Skip to content

feat(anthropic): Record finish reasons in AI monitoring spans #5678

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
ericapisani merged 4 commits into from
Mar 17, 2026
Merged

feat(anthropic): Record finish reasons in AI monitoring spans #5678

Show file tree
Hide file tree
Changes from 2 commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
9998646
feat(anthropic): Record finish reasons in AI monitoring spans
ericapisani Mar 16, 2026
c0283c3
Merge branch 'master' into py-2136-take-2
ericapisani Mar 16, 2026
e146224
ref(anthropic): Simplify finish_reasons to single finish_reason inter…
ericapisani Mar 17, 2026
c5feb0c
Merge branch 'py-2136-take-2' of github.com:getsentry/sentry-python i…
ericapisani Mar 17, 2026
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
45 changes: 32 additions & 13 deletions sentry_sdk/integrations/anthropic.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -159,7 +159,8 @@ def _collect_ai_data(
usage: "_RecordedUsage",
content_blocks: "list[str]",
response_id: "str | None" = None,
) -> "tuple[str | None, _RecordedUsage, list[str], str | None]":
finish_reasons: "list[str] | None" = None,
) -> "tuple[str | None, _RecordedUsage, list[str], str | None, list[str] | None]":
"""
Collect model information, token usage, and collect content blocks from the AI streaming response.
"""
Expand Down Expand Up @@ -197,6 +198,7 @@ def _collect_ai_data(
usage,
content_blocks,
response_id,
finish_reasons,
)

# Counterintuitive, but message_delta contains cumulative token counts :)
Expand All @@ -221,18 +223,18 @@ def _collect_ai_data(
usage.cache_read_input_tokens = cache_read_input_tokens
# TODO: Record event.usage.server_tool_use

return (
model,
usage,
content_blocks,
response_id,
)
stop_reason = getattr(event.delta, "stop_reason", None)
if stop_reason is not None:
finish_reasons = [stop_reason]
Comment thread
ericapisani marked this conversation as resolved.
Outdated

return (model, usage, content_blocks, response_id, finish_reasons)

return (
model,
usage,
content_blocks,
response_id,
finish_reasons,
)


Expand Down Expand Up @@ -411,6 +413,7 @@ def _wrap_synchronous_message_iterator(
usage = _RecordedUsage()
content_blocks: "list[str]" = []
response_id = None
finish_reasons = None

try:
for event in iterator:
Expand All @@ -430,12 +433,15 @@ def _wrap_synchronous_message_iterator(
yield event
continue

(model, usage, content_blocks, response_id) = _collect_ai_data(
event,
model,
usage,
content_blocks,
response_id,
(model, usage, content_blocks, response_id, finish_reasons) = (
_collect_ai_data(
event,
model,
usage,
content_blocks,
response_id,
finish_reasons,
)
)
yield event
finally:
Expand All @@ -459,6 +465,7 @@ def _wrap_synchronous_message_iterator(
content_blocks=[{"text": "".join(content_blocks), "type": "text"}],
finish_span=True,
response_id=response_id,
finish_reasons=finish_reasons,
)


Expand All @@ -475,6 +482,7 @@ async def _wrap_asynchronous_message_iterator(
usage = _RecordedUsage()
content_blocks: "list[str]" = []
response_id = None
finish_reasons = None

try:
async for event in iterator:
Expand All @@ -499,12 +507,14 @@ async def _wrap_asynchronous_message_iterator(
usage,
content_blocks,
response_id,
finish_reasons,
) = _collect_ai_data(
event,
model,
usage,
content_blocks,
response_id,
finish_reasons,
)
yield event
finally:
Expand All @@ -528,6 +538,7 @@ async def _wrap_asynchronous_message_iterator(
content_blocks=[{"text": "".join(content_blocks), "type": "text"}],
finish_span=True,
response_id=response_id,
finish_reasons=finish_reasons,
)


Expand All @@ -542,12 +553,15 @@ def _set_output_data(
content_blocks: "list[Any]",
finish_span: bool = False,
response_id: "str | None" = None,
finish_reasons: "list[str] | None" = None,
) -> None:
"""
Set output data for the span based on the AI response."""
span.set_data(SPANDATA.GEN_AI_RESPONSE_MODEL, model)
if response_id is not None:
span.set_data(SPANDATA.GEN_AI_RESPONSE_ID, response_id)
if finish_reasons is not None:
span.set_data(SPANDATA.GEN_AI_RESPONSE_FINISH_REASONS, finish_reasons)
Comment thread
ericapisani marked this conversation as resolved.
Outdated
if should_send_default_pii() and integration.include_prompts:
output_messages: "dict[str, list[Any]]" = {
"response": [],
Expand Down Expand Up @@ -641,6 +655,10 @@ def _sentry_patched_create_common(f: "Any", *args: "Any", **kwargs: "Any") -> "A
elif hasattr(content_block, "text"):
content_blocks.append({"type": "text", "text": content_block.text})

finish_reasons = None
if getattr(result, "stop_reason", None) is not None:
finish_reasons = [getattr(result, "stop_reason")]

_set_output_data(
span=span,
integration=integration,
Expand All @@ -652,6 +670,7 @@ def _sentry_patched_create_common(f: "Any", *args: "Any", **kwargs: "Any") -> "A
content_blocks=content_blocks,
finish_span=True,
response_id=getattr(result, "id", None),
finish_reasons=finish_reasons,
)
else:
span.set_data("unknown_response", True)
Expand Down
19 changes: 14 additions & 5 deletions tests/integrations/anthropic/test_anthropic.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -63,6 +63,7 @@ async def __call__(self, *args, **kwargs):
role="assistant",
content=[TextBlock(type="text", text="Hi, I'm Claude.")],
type="message",
stop_reason="end_turn",
usage=Usage(input_tokens=10, output_tokens=20),
)

