fix(doctor): register onboard check names in doctor-categories to stop unknown-check warnings

doctor.ts pushes runAllOnboardChecks results into the checks list, but the
7 onboard check names (embed_staleness, entity_link_coverage,
timeline_coverage, takes_count, dangling_aliases, pack_upgrade_available,
type_proliferation) were never added to doctor-categories.ts, so every
doctor run emitted an 'unknown check name' stderr warn per onboard check.

Registers the 5 data-quality names under BRAIN and the 2 schema-pack names
under META (alphabetical order preserved), and widens the drift-guard test
to scan src/core/onboard/checks.ts alongside src/commands/doctor.ts so
future onboard checks can't drift uncategorized.

Takeover of #1839, rebased onto master (keeps master's timeline_dedup_index).

Co-authored-by: mvanhorn <mvanhorn@users.noreply.github.com>
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

src/commands/autopilot-fanout.ts

@@ -186,18 +186,6 @@ export function isSourceStale(src: SourceRow, now = Date.now(), floorMin = FULL_
   return ageMin >= floorMin;
 }
 
-/**
- * #2060: count sources past the per-source cycle freshness floor. Consumed
- * by autopilot's dispatch decision — a stale source forces the fanout path
- * even when the doctor plan is small (score 70–94, plan ≤ 3, est < 300s),
- * so targeted mode can't leave cycle_freshness stale indefinitely.
- * dispatchPerSource's own throttles (skipped_fresh / fanoutMax / failure
- * cooldown) bound the resulting work.
- */
-export function countStaleSources(sources: SourceRow[], now = Date.now(), floorMin = FULL_CYCLE_FLOOR_MIN): number {
-  return sources.filter((s) => isSourceStale(s, now, floorMin)).length;
-}
-
 /**
  * Most recent SUCCESSFUL cycle for a source. Prefers `last_source_cycle_at`
  * (per-source phases, written by the split cycle) and falls back to the legacy

src/commands/autopilot.ts

@@ -901,27 +901,13 @@ export async function runAutopilot(engine: BrainEngine, args: string[]) {
         const FULL_CYCLE_FLOOR_MIN = 60;
         const minutesSinceLastFull = (Date.now() - lastFullCycleAt) / 60000;
 
-        // #2060: stale per-source cycle freshness is a dispatch input. Without
-        // it, a brain sitting at score 70–94 with a small targeted plan (≤3
-        // steps, <300s) stays in targeted mode indefinitely and no per-source
-        // cycle is ever dispatched — cycle_freshness never advances. A stale
-        // source forces the fanout path; dispatchPerSource's throttles
-        // (skipped_fresh / fanoutMax / failure cooldown) bound the work.
-        // Fail-open to 0: a read failure must not block dispatch.
-        let staleCycleSources = 0;
-        try {
-          const { countStaleSources } = await import('./autopilot-fanout.ts');
-          staleCycleSources = countStaleSources(await engine.listAllSources({ localPathOnly: true }));
-        } catch { /* fail-open: freshness is a dispatch hint, not a gate */ }
-
         const shouldFullCycle =
           (score >= 95 && plan.length === 0 && minutesSinceLastFull >= FULL_CYCLE_FLOOR_MIN) ||
           plan.length > 3 ||
           estTotal >= 300 ||
-          score < 70 ||
-          staleCycleSources > 0;
+          score < 70;
 
-        const shouldSleep = score >= 95 && plan.length === 0 && minutesSinceLastFull < FULL_CYCLE_FLOOR_MIN && staleCycleSources === 0;
+        const shouldSleep = score >= 95 && plan.length === 0 && minutesSinceLastFull < FULL_CYCLE_FLOOR_MIN;
 
         if (shouldSleep) {
           if (jsonMode) {

src/core/cycle.ts

@@ -854,10 +854,7 @@ interface SyncPhaseResult extends PhaseResult {
 /**
  * Resolve the source id for a brain directory by looking up the sources
  * table. Returns undefined when no registered source matches (falls back
- * to pre-v0.18 global config.sync.* keys) OR when MORE than one source
- * claims the path — an ambiguous match must not scope phases or stamp
- * last_full_cycle_at for an arbitrarily-picked source (the "freshness
- * stamp that lies" this resolution exists to prevent).
+ * to pre-v0.18 global config.sync.* keys).
  */
 async function resolveSourceForDir(
   engine: BrainEngine,
@@ -868,10 +865,10 @@ async function resolveSourceForDir(
   if (brainDir === null) return undefined;
   try {
     const rows = await engine.executeRaw<{ id: string }>(
-      `SELECT id FROM sources WHERE local_path = $1 LIMIT 2`,
+      `SELECT id FROM sources WHERE local_path = $1 LIMIT 1`,
       [brainDir],
     );
-    return rows.length === 1 ? rows[0]!.id : undefined;
+    return rows[0]?.id;
   } catch {
     // sources table might not exist on very old brains — fall through.
     return undefined;
@@ -2368,23 +2365,17 @@ export async function runCycle(
   }
 
