W3.6: chat request_investigation tool + /jobs/[id] case-file viewer
Closes the loop between the chat UI and the Investigation Bureau runtime.
Chat tool (web/lib/chat/tools.ts):
- request_investigation { kind, question, doc_id?, chunks?, claim? }
INSERTs a row in public.investigation_jobs and returns
{ job_id, kind, status, eta_seconds, status_url, detective }.
- kind=hypothesis_tournament → Holmes (1 question → 2-3 rival hypotheses)
- kind=evidence_chain → Locard (1 doc → grade-A/B/C evidence with chain
of custody, default top-5 anomaly chunks)
- Plumbed user.email through ToolHandlerContext so triggered_by audits
the requesting user.
Public job viewer:
- GET /api/jobs/[id] joins investigation_jobs → public.evidence +
public.hypotheses for the IDs surfaced in outputs[]. Returns one
payload the page can render without n+1 round-trips. Strips
triggered_by from the response (it carries the user's email).
- app/jobs/[id]/page.tsx server-renders the case-file shell:
detective lore header (Holmes blue or Locard green), question chip,
scope chip with link back to the document.
- components/job-status-poller.tsx client island that polls every 3 s
while non-terminal, then once on terminal to hydrate evidence +
hypotheses. Renders:
· Phase tracker (queued → running → complete | failed)
· Hypothesis cards w/ prior + posterior bars + Δ delta indicator
+ Tetlock band badge (high/medium/low/speculation)
· Argument-for / argument-against with [[wiki-link]] auto-linking
to /d/<doc>/p<NNN>#<cNNNN>
· Evidence cards w/ Grade A/B/C badge + verbatim blockquote +
bbox crop preview via /api/crop + custody-steps disclosure
· Empty/in-flight panel ("os detetives estão lendo o corpus")
· Failure panel surfacing error + partial outputs
Inline chat-bubble card (components/chat-bubble.tsx):
- ToolTrace.richRender recognises request_investigation results and
renders a detective banner with status + ETA + link to /jobs/[id]
(target=_blank). Error case renders a red strip with the message.
UX flow now: user asks Sherlock a question → request_investigation
queues the job → chat card shows "🔎 Holmes · hypothesis_tournament ·
ETA ~60s" → user clicks → /jobs/<id> live-updates → 60 s later, 2-3
rival hypotheses + their arguments + chunk citations are rendered with
Bayesian update visible.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-24 00:26:18 +00:00
|
|
|
/**
|
|
|
|
|
* /jobs/[id] — Investigation Bureau case file viewer.
|
|
|
|
|
*
|
|
|
|
|
* Server-rendered shell with the first snapshot fetched directly from
|
|
|
|
|
* pg (one round-trip). A client island then polls /api/jobs/[id] every 3s
|
|
|
|
|
* while the job is non-terminal (queued | running).
|
|
|
|
|
*
|
|
|
|
|
* Detectives:
|
|
|
|
|
* - hypothesis_tournament → Sherlock Holmes
|
|
|
|
|
* - evidence_chain → Edmond Locard
|
|
|
|
|
*
|
|
|
|
|
* Renders:
|
|
|
|
|
* - Phase tracker (queued → claimed → running → complete | failed)
|
|
|
|
|
* - Hypothesis cards w/ prior+posterior bars + Tetlock confidence_band badge
|
|
|
|
|
* - Evidence cards w/ grade A/B/C badge + verbatim_excerpt + bbox crop link
|
|
|
|
|
*/
|
|
|
|
|
import { notFound } from "next/navigation";
|
|
|
|
|
import Link from "next/link";
|
|
|
|
|
import { pgQuery } from "@/lib/retrieval/db";
|
|
|
|
|
import { AuthBar } from "@/components/auth-bar";
|
W4.1+W4.2: anti-AI-tics house style + bureau nav (back/home everywhere)
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>
2026-05-24 16:27:58 +00:00
|
|
|
import { BureauNav } from "@/components/bureau-nav";
|
W3.6: chat request_investigation tool + /jobs/[id] case-file viewer
Closes the loop between the chat UI and the Investigation Bureau runtime.
Chat tool (web/lib/chat/tools.ts):
- request_investigation { kind, question, doc_id?, chunks?, claim? }
INSERTs a row in public.investigation_jobs and returns
{ job_id, kind, status, eta_seconds, status_url, detective }.
- kind=hypothesis_tournament → Holmes (1 question → 2-3 rival hypotheses)
- kind=evidence_chain → Locard (1 doc → grade-A/B/C evidence with chain
of custody, default top-5 anomaly chunks)
- Plumbed user.email through ToolHandlerContext so triggered_by audits
the requesting user.
