fix: prevent duplicate historical events and filter reasoning parts#435
Merged
fix: prevent duplicate historical events and filter reasoning parts#435
Conversation
|
Codecov Report❌ Patch coverage is
📢 Thoughts on this report? Let us know! |
- fix(tui): prevent duplicate display of historical events on continue Changed the execution loop to only pass historical events on the first iteration, preventing duplicate query/complete activities. - fix(runtime): filter reasoning parts for non-Anthropic providers Added filtering to remove reasoning parts from message history when sending to OpenAI, Azure OpenAI, DeepSeek, or Ollama providers. This prevents "Non-OpenAI reasoning parts are not supported" warnings. Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
ebaecb9 to
05427b2
Compare
Merged
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 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
fix(tui): prevent duplicate display of historical events on continue
Changed the execution loop to only pass historical events on the first iteration.
Subsequent iterations no longer receive historical events since the previous TUI
output remains visible on screen, preventing duplicate display of query/complete
activities.
fix(runtime): filter reasoning parts for non-Anthropic providers
Added filtering to remove reasoning parts from message history when sending
to OpenAI, Azure OpenAI, DeepSeek, or Ollama providers. This prevents the
"Non-OpenAI reasoning parts are not supported" warning from AI SDK when
resuming runs that were previously executed with Anthropic's extended thinking.
Test plan
perstack startand interactive tool continue flow🤖 Generated with Claude Code