fix(ci): pin container image with Node.js for act runner compatibility

The bezalel-vps-runner (act v0.2.11) fails in 1-6s because Node.js is
not in PATH of the default runner container, preventing any GitHub
Actions (actions/checkout, setup-uv, setup-node, etc.) from executing.

Add `container: catthehacker/ubuntu:act-22.04` to all workflow jobs.
This image is purpose-built for act runners and includes Node.js, git,
Python, npm, and other common CI tooling needed to run GitHub Actions.

Fixes #174

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

.claw/sessions/session-1775533542734-0.jsonl

@@ -0,0 +1,2 @@
+{"created_at_ms":1775533542734,"session_id":"session-1775533542734-0","type":"session_meta","updated_at_ms":1775533542734,"version":1}
+{"message":{"blocks":[{"text":"You are Code Claw running as the Gitea user claw-code.\n\nRepository: Timmy_Foundation/hermes-agent\nIssue: #126 — P2: Validate Documentation Audit & Apply to Our Fork\nBranch: claw-code/issue-126\n\nRead the issue and recent comments, then implement the smallest correct change.\nYou are in a git repo checkout already.\n\nIssue body:\n## Context\n\nCommit `43d468ce` is a comprehensive documentation audit — fixes stale info, expands thin pages, adds depth across all docs.\n\n## Acceptance Criteria\n\n- [ ] **Catalog all doc changes**: Run `git show 43d468ce --stat` to list all files changed, then review each for what was fixed/expanded\n- [ ] **Verify key docs are accurate**: Pick 3 docs that were previously thin (setup, deployment, plugin development), confirm they now have comprehensive content\n- [ ] **Identify stale info that was corrected**: Note at least 3 pieces of stale information that were removed or updated\n- [ ] **Apply fixes to our fork if needed**: Check if any of the doc fixes apply to our `Timmy_Foundation/hermes-agent` fork (Timmy-specific references, custom config sections)\n\n## Why This Matters\n\nAccurate documentation is critical for onboarding new agents and maintaining the fleet. Stale docs cost more debugging time than writing them initially.\n\n## Hints\n\n- Run `cd ~/.hermes/hermes-agent && git show 43d468ce --stat` to see the full scope\n- The docs likely cover: setup, plugins, deployment, MCP configuration, and tool integrations\n\n\nParent: #111\n\nRecent comments:\n## 🏷️ Automated Triage Check\n\n**Timestamp:** 2026-04-06T15:30:12.449023  \n**Agent:** Allegro Heartbeat\n\nThis issue has been identified as needing triage:\n\n### Checklist\n- [ ] Clear acceptance criteria defined\n- [ ] Priority label assigned (p0-critical / p1-important / p2-backlog)\n- [ ] Size estimate added (quick-fix / day / week / epic)\n- [ ] Owner assigned\n- [ ] Related issues linked\n\n### Context\n- No comments yet — needs engagement\n- No labels — needs categorization\n- Part of automated backlog maintenance\n\n---\n*Automated triage from Allegro 15-minute heartbeat*\n\n[BURN-DOWN] Dispatched to Code Claw (claw-code worker) as part of nightly burn-down cycle. Heartbeat active.\n\n🟠 Code Claw (OpenRouter qwen/qwen3.6-plus:free) picking up this issue via 15-minute heartbeat.\n\nTimestamp: 2026-04-07T03:45:37Z\n\nRules:\n- Make focused code/config/doc changes only if they directly address the issue.\n- Prefer the smallest proof-oriented fix.\n- Run relevant verification commands if obvious.\n- Do NOT create PRs yourself; the outer worker handles commit/push/PR.\n- If the task is too large or not code-fit, leave the tree unchanged.\n","type":"text"}],"role":"user"},"type":"message"}

