Show live progress on a dispatched sub-agent's transcript row - #352
Merged
Conversation
A task call's row painted a bare dot until its result landed, so a parent that dispatched several sub-agents at once had no way to tell a worker mid-turn from one that had gone silent — every unfinished dispatch looked identical. The sub-agent session store already tracks each worker's current tool and now its last activity clock; the runtime bridge polls it on the same cadence it already ticks the chrome and rewrites each outstanding task call's row in place with elapsed time, current tool, and a mark that tells working apart from stalled. The row itself never grows an extra line and the rewrite touches only that one row, regardless of how many other rows sit above it. Resolving a dispatch drops its live elapsed-time trailer for the result's own answer rather than leaving the last progress reading stuck on a finished row.
TheGreatAxios
force-pushed
the
cl-5576-subagent-progress
branch
from
August 7, 2026 07:24
3769dd9 to
58e3b15
Compare
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
taskcall row now updates in place with liveelapsed time, its current tool, and a mark that distinguishes actively
working, quietly finished, and stalled (no progress signal past 30s).
SubAgentSessionStoresessions(status, currentToolName, startedAt, plus a new
lastActivityAt) areread on the existing chrome poll cadence and folded into the row the
runtime bridge already tracks by callId — no new event channel.
in favor of the result's own answer, fixing a case where a stale
in-flight stat could survive onto a finished row.
Verification
bun run typecheckbun run buildbun run test— 3912 pass, 0 failconcurrent dispatches (two working, one resolved):
Closes CL-5576