scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-18 04:44:37 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 123

test(integration): send post-kill requests on a fresh connection in two worker-kill tests (#47080)

Browse source 
kill() returns once the killed worker's main thread is a zombie, but its other threads can
still be exiting and holding its sockets open. A keep-alive connection pooled to that worker
still looks healthy, so the next request goes out on it and the closing socket answers with
a reset. The old reap wait used to hide this. A new connection can only be accepted by a
live worker, so the surviving-worker assertions now run on a fresh client
This commit is contained in:
yuneng-jiang 2026-10-16 23:27:51 -07:00 • committed by GitHub
parent 6b45a196c4
commit c32eea634a
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 19 additions and 13 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

22
tests/integration/compatibility/test_missing_body_param_status.py
View file

@ -1695,15 +1695,19 @@ def test_upstream_pause_and_worker_kill_preserve_required_body_status(
record_property("chaos_spend_row_counts", str(tuple(len(rows) for rows in spend_rows)))
with owned.replacing_worker(min(workers)) as kill:
kill()
post_kill: Final = tuple(
_post(candidate, path, body) for path, body, _expected, _identity in missing_calls[:5]
)
assert all(
response.status_code == 400 and response.json() == expected
for response, (_path, _body, expected, _identity) in zip(post_kill, missing_calls[:5])
), [response.text for response in post_kill]
recovered: Final = _post(candidate, "/v1/chat/completions", _chat_body(chat_model, "recovered", True))
assert recovered.status_code == 200, recovered.text
with httpx.Client(base_url=candidate.client.base_url, timeout=15, trust_env=False) as fresh:
survivor: Final = Gateway(fresh, candidate.key, candidate.upstream_url)
post_kill: Final = tuple(
_post(survivor, path, body) for path, body, _expected, _identity in missing_calls[:5]
)
assert all(
response.status_code == 400 and response.json() == expected
for response, (_path, _body, expected, _identity) in zip(post_kill, missing_calls[:5])
), [response.text for response in post_kill]
recovered: Final = _post(
survivor, "/v1/chat/completions", _chat_body(chat_model, "recovered", True)
)
assert recovered.status_code == 200, recovered.text
def test_eval_create_and_run_forward_client_metadata(gateway: Gateway) -> None:

10
tests/integration/providers/test_bedrock_mantle_context_overflow_fallbacks_wire.py
View file

@ -519,10 +519,12 @@ def test_killing_one_worker_leaves_the_sibling_serving_the_fallback(fb_rig: Rig)
workers: Final = eventually(fb_rig.owned.worker_pids, lambda pids: len(pids) >= 2, seconds=30)
with fb_rig.owned.replacing_worker(min(workers)) as kill:
kill()
responses: Final = tuple(
fb_rig.gateway.request("POST", "/v1/chat/completions", _chat(fb_rig.models["fb"], _prompt("after kill")))
for _ in range(3)
)
with httpx.Client(base_url=fb_rig.gateway.client.base_url, timeout=15, trust_env=False) as fresh:
survivor: Final = Gateway(fresh, fb_rig.gateway.key, fb_rig.gateway.upstream_url)
responses: Final = tuple(
survivor.request("POST", "/v1/chat/completions", _chat(fb_rig.models["fb"], _prompt("after kill")))
for _ in range(3)
)
for response in responses:
assert response.status_code == 200, response.text
assert _FALLBACK_TEXT in response.text, response.text