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>

.github/workflows/test.yml

@@ -206,11 +206,7 @@ jobs:
     needs: cache-check
     if: needs.cache-check.outputs.hit != 'true'
     runs-on: ubuntu-latest
-    # 20 (was 15): shard 4 runs ~14.5 min on master (dream.test.ts ~29s/test
-    # dominates it) and hits the 15-min ceiling on slower runners, cancelling
-    # mid-run with 0 test failures. Rebalancing via
-    # scripts/mine-shard-weights.ts is the real fix; this stops the bleeding.
-    timeout-minutes: 20
+    timeout-minutes: 15
     strategy:
       fail-fast: false
       matrix:

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/skill-manifest.ts

@@ -23,15 +23,6 @@
  * hold conventions and shared rule files, not skills. Files like
  * `_brain-filing-rules.md` live at the root and are not considered
  * skills by either loader.
- *
- * ClawHub-installed workspace skills (#1767): a skill dir carrying
- * `.clawhub/origin.json` is an externally-managed runtime integration
- * (e.g. an email or catalog skill), not a gbrain-routable skill. The
- * derive path SKIPS those so `gbrain doctor` resolver_health doesn't
- * hard-fail on them — UNLESS the skill's SKILL.md frontmatter declares
- * `triggers:`, which is the explicit opt-in to gbrain routing (and the
- * same surface that makes it reachable). An explicit manifest.json that
- * lists a ClawHub skill also keeps strict checking (verbatim path).
  */
 
 import { existsSync, readFileSync, readdirSync, statSync } from 'fs';
@@ -69,27 +60,9 @@ function parseSkillName(skillMdPath: string): string | null {
   }
 }
 
-/**
- * Does the SKILL.md frontmatter declare a `triggers:` key? A ClawHub-
- * installed skill that ships gbrain `triggers:` has explicitly opted in
- * to gbrain routing and gets full resolver checks (#1767).
- */
-function declaresTriggers(skillMdPath: string): boolean {
-  try {
-    const content = readFileSync(skillMdPath, 'utf-8');
-    const fmMatch = content.match(/^---\n([\s\S]*?)\n---/);
-    if (!fmMatch) return false;
-    return /^triggers:/m.test(fmMatch[1]);
-  } catch {
-    return false;
-  }
-}
-
 /**
  * Walk skillsDir, return every `<skillsDir>/<dir>/SKILL.md` as a
- * ManifestEntry. Dotfile and underscore-prefixed dirs are skipped, as
- * are ClawHub-installed external skills that haven't opted in to gbrain
- * routing via `triggers:` frontmatter (#1767).
+ * ManifestEntry. Dotfile and underscore-prefixed dirs are skipped.
  */
 function deriveManifest(skillsDir: string): ManifestEntry[] {
   const out: ManifestEntry[] = [];
@@ -120,12 +93,6 @@ function deriveManifest(skillsDir: string): ManifestEntry[] {
     const skillMd = join(subdirAbs, 'SKILL.md');
     if (!existsSync(skillMd)) continue;
 
-    // ClawHub-installed external skill (#1767): skip unless it opts in
-    // to gbrain routing by declaring `triggers:` in its frontmatter.
-    if (existsSync(join(subdirAbs, '.clawhub', 'origin.json')) && !declaresTriggers(skillMd)) {
-      continue;
-    }
-
     const frontmatterName = parseSkillName(skillMd);
     const name = frontmatterName && frontmatterName !== '' ? frontmatterName : entry;
     out.push({ name, path: `${entry}/SKILL.md` });

test/check-resolvable.test.ts

@@ -382,35 +382,6 @@ describe("DRY detection — checkResolvable", () => {
   });
 });
 