.claw/sessions/session-1775534636684-0.jsonl

@@ -0,0 +1,2 @@
+{"created_at_ms":1775534636684,"session_id":"session-1775534636684-0","type":"session_meta","updated_at_ms":1775534636684,"version":1}
+{"message":{"blocks":[{"text":"You are Code Claw running as the Gitea user claw-code.\n\nRepository: Timmy_Foundation/hermes-agent\nIssue: #151 — [CONFIG] Add Kimi model to fallback chain for Allegro and Bezalel\nBranch: claw-code/issue-151\n\nRead the issue and recent comments, then implement the smallest correct change.\nYou are in a git repo checkout already.\n\nIssue body:\n## Problem\nAllegro and Bezalel are choking because the Kimi model code is not on their fallback chain. When primary models fail or rate-limit, Kimi should be available as a fallback option but is currently missing.\n\n## Expected Behavior\nKimi model code should be at the front of the fallback chain for both Allegro and Bezalel, so they can remain responsive when primary models are unavailable.\n\n## Context\nThis was reported in Telegram by Alexander Whitestone after observing both agents becoming unresponsive. Ezra was asked to investigate the fallback chain configuration.\n\n## Related\n- timmy-config #302: [ARCH] Fallback Portfolio Runtime Wiring (general fallback framework)\n- hermes-agent #150: [BEZALEL][AUDIT] Telegram Request-to-Gitea Tracking Audit\n\n## Acceptance Criteria\n- [ ] Kimi model code is added to Allegro fallback chain\n- [ ] Kimi model code is added to Bezalel fallback chain\n- [ ] Fallback ordering places Kimi appropriately (front of chain as requested)\n- [ ] Test and confirm both agents can successfully fall back to Kimi\n- [ ] Document the fallback chain configuration for both agents\n\n/assign @ezra\n\nRecent comments:\n[BURN-DOWN] Dispatched to Code Claw (claw-code worker) as part of nightly burn-down cycle. Heartbeat active.\n\n🟠 Code Claw (OpenRouter qwen/qwen3.6-plus:free) picking up this issue via 15-minute heartbeat.\n\nTimestamp: 2026-04-07T04:03:49Z\n\nRules:\n- Make focused code/config/doc changes only if they directly address the issue.\n- Prefer the smallest proof-oriented fix.\n- Run relevant verification commands if obvious.\n- Do NOT create PRs yourself; the outer worker handles commit/push/PR.\n- If the task is too large or not code-fit, leave the tree unchanged.\n","type":"text"}],"role":"user"},"type":"message"}

.gitea/workflows/ci.yml

@@ -13,6 +13,7 @@ concurrency:
 jobs:
   smoke-and-build:
     runs-on: ubuntu-latest
+    container: catthehacker/ubuntu:act-22.04
     timeout-minutes: 5
     steps:
       - name: Checkout code

.gitea/workflows/notebook-ci.yml

@@ -11,6 +11,7 @@ on:
 jobs:
   notebook-smoke:
     runs-on: ubuntu-latest
+    container: catthehacker/ubuntu:act-22.04
     steps:
       - name: Checkout
         uses: actions/checkout@v4

.github/workflows/dependency-audit.yml

@@ -19,6 +19,7 @@ jobs:
   audit:
     name: Audit Python dependencies
     runs-on: ubuntu-latest
+    container: catthehacker/ubuntu:act-22.04
     steps:
       - uses: actions/checkout@v4
       - uses: astral-sh/setup-uv@v5

.github/workflows/docs-site-checks.yml

@@ -10,6 +10,7 @@ on:
 jobs:
   docs-site-checks:
     runs-on: ubuntu-latest
+    container: catthehacker/ubuntu:act-22.04
     steps:
       - uses: actions/checkout@v4
 

.github/workflows/quarterly-security-audit.yml

@@ -19,6 +19,7 @@ jobs:
   create-audit-issue:
     name: Create quarterly security audit issue
     runs-on: ubuntu-latest
+    container: catthehacker/ubuntu:act-22.04
     steps:
       - uses: actions/checkout@v4
 

.github/workflows/secret-scan.yml

@@ -12,6 +12,7 @@ jobs:
   scan:
     name: Scan for secrets
     runs-on: ubuntu-latest
+    container: catthehacker/ubuntu:act-22.04
     steps:
       - uses: actions/checkout@v4
         with:

.github/workflows/supply-chain-audit.yml

@@ -12,6 +12,7 @@ jobs:
   scan:
     name: Scan PR for supply chain risks
     runs-on: ubuntu-latest
+    container: catthehacker/ubuntu:act-22.04
     steps:
       - name: Checkout
         uses: actions/checkout@v4

.github/workflows/tests.yml

@@ -14,6 +14,7 @@ concurrency:
 jobs:
   test:
     runs-on: ubuntu-latest
+    container: catthehacker/ubuntu:act-22.04
     timeout-minutes: 10
     steps:
       - name: Checkout code