This repository was archived by the owner on May 15, 2026. It is now read-only.
fix: omit parallel_tool_calls from LiteLLM provider - #10241
Closed
ghost wants to merge 1 commit into
Closed
Conversation
- Remove parallel_tool_calls parameter from all LiteLLM requests - This parameter is not supported by all LiteLLM backends (e.g., Bedrock) - Parallel tool calling is already handled via system prompts - Update tests to verify parallel_tool_calls is omitted for all models
Author
Review completed. No issues found.
Mention @roomote in a comment to request specific changes to this pull request or fix all unresolved issues. |
hannesrudolph
added
the
Issue/PR - Triage
Author
|
Closing this PR in favor of updating the original PR #10235 with the correct Bedrock detection logic. |
ghost
closed this
This pull request was closed.
This file contains hidden or 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
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Fixes the issue where the
parallel_tool_callsparameter was being sent to LiteLLM backends that do not support it (e.g., AWS Bedrock).Problem
The previous approach (PR #10235) attempted to detect Bedrock models specifically, but this incorrectly marked all Anthropic models as Bedrock models due to the
anthropic.prefix check. This caused issues for users using Anthropic models directly through LiteLLM.Solution
Instead of trying to detect which backends support
parallel_tool_calls, we simply omit the parameter entirely from all LiteLLM requests. This is acceptable because:Changes
parallel_tool_callsparameter from LiteLLM request optionsisBedrockModel()detection logicTesting
✅ All existing tests pass
✅ Added 2 new test cases to verify
parallel_tool_callsis omitted for all modelsView task on Roo Code Cloud