 |
change, and this is a performance change.
|
| 403 |
|
| 404 |
+
β It does NOT make the write cheap on its own: `_defn_or_refuse` still costs a whole-document
|
| 405 |
+
read, which is D-87 and W30-T31. This removes the row pass.
|
| 406 |
+
β CORRECTED 2026-08-14 (W33-T01): that sentence said **two** deep copies (`ut.get` then
|
| 407 |
+
`may_open`) and had been stale since W31 QA taught the wall to `lend()` β the two questions
|
| 408 |
+
have shared ONE read since `routes_tables.py`'s lend line. And as of this ticket the read is a
|
| 409 |
+
PROJECTION on the read-through arm, so the sentence is now true only of the materialised one.
|
| 410 |
+
Booked because a stale performance note is how a wave re-fixes something twice
|
| 411 |
+
([[stale-baseline-unreadable-deltas]]).
|
| 412 |
|
| 413 |
ββ W31-T20 / D-174 β `limits` IS AN OUT-PARAMETER, AND IT IS THE POINT OF THE TICKET. Pass a
|
| 414 |
list and this function APPENDS R6's sentence to it when the pid set could not be resolved (a
|
|
|
|
| 418 |
write is expected to carry the sentence through. Omitting the list means the caller accepts an
|
| 419 |
unannounced empty scope, which is only ever right for a caller that does not use the pids.
|
| 420 |
"""
|
| 421 |
+
# ββ W33-T01 / D-213 β THE DATABASE-SWITCH PATH, AND IT STARTS ON A PROJECTION.
|
| 422 |
+
#
|
| 423 |
+
# `GET /workspace?scope=<key>` reaches here through `ut_assembly(with_rows=False)`
|
| 424 |
+
# (`routes_grid.py`'s ut_ branch), which is what a person is waiting for when they click a
|
| 425 |
+
# database in the nav flyout: 1.8-7.3 s live for a 3-6 KB payload, of which one whole-document
|
| 426 |
+
# read is ~703 ms warm and 20.6 s cold. This function reads `fields` and (below) `readThrough`
|
| 427 |
+
# off the definition β no row β so the WALL can be answered from the 0.1% projection.
|
| 428 |
+
#
|
| 429 |
+
# β IT IS THE TRAP ON THIS BOARD, SO IT IS SAID TWICE: this function is NAMED and DOCUMENTED
|
| 430 |
+
# as the rows-free twin of `scoped_pool` and the materialised arm below still reads `rows`.
|
| 431 |
+
# The opt-in is therefore CONDITIONAL, and the condition is `materialises`, which reads
|
| 432 |
+
# `readThrough` β a definition key, safe under the projection, and already lent the defn so it
|
| 433 |
+
# costs no read of its own.
|
| 434 |
+
defn = _defn_or_refuse(session, table_key, defs_only=True)
|
| 435 |
fields_base = [dict(f) for f in (defn.get("fields") or [])]
|
| 436 |
# β W30-T31: on a read-through database the stored `rows` is `{}` by construction, so the
|
| 437 |
# comprehension below would answer an EMPTY pid set β and the promise this function makes is
|
|
|
|
| 452 |
return frozenset(), fields_base, defn
|
| 453 |
except RuntimeError as e:
|
| 454 |
raise err(503, "store_not_ready", str(e))
|
| 455 |
+
# ββ MATERIALISED: THE PID SET *IS* `rows`, SO THIS ARM TAKES THE WHOLE READ β the projection
|
| 456 |
+
# above cannot serve it and would raise rather than answer `{}` (that is the whole design of
|
| 457 |
+
# `_Projected`). The wall has already passed on the projected document, so this re-reads the
|
| 458 |
+
# DEFINITION and does not re-ask `may_open`: re-walling would be a second, differently-shaped
|
| 459 |
+
# answer to a question already answered, which is how two ideas of ownership got into this file
|
| 460 |
+
# once before (see `may_open`'s own note in `core/user_tables.py`).
|
| 461 |
+
#
|
| 462 |
+
# β THE HONEST COST, STATED RATHER THAN BURIED: a materialised table now pays the projection
|
| 463 |
+
# PLUS the whole read β ~1.4 ms on top of ~703 ms on tenant #0, i.e. 0.2%. The pid set, the
|
| 464 |
+
# wall and the returned shape are byte-for-byte what they were; only tenant #0's ten
|
| 465 |
+
# read-through databases (every one of them, which is why the switch was slow) skip the big
|
| 466 |
+
# read entirely.
|
| 467 |
+
whole = _ut().get(table_key, st=session.runtime)
|
| 468 |
+
if whole is None:
|
| 469 |
+
# Between the wall and here the table was deleted by another request. Same refusal the
|
| 470 |
+
# wall gives, rather than an empty pid set nobody can distinguish from an empty table.
|
| 471 |
+
raise err(404, "unknown_table", "that database does not exist")
|
| 472 |
+
pids = frozenset(int(rid) for rid in (whole.get("rows") or {}) if str(rid).isdigit())
|
| 473 |
+
return pids, fields_base, whole
|
| 474 |
|
| 475 |
|
| 476 |
def ut_write_ctx(session: Session, table_key: str):
|
|
|
|
| 503 |
|
| 504 |
|
| 505 |
def ut_assembly(session: Session, table_key: str, storage_key: str = "",
|
| 506 |
+
consume_corrections: bool = True, with_rows: bool = True, st=None):
|
| 507 |
"""The user-table mirror of `grid_assembly` / `product_assembly` β SAME g-dict keys, so
|
| 508 |
`/workspace` and the events route consume any of the three interchangeably.
|
| 509 |
|
|
|
|
| 532 |
|
| 533 |
limits = []
|
| 534 |
if with_rows:
|
| 535 |
+
# β W33-T03 (D-214): `st` is a caller's LEND, threaded to the wall and nowhere else. Only
|
| 536 |
+
# a READ route passes one β see `scoped_pool`'s own note and contract C5.
|
| 537 |
+
pids, rows_src, fields_base, defn = scoped_pool(session, table_key, st=st)
|
| 538 |
else:
|
| 539 |
pids, fields_base, defn = scoped_pids(session, table_key, limits=limits)
|
| 540 |
rows_src = []
|
|
|
|
| 735 |
raise err(400, "bad_label", "give the database a name")
|
| 736 |
if not session.runtime.available():
|
| 737 |
raise err(503, "store_unavailable",
|
| 738 |
+
"the tenant store is unavailable. Nothing was created")
|
| 739 |
source = body.get("source")
|
| 740 |
try:
|
| 741 |
key = ut.create(label, session.uname, fields=body.get("fields"),
|
| 742 |
source=source, st=session.runtime)
|
| 743 |
except Exception:
|
| 744 |
raise err(503, "store_unavailable",
|
| 745 |
+
"the tenant store refused the write. Nothing was created")
|
| 746 |
if not key:
|
| 747 |
raise err(400, "refused",
|
| 748 |
+
f"could not create it. The name may be empty or this tenant already has "
|
| 749 |
f"{ut.MAX_TABLES} databases")
|
| 750 |
return {"key": key}
|
| 751 |
|
|
|
|
| 777 |
|
| 778 |
Counts drill to the SAME buckets `user_tables.delete` cleans; a dialog listing categories
|
| 779 |
without numbers would break [[no-unverifiable-aggregates]] at the scariest moment. Walled
|
| 780 |
+
like the delete itself: only someone who could delete may case the joint.
|
| 781 |
+
|
| 782 |
+
β W33-T01 / D-213: the wall and `createdBy`/`fields` come off the PROJECTION; only the row
|
| 783 |
+
COUNT needs the whole document, and only on a materialised table."""
|
| 784 |
+
defn = _defn_or_refuse(session, table_key, defs_only=True)
|
| 785 |
if not (session.admin or defn.get("createdBy") == session.uname):
|
| 786 |
raise err(403, "forbidden", "only the database's creator or an admin can delete it")
|
| 787 |
s = session.runtime
|
|
|
|
| 804 |
auto.append({"id": str(aid), "name": d.get("name") or str(aid)})
|
| 805 |
except Exception:
|
| 806 |
pass
|
| 807 |
+
# β THE ROW COUNT IS THE ONE FIELD THAT NEEDS THE WHOLE DOCUMENT, and it needs it only where
|
| 808 |
+
# the rows are actually stored here. A read-through database keeps `rows: {}` by construction,
|
| 809 |
+
# so `len(...)` answered **0** for it before this change and answers 0 now β identical, and the
|
| 810 |
+
# projection is not what makes it wrong.
|
| 811 |
+
# β 0 IS A WRONG NUMBER FOR A READ-THROUGH GRID and always was (`ut_odoo_gl_lines` would say 0
|
| 812 |
+
# in a dialog headed "what dies with this database"). Booked rather than fixed here: this
|
| 813 |
+
# ticket is a read-path change and correcting it means asking the mirror for a `count(*)`
|
| 814 |
+
# inside a confirm dialog. See the `PENDING:` line in `mailbox/A.md`.
|
| 815 |
+
if _ut().materialises(table_key, st=s, defn=defn):
|
| 816 |
+
rows = len((_ut().get(table_key, st=s) or {}).get("rows") or {})
|
| 817 |
+
else:
|
| 818 |
+
rows = 0
|
| 819 |
+
return {"rows": rows, "fields": fields, "views": len(views),
|
| 820 |
"sharedUsers": len(g.get("entries") or []),
|
| 821 |
"automations": sorted(auto, key=lambda a: a["name"].lower())}
|
| 822 |
|
|
|
|
| 845 |
try:
|
| 846 |
_ut().delete(table_key, st=session.runtime)
|
| 847 |
except Exception:
|
| 848 |
+
raise err(503, "store_unavailable", "the delete did not land. Try again")
|
| 849 |
return {"ok": True}
|
| 850 |
|
| 851 |
|
|
|
|
| 935 |
import aios_grid
|
| 936 |
|
| 937 |
_ig_forward(session)
|
| 938 |
+
# ββ W33-T03 / D-214 β ONE READ OF THE TENANT DOCUMENT FOR THE WHOLE REQUEST, MEASURED.
|
| 939 |
+
# This route asked for it FOUR times: the wall (via `scoped_pool`), then `limit_report` TWICE
|
| 940 |
+
# (`row_limit` calls `materialises` and then `is_connected`, and each takes its own whole copy),
|
| 941 |
+
# then `records_mutable` at the envelope. Each is ~703 ms warm on tenant #0, and all four ask
|
| 942 |
+
# about the SAME document in the SAME request. The lend is the fix W31 QA already built for
|
| 943 |
+
# `_defn_or_refuse`; this threads it through the three sites that never got it.
|
| 944 |
+
# β SAFE HERE FOR THE SAME REASON IT IS SAFE THERE: this is a pure READ route. A lend is a
|
| 945 |
+
# PRE-WRITE snapshot, and handing one to a path that writes and then reads back would report the
|
| 946 |
+
# value it replaced (contract C5).
|
| 947 |
+
_lent = _ut().lend(session.runtime)
|
| 948 |
+
g = ut_assembly(session, table_key, st=_lent)
|
| 949 |
# β THE OVERLAY WAS NEVER ACTUALLY MERGED, and the docstring above has described the merge
|
| 950 |
# this line does not perform since the route was written (owner item 3, 2026-08-09:
|
| 951 |
# *"Using the swipe, fast doesn't register the CHANGE. I went back and it all got reseted"*).
|
|
|
|
| 993 |
# so a tenant using `json` for a short config sees no change at all.
|
| 994 |
rows = aios_grid.rows_from_pool(
|
| 995 |
g["rows_src"], g["fields"], _thin_json(g["fields"], merged, table_key), derived=g["derived"])
|
| 996 |
+
# ββ WAVE-34 (R13) β the per-cell enrichment STATE rides the row, beside `_created`/`lat`/
|
| 997 |
+
# `lon`. See `_stamp_ai_states` for why it is a row key rather than a map beside `rows`.
|
| 998 |
+
_stamp_ai_states(table_key, g["fields"], rows, st=_lent)
|
| 999 |
# β R6's SECOND SENTENCE, ON THE WIRE (W30-T29). *"if there is lag or it can't be done, you
|
| 1000 |
# need to explicitly tell me why and recommend a fix."* A ceiling that still applies to this
|
| 1001 |
# database says so here, with its cause and the recommendation, rather than waiting to be
|
| 1002 |
# discovered as a refused paste. `None` for a connected source, and an EMPTY LIST is the
|
| 1003 |
# honest answer for a table nothing limits β never an absent key, which a client cannot tell
|
| 1004 |
# apart from an older server.
|
| 1005 |
+
_report = _ut().limit_report(table_key, st=_lent)
|
| 1006 |
# β C4 / D-138 β THE DOCUMENTS PRODUCER. Absent since EXIT-6 deleted `app.py`, which was the
|
| 1007 |
# only thing that ever set this key; the write door never stopped working and every client
|
| 1008 |
# half is complete, but all six `onDoc*` handlers read `payload?.docs ? β¦ : undefined`, so a
|
|
|
|
| 1016 |
"identity": {"pid": "pid"},
|
| 1017 |
"scope": {"table": table_key, "rowCount": len(rows)},
|
| 1018 |
"limits": [_report] if _report else [],
|
| 1019 |
+
"recordsMutable": _ut().records_mutable(table_key, st=_lent)}
|
| 1020 |
+
|
| 1021 |
+
|
| 1022 |
+
#: The per-cell provenance a row carries on the wire, one key per enrichment column.
|
| 1023 |
+
#: β A ROW KEY RATHER THAN A SIBLING MAP, and the choice is load-bearing rather than cosmetic.
|
| 1024 |
+
#: A `{colId: {pid: state}}` map beside `rows` would need a new PROP on `RecordDetail` and a new
|
| 1025 |
+
#: argument at `CustomerGrid`'s call site, both in another lane's fence, to reach the two surfaces
|
| 1026 |
+
#: that must paint it. The row already carries `_created`, `lat` and `lon` for exactly this
|
| 1027 |
+
#: reason, so every reader already tolerates keys that are not columns, and both surfaces hold the
|
| 1028 |
+
#: row already. β COLLISION-PROOF BY CONSTRUCTION: `_clean_field` strips leading underscores off
|
| 1029 |
+
#: every field key, so no column can ever be called `_ai_*`.
|
| 1030 |
+
AI_STATE_PREFIX = "_ai_"
|
| 1031 |
+
|
| 1032 |
+
|
| 1033 |
+
def _stamp_ai_states(table_key, fields, rows, st=None):
|
| 1034 |
+
"""Add `_ai_<colId>` to each row for every `ai_enrich` column. Mutates and returns `rows`.
|
| 1035 |
+
|
| 1036 |
+
β A PROJECTION, NOT THE MARK SET. The stratum holds a hash, a model, a timestamp, a token
|
| 1037 |
+
count and an error per cell; a browser needs ONE WORD to paint a state, and shipping the rest
|
| 1038 |
+
would grow this payload by a dict per enriched cell for data no reader reads. The vocabulary
|
| 1039 |
+
is `agent`/`human`/`stale`/`error` (`api/ai_enrich.py::cell_state`), which is also what the
|
| 1040 |
+
RUNNER obeys, so the badge and the behaviour cannot disagree about whose cell it is.
|
| 1041 |
+
|
| 1042 |
+
β AN ABSENT KEY MEANS `empty`, and only non-empty states are stamped: a table with no
|
| 1043 |
+
enrichment column is untouched, and a freshly created column adds nothing until something
|
| 1044 |
+
runs. β `stale` is DERIVED here rather than stored, so it is computed against TODAY'S row
|
| 1045 |
+
instead of against whatever was true when the value was written.
|
| 1046 |
+
"""
|
| 1047 |
+
cols = [f for f in (fields or []) if str(f.get("type") or "") == "ai_enrich"]
|
| 1048 |
+
if not cols:
|
| 1049 |
+
return rows
|
| 1050 |
+
import ai_enrich as _ae
|
| 1051 |
+
for field in cols:
|
| 1052 |
+
col = str(field.get("key") or "")
|
| 1053 |
+
marks = _ut().ai_enrich_marks(table_key, col, st=st)
|
| 1054 |
+
cfg = field.get("aiEnrich") if isinstance(field.get("aiEnrich"), dict) else {}
|
| 1055 |
+
for row in (rows or []):
|
| 1056 |
+
if not isinstance(row, dict):
|
| 1057 |
+
continue
|
| 1058 |
+
state = _ae.cell_state(marks.get(str(row.get("pid"))), cfg, row, col)
|
| 1059 |
+
if state != "empty":
|
| 1060 |
+
row[AI_STATE_PREFIX + col] = state
|
| 1061 |
+
return rows
|
| 1062 |
|
| 1063 |
|
| 1064 |
@router.get("/tables/{table_key}/rows/{pid}/fields/{fkey}")
|
|
|
|
| 1107 |
rid = ut.add_row(table_key, values, session.uname, st=session.runtime,
|
| 1108 |
rid=(body or {}).get("rid"))
|
| 1109 |
except Exception:
|
| 1110 |
+
raise err(503, "store_unavailable", "the row was not saved. The store refused")
|
| 1111 |
if rid is None:
|
| 1112 |
# C3 (wave 25): `add_row` also refuses a profile cell that is not a handle, so the cap
|
| 1113 |
# sentence alone would misdirect β the reader would go and count rows. Ask the same
|
|
|
|
| 1117 |
_h, ok = ut.normalize_profile(values[pf["key"]], pf["profile"].get("source"))
|
| 1118 |
if not ok:
|
| 1119 |
raise err(400, "refused",
|
| 1120 |
+
f"{str(values[pf['key']])[:80]!r} is not an Instagram profile. "
|
| 1121 |
f"{pf.get('label') or pf['key']!r} takes a handle (@name) or a "
|
| 1122 |
f"profile link (instagram.com/name)")
|
| 1123 |
raise err(400, "refused",
|
| 1124 |
+
f"row refused. The table may be at its {ut.MAX_ROWS}-row cap")
|
| 1125 |
_refresh_relations(session)
|
| 1126 |
return {"rid": rid, "pid": int(rid)}
|
| 1127 |
|
|
|
|
| 1175 |
for key, value in row.items():
|
| 1176 |
why = ut.cell_type_refusal(by_key[key], value)
|
| 1177 |
if why:
|
| 1178 |
+
raise err(400, "bad_value", f"row {index + 1}: {why}. Nothing was imported")
|
| 1179 |
try:
|
| 1180 |
made = ut.add_rows(table_key, rows_in, session.uname, st=session.runtime)
|
| 1181 |
except Exception:
|
| 1182 |
+
raise err(503, "store_unavailable", "nothing was imported. The store refused")
|
| 1183 |
if made is None:
|
| 1184 |
raise err(400, "refused",
|
| 1185 |
+
f"nothing was imported. {len(rows_in)} rows would take this database past "
|
| 1186 |
f"its {ut.MAX_ROWS}-row cap, or a profile column rejected a value")
|
| 1187 |
_refresh_relations(session)
|
| 1188 |
return {"imported": len(made), "pids": [int(r) for r in made]}
|
|
|
|
| 1202 |
# as the rename (item 6a): two places to look, and the surfaces disagreed silently.
|
| 1203 |
|
| 1204 |
def _field_or_refuse(session, table_key, fkey=""):
|
| 1205 |
+
"""The schema wall. `_defn_or_refuse` first (404/403 on the table), then the per-field rule.
|
| 1206 |
+
|
| 1207 |
+
β W33-T01 / D-213: definitions only. Everything read off `defn` here is `fields` and
|
| 1208 |
+
`createdBy`; the returned value is DISCARDED by all three callers (they re-fetch what they
|
| 1209 |
+
write through the `user_tables` write doors), so no projected snapshot survives into a write.
|
| 1210 |
+
β It is a SCHEMA wall on a write route, not a row-write wall β the distinction contract C5
|
| 1211 |
+
draws is about the snapshot reaching a read-BACK, and this one does not escape the function."""
|
| 1212 |
+
defn = _defn_or_refuse(session, table_key, defs_only=True)
|
| 1213 |
ut = _ut()
|
| 1214 |
if not ut.is_user_table(table_key, st=session.runtime):
|
| 1215 |
raise err(400, "not_a_user_table",
|
| 1216 |
+
"only a user-created database has an editable schema. A connected source "
|
| 1217 |
"owns its own columns")
|
| 1218 |
if fkey and not ut.may_edit_field(table_key, fkey, session.uname, session.admin,
|
| 1219 |
st=session.runtime):
|
|
|
|
| 1266 |
# field relational", which is the question that was always meant.
|
| 1267 |
if field.get("type") in ("link", "rollup"):
|
| 1268 |
_refresh_relations(session)
|
| 1269 |
+
return _with_dropped(ut, {"field": field}, body)
|
| 1270 |
+
|
| 1271 |
+
|
| 1272 |
+
def _with_dropped(ut, out, body):
|
| 1273 |
+
"""Attach the NAMED list of config keys the validator did not keep (wave 34, R13 / W34-T51).
|
| 1274 |
+
|
| 1275 |
+
ββ THIS EXISTS BECAUSE THE VALIDATOR HAS NO ERROR CHANNEL AND CANNOT GROW ONE. Every bag
|
| 1276 |
+
cleaner in `core/user_tables.py` returns `dict | None` and drops unknown keys in silence, and
|
| 1277 |
+
`verify_fields_contract` asserts that they do -- so the drop is correct and the SILENCE is the
|
| 1278 |
+
defect. T51's contract is that an unknown config key is dropped **and named**, so the naming
|
| 1279 |
+
rides the response beside the accepted field rather than inside the validator.
|
| 1280 |
+
|
| 1281 |
+
β OMITTED WHEN EMPTY, deliberately: an always-present `dropped: []` teaches every reader to
|
| 1282 |
+
ignore the key, which is how a report stops being read before it stops being true.
|
| 1283 |
+
"""
|
| 1284 |
+
dropped = ut.ai_enrich_dropped_keys((body or {}).get("aiEnrich"))
|
| 1285 |
+
if dropped:
|
| 1286 |
+
out = dict(out)
|
| 1287 |
+
out["dropped"] = dropped
|
| 1288 |
+
return out
|
| 1289 |
|
| 1290 |
|
| 1291 |
def _refusal_sentence(ut, session, body, table_key="", fkey=""):
|
| 1292 |
"""Why was this column refused? The specific reason when we can name one, the general list
|
| 1293 |
otherwise β never a specific-sounding guess."""
|
| 1294 |
+
# β WAVE-34 (R13): the enrichment column's own sentence, named BEFORE the automation bag
|
| 1295 |
+
# below. `_clean_field` DERIVES `field.automation` for this kind, so a refused enrichment
|
| 1296 |
+
# column would otherwise be explained by the flow law -- "pick a flow, or make this an
|
| 1297 |
+
# ordinary column" -- which is the D-46 misdirection exactly, pointing at a control the user
|
| 1298 |
+
# never touched.
|
| 1299 |
+
if str((body or {}).get("type") or "").strip().lower() == "ai_enrich":
|
| 1300 |
+
bag = (body or {}).get("aiEnrich")
|
| 1301 |
+
if not isinstance(bag, dict) or not str(bag.get("prompt") or "").strip():
|
| 1302 |
+
return ("an AI enrichment column needs a prompt. It is the only thing that can "
|
| 1303 |
+
"produce a value here, so a column without one would stay empty forever")
|
| 1304 |
# β C3 (wave 25, R7): the one-profile-per-table refusal NAMES THE EXISTING COLUMN, which is
|
| 1305 |
# what the contract asks for and what makes it actionable β "at most one" sends the reader
|
| 1306 |
# hunting through a 40-column schema for a flag they cannot see from the header.
|
|
|
|
| 1312 |
# real mistake was the column type sends them to fix the wrong thing, which is the
|
| 1313 |
# misdirection D-46 closed one door over.
|
| 1314 |
if str((body or {}).get("type") or "text").strip().lower() != "text":
|
| 1315 |
+
return ("a profile column is a flag on an ordinary TEXT column. It validates what "
|
| 1316 |
"is typed into it, which it can only do for text")
|
| 1317 |
existing = ut.profile_field(table_key, st=session.runtime) if table_key else None
|
| 1318 |
if existing and existing.get("key") != str(fkey):
|
| 1319 |
+
return (f"this database already has a profile column: "
|
| 1320 |
f"{existing.get('label') or existing.get('key')!r}. A database has at most "
|
| 1321 |
f"one, so the automation knows which handle to enrich; edit that column, or "
|
| 1322 |
f"take the flag off it first")
|
|
|
|
| 1324 |
if isinstance(bag, dict):
|
| 1325 |
flow = str(bag.get("flowId") or "").strip()
|
| 1326 |
if not flow:
|
| 1327 |
+
return ("an automation column has to name the automation that fills it. Pick a "
|
| 1328 |
"flow, or make this an ordinary column")
|
| 1329 |
if not ut.flow_bound(bag, st=session.runtime):
|
| 1330 |
return (f"this column names automation {flow!r}, which does not exist in this "
|
| 1331 |
+
f"workspace. It may have been deleted; pick a flow that is still there")
|
| 1332 |
kind = str((body or {}).get("type") or "").strip()
|
| 1333 |
if kind and kind not in ut.UT_FIELD_TYPES:
|
| 1334 |
return (f"{kind!r} is not a column type here (types: "
|
| 1335 |
f"{', '.join(sorted(ut.UT_FIELD_TYPES))})")
|
| 1336 |
+
return (f"the column was refused. Check the name and type, or the table may be at its "
|
| 1337 |
f"{ut.MAX_FIELDS}-column cap (types: {', '.join(sorted(ut.UT_FIELD_TYPES))})")
|
| 1338 |
|
| 1339 |
|
|
|
|
| 1356 |
try:
|
| 1357 |
migrated = ut.rename_choice_values(table_key, fkey, renames, st=session.runtime)
|
| 1358 |
except Exception:
|
| 1359 |
+
raise err(503, "store_unavailable", "the rename did not land. Try again")
|
| 1360 |
# The per-user workspace strata and any view filter naming the old value are the OTHER
|
| 1361 |
# half of C-RENAME and belong to `core.table_store`. Called only if it is there: an
|
| 1362 |
# enumerator's mirror waits for its counterpart rather than guessing at its shape, and a
|
|
|
|
| 1383 |
out = {"field": field}
|
| 1384 |
if migrated is not None:
|
| 1385 |
out["migrated"] = migrated
|
| 1386 |
+
return _with_dropped(ut, out, body)
|
| 1387 |
+
|
| 1388 |
+
|
| 1389 |
+
def _fire_on_change(table_key, pid, changed, session):
|
| 1390 |
+
"""Run any `on_change` enrichment column whose prompt names a cell that just moved.
|
| 1391 |
+
|
| 1392 |
+
β ONE DEFINITION READ FOR THE WHOLE WRITE, and that is the point rather than an optimisation.
|
| 1393 |
+
`automation_engine.grid_hook` calls `all_definitions(st)` once PER EVENT, which turns a
|
| 1394 |
+
20,000-row import into 20,000 whole-document reads on the single process this product runs
|
| 1395 |
+
(`D-134`, and `W34-T54`'s own `how:` says not to rebuild it). `on_change_fields` is pure and
|
| 1396 |
+
takes the definition, so this reads once and asks about every column.
|
| 1397 |
+
|
| 1398 |
+
β AND IT NEVER FAILS THE WRITE. The cell edit has already succeeded and been acknowledged;
|
| 1399 |
+
an enrichment that could not run is a missing value, not a lost edit, and the run's own report
|
| 1400 |
+
carries the reason. β It is also deliberately SYNCHRONOUS and bounded to this one row: a
|
| 1401 |
+
fan-out here would put a vendor call on the critical path of every keystroke-commit.
|
| 1402 |
+
"""
|
| 1403 |
+
import ai_enrich as _ae
|
| 1404 |
+
|
| 1405 |
+
try:
|
| 1406 |
+
defn = _ut().get(table_key, st=session.runtime) or {}
|
| 1407 |
+
wanted = _ae.on_change_fields(defn, changed.keys())
|
| 1408 |
+
for field in wanted:
|
| 1409 |
+
# β W35-T41 / C7 β `user` is the usage ledger's attribution. An on-change run is still
|
| 1410 |
+
# somebody's edit spending somebody's tokens, so it is booked against the person who
|
| 1411 |
+
# typed rather than left unattributed.
|
| 1412 |
+
_ae.run_field(table_key, field["key"], st=session.runtime, rows=[str(pid)],
|
| 1413 |
+
user=session.uname)
|
| 1414 |
+
except Exception: # noqa: BLE001
|
| 1415 |
+
pass
|
| 1416 |
+
|
| 1417 |
+
|
| 1418 |
+
@router.post("/tables/{table_key}/fields/{fkey}/enrich")
|
| 1419 |
+
def enrich_field(table_key: str, fkey: str, body: dict = Body(default=None),
|
| 1420 |
+
session: Session = Depends(require_session)):
|
| 1421 |
+
"""Run an AI enrichment column (wave 34, owner ruling R13). Returns the run's own REPORT.
|
| 1422 |
+
|
| 1423 |
+
β THIS DOOR SPENDS MONEY, so it rides the same wall every other schema write rides
|
| 1424 |
+
(`_field_or_refuse`) rather than a looser one of its own. A read-only viewer cannot bill the
|
| 1425 |
+
tenant by opening a grid.
|
| 1426 |
+
|
| 1427 |
+
`{"rows": ["3"]}` is a MANUAL run of exactly those records: a person asked, in front of the
|
| 1428 |
+
value being replaced, so it skips the `overwrite` policy. An ABSENT `rows` is the automatic
|
| 1429 |
+
plan, where the policy and the never-overwrite-a-human law both apply. The two are one
|
| 1430 |
+
function with one flag, not two runners.
|
| 1431 |
+
|
| 1432 |
+
β THE REPORT IS THE PRODUCT, not a status code. It carries `filled`, `failed`, `skipped` by
|
| 1433 |
+
reason, `tokens` spent, the provider, per-row errors, and `limit` (R6's second sentence: a
|
| 1434 |
+
ceiling that stopped the run names its cause and a remedy). A 200 with `filled: 0` and a
|
| 1435 |
+
populated `skipped` is a correct, informative answer, and the client must render it rather
|
| 1436 |
+
than treat it as success.
|
| 1437 |
+
"""
|
| 1438 |
+
_field_or_refuse(session, table_key, fkey)
|
| 1439 |
+
import ai_enrich as _ae
|
| 1440 |
+
|
| 1441 |
+
rows = (body or {}).get("rows")
|
| 1442 |
+
if rows is not None and not isinstance(rows, list):
|
| 1443 |
+
raise err(400, "bad_rows", "`rows` must be a list of record ids, or absent to run the "
|
| 1444 |
+
"rows this column's own settings choose")
|
| 1445 |
+
# The caller's permitted pool, the same one the row doors use. A named row outside it is
|
| 1446 |
+
# dropped rather than refused: a stale client naming a record that has been deleted or moved
|
| 1447 |
+
# out of scope should not fail a run over the rows it can legitimately fill.
|
| 1448 |
+
if rows is not None:
|
| 1449 |
+
allowed = {str(p) for p in scoped_pids(session, table_key)[0]}
|
| 1450 |
+
rows = [str(r) for r in rows if str(r) in allowed]
|
| 1451 |
+
# β `W34-T54`'s bulk menu is this one field: "Rows never filled" sends `blank`, "All rows"
|
| 1452 |
+
# sends `always`. Anything else falls back to the column's own saved policy rather than to a
|
| 1453 |
+
# default, so a typo cannot quietly widen what a run touches.
|
| 1454 |
+
report = _ae.run_field(table_key, fkey, st=session.runtime, rows=rows,
|
| 1455 |
+
policy=str((body or {}).get("scope") or "") or None,
|
| 1456 |
+
# A named row set through THIS door is a person asking.
|
| 1457 |
+
manual=rows is not None,
|
| 1458 |
+
# β W35-T41 / C7 β the usage ledger's attribution.
|
| 1459 |
+
user=session.uname)
|
| 1460 |
+
if report.get("problem"):
|
| 1461 |
+
# A run that could not start at all is not a 200: nothing was attempted, nothing was
|
| 1462 |
+
# spent, and the reason is actionable (no provider configured, or the wrong column).
|
| 1463 |
+
raise err(400, "enrich_refused", str(report["problem"]))
|
| 1464 |
+
return report
|
| 1465 |
|
| 1466 |
|
| 1467 |
@router.delete("/tables/{table_key}/fields/{fkey}")
|
|
|
|
| 1469 |
_field_or_refuse(session, table_key, fkey)
|
| 1470 |
if not _ut().delete_field(table_key, fkey, st=session.runtime):
|
| 1471 |
raise err(400, "refused",
|
| 1472 |
+
"that column could not be removed. A database must keep at least one")
|
| 1473 |
_refresh_relations(session)
|
| 1474 |
return {"deleted": fkey}
|
| 1475 |
|
|
|
|
| 1494 |
try:
|
| 1495 |
ok = _ut().delete_row(table_key, rid, st=lent)
|
| 1496 |
except Exception:
|
| 1497 |
+
raise err(503, "store_unavailable", "the delete did not land. Try again")
|
| 1498 |
if not ok:
|
| 1499 |
raise err(400, "refused", "rows can only be deleted from user-created databases")
|
| 1500 |
_refresh_relations(session)
|
|
|
|
| 1527 |
"pid": pid, "updates": updates}, ctx)
|
| 1528 |
except grid_events.StoreUnavailable:
|
| 1529 |
raise err(503, "store_unavailable",
|
| 1530 |
+
"the tenant store is unavailable. Your change was not saved")
|
| 1531 |
# β THE READ-BACK IS THE DEFINITION ROW, AND ON A `ut_` SCOPE THAT IS THE WHOLE OF IT.
|
| 1532 |
#
|
| 1533 |
# β CORRECTED, wave-29 T22 (owner item 2a): this note used to say "THE READ-BACK SPANS BOTH
|
|
|
|
| 1566 |
return False
|
| 1567 |
|
| 1568 |
refused = sorted(k for k in updates if not _took(k))
|
| 1569 |
+
# ββ WAVE-34 (R13) β THE HUMAN-EDIT STAMP, AND IT HAS TO HAPPEN HERE. "Did a person write
|
| 1570 |
+
# this cell?" is not recoverable from the value afterwards, so the only place to record it is
|
| 1571 |
+
# the door a person writes through. `ai_enrich_may_write` then refuses to let any automatic
|
| 1572 |
+
# run overwrite it, whatever the column's `overwrite` policy says.
|
| 1573 |
+
# β STAMPED FROM THE CELLS THAT ACTUALLY TOOK, never from what was asked: marking a refused
|
| 1574 |
+
# write `human` would freeze a cell against the agent on the strength of an edit that never
|
| 1575 |
+
# landed. `note_human_edit` filters to the enrichment columns itself and is a no-op otherwise.
|
| 1576 |
+
took = {k: v for k, v in accepted.items() if k not in refused}
|
| 1577 |
+
if took:
|
| 1578 |
+
try:
|
| 1579 |
+
_ut().note_human_edit(table_key, took, pid, st=session.runtime)
|
| 1580 |
+
except Exception: # noqa: BLE001
|
| 1581 |
+
# Provenance is metadata about a write that has already succeeded. Failing the
|
| 1582 |
+
# request here would tell the user their edit was lost when it was not.
|
| 1583 |
+
pass
|
| 1584 |
+
_fire_on_change(table_key, pid, took, session)
|
| 1585 |
out = {"pid": pid, "updates": accepted}
|
| 1586 |
if refused:
|
| 1587 |
out["refused"] = refused
|
api/routes_usage.py
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"""routes_usage.py β WAVE 35 (ruling R9, contract C7): `GET /api/v1/usage`, the AI meter.
|
| 2 |
+
|
| 3 |
+
Owner item 13's second door. R9: the dashboard REPORTS weekly usage per surface against an
|
| 4 |
+
allowance and does **not** cut anyone off this wave; over the allowance the product still works and
|
| 5 |
+
the bar is red.
|
| 6 |
+
|
| 7 |
+
β THIS ROUTE ENFORCES NOTHING AND MUST NOT START. It is the only reader of `usage_ledger`, and the
|
| 8 |
+
ledger has no ceiling in it (see that module's header). A `403 over_allowance` here would turn a
|
| 9 |
+
reporting feature into a wall the owner explicitly did not ask for this wave.
|
| 10 |
+
|
| 11 |
+
β TWO SCOPES, AND THE WIDER ONE IS ADMIN-ONLY. `?scope=me` (the default) is the caller's own week;
|
| 12 |
+
`?scope=tenant` folds every account and is refused for a non-admin β how much AI another employee
|
| 13 |
+
used is not a fact this product hands out sideways.
|
| 14 |
+
"""
|
| 15 |
+
from fastapi import APIRouter, Depends
|
| 16 |
+
|
| 17 |
+
import usage_ledger
|
| 18 |
+
from deps import Session, err, require_session
|
| 19 |
+
|
| 20 |
+
router = APIRouter(prefix="/api/v1")
|
| 21 |
+
|
| 22 |
+
|
| 23 |
+
@router.get("/usage")
|
| 24 |
+
def usage(scope: str = "me", session: Session = Depends(require_session)):
|
| 25 |
+
"""`{week, resets, allowance, total, over, calls, unmeasured, scope, surfaces: [...]}`.
|
| 26 |
+
|
| 27 |
+
Every one of the four surfaces is present whether or not it was used β see
|
| 28 |
+
`usage_ledger.usage`'s note on why a missing row and a quiet week must not look the same.
|
| 29 |
+
"""
|
| 30 |
+
wanted = str(scope or "me").strip().lower()
|
| 31 |
+
if wanted not in ("me", "tenant"):
|
| 32 |
+
raise err(400, "bad_request", "scope must be me or tenant")
|
| 33 |
+
if wanted == "tenant" and not session.admin:
|
| 34 |
+
raise err(403, "forbidden",
|
| 35 |
+
"only an administrator can see the whole workspace's AI usage")
|
| 36 |
+
out = usage_ledger.usage(session.runtime, session.uname,
|
| 37 |
+
tenant_wide=(wanted == "tenant"))
|
| 38 |
+
if session.admin and usage_ledger.UNATTRIBUTED["calls"]:
|
| 39 |
+
# β THE METER REPORTS ITS OWN BLIND SPOT (R6's second sentence). A call `record()` could not
|
| 40 |
+
# attribute β no store handle reached it, or the store refused β is absent from every number
|
| 41 |
+
# above, and an operator has to be able to see that rather than infer it.
|
| 42 |
+
# β ADMIN ONLY, and labelled as a PROCESS figure rather than a tenant one: the counter is a
|
| 43 |
+
# module global in this container, so it spans every tenant this process has served and is
|
| 44 |
+
# not a fact about the workspace being asked about.
|
| 45 |
+
out["unattributed"] = {
|
| 46 |
+
"calls": usage_ledger.UNATTRIBUTED["calls"],
|
| 47 |
+
"surfaces": dict(usage_ledger.UNATTRIBUTED["surfaces"]),
|
| 48 |
+
"note": ("these AI calls reached no ledger target in this container and are missing "
|
| 49 |
+
"from every figure above. It is a wiring gap, not usage"),
|
| 50 |
+
}
|
| 51 |
+
return out
|
api/usage_ledger.py
ADDED
|
@@ -0,0 +1,281 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"""usage_ledger.py β WAVE 35 (ruling R9, contract C7): ONE METER FOR EVERY AI SURFACE.
|
| 2 |
+
|
| 3 |
+
R9: *"ONE meter for every AI surface. The dashboard REPORTS weekly usage against an allowance and
|
| 4 |
+
does NOT cut anyone off this wave; over the allowance it still works, shown red."*
|
| 5 |
+
|
| 6 |
+
β SO THIS FILE MEASURES AND NEVER ENFORCES. There is no ceiling here, no refusal, and no caller of
|
| 7 |
+
this module may branch on its answer. The one limit the product does enforce is per COLUMN and lives
|
| 8 |
+
where it was built (`ai_enrich.ceiling_report`); this is the tenant-wide REPORT, and mixing the two
|
| 9 |
+
would make an over-allowance week silently stop somebody's enrichment run.
|
| 10 |
+
|
| 11 |
+
**THE FOUR SURFACES.** `assistant` (a person asking the Assistant a question) Β· `field_agent` (an AI
|
| 12 |
+
enrichment column filling cells) Β· `ai_review` (a model deciding a review stage) Β· `automation_draft`
|
| 13 |
+
(a sentence becoming a draft flow). They are the four LLM entry points the product has, and the gate
|
| 14 |
+
in `verify_api.py` DERIVES them from the code rather than reading this list, so a fifth entry point
|
| 15 |
+
is caught by the gate and not by somebody remembering to edit a tuple.