Public job viewer:
- GET /api/jobs/[id] joins investigation_jobs → public.evidence +
public.hypotheses for the IDs surfaced in outputs[]. Returns one
payload the page can render without n+1 round-trips. Strips
triggered_by from the response (it carries the user's email).
- app/jobs/[id]/page.tsx server-renders the case-file shell:
detective lore header (Holmes blue or Locard green), question chip,
scope chip with link back to the document.
- components/job-status-poller.tsx client island that polls every 3 s
while non-terminal, then once on terminal to hydrate evidence +
hypotheses. Renders:
· Phase tracker (queued → running → complete | failed)
· Hypothesis cards w/ prior + posterior bars + Δ delta indicator
+ Tetlock band badge (high/medium/low/speculation)
· Argument-for / argument-against with [[wiki-link]] auto-linking
to /d/<doc>/p<NNN>#<cNNNN>
· Evidence cards w/ Grade A/B/C badge + verbatim blockquote +
bbox crop preview via /api/crop + custody-steps disclosure
· Empty/in-flight panel ("os detetives estão lendo o corpus")
· Failure panel surfacing error + partial outputs
Inline chat-bubble card (components/chat-bubble.tsx):
- ToolTrace.richRender recognises request_investigation results and
renders a detective banner with status + ETA + link to /jobs/[id]
(target=_blank). Error case renders a red strip with the message.
UX flow now: user asks Sherlock a question → request_investigation
queues the job → chat card shows "🔎 Holmes · hypothesis_tournament ·
ETA ~60s" → user clicks → /jobs/<id> live-updates → 60 s later, 2-3
rival hypotheses + their arguments + chunk citations are rendered with
Bayesian update visible.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-24 00:26:18 +00:00
|
|
|
import { JobStatusPoller } from "@/components/job-status-poller";
|
|
|
|
|
|
|
|
|
|
export const runtime = "nodejs";
|
|
|
|
|
export const dynamic = "force-dynamic";
|
|
|
|
|
|
|
|
|
|
interface InitialJob {
|
|
|
|
|
job_id: string;
|
|
|
|
|
kind: string;
|
|
|
|
|
payload: Record<string, unknown> | null;
|
|
|
|
|
status: string;
|
|
|
|
|
worker_id: string | null;
|
|
|
|
|
started_at: string | null;
|
|
|
|
|
finished_at: string | null;
|
|
|
|
|
outputs: unknown;
|
|
|
|
|
error: string | null;
|
|
|
|
|
created_at: string;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
export default async function JobPage({
|
|
|
|
|
params,
|
|
|
|
|
}: { params: Promise<{ id: string }> }) {
|
|
|
|
|
const { id } = await params;
|
|
|
|
|
if (!/^[0-9a-f-]{36}$/i.test(id)) notFound();
|
|
|
|
|
|
|
|
|
|
const rows = await pgQuery<InitialJob>(
|
|
|
|
|
`SELECT job_id, kind, payload, status, worker_id, started_at, finished_at,
|
|
|
|
|
outputs, error, created_at
|
|
|
|
|
FROM public.investigation_jobs WHERE job_id = $1`,
|
|
|
|
|
[id],
|
|
|
|
|
).catch(() => [] as InitialJob[]);
|
|
|
|
|
const job = rows[0];
|
|
|
|
|
if (!job) notFound();
|
|
|
|
|
|
W5.1: enthusiast pivot — strip detective surfacing, magazine homepage
User explicit: "1 bilhão de entusiastas pelo mundo ovni" — site is for the
UFO-curious public, not for skeptics. The 8-detective scaffolding becomes
invisible plumbing; the reader sees stories about what was observed.
