mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-05-18 04:41:56 +00:00
fix(auxiliary): evict async wrappers on poisoned client (follow-up to #23482)
#23482 fixed cache poisoning in the sync path: when a Codex auxiliary timeout closes the underlying OpenAI client, _evict_cached_client_instance walks CodexAuxiliaryClient wrappers via their _real_client attribute and drops the cache entry so the next aux call rebuilds. The cache key includes async_mode (see _client_cache_key), so the sync and async clients for the same provider live in two distinct entries pointing at the same underlying transport. The fix walked the sync wrapper's _real_client correctly but the async wrappers (AsyncCodexAuxiliaryClient, AsyncAnthropicAuxiliaryClient, AsyncGeminiNativeClient) never exposed _real_client at all, so the async entry survived eviction and kept handing out the poisoned client. Effect on async aux callers: one timeout now poisons every subsequent async aux call (compression, vision, session_search, title_generation) with 'Connection error' until gateway restart -- even while the sync route recovered as designed in #23482. Mirror the sync wrapper's _real_client onto each async wrapper so the existing eviction helper finds them. Three changes, one per wrapper: - AsyncCodexAuxiliaryClient: self._real_client = sync_wrapper._real_client (the underlying OpenAI client) - AsyncAnthropicAuxiliaryClient: same shape - AsyncGeminiNativeClient: self._real_client = sync_client (Gemini's native facade is itself the leaf; no OpenAI client beneath it) Update _evict_cached_client_instance docstring to reflect that it now covers both sync and async wrappers via the same attribute walk. Test: TestAuxiliaryClientPoisonedCacheEviction.test_evict_cached_client_instance_walks_async_wrapper seeds both sync and async cache entries pointing at the same leaf and asserts both are dropped on a single eviction call. Verified the test fails without the wrapper changes ("async cache entry survived eviction -- wrapper is missing _real_client") and passes with them. Refs #23482, #23432
This commit is contained in:
parent
1d00716754
commit
111b859e49
3 changed files with 60 additions and 3 deletions
|
|
@ -2183,6 +2183,42 @@ class TestAuxiliaryClientPoisonedCacheEviction:
|
|||
assert _evict_cached_client_instance(None) is False
|
||||
assert _evict_cached_client_instance(MagicMock()) is False
|
||||
|
||||
def test_evict_cached_client_instance_walks_async_wrapper(self):
|
||||
"""async_mode is part of the cache key so sync and async share the same
|
||||
underlying OpenAI client across two distinct cache entries. A single
|
||||
timeout that closes the leaf must evict BOTH — otherwise the async
|
||||
entry survives, keeps reusing the dead transport, and every async
|
||||
aux call (compression, vision, session_search) fails fast with
|
||||
'Connection error' until gateway restart even while the sync route
|
||||
recovers.
|
||||
|
||||
Regression for the async-side gap left by #23482, which fixed the
|
||||
sync wrapper's _real_client walk but missed the async wrappers.
|
||||
"""
|
||||
from agent.auxiliary_client import (
|
||||
_client_cache, _client_cache_lock, _evict_cached_client_instance,
|
||||
CodexAuxiliaryClient, AsyncCodexAuxiliaryClient,
|
||||
)
|
||||
|
||||
real = SimpleNamespace(api_key="k", base_url="https://chatgpt.com/backend-api/codex",
|
||||
responses=SimpleNamespace(stream=lambda **k: None),
|
||||
close=lambda: None)
|
||||
sync_wrapper = CodexAuxiliaryClient(real, "gpt-5.5")
|
||||
async_wrapper = AsyncCodexAuxiliaryClient(sync_wrapper)
|
||||
with _client_cache_lock:
|
||||
_client_cache.clear()
|
||||
_client_cache[("openai-codex", False, None, None, None)] = (sync_wrapper, "gpt-5.5", None)
|
||||
_client_cache[("openai-codex", True, None, None, None)] = (async_wrapper, "gpt-5.5", None)
|
||||
try:
|
||||
assert _evict_cached_client_instance(real) is True
|
||||
assert ("openai-codex", False, None, None, None) not in _client_cache
|
||||
assert ("openai-codex", True, None, None, None) not in _client_cache, (
|
||||
"async cache entry survived eviction — wrapper is missing _real_client"
|
||||
)
|
||||
finally:
|
||||
with _client_cache_lock:
|
||||
_client_cache.clear()
|
||||
|
||||
def test_codex_timeout_evicts_cached_wrapper(self):
|
||||
"""The timeout closer evicts the cache entry that wraps the closed client."""
|
||||
from agent.auxiliary_client import (
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue