fix(dream): stamp incremental extraction watermark (#2636)

The Dream cycle disables sync's inline extraction and routes changed
slugs through extractForSlugs, which flushed link/timeline batches but
never stamped links_extracted_at — so incrementally extracted pages
stayed permanently visible to `extract --stale` / doctor.

Collect processedRefs per successfully processed page and stamp them
via stampExtracted (best-effort) after both batch flushes, non-dry-run
mode 'all' only. Source-id threading from the original PR #2637 already
landed on master via #1503/#1747, so this rebase carries only the
missing watermark stamp plus regression tests.

Takeover of #2637.

Co-authored-by: JavanC <JavanC@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/commands/extract.ts

@@ -1025,6 +1025,10 @@ async function extractForSlugs(
   let linksCreated = 0;
   let timelineCreated = 0;
   let pagesProcessed = 0;
+  // #2636: successfully processed pages get their extraction watermark
+  // stamped after the final flush (mode 'all' only — a partial-mode run
+  // hasn't done the full extraction the watermark asserts).
+  const processedRefs: Array<{ slug: string; source_id: string }> = [];
 
   // Issue #972: read the basename flag once per extract run.
   const globalBasename = await isGlobalBasenameEnabled(engine);
@@ -1113,6 +1117,7 @@ async function extractForSlugs(
         }
 
         pagesProcessed++;
+        if (!dryRun) processedRefs.push({ slug, source_id: sourceId ?? 'default' });
       } catch { /* skip unreadable */ }
       progress.tick(1);
     },
@@ -1120,6 +1125,13 @@ async function extractForSlugs(
 
   await flushLinks();
   await flushTimeline();
+  // #2636: the Dream cycle disables sync's inline extraction and routes
+  // changed slugs through this incremental path — without a stamp here,
+  // those pages never get links_extracted_at and stay permanently visible
+  // to `extract --stale` / doctor. Stamp only after BOTH batches flushed.
+  if (!dryRun && mode === 'all') {
+    await stampExtracted(engine, processedRefs);
+  }
   progress.finish();
 
   if (!jsonMode) {

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/extract-incremental.test.ts

@@ -60,6 +60,51 @@ async function seedPage(slug: string, body: string): Promise<void> {
 }
 
 describe('runExtractCore — incremental cycle path (#417)', () => {
+  test('Dream incremental all-mode stamps the source-scoped extraction watermark (#2636)', async () => {
+    await engine.executeRaw(
+      `INSERT INTO sources (id, name, local_path) VALUES ($1, $2, $3)`,
+      ['repo-a', 'repo-a', tempDir],
+    );
+    await engine.putPage('people/alice-example', {
+      type: 'person',
+      title: 'alice-example',
+      compiled_truth: '# alice',
+      timeline: '',
+      frontmatter: {},
+      content_hash: 'h',
+    }, { sourceId: 'repo-a' });
+    writeFileSync(join(tempDir, 'people/alice-example.md'), '# alice');
+
+    await runExtractCore(engine as unknown as BrainEngine, {
+      mode: 'all',
+      dir: tempDir,
+      slugs: ['people/alice-example'],
+      sourceId: 'repo-a',
+    });
+
+    const rows = await engine.executeRaw<{ links_extracted_at: string | null }>(
+      `SELECT links_extracted_at FROM pages WHERE slug = $1 AND source_id = $2`,
+      ['people/alice-example', 'repo-a'],
+    );
+    expect(rows[0]?.links_extracted_at).not.toBeNull();
+    expect(await engine.countStalePagesForExtraction({ sourceId: 'repo-a' })).toBe(0);
+  });
+
+  test('Dream incremental dry-run does NOT stamp the watermark', async () => {
+    await seedPage('people/alice-example', '# alice');
+    await runExtractCore(engine as unknown as BrainEngine, {
+      mode: 'all',
+      dir: tempDir,
+      slugs: ['people/alice-example'],
+      dryRun: true,
+    });
+    const rows = await engine.executeRaw<{ links_extracted_at: string | null }>(
+      `SELECT links_extracted_at FROM pages WHERE slug = $1`,
+      ['people/alice-example'],
+    );
+    expect(rows[0]?.links_extracted_at ?? null).toBeNull();
+  });
+
   test('1. slugs: [] returns immediately with zero counts (early-return path)', async () => {
     await seedPage('people/alice-example', '# alice');
     const result = await runExtractCore(engine as unknown as BrainEngine, {

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');