-describe("#1767 — ClawHub workspace skills are not resolver-required", () => {
-  let dir: string;
-  afterEachCleanup(() => dir && rmSync(dir, { recursive: true, force: true }));
-
-  test("ClawHub skill without gbrain metadata produces no unreachable/mece_gap", () => {
-    dir = mkdtempSync(join(tmpdir(), "gbrain-clawhub-"));
-    // Native gbrain skill: routable via frontmatter triggers. No manifest.json
-    // (the OpenClaw derive path from the issue repro).
-    mkdirSync(join(dir, "query"), { recursive: true });
-    writeFileSync(
-      join(dir, "query", "SKILL.md"),
-      `---\nname: query\ndescription: test\ntriggers:\n  - "what do we know"\n---\n\n# query\n`
-    );
-    // ClawHub-installed integration: no triggers, no resolver row.
-    mkdirSync(join(dir, "agentmail", ".clawhub"), { recursive: true });
-    writeFileSync(
-      join(dir, "agentmail", ".clawhub", "origin.json"),
-      JSON.stringify({ registry: "https://clawhub.ai", slug: "agentmail" })
-    );
-    writeFileSync(join(dir, "agentmail", "SKILL.md"), `---\nname: agentmail\ndescription: email integration\n---\n\n# agentmail\n`);
-
-    const report = checkResolvable(dir);
-    const agentmailIssues = report.issues.filter(i => i.skill === "agentmail");
-    expect(agentmailIssues).toEqual([]);
-    expect(report.ok).toBe(true);
-    expect(report.summary.total_skills).toBe(1);
-  });
-});
-
 describe("v0.22.4 regression — actual repo skills/ has 0 errors", () => {
   test("repo skills/ pass check-resolvable cleanly (zero errors AND zero warnings)", () => {
     // The v0.22.4 (Part A) contract was zero warnings AND zero errors.

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/skill-manifest.test.ts

@@ -166,55 +166,6 @@ describe('loadOrDeriveManifest', () => {
     expect(r.skills.map(s => s.name)).toEqual(['apple', 'mango', 'zebra']);
   });
 
-  // #1767 — ClawHub-installed workspace skills are external integrations,
-  // not gbrain-routable skills. The derive path skips them unless they
-  // opt in via `triggers:` frontmatter.
-  it('skips ClawHub-origin skills without triggers frontmatter (#1767)', () => {
-    const dir = scratch();
-    writeSkill(dir, 'query', 'query');
-    writeSkill(dir, 'agentmail', 'agentmail');
-    mkdirSync(join(dir, 'agentmail', '.clawhub'), { recursive: true });
-    writeFileSync(
-      join(dir, 'agentmail', '.clawhub', 'origin.json'),
-      JSON.stringify({ registry: 'https://clawhub.ai', slug: 'agentmail' })
-    );
-    const r = loadOrDeriveManifest(dir);
-    expect(r.derived).toBe(true);
-    expect(r.skills.map(s => s.name)).toEqual(['query']);
-  });
-
-  it('includes ClawHub-origin skills that opt in via triggers frontmatter (#1767)', () => {
-    const dir = scratch();
-    writeSkill(dir, 'agentmail', 'agentmail');
-    mkdirSync(join(dir, 'agentmail', '.clawhub'), { recursive: true });
-    writeFileSync(
-      join(dir, 'agentmail', '.clawhub', 'origin.json'),
-      JSON.stringify({ registry: 'https://clawhub.ai', slug: 'agentmail' })
-    );
-    writeFileSync(
-      join(dir, 'agentmail', 'SKILL.md'),
-      `---\nname: agentmail\ndescription: test\ntriggers:\n  - "send email"\n---\n\n# agentmail\n`
-    );
-    const r = loadOrDeriveManifest(dir);
-    expect(r.derived).toBe(true);
-    expect(r.skills.map(s => s.name)).toEqual(['agentmail']);
-  });
-
-  it('keeps ClawHub-origin skills listed in an explicit manifest.json (#1767)', () => {
-    // Explicit manifest.json is a deliberate declaration — strict checking stays.
-    const dir = scratch();
-    writeSkill(dir, 'agentmail', 'agentmail');
-    mkdirSync(join(dir, 'agentmail', '.clawhub'), { recursive: true });
-    writeFileSync(
-      join(dir, 'agentmail', '.clawhub', 'origin.json'),
-      JSON.stringify({ registry: 'https://clawhub.ai', slug: 'agentmail' })
-    );
-    writeManifest(dir, { skills: [{ name: 'agentmail', path: 'agentmail/SKILL.md' }] });
-    const r = loadOrDeriveManifest(dir);
-    expect(r.derived).toBe(false);
-    expect(r.skills.map(s => s.name)).toEqual(['agentmail']);
-  });
-
   it('treats dirs without SKILL.md as not-a-skill', () => {
     const dir = scratch();
     writeSkill(dir, 'query', 'query');