feat(agent): 15-min timeout, remove single-run concurrency cap#251
Merged
Conversation
Bump the agent watchdog default to 900000ms (15 min) and drop the one-run-at-a-time Semaphore, so requests run concurrently instead of being turned away with a busy message. Each run is still bounded by the kill-tree! watchdog and isolated per-run scratch dirs.
Reflect the removed single-run concurrency cap and the 900000ms default.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What
agent-timeout-msdefault 300000 → 900000ms (15 min) (still overridable via[:gemini :agent :timeout-ms]).Semaphore(run-permit) and the "🦴 grug already smashing one rock" busy reply.!agentrequests now run concurrently with no cap.Each run is still bounded by the
kill-tree!wall-clock watchdog and isolated per-run/tmpscratch dirs, so a hung run self-terminates and runs don't share state.Note
No concurrency limit means N simultaneous
!agentcalls spawn N Gemini (bun/node) + git-clone trees. On a small host that can over-subscribe CPU; the box was resized to 16GB so OOM is unlikely, but heavy parallelism on 2 cores will be slow.