   // v0.38 (codex r1 P0-5): persist per-source cycle completion timestamp
-  // when the cycle ran successfully against a resolvable source. Read by
-  // autopilot's per-source freshness gate next tick.
-  //
-  // #1993: keyed off `cycleSourceId` (opts.sourceId ?? the source resolved
-  // from brainDir) — the SAME id the cycle locked + scoped its phases to —
-  // NOT raw opts.sourceId. The autopilot's inline cycle sets brainDir but
-  // passes no explicit sourceId, so keying off opts.sourceId alone never
-  // advanced last_full_cycle_at and cycle_freshness stayed stale even while
-  // the autopilot cycled every interval. Skipped when:
-  //   - no source resolves (engine null, or no checkout AND no opts.sourceId)
+  // when the cycle ran successfully against an explicit source. Read by
+  // autopilot's per-source freshness gate next tick. Skipped when:
+  //   - opts.sourceId is unset (legacy callers — autopilot still here)
+  //   - engine is null (no-DB path)
   //   - status is 'failed' or 'skipped' (don't mark a non-run as fresh)
   //   - dryRun (writes are out of scope)
   //
   // Best-effort: a write failure does NOT change the CycleReport status.
   // The cost of writing the wrong timestamp post-failure is higher than
   // the cost of missing a successful write (next cycle will redo work).
-  if (cycleSourceId && engine && !dryRun && !aborted && (status === 'ok' || status === 'clean' || status === 'partial')) {
+  if (opts.sourceId && engine && !dryRun && !aborted && (status === 'ok' || status === 'clean' || status === 'partial')) {
     try {
       const nowIso = new Date().toISOString();
       // #2194 fix #3 (the cycle split): `last_source_cycle_at` is the NEW gate
@@ -2394,13 +2385,13 @@ export async function runCycle(
       // phases (those gate on autopilot.last_global_at), so writing it on a
       // source-only cycle does not re-introduce the freshness poisoning codex
       // flagged in the rejected skip-based design.
-      await engine.updateSourceConfig(cycleSourceId, {
+      await engine.updateSourceConfig(opts.sourceId, {
         last_source_cycle_at: nowIso,
         last_full_cycle_at: nowIso,
       });
     } catch (e) {
       // Best-effort; cycle already succeeded by the time we get here.
-      console.warn(`[cycle] failed to write last_source_cycle_at for source ${cycleSourceId}: ${e instanceof Error ? e.message : String(e)}`);
+      console.warn(`[cycle] failed to write last_source_cycle_at for source ${opts.sourceId}: ${e instanceof Error ? e.message : String(e)}`);
     }
   }
 

src/core/doctor-categories.ts

@@ -35,10 +35,11 @@
  *
  * The doctor renders both side by side.
  *
- * Drift contract: every check name that ships in doctor.ts MUST appear in
+ * Drift contract: every check name that ships through doctor MUST appear in
  * exactly one set below. The drift-guard test in
- * `test/doctor-categories.test.ts` enforces this by reading doctor.ts source
- * via a tagged-string scan and asserting set membership exactly.
+ * `test/doctor-categories.test.ts` enforces this by reading doctor check
+ * emitter sources via a tagged-string scan and asserting set membership
+ * exactly.
  *
  * If you add a new doctor check, you MUST add its name to the appropriate
  * set here. The categorize step in `src/commands/doctor.ts` falls through
@@ -67,12 +68,15 @@ export const BRAIN_CHECK_NAMES: ReadonlySet<string> = new Set([
   'conversation_parser_probe_health',
   'cross_modal_modality_backfill',
   'cycle_freshness',
+  'dangling_aliases',
   'effective_date_health',
+  'embed_staleness',
   'embedding_column_registry',
   'embedding_env_override',
   'embedding_provider',
   'embedding_width_consistency',
   'embeddings',
+  'entity_link_coverage',
   'eval_drift',
   'extract_atoms_backlog',
   'extract_health',
@@ -102,7 +106,9 @@ export const BRAIN_CHECK_NAMES: ReadonlySet<string> = new Set([
   'stub_guard_24h',
   'sync_failures',
   'sync_freshness',
+  'takes_count',
   'takes_weight_grid',
+  'timeline_coverage',
   'unified_multimodal_coverage',
   'voice_gate_health',
 ]);
@@ -170,12 +176,14 @@ export const META_CHECK_NAMES: ReadonlySet<string> = new Set([
   'eval_capture',
   'minions_migration',
   'multi_source_drift',
+  'pack_upgrade_available',
   'schema_pack_active',
   'schema_pack_consistency',
   'schema_pack_source_drift',
   'schema_version',
   'slug_fallback_audit',
   'timeline_dedup_index',
+  'type_proliferation',
   'upgrade_errors',
 ]);
 

