4 commits

Author	SHA1	Message	Date
Adil Hafeez	1605d2caa6	refactor filter pipeline: introduce ResolvedFilterChain and FilterPipeline types ... - Replace 4 separate filter params with single Arc<FilterPipeline> in llm_chat - Add ResolvedFilterChain (filter_ids + agents) and FilterPipeline (input + output) - Rename utils.rs to streaming.rs, extract STREAM_BUFFER_SIZE constant - Deduplicate output filter logic via Box<dyn StreamProcessor> - Rename upstream_path param to request_path for consistency Made-with: Cursor	2026-03-18 16:47:16 -07:00
Adil Hafeez	46de89590b	use standard tracing and logging in brightstaff (#721)	2026-02-09 13:33:27 -08:00
Adil Hafeez	ca95ffb63d	cargo clippy (#660)	2025-12-25 21:08:37 -08:00
Salman Paracha	d5a273f740	enable state management for v1/responses (#631) ... * first commit with tests to enable state mamangement via memory * fixed logs to follow the conversational flow a bit better * added support for supabase * added the state_storage_v1_responses flag, and use that to store state appropriately * cleaned up logs and fixed issue with connectivity for llm gateway in weather forecast demo * fixed mixed inputs from openai v1/responses api (#632) * fixed mixed inputs from openai v1/responses api * removing tracing from model-alias-rouing * handling additional input types from openairs --------- Co-authored-by: Salman Paracha <salmanparacha@MacBook-Pro-342.local> * resolving PR comments --------- Co-authored-by: Salman Paracha <salmanparacha@MacBook-Pro-342.local>	2025-12-17 12:18:38 -08:00