fix(acp): separate v2 thinking blocks - #65
Merged
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Preserve ACP v2 reasoning-part boundaries by assigning each AgentKit reasoning part a distinct thought message ID. This restores separate thinking blocks in clients that group streamed chunks by message ID.
Motivation
The ACP v2 integration reused one thought message ID for all reasoning parts between tool boundaries, causing the TUI and desktop app to append distinct thinking sections into a single block.
Technical details
Streaming and response replacement
Chunks from the same reasoning part retain one stable message ID, while separate parts receive distinct IDs. Cancellation and superseded-response cleanup now clears every active thought message rather than only the latest one.