Skip to content

Google: Continue on MALFORMED_FUNCTION_CALL #3095

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom
Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Google: Continue on MALFORMED_FUNCTION_CALL #3095

wants to merge 1 commit into from
+2 −0

Conversation

ArneZsng
Copy link
Contributor

@ArneZsng ArneZsng commented Oct 6, 2025 •
edited by DouweM
Loading

Using Gemini, we are frequently running into the MALFORMED_FUNCTION_CALL as the finish reason.
Google seemingly does not provide any context in the response for the reason of the MALFORMED_FUNCTION_CALL.

In these cases, the agent can continue retrying which I why I suggest to simply continue in the case of a MALFORMED_FUNCTION_CALL.

Closes #631

The issue is most prevalent when using Gemini 2.5 Flash (compared to Gemini 2.5 Pro where it also happens but less frequently).

Example chunk:

sdk_http_response=HttpResponse(
  headers=<dict len=11>
) candidates=[Candidate(
  finish_reason=<FinishReason.MALFORMED_FUNCTION_CALL: 'MALFORMED_FUNCTION_CALL'>,
  index=0
)] create_time=None model_version=None prompt_feedback=None response_id=None usage_metadata=GenerateContentResponseUsageMetadata(
  prompt_token_count=2595,
  prompt_tokens_details=[
    ModalityTokenCount(
      modality=<MediaModality.TEXT: 'TEXT'>,
      token_count=2595
    ),
  ],
  total_token_count=2595
) automatic_function_calling_history=None parsed=None

DouweM
DouweM requested changes Oct 7, 2025
View reviewed changes
pydantic_ai_slim/pydantic_ai/models/google.py
if candidate.finish_reason == 'STOP': # pragma: no cover
# Normal completion - skip this chunk
continue
elif candidate.finish_reason == 'MALFORMED_FUNCTION_CALL': # pragma: no cover
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Can we add a test for this, based on a real-world response with this finish reason?

Is skipping the chunk the right thing to do? Would any more chunks follow or would this be the last one in the response? Is it valid to just move on and ignore the error?

If the response before this failure is empty, we retry the request, which I suppose is the goal:

pydantic-ai/pydantic_ai_slim/pydantic_ai/_agent_graph.py

Lines 567 to 572 in 9b1913e

# Go back to the model request node with an empty request, which means we'll essentially
# resubmit the most recent request that resulted in an empty response,
# as the empty response and request will not create any items in the API payload,
# in the hope the model will return a non-empty response this time.
ctx.state.increment_retries(ctx.deps.max_result_retries)
self._next_node = ModelRequestNode[DepsT, NodeRunEndT](_messages.ModelRequest(parts=[]))

@DouweM DouweM self-assigned this Oct 7, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@DouweM DouweM DouweM requested changes

Assignees

@DouweM DouweM

Labels
awaiting author revision
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.

MALFORMED_FUNCTION finishReason in Gemini candidate
2 participants
@ArneZsng @DouweM