Skip to content

Fix Anthropic streaming usage counting #2771

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

Merged
DouweM merged 2 commits into from
Sep 2, 2025
Merged

Fix Anthropic streaming usage counting #2771

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
7361dbb
Fix Anthropic streaming usage counting
DouweM Sep 2, 2025
3ca1883
Fix coverage
DouweM Sep 2, 2025
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
15 changes: 4 additions & 11 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 @@ -536,20 +536,15 @@ def _map_tool_definition(f: ToolDefinition) -> BetaToolParam:
}


def _map_usage(message: BetaMessage | BetaRawMessageStreamEvent) -> usage.RequestUsage:
def _map_usage(message: BetaMessage | BetaRawMessageStartEvent | BetaRawMessageDeltaEvent) -> usage.RequestUsage:
if isinstance(message, BetaMessage):
response_usage = message.usage
elif isinstance(message, BetaRawMessageStartEvent):
response_usage = message.message.usage
elif isinstance(message, BetaRawMessageDeltaEvent):
response_usage = message.usage
else:
# No usage information provided in:
# - RawMessageStopEvent
# - RawContentBlockStartEvent
# - RawContentBlockDeltaEvent
# - RawContentBlockStopEvent
return usage.RequestUsage()
assert_never(message)

# Store all integer-typed usage values in the details, except 'output_tokens' which is represented exactly by
# `response_tokens`
Expand Down Expand Up @@ -586,10 +581,8 @@ async def _get_event_iterator(self) -> AsyncIterator[ModelResponseStreamEvent]:
current_block: BetaContentBlock | None = None

async for event in self._response:
self._usage += _map_usage(event)

if isinstance(event, BetaRawMessageStartEvent):
pass
self._usage = _map_usage(event)

elif isinstance(event, BetaRawContentBlockStartEvent):
current_block = event.content_block
Expand Down Expand Up @@ -652,7 +645,7 @@ async def _get_event_iterator(self) -> AsyncIterator[ModelResponseStreamEvent]:
pass

elif isinstance(event, BetaRawMessageDeltaEvent):
pass
self._usage = _map_usage(event)

elif isinstance(event, BetaRawContentBlockStopEvent | BetaRawMessageStopEvent): # pragma: no branch
current_block = None
Expand Down
9 changes: 4 additions & 5 deletions tests/models/test_anthropic.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -608,7 +608,7 @@ async def test_stream_structured(allow_model_requests: None):
BetaRawMessageDeltaEvent(
type='message_delta',
delta=Delta(stop_reason='end_turn'),
usage=BetaMessageDeltaUsage(output_tokens=5),
usage=BetaMessageDeltaUsage(input_tokens=20, output_tokens=5),
),
# Mark message as complete
BetaRawMessageStopEvent(type='message_stop'),
Expand Down Expand Up @@ -1291,12 +1291,11 @@ def anth_msg(usage: BetaUsage) -> BetaMessage:
snapshot(RequestUsage(output_tokens=5, details={'output_tokens': 5})),
id='RawMessageDeltaEvent',
),
pytest.param(
lambda: BetaRawMessageStopEvent(type='message_stop'), snapshot(RequestUsage()), id='RawMessageStopEvent'
),
],
)
def test_usage(message_callback: Callable[[], BetaMessage | BetaRawMessageStreamEvent], usage: RunUsage):
def test_usage(
message_callback: Callable[[], BetaMessage | BetaRawMessageStartEvent | BetaRawMessageDeltaEvent], usage: RunUsage
):
assert _map_usage(message_callback()) == usage


Expand Down