scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-08 22:21:35 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 78

Add support for server_tool_use and web_search_tool_result in FakeAnthropicMessagesStreamIterator

Browse source 
- Implemented handling for "server_tool_use" and "web_search_tool_result" block types in the FakeAnthropicMessagesStreamIterator.
- Added logic to emit content_block_start and content_block_stop events for both block types, aligning with Anthropic's native streaming format.
- Enhanced the iterator's functionality to support new message types, improving integration with external tools.
This commit is contained in:
0xxmemo 2026-04-06 15:56:14 -05:00
parent d210bd4c4e
commit cf6c277386
1 changed files with 36 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

36
litellm/llms/anthropic/experimental_pass_through/messages/fake_stream_iterator.py
View file

@ -169,6 +169,42 @@ class FakeAnthropicMessagesStreamIterator:
block_dict = cast(Dict[str, Any], block)
chunks.extend(self._create_content_block_chunks(block_dict, index))
elif block_type == "server_tool_use":
# Emit the full block as content_block_start (same as
# Anthropic's native streaming format).
content_block_start = {
"type": "content_block_start",
"index": index,
"content_block": block_dict,
}
chunks.append(
f"event: content_block_start\ndata: {json.dumps(content_block_start)}\n\n".encode()
)
# content_block_stop
content_block_stop = {"type": "content_block_stop", "index": index}
chunks.append(
f"event: content_block_stop\ndata: {json.dumps(content_block_stop)}\n\n".encode()
)
elif block_type == "web_search_tool_result":
# Emit the full block as content_block_start (same as
# Anthropic's native streaming format).
content_block_start = {
"type": "content_block_start",
"index": index,
"content_block": block_dict,
}
chunks.append(
f"event: content_block_start\ndata: {json.dumps(content_block_start)}\n\n".encode()
)
# content_block_stop
content_block_stop = {"type": "content_block_stop", "index": index}
chunks.append(
f"event: content_block_stop\ndata: {json.dumps(content_block_stop)}\n\n".encode()
)
# 5. message_delta event (with final usage and stop_reason)
# Include cache usage fields so clients that only read message_delta
# (like Claude Code's SDK) see the full input token breakdown.