|
| 16 |
+
|
| 17 |
+
ββ **`record()` MUST BE HANDED ITS TARGET, AND THAT IS A MEASUREMENT, NOT A STYLE CHOICE.** The
|
| 18 |
+
obvious design is to bind `(runtime, username)` into a `contextvars.ContextVar` inside
|
| 19 |
+
`deps.require_session` β every session-authed request passes through it β so `record()` could take
|
| 20 |
+
C7's five arguments and resolve the rest itself. **It does not work here and it fails SILENTLY.**
|
| 21 |
+
Measured 2026-08-17 with a FastAPI `TestClient`: a `ContextVar` set inside a sync dependency reads
|
| 22 |
+
back `None` in the handler *and in every function the handler calls*, on the SAME OS thread (17820
|
| 23 |
+
both sides) β anyio copies the context per callable, so a `.set()` in the dependency's copy is
|
| 24 |
+
invisible to the endpoint's. An async endpoint reads `None` too. A ledger built that way would have
|
| 25 |
+
recorded nothing, answered no error, and shown a dashboard of zeros that looks exactly like a quiet
|
| 26 |
+
week ([[flag-shipped-without-its-writer]]).
|
| 27 |
+
|
| 28 |
+
β THEREFORE `st` AND `user` ARE KEYWORD ARGUMENTS AFTER C7'S FIVE, and a call that omits them is
|
| 29 |
+
COUNTED as unattributed and REPORTED rather than dropped β R6's second sentence applied to the meter
|
| 30 |
+
itself. A surface whose caller cannot reach a store handle is a gap somebody has to close; a meter
|
| 31 |
+
that hides the gap is worse than one that admits it.
|
| 32 |
+
"""
|
| 33 |
+
from __future__ import annotations
|
| 34 |
+
|
| 35 |
+
import os
|
| 36 |
+
import time
|
| 37 |
+
|
| 38 |
+
#: The store bucket. Small by construction β counters only, never a per-call log: a log would grow
|
| 39 |
+
#: without bound on a route that runs per row, and nothing in R9 asks a question a log answers.
|
| 40 |
+
STORE_KEY = "ai_usage"
|
| 41 |
+
|
| 42 |
+
#: The four AI surfaces (C7). β A surface this list does not name is REFUSED rather than stored under
|
| 43 |
+
#: whatever string arrived, because a typo'd surface is a meter that reads low forever with a second
|
| 44 |
+
#: row nobody looks at.
|
| 45 |
+
SURFACES = ("assistant", "field_agent", "ai_review", "automation_draft")
|
| 46 |
+
|
| 47 |
+
#: The weekly allowance the dashboard measures against (R9). β IT IS A REPORTING LINE, NOT A GATE.
|
| 48 |
+
#: Env-tunable so a deployment can set a real number without a release.
|
| 49 |
+
WEEKLY_ALLOWANCE = int(os.environ.get("AIOS_AI_WEEKLY_TOKENS") or 1_000_000)
|
| 50 |
+
|
| 51 |
+
#: How many weeks stay in the bucket. A meter is about this week and the trend behind it; keeping
|
| 52 |
+
#: every week forever turns a counter document into an append-only log by another route.
|
| 53 |
+
MAX_WEEKS = 8
|
| 54 |
+
|
| 55 |
+
#: Calls this PROCESS could not attribute to a store and a user β see the header. Reported to an
|
| 56 |
+
#: admin by `GET /usage`, never silently zero.
|
| 57 |
+
UNATTRIBUTED = {"calls": 0, "surfaces": {}}
|
| 58 |
+
|
| 59 |
+
|
| 60 |
+
def week_of(when=None):
|
| 61 |
+
"""The ISO week this instant belongs to, as `"2026-W33"`.
|
| 62 |
+
|
| 63 |
+
β UTC, EXPLICITLY, and never a naive local stamp. `routes_nav` records the same correction for
|
| 64 |
+
its own stamps: a naive local time written on a UTC host and parsed by a non-UTC browser misfiles
|
| 65 |
+
into the wrong bucket with nothing to go red. `%G`/`%V` are the ISO year and ISO week, which is
|
| 66 |
+
the only pair that agrees with itself across a year boundary (`%Y-%W` does not).
|
| 67 |
+
"""
|
| 68 |
+
return time.strftime("%G-W%V", time.gmtime(when if when is not None else time.time()))
|
| 69 |
+
|
| 70 |
+
|
| 71 |
+
def resets_at(when=None):
|
| 72 |
+
"""The UTC date the CURRENT week's counters roll over, as `"YYYY-MM-DD"`.
|
| 73 |
+
|
| 74 |
+
R9 asks the page to state when the allowance resets, so the server answers it β a client that
|
| 75 |
+
computed "next Monday" itself would be a second implementation of the week boundary, and the two
|
| 76 |
+
would disagree for anybody whose clock is not UTC ([[one-question-two-normalizers]]).
|
| 77 |
+
"""
|
| 78 |
+
now = when if when is not None else time.time()
|
| 79 |
+
tm = time.gmtime(now)
|
| 80 |
+
# `tm_wday` is 0 for Monday, so days-until-next-Monday is 7 minus however far in we are.
|
| 81 |
+
return time.strftime("%Y-%m-%d", time.gmtime(now + (7 - tm.tm_wday) * 86400))
|
| 82 |
+
|
| 83 |
+
|
| 84 |
+
def tokens_from(body):
|
| 85 |
+
"""`(tokens_in, tokens_out)` for one provider response. Either may be None.
|
| 86 |
+
|
| 87 |
+
β `None` MEANS THE PROVIDER DID NOT SAY, AND IT IS NOT ZERO. A ledger that books an unmeasured
|
| 88 |
+
call at zero reports a cheaper week than happened, which is exactly the cost-surprise complaint
|
| 89 |
+
R13 cited when the first token accounting was built. `ai_enrich._usage_tokens` has said this
|
| 90 |
+
since wave 34; this is that reader SPLIT, because C7 asks for input and output separately.
|
| 91 |
+
|
| 92 |
+
β THE TOTAL-ONLY SHAPE IS REAL AND IS NOT A SPLIT. Some providers answer only `total_tokens`.
|
| 93 |
+
That is reported by `record(total=...)` rather than by inventing a split, because halving a
|
| 94 |
+
total would put two numbers on a dashboard that were never measured.
|
| 95 |
+
"""
|
| 96 |
+
usage = (body or {}).get("usage")
|
| 97 |
+
if not isinstance(usage, dict):
|
| 98 |
+
return (None, None)
|
| 99 |
+
|
| 100 |
+
def _int(*keys):
|
| 101 |
+
for key in keys:
|
| 102 |
+
got = usage.get(key)
|
| 103 |
+
if isinstance(got, int) and not isinstance(got, bool):
|
| 104 |
+
return got
|
| 105 |
+
return None
|
| 106 |
+
|
| 107 |
+
return (_int("prompt_tokens", "input_tokens"),
|
| 108 |
+
_int("completion_tokens", "output_tokens"))
|
| 109 |
+
|
| 110 |
+
|
| 111 |
+
def total_from(body):
|
| 112 |
+
"""One call's TOTAL tokens, or None β the shape a caller with no use for the split wants.
|
| 113 |
+
|
| 114 |
+
β Prefers the provider's own `total_tokens` over a sum, because a provider that reports both may
|
| 115 |
+
count cached or reasoning tokens in the total and in neither half.
|
| 116 |
+
"""
|
| 117 |
+
usage = (body or {}).get("usage")
|
| 118 |
+
if isinstance(usage, dict):
|
| 119 |
+
for key in ("total_tokens", "totalTokens"):
|
| 120 |
+
got = usage.get(key)
|
| 121 |
+
if isinstance(got, int) and not isinstance(got, bool):
|
| 122 |
+
return got
|
| 123 |
+
ins, outs = tokens_from(body)
|
| 124 |
+
if ins is None and outs is None:
|
| 125 |
+
return None
|
| 126 |
+
return (ins or 0) + (outs or 0)
|
| 127 |
+
|
| 128 |
+
|
| 129 |
+
def _int_or_none(value):
|
| 130 |
+
if isinstance(value, int) and not isinstance(value, bool):
|
| 131 |
+
return max(0, value)
|
| 132 |
+
return None
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
def record(surface, provider, model, tokens_in=None, tokens_out=None, *,
|
| 136 |
+
total=None, calls=1, st=None, user=""):
|
| 137 |
+
"""Book ONE AI call. Returns True when the line landed durably, False when it could not.
|
| 138 |
+
|
| 139 |
+
C7's signature is the five positional parameters; everything after `*` is this module's own
|
| 140 |
+
extension and each one has a reason:
|
| 141 |
+
|
| 142 |
+
Β· `total` β for a caller that knows the total and not the split (`ai_enrich.run_field`
|
| 143 |
+
accumulates a per-run total through an `_ask` contract a gate injects against, and changing
|
| 144 |
+
that contract to carry a split would break the injected shape for no gain here).
|
| 145 |
+
Β· `calls` β so a RUN over many rows books one line with its real call count instead of one
|
| 146 |
+
store write per row.
|
| 147 |
+
Β· `st` / `user` β the target. Required in practice; see this module's header for the measured
|
| 148 |
+
reason a contextvar cannot supply them.
|
| 149 |
+
|
| 150 |
+
β IT NEVER RAISES. A meter that can break the feature it measures is worse than no meter: a
|
| 151 |
+
store blip during an enrichment run would abort the run and lose the cells.
|
| 152 |
+
β AND IT NEVER SILENTLY SUCCEEDS. A call it cannot attribute increments `UNATTRIBUTED`, which
|
| 153 |
+
`GET /usage` shows an admin.
|
| 154 |
+
"""
|
| 155 |
+
key = str(surface or "").strip()
|
| 156 |
+
if key not in SURFACES:
|
| 157 |
+
# Refused rather than stored: a surface nobody named is a row nobody reads, and the meter
|
| 158 |
+
# would read low forever with no sign of why.
|
| 159 |
+
return False
|
| 160 |
+
ins, outs = _int_or_none(tokens_in), _int_or_none(tokens_out)
|
| 161 |
+
tot = _int_or_none(total)
|
| 162 |
+
if tot is None and (ins is not None or outs is not None):
|
| 163 |
+
tot = (ins or 0) + (outs or 0)
|
| 164 |
+
n = max(0, int(calls) if isinstance(calls, int) and not isinstance(calls, bool) else 1)
|
| 165 |
+
if not n:
|
| 166 |
+
return False
|
| 167 |
+
uname = str(user or "").strip().lower()
|
| 168 |
+
if st is None:
|
| 169 |
+
UNATTRIBUTED["calls"] += n
|
| 170 |
+
UNATTRIBUTED["surfaces"][key] = UNATTRIBUTED["surfaces"].get(key, 0) + n
|
| 171 |
+
return False
|
| 172 |
+
week = week_of()
|
| 173 |
+
prov, mdl = str(provider or "")[:40], str(model or "")[:80]
|
| 174 |
+
|
| 175 |
+
def _up(data):
|
| 176 |
+
data = data if isinstance(data, dict) else {}
|
| 177 |
+
weeks = {w: v for w, v in data.items() if isinstance(v, dict)}
|
| 178 |
+
row = ((weeks.setdefault(week, {})
|
| 179 |
+
.setdefault(uname or "-", {}))
|
| 180 |
+
.setdefault(key, {}))
|
| 181 |
+
row["calls"] = int(row.get("calls") or 0) + n
|
| 182 |
+
if tot is None:
|
| 183 |
+
# β "the call happened, the tokens are unknown" IS A STATE, and it has to be
|
| 184 |
+
# representable or the meter quietly under-reports. The dashboard shows it as a count of
|
| 185 |
+
# unmeasured calls beside the token total.
|
| 186 |
+
row["unmeasured"] = int(row.get("unmeasured") or 0) + n
|
| 187 |
+
else:
|
| 188 |
+
row["tokens"] = int(row.get("tokens") or 0) + tot
|
| 189 |
+
if ins is not None:
|
| 190 |
+
row["tokens_in"] = int(row.get("tokens_in") or 0) + ins
|
| 191 |
+
if outs is not None:
|
| 192 |
+
row["tokens_out"] = int(row.get("tokens_out") or 0) + outs
|
| 193 |
+
if prov:
|
| 194 |
+
row["provider"] = prov
|
| 195 |
+
if mdl:
|
| 196 |
+
row["model"] = mdl
|
| 197 |
+
# Oldest weeks first to go. Sorting ISO week strings sorts chronologically by construction,
|
| 198 |
+
# which is the second reason `%G-W%V` is the format rather than a prettier one.
|
| 199 |
+
for stale in sorted(weeks)[:-MAX_WEEKS]:
|
| 200 |
+
weeks.pop(stale, None)
|
| 201 |
+
return weeks
|
| 202 |
+
|
| 203 |
+
try:
|
| 204 |
+
# β `flush='async'` β the coalescing mode ([[store-async-flush]]). This is the hot path of
|
| 205 |
+
# every AI surface in the product (an enrichment run books one line per RUN, but the
|
| 206 |
+
# assistant books one per question), and a blocking hub upload per call would put a network
|
| 207 |
+
# round trip inside the answer a person is waiting for. The mutation applies to the
|
| 208 |
+
# in-process cache immediately, so `GET /usage` reads its own writes.
|
| 209 |
+
st.update(STORE_KEY, _up, flush="async")
|
| 210 |
+
return True
|
| 211 |
+
except Exception: # noqa: BLE001
|
| 212 |
+
UNATTRIBUTED["calls"] += n
|
| 213 |
+
UNATTRIBUTED["surfaces"][key] = UNATTRIBUTED["surfaces"].get(key, 0) + n
|
| 214 |
+
return False
|
| 215 |
+
|
| 216 |
+
|
| 217 |
+
def _blank_row():
|
| 218 |
+
return {"calls": 0, "tokens": 0, "tokens_in": 0, "tokens_out": 0, "unmeasured": 0}
|
| 219 |
+
|
| 220 |
+
|
| 221 |
+
def _fold(rows):
|
| 222 |
+
out = _blank_row()
|
| 223 |
+
for row in rows:
|
| 224 |
+
if not isinstance(row, dict):
|
| 225 |
+
continue
|
| 226 |
+
for field in ("calls", "tokens", "tokens_in", "tokens_out", "unmeasured"):
|
| 227 |
+
got = row.get(field)
|
| 228 |
+
if isinstance(got, int) and not isinstance(got, bool):
|
| 229 |
+
out[field] += max(0, got)
|
| 230 |
+
return out
|
| 231 |
+
|
| 232 |
+
|
| 233 |
+
def usage(st, user="", *, tenant_wide=False, week=None):
|
| 234 |
+
"""This week's meter. `{week, resets, allowance, total, over, surfaces: [...], ...}`.
|
| 235 |
+
|
| 236 |
+
`tenant_wide=True` folds every account in the tenant β the admin view. Otherwise only `user`.
|
| 237 |
+
|
| 238 |
+
β EVERY SURFACE IS PRESENT WHETHER OR NOT IT WAS USED, at zero. A surface a consumer has to test
|
| 239 |
+
for is a surface a consumer forgets to test for, and R9 says ONE meter for every AI surface: a
|
| 240 |
+
missing row and a quiet week would render identically, and only one of them is true.
|
| 241 |
+
β NOTHING HERE IS ESTIMATED. A surface with no ledger line reports zero, never a guess
|
| 242 |
+
([[no-unverifiable-aggregates]]).
|
| 243 |
+
"""
|
| 244 |
+
wk = str(week or week_of())
|
| 245 |
+
try:
|
| 246 |
+
stored = st.get(STORE_KEY) or {}
|
| 247 |
+
except Exception: # noqa: BLE001
|
| 248 |
+
stored = {}
|
| 249 |
+
by_week = stored.get(wk) if isinstance(stored, dict) else {}
|
| 250 |
+
by_week = by_week if isinstance(by_week, dict) else {}
|
| 251 |
+
uname = str(user or "").strip().lower()
|
| 252 |
+
if tenant_wide:
|
| 253 |
+
buckets = [b for b in by_week.values() if isinstance(b, dict)]
|
| 254 |
+
else:
|
| 255 |
+
buckets = [by_week.get(uname or "-")] if isinstance(by_week.get(uname or "-"), dict) else []
|
| 256 |
+
surfaces = []
|
| 257 |
+
for key in SURFACES:
|
| 258 |
+
folded = _fold([b.get(key) for b in buckets])
|
| 259 |
+
folded["surface"] = key
|
| 260 |
+
surfaces.append(folded)
|
| 261 |
+
total = sum(s["tokens"] for s in surfaces)
|
| 262 |
+
unmeasured = sum(s["unmeasured"] for s in surfaces)
|
| 263 |
+
out = {
|
| 264 |
+
"week": wk,
|
| 265 |
+
"resets": resets_at(),
|
| 266 |
+
"allowance": WEEKLY_ALLOWANCE,
|
| 267 |
+
"total": total,
|
| 268 |
+
# R9: over the allowance the product STILL WORKS and the bar goes red. This flag is the
|
| 269 |
+
# colour, never a wall β nothing in the API reads it.
|
| 270 |
+
"over": bool(WEEKLY_ALLOWANCE and total > WEEKLY_ALLOWANCE),
|
| 271 |
+
"calls": sum(s["calls"] for s in surfaces),
|
| 272 |
+
"unmeasured": unmeasured,
|
| 273 |
+
"scope": "tenant" if tenant_wide else "me",
|
| 274 |
+
"surfaces": surfaces,
|
| 275 |
+
}
|
| 276 |
+
if unmeasured:
|
| 277 |
+
# R6's second sentence: the number is short by an unknown amount and the payload says so
|
| 278 |
+
# rather than presenting a confident total.
|
| 279 |
+
out["note"] = (f"{unmeasured} call(s) this week did not report a token count, so the total "
|
| 280 |
+
f"above is a floor. The provider decides whether to report usage")
|
| 281 |
+
return out
|
api/web_agent.py
CHANGED
|
@@ -1,9 +1,10 @@
|
|
| 1 |
"""web_agent.py β THE SEAM between an automation step and a browser that runs somewhere else.
|
| 2 |
|
| 3 |
-
CONTRACT C5 (wave 31, ruling R10 / D-51). E
|
| 4 |
-
`automation_engine.py`'s action dispatch
|
| 5 |
-
|
| 6 |
-
|
|
|
|
| 7 |
|
| 8 |
result, error = web_agent.run_step(step, ctx) # -> (dict|None, str)
|
| 9 |
|
|
@@ -30,22 +31,39 @@ foreground step of an automation RUN and far too slow for a route a person is wa
|
|
| 30 |
cost is per JOB, not per step β `run_plan` sends a whole flow's steps in ONE job for that reason.
|
| 31 |
|
| 32 |
ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
|
| 33 |
-
β
|
| 34 |
-
|
| 35 |
-
|
| 36 |
-
|
| 37 |
-
|
| 38 |
-
|
| 39 |
-
|
| 40 |
-
|
| 41 |
-
|
| 42 |
-
|
| 43 |
-
|
| 44 |
-
`
|
| 45 |
-
|
| 46 |
-
|
| 47 |
-
|
| 48 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 49 |
"""
|
| 50 |
import base64
|
| 51 |
import hashlib
|
|
@@ -223,7 +241,7 @@ def _sentence_for(exc, namespace):
|
|
| 223 |
f"point this deployment at one that has it ({ENV_NAMESPACE} / {ENV_TOKEN[0]}). "
|
| 224 |
f"Nothing was read.")
|
| 225 |
if status in (401, 403):
|
| 226 |
-
return (f"Hugging Face refused the browser job as unauthorised for {where}
|
| 227 |
f"deployment's token does not carry `job.write` on that account. Point it at an "
|
| 228 |
f"account the token owns ({ENV_NAMESPACE}), or configure a token that owns this "
|
| 229 |
f"one ({ENV_TOKEN[0]}). Nothing was read.")
|
|
@@ -524,7 +542,7 @@ def _await(api, job_id, namespace, started, log):
|
|
| 524 |
break
|
| 525 |
if state in ("COMPLETED", "ERROR", "CANCELED"):
|
| 526 |
return None, (f"The browser job {job_id} ended {state} without returning a result"
|
| 527 |
-
f"{'
|
| 528 |
f"Nothing was read.")
|
| 529 |
if not booted and waited > START_TIMEOUT:
|
| 530 |
# The submitted-but-never-started case, named as itself.
|
|
@@ -534,7 +552,7 @@ def _await(api, job_id, namespace, started, log):
|
|
| 534 |
pass
|
| 535 |
return None, (f"The browser job {job_id} was accepted but had not started after "
|
| 536 |
f"{int(START_TIMEOUT)}s (it stayed {state or 'queued'}), so it was "
|
| 537 |
-
f"cancelled. Nothing was read
|
| 538 |
if waited > RUN_TIMEOUT:
|
| 539 |
try:
|
| 540 |
api.cancel_job(job_id=job_id, namespace=namespace)
|
|
|
|
| 1 |
"""web_agent.py β THE SEAM between an automation step and a browser that runs somewhere else.
|
| 2 |
|
| 3 |
+
CONTRACT C5 (wave 31, ruling R10 / D-51). E shipped this and C mounted it in
|
| 4 |
+
`automation_engine.py`'s action dispatch; both halves landed and the `verify_wiring` row exists.
|
| 5 |
+
β That sentence was written in the FUTURE TENSE as a wave-31 hand-off and stayed that way for
|
| 6 |
+
three waves, which is the smaller cousin of the correction below: a fence note describes one
|
| 7 |
+
wave's division of labour and reads, afterwards, as a description of the code.
|
| 8 |
|
| 9 |
result, error = web_agent.run_step(step, ctx) # -> (dict|None, str)
|
| 10 |
|
|
|
|
| 31 |
cost is per JOB, not per step β `run_plan` sends a whole flow's steps in ONE job for that reason.
|
| 32 |
|
| 33 |
ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
|
| 34 |
+
ββ WAVE 34 Β· W34-T44 β THIS BLOCK LISTED "THREE THINGS TRUE OF PRODUCTION TODAY". ALL THREE WERE
|
| 35 |
+
FALSE BY THE TIME ANYBODY READ THEM, AND THIS DOCSTRING IS WHERE THE ERROR CAME FROM.
|
| 36 |
+
|
| 37 |
+
It said the Space token 402s, that `deploy_web.py` never uploads `jobs/`, and that
|
| 38 |
+
`routes_web_agent.py` is not mounted β so the whole web-action family was inert in production.
|
| 39 |
+
**Four later documents repeated it** (the wave-34 PRD's scouted index, the plan-time scout's
|
| 40 |
+
report, `W34-T44`'s own `how:`, and `run_gates.ps1`'s annotation telling a deploy to expect
|
| 41 |
+
`web_agent` at 48/50), and every one of them traced back here. Re-checked line by line, against
|
| 42 |
+
the files themselves, on 2026-08-16:
|
| 43 |
+
|
| 44 |
+
1. THE TOKEN IS PUSHED. `deploy_web.py:1128` adds `AIOS_HF_TOKEN` to the Space's secrets when it
|
| 45 |
+
is set, and `ENV_TOKEN` below prefers it over `HF_TOKEN`, so the org token that 402s is never
|
| 46 |
+
the one reached. The 402 itself is still true OF THAT TOKEN and is why the order matters.
|
| 47 |
+
2. THE JOB SCRIPT SHIPS. `deploy_web.py::_jobs_files` (:413) collects `jobs/` and :867 uploads
|
| 48 |
+
it. The `check_upload()` caveat stands as a caveat: it walks IMPORTS and cannot see a file
|
| 49 |
+
opened by PATH, so this upload is covered by the manifest, never by that check.
|
| 50 |
+
3. IT IS MOUNTED. `main.py:264`, `app.include_router(routes_web_agent.router)` β and
|
| 51 |
+
`verify_web_agent.py` asserts the route is in the SERVED set (`app.openapi()["paths"]`),
|
| 52 |
+
which is green.
|
| 53 |
+
|
| 54 |
+
β MEASURED END TO END the same day, from a dev box: `capability()` = ready True / "configured" /
|
| 55 |
+
`AIOS_HF_TOKEN` / playwright 1.62.0, and a real `web_read` of `https://example.com h1` submitted in
|
| 56 |
+
3.8 s, was alive at 21.4 s and returned `value "Example Domain"`, status 200, 106 ms in-browser,
|
| 57 |
+
24.5 s wall clock cold.
|
| 58 |
+
β STILL UNPROVEN, so nobody over-corrects in the other direction: that run was NOT on the deployed
|
| 59 |
+
Space, which carries the secret only if the last deploy read this `.env`. Proving it needs a click
|
| 60 |
+
on staging, and until then "it works" means "it works from a box with the token".
|
| 61 |
+
|
| 62 |
+
β THE STANDING LESSON, kept here because this file is where it started: **a docstring stating
|
| 63 |
+
facts about PRODUCTION has no expiry and nothing re-reads it when the world changes.** Three
|
| 64 |
+
sentences about somebody else's file outlived all three of those files' fixes, and were quoted as
|
| 65 |
+
current by four documents and a ticket. `capability()` answers the same question in under a second
|
| 66 |
+
and returns TODAY's answer; prefer calling it to reading this.
|
| 67 |
"""
|
| 68 |
import base64
|
| 69 |
import hashlib
|
|
|
|
| 241 |
f"point this deployment at one that has it ({ENV_NAMESPACE} / {ENV_TOKEN[0]}). "
|
| 242 |
f"Nothing was read.")
|
| 243 |
if status in (401, 403):
|
| 244 |
+
return (f"Hugging Face refused the browser job as unauthorised for {where}. This "
|
| 245 |
f"deployment's token does not carry `job.write` on that account. Point it at an "
|
| 246 |
f"account the token owns ({ENV_NAMESPACE}), or configure a token that owns this "
|
| 247 |
f"one ({ENV_TOKEN[0]}). Nothing was read.")
|
|
|
|
| 542 |
break
|
| 543 |
if state in ("COMPLETED", "ERROR", "CANCELED"):
|
| 544 |
return None, (f"The browser job {job_id} ended {state} without returning a result"
|
| 545 |
+
f"{'. It never started printing' if not booted else ''}. "
|
| 546 |
f"Nothing was read.")
|
| 547 |
if not booted and waited > START_TIMEOUT:
|
| 548 |
# The submitted-but-never-started case, named as itself.
|
|
|
|
| 552 |
pass
|
| 553 |
return None, (f"The browser job {job_id} was accepted but had not started after "
|
| 554 |
f"{int(START_TIMEOUT)}s (it stayed {state or 'queued'}), so it was "
|
| 555 |
+
f"cancelled. Nothing was read. Try again, or the platform is busy.")
|
| 556 |
if waited > RUN_TIMEOUT:
|
| 557 |
try:
|
| 558 |
api.cancel_job(job_id=job_id, namespace=namespace)
|
jobs/web_agent_job.py
CHANGED
|
@@ -113,6 +113,21 @@ INSTALL_DEPS = os.environ.get("WEB_AGENT_INSTALL_DEPS", "1") != "0"
|
|
| 113 |
INSTALL_BROWSER = os.environ.get("WEB_AGENT_INSTALL_BROWSER", "1") != "0"
|
| 114 |
MAX_VALUE_CHARS = 8000 # one cell's worth; a page is not a payload
|
| 115 |
MAX_STEPS = 20 # matches the engine's MAX_ACTIONS β one flow, one job
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 116 |
|
| 117 |
|
| 118 |
def _fail(sentence: str, *, kind: str = "refused", steps=None) -> None:
|
|
@@ -162,6 +177,8 @@ def _checkpoint(blob: str, payload: dict) -> None:
|
|
| 162 |
repo_id=CHECKPOINT_REPO, repo_type="dataset",
|
| 163 |
commit_message=f"web-agent run {run_id}")
|
| 164 |
say(f"CHECKPOINT wrote runs/{run_id}.json to {CHECKPOINT_REPO}")
|
|
|
|
|
|
|
| 165 |
except Exception as exc: # noqa: BLE001 β a boundary
|
| 166 |
# β CATCH EVERYTHING. This is a report-don't-raise boundary and the ways an upload can
|
| 167 |
# fail are not enumerable (429 commit budget, 403 scope, DNS, a repo that does not
|
|
@@ -171,8 +188,94 @@ def _checkpoint(blob: str, payload: dict) -> None:
|
|
| 171 |
f"the stdout frame still carries the result")
|
| 172 |
|
| 173 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 174 |
def _resume(run_id: str):
|
| 175 |
-
"""A prior run's result, if
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 176 |
if not (CHECKPOINT_REPO and HF_TOKEN and run_id):
|
| 177 |
return None
|
| 178 |
try:
|
|
@@ -181,9 +284,21 @@ def _resume(run_id: str):
|
|
| 181 |
filename=f"runs/{run_id}.json", token=HF_TOKEN,
|
| 182 |
force_download=True)
|
| 183 |
with open(path, encoding="utf-8") as fh:
|
| 184 |
-
|
| 185 |
except Exception: # noqa: BLE001
|
| 186 |
return None # absent is the normal case
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 187 |
|
| 188 |
|
| 189 |
# ββ the plan ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
|
|
|
|
| 113 |
INSTALL_BROWSER = os.environ.get("WEB_AGENT_INSTALL_BROWSER", "1") != "0"
|
| 114 |
MAX_VALUE_CHARS = 8000 # one cell's worth; a page is not a payload
|
| 115 |
MAX_STEPS = 20 # matches the engine's MAX_ACTIONS β one flow, one job
|
| 116 |
+
#: β D-193 β HOW OLD A CHECKPOINT MAY BE AND STILL BE SERVED, in hours. **Deliberately SHORT.**
|
| 117 |
+
#: The key is content-addressed (`runId` + a hash of the steps), so a scheduled automation with a
|
| 118 |
+
#: stable run id hits the same key every time it runs; with no ceiling it would be served the same
|
| 119 |
+
#: stored page for as long as the file existed, which is a measurement of a web page presented with
|
| 120 |
+
#: today's date on it. Six hours makes a same-morning retry cheap and a next-day run honest.
|
| 121 |
+
#: β A CEILING, NOT A CACHE POLICY. The point of the checkpoint is that a RETRY of a job that
|
| 122 |
+
#: already paid for a fetch does not pay again; that window is minutes, not days.
|
| 123 |
+
try:
|
| 124 |
+
CHECKPOINT_MAX_AGE_H = float(os.environ.get("WEB_AGENT_CHECKPOINT_MAX_AGE_H", "6") or 6)
|
| 125 |
+
except (TypeError, ValueError):
|
| 126 |
+
CHECKPOINT_MAX_AGE_H = 6.0
|
| 127 |
+
#: How many expired `runs/*.json` one job may delete, in ONE commit. β Bounded because the repo
|
| 128 |
+
#: already spends a commit per run against HF's 256-commits/hr budget, and a sweep that spent one
|
| 129 |
+
#: commit per FILE would be a denial of service on the store it is tidying.
|
| 130 |
+
CHECKPOINT_SWEEP_MAX = 200
|
| 131 |
|
| 132 |
|
| 133 |
def _fail(sentence: str, *, kind: str = "refused", steps=None) -> None:
|
|
|
|
| 177 |
repo_id=CHECKPOINT_REPO, repo_type="dataset",
|
| 178 |
commit_message=f"web-agent run {run_id}")
|
| 179 |
say(f"CHECKPOINT wrote runs/{run_id}.json to {CHECKPOINT_REPO}")
|
| 180 |
+
# β AFTER the write, never before: the sweep is housekeeping and the result is the job.
|
| 181 |
+
_sweep_expired()
|
| 182 |
except Exception as exc: # noqa: BLE001 β a boundary
|
| 183 |
# β CATCH EVERYTHING. This is a report-don't-raise boundary and the ways an upload can
|
| 184 |
# fail are not enumerable (429 commit budget, 403 scope, DNS, a repo that does not
|
|
|
|
| 188 |
f"the stdout frame still carries the result")
|
| 189 |
|
| 190 |
|
| 191 |
+
def _too_old(payload: dict) -> str:
|
| 192 |
+
""""" if this checkpoint may still be served, else the SENTENCE saying why it may not.
|
| 193 |
+
|
| 194 |
+
β D-193 β A RESUME THAT IS A YEAR OLD IS NOT A RESUME, IT IS A STALE ANSWER SERVED AS FRESH.
|
| 195 |
+
The key is deliberately content-addressed (`runId` + a hash of the steps), so a scheduled
|
| 196 |
+
automation reusing a stable run id resumed the SAME STORED PAGE for as long as the file
|
| 197 |
+
existed. `finishedAt` was written by `_emit` from the first day and read by nothing.
|
| 198 |
+
β AN UNREADABLE OR ABSENT TIMESTAMP IS TREATED AS TOO OLD, not as fresh. A checkpoint written
|
| 199 |
+
before this field existed carries no date, and "no date" must not be the one input that gets
|
| 200 |
+
served forever β fail toward re-fetching, which costs a job, rather than toward a wrong answer,
|
| 201 |
+
which costs a number nobody can explain.
|
| 202 |
+
"""
|
| 203 |
+
stamp = str(payload.get("finishedAt") or "")
|
| 204 |
+
if not stamp:
|
| 205 |
+
return "it carries no finishedAt, so its age cannot be established"
|
| 206 |
+
try:
|
| 207 |
+
when = datetime.fromisoformat(stamp)
|
| 208 |
+
if when.tzinfo is None:
|
| 209 |
+
when = when.replace(tzinfo=timezone.utc)
|
| 210 |
+
except Exception: # noqa: BLE001
|
| 211 |
+
return f"its finishedAt ({stamp[:40]}) is not a date this job can read"
|
| 212 |
+
hours = (datetime.now(timezone.utc) - when).total_seconds() / 3600.0
|
| 213 |
+
if hours > CHECKPOINT_MAX_AGE_H:
|
| 214 |
+
return (f"it finished {hours:.1f} h ago and the ceiling is {CHECKPOINT_MAX_AGE_H} h "
|
| 215 |
+
f"(WEB_AGENT_CHECKPOINT_MAX_AGE_H)")
|
| 216 |
+
return ""
|
| 217 |
+
|
| 218 |
+
|
| 219 |
+
def _sweep_expired() -> None:
|
| 220 |
+
"""Delete checkpoints past the ceiling, ONE COMMIT, at most `CHECKPOINT_SWEEP_MAX` of them.
|
| 221 |
+
|
| 222 |
+
β D-193's SECOND CLAUSE, and it is a different problem from the first. Ageing out the READ
|
| 223 |
+
stops a stale answer being served; it does not stop the repo growing one file per run forever.
|
| 224 |
+
β ONE COMMIT FOR THE WHOLE SWEEP. `upload_file`/`delete_file` each spend a commit, and this
|
| 225 |
+
repo already spends one per run against HF's 256-per-hour budget β a per-file sweep would
|
| 226 |
+
exhaust the budget it exists to protect, and the failure would land on the next run's WRITE.
|
| 227 |
+
`create_commit` with a list of delete operations is one commit whatever the count.
|
| 228 |
+
β AGE IS READ FROM THE LISTING, not by downloading each file. `last_commit` is what the API
|
| 229 |
+
gives cheaply; downloading N files to read a timestamp inside them would make a tidy-up cost
|
| 230 |
+
more than the runs it is tidying.
|
| 231 |
+
β REPORT-DON'T-RAISE, like `_checkpoint`: this runs AFTER the result is in hand, and a
|
| 232 |
+
housekeeping failure must never destroy a result that has already been paid for.
|
| 233 |
+
"""
|
| 234 |
+
if not (CHECKPOINT_REPO and HF_TOKEN):
|
| 235 |
+
return
|
| 236 |
+
try:
|
| 237 |
+
from huggingface_hub import CommitOperationDelete, HfApi
|
| 238 |
+
api = HfApi(token=HF_TOKEN)
|
| 239 |
+
cutoff = datetime.now(timezone.utc).timestamp() - CHECKPOINT_MAX_AGE_H * 3600.0
|
| 240 |
+
doomed = []
|
| 241 |
+
for info in api.list_repo_tree(CHECKPOINT_REPO, repo_type="dataset", path_in_repo="runs",
|
| 242 |
+
expand=True, recursive=False):
|
| 243 |
+
path = getattr(info, "path", "")
|
| 244 |
+
when = getattr(getattr(info, "last_commit", None), "date", None)
|
| 245 |
+
if not path.endswith(".json") or when is None:
|
| 246 |
+
continue
|
| 247 |
+
if when.timestamp() < cutoff:
|
| 248 |
+
doomed.append(path)
|
| 249 |
+
if len(doomed) >= CHECKPOINT_SWEEP_MAX:
|
| 250 |
+
break
|
| 251 |
+
if not doomed:
|
| 252 |
+
return
|
| 253 |
+
api.create_commit(repo_id=CHECKPOINT_REPO, repo_type="dataset",
|
| 254 |
+
operations=[CommitOperationDelete(path_in_repo=p) for p in doomed],
|
| 255 |
+
commit_message=f"sweep {len(doomed)} checkpoints past "
|
| 256 |
+
f"{CHECKPOINT_MAX_AGE_H} h")
|
| 257 |
+
say(f"CHECKPOINT swept {len(doomed)} expired run(s) in one commit")
|
| 258 |
+
except Exception as exc: # noqa: BLE001 β a boundary
|
| 259 |
+
say(f"CHECKPOINT sweep skipped ({type(exc).__name__}: {str(exc)[:160]}) β "
|
| 260 |
+
f"the result is unaffected")
|
| 261 |
+
|
| 262 |
+
|
| 263 |
def _resume(run_id: str):
|
| 264 |
+
"""A prior run's SUCCESSFUL and RECENT result, if one exists. None otherwise.
|
| 265 |
+
|
| 266 |
+
β D-199 β A FAILED RUN'S CHECKPOINT USED TO REPLAY FOREVER. `_fail` checkpoints too
|
| 267 |
+
(`_fail` β `_emit` β `_checkpoint`), so the stored envelope for a failure is exactly as
|
| 268 |
+
truthy as one for a success; the caller tested `if prior:` and nothing ever looked at `ok`.
|
| 269 |
+
Under a stable `runId` a failed fetch could then never be re-attempted β it replayed the
|
| 270 |
+
stored failure unchanged, with `resumedFromCheckpoint: True` on it. The defect was LATENT
|
| 271 |
+
only because no deployment set `WEB_AGENT_REPO`, i.e. it armed itself on the day somebody
|
| 272 |
+
switched checkpointing on, which is the day nobody would be reading this function.
|
| 273 |
+
β THE TEST BELONGS HERE, NOT AT THE CALL SITE. `_resume` is the one place that decides what a
|
| 274 |
+
resumable checkpoint IS; a caller-side `if prior and prior.get("ok")` would be a second
|
| 275 |
+
definition, and the next caller would be written from the first one.
|
| 276 |
+
β A REFUSED CHECKPOINT SAYS SO IN THE LOG. Silently re-running looks identical to never
|
| 277 |
+
having had a checkpoint, and those two need to be distinguishable at 3am.
|
| 278 |
+
"""
|
| 279 |
if not (CHECKPOINT_REPO and HF_TOKEN and run_id):
|
| 280 |
return None
|
| 281 |
try:
|
|
|
|
| 284 |
filename=f"runs/{run_id}.json", token=HF_TOKEN,
|
| 285 |
force_download=True)
|
| 286 |
with open(path, encoding="utf-8") as fh:
|
| 287 |
+
prior = json.load(fh)
|
| 288 |
except Exception: # noqa: BLE001
|
| 289 |
return None # absent is the normal case
|
| 290 |
+
if not isinstance(prior, dict):
|
| 291 |
+
say(f"RESUME refused β runs/{run_id}.json is not an object; re-running")
|
| 292 |
+
return None
|
| 293 |
+
if not prior.get("ok"):
|
| 294 |
+
say(f"RESUME refused β the stored run FAILED "
|
| 295 |
+
f"({str(prior.get('error') or 'no reason recorded')[:120]}); re-running")
|
| 296 |
+
return None
|
| 297 |
+
stale = _too_old(prior)
|
| 298 |
+
if stale:
|
| 299 |
+
say(f"RESUME refused β {stale}; re-running")
|
| 300 |
+
return None
|
| 301 |
+
return prior
|
| 302 |
|
| 303 |
|
| 304 |
# ββ the plan ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
|
platform/aios_grid.py
CHANGED
|
@@ -120,9 +120,20 @@ def _round(v):
|
|
| 120 |
#: surfaces that CREATE them are the user-table databases, where a relation between two tables is
|
| 121 |
#: a thing that exists. On the Odoo-backed Customer/Product grids there is no second user table to
|
| 122 |
#: point at, so the column menu there simply never offers one.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 123 |
CUSTOM_FIELD_TYPES = {"text", "select", "multiselect", "user", "int", "currency", "pct", "date",
|
| 124 |
"checkbox", "phone", "email", "url", "rating", "created_time", "formula",
|
| 125 |
-
"automation", "image", "json", "link", "rollup", "code"}
|
| 126 |
|
| 127 |
#: β WAVE-27 item 13 (owner ruling R13) β the `code` field's LANGUAGES.
