Today /sightings, /witnesses, /objects, /locations and /operations show
a name + mention count and nothing else. After this each row carries a
60-100 word bilingual narrative summary written from the chunks where
the entity actually appears.
Migration 0008 (apply as supabase_admin):
public.entities +summary_en TEXT
+summary_pt_br TEXT
+summary_generated_at TIMESTAMPTZ
+summary_model TEXT
+summary_status TEXT
CHECK ('pending'|'ai_generated'|'curated'|'refused')
+ index on summary_status
+ GRANT UPDATE (summary_*) ON entities TO investigator
+ new policy entities_investigator_update_summary (RLS UPDATE for
investigator role)
Enrichment script (investigator-runtime/scripts/enrich_entity_summaries.ts):
- Per-class config (chunk_k, min_mentions, max_per_class)
- Path A: entity_mentions JOIN chunks (high-precision linker)
- Path B (fallback): hybridSearch on canonical_name + aliases when
entity_mentions returns zero. This is what unlocked Kenneth Arnold
and similar entities — their wiki YAML has high total_mentions
counted from frontmatter mentioned_in[], but the entity_mentions
extractor was silent because the matches came from the wiki text,
not the OCR chunks.
- Sonnet 4.6 via OAuth Max, ~$0.04 per entity, ~$10 for the full
260-entity bulk run.
- INSUFFICIENT skip when chunks can't sustain a 60-word summary —
refused entries get summary_status='refused' so they're not retried.
UI uplift:
- lib/retrieval/entity-pages.ts: getEntityCore now prefers the DB
summary (ai_generated or curated) over wiki YAML narrative.
- components/entity-list-page.tsx:
* SELECT now pulls summary_en, summary_pt_br, summary_status
* Sorted with summary-enriched rows first (so the magazine grid
lands on quality content immediately)
* MagazineGrid: 4-line summary preview replaces aliases line
* CompactGrid: enriched rows render as full editorial cards,
bare rows fall back to a compact table below
Smoke results:
- Kenneth Arnold sighting: "On June 24, 1947, pilot Kenneth Arnold
reported sighting unidentified objects over the Pacific Northwest,
and the account spread worldwide. It set off a run of similar
reports: County Commissioner Crankes saw comparable objects after
Arnold's account reached the press, and United Airlines pilot
Emil H. Smith spotted flying discs on July 4 during a routine
flight out of Boise, Idaho..."
- Roswell Incident: includes Colonel Corso's 1997 book + the 1995
GAO finding that radio messages from Oct 46–Feb 47 were destroyed
+ Senator Strom Thurmond's foreword. Real magazine-grade content.
Background bulk run kicked off across all 5 classes (event,
uap_object, person, location, organization) — populating live as
the homepage rebuilds.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
User: "shouldn't mention the names of the mind-clones, should merge all
analyses and write like a best-seller author would, about what happened."
Voice rewrite (prompts/case-writer.md):
- Reference voices: Erik Larson, Sam Kean, John McPhee, Mark Bowden.
Plainspoken non-fiction, scene-driven, fascinated.
- One narrator. NEVER say "Sherlock Holmes argues" / "Sun-Tzu builds
the case" / "the team concluded". No internal-process names reach
the reader.
- Hook the first paragraph. Open in a scene with a date, place, and
person doing something specific. NOT "This case investigates..."
- Show, don't argue. Verbatim quotes stay source-language in
blockquotes; the narration around them is the narrator's voice.
- Every claim cites a chunk with [[doc-id/pNNN#cNNNN]].
- Forbidden ceremony: "In summary…", "Em suma…", "Ultimately…",
"It is worth noting…", detective names, probability tables,
hypothesis tournaments.
- The honest unknown is the subject, not a failure: "Whatever was in
the sky over Sandia in December 1948, the government never said."
- 4-6 numbered scenes, each title-cased specifically ("The Green
Sphere Over Highway 60" not "Background").
- Bilingual EN + PT-BR per CLAUDE.md §3 — sections alternate, no
mid-paragraph language mixing.
- Refusal: emit INSUFFICIENT_ARTEFACTS rather than padding when the
corpus is thin.