Reader-facing changes:
New homepage (web/app/page.tsx)
- SiteHeader: magazine-style top nav (no detective tiles)
- HeroBanner: full-bleed editorial opener with declassified-page art
background, display-serif headline, live stats row (122 docs,
2047 events, 1861 witnesses, 867 craft catalogued)
- FeaturedCase: cover-story treatment of the most recent case_report,
uses a real document page as hero image, links to /c/[slug]
- PortalGrid: 6 thematic doorways into the archive — Sightings,
Witnesses, Craft, Hot spots, Programs, Documents — each tile shows
a real entity count and short editorial blurb
- GreatestHits: top 9 most-cited events from the corpus
(Kenneth Arnold 1947, Mantell 1948, …) as a magazine grid
- Doc list kept but reframed as "the primary record"
New sub-pages (5)
- /sightings → events (2047), magazine grid
- /witnesses → people (1861), compact table
- /objects → uap_objects (867), magazine grid
- /locations → locations (1757), compact table
- /operations → organizations (1596), compact table
- /documents → full doc list with thumbnails (mirrors homepage section
for direct deep-link)
All share <EntityListPage> shell with per-page i18n + JSON-LD ItemList
Stripped detective surfacing
- /jobs/[id]: "Sherlock Holmes / Dr. Watson" → "Investigation in progress"
- chat-bubble: detective-named card → neutral "Investigação em andamento"
- quick-launch: 7-kind detective dropdown → single "investigar um caso"
input (kind=case_report hardcoded)
- /bureau: rewritten as the case-file library (no artefact dumps)
Typography + design
- Fraunces variable serif loaded for display headings
(`.font-display` class)
- Gold-amber accent (#e0c080) unified as the brand colour
- Asymmetric magazine grids (1+2+3 column, generous whitespace)
- Hover micro-interactions (image scale on featured case, translateX
on portal arrows)
SEO + GEO
- layout.tsx metadataBase + title.template + per-route Metadata exports
- Organization JSON-LD on root layout
- WebSite + SearchAction JSON-LD on homepage
- CollectionPage + ItemList JSON-LD on every entity list page
- openGraph + twitter cards, pt-BR primary + en-US alternate
- ai:purpose meta tag for Generative Engine Optimization — declares
the site as a citation-linked primary-source archive
- robots: index + follow with large image preview
The detectives themselves remain alive in the backend (runtime, DB, audit
log), but the reader never sees "Holmes / Sun-Tzu / Watson" in the UI. The
next phase will reorient case-writer to write as a single best-seller voice
synthesising all the internal sources.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-24 17:09:46 +00:00
|
|
|
// Reader-facing: no detective surfacing. Every kind reads as "case
|
|
|
|
|
// investigation in progress" with neutral copy. Detective identities
|
|
|
|
|
// remain internal in the runtime (audit log) but never reach the UI.
|
|
|
|
|
const detectiveName = "Investigation in progress";
|
W3.7: Dupin contradiction-scan detective + UI integration
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>
2026-05-24 00:34:04 +00:00
|
|
|
const detectiveSubtitle =
|
W5.1: enthusiast pivot — strip detective surfacing, magazine homepage
User explicit: "1 bilhão de entusiastas pelo mundo ovni" — site is for the
UFO-curious public, not for skeptics. The 8-detective scaffolding becomes
invisible plumbing; the reader sees stories about what was observed.
Reader-facing changes:
New homepage (web/app/page.tsx)
- SiteHeader: magazine-style top nav (no detective tiles)
- HeroBanner: full-bleed editorial opener with declassified-page art
background, display-serif headline, live stats row (122 docs,
2047 events, 1861 witnesses, 867 craft catalogued)
- FeaturedCase: cover-story treatment of the most recent case_report,
uses a real document page as hero image, links to /c/[slug]
- PortalGrid: 6 thematic doorways into the archive — Sightings,
Witnesses, Craft, Hot spots, Programs, Documents — each tile shows
a real entity count and short editorial blurb
- GreatestHits: top 9 most-cited events from the corpus
(Kenneth Arnold 1947, Mantell 1948, …) as a magazine grid
- Doc list kept but reframed as "the primary record"
New sub-pages (5)
- /sightings → events (2047), magazine grid
- /witnesses → people (1861), compact table
- /objects → uap_objects (867), magazine grid
- /locations → locations (1757), compact table
- /operations → organizations (1596), compact table
- /documents → full doc list with thumbnails (mirrors homepage section
for direct deep-link)
All share <EntityListPage> shell with per-page i18n + JSON-LD ItemList
Stripped detective surfacing
- /jobs/[id]: "Sherlock Holmes / Dr. Watson" → "Investigation in progress"
- chat-bubble: detective-named card → neutral "Investigação em andamento"
- quick-launch: 7-kind detective dropdown → single "investigar um caso"
input (kind=case_report hardcoded)
- /bureau: rewritten as the case-file library (no artefact dumps)
Typography + design
- Fraunces variable serif loaded for display headings
