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>
140 lines
4.7 KiB
TypeScript
140 lines
4.7 KiB
TypeScript
/**
|
|
* GET /api/jobs/[id] — public read of an investigation_jobs row.
|
|
*
|
|
* Hydrates the outputs[] payload by joining to public.evidence / public.hypotheses
|
|
* so the /jobs/[id] page can render evidence cards + hypothesis cards without
|
|
* n+1 round-trips.
|
|
*
|
|
* No auth required (read-only): anyone with a job_id can see status. This
|
|
* matches the chat tool's UX: the chat reveals the URL, the user opens it,
|
|
* the page renders. No PII is exposed beyond what the user already typed
|
|
* (triggered_by carries their email — we strip it).
|
|
*/
|
|
import { NextResponse } from "next/server";
|
|
import { pgQuery } from "@/lib/retrieval/db";
|
|
|
|
export const runtime = "nodejs";
|
|
export const dynamic = "force-dynamic";
|
|
|
|
interface JobRow {
|
|
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;
|
|
}
|
|
|
|
interface EvidenceRow {
|
|
evidence_id: string;
|
|
grade: string | null;
|
|
source_page_id: string;
|
|
doc_id: string | null;
|
|
page: number | null;
|
|
chunk_id: string | null;
|
|
verbatim_excerpt: string | null;
|
|
custody_steps: unknown;
|
|
bbox: unknown;
|
|
confidence_band: string | null;
|
|
related_hypotheses: unknown;
|
|
}
|
|
|
|
interface HypothesisRow {
|
|
hypothesis_id: string;
|
|
question: string | null;
|
|
position: string | null;
|
|
argument_for: string | null;
|
|
argument_against: string | null;
|
|
prior: number | null;
|
|
posterior: number | null;
|
|
confidence_band: string | null;
|
|
status: string | null;
|
|
evidence_refs: unknown;
|
|
}
|
|
|
|
function durationMs(started: string | null, finished: string | null, created: string): number | null {
|
|
const a = started ? new Date(started).getTime() : null;
|
|
const b = finished ? new Date(finished).getTime() : null;
|
|
if (a !== null && b !== null) return b - a;
|
|
if (a !== null) return Date.now() - a;
|
|
return Date.now() - new Date(created).getTime();
|
|
}
|
|
|
|
export async function GET(
|
|
_request: Request,
|
|
ctx: { params: Promise<{ id: string }> },
|
|
) {
|
|
const { id } = await ctx.params;
|
|
if (!/^[0-9a-f-]{36}$/i.test(id)) {
|
|
return NextResponse.json({ error: "bad_job_id" }, { status: 400 });
|
|
}
|
|
try {
|
|
const rows = await pgQuery<JobRow>(
|
|
`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],
|
|
);
|
|
const job = rows[0];
|
|
if (!job) return NextResponse.json({ error: "not_found" }, { status: 404 });
|
|
|
|
// Collect IDs surfaced in outputs[] for hydration.
|
|
const evidenceIds: string[] = [];
|
|
const hypothesisIds: string[] = [];
|
|
if (Array.isArray(job.outputs)) {
|
|
for (const o of job.outputs as Array<Record<string, unknown>>) {
|
|
if (typeof o.evidence_id === "string") evidenceIds.push(o.evidence_id);
|
|
if (typeof o.hypothesis_id === "string") hypothesisIds.push(o.hypothesis_id);
|
|
}
|
|
}
|
|
|
|
const [evidence, hypotheses] = await Promise.all([
|
|
evidenceIds.length > 0
|
|
? pgQuery<EvidenceRow>(
|
|
`SELECT e.evidence_id, e.grade, e.source_page_id,
|
|
split_part(e.source_page_id, '/p', 1) AS doc_id,
|
|
NULLIF(split_part(e.source_page_id, '/p', 2), '')::int AS page,
|
|
c.chunk_id, e.verbatim_excerpt, e.custody_steps, e.bbox,
|
|
e.confidence_band, e.related_hypotheses
|
|
FROM public.evidence e
|
|
LEFT JOIN public.chunks c ON c.chunk_pk = e.source_chunk_pk
|
|
WHERE e.evidence_id = ANY($1::text[])
|
|
ORDER BY e.evidence_id`,
|
|
[evidenceIds],
|
|
)
|
|
: Promise.resolve([] as EvidenceRow[]),
|
|
hypothesisIds.length > 0
|
|
? pgQuery<HypothesisRow>(
|
|
`SELECT hypothesis_id, question, position, argument_for, argument_against,
|
|
prior, posterior, confidence_band, status, evidence_refs
|
|
FROM public.hypotheses
|
|
WHERE hypothesis_id = ANY($1::text[])
|
|
ORDER BY hypothesis_id`,
|
|
[hypothesisIds],
|
|
)
|
|
: Promise.resolve([] as HypothesisRow[]),
|
|
]);
|
|
|
|
return NextResponse.json({
|
|
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,
|
|
duration_ms: durationMs(job.started_at, job.finished_at, job.created_at),
|
|
error: job.error,
|
|
outputs: Array.isArray(job.outputs) ? job.outputs : [],
|
|
evidence,
|
|
hypotheses,
|
|
});
|
|
} catch (e) {
|
|
return NextResponse.json({ error: "db_unavailable", message: (e as Error).message }, { status: 503 });
|
|
}
|
|
}
|