Skip to content

Stream tool calls and structured output from Anthropic as it's received instead of in one go #1669

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Stream tool calls and structured output from Anthropic as it's received instead of in one go #1669

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
16 changes: 2 additions & 14 deletions pydantic_ai_slim/pydantic_ai/models/anthropic.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,6 @@
from contextlib import asynccontextmanager
from dataclasses import dataclass, field
from datetime import datetime, timezone
from json import JSONDecodeError, loads as json_loads
from typing import Any, Literal, Union, cast, overload

from typing_extensions import assert_never
Expand Down Expand Up @@ -441,7 +440,6 @@ class AnthropicStreamedResponse(StreamedResponse):

async def _get_event_iterator(self) -> AsyncIterator[ModelResponseStreamEvent]:
current_block: ContentBlock | None = None
current_json: str = ''

async for event in self._response:
self._usage += _map_usage(event)
Expand All @@ -454,7 +452,7 @@ async def _get_event_iterator(self) -> AsyncIterator[ModelResponseStreamEvent]:
maybe_event = self._parts_manager.handle_tool_call_delta(
vendor_part_id=current_block.id,
tool_name=current_block.name,
args=cast(dict[str, Any], current_block.input),
args=cast(dict[str, Any], current_block.input) or None,
tool_call_id=current_block.id,
)
if maybe_event is not None:
Expand All @@ -466,20 +464,10 @@ async def _get_event_iterator(self) -> AsyncIterator[ModelResponseStreamEvent]:
elif (
current_block and event.delta.type == 'input_json_delta' and isinstance(current_block, ToolUseBlock)
):
# Try to parse the JSON immediately, otherwise cache the value for later. This handles
# cases where the JSON is not currently valid but will be valid once we stream more tokens.
try:
parsed_args = json_loads(current_json + event.delta.partial_json)
current_json = ''
except JSONDecodeError:
current_json += event.delta.partial_json
continue

# For tool calls, we need to handle partial JSON updates
maybe_event = self._parts_manager.handle_tool_call_delta(
vendor_part_id=current_block.id,
tool_name='',
args=parsed_args,
args=event.delta.partial_json,
tool_call_id=current_block.id,
)
if maybe_event is not None:
Expand Down
11 changes: 8 additions & 3 deletions tests/models/test_anthropic.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -529,18 +529,23 @@ async def test_stream_structured(allow_model_requests: None):
RawContentBlockStartEvent(
type='content_block_start',
index=0,
content_block=ToolUseBlock(type='tool_use', id='tool_1', name='my_tool', input={'first': 'One'}),
content_block=ToolUseBlock(type='tool_use', id='tool_1', name='my_tool', input={}),
),
# Add more data through an incomplete JSON delta
RawContentBlockDeltaEvent(
type='content_block_delta',
index=0,
delta=InputJSONDelta(type='input_json_delta', partial_json='{"second":'),
delta=InputJSONDelta(type='input_json_delta', partial_json='{"first": "One'),
),
RawContentBlockDeltaEvent(
type='content_block_delta',
index=0,
delta=InputJSONDelta(type='input_json_delta', partial_json='"Two"}'),
delta=InputJSONDelta(type='input_json_delta', partial_json='", "second": "Two"'),
),
RawContentBlockDeltaEvent(
type='content_block_delta',
index=0,
delta=InputJSONDelta(type='input_json_delta', partial_json='}'),
),
# Mark tool block as complete
RawContentBlockStopEvent(type='content_block_stop', index=0),
Expand Down
Loading