3 Commits

Include renames

Author	SHA1	Message	Date
jpmschweitzerandClaude Opus 4.6	427ad311dc	feat: switch default Ollama model to gemma4:e2b ... gemma4:e2b has native function calling with dedicated tool tokens, achieving 100% tool selection accuracy in benchmarks vs 67% for mistral-nemo-large, with 5-8x faster response times (2-4s vs 15-20s) and lower VRAM usage (8GB vs 9.2GB). Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>	2026-04-04 22:44:27 +02:00
jpmschweitzerandClaude Opus 4.5	363ab378af	feat: optimize Housekeeper for Mistral-Nemo tool calling ... - Rewrite system prompt with negative constraints and step-by-step process - Set temperature to 0.1 for deterministic tool calling - Sort room groups to top of device list (address positional bias) - Add [ROOM GROUP] marker in list_devices output - Update tool docstrings with explicit entity_id= parameter examples - Add optimization findings doc (experiment log: 0% → 100% success) - Add test script for room group detection regression testing 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>	2025-12-18 20:58:39 +01:00
jpmschweitzerandClaude Sonnet 4.5	6eed5f4d13	feat: implement Phase 2 two-tier architecture with Steward ... Add comprehensive two-tier architecture where Steward analyzes requests and Tatlock executes with scoped tools. Includes full infrastructure for request preprocessing, tool tracking, benchmarking, and streaming. **Added:** - Steward agent for request analysis and capability recommendation - Household Registry for centralized capability management - Request preprocessing pipeline (Steward → Tatlock flow) - Tool usage tracking and benchmarking system - Streaming transparency (Steward reasoning visible in streams) - Structured logging with operation timing - Redis benchmark storage with 30-day expiry - Benchmark analysis CLI tools **Infrastructure:** - src/agents/steward/ - Steward agent implementation - src/agents/tatlock_core/ - Tatlock capability domain - src/core/preprocessing.py - Request preprocessing pipeline - src/core/tool_tracking.py - Tool call tracking - src/core/benchmarks.py - Benchmark recording system - src/core/household_registry.py - Capability registry - src/core/startup.py - Application startup coordination - src/core/logging_config.py - Structured logging setup **Integration:** - Responses API uses Steward for Tatlock requests - Chat Completions wraps Responses API for OpenAI compatibility - Streaming coordinator supports Steward + Tatlock flow - Tool scoping per request based on Steward recommendations **Testing:** - Integration tests for Steward-Tatlock flow - Benchmark and registry unit tests - Steward streaming tests See PHASE2_PLAN.md and PHASE2_COMPLETE.md for detailed documentation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>	2025-12-07 15:39:20 +01:00