4 Commits

Include renames

Author	SHA1	Message	Date
BiFangKNT	807de8d24a	fix(provider): sanitize replayed Groq message metadata ... Remove response-only finish_reason metadata when converting stored messages into subsequent model requests. Strip provider_specific_fields from Groq messages and tool calls to avoid strict request validation failures after a tool response. Preserve metadata required by other providers, including Gemini thought signatures, without mutating the original message entities. Cover streaming and non-streaming request construction with regression tests.	2026-10-17 19:48:25 +08:00
RockChinQ	f24a7c9bb2	feat(runner): unify plugin execution across agents and event processors	2026-09-10 18:04:38 +08:00
huanghuoguoguo	517986bd10	feat(agent-runner): support scoped token counting	2026-07-19 22:41:31 +08:00
huanghuoguoguo	acfac42107	fix(litellmchat): preserve provider_specific_fields for Gemini thought_signature (#2265) ... Update _normalize_stream_tool_calls to preserve provider_specific_fields (including thought_signature) from streaming tool call chunks. Also preserve provider_specific_fields from delta in invoke_llm_stream. This ensures Gemini's thought_signature is round-tripped correctly: 1. LiteLLM extracts thought_signature from Gemini response 2. It's preserved in Message/ToolCall entities (via SDK changes) 3. _convert_messages includes it in the next request Also add unit tests for provider_specific_fields round-tripping. Fixes: langbot-app/LangBot#1899	2026-06-19 23:26:12 +08:00