- 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
- Update botserver submodule with LLM feature enabled by default
- Fix duplicate module declarations and move errors
- Remove unused imports and variables
- Improve code formatting
This enables the LLM feature by default so it's always available
when building the project.