test/autopilot-fanout-wiring.test.ts

@@ -54,20 +54,6 @@ describe('autopilot.ts ↔ dispatchPerSource wiring', () => {
     expect(AUTOPILOT_SRC).toMatch(/lastFullCycleAt\s*=\s*Date\.now\(\)/);
   });
 
-  test('stale per-source cycle freshness is a shouldFullCycle input (#2060)', () => {
-    // Targeted mode (score 70–94, plan ≤3, est <300s) must not be able to
-    // starve per-source cycle dispatch: a stale source (per countStaleSources
-    // over listAllSources) forces the fanout path, and the sleep gate must
-    // not fire while stale sources exist. Without these terms, cycle
-    // freshness never advances for a brain that always lands in targeted mode.
-    expect(AUTOPILOT_SRC).toMatch(/countStaleSources/);
-    const fullCycleDeclIdx = AUTOPILOT_SRC.indexOf('const shouldFullCycle');
-    expect(fullCycleDeclIdx).toBeGreaterThan(-1);
-    const decl = AUTOPILOT_SRC.slice(fullCycleDeclIdx, fullCycleDeclIdx + 700);
-    expect(decl).toMatch(/staleCycleSources\s*>\s*0/);
-    expect(decl).toMatch(/const shouldSleep[^;]*staleCycleSources\s*===\s*0/);
-  });
-
   test('does NOT regress to the single-job dispatch on the full-cycle path', () => {
     // Pre-PR: the shouldFullCycle branch did:
     //   const job = await queue.add('autopilot-cycle', { repoPath }, {

test/autopilot-fanout.test.ts

@@ -14,7 +14,6 @@ import { describe, test, expect } from 'bun:test';
 import {
   readLastFullCycleAt,
   isSourceStale,
-  countStaleSources,
   selectSourcesForDispatch,
   resolveFanoutMax,
   dispatchPerSource,
@@ -75,23 +74,6 @@ describe('isSourceStale', () => {
   });
 });
 
-describe('countStaleSources (#2060 dispatch-decision input)', () => {
-  const NOW = Date.parse('2026-05-22T12:00:00.000Z');
-  test('counts never-cycled + past-floor sources, ignores fresh', () => {
-    const sources = [
-      src('never-cycled'), // stale (null)
-      src('old', new Date(NOW - 2 * 60 * 60_000).toISOString()), // stale (2h)
-      src('fresh', new Date(NOW - 30 * 60_000).toISOString()), // fresh (30min)
-    ];
-    expect(countStaleSources(sources, NOW)).toBe(2);
-  });
-  test('returns 0 for all-fresh and for empty list', () => {
-    const fresh = src('a', new Date(NOW - 10 * 60_000).toISOString());
-    expect(countStaleSources([fresh], NOW)).toBe(0);
-    expect(countStaleSources([], NOW)).toBe(0);
-  });
-});
-
 describe('selectSourcesForDispatch', () => {
   const NOW = Date.parse('2026-05-22T12:00:00.000Z');
   const fresh = (id: string, agoMin: number) =>

test/cycle-last-full-cycle-at.test.ts

@@ -3,10 +3,8 @@
  * cycles. Closes codex round-1 P0-5 (write site for last_full_cycle_at
  * was unspecified pre-PR).
  *
- * Conditions for write (keyed off `cycleSourceId` = opts.sourceId ?? the
- * source resolved from brainDir, so the autopilot's inline cycle — brainDir
- * set, no explicit sourceId — also advances the timestamp, #1993):
- *   - a source resolves (explicit sourceId, or brainDir matches a source)
+ * Conditions for write:
+ *   - opts.sourceId is set (legacy callers without sourceId skip the write)
  *   - engine is non-null (no-DB path skips)
  *   - status is 'ok' | 'clean' | 'partial' (failed/skipped don't mark fresh)
  *   - dryRun is false
@@ -92,45 +90,17 @@ describe('runCycle last_full_cycle_at exit hook', () => {
     });
   });
 