Raw-material pipeline (src/detectives/case_writer.ts):
- hybridSearch(topic, lang, top_k=18) gives the narrator real corpus
scenes with verbatim text + chunk_id citations + bbox metadata.
This is what was missing — v1 only saw pre-digested hypothesis
artefacts, which is how the academic prose got there.
- Dropped the hypotheses + contradictions queries from the loader.
They were skeptic-framing scaffolding that doesn't belong in the
raw material a best-seller narrator works from.
- New buildPrompt sections: "Primary-source scenes", "Curated
verbatim quotes", "Anomalies and surprises", "Named witnesses".
Anomalies (Taleb's outlier gaps) reframed: drop dominant_model
skeptic baseline, keep title + why_surprising as gold material.
- Refusal floor: < 4 scenes from hybridSearch → skip with reason.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Live failure surfaced by user feedback: Poirot wrote a low-credibility
verdict on J. Edgar Hoover (W-0002) based on 1 actual chunk and 11
entity_mentions false positives where 'DIRECTOR'/'DIRETOR' was linked to
him by mistake. Poirot's own bias_notes correctly identified this — yet
still produced a verdict. Published on a 'Disclosure Bureau' site, that's
libellously misleading.
Deleted W-0001 (Donald Keyhoe) and W-0002 (J. Edgar Hoover) from
public.witnesses + their .md files.
Prompt rewrite (prompts/poirot.md):
- New "What counts as testimony" section up front, before discipline.
Direct testimony = the person AUTHORED, was QUOTED verbatim with
attribution, or GAVE testimony in a recorded hearing. Not: third-
party mentions, generic title appearances ('Director'/'Diretor'
that entity-extraction speculatively linked), CC lines.
- HARD FLOOR rule: emit `direct_testimony_chunk_ids[]`. If < 3, refuse
with INSUFFICIENT_TESTIMONY. For famous historical figures
(Wikipedia-worthy public figures) the floor is 5.
- Bias claims MUST cite a specific chunk; ungrounded bias claims drop.
- Tone: "careful prosecutor preparing a brief, not debunker scoring
points."
Defense in depth (poirot.ts):
- Detective enforces the same floor before calling writeWitnessAnalysis,
using a FAMOUS slug list (j-edgar-hoover, donald-keyhoe, j-allen-
hynek, curtis-lemay, vannevar-bush, eisenhower, truman, kennedy,
ted-bloecher, ...).
- When the floor isn't met, emit `poirot_refused_floor` audit event +
skip with reason like `insufficient_direct_testimony_1_of_5`.
- Sentinel parser now also catches INSUFFICIENT_TESTIMONY when it
appears on the first line of an otherwise-prose response.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Two complaints in one wave:
(W4.1) User: "Não pode ter vícios de IA como uso excessivo de '-' que a IA
coloca geralmente no lugar de vírgulas por exemplo. Isso deve fazer parte
do prompt geral."
- New prompts/_house-style.md banning the 9 most common AI prose tells
in both EN and PT-BR:
1. Em dashes as comma replacements (—)
2. Rule-of-three lists ("concrete, rigorous, and grounded")
3. Conjunctive openers ("Moreover", "Notably", "Ademais")
4. Superficial -ing analyses ("marking a shift", "destacando")
5. Inflated symbolism + AI vocab (tapestry, navigate, delve,
underscore, robust, multifaceted, marco histórico, ...)
6. Negative parallelisms ("Not just X but Y")
7. Vague attribution ("Some scholars say...")
8. Summary closers ("In summary...", "Em suma...")
9. Hedging fluff ("It's important to note...")
Verbatim chunk quotes are explicitly exempt; preserve as-is.
- claude.ts callClaude() lazily loads _house-style.md once per process
and PREPENDS it to every detective's system prompt:
composedSystem = houseStyle + "---" + detective.systemPrompt
This means all 7 detectives + future ones get the rules without any
per-prompt change.
(W4.2) User: "Quando entra em uma página da investigação não tem como
voltar! UX terrível!"
- New <BureauNav> sticky topbar with explicit "← home" + "🔎 bureau"
buttons + clickable breadcrumb trail. Always visible at the top of
every bureau page so the user can escape in one click.
- Wired into /bureau, /h/[hypothesisId], /c/[slug], /jobs/[id]. Each
page passes its sensible parent crumb (/bureau#hypotheses,
/bureau#reports, /bureau#jobs).
