fix: eliminate 'Event loop is closed' / 'Press ENTER to continue' during idle#3398
Merged
fix: eliminate 'Event loop is closed' / 'Press ENTER to continue' during idle#3398
Conversation
…ing idle
The OpenAI SDK's AsyncHttpxClientWrapper.__del__ schedules aclose() via
asyncio.get_running_loop().create_task(). When an AsyncOpenAI client is
garbage-collected while prompt_toolkit's event loop is running (the common
CLI idle state), the aclose() task runs on prompt_toolkit's loop but the
underlying TCP transport is bound to a different (dead) worker loop.
The transport's self._loop.call_soon() then raises RuntimeError('Event
loop is closed'), which prompt_toolkit surfaces as the disruptive
'Unhandled exception in event loop ... Press ENTER to continue...' error.
Three-layer fix:
1. neuter_async_httpx_del(): Monkey-patches __del__ to a no-op at CLI
startup before any AsyncOpenAI clients are created. Safe because
cached clients are explicitly cleaned via _force_close_async_httpx,
and uncached clients' TCP connections are cleaned by the OS on exit.
2. Custom asyncio exception handler: Installed on prompt_toolkit's event
loop to silently suppress 'Event loop is closed' RuntimeError.
Defense-in-depth for SDK upgrades that might change the class name.
3. cleanup_stale_async_clients(): Called after each agent turn (when the
agent thread joins) to proactively evict cache entries whose event
loop is closed, preventing stale clients from accumulating.
binhnt92
added a commit
to binhnt92/hermes-agent
that referenced
this pull request
Mar 29, 2026
…ed event loop The AsyncOpenAI client was created once at __init__ and stored as an instance attribute. process_directory() calls asyncio.run() which creates and closes a fresh event loop. On a second call, the client's httpx transport is still bound to the closed loop, raising RuntimeError: "Event loop is closed" — the same pattern fixed by PR NousResearch#3398 for the main agent loop. Create the client lazily in _get_async_client() so each asyncio.run() gets a client bound to the current loop.
3 tasks
teknium1
pushed a commit
that referenced
this pull request
Mar 30, 2026
…ed event loop The AsyncOpenAI client was created once at __init__ and stored as an instance attribute. process_directory() calls asyncio.run() which creates and closes a fresh event loop. On a second call, the client's httpx transport is still bound to the closed loop, raising RuntimeError: "Event loop is closed" — the same pattern fixed by PR #3398 for the main agent loop. Create the client lazily in _get_async_client() so each asyncio.run() gets a client bound to the current loop.
teknium1
added a commit
that referenced
this pull request
Mar 30, 2026
…ed event loop (#4013) The AsyncOpenAI client was created once at __init__ and stored as an instance attribute. process_directory() calls asyncio.run() which creates and closes a fresh event loop. On a second call, the client's httpx transport is still bound to the closed loop, raising RuntimeError: "Event loop is closed" — the same pattern fixed by PR #3398 for the main agent loop. Create the client lazily in _get_async_client() so each asyncio.run() gets a client bound to the current loop. Co-authored-by: binhnt92 <binhnt.ht.92@gmail.com>
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.
Summary
Fixes the "Unhandled exception in event loop: ... RuntimeError: Event loop is closed ... Press ENTER to continue..." error that occurs ~1 minute after an agent turn completes (during CLI idle time).
Root cause
The OpenAI SDK's
AsyncHttpxClientWrapper.__del__schedulesaclose()viaasyncio.get_running_loop().create_task(). When anAsyncOpenAIclient is garbage-collected while prompt_toolkit's event loop is running (the common CLI idle state), theaclose()task runs on prompt_toolkit's loop but the underlying TCP transport is bound to a different (dead) worker loop. The transport'sself._loop.call_soon()then raisesRuntimeError('Event loop is closed').The existing
_force_close_async_httpxfix only runs on cache access or CLI exit — there's a window between the agent thread finishing and the next cache access where GC can hit an uncleaned client.Three-layer fix
neuter_async_httpx_del()— Monkey-patchesAsyncHttpxClientWrapper.__del__to a no-op at CLI startup. Safe because cached clients are explicitly cleaned via_force_close_async_httpx, and uncached clients' TCP connections are cleaned by the OS on exit.Custom asyncio exception handler — Installed on prompt_toolkit's event loop to silently suppress
RuntimeError('Event loop is closed'). Defense-in-depth for SDK upgrades that might change the class name.cleanup_stale_async_clients()— Called after each agent turn to proactively evict cache entries whose event loop is closed.Test plan
tests/test_async_httpx_del_neuter.pytest_model_tools_async_bridge.py— 10/10 ✔test_crossloop_client_cache.py— 5/5 ✔test_cli_init.py— 20/20 ✔