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>
- Fix test_autoresearch_perplexity: patch target was
dashboard.routes.experiments.get_experiment_history but the function
is imported locally inside the route handler, so patch the source
module timmy.autoresearch.get_experiment_history instead.
- Add tests for src/timmy/interview.py (previously 0% coverage):
question structure, run_interview flow, error handling, formatting.
- Produce interview transcript document from structured Timmy interview.
https://claude.ai/code/session_01EXDzXqgsC2ohS8qreF1fBo
Co-authored-by: Claude <noreply@anthropic.com>
Replaces the marketing landing page with a minimal, full-screen chat
interface that connects to a running Timmy instance. Mobile-first design
with single vertical scroll direction, looping scroll, no zoom, no
buttons — just type and press Enter to talk to Timmy.
- docs/index.html: full rewrite as a clean chat UI with dark terminal
theme, looping infinite scroll, markdown rendering, connection status,
and /connect, /clear, /help slash commands
- src/dashboard/app.py: add CORS middleware so the GitHub Pages site can
reach a local Timmy server cross-origin
- src/config.py: add cors_origins setting (defaults to ["*"])
https://claude.ai/code/session_01AWLxg6KDWsfCATiuvsRMGr
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.
Keep Mission Control link from this branch alongside SWARM and SPARK
links from main. All 939 tests pass.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Incorporates findings from deep-dive audits of all 5 subsystems:
- Swarm auction timing bug (sleep(0) instead of 15s)
- Docker agent HTTP API partially wired
- L402 macaroons are HMAC-only (no caveats/delegation)
- Agent sats are bid-only, no settlement occurs
- CLI test coverage gap (2 tests for 3 commands)
- agent_core persist_memory/communicate are stubs
https://claude.ai/code/session_01SZTwAkTg6v4ybv8g9NLxqN
- 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
Assess practical usefulness of spark.vibeship.co as an
integration into Timmy's agent system. Conclusion: low value
due to fundamental purpose mismatch (developer meta-tool vs
autonomous agent system), redundant persistence/orchestration
layers, and non-trivial integration effort for unclear benefit.
https://claude.ai/code/session_01E5jhTCwSUnJk9p9zrTMVUJ
