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/extract.ts

@@ -509,12 +509,8 @@ export function extractTimelineFromContent(content: string, slug: string): Extra
   // DB-level uniqueness cannot collapse.
   const citationPattern = /\[Source:\s*([^\]]+?),\s*(\d{4}-\d{2}-\d{2})\s*\]/g;
   const bulletLinePattern = /^-\s+\*\*\d{4}-\d{2}-\d{2}\*\*\s*\|/;
-  // Lines captured by Format 4 (plain bullet) are skipped for the same
-  // reason: quality.md mandates a trailing [Source: ...] on those bullets,
-  // and re-extracting the citation would double-count the event.
-  const plainBulletLinePattern = /^-\s+\d{4}-\d{2}-\d{2}\s*[—–-]/;
   for (const line of content.split(/\r?\n/)) {
-    if (bulletLinePattern.test(line) || plainBulletLinePattern.test(line)) continue;
+    if (bulletLinePattern.test(line)) continue;
     const lineMatches = [...line.matchAll(citationPattern)];
     if (lineMatches.length === 0) continue;
     // Strip every citation marker from the line to leave the annotated text.
@@ -530,19 +526,6 @@ export function extractTimelineFromContent(content: string, slug: string): Extra
     }
   }
 
-  // Format 4: Plain bullet — - YYYY-MM-DD — Summary
-  // This is the format gbrain's own enrich skill writes (no bold, no source
-  // pipe). Without it, every brain-authored timeline entry is invisible to
-  // extraction and timeline_coverage stays at 0%. Anchored at line start so a
-  // date inside a summary/link cannot start a spurious entry; a bold Format-1
-  // line (`- **…**`) cannot match here (a `*` follows the bullet, not a
-  // digit), and the citation loop above skips these lines, so a plain bullet
-  // carrying its own [Source: ...] files exactly one entry.
-  const plainBulletPattern = /^-\s+(\d{4}-\d{2}-\d{2})\s*[—–-]\s*(.+)$/gm;
-  while ((match = plainBulletPattern.exec(content)) !== null) {
-    entries.push({ slug, date: match[1], source: 'markdown', summary: match[2].trim() });
-  }
-
   return entries;
 }
 

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',
 ]);
 

src/core/link-extraction.ts

@@ -1103,11 +1103,6 @@ export interface TimelineCandidate {
 // Match: `- **YYYY-MM-DD** | summary` or `- **YYYY-MM-DD** -- summary`
 // or `- **YYYY-MM-DD** - summary` or just `**YYYY-MM-DD** | summary`.
 const TIMELINE_LINE_RE = /^\s*-?\s*\*\*(\d{4}-\d{2}-\d{2})\*\*\s*[|\-–—]+\s*(.+?)\s*$/;
-// Plain bullet: `- YYYY-MM-DD — summary` (no bold, no source pipe). Kept in
-// sync with extractTimelineFromContent's Format 4 (the fs-source path).
-// Anchored flush-left so a date inside an indented continuation line cannot
-// start a spurious entry.
-const PLAIN_TIMELINE_LINE_RE = /^-\s+(\d{4}-\d{2}-\d{2})\s*[—–-]\s*(.+?)\s*$/;
 
 /**
  * Parse timeline entries from content. Looks at:
@@ -1124,7 +1119,7 @@ export function parseTimelineEntries(content: string): TimelineCandidate[] {
 
   let i = 0;
   while (i < lines.length) {
-    const m = TIMELINE_LINE_RE.exec(lines[i]) ?? PLAIN_TIMELINE_LINE_RE.exec(lines[i]);
+    const m = TIMELINE_LINE_RE.exec(lines[i]);
     if (!m) {
       i++;
       continue;
@@ -1141,7 +1136,7 @@ export function parseTimelineEntries(content: string): TimelineCandidate[] {
     let j = i + 1;
     while (j < lines.length) {
       const next = lines[j];
-      if (TIMELINE_LINE_RE.test(next) || PLAIN_TIMELINE_LINE_RE.test(next)) break;
+      if (TIMELINE_LINE_RE.test(next)) break;
       if (/^#{1,6}\s/.test(next)) break;
       if (next.trim().length === 0 && detailLines.length === 0) {
         // skip leading blank line; if we hit a blank after detail content
@@ -1171,7 +1166,7 @@ export function parseTimelineEntries(content: string): TimelineCandidate[] {
   // bullet pass are skipped (a bullet often carries its own citation).
   const citationRe = /\[Source:\s*([^\]]+?),\s*(\d{4}-\d{2}-\d{2})\s*\]/g;
   for (const line of lines) {
-    if (TIMELINE_LINE_RE.test(line) || PLAIN_TIMELINE_LINE_RE.test(line)) continue;
+    if (TIMELINE_LINE_RE.test(line)) continue;
     const matches = [...line.matchAll(citationRe)];
     if (matches.length === 0) continue;
     const summary = line

