[router] Fix flaky router e2e tests (#13306)

This commit is contained in:
Xinyue Zhang
2025-11-15 02:00:25 -08:00
committed by GitHub
parent b051d76dab
commit 4a10e37ba7
2 changed files with 43 additions and 22 deletions

View File

@@ -112,17 +112,28 @@ def test_circuit_breaker_disable_flag(router_manager, mock_workers):
"disable_retries": True,
},
)
r = requests.post(
f"{rh.url}/v1/completions",
json={
"model": "test-model",
"prompt": "x",
"max_tokens": 1,
"stream": False,
},
timeout=3,
)
assert r.status_code == 500
saw_500 = False
for _ in range(8):
r = requests.post(
f"{rh.url}/v1/completions",
json={
"model": "test-model",
"prompt": "x",
"max_tokens": 1,
"stream": False,
},
timeout=3,
)
if r.status_code == 500:
# Worker starts, continue to check
saw_500 = True
break
assert (
r.status_code == 503
), "Should only see 503 when waiting for worker to start"
assert saw_500
@pytest.mark.integration

View File

@@ -47,15 +47,25 @@ def test_disable_retries_surfaces_failure(router_manager, mock_workers):
},
)
r = requests.post(
f"{rh.url}/v1/completions",
json={
"model": "test-model",
"prompt": "x",
"max_tokens": 1,
"stream": False,
},
timeout=5,
)
assert r.status_code == 500
saw_500 = False
for _ in range(8):
r = requests.post(
f"{rh.url}/v1/completions",
json={
"model": "test-model",
"prompt": "x",
"max_tokens": 1,
"stream": False,
},
timeout=5,
)
if r.status_code == 500:
# Worker starts, continue to check
saw_500 = True
break
assert (
r.status_code == 503
), "Should only see 503 when waiting for worker to start"
assert saw_500
# mock_workers fixture handles cleanup