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>
- Swap OLLAMA_MODEL_PRIMARY to qwen2.5:14b for better reasoning
- llama3.1:8b-instruct becomes fallback
- Update .env default and README quick start
- Fix hardcoded model assertions in tests
qwen2.5:14b provides significantly better multi-step reasoning
and tool calling reliability while still running locally on
modest hardware. The 8B model remains as automatic fallback.
Co-authored-by: Trip T <trip@local>
Change 1: Model Upgrade (Primary Fix)
- Changed default model from llama3.2 to llama3.1:8b-instruct
- llama3.1:8b-instruct is fine-tuned for reliable tool/function calling
- llama3.2 (3B) consistently hallucinated tool output in testing
- Added fallback to qwen2.5:14b if primary unavailable
Change 2: Structured Output Foundation
- Enhanced session init to load real data on first message
- Preparation for JSON schema enforcement
Change 3: Git Tool Working Directory Fix
- Rewrote git_tools.py to use subprocess with cwd=REPO_ROOT
- REPO_ROOT auto-detected at module load time
- All git commands now run from correct directory
Change 4: Session Init with Git Log
- _session_init() reads git log --oneline -15 on first message
- Recent commits prepended to system prompt
- Timmy can now answer 'what's new?' from actual commit data
Change 5: Documentation
- Updated README with new model requirement
- Added CHANGELOG_2025-02-27.md
User must run: ollama pull llama3.1:8b-instruct
All 18 git tool tests pass.
selenium depends on websocket-client which installs a top-level
`websocket` package that shadows our src/websocket/ module on CI.
Renaming to ws_manager eliminates the conflict entirely — no more
sys.path hacks needed in conftest or Selenium tests.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Fix /serve/chat AttributeError: split Request and ChatRequest params
so auth headers are read from HTTP request, not Pydantic body
- Add regression tests for the serve_chat endpoint bug
- Add agent_core and lightning to pyproject.toml wheel includes
- Replace Apache 2.0 LICENSE with MIT to match pyproject.toml
- Update test count from "228" to "600+" across README, docs, AGENTS.md
- Add 5 missing subsystems to README table (Spark, Creative, Tools,
Telegram, agent_core/lightning)
- Update AGENTS.md project structure with 6 missing modules
- Mark completed v2 roadmap items (personas, MCP tools) in AGENTS.md
https://claude.ai/code/session_01GMiccXbo77GkV3TA69x6KS
Update GitHub URLs, clone commands, CI badge links, GitHub Pages URL,
agent team name, and hardcoded macOS paths in handoff scripts to reflect
the new GitHub username. Handoff scripts now use relative paths instead
of hardcoded /Users/apayne paths.
https://claude.ai/code/session_01GMiccXbo77GkV3TA69x6KS
agno ships sqlalchemy as an optional dependency under its `sqlite` extra.
Installing bare `agno` (without the extra) left sqlalchemy absent, causing
`ModuleNotFoundError: No module named 'sqlalchemy'` on `make dev`.
Changing the dependency spec from `agno>=1.4.0` to `agno[sqlite]>=1.4.0`
ensures sqlalchemy is installed automatically by `make install`.
Also added a troubleshooting entry to README.md for this error.
https://claude.ai/code/session_01W8jeKbHYNS75mPhGLYJxVq
Workflow upgrades:
- permissions: checks: write + pull-requests: write (required for annotations)
- pytest now outputs --junitxml=reports/junit.xml and --cov-report=xml
- EnricoMi/publish-unit-test-result-action@v2: posts a "pytest results"
check annotation AND a PR comment showing pass/fail counts with
per-test breakdown — both visible in the GitHub mobile app
- actions/upload-artifact@v4: uploads coverage.xml (14-day retention)
browsable from the Actions tab on mobile
README:
- Live test badge at the top (green/red, links to Actions run history)
.gitignore:
- Add reports/ so generated junit.xml + coverage.xml are never committed
https://claude.ai/code/session_01M4L3R98N5fgXFZRvV8X9b6
