fix: normalize None reasoning/response deltas to prevent TypeError #887
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
When some LLM providers return None for reasoning_delta or response_delta in streaming chunks, the string concatenation in add_chunk() and _process_thinking_chunk() would fail with: TypeError: can only concatenate str (not 'NoneType') to str This fix normalizes None values to empty strings before concatenation, preventing crashes during memory recall and other streaming operations.
There was a problem hiding this comment.
Pull request overview
This pull request fixes a TypeError that occurs when LLM providers (such as certain Ollama models) return None values for reasoning_delta or response_delta in streaming chunks, which causes string concatenation to fail.
Key changes:
- Added None-to-empty-string normalization at the entry point of
add_chunk()method - Added defensive guards in
_process_thinking_chunk()to handle potential None values during concatenation - Fixed a typo in a comment ("ned" → "need")
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
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Outdated suggestions cannot be applied.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
When some LLM providers (e.g., certain Ollama models) return
Noneforreasoning_deltaorresponse_deltain streaming chunks, the string concatenation inChatGenerationResult.add_chunk()and_process_thinking_chunk()fails with:This crash occurs during memory recall operations and other streaming workflows.
Solution
Normalize
Nonevalues to empty strings ("") before any concatenation in:add_chunk()- at the start, coerce incoming chunk values_process_thinking_chunk()- guard the concatenation withor ""Testing
dolphin-mixtral:org-uncensoredvia OllamaRelated
Fixes crashes observed when using local Ollama models that sometimes emit null reasoning deltas.