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 Support for DELETE /v1/responses/{response_id} on OpenAI, Azure OpenAI (#10205)

Browse source 
* add transform_delete_response_api_request to base responses config

* add transform_delete_response_api_request

* add delete_response_api_handler

* fixes for deleting responses, response API

* add adelete_responses

* add async test_basic_openai_responses_delete_endpoint

* test_basic_openai_responses_delete_endpoint

* working delete for streaming on responses API

* fixes azure transformation

* TestAnthropicResponsesAPITest

* fix code check

* fix linting

* fixes for get_complete_url

* test_basic_openai_responses_streaming_delete_endpoint

* streaming fixes
This commit is contained in:
Ishaan Jaff 2025-04-22 18:27:03 -07:00 • committed by GitHub
parent 2bb51866b1
commit 868cdd0226
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
15 changed files with 729 additions and 83 deletions
Download patch file Download diff file Expand all files Collapse all files

66
litellm/responses/utils.py
View file

@ -1,5 +1,5 @@
import base64
from typing import Any, Dict, Optional, Tuple, Union, cast, get_type_hints
from typing import Any, Dict, Optional, Union, cast, get_type_hints
import litellm
from litellm._logging import verbose_logger
@ -9,6 +9,7 @@ from litellm.types.llms.openai import (
ResponsesAPIOptionalRequestParams,
ResponsesAPIResponse,
)
from litellm.types.responses.main import DecodedResponseId
from litellm.types.utils import SpecialEnums, Usage
@ -83,30 +84,36 @@ class ResponsesAPIRequestUtils:
@staticmethod
def _update_responses_api_response_id_with_model_id(
responses_api_response: ResponsesAPIResponse,
kwargs: Dict[str, Any],
custom_llm_provider: Optional[str],
litellm_metadata: Optional[Dict[str, Any]] = None,
) -> ResponsesAPIResponse:
"""Update the responses_api_response_id with the model_id"""
litellm_metadata: Dict[str, Any] = kwargs.get("litellm_metadata", {}) or {}
"""
Update the responses_api_response_id with model_id and custom_llm_provider
This builds a composite ID containing the custom LLM provider, model ID, and original response ID
"""
litellm_metadata = litellm_metadata or {}
model_info: Dict[str, Any] = litellm_metadata.get("model_info", {}) or {}
model_id = model_info.get("id")
updated_id = ResponsesAPIRequestUtils._build_responses_api_response_id(
model_id=model_id,
custom_llm_provider=custom_llm_provider,
response_id=responses_api_response.id,
)
responses_api_response.id = updated_id
return responses_api_response
@staticmethod
def _build_responses_api_response_id(
custom_llm_provider: Optional[str],
model_id: Optional[str],
response_id: str,
) -> str:
"""Build the responses_api_response_id"""
if model_id is None:
return response_id
assembled_id: str = str(
SpecialEnums.LITELLM_MANAGED_RESPONSE_COMPLETE_STR.value
).format(model_id, response_id)
).format(custom_llm_provider, model_id, response_id)
base64_encoded_id: str = base64.b64encode(assembled_id.encode("utf-8")).decode(
"utf-8"
)
@ -115,12 +122,12 @@ class ResponsesAPIRequestUtils:
@staticmethod
def _decode_responses_api_response_id(
response_id: str,
) -> Tuple[Optional[str], str]:
) -> DecodedResponseId:
"""
Decode the responses_api_response_id
Returns:
Tuple of model_id, response_id (from upstream provider)
DecodedResponseId: Structured tuple with custom_llm_provider, model_id, and response_id
"""
try:
# Remove prefix and decode
@ -129,16 +136,45 @@ class ResponsesAPIRequestUtils:
# Parse components using known prefixes
if ";" not in decoded_id:
return None, response_id
return DecodedResponseId(
custom_llm_provider=None,
model_id=None,
response_id=response_id,
)
model_part, response_part = decoded_id.split(";", 1)
model_id = model_part.replace("litellm:model_id:", "")
decoded_response_id = response_part.replace("response_id:", "")
parts = decoded_id.split(";")
return model_id, decoded_response_id
# Format: litellm:custom_llm_provider:{};model_id:{};response_id:{}
custom_llm_provider = None
model_id = None
if (
len(parts) >= 3
): # Full format with custom_llm_provider, model_id, and response_id
custom_llm_provider_part = parts[0]
model_id_part = parts[1]
response_part = parts[2]
custom_llm_provider = custom_llm_provider_part.replace(
"litellm:custom_llm_provider:", ""
)
model_id = model_id_part.replace("model_id:", "")
decoded_response_id = response_part.replace("response_id:", "")
else:
decoded_response_id = response_id
return DecodedResponseId(
custom_llm_provider=custom_llm_provider,
model_id=model_id,
response_id=decoded_response_id,
)
except Exception as e:
verbose_logger.debug(f"Error decoding response_id '{response_id}': {e}")
return None, response_id
return DecodedResponseId(
custom_llm_provider=None,
model_id=None,
response_id=response_id,
)
class ResponseAPILoggingUtils: