Skip to content

fix: per-job EventLoopThread + timeout kill for parallel tools #1781

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
redcomet168 wants to merge 1 commit into
base: main
Choose a base branch
from
Open

fix: per-job EventLoopThread + timeout kill for parallel tools #1781

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 7 additions & 3 deletions helpers/parallel_tools.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -216,7 +216,7 @@ async def start_parallel_jobs(
try:
job.state = "running"
job.started_at = time.time()
task = DeferredTask(thread_name=THREAD_BACKGROUND)
task = DeferredTask(thread_name=f"parallel-{job.id}")
job.deferred_task = task
task.start_task(_run_parallel_job, context.id, job.id)
except Exception as exc:
Expand Down Expand Up @@ -252,6 +252,10 @@ async def await_parallel_jobs(

if time.time() >= deadline:
wait_timed_out_job_ids = {job.id for job in active}
for job in active:
if job.deferred_task:
job.deferred_task.kill(terminate_thread=True)
_finish_job(job, "timeout", error="Job exceeded timeout and was killed.")
break

await asyncio.sleep(POLL_INTERVAL_SECONDS)
Expand Down Expand Up @@ -316,7 +320,7 @@ async def refresh_parallel_jobs(agent: "Agent") -> list[ParallelJob]:

async def cleanup_parallel_job(agent: "Agent", job: ParallelJob) -> None:
if job.deferred_task and job.deferred_task.is_alive():
job.deferred_task.kill()
job.deferred_task.kill(terminate_thread=True)
if job.kind == "tool":
await _remove_context(job.worker_context_id)

Expand Down Expand Up @@ -604,7 +608,7 @@ async def _cancel_job(
message: str = "Parallel job was cancelled.",
) -> None:
if job.deferred_task and job.deferred_task.is_alive():
job.deferred_task.kill()
job.deferred_task.kill(terminate_thread=True)
_finish_job(job, state, error=message)


Expand Down