Fix 400 Error with Parallel Tool Calls (LiteLLM Adapter) #231
+18
−5
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
When the LLM returns multiple tool calls in a single assistant message, the OpenAI API requires a subsequent 'tool' message for each tool_call_id provided. The previous implementation in `_get_completion_inputs` only processed the first `function_response` found within an aggregated ADK event (Content with multiple parts), creating only one 'tool' message. This resulted in a `400 Bad Request` error from the API. This commit modifies `_get_completion_inputs` in `lite_llm.py` to iterate through all parts containing a `function_response` in the aggregated event and generate a distinct `ChatCompletionToolMessage` for each one, ensuring API compliance.
|
Thanks for your pull request! It looks like this may be your first contribution to a Google open source project. Before we can look at your pull request, you'll need to sign a Contributor License Agreement (CLA). View this failed invocation of the CLA check for more information. For the most up to date status, view the checks section at the bottom of the pull request. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
API calls via the LiteLLM adapter failed with a 400 Bad Request when models like OpenAI returned multiple tool_calls (requesting parallel execution). The adapter incorrectly sent only one tool response message back, while the API requires a separate tool message for each requested tool_call_id.
Cause:
The _get_completion_inputs function in lite_llm.py only processed the first function_response part from the ADK's aggregated tool response event, ignoring subsequent ones.
Solution:
Modified _get_completion_inputs to iterate through all function_response parts in the aggregated event. It now correctly generates a distinct ChatCompletionToolMessage (role: 'tool') for each tool_call_id.
Impact:
Resolves the 400 Bad Request error. Ensures correct message formatting for the API when handling parallel tool calls, enabling agent flows with multiple simultaneous tool executions.