chopratejas 7cf10675ea Add centralized ML model configuration ... - Create headroom/models/config.py as single source of truth for all ML model defaults - Support environment variable overrides (HEADROOM_SENTENCE_TRANSFORMER, etc.) - Update all components to use ML_MODEL_DEFAULTS instead of hardcoded values - Switch LLMLingua default to smaller bert-base model (~350MB vs 1GB) - Total memory footprint reduced from ~1.6GB to ~980MB Updated files: - MLModelRegistry now resolves defaults from config - EmbeddingScorer, LocalEmbedder, TrainedRouter use config - All dataclass configs use field(default_factory=...) for consistency - Tests updated to handle auto-selected vector backends		2026-02-01 23:47:42 -08:00
..
__init__.py	Add persistent memory system with zero-latency inline extraction	2026-01-14 21:32:09 -08:00
conftest.py	Add global httpx.ReadTimeout handler for memory tests	2026-01-28 09:43:44 -08:00
test_core_operations.py	Add multi-provider memory system with auto-detection	2026-02-01 14:42:50 -08:00
test_easy.py	fix(tests): skip memory tests when hnswlib not available	2026-01-31 16:09:53 -08:00
test_extraction.py	Add hierarchical memory system with graph + vector storage	2026-01-26 21:58:47 -08:00
test_factory.py	Add centralized ML model configuration	2026-02-01 23:47:42 -08:00
test_hierarchical.py	Add DiffCompressor and fix hnswlib SIGILL crash on CI	2026-01-31 08:09:55 -08:00