|
| 128 |
#:
|
|
@@ -1344,6 +1355,13 @@ def _clean_display(raw, valid_keys):
|
|
| 1344 |
dashboard `charts` (I19). A chart whose x/y names a deleted field is dropped INDIVIDUALLY β
|
| 1345 |
never the whole array, because losing one column should not cost the user a dashboard they
|
| 1346 |
spent time building.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1347 |
"""
|
| 1348 |
if not isinstance(raw, dict):
|
| 1349 |
return None
|
|
@@ -1522,6 +1540,28 @@ def _clean_display(raw, valid_keys):
|
|
| 1522 |
form = _clean_form(raw.get('form'), valid_keys)
|
| 1523 |
if form:
|
| 1524 |
out['form'] = form
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1525 |
return out
|
| 1526 |
|
| 1527 |
|
|
|
|
| 120 |
#: surfaces that CREATE them are the user-table databases, where a relation between two tables is
|
| 121 |
#: a thing that exists. On the Odoo-backed Customer/Product grids there is no second user table to
|
| 122 |
#: point at, so the column menu there simply never offers one.
|
| 123 |
+
#: ββ WAVE-34 (owner ruling R13) β `ai_enrich` JOINS, and it had to join HERE in the same change
|
| 124 |
+
#: that put it in `UT_FIELD_TYPES`, not a ticket later. The wave planned a SERVER-FIRST landing on
|
| 125 |
+
#: the reasoning that a kind the client does not offer is invisible while a kind the server refuses
|
| 126 |
+
#: deletes a column. That reasoning is sound and the conclusion was still wrong, because THREE
|
| 127 |
+
#: parity gates chain over these sets and none of them permits a partial landing:
|
| 128 |
+
#: `verify_api` W18-UT `UT_FIELD_TYPES - CUSTOM_FIELD_TYPES == set()` (this line)
|
| 129 |
+
#: `aw_fields_contract` Β§5 `CREATABLE_TYPES == CUSTOM_FIELD_TYPES`, EXACT set equality
|
| 130 |
+
#: `types.ts` `CREATABLE_TYPES: readonly FieldType[]`, so the union must carry it too
|
| 131 |
+
#: Measured live by lane B at 17:09: `api_api` went 969/969 to 968/969 the moment the kind entered
|
| 132 |
+
#: `core/user_tables.py` alone, printing `got {'ai_enrich'} want set()`. The comments on
|
| 133 |
+
#: `json`, `link`/`rollup` and `code` below all say the same thing in their own words.
|
| 134 |
CUSTOM_FIELD_TYPES = {"text", "select", "multiselect", "user", "int", "currency", "pct", "date",
|
| 135 |
"checkbox", "phone", "email", "url", "rating", "created_time", "formula",
|
| 136 |
+
"automation", "image", "json", "link", "rollup", "code", "ai_enrich"}
|
| 137 |
|
| 138 |
#: β WAVE-27 item 13 (owner ruling R13) β the `code` field's LANGUAGES.
|
| 139 |
#:
|
|
|
|
| 1355 |
dashboard `charts` (I19). A chart whose x/y names a deleted field is dropped INDIVIDUALLY β
|
| 1356 |
never the whole array, because losing one column should not cost the user a dashboard they
|
| 1357 |
spent time building.
|
| 1358 |
+
|
| 1359 |
+
W33-T45 (contract C1, ruling R5) adds `published` + `publishAccess`. β THE HALF OF THE ROUND
|
| 1360 |
+
TRIP THIS FUNCTION CANNOT ENFORCE: `customer-grid/types.ts::cleanDisplay` is a SECOND
|
| 1361 |
+
normalizer, in the browser, which rebuilds the config key by key on every autosave and drops
|
| 1362 |
+
anything it does not name. A key accepted here and unknown there dies on the next column
|
| 1363 |
+
resize β silently, because the client then POSTs the stripped config and the host REPLACES
|
| 1364 |
+
the stored one. "The host accepts it" is half a round trip; that file is the other half.
|
| 1365 |
"""
|
| 1366 |
if not isinstance(raw, dict):
|
| 1367 |
return None
|
|
|
|
| 1540 |
form = _clean_form(raw.get('form'), valid_keys)
|
| 1541 |
if form:
|
| 1542 |
out['form'] = form
|
| 1543 |
+
# ββ ββ W33-T45 / CONTRACT C1 / RULING R5 (owner item 8b): IS THIS INTERFACE PUBLISHED ββββ
|
| 1544 |
+
#
|
| 1545 |
+
# β TWO KEYS LIVE HERE AND TWO DELIBERATELY DO NOT. The `published` flag and the sharer's
|
| 1546 |
+
# `public | password` choice are DISPLAY state β the view says what it is, the client renders
|
| 1547 |
+
# a badge from it, and it travels with the view like every other key in this dict. The SECRET
|
| 1548 |
+
# TOKEN and the PASSPHRASE HASH do not: they live in the server-only bucket, exactly as
|
| 1549 |
+
# `routes_forms.py`'s `TOKENS_KEY` holds the form token. `config.display` is echoed back to
|
| 1550 |
+
# every user who can open the view, so a token in here is a token published to the audience
|
| 1551 |
+
# the password was meant to exclude. `_clean_form` above carries the same rule and the same
|
| 1552 |
+
# reason; this is the second door, not a new one.
|
| 1553 |
+
#
|
| 1554 |
+
# β AND THE COERCION IS FAIL-CLOSED, WHICH IS WHY THIS IS NOT A BARE ALLOWLIST. A plain
|
| 1555 |
+
# allowlist drops an unrecognised `publishAccess` and KEEPS `published: True` β leaving a
|
| 1556 |
+
# published view with no stated access, i.e. a third state neither the ruling nor the client
|
| 1557 |
+
# has a meaning for, on the one key where guessing wrong publishes a tenant's data to the
|
| 1558 |
+
# open internet. So: a published view ALWAYS carries an access, and anything that is not the
|
| 1559 |
+
# literal `'public'` reads as `'password'`. The unpublished case stores nothing at all β
|
| 1560 |
+
# absent means unpublished, and a `published: False` would be the second way to say nothing
|
| 1561 |
+
# that `kanbanClamp` and `mode: 'grid'` are both here to forbid.
|
| 1562 |
+
if raw.get('published') is True:
|
| 1563 |
+
out['published'] = True
|
| 1564 |
+
out['publishAccess'] = 'public' if raw.get('publishAccess') == 'public' else 'password'
|
| 1565 |
return out
|
| 1566 |
|
| 1567 |
|
platform/aios_grid_fields.json
CHANGED
|
@@ -10,12 +10,25 @@
|
|
| 10 |
"default": true,
|
| 11 |
"description": "The customer's name in Odoo. One row per customer who ordered in the last 24 months."
|
| 12 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13 |
{
|
| 14 |
"key": "odoo_status",
|
| 15 |
"label": "Odoo record",
|
| 16 |
"type": "status",
|
| 17 |
"source": "odoo",
|
| 18 |
"default": false,
|
|
|
|
|
|
|
|
|
|
|
|
|
| 19 |
"description": "Whether this customer still exists in Odoo. Archived means deleted there."
|
| 20 |
},
|
| 21 |
{
|
|
@@ -458,6 +471,63 @@
|
|
| 458 |
"type": "select",
|
| 459 |
"source": "odoo",
|
| 460 |
"description": "Dead / excess / healthy bucket from the inventory module. Consolidated; absent for a BU-scoped caller."
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 461 |
}
|
| 462 |
]
|
| 463 |
}
|
|
|
|
| 10 |
"default": true,
|
| 11 |
"description": "The customer's name in Odoo. One row per customer who ordered in the last 24 months."
|
| 12 |
},
|
| 13 |
+
{
|
| 14 |
+
"key": "partner_id",
|
| 15 |
+
"label": "Odoo ID",
|
| 16 |
+
"type": "int",
|
| 17 |
+
"source": "odoo",
|
| 18 |
+
"derived": true,
|
| 19 |
+
"default": false,
|
| 20 |
+
"description": "The Odoo res.partner id β the key every Odoo document joins on. DERIVED: this row's pid IS the partner id, so a stored copy would be a second source."
|
| 21 |
+
},
|
| 22 |
{
|
| 23 |
"key": "odoo_status",
|
| 24 |
"label": "Odoo record",
|
| 25 |
"type": "status",
|
| 26 |
"source": "odoo",
|
| 27 |
"default": false,
|
| 28 |
+
"options": [
|
| 29 |
+
"Active",
|
| 30 |
+
"Archived"
|
| 31 |
+
],
|
| 32 |
"description": "Whether this customer still exists in Odoo. Archived means deleted there."
|
| 33 |
},
|
| 34 |
{
|
|
|
|
| 471 |
"type": "select",
|
| 472 |
"source": "odoo",
|
| 473 |
"description": "Dead / excess / healthy bucket from the inventory module. Consolidated; absent for a BU-scoped caller."
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"key": "needs_pricing",
|
| 477 |
+
"label": "Needs pricing",
|
| 478 |
+
"type": "select",
|
| 479 |
+
"source": "overlay",
|
| 480 |
+
"default": false,
|
| 481 |
+
"options": [
|
| 482 |
+
"Yes"
|
| 483 |
+
],
|
| 484 |
+
"shared": true,
|
| 485 |
+
"description": "Team-maintained. A SKU carries βYesβ when it appears on the NEEDS PRICING tab of the 2027 catalog workbook; no value means it is not on that list. Shared with everyone in the workspace β the whole point of R8 is that the TEAM's work lands in the system, not one importer's private column."
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"key": "march_pricelist",
|
| 489 |
+
"label": "March pricelist",
|
| 490 |
+
"type": "select",
|
| 491 |
+
"source": "overlay",
|
| 492 |
+
"default": false,
|
| 493 |
+
"options": [
|
| 494 |
+
"Yes"
|
| 495 |
+
],
|
| 496 |
+
"shared": true,
|
| 497 |
+
"description": "Team-maintained. A SKU carries βYesβ when it appears on the March Pricelist tab of the 2027 catalog workbook; no value means it is not on that list. Shared with everyone in the workspace β the whole point of R8 is that the TEAM's work lands in the system, not one importer's private column."
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"key": "price_changes",
|
| 501 |
+
"label": "Price changes",
|
| 502 |
+
"type": "select",
|
| 503 |
+
"source": "overlay",
|
| 504 |
+
"default": false,
|
| 505 |
+
"options": [
|
| 506 |
+
"Yes"
|
| 507 |
+
],
|
| 508 |
+
"shared": true,
|
| 509 |
+
"description": "Team-maintained. A SKU carries βYesβ when it appears on the Price Changes tab of the 2027 catalog workbook; no value means it is not on that list. Shared with everyone in the workspace β the whole point of R8 is that the TEAM's work lands in the system, not one importer's private column."
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"key": "closeouts",
|
| 513 |
+
"label": "Closeouts",
|
| 514 |
+
"type": "select",
|
| 515 |
+
"source": "overlay",
|
| 516 |
+
"default": false,
|
| 517 |
+
"options": [
|
| 518 |
+
"Yes"
|
| 519 |
+
],
|
| 520 |
+
"shared": true,
|
| 521 |
+
"description": "Team-maintained. A SKU carries βYesβ when it appears on the Closeouts tab of the 2027 catalog workbook; no value means it is not on that list. Shared with everyone in the workspace β the whole point of R8 is that the TEAM's work lands in the system, not one importer's private column."
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"key": "notes",
|
| 525 |
+
"label": "Notes",
|
| 526 |
+
"type": "text",
|
| 527 |
+
"source": "overlay",
|
| 528 |
+
"default": false,
|
| 529 |
+
"shared": true,
|
| 530 |
+
"description": "Team-maintained. The 2027 workbook's own non-Odoo columns (Product Description, Packing) folded into one field. Shared with everyone in the workspace."
|
| 531 |
}
|
| 532 |
]
|
| 533 |
}
|
platform/core/alerts.py
CHANGED
|
@@ -209,7 +209,7 @@ def _queue(rec, pids, labels, st=None):
|
|
| 209 |
_st(st).update(NOTIFICATIONS_KEY, _apply, flush='async')
|
| 210 |
|
| 211 |
|
| 212 |
-
def notify(owner, label, *, topic='automation', key='', row_id='', detail='', st=None):
|
| 213 |
"""β WAVE 23 (C6) β put ONE notification in a named user's inbox, for a producer that is not
|
| 214 |
a view-alert evaluation.
|
| 215 |
|
|
@@ -222,6 +222,24 @@ def notify(owner, label, *, topic='automation', key='', row_id='', detail='', st
|
|
| 222 |
The inbox shape is UNCHANGED, deliberately: `AlertsPane` reads one list, and a second row
|
| 223 |
shape would mean a client that must branch on where a notification came from. `alertId`
|
| 224 |
carries the producer's key so a click-through can route (W23-W5).
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 225 |
"""
|
| 226 |
owner = str(owner or '').strip()
|
| 227 |
if not owner or not label:
|
|
@@ -230,7 +248,8 @@ def notify(owner, label, *, topic='automation', key='', row_id='', detail='', st
|
|
| 230 |
item = {'id': f"{key or topic}:{row_id or 'n'}:{at}",
|
| 231 |
'alertId': str(key or ''), 'viewId': '', 'topic': str(topic),
|
| 232 |
'rowId': str(row_id or ''), 'label': str(detail or label),
|
| 233 |
-
'alertLabel': str(label), 'at': at, 'read': False
|
|
|
|
| 234 |
|
| 235 |
def _apply(data):
|
| 236 |
box = list(data.get(owner) or [])
|
|
|
|
| 209 |
_st(st).update(NOTIFICATIONS_KEY, _apply, flush='async')
|
| 210 |
|
| 211 |
|
| 212 |
+
def notify(owner, label, *, topic='automation', key='', row_id='', detail='', actor='', st=None):
|
| 213 |
"""β WAVE 23 (C6) β put ONE notification in a named user's inbox, for a producer that is not
|
| 214 |
a view-alert evaluation.
|
| 215 |
|
|
|
|
| 222 |
The inbox shape is UNCHANGED, deliberately: `AlertsPane` reads one list, and a second row
|
| 223 |
shape would mean a client that must branch on where a notification came from. `alertId`
|
| 224 |
carries the producer's key so a click-through can route (W23-W5).
|
| 225 |
+
|
| 226 |
+
ββ W33-T28 (`ASK C-14`) β `actor` IS THE ONLY THING THAT KNOWS WHO. Owner item: *"the Inbox
|
| 227 |
+
reads like email"*, and a verifier reading the carried wave-32 surface found the SENDER position
|
| 228 |
+
occupied by `kindLabel(n.kind)` β the literals "Alert" / "Automation" / "Shared with you", i.e. a
|
| 229 |
+
CATEGORY where mail puts a who β with no sender field anywhere on the wire, in the model or in
|
| 230 |
+
the markup. An alert and an automation have no person behind them and are honestly named by
|
| 231 |
+
their machine; **a SHARE has a real person, and only the PRODUCER knows their name.** By the time
|
| 232 |
+
the read path sees the row that fact is gone, so it has to be carried at write time.
|
| 233 |
+
|
| 234 |
+
β ADDITIVE, AND THAT IS THE WHOLE DESIGN. No existing caller changes, no stored row changes
|
| 235 |
+
shape, and every reader already tolerates the key's absence β so an inbox written before this
|
| 236 |
+
line reads exactly as it did. The alternative C rejected is worth recording because it is the
|
| 237 |
+
tempting one: recovering the name by REGEXING the body prose (`"<name> shared this with you"`).
|
| 238 |
+
A sender parsed out of a sentence breaks the first time the sentence is reworded, and it breaks
|
| 239 |
+
SILENTLY, in the header β [[one-question-two-normalizers]] with the second normaliser being
|
| 240 |
+
English.
|
| 241 |
+
β Blank is a legitimate value and means *"no person did this"*, NOT "unknown". The client falls
|
| 242 |
+
back BY KIND rather than to an empty From column, so an automation never borrows a human's name.
|
| 243 |
"""
|
| 244 |
owner = str(owner or '').strip()
|
| 245 |
if not owner or not label:
|
|
|
|
| 248 |
item = {'id': f"{key or topic}:{row_id or 'n'}:{at}",
|
| 249 |
'alertId': str(key or ''), 'viewId': '', 'topic': str(topic),
|
| 250 |
'rowId': str(row_id or ''), 'label': str(detail or label),
|
| 251 |
+
'alertLabel': str(label), 'at': at, 'read': False,
|
| 252 |
+
'actor': str(actor or '')}
|
| 253 |
|
| 254 |
def _apply(data):
|
| 255 |
box = list(data.get(owner) or [])
|
platform/core/data_binding.py
ADDED
|
@@ -0,0 +1,270 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"""WHICH STORE THIS DEPLOYMENT IS ALLOWED TO WRITE β the fail-closed binding (D-315 / D-298).
|
| 2 |
+
|
| 3 |
+
ββ THE SENTENCE THIS FILE EXISTS TO MAKE IMPOSSIBLE. Owner, 2026-08-18, verbatim: *"this is so
|
| 4 |
+
critical that whenever we do staging, we don't fuck up anyone's data. EVER."* It had already
|
| 5 |
+
happened once: `fsanyoto/loopable` became STAGING on 2026-08-14 having never been given a store of
|
| 6 |
+
its own, so two different builds wrote tenant #0's real business data. Compose that with D-305
|
| 7 |
+
(the store is last-write-wins at whole-document granularity) and a routine staging deploy does not
|
| 8 |
+
merely add test rows β it can erase a real user's views, fields and typed cell values.
|
| 9 |
+
|
| 10 |
+
β A DEPLOY FLAG IS NOT THE FIX; THE FLAG IS THE THING THAT ALREADY FAILED. The isolation that
|
| 11 |
+
existed was bound to a ROLE ("the staging Space"), and a guard bound to a role stops guarding the
|
| 12 |
+
moment the role moves β which these two Spaces have done twice. So the binding here is on the
|
| 13 |
+
container's OWN IDENTITY, which no deploy can forget to pass and no role swap can invalidate.
|
| 14 |
+
|
| 15 |
+
ββ THE RULE, AND IT CLASSIFIES THE DEPLOYMENT RATHER THAN THE REPO:
|
| 16 |
+
|
| 17 |
+
1. the PRODUCTION deployment (identity in `PRODUCTION_SPACES`) -> may write anything
|
| 18 |
+
2. any other deployment writing a KNOWN production store -> REFUSED
|
| 19 |
+
3. any other deployment writing a repo on its OWN allowlist -> allowed
|
| 20 |
+
4. anything else -> REFUSED
|
| 21 |
+
|
| 22 |
+
β WHY NOT CLASSIFY THE REPO, which is the design everybody reaches for first. A DENYLIST of
|
| 23 |
+
production stores fails OPEN for the next tenant nobody remembered to add. A SUFFIX RULE
|
| 24 |
+
(`*-staging-data`) pins a SPELLING rather than a claim β see [[gate-pins-a-spelling-not-a-claim]] β
|
| 25 |
+
and a store named without the suffix is unprotected while reading as protected. Rule 4 is the one
|
| 26 |
+
that survives a tenant nobody has provisioned yet: an unknown repo is refused, so a store this
|
| 27 |
+
deployment was never handed cannot be written by accident.
|
| 28 |
+
|
| 29 |
+
ββ AND RULE 4 IS NOT THEORETICAL β IT IS THE HALF OF D-315 THE REGISTER ROW DID NOT KNOW ABOUT.
|
| 30 |
+
Measured 2026-08-18 by reading both control planes: `royal-imports/cfo-os-staging-data`'s own
|
| 31 |
+
`tenants.json` is byte-identical to live's and names **`royal-imports/aios-nurilab-data`,
|
| 32 |
+
`aios-gtmlab-data` and `aios-loopable-data`** β the three other tenants' REAL stores. So
|
| 33 |
+
`--data-repo=` only ever isolated tenant #0; `harness/runtime.py`'s `store.for_repo(repo)` path
|
| 34 |
+
resolved three PRODUCTION repos out of the staging store and wrote them, and no flag has ever
|
| 35 |
+
touched that path. The exposure is FOUR production stores, not one.
|
| 36 |
+
|
| 37 |
+
β READS ARE NOT REFUSED, AND THAT IS A DELIBERATE, STATED SCOPE DECISION. `Store.get` is lenient
|
| 38 |
+
by contract: a refused read would hand back `{}`, a caller would paint an empty grid, and the whole
|
| 39 |
+
Space would read as "no data" rather than as "refused" β the exact
|
| 40 |
+
[[empty-answer-vs-unfinished-answer]] shape this codebase has shipped before. A refused WRITE is
|
| 41 |
+
loud (503, with the reason). So staging still SEES production data when pointed at it; it can no
|
| 42 |
+
longer CHANGE it. Narrowing the read is a separate decision and is booked, not smuggled in here.
|
| 43 |
+
|
| 44 |
+
β ABSENT IDENTITY FAILS CLOSED, AND THE FAILURE LOOKS LIKE AN OUTAGE. If a container exposes none
|
| 45 |
+
of the identity variables, it is treated as "not the production deployment" and every write to a
|
| 46 |
+
production store refuses. That is the safe direction, but on a live Space it would read as a total
|
| 47 |
+
product outage β which is why `describe()` reports the RAW observations and not just the verdict:
|
| 48 |
+
per D-160 the Space environment cannot be read from outside, so the container has to say what it
|
| 49 |
+
saw. One deploy then answers "does SPACE_ID exist here", instead of three.
|
| 50 |
+
"""
|
| 51 |
+
import os
|
| 52 |
+
|
| 53 |
+
#: The deployment that OWNS production data. A frozenset rather than a string because the product
|
| 54 |
+
#: has had two public addresses before and will again.
|
| 55 |
+
#:
|
| 56 |
+
#: β THIS SET IS DUPLICATED IN `aios-web/deploy_web.py` AS `PUBLIC_LIVE`, on purpose and with a
|
| 57 |
+
#: gate: `deploy_web` is a standalone CLI that must run without the platform package importable, so
|
| 58 |
+
#: it cannot import this. `verify_store_binding.py::section_constants` asserts the two literals
|
| 59 |
+
#: agree β a constant two features share is a constant that drifts ([[constant-two-features-share]]).
|
| 60 |
+
PRODUCTION_SPACES = frozenset({'fsanyoto/runloopable'})
|
| 61 |
+
|
| 62 |
+
#: The stores that hold REAL customer business data. Enumerated 2026-08-18 from the live control
|
| 63 |
+
#: plane (`royal-imports/cfo-os-data::tenants.json`), not guessed.
|
| 64 |
+
#:
|
| 65 |
+
#: β THIS LIST IS RULE 2, NOT THE WHOLE GUARD. It exists to make a DELIBERATE mis-pointing loud β
|
| 66 |
+
#: `OS_DATA_REPO=royal-imports/cfo-os-data` typed on a laptop, or a production repo added to a
|
| 67 |
+
#: sandbox allowlist by hand. Rule 4 is what covers a tenant provisioned after this line was
|
| 68 |
+
#: written, which is why the file does not depend on this staying complete.
|
| 69 |
+
PRODUCTION_STORES = frozenset({
|
| 70 |
+
'royal-imports/cfo-os-data', # tenant #0 β Royal Imports
|
| 71 |
+
'royal-imports/aios-nurilab-data', # Nurilab
|
| 72 |
+
'royal-imports/aios-gtmlab-data', # GTM Lab
|
| 73 |
+
'royal-imports/aios-loopable-data', # Loopable
|
| 74 |
+
})
|
| 75 |
+
|
| 76 |
+
#: The historical default of `OS_DATA_REPO`. Kept as a name so the resolution below can say what it
|
| 77 |
+
#: is refusing to assume, rather than repeating a literal.
|
| 78 |
+
PRODUCTION_DEFAULT_STORE = 'royal-imports/cfo-os-data'
|
| 79 |
+
|
| 80 |
+
#: The env vars a Hugging Face Space container sets to describe itself, in the order they are
|
| 81 |
+
#: trusted. `SPACE_ID` is the canonical one; the pair is the documented fallback. Read as a LIST so
|
| 82 |
+
#: `describe()` can report every one of them and what it held.
|
| 83 |
+
_IDENTITY_VARS = ('SPACE_ID', 'SPACE_AUTHOR_NAME', 'SPACE_REPO_NAME', 'SPACE_HOST')
|
| 84 |
+
|
| 85 |
+
#: The env a NON-production deployment uses to name the stores it may write, beyond `OS_DATA_REPO`.
|
| 86 |
+
#: Comma-separated.
|
| 87 |
+
#:
|
| 88 |
+
#: β THE POLARITY IS THE POINT, and it is what keeps trap 1 satisfied. Forgetting to set this
|
| 89 |
+
#: makes a deployment write LESS, never more β so an omitted deploy argument is a refusal, not a
|
| 90 |
+
#: silent grant. That is the exact inverse of `--data-repo`, whose omission printed
|
| 91 |
+
#: "OS_DATA_REPO unchanged" and left a Space on production.
|
| 92 |
+
_SANDBOX_STORES_VAR = 'AIOS_SANDBOX_STORES'
|
| 93 |
+
|
| 94 |
+
#: The local (no-identity) escape hatch. Present β writes to production stores are permitted from a
|
| 95 |
+
#: machine with no Space identity, AND every commit this process makes is stamped distinguishably
|
| 96 |
+
#: (see `local_commit_suffix`). Deliberately does NOT widen a Space: a container that HAS an
|
| 97 |
+
#: identity and is not production is refused with no override, because that is the case the owner
|
| 98 |
+
#: said "EVER" about.
|
| 99 |
+
_LOCAL_OPT_IN_VAR = 'AIOS_ALLOW_PRODUCTION_DATA'
|
| 100 |
+
|
| 101 |
+
|
| 102 |
+
class StoreWriteRefused(RuntimeError):
|
| 103 |
+
"""A write this deployment is not allowed to make.
|
| 104 |
+
|
| 105 |
+
β DELIBERATELY NOT A SUBCLASS OF `grid_events.StoreUnavailable`, and the reason is the routes.
|
| 106 |
+
Several of them carry `except StoreUnavailable:` blocks that DEGRADE to a session-scoped
|
| 107 |
+
fallback workspace β correct for an outage, catastrophic for a refusal, because the user would
|
| 108 |
+
be told the change was saved somewhere. A distinct type falls through all of them to the
|
| 109 |
+
app-level handler, which answers 503 with the reason and never claims a save.
|
| 110 |
+
"""
|
| 111 |
+
|
| 112 |
+
|
| 113 |
+
def _env(name):
|
| 114 |
+
return str(os.environ.get(name) or '').strip()
|
| 115 |
+
|
| 116 |
+
|
| 117 |
+
def deployment_id():
|
| 118 |
+
"""This container's own identity, or `''` when it is not a Space (i.e. local dev).
|
| 119 |
+
|
| 120 |
+
β NOT DERIVED FROM ANY DEPLOY ARGUMENT. That is the whole design: `SPACE_ID` is set by the
|
| 121 |
+
platform inside the container, so it cannot be forgotten, mistyped, or left behind by a Space
|
| 122 |
+
that changed role without being redeployed.
|
| 123 |
+
"""
|
| 124 |
+
sid = _env('SPACE_ID')
|
| 125 |
+
if sid:
|
| 126 |
+
return sid
|
| 127 |
+
author, repo = _env('SPACE_AUTHOR_NAME'), _env('SPACE_REPO_NAME')
|
| 128 |
+
if author and repo:
|
| 129 |
+
return f'{author}/{repo}'
|
| 130 |
+
return ''
|
| 131 |
+
|
| 132 |
+
|
| 133 |
+
def is_production_deployment():
|
| 134 |
+
"""True only on the deployment that owns production data. Unknown β False (fail closed)."""
|
| 135 |
+
return deployment_id() in PRODUCTION_SPACES
|
| 136 |
+
|
| 137 |
+
|
| 138 |
+
def is_space():
|
| 139 |
+
"""True when this process is running inside a Space at all.
|
| 140 |
+
|
| 141 |
+
The distinction matters exactly once: a Space that is not production gets NO override, while a
|
| 142 |
+
laptop does. `deployment_id()` conflates them into `''`, so ask separately.
|
| 143 |
+
"""
|
| 144 |
+
return bool(deployment_id())
|
| 145 |
+
|
| 146 |
+
|
| 147 |
+
def sandbox_allowlist():
|
| 148 |
+
"""The repos a non-production deployment may write: `OS_DATA_REPO` + `AIOS_SANDBOX_STORES`."""
|
| 149 |
+
allowed = {r.strip() for r in _env(_SANDBOX_STORES_VAR).split(',') if r.strip()}
|
| 150 |
+
own = _env('OS_DATA_REPO')
|
| 151 |
+
if own:
|
| 152 |
+
allowed.add(own)
|
| 153 |
+
return frozenset(allowed)
|
| 154 |
+
|
| 155 |
+
|
| 156 |
+
def local_override():
|
| 157 |
+
"""True when a machine with no Space identity has explicitly opted in to production data."""
|
| 158 |
+
return (not is_space()) and _env(_LOCAL_OPT_IN_VAR) == '1'
|
| 159 |
+
|
| 160 |
+
|
| 161 |
+
def default_store():
|
| 162 |
+
"""What `OS_DATA_REPO` resolves to when it is unset.
|
| 163 |
+
|
| 164 |
+
ββ FACT (1) OF D-315 DIES HERE: `core/store.py` used to read
|
| 165 |
+
`os.environ.get('OS_DATA_REPO', 'royal-imports/cfo-os-data')`, so a Space that was never given
|
| 166 |
+
the key β every NEW Space, by construction β came up bound to tenant #0's real business data.
|
| 167 |
+
The default now exists ONLY on the deployment that owns it.
|
| 168 |
+
|
| 169 |
+
β IT STILL RETURNS THE PRODUCTION ID ELSEWHERE, RATHER THAN `None` OR `''`, AND THAT IS
|
| 170 |
+
DELIBERATE. A `None` repo would make `Store.__init__` β which runs at IMPORT time via
|
| 171 |
+
`_DEFAULT = for_repo(REPO)` β raise or bind something nonsensical, killing the app and every
|
| 172 |
+
gate on any non-production machine. Returning the real id keeps binding total and lets
|
| 173 |
+
`write_refusal` refuse the WRITE with a message that names the actual problem. Reads still
|
| 174 |
+
work, so a developer sees a populated app that will not let them damage it.
|
| 175 |
+
"""
|
| 176 |
+
return PRODUCTION_DEFAULT_STORE
|
| 177 |
+
|
| 178 |
+
|
| 179 |
+
def write_refusal(repo):
|
| 180 |
+
"""`None` if this deployment may write `repo`, else the sentence explaining why not.
|
| 181 |
+
|
| 182 |
+
β RETURNS A REASON RATHER THAN A BOOL, because [[report-the-cause-before-you-fix-it]]: a
|
| 183 |
+
silent refusal makes every theory about it unfalsifiable, and this one fires on a path where
|
| 184 |
+
the operator cannot read the container's environment (D-160).
|
| 185 |
+
"""
|
| 186 |
+
rid = str(repo or '').strip()
|
| 187 |
+
if not rid:
|
| 188 |
+
return ('no store repo is bound. Refusing to guess: an unnamed store is how a deployment '
|
| 189 |
+
'ends up on somebody else\'s data.')
|
| 190 |
+
if is_production_deployment():
|
| 191 |
+
return None # rule 1 β the live Space owns its data
|
| 192 |
+
if rid in PRODUCTION_STORES: # rule 2 β never, from anywhere else
|
| 193 |
+
if local_override():
|
| 194 |
+
return None
|
| 195 |
+
who = deployment_id() or 'this machine (no Space identity)'
|
| 196 |
+
if is_space():
|
| 197 |
+
return (f'{who} is not the production deployment, so it may not write {rid}, which '
|
| 198 |
+
f'holds real customer data. Point this Space at its own store with '
|
| 199 |
+
f'--data-repo=, or add it to {_SANDBOX_STORES_VAR}. There is no override for '
|
| 200 |
+
f'a Space: a build that is not live never writes live data.')
|
| 201 |
+
return (f'{who} may not write {rid}, which holds real customer data. Set OS_DATA_REPO to a '
|
| 202 |
+
f'sandbox store, or set {_LOCAL_OPT_IN_VAR}=1 to opt in deliberately (every commit '
|
| 203 |
+
f'is then stamped as a local write so it can be told apart afterwards).')
|
| 204 |
+
allow = sandbox_allowlist() # rule 3 β what it was explicitly handed
|
| 205 |
+
if rid in allow:
|
| 206 |
+
return None
|
| 207 |
+
who = deployment_id() or 'this machine (no Space identity)'
|
| 208 |
+
listed = ', '.join(sorted(allow)) or '(nothing)'
|
| 209 |
+
return (f'{who} was not given {rid}. A non-production deployment may write only the stores it '
|
| 210 |
+
f'was handed: {listed}. Add it to {_SANDBOX_STORES_VAR} if that is intended.')
|
| 211 |
+
|
| 212 |
+
|
| 213 |
+
def check_write(repo, operation='write'):
|
| 214 |
+
"""Raise `StoreWriteRefused` unless this deployment may write `repo`. The one enforcement door."""
|
| 215 |
+
reason = write_refusal(repo)
|
| 216 |
+
if reason:
|
| 217 |
+
raise StoreWriteRefused(f'{operation} to {repo!r} refused: {reason}')
|
| 218 |
+
|
| 219 |
+
|
| 220 |
+
def local_commit_suffix():
|
| 221 |
+
"""A marker appended to commit messages made under the local override, else `''`.
|
| 222 |
+
|
| 223 |
+
β THIS IS THE SECOND HALF OF D-298's EXIT CONDITION, satisfied rather than argued around: *"a
|
| 224 |
+
local run either cannot reach the live store without an explicit opt-in, OR stamps its commits
|
| 225 |
+
distinguishably"*. The measured complaint was that a laptop's commits were titled
|
| 226 |
+
`update user_tables` β byte-identical to what the live Space writes every few minutes β so a
|
| 227 |
+
local run and production were indistinguishable in the store's git history, which is the ONLY
|
| 228 |
+
audit trail this product has. Both clauses now hold: the opt-in is required AND it stamps.
|
| 229 |
+
"""
|
| 230 |
+
if not local_override():
|
| 231 |
+
return ''
|
| 232 |
+
import getpass # noqa: PLC0415 β only on the opt-in path
|
| 233 |
+
import socket # noqa: PLC0415
|
| 234 |
+
try:
|
| 235 |
+
who = getpass.getuser()
|
| 236 |
+
except Exception: # noqa: BLE001
|
| 237 |
+
who = 'unknown'
|
| 238 |
+
try:
|
| 239 |
+
host = socket.gethostname()
|
| 240 |
+
except Exception: # noqa: BLE001
|
| 241 |
+
host = 'unknown'
|
| 242 |
+
return f' [LOCAL DEV {who}@{host}]'
|
| 243 |
+
|
| 244 |
+
|
| 245 |
+
def describe(repo=None):
|
| 246 |
+
"""What this container sees about itself β the payload behind the status field.
|
| 247 |
+
|
| 248 |
+
β IT REPORTS THE RAW OBSERVATIONS, NOT ONLY THE VERDICT, and that is the point rather than
|
| 249 |
+
debug noise. D-160 established that a Space's environment cannot be read from outside, so
|
| 250 |
+
"is staging on the right store?" is a question only the container can answer. A verdict alone
|
| 251 |
+
("production: false") cannot distinguish "SPACE_ID says staging" from "SPACE_ID does not exist
|
| 252 |
+
on this platform at all" β two states with the same verdict and completely different fixes.
|
| 253 |
+
Reporting the variables makes ONE deploy answer it.
|
| 254 |
+
|
| 255 |
+
β Carries no secret: a Space id and a dataset repo id are public names. The DATA is not, and
|
| 256 |
+
none of it is here. The field is session-gated anyway (see `routes_admin.settings`).
|
| 257 |
+
"""
|
| 258 |
+
rid = str(repo or '').strip()
|
| 259 |
+
return {
|
| 260 |
+
'deployment': deployment_id(),
|
| 261 |
+
'production': is_production_deployment(),
|
| 262 |
+
'repo': rid,
|
| 263 |
+
'writable': write_refusal(rid) is None if rid else False,
|
| 264 |
+
'refusal': write_refusal(rid) if rid else None,
|
| 265 |
+
'localOverride': local_override(),
|
| 266 |
+
'allowlist': sorted(sandbox_allowlist()),
|
| 267 |
+
# The raw half. `''` means "the variable is absent", which is itself the answer on a
|
| 268 |
+
# platform that does not set it.
|
| 269 |
+
'observed': {name: _env(name) for name in _IDENTITY_VARS},
|
| 270 |
+
}
|
platform/core/grid_events.py
CHANGED
|
@@ -40,7 +40,12 @@ down, and this note is the marker for that work.
|
|
| 40 |
import datetime as dt
|
| 41 |
import json as _json_ev # wave 23 (C7): the json field's parse wall
|
| 42 |
from dataclasses import dataclass, field
|
| 43 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 44 |
|
| 45 |
import core.store as store
|
| 46 |
import core.table_store as _tstore # wave-9 I17: the shared-view authorisation predicates
|
|
@@ -92,6 +97,21 @@ class EventResult:
|
|
| 92 |
rerender: bool = False
|
| 93 |
doc: Optional[dict] = None # doc_fetch's answer β the bridge has no response channel
|
| 94 |
toast: Optional[str] = None # add_to_list's confirmation
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 95 |
|
| 96 |
|
| 97 |
@dataclass
|
|
@@ -579,6 +599,39 @@ def _known_usernames():
|
|
| 579 |
|
| 580 |
|
| 581 |
# ------------------------------------------------------------------ THE SEAM
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 582 |
def handle_events(events, ctx):
|
| 583 |
"""The event LOG entry point β one EventResult. The `[-24:]` window lives here.
