feat: upgrade to qwen3.5, self-hosted Gitea CI, optimize Docker image

Model upgrade:
- qwen2.5:14b → qwen3.5:latest across config, tools, and docs
- Added qwen3.5 to multimodal model registry

Self-hosted Gitea CI:
- .gitea/workflows/tests.yml: lint + test jobs via act_runner
- Unified Dockerfile: pre-baked deps from poetry.lock for fast CI
- sitepackages=true in tox for ~2s dep resolution (was ~40s)
- OLLAMA_URL set to dead port in CI to prevent real LLM calls

Test isolation fixes:
- Smoke test fixture mocks create_timmy (was hitting real Ollama)
- WebSocket sends initial_state before joining broadcast pool (race fix)
- Tests use settings.ollama_model/url instead of hardcoded values
- skip_ci marker for Ollama-dependent tests, excluded in CI tox envs

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

.gitea/workflows/tests.yml

@@ -0,0 +1,40 @@
+name: Tests
+
+on:
+  push:
+    branches: [main]
+  pull_request:
+    branches: [main]
+
+# Runs in timmy-time:latest — tox, ruff, and all deps are pre-installed.
+# Rebuild the image only when poetry.lock changes:
+#   docker build -t timmy-time:latest .
+
+jobs:
+  lint:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - name: Lint (ruff via tox)
+        run: tox -e lint
+
+  test:
+    runs-on: ubuntu-latest
+    needs: lint
+    steps:
+      - uses: actions/checkout@v4
+      - name: Run tests (via tox)
+        env:
+          OLLAMA_URL: "http://127.0.0.1:1"
+        run: tox -e ci
+      - name: Test summary
+        if: always()
+        run: |
+          if [ -f reports/junit.xml ]; then
+            python3 -c "
+          import xml.etree.ElementTree as ET
+          root = ET.parse('reports/junit.xml').getroot()
+          t,f,e,s = (root.attrib.get(k,'0') for k in ('tests','failures','errors','skipped'))
+          print(f'Tests: {t} | Failures: {f} | Errors: {e} | Skipped: {s}')
+          "
+          fi