phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-25 18:54:30 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

[Feat] Add Responses API - Routing Affinity logic for sessions (#10193)

Browse source 
* test for test_responses_api_routing_with_previous_response_id

* test_responses_api_routing_with_previous_response_id

* add ResponsesApiDeploymentCheck

* ResponsesApiDeploymentCheck

* ResponsesApiDeploymentCheck

* fix ResponsesApiDeploymentCheck

* test_responses_api_routing_with_previous_response_id

* ResponsesApiDeploymentCheck

* test_responses_api_deployment_check.py

* docs routing affinity

* simplify ResponsesApiDeploymentCheck

* test response id

* fix code quality check
This commit is contained in:
Ishaan Jaff 2025-04-21 20:00:27 -07:00 • committed by GitHub
parent 4eac0f64f3
commit 0c2f705417
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
9 changed files with 862 additions and 29 deletions
Download patch file Download diff file Expand all files Collapse all files

37
litellm/router.py
View file

@ -98,6 +98,9 @@ from litellm.router_utils.handle_error import (
from litellm.router_utils.pre_call_checks.prompt_caching_deployment_check import (
PromptCachingDeploymentCheck,
)
from litellm.router_utils.pre_call_checks.responses_api_deployment_check import (
ResponsesApiDeploymentCheck,
)
from litellm.router_utils.router_callbacks.track_deployment_metrics import (
increment_deployment_failures_for_current_minute,
increment_deployment_successes_for_current_minute,
@ -339,9 +342,9 @@ class Router:
) # names of models under litellm_params. ex. azure/chatgpt-v-2
self.deployment_latency_map = {}
### CACHING ###
cache_type: Literal[
"local", "redis", "redis-semantic", "s3", "disk"
] = "local" # default to an in-memory cache
cache_type: Literal["local", "redis", "redis-semantic", "s3", "disk"] = (
"local" # default to an in-memory cache
)
redis_cache = None
cache_config: Dict[str, Any] = {}
@ -562,9 +565,9 @@ class Router:
)
)
self.model_group_retry_policy: Optional[
Dict[str, RetryPolicy]
] = model_group_retry_policy
self.model_group_retry_policy: Optional[Dict[str, RetryPolicy]] = (
model_group_retry_policy
)
self.allowed_fails_policy: Optional[AllowedFailsPolicy] = None
if allowed_fails_policy is not None:
@ -765,6 +768,8 @@ class Router:
provider_budget_config=self.provider_budget_config,
model_list=self.model_list,
)
elif pre_call_check == "responses_api_deployment_check":
_callback = ResponsesApiDeploymentCheck()
if _callback is not None:
litellm.logging_callback_manager.add_litellm_callback(_callback)
@ -3247,11 +3252,11 @@ class Router:
if isinstance(e, litellm.ContextWindowExceededError):
if context_window_fallbacks is not None:
fallback_model_group: Optional[
List[str]
] = self._get_fallback_model_group_from_fallbacks(
fallbacks=context_window_fallbacks,
model_group=model_group,
fallback_model_group: Optional[List[str]] = (
self._get_fallback_model_group_from_fallbacks(
fallbacks=context_window_fallbacks,
model_group=model_group,
)
)
if fallback_model_group is None:
raise original_exception
@ -3283,11 +3288,11 @@ class Router:
e.message += "\n{}".format(error_message)
elif isinstance(e, litellm.ContentPolicyViolationError):
if content_policy_fallbacks is not None:
fallback_model_group: Optional[
List[str]
] = self._get_fallback_model_group_from_fallbacks(
fallbacks=content_policy_fallbacks,
model_group=model_group,
fallback_model_group: Optional[List[str]] = (
self._get_fallback_model_group_from_fallbacks(
fallbacks=content_policy_fallbacks,
model_group=model_group,
)
)
if fallback_model_group is None:
raise original_exception