|
| 584 |
|
|
@@ -963,8 +1016,30 @@ def handle_one(event, ctx):
|
|
| 963 |
# broken). Role `edit` (or admin) writes THROUGH to the owner's record β config only,
|
| 964 |
# never identity or reach: `createdBy`/`permissions` are pinned from the stored record.
|
| 965 |
# Role `view` (or no grant) refuses with a toast instead of forking.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 966 |
_save_as = uname
|
| 967 |
-
if _store_of(ctx).available():
|
| 968 |
_foreign = _tops(ctx).find_view(view_id)
|
| 969 |
if _foreign and _foreign[0] != uname:
|
| 970 |
_o_uname, _stored = _foreign
|
|
@@ -1077,7 +1152,8 @@ def handle_one(event, ctx):
|
|
| 1077 |
if kind == 'field_upsert':
|
| 1078 |
raw = event.get('field')
|
| 1079 |
if not isinstance(raw, dict):
|
| 1080 |
-
return
|
|
|
|
| 1081 |
key = str(raw.get('key') or '')[:80]
|
| 1082 |
import aios_grid as _ag2
|
| 1083 |
if key.startswith(_ag2.MEASURE_FIELD_PREFIX):
|
|
@@ -1086,7 +1162,10 @@ def handle_one(event, ctx):
|
|
| 1086 |
# measure this user could also filter by. Fail closed on anything else.
|
| 1087 |
field = _ag2.clean_measure_field(raw, {m['key']: m for m in measure_offer})
|
| 1088 |
if field is None:
|
| 1089 |
-
return
|
|
|
|
|
|
|
|
|
|
| 1090 |
fmt = _ag2._clean_format(raw.get('format'), field.get('type'))
|
| 1091 |
if fmt:
|
| 1092 |
field['format'] = fmt
|
|
@@ -1138,13 +1217,19 @@ def handle_one(event, ctx):
|
|
| 1138 |
# second, private, non-computing copy here would be a second definition of the same
|
| 1139 |
# column. A refusal repaints, so a stale client says something rather than nothing.
|
| 1140 |
if ftype in ('link', 'rollup'):
|
| 1141 |
-
return
|
|
|
|
|
|
|
|
|
|
| 1142 |
readonly = ftype in _ag2.READONLY_CUSTOM_TYPES
|
| 1143 |
# The editable family must SAY it is overlay (the client's own contract); the
|
| 1144 |
# read-only pair (formula / created_time) is stored under the cohort column's
|
| 1145 |
# mechanism instead, so no cell write can ever be accepted for it.
|
| 1146 |
if not readonly and raw.get('source') != 'overlay':
|
| 1147 |
-
return
|
|
|
|
|
|
|
|
|
|
| 1148 |
field = {'key': key, 'label': str(raw.get('label') or 'Untitled')[:120],
|
| 1149 |
'type': ftype, 'source': 'odoo' if readonly else 'overlay',
|
| 1150 |
'default': True, 'custom': True,
|
|
@@ -1170,7 +1255,10 @@ def handle_one(event, ctx):
|
|
| 1170 |
if ftype in ('select', 'multiselect'):
|
| 1171 |
field['options'] = _ag2._clean_options(raw.get('options'))
|
| 1172 |
if not field['options']:
|
| 1173 |
-
|
|
|
|
|
|
|
|
|
|
| 1174 |
field.update(_ag2._choice_appearance(raw, field['options']))
|
| 1175 |
if ftype == 'rating':
|
| 1176 |
field['max'] = _ag2._clean_rating_max(raw.get('max'))
|
|
@@ -1179,7 +1267,13 @@ def handle_one(event, ctx):
|
|
| 1179 |
# alone so a later-deleted ref blanks the CELLS, not the column.
|
| 1180 |
formula = _ag2._clean_formula(raw.get('formula'), valid_keys)
|
| 1181 |
if formula is None:
|
| 1182 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1183 |
field['formula'] = formula
|
| 1184 |
if ftype == 'automation':
|
| 1185 |
# C5-AUTOFIELD (wave 18): persist the validated config bag. No `return False`
|
|
@@ -1199,7 +1293,9 @@ def handle_one(event, ctx):
|
|
| 1199 |
auto = _ag2._clean_automation(raw.get('automation'), valid_keys,
|
| 1200 |
flow_ids=_flow_ids)
|
| 1201 |
if auto is None:
|
| 1202 |
-
return
|
|
|
|
|
|
|
| 1203 |
field['automation'] = auto
|
| 1204 |
# β WAVE-27 item 13 (R13): the code column's language. OPTIONAL, like the
|
| 1205 |
# `automation` bag above and unlike `formula` β an unconfigured code column is a
|
|
@@ -1216,7 +1312,14 @@ def handle_one(event, ctx):
|
|
| 1216 |
if fmt:
|
| 1217 |
field['format'] = fmt
|
| 1218 |
else:
|
| 1219 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1220 |
# Wave-5 item 1 β createdBy + permissions on the CREATED strata (custom_/measure_).
|
| 1221 |
# `createdBy` is stamped HOST-SIDE at create and preserved on every later write: the
|
| 1222 |
# client never supplies it, so a browser cannot claim someone else's field. A
|
|
|
|
| 40 |
import datetime as dt
|
| 41 |
import json as _json_ev # wave 23 (C7): the json field's parse wall
|
| 42 |
from dataclasses import dataclass, field
|
| 43 |
+
# β ALIASED ON PURPOSE. `field` is imported above for the dataclasses that need it, and this file
|
| 44 |
+
# uses `field` as a LOCAL VARIABLE in a dozen handlers (`field = {'key': key, β¦}`). A
|
| 45 |
+
# `field(default_factory=list)` written inside one of those functions would resolve to the local
|
| 46 |
+
# dict and raise. The alias is unshadowable, so D-291's channel cannot be broken by a rename.
|
| 47 |
+
from dataclasses import field as dataclass_field
|
| 48 |
+
from typing import List, MutableMapping, Optional
|
| 49 |
|
| 50 |
import core.store as store
|
| 51 |
import core.table_store as _tstore # wave-9 I17: the shared-view authorisation predicates
|
|
|
|
| 97 |
rerender: bool = False
|
| 98 |
doc: Optional[dict] = None # doc_fetch's answer β the bridge has no response channel
|
| 99 |
toast: Optional[str] = None # add_to_list's confirmation
|
| 100 |
+
#: ββ D-291 β WHY A WRITE WAS DECLINED. Until 2026-08-17 this door had NO disclosure channel
|
| 101 |
+
#: at all: `field_upsert` carries EIGHT distinct `return False` refusals and every one of them
|
| 102 |
+
#: answered `{"results":[{"id":"β¦","rerender":false}]}` β byte-identical to a success.
|
| 103 |
+
#: β THE COST WAS NOT THE MISSING MESSAGE, IT WAS THAT EVERY THEORY BECAME UNFALSIFIABLE.
|
| 104 |
+
#: D-275 (a custom field on the product grid answers 200 and is absent from a fresh read) sat
|
| 105 |
+
#: open across TWO waves because no amount of reading the source can say WHICH of the eight
|
| 106 |
+
#: fired on a given request β and the register's own advice is that reporting the cause IS the
|
| 107 |
+
#: diagnostic ([[report-the-cause-before-you-fix-it]]). D-276 is the precedent: shipping the
|
| 108 |
+
#: report first produced, in one deploy, a measurement that REFUTED a clean by-elimination
|
| 109 |
+
#: argument about the cause.
|
| 110 |
+
#: β SAFE BY CONSTRUCTION, and this is the check to re-run if a new refusal is added: every
|
| 111 |
+
#: entry describes the caller's OWN submitted event. It never names another user, another
|
| 112 |
+
#: tenant, or a row the caller cannot see β the failure mode D-276's `visible` flag exists to
|
| 113 |
+
#: avoid one layer up.
|
| 114 |
+
refusals: List[dict] = dataclass_field(default_factory=list)
|
| 115 |
|
| 116 |
|
| 117 |
@dataclass
|
|
|
|
| 599 |
|
| 600 |
|
| 601 |
# ------------------------------------------------------------------ THE SEAM
|
| 602 |
+
#: ββ D-291's WRITER. Every refusal in `field_upsert` goes through here so the caller learns WHY
|
| 603 |
+
#: instead of receiving a success-shaped answer.
|
| 604 |
+
#:
|
| 605 |
+
#: β IT RETURNS **True**, NOT False, AND THAT HALF IS A SECOND DEFECT THIS CLOSES. `handle_one`'s
|
| 606 |
+
#: return value means *"this page must re-render from server state"* β so a refusal that returned
|
| 607 |
+
#: False left the browser's OPTIMISTIC column on screen indefinitely. The user typed a column, saw
|
| 608 |
+
#: it appear, and it was never stored; only a reload revealed it had never existed. The file already
|
| 609 |
+
#: states the rule for the one refusal that got it right (`refused_perms`): *"the client's optimistic
|
| 610 |
+
#: copy is a lie that must be repainted"*. Now every refusal obeys it.
|
| 611 |
+
#:
|
| 612 |
+
#: `code` is a stable machine token (the client may branch on it); `message` is the sentence a
|
| 613 |
+
#: person reads. β The message must name what the CALLER can change β a refusal a user cannot act
|
| 614 |
+
#: on is only marginally better than silence.
|
| 615 |
+
def _refuse(ctx, code, message, key=''):
|
| 616 |
+
"""Record a NAMED refusal on the result and demand a repaint. Always returns True."""
|
| 617 |
+
try:
|
| 618 |
+
out = getattr(ctx, 'out', None)
|
| 619 |
+
if out is not None and hasattr(out, 'refusals'):
|
| 620 |
+
if len(out.refusals) < 24: # one per event in the window; never unbounded
|
| 621 |
+
out.refusals.append({
|
| 622 |
+
'event': 'field_upsert',
|
| 623 |
+
'key': str(key or '')[:80],
|
| 624 |
+
'code': str(code)[:40],
|
| 625 |
+
'message': str(message)[:300],
|
| 626 |
+
})
|
| 627 |
+
except Exception: # noqa: BLE001
|
| 628 |
+
# β REPORTING MUST NEVER BE THE THING THAT BREAKS THE WRITE PATH. A refusal that raises
|
| 629 |
+
# while explaining itself would turn a declined field into a 500 β strictly worse than the
|
| 630 |
+
# silence this replaces.
|
| 631 |
+
pass
|
| 632 |
+
return True
|
| 633 |
+
|
| 634 |
+
|
| 635 |
def handle_events(events, ctx):
|
| 636 |
"""The event LOG entry point β one EventResult. The `[-24:]` window lives here.
|
| 637 |
|
|
|
|
| 1016 |
# broken). Role `edit` (or admin) writes THROUGH to the owner's record β config only,
|
| 1017 |
# never identity or reach: `createdBy`/`permissions` are pinned from the stored record.
|
| 1018 |
# Role `view` (or no grant) refuses with a toast instead of forking.
|
| 1019 |
+
#
|
| 1020 |
+
# ββ WAVE 33 Β· T13 (owner item 3) β A PINNED PER-USER ID IS NOT A FOREIGN VIEW, AND
|
| 1021 |
+
# TREATING IT AS ONE IS A CROSS-USER WRITE THAT REPORTS SUCCESS.
|
| 1022 |
+
#
|
| 1023 |
+
# `find_view` scans EVERY personal stratum and returns the FIRST match. `all-customers`
|
| 1024 |
+
# and `tpl_overview` are PINNED ids that every user of a table has their own copy of β
|
| 1025 |
+
# so the moment ANY colleague autosaves one (a column resize is enough), the wall reads
|
| 1026 |
+
# "somebody else owns this id" for everybody else. MEASURED, on this exact path, after
|
| 1027 |
+
# one colleague resized a column on the Overview:
|
| 1028 |
+
# Β· a NON-ADMIN marking it is REFUSED, with a toast blaming sharing β a view nobody
|
| 1029 |
+
# ever shared, on their own database;
|
| 1030 |
+
# Β· an ADMIN marking it answers 200 and writes the mark into the OTHER USER'S
|
| 1031 |
+
# stratum. The admin's own workspace still serves the un-marked view, so the mark
|
| 1032 |
+
# "does not work"; the colleague silently gains a mark they never made.
|
| 1033 |
+
# That is item 3's second mechanism, and it is a residency bug wearing a sharing bug's
|
| 1034 |
+
# error message.
|
| 1035 |
+
#
|
| 1036 |
+
# β THIS FUNCTION ALREADY STATES THE RULE THE WALL BREAKS, seventy lines up: "A SYSTEM
|
| 1037 |
+
# VIEW IS PER-USER STATE AND MUST NEVER BE SHARED", enforced there by pinning
|
| 1038 |
+
# `perms = {'edit': 'personal'}`. A per-user view can therefore never BE a grant, which
|
| 1039 |
+
# is the only thing this wall exists to protect β so exempting it narrows nothing.
|
| 1040 |
+
_pinned_per_user = (_kind == 'system' or view_id in ('all-customers', _ag_overview_id()))
|
| 1041 |
_save_as = uname
|
| 1042 |
+
if _store_of(ctx).available() and not _pinned_per_user:
|
| 1043 |
_foreign = _tops(ctx).find_view(view_id)
|
| 1044 |
if _foreign and _foreign[0] != uname:
|
| 1045 |
_o_uname, _stored = _foreign
|
|
|
|
| 1152 |
if kind == 'field_upsert':
|
| 1153 |
raw = event.get('field')
|
| 1154 |
if not isinstance(raw, dict):
|
| 1155 |
+
return _refuse(ctx, 'malformed',
|
| 1156 |
+
'the event carried no field object')
|
| 1157 |
key = str(raw.get('key') or '')[:80]
|
| 1158 |
import aios_grid as _ag2
|
| 1159 |
if key.startswith(_ag2.MEASURE_FIELD_PREFIX):
|
|
|
|
| 1162 |
# measure this user could also filter by. Fail closed on anything else.
|
| 1163 |
field = _ag2.clean_measure_field(raw, {m['key']: m for m in measure_offer})
|
| 1164 |
if field is None:
|
| 1165 |
+
return _refuse(
|
| 1166 |
+
ctx, 'measure_not_offered',
|
| 1167 |
+
'this measure is not one you can filter by on this page, so a column '
|
| 1168 |
+
'cannot be built from it', key)
|
| 1169 |
fmt = _ag2._clean_format(raw.get('format'), field.get('type'))
|
| 1170 |
if fmt:
|
| 1171 |
field['format'] = fmt
|
|
|
|
| 1217 |
# second, private, non-computing copy here would be a second definition of the same
|
| 1218 |
# column. A refusal repaints, so a stale client says something rather than nothing.
|
| 1219 |
if ftype in ('link', 'rollup'):
|
| 1220 |
+
return _refuse(
|
| 1221 |
+
ctx, 'wrong_door',
|
| 1222 |
+
'a link or rollup column belongs to the table schema, not to a personal '
|
| 1223 |
+
'overlay - create it from the Fields panel instead', key)
|
| 1224 |
readonly = ftype in _ag2.READONLY_CUSTOM_TYPES
|
| 1225 |
# The editable family must SAY it is overlay (the client's own contract); the
|
| 1226 |
# read-only pair (formula / created_time) is stored under the cohort column's
|
| 1227 |
# mechanism instead, so no cell write can ever be accepted for it.
|
| 1228 |
if not readonly and raw.get('source') != 'overlay':
|
| 1229 |
+
return _refuse(
|
| 1230 |
+
ctx, 'source_not_overlay',
|
| 1231 |
+
"an editable column must declare source 'overlay'; this one declared "
|
| 1232 |
+
'%r' % (raw.get('source'),), key)
|
| 1233 |
field = {'key': key, 'label': str(raw.get('label') or 'Untitled')[:120],
|
| 1234 |
'type': ftype, 'source': 'odoo' if readonly else 'overlay',
|
| 1235 |
'default': True, 'custom': True,
|
|
|
|
| 1255 |
if ftype in ('select', 'multiselect'):
|
| 1256 |
field['options'] = _ag2._clean_options(raw.get('options'))
|
| 1257 |
if not field['options']:
|
| 1258 |
+
# a select with no choices can never hold a value
|
| 1259 |
+
return _refuse(
|
| 1260 |
+
ctx, 'no_options',
|
| 1261 |
+
'a select column needs at least one choice', key)
|
| 1262 |
field.update(_ag2._choice_appearance(raw, field['options']))
|
| 1263 |
if ftype == 'rating':
|
| 1264 |
field['max'] = _ag2._clean_rating_max(raw.get('max'))
|
|
|
|
| 1267 |
# alone so a later-deleted ref blanks the CELLS, not the column.
|
| 1268 |
formula = _ag2._clean_formula(raw.get('formula'), valid_keys)
|
| 1269 |
if formula is None:
|
| 1270 |
+
# β THE ONE D-275 IS MOST LIKELY TO BE. `valid_keys` is THIS page's column
|
| 1271 |
+
# set, so a formula naming a column that exists on another grid is refused
|
| 1272 |
+
# here and was, until now, indistinguishable from a save.
|
| 1273 |
+
return _refuse(
|
| 1274 |
+
ctx, 'formula_refs',
|
| 1275 |
+
'the formula is empty or names a column this table does not have',
|
| 1276 |
+
key)
|
| 1277 |
field['formula'] = formula
|
| 1278 |
if ftype == 'automation':
|
| 1279 |
# C5-AUTOFIELD (wave 18): persist the validated config bag. No `return False`
|
|
|
|
| 1293 |
auto = _ag2._clean_automation(raw.get('automation'), valid_keys,
|
| 1294 |
flow_ids=_flow_ids)
|
| 1295 |
if auto is None:
|
| 1296 |
+
return _refuse(
|
| 1297 |
+
ctx, 'automation_flow',
|
| 1298 |
+
'the automation this column names does not exist', key)
|
| 1299 |
field['automation'] = auto
|
| 1300 |
# β WAVE-27 item 13 (R13): the code column's language. OPTIONAL, like the
|
| 1301 |
# `automation` bag above and unlike `formula` β an unconfigured code column is a
|
|
|
|
| 1312 |
if fmt:
|
| 1313 |
field['format'] = fmt
|
| 1314 |
else:
|
| 1315 |
+
# β THE FALL-THROUGH, AND IT IS THE WIDEST OF THE EIGHT: the key is neither a base
|
| 1316 |
+
# contract field (a note/format override) nor a `custom_`/`measure_` key, so there is
|
| 1317 |
+
# no stratum it could be written to. A client sending an unprefixed new key lands
|
| 1318 |
+
# here β and until D-291 that answered exactly like a save.
|
| 1319 |
+
return _refuse(
|
| 1320 |
+
ctx, 'unknown_key',
|
| 1321 |
+
"a new column's key must start with 'custom_'; a base column can only take a "
|
| 1322 |
+
'note or a format override', key)
|
| 1323 |
# Wave-5 item 1 β createdBy + permissions on the CREATED strata (custom_/measure_).
|
| 1324 |
# `createdBy` is stamped HOST-SIDE at create and preserved on every later write: the
|
| 1325 |
# client never supplies it, so a browser cannot claim someone else's field. A
|
platform/core/keychain.py
CHANGED
|
@@ -166,6 +166,52 @@ def read_fields(rt, entry_id):
|
|
| 166 |
return None
|
| 167 |
|
| 168 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 169 |
def odoo_creds(rt):
|
| 170 |
"""R3's resolver seam: the FIRST odoo-type entry's fields, else None (the caller falls
|
| 171 |
back to the environment). Deterministic order = insertion-id sort, so 'first' is stable."""
|
|
|
|
| 166 |
return None
|
| 167 |
|
| 168 |
|
| 169 |
+
def first_entry_of_type(rt, etype):
|
| 170 |
+
"""The metadata row of the FIRST entry of `etype`, or None. Never decrypts anything.
|
| 171 |
+
|
| 172 |
+
β W35-T45 β the same "first, by insertion-id sort" rule `_first_creds` resolves on, exposed as
|
| 173 |
+
an IDENTITY question rather than a credential one. `ensure_entry_of_type` needs to know whether
|
| 174 |
+
an entry exists WITHOUT unlocking it, and `list_entries` + a hand-rolled `next()` at each caller
|
| 175 |
+
is how two places come to disagree about which entry is "the" one.
|
| 176 |
+
"""
|
| 177 |
+
return next((e for e in list_entries(rt) if e.get('type') == str(etype or '')), None)
|
| 178 |
+
|
| 179 |
+
|
| 180 |
+
def ensure_entry_of_type(rt, etype, label, fields, username):
|
| 181 |
+
"""Create ONE entry of `etype` only if the tenant has none. `(row, why)`; `row` is None on skip.
|
| 182 |
+
|
| 183 |
+
β W35-T45 / R11 β the primitive tenant #0's env-to-keychain migration is built from, and the
|
| 184 |
+
reason it lives here is that only this module knows what "already has one" means: `odoo_creds`
|
| 185 |
+
resolves to the FIRST entry of a type, so a second one would be stored, invisible in every
|
| 186 |
+
resolver, and impossible to tell from the one that serves.
|
| 187 |
+
|
| 188 |
+
β IDEMPOTENT BY TYPE, NOT BY A FLAG. A migration that keys idempotency on a marker it writes
|
| 189 |
+
itself is one lost marker away from running twice ([[a-migration-that-runs-on-the-next-write]]);
|
| 190 |
+
keying it on the thing it would create cannot double-apply, whatever else fails.
|
| 191 |
+
|
| 192 |
+
β AND IT REFUSES ON A LOCKED KEYCHAIN RATHER THAN STORING A SECRET IN THE CLEAR. `add_entry`
|
| 193 |
+
would raise `KeychainLocked`; this answers with a REASON instead, because "there is no Fernet key
|
| 194 |
+
on this deployment" is an operator fact to report, not an exception to propagate out of a boot
|
| 195 |
+
thread where nobody reads it.
|
| 196 |
+
|
| 197 |
+
β `why` IS RETURNED EVEN ON SUCCESS-BY-SKIP. "Already migrated" and "could not migrate" are
|
| 198 |
+
different operator actions and a bare None cannot tell them apart.
|
| 199 |
+
"""
|
| 200 |
+
etype = str(etype or '').strip().lower()
|
| 201 |
+
if etype not in ENTRY_TYPES:
|
| 202 |
+
return None, f'{etype!r} is not a keychain entry type'
|
| 203 |
+
existing = first_entry_of_type(rt, etype)
|
| 204 |
+
if existing:
|
| 205 |
+
return None, f'this tenant already has a {etype} entry ({existing["id"]})'
|
| 206 |
+
if not unlocked():
|
| 207 |
+
return None, ('this deployment has no keychain key, and a credential must never be stored '
|
| 208 |
+
'in the clear')
|
| 209 |
+
try:
|
| 210 |
+
return add_entry(rt, label, etype, fields, username), ''
|
| 211 |
+
except Exception as exc: # noqa: BLE001
|
| 212 |
+
return None, f'{type(exc).__name__}: {exc}'
|
| 213 |
+
|
| 214 |
+
|
| 215 |
def odoo_creds(rt):
|
| 216 |
"""R3's resolver seam: the FIRST odoo-type entry's fields, else None (the caller falls
|
| 217 |
back to the environment). Deterministic order = insertion-id sort, so 'first' is stable."""
|
platform/core/perm_scope.py
CHANGED
|
@@ -87,6 +87,22 @@ def may_access(user, module):
|
|
| 87 |
return perms.may_open(user, module) # legacy record: the old grant wall
|
| 88 |
|
| 89 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 90 |
# ββ FIELDS βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
|
| 91 |
def hidden_keys(user, module, fields):
|
| 92 |
"""The TRANSITIVE closure of hidden field keys (C-PERM amendment 5).
|
|
@@ -143,6 +159,37 @@ def visible_fields(fields, user, module):
|
|
| 143 |
if not (isinstance(f, dict) and f.get('key') in hide)]
|
| 144 |
|
| 145 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 146 |
def strip_row(row, hide):
|
| 147 |
"""Drop hidden keys from ONE assembled row. Cheap enough to run per row, and it must run
|
| 148 |
per row: the field list and the row payload are two different wires, and stripping only the
|
|
@@ -170,6 +217,89 @@ def apply_row_scope(rows, user, module, fields, ctx=None):
|
|
| 170 |
return [r for r in (rows or ()) if fe.permits(tree, r, fields, ctx)]
|
| 171 |
|
| 172 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 173 |
# ββ THE PUSHDOWN βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
|
| 174 |
#: `dba` value sets that pin a BU, and the Odoo team they pin. `_dba_attrs` emits exactly
|
| 175 |
#: {'Fisch','Royal','Both'} (blank for "no brand attributable in 24 months"), so a permission
|
|
|
|
| 87 |
return perms.may_open(user, module) # legacy record: the old grant wall
|
| 88 |
|
| 89 |
|
| 90 |
+
def assistant_entry(user, module):
|
| 91 |
+
"""The explicit database grant an Assistant snapshot may rely on, else ``None``.
|
| 92 |
+
|
| 93 |
+
The interactive application retains an admin break-glass path and a temporary legacy-grant
|
| 94 |
+
compatibility path. Neither is an answer at the Assistant's app-stored data boundary:
|
| 95 |
+
that reader must be able to name the migrated grant that admitted a database. In particular,
|
| 96 |
+
a store-outage admin identity with no ``perms`` document is not an unresolved permission that
|
| 97 |
+
may be widened into data access.
|
| 98 |
+
"""
|
| 99 |
+
e = entry(user, module)
|
| 100 |
+
if (not is_migrated(user) or not isinstance(e, dict)
|
| 101 |
+
or not bool(e.get('access', True)) or not may_access(user, module)):
|
| 102 |
+
return None
|
| 103 |
+
return e
|
| 104 |
+
|
| 105 |
+
|
| 106 |
# ββ FIELDS βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
|
| 107 |
def hidden_keys(user, module, fields):
|
| 108 |
"""The TRANSITIVE closure of hidden field keys (C-PERM amendment 5).
|
|
|
|
| 159 |
if not (isinstance(f, dict) and f.get('key') in hide)]
|
| 160 |
|
| 161 |
|
| 162 |
+
def assistant_visible_fields(fields, user, module):
|
| 163 |
+
"""Visible closure under one explicit Assistant grant, including for an admin caller."""
|
| 164 |
+
e = assistant_entry(user, module)
|
| 165 |
+
if e is None:
|
| 166 |
+
return []
|
| 167 |
+
# `hidden_keys` deliberately preserves the interactive admin break-glass behaviour. The
|
| 168 |
+
# Assistant uses its explicit grant instead, but shares the same transitive formula closure.
|
| 169 |
+
hidden = {str(k) for k in (e.get('hiddenFields') or ()) if k}
|
| 170 |
+
if not hidden:
|
| 171 |
+
return list(fields or ())
|
| 172 |
+
|
| 173 |
+
refs = {}
|
| 174 |
+
for field in fields or ():
|
| 175 |
+
if not isinstance(field, dict) or not field.get('key'):
|
| 176 |
+
continue
|
| 177 |
+
expr = field.get('formula')
|
| 178 |
+
if isinstance(expr, str) and expr:
|
| 179 |
+
refs[field['key']] = {match.strip() for match in _FORMULA_REF.findall(expr)
|
| 180 |
+
if match.strip()}
|
| 181 |
+
for _ in range(12):
|
| 182 |
+
grew = False
|
| 183 |
+
for key, deps in refs.items():
|
| 184 |
+
if key not in hidden and deps & hidden:
|
| 185 |
+
hidden.add(key)
|
| 186 |
+
grew = True
|
| 187 |
+
if not grew:
|
| 188 |
+
break
|
| 189 |
+
return [field for field in (fields or ())
|
| 190 |
+
if not (isinstance(field, dict) and field.get('key') in hidden)]
|
| 191 |
+
|
| 192 |
+
|
| 193 |
def strip_row(row, hide):
|
| 194 |
"""Drop hidden keys from ONE assembled row. Cheap enough to run per row, and it must run
|
| 195 |
per row: the field list and the row payload are two different wires, and stripping only the
|
|
|
|
| 217 |
return [r for r in (rows or ()) if fe.permits(tree, r, fields, ctx)]
|
| 218 |
|
| 219 |
|
| 220 |
+
def assistant_apply_row_scope(rows, user, module, fields, ctx=None):
|
| 221 |
+
"""Apply an explicit Assistant grant's permanent filter without an admin bypass."""
|
| 222 |
+
e = assistant_entry(user, module)
|
| 223 |
+
if e is None:
|
| 224 |
+
return []
|
| 225 |
+
tree = e.get('filter')
|
| 226 |
+
if not tree:
|
| 227 |
+
return list(rows or ())
|
| 228 |
+
from harness import filter_eval as fe
|
| 229 |
+
return [row for row in (rows or ()) if fe.permits(tree, row, fields, ctx)]
|
| 230 |
+
|
| 231 |
+
|
| 232 |
+
def validate_assistant_filter(tree, fields):
|
| 233 |
+
"""Return a strict, detached Assistant filter tree or raise ``ValueError``.
|
| 234 |
+
|
| 235 |
+
The display filter cleaner is intentionally permissive: it drops a stale column or leaves an
|
| 236 |
+
inactive condition alone so an old saved view can still open. An Assistant data reader cannot
|
| 237 |
+
inherit that behaviour β dropping a predicate turns a request for a subset into a wider read.
|
| 238 |
+
This validator therefore admits only visible field operands that the existing evaluator can
|
| 239 |
+
answer from one stored row. Cohort, measure and rank conditions need separate materialised
|
| 240 |
+
set resolvers and are refused here rather than guessed.
|
| 241 |
+
"""
|
| 242 |
+
if tree is None:
|
| 243 |
+
return None
|
| 244 |
+
from harness import filter_eval as fe
|
| 245 |
+
|
| 246 |
+
by_key = {str(field.get('key')): field for field in (fields or ())
|
| 247 |
+
if isinstance(field, dict) and field.get('key')}
|
| 248 |
+
if not by_key:
|
| 249 |
+
raise ValueError('assistant filter has no visible field contract')
|
| 250 |
+
|
| 251 |
+
def _leaf(raw):
|
| 252 |
+
if not isinstance(raw, dict):
|
| 253 |
+
raise ValueError('assistant filter leaf must be an object')
|
| 254 |
+
allowed = {'id', 'colId', 'op', 'value', 'value2', 'rhs'}
|
| 255 |
+
if set(raw) - allowed:
|
| 256 |
+
raise ValueError('assistant filter carries an unsupported operand')
|
| 257 |
+
col = raw.get('colId')
|
| 258 |
+
op = raw.get('op')
|
| 259 |
+
if not isinstance(col, str) or col not in by_key:
|
| 260 |
+
raise ValueError('assistant filter names an unknown or hidden field')
|
| 261 |
+
if (not isinstance(op, str) or op not in fe.FILTER_OPS or op in fe.RANK_OPS
|
| 262 |
+
or op in {'between', 'within'} or col == fe.COHORT_FIELD):
|
| 263 |
+
raise ValueError('assistant filter uses an unsupported operator')
|
| 264 |
+
rhs = raw.get('rhs')
|
| 265 |
+
if rhs is not None:
|
| 266 |
+
if (not isinstance(rhs, dict) or rhs.get('kind') != 'field'
|
| 267 |
+
or set(rhs) - {'kind', 'colId'}
|
| 268 |
+
or not isinstance(rhs.get('colId'), str)
|
| 269 |
+
or rhs['colId'] not in by_key):
|
| 270 |
+
raise ValueError('assistant filter names an unknown or hidden right-hand field')
|
| 271 |
+
out = {name: raw[name] for name in ('id', 'colId', 'op', 'value', 'value2')
|
| 272 |
+
if name in raw}
|
| 273 |
+
if rhs is not None:
|
| 274 |
+
out['rhs'] = {'kind': rhs.get('kind'), 'colId': rhs['colId']}
|
| 275 |
+
if not fe.is_rule_active(out, by_key):
|
| 276 |
+
raise ValueError('assistant filter is inactive or unanswerable')
|
| 277 |
+
return out
|
| 278 |
+
|
| 279 |
+
def _node(raw):
|
| 280 |
+
if not isinstance(raw, dict):
|
| 281 |
+
raise ValueError('assistant filter node must be an object')
|
| 282 |
+
if 'children' not in raw:
|
| 283 |
+
return _leaf(raw)
|
| 284 |
+
if set(raw) - {'conj', 'children'}:
|
| 285 |
+
raise ValueError('assistant filter group carries an unsupported operand')
|
| 286 |
+
children = raw.get('children')
|
| 287 |
+
if raw.get('conj') not in ('and', 'or') or not isinstance(children, list) or not children:
|
| 288 |
+
raise ValueError('assistant filter group must be a non-empty and/or group')
|
| 289 |
+
return {'conj': raw['conj'], 'children': [_node(child) for child in children]}
|
| 290 |
+
|
| 291 |
+
if isinstance(tree, list):
|
| 292 |
+
if not tree:
|
| 293 |
+
raise ValueError('assistant filter list must not be empty')
|
| 294 |
+
return {'conj': 'and', 'nodes': [_node(node) for node in tree]}
|
| 295 |
+
if not isinstance(tree, dict) or set(tree) - {'conj', 'nodes'}:
|
| 296 |
+
raise ValueError('assistant filters must be a tree with nodes')
|
| 297 |
+
nodes = tree.get('nodes')
|
| 298 |
+
if tree.get('conj') not in ('and', 'or') or not isinstance(nodes, list) or not nodes:
|
| 299 |
+
raise ValueError('assistant filter tree must be a non-empty and/or tree')
|
| 300 |
+
return {'conj': tree['conj'], 'nodes': [_node(node) for node in nodes]}
|
| 301 |
+
|
| 302 |
+
|
| 303 |
# ββ THE PUSHDOWN βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
|
| 304 |
#: `dba` value sets that pin a BU, and the Odoo team they pin. `_dba_attrs` emits exactly
|
| 305 |
#: {'Fisch','Royal','Both'} (blank for "no brand attributable in 24 months"), so a permission
|
platform/core/perms.py
CHANGED
|
@@ -199,6 +199,116 @@ def nav_pages(user):
|
|
| 199 |
return out
|
| 200 |
|
| 201 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 202 |
def landing_page(user):
|
| 203 |
"""Where a restricted user lands: the first MAIN-chrome page in their grant. None for
|
| 204 |
unrestricted users (the client lands on the Analyst, as the host does).
|
|
|
|
| 199 |
return out
|
| 200 |
|
| 201 |
|
| 202 |
+
# ------------------------------------------------------------------ governable modules (C3)
|
| 203 |
+
#: ββ WAVE 33, OWNER ITEM 11 β *"its an error that ALL fucking tenant can see both Customer and
|
| 204 |
+
#: Product database under Manage User, this is only for Royal Imports tenant. Make sure per tenant
|
| 205 |
+
#: configuration always work, this is my fourth time I flag it."*
|
| 206 |
+
#:
|
| 207 |
+
#: The cause was two lines in `routes_admin.py`: `_PERM_MODULES = ("customer_data","product_data")`
|
| 208 |
+
#: and a `_MODULE_LABELS` dict beside it. `get_perms` built its answer from the literal and never
|
| 209 |
+
#: touched `session.runtime`, so the permission editor was TENANT-BLIND BY CONSTRUCTION β every
|
| 210 |
+
#: tenant was handed tenant #0's two grid modules whether or not it is provisioned for either.
|
| 211 |
+
#:
|
| 212 |
+
#: β WHY THE DERIVATION LIVES HERE AND NOT AT THE ROUTE. `routes_nav.py::nav` already applies
|
| 213 |
+
#: exactly this rule and has since wave 18; the perms route is the ONE surface that skipped it.
|
| 214 |
+
#: A second copy of the rule at a second call site is how the two came apart in the first place,
|
| 215 |
+
#: so the rule is stated once, as a pure function of (runtime, catalogue), and both the route and
|
| 216 |
+
#: `verify_perm_scope` ask THIS.
|
| 217 |
+
def tenant_modules(runtime):
|
| 218 |
+
"""The registry keys this TENANT is provisioned for. None means "every key".
|
| 219 |
+
|
| 220 |
+
β FAIL-CLOSED ON THE EMPTY LIST, and that is not the obvious reading. `routes_admin`'s own
|
| 221 |
+
docstring records two shipped fail-OPENs of exactly this shape (`modules: []` and
|
| 222 |
+
`bus: [<unknown id>]` both read as UNRESTRICTED), so ONLY the literal `'all'` β or an absent
|
| 223 |
+
key, which is how the compiled-in tenant #0 record is written β means every module. A
|
| 224 |
+
bucket-provisioned tenant gets `{"modules": rec.get("modules", [])}`
|
| 225 |
+
(`harness/runtime.py::_builder_from_record`), so `[]` there means the tenant was provisioned
|
| 226 |
+
for NOTHING and must be told so, never handed the catalogue.
|
| 227 |
+
|
| 228 |
+
Legacy keys are migrated on read for the same reason `allowed_modules` does it: a tenant
|
| 229 |
+
record written before a rename must not silently lose the module it names.
|
| 230 |
+
"""
|
| 231 |
+
cfg = getattr(getattr(runtime, 'tenant', None), 'config', None) or {}
|
| 232 |
+
raw = cfg.get('modules', 'all')
|
| 233 |
+
if raw is None or raw == 'all':
|
| 234 |
+
return None
|
| 235 |
+
if isinstance(raw, str):
|
| 236 |
+
raw = [raw]
|
| 237 |
+
return {_LEGACY_KEYS.get(str(k).strip(), str(k).strip())
|
| 238 |
+
for k in raw if str(k or '').strip()}
|
| 239 |
+
|
| 240 |
+
|
| 241 |
+
def tenant_has_module(runtime, key):
|
| 242 |
+
"""Is `key` in this tenant's provisioned set? PARENT-AWARE, like `may_open`.
|
| 243 |
+
|
| 244 |
+
`routes_nav` keeps a page whose `parent` is granted even when the child key is not, and a
|
| 245 |
+
governable list that disagreed with the nav would offer an admin a wall for a database the
|
| 246 |
+
tenant cannot open β or hide one it can.
|
| 247 |
+
"""
|
| 248 |
+
allowed = tenant_modules(runtime)
|
| 249 |
+
if allowed is None or key in allowed:
|
| 250 |
+
return True
|
| 251 |
+
parent = registry.BY_KEY.get(key, {}).get('parent')
|
| 252 |
+
return parent in allowed if parent else False
|
| 253 |
+
|
| 254 |
+
|
| 255 |
+
def tenant_governable_modules(runtime, topics, ut_entries=()):
|
| 256 |
+
"""The databases the permission editor may render for THIS tenant, in stable order.
|
| 257 |
+
|
| 258 |
+
β NAMED `tenant_*` TO STAY DISTINCT FROM `registry.governable_modules()`, which lane E
|
| 259 |
+
published under contract C3 and which this consumes. They answer different questions β
|
| 260 |
+
registry's is "which topics are governable at all, platform-wide"; this one is "which
|
| 261 |
+
databases does THIS tenant govern" β and two same-named functions one import apart is the
|
| 262 |
+
[[one-question-two-normalizers]] shape waiting to happen.
|
| 263 |
+
|
| 264 |
+
`topics` β the registry-backed grid modules the editor can build pickers for, as
|
| 265 |
+
`[{'key': ..., 'label'?: ...}]`, i.e. `registry.governable_modules()` narrowed
|
| 266 |
+
to the topics the caller has a field-schema arm for. The CALLER owns that
|
| 267 |
+
narrowing because the schema behind each arm is code
|
| 268 |
+
(`routes_admin::_module_fields`), not a policy list. Tenant-blind on the way
|
| 269 |
+
in; this function is the only place the tenant is applied.
|
| 270 |
+
`ut_entries` β this tenant's own `ut_*` databases, in `user_tables.nav_entries` shape.
|
| 271 |
+
|
| 272 |
+
Returns `[{'key', 'label', 'enforced'}]`.
|
| 273 |
+
|
| 274 |
+
ββ `enforced` IS THE HONEST HALF AND IT IS NOT DECORATION. `perm_scope` walls the REGISTRY
|
| 275 |
+
topics β `grid_assembly` calls `may_access`, `visible_fields` and `apply_row_scope` on every
|
| 276 |
+
read. It is never consulted for a `ut_*` database: `routes_tables`' visibility is
|
| 277 |
+
`user_tables.may_open` (creator, admin, or a `core.shares` grant) and there is no module
|
| 278 |
+
grant in that path at all. So a stored `ut_*` wall would be INERT β the editor would say
|
| 279 |
+
DENY, the table routes would keep serving, and nothing anywhere would say so. That is the
|
| 280 |
+
same class as the empty-dropdown defect (wave 26 item 24): a control that answers when it
|
| 281 |
+
cannot. The database is LISTED, because the owner asked to see every database; the wall is
|
| 282 |
+
declared unenforced, and `routes_admin::_clean_perms` REFUSES to store one against it rather
|
| 283 |
+
than accepting a rule nobody applies. Arming `perm_scope` over `ut_*` is a change to
|
| 284 |
+
`routes_tables`/`user_tables` (lane A's fence) β booked, not faked.
|
| 285 |
+
"""
|
| 286 |
+
out = []
|
| 287 |
+
for t in topics or ():
|
| 288 |
+
key = str((t or {}).get('key') or '').strip()
|
| 289 |
+
if not key or not tenant_has_module(runtime, key):
|
| 290 |
+
continue
|
| 291 |
+
# The LABEL comes from the registry, never from a dict beside the list. `_MODULE_LABELS`
|
| 292 |
+
# was a hardcoded copy of two registry labels, so wave 33's R2 relabel ("Odoo customers" /
|
| 293 |
+
# "Odoo products") would have moved one of them and left the permission editor showing the
|
| 294 |
+
# old name with nothing to notice.
|
| 295 |
+
label = (t.get('label') or registry.BY_KEY.get(key, {}).get('label') or key)
|
| 296 |
+
out.append({'key': key, 'label': label, 'enforced': True})
|
| 297 |
+
seen = {r['key'] for r in out}
|
| 298 |
+
for e in ut_entries or ():
|
| 299 |
+
key = str((e or {}).get('key') or '').strip()
|
| 300 |
+
if not key or key in seen:
|
| 301 |
+
continue
|
| 302 |
+
seen.add(key)
|
| 303 |
+
out.append({'key': key, 'label': (e.get('label') or key), 'enforced': False})
|
| 304 |
+
return out
|
| 305 |
+
|
| 306 |
+
|
| 307 |
+
def enforced_module_keys(modules):
|
| 308 |
+
"""The subset of `governable_modules`' answer a permission block may actually be stored for."""
|
| 309 |
+
return {m['key'] for m in (modules or ()) if m.get('enforced')}
|
| 310 |
+
|
| 311 |
+
|
| 312 |
def landing_page(user):
|
| 313 |
"""Where a restricted user lands: the first MAIN-chrome page in their grant. None for
|
| 314 |
unrestricted users (the client lands on the Analyst, as the host does).
