Alexander Payne
7838df19b0
Implement three-tier memory architecture (Hot/Vault/Handoff)
...
This commit replaces the previous memory_layers.py with a proper three-tier
memory system as specified by the user:
## Tier 1 — Hot Memory (MEMORY.md)
- Single flat file always loaded into system context
- Contains: current status, standing rules, agent roster, key decisions
- ~300 lines max, pruned monthly
- Managed by HotMemory class
## Tier 2 — Structured Vault (memory/)
- Directory with three namespaces:
• self/ — identity.md, user_profile.md, methodology.md
• notes/ — session logs, AARs, research
• aar/ — post-task retrospectives
- Markdown format, Obsidian-compatible
- Append-only, date-stamped
- Managed by VaultMemory class
## Handoff Protocol
- last-session-handoff.md written at session end
- Contains: summary, key decisions, open items, next steps
- Auto-loaded at next session start
- Maintains continuity across resets
## Implementation
### New Files:
- src/timmy/memory_system.py — Core memory system
- MEMORY.md — Hot memory template
- memory/self/*.md — Identity, user profile, methodology
### Modified:
- src/timmy/agent.py — Integrated with memory system
- create_timmy() injects memory context
- TimmyWithMemory class with automatic fact extraction
- tests/test_agent.py — Updated for memory context
## Key Principles
- Hot memory = small and curated
- Vault = append-only, never delete
- Handoffs = continuity mechanism
- Flat files = human-readable, portable
## Usage
All 973 tests pass.
2026-02-25 18:17:43 -05:00
Alexander Payne
625806daf5
Fine-tune Timmy's conversational AI with memory layers
...
## Enhanced System Prompt
- Detailed tool usage guidelines with explicit examples
- Clear DO and DON'T examples for tool selection
- Memory system documentation
- Conversation flow guidelines
- Context awareness instructions
## Memory Layer System (NEW)
Implemented 3-layer memory architecture:
1. WORKING MEMORY (src/timmy/memory_layers.py)
- Immediate context (last 20 messages)
- Topic tracking
- Tool call tracking
- Fast, ephemeral
2. SHORT-TERM MEMORY (Agno SQLite)
- Recent conversations (100)
- Persists across restarts
- Managed by Agno Agent
3. LONG-TERM MEMORY (src/timmy/memory_layers.py)
- Facts about user (name, preferences)
- SQLite storage in data/memory/
- Auto-extraction from conversations
- User profile generation
## Memory Manager (NEW)
- Central coordinator for all memory layers
- Context injection into prompts
- Fact extraction and storage
- Session management
## TimmyWithMemory Class (NEW)
- Wrapper around Agno Agent with explicit memory
- Auto-injects user context from LTM
- Tracks exchanges across all layers
- Simple chat() interface
## Agent Configuration
- Increased num_history_runs: 10 -> 20
- Better conversational context retention
## Tests
- All 973 tests pass
- Fixed test expectations for new config
- Fixed module path in test_scary_paths.py
## Files Added/Modified
- src/timmy/prompts.py - Enhanced with memory and tool guidance
- src/timmy/agent.py - Added TimmyWithMemory class
- src/timmy/memory_layers.py - NEW memory system
- src/timmy/conversation.py - NEW conversation manager
- tests/ - Updated for new config
2026-02-25 18:07:44 -05:00
Alexander Payne
29292cfb84
feat: single-command Docker startup, fix UI bugs, add Selenium tests
...
- Add `make up` / `make up DEV=1` for one-command Docker startup with
optional hot-reload via docker-compose.dev.yml overlay
- Add `timmy up --dev` / `timmy down` CLI commands
- Fix cross-platform font resolution in creative assembler (7 test failures)
- Fix Ollama host URL not passed to Agno model (container connectivity)
- Fix task panel route shadowing by reordering literal routes before
parameterized routes in swarm.py
- Fix chat input not clearing after send (hx-on::after-request)
- Fix chat scroll overflow (CSS min-height: 0 on flex children)
- Add Selenium UI smoke tests (17 tests, gated behind SELENIUM_UI=1)
- Install fonts-dejavu-core in Dockerfile for container font support
- Remove obsolete docker-compose version key
- Bump CSS cache-bust to v4
833 unit tests pass, 15 Selenium tests pass (2 skipped).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com >
2026-02-25 07:20:56 -05:00
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
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
