tiennm99/litellm
1
0
Fork 0
mirror of https://github.com/tiennm99/litellm.git synced 2026-08-01 06:22:01 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add container field in streaming response

Browse Source
This commit is contained in:
Sameer Kankute
2025-12-16 10:02:07 +05:30
parent e40ad5203e
commit 9802a6a19e
1 changed files with 10 additions and 19 deletions
Download Patch File Download Diff File Expand all files Collapse all files
litellm/llms/anthropic/chat/handler.py
+10 -19
View File
@@ -690,14 +690,14 @@ class ModelResponseIterator:
self.current_content_block_type = content_block_start["content_block"]["type"]
if content_block_start["content_block"]["type"] == "text":
text = content_block_start["content_block"]["text"]
elif content_block_start["content_block"]["type"] == "tool_use":
elif content_block_start["content_block"]["type"] == "tool_use" or content_block_start["content_block"]["type"] == "server_tool_use":
self.tool_index += 1
tool_use = ChatCompletionToolCallChunk(
id=content_block_start["content_block"]["id"],
type="function",
function=ChatCompletionToolCallFunctionChunk(
name=content_block_start["content_block"]["name"],
arguments="",
arguments=content_block_start["content_block"]["input"],
),
index=self.tool_index,
)
@@ -706,18 +706,6 @@ class ModelResponseIterator:
caller_data = content_block_start["content_block"]["caller"]
if caller_data:
tool_use["caller"] = cast(Dict[str, Any], caller_data) # type: ignore[typeddict-item]
elif content_block_start["content_block"]["type"] == "server_tool_use":
# Handle server tool use (for tool search)
self.tool_index += 1
tool_use = ChatCompletionToolCallChunk(
id=content_block_start["content_block"]["id"],
type="function",
function=ChatCompletionToolCallFunctionChunk(
name=content_block_start["content_block"]["name"],
arguments="",
),
index=self.tool_index,
)
elif (
content_block_start["content_block"]["type"] == "redacted_thinking"
):
@@ -765,7 +753,9 @@ class ModelResponseIterator:
# These are automatically handled by Anthropic API, we just pass them through
pass
elif type_chunk == "message_delta":
finish_reason, usage = self._handle_message_delta(chunk)
finish_reason, usage, container = self._handle_message_delta(chunk)
if container:
provider_specific_fields["container"] = container
elif type_chunk == "message_start":
"""
Anthropic
@@ -881,15 +871,15 @@ class ModelResponseIterator:
return text, tool_use
def _handle_message_delta(self, chunk: dict) -> Tuple[str, Optional[Usage]]:
def _handle_message_delta(self, chunk: dict) -> Tuple[str, Optional[Usage], Optional[Dict[str, Any]]]:
"""
Handle message_delta event for finish_reason and usage.
Handle message_delta event for finish_reason, usage, and container.
Args:
chunk: The message_delta chunk
Returns:
Tuple of (finish_reason, usage)
Tuple of (finish_reason, usage, container)
"""
message_delta = MessageBlockDelta(**chunk) # type: ignore
finish_reason = map_finish_reason(
@@ -900,7 +890,8 @@ class ModelResponseIterator:
if self.converted_response_format_tool:
finish_reason = "stop"
usage = self._handle_usage(anthropic_usage_chunk=message_delta["usage"])
return finish_reason, usage
container = message_delta["delta"].get("container")
return finish_reason, usage, container
def _handle_accumulated_json_chunk(
self, data_str: str