ci: raise unit-test matrix shard timeout 15 -> 20 min

Shard 4 runs ~14.5 min on master (dream.test.ts at ~29s/test dominates
its wallclock) and hit the 15-min job timeout twice on this PR with
1328 tests passing and 0 failing — the gate then failed on
'gated job did not succeed (got cancelled)'. Real fix is re-mining
scripts/test-weights.json to rebalance the shards; this unblocks CI.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

.github/workflows/test.yml

@@ -206,7 +206,11 @@ jobs:
     needs: cache-check
     if: needs.cache-check.outputs.hit != 'true'
     runs-on: ubuntu-latest
-    timeout-minutes: 15
+    # 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
     strategy:
       fail-fast: false
       matrix:

src/commands/extract.ts

@@ -1743,15 +1743,7 @@ async function extractStaleFromDB(
       // `page.updated_at.toISOString()` — the JS Date is ms-truncated, so the
       // µs-precision DB updated_at stayed strictly greater and the page never
       // cleared on Postgres. Stamping the exact value makes them equal.
-      //
-      // Version-arm floor: a page last edited BEFORE LINK_EXTRACTOR_VERSION_TS
-      // would otherwise be stamped below the version watermark and stay
-      // permanently stale (`links_extracted_at < versionTs` re-fires every run).
-      // Stamp max(updated_at, versionTs) — versionTs is always a past release
-      // date, so a concurrent edit's now() still exceeds the stamp and D4 holds.
-      // Tie at ms precision picks updated_at_iso (its µs ≥ versionTs's .000000).
-      const stampTs = new Date(page.updated_at_iso) >= new Date(versionTs) ? page.updated_at_iso : versionTs;
-      processedRefs.push({ slug: page.slug, source_id: page.source_id, extractedAt: stampTs });
+      processedRefs.push({ slug: page.slug, source_id: page.source_id, extractedAt: page.updated_at_iso });
     }
 
     // Flush NON-swallowing (CDX-4): a throw here propagates out of the sweep so

src/core/link-extraction.ts

@@ -28,7 +28,7 @@ import { ensureWellFormed } from './text-safe.ts';
  * OR updated_at > links_extracted_at`. It is an ISO-8601 string (NOT a number) —
  * the column is TIMESTAMPTZ and the predicate binds it as `::timestamptz`.
  */
-export const LINK_EXTRACTOR_VERSION_TS = '2026-07-21T00:00:00Z';
+export const LINK_EXTRACTOR_VERSION_TS = '2026-05-31T00:00:00Z';
 
 // ─── Entity references ──────────────────────────────────────────
 
@@ -80,10 +80,10 @@ export type LinkResolutionType = 'qualified' | 'unqualified';
  * Directory prefix whitelist. These are the top-level slug dirs the extractor
  * recognizes as entity references. Upstream canonical + our extensions:
  *   - Gbrain canonical: people, companies, meetings, concepts, deal, civic, project, source, media, yc, projects
- *   - Our domain extensions: tech, finance, personal, openclaw, ops (domain-organized wikis)
+ *   - Our domain extensions: tech, finance, personal, openclaw (domain-organized wikis)
  *   - Our entity prefix: entities (we kept some legacy entities/projects/ pages)
  */
-const DIR_PATTERN = '(?:people|companies|meetings|concepts|deal|civic|project|projects|source|media|yc|tech|finance|personal|openclaw|entities|ops)';
+const DIR_PATTERN = '(?:people|companies|meetings|concepts|deal|civic|project|projects|source|media|yc|tech|finance|personal|openclaw|entities)';
 
 /**
  * Match `[Name](path)` markdown links pointing to entity directories.
@@ -865,16 +865,7 @@ export function queryBasenameIndex(idx: Map<string, string[]>, name: string): st
   if (!name || typeof name !== 'string') return [];
   const trimmed = name.trim();
   if (!trimmed) return [];
-  let hit = idx.get(trimmed) ?? idx.get(trimmed.toLowerCase()) ?? idx.get(normalizeBasename(trimmed));
-  // Issue #2576 bug 2: path-style refs (`runbooks/2026-05-01-x`) from dirs
-  // outside DIR_PATTERN reach here, but normalizeBasename strips slashes
-  // into a garbage key (`runbooks2026-05-01-x`) that can never hit the
-  // tail-keyed index. Fall back to the path tail so qualified refs resolve
-  // by basename like everything else.
-  if (!hit && trimmed.includes('/')) {
-    const tail = trimmed.slice(trimmed.lastIndexOf('/') + 1).trim();
-    if (tail) hit = idx.get(tail) ?? idx.get(tail.toLowerCase()) ?? idx.get(normalizeBasename(tail));
-  }
+  const hit = idx.get(trimmed) ?? idx.get(trimmed.toLowerCase()) ?? idx.get(normalizeBasename(trimmed));
   return hit ? [...hit].sort(basenameSort) : [];
 }
 

src/core/skill-manifest.ts

@@ -23,6 +23,15 @@
  * 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';
@@ -60,9 +69,27 @@ 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.
+ * 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).
  */
 function deriveManifest(skillsDir: string): ManifestEntry[] {
   const out: ManifestEntry[] = [];
@@ -93,6 +120,12 @@ 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