- Replaces the previous plain-text "disclosure.top / hypothesis /
H-0004" line which had no visual affordance.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Live PT-BR smoke on j-edgar-hoover produced verdict_pt_br at 304 chars
(prompt says ≤ 280). The writer correctly rejected it ("verdict too long
(304 > 280)") but the job failed instead of trimming.
Fix: detective now trims each language field at the nearest sentence
boundary (period or semicolon) above 60% of the cap; falls back to a hard
cut at the cap. Applied to verdict / verdict_pt_br (≤280), and to
access_to_event*, bias_notes* (≤800) for defense in depth.
The contract with the writer stays strict; the detective just becomes
forgiving about the model going 5-10% over.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
User flagged that the bureau was emitting English-only output, violating
the project's bilingual rule. Every narrative field now ships in both
languages: stored in sibling DB columns + rendered as adjacent markdown
sections per CLAUDE.md §3.
Migration 0007 (apply as supabase_admin):
- public.hypotheses +question_pt_br, +position_pt_br,
+argument_for_pt_br, +argument_against_pt_br
- public.contradictions +topic_pt_br, +notes_pt_br
- public.witnesses +access_to_event_pt_br, +bias_notes_pt_br,
+verdict_pt_br
- public.gaps +description_pt_br, +suggested_next_move_pt_br
- public.evidence: unchanged (verbatim_excerpt stays source-language)
- JSONB siblings inside contradictions.chunks + gaps.scope handled at
runtime (statement_pt_br, title_pt_br, dominant_model_pt_br,
why_surprising_pt_br, what_it_implies_pt_br).
Detective prompts (all 7) rewritten with explicit bilingual JSON contract:
- Output protocol section names every EN field + its _pt_br sibling
- "Bilingual is mandatory" warning in the task instruction
- Sentinel skip-states unchanged (NO_HYPOTHESES, NO_CONTRADICTIONS,
INSUFFICIENT_TESTIMONY, INSUFFICIENT_HYPOTHESIS, NO_OUTLIERS,
NO_NEW_EVIDENCE, INSUFFICIENT_ARTEFACTS)
- Schneier: parallel arrays — hidden_assumptions[i] matches
hidden_assumptions_pt_br[i], lengths must match
- Case-Writer: interleaved §1 (EN) / §1 (PT-BR) per act in the body
Writer-side validation (all 7 tools):
- Reject INSERT if PT-BR sibling missing when EN field is set
- Persist both languages atomically in one INSERT (no half-updates)
- Markdown renderers write adjacent EN+PT-BR sections in case files
(## Argument for (EN) followed by ## Argumento a favor (PT-BR), etc.)
Detective parse layer (all 7 detectives):
- Coerce both keys from JSON output
- "incomplete_bilingual_*" skip reason when either side missing
- Defensive: PT-BR fields trimmed + length-capped same as EN
Orchestrator propagates question_pt_br + topic_pt_br through job payload
to runHolmes / runCaseWriter, mirroring the chat-tool entry point.
Web (UI):
- /api/jobs/[id] hydrates _pt_br siblings from pg
- job-status-poller HypothesisCard: PT-BR primary, EN in <details>
fallback when both exist
- ContradictionCard: PT-BR statement primary + secondary EN quote
- WitnessCard: PT-BR verdict primary + secondary EN quote, panels in PT
- GapCard: PT-BR title/why/implies primary
- /bureau hub: SELECTs both columns, renders PT-BR primary
- /h/[id]: ArgumentPanel renders PT-BR primary with collapsible EN
fallback when both exist
- BureauSnapshot homepage: position_pt_br / topic_pt_br / verdict_pt_br
primary
- DocBureauPanel /d/[doc]: same primary-PT-BR pattern
- New web/lib/i18n/pick.ts helper (unused yet by chat/agents — kept
for future locale-driven switching when both languages are equally
full; current rule is PT-BR-first since the user is brasileiro)
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Closes a UX gap the user surfaced: W3.5-3.8 built 8 detectives, 4 new
URL endpoints (/jobs/[id], /h/[id], /c/[slug], /api/h/[id]/red-team)
and a chat tool, but the homepage was unchanged — the bureau was
invisible unless you knew the URL or asked the chat to invoke
request_investigation.