|
platform/core/registry.py
CHANGED
|
@@ -22,6 +22,22 @@ Fields:
|
|
| 22 |
2026-07-27 pass (keep = Sales + Customers family + Agents + Procurement +
|
| 23 |
Collections + Analyst/plumbing): products, assortment, financial, management,
|
| 24 |
pricing, inventory, vendor, warehouse, returns, outreach, complexity, health.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 25 |
note one-line scope note shown in the UI / docs
|
| 26 |
"""
|
| 27 |
# WAVE-9 I8 β `'source'`: which connected system a module's data comes from.
|
|
@@ -41,7 +57,7 @@ REGISTRY = [
|
|
| 41 |
# briefing still read it, and pages_sales.py survives UNREGISTERED as the Y1 envelope's
|
| 42 |
# template + verify_api's fixture.
|
| 43 |
{'key': 'sales', 'label': 'Sales', 'brand': True, 'hq': False, 'validate': True, 'source': 'Odoo', 'archived': True,
|
| 44 |
-
'note': 'Revenue, YoY, seasonality, reps, customers, SKUs
|
| 45 |
'rebuild as grid chart/dashboard views (compare series, KPI deltas, tables).'},
|
| 46 |
# ARCHIVED AS A PAGE (owner item 14, wave 8): "archive the current form of the Customer
|
| 47 |
# dashboard completely, i want to redesign it, exactly with the backend we have". So the
|
|
@@ -65,7 +81,14 @@ REGISTRY = [
|
|
| 65 |
# myday->customer_list was done. The STORE keys are deliberately NOT renamed:
|
| 66 |
# 'customer_table_workspace' and 'customer_lists' hold real user data, and renaming them
|
| 67 |
# would orphan every saved view. Label-only changes need none of that machinery.
|
| 68 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 69 |
'note': 'Build, filter and save customer lists: the whole scoped book with per-customer '
|
| 70 |
'metrics; saved lists are visible, editable formulas (Call list and Win-back ship '
|
| 71 |
'as templates) plus hand-picked members. Sub-module of Customers (owner nav redesign 2026-07-23; replaced My Day).'},
|
|
@@ -81,7 +104,7 @@ REGISTRY = [
|
|
| 81 |
# _LEGACY_KEYS maps cohortβcustomer_data so grants + ?page= deep links land on the grid
|
| 82 |
# that now hosts the cohorts.
|
| 83 |
{'key': 'cohort', 'label': 'Cohort', 'brand': True, 'hq': False, 'validate': False, 'source': 'Odoo', 'parent': 'customers', 'archived': True,
|
| 84 |
-
'note': 'Hand-curated, unchanging customer lists
|
| 85 |
'locked views (wave 16). The set is fixed: it changes only when someone adds '
|
| 86 |
'or removes a member. Open them from Customer > Views > Cohorts.'},
|
| 87 |
# ARCHIVED wave 16 (owner item 7, R11, 2026-08-02) beside Sales. The agent DRAWER and the
|
|
@@ -101,13 +124,16 @@ REGISTRY = [
|
|
| 101 |
'group_only': True,
|
| 102 |
'note': 'Folder for the product surfaces (Product table). The archived SKU dashboard is '
|
| 103 |
'not part of this family.'},
|
| 104 |
-
|
|
|
|
|
|
|
|
|
|
| 105 |
'note': 'The SKU catalogue as a grid: per-product revenue, units and (consolidated) '
|
| 106 |
'stock columns, with saved views and custom fields. Identity = the SKU code.'},
|
| 107 |
{'key': 'products', 'label': 'SKU', 'brand': True, 'hq': False, 'validate': True, 'archived': True,
|
| 108 |
-
'note': 'SKU movers, zombies, velocity, coverage, drawers
|
| 109 |
{'key': 'assortment', 'label': 'Assortment', 'brand': True, 'hq': False, 'validate': True, 'archived': True,
|
| 110 |
-
'note': 'Facet-level performance (category/color/occasion/collection/season) + season readiness
|
| 111 |
{'key': 'financial', 'label': 'Financial', 'brand': True, 'hq': False, 'validate': True, 'archived': True,
|
| 112 |
'note': 'Gross margin by BU/category/SKU. Cash-conversion cycle is HQ-consolidated.'},
|
| 113 |
{'key': 'pricing', 'label': 'Pricing', 'brand': True, 'hq': False, 'validate': True, 'archived': True,
|
|
@@ -122,7 +148,7 @@ REGISTRY = [
|
|
| 122 |
'note': 'PAGE RETIRED 2026-08-03 (owner wave-17 item 13: "We should be able to replace '
|
| 123 |
'Procurement completely, and add it as part of the Product database"). The buy '
|
| 124 |
'list is now a saved VIEW on the Product grid, filtered on a FORMULA field over '
|
| 125 |
-
'the supplier/lead-time columns and the demand measure
|
| 126 |
'"Buy list is just a View, with a Filter from a Formula field that taps into '
|
| 127 |
'Metrics Fields... the 8-month demand baseline etc. is just math in a Formula '
|
| 128 |
'field." The ROW STAYS validate_only: `modules/procurement.py` still owns the '
|
|
@@ -136,7 +162,7 @@ REGISTRY = [
|
|
| 136 |
'source': 'Odoo', 'api_surface': False, 'admin_only': True,
|
| 137 |
'note': 'PAGE RETIRED 2026-08-03 (owner wave-17 item 15: "Collections should also be '
|
| 138 |
'entirely replicable as just a View under Customer"). The worklist is the shared '
|
| 139 |
-
'"Collections" view on the Customer grid
|
| 140 |
'reconciled blocks (ar_open/ar_overdue/ar_exposure/days_to_pay + the four aging '
|
| 141 |
'buckets). The ROW STAYS validate_only so validate.py keeps running ar.validate(), '
|
| 142 |
'which is the proof those columns rest on; archiving it would have skipped the '
|
|
@@ -145,7 +171,7 @@ REGISTRY = [
|
|
| 145 |
'sender (app._collections_statements -> modules/collections_send), the ONE '
|
| 146 |
'sanctioned Odoo writer, which the same ruling says stays untouched. So the row '
|
| 147 |
'keeps a Streamlit page for ADMINS ONLY (`admin_only`) and leaves the API payload '
|
| 148 |
-
'entirely (`api_surface: False`)
|
| 149 |
'worklist, and the biweekly send keeps its door.'},
|
| 150 |
{'key': 'returns', 'label': 'Returns', 'brand': False, 'hq': True, 'validate': True, 'archived': True,
|
| 151 |
'note': 'Credit-note lens: refund concentration by SKU (quality) and customer (behavior). Company-level.'},
|
|
@@ -154,7 +180,7 @@ REGISTRY = [
|
|
| 154 |
{'key': 'backorders', 'label': 'Backorders', 'brand': True, 'hq': False, 'validate': True, 'archived': True,
|
| 155 |
'note': 'Confirmed-undelivered order lines aged vs promise date, valued, with a supply-aware next action per row (ship / expedite / call). Wholesale scope.'},
|
| 156 |
{'key': 'pricecomp', 'label': 'Price Compliance', 'brand': True, 'hq': False, 'validate': True, 'archived': True,
|
| 157 |
-
'note': 'Selling below the customer pricelist tier (LTM, per customer x SKU): the pocket-price floor worklist with annualized leak $. Sub-30% ratios usually mean a stale or pack-basis RULE
|
| 158 |
{'key': 'o2c', 'label': 'Cash Timing', 'brand': True, 'hq': False, 'validate': True, 'archived': True,
|
| 159 |
'note': 'Order-to-cash stage decomposition (order-to-ship / ship-to-invoice / invoice-to-paid, each with its owner) + the terms-gap rollup: contractual vs actual days per payment term with the free-credit $ it strands.'},
|
| 160 |
{'key': 'bookings', 'label': 'Order Book', 'brand': True, 'hq': False, 'validate': True, 'archived': True,
|
|
@@ -167,29 +193,37 @@ REGISTRY = [
|
|
| 167 |
'note': 'Operating expense from the GL (all expense-type accounts; COGS excluded): trend, operating leverage (opex % of revenue), the YoY cost bridge, XmR control-limit spike watch list, fixed/variable split and a drill-to-ledger category directory. Company-level.'},
|
| 168 |
{'key': 'health', 'label': 'Data Health', 'brand': False, 'hq': True, 'validate': True, 'archived': True,
|
| 169 |
'note': 'Close/reconciliation scan; period-filtered, mostly company-level. ARCHITECTURE '
|
| 170 |
-
'(owner 2026-07-23): every discrepancy / potential-error marker lives here
|
| 171 |
'procurement mapping gaps, count-trust (unverified on-hand counts), untracked-on-'
|
| 172 |
-
'order
|
| 173 |
{'key': 'dictionary', 'label': 'Metric Dictionary', 'brand': False, 'hq': True, 'validate': True,
|
| 174 |
'nav': False, 'validate_only': True,
|
| 175 |
-
'note': 'PAGE RETIRED 2026-07-23 (owner: broken/not customer-facing)
|
| 176 |
'validate.py keeps running the semantic-layer contracts (the Analyst grounding '
|
| 177 |
-
'proof). No nav, no page. Wave 17 R8 ("I don\'t even know what it does
|
| 178 |
'them") made that literal: `validate_only` takes it out of the account menu too, '
|
| 179 |
'which is the last place it was still visible. The proof survives; the door does not.'},
|
| 180 |
-
{'key': 'automation', 'label': '
|
| 181 |
'nav': True,
|
| 182 |
-
'note': 'Wave 18 (C-AUTONAV):
|
| 183 |
-
'
|
| 184 |
-
'
|
| 185 |
-
'
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 186 |
{'key': 'settings', 'label': 'Settings', 'brand': False, 'hq': True, 'validate': False,
|
| 187 |
'nav': False, # sidebar sentinel (account group) β owner IA 2026-07-12
|
| 188 |
'note': 'User scope settings: the Business Unit toggle (strict isolation) and the Data basis '
|
| 189 |
'toggle (Orders vs Invoiced) moved here from the sidebar.'},
|
| 190 |
{'key': 'analyst', 'label': 'AIOS Analyst', 'brand': False, 'hq': True, 'validate': False,
|
| 191 |
'nav': False, # sidebar sentinel button; eval gate = harness/evals.py (run pre-ship, NOT in validate.py β live LLM cost)
|
| 192 |
-
'note': 'Ask the business a question in plain language: a small AI model calls governed tools over the semantic layer
|
| 193 |
]
|
| 194 |
|
| 195 |
BY_KEY = {m['key']: m for m in REGISTRY}
|
|
@@ -197,3 +231,90 @@ BY_KEY = {m['key']: m for m in REGISTRY}
|
|
| 197 |
|
| 198 |
def brand_filterable(key) -> bool:
|
| 199 |
return bool(BY_KEY.get(key, {}).get('brand'))
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 22 |
2026-07-27 pass (keep = Sales + Customers family + Agents + Procurement +
|
| 23 |
Collections + Analyst/plumbing): products, assortment, financial, management,
|
| 24 |
pricing, inventory, vendor, warehouse, returns, outreach, complexity, health.
|
| 25 |
+
subject set -> the REAL-WORLD POPULATION this row presents, as a source-qualified id
|
| 26 |
+
('odoo:res.partner'). β W33-T41 / item 12a: it is what makes "two databases present
|
| 27 |
+
the same thing" a statement code can refuse, and it exists because NO OTHER FIELD
|
| 28 |
+
CAN CARRY THAT TEST. Not the key (`product_data` and `ut_odoo_products` are different
|
| 29 |
+
keys by construction β that is the bug, not the check), and NOT THE LABEL: the owner's
|
| 30 |
+
own complaint is "why do we have 'Odoo products' ALREADY with the current Products
|
| 31 |
+
database?", i.e. the twin was already carrying the label the legacy row is about to
|
| 32 |
+
take (W33-T42). Between T42 and T44 the two rows legitimately share a label, so a
|
| 33 |
+
label-keyed check would refuse the rename that fixes the bug.
|
| 34 |
+
β A row without `subject` claims nothing and conflicts with nothing β silence is not
|
| 35 |
+
a claim, so adding this field cannot retro-refuse anything already shipped.
|
| 36 |
+
topic set -> this row is a GOVERNABLE DATABASE and this is the word the rest of the codebase
|
| 37 |
+
already calls it by (`routes_grid._SCOPES`, `routes_alerts._TOPICS`, `scope=` on the
|
| 38 |
+
grid routes). β W33-T46 / contract C3: it is what `governable_modules()` keys on, and
|
| 39 |
+
it exists so `routes_admin`'s permission list can be DERIVED from the registry instead
|
| 40 |
+
of being the hardcoded two-element tuple that made every tenant see Customer + Product.
|
| 41 |
note one-line scope note shown in the UI / docs
|
| 42 |
"""
|
| 43 |
# WAVE-9 I8 β `'source'`: which connected system a module's data comes from.
|
|
|
|
| 57 |
# briefing still read it, and pages_sales.py survives UNREGISTERED as the Y1 envelope's
|
| 58 |
# template + verify_api's fixture.
|
| 59 |
{'key': 'sales', 'label': 'Sales', 'brand': True, 'hq': False, 'validate': True, 'source': 'Odoo', 'archived': True,
|
| 60 |
+
'note': 'Revenue, YoY, seasonality, reps, customers, SKUs. By BU. Retired wave 16: '
|
| 61 |
'rebuild as grid chart/dashboard views (compare series, KPI deltas, tables).'},
|
| 62 |
# ARCHIVED AS A PAGE (owner item 14, wave 8): "archive the current form of the Customer
|
| 63 |
# dashboard completely, i want to redesign it, exactly with the backend we have". So the
|
|
|
|
| 81 |
# myday->customer_list was done. The STORE keys are deliberately NOT renamed:
|
| 82 |
# 'customer_table_workspace' and 'customer_lists' hold real user data, and renaming them
|
| 83 |
# would orphan every saved view. Label-only changes need none of that machinery.
|
| 84 |
+
# LABEL renamed 'Customer' -> 'Odoo customers' (owner item 12, 2026-08-14 / W33-T42): the
|
| 85 |
+
# naming convention of every other database from this connector ("Odoo orders", "Odoo vendor
|
| 86 |
+
# bills"). β STILL LABEL-ONLY, and the note above is the precedent β the KEY does not move, so
|
| 87 |
+
# no grant, saved view, cohort, formula, shared column or `?page=` deep link is touched.
|
| 88 |
+
# β `nav_meta` could not have done this: `routes_nav.py` raises `400 name_not_allowed` for any
|
| 89 |
+
# key that does not start with `ut_`, so a tenant rename cannot reach a registry module at all.
|
| 90 |
+
{'key': 'customer_data', 'label': 'Odoo customers', 'brand': True, 'hq': False, 'validate': False, 'source': 'Odoo', 'parent': 'customers',
|
| 91 |
+
'subject': 'odoo:res.partner', 'topic': 'customer',
|
| 92 |
'note': 'Build, filter and save customer lists: the whole scoped book with per-customer '
|
| 93 |
'metrics; saved lists are visible, editable formulas (Call list and Win-back ship '
|
| 94 |
'as templates) plus hand-picked members. Sub-module of Customers (owner nav redesign 2026-07-23; replaced My Day).'},
|
|
|
|
| 104 |
# _LEGACY_KEYS maps cohortβcustomer_data so grants + ?page= deep links land on the grid
|
| 105 |
# that now hosts the cohorts.
|
| 106 |
{'key': 'cohort', 'label': 'Cohort', 'brand': True, 'hq': False, 'validate': False, 'source': 'Odoo', 'parent': 'customers', 'archived': True,
|
| 107 |
+
'note': 'Hand-curated, unchanging customer lists. Folded into the Customer rail as '
|
| 108 |
'locked views (wave 16). The set is fixed: it changes only when someone adds '
|
| 109 |
'or removes a member. Open them from Customer > Views > Cohorts.'},
|
| 110 |
# ARCHIVED wave 16 (owner item 7, R11, 2026-08-02) beside Sales. The agent DRAWER and the
|
|
|
|
| 124 |
'group_only': True,
|
| 125 |
'note': 'Folder for the product surfaces (Product table). The archived SKU dashboard is '
|
| 126 |
'not part of this family.'},
|
| 127 |
+
# LABEL renamed 'Product' -> 'Odoo products' (owner item 12, 2026-08-14 / W33-T42) β see the
|
| 128 |
+
# customer_data note above; label-only, the key stays `product_data`.
|
| 129 |
+
{'key': 'product_data', 'label': 'Odoo products', 'brand': True, 'hq': False, 'validate': True, 'source': 'Odoo', 'parent': 'products_family',
|
| 130 |
+
'subject': 'odoo:product.product', 'topic': 'product',
|
| 131 |
'note': 'The SKU catalogue as a grid: per-product revenue, units and (consolidated) '
|
| 132 |
'stock columns, with saved views and custom fields. Identity = the SKU code.'},
|
| 133 |
{'key': 'products', 'label': 'SKU', 'brand': True, 'hq': False, 'validate': True, 'archived': True,
|
| 134 |
+
'note': 'SKU movers, zombies, velocity, coverage, drawers. By BU (sales-derived).'},
|
| 135 |
{'key': 'assortment', 'label': 'Assortment', 'brand': True, 'hq': False, 'validate': True, 'archived': True,
|
| 136 |
+
'note': 'Facet-level performance (category/color/occasion/collection/season) + season readiness. By BU.'},
|
| 137 |
{'key': 'financial', 'label': 'Financial', 'brand': True, 'hq': False, 'validate': True, 'archived': True,
|
| 138 |
'note': 'Gross margin by BU/category/SKU. Cash-conversion cycle is HQ-consolidated.'},
|
| 139 |
{'key': 'pricing', 'label': 'Pricing', 'brand': True, 'hq': False, 'validate': True, 'archived': True,
|
|
|
|
| 148 |
'note': 'PAGE RETIRED 2026-08-03 (owner wave-17 item 13: "We should be able to replace '
|
| 149 |
'Procurement completely, and add it as part of the Product database"). The buy '
|
| 150 |
'list is now a saved VIEW on the Product grid, filtered on a FORMULA field over '
|
| 151 |
+
'the supplier/lead-time columns and the demand measure. The owner\'s ruling R3: '
|
| 152 |
'"Buy list is just a View, with a Filter from a Formula field that taps into '
|
| 153 |
'Metrics Fields... the 8-month demand baseline etc. is just math in a Formula '
|
| 154 |
'field." The ROW STAYS validate_only: `modules/procurement.py` still owns the '
|
|
|
|
| 162 |
'source': 'Odoo', 'api_surface': False, 'admin_only': True,
|
| 163 |
'note': 'PAGE RETIRED 2026-08-03 (owner wave-17 item 15: "Collections should also be '
|
| 164 |
'entirely replicable as just a View under Customer"). The worklist is the shared '
|
| 165 |
+
'"Collections" view on the Customer grid. Same numbers, from this module\'s own '
|
| 166 |
'reconciled blocks (ar_open/ar_overdue/ar_exposure/days_to_pay + the four aging '
|
| 167 |
'buckets). The ROW STAYS validate_only so validate.py keeps running ar.validate(), '
|
| 168 |
'which is the proof those columns rest on; archiving it would have skipped the '
|
|
|
|
| 171 |
'sender (app._collections_statements -> modules/collections_send), the ONE '
|
| 172 |
'sanctioned Odoo writer, which the same ruling says stays untouched. So the row '
|
| 173 |
'keeps a Streamlit page for ADMINS ONLY (`admin_only`) and leaves the API payload '
|
| 174 |
+
'entirely (`api_surface: False`). No "Collections" in the React nav, no second '
|
| 175 |
'worklist, and the biweekly send keeps its door.'},
|
| 176 |
{'key': 'returns', 'label': 'Returns', 'brand': False, 'hq': True, 'validate': True, 'archived': True,
|
| 177 |
'note': 'Credit-note lens: refund concentration by SKU (quality) and customer (behavior). Company-level.'},
|
|
|
|
| 180 |
{'key': 'backorders', 'label': 'Backorders', 'brand': True, 'hq': False, 'validate': True, 'archived': True,
|
| 181 |
'note': 'Confirmed-undelivered order lines aged vs promise date, valued, with a supply-aware next action per row (ship / expedite / call). Wholesale scope.'},
|
| 182 |
{'key': 'pricecomp', 'label': 'Price Compliance', 'brand': True, 'hq': False, 'validate': True, 'archived': True,
|
| 183 |
+
'note': 'Selling below the customer pricelist tier (LTM, per customer x SKU): the pocket-price floor worklist with annualized leak $. Sub-30% ratios usually mean a stale or pack-basis RULE. Fix the rule, not the rep.'},
|
| 184 |
{'key': 'o2c', 'label': 'Cash Timing', 'brand': True, 'hq': False, 'validate': True, 'archived': True,
|
| 185 |
'note': 'Order-to-cash stage decomposition (order-to-ship / ship-to-invoice / invoice-to-paid, each with its owner) + the terms-gap rollup: contractual vs actual days per payment term with the free-credit $ it strands.'},
|
| 186 |
{'key': 'bookings', 'label': 'Order Book', 'brand': True, 'hq': False, 'validate': True, 'archived': True,
|
|
|
|
| 193 |
'note': 'Operating expense from the GL (all expense-type accounts; COGS excluded): trend, operating leverage (opex % of revenue), the YoY cost bridge, XmR control-limit spike watch list, fixed/variable split and a drill-to-ledger category directory. Company-level.'},
|
| 194 |
{'key': 'health', 'label': 'Data Health', 'brand': False, 'hq': True, 'validate': True, 'archived': True,
|
| 195 |
'note': 'Close/reconciliation scan; period-filtered, mostly company-level. ARCHITECTURE '
|
| 196 |
+
'(owner 2026-07-23): every discrepancy / potential-error marker lives here. '
|
| 197 |
'procurement mapping gaps, count-trust (unverified on-hand counts), untracked-on-'
|
| 198 |
+
'order. So operational workflows stay clean for doing the work.'},
|
| 199 |
{'key': 'dictionary', 'label': 'Metric Dictionary', 'brand': False, 'hq': True, 'validate': True,
|
| 200 |
'nav': False, 'validate_only': True,
|
| 201 |
+
'note': 'PAGE RETIRED 2026-07-23 (owner: broken/not customer-facing). Row kept ONLY so '
|
| 202 |
'validate.py keeps running the semantic-layer contracts (the Analyst grounding '
|
| 203 |
+
'proof). No nav, no page. Wave 17 R8 ("I don\'t even know what it does. Delete '
|
| 204 |
'them") made that literal: `validate_only` takes it out of the account menu too, '
|
| 205 |
'which is the last place it was still visible. The proof survives; the door does not.'},
|
| 206 |
+
{'key': 'automation', 'label': 'Agents', 'brand': False, 'hq': True, 'validate': False,
|
| 207 |
'nav': True,
|
| 208 |
+
'note': 'Wave 18 (C-AUTONAV): scheduled jobs that create and refresh user databases '
|
| 209 |
+
'(website scrape-to-DB, the Instagram field). React-only surface (no PAGE_FUNCS '
|
| 210 |
+
'entry, the no-new-Streamlit rule); admins hold it via "all", other users need the '
|
| 211 |
+
'explicit grant, fail-closed default. '
|
| 212 |
+
'β WAVE 34 Β· R12. THE LABEL IS "Agents" AND THE KEY IS STILL `automation`. The '
|
| 213 |
+
'owner ruled the module becomes Agent: this is our agent deployment surface going '
|
| 214 |
+
'forward. Only the LABEL moved, because the key is a permission scope, a nav '
|
| 215 |
+
'placement key, a grant name and the `#/automation` route; renaming it would revoke '
|
| 216 |
+
'every stored grant and 404 every bookmark to buy a caption. β The plural is not a '
|
| 217 |
+
'slip: R15 and the wave PRD both spell the rail row "Agents", and the degraded '
|
| 218 |
+
'fallback row in Shell.tsx hard-codes that spelling, so a singular here would paint '
|
| 219 |
+
'two different words in one list depending on whether /nav answered.'},
|
| 220 |
{'key': 'settings', 'label': 'Settings', 'brand': False, 'hq': True, 'validate': False,
|
| 221 |
'nav': False, # sidebar sentinel (account group) β owner IA 2026-07-12
|
| 222 |
'note': 'User scope settings: the Business Unit toggle (strict isolation) and the Data basis '
|
| 223 |
'toggle (Orders vs Invoiced) moved here from the sidebar.'},
|
| 224 |
{'key': 'analyst', 'label': 'AIOS Analyst', 'brand': False, 'hq': True, 'validate': False,
|
| 225 |
'nav': False, # sidebar sentinel button; eval gate = harness/evals.py (run pre-ship, NOT in validate.py β live LLM cost)
|
| 226 |
+
'note': 'Ask the business a question in plain language: a small AI model calls governed tools over the semantic layer. Answers carry their query trace and drill links. AI-generated output (Art. 50 labeled).'},
|
| 227 |
]
|
| 228 |
|
| 229 |
BY_KEY = {m['key']: m for m in REGISTRY}
|
|
|
|
| 231 |
|
| 232 |
def brand_filterable(key) -> bool:
|
| 233 |
return bool(BY_KEY.get(key, {}).get('brand'))
|
| 234 |
+
|
| 235 |
+
|
| 236 |
+
# βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
|
| 237 |
+
# ββ W33-T41 / item 12a β ONE SUBJECT, ONE DATABASE
|
| 238 |
+
# βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
|
| 239 |
+
#
|
| 240 |
+
# The owner: *"why do we have 'Odoo products' already with the current Products database? The
|
| 241 |
+
# Unique ID is redundant, make sure this never happens. One unique ID per database always."*
|
| 242 |
+
#
|
| 243 |
+
# β THE CHECK HAD TO GO WHERE THE BUG WAS MADE, AND THAT IS NOT WHERE ANYONE WOULD LOOK.
|
| 244 |
+
# `core.user_tables.create` β the UI door β HAS had a collision loop all along: it slugs the
|
| 245 |
+
# label to a key and appends `_2 β¦ _49` until the key is free. It never fired here for two
|
| 246 |
+
# reasons, and both matter. (1) It compares KEYS inside ONE tenant's `user_tables` document,
|
| 247 |
+
# and `customer_data` / `product_data` are compiled REGISTRY rows that never enter that
|
| 248 |
+
# document at all β the two halves of the duplicate live in different namespaces and only meet
|
| 249 |
+
# in `routes_nav.py::nav`, where the registry pages and `user_tables.nav_entries` are merged
|
| 250 |
+
# for display. (2) The connector path never calls `create()`: `odoo_relational.
|
| 251 |
+
# _ensure_table_inplace` writes `cur[key] = {...}` straight into the document. So a check bolted
|
| 252 |
+
# onto `create()` would have been green through the entire life of this defect.
|
| 253 |
+
#
|
| 254 |
+
# β THE SUFFIX LOOP IS ALSO WHY A RELABEL ALONE WOULD HAVE MADE THIS WORSE, MECHANICALLY: a
|
| 255 |
+
# naive "just rename Product to Odoo products" mints `ut_odoo_products_2` β the owner's
|
| 256 |
+
# redundant id again, from the fix for it.
|
| 257 |
+
#
|
| 258 |
+
#: subject -> the ONE registry key entitled to present it. Derived, never typed twice.
|
| 259 |
+
SUBJECT_CLAIMS = {m['subject']: m['key'] for m in REGISTRY if m.get('subject')}
|
| 260 |
+
|
| 261 |
+
|
| 262 |
+
# βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
|
| 263 |
+
# ββ W33-T46 / CONTRACT C3 β THE GOVERNABLE MODULE LIST IS DERIVED, NOT A LITERAL
|
| 264 |
+
# βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
|
| 265 |
+
#
|
| 266 |
+
# The owner, on his FOURTH flag of the same thing: *"its an error that ALL fucking tenant can see
|
| 267 |
+
# both Customer and Product database under Manage User, this is only for Royal Imports tenant.
|
| 268 |
+
# Make sure per tenant configuration always work."*
|
| 269 |
+
#
|
| 270 |
+
# β THE CAUSE IS A TWO-ELEMENT TUPLE. `routes_admin._PERM_MODULES = ("customer_data",
|
| 271 |
+
# "product_data")` β a compiled literal that `get_perms` builds its whole list from without ever
|
| 272 |
+
# touching `session.runtime`. It is tenant-blind BY CONSTRUCTION, which is why no amount of
|
| 273 |
+
# per-tenant work elsewhere ever fixed it, and why the answer is not "filter the tuple" but
|
| 274 |
+
# "delete the tuple": a second hand-typed copy of a fact the registry already holds is a thing
|
| 275 |
+
# that CAN go stale, and this one did, four times.
|
| 276 |
+
#
|
| 277 |
+
# β THE LINE BETWEEN THE TWO HALVES, stated because both sides need it: this map is
|
| 278 |
+
# REGISTRY-SIDE and TENANT-BLIND β it answers *"which compiled modules are governable, and what
|
| 279 |
+
# are they called"*, nothing more. Applying the tenant's own `config["modules"]` filter and
|
| 280 |
+
# merging that tenant's `ut_*` databases is the CALLER's half (`routes_admin`, D's fence), which
|
| 281 |
+
# is exactly what `routes_nav.py` already does correctly and `routes_admin` never did.
|
| 282 |
+
def governable_modules():
|
| 283 |
+
"""`{topic: {'key','label','subject'}}` β every registry row that is a governable DATABASE.
|
| 284 |
+
|
| 285 |
+
A fresh dict per call, deliberately: a module-level mapping handed to a route is one
|
| 286 |
+
`.pop()` away from being a different list for every request after the first.
|
| 287 |
+
"""
|
| 288 |
+
return {m['topic']: {'key': m['key'], 'label': m['label'], 'subject': m.get('subject')}
|
| 289 |
+
for m in REGISTRY
|
| 290 |
+
if m.get('topic') and not m.get('archived') and not m.get('group_only')}
|
| 291 |
+
|
| 292 |
+
|
| 293 |
+
def subject_of(key):
|
| 294 |
+
"""The subject a REGISTRY row claims, or None. (`ut_*` databases carry theirs on the stored
|
| 295 |
+
definition instead β they are per-tenant data, not compiled rows.)"""
|
| 296 |
+
return (BY_KEY.get(key) or {}).get('subject')
|
| 297 |
+
|
| 298 |
+
|
| 299 |
+
def subject_conflict(subject, key, claimed=None):
|
| 300 |
+
"""The OTHER key already presenting `subject`, or None.
|
| 301 |
+
|
| 302 |
+
`claimed` is an optional {subject: key} of claims outside the registry β in practice the
|
| 303 |
+
caller's own tenant document, whose stored definitions carry a `subject` stamp. It is a
|
| 304 |
+
PARAMETER rather than a lookup on purpose: the store is per-tenant, two tenants both holding
|
| 305 |
+
an "Odoo customers" is entirely legitimate, and a module-level cache of somebody's tables is
|
| 306 |
+
how D-169 happened. This function knows nothing about which tenant it is serving.
|
| 307 |
+
|
| 308 |
+
β THE TEST IS "A DIFFERENT KEY", NOT "IS THIS SUBJECT TAKEN". `_ensure_table_inplace` and
|
| 309 |
+
`ut_ensure` re-run on every boot and every 1800 s resync, adopting their table BY KEY β so a
|
| 310 |
+
check phrased "is this subject already claimed?" goes red on the second boot against the very
|
| 311 |
+
table it created on the first, and the container fails to start. Idempotency is not an
|
| 312 |
+
exception to the rule here; it is the common case.
|
| 313 |
+
"""
|
| 314 |
+
if not subject:
|
| 315 |
+
return None # silence is not a claim
|
| 316 |
+
for holder in (SUBJECT_CLAIMS, claimed or {}):
|
| 317 |
+
other = holder.get(subject)
|
| 318 |
+
if other and other != key:
|
| 319 |
+
return other
|
| 320 |
+
return None
|
platform/core/shared_overlay.py
CHANGED
|
@@ -230,6 +230,44 @@ def put_cells(table_key, pid, values, st=None):
|
|
| 230 |
return clean
|
| 231 |
|
| 232 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 233 |
def clear_row(table_key, pid, st=None):
|
| 234 |
"""Forget every shared cell on one row. True when there was something to forget."""
|
| 235 |
row_id = _pid(pid)
|
|
|
|
| 230 |
return clean
|
| 231 |
|
| 232 |
|
| 233 |
+
def put_rows(table_key, rows, st=None):
|
| 234 |
+
"""Write shared cells on MANY rows in ONE store update. Returns `{row_id: {key: value}}`.
|
| 235 |
+
|
| 236 |
+
ββ THE WHOLE POINT IS THE *ONE*, AND IT IS NOT AN OPTIMISATION. `put_cells` is one row per
|
| 237 |
+
store write, so a 1,397-row catalog import is 1,397 download-modify-upload cycles against one
|
| 238 |
+
JSON document. This repo has a MEASURED scar for that shape: **18 writes against one document
|
| 239 |
+
under the store's coalescing single-flight landed ZERO while answering 200 eighteen times.**
|
| 240 |
+
Batching is what makes a bulk import land at all, not what makes it fast.
|
| 241 |
+
|
| 242 |
+
β It deliberately takes the WHOLE SET rather than accepting a stream: a caller that loops over
|
| 243 |
+
this function has simply rebuilt `put_cells` with extra steps, and the failure it reintroduces
|
| 244 |
+
is silent. If the set does not fit in memory it does not fit in this store either β that is a
|
| 245 |
+
signal to change substrate, not to chunk.
|
| 246 |
+
|
| 247 |
+
β NO CAP HERE, ON PURPOSE. The bound belongs at the DOOR, where a caller identity and a
|
| 248 |
+
reportable refusal exist (`routes_grid.bulk_cells`). A silent ceiling in a store primitive is
|
| 249 |
+
exactly the shape the standing no-cap rule forbids.
|
| 250 |
+
"""
|
| 251 |
+
clean = {}
|
| 252 |
+
for pid, values in dict(rows or {}).items():
|
| 253 |
+
row_id = _pid(pid)
|
| 254 |
+
cells_for_row = {str(k): _value(v) for k, v in dict(values or {}).items() if str(k)}
|
| 255 |
+
if cells_for_row:
|
| 256 |
+
clean.setdefault(row_id, {}).update(cells_for_row)
|
| 257 |
+
if not clean:
|
| 258 |
+
return {}
|
| 259 |
+
|
| 260 |
+
def _patch(data):
|
| 261 |
+
for row_id, values in clean.items():
|
| 262 |
+
data['cells'].setdefault(row_id, {}).update(values)
|
| 263 |
+
|
| 264 |
+
# `flush='sync'` because a bulk import must be durable when the call returns: the caller is a
|
| 265 |
+
# script that will report "1,397 rows written" and exit, and an async flush would make that
|
| 266 |
+
# sentence a prediction rather than a fact.
|
| 267 |
+
_write(table_key, _patch, st, flush='sync')
|
| 268 |
+
return clean
|
| 269 |
+
|
| 270 |
+
|
| 271 |
def clear_row(table_key, pid, st=None):
|
| 272 |
"""Forget every shared cell on one row. True when there was something to forget."""
|
| 273 |
row_id = _pid(pid)
|
platform/core/shares.py
CHANGED
|
@@ -43,10 +43,32 @@ SHARES_KEY = 'object_shares'
|
|
| 43 |
#: namespace by typo, which would silently grant nothing to nobody and read as "sharing is broken".
|
| 44 |
KINDS = ('view', 'folder', 'database')
|
| 45 |
|
| 46 |
-
#: `*` is "everyone who can already open the surface". It is NOT "every account on the platform"
|
| 47 |
-
#:
|
| 48 |
-
#:
|
| 49 |
-
#:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 50 |
EVERYONE = '*'
|
| 51 |
|
| 52 |
ROLES = ('view', 'edit')
|
|
|
|
| 43 |
#: namespace by typo, which would silently grant nothing to nobody and read as "sharing is broken".
|
| 44 |
KINDS = ('view', 'folder', 'database')
|
| 45 |
|
| 46 |
+
#: `*` is "everyone who can already open the surface". It is NOT "every account on the platform".
|
| 47 |
+
#: Spelled as a single character so it can never collide with a username (usernames are lower-case
|
| 48 |
+
#: and non-empty by `core/users.py`, and are checked against this explicitly below).
|
| 49 |
+
#:
|
| 50 |
+
#: ββ **AND WHAT THAT MEANS DEPENDS ON THE KIND β THE LINE THIS NOTE USED TO CARRY WAS FALSE FOR
|
| 51 |
+
#: ONE OF THE THREE** (W33-T30, `waves/wave32/sharing-audit.md` S-8). It read *"the module/table
|
| 52 |
+
#: wall runs FIRST and this never widens past it"*, flatly, and the audit's own words for that are
|
| 53 |
+
#: *"the third docstring in this audit describing a check that is not on the path"*. Corrected
|
| 54 |
+
#: here rather than deleted, because the sentence is TRUE of two kinds and the difference is the
|
| 55 |
+
#: whole point:
|
| 56 |
+
#: * `kind='view'` / `kind='folder'` on a GOVERNED module (`customer_data`, `product_data`) β
|
| 57 |
+
#: the sentence holds. `require_session` plus the topic's own gate run first, and the
|
| 58 |
+
#: receiver's row scope and hidden-field closure are applied BEFORE any foreign view is
|
| 59 |
+
#: merged, so a grant can only narrow-or-equal what that account could already reach.
|
| 60 |
+
#: * `kind='database'` on a `ut_*` table β **THE SENTENCE IS FALSE AND THIS REGISTRY IS THE
|
| 61 |
+
#: ONLY WALL.** `routes_admin._PERM_MODULES` is `("customer_data", "product_data")` and
|
| 62 |
+
#: `_clean_perms` 400s anything else, so no row filter and no hidden field can even be
|
| 63 |
+
#: DECLARED for a user table; `routes_tables.py` makes zero `perm_scope` calls and passes
|
| 64 |
+
#: `hidden_keys=frozenset()`. A `database` grant is therefore ALL-OR-NOTHING β every row,
|
| 65 |
+
#: every column β and an `*` database grant admits every account in the tenant to all of it.
|
| 66 |
+
#:
|
| 67 |
+
#: β THAT IS A REAL CAPABILITY, DELIBERATELY KEPT, not a hole to plug in passing. What was wrong
|
| 68 |
+
#: was a docstring promising a second wall that does not exist for this kind; scoping user tables
|
| 69 |
+
#: is booked (S-8), not done. `routes_shares.py`'s module docstring says the same thing at the
|
| 70 |
+
#: OTHER door β the audit's fix is "say so at both", and one door saying it is how the next reader
|
| 71 |
+
#: gets the confident half [[one-question-two-normalizers]].
|
| 72 |
EVERYONE = '*'
|
| 73 |
|
| 74 |
ROLES = ('view', 'edit')
|
platform/core/store.py
CHANGED
|
@@ -27,12 +27,35 @@ except Exception:
|
|
| 27 |
pass
|
| 28 |
|
| 29 |
from huggingface_hub import HfApi, hf_hub_download
|
| 30 |
-
from huggingface_hub.utils import EntryNotFoundError,
|
| 31 |
-
|
| 32 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 33 |
_FLUSH_DELAY = 2.0 # coalesce a burst of edits into one commit
|
| 34 |
_FLUSH_MIN_GAP = 20.0 # floor between commits of one key (the 256-commits/hr budget)
|
| 35 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 36 |
#: WAVE 29 (item 20 / ruling R11, contract C6) β THE CHANGE TOKEN'S PROCESS STAMP.
|
| 37 |
#:
|
| 38 |
#: `Store`'s revision counter is IN-MEMORY, so a restarted Space would begin again at 0 and a
|
|
@@ -48,6 +71,51 @@ def _token():
|
|
| 48 |
return os.environ.get('HF_TOKEN') or None
|
| 49 |
|
| 50 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 51 |
class _Projected(dict):
|
| 52 |
"""One top-level value of a PROJECTED read β a dict that RAISES for the keys that were dropped.
|
| 53 |
|
|
@@ -111,6 +179,27 @@ def _project(doc, drop):
|
|
| 111 |
return {k: (_Projected(v, drop) if isinstance(v, dict) else v) for k, v in copied.items()}
|
| 112 |
|
| 113 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 114 |
class Store:
|
| 115 |
"""One repo's persistence: JSON-per-key + raw byte paths, with the wave-7 async flush.
|
| 116 |
|
|
@@ -156,23 +245,51 @@ class Store:
|
|
| 156 |
self._key_locks = {}
|
| 157 |
self._key_locks_guard = threading.Lock()
|
| 158 |
self._rev_at = {}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 159 |
|
| 160 |
def available(self):
|
| 161 |
"""True when a token is configured β callers degrade gracefully without one."""
|
| 162 |
return bool(_token())
|
| 163 |
|
| 164 |
def _download(self, name):
|
| 165 |
-
"""
|
| 166 |
Any other failure (network, auth, rate-limit, corrupt JSON) RAISES β a transient read
|
| 167 |
error must never be mistaken for an empty store, or a caller could overwrite real data
|
| 168 |
-
with an empty dict (this is what wiped the user registry on restart).
