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/apply-migrations.ts

@@ -438,13 +438,6 @@ export async function runApplyMigrations(args: string[]): Promise<void> {
       const result = await m.orchestrator(orchestratorOptsFrom(cli));
       if (result.status === 'failed') {
         console.error(`Migration v${m.version} reported status=failed.`);
-        // Surface each failed phase's detail — the ledger records it, but
-        // the operator needs it on stderr to act (#921).
-        for (const p of result.phases) {
-          if (p.status === 'failed') {
-            console.error(`  phase ${p.name}: ${p.detail ?? '(no detail)'}`);
-          }
-        }
         // Record the attempt as 'partial' (not 'complete') so the cap counts
         // it. Don't let a failed orchestrator look like it never ran.
         try {

src/commands/migrations/v0_32_2.ts

@@ -186,6 +186,17 @@ async function phaseBFenceFacts(
     const localPathById = new Map<string, string | null>();
     for (const s of sources) localPathById.set(s.id, s.local_path);
 
+    // Dirty-tree refusal: check every source's local_path before writing.
+    for (const [id, localPath] of localPathById) {
+      if (localPath && isLocalPathDirty(localPath)) {
+        return {
+          name: 'fence_facts',
+          status: 'failed',
+          detail: `source "${id}" has uncommitted changes in ${localPath}. Commit or stash, then re-run.`,
+        };
+      }
+    }
+
     // Walk legacy rows in (source_id, entity_slug) groups for per-page
     // atomic writes.
     const legacy = await engine.executeRaw<LegacyFactRow>(
@@ -224,21 +235,6 @@ async function phaseBFenceFacts(
       groups.set(key, list);
     }
 
-    // Dirty-tree refusal: check ONLY the sources we are about to write
-    // into. A dirty tree in an unrelated source (or zero fenceable rows
-    // at all) must not block a no-op or a targeted backfill (#927).
-    const targetSourceIds = new Set([...groups.keys()].map(k => k.split('\0')[0]));
-    for (const id of targetSourceIds) {
-      const localPath = localPathById.get(id);
-      if (localPath && isLocalPathDirty(localPath)) {
-        return {
-          name: 'fence_facts',
-          status: 'failed',
-          detail: `source "${id}" has uncommitted changes in ${localPath}. Commit or stash, then re-run.`,
-        };
-      }
-    }
-
     for (const [key, group] of groups) {
       const [sourceId, entitySlug] = key.split('\0');
       const localPath = localPathById.get(sourceId)!;

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/apply-migrations.test.ts

@@ -180,16 +180,3 @@ describe('runApplyMigrations exit codes (v0.36.1.x #1062)', () => {
     expect(src).toMatch(/All migrations up to date[\s\S]{0,80}process\.exit\(0\)/);
   });
 });
-
-// #921: a failed orchestrator must print each failed phase's detail to
-// stderr — not just "reported status=failed" — so the operator can act
-// without digging through the ledger.
-describe('failed migration prints phase detail (#921)', () => {
-  test('runner loops result.phases and console.errors failed phase details', async () => {
-    const { readFileSync } = await import('fs');
-    const src = readFileSync('src/commands/apply-migrations.ts', 'utf8');
-    expect(src).toMatch(
-      /reported status=failed[\s\S]{0,400}for \(const p of result\.phases\)[\s\S]{0,200}p\.status === 'failed'[\s\S]{0,200}console\.error\([\s\S]{0,80}p\.name[\s\S]{0,80}p\.detail/,
-    );
-  });
-});

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[] = [];

test/migrations-v0_32_2.test.ts

@@ -10,11 +10,10 @@
  * __setTestEngineOverride so we don't need a configured brain.
  */
 
-import { describe, test, expect, beforeAll, afterAll, beforeEach, afterEach } from 'bun:test';
+import { describe, test, expect, beforeAll, afterAll, beforeEach } from 'bun:test';
 import { mkdtempSync, rmSync, existsSync, readFileSync, writeFileSync, mkdirSync } from 'node:fs';
 import { tmpdir } from 'node:os';
 import { join } from 'node:path';
-import { execFileSync } from 'node:child_process';
 
 import { PGLiteEngine } from '../src/core/pglite-engine.ts';
 import { v0_32_2, __setTestEngineOverride, __testing } from '../src/commands/migrations/v0_32_2.ts';
@@ -239,52 +238,6 @@ describe('phaseBFenceFacts — happy path backfill', () => {
   });
 });
 
-describe('phaseBFenceFacts — dirty-tree refusal scoping (#927)', () => {
-  let dirtyDir: string;
-
-  beforeEach(async () => {
-    // A second source whose local_path is a git repo with uncommitted changes.
-    dirtyDir = mkdtempSync(join(tmpdir(), 'mig-v0_32_2-dirty-'));
-    execFileSync('git', ['-C', dirtyDir, 'init', '-q']);
-    writeFileSync(join(dirtyDir, 'uncommitted.md'), 'dirty', 'utf-8');
-    // eslint-disable-next-line @typescript-eslint/no-explicit-any
-    await (engine as any).db.query(
-      `INSERT INTO sources (id, name, local_path) VALUES ('other', 'other', $1)`,
-      [dirtyDir],
-    );
-  });
-
-  afterEach(async () => {
-    // eslint-disable-next-line @typescript-eslint/no-explicit-any
-    await (engine as any).db.query(`DELETE FROM sources WHERE id = 'other'`);
-    rmSync(dirtyDir, { recursive: true, force: true });
-  });
-
-  test('no legacy facts at all → complete, dirty unrelated source ignored', async () => {
-    const r = await __testing.phaseBFenceFacts(engine, OPTS);
-    expect(r.status).toBe('complete');
-    expect(r.detail).toContain('scanned=0');
-  });
-
-  test('facts scoped to a clean source fence despite dirty unrelated source', async () => {
-    await seedLegacyFact({ entity_slug: 'people/alice', fact: 'Founded Acme' });
-
-    const r = await __testing.phaseBFenceFacts(engine, OPTS);
-    expect(r.status).toBe('complete');
-    expect(r.detail).toContain('fenced=1');
-    expect(existsSync(join(brainDir, 'people/alice.md'))).toBe(true);
-  });
-
-  test('still refuses when the TARGETED source is dirty', async () => {
-    await seedLegacyFact({ entity_slug: 'people/alice', fact: 'F1', source_id: 'other' });
-
-    const r = await __testing.phaseBFenceFacts(engine, OPTS);
-    expect(r.status).toBe('failed');
-    expect(r.detail).toContain('"other"');
-    expect(r.detail).toContain('uncommitted changes');
-  });
-});
-
 describe('phaseCVerify', () => {
   test('returns complete when fence + DB row counts match', async () => {
     await seedLegacyFact({ entity_slug: 'people/alice', fact: 'F1' });