(`.font-display` class)
- Gold-amber accent (#e0c080) unified as the brand colour
- Asymmetric magazine grids (1+2+3 column, generous whitespace)
- Hover micro-interactions (image scale on featured case, translateX
on portal arrows)
SEO + GEO
- layout.tsx metadataBase + title.template + per-route Metadata exports
- Organization JSON-LD on root layout
- WebSite + SearchAction JSON-LD on homepage
- CollectionPage + ItemList JSON-LD on every entity list page
- openGraph + twitter cards, pt-BR primary + en-US alternate
- ai:purpose meta tag for Generative Engine Optimization — declares
the site as a citation-linked primary-source archive
- robots: index + follow with large image preview
The detectives themselves remain alive in the backend (runtime, DB, audit
log), but the reader never sees "Holmes / Sun-Tzu / Watson" in the UI. The
next phase will reorient case-writer to write as a single best-seller voice
synthesising all the internal sources.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-24 17:09:46 +00:00
|
|
|
job.kind === "case_report" ? "Assembling a narrative case file from the primary record" :
|
|
|
|
|
job.kind === "evidence_chain" ? "Pulling verbatim citations from the document" :
|
|
|
|
|
"Reading the archive for this case";
|
|
|
|
|
const detectiveTone = "text-[#e0c080]";
|
|
|
|
|
const detectiveBg = "from-[rgba(224,192,128,0.06)]";
|
W3.7: Dupin contradiction-scan detective + UI integration
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>
2026-05-24 00:34:04 +00:00
|
|
|
const payload = (job.payload ?? {}) as Record<string, unknown>;
|
W3.8: Investigation Bureau complete — Poirot, Taleb, Tetlock, Case-Writer
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>
2026-05-24 01:11:39 +00:00
|
|
|
const question = (payload.question ?? payload.topic ?? payload.hypothesis_id ?? payload.person_id) as string | undefined;
|
W3.8: Schneier red-team detective + /h/[hypothesisId] dossier page
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>
2026-05-24 00:48:12 +00:00
|
|
|
const questionLabel =
|
|
|
|
|
job.kind === "contradiction_scan" ? "Topic" :
|
|
|
|
|
job.kind === "red_team_review" ? "Hypothesis under attack" :
|
W3.8: Investigation Bureau complete — Poirot, Taleb, Tetlock, Case-Writer
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>
2026-05-24 01:11:39 +00:00
|
|
|
job.kind === "witness_analysis" ? "Witness under analysis" :
|
|
|
|
|
job.kind === "outlier_scan" ? "Topic to outlier-scan" :
|
|
|
|
|
job.kind === "calibrate_hypothesis" ? "Hypothesis under recalibration" :
|
|
|
|
|
job.kind === "case_report" ? "Case to assemble" :
|
W3.8: Schneier red-team detective + /h/[hypothesisId] dossier page
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>
2026-05-24 00:48:12 +00:00
|
|
|
"Question";
|
W3.7: Dupin contradiction-scan detective + UI integration
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>
2026-05-24 00:34:04 +00:00
|
|
|
const docId = payload.doc_id as string | undefined;
|
W3.6: chat request_investigation tool + /jobs/[id] case-file viewer
Closes the loop between the chat UI and the Investigation Bureau runtime.
Chat tool (web/lib/chat/tools.ts):
- request_investigation { kind, question, doc_id?, chunks?, claim? }
INSERTs a row in public.investigation_jobs and returns
{ job_id, kind, status, eta_seconds, status_url, detective }.
- kind=hypothesis_tournament → Holmes (1 question → 2-3 rival hypotheses)
- kind=evidence_chain → Locard (1 doc → grade-A/B/C evidence with chain
of custody, default top-5 anomaly chunks)
- Plumbed user.email through ToolHandlerContext so triggered_by audits
the requesting user.
Public job viewer:
- GET /api/jobs/[id] joins investigation_jobs → public.evidence +
public.hypotheses for the IDs surfaced in outputs[]. Returns one
payload the page can render without n+1 round-trips. Strips
triggered_by from the response (it carries the user's email).
- app/jobs/[id]/page.tsx server-renders the case-file shell:
detective lore header (Holmes blue or Locard green), question chip,
scope chip with link back to the document.
- components/job-status-poller.tsx client island that polls every 3 s
while non-terminal, then once on terminal to hydrate evidence +
hypotheses. Renders:
· Phase tracker (queued → running → complete | failed)
· Hypothesis cards w/ prior + posterior bars + Δ delta indicator
+ Tetlock band badge (high/medium/low/speculation)
· Argument-for / argument-against with [[wiki-link]] auto-linking
to /d/<doc>/p<NNN>#<cNNNN>
· Evidence cards w/ Grade A/B/C badge + verbatim blockquote +
bbox crop preview via /api/crop + custody-steps disclosure
· Empty/in-flight panel ("os detetives estão lendo o corpus")
· Failure panel surfacing error + partial outputs
Inline chat-bubble card (components/chat-bubble.tsx):
- ToolTrace.richRender recognises request_investigation results and
renders a detective banner with status + ETA + link to /jobs/[id]
(target=_blank). Error case renders a red strip with the message.