Expand Down Expand Up @@ -136,6 +137,7 @@ def test_nonstreaming_create_message(
assert span["data"][SPANDATA.GEN_AI_USAGE_TOTAL_TOKENS] == 30
assert span["data"][SPANDATA.GEN_AI_RESPONSE_STREAMING] is False
assert span["data"][SPANDATA.GEN_AI_RESPONSE_ID] == "msg_01XFDUDYJgAACzvnptvVoYEL"
assert span["data"][SPANDATA.GEN_AI_RESPONSE_FINISH_REASONS] == ["end_turn"]


@pytest.mark.asyncio
Expand Down Expand Up @@ -258,7 +260,7 @@ def test_streaming_create_message(
),
ContentBlockStopEvent(type="content_block_stop", index=0),
MessageDeltaEvent(
delta=Delta(),
delta=Delta(stop_reason="max_tokens"),
usage=MessageDeltaUsage(output_tokens=10),
type="message_delta",
),
Expand Down Expand Up @@ -323,6 +325,7 @@ def test_streaming_create_message(
assert span["data"][SPANDATA.GEN_AI_USAGE_TOTAL_TOKENS] == 20
assert span["data"][SPANDATA.GEN_AI_RESPONSE_STREAMING] is True
assert span["data"][SPANDATA.GEN_AI_RESPONSE_ID] == "msg_01XFDUDYJgAACzvnptvVoYEL"
assert span["data"][SPANDATA.GEN_AI_RESPONSE_FINISH_REASONS] == ["max_tokens"]


@pytest.mark.parametrize(
Expand Down Expand Up @@ -373,7 +376,7 @@ def test_stream_messages(
),
ContentBlockStopEvent(type="content_block_stop", index=0),
MessageDeltaEvent(
delta=Delta(),
delta=Delta(stop_reason="max_tokens"),
usage=MessageDeltaUsage(output_tokens=10),
type="message_delta",
),
Expand Down Expand Up @@ -439,6 +442,7 @@ def test_stream_messages(
assert span["data"][SPANDATA.GEN_AI_USAGE_TOTAL_TOKENS] == 20
assert span["data"][SPANDATA.GEN_AI_RESPONSE_STREAMING] is True
assert span["data"][SPANDATA.GEN_AI_RESPONSE_ID] == "msg_01XFDUDYJgAACzvnptvVoYEL"
assert span["data"][SPANDATA.GEN_AI_RESPONSE_FINISH_REASONS] == ["max_tokens"]


@pytest.mark.asyncio
Expand Down Expand Up @@ -492,7 +496,7 @@ async def test_streaming_create_message_async(
),
ContentBlockStopEvent(type="content_block_stop", index=0),
MessageDeltaEvent(
delta=Delta(),
delta=Delta(stop_reason="max_tokens"),
usage=MessageDeltaUsage(output_tokens=10),
type="message_delta",
),
Expand All @@ -504,6 +508,7 @@ async def test_streaming_create_message_async(
sentry_init(
integrations=[AnthropicIntegration(include_prompts=include_prompts)],
traces_sample_rate=1.0,
default_integrations=False,
Comment thread
ericapisani marked this conversation as resolved.
send_default_pii=send_default_pii,
)
events = capture_events()
Expand Down Expand Up @@ -559,6 +564,7 @@ async def test_streaming_create_message_async(
assert span["data"][SPANDATA.GEN_AI_USAGE_TOTAL_TOKENS] == 20
assert span["data"][SPANDATA.GEN_AI_RESPONSE_STREAMING] is True
assert span["data"][SPANDATA.GEN_AI_RESPONSE_ID] == "msg_01XFDUDYJgAACzvnptvVoYEL"
assert span["data"][SPANDATA.GEN_AI_RESPONSE_FINISH_REASONS] == ["max_tokens"]


@pytest.mark.asyncio
Expand Down Expand Up @@ -1471,14 +1477,15 @@ def test_collect_ai_data_with_input_json_delta():

content_blocks = []

model, new_usage, new_content_blocks, response_id = _collect_ai_data(
event, model, usage, content_blocks
model, new_usage, new_content_blocks, response_id, finish_reasons = (
_collect_ai_data(event, model, usage, content_blocks)
)
assert model is None
assert new_usage.input_tokens == usage.input_tokens
assert new_usage.output_tokens == usage.output_tokens
assert new_content_blocks == ["test"]
assert response_id is None
assert finish_reasons is None


@pytest.mark.skipif(
Expand Down Expand Up @@ -1766,6 +1773,7 @@ def test_nonstreaming_create_message_with_system_prompt(
assert span["data"][SPANDATA.GEN_AI_USAGE_OUTPUT_TOKENS] == 20
assert span["data"][SPANDATA.GEN_AI_USAGE_TOTAL_TOKENS] == 30
assert span["data"][SPANDATA.GEN_AI_RESPONSE_STREAMING] is False
assert span["data"][SPANDATA.GEN_AI_RESPONSE_FINISH_REASONS] == ["end_turn"]


@pytest.mark.asyncio
Expand Down Expand Up @@ -1851,6 +1859,7 @@ async def test_nonstreaming_create_message_with_system_prompt_async(
assert span["data"][SPANDATA.GEN_AI_USAGE_OUTPUT_TOKENS] == 20
assert span["data"][SPANDATA.GEN_AI_USAGE_TOTAL_TOKENS] == 30
assert span["data"][SPANDATA.GEN_AI_RESPONSE_STREAMING] is False
assert span["data"][SPANDATA.GEN_AI_RESPONSE_FINISH_REASONS] == ["end_turn"]


@pytest.mark.parametrize(
Expand Down
Loading