Skip to content

fix(openai): Use max_output_tokens for Responses API #5693

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
alexander-alderman-webb merged 10 commits into from
Mar 26, 2026
Merged

fix(openai): Use max_output_tokens for Responses API #5693

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
10 commits
Select commit Hold shift + click to select a range
4917b6a
ref(openai): Move input handling code into API-specific functions
alexander-alderman-webb Mar 18, 2026
4261546
keep set_data_normalized
alexander-alderman-webb Mar 18, 2026
1f6149e
.
alexander-alderman-webb Mar 18, 2026
36842e0
.
alexander-alderman-webb Mar 18, 2026
532fa65
.
alexander-alderman-webb Mar 18, 2026
9fb4bff
fix(openai): Use max_output_tokens for Responses API
alexander-alderman-webb Mar 18, 2026
9935178
.
alexander-alderman-webb Mar 18, 2026
4de8cdb
Merge branch 'master' into webb/openai/remove-common-input-data
alexander-alderman-webb Mar 25, 2026
cef5444
Merge branch 'webb/openai/remove-common-input-data' into webb/openai/…
alexander-alderman-webb Mar 25, 2026
40acdf1
merge master
alexander-alderman-webb Mar 26, 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
4 changes: 2 additions & 2 deletions sentry_sdk/integrations/openai.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -241,9 +241,9 @@ def _set_responses_api_input_data(
if stream is not None and _is_given(stream):
set_data_normalized(span, SPANDATA.GEN_AI_RESPONSE_STREAMING, stream)

max_tokens = kwargs.get("max_tokens")
max_tokens = kwargs.get("max_output_tokens")
if max_tokens is not None and _is_given(max_tokens):
set_data_normalized(span, SPANDATA.GEN_AI_REQUEST_MAX_TOKENS, max_tokens)
span.set_data(SPANDATA.GEN_AI_REQUEST_MAX_TOKENS, max_tokens)

presence_penalty = kwargs.get("presence_penalty")
if presence_penalty is not None and _is_given(presence_penalty):
Expand Down
12 changes: 12 additions & 0 deletions tests/integrations/openai/test_openai.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1874,6 +1874,7 @@ def test_ai_client_span_responses_api_no_pii(sentry_init, capture_events):
model="gpt-4o",
instructions="You are a coding assistant that talks like a pirate.",
input="How do I check if a Python object is an instance of a class?",
max_output_tokens=100,
)

(transaction,) = events
Expand All @@ -1884,6 +1885,7 @@ def test_ai_client_span_responses_api_no_pii(sentry_init, capture_events):
assert spans[0]["origin"] == "auto.ai.openai"
assert spans[0]["data"] == {
"gen_ai.operation.name": "responses",
"gen_ai.request.max_tokens": 100,
"gen_ai.request.model": "gpt-4o",
"gen_ai.response.model": "response-model-id",
"gen_ai.system": "openai",
Expand Down Expand Up @@ -1984,6 +1986,7 @@ def test_ai_client_span_responses_api(
model="gpt-4o",
instructions=instructions,
input=input,
max_output_tokens=100,
)

(transaction,) = events
Expand All @@ -1995,6 +1998,7 @@ def test_ai_client_span_responses_api(

expected_data = {
"gen_ai.operation.name": "responses",
"gen_ai.request.max_tokens": 100,
"gen_ai.system": "openai",
"gen_ai.response.model": "response-model-id",
"gen_ai.usage.input_tokens": 20,
Expand Down Expand Up @@ -2286,6 +2290,7 @@ async def test_ai_client_span_responses_async_api(
model="gpt-4o",
instructions=instructions,
input=input,
max_output_tokens=100,
)

(transaction,) = events
Expand All @@ -2297,6 +2302,7 @@ async def test_ai_client_span_responses_async_api(

expected_data = {
"gen_ai.operation.name": "responses",
"gen_ai.request.max_tokens": 100,
"gen_ai.request.messages": '["How do I check if a Python object is an instance of a class?"]',
"gen_ai.request.model": "gpt-4o",
"gen_ai.response.model": "response-model-id",
Expand Down Expand Up @@ -2555,6 +2561,7 @@ async def test_ai_client_span_streaming_responses_async_api(
instructions=instructions,
input=input,
stream=True,
max_output_tokens=100,
)
async for _ in result:
pass
Expand All @@ -2568,6 +2575,7 @@ async def test_ai_client_span_streaming_responses_async_api(

expected_data = {
"gen_ai.operation.name": "responses",
"gen_ai.request.max_tokens": 100,
"gen_ai.response.model": "response-model-id",
"gen_ai.response.streaming": True,
"gen_ai.system": "openai",
Expand Down Expand Up @@ -2880,6 +2888,7 @@ def test_streaming_responses_api(
model="some-model",
input="hello",
stream=True,
max_output_tokens=100,
)

response_string = ""
Expand All @@ -2893,6 +2902,7 @@ def test_streaming_responses_api(
(span,) = transaction["spans"]
assert span["op"] == "gen_ai.responses"
assert span["data"][SPANDATA.GEN_AI_SYSTEM] == "openai"
assert span["data"][SPANDATA.GEN_AI_REQUEST_MAX_TOKENS] == 100

assert span["data"][SPANDATA.GEN_AI_RESPONSE_MODEL] == "response-model-id"

Expand Down Expand Up @@ -2938,6 +2948,7 @@ async def test_streaming_responses_api_async(
model="some-model",
input="hello",
stream=True,
max_output_tokens=100,
)

response_string = ""
Expand All @@ -2951,6 +2962,7 @@ async def test_streaming_responses_api_async(
(span,) = transaction["spans"]
assert span["op"] == "gen_ai.responses"
assert span["data"][SPANDATA.GEN_AI_SYSTEM] == "openai"
assert span["data"][SPANDATA.GEN_AI_REQUEST_MAX_TOKENS] == 100

assert span["data"][SPANDATA.GEN_AI_RESPONSE_MODEL] == "response-model-id"

Expand Down
Loading