scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-09 22:31:41 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 133

fix(lint): migrate remaining StreamingChoices callers to ModelResponseStream

Browse source 
After narrowing ModelResponse.choices to List[Choices], several files
still assigned StreamingChoices into ModelResponse. Migrate streaming
call sites to ModelResponseStream and remove dead streaming branches
in qwen2/qwen3 transform_response methods.
This commit is contained in:
Chesars 2026-02-22 09:03:12 -03:00
parent b370fcd8de
commit 5eeee88ff8
6 changed files with 25 additions and 37 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

14
litellm/llms/bedrock/chat/agentcore/transformation.py
View file

@ -26,7 +26,7 @@ from litellm.types.llms.bedrock_agentcore import (
AgentCoreUsage,
)
from litellm.types.llms.openai import AllMessageValues
from litellm.types.utils import Choices, Delta, Message, ModelResponse, StreamingChoices, Usage
from litellm.types.utils import Choices, Delta, Message, ModelResponse, ModelResponseStream, StreamingChoices, Usage
if TYPE_CHECKING:
from litellm.litellm_core_utils.litellm_logging import Logging as _LiteLLMLoggingObj
@ -481,7 +481,7 @@ class AmazonAgentCoreConfig(BaseConfig, BaseAWSLLM):
text = delta.get("text", "")
if text:
chunk = ModelResponse(
chunk = ModelResponseStream(
id=f"chatcmpl-{uuid.uuid4()}",
created=0,
model=model,
@ -499,7 +499,7 @@ class AmazonAgentCoreConfig(BaseConfig, BaseAWSLLM):
# Process metadata/usage
metadata = event_payload.get("metadata")
if metadata and "usage" in metadata:
chunk = ModelResponse(
chunk = ModelResponseStream(
id=f"chatcmpl-{uuid.uuid4()}",
created=0,
model=model,
@ -522,7 +522,7 @@ class AmazonAgentCoreConfig(BaseConfig, BaseAWSLLM):
# Process final message
if "message" in data_obj and isinstance(data_obj["message"], dict):
chunk = ModelResponse(
chunk = ModelResponseStream(
id=f"chatcmpl-{uuid.uuid4()}",
created=0,
model=model,
@ -636,7 +636,7 @@ class AmazonAgentCoreConfig(BaseConfig, BaseAWSLLM):
text = delta.get("text", "")
if text:
chunk = ModelResponse(
chunk = ModelResponseStream(
id=f"chatcmpl-{uuid.uuid4()}",
created=0,
model=model,
@ -654,7 +654,7 @@ class AmazonAgentCoreConfig(BaseConfig, BaseAWSLLM):
# Process metadata/usage
metadata = event_payload.get("metadata")
if metadata and "usage" in metadata:
chunk = ModelResponse(
chunk = ModelResponseStream(
id=f"chatcmpl-{uuid.uuid4()}",
created=0,
model=model,
@ -677,7 +677,7 @@ class AmazonAgentCoreConfig(BaseConfig, BaseAWSLLM):
# Process final message
if "message" in data_obj and isinstance(data_obj["message"], dict):
chunk = ModelResponse(
chunk = ModelResponseStream(
id=f"chatcmpl-{uuid.uuid4()}",
created=0,
model=model,

9
litellm/llms/bedrock/chat/invoke_transformations/amazon_qwen2_transformation.py
View file

@ -68,13 +68,8 @@ class AmazonQwen2Config(AmazonQwen3Config):
# Set the content in the existing model_response structure
if hasattr(model_response, 'choices') and len(model_response.choices) > 0:
choice = model_response.choices[0]
if hasattr(choice, 'message'):
choice.message.content = generated_text
choice.finish_reason = "stop"
else:
# Handle streaming choices
choice.delta.content = generated_text
choice.finish_reason = "stop"
choice.message.content = generated_text
choice.finish_reason = "stop"
# Set usage information if available in response
if "usage" in response_data:

9
litellm/llms/bedrock/chat/invoke_transformations/amazon_qwen3_transformation.py
View file

@ -190,13 +190,8 @@ class AmazonQwen3Config(AmazonInvokeConfig, BaseConfig):
# Set the content in the existing model_response structure
if hasattr(model_response, 'choices') and len(model_response.choices) > 0:
choice = model_response.choices[0]
if hasattr(choice, 'message'):
choice.message.content = generated_text
choice.finish_reason = "stop"
else:
# Handle streaming choices
choice.delta.content = generated_text
choice.finish_reason = "stop"
choice.message.content = generated_text
choice.finish_reason = "stop"
# Set usage information if available in response
if "usage" in response_data:

14
litellm/llms/langgraph/chat/sse_iterator.py
View file

@ -11,7 +11,7 @@ from typing import TYPE_CHECKING, Optional
import httpx
from litellm._logging import verbose_logger
from litellm.types.utils import Delta, ModelResponse, StreamingChoices
from litellm.types.utils import Delta, ModelResponseStream, StreamingChoices
if TYPE_CHECKING:
pass
@ -139,9 +139,9 @@ class LangGraphSSEStreamIterator:
return self._create_final_chunk()
return None
def _create_content_chunk(self, text: str) -> ModelResponse:
"""Create a ModelResponse chunk with content."""
chunk = ModelResponse(
def _create_content_chunk(self, text: str) -> ModelResponseStream:
"""Create a ModelResponseStream chunk with content."""
chunk = ModelResponseStream(
id=f"chatcmpl-{uuid.uuid4()}",
created=0,
model=self.model,
@ -158,9 +158,9 @@ class LangGraphSSEStreamIterator:
return chunk
def _create_final_chunk(self) -> ModelResponse:
"""Create a final ModelResponse chunk with finish_reason."""
chunk = ModelResponse(
def _create_final_chunk(self) -> ModelResponseStream:
"""Create a final ModelResponseStream chunk with finish_reason."""
chunk = ModelResponseStream(
id=f"chatcmpl-{uuid.uuid4()}",
created=0,
model=self.model,

12
litellm/llms/openai/chat/guardrail_translation/handler.py
View file

@ -542,16 +542,16 @@ class OpenAIChatCompletionsHandler(BaseTranslation):
if len(choice.message.tool_calls) > 0:
return True
elif isinstance(response, ModelResponseStream):
for choice in response.choices:
if isinstance(choice, litellm.StreamingChoices):
for streaming_choice in response.choices:
if isinstance(streaming_choice, litellm.StreamingChoices):
# Check for text content
if choice.delta.content and isinstance(choice.delta.content, str):
if streaming_choice.delta.content and isinstance(streaming_choice.delta.content, str):
return True
# Check for tool calls
if choice.delta.tool_calls and isinstance(
choice.delta.tool_calls, list
if streaming_choice.delta.tool_calls and isinstance(
streaming_choice.delta.tool_calls, list
):
if len(choice.delta.tool_calls) > 0:
if len(streaming_choice.delta.tool_calls) > 0:
return True
return False

4
litellm/utils.py
View file

@ -4960,9 +4960,7 @@ def get_response_string(response_obj: Union[ModelResponse, ModelResponseStream])
return delta if isinstance(delta, str) else ""
# Handle standard ModelResponse and ModelResponseStream
_choices: Union[List[Union[Choices, StreamingChoices]], List[StreamingChoices]] = (
response_obj.choices
)
_choices: Union[List[Choices], List[StreamingChoices]] = response_obj.choices
# Use list accumulation to avoid O(n^2) string concatenation across choices
response_parts: List[str] = []