UX flow now: user asks Sherlock a question → request_investigation
queues the job → chat card shows "🔎 Holmes · hypothesis_tournament ·
ETA ~60s" → user clicks → /jobs/<id> live-updates → 60 s later, 2-3
rival hypotheses + their arguments + chunk citations are rendered with
Bayesian update visible.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-24 00:26:18 +00:00
|
|
|
|
|
|
|
|
return (
|
|
|
|
|
<div className="min-h-screen bg-[#0a0e1a] text-[#e7ecf3]">
|
W4.1+W4.2: anti-AI-tics house style + bureau nav (back/home everywhere)
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>
2026-05-24 16:27:58 +00:00
|
|
|
<BureauNav crumbs={[
|
|
|
|
|
{ label: "bureau", href: "/bureau" },
|
|
|
|
|
{ label: "jobs", href: "/bureau#jobs" },
|
|
|
|
|
{ label: job.job_id.slice(0, 8) },
|
|
|
|
|
]} />
|
W3.6: chat request_investigation tool + /jobs/[id] case-file viewer
Closes the loop between the chat UI and the Investigation Bureau runtime.
Chat tool (web/lib/chat/tools.ts):
- request_investigation { kind, question, doc_id?, chunks?, claim? }
INSERTs a row in public.investigation_jobs and returns
{ job_id, kind, status, eta_seconds, status_url, detective }.
- kind=hypothesis_tournament → Holmes (1 question → 2-3 rival hypotheses)
- kind=evidence_chain → Locard (1 doc → grade-A/B/C evidence with chain
of custody, default top-5 anomaly chunks)
- Plumbed user.email through ToolHandlerContext so triggered_by audits
the requesting user.
Public job viewer:
- GET /api/jobs/[id] joins investigation_jobs → public.evidence +
public.hypotheses for the IDs surfaced in outputs[]. Returns one
payload the page can render without n+1 round-trips. Strips
triggered_by from the response (it carries the user's email).
- app/jobs/[id]/page.tsx server-renders the case-file shell:
detective lore header (Holmes blue or Locard green), question chip,
scope chip with link back to the document.
- components/job-status-poller.tsx client island that polls every 3 s
while non-terminal, then once on terminal to hydrate evidence +
hypotheses. Renders:
· Phase tracker (queued → running → complete | failed)
· Hypothesis cards w/ prior + posterior bars + Δ delta indicator
+ Tetlock band badge (high/medium/low/speculation)
· Argument-for / argument-against with [[wiki-link]] auto-linking
to /d/<doc>/p<NNN>#<cNNNN>
· Evidence cards w/ Grade A/B/C badge + verbatim blockquote +
bbox crop preview via /api/crop + custody-steps disclosure
· Empty/in-flight panel ("os detetives estão lendo o corpus")
· Failure panel surfacing error + partial outputs
Inline chat-bubble card (components/chat-bubble.tsx):
- ToolTrace.richRender recognises request_investigation results and
renders a detective banner with status + ETA + link to /jobs/[id]
(target=_blank). Error case renders a red strip with the message.
UX flow now: user asks Sherlock a question → request_investigation
queues the job → chat card shows "🔎 Holmes · hypothesis_tournament ·
ETA ~60s" → user clicks → /jobs/<id> live-updates → 60 s later, 2-3
rival hypotheses + their arguments + chunk citations are rendered with
Bayesian update visible.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-24 00:26:18 +00:00
|
|
|
<AuthBar />
|
W4.1+W4.2: anti-AI-tics house style + bureau nav (back/home everywhere)
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>
2026-05-24 16:27:58 +00:00
|
|
|
<div className="mx-auto max-w-5xl px-4 py-6 pt-4">
|
W3.6: chat request_investigation tool + /jobs/[id] case-file viewer
Closes the loop between the chat UI and the Investigation Bureau runtime.
Chat tool (web/lib/chat/tools.ts):
- request_investigation { kind, question, doc_id?, chunks?, claim? }
INSERTs a row in public.investigation_jobs and returns
{ job_id, kind, status, eta_seconds, status_url, detective }.
- kind=hypothesis_tournament → Holmes (1 question → 2-3 rival hypotheses)
- kind=evidence_chain → Locard (1 doc → grade-A/B/C evidence with chain
of custody, default top-5 anomaly chunks)
- Plumbed user.email through ToolHandlerContext so triggered_by audits
the requesting user.
Public job viewer:
- GET /api/jobs/[id] joins investigation_jobs → public.evidence +
public.hypotheses for the IDs surfaced in outputs[]. Returns one
payload the page can render without n+1 round-trips. Strips
triggered_by from the response (it carries the user's email).
- app/jobs/[id]/page.tsx server-renders the case-file shell:
detective lore header (Holmes blue or Locard green), question chip,
scope chip with link back to the document.
