Fixes the federal mismatch class (boys' camp × NIH research center):
- Peer precedent: federalPrecedent paginates USASpending (≤500 awards/
program) and name-matches every recipient against primary-ICP NH
registry orgs (shared normalizeOrgNameForMatching, also used by the
self-match gate). The 25-pt precedent tiers now key off
program_state_peer_award_count — Dartmouth renewals and SBIR LLCs no
longer grant precedent to community nonprofits. Raw count + peer-
annotated award list stay as review evidence (peer badges, peers-first).
- Mission-fit floor (12/30, grants_gov only): below it a match is stored
with fit_viable=false and hidden from the pending queue, hero selection,
and easy-win. Foundation-synthesized grants exempt (generic synopses).
- Mission-fit judge live (judgeMatches, 06:15, 200/night best-first):
JUDGE_MODEL reads the synopsis against the org profile with an explicit
ignore-eligibility-breadth instruction; graded verdict with required
citations; deterministic verdict→points map (27/18/8/0) sets missionFit,
total, easy-win, and viability. Verdicts survive nightly re-scores via
an upsert splice and re-enter the judge queue when the org profile is
re-researched (org_profiles.updated_at).
First sweep: 81/149 programs have NH history, only 6 have peer history;
queue-head judging zeroes the research-mechanism garbage (mismatch) while
surfacing genuine strong fits.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
profileOrgs (nightly 05:45, 25/run, easy-win orgs best-first per the
plan's coarse-match-gates-profiling rule): two-pass Gemini flash —
Google Search-grounded research (groundingMetadata = citation universe)
then JSON-schema extraction citing only from it. Overwrites the stub
profile (mission/programs/geography/funders/staff/news/sources/
confidence); re-embeds mission fit from researched text unless identity
unconfirmed or confidence <0.5 (then the NTEE embedding stays —
unverified research must not steer scoring). Detail page renders
researched programs w/ source links, funders, staff.
Fixes: org_profiles.confidence is float4 — 0.2 stores as 0.20000000298
so 'confidence <= 0.2' excluded every stub (epsilon comparison); RR7
loader serialization turns unknown into never (hoisted casts).
Live: 55 orgs profiled (41 research-grade, 2 low-confidence, 0 failed).
Scoring effect verified both directions: Annie's Angels x NIH mammalian
models fit 19->12; Seacoast Pathways x Foundation for Seacoast Health
fit 25/30 — and the researched knownFunders independently names that
funder. 161 tests green.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
embedGrants (cron 04:15, after the ingest crons): open grants with a
synopsis and no vector → buildGrantEmbeddingText (pure, tested:
title+funder+program areas+synopsis, 8K cap) → gemini-embedding-001 @
1536 dims RETRIEVAL_DOCUMENT (org profiles will embed as
RETRIEVAL_QUERY on the other side) → grants.synopsis_embedding.
Chunked embed→store (100/chunk) so failures resume from the last
stored chunk; 500/run spend cap.
Core: serverListGrantsNeedingEmbedding (open+unembedded, closest
deadline first), serverSetGrantEmbeddings. Worker gains
@novelpad/outreach-ai dep; wired into main.ts and run-once (incl. the
missed run-once deps injection).
Live-verified: 199/199 open grants embedded in 16s; semantic probe
('after-school STEM education for youth') ranks NCI Youth Enjoy
Science R25 first at 0.639 cosine via the hnsw index.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
