fix: restart the stalled autonomy pipeline and make calibration honest

Archive ingestion had been dead since 2026-08-02 because nothing in the
compose stack actually ran it. Everything downstream starved from there.

- add ingest + enrichment services. server.js only starts the scheduler when
  DURIIN_RUN_SCHEDULER is not "false", and workers/index.js was not running at
  all, so articles never got event_id/content/has_embedding and the coordinator
  had nothing to lease.
- pass an explicit origin from coordinatorWorker. it was never passed, so
  acceptProposal defaulted to 'live' and 464 historical backfill predictions
  were recorded as live. that also meant verifyEvidence got a null cutoff and
  skipped its date check entirely.
- coarsen cohortKey to event families + horizon buckets. 201 free text event
  types produced 221 cohorts averaging 2.76 samples, so the n>=30 gate could
  never be reached and everything abstained for the wrong reason.
- gate on cohort diversity, not just sample count. one ticker was roughly half
  of all resolved outcomes, so a pure count gate was measuring one company.
  unknown diversity abstains rather than passing.
- resolve the admin archive db explicitly and probe it. it relied on a
  Dockerfile symlink, and without it better-sqlite3 quietly creates an empty
  file and serves a phantom archive.
- clamp implausible future publication dates at ingest.
- pin the db backend to sqlite by default. compose hardcoded postgres "true",
  which would have overridden the operator's own .env on the next redeploy and
  pointed everything at a stale snapshot.

scripts/repair-autonomy-labels.js relabels the affected rows. it is dry run by
default and has not been applied.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01WnNxwxfXSbeNtjvtz5gayb

test/autonomy.test.js

@@ -12,7 +12,7 @@ const { calculateOutcome } = require('../src/autonomy/outcomes');
 const { createOrderIntent } = require('../src/autonomy/orderIntents');
 const { enqueueCoordinatorEvent, reconcileArchiveBatch, reconcileLiveBatch } = require('../workers/autonomyWorker');
 const { scheduleNext } = require('../workers/replayWorker');
-const { refreshHistoricalCalibration, createDecisions } = require('../workers/calibrationWorker');
+const { refreshHistoricalCalibration, createDecisions, ensureCalibrationColumns } = require('../workers/calibrationWorker');
 
 test('autonomy schema and leased jobs are restart-safe', () => {
   const db = new Database(':memory:');
@@ -117,8 +117,11 @@ test('calibration and policy abstain on insufficient evidence', () => {
   assert.equal(calibration.sampleSize, 2);
   const result = decide({ ...calibration }, { minSampleSize: 30 });
   assert.equal(result.action, 'ABSTAIN');
-  assert.equal(cohortKey({ sector: 'tech', eventType: 'earnings', horizonDays: 10, direction: 'positive' }), 'tech|earnings|10|positive');
-  assert.equal(decide({ direction: 'negative', probability: 0.8, expectedExcessReturn: -0.02, lowerReturn: -0.04, sampleSize: 40 }).action, 'SELL');
+  assert.equal(cohortKey({ sector: 'tech', eventType: 'earnings', horizonDays: 10, direction: 'positive' }), 'v2|tech|earnings|medium|positive');
+  assert.equal(decide({
+    direction: 'negative', probability: 0.8, expectedExcessReturn: -0.02, lowerReturn: -0.04,
+    sampleSize: 40, distinctInstruments: 9, topInstrumentShare: 0.25,
+  }).action, 'SELL');
 });
 
 test('historical replay outcomes create replay calibration snapshots', () => {
@@ -136,8 +139,9 @@ test('historical replay outcomes create replay calibration snapshots', () => {
     VALUES (?, 0.04, 1)
   `).run(prediction.lastInsertRowid);
 
-  assert.equal(refreshHistoricalCalibration(db, 'test-cal'), 1);
-  const snapshot = db.prepare("SELECT source, replay_run_id, sample_size, directional_probability FROM autonomy_calibration_snapshots").get();
+  // one per-run replay snapshot plus the pooled historical/replay snapshot
+  assert.equal(refreshHistoricalCalibration(db, 'test-cal'), 2);
+  const snapshot = db.prepare("SELECT source, replay_run_id, sample_size, directional_probability FROM autonomy_calibration_snapshots WHERE source='replay'").get();
   assert.equal(snapshot.source, 'replay');
   assert.equal(snapshot.replay_run_id, 7);
   assert.equal(snapshot.sample_size, 1);
@@ -154,12 +158,14 @@ test('live decisions map calibration snapshot fields into policy inputs', () =>
        learning_eligible, strategy_version, origin, status)
     VALUES (?, 'NVDA', 'positive', 'earnings', 10, datetime('now'), '[1]', 1, 'test', 'live', 'open')
   `).run(proposal.lastInsertRowid);
+  ensureCalibrationColumns(db);
   db.prepare(`
     INSERT INTO autonomy_calibration_snapshots
       (cohort_key, sample_size, effective_sample_size, directional_probability, expected_excess_return,
        lower_return, upper_return, parent_cohort_key, version, source)
-    VALUES ('unknown|earnings|10|positive', 40, 42, 0.7, 0.02, -0.01, 0.06, NULL, 'test-cal', 'replay')
+    VALUES ('v2|unknown|earnings|medium|positive', 40, 42, 0.7, 0.02, -0.01, 0.06, NULL, 'test-cal', 'historical')
   `).run();
+  db.prepare("UPDATE autonomy_calibration_snapshots SET distinct_instruments = 11, top_instrument_share = 0.2").run();
 
   assert.equal(createDecisions(db), 1);
   const decision = db.prepare('SELECT * FROM autonomy_decisions WHERE prediction_id=?').get(prediction.lastInsertRowid);