- components/job-status-poller.tsx client island that polls every 3 s
while non-terminal, then once on terminal to hydrate evidence +
hypotheses. Renders:
· Phase tracker (queued → running → complete | failed)
· Hypothesis cards w/ prior + posterior bars + Δ delta indicator
+ Tetlock band badge (high/medium/low/speculation)
· Argument-for / argument-against with [[wiki-link]] auto-linking
to /d/<doc>/p<NNN>#<cNNNN>
· Evidence cards w/ Grade A/B/C badge + verbatim blockquote +
bbox crop preview via /api/crop + custody-steps disclosure
· Empty/in-flight panel ("os detetives estão lendo o corpus")
· Failure panel surfacing error + partial outputs
Inline chat-bubble card (components/chat-bubble.tsx):
- ToolTrace.richRender recognises request_investigation results and
renders a detective banner with status + ETA + link to /jobs/[id]
(target=_blank). Error case renders a red strip with the message.
UX flow now: user asks Sherlock a question → request_investigation
queues the job → chat card shows "🔎 Holmes · hypothesis_tournament ·
ETA ~60s" → user clicks → /jobs/<id> live-updates → 60 s later, 2-3
rival hypotheses + their arguments + chunk citations are rendered with
Bayesian update visible.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-24 00:26:18 +00:00
|
|
|
|
|
|
|
|
<div className={`rounded-lg border border-[rgba(127,219,255,0.18)] bg-gradient-to-br ${detectiveBg} to-transparent p-5`}>
|
|
|
|
|
<div className="flex items-baseline justify-between gap-4 flex-wrap">
|
|
|
|
|
<div>
|
|
|
|
|
<h1 className={`text-2xl font-mono font-bold ${detectiveTone}`}>
|
|
|
|
|
{detectiveName}
|
|
|
|
|
</h1>
|
W3.7: Dupin contradiction-scan detective + UI integration
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>
2026-05-24 00:34:04 +00:00
|
|
|
<p className="text-[12px] text-[#9aa6b8] mt-1 font-mono">{detectiveSubtitle}</p>
|
W3.6: chat request_investigation tool + /jobs/[id] case-file viewer
Closes the loop between the chat UI and the Investigation Bureau runtime.
Chat tool (web/lib/chat/tools.ts):
- request_investigation { kind, question, doc_id?, chunks?, claim? }
INSERTs a row in public.investigation_jobs and returns
{ job_id, kind, status, eta_seconds, status_url, detective }.
- kind=hypothesis_tournament → Holmes (1 question → 2-3 rival hypotheses)
- kind=evidence_chain → Locard (1 doc → grade-A/B/C evidence with chain
of custody, default top-5 anomaly chunks)
- Plumbed user.email through ToolHandlerContext so triggered_by audits
the requesting user.
Public job viewer:
- GET /api/jobs/[id] joins investigation_jobs → public.evidence +
public.hypotheses for the IDs surfaced in outputs[]. Returns one
payload the page can render without n+1 round-trips. Strips
triggered_by from the response (it carries the user's email).
- app/jobs/[id]/page.tsx server-renders the case-file shell:
detective lore header (Holmes blue or Locard green), question chip,
scope chip with link back to the document.
- components/job-status-poller.tsx client island that polls every 3 s
while non-terminal, then once on terminal to hydrate evidence +
hypotheses. Renders:
· Phase tracker (queued → running → complete | failed)
· Hypothesis cards w/ prior + posterior bars + Δ delta indicator
+ Tetlock band badge (high/medium/low/speculation)
· Argument-for / argument-against with [[wiki-link]] auto-linking
to /d/<doc>/p<NNN>#<cNNNN>
· Evidence cards w/ Grade A/B/C badge + verbatim blockquote +
bbox crop preview via /api/crop + custody-steps disclosure
· Empty/in-flight panel ("os detetives estão lendo o corpus")
· Failure panel surfacing error + partial outputs
Inline chat-bubble card (components/chat-bubble.tsx):
- ToolTrace.richRender recognises request_investigation results and
renders a detective banner with status + ETA + link to /jobs/[id]
(target=_blank). Error case renders a red strip with the message.
UX flow now: user asks Sherlock a question → request_investigation
queues the job → chat card shows "🔎 Holmes · hypothesis_tournament ·
ETA ~60s" → user clicks → /jobs/<id> live-updates → 60 s later, 2-3
rival hypotheses + their arguments + chunk citations are rendered with
Bayesian update visible.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-24 00:26:18 +00:00
|
|
|
</div>
|
|
|
|
|
<span className={`px-2 py-0.5 rounded text-[10px] font-mono uppercase border ${detectiveTone} border-current`}>
|
W5.1: enthusiast pivot — strip detective surfacing, magazine homepage
User explicit: "1 bilhão de entusiastas pelo mundo ovni" — site is for the
UFO-curious public, not for skeptics. The 8-detective scaffolding becomes
invisible plumbing; the reader sees stories about what was observed.
