fix(dashboard): Polish subagent transcript handling#819
Merged
Conversation
Keep parent tool calls paired with results across nested advisor activity while avoiding ambiguous name-only matches. Render advisor requests without internal XML in reporting, add reusable Markdown copying to the subagent drawer, and preserve the shared transcript formatting and privacy boundaries. Fixes #745 Co-Authored-By: GPT-5.5 Codex <noreply@openai.com>
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Advisor transcript drawers now project the internal advisor request envelope into readable task and context content, keep tool calls paired with results across synthetic subagent and thinking entries, and expose a shared Markdown copy action in both conversation and subagent views. Completed subagent rows also use the expected pointer affordance, and the drawer adapts cleanly to narrow screens.
Pairing remains bounded by real message boundaries and rejects ambiguous name-only matches, so unrelated tool activity is not combined. Regression coverage exercises the render-model edge cases, advisor reporting projection, copy behavior, and responsive drawer interaction.
Fixes #745