LangBot

mirror of https://github.com/langbot-app/LangBot.git synced 2026-06-19 20:14:20 +00:00

Files

T

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

requesters

refactor(provider): use LiteLLM as unified LLM requester backend (#2150 )

2026-06-13 16:59:48 +08:00

runners

test: format test suite (#2252 )

2026-06-16 11:22:29 +08:00

__init__.py

refactor(provider): use LiteLLM as unified LLM requester backend (#2150 )

2026-06-13 16:59:48 +08:00

conftest.py

test: format test suite (#2252 )