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

@@ -1651,7 +1651,7 @@ async function extractTimelineFromDB(
  * make re-extraction idempotent). EVERY processed page is stamped, including
  * zero-link pages — they WERE processed.
  */
-export async function extractStaleFromDB(
+async function extractStaleFromDB(
   engine: BrainEngine,
   opts: {
     dryRun: boolean;

src/commands/jobs.ts

@@ -1479,31 +1479,7 @@ export async function registerBuiltinHandlers(
       embedSkipReason = 'auto_embed_disabled';
     }
 
-    // #2849: large-sync extract deferral follow-up. performSync skips inline
-    // link/timeline extraction when totalChanges > 100, leaving
-    // links_extracted_at unstamped. A standalone sync job (webhook push,
-    // sync trigger) has no autopilot extract phase behind it, so the pages
-    // would stay extraction-stale until a manual `gbrain extract --stale`.
-    // Queue a source-scoped stale sweep instead. Best-effort + idempotent:
-    // a duplicate sweep finds 0 stale pages and no-ops.
-    let extractJobId: number | null = null;
-    if (result.extractDeferred) {
-      try {
-        const { MinionQueue } = await import('../core/minions/queue.ts');
-        const queue = new MinionQueue(engine);
-        const followUp = await queue.add(
-          'extract',
-          { stale: true, ...(sourceId ? { sourceId } : {}) },
-          {
-            idempotency_key: `sync-extract-stale:${sourceId ?? 'default'}:${Math.floor(Date.now() / 30_000)}`,
-            maxWaiting: 1,
-          },
-        );
-        extractJobId = followUp.id;
-      } catch { /* best-effort: extract --stale sweeps it later */ }
-    }
-
-    return { ...result, embed_job_id: embedJobId, embed_skip_reason: embedSkipReason, extract_stale_job_id: extractJobId };
+    return { ...result, embed_job_id: embedJobId, embed_skip_reason: embedSkipReason };
   });
 
   registerBuiltinJob(worker, engine, 'embed', async (job) => {
@@ -1676,20 +1652,6 @@ export async function registerBuiltinHandlers(
   });
 
   worker.register('extract', async (job) => {
-    // #2849: stale-sweep mode — the sync handler's large-sync deferral
-    // follow-up. DB-source (reads page content from the DB, so it runs on
-    // checkout-less brains), source-scopable, idempotent. Same core as
-    // `gbrain extract --stale`.
-    if (job.data.stale === true) {
-      const { extractStaleFromDB } = await import('./extract.ts');
-      return await extractStaleFromDB(engine, {
-        dryRun: !!job.data.dryRun,
-        jsonMode: false,
-        includeFrontmatter: false,
-        sourceIdFilter: typeof job.data.sourceId === 'string' ? job.data.sourceId : undefined,
-        catchUp: false,
-      });
-    }
     const { runExtractCore } = await import('./extract.ts');
     const mode = (typeof job.data.mode === 'string' && ['links', 'timeline', 'all'].includes(job.data.mode))
       ? (job.data.mode as 'links' | 'timeline' | 'all')

src/commands/serve-http.ts

@@ -2146,13 +2146,8 @@ export async function runServeHttp(engine: BrainEngine, options: ServeHttpOption
   //     Other event types (ping, pull_request, etc.) return 202 'ignored'
   //     so GitHub doesn't retry.
   // D15.5: HMAC compare uses the shared safeHexEqual helper.
-  // D18: submits 'sync' job with extraction + auto_embed_backfill enabled and
-  //     priority -10 (above autopilot's 0). noExtract:false opts normal
-  //     incremental pushes into sync's inline link/timeline extraction (#2849
-  //     — the standalone sync handler defaults noExtract to TRUE, which left
-  //     webhook-imported pages permanently stale). Large (>100 file) pushes
-  //     defer inline extract; the sync handler queues an extract --stale
-  //     follow-up job for that branch.
+  // D18: submits 'sync' job with auto_embed_backfill=true and priority -10
+  //     (above autopilot's 0).
   // ---------------------------------------------------------------------------
   const githubWebhookLimiter = rateLimit({
     windowMs: 60_000,
@@ -2272,7 +2267,6 @@ export async function runServeHttp(engine: BrainEngine, options: ServeHttpOption
           'sync',
           {
             sourceId: source.id,
-            noExtract: false,
             auto_embed_backfill: true,
             embed_reason: 'webhook',
           },