Homepage (web/app/page.tsx):
- Title `▍ war.gov/ufo — Investigative Wiki` → `▍ The Disclosure Bureau`
- Subtitle expanded from "Holmes · Poirot · Dupin · Locard" to all 8
detectives (Holmes · Locard · Dupin · Schneier · Poirot · Taleb ·
Tetlock · Case-Writer)
- New `🔎 bureau` topbar link (gold, between graph/stats and batch)
- BureauSnapshot inserted right after the header
BureauSnapshot (web/components/bureau-snapshot.tsx) — server component:
- 8 detective tiles with role labels (each in its tone color)
- 6 clickable counters (evidence / hypotheses / contradictions /
witnesses / outliers / case reports) — anchor to /bureau#section
- 6 "recent artefacts" columns surfacing the last 3-4 of each kind:
hypotheses with prior→posterior + band + ↳reviewed_by marker,
contradictions with topic + resolution_status, evidence with
Grade badge + verbatim quote, outliers with title + scope.kind,
witness analyses with canonical_name + credibility + verdict,
case reports with slug + link to /c/<slug>
- "Recent jobs" strip linking to /jobs/[id] color-coded by status
- Reports read from /data/ufo/case/reports/ via fs.readdir + stat,
sorted by mtime — no DB round-trip needed for that section
/bureau (web/app/bureau/page.tsx) — full hub:
- Header with full counts
- 7 sections (anchored to homepage counter links): Case reports,
Hypotheses, Evidence, Contradictions, Outliers, Witnesses,
Recent jobs table — each rendering up to 100 rows
- Reports section parses frontmatter from each .md to surface topic
+ n_hypotheses + n_evidence on the card
Runtime fixes batched in:
- Poirot: coerce entity_pk via Number() — node-postgres returns
BIGINT as string by default; writer's Number.isFinite() rejected
it as "person_entity_pk required" (j-edgar-hoover retry path)
- Tetlock: write_calibration rationale cap 600 → 1200 chars. Prompt
still asks ≤ 600 but a 2× slack beats failing the job on honest
analysis. Observed live: Tetlock emitted ~620 chars on H-0003 and
the writer rejected the entire calibration.
- Case-Writer: Promise.all of 5 queries × max_parallel=2 jobs
demanded up to 10 connections against the investigator role's
rolconnlimit=4 → "too many connections for role investigator".
Sequentialized — the LLM call is the hot path, not these queries.
Smoke results visible now on the homepage:
- 3 hypotheses (H-0001/2/3) about green fireballs origin
- 3 contradictions (R-0001/2/3) about color, geographic confinement,
exclusive-green vs multicolored
- 2 evidence cards (E-0002/3) Grade B
- 3 outliers (G-0001/2/3) — including Taleb's deliberate
meteor-shower-camouflage flag
- 1 case report at /c/green-fireballs-sandia (Watson 13.4 KB,
five-act narrative, fully cited)
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Brings the bureau from 4 → 8 detectives. All eight run as Bun + claude-CLI
subprocesses against the same Supabase + investigation_jobs LISTEN/NOTIFY
queue, sharing search.ts hybridSearch and writer-side validators that
gate writes against schema + FK.
New detectives:
Poirot (witness_analysis)
- prompts/poirot.md — credibility / access / bias / corroboration /
verdict; uses entity_mentions JOIN chunks to pull 12 chunks per
person; resolves corroboration_refs chunk_ids defensively (accepts
bare cNNNN even when the model emits pNNN/cNNNN).
- INSERT into public.witnesses with W-NNNN naming.
- Tone: purple (#9b5de5).
Taleb (outlier_scan)
- prompts/taleb.md — "surprise is relative to a model"; at most 3
outliers; each requires explicit dominant_model + why_surprising +
what_it_implies; fan-out into public.gaps with scope.kind="outlier".
- Same unscoped-fallback as Dupin (Pass 1 with doc_id, Pass 2 widens
to corpus if hits < 3).
- Tone: yellow (#ffd23f).
Tetlock (calibrate_hypothesis)
- prompts/tetlock.md — honest Bayesian update; emits new_posterior +
Δ + recommended_action ∈ {keep, downgrade, upgrade, supersede}.