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 169 |
try:
|
| 170 |
path = hf_hub_download(self.repo, f'{name}.json', repo_type='dataset',
|
| 171 |
token=_token(), force_download=True)
|
| 172 |
with open(path, encoding='utf-8') as f:
|
| 173 |
-
return json.load(f)
|
| 174 |
except (EntryNotFoundError, RepositoryNotFoundError, FileNotFoundError):
|
| 175 |
-
return {}
|
| 176 |
except ValueError as e:
|
| 177 |
# Wave 18 (R2, found by SESSION D): current huggingface_hub wraps a missing REPO in
|
| 178 |
# ValueError("Force download failedβ¦") with the 404 as __cause__ β so a brand-new
|
|
@@ -180,7 +297,7 @@ class Store:
|
|
| 180 |
# A genuinely-absent repo is the same fact as a genuinely-absent file: {}.
|
| 181 |
cause = getattr(e, '__cause__', None)
|
| 182 |
if isinstance(cause, (EntryNotFoundError, RepositoryNotFoundError)):
|
| 183 |
-
return {}
|
| 184 |
raise
|
| 185 |
|
| 186 |
def get(self, name, fresh=False):
|
|
@@ -191,7 +308,7 @@ class Store:
|
|
| 191 |
if not fresh and name in self._cache:
|
| 192 |
return json.loads(json.dumps(self._cache[name])) # hand back a copy
|
| 193 |
try:
|
| 194 |
-
data = self._download(name)
|
| 195 |
except Exception as e:
|
| 196 |
try: # lazy import β core stays layer-clean
|
| 197 |
import harness.telemetry as _tel # noqa: PLC0415
|
|
@@ -203,6 +320,10 @@ class Store:
|
|
| 203 |
return json.loads(json.dumps(self._cache[name]))
|
| 204 |
return {}
|
| 205 |
self._cache[name] = data
|
|
|
|
|
|
|
|
|
|
|
|
|
| 206 |
return json.loads(json.dumps(data))
|
| 207 |
|
| 208 |
def get_projection(self, name, drop=()):
|
|
@@ -242,7 +363,7 @@ class Store:
|
|
| 242 |
if name in self._cache:
|
| 243 |
return _project(self._cache[name], drop)
|
| 244 |
try:
|
| 245 |
-
data = self._download(name)
|
| 246 |
except Exception as e:
|
| 247 |
try: # lazy import β core stays layer-clean
|
| 248 |
import harness.telemetry as _tel # noqa: PLC0415
|
|
@@ -256,6 +377,7 @@ class Store:
|
|
| 256 |
return {}
|
| 257 |
with self._lock:
|
| 258 |
self._cache[name] = data # β the WHOLE document, never the projection
|
|
|
|
| 259 |
return _project(data, drop)
|
| 260 |
|
| 261 |
def _key_lock(self, name):
|
|
@@ -280,15 +402,25 @@ class Store:
|
|
| 280 |
So the dirty mark is re-read AFTER the download, under the short lock, and a key that
|
| 281 |
became dirty keeps its cache.
|
| 282 |
"""
|
| 283 |
-
data = self._download(name)
|
| 284 |
with self._lock:
|
| 285 |
if self._dirty.get(name) and self._owned.get(name) and name in self._cache:
|
| 286 |
-
#
|
| 287 |
-
#
|
| 288 |
-
#
|
| 289 |
-
#
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 290 |
return json.loads(json.dumps(self._cache[name]))
|
| 291 |
self._cache[name] = data
|
|
|
|
| 292 |
return json.loads(json.dumps(data))
|
| 293 |
|
| 294 |
def exists(self, name):
|
|
@@ -345,30 +477,199 @@ class Store:
|
|
| 345 |
at = self._rev_at.get(n)
|
| 346 |
return {'rev': rev, 'updated_at': at, 'token': f'{REV_EPOCH}:{rev}'}
|
| 347 |
|
| 348 |
-
def
|
| 349 |
-
"""
|
| 350 |
-
|
| 351 |
-
|
|
|
|
|
|
|
|
|
|
| 352 |
if not self._repo_ok:
|
| 353 |
-
|
|
|
|
| 354 |
self._repo_ok = True
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 355 |
buf = io.BytesIO(json.dumps(data, ensure_ascii=False, indent=2).encode('utf-8'))
|
| 356 |
-
|
| 357 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 358 |
|
| 359 |
def upload_bytes(self, path_in_repo, data, message=None):
|
| 360 |
"""Persist RAW BYTES at an arbitrary path in the tenant dataset (wave-8 C5, documents).
|
| 361 |
Bytes are never cached in-process: large, cold, fetched on explicit user action."""
|
| 362 |
if not self.available():
|
| 363 |
raise RuntimeError('No HF_TOKEN configured β persistence is unavailable.')
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 364 |
with self._lock:
|
| 365 |
-
|
| 366 |
-
|
| 367 |
-
|
| 368 |
-
self.
|
| 369 |
-
|
| 370 |
-
|
| 371 |
-
commit_message=message or f'add {path_in_repo}')
|
| 372 |
|
| 373 |
def download_bytes(self, path_in_repo):
|
| 374 |
"""Raw bytes back, or None when absent/unreachable β a missing attachment degrades to
|
|
@@ -385,13 +686,20 @@ class Store:
|
|
| 385 |
return None
|
| 386 |
|
| 387 |
def delete_path(self, path_in_repo):
|
| 388 |
-
"""Remove a stored file. Absent is SUCCESS β deleting what is already gone is the goal.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 389 |
if not self.available():
|
| 390 |
return False
|
|
|
|
| 391 |
try:
|
| 392 |
-
HfApi(token=_token()).delete_file(
|
| 393 |
-
|
| 394 |
-
|
| 395 |
return True
|
| 396 |
except (EntryNotFoundError, RepositoryNotFoundError):
|
| 397 |
return True
|
|
@@ -399,16 +707,44 @@ class Store:
|
|
| 399 |
return False
|
| 400 |
|
| 401 |
def put(self, name, data):
|
| 402 |
-
"""Persist {name}.json (creates the private repo on first write). Updates the cache.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 403 |
if not self.available():
|
| 404 |
raise RuntimeError('No HF_TOKEN configured β persistence is unavailable.')
|
| 405 |
-
|
| 406 |
-
|
| 407 |
-
|
| 408 |
-
|
| 409 |
-
self.
|
| 410 |
-
|
| 411 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 412 |
|
| 413 |
def _flush_worker(self, name):
|
| 414 |
"""Coalescing uploader for one key. Runs while dirty; retries with backoff on failure β
|
|
@@ -433,11 +769,17 @@ class Store:
|
|
| 433 |
this must too; taking `self._lock` first on this path is the deadlock. Both sleeps stay
|
| 434 |
OUTSIDE the key lock β a worker that dozed while holding it would block every writer of
|
| 435 |
that key for `_FLUSH_MIN_GAP`, which is the freeze this ticket exists to remove.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 436 |
"""
|
| 437 |
backoff = 2.0
|
| 438 |
while True:
|
| 439 |
_time.sleep(_FLUSH_DELAY)
|
| 440 |
-
wait, err, snapshot = None, None, None
|
| 441 |
with self._key_lock(name):
|
| 442 |
with self._lock:
|
| 443 |
gap = _time.monotonic() - self._last_flush.get(name, 0.0)
|
|
@@ -449,10 +791,17 @@ class Store:
|
|
| 449 |
else:
|
| 450 |
self._dirty[name] = False
|
| 451 |
snapshot = json.loads(json.dumps(self._cache.get(name, {})))
|
|
|
|
|
|
|
|
|
|
| 452 |
if wait is None:
|
| 453 |
try:
|
| 454 |
-
self.
|
| 455 |
with self._lock:
|
|
|
|
|
|
|
|
|
|
|
|
|
| 456 |
self._last_flush[name] = _time.monotonic()
|
| 457 |
backoff = 2.0
|
| 458 |
except Exception as e: # noqa: BLE001
|
|
@@ -507,15 +856,28 @@ class Store:
|
|
| 507 |
finish, so waiting for its key lock could only turn a partial save into no save at all.
|
| 508 |
Best-effort is the correct contract here, and it is the one case where taking the lock
|
| 509 |
would be worse than skipping it.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 510 |
"""
|
| 511 |
with self._lock:
|
| 512 |
dirty = [k for k, v in self._dirty.items() if v]
|
| 513 |
snaps = {k: json.loads(json.dumps(self._cache.get(k, {}))) for k in dirty}
|
|
|
|
| 514 |
for k in dirty:
|
| 515 |
self._dirty[k] = False
|
| 516 |
for k, d in snaps.items():
|
| 517 |
try:
|
| 518 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 519 |
except Exception:
|
| 520 |
pass # exiting anyway β nothing left to reschedule
|
| 521 |
|
|
@@ -528,9 +890,19 @@ class Store:
|
|
| 528 |
returns immediately; a coalescing worker commits. The strict read still guards the
|
| 529 |
FIRST async update of a key per process.
|
| 530 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 531 |
ββ W31-T13 (D-177(d)) β TWO LOCKS, AND THE SPLIT IS THE WHOLE TICKET.
|
| 532 |
`self._key_lock(name)` is held for the entire read-modify-write, so two writers of one key
|
| 533 |
-
still cannot interleave
|
| 534 |
`self._lock` β the one every `get()` takes β is now held only for the microseconds a cache
|
| 535 |
read or write needs, never across a download or an upload. Before this, one sync write
|
| 536 |
froze every reader in the process for two network round trips, on a store whose warm
|
|
@@ -538,6 +910,13 @@ class Store:
|
|
| 538 |
β Uploading outside `self._lock` is not a new posture: `_flush_worker` has done exactly
|
| 539 |
that since wave 7, and `_repo_ok` racing is benign because `create_repo` is `exist_ok=True`.
|
| 540 |
"""
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 541 |
with self._key_lock(name):
|
| 542 |
return self._update_locked(name, fn, flush)
|
| 543 |
|
|
@@ -596,6 +975,15 @@ class Store:
|
|
| 596 |
result = fn(data)
|
| 597 |
data = result if result is not None else data
|
| 598 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 599 |
if flush == 'async':
|
| 600 |
if not self.available():
|
| 601 |
raise RuntimeError('No HF_TOKEN configured β persistence is unavailable.')
|
|
@@ -606,21 +994,24 @@ class Store:
|
|
| 606 |
self._schedule_flush(name)
|
| 607 |
return data
|
| 608 |
|
| 609 |
-
#
|
| 610 |
-
# `put()`
|
| 611 |
-
#
|
| 612 |
-
#
|
| 613 |
-
#
|
| 614 |
-
#
|
| 615 |
-
#
|
| 616 |
if not self.available():
|
| 617 |
raise RuntimeError('No HF_TOKEN configured β persistence is unavailable.')
|
| 618 |
-
self.
|
| 619 |
with self._lock:
|
| 620 |
-
|
|
|
|
|
|
|
|
|
|
| 621 |
self._owned[name] = True
|
| 622 |
self._last_flush[name] = _time.monotonic()
|
| 623 |
-
# β AFTER THE UPLOAD, NEVER BEFORE β `put()`'s own law. `
|
| 624 |
# and a bump on that path would have `revision()` report a change that never landed.
|
| 625 |
self._bump(name)
|
| 626 |
# The upload above CARRIED whatever was pending, so the key is no longer ahead of
|
|
@@ -629,9 +1020,9 @@ class Store:
|
|
| 629 |
# β AFTER the upload, for the same reason: on a raise the mark MUST survive (the cache
|
| 630 |
# is still the truth and the row must still be committed by the worker). Clearing it
|
| 631 |
# first would turn a transient upload error into the very silent loss the branch above
|
| 632 |
-
# exists to stop β which is why it sits here and not before
|
| 633 |
self._dirty[name] = False
|
| 634 |
-
return
|
| 635 |
|
| 636 |
|
| 637 |
# ------------------------------------------------------------------- instances + module API
|
|
|
|
| 27 |
pass
|
| 28 |
|
| 29 |
from huggingface_hub import HfApi, hf_hub_download
|
| 30 |
+
from huggingface_hub.utils import (EntryNotFoundError, HfHubHTTPError,
|
| 31 |
+
RepositoryNotFoundError)
|
| 32 |
+
|
| 33 |
+
import core.data_binding as data_binding
|
| 34 |
+
|
| 35 |
+
#: ββ D-315 β THE BARE DEFAULT IS GONE. This line used to read
|
| 36 |
+
#: `os.environ.get('OS_DATA_REPO', 'royal-imports/cfo-os-data')`, i.e. every Space that was never
|
| 37 |
+
#: handed the key came up bound to tenant #0's REAL business data β which is how two different
|
| 38 |
+
#: builds wrote it on 2026-08-14. The value it resolves to is unchanged (see
|
| 39 |
+
#: `data_binding.default_store` for why returning the real id beats `None`); what changed is that
|
| 40 |
+
#: WRITING it is now refused unless this deployment is the one that owns it.
|
| 41 |
+
REPO = os.environ.get('OS_DATA_REPO') or data_binding.default_store()
|
| 42 |
_FLUSH_DELAY = 2.0 # coalesce a burst of edits into one commit
|
| 43 |
_FLUSH_MIN_GAP = 20.0 # floor between commits of one key (the 256-commits/hr budget)
|
| 44 |
|
| 45 |
+
#: ββ D-305 β HOW MANY TIMES A WRITE MAY REBASE ONTO A MOVED HEAD BEFORE GIVING UP.
|
| 46 |
+
#:
|
| 47 |
+
#: Bounded rather than unbounded, and the cost is one extra DOWNLOAD per rebase. β Not an extra
|
| 48 |
+
#: commit: a refused write answers 412 and creates nothing, so only the attempt that finally lands
|
| 49 |
+
#: spends the 256-commits/hr budget. Four is generous for the measured case
|
| 50 |
+
#: (two humans editing one grid) and small enough that a genuinely hot key fails loudly instead of
|
| 51 |
+
#: spinning. β Hitting the bound RAISES β it never falls through to an unconditional upload, which
|
| 52 |
+
#: is the pre-fix behaviour wearing a retry loop ([[fallback-that-became-the-rule]]).
|
| 53 |
+
_MAX_REBASE = 4
|
| 54 |
+
|
| 55 |
+
#: How many unconfirmed intents one key may hold before the oldest are dropped. See
|
| 56 |
+
#: `_journal_append` for why a cap exists at all and what is reported when it bites.
|
| 57 |
+
_MAX_JOURNAL = 500
|
| 58 |
+
|
| 59 |
#: WAVE 29 (item 20 / ruling R11, contract C6) β THE CHANGE TOKEN'S PROCESS STAMP.
|
| 60 |
#:
|
| 61 |
#: `Store`'s revision counter is IN-MEMORY, so a restarted Space would begin again at 0 and a
|
|
|
|
| 71 |
return os.environ.get('HF_TOKEN') or None
|
| 72 |
|
| 73 |
|
| 74 |
+
class StoreConflict(RuntimeError):
|
| 75 |
+
"""A write that could not be landed without overwriting somebody else's (D-305).
|
| 76 |
+
|
| 77 |
+
Raised only after `_MAX_REBASE` rebases, or when no parent commit can be resolved at all. Both
|
| 78 |
+
are "we could not make this safe", and both must reach the caller as a failure: the alternative
|
| 79 |
+
β uploading anyway β is exactly the lost update this whole mechanism exists to prevent, and it
|
| 80 |
+
would answer 200 while destroying an hour of another person's work.
|
| 81 |
+
"""
|
| 82 |
+
|
| 83 |
+
|
| 84 |
+
def _is_conflict(exc):
|
| 85 |
+
"""True for the ONE hub failure that means "the branch moved under you".
|
| 86 |
+
|
| 87 |
+
β NARROW ON PURPOSE, AND THE PROBE IS WHY. Measured against a scratch dataset repo on
|
| 88 |
+
2026-08-18: a stale `parent_commit` returns **HTTP 412** with the server message *"The branch
|
| 89 |
+
was updated since you opened this page. Please refresh and try again."*, and the write does NOT
|
| 90 |
+
land. A NONSENSE `parent_commit` returns a **404 `RevisionNotFoundError`** β a different fault
|
| 91 |
+
that must not be retried, because rebasing on it would loop against a bad sha. A broad
|
| 92 |
+
`except HfHubHTTPError` would swallow both, plus every 401/429/500, and turn a network blip
|
| 93 |
+
into a silent rebase.
|
| 94 |
+
"""
|
| 95 |
+
return getattr(getattr(exc, 'response', None), 'status_code', None) == 412
|
| 96 |
+
|
| 97 |
+
|
| 98 |
+
def _sha_from_path(path):
|
| 99 |
+
"""The commit sha out of a hub cache path, or `None` if it does not look like one.
|
| 100 |
+
|
| 101 |
+
β VALIDATED, NOT ASSUMED. The layout is `β¦/snapshots/<40-hex>/<file>`, but a caller may have
|
| 102 |
+
an unusual `HF_HOME`, symlinks disabled (this repo's own machines warn about exactly that), or
|
| 103 |
+
a future hub version. A directory name that is not a 40-character hex sha is reported as "I do
|
| 104 |
+
not know", which routes the write through the explicit head lookup β the safe branch. Returning
|
| 105 |
+
a bad sha would surface as a 404 `RevisionNotFoundError` on every write instead.
|
| 106 |
+
"""
|
| 107 |
+
try:
|
| 108 |
+
parent = Path(path).parent
|
| 109 |
+
if parent.parent.name != 'snapshots':
|
| 110 |
+
return None
|
| 111 |
+
name = parent.name
|
| 112 |
+
if len(name) == 40 and all(c in '0123456789abcdef' for c in name.lower()):
|
| 113 |
+
return name
|
| 114 |
+
except Exception: # noqa: BLE001
|
| 115 |
+
pass
|
| 116 |
+
return None
|
| 117 |
+
|
| 118 |
+
|
| 119 |
class _Projected(dict):
|
| 120 |
"""One top-level value of a PROJECTED read β a dict that RAISES for the keys that were dropped.
|
| 121 |
|
|
|
|
| 179 |
return {k: (_Projected(v, drop) if isinstance(v, dict) else v) for k, v in copied.items()}
|
| 180 |
|
| 181 |
|
| 182 |
+
def is_projected(value):
|
| 183 |
+
"""Did this value come back from a PROJECTED read? β the TAKEN-PATH predicate (W33-T01/D-213).
|
| 184 |
+
|
| 185 |
+
ββ WHY A PREDICATE AND NOT A COUNTER, and it is the whole reason this exists. `all_defs`
|
| 186 |
+
FALLS BACK to the whole read on any failure, silently and by design β so a caller that gets the
|
| 187 |
+
right answer has learned nothing about which read produced it. A gate asserting only "the
|
| 188 |
+
definitions came back" passes identically when the projection worked and when it quietly did
|
| 189 |
+
not, which is [[gate-can-report-green-on-nothing]] wearing a green tick.
|
| 190 |
+
|
| 191 |
+
β This is INTRINSIC rather than instrumented: `_project` stamps every top-level value as a
|
| 192 |
+
`_Projected`, so the evidence rides the document itself. Nothing has to be wrapped, no counter
|
| 193 |
+
can be installed on the wrong object ([[measure-the-real-call]]), and the answer is the same in
|
| 194 |
+
production as it is under a gate β a monkey-patched tally is true only while the patch is on.
|
| 195 |
+
|
| 196 |
+
β It answers about ONE VALUE (a table's definition), not about a document: `_project` returns a
|
| 197 |
+
plain dict OF `_Projected` values, so `is_projected(doc)` is False and `is_projected(doc[key])`
|
| 198 |
+
is True. That is the right grain β the thing a route holds and reads is the definition.
|
| 199 |
+
"""
|
| 200 |
+
return isinstance(value, _Projected)
|
| 201 |
+
|
| 202 |
+
|
| 203 |
class Store:
|
| 204 |
"""One repo's persistence: JSON-per-key + raw byte paths, with the wave-7 async flush.
|
| 205 |
|
|
|
|
| 245 |
self._key_locks = {}
|
| 246 |
self._key_locks_guard = threading.Lock()
|
| 247 |
self._rev_at = {}
|
| 248 |
+
# --- ββ D-305 β THE TWO FIELDS THAT MAKE A CROSS-PROCESS WRITE SURVIVABLE -----------
|
| 249 |
+
# `_base[name]` the hub commit sha this key's cached document was built ON. Learned for
|
| 250 |
+
# free from the download path and from `CommitInfo.oid` after a write, so
|
| 251 |
+
# it costs no extra round trip in the common case.
|
| 252 |
+
# `_journal[name]` the `fn`s applied to this key since the last CONFIRMED upload β our
|
| 253 |
+
# INTENT, not our result. On a conflict the intent is replayed onto the
|
| 254 |
+
# hub's newer document instead of the result being uploaded over it.
|
| 255 |
+
#
|
| 256 |
+
# β WHY A JOURNAL AND NOT A RETRY. The writers here are DIFFERENT PEOPLE in DIFFERENT
|
| 257 |
+
# CONTAINERS, and this instance's cache holds an hour of its own edits over a base that has
|
| 258 |
+
# moved. Re-uploading that snapshot β which is what a retry does β reproduces the loss
|
| 259 |
+
# exactly. Replaying "add this view" onto the fresher document keeps both writers' work,
|
| 260 |
+
# which is the only outcome that answers the defect.
|
| 261 |
+
self._base = {}
|
| 262 |
+
self._journal = {}
|
| 263 |
|
| 264 |
def available(self):
|
| 265 |
"""True when a token is configured β callers degrade gracefully without one."""
|
| 266 |
return bool(_token())
|
| 267 |
|
| 268 |
def _download(self, name):
|
| 269 |
+
"""`(document, commit_sha)` for {name}.json. `({}, None)` ONLY when it is genuinely absent.
|
| 270 |
Any other failure (network, auth, rate-limit, corrupt JSON) RAISES β a transient read
|
| 271 |
error must never be mistaken for an empty store, or a caller could overwrite real data
|
| 272 |
+
with an empty dict (this is what wiped the user registry on restart).
|
| 273 |
+
|
| 274 |
+
ββ D-305 β THE SHA COMES FROM THE PATH, WHICH COSTS NOTHING. `hf_hub_download` writes into
|
| 275 |
+
`β¦/snapshots/<commit sha>/<file>`, so the revision the bytes came from is already in the
|
| 276 |
+
return value. Measured 2026-08-18 against a scratch repo: that directory name equals the
|
| 277 |
+
`CommitInfo.oid` of the commit that wrote the file, and equals
|
| 278 |
+
`get_hf_file_metadata(...).commit_hash` β which would have cost an extra HTTP round trip on
|
| 279 |
+
the hottest read in the product. **The parent of our write is therefore known by every
|
| 280 |
+
reader, for free.**
|
| 281 |
+
|
| 282 |
+
β A sha we cannot parse comes back as `None`, and `_commit` resolves that with an explicit
|
| 283 |
+
head lookup rather than uploading without a precondition. "I do not know my parent" must
|
| 284 |
+
take the careful path, never the fast one.
|
| 285 |
+
"""
|
| 286 |
try:
|
| 287 |
path = hf_hub_download(self.repo, f'{name}.json', repo_type='dataset',
|
| 288 |
token=_token(), force_download=True)
|
| 289 |
with open(path, encoding='utf-8') as f:
|
| 290 |
+
return json.load(f), _sha_from_path(path)
|
| 291 |
except (EntryNotFoundError, RepositoryNotFoundError, FileNotFoundError):
|
| 292 |
+
return {}, None
|
| 293 |
except ValueError as e:
|
| 294 |
# Wave 18 (R2, found by SESSION D): current huggingface_hub wraps a missing REPO in
|
| 295 |
# ValueError("Force download failedβ¦") with the 404 as __cause__ β so a brand-new
|
|
|
|
| 297 |
# A genuinely-absent repo is the same fact as a genuinely-absent file: {}.
|
| 298 |
cause = getattr(e, '__cause__', None)
|
| 299 |
if isinstance(cause, (EntryNotFoundError, RepositoryNotFoundError)):
|
| 300 |
+
return {}, None
|
| 301 |
raise
|
| 302 |
|
| 303 |
def get(self, name, fresh=False):
|
|
|
|
| 308 |
if not fresh and name in self._cache:
|
| 309 |
return json.loads(json.dumps(self._cache[name])) # hand back a copy
|
| 310 |
try:
|
| 311 |
+
data, sha = self._download(name)
|
| 312 |
except Exception as e:
|
| 313 |
try: # lazy import β core stays layer-clean
|
| 314 |
import harness.telemetry as _tel # noqa: PLC0415
|
|
|
|
| 320 |
return json.loads(json.dumps(self._cache[name]))
|
| 321 |
return {}
|
| 322 |
self._cache[name] = data
|
| 323 |
+
# D-305: the cached document and the revision it derives from are set TOGETHER, always.
|
| 324 |
+
# A base that can disagree with the cache it describes is worse than no base at all β
|
| 325 |
+
# it would make a stale write look like a fresh one and pass the precondition.
|
| 326 |
+
self._base[name] = sha
|
| 327 |
return json.loads(json.dumps(data))
|
| 328 |
|
| 329 |
def get_projection(self, name, drop=()):
|
|
|
|
| 363 |
if name in self._cache:
|
| 364 |
return _project(self._cache[name], drop)
|
| 365 |
try:
|
| 366 |
+
data, sha = self._download(name)
|
| 367 |
except Exception as e:
|
| 368 |
try: # lazy import β core stays layer-clean
|
| 369 |
import harness.telemetry as _tel # noqa: PLC0415
|
|
|
|
| 377 |
return {}
|
| 378 |
with self._lock:
|
| 379 |
self._cache[name] = data # β the WHOLE document, never the projection
|
| 380 |
+
self._base[name] = sha # D-305 β set with the cache, never apart from it
|
| 381 |
return _project(data, drop)
|
| 382 |
|
| 383 |
def _key_lock(self, name):
|
|
|
|
| 402 |
So the dirty mark is re-read AFTER the download, under the short lock, and a key that
|
| 403 |
became dirty keeps its cache.
|
| 404 |
"""
|
| 405 |
+
data, sha = self._download(name) # network, no lock held
|
| 406 |
with self._lock:
|
| 407 |
if self._dirty.get(name) and self._owned.get(name) and name in self._cache:
|
| 408 |
+
# ββ D-305 REWROTE THIS BRANCH'S JUSTIFICATION, NOT ITS BEHAVIOUR β AND THE OLD
|
| 409 |
+
# ONE HAD TO GO, because it asserted the defect. It read: *"a pending upload is
|
| 410 |
+
# going to overwrite the hub anyway, so the fresh read cannot preserve a remote
|
| 411 |
+
# write."* That sentence IS the lost update: "we are going to overwrite whatever
|
| 412 |
+
# the other person did" was stated as a reason to stop worrying about it.
|
| 413 |
+
#
|
| 414 |
+
# β It is no longer true. A pending upload now carries a `parent_commit`
|
| 415 |
+
# precondition, so it CANNOT overwrite a remote write β it will be refused and
|
| 416 |
+
# rebased onto it (`_commit`). The branch survives for its OTHER, still-correct
|
| 417 |
+
# reason: this cache holds an async write nobody has flushed yet, and replacing it
|
| 418 |
+
# with the hub's copy destroys a row we have already answered 201 for (D-177).
|
| 419 |
+
# β keep the local delta here; preserve the REMOTE work at commit time, which is
|
| 420 |
+
# the only place that can see it.
|
| 421 |
return json.loads(json.dumps(self._cache[name]))
|
| 422 |
self._cache[name] = data
|
| 423 |
+
self._base[name] = sha
|
| 424 |
return json.loads(json.dumps(data))
|
| 425 |
|
| 426 |
def exists(self, name):
|
|
|
|
| 477 |
at = self._rev_at.get(n)
|
| 478 |
return {'rev': rev, 'updated_at': at, 'token': f'{REV_EPOCH}:{rev}'}
|
| 479 |
|
| 480 |
+
def _ensure_repo(self):
|
| 481 |
+
"""create_repo is confirmed ONCE per instance β it was a full extra API round-trip on
|
| 482 |
+
every put(), pure latency after the first success.
|
| 483 |
+
|
| 484 |
+
Lifted out of `_upload` (D-305) because `_commit` has to resolve a parent commit BEFORE the
|
| 485 |
+
first write, and a repo that does not exist yet has no head to resolve.
|
| 486 |
+
"""
|
| 487 |
if not self._repo_ok:
|
| 488 |
+
HfApi(token=_token()).create_repo(self.repo, repo_type='dataset', private=True,
|
| 489 |
+
exist_ok=True)
|
| 490 |
self._repo_ok = True
|
| 491 |
+
|
| 492 |
+
def _head_sha(self):
|
| 493 |
+
"""The repo's current head commit, or `None` if the repo does not exist yet.
|
| 494 |
+
|
| 495 |
+
β ONE EXTRA ROUND TRIP, AND IT IS THE COLD PATH ONLY. `_base[name]` is populated by every
|
| 496 |
+
download and by every successful write, so this is reached on a first write into a process
|
| 497 |
+
that has never read the key β and on the rebase path, where a round trip is already the
|
| 498 |
+
price of correctness.
|
| 499 |
+
"""
|
| 500 |
+
try:
|
| 501 |
+
return HfApi(token=_token()).repo_info(self.repo, repo_type='dataset').sha
|
| 502 |
+
except RepositoryNotFoundError:
|
| 503 |
+
return None
|
| 504 |
+
|
| 505 |
+
def _upload(self, name, data, parent):
|
| 506 |
+
"""The raw hub write, WITH A PRECONDITION. Returns the new head commit sha.
|
| 507 |
+
|
| 508 |
+
β `parent` IS MANDATORY AND HAS NO DEFAULT, deliberately. A default of `None` would make
|
| 509 |
+
"upload unconditionally" the thing you get by forgetting an argument β and unconditional
|
| 510 |
+
upload is precisely D-305. Every caller goes through `_commit`, which is the one place
|
| 511 |
+
allowed to decide what the parent is.
|
| 512 |
+
"""
|
| 513 |
+
data_binding.check_write(self.repo, f'write {name!r}') # D-315 backstop, see `update`
|
| 514 |
+
self._ensure_repo()
|
| 515 |
buf = io.BytesIO(json.dumps(data, ensure_ascii=False, indent=2).encode('utf-8'))
|
| 516 |
+
info = HfApi(token=_token()).upload_file(
|
| 517 |
+
path_or_fileobj=buf, path_in_repo=f'{name}.json', repo_id=self.repo,
|
| 518 |
+
repo_type='dataset',
|
| 519 |
+
# D-298: under the local opt-in this suffix is what makes a laptop's commit
|
| 520 |
+
# distinguishable from the live Space's in the store's git history β the only audit
|
| 521 |
+
# trail this product has.
|
| 522 |
+
commit_message=f'update {name}' + data_binding.local_commit_suffix(),
|
| 523 |
+
parent_commit=parent)
|
| 524 |
+
return getattr(info, 'oid', None)
|
| 525 |
+
|
| 526 |
+
def _commit(self, name, data, replay=(), max_rebase=None):
|
| 527 |
+
"""Land `data` for `name` without overwriting anyone β D-305's whole mechanism.
|
| 528 |
+
|
| 529 |
+
ββ THE SHAPE, and every step of it is measured rather than assumed (scratch-repo probe,
|
| 530 |
+
2026-08-18):
|
| 531 |
+
|
| 532 |
+
1. upload with `parent_commit = the revision our document was built on`;
|
| 533 |
+
2. the hub answers **412** if the branch moved β and the write does NOT land, so there
|
| 534 |
+
is nothing to undo;
|
| 535 |
+
3. re-read the head, REPLAY our intent (`replay`, the `fn`s applied since our last
|
| 536 |
+
confirmed upload) onto it, and try again against the new parent;
|
| 537 |
+
4. after `_MAX_REBASE` attempts, RAISE.
|
| 538 |
+
|
| 539 |
+
β REPLAYING THE INTENT IS WHAT MAKES THIS DIFFERENT FROM A RETRY. Uploading our snapshot
|
| 540 |
+
again would reproduce the loss; re-applying "add this view" to the newer document keeps
|
| 541 |
+
both writers. The one place it changes an answer is a `fn` that ALLOCATES from the document
|
| 542 |
+
β `table_store._unique_name` picks the first free display name β which on a rebase may pick
|
| 543 |
+
a different name than the one already handed to the caller. That is a rename where the
|
| 544 |
+
pre-fix behaviour was a DELETION, and the trade is stated rather than hidden.
|
| 545 |
+
|
| 546 |
+
β NO PARENT β RAISE, NEVER UPLOAD BLIND. If neither the cached base nor `_head_sha()` can
|
| 547 |
+
name a revision, the safe answer is "this write cannot be made safe", not "make it the old
|
| 548 |
+
way". A fallback that quietly restores the unguarded path is how a fix becomes decorative
|
| 549 |
+
([[fallback-that-became-the-rule]]).
|
| 550 |
+
|
| 551 |
+
Returns `(document_that_landed, new_sha)` β the document may differ from the one passed in,
|
| 552 |
+
because a rebase rebuilds it.
|
| 553 |
+
"""
|
| 554 |
+
data_binding.check_write(self.repo, f'write {name!r}')
|
| 555 |
+
# β `_ensure_repo()` IS NOT CALLED HERE, and that is a deliberate reversal. It was, for one
|
| 556 |
+
# revision, so that a brand-new repo would have a head to name as a parent β and it broke
|
| 557 |
+
# three existing gates, because their fixtures replace `_upload` (which is where
|
| 558 |
+
# `create_repo` has always lived) and suddenly found themselves calling the real hub. The
|
| 559 |
+
# ordering works without it: a repo that does not exist resolves no head and no `exists`,
|
| 560 |
+
# so the first write goes out with `parent=None` and `_upload` creates the repo on its way
|
| 561 |
+
# through, exactly as before.
|
| 562 |
+
budget = _MAX_REBASE if max_rebase is None else int(max_rebase)
|
| 563 |
+
for attempt in range(budget + 1):
|
| 564 |
+
with self._lock:
|
| 565 |
+
parent = self._base.get(name)
|
| 566 |
+
if not parent:
|
| 567 |
+
parent = self._head_sha()
|
| 568 |
+
if not parent:
|
| 569 |
+
# A repo with no commits at all: `_upload` creates it on the way through, so this
|
| 570 |
+
# is the genuinely-first write and there is nothing that could be lost.
|
| 571 |
+
# β NO EM DASH IN THIS MESSAGE, OR THE ONE BELOW. Both are raised, and a raised
|
| 572 |
+
# store message reaches the client through the 503 handler, which puts them inside
|
| 573 |
+
# STANDING RULE 2's scope ("any Python string returned to the client"). `web_prose`
|
| 574 |
+
# caught exactly these two.
|
| 575 |
+
if self.exists(name):
|
| 576 |
+
raise StoreConflict(
|
| 577 |
+
f'cannot resolve a parent commit for {self.repo}:{name}, so this write '
|
| 578 |
+
f'cannot be made safe. Refusing to upload without a precondition: an '
|
| 579 |
+
f'unconditional write is what silently erases another session\'s work.')
|
| 580 |
+
parent = None
|
| 581 |
+
try:
|
| 582 |
+
oid = self._upload(name, data, parent)
|
| 583 |
+
except HfHubHTTPError as e:
|
| 584 |
+
if not _is_conflict(e):
|
| 585 |
+
raise # 401/404/429/500 β a different fault, never a rebase
|
| 586 |
+
if attempt >= budget:
|
| 587 |
+
# β THE EXHAUSTED CASE RAISES `StoreConflict`, NOT THE RAW 412, and this gate
|
| 588 |
+
# caught the first version doing the latter. A caller cannot be asked to know
|
| 589 |
+
# that one particular HTTP status out of the hub means "your change was not
|
| 590 |
+
# saved and nothing was damaged"; that is a domain fact and it needs a domain
|
| 591 |
+
# type. `from e` keeps the hub's own message in the traceback.
|
| 592 |
+
raise StoreConflict(
|
| 593 |
+
f'{self.repo}:{name} moved under this write {budget + 1} times in a '
|
| 594 |
+
f'row. Refusing to overwrite it. Nothing was saved.') from e
|
| 595 |
+
data = self._rebase(name, replay)
|
| 596 |
+
continue
|
| 597 |
+
with self._lock:
|
| 598 |
+
self._base[name] = oid
|
| 599 |
+
self._journal[name] = []
|
| 600 |
+
return data, oid
|
| 601 |
+
# Unreachable by construction β every iteration returns or raises. Kept so that an edit to
|
| 602 |
+
# the loop above cannot make this function fall out and return `None`, which callers would
|
| 603 |
+
# unpack into a crash two frames away from the cause.
|
| 604 |
+
raise StoreConflict(f'{self.repo}:{name}: the write loop exited without committing.')
|
| 605 |
+
|
| 606 |
+
def _journal_append(self, name, fn):
|
| 607 |
+
"""Record one intent and return the replay list. THE CALLER HOLDS THE CACHE LOCK.
|
| 608 |
+
|
| 609 |
+
β CAPPED, BECAUSE AN UNCONFIRMED WRITE STREAM IS AN UNBOUNDED LIST OF CLOSURES. In normal
|
| 610 |
+
operation the cap is unreachable β `_commit` empties this every few seconds β so it only
|
| 611 |
+
bites during a sustained hub outage, where the alternative is a process that grows until it
|
| 612 |
+
dies. When it bites, the OLDEST intents are dropped and it is reported: a rebase afterwards
|
| 613 |
+
replays the most recent `_MAX_JOURNAL` changes rather than all of them. Stated rather than
|
| 614 |
+
silently enforced, per the standing rule about limits that cannot be removed.
|
| 615 |
+
"""
|
| 616 |
+
j = self._journal.setdefault(name, [])
|
| 617 |
+
j.append(fn)
|
| 618 |
+
if len(j) > _MAX_JOURNAL:
|
| 619 |
+
dropped = len(j) - _MAX_JOURNAL
|
| 620 |
+
del j[:dropped]
|
| 621 |
+
try: # lazy import β core stays layer-clean
|
| 622 |
+
import harness.telemetry as _tel # noqa: PLC0415
|
| 623 |
+
_tel.error(f'store:journal_full:{name}', StoreConflict(
|
| 624 |
+
f'{self.repo}:{name} has {_MAX_JOURNAL}+ unconfirmed writes; dropped '
|
| 625 |
+
f'{dropped} oldest replay entr(ies). A rebase will re-apply only the most '
|
| 626 |
+
f'recent {_MAX_JOURNAL}.'))
|
| 627 |
+
except Exception: # noqa: BLE001
|
| 628 |
+
pass
|
| 629 |
+
return list(j)
|
| 630 |
+
|
| 631 |
+
def _rebase(self, name, replay):
|
| 632 |
+
"""Re-read the hub's newer document and re-apply our intent onto it. Caller holds the key
|
| 633 |
+
lock, so nothing else can be mid-write on this key while we do.
|
| 634 |
+
|
| 635 |
+
β THE CACHE IS REPLACED WITH THE REBASED RESULT, and forgetting that line would make the
|
| 636 |
+
whole mechanism single-shot: the next write would start from the same stale snapshot and
|
| 637 |
+
conflict again, burning a rebase per write forever. It also has a second, welcome effect β
|
| 638 |
+
this instance now HOLDS the other container's work, which is the only moment a process
|
| 639 |
+
whose cache is never re-read gets to learn that anything changed.
|
| 640 |
+
"""
|
| 641 |
+
fresh, sha = self._download(name)
|
| 642 |
+
for fn in list(replay):
|
| 643 |
+
out = fn(fresh)
|
| 644 |
+
fresh = out if out is not None else fresh
|
| 645 |
+
with self._lock:
|
| 646 |
+
self._cache[name] = json.loads(json.dumps(fresh))
|
| 647 |
+
self._base[name] = sha
|
| 648 |
+
try: # lazy import β core stays layer-clean
|
| 649 |
+
import harness.telemetry as _tel # noqa: PLC0415
|
| 650 |
+
_tel.error(f'store:rebase:{name}',
|
| 651 |
+
StoreConflict(f'{self.repo}:{name} moved; replayed {len(replay)} change(s)'))
|
| 652 |
+
except Exception: # noqa: BLE001
|
| 653 |
+
pass
|
| 654 |
+
return fresh
|
| 655 |
|
| 656 |
def upload_bytes(self, path_in_repo, data, message=None):
|
| 657 |
"""Persist RAW BYTES at an arbitrary path in the tenant dataset (wave-8 C5, documents).
|
| 658 |
Bytes are never cached in-process: large, cold, fetched on explicit user action."""
|
| 659 |
if not self.available():
|
| 660 |
raise RuntimeError('No HF_TOKEN configured β persistence is unavailable.')
|
| 661 |
+
# D-315: a blob is still this tenant's data. β No `parent_commit` here and that is correct,
|
| 662 |
+
# not an omission: a blob is written at its own path and read whole, so two writers cannot
|
| 663 |
+
# silently merge into one damaged document the way `{name}.json` can. The concurrency
|
| 664 |
+
# hazard D-305 describes is specific to the shared JSON blob.
|
| 665 |
+
data_binding.check_write(self.repo, f'write bytes {path_in_repo!r}')
|
| 666 |
with self._lock:
|
| 667 |
+
self._ensure_repo()
|
| 668 |
+
HfApi(token=_token()).upload_file(
|
| 669 |
+
path_or_fileobj=io.BytesIO(data), path_in_repo=path_in_repo,
|
| 670 |
+
repo_id=self.repo, repo_type='dataset',
|
| 671 |
+
commit_message=(message or f'add {path_in_repo}')
|
| 672 |
+
+ data_binding.local_commit_suffix())
|
|
|
|
| 673 |
|
| 674 |
def download_bytes(self, path_in_repo):
|
| 675 |
"""Raw bytes back, or None when absent/unreachable β a missing attachment degrades to
|
|
|
|
| 686 |
return None
|
| 687 |
|
| 688 |
def delete_path(self, path_in_repo):
|
| 689 |
+
"""Remove a stored file. Absent is SUCCESS β deleting what is already gone is the goal.
