2 commits

Author	SHA1	Message	Date
Rodrigo Rodriguez (Pragmatismo)	3befc141e5	Fix token limits for local llama.cpp server ... - Add token-aware text truncation utility in core/shared/utils.rs - Fix embedding generators to use 600 token limit (safe under 768) - Fix LLM context limit detection for local models (768 vs 4096) - Prevent 'exceed context size' errors for both embeddings and chat	2026-02-02 11:56:13 -03:00
Rodrigo Rodriguez (Pragmatismo)	43b168a4b5	Update workspace configuration and submodules	2026-01-30 23:25:02 -03:00