- write_calibration UPDATEs public.hypotheses + APPENDS a
"## Calibration history" section to the H-NNNN.md case file
(calibration is append-only — each datapoint matters). Posterior
band auto-corrected to match Tetlock thresholds.
- NO_NEW_EVIDENCE sentinel handled; pure 'keep' with |Δ|<0.005 only
touches updated_at + reviewed_by.
- Tone: teal (#26d4cc).
Case-Writer (case_report)
- prompts/case-writer.md — Dr. Watson assembles all artefacts
(E-NNNN, H-NNNN, R-NNNN, W-NNNN, G-NNNN) into a five-act narrative.
ILIKE filter on topic; doc_id optional scope.
- Larger budget cap (≥ $0.50) + longer timeout for prose generation.
- Writes case/reports/<slug>.md with frontmatter (topic + counts);
no DB table for v0.
- New page /c/[slug] renders the report via MarkdownBody + stat chips.
- Tone: gold (#e0c080).
Hardening across the bureau:
- Sentinel parsing now accepts backticked AND prose-trailing forms
(Holmes NO_HYPOTHESES, Dupin NO_CONTRADICTIONS, Schneier
INSUFFICIENT_HYPOTHESIS, Poirot INSUFFICIENT_TESTIMONY, Taleb
NO_OUTLIERS, Tetlock NO_NEW_EVIDENCE, Case-Writer
INSUFFICIENT_ARTEFACTS). Avoids the failure mode where the model
refuses honestly but the runtime treated it as a parse error
(observed live with Poirot+Hoover identifying the DIRECTOR
false-positive disambiguation issue in entity_mentions).
Chat tool extensions (web/lib/chat/tools.ts):
- request_investigation now accepts 7 kinds. Each routes to its
detective with appropriate validation (hypothesis_id regex,
person_id kebab-case, topic non-empty, doc_id for evidence_chain).
- ETA per kind: Holmes/Dupin 60s, Poirot 45s, Schneier/Tetlock 30s,
Taleb 50s, Case-Writer 180s (longer prose), Locard 30×n_chunks.
UI integration:
- chat-bubble inline card paints each detective in its tone color.
- /jobs/[id] page header swaps name/subtitle/tone per detective;
question label adapts ("Topic" / "Hypothesis under attack" /
"Witness under analysis" / "Topic to outlier-scan" / "Hypothesis
under recalibration" / "Case to assemble").
- job-status-poller renders: case-report link card (gold), outlier
cards (yellow), witness cards (purple) — alongside existing
hypothesis, evidence, contradiction cards.
- /api/jobs/[id] hydrates witnesses (JOIN entities for canonical_name)
+ gaps (with scope JSONB).
- /c/[slug] page reads /data/ufo/case/reports/<slug>.md and renders
with MarkdownBody, frontmatter parsed for stat chips.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Adds the fourth AI detective in the Investigation Bureau runtime: Bruce
Schneier, who attacks an existing hypothesis as a red-team operator.
Runtime:
- prompts/schneier.md — discipline (don't disprove, just attack;
structured output with hidden_assumptions, failure_modes,
alternative_explanations, recommended_tests, verdict_one_sentence;
severity ∈ {low, medium, high}; emit INSUFFICIENT_HYPOTHESIS when
the input is too thin)
- src/detectives/schneier.ts — reads the hypothesis row + evidence
chain (joined via evidence_refs FK), feeds Claude with the
arguments + verbatim quotes, parses strict JSON object
- src/tools/write_red_team_review.ts — UPDATEs hypotheses.reviewed_by
+ updated_at; APPENDS (or replaces if re-reviewed) a structured
"## Red-team review (Schneier · X severity)" section to
case/hypotheses/H-NNNN.md. Caps each list at 5 entries × 240 chars,
validates verdict ≤ 280 chars.
