Claude
3a3b03e1e8
docs: development standards, Makefile, GitHub Pages landing page
...
- Remove stale STATUS.md and DEVELOPMENT_REPORT.md (content superseded)
- Rewrite README.md to reflect v2 state (228 tests, swarm, L402, voice,
WebSocket, mobile; Makefile commands; updated architecture diagram)
- Add AGENTS.md — per-agent development standards for Claude, Kimi, and
Manus; coding conventions, architecture patterns, roadmap, file layout
- Add Makefile — install, dev, test, test-cov, watch, lint, clean targets
- Add docs/index.html — GitHub Pages landing page (dark mission-control
theme, scanline overlay, feature grid, architecture diagram, quickstart
steps, agent team cards, roadmap, stats bar)
https://claude.ai/code/session_0181LU8dCresHiLzYxjK4vUC
2026-02-22 00:22:04 +00:00
Claude
19af4ae540
feat: integrate AirLLM as optional high-performance backend
...
Adds the `bigbrain` optional dependency group (airllm>=2.9.0) and a
complete second inference path that runs 8B / 70B / 405B Llama models
locally via layer-by-layer loading — no GPU required, no cloud, fully
sovereign.
Key changes:
- src/timmy/backends.py — TimmyAirLLMAgent (same print_response interface
as Agno Agent); auto-selects AirLLMMLX on Apple
Silicon, AutoModel (PyTorch) everywhere else
- src/timmy/agent.py — _resolve_backend() routing with explicit override,
env-config, and 'auto' Apple-Silicon detection
- src/timmy/cli.py — --backend / --model-size flags on all commands
- src/config.py — timmy_model_backend + airllm_model_size settings
- src/timmy/prompts.py — mentions AirLLM "even bigger brains, still fully
sovereign"
- pyproject.toml — bigbrain optional dep; wheel includes updated
- .env.example — TIMMY_MODEL_BACKEND + AIRLLM_MODEL_SIZE docs
- tests/conftest.py — stubs 'airllm' module so tests run without GPU
- tests/test_backends.py — 13 new tests covering helpers + TimmyAirLLMAgent
- tests/test_agent.py — 7 new tests for backend routing
- README.md — Big Brain section with one-line install
- activate_self_tdd.sh — bootstrap script (venv + install + tests +
watchdog + dashboard); --big-brain flag
All 61 tests pass. Self-TDD watchdog unaffected.
https://claude.ai/code/session_01DMjQ5qMZ8iHeyix1j3GS7c
2026-02-21 16:53:16 +00:00
Claude
7829536952
ci: mobile-friendly test results via GitHub Actions
...
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
2026-02-19 19:41:01 +00:00
Claude
a84225b25a
docs: architecture diagram + config reference table in README
...
- Mermaid graph showing Browser/Phone → FastAPI → Timmy → Ollama/SQLite
data flow; makes the local-first architecture immediately obvious
- Configuration table: OLLAMA_URL, OLLAMA_MODEL, DEBUG with defaults
- Updated project layout to include src/config.py and .env.example
https://claude.ai/code/session_01M4L3R98N5fgXFZRvV8X9b6
2026-02-19 19:31:57 +00:00
Claude
f9ccfa9177
feat: mobile-optimized layout + phone access instructions
...
CSS:
- Responsive grid: 2-col desktop → 1-col mobile (≤768px)
- Sidebar becomes horizontal scroll strip on mobile
- 100dvh for correct mobile viewport height
- env(safe-area-inset-*) for iPhone notch/home bar
- 16px input font-size prevents iOS auto-zoom
- 44px min touch targets on input + send button
- touch-action: manipulation stops double-tap zoom
- overscroll-behavior: none prevents iOS bounce bleed
- -webkit-overflow-scrolling: touch for smooth scroll
HTML (base.html):
- viewport-fit=cover for full-bleed on notched iPhones
- apple-mobile-web-app-capable + status-bar-style meta
- theme-color meta (#060d14)
README:
- "Access from your phone" section with exact steps:
--host 0.0.0.0, ipconfig getifaddr en0, same-WiFi note
https://claude.ai/code/session_01M4L3R98N5fgXFZRvV8X9b6
2026-02-19 19:15:43 +00:00
Claude
03f4027f43
docs: rewrite README as human-friendly Mac quickstart
...
Step-by-step clone → venv → install → Ollama → run sequence,
what to expect in the browser, troubleshooting section for
common Mac failure modes.
https://claude.ai/code/session_01M4L3R98N5fgXFZRvV8X9b6
2026-02-19 19:11:42 +00:00
Claude
5e7d805245
feat: scaffold Timmy Time Mission Control (v1.0.0 Genesis)
...
- src/timmy/ — Agno agent wrapper (llama3.2 via Ollama, SQLite memory, TIMMY_SYSTEM_PROMPT)
- src/dashboard/ — FastAPI + HTMX + Jinja2 Mission Control UI
- /health + /health/status (Ollama ping, HTMX 30s poll)
- /agents list + /agents/timmy/chat (HTMX form submission)
- static/style.css — dark terminal mission-control aesthetic
- tests/ — 27 pytest tests (prompts, agent config, dashboard routes); no Ollama required
- pyproject.toml — hatchling build, pytest configured with pythonpath=src
https://claude.ai/code/session_01M4L3R98N5fgXFZRvV8X9b6
2026-02-19 19:05:01 +00:00
