scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-05 08:07:05 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 137

Fix #20557: Fix Gemini multi-turn tool calling message formatting (#20569)

Browse source 
- Add missing 'role' field to tool result ContentType objects
- Tool result messages must have role='user' to match Gemini API requirements
- Fixes 'contents[2].parts[0].data: required oneof field data' error on second turn
- Prevents uninitialized data field in tool result messages
This commit is contained in:
Rahul Dhanawade 2026-02-11 23:57:09 +05:30 • committed by GitHub
parent ce421df1ef
commit 49078b3c6b
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 2 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
litellm/llms/vertex_ai/gemini/transformation.py
View file

@ -500,7 +500,7 @@ def _gemini_convert_messages_with_history( # noqa: PLR0915
messages[msg_i]["role"] not in tool_call_message_roles
):
if len(tool_call_responses) > 0:
contents.append(ContentType(parts=tool_call_responses))
contents.append(ContentType(role="user", parts=tool_call_responses))
tool_call_responses = []
if msg_i == init_msg_i: # prevent infinite loops
@ -510,7 +510,7 @@ def _gemini_convert_messages_with_history( # noqa: PLR0915
)
)
if len(tool_call_responses) > 0:
contents.append(ContentType(parts=tool_call_responses))
contents.append(ContentType(role="user", parts=tool_call_responses))
if len(contents) == 0:
verbose_logger.warning(