-  test('no explicit sourceId but brainDir resolves a source → writes the resolved source timestamp', async () => {
+  test('legacy caller (no sourceId) does NOT write any source timestamp', async () => {
     await withEnv({ GBRAIN_HOME: gbrainHome }, async () => {
-      // The autopilot's inline cycle sets brainDir but passes no sourceId.
-      // runCycle resolves the source from brainDir (local_path match) into
-      // cycleSourceId and stamps last_full_cycle_at for it — otherwise
-      // cycle_freshness reports the brain stale even while the autopilot
-      // cycles every interval (#1993).
-      await seedSource('resolved-from-dir'); // local_path = brainDir
-      expect(await readLastFullCycleAt('resolved-from-dir')).toBeNull();
-
-      const t0 = Date.now();
-      const report = await runCycle(engine, {
-        brainDir,
-        phases: ['lint'],
-      });
-      expect(['ok', 'clean']).toContain(report.status);
-
-      const after = await readLastFullCycleAt('resolved-from-dir');
-      expect(after).not.toBeNull();
-      expect(new Date(after!).getTime()).toBeGreaterThanOrEqual(t0);
-    });
-  });
-
-  test('no sourceId and brainDir matches no source → does not write', async () => {
-    await withEnv({ GBRAIN_HOME: gbrainHome }, async () => {
-      // A source exists but its local_path does NOT match brainDir, so
-      // resolveSourceForDir returns undefined, cycleSourceId is undefined,
-      // and no per-source timestamp is written.
-      await engine.executeRaw(
-        `INSERT INTO sources (id, name, local_path, config, archived, created_at)
-         VALUES ('unmatched', 'unmatched', '/no/such/repo', '{}'::jsonb, false, NOW())
-         ON CONFLICT (id) DO UPDATE SET local_path = EXCLUDED.local_path`,
-        [],
-      );
+      await seedSource('default-like');
+      // No sourceId passed; should remain untouched.
       await runCycle(engine, {
         brainDir,
         phases: ['lint'],
       });
-      expect(await readLastFullCycleAt('unmatched')).toBeNull();
+      // No per-source write happens; default source's config stays empty.
+      const after = await readLastFullCycleAt('default-like');
+      expect(after).toBeNull();
     });
   });
 

test/doctor-categories.test.ts

@@ -1,10 +1,10 @@
 /**
  * Drift guard for src/core/doctor-categories.ts.
  *
- * Reads src/commands/doctor.ts source via a literal-string scan, enumerates
- * every `name: '<...>'` Check name, and asserts each appears in exactly ONE
- * category set. The union of the four sets must equal the discovered names
- * exactly — no orphans, no extras.
+ * Reads doctor check emitter source via a literal-string scan, enumerates every
+ * `name: '<...>'` Check name, and asserts each appears in exactly ONE category
+ * set. The union of the four sets must equal the discovered names exactly —
+ * no orphans, no extras.
  *
  * This is the structural failure the v0.41.19.0 plan-eng-review caught:
  * doctor.ts grows new checks regularly; without this guard, the
@@ -25,26 +25,30 @@ import {
 } from '../src/core/doctor-categories.ts';
 
 const DOCTOR_TS_PATH = join(import.meta.dir, '..', 'src', 'commands', 'doctor.ts');
+const ONBOARD_CHECKS_TS_PATH = join(import.meta.dir, '..', 'src', 'core', 'onboard', 'checks.ts');
+const CHECK_SOURCE_PATHS = [DOCTOR_TS_PATH, ONBOARD_CHECKS_TS_PATH];
 