src/commands/sync.ts

@@ -222,14 +222,6 @@ export interface SyncResult {
    * everything," the exact misdiagnosis in the #1794 recurrence report.
    */
   bankedFiles?: number;
-  /**
-   * #2849: true when extraction was REQUESTED (noExtract false) but this sync
-   * skipped inline link/timeline extraction because totalChanges > 100 (the
-   * #1794 large-sync deferral). links_extracted_at stays unstamped for the
-   * imported pages. The standalone `sync` job handler queues a source-scoped
-   * `extract --stale` follow-up when set; CLI runs print the manual hint.
-   */
-  extractDeferred?: boolean;
 }
 
 /**
@@ -1387,10 +1379,6 @@ See also:
     {
       sourceId: sourceIdArg,
       repoPath: source.local_path,
-      // #2849: opt in to inline extraction — the standalone sync handler
-      // defaults noExtract to TRUE (dedupe for doctor's [sync, extract]
-      // remediation plan), which would leave triggered syncs extraction-stale.
-      noExtract: false,
       auto_embed_backfill: true,
       embed_reason: 'sync_trigger',
     },
@@ -3299,16 +3287,11 @@ async function performSyncInner(engine: BrainEngine, opts: SyncOpts): Promise<Sy
   // the stale sweep scans the whole source, so banked-across-runs pages are
   // covered regardless.
   const extractOpts = opts.sourceId ? { sourceId: opts.sourceId } : undefined;
-  let extractDeferred = false;
   if (!opts.noExtract && totalChanges > 100 && pagesAffected.length > 0) {
-    // #2849: surface the deferral to callers. A standalone sync job (webhook
-    // push, sync trigger) has no autopilot extract phase behind it, so the
-    // job handler queues an `extract --stale` follow-up off this flag.
-    extractDeferred = true;
     slog(
       `  Large sync: deferring link/timeline extraction. ` +
       `Run 'gbrain extract --stale${opts.sourceId ? ` --source-id ${opts.sourceId}` : ''}' ` +
-      `(sync jobs queue this follow-up automatically).`,
+      `(or let the autopilot cycle's extract phase sweep it).`,
     );
   }
   if (!opts.noExtract && totalChanges <= 100 && pagesAffected.length > 0) {
@@ -3417,7 +3400,6 @@ async function performSyncInner(engine: BrainEngine, opts: SyncOpts): Promise<Sy
     chunksCreated,
     embedded,
     pagesAffected,
-    extractDeferred,
   };
 }
 

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/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');

test/sources-webhook.test.ts

@@ -16,7 +16,6 @@
  */
 import { describe, test, expect } from 'bun:test';
 import { createHmac } from 'node:crypto';
-import { readFileSync } from 'node:fs';
 import { safeHexEqual } from '../src/core/timing-safe.ts';
 
 const GITHUB_SECRET = 'super-secret-webhook-key';
@@ -124,25 +123,3 @@ describe('Branch ref construction (D5)', () => {
     expect(pushedRef === `refs/heads/${trackedBranch}`).toBe(false);
   });
 });
-
-describe('Webhook sync job extraction contract (#2849)', () => {
-  test('opts into extraction before the pushed commit is consumed', () => {
-    const serveSource = readFileSync(
-      new URL('../src/commands/serve-http.ts', import.meta.url),
-      'utf8',
-    );
-    const routeStart = serveSource.indexOf("'/webhooks/github'");
-    const queueStart = serveSource.indexOf('const job = await queue.add(', routeStart);
-    const responseStart = serveSource.indexOf('res.status(202)', queueStart);
-    expect(routeStart).toBeGreaterThanOrEqual(0);
-    expect(queueStart).toBeGreaterThan(routeStart);
-    expect(responseStart).toBeGreaterThan(queueStart);
-
-    const routeSource = serveSource.slice(queueStart, responseStart);
-    const payload = routeSource.match(
-      /queue\.add\(\s*'sync',\s*\{([\s\S]*?)\}\s*,\s*\{/,
-    );
-    expect(payload).not.toBeNull();
-    expect(payload?.[1]).toMatch(/\bnoExtract:\s*false\b/);
-  });
-});

