2 Commits

Author	SHA1	Message	Date
Alvis	ab68bba935	Add routing benchmark scripts; gitignore dataset and results ... - run_benchmark.py: sends queries to /message, extracts tier= from docker logs, reports per-tier accuracy, saves results_latest.json - run_voice_benchmark.py: voice path benchmark - .gitignore: ignore benchmark.json (dataset) and results_latest.json (runtime output); benchmark scripts are tracked, data files are not Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>	2026-03-24 02:00:17 +00:00
Alvis	f9618a9bbf	Integrate Bifrost LLM gateway, add test suite, implement memory pipeline ... - Add Bifrost (maximhq/bifrost) as LLM gateway: all inference routes through bifrost:8080/v1 with retry logic and observability; VRAMManager keeps direct Ollama access for VRAM flush/prewarm operations - Switch medium model from qwen3:4b to qwen2.5:1.5b (direct call, no tools) via _DirectModel wrapper; complex keeps create_deep_agent with qwen3:8b - Implement out-of-agent memory pipeline: _retrieve_memories pre-fetches relevant context (injected into all tiers), _store_memory runs as background task after each reply writing to openmemory/Qdrant - Add tests/unit/ with 133 tests covering router, channels, vram_manager, agent helpers; move integration test to tests/integration/ - Add bifrost-config.json with GPU Ollama (qwen2.5:0.5b/1.5b, qwen3:4b/8b, gemma3:4b) and CPU Ollama providers - Integration test 28/29 pass (only grammy fails — no TELEGRAM_BOT_TOKEN) Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>	2026-03-12 13:50:12 +00:00