yf176 commited on
Commit ·
88fe16f
1
Parent(s): e44f80d
docs: record typed asset analyst verification
Browse files
docs/V8.0_IMPLEMENTATION_PLAN.md
CHANGED
|
@@ -293,9 +293,30 @@ and an explicit missing-input case. Keep existing reasoning duties intact.
|
|
| 293 |
Keep M08 open until coordinator, cost/trace, and live configured-LLM
|
| 294 |
integration are verified.
|
| 295 |
- [ ] M09 BTCAnalyst: migrate its BTC-specific reasoning and delta contract.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 296 |
- [ ] M10 SPYAnalyst: migrate its SPY-specific reasoning and delta contract.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 297 |
- [ ] M11 QQQAnalyst: migrate its QQQ-specific reasoning and delta contract.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 298 |
- [ ] M12 GLDAnalyst: migrate its GLD-specific reasoning and delta contract.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 299 |
- [ ] M13 QuantResearcher: consume the conditional join, retain signal IDs
|
| 300 |
across delta updates, and allow an evidence-supported empty signal result.
|
| 301 |
- [ ] M14 Backtester: retain validation duties and distinguish LLM assessment
|
|
@@ -441,3 +462,4 @@ actual migrated runtime or live verification.
|
|
| 441 |
| M06a | `cf7a68e` | `tests/test_macro_context_typed.py`, the real structured-completion boundary with a controlled text response, conditional market-event/options inputs, macro and options contracts, I/O bindings, evidence verification, publication, existing V6 options behavior, and the applicable typed regression set: the existing MacroContextWatcher preserves exact scope and upstream gaps, requires positive weighted drivers with current evidence, consumes approved prior context for cited delta comparison, records usage when state is supplied, and publishes `UNCLEAR`/`UNKNOWN` without LLM inference when no usable current evidence exists. | Passed; 277 tests, 1 Windows symlink test skipped | No live LLM request or coordinator activation. Current MarketEventWatcher output is intentionally partial while no external event feed is approved, so that limitation propagates into macro availability. Product-path execution remains M06/R02/R03/R06 work. |
|
| 442 |
| M07a | `cef6290` | `tests/test_unusual_event_typed.py`, the real structured-completion boundary with a controlled text response, conditional market-event/macro/options inputs, event contracts, I/O bindings, evidence verification, publication, existing V6 options behavior, and the applicable typed regression set: the existing UnusualEventDetector separates meaningful, suppressed, and monitoring records; requires positive significance, known confidence, current evidence, stable global IDs, and cited prior context for carried delta events; records usage when state is supplied; and publishes monitoring-only unavailable output without LLM inference when current evidence is absent. | Passed; 280 tests, 1 Windows symlink test skipped | No live LLM request or coordinator activation. A usable-evidence run with no meaningful event remains an LLM-owned classification, distinct from deterministic `UNAVAILABLE`. Product-path execution remains M07/R02/R03/R06 work. |
|
| 443 |
| M08a | `7e0ccc3` | `tests/test_event_router_typed.py`, the real structured-completion boundary with a controlled text response, event-route and analysis contracts, exact current-event evidence verification, immutable publication, prompt constraints, and the applicable typed regression set: the existing EventRouter accounts for every meaningful event, permits explicit unassignment, rejects out-of-event-scope and zero-relevance assignments, records usage when state is supplied, and publishes an empty route without LLM inference when no meaningful event exists. | Passed; 330 tests, 1 Windows symlink test skipped | No live LLM request or coordinator activation. EventRouter publishes evidence assignments only; the fixed routing plan remains the sole activation authority. Product-path execution remains M08/R02/R03/R06 work. |
|
|
|
|
|
|
| 293 |
Keep M08 open until coordinator, cost/trace, and live configured-LLM
|
| 294 |
integration are verified.
|
| 295 |
- [ ] M09 BTCAnalyst: migrate its BTC-specific reasoning and delta contract.
|
| 296 |
+
- [x] M09a Add typed execution to the existing BTCAnalyst class with its fixed
|
| 297 |
+
BTC schema, crypto-specific registered prompt, current evidence verification,
|
| 298 |
+
read-only baseline resolution, delta citation, data-gap preservation, and
|
| 299 |
+
deterministic unavailable output. Keep M09 open until coordinator,
|
| 300 |
+
cost/trace, and live configured-LLM integration are verified.
|
| 301 |
- [ ] M10 SPYAnalyst: migrate its SPY-specific reasoning and delta contract.
|
| 302 |
+
- [x] M10a Add typed execution to the existing SPYAnalyst class with its fixed
|
| 303 |
+
SPY schema, broad-market-specific registered prompt, exact routed-event
|
| 304 |
+
citation, current evidence verification, read-only baseline resolution,
|
| 305 |
+
delta citation, data-gap preservation, and deterministic unavailable output.
