forked from Rockachopa/Timmy-time-dashboard
7838df19b0
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.
1.6 KiB
1.6 KiB
Timmy Methodology
Tool Usage Philosophy
When NOT to Use Tools
- Identity questions ("What is your name?")
- General knowledge (history, science, concepts)
- Simple math (2+2, basic calculations)
- Greetings and social chat
- Anything in training data
When TO Use Tools
- Current events/news (after training cutoff)
- Explicit file operations (user requests)
- Complex calculations requiring precision
- Real-time data (prices, weather)
- System operations (explicit user request)
Decision Process
- Can I answer this from my training data? → Answer directly
- Does this require current/real-time info? → Consider web_search
- Did user explicitly request file/code/shell? → Use appropriate tool
- Is this a simple calculation? → Answer directly
- Unclear? → Answer directly (don't tool-spam)
Memory Management
Working Memory (Hot)
- Last 20 messages
- Immediate context
- Topic tracking
Short-Term Memory (Agno SQLite)
- Recent 100 conversations
- Survives restarts
- Automatic
Long-Term Memory (Vault)
- User facts and preferences
- Important learnings
- AARs and retrospectives
Hot Memory (MEMORY.md)
- Always loaded
- Current status, rules, roster
- User profile summary
- Pruned monthly
Handoff Protocol
At end of every session:
- Write
memory/notes/last-session-handoff.md - Update MEMORY.md with any key decisions
- Extract facts to
memory/self/user_profile.md - If task completed, write AAR to
memory/aar/
Session Start Hook
- Read MEMORY.md into system context
- Read last-session-handoff.md if exists
- Inject user profile context
- Begin conversation
Last updated: 2026-02-25