Remove unused imports (F401) and duplicate/shadowed import
redefinitions (F811) across the codebase using ruff's safe
autofixes. No behavioral changes -- imports only.
- ~1400 safe autofixes applied across 644 files (net -1072 lines)
- __init__.py re-exports preserved (excluded from F401 removal so
public re-export surfaces stay intact)
- Re-exports that are imported or monkeypatched by tests but look
unused in their defining module are kept with explicit # noqa:
F401 (gateway/run.py load_dotenv; run_agent re-exports from
agent.message_sanitization, agent.context_compressor,
agent.retry_utils, agent.prompt_builder, agent.process_bootstrap,
agent.codex_responses_adapter)
- Unsafe F841 (unused-variable) fixes deliberately skipped -- those
can change behavior when the RHS has side effects
- ruff lints remain disabled in pyproject.toml (only PLW1514 is
selected); this is a one-time cleanup, not a config change
Verification:
- python -m compileall: clean
- pytest --collect-only: all 27161 tests collect (zero import errors)
- core entry points import clean (run_agent, model_tools, cli,
toolsets, hermes_state, batch_runner, gateway)
- static scan: every name any test imports directly from an edited
module still resolves
_run_async() bridges sync tool handlers to async code. When the handler
is invoked from inside a running event loop (gateway / nested async),
it spawns a worker thread and blocks on future.result(timeout=300).
Before this change, a coroutine that ran past 300s leaked its worker
thread:
- future.cancel() is a no-op on a running ThreadPoolExecutor future
(cancel only works on not-yet-started work).
- pool.shutdown(wait=False, cancel_futures=True) let the caller
proceed but the worker kept running the coroutine until it
returned on its own.
Every tool timeout leaked one thread. In long-lived gateway / RL
sessions this is cumulative.
The fix replaces bare asyncio.run() with a worker wrapper that
creates its own event loop. On timeout, _run_async schedules
task.cancel() on that loop via call_soon_threadsafe, then shuts the
pool down with wait=False so the caller returns immediately. The
coroutine observes CancelledError at its next await and the worker
thread exits cleanly.
Also switches logger.error() to logger.exception() in the top-level
handle_function_call() except block so tool failures produce full
stack traces in errors.log instead of just the message.
Related: #17420 (contributor flagged the leak; the original fix used
pool.shutdown(wait=True) which would have converted the leak into a
hang — caller blocks forever on the same stuck coroutine). Credit
for identifying the leak goes to the contributor.
Co-authored-by: 0z! <162235745+0z1-ghb@users.noreply.github.com>
Replace asyncio.run() with thread-local persistent event loops for
worker threads (e.g., delegate_task's ThreadPoolExecutor). asyncio.run()
creates and closes a fresh loop on every call, leaving cached
httpx/AsyncOpenAI clients bound to a dead loop — causing 'Event loop is
closed' errors during GC when parallel subagents clean up connections.
The fix mirrors the main thread's _get_tool_loop() pattern but uses
threading.local() so each worker thread gets its own long-lived loop,
avoiding both cross-thread contention and the create-destroy lifecycle.
Added 4 regression tests covering worker loop persistence, reuse,
per-thread isolation, and separation from the main thread's loop.
Cherry-picked from PR #2146 by @crazywriter1. Fixes#2104.
asyncio.run() creates and closes a fresh event loop each call. Cached
httpx/AsyncOpenAI clients bound to the dead loop crash on GC with
'Event loop is closed'. This hit vision_analyze on first use in CLI.
Two-layer fix:
- model_tools._run_async(): replace asyncio.run() with persistent
loop via _get_tool_loop() + run_until_complete()
- auxiliary_client._get_cached_client(): track which loop created
each async client, discard stale entries if loop is closed
6 regression tests covering loop lifecycle, reuse, and full vision
dispatch chain.
Co-authored-by: Test <test@test.com>