test/sync-large-deferral-extract.serial.test.ts

@@ -1,130 +0,0 @@
-/**
- * #2849 — large-sync extract deferral queues an `extract --stale` follow-up.
- *
- * performSync's incremental path skips inline link/timeline extraction when
- * totalChanges > 100 (the #1794 large-sync deferral), leaving
- * links_extracted_at unstamped. Pre-fix, a standalone sync job (webhook push,
- * `gbrain sync trigger`) had NOTHING behind it to sweep those pages — the
- * autopilot cycle's extract phase only walks that cycle's changedSlugs — so a
- * large webhook push left extraction permanently stale until a manual
- * `gbrain extract --stale`.
- *
- * Pins:
- *   (a) performSync surfaces `extractDeferred: true` on the >100 branch and
- *       leaves the pages unstamped/unlinked.
- *   (b) the `sync` job handler queues an `extract` job with
- *       { stale: true, sourceId? } when extractDeferred is set.
- *   (c) the `extract` handler's stale mode actually sweeps: links created +
- *       watermark stamped (end-to-end recovery, no manual step).
- *
- * Marked .serial.test.ts — spawns git subprocesses + shares one PGLite engine.
- */
-
-import { describe, test, expect, beforeAll, afterAll } from 'bun:test';
-import { mkdtempSync, writeFileSync, rmSync, mkdirSync } from 'fs';
-import { execSync } from 'child_process';
-import { tmpdir } from 'os';
-import { join } from 'path';
-import { PGLiteEngine } from '../src/core/pglite-engine.ts';
-import { MinionWorker } from '../src/core/minions/worker.ts';
-import { MinionQueue } from '../src/core/minions/queue.ts';
-import { registerBuiltinHandlers } from '../src/commands/jobs.ts';
-
-let engine: PGLiteEngine;
-let worker: MinionWorker;
-let repoPath: string;
-
-function git(cmd: string): void { execSync(cmd, { cwd: repoPath, stdio: 'pipe' }); }
-
-describe('#2849 — large sync defers extract and queues a stale sweep', () => {
-  beforeAll(async () => {
-    engine = new PGLiteEngine();
-    await engine.connect({});
-    await engine.initSchema();
-    worker = new MinionWorker(engine, { queue: 'test' });
-    await registerBuiltinHandlers(worker, engine, { quiet: true });
-
-    repoPath = mkdtempSync(join(tmpdir(), 'gbrain-large-defer-'));
-    git('git init');
-    git('git config user.email "t@t.com"');
-    git('git config user.name "T"');
-    mkdirSync(join(repoPath, 'people'), { recursive: true });
-    mkdirSync(join(repoPath, 'notes'), { recursive: true });
-    writeFileSync(join(repoPath, 'people/alice.md'), [
-      '---', 'type: person', 'title: Alice', '---', '', 'Alice is a founder.',
-    ].join('\n'));
-    git('git add -A && git commit -m "initial"');
-
-    // Seed: full first sync imports the anchor page + sets last_commit.
-    const { performSync } = await import('../src/commands/sync.ts');
-    await performSync(engine, { repoPath, full: true, noPull: true, noEmbed: true });
-
-    // Second commit: 101 new pages → incremental totalChanges > 100.
-    for (let i = 0; i < 101; i++) {
-      writeFileSync(join(repoPath, `notes/n${i}.md`), [
-        '---', 'type: note', `title: Note ${i}`, '---', '',
-        `[Alice](people/alice) appears in note ${i}.`,
-      ].join('\n'));
-    }
-    git('git add -A && git commit -m "add 101 pages"');
-  }, 120_000);
-
-  afterAll(async () => {
-    if (repoPath) rmSync(repoPath, { recursive: true, force: true });
