Asked about a date or a recent event, the agent answered from its training cutoff
("I don't know, my knowledge ends ...") because nothing ever told it what today is.
That also blocked instructions it already had — resolving "today", "yesterday",
"recent" and "latest" into a real range for the tools.
Appended per request rather than folded into SYSTEM_PROMPT, which is built once at
import: a Space that stays up for days would otherwise keep asserting its boot date.
Not a substitute for the tools — the note also says the training cutoff implies nothing
about what data exists, since coverage and recency come from the tools (granule
coverage, event feeds) rather than from the model.
Make inline code readable: light chip, not Gradio's dark one
rohit-sahoo
68c7315
Gradio 6 styles inline code as a dark chip, which lands dark-on-dark inside these
light chat bubbles — identifiers the agents return constantly (CMR concept-ids, GIBS
layer names) were effectively illegible. Adopt the light chip the Illustration agent
already used, so all seven render code identically: #3d33ab on #efeefb, measured at
8.09:1 contrast (WCAG AAA). Headings and table cells stay plain, where a chip would
just add clutter; fenced blocks get a light surround with transparent inner code.
Fix collaborator row labels rendering as SMES
rohit-sahoo
1436d2a
The row-label span was styled text-transform:uppercase, so the label text "SMEs"
rendered as "SMES" — the lowercase plural s cannot survive that transform. Drop the
transform from the row labels only, so they render as written: "SMEs" and
"Implementation Team". The COLLABORATORS heading and the AKD eyebrow keep their
all-caps treatment (the changed style string is unique to _collab_row).
Collaborators: SMEs / Implementation Team rows; live auto-updating model list
rohit-sahoo
87a5963
Collaborators now follow the MIO Agent layout — an SMEs row above an Implementation
Team row — instead of one flat list.
Model selection no longer goes stale: the dropdown was a hardcoded list, which is how
it still offered gpt-5.2/5.5 after the GPT-5.6 family (sol/terra/luna) shipped. It now
builds from the visitor's own live catalogue (GET /v1/models), ranked by OpenAI's
created stamp with release tiers kept in order (flagship before the cheaper tiers), so
a new release appears AND becomes the default on its own with no redeploy. An explicit
visitor choice is preserved, AGENT_MODEL still pins, and any failure falls back to the
static list rather than emptying the dropdown. Filtering is a denylist, not an
allowlist, so a future family that drops the gpt- prefix isn't silently hidden.
Reasoning effort gains 5.6's max and ultra depths; previously anything past high was
silently downgraded to medium.
Count visitors in-app (HF exposes no visitor API for Spaces)
rohit-sahoo
053c968
Every HF analytics endpoint 404s and the Space API's expand field list has no
views/visitors equivalent, so there is nothing to query — the app counts its own.
Gradio issues a fresh session_hash per page load, so one log line per unseen
session is one visit; the ops dashboard tallies page loads and distinct visitors.
Privacy: the client IP is never logged raw. It is hashed with a salt and truncated
to 10 hex chars — enough to count distinct visitors, non-reversible. The salt comes
from the VISIT_SALT secret (shared across the agents so one person using several
counts once) and falls back to a per-boot random value if unset.
Light file-row palette for corpus/reference uploads + friendlier output-block message
rohit-sahoo
a026886
The theme's default even/odd table fills rendered the uploaded-file rows dark
against the light design — pin table fills light in both modes and force the
row palette inside #uploadbox. When the risk_agent output guard blocks an
answer, append a retry note (resend or rephrase; conversation intact) so the
block reads as recoverable rather than a dead end.
Header/branding polish: drop Running+logo, collaborators, About AKD in eyebrow
rohit-sahoo
96433a4
Remove the dev header (repo slug + Running pill + logo mark); add a Collaborators
row (Nidhi Jha & Rahul Ramachandran ORCID-linked, others as name chips); move the
About AKD link into the eyebrow row; widen to 1200px. HF card title (README) ->
'AKD - Scope Interview Agent'; on-page h1 stays 'Accelerated Knowledge Discovery:
Scope Interview Agent'.
Upgrade to pydantic-ai 2.16 + AKD guardrails via harness capabilities
rohit-sahoo
9241d94
pydantic-ai 1.81 -> 2.16.0 with pydantic-ai-harness 0.10.0: gliguard input
guard and risk_agent output guard attached as InputGuard/OutputGuard
capabilities on the Agent (the akd-guardrails demo pattern), relaying verdicts
to the AKD guardrails service. Input blocks render as a single bubble with the
model never invoked; output blocks (OutputBlocked) replace the answer and are
kept out of conversation memory. Fail-open when the service is unreachable.
Scope interview agent v2 — CARE v2 artifact from akd-plugins
rohit-sahoo
2cb5269
Replaces the v1 CARE workspace (agents.md + references) with the v2 artifact:
the scope-interview skill from NASA-IMPACT/akd-plugins, bundled verbatim as
artifact/agents.md. A web-chat session addendum adapts its original runtime-specific parts
(Step 0 codebase exploration, document file-saving) to this UI. read_reference
attaches only when reference files ship alongside the skill. UI unchanged.