Reader-facing changes:
New homepage (web/app/page.tsx)
- SiteHeader: magazine-style top nav (no detective tiles)
- HeroBanner: full-bleed editorial opener with declassified-page art
background, display-serif headline, live stats row (122 docs,
2047 events, 1861 witnesses, 867 craft catalogued)
- FeaturedCase: cover-story treatment of the most recent case_report,
uses a real document page as hero image, links to /c/[slug]
- PortalGrid: 6 thematic doorways into the archive — Sightings,
Witnesses, Craft, Hot spots, Programs, Documents — each tile shows
a real entity count and short editorial blurb
- GreatestHits: top 9 most-cited events from the corpus
(Kenneth Arnold 1947, Mantell 1948, …) as a magazine grid
- Doc list kept but reframed as "the primary record"
New sub-pages (5)
- /sightings → events (2047), magazine grid
- /witnesses → people (1861), compact table
- /objects → uap_objects (867), magazine grid
- /locations → locations (1757), compact table
- /operations → organizations (1596), compact table
- /documents → full doc list with thumbnails (mirrors homepage section
for direct deep-link)
All share <EntityListPage> shell with per-page i18n + JSON-LD ItemList
Stripped detective surfacing
- /jobs/[id]: "Sherlock Holmes / Dr. Watson" → "Investigation in progress"
- chat-bubble: detective-named card → neutral "Investigação em andamento"
- quick-launch: 7-kind detective dropdown → single "investigar um caso"
input (kind=case_report hardcoded)
- /bureau: rewritten as the case-file library (no artefact dumps)
Typography + design
- Fraunces variable serif loaded for display headings
(`.font-display` class)
- Gold-amber accent (#e0c080) unified as the brand colour
- Asymmetric magazine grids (1+2+3 column, generous whitespace)
- Hover micro-interactions (image scale on featured case, translateX
on portal arrows)
SEO + GEO
- layout.tsx metadataBase + title.template + per-route Metadata exports
- Organization JSON-LD on root layout
- WebSite + SearchAction JSON-LD on homepage
- CollectionPage + ItemList JSON-LD on every entity list page
- openGraph + twitter cards, pt-BR primary + en-US alternate
- ai:purpose meta tag for Generative Engine Optimization — declares
the site as a citation-linked primary-source archive
- robots: index + follow with large image preview
The detectives themselves remain alive in the backend (runtime, DB, audit
log), but the reader never sees "Holmes / Sun-Tzu / Watson" in the UI. The
next phase will reorient case-writer to write as a single best-seller voice
synthesising all the internal sources.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-24 17:09:46 +00:00
|
|
|
{job.kind}
|
W3.6: chat request_investigation tool + /jobs/[id] case-file viewer
Closes the loop between the chat UI and the Investigation Bureau runtime.
Chat tool (web/lib/chat/tools.ts):
- request_investigation { kind, question, doc_id?, chunks?, claim? }
INSERTs a row in public.investigation_jobs and returns
{ job_id, kind, status, eta_seconds, status_url, detective }.
- kind=hypothesis_tournament → Holmes (1 question → 2-3 rival hypotheses)
- kind=evidence_chain → Locard (1 doc → grade-A/B/C evidence with chain
of custody, default top-5 anomaly chunks)
- Plumbed user.email through ToolHandlerContext so triggered_by audits
the requesting user.
Public job viewer:
- GET /api/jobs/[id] joins investigation_jobs → public.evidence +
public.hypotheses for the IDs surfaced in outputs[]. Returns one
payload the page can render without n+1 round-trips. Strips
triggered_by from the response (it carries the user's email).
- app/jobs/[id]/page.tsx server-renders the case-file shell:
detective lore header (Holmes blue or Locard green), question chip,
scope chip with link back to the document.
- components/job-status-poller.tsx client island that polls every 3 s
while non-terminal, then once on terminal to hydrate evidence +
hypotheses. Renders:
· Phase tracker (queued → running → complete | failed)
· Hypothesis cards w/ prior + posterior bars + Δ delta indicator
+ Tetlock band badge (high/medium/low/speculation)
· Argument-for / argument-against with [[wiki-link]] auto-linking
to /d/<doc>/p<NNN>#<cNNNN>
· Evidence cards w/ Grade A/B/C badge + verbatim blockquote +
bbox crop preview via /api/crop + custody-steps disclosure
· Empty/in-flight panel ("os detetives estão lendo o corpus")
· Failure panel surfacing error + partial outputs
Inline chat-bubble card (components/chat-bubble.tsx):
- ToolTrace.richRender recognises request_investigation results and
renders a detective banner with status + ETA + link to /jobs/[id]
(target=_blank). Error case renders a red strip with the message.