 function enumerateCheckNames(): Set<string> {
-  const source = readFileSync(DOCTOR_TS_PATH, 'utf-8');
   const names = new Set<string>();
-  // 1) Inline object-literal form: `{ name: 'foo', ... }`.
-  for (const m of source.matchAll(/name:\s*['"]([a-z][a-z0-9_]+)['"]/g)) {
-    names.add(m[1]);
-  }
-  // 2) Helper-function form: `const name = 'foo';` inside a check helper.
-  //    Catches checks like `nightly_quality_probe_health` and
-  //    `conversation_facts_backlog` that build the Check from a captured
-  //    name constant.
-  for (const m of source.matchAll(/const\s+name\s*=\s*['"]([a-z][a-z0-9_]+)['"]/g)) {
-    names.add(m[1]);
+  for (const path of CHECK_SOURCE_PATHS) {
+    const source = readFileSync(path, 'utf-8');
+    // 1) Inline object-literal form: `{ name: 'foo', ... }`.
+    for (const m of source.matchAll(/name:\s*['"]([a-z][a-z0-9_]+)['"]/g)) {
+      names.add(m[1]);
+    }
+    // 2) Helper-function form: `const name = 'foo';` inside a check helper.
+    //    Catches checks like `nightly_quality_probe_health` and
+    //    `conversation_facts_backlog` that build the Check from a captured
+    //    name constant.
+    for (const m of source.matchAll(/const\s+name\s*=\s*['"]([a-z][a-z0-9_]+)['"]/g)) {
+      names.add(m[1]);
+    }
   }
   return names;
 }
 
 describe('doctor-categories drift guard', () => {
-  test('every check name in doctor.ts source belongs to exactly one category set', () => {
+  test('every doctor-emitted check name belongs to exactly one category set', () => {
     const discovered = enumerateCheckNames();
     const allCategorized = new Set<string>([
       ...BRAIN_CHECK_NAMES,
@@ -59,7 +63,7 @@ describe('doctor-categories drift guard', () => {
     }
     if (missing.length > 0) {
       throw new Error(
-        `These check names appear in doctor.ts but are not categorized in ` +
+        `These check names appear in doctor check emitters but are not categorized in ` +
           `src/core/doctor-categories.ts: ${missing.sort().join(', ')}. ` +
           `Add each to BRAIN/SKILL/OPS/META_CHECK_NAMES.`,
       );
@@ -86,7 +90,7 @@ describe('doctor-categories drift guard', () => {
     expect(dupes).toEqual([]);
   });
 
-  test('every categorized name is currently used in doctor.ts source (no stale entries)', () => {
+  test('every categorized name is currently used in doctor check emitters (no stale entries)', () => {
     const discovered = enumerateCheckNames();
     const allCategorized = new Set<string>([
       ...BRAIN_CHECK_NAMES,
@@ -124,6 +128,14 @@ describe('categorizeCheck', () => {
     expect(categorizeCheck('sync_freshness')).toBe('brain');
   });
 
+  test('returns the right category for onboard data-quality check names', () => {
+    expect(categorizeCheck('embed_staleness')).toBe('brain');
+    expect(categorizeCheck('entity_link_coverage')).toBe('brain');
+    expect(categorizeCheck('timeline_coverage')).toBe('brain');
+    expect(categorizeCheck('takes_count')).toBe('brain');
+    expect(categorizeCheck('dangling_aliases')).toBe('brain');
+  });
+
   test('returns the right category for a known skill name', () => {
     expect(categorizeCheck('resolver_health')).toBe('skill');
     expect(categorizeCheck('skill_conformance')).toBe('skill');
@@ -140,6 +152,24 @@ describe('categorizeCheck', () => {
     expect(categorizeCheck('upgrade_errors')).toBe('meta');
   });
 
+  test('returns the right category for onboard schema-pack check names without warning', () => {
+    const originalWrite = process.stderr.write.bind(process.stderr);
+    const captured: string[] = [];
+    (process.stderr as { write: typeof process.stderr.write }).write = ((
+      chunk: string | Uint8Array,
+    ) => {
+      captured.push(typeof chunk === 'string' ? chunk : Buffer.from(chunk).toString());
+      return true;
+    }) as typeof process.stderr.write;
+    try {
+      expect(categorizeCheck('pack_upgrade_available')).toBe('meta');
+      expect(categorizeCheck('type_proliferation')).toBe('meta');
+      expect(captured.filter((c) => c.includes('[doctor-categories]'))).toEqual([]);
+    } finally {
+      (process.stderr as { write: typeof process.stderr.write }).write = originalWrite;
+    }
+  });
+
   test('unknown check name falls through to meta with a stderr warn (once per process)', () => {
     const originalWrite = process.stderr.write.bind(process.stderr);
     const captured: string[] = [];