|
| 306 |
+
Keep M10 open until coordinator, cost/trace, and live configured-LLM
|
| 307 |
+
integration are verified.
|
| 308 |
- [ ] M11 QQQAnalyst: migrate its QQQ-specific reasoning and delta contract.
|
| 309 |
+
- [x] M11a Add typed execution to the existing QQQAnalyst class with its fixed
|
| 310 |
+
QQQ schema, technology/growth-specific registered prompt, current evidence
|
| 311 |
+
verification, read-only baseline resolution, delta citation, data-gap
|
| 312 |
+
preservation, and deterministic unavailable output. Keep M11 open until
|
| 313 |
+
coordinator, cost/trace, and live configured-LLM integration are verified.
|
| 314 |
- [ ] M12 GLDAnalyst: migrate its GLD-specific reasoning and delta contract.
|
| 315 |
+
- [x] M12a Add typed execution to the existing GLDAnalyst class with its fixed
|
| 316 |
+
GLD schema, gold/rates-specific registered prompt, current evidence
|
| 317 |
+
verification, read-only baseline resolution, delta citation, data-gap
|
| 318 |
+
preservation, and deterministic unavailable output. Keep M12 open until
|
| 319 |
+
coordinator, cost/trace, and live configured-LLM integration are verified.
|
| 320 |
- [ ] M13 QuantResearcher: consume the conditional join, retain signal IDs
|
| 321 |
across delta updates, and allow an evidence-supported empty signal result.
|
| 322 |
- [ ] M14 Backtester: retain validation duties and distinguish LLM assessment
|
|
|
|
| 462 |
| M06a | `cf7a68e` | `tests/test_macro_context_typed.py`, the real structured-completion boundary with a controlled text response, conditional market-event/options inputs, macro and options contracts, I/O bindings, evidence verification, publication, existing V6 options behavior, and the applicable typed regression set: the existing MacroContextWatcher preserves exact scope and upstream gaps, requires positive weighted drivers with current evidence, consumes approved prior context for cited delta comparison, records usage when state is supplied, and publishes `UNCLEAR`/`UNKNOWN` without LLM inference when no usable current evidence exists. | Passed; 277 tests, 1 Windows symlink test skipped | No live LLM request or coordinator activation. Current MarketEventWatcher output is intentionally partial while no external event feed is approved, so that limitation propagates into macro availability. Product-path execution remains M06/R02/R03/R06 work. |
|
| 463 |
| M07a | `cef6290` | `tests/test_unusual_event_typed.py`, the real structured-completion boundary with a controlled text response, conditional market-event/macro/options inputs, event contracts, I/O bindings, evidence verification, publication, existing V6 options behavior, and the applicable typed regression set: the existing UnusualEventDetector separates meaningful, suppressed, and monitoring records; requires positive significance, known confidence, current evidence, stable global IDs, and cited prior context for carried delta events; records usage when state is supplied; and publishes monitoring-only unavailable output without LLM inference when current evidence is absent. | Passed; 280 tests, 1 Windows symlink test skipped | No live LLM request or coordinator activation. A usable-evidence run with no meaningful event remains an LLM-owned classification, distinct from deterministic `UNAVAILABLE`. Product-path execution remains M07/R02/R03/R06 work. |
|
| 464 |
| M08a | `7e0ccc3` | `tests/test_event_router_typed.py`, the real structured-completion boundary with a controlled text response, event-route and analysis contracts, exact current-event evidence verification, immutable publication, prompt constraints, and the applicable typed regression set: the existing EventRouter accounts for every meaningful event, permits explicit unassignment, rejects out-of-event-scope and zero-relevance assignments, records usage when state is supplied, and publishes an empty route without LLM inference when no meaningful event exists. | Passed; 330 tests, 1 Windows symlink test skipped | No live LLM request or coordinator activation. EventRouter publishes evidence assignments only; the fixed routing plan remains the sole activation authority. Product-path execution remains M08/R02/R03/R06 work. |
|
| 465 |
+
| M09a-M12a | `e44f80d` | `tests/test_asset_analysts_typed.py`, the real structured-completion boundary with controlled text responses, all four concrete asset schemas and registered expertise prompts, exact current and routed-event evidence verification, immutable per-agent publication, approved baseline loading/citation, upstream-gap preservation, deterministic unavailable output, and the applicable typed regression set. The legacy V6 specialized-node handoff test was also included. | Passed; 339 tests, 1 Windows symlink test skipped | No live LLM request or coordinator activation. Shared execution plumbing preserves four distinct agents, fixed tickers, prompts, payload schemas, and artifacts; no shared asset-analysis file is written. Product-path execution remains M09-M12/R02/R03/R06 work. |
|