/workspace/source/test/e2e/tests/test_crd_watch_resilience.py:224: requires a disposable cluster: deletes the cluster-scoped KServe CRD; set E2E_RUN_CRD_WATCH_RESILIENCE=true to opt in/workspace/source/test/e2e/tests/test_crd_watch_resilience.py:262: requires a disposable cluster: deletes the cluster-scoped KServe CRD; set E2E_RUN_CRD_WATCH_RESILIENCE=true to opt in/workspace/source/test/e2e/tests/test_crd_watch_resilience.py:312: requires a disposable cluster: deletes the cluster-scoped KServe CRD; set E2E_RUN_CRD_WATCH_RESILIENCE=true to opt inself = <test_models_endpoint.TestModelsEndpoint object at 0x7f60e3db1bd0> @pytest.mark.serial def test_central_models_endpoint_exempt_from_rate_limiting(self): """Central model discovery remains available after inference quota exhaustion.""" model_ref = UNCONFIGURED_MODEL_REF model_path = UNCONFIGURED_MODEL_PATH suffix = uuid.uuid4().hex[:6] auth_policy_name = f"e2e-central-models-exempt-auth-{suffix}" subscription_name = f"e2e-central-models-exempt-sub-{suffix}" sa_name = f"e2e-central-models-exempt-sa-{suffix}" token_limit = 3 max_requests = 5 try: _create_test_auth_policy( name=auth_policy_name, model_refs=[model_ref], groups=["system:authenticated"], ) _wait_for_maas_auth_policy_phase(auth_policy_name, timeout=90) _wait_for_gateway_auth_enforced() _create_test_subscription( name=subscription_name, model_refs=[model_ref], groups=["system:authenticated"], token_limit=token_limit, window="1m", ) _wait_for_maas_subscription_phase(subscription_name, timeout=90) _wait_for_token_rate_limit_policy( model_ref, model_namespace=MODEL_NAMESPACE, timeout=180, subscription_name=subscription_name, ) _wait_for_subscription_trlp_status( subscription_name, model=model_ref, expected_ready=True, timeout=180, ) _wait_for_model_ready(model_ref, namespace=MODEL_NAMESPACE, timeout=90) sa_token = _create_sa_token(sa_name, namespace=_ns()) api_key = _create_api_key( sa_token, name=f"e2e-central-exempt-{suffix}", subscription=subscription_name, ) # Establish that discovery works before consuming the quota. This # keeps a setup/readiness failure distinct from an exemption failure. _, baseline_models = _wait_for_central_models_in_subscription( api_key, subscription_name, ) log.info("Central discovery baseline: %s", baseline_models) success_count = 0 rate_limited = False for request_num in range(1, max_requests + 1): response = _inference(api_key, path=model_path, max_tokens=1) log.info("Inference request %d: %d", request_num, response.status_code) if response.status_code == 200: success_count += 1 elif response.status_code == 429: rate_limited = True break else: raise AssertionError( f"Unexpected inference status {response.status_code}: " f"{response.text[:500]}" ) > assert rate_limited, ( f"Expected quota exhaustion within {max_requests} requests at " f"{token_limit} tokens/minute; {success_count} requests succeeded" ) E AssertionError: Expected quota exhaustion within 5 requests at 3 tokens/minute; 5 requests succeeded E assert False test/e2e/tests/test_models_endpoint.py:2316: AssertionError/workspace/source/test/e2e/tests/test_subscription.py:951: no Kuadrant WasmPlugin for gateway maas-default-gateway/workspace/source/test/e2e/tests/test_subscription.py:1746: gateway-only mode: per-model AuthPolicy is not created/workspace/source/test/e2e/tests/test_tenant.py:401: default payload-processing is praxis-extproc; MaasTenantConfig.spec.payloadProcessing.resources is MaaS IPP-only/workspace/source/test/e2e/tests/test_tenant_external_model_compat.py:377: legacy IPP coexistence E2E requires the MaaS IPP image pin containing the legacy-controller exclusion guard; set TENANT_EXTERNAL_MODEL_LEGACY_IPP_E2E=true to enable/workspace/source/test/e2e/tests/test_tenant_external_model_compat.py:386: legacy IPP coexistence E2E requires the MaaS IPP image pin containing the legacy-controller exclusion guard; set TENANT_EXTERNAL_MODEL_LEGACY_IPP_E2E=true to enable/workspace/source/test/e2e/tests/test_tenant_external_model_compat.py:401: legacy IPP coexistence E2E requires the MaaS IPP image pin containing the legacy-controller exclusion guard; set TENANT_EXTERNAL_MODEL_LEGACY_IPP_E2E=true to enable/workspace/source/test/e2e/tests/test_tenant_external_model_compat.py:411: legacy IPP coexistence E2E requires the MaaS IPP image pin containing the legacy-controller exclusion guard; set TENANT_EXTERNAL_MODEL_LEGACY_IPP_E2E=true to enable/workspace/source/test/e2e/tests/test_tenant_external_model_compat.py:425: legacy IPP coexistence E2E requires the MaaS IPP image pin containing the legacy-controller exclusion guard; set TENANT_EXTERNAL_MODEL_LEGACY_IPP_E2E=true to enable/workspace/source/test/e2e/tests/test_tenant_namespace_discovery.py:357: Dormant-mode test mutates controller flags; set ENABLE_TENANT_DISCOVERY_DORMANT_E2E=true