Fix: Empty tool results cause OpenAI models to halt #67
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
OpenAI models can halt when receiving empty tool results (from empty files, commands with no output, etc.). This adds an opt-in fix via FIX_EMPTY_TOOL_RESULTS=1 that replaces empty content with a placeholder string. Co-authored with Claude Code (https://claude.ai/claude-code)
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Outdated suggestions cannot be applied.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.
Problem
OpenAI models can halt or produce unexpected behavior when they receive empty tool results. This commonly happens when using the Claude CLI with:
The Claude CLI sends these empty results normally (Anthropic handles them fine), but OpenAI models often just stop generating without any error. This is particularly frustrating when using the proxy with agentic workflows.
Solution
Add an opt-in fix via environment variables:
FIX_EMPTY_TOOL_RESULTS=1- Enable the fixEMPTY_TOOL_RESULT_PLACEHOLDER- Custom placeholder (default: "NULL")When enabled, empty tool result content is replaced with the placeholder string, which OpenAI models handle correctly.
Usage
Changes
fix_empty_tool_result()helper functionparse_tool_result_content()at all return pointsCo-authored with Claude Code