|
| 690 |
+
|
| 691 |
+
β THE REFUSAL IS RAISED, NOT SWALLOWED INTO THE `return False` BELOW, and the distinction
|
| 692 |
+
matters: `False` here means "the delete did not happen", which several callers treat as a
|
| 693 |
+
tolerable no-op. "You are not allowed to touch this store" is not a no-op β it is the
|
| 694 |
+
thing the operator has to be told.
|
| 695 |
+
"""
|
| 696 |
if not self.available():
|
| 697 |
return False
|
| 698 |
+
data_binding.check_write(self.repo, f'delete {path_in_repo!r}')
|
| 699 |
try:
|
| 700 |
+
HfApi(token=_token()).delete_file(
|
| 701 |
+
path_in_repo=path_in_repo, repo_id=self.repo, repo_type='dataset',
|
| 702 |
+
commit_message=f'delete {path_in_repo}' + data_binding.local_commit_suffix())
|
| 703 |
return True
|
| 704 |
except (EntryNotFoundError, RepositoryNotFoundError):
|
| 705 |
return True
|
|
|
|
| 707 |
return False
|
| 708 |
|
| 709 |
def put(self, name, data):
|
| 710 |
+
"""Persist {name}.json (creates the private repo on first write). Updates the cache.
|
| 711 |
+
|
| 712 |
+
β D-305 β `put` NOW TAKES THE KEY LOCK AND GOES THROUGH `_commit`, and both halves are
|
| 713 |
+
required. Without the precondition this method is the hole in the whole mechanism: seven
|
| 714 |
+
callers outside this file reach it (`users.py`, `modules/ar.py`, `modules/map.py`,
|
| 715 |
+
`runtime.py`, `store_backend.py`, `ops/seed_pg_from_hf.py`) and `users.json` is a document
|
| 716 |
+
every account shares, so an unguarded whole-file `put` clobbers exactly as `update` used to.
|
| 717 |
+
|
| 718 |
+
β THE CACHE LOCK NO LONGER SPANS THE NETWORK, which is a change to this method's
|
| 719 |
+
concurrency and is deliberate. The old body held `self._lock` β the lock every `get()`
|
| 720 |
+
takes β across the upload, so one `put` froze every reader for a round trip (D-181's
|
| 721 |
+
shape); with up to `_MAX_REBASE` extra round trips now possible that freeze would get
|
| 722 |
+
strictly worse. The per-key write lock gives the callers a STRONGER guarantee than they had
|
| 723 |
+
(two writers of one key can no longer interleave) while readers stop waiting. Lock order is
|
| 724 |
+
key-then-cache, as everywhere else in this class.
|
| 725 |
+
|
| 726 |
+
β REPLAY SEMANTICS FOR A WHOLE-DOCUMENT WRITE ARE LAST-WRITE-WINS, STATED RATHER THAN
|
| 727 |
+
IMPLIED. `put` means "the document is this now", so its journal entry replaces rather than
|
| 728 |
+
merges. What the precondition buys here is that the replacement is applied to a document we
|
| 729 |
+
have actually SEEN β and that any `update` queued behind it replays on top β instead of
|
| 730 |
+
being uploaded over an hour of unseen work.
|
| 731 |
+
"""
|
| 732 |
if not self.available():
|
| 733 |
raise RuntimeError('No HF_TOKEN configured β persistence is unavailable.')
|
| 734 |
+
data_binding.check_write(self.repo, f'put {name!r}')
|
| 735 |
+
with self._key_lock(name):
|
| 736 |
+
def _replace(_current):
|
| 737 |
+
return json.loads(json.dumps(data))
|
| 738 |
+
with self._lock:
|
| 739 |
+
replay = self._journal_append(name, _replace)
|
| 740 |
+
landed, _oid = self._commit(name, data, replay)
|
| 741 |
+
with self._lock:
|
| 742 |
+
self._cache[name] = json.loads(json.dumps(landed))
|
| 743 |
+
self._owned[name] = True
|
| 744 |
+
self._last_flush[name] = _time.monotonic()
|
| 745 |
+
self._dirty[name] = False
|
| 746 |
+
self._bump(name) # C6 β AFTER the upload: a raise here is not a write
|
| 747 |
+
return self._cache[name]
|
| 748 |
|
| 749 |
def _flush_worker(self, name):
|
| 750 |
"""Coalescing uploader for one key. Runs while dirty; retries with backoff on failure β
|
|
|
|
| 769 |
this must too; taking `self._lock` first on this path is the deadlock. Both sleeps stay
|
| 770 |
OUTSIDE the key lock β a worker that dozed while holding it would block every writer of
|
| 771 |
that key for `_FLUSH_MIN_GAP`, which is the freeze this ticket exists to remove.
|
| 772 |
+
|
| 773 |
+
ββ D-305 β THIS WORKER IS ALSO WHERE MOST CROSS-CONTAINER LOSS HAPPENED, because the
|
| 774 |
+
table workspace (views, fields, folders, overlays) is written `flush='async'`. It uploads a
|
| 775 |
+
SNAPSHOT of a cache that may be minutes old, so it takes the `replay` journal with it: on a
|
| 776 |
+
412 the snapshot is thrown away and the journalled `fn`s are re-applied to the hub's newer
|
| 777 |
+
document instead. The journal is cleared inside `_commit`, only on success.
|
| 778 |
"""
|
| 779 |
backoff = 2.0
|
| 780 |
while True:
|
| 781 |
_time.sleep(_FLUSH_DELAY)
|
| 782 |
+
wait, err, snapshot, replay = None, None, None, ()
|
| 783 |
with self._key_lock(name):
|
| 784 |
with self._lock:
|
| 785 |
gap = _time.monotonic() - self._last_flush.get(name, 0.0)
|
|
|
|
| 791 |
else:
|
| 792 |
self._dirty[name] = False
|
| 793 |
snapshot = json.loads(json.dumps(self._cache.get(name, {})))
|
| 794 |
+
# Snapshotted WITH the document and under the same lock: a journal that
|
| 795 |
+
# could drift from the snapshot it describes would replay the wrong set.
|
| 796 |
+
replay = list(self._journal.get(name) or ())
|
| 797 |
if wait is None:
|
| 798 |
try:
|
| 799 |
+
landed, _oid = self._commit(name, snapshot, replay)
|
| 800 |
with self._lock:
|
| 801 |
+
# A rebase rebuilt the document, so the cache must take the result β
|
| 802 |
+
# `_rebase` already wrote it, and this keeps the no-conflict path
|
| 803 |
+
# identical to it rather than leaving two ways for the cache to be set.
|
| 804 |
+
self._cache[name] = json.loads(json.dumps(landed))
|
| 805 |
self._last_flush[name] = _time.monotonic()
|
| 806 |
backoff = 2.0
|
| 807 |
except Exception as e: # noqa: BLE001
|
|
|
|
| 856 |
finish, so waiting for its key lock could only turn a partial save into no save at all.
|
| 857 |
Best-effort is the correct contract here, and it is the one case where taking the lock
|
| 858 |
would be worse than skipping it.
|
| 859 |
+
|
| 860 |
+
β D-305 β IT STILL GOES THROUGH `_commit`, so the last write of a dying process cannot be
|
| 861 |
+
the one that erases somebody. Exiting is not a licence to overwrite: if the branch has
|
| 862 |
+
moved, this rebases like any other write, and if it cannot, it gives up rather than
|
| 863 |
+
clobbering. `_commit`'s own `data_binding` check applies too, so a container that was never
|
| 864 |
+
allowed to write this store does not get one last unguarded upload on the way out.
|
| 865 |
"""
|
| 866 |
with self._lock:
|
| 867 |
dirty = [k for k, v in self._dirty.items() if v]
|
| 868 |
snaps = {k: json.loads(json.dumps(self._cache.get(k, {}))) for k in dirty}
|
| 869 |
+
replays = {k: list(self._journal.get(k) or ()) for k in dirty}
|
| 870 |
for k in dirty:
|
| 871 |
self._dirty[k] = False
|
| 872 |
for k, d in snaps.items():
|
| 873 |
try:
|
| 874 |
+
# β ONE REBASE, NOT `_MAX_REBASE`, and the docstring above is the argument: this
|
| 875 |
+
# runs at interpreter exit with the process going away. The full budget is up to
|
| 876 |
+
# four extra downloads and five upload attempts PER DIRTY KEY on a path that may be
|
| 877 |
+
# killed at any moment, which turns a best-effort save into a hang. One attempt
|
| 878 |
+
# keeps the safety this method exists for (a conflicting write still rebases rather
|
| 879 |
+
# than clobbering) at a cost the exit path can actually pay.
|
| 880 |
+
self._commit(k, d, replays.get(k, ()), max_rebase=1)
|
| 881 |
except Exception:
|
| 882 |
pass # exiting anyway β nothing left to reschedule
|
| 883 |
|
|
|
|
| 890 |
returns immediately; a coalescing worker commits. The strict read still guards the
|
| 891 |
FIRST async update of a key per process.
|
| 892 |
|
| 893 |
+
ββ D-305 β "LAST-WRITE-WINS IS THE CONTRACT" IS NO LONGER TRUE ACROSS PROCESSES, AND THE
|
| 894 |
+
SENTENCE BELOW USED TO SAY IT WITHOUT THE QUALIFIER. Two writers in ONE process cannot lose
|
| 895 |
+
an update β they share `self._cache`, which is why every gate in this repo passed over the
|
| 896 |
+
defect. Two writers in two CONTAINERS could, and did: measured on tenant #0's live store in
|
| 897 |
+
commit `dee7481a77`, where one session's write rolled the document back an hour and cost a
|
| 898 |
+
real user 3 views, 49 typed cell values and a field id. The commit now carries a
|
| 899 |
+
`parent_commit` precondition and rebases (`_commit`), so the contract is: **within a
|
| 900 |
+
process, last write wins; across processes, a write that would overwrite unseen work is
|
| 901 |
+
refused and re-applied.** A lost update is not the contract at either grain.
|
| 902 |
+
|
| 903 |
ββ W31-T13 (D-177(d)) β TWO LOCKS, AND THE SPLIT IS THE WHOLE TICKET.
|
| 904 |
`self._key_lock(name)` is held for the entire read-modify-write, so two writers of one key
|
| 905 |
+
still cannot interleave.
|
| 906 |
`self._lock` β the one every `get()` takes β is now held only for the microseconds a cache
|
| 907 |
read or write needs, never across a download or an upload. Before this, one sync write
|
| 908 |
froze every reader in the process for two network round trips, on a store whose warm
|
|
|
|
| 910 |
β Uploading outside `self._lock` is not a new posture: `_flush_worker` has done exactly
|
| 911 |
that since wave 7, and `_repo_ok` racing is benign because `create_repo` is `exist_ok=True`.
|
| 912 |
"""
|
| 913 |
+
# β D-315 β REFUSED AT THE ACCEPTANCE POINT, NOT AT THE UPLOAD. `_upload` carries the same
|
| 914 |
+
# check as a backstop, but refusing only there would let the async branch accept the
|
| 915 |
+
# mutation into the cache, answer 200, mark the key dirty, and hand the flush worker a
|
| 916 |
+
# write that can never succeed β which retries with backoff forever and reports the refusal
|
| 917 |
+
# to nobody. Refuse before anything is accepted, and the caller gets a 503 that tells the
|
| 918 |
+
# truth: no change was saved.
|
| 919 |
+
data_binding.check_write(self.repo, f'update {name!r}')
|
| 920 |
with self._key_lock(name):
|
| 921 |
return self._update_locked(name, fn, flush)
|
| 922 |
|
|
|
|
| 975 |
result = fn(data)
|
| 976 |
data = result if result is not None else data
|
| 977 |
|
| 978 |
+
# ββ D-305 β THE INTENT IS RECORDED, NOT JUST THE RESULT, and this one line is what makes
|
| 979 |
+
# a conflict survivable. `data` is our answer over OUR base; `fn` is what we MEANT, and
|
| 980 |
+
# only the intent can be re-applied to somebody else's newer document. The journal holds
|
| 981 |
+
# every `fn` since the last confirmed upload β which for an async key is a whole flush
|
| 982 |
+
# window of edits, not one β and `_commit` clears it only when the hub has accepted them.
|
| 983 |
+
# β Appended AFTER `fn` ran: a `fn` that raised changed nothing and must not be replayed.
|
| 984 |
+
with self._lock:
|
| 985 |
+
replay = self._journal_append(name, fn)
|
| 986 |
+
|
| 987 |
if flush == 'async':
|
| 988 |
if not self.available():
|
| 989 |
raise RuntimeError('No HF_TOKEN configured β persistence is unavailable.')
|
|
|
|
| 994 |
self._schedule_flush(name)
|
| 995 |
return data
|
| 996 |
|
| 997 |
+
# οΏ½οΏ½οΏ½ THE SYNC COMMIT. It used to be spelled out here rather than calling `put()`, because
|
| 998 |
+
# `put()` held `self._lock` across its own upload β the freeze W31-T13 removed β and is
|
| 999 |
+
# PUBLIC with seven callers outside this file whose concurrency semantics changing it would
|
| 1000 |
+
# alter. D-305 made that duplication untenable: an unguarded whole-file write is the hole
|
| 1001 |
+
# the precondition exists to close, so BOTH now go through `_commit`, which is the single
|
| 1002 |
+
# place that resolves a parent, rebases and clears the journal. `put` still keeps its own
|
| 1003 |
+
# body (its op REPLACES rather than merges), but neither can upload unconditionally.
|
| 1004 |
if not self.available():
|
| 1005 |
raise RuntimeError('No HF_TOKEN configured β persistence is unavailable.')
|
| 1006 |
+
landed, _oid = self._commit(name, data, replay) # network, no cache lock held
|
| 1007 |
with self._lock:
|
| 1008 |
+
# β `landed`, NOT `data`. A rebase rebuilt the document from the hub's newer copy, so
|
| 1009 |
+
# caching what we TRIED to write would leave the cache diverged from what is stored β
|
| 1010 |
+
# and the next write would rebase off that divergence forever.
|
| 1011 |
+
self._cache[name] = json.loads(json.dumps(landed))
|
| 1012 |
self._owned[name] = True
|
| 1013 |
self._last_flush[name] = _time.monotonic()
|
| 1014 |
+
# β AFTER THE UPLOAD, NEVER BEFORE β `put()`'s own law. `_commit` raises on failure,
|
| 1015 |
# and a bump on that path would have `revision()` report a change that never landed.
|
| 1016 |
self._bump(name)
|
| 1017 |
# The upload above CARRIED whatever was pending, so the key is no longer ahead of
|
|
|
|
| 1020 |
# β AFTER the upload, for the same reason: on a raise the mark MUST survive (the cache
|
| 1021 |
# is still the truth and the row must still be committed by the worker). Clearing it
|
| 1022 |
# first would turn a transient upload error into the very silent loss the branch above
|
| 1023 |
+
# exists to stop β which is why it sits here and not before the commit.
|
| 1024 |
self._dirty[name] = False
|
| 1025 |
+
return landed
|
| 1026 |
|
| 1027 |
|
| 1028 |
# ------------------------------------------------------------------- instances + module API
|
platform/core/user_tables.py
CHANGED
|
@@ -336,7 +336,7 @@ def limit_report(table_key, st=None):
|
|
| 336 |
'cause': f'this database is EDITABLE, so its rows live in the shared `{STORE_KEY}` '
|
| 337 |
f'document that every request copies; at the widest shipped row (0.318 KB) '
|
| 338 |
f'{cap:,} rows is 19.1 MB against a 32 MB per-table budget',
|
| 339 |
-
'recommendation': 'connect it to a source instead
|
| 340 |
'read-through from the mirror and is not bounded (R6); for typed data '
|
| 341 |
'the increment is D-87, a per-table row key, not a bigger number',
|
| 342 |
}
|
|
@@ -439,9 +439,15 @@ def records_mutable(table_key, st=None):
|
|
| 439 |
#: waves because `verify_fields_contract` diffed the client's offer against the ODOO grid's
|
| 440 |
#: acceptance and never against this set. Wave-27 item 13 adds that derived leg, which is what
|
| 441 |
#: found it (measured, not reviewed: `_clean_field({'type':'image'})` returned None).
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 442 |
UT_FIELD_TYPES = {'text', 'select', 'multiselect', 'user', 'int', 'currency', 'pct', 'date',
|
| 443 |
'checkbox', 'phone', 'email', 'url', 'rating', 'automation', 'json',
|
| 444 |
-
'link', 'rollup', 'code', 'image', 'formula'}
|
| 445 |
#: A cell is still a scalar on the wire (`Row` values are strings/numbers) β what this bounds is
|
| 446 |
#: the DOCUMENT inside it. Source data is one already-paid provider response; keep it whole so a
|
| 447 |
#: provider field is never silently discarded merely because the response is rich. 32 MiB matches
|
|
@@ -902,6 +908,19 @@ def clean_fields(raw):
|
|
| 902 |
entry = None
|
| 903 |
elif fx is not None:
|
| 904 |
entry['formula'] = fx
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 905 |
if entry is None:
|
| 906 |
seen.discard(key)
|
| 907 |
continue
|
|
@@ -949,13 +968,26 @@ def all_defs(st=None):
|
|
| 949 |
fake store installed by a gate, a `_Lent` handle serving a document somebody else read). The
|
| 950 |
fallback is CORRECT-but-slow by construction β it can only ever return MORE than was asked for
|
| 951 |
β which is the one direction a fallback here is allowed to be wrong in.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 952 |
"""
|
| 953 |
try:
|
| 954 |
return dict(_st(st).get_projection(STORE_KEY, drop=DEF_ONLY_DROPS) or {})
|
| 955 |
-
except AttributeError:
|
| 956 |
-
return all_tables(st)
|
| 957 |
except Exception:
|
| 958 |
-
|
|
|
|
|
|
|
|
|
|
| 959 |
|
| 960 |
|
| 961 |
def get(table_key, st=None):
|
|
@@ -1651,6 +1683,308 @@ def _clean_rollup(raw):
|
|
| 1651 |
return out
|
| 1652 |
|
| 1653 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1654 |
def _clean_field(raw, previous=None):
|
| 1655 |
"""One field dict β the stored shape, or None. The single validator for create AND patch, so
|
| 1656 |
a column cannot be typed one way on the way in and another on the way back."""
|
|
@@ -1886,6 +2220,28 @@ def _clean_field(raw, previous=None):
|
|
| 1886 |
out['formula'] = fx
|
| 1887 |
elif ftype == 'formula':
|
| 1888 |
return None
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1889 |
return out
|
| 1890 |
|
| 1891 |
|
|
@@ -2081,6 +2437,16 @@ def flow_bound(bag, st=None):
|
|
| 2081 |
lives in `aios_grid._clean_automation` β this guards the WRITE doors only.)"""
|
| 2082 |
if not isinstance(bag, dict):
|
| 2083 |
return True # no bag, no law β an ordinary column
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2084 |
flow = str(bag.get('flowId') or '').strip()
|
| 2085 |
if not flow:
|
| 2086 |
return False
|
|
@@ -2386,6 +2752,41 @@ def patch_cells(table_key, row_id, values, st=None):
|
|
| 2386 |
return True
|
| 2387 |
|
| 2388 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2389 |
def patch_link_cell(table_key, row_id, fkey, value, st=None):
|
| 2390 |
"""Persist one user-picked Link cell in the shared row and return its canonical id string.
|
| 2391 |
|
|
@@ -2647,6 +3048,28 @@ def lend(st=None, **docs):
|
|
| 2647 |
return _Lent(_st(st), {k: v for k, v in docs.items() if v is not None})
|
| 2648 |
|
| 2649 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2650 |
def nav_entries(viewer=None, is_admin=False, st=None):
|
| 2651 |
"""Registry-SHAPED dicts so the nav can render user tables beside real modules with no
|
| 2652 |
special-casing: the same keys the flat nav reads (`key`, `label`, `source`).
|
|
|
|
| 336 |
'cause': f'this database is EDITABLE, so its rows live in the shared `{STORE_KEY}` '
|
| 337 |
f'document that every request copies; at the widest shipped row (0.318 KB) '
|
| 338 |
f'{cap:,} rows is 19.1 MB against a 32 MB per-table budget',
|
| 339 |
+
'recommendation': 'connect it to a source instead. Connected data is served '
|
| 340 |
'read-through from the mirror and is not bounded (R6); for typed data '
|
| 341 |
'the increment is D-87, a per-table row key, not a bigger number',
|
| 342 |
}
|
|
|
|
| 439 |
#: waves because `verify_fields_contract` diffed the client's offer against the ODOO grid's
|
| 440 |
#: acceptance and never against this set. Wave-27 item 13 adds that derived leg, which is what
|
| 441 |
#: found it (measured, not reviewed: `_clean_field({'type':'image'})` returned None).
|
| 442 |
+
#: β WAVE-34 (owner ruling R13) β `ai_enrich` JOINS, and it lands HERE FIRST rather than last.
|
| 443 |
+
#: The block above records that `image` reached four of the five surfaces and missed this one, so
|
| 444 |
+
#: the client offered a column the server deleted on the next read. `ai_enrich` is added to this
|
| 445 |
+
#: set in `W34-T51` (server) while the CLIENT half waits for `W34-T53`, which is the safe order:
|
| 446 |
+
#: a kind the server accepts and the client does not offer is invisible, whereas a kind the client
|
| 447 |
+
#: offers and the server refuses is a column created, named, configured and gone.
|
| 448 |
UT_FIELD_TYPES = {'text', 'select', 'multiselect', 'user', 'int', 'currency', 'pct', 'date',
|
| 449 |
'checkbox', 'phone', 'email', 'url', 'rating', 'automation', 'json',
|
| 450 |
+
'link', 'rollup', 'code', 'image', 'formula', 'ai_enrich'}
|
| 451 |
#: A cell is still a scalar on the wire (`Row` values are strings/numbers) β what this bounds is
|
| 452 |
#: the DOCUMENT inside it. Source data is one already-paid provider response; keep it whole so a
|
| 453 |
#: provider field is never silently discarded merely because the response is rich. 32 MiB matches
|
|
|
|
| 908 |
entry = None
|
| 909 |
elif fx is not None:
|
| 910 |
entry['formula'] = fx
|
| 911 |
+
# ββ WAVE-34 (R13) β the AI ENRICHMENT bag rides THIS door too, and it is the SIXTH time
|
| 912 |
+
# this seam has been fixed after the fact (`pinned`, `code`, `link`/`rollup`, `formula`,
|
| 913 |
+
# `agg`). It is written in the same change as `_clean_field`'s arm rather than a wave
|
| 914 |
+
# later, which is the only difference between this entry and the five above it.
|
| 915 |
+
if entry is not None:
|
| 916 |
+
ae = (_clean_ai_enrich(f.get('aiEnrich'))
|
| 917 |
+
if f.get('aiEnrich') is not None else None)
|
| 918 |
+
if (ftype == 'ai_enrich') != (ae is not None):
|
| 919 |
+
entry = None
|
| 920 |
+
elif ae is not None:
|
| 921 |
+
entry['aiEnrich'] = ae
|
| 922 |
+
# C3: derived, never typed beside the config. Same call as the other door.
|
| 923 |
+
entry['automation'] = _field_agent_binding(entry)
|
| 924 |
if entry is None:
|
| 925 |
seen.discard(key)
|
| 926 |
continue
|
|
|
|
| 968 |
fake store installed by a gate, a `_Lent` handle serving a document somebody else read). The
|
| 969 |
fallback is CORRECT-but-slow by construction β it can only ever return MORE than was asked for
|
| 970 |
β which is the one direction a fallback here is allowed to be wrong in.
|
| 971 |
+
|
| 972 |
+
ββ W33-T01 (D-213) β **THAT PARAGRAPH WAS FALSE ON THIS FUNCTION'S OWN BODY UNTIL 2026-08-14,
|
| 973 |
+
AND THE LIE WAS THE DANGEROUS DIRECTION.** Only `AttributeError` fell back; every other
|
| 974 |
+
exception returned `{}` β the exact silent-empty answer the paragraph ABOVE it forbids, three
|
| 975 |
+
lines earlier, in bold. `/nav`, `/nav/prefs` and `routes_shares` would have rendered ZERO
|
| 976 |
+
databases and looked entirely correct doing it ([[empty-answer-vs-unfinished-answer]]).
|
| 977 |
+
Nothing had noticed because the projection does not fail on a healthy store β a fallback is
|
| 978 |
+
dead code until the day it is the only code running. **Every failure now falls back to the
|
| 979 |
+
whole read**, which keeps `all_tables`' own `except: return {}` as the single backstop instead
|
| 980 |
+
of two competing ones ([[one-question-two-normalizers]]). This ticket puts the table WALL on
|
| 981 |
+
this function, so an empty answer here stops being a blank nav and becomes a 404 on every
|
| 982 |
+
database in the tenant.
|
| 983 |
"""
|
| 984 |
try:
|
| 985 |
return dict(_st(st).get_projection(STORE_KEY, drop=DEF_ONLY_DROPS) or {})
|
|
|
|
|
|
|
| 986 |
except Exception:
|
| 987 |
+
# β `AttributeError` (a store too old to project) is not special-cased any more β it was
|
| 988 |
+
# only ever ONE of the ways this can fail, and singling it out is what made the other ways
|
| 989 |
+
# silent. `all_tables` is correct for all of them.
|
| 990 |
+
return all_tables(st)
|
| 991 |
|
| 992 |
|
| 993 |
def get(table_key, st=None):
|
|
|
|
| 1683 |
return out
|
| 1684 |
|
| 1685 |
|
| 1686 |
+
# ---------------------------------------------------------------------------------------------
|
| 1687 |
+
# THE AI ENRICHMENT COLUMN (wave 34, owner ruling R13)
|
| 1688 |
+
# ---------------------------------------------------------------------------------------------
|
| 1689 |
+
# R13: *"a field kind called AI enrichment: a prompt per row that populates text. Detailed
|
| 1690 |
+
# configuration in the field's own config, including a token-usage limit."*
|
| 1691 |
+
#
|
| 1692 |
+
# β POSTURE: `link`/`rollup`/`formula`'s, NOT `code`'s. The bag DEFINES the column β a prompt is
|
| 1693 |
+
# the only thing that can ever produce a value here β so the type/bag pairing is enforced BOTH
|
| 1694 |
+
# WAYS and either half alone refuses the field. An `ai_enrich` column with no prompt is a column
|
| 1695 |
+
# that renders, sorts, filters and can never hold anything, which is the silent kind of broken
|
| 1696 |
+
# every other bag on this door is paired to prevent.
|
| 1697 |
+
#
|
| 1698 |
+
# β AND THE VALUE IS STORED, NOT COMPUTED. `formula` is client-recomputed on every paint and
|
| 1699 |
+
# `rollup` is read-through; neither persists. An enrichment that vanished on reload would not be
|
| 1700 |
+
# the feature (PRD assumption A6), so an `ai_enrich` cell is an ordinary stored string, a human
|
| 1701 |
+
# may type over it, and it is deliberately NOT in `is_computed_cell`.
|
| 1702 |
+
|
| 1703 |
+
#: The bag's own key set, read by BOTH the cleaner and the reporter below so they cannot disagree
|
| 1704 |
+
#: about what "unknown" means. β ONE constant, because T51's contract is that an unknown key is
|
| 1705 |
+
#: DROPPED **and NAMED** β two hand-maintained lists would eventually drop a key the report did
|
| 1706 |
+
#: not mention, which reads to a user as the config silently not saving.
|
| 1707 |
+
AI_ENRICH_KEYS = ('prompt', 'model', 'maxTokens', 'trigger', 'overwrite')
|
| 1708 |
+
#: When the column runs. `manual` = only when a person asks; `on_change` = when a referenced cell
|
| 1709 |
+
#: moves; `schedule` = on a cadence. The community ask R13 cites ("enrichment on a schedule") is
|
| 1710 |
+
#: the third of these, so it is in the vocabulary from the start rather than added later.
|
| 1711 |
+
AI_ENRICH_TRIGGER_MODES = ('manual', 'on_change', 'schedule')
|
| 1712 |
+
#: What an AUTOMATIC run may replace. β A HUMAN-EDITED CELL IS NEVER OVERWRITTEN AND THAT IS NOT
|
| 1713 |
+
#: IN THIS VOCABULARY β it is a law (`ai_enrich_may_write`), not a policy, so no configuration can
|
| 1714 |
+
#: turn it off. These three decide only what happens to cells the AGENT itself wrote.
|
| 1715 |
+
AI_ENRICH_OVERWRITE = ('blank', 'stale', 'always')
|
| 1716 |
+
#: Bounded because the ceiling is the feature (R13). The floor is one useful sentence; the roof is
|
| 1717 |
+
#: what one cell can cost before the run has to say so out loud.
|
| 1718 |
+
AI_ENRICH_MIN_TOKENS, AI_ENRICH_MAX_TOKENS = 16, 4000
|
| 1719 |
+
AI_ENRICH_DEFAULT_TOKENS = 300
|
| 1720 |
+
#: A prompt is a template, not an essay. Long enough for real instructions plus a few `{field}`
|
| 1721 |
+
#: tokens, short enough that the per-cell input cost is predictable.
|
| 1722 |
+
AI_ENRICH_PROMPT_MAX = 2000
|
| 1723 |
+
#: `cron` is stored as an opaque bounded string. β It is NOT parsed here on purpose: this module
|
| 1724 |
+
#: owns the field contract, and the scheduler that reads it owns the cadence vocabulary. Parsing
|
| 1725 |
+
#: it in two places is how one door starts refusing a cadence the other accepts.
|
| 1726 |
+
AI_ENRICH_CRON_MAX = 120
|
| 1727 |
+
|
| 1728 |
+
|
| 1729 |
+
def _clean_ai_enrich(raw):
|
| 1730 |
+
"""The `ai_enrich` config bag β the stored shape, or None if the column cannot run.
|
| 1731 |
+
|
| 1732 |
+
β Every key is normalised to a canonical form, so a definition saved and re-read is
|
| 1733 |
+
byte-identical (`_clean_ai_enrich(_clean_ai_enrich(x)) == _clean_ai_enrich(x)`). That
|
| 1734 |
+
idempotence is what makes the round-trip clause testable rather than a claim.
|
| 1735 |
+
"""
|
| 1736 |
+
if not isinstance(raw, dict):
|
| 1737 |
+
return None
|
| 1738 |
+
prompt = str(raw.get('prompt') or '').strip()[:AI_ENRICH_PROMPT_MAX]
|
| 1739 |
+
if not prompt:
|
| 1740 |
+
return None # the prompt IS the column; see the posture note above
|
| 1741 |
+
out = {'prompt': prompt}
|
| 1742 |
+
# The model is OPTIONAL and an unknown name is DROPPED rather than refused: it selects a
|
| 1743 |
+
# PROVIDER for a column that already knows what to ask, so a stale name should fall back to
|
| 1744 |
+
# the ladder's own order, never destroy the column. (`code`'s language argument, same shape.)
|
| 1745 |
+
model = str(raw.get('model') or '').strip().lower()[:60]
|
| 1746 |
+
if model:
|
| 1747 |
+
out['model'] = model
|
| 1748 |
+
tokens = raw.get('maxTokens')
|
| 1749 |
+
# `bool` is an `int` subclass β `True` would otherwise validate as a 1-token ceiling.
|
| 1750 |
+
if isinstance(tokens, bool) or not isinstance(tokens, (int, float)):
|
| 1751 |
+
tokens = AI_ENRICH_DEFAULT_TOKENS
|
| 1752 |
+
out['maxTokens'] = max(AI_ENRICH_MIN_TOKENS, min(int(tokens), AI_ENRICH_MAX_TOKENS))
|
| 1753 |
+
trig = raw.get('trigger') if isinstance(raw.get('trigger'), dict) else {}
|
| 1754 |
+
mode = str(trig.get('mode') or '').strip().lower()
|
| 1755 |
+
trigger = {'mode': mode if mode in AI_ENRICH_TRIGGER_MODES else 'manual'}
|
| 1756 |
+
# β `cron` is kept ONLY on a scheduled column. A cadence stored under `manual` is a setting
|
| 1757 |
+
# the user can see and nothing will ever read β the shape D-246 wears on the Odoo sync, where
|
| 1758 |
+
# a `manual` preset does nothing because no branch reads it.
|
| 1759 |
+
cron = str(trig.get('cron') or '').strip()[:AI_ENRICH_CRON_MAX]
|
| 1760 |
+
if trigger['mode'] == 'schedule' and cron:
|
| 1761 |
+
trigger['cron'] = cron
|
| 1762 |
+
out['trigger'] = trigger
|
| 1763 |
+
overwrite = str(raw.get('overwrite') or '').strip().lower()
|
| 1764 |
+
out['overwrite'] = overwrite if overwrite in AI_ENRICH_OVERWRITE else 'blank'
|
| 1765 |
+
return out
|
| 1766 |
+
|
| 1767 |
+
|
| 1768 |
+
def ai_enrich_dropped_keys(raw):
|
| 1769 |
+
"""The config keys `_clean_ai_enrich` will NOT keep, sorted β the NAMING half of T51's
|
| 1770 |
+
"an unknown config key is DROPPED and NAMED, never silently eaten".
|
| 1771 |
+
|
| 1772 |
+
β IT EXISTS BECAUSE EVERY OTHER BAG CLEANER IN THIS FILE HAS NO ERROR CHANNEL. `_clean_link`,
|
| 1773 |
+
`_clean_rollup`, `_clean_profile` and `_clean_format` all return `dict | None` and drop
|
| 1774 |
+
unknown keys in silence β `verify_fields_contract` even asserts that they do. Copying one of
|
| 1775 |
+
them as a template gets the DROP right and the NAMING wrong by construction, so the report is
|
| 1776 |
+
a separate function reading the SAME `AI_ENRICH_KEYS` constant rather than a second list.
|
| 1777 |
+
|
| 1778 |
+
β It reports UNKNOWN keys only. A known key whose VALUE was normalised (an out-of-range
|
| 1779 |
+
ceiling clamped, an unknown model dropped) is not a surprise worth a sentence β the stored
|
| 1780 |
+
definition comes straight back to the editor, so the user sees the accepted value itself.
|
| 1781 |
+
"""
|
| 1782 |
+
if not isinstance(raw, dict):
|
| 1783 |
+
return []
|
| 1784 |
+
return sorted(str(k) for k in raw if k not in AI_ENRICH_KEYS)
|
| 1785 |
+
|
| 1786 |
+
|
| 1787 |
+
def ai_enrich_fields(defn):
|
| 1788 |
+
"""Every `ai_enrich` column in this table definition, in declaration order.
|
| 1789 |
+
|
| 1790 |
+
One reader for "which columns are field agents", so the Agents module (contract C3), the
|
| 1791 |
+
runner and the scheduler cannot disagree about the set ([[one-evaluator-per-question]]).
|
| 1792 |
+
"""
|
| 1793 |
+
return [f for f in ((defn or {}).get('fields') or [])
|
| 1794 |
+
if isinstance(f, dict) and f.get('type') == 'ai_enrich'
|
| 1795 |
+
and isinstance(f.get('aiEnrich'), dict)]
|
| 1796 |
+
|
| 1797 |
+
|
| 1798 |
+
def _field_agent_binding(field):
|
| 1799 |
+
"""Contract C3's `field.automation` bag, DERIVED from the column rather than typed beside it.
|
| 1800 |
+
|
| 1801 |
+
ββ THIS IS DERIVED ON PURPOSE AND IT IS THE ONE DESIGN CALL IN T51 WORTH ARGUING WITH.
|
| 1802 |
+
C3 as drafted has F *store* `{kind, table, field, trigger}` β but `field` is already
|
| 1803 |
+
`field['key']` and `trigger` is already `aiEnrich['trigger']`, so two of its four keys would
|
| 1804 |
+
be a second copy of a fact this same dict already carries. Two copies of one fact is
|
| 1805 |
+
[[one-question-two-normalizers]] with a guaranteed drift date: the first PATCH that changes
|
| 1806 |
+
the trigger through the enrichment editor and not through the automation editor.
|
| 1807 |
+
Computing it inside the SINGLE validator both write doors run means they cannot diverge.
|
| 1808 |
+
|
| 1809 |
+
β `table` IS ABSENT, and that is the deviation E must know about: this function is handed one
|
| 1810 |
+
field dict and no table context, while `_clean_field(f) == f` is asserted by two gates over
|
| 1811 |
+
engine-seeded field lists β stamping the table key from a caller that happens to know it would
|
| 1812 |
+
make a stored field unequal to its own validator's output. E iterates tables to build the
|
| 1813 |
+
synthetic rows, so E already holds the key that would go here.
|
| 1814 |
+
"""
|
| 1815 |
+
bag = (field or {}).get('aiEnrich')
|
| 1816 |
+
if not isinstance(bag, dict):
|
| 1817 |
+
return None
|
| 1818 |
+
return {'kind': 'field_agent', 'field': str((field or {}).get('key') or ''),
|
| 1819 |
+
'trigger': dict(bag.get('trigger') or {'mode': 'manual'})}
|
| 1820 |
+
|
| 1821 |
+
|
| 1822 |
+
# ---------------------------------------------------------------------------------------------
|
| 1823 |
+
# PER-CELL PROVENANCE (wave 34, W34-T51 β "stamp it FROM DAY ONE")
|
| 1824 |
+
# ---------------------------------------------------------------------------------------------
|
| 1825 |
+
# ββ IT CANNOT LIVE IN THE ROW, AND THAT IS MEASURED RATHER THAN ASSUMED. `add_row` builds its
|
| 1826 |
+
# row as `{k: str(v) for k, v in values.items() if k in valid}` where `valid` is the declared
|
| 1827 |
+
# field keys β a row dict is field-keys-only by construction, so a reserved `__ai__` key inside
|
| 1828 |
+
# one would be stripped on the way in. Widening that filter to admit a private key would weaken
|
| 1829 |
+
# the wall that stops a client inventing columns. So provenance is a SIBLING STRATUM of `rows`,
|
| 1830 |
+
# exactly as `fields` and `rows` are siblings today.
|
| 1831 |
+
#
|
| 1832 |
+
# β AND `stale` IS DERIVED, NEVER STORED. A stored `stale` flag needs a sweep to stay true, and a
|
| 1833 |
+
# sweep nobody runs is [[flag-shipped-without-its-writer]]. What IS stored is the INPUT HASH the
|
| 1834 |
+
# value was produced from; `ai_enrich_is_stale` compares it to today's inputs, so staleness is a
|
| 1835 |
+
# question asked at read time and can never be out of date.
|
| 1836 |
+
|
| 1837 |
+
#: The stratum's key inside a table document, beside `fields` and `rows`.
|
| 1838 |
+
AI_ENRICH_MARK_KEY = 'aiEnrich'
|
| 1839 |
+
#: What a mark can say. β `stale` is absent ON PURPOSE (see above) and so is `generating`: an
|
| 1840 |
+
#: in-flight run is a fact about a REQUEST, not about stored data, and persisting it would leave
|
| 1841 |
+
#: a cell stuck on "generating" forever the first time a process dies mid-run.
|
| 1842 |
+
AI_ENRICH_STATES = ('agent', 'human', 'error')
|
| 1843 |
+
#: A bound on the stratum, in the shape `row_limit` uses: this document is copied whole on every
|
| 1844 |
+
#: read, so a mark set that can outgrow the rows it describes is a store problem wearing a
|
| 1845 |
+
#: feature's name. One mark per (row, column) is the natural size; the cap is the guard against a
|
| 1846 |
+
#: column deleted without its marks.
|
| 1847 |
+
AI_ENRICH_MAX_MARKS = MAX_ROWS
|
| 1848 |
+
#
|
| 1849 |
+
# β THERE IS DELIBERATELY NO `drop_marks(column)`, AND THE ABSENCE IS THE DECISION. `delete_field`
|
| 1850 |
+
# leaves a deleted column's CELLS in the rows on purpose β an accidental delete stays recoverable,
|
| 1851 |
+
# and re-adding the column under the same key brings the values back. Marks must follow the same
|
| 1852 |
+
# rule or a restored column's agent-written values would come back looking human-authored, which
|
| 1853 |
+
# is the one distinction this whole stratum exists to make. A table that is deleted takes its
|
| 1854 |
+
# document (and therefore its marks) with it, so neither lifecycle leaks.
|
| 1855 |
+
|
| 1856 |
+
|
| 1857 |
+
def ai_enrich_input_hash(prompt, row, refs):
|
| 1858 |
+
"""The fingerprint a stored value was produced FROM: the prompt plus the referenced cells.