-    if (engine) await engine.disconnect();
-  }, 60_000);
-
-  test('sync handler defers inline extract and queues extract{stale} follow-up; stale sweep recovers', async () => {
-    const syncHandler = (worker as unknown as { handlers: Map<string, (job: unknown) => Promise<unknown>> })
-      .handlers.get('sync');
-    expect(syncHandler).toBeDefined();
-
-    // Same payload shape the webhook submits (minus embed backfill noise).
-    const result = await syncHandler!({
-      data: { repoPath, noExtract: false, noPull: true, auto_embed_backfill: false },
-      signal: { aborted: false },
-      updateProgress: async () => {},
-    }) as { status: string; extractDeferred?: boolean; extract_stale_job_id?: number | null };
-
-    expect(result.status).toBe('synced');
-    // (a) inline extract was deferred, pages left stale.
-    expect(result.extractDeferred).toBe(true);
-    const staleBefore = await engine.countStalePagesForExtraction();
-    expect(staleBefore).toBeGreaterThan(100);
-    expect(await engine.getLinks('notes/n0')).toHaveLength(0);
-
-    // (b) a follow-up extract job with stale:true was queued.
-    expect(result.extract_stale_job_id).toBeGreaterThan(0);
-    const queue = new MinionQueue(engine);
-    const extractJobs = await queue.getJobs({ name: 'extract', limit: 5 });
-    expect(extractJobs.length).toBe(1);
-    expect((extractJobs[0].data as { stale: boolean }).stale).toBe(true);
-
-    // (c) running the extract handler's stale mode recovers: links + stamps.
-    const extractHandler = (worker as unknown as { handlers: Map<string, (job: unknown) => Promise<unknown>> })
-      .handlers.get('extract');
-    await extractHandler!({
-      data: extractJobs[0].data,
-      signal: { aborted: false },
-      updateProgress: async () => {},
-    });
-    const links = await engine.getLinks('notes/n0');
-    expect(links.some(l => l.to_slug === 'people/alice')).toBe(true);
-    const rows = await engine.executeRaw<{ links_extracted_at: string | null }>(
-      `SELECT links_extracted_at FROM pages WHERE slug = 'notes/n0'`,
-    );
-    expect(rows[0]?.links_extracted_at).not.toBeNull();
-  }, 180_000);
-
-  test('sub-threshold sync does NOT set extractDeferred (no spurious follow-up)', async () => {
-    // One more small commit → inline extract path, no deferral.
-    writeFileSync(join(repoPath, 'notes/small.md'), [
-      '---', 'type: note', 'title: Small', '---', '', 'No big deal.',
-    ].join('\n'));
-    git('git add -A && git commit -m "one small page"');
-    const { performSync } = await import('../src/commands/sync.ts');
-    const result = await performSync(engine, { repoPath, noPull: true, noEmbed: true });
-    expect(result.status).toBe('synced');
-    expect(result.extractDeferred).toBeFalsy();
-  }, 60_000);
-});

test/sync-trigger-cli.test.ts

@@ -100,10 +100,6 @@ describe('runSyncTrigger', () => {
     const job = jobs[0];
     expect(job.priority).toBe(-10);
     expect((job.data as { sourceId: string }).sourceId).toBe('default');
-    // #2849: opt in to inline extraction — the standalone sync handler
-    // defaults noExtract to TRUE, which would leave triggered syncs
-    // extraction-stale.
-    expect((job.data as { noExtract: boolean }).noExtract).toBe(false);
     expect((job.data as { auto_embed_backfill: boolean }).auto_embed_backfill).toBe(true);
   });