(FIX) lm studio empty tool calls #6054
Open
+246
−3
Conversation
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
Introduced a new middleware to intercept API responses and filter out empty tool_calls arrays, preventing indefinite waits in the AI SDK. This includes handling both streaming and non-streaming responses. Additionally, updated the OpenAI-compatible provider to utilize this middleware and ensure proper cleanup of pending tool calls in session processing.
…ion processing Updated the createFilteredFetch function to specify the return type and clarified the filtering mechanism for empty tool_calls. Removed unnecessary middleware wrapping in filterEmptyToolCalls, as filtering is now handled at the fetch level. Enhanced session processing to correctly handle empty tool_calls by updating the error state with the appropriate timestamps.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.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 #4255
Problem
OpenCode hangs indefinitely when using LM Studio (and other OpenAI-compatible providers) that include empty
tool_calls: []arrays in responses. The AI SDK sees thetool_callsfield and waits for tool execution, but since the array is empty, it never completes.Solution
Added middleware to filter empty
tool_callsarrays from API responses before they reach the AI SDK:Fetch-level filtering: Intercepts responses at the HTTP layer and removes empty
tool_calls: []whenfinish_reasonis"stop". Works for both streaming (SSE) and non-streaming responses.Processor fallback: Cleans up any pending tool calls that were never invoked when
finish_reasonis"stop", handling edge cases where empty arrays slip through.The fix is applied automatically to all
@ai-sdk/openai-compatibleproviders, ensuring LM Studio and similar providers work correctly without requiring configuration changes.