- orchestrator: new `red_team_review` kind dispatching to runSchneier
Chat + UI:
- request_investigation gains kind=red_team_review + hypothesis_id arg
(validated against H-NNNN regex); detective auto-resolves to schneier
- chat-bubble inline card paints Schneier in red (#ff3344)
- /jobs/[id] page swaps title/subtitle/tone per detective; the
"Question" label becomes "Hypothesis under attack" for red_team_review
New /h/[hypothesisId] page (hypothesis dossier):
- Server-rendered from public.hypotheses + public.evidence (joined
via evidence_refs FK + chunk lookup)
- Header: ID + creator + reviewer (highlighted when Schneier has
visited), position as headline, question subtitle, Tetlock band
- Prior + posterior bars with Δ-delta indicator
- Argument grid: argument_for (green) vs argument_against (pink)
side-by-side with [[wiki-link]] auto-linking to source chunks
- Evidence chain: each E-NNNN with Grade A/B/C badge, verbatim
blockquote, link to source page
- Red-team review panel: parses the markdown section in the case
file (severity badge, verdict, 4 bullet panels for
hidden_assumptions / failure_modes / alternative_explanations /
recommended_tests). Empty state when not yet reviewed.
RedTeamRequestButton client component + POST /api/h/[id]/red-team —
authenticated user can trigger Schneier in one click; UI swaps to
"acompanhar" link to /jobs/[id] once queued.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Two regressions surfaced in the smoke test that put Dupin from
0/3 contradictions written → 3/3 in the next run.
1. Single-doc scope was too narrow for Dupin's task.
Holmes's question about Sandia returned 4 chunks scoped to one doc,
but Dupin's terser "topic" form yielded only 1. Solution: Pass-1
tries the requested doc_id; if the head is < 2 chunks, Pass-2
widens to the whole corpus. Audit event carries `scope_widened`
so the case-writer can later flag cross-doc contradictions
distinctly. The unscoped retry hit 9 chunks and produced 3
contradictions across 3 different docs.
2. Chunk-block header was ambiguous to the model.
`--- doc-id/p007#c0042 ---` led Claude to parse `chunk_id` as
"p007#c0042" or "p007/c0042" in the JSON output. write_contradiction
then refused the FK lookup with "chunk not found". Fix:
- Explicit `doc_id:` / `chunk_id:` / `page:` lines per chunk
in the rendered block (no slashes/hashes the model can fold).
- Defensive normalizeChunkId() in write_contradiction.ts strips
any pNNN prefix and keeps only the trailing cNNNN — so the
writer is forgiving without losing strictness on the topic +
statement validation.
Smoke now produces (job 6deddf4b):
R-0001 (3 chunks) — Color of the fireball(s) in incident summaries
R-0002 (2 chunks) — Geographic confinement of green-fireball sightings
R-0003 (3 chunks) — Whether the phenomenon was exclusively green or
also red/multicolored
R-0003 connects 3 different declassified documents: the Los Alamos
conference (exclusively-green category), a retrospective document
(red OR green), and Incident 229 (red, blue, yellow — no green).
Real cross-doc contradiction, fully cited.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Adds the third AI detective in the Investigation Bureau runtime: C. Auguste
Dupin, who scans a corpus shortlist for pairs (or small groups) of chunks
that cannot both be true under any ordinary reading.
Runtime:
- prompts/dupin.md — discipline (no contradiction without ≥2 distinct
chunk_ids; reject same-vocabulary near-misses; FEW high-confidence
over MANY weak ones; emit `NO_CONTRADICTIONS` when corpus is silent)
- src/detectives/dupin.ts — hybridSearch with k=18 (more chunks than
Holmes because contradictions emerge from comparing dispersed
claims), strict JSON-array parsing, AT MOST 3 contradictions per call
- src/tools/write_contradiction.ts — validates topic + ≥2 positions
drawn from ≥2 distinct chunks, resolves chunk_pk via DB lookup
(rejects positions citing unknown chunks), INSERTs into
public.contradictions + writes case/contradictions/R-NNNN.md
- orchestrator: new `contradiction_scan` kind dispatching to runDupin;
payload { topic, doc_id?, lang?, context_chunks? }
Chat + UI:
- request_investigation gains kind=contradiction_scan + topic arg;
triggered detective auto-resolves to dupin
- chat-bubble inline card renders dupin in orange (#ff8a4d) to
distinguish from holmes (cyan) and locard (green)
- /jobs/[id] page swaps title + subtitle + tone per detective;
"Question" label becomes "Topic" for contradiction_scan
- /api/jobs/[id] hydrates public.contradictions when outputs[] surfaces
contradiction_ids
- job-status-poller renders ContradictionCard: topic + N positions
(verbatim statements quoted, stance label optional, link to source
chunk) + optional notes panel, with resolution_status badge
(open/resolved/irreconcilable)
R-NNNN shares the contradiction_id_seq slot with relation per
CLAUDE.md naming — same conceptual class (a connection between two
pieces of evidence in tension).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Adds the second AI detective in the Investigation Bureau runtime: Sherlock
Holmes, who builds 2-3 rival hypotheses with calibrated priors + posteriors
against a corpus shortlist.