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/extract.test.ts

@@ -185,49 +185,6 @@ describe('extractTimelineFromContent', () => {
     expect(entries).toHaveLength(1);
     expect(entries[0].summary).toBe('Landed the enterprise pilot with acme-example.');
   });
-
-  // Format 4: the plain bullet `- YYYY-MM-DD — Summary` that gbrain's own
-  // enrich skill writes. Before this was supported, every brain-authored
-  // timeline entry was invisible and timeline_coverage was stuck at 0%.
-  it('extracts plain bullet format (- YYYY-MM-DD — Summary)', () => {
-    const content = `## Timeline\n- 2026-06-01 — Catch-up call with alice-example; intros offered.`;
-    const entries = extractTimelineFromContent(content, 'people/alice-example');
-    expect(entries).toHaveLength(1);
-    expect(entries[0].date).toBe('2026-06-01');
-    expect(entries[0].source).toBe('markdown');
-    expect(entries[0].summary).toBe('Catch-up call with alice-example; intros offered.');
-  });
-
-  it('files exactly one entry for a plain bullet that carries its own citation', () => {
-    // quality.md mandates this shape; it must not double-count via the
-    // citation arm (Format 3) AND the plain-bullet arm (Format 4).
-    const content = `- 2026-05-31 — Confirmed full name. [Source: User, 2026-05-31]`;
-    const entries = extractTimelineFromContent(content, 'people/charlie-example');
-    expect(entries).toHaveLength(1);
-    expect(entries[0].date).toBe('2026-05-31');
-    expect(entries[0].source).toBe('markdown');
-    expect(entries[0].summary).toContain('Confirmed full name.');
-  });
-
-  it('does not double-count bold (Format 1) lines as plain bullets', () => {
-    const content = `- **2025-03-18** | Meeting — Discussed partnership`;
-    const entries = extractTimelineFromContent(content, 'test');
-    expect(entries).toHaveLength(1);
-    expect(entries[0].source).toBe('Meeting');
-  });
-
-  it('does not start a spurious entry from a date inside a summary', () => {
-    const content = `- 2026-06-01 — See [meeting](meetings/2026-06-01).`;
-    const entries = extractTimelineFromContent(content, 'people/alice-example');
-    expect(entries).toHaveLength(1);
-    expect(entries[0].date).toBe('2026-06-01');
-  });
-
-  it('handles en dash and hyphen separators in plain bullets', () => {
-    const content = `- 2026-06-01 – First\n- 2026-06-02 - Second`;
-    const entries = extractTimelineFromContent(content, 'test');
-    expect(entries).toHaveLength(2);
-  });
 });
 
 describe('walkMarkdownFiles', () => {

test/link-extraction.test.ts

@@ -720,30 +720,6 @@ More prose here.
     const entries = parseTimelineEntries(content);
     expect(entries.length).toBe(2);
   });
-
-  // Plain bullet (extract.ts Format 4 parity — the db-source path must see
-  // the same entries as the fs-source path).
-  test('parses plain bullet: - YYYY-MM-DD — summary', () => {
-    const entries = parseTimelineEntries('## Timeline\n- 2026-06-01 — Catch-up call with alice-example');
-    expect(entries.length).toBe(1);
-    expect(entries[0].date).toBe('2026-06-01');
-    expect(entries[0].summary).toBe('Catch-up call with alice-example');
-  });
-
-  test('files exactly one entry for a plain bullet carrying its own citation', () => {
-    const entries = parseTimelineEntries('- 2026-05-31 — Confirmed full name. [Source: User, 2026-05-31]');
-    expect(entries.length).toBe(1);
-    expect(entries[0].date).toBe('2026-05-31');
-  });
-
-  test('skips invalid dates in plain bullets', () => {
-    expect(parseTimelineEntries('- 2026-13-45 — Bad date').length).toBe(0);
-  });
-
-  test('does not double-count a bold bullet as a plain bullet', () => {
-    const entries = parseTimelineEntries('- **2026-01-15** | Met with Alice');
-    expect(entries.length).toBe(1);
-  });
 });
 
 // ─── isAutoLinkEnabled ─────────────────────────────────────────