Repository navigation
Conversation
lilly-luo
changed the title
lilly-luo
changed the title
Claude folds parallel Agent rows into its own "Running N agents" block, which raises no render hook, so the above-prompt panel and row annotations could not show parallel decisions in place. Draw every decision, single or parallel, as a card above the parent's first reply after routing, in call order, and show routing progress on the turn spinner while calls wait. Remove the above-prompt panel, its prompt-reset handling, and the TUI preview that exercised it. Co-authored-by: Isaac <no-reply@databricks.com>
lilly-luo
changed the title
lilly-luo
changed the title
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
before: when multiple subagents spawned, we did not show the model selected and rationale. we only showed model + rationale for a single subagent.
after: render the model selected and rationale for multiple simultaneous subagent spawns
Testing
before:
2 subagents (no model or rationale)
https://github.com/user-attachments/assets/116d1940-0893-4db1-b2d5-94c80d774422
1 subagent (model + rationale)
after:
2 subagents (model + rationale)
https://github.com/user-attachments/assets/c5ad9891-db35-4444-bcd1-044a82498789
1 subagent (model + rationale), although formatted slightly diff to be consistent w 2 subagents. preserving the original format wasnt doable because of what anthropic restricts
This pull request and its description were written by Isaac.