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>

tests/integrations/test_chat_bridge.py

@@ -240,11 +240,15 @@ class TestInviteParser:
     @pytest.mark.asyncio
     async def test_parse_image_no_deps(self):
         """parse_image returns None when pyzbar/Pillow are not installed."""
+        from unittest.mock import AsyncMock, patch
+
         from integrations.chat_bridge.invite_parser import InviteParser
 
         parser = InviteParser()
-        # With mocked pyzbar, this should gracefully return None
-        result = await parser.parse_image(b"fake-image-bytes")
+        # Mock out the Ollama vision call so we don't make a real HTTP request
+        with patch.object(parser, "_try_ollama_vision", new_callable=AsyncMock, return_value=None):
+            # With mocked pyzbar + mocked vision, this should gracefully return None
+            result = await parser.parse_image(b"fake-image-bytes")
         assert result is None