UX flow now: user asks Sherlock a question → request_investigation
queues the job → chat card shows "🔎 Holmes · hypothesis_tournament ·
ETA ~60s" → user clicks → /jobs/<id> live-updates → 60 s later, 2-3
rival hypotheses + their arguments + chunk citations are rendered with
Bayesian update visible.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-24 00:26:18 +00:00
|
|
|
</span>
|
|
|
|
|
</div>
|
|
|
|
|
|
|
|
|
|
{question && (
|
|
|
|
|
<div className="mt-4 p-3 bg-[#060a13] rounded border border-[rgba(127,219,255,0.1)]">
|
W3.7: Dupin contradiction-scan detective + UI integration
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>
2026-05-24 00:34:04 +00:00
|
|
|
<div className="text-[10px] text-[#5a6678] font-mono uppercase mb-1">{questionLabel}</div>
|
W3.6: chat request_investigation tool + /jobs/[id] case-file viewer
Closes the loop between the chat UI and the Investigation Bureau runtime.
Chat tool (web/lib/chat/tools.ts):
- request_investigation { kind, question, doc_id?, chunks?, claim? }
INSERTs a row in public.investigation_jobs and returns
{ job_id, kind, status, eta_seconds, status_url, detective }.
- kind=hypothesis_tournament → Holmes (1 question → 2-3 rival hypotheses)
- kind=evidence_chain → Locard (1 doc → grade-A/B/C evidence with chain
of custody, default top-5 anomaly chunks)
- Plumbed user.email through ToolHandlerContext so triggered_by audits
the requesting user.
Public job viewer:
- GET /api/jobs/[id] joins investigation_jobs → public.evidence +
public.hypotheses for the IDs surfaced in outputs[]. Returns one
payload the page can render without n+1 round-trips. Strips
triggered_by from the response (it carries the user's email).
- app/jobs/[id]/page.tsx server-renders the case-file shell:
detective lore header (Holmes blue or Locard green), question chip,
scope chip with link back to the document.
- components/job-status-poller.tsx client island that polls every 3 s
while non-terminal, then once on terminal to hydrate evidence +
hypotheses. Renders:
· Phase tracker (queued → running → complete | failed)
· Hypothesis cards w/ prior + posterior bars + Δ delta indicator
+ Tetlock band badge (high/medium/low/speculation)
· Argument-for / argument-against with [[wiki-link]] auto-linking
to /d/<doc>/p<NNN>#<cNNNN>
· Evidence cards w/ Grade A/B/C badge + verbatim blockquote +
bbox crop preview via /api/crop + custody-steps disclosure
· Empty/in-flight panel ("os detetives estão lendo o corpus")
· Failure panel surfacing error + partial outputs
Inline chat-bubble card (components/chat-bubble.tsx):
- ToolTrace.richRender recognises request_investigation results and
renders a detective banner with status + ETA + link to /jobs/[id]
(target=_blank). Error case renders a red strip with the message.
UX flow now: user asks Sherlock a question → request_investigation
queues the job → chat card shows "🔎 Holmes · hypothesis_tournament ·
ETA ~60s" → user clicks → /jobs/<id> live-updates → 60 s later, 2-3
rival hypotheses + their arguments + chunk citations are rendered with
Bayesian update visible.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-24 00:26:18 +00:00
|
|
|
<div className="text-[14px] text-[#e7ecf3] leading-snug">{question}</div>
|
|
|
|
|
</div>
|
|
|
|
|
)}
|
|
|
|
|
{docId && (
|
|
|
|
|
<div className="mt-2 text-[11px] font-mono text-[#9aa6b8]">
|
|
|
|
|
Scope: <Link href={`/d/${docId}`} className="text-[#7fdbff] hover:underline">{docId}</Link>
|
|
|
|
|
</div>
|
|
|
|
|
)}
|
|
|
|
|
</div>
|
|
|
|
|
|
|
|
|
|
<JobStatusPoller
|
|
|
|
|
jobId={job.job_id}
|
|
|
|
|
initialJob={{
|
|
|
|
|
job_id: job.job_id,
|
|
|
|
|
kind: job.kind,
|
|
|
|
|
payload: job.payload,
|
|
|
|
|
status: job.status,
|
|
|
|
|
worker_id: job.worker_id,
|
|
|
|
|
started_at: job.started_at,
|
|
|
|
|
finished_at: job.finished_at,
|
|
|
|
|
created_at: job.created_at,
|
|
|
|
|
outputs: Array.isArray(job.outputs) ? job.outputs : [],
|
|
|
|
|
error: job.error,
|
|
|
|
|
}}
|
|
|
|
|
/>
|
|
|
|
|
</div>
|
|
|
|
|
</div>
|
|
|
|
|
);
|
|
|
|
|
}
|