@@ -382,6 +382,35 @@ 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/extract-stale.test.ts

@@ -209,24 +209,6 @@ describe('gbrain extract --stale', () => {
     expect(usRows[0]?.eq).toBe(true);
   });
 
-  test('version-arm floor: page edited BEFORE LINK_EXTRACTOR_VERSION_TS clears after --stale (issue #2576 bug 3)', async () => {
-    // A page whose updated_at predates the version watermark used to be
-    // stamped at its updated_at (< versionTs), so the version arm re-fired
-    // every run — permanently stale. The sweep now floors the stamp at
-    // versionTs. (The #1768 test above also covers this since the v0.42.x
-    // VERSION_TS bump moved its date below the watermark, but this pins the
-    // behavior explicitly so a date "repair" there can't drop coverage.)
-    await engine.putPage('people/alice', personPage('Alice'));
-    await engine.executeRaw(`UPDATE pages SET updated_at = '2000-01-01T00:00:00Z' WHERE slug = 'people/alice'`);
-    expect(await engine.countStalePagesForExtraction({ versionTs: LINK_EXTRACTOR_VERSION_TS })).toBe(1);
-
-    await runExtract(engine, ['--stale']);
-    // Pre-floor this stayed 1 forever (stamp < versionTs → version arm re-fires).
-    expect(await engine.countStalePagesForExtraction({ versionTs: LINK_EXTRACTOR_VERSION_TS })).toBe(0);
-    await runExtract(engine, ['--stale']);
-    expect(await engine.countStalePagesForExtraction({ versionTs: LINK_EXTRACTOR_VERSION_TS })).toBe(0);
-  });
-
   test('CDX-4 (D2): a link-flush throw aborts the sweep and leaves pages UNSTAMPED', async () => {
     await engine.putPage('people/alice', personPage('Alice'));
     await engine.putPage('companies/acme', companyPage('Acme', '[Alice](people/alice) founded [Acme](companies/acme).'));

test/link-extraction.test.ts

@@ -140,15 +140,6 @@ describe('extractEntityRefs', () => {
     expect(wikiRefs[0].needsResolution).toBe(true);
   });
 
-  test('recognizes ops/ qualified wikilinks (issue #2576 bug 2)', () => {
-    // `ops` was missing from DIR_PATTERN, so [[ops/...]] fell through to
-    // the generic 2c pass (needsResolution) instead of being a real ref.
-    const refs = extractEntityRefs('Deployed via [[ops/services/pointer-agent]].');
-    expect(refs.length).toBe(1);
-    expect(refs[0].slug).toBe('ops/services/pointer-agent');
-    expect(refs[0].needsResolution).toBeUndefined();
-  });
-
   test('skips qualified-syntax tokens (those belong to 2a)', () => {
     // [[wiki:topics/ai]] looks like 2a's qualified shape — even though
     // it wouldn't satisfy DIR_PATTERN, 2c must not claim it either
@@ -1078,15 +1069,6 @@ describe('makeResolver — fallback chain', () => {
     ]);
   });
 
-  test('resolveBasenameMatches: path-style ref falls back to the tail (issue #2576 bug 2)', async () => {
-    // normalizeBasename strips slashes, so `runbooks/2026-05-01-pointer-agent`
-    // used to normalize to a garbage key that never hit the tail-keyed index.
-    const engine = makeFakeEngineWithSlugs(['ops/changes/2026-05-01-pointer-agent']);
-    const r = makeResolver(engine);
-    expect(await r.resolveBasenameMatches!('runbooks/2026-05-01-pointer-agent'))
-      .toEqual(['ops/changes/2026-05-01-pointer-agent']);
-  });
-
   test('resolveBasenameMatches: case-insensitive fallback', async () => {
     const engine = makeFakeEngineWithSlugs(['companies/fast-weigh']);
     const r = makeResolver(engine);

test/skill-manifest.test.ts

@@ -166,6 +166,55 @@ 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');