fix(web): subagent transcript always shows the prompt it was spawned with - #238
Merged
Merged
Conversation
…with The instruction block above a subagent's transcript only rendered when the loaded page began at the transcript's first record. The panel opens on the newest 60 records and a working agent's transcript runs into the hundreds, so the block almost never appeared. The server also capped every record at 4,000 characters, while real spawn prompts run past 10,000. The panel now reads the first record once when the newest page starts past it, pins the instruction above the "Load earlier" control, and shows the objective fallback regardless of which page is visible. On the server, text sent to the agent keeps up to 32,000 characters; the agent's own output keeps the existing cap.
|
The latest updates on your projects. Learn more about Vercel for GitHub. 1 Skipped Deployment
|
github-actions
Bot
added
vouch:trusted
badcuban
enabled auto-merge
September 6, 2026 06:52
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
The instruction block above a subagent's transcript (the prompt the main agent gave it, folded with a "Show all" toggle) only rendered when the loaded page began at the transcript's first record. The panel opens on the newest 60 records and a working agent's transcript runs into the hundreds, so the block almost never appeared. Separately, the server capped every transcript record at 4,000 characters while real spawn prompts run past 10,000, so even after paging back the prompt was cut mid-sentence.
Fix:
Tests: new browser case for a mid-transcript first page, a logic test for the separately read lead, and a server test for the input-text cap. fmt, lint, typecheck, the Claude adapter suite, and the transcript and agents-panel browser suites pass.