|
| 1859 |
+
|
| 1860 |
+
β `refs` is passed in rather than re-parsed here, so the token vocabulary is owned by one
|
| 1861 |
+
module (`api/ai_enrich.py::prompt_refs`) instead of two. A hash built from a second parse
|
| 1862 |
+
would disagree with the runner's the first time the token syntax gains a form.
|
| 1863 |
+
"""
|
| 1864 |
+
payload = [str(prompt or '')]
|
| 1865 |
+
for key in sorted(str(r) for r in (refs or ())):
|
| 1866 |
+
payload.append(f'{key}={(row or {}).get(key, "")}')
|
| 1867 |
+
return hashlib.sha256('\x1f'.join(payload).encode('utf-8')).hexdigest()[:32]
|
| 1868 |
+
|
| 1869 |
+
|
| 1870 |
+
def ai_enrich_marks(table_key, col_id, st=None):
|
| 1871 |
+
"""`{row_id: mark}` for ONE column. Absent = a cell nobody has written yet."""
|
| 1872 |
+
stratum = (get(table_key, st) or {}).get(AI_ENRICH_MARK_KEY) or {}
|
| 1873 |
+
got = stratum.get(str(col_id))
|
| 1874 |
+
return dict(got) if isinstance(got, dict) else {}
|
| 1875 |
+
|
| 1876 |
+
|
| 1877 |
+
def ai_enrich_is_stale(mark, fresh_hash):
|
| 1878 |
+
"""Was this value produced from inputs that have since changed?
|
| 1879 |
+
|
| 1880 |
+
A human edit is never stale β a person's own words do not go out of date because a
|
| 1881 |
+
neighbouring cell moved. Only an agent-written value can be.
|
| 1882 |
+
"""
|
| 1883 |
+
if not isinstance(mark, dict) or mark.get('state') != 'agent':
|
| 1884 |
+
return False
|
| 1885 |
+
return bool(fresh_hash) and str(mark.get('hash') or '') != str(fresh_hash)
|
| 1886 |
+
|
| 1887 |
+
|
| 1888 |
+
def ai_enrich_human_authored(mark, has_value=False):
|
| 1889 |
+
"""Did somebody other than the agent put this value here?
|
| 1890 |
+
|
| 1891 |
+
β TWO CASES, AND THE SECOND IS THE ONE THAT GETS MISSED. An explicit `human` mark is obvious.
|
| 1892 |
+
The other is a cell that holds a value with NO mark at all: a value typed, pasted or imported
|
| 1893 |
+
before the column became an enrichment column. The agent did not write it, so the agent does
|
| 1894 |
+
not own it. Without this arm, `overwrite: 'always'` would eat exactly the pre-existing work
|
| 1895 |
+
R8's *"we are helping the team put their work into the system"* is about.
|
| 1896 |
+
|
| 1897 |
+
β ONE PREDICATE, because `ai_enrich_may_write` and `api/ai_enrich.py::cell_state` both answer
|
| 1898 |
+
"is this the human's?" and a cell the UI labels human-written while the runner overwrites it
|
| 1899 |
+
is the worst of both ([[one-question-two-normalizers]]).
|
| 1900 |
+
"""
|
| 1901 |
+
if isinstance(mark, dict) and mark.get('state') == 'human':
|
| 1902 |
+
return True
|
| 1903 |
+
return bool(has_value) and not (isinstance(mark, dict) and mark.get('state') == 'agent')
|
| 1904 |
+
|
| 1905 |
+
|
| 1906 |
+
def ai_enrich_may_write(mark, policy, fresh_hash, has_value=False):
|
| 1907 |
+
"""May an AUTOMATIC run write this cell? The law, in one place.
|
| 1908 |
+
|
| 1909 |
+
β THE FIRST CLAUSE IS NOT CONFIGURABLE. A cell a person typed into is never overwritten by an
|
| 1910 |
+
agent, whatever `overwrite` says β that is why `human` is not one of the `AI_ENRICH_OVERWRITE`
|
| 1911 |
+
values, and why `always` means "always refresh what the AGENT owns" rather than "overwrite
|
| 1912 |
+
everything". A policy that could turn it off would make the column unsafe to hand to a team.
|
| 1913 |
+
β A MANUAL, per-cell run is a different act with a different door; this predicate governs the
|
| 1914 |
+
automatic paths (`on_change`, `schedule`, and a bulk "all rows" sweep).
|
| 1915 |
+
"""
|
| 1916 |
+
if ai_enrich_human_authored(mark, has_value):
|
| 1917 |
+
return False
|
| 1918 |
+
if not has_value:
|
| 1919 |
+
return True # a blank cell is fillable under every policy
|
| 1920 |
+
if policy == 'always':
|
| 1921 |
+
return True
|
| 1922 |
+
if policy == 'stale':
|
| 1923 |
+
return ai_enrich_is_stale(mark, fresh_hash)
|
| 1924 |
+
return False # 'blank': an agent never replaces a value it wrote
|
| 1925 |
+
|
| 1926 |
+
|
| 1927 |
+
def stamp_ai_enrich(table_key, col_id, marks, st=None):
|
| 1928 |
+
"""Write MANY marks for one column in ONE store update. Returns the number stored.
|
| 1929 |
+
|
| 1930 |
+
β BULK BY CONSTRUCTION, and the signature is what enforces it. Every write here is a
|
| 1931 |
+
read-modify-write of the whole tenant document, so a per-row stamp inside a run loop is the
|
| 1932 |
+
same shape as the 2,000-full-document-copies problem `add_rows` exists to avoid. There is
|
| 1933 |
+
deliberately no `stamp_one`.
|
| 1934 |
+
"""
|
| 1935 |
+
col_id = str(col_id)
|
| 1936 |
+
clean = {}
|
| 1937 |
+
for row_id, mark in (marks or {}).items():
|
| 1938 |
+
if not isinstance(mark, dict):
|
| 1939 |
+
continue
|
| 1940 |
+
state = str(mark.get('state') or '')
|
| 1941 |
+
if state not in AI_ENRICH_STATES:
|
| 1942 |
+
continue
|
| 1943 |
+
entry = {'state': state, 'at': _dt.datetime.now(_dt.timezone.utc)
|
| 1944 |
+
.replace(microsecond=0).isoformat()}
|
| 1945 |
+
for key, cap in (('hash', 64), ('model', 60), ('error', 300)):
|
| 1946 |
+
got = str(mark.get(key) or '').strip()[:cap]
|
| 1947 |
+
if got:
|
| 1948 |
+
entry[key] = got
|
| 1949 |
+
tokens = mark.get('tokens')
|
| 1950 |
+
if isinstance(tokens, int) and not isinstance(tokens, bool) and tokens >= 0:
|
| 1951 |
+
entry['tokens'] = tokens
|
| 1952 |
+
clean[str(row_id)] = entry
|
| 1953 |
+
if not clean:
|
| 1954 |
+
return 0
|
| 1955 |
+
|
| 1956 |
+
def _set(cur):
|
| 1957 |
+
t = cur.get(str(table_key))
|
| 1958 |
+
if t is not None:
|
| 1959 |
+
col = t.setdefault(AI_ENRICH_MARK_KEY, {}).setdefault(col_id, {})
|
| 1960 |
+
col.update(clean)
|
| 1961 |
+
# The cap is enforced by DROPPING THE OLDEST, never by refusing the write: a run that
|
| 1962 |
+
# produced values and could not record where they came from would leave the cells
|
| 1963 |
+
# looking human-authored, which is the one state this stratum exists to distinguish.
|
| 1964 |
+
if len(col) > AI_ENRICH_MAX_MARKS:
|
| 1965 |
+
for rid in sorted(col, key=lambda r: str(col[r].get('at') or ''))[
|
| 1966 |
+
:len(col) - AI_ENRICH_MAX_MARKS]:
|
| 1967 |
+
col.pop(rid, None)
|
| 1968 |
+
return cur
|
| 1969 |
+
|
| 1970 |
+
_st(st).update(STORE_KEY, _set, flush='async')
|
| 1971 |
+
return len(clean)
|
| 1972 |
+
|
| 1973 |
+
|
| 1974 |
+
def note_human_edit(table_key, values, row_id, st=None):
|
| 1975 |
+
"""A person typed into these cells: mark any `ai_enrich` column among them `human`.
|
| 1976 |
+
|
| 1977 |
+
β THE STAMP HAS TO HAPPEN AT THE WRITE DOOR, not at read time, because "did a human write
|
| 1978 |
+
this" is not recoverable from the value afterwards. Called by `routes_tables.patch_row`;
|
| 1979 |
+
a no-op (and cheap) for the overwhelming case where the edited columns are ordinary.
|
| 1980 |
+
"""
|
| 1981 |
+
defn = get(table_key, st) or {}
|
| 1982 |
+
touched = {f['key'] for f in ai_enrich_fields(defn)} & {str(k) for k in (values or {})}
|
| 1983 |
+
for col_id in touched:
|
| 1984 |
+
stamp_ai_enrich(table_key, col_id, {str(row_id): {'state': 'human'}}, st=st)
|
| 1985 |
+
return sorted(touched)
|
| 1986 |
+
|
| 1987 |
+
|
| 1988 |
def _clean_field(raw, previous=None):
|
| 1989 |
"""One field dict β the stored shape, or None. The single validator for create AND patch, so
|
| 1990 |
a column cannot be typed one way on the way in and another on the way back."""
|
|
|
|
| 2220 |
out['formula'] = fx
|
| 2221 |
elif ftype == 'formula':
|
| 2222 |
return None
|
| 2223 |
+
# ββ WAVE-34 (owner ruling R13) β THE AI ENRICHMENT BAG. Posture and inheritance copied from
|
| 2224 |
+
# `formula` two lines up, deliberately and for the same reason: the bag defines the column, so
|
| 2225 |
+
# the pairing is enforced both ways, and an inherited bag is only inherited while the type
|
| 2226 |
+
# still wants it (retyping an enrichment column to text must not resurrect its prompt through
|
| 2227 |
+
# `prev` and then refuse the whole write, which is the bug the `prev_type == ftype` guard on
|
| 2228 |
+
# `link`/`rollup`/`formula` exists to record).
|
| 2229 |
+
enrich_raw = (raw.get('aiEnrich') if 'aiEnrich' in raw
|
| 2230 |
+
else (prev.get('aiEnrich') if prev_type == ftype else None))
|
| 2231 |
+
if enrich_raw is not None:
|
| 2232 |
+
ae = _clean_ai_enrich(enrich_raw)
|
| 2233 |
+
if ae is None or ftype != 'ai_enrich':
|
| 2234 |
+
return None
|
| 2235 |
+
out['aiEnrich'] = ae
|
| 2236 |
+
elif ftype == 'ai_enrich':
|
| 2237 |
+
return None
|
| 2238 |
+
# C3 (wave 34): the Agents module reads field agents off this bag. DERIVED here, inside the
|
| 2239 |
+
# one validator both write doors run, so the binding can never drift from the config it
|
| 2240 |
+
# describes β see `_field_agent_binding` for why it is computed rather than stored beside it.
|
| 2241 |
+
# β It is written AFTER the generic `automation` passthrough above, so a caller cannot hand us
|
| 2242 |
+
# a `field_agent` bag that disagrees with the column. Every OTHER automation bag is untouched.
|
| 2243 |
+
if ftype == 'ai_enrich':
|
| 2244 |
+
out['automation'] = _field_agent_binding(out)
|
| 2245 |
return out
|
| 2246 |
|
| 2247 |
|
|
|
|
| 2437 |
lives in `aios_grid._clean_automation` β this guards the WRITE doors only.)"""
|
| 2438 |
if not isinstance(bag, dict):
|
| 2439 |
return True # no bag, no law β an ordinary column
|
| 2440 |
+
# ββ WAVE-34 (R13 / contract C3) β A FIELD AGENT IS BOUND BY ITS OWN COLUMN, NOT BY A FLOW,
|
| 2441 |
+
# and without this arm the whole feature is unsavable. `_clean_field` stamps
|
| 2442 |
+
# `{kind:'field_agent', ...}` on every `ai_enrich` column; `add_field` then asks this
|
| 2443 |
+
# predicate, which read `flowId` and only `flowId` β so every AI enrichment column would have
|
| 2444 |
+
# been refused at the create door by the guard for a different feature that happens to share
|
| 2445 |
+
# the `automation` key. β The binding is REAL, not waived: the bag names the column it belongs
|
| 2446 |
+
# to, and `_clean_field` derives that name from the field itself, so it cannot name a column
|
| 2447 |
+
# that does not exist the way a stale `flowId` can name a deleted flow.
|
| 2448 |
+
if bag.get('kind') == 'field_agent':
|
| 2449 |
+
return bool(str(bag.get('field') or '').strip())
|
| 2450 |
flow = str(bag.get('flowId') or '').strip()
|
| 2451 |
if not flow:
|
| 2452 |
return False
|
|
|
|
| 2752 |
return True
|
| 2753 |
|
| 2754 |
|
| 2755 |
+
def patch_many_cells(table_key, updates, st=None):
|
| 2756 |
+
"""Write cells across MANY rows in ONE store update. Returns the number of rows touched.
|
| 2757 |
+
|
| 2758 |
+
β WHY THIS EXISTS RATHER THAN A LOOP OVER `patch_cells`, which is the same argument
|
| 2759 |
+
`add_rows` makes one screen up: every write here is a read-modify-write of the WHOLE tenant
|
| 2760 |
+
document, so filling a 1,000-row enrichment column row by row is 1,000 full-document copies
|
| 2761 |
+
under one lock on the single uvicorn process this product runs. One `update()` writes them
|
| 2762 |
+
all.
|
| 2763 |
+
|
| 2764 |
+
β `updates` is `{row_id: {field_key: value}}`, and a row id that does not exist is SKIPPED
|
| 2765 |
+
rather than created: this is a cell writer, not an insert door, and inventing a row here would
|
| 2766 |
+
let a stale plan resurrect a record somebody deleted mid-run.
|
| 2767 |
+
"""
|
| 2768 |
+
if not is_user_table(table_key, st):
|
| 2769 |
+
return 0
|
| 2770 |
+
have = set((get(table_key, st) or {}).get('rows') or {})
|
| 2771 |
+
clean = {str(r): {str(k): str(v) for k, v in (cells or {}).items()}
|
| 2772 |
+
for r, cells in (updates or {}).items()
|
| 2773 |
+
if str(r) in have and isinstance(cells, dict) and cells}
|
| 2774 |
+
if not clean:
|
| 2775 |
+
return 0
|
| 2776 |
+
|
| 2777 |
+
def _set(cur):
|
| 2778 |
+
t = cur.get(str(table_key))
|
| 2779 |
+
if t is not None:
|
| 2780 |
+
rows = t.setdefault('rows', {})
|
| 2781 |
+
for rid, cells in clean.items():
|
| 2782 |
+
if rid in rows:
|
| 2783 |
+
rows[rid].update(cells)
|
| 2784 |
+
return cur
|
| 2785 |
+
|
| 2786 |
+
_st(st).update(STORE_KEY, _set, flush='sync')
|
| 2787 |
+
return len(clean)
|
| 2788 |
+
|
| 2789 |
+
|
| 2790 |
def patch_link_cell(table_key, row_id, fkey, value, st=None):
|
| 2791 |
"""Persist one user-picked Link cell in the shared row and return its canonical id string.
|
| 2792 |
|
|
|
|
| 3048 |
return _Lent(_st(st), {k: v for k, v in docs.items() if v is not None})
|
| 3049 |
|
| 3050 |
|
| 3051 |
+
def lend_defs(st=None):
|
| 3052 |
+
"""`lend`, but the `user_tables` document it serves is the PROJECTION β definitions, no rows.
|
| 3053 |
+
|
| 3054 |
+
ββ W33-T01 (D-213). `nav_entries` has done exactly this inline since W32-T02
|
| 3055 |
+
(`all_defs` then `lend(st, user_tables=tables)`); this is that pair named, so the TABLE WALL
|
| 3056 |
+
can take it too. `routes_tables._defn_or_refuse` is the wall a database SWITCH goes through and
|
| 3057 |
+
it read the whole 28.6 MB document to answer two questions β "does this key exist" and
|
| 3058 |
+
"may this session open it" β neither of which has ever looked at a row.
|
| 3059 |
+
|
| 3060 |
+
β **HAND THIS TO A READ, NEVER TO A WRITE.** Every value it serves is a `_Projected`, so a
|
| 3061 |
+
caller that reaches `defn['rows']` gets a `KeyError` naming the projection β loud, which is the
|
| 3062 |
+
point β and a read-modify-write handed this document would upload a tenant with its rows
|
| 3063 |
+
removed. `store.update`/`_read_strict` are unaffected (they never project), and the six write
|
| 3064 |
+
walls in `routes_tables` deliberately do not opt in. C5's second clause is the same rule from
|
| 3065 |
+
the other end: a projected snapshot is never handed to a post-write read-back.
|
| 3066 |
+
|
| 3067 |
+
β It is not free β it is ~0.1% of the bytes, not zero. A caller that will need rows ANYWAY
|
| 3068 |
+
should take the whole read once rather than this plus that.
|
| 3069 |
+
"""
|
| 3070 |
+
return lend(st, **{STORE_KEY: all_defs(st)})
|
| 3071 |
+
|
| 3072 |
+
|
| 3073 |
def nav_entries(viewer=None, is_admin=False, st=None):
|
| 3074 |
"""Registry-SHAPED dicts so the nav can render user tables beside real modules with no
|
| 3075 |
special-casing: the same keys the flat nav reads (`key`, `label`, `source`).
|
platform/core/users.py
CHANGED
|
@@ -445,21 +445,20 @@ def assignable_people(tenant=None):
|
|
| 445 |
|
| 446 |
Wave 18 (C1-TENANT): pass `tenant` to scope the choices to ONE company β the user registry
|
| 447 |
is a global control-plane bucket, and a Nurilab picker offering Royal's staff is a
|
| 448 |
-
cross-tenant name leak.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 449 |
"""
|
| 450 |
-
|
| 451 |
-
reg = registry() or {}
|
| 452 |
-
except Exception:
|
| 453 |
-
return []
|
| 454 |
-
want = str(tenant or '').strip().lower()
|
| 455 |
-
out = []
|
| 456 |
-
for username, u in reg.items():
|
| 457 |
-
if not isinstance(u, dict) or u.get('active') is False:
|
| 458 |
-
continue
|
| 459 |
-
if want and str(u.get('tenant') or 'royal-imports').strip().lower() != want:
|
| 460 |
-
continue
|
| 461 |
-
out.append(str(u.get('name') or username))
|
| 462 |
-
return sorted(set(out))
|
| 463 |
|
| 464 |
|
| 465 |
def set_avatar(username, data_url):
|
|
@@ -486,20 +485,41 @@ def avatar_map(tenant=None):
|
|
| 486 |
name, so the display name is the only join a renderer has. Two active accounts sharing a
|
| 487 |
display name share one option; the first WITH a photo wins the key rather than a coin
|
| 488 |
flip deciding whether the option has a face. `tenant` scopes it exactly as
|
| 489 |
-
`assignable_people(tenant)` does, and for the same leak
|
| 490 |
-
|
| 491 |
-
|
| 492 |
-
except Exception:
|
| 493 |
-
return {}
|
| 494 |
-
want = str(tenant or '').strip().lower()
|
| 495 |
out = {}
|
| 496 |
-
for username, u in sorted(
|
| 497 |
-
if not isinstance(u, dict) or u.get('active') is False:
|
| 498 |
-
continue
|
| 499 |
-
if want and str(u.get('tenant') or 'royal-imports').strip().lower() != want:
|
| 500 |
-
continue
|
| 501 |
av = u.get('avatar')
|
| 502 |
nm = str(u.get('name') or username)
|
| 503 |
if av and nm not in out:
|
| 504 |
out[nm] = str(av)
|
| 505 |
return out
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 445 |
|
| 446 |
Wave 18 (C1-TENANT): pass `tenant` to scope the choices to ONE company β the user registry
|
| 447 |
is a global control-plane bucket, and a Nurilab picker offering Royal's staff is a
|
| 448 |
+
cross-tenant name leak.
|
| 449 |
+
|
| 450 |
+
ββ WAVE 33 (W33-T37) β A BLANK `tenant` NOW RETURNS NOTHING. It used to skip the filter and
|
| 451 |
+
return EVERY tenant's staff: `if want and β¦` is structurally fail-OPEN, and the exemption was
|
| 452 |
+
written for "None = unscoped (the Streamlit host, tenant #0's process)" β a host DELETED at
|
| 453 |
+
EXIT-6. So the sanctioned caller no longer exists, and what was left is a whole-platform
|
| 454 |
+
roster one forgotten kwarg away, with no error to notice
|
| 455 |
+
([[gate-must-go-red-not-crash]]'s sibling: a wall that answers instead of refusing).
|
| 456 |
+
β The direction is the safety: this can only ever NARROW. All six live call sites pass
|
| 457 |
+
`session.tenant`, which `aios_session.read` refuses to admit blank, so nothing legitimate
|
| 458 |
+
changes β and a future caller that forgets gets an empty picker somebody notices instead of a
|
| 459 |
+
leak nobody does.
|
| 460 |
"""
|
| 461 |
+
return sorted({str(u.get('name') or n) for n, u in _tenant_accounts(tenant)})
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 462 |
|
| 463 |
|
| 464 |
def set_avatar(username, data_url):
|
|
|
|
| 485 |
name, so the display name is the only join a renderer has. Two active accounts sharing a
|
| 486 |
display name share one option; the first WITH a photo wins the key rather than a coin
|
| 487 |
flip deciding whether the option has a face. `tenant` scopes it exactly as
|
| 488 |
+
`assignable_people(tenant)` does, and for the same leak β including wave 33's fail-closed
|
| 489 |
+
blank, which both take from the ONE resolver below rather than each writing `if want and β¦`.
|
| 490 |
+
"""
|
|
|
|
|
|
|
|
|
|
| 491 |
out = {}
|
| 492 |
+
for username, u in sorted(_tenant_accounts(tenant), key=lambda kv: kv[0]):
|
|
|
|
|
|
|
|
|
|
|
|
|
| 493 |
av = u.get('avatar')
|
| 494 |
nm = str(u.get('name') or username)
|
| 495 |
if av and nm not in out:
|
| 496 |
out[nm] = str(av)
|
| 497 |
return out
|
| 498 |
+
|
| 499 |
+
|
| 500 |
+
def _tenant_accounts(tenant):
|
| 501 |
+
"""`[(username, record), β¦]` β the ACTIVE accounts of exactly ONE tenant. FAIL-CLOSED.
|
| 502 |
+
|
| 503 |
+
β THE ONE PLACE THE TENANT FILTER FOR THE USER REGISTRY IS WRITTEN. It was written twice,
|
| 504 |
+
identically, in `assignable_people` and `avatar_map`, and both copies were fail-OPEN on a
|
| 505 |
+
blank slug in the same way (`if want and β¦`). Two copies of a wall is two places for one of
|
| 506 |
+
them to be fixed [[one-question-two-normalizers]]; `routes_shares._people` is a THIRD copy of
|
| 507 |
+
the same predicate and is lane C's to fold in.
|
| 508 |
+
|
| 509 |
+
β `str(u.get('tenant') or 'royal-imports')` is kept on the RECORD side deliberately: a
|
| 510 |
+
pre-wave-18 account genuinely has no `tenant` key and IS tenant #0's, and `users._public`
|
| 511 |
+
normalises it the same way. What changed is the WANT side β a blank want is now a refusal
|
| 512 |
+
rather than a wildcard.
|
| 513 |
+
"""
|
| 514 |
+
want = str(tenant or '').strip().lower()
|
| 515 |
+
if not want:
|
| 516 |
+
# Not an error and not everything: nobody. See `assignable_people`'s note β the one
|
| 517 |
+
# caller this exemption was written for (the Streamlit host) was deleted at EXIT-6.
|
| 518 |
+
return []
|
| 519 |
+
try:
|
| 520 |
+
reg = registry() or {}
|
| 521 |
+
except Exception:
|
| 522 |
+
return []
|
| 523 |
+
return [(n, u) for n, u in reg.items()
|
| 524 |
+
if isinstance(u, dict) and u.get('active') is not False
|
| 525 |
+
and str(u.get('tenant') or 'royal-imports').strip().lower() == want]
|
platform/harness/datastore.py
CHANGED
|
@@ -188,14 +188,35 @@ ENTITIES = {
|
|
| 188 |
# backfill below has walked every partner (a partner's `write_date` did not move because
|
| 189 |
# WE changed the schema). Every projection degrades a missing/NULL column to blank rather
|
| 190 |
# than raising, so declaring early is safe β it is just not yet true.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 191 |
"fields": ["name", "team_id", "city", "state_id", "country_id", "active",
|
| 192 |
"agent", "salesman_as_agent", "customer_rank",
|
| 193 |
-
"street", "street2", "zip",
|
|
|
|
|
|
|
| 194 |
# `backfill_fields` carries it too, so mirrors that already exist pick it up on the next
|
| 195 |
# sync_all() instead of needing a reseed.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 196 |
"backfill_fields": ["agent", "salesman_as_agent", # added 2026-07-28
|
| 197 |
"customer_rank", # added 2026-08-11 (W29-T54)
|
| 198 |
-
"street", "street2", "zip"
|
|
|
|
|
|
|
| 199 |
# m2m fields land as <base>_id (the FIRST linked id β the Customers-module convention:
|
| 200 |
# a customer's assigned agent is agent_ids[0], ~one per customer, MECE) + <field> as a
|
| 201 |
# JSON list of ALL ids. Declared explicitly: a 2-element m2m read would otherwise be
|
|
|
|
| 188 |
# backfill below has walked every partner (a partner's `write_date` did not move because
|
| 189 |
# WE changed the schema). Every projection degrades a missing/NULL column to blank rather
|
| 190 |
# than raising, so declaring early is safe β it is just not yet true.
|
| 191 |
+
# ββ WAVE 33 (W33-T48, owner item 13) β THE CONTACT/IDENTITY HALF, MEASURED BEFORE IT WAS
|
| 192 |
+
# ADDED. The owner: *"I could have sworn we have more relevant Fields under 'Odoo vendors'
|
| 193 |
+
# etc."* He was right, and the census
|
| 194 |
+
# (`.claude/wiki/waves/wave33/odoo-field-census.md`, live read-only, 2026-08-14) says by how
|
| 195 |
+
# much: `res.partner` declares 198 fields, **77 are populated on all 3,621 customers and 76
|
| 196 |
+
# on all 658 vendors**, and this mirror carried THIRTEEN. Every one of the six added here
|
| 197 |
+
# was measured non-empty on the live population first β none is added on the strength of
|
| 198 |
+
# "Odoo probably has that", which is how a schema grows columns nobody can fill.
|
| 199 |
+
# β THE MIRROR IS THE CEILING, NOT THE GRID. Every reader in `odoo_relational.py` reads
|
| 200 |
+
# THIS file, so a column added to a `*_fields()` contract with no entry here renders as a
|
| 201 |
+
# blank column forever β which is D-165's shape exactly, and the reason the widening starts
|
| 202 |
+
# on this line rather than on the grid.
|
| 203 |
"fields": ["name", "team_id", "city", "state_id", "country_id", "active",
|
| 204 |
"agent", "salesman_as_agent", "customer_rank",
|
| 205 |
+
"street", "street2", "zip",
|
| 206 |
+
"email", "phone", "mobile", "website", "vat", "ref",
|
| 207 |
+
"write_date"],
|
| 208 |
# `backfill_fields` carries it too, so mirrors that already exist pick it up on the next
|
| 209 |
# sync_all() instead of needing a reseed.
|
| 210 |
+
# β D-165 IS ABOUT THIS LIST, AND THE CENSUS SETTLED WHICH HALF IS WRONG: `street`,
|
| 211 |
+
# `street2` and `zip` are `store=True` on `res.partner` and POPULATED in live Odoo β they
|
| 212 |
+
# are declared here and still NULL in the mirror purely because a backfill pass has not
|
| 213 |
+
# walked every partner (changing OUR schema does not move a partner's `write_date`, so an
|
| 214 |
+
# incremental sync never revisits them). Declaring is not filling; the fix is a run.
|
| 215 |
"backfill_fields": ["agent", "salesman_as_agent", # added 2026-07-28
|
| 216 |
"customer_rank", # added 2026-08-11 (W29-T54)
|
| 217 |
+
"street", "street2", "zip", # added 2026-08-12 (W30-T33)
|
| 218 |
+
"email", "phone", "mobile", # added 2026-08-14 (W33-T48)
|
| 219 |
+
"website", "vat", "ref"],
|
| 220 |
# m2m fields land as <base>_id (the FIRST linked id β the Customers-module convention:
|
| 221 |
# a customer's assigned agent is agent_ids[0], ~one per customer, MECE) + <field> as a
|
| 222 |
# JSON list of ALL ids. Declared explicitly: a 2-element m2m read would otherwise be
|
platform/harness/tools.py
CHANGED
|
@@ -65,13 +65,22 @@ def _err(msg):
|
|
| 65 |
# ------------------------------------------------------------------ schema tools
|
| 66 |
|
| 67 |
def list_topics():
|
| 68 |
-
"""The 'what data exists' tool.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 69 |
out = []
|
| 70 |
for k, t in SEM.topics().items():
|
| 71 |
-
|
| 72 |
-
|
| 73 |
-
|
| 74 |
-
|
|
|
|
|
|
|
|
|
|
| 75 |
return out
|
| 76 |
|
| 77 |
|
|
@@ -83,10 +92,30 @@ def describe_topic(topic):
|
|
| 83 |
mets = {k: {"label": m.get("label"), "description": m.get("description"),
|
| 84 |
"format": m.get("format"), "ai_context": m.get("ai_context")}
|
| 85 |
for k, m in SEM.metrics().items() if m["topic"] == topic}
|
| 86 |
-
|
| 87 |
-
|
| 88 |
-
|
| 89 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 90 |
|
| 91 |
|
| 92 |
# ------------------------------------------------------------------ query tools
|
|
|
|
| 65 |
# ------------------------------------------------------------------ schema tools
|
| 66 |
|
| 67 |
def list_topics():
|
| 68 |
+
"""The 'what data exists' tool.
|
| 69 |
+
|
| 70 |
+
W33-T49 adds `grid` β the store key of the database this topic describes, when it describes
|
| 71 |
+
one. It is what lets the agent connect "the thing the person is looking at" to "the topic I
|
| 72 |
+
can query", which is the whole point of the entity topics: before this, the semantic layer
|
| 73 |
+
could see `sale_order_line` and `account_move` and had never heard of `ut_odoo_customers`.
|
| 74 |
+
"""
|
| 75 |
out = []
|
| 76 |
for k, t in SEM.topics().items():
|
| 77 |
+
row = {"topic": k, "label": t.get("label"), "entity": t.get("entity"),
|
| 78 |
+
"grain": t.get("grain"),
|
| 79 |
+
"dims": list((t.get("store") or {}).get("dims") or {}),
|
| 80 |
+
"metrics": [m for m, d in SEM.metrics().items() if d["topic"] == k]}
|
| 81 |
+
if t.get("grid"):
|
| 82 |
+
row["grid"] = t["grid"]
|
| 83 |
+
out.append(row)
|
| 84 |
return out
|
| 85 |
|
| 86 |
|
|
|
|
| 92 |
mets = {k: {"label": m.get("label"), "description": m.get("description"),
|
| 93 |
"format": m.get("format"), "ai_context": m.get("ai_context")}
|
| 94 |
for k, m in SEM.metrics().items() if m["topic"] == topic}
|
| 95 |
+
out = {"topic": topic, "label": t.get("label"), "scope": t.get("scope"),
|
| 96 |
+
"grain": t.get("grain"), "ai_context": t.get("ai_context"),
|
| 97 |
+
"dims": {k: v.get("label") for k, v in ((t.get("store") or {}).get("dims") or {}).items()},
|
| 98 |
+
"metrics": mets}
|
| 99 |
+
# ββ W33-T49 β THE FIELD SEMANTICS, which this tool did not carry AT ALL.
|
| 100 |
+
#
|
| 101 |
+
# β THE GAP WAS NOT THE TOPIC FILES, IT WAS THIS RETURN. Before this, `describe_topic`
|
| 102 |
+
# answered with scope, grain, dims, metrics and `ai_context` β and **no vocabulary of
|
| 103 |
+
# COLUMNS**. So an agent told to describe a database could name what it MEASURES and never
|
| 104 |
+
# what it HOLDS: the owner's item 13 asks for "ALL populated fields β¦ including its semantic
|
| 105 |
+
# layer", and adding eight topic files without this would have left `describe_topic` returning
|
| 106 |
+
# the same field-free shape it always did, one screen away from the fields.
|
| 107 |
+
#
|
| 108 |
+
# β `kind` is the part worth reading, and it is the difference between a column an agent can
|
| 109 |
+
# FILTER and one it cannot: `data` is stored on the row; `rollup` is computed from another
|
| 110 |
+
# topic (`from_topic` names it, and that is where a windowed or reconciled number must come
|
| 111 |
+
# from); `link` points at another database. An agent that treats a rollup as a stored column
|
| 112 |
+
# will ask this topic for a number this topic does not hold.
|
| 113 |
+
if t.get("fields"):
|
| 114 |
+
out["fields"] = [dict(f) for f in t["fields"]]
|
| 115 |
+
for k in ("grid", "subject", "entity"):
|
| 116 |
+
if t.get(k):
|
| 117 |
+
out[k] = t[k]
|
| 118 |
+
return out
|
| 119 |
|
| 120 |
|
| 121 |
# ------------------------------------------------------------------ query tools
|
platform/model/topics/odoo_accounts.yml
ADDED
|
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# ββ W33-T49 (owner item 13) β an ENTITY topic: the semantic layer can finally see
|
| 2 |
+
# the databases a person actually opens, not only the line and document grains.
|
| 3 |
+
#
|
| 4 |
+
# β THE `fields:` BLOCK IS GENERATED FROM THE GRID'S OWN FIELD CONTRACT
|
| 5 |
+
# and is held to it by `verify_query.py::section_entity_topics`. Do not hand-edit a
|
| 6 |
+
# field row: add the column to the grid contract and re-emit, or the agent is being
|
| 7 |
+
# trained on a schema the product does not have.
|
| 8 |
+
key: odoo_accounts
|
| 9 |
+
label: "Odoo GL accounts"
|
| 10 |
+
entity: account.account
|
| 11 |
+
# The database this topic DESCRIBES β the same store key the nav opens (W33-T46).
|
| 12 |
+
grid: ut_odoo_accounts
|
| 13 |
+
subject: "odoo:account.account"
|
| 14 |
+
grain: "one row per GL account in the chart of accounts"
|
| 15 |
+
scope:
|
| 16 |
+
population: "every account.account record (192 measured)"
|
| 17 |
+
store:
|
| 18 |
+
table: account_account
|
| 19 |
+
alias: a
|
| 20 |
+
# NO date_col β a registry is not a dated event stream. Stated rather than
|
| 21 |
+
# omitted, so its absence reads as a fact and not as an unfinished file.
|
| 22 |
+
dims:
|
| 23 |
+
account_type: {label: "Account type"}
|
| 24 |
+
|
| 25 |
+
# key / label / type / kind, derived from the grid contract. `kind` says where the
|
| 26 |
+
# value COMES FROM: a `data` column is stored on the row; a `rollup` is computed
|
| 27 |
+
# from another topic; a `link` points at another database.
|
| 28 |
+
fields:
|
| 29 |
+
- key: account_code
|
| 30 |
+
label: "Code"
|
| 31 |
+
type: text
|
| 32 |
+
kind: data
|
| 33 |
+
- key: account_name
|
| 34 |
+
label: "Account"
|
| 35 |
+
type: text
|
| 36 |
+
kind: data
|
| 37 |
+
- key: odoo_id
|
| 38 |
+
label: "Odoo ID"
|
| 39 |
+
type: int
|
| 40 |
+
kind: data
|
| 41 |
+
means: "The `account.account` id. Also this row's id."
|
| 42 |
+
- key: account_type
|
| 43 |
+
label: "Type"
|
| 44 |
+
type: select
|
| 45 |
+
kind: data
|
| 46 |
+
- key: is_expense
|
| 47 |
+
label: "Expense account"
|
| 48 |
+
type: checkbox
|
| 49 |
+
kind: data
|
| 50 |
+
means: "Ticked for the expense family - the same predicate the semantic layer's gl_lines topic uses, so this column and that topic cannot disagree."
|
| 51 |
+
- key: refreshed
|
| 52 |
+
label: "Refreshed"
|
| 53 |
+
type: date
|
| 54 |
+
kind: data
|
| 55 |
+
means: "When this row was last reconciled against Odoo."
|
| 56 |
+
|
| 57 |
+
ai_context: >
|
| 58 |
+
The chart of accounts β the registry gl_lines posts against.
|
| 59 |
+
Use it to resolve an account code to a name or a type.
|
| 60 |
+
β `is_expense` is a DERIVED boolean standing in for Odoo's five-value `internal_group` (asset/liability/equity/income/expense), which the mirror does not yet carry.
|
platform/model/topics/odoo_agents.yml
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# ββ W33-T49 (owner item 13) β an ENTITY topic: the semantic layer can finally see
|
| 2 |
+
# the databases a person actually opens, not only the line and document grains.
|
| 3 |
+
#
|
| 4 |
+
# β THE `fields:` BLOCK IS GENERATED FROM THE GRID'S OWN FIELD CONTRACT
|
| 5 |
+
# and is held to it by `verify_query.py::section_entity_topics`. Do not hand-edit a
|
| 6 |
+
# field row: add the column to the grid contract and re-emit, or the agent is being
|
| 7 |
+
# trained on a schema the product does not have.
|
| 8 |
+
key: odoo_agents
|
| 9 |
+
label: "Odoo agents"
|
| 10 |
+
entity: res.partner
|
| 11 |
+
# The database this topic DESCRIBES β the same store key the nav opens (W33-T46).
|
| 12 |
+
grid: ut_odoo_agents
|
| 13 |
+
subject: "odoo:res.partner.agent"
|
| 14 |
+
grain: "one row per sales agent"
|
| 15 |
+
scope:
|
| 16 |
+
population: "a UNION of two disagreeing sources β partners carrying commission lines, and partners flagged res_partner.agent = TRUE"
|
| 17 |
+
why_union: "measured 2026-08-09: 16 carry commission lines, 17 carry the flag, and the union is 19 β either source alone silently drops real agents"
|
| 18 |
+
store:
|
| 19 |
+
table: res_partner
|
| 20 |
+
alias: p
|
| 21 |
+
# NO date_col β a registry is not a dated event stream. Stated rather than
|
| 22 |
+
# omitted, so its absence reads as a fact and not as an unfinished file.
|
| 23 |
+
|
| 24 |
+
# key / label / type / kind, derived from the grid contract. `kind` says where the
|
| 25 |
+
# value COMES FROM: a `data` column is stored on the row; a `rollup` is computed
|
| 26 |
+
# from another topic; a `link` points at another database.
|
| 27 |
+
fields:
|
| 28 |
+
- key: agent
|
| 29 |
+
label: "Agent"
|
| 30 |
+
type: text
|
| 31 |
+
kind: data
|
| 32 |
+
- key: odoo_id
|
| 33 |
+
label: "Odoo ID"
|
| 34 |
+
type: int
|
| 35 |
+
kind: data
|
| 36 |
+
means: "The `res.partner` id. Also this row's id."
|
| 37 |
+
- key: agent_id
|
| 38 |
+
label: "Odoo agent id"
|
| 39 |
+
type: int
|
| 40 |
+
kind: data
|
| 41 |
+
- key: flagged
|
| 42 |
+
label: "Flagged in Odoo"
|
| 43 |
+
type: checkbox
|
| 44 |
+
kind: data
|
| 45 |
+
means: "Ticked = `res.partner.agent` is set. Unticked agents were found by their commission lines instead - both are real, which is why this table is the union of the two."
|
| 46 |
+
- key: commissioned
|
| 47 |
+
label: "Has commission lines"
|
| 48 |
+
type: checkbox
|
| 49 |
+
kind: data
|
| 50 |
+
- key: refreshed
|
| 51 |
+
label: "Refreshed"
|
| 52 |
+
type: date
|
| 53 |
+
kind: data
|
| 54 |
+
means: "When this row was last reconciled against Odoo."
|
| 55 |
+
|
| 56 |
+
ai_context: >
|
| 57 |
+
The sales-agent registry.
|
| 58 |
+
`flagged` and `commissioned` are the two SOURCES, kept as separate columns rather than merged, because they disagree and the disagreement is information.
|
| 59 |
+
For an agent's BOOK use sales_lines/commission_lines with the agent dim.
|