Pipeline:
1. hybridSearch() grounds Holmes with 8-15 chunks via the same
hybrid_search_chunks RPC the web uses (BM25 + dense + RRF). Default
max_dense_dist=0.55 (runtime favors recall over precision; web's
/api/search/hybrid stays at 0.40 for chat).
2. claude-sonnet-4-6 emits a strict JSON array with position +
argument_for + argument_against + prior + posterior + confidence_band
+ evidence_refs. Citations use [[doc-id/pNNN#cNNNN]] wiki-links.
3. writeHypothesis() validates posterior ∈ [0,1], auto-corrects the
Tetlock band from the posterior (high ≥0.90, medium 0.60-0.89,
low 0.30-0.59, speculation <0.30), checks evidence_refs FK against
public.evidence, INSERTs into public.hypotheses + writes
case/hypotheses/H-NNNN.md.
Discipline guarantees (prompts/holmes.md):
- posteriors across rivals sum to ≈1.0
- no claim without chunk citation
- prefer lower band when ambiguous (anti-inflation)
- declarative one-sentence position, no hedging
- emit `NO_HYPOTHESES` when corpus is silent (refuses to fabricate)
Smoke test (Sandia green fireballs 1948-49):
- H-0001 prior 0.5 → posterior 0.2 (speculation): natural meteoric
- H-0002 prior 0.3 → posterior 0.4 (low): classified weapons / tests
- H-0003 prior 0.2 → posterior 0.4 (low): genuinely unidentified
Bayesian update visible: "natural meteoric" prior dropped 60%; both
rivals climbed. 4 unique chunk citations across the 3 hypotheses.
orchestrator dispatches `hypothesis_tournament` kind via runHolmes;
job marked `failed` if all rivals error, `complete` otherwise.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Token consolidation:
- docker-compose web service now reads ${CLAUDE_CODE_OAUTH_TOKEN} directly,
drop the W1-F8 CLAUDE_CODE_OAUTH_TOKEN_FOR_WEB indirection (user feedback:
one var name, no _FOR_WEB suffix).
investigator-runtime claude.ts:
- --system-prompt silently dropped by CLI v2.1.150 for multi-KB prompts;
inline the system content into the user prompt with a separator
(mirrors scripts/reextract/run.py pattern).
- Multi-line prompts via positional -- broke ("Input must be provided …");
pipe via stdin instead.
- --allowedTools "" is rejected; when no tools wanted, omit it and explicitly
--disallowedTools the writer/reader set so the model can't reach for any.
investigator-runtime locard.ts:
- Log the raw response (first 600 chars) to container stderr — saved hours
of debugging when the writer rejected.
- Grade fallback: when Locard omits `grade` but provides custody_steps,
infer the highest grade that fits (≥3 → A, ≥2 → B, ≥1 → C).
investigator-runtime write_evidence.ts:
- Filter related_hypotheses entries with empty/null hypothesis_id silently
(Locard sometimes emits [{}] when it knows no link yet) instead of
failing the whole write.
Migration 0006_investigator_serial_sequences.sql:
- BIGSERIAL on the 7 investigation tables created auto-sequences
(evidence_evidence_pk_seq etc) that 0004 forgot to GRANT to the
investigator role. Without those grants every INSERT failed with
"permission denied for sequence …". Grant USAGE/SELECT/UPDATE on each
auto-seq.
Verified live: Locard wrote E-0002 + E-0003 from real Sandia chunks
(green fireball Feb 1949; cobalt particle analysis). Grade B, confidence
high, custody chain of 3 steps with honest gaps. Cost $0.09 for both,
~70s wall.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Luiz Gustavo