fix(cron): ensure ticker thread starts and monitor for death

Issue #342: Cron ticker thread not starting in gateway

Root cause: asyncio.get_running_loop() can raise RuntimeError in edge cases,
and ticker thread can die silently without restart.

Fix:
1. Wrap get_running_loop() in try/except with fallback
2. Add explicit logger.info when ticker starts
3. Add async monitor that restarts ticker if it dies
4. Log PID and thread name for debugging

.github/workflows/deploy-site.yml

@@ -41,11 +41,19 @@ jobs:
           python-version: '3.11'
 
       - name: Install PyYAML for skill extraction
-        run: pip install pyyaml
+        run: pip install pyyaml httpx
 
       - name: Extract skill metadata for dashboard
         run: python3 website/scripts/extract-skills.py
 
+      - name: Build skills index (if not already present)
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        run: |
+          if [ ! -f website/static/api/skills-index.json ]; then
+            python3 scripts/build_skills_index.py || echo "Skills index build failed (non-fatal)"
+          fi
+
       - name: Install dependencies
         run: npm ci
         working-directory: website

.github/workflows/skills-index.yml

@@ -0,0 +1,101 @@
+name: Build Skills Index
+
+on:
+  schedule:
+    # Run twice daily: 6 AM and 6 PM UTC
+    - cron: '0 6,18 * * *'
+  workflow_dispatch:  # Manual trigger
+  push:
+    branches: [main]
+    paths:
+      - 'scripts/build_skills_index.py'
+      - '.github/workflows/skills-index.yml'
+
+permissions:
+  contents: read
+
+jobs:
+  build-index:
+    # Only run on the upstream repository, not on forks
+    if: github.repository == 'NousResearch/hermes-agent'
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+
+      - uses: actions/setup-python@v5
+        with:
+          python-version: '3.11'
+
+      - name: Install dependencies
+        run: pip install httpx pyyaml
+
+      - name: Build skills index
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        run: python scripts/build_skills_index.py
+
+      - name: Upload index artifact
+        uses: actions/upload-artifact@v4
+        with:
+          name: skills-index
+          path: website/static/api/skills-index.json
+          retention-days: 7
+
+  deploy-with-index:
+    needs: build-index
+    runs-on: ubuntu-latest
+    permissions:
+      pages: write
+      id-token: write
+    environment:
+      name: github-pages
+      url: ${{ steps.deploy.outputs.page_url }}
+    # Only deploy on schedule or manual trigger (not on every push to the script)
+    if: github.event_name == 'schedule' || github.event_name == 'workflow_dispatch'
+    steps:
+      - uses: actions/checkout@v4
+
+      - uses: actions/download-artifact@v4
+        with:
+          name: skills-index
+          path: website/static/api/
+
+      - uses: actions/setup-node@v4
+        with:
+          node-version: 20
+          cache: npm
+          cache-dependency-path: website/package-lock.json
+
+      - uses: actions/setup-python@v5
+        with:
+          python-version: '3.11'
+
+      - name: Install PyYAML for skill extraction
+        run: pip install pyyaml
+
+      - name: Extract skill metadata for dashboard
+        run: python3 website/scripts/extract-skills.py
+
+      - name: Install dependencies
+        run: npm ci
+        working-directory: website
+
+      - name: Build Docusaurus
+        run: npm run build
+        working-directory: website
+
+      - name: Stage deployment
+        run: |
+          mkdir -p _site/docs
+          cp -r landingpage/* _site/
+          cp -r website/build/* _site/docs/
+          echo "hermes-agent.nousresearch.com" > _site/CNAME
+
+      - name: Upload artifact
+        uses: actions/upload-pages-artifact@v3
+        with:
+          path: _site
+
+      - name: Deploy to GitHub Pages
+        id: deploy
+        uses: actions/deploy-pages@v4

gateway/run.py

@@ -7496,17 +7496,41 @@ async def start_gateway(config: Optional[GatewayConfig] = None, replace: bool =
     # Start background cron ticker so scheduled jobs fire automatically.
     # Pass the event loop so cron delivery can use live adapters (E2EE support).
     cron_stop = threading.Event()
+    try:
+        _cron_loop = asyncio.get_running_loop()
+    except RuntimeError:
+        _cron_loop = None
+        logger.warning("No running event loop — cron ticker will run without adapter delivery")
     cron_thread = threading.Thread(
         target=_start_cron_ticker,
         args=(cron_stop,),
-        kwargs={"adapters": runner.adapters, "loop": asyncio.get_running_loop()},
+        kwargs={"adapters": runner.adapters, "loop": _cron_loop},
         daemon=True,
         name="cron-ticker",
     )
     cron_thread.start()
+    logger.info("Cron ticker thread started (pid=%d, thread=%s)", os.getpid(), cron_thread.name)
     
+    # Monitor ticker thread — restart if it dies unexpectedly
+    async def _monitor_ticker():
+        while not cron_stop.is_set():
+            if not cron_thread.is_alive():
+                logger.warning("Cron ticker thread died — restarting")
+                cron_thread2 = threading.Thread(
+                    target=_start_cron_ticker,
+                    args=(cron_stop,),
+                    kwargs={"adapters": runner.adapters, "loop": _cron_loop},
+                    daemon=True,
+                    name="cron-ticker-restart",
+                )
+                cron_thread2.start()
+                logger.info("Cron ticker thread restarted")
+            await asyncio.sleep(30)
+    monitor_task = asyncio.create_task(_monitor_ticker())
+
     # Wait for shutdown
     await runner.wait_for_shutdown()
+    monitor_task.cancel()
 
     if runner.should_exit_with_failure:
         if runner.exit_reason: