Skip to content

fix(openai-agents): Stop setting response model based on the request model #7413

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

Closed
alexander-alderman-webb wants to merge 2 commits into from
Closed

fix(openai-agents): Stop setting response model based on the request model #7413

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
c34c885
fix(openai-agents): Stop setting response model based on the request …
alexander-alderman-webb Sep 7, 2026
5bb18fd
remove comments
alexander-alderman-webb Sep 7, 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: 0 additions & 4 deletions sentry_sdk/integrations/openai_agents/patches/models.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -71,10 +71,6 @@ def _get_model(
# because we only patch its direct methods, all underlying data can remain unchanged.
model = copy.copy(original_get_model(agent, run_config))

# Capture the request model name for spans (agent.model can be None when using defaults)
request_model_name = model.model if hasattr(model, "model") else str(model)
agent._sentry_request_model = request_model_name

# Wrap _fetch_response if it exists (for OpenAI models) to capture response model
if hasattr(model, "_fetch_response"):
original_fetch_response = model._fetch_response
Expand Down
3 changes: 0 additions & 3 deletions sentry_sdk/integrations/openai_agents/spans/ai_client.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -201,12 +201,9 @@ def ai_client_span(
agent: "Agent", get_response_kwargs: "dict[str, Any]"
) -> "Union[sentry_sdk.tracing.Span, StreamedSpan]":
# TODO-anton: implement other types of operations. Now "chat" is hardcoded.
# Get model name from agent.model or fall back to request model (for when agent.model is None/default)
model_name = None
if agent.model:
model_name = agent.model.model if hasattr(agent.model, "model") else agent.model
elif hasattr(agent, "_sentry_request_