mirror of
https://github.com/BerriAI/litellm.git
synced 2026-08-28 05:25:59 +00:00
0580465384
* feat(router): add per-deployment allowed_fails_policy and cooldown_time override support
Three bugs fixed in the router cooldown system: (1) deployment-level allowed_fails and
allowed_fails_policy in model_info now take precedence over router-level settings in
_should_cooldown_deployment; (2) failed fallback deployments now get evaluated for
cooldown via _trigger_cooldown_for_failed_deployment, bypassing the Logging dedup gate;
(3) DualCache promotes Redis cooldown entries using default 600s TTL instead of true
remaining cooldown time -- _corrected_active_cooldown now evicts expired entries and
corrects stale in-memory TTLs on backfill. Adds ServiceUnavailableError, BadGatewayError,
and NotFoundError fields to AllowedFailsPolicy and cooldown_time to LiteLLMParamsTypedDict.
* fix(router): gate fallback cooldown trigger on has_logged_async_failure; use only litellm_metadata for deployment ID
* fix(router): use X | Y union syntax to fix UP007 strict lint gate
* test(router_utils): add coverage for _trigger_cooldown_for_failed_deployment and has_logged_async_failure gate
* test(router_utils): cover deployment cooldown override and exception swallow paths
* fix(router): add InternalServerError/ServiceUnavailableError/BadGatewayError/NotFoundError to router-level get_allowed_fails_from_policy
* fix(router): format router.py and add router-level policy tests
* test(router): add CI-visible coverage for per-deployment cooldown policy
Tests for `_get_deployment_cooldown_policy`, `_resolve_allowed_fails_from_policy`,
and `_should_cooldown_based_on_deployment_policy` (cooldown_handlers.py), the
`_corrected_active_cooldown` branches in CooldownCache, and the four new
exception-type branches in `Router.get_allowed_fails_from_policy` (router.py) --
all in `tests/test_litellm/` which the enterprise-routing CI job runs.
* fix(router): use is not None guard for cooldown_time_override in should_cooldown_based_on_allowed_fails_policy
A cooldown_time_override of 0 was previously treated as falsy and silently
fell through to the router-level cooldown_time value. Switched to an explicit
is not None check so that zero is honored as a valid override.
Added a regression test covering the zero case.
* fix(router): honor has_logged_async_failure and metadata for fallback cooldown; support both model_info and litellm_params locations
Manual verification against a live proxy surfaced that the fallback-cooldown-gap
trigger never actually fired: the has_logged_async_failure check read a plain
attribute that Logging never sets (the real flag lives in model_call_details),
and the deployment_id lookup only trusted litellm_metadata, which regular chat
completions never populate (only batch/thread/file endpoints do). Router
overwrites model_info on whichever key is present before every attempt, so
metadata is equally authoritative there, not caller-controlled as previously
assumed. Also let allowed_fails/allowed_fails_policy/cooldown_time be set under
either model_info or litellm_params, each preferring its own canonical location.
* fix(router): fix ContentPolicyViolationError policy shadowing and partial-policy zero-threshold
Two bugs from Greptile review on PR #34416:
- ContentPolicyViolationError subclasses BadRequestError, so listing
BadRequestError first in _EXCEPTION_POLICY_FIELDS made the isinstance
check always match BadRequestError for content-policy errors, using the
wrong allowed_fails threshold. Reordered so the subclass is checked first.
- A deployment with a partial allowed_fails_policy and no deployment-wide
allowed_fails forced allowed_fails_override=0 for any exception type its
policy didn't cover, cooling the deployment down on the first unrelated
failure. Now defers to router-level behavior for uncovered exception
types instead of forcing an immediate cooldown.
* fix(router): only trust a metadata/litellm_metadata bucket the router itself wrote deployment info into
veria-ai flagged that preferring litellm_metadata whenever present could pick up a
caller-supplied litellm_metadata.model_info.id (preserved via allow_client_pricing_override)
instead of the metadata bucket the router actually populated for a regular completion's
fallback attempt, naming an arbitrary "victim" deployment for cooldown.
Router._update_kwargs_with_deployment() always writes model_info and
deployment_model_name into the same bucket together. Only trust a bucket that
carries deployment_model_name alongside model_info, since that marker is only
ever set by the router itself, not by request-body metadata.
* test(router): add regression coverage for ContentPolicyViolationError policy shadowing
The subclass-ordering fix in commit
|
||
|---|---|---|
| .. | ||
| example_config_yaml | ||
| test_configs | ||
| test_model_response_typing | ||
| azure_fine_tune.jsonl | ||
| batch_job_results_furniture.jsonl | ||
| conftest copy.py | ||
| conftest.py | ||
| data_map.txt | ||
| eagle.wav | ||
| gettysburg.wav | ||
| large_text.py | ||
| messages_with_counts.py | ||
| model_cost.json | ||
| openai_batch_completions.jsonl | ||
| openai_batch_completions_router.jsonl | ||
| speech_vertex.mp3 | ||
| test_aproxy_startup.py | ||
| test_audit_logs_proxy.py | ||
| test_auth_checks.py | ||
| test_banned_keyword_list.py | ||
| test_blog_posts_endpoint.py | ||
| test_check_batch_cost.py | ||
| test_check_responses_cost.py | ||
| test_custom_callback_input.py | ||
| test_custom_logger_s3_gcs.py | ||
| test_custom_tokenizer_bug.py | ||
| test_db_schema_changes.py | ||
| test_default_end_user_budget_simple.py | ||
| test_deployed_proxy_keygen.py | ||
| test_deprecated_key_grace_period.py | ||
| test_e2e_pod_lock_manager.py | ||
| test_gemini_agents_endpoints.py | ||
| test_get_favicon.py | ||
| test_get_image.py | ||
| test_google_endpoint_routing.py | ||
| test_google_gemini_proxy_request.py | ||
| test_jwt.py | ||
| test_jwt_key_mapping.py | ||
| test_key_generate_dynamodb.py | ||
| test_key_generate_prisma.py | ||
| test_models_fallback_endpoint.py | ||
| test_multipart_bypass_repro.py | ||
| test_prisma_client_backoff_retry.py | ||
| test_prompt_test_endpoint.py | ||
| test_proxy_config_unit_test.py | ||
| test_proxy_custom_auth.py | ||
| test_proxy_custom_logger.py | ||
| test_proxy_encrypt_decrypt.py | ||
| test_proxy_exception_mapping.py | ||
| test_proxy_gunicorn.py | ||
| test_proxy_pass_user_config.py | ||
| test_proxy_reject_logging.py | ||
| test_proxy_routes.py | ||
| test_proxy_server.py | ||
| test_proxy_server_caching.py | ||
| test_proxy_server_keys.py | ||
| test_proxy_server_langfuse.py | ||
| test_proxy_server_spend.py | ||
| test_proxy_setting_guardrails.py | ||
| test_proxy_token_counter.py | ||
| test_proxy_utils.py | ||
| test_realtime_cache.py | ||
| test_reducto_ocr_route.py | ||
| test_request_size_limit_middleware.py | ||
| test_response_polling_handler.py | ||
| test_response_polling_pre_call_checks.py | ||
| test_search_api_logging.py | ||
| test_server_root_path.py | ||
| test_skills_db.py | ||
| test_ui_path_detection.py | ||
| test_unit_test_max_model_budget_limiter.py | ||
| test_unit_test_proxy_hooks.py | ||
| test_update_daily_tag_spend.py | ||
| test_update_spend.py | ||
| test_user_api_key_auth.py | ||
| test_zero_cost_model_budget_bypass.py | ||
| vertex_key.json | ||