CREDO23 71dead0406 perf(kb-planner): route internal planner calls to dedicated small/fast LLM ... Adds an optional planner LLM role wired through KnowledgePriorityMiddleware so KB query rewriting, date extraction, and recency classification run on a cheap model (e.g. gpt-4o-mini, Haiku, Azure nano) instead of the user's chat LLM. Operators opt in by setting is_planner: true on exactly one global config; without it, behavior is unchanged.		2026-05-20 11:42:52 +02:00
..
main_agent	chore: linting	2026-05-15 17:33:44 -07:00
middleware	perf(kb-planner): route internal planner calls to dedicated small/fast LLM	2026-05-20 11:42:52 +02:00
subagents	perf(kb subagent, desktop): cap evidence.content_excerpt to 500 chars	2026-05-20 09:43:36 +02:00
__init__.py	fix(stream): route every agent (re)build through one helper to prevent factory drift	2026-05-05 23:35:23 +02:00
constants.py	multi_agent_chat/subagents: dict-keyed middleware_stack + always-on KB	2026-05-12 18:04:54 +02:00