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
..
directory_config.json	Fix token limits for local llama.cpp server	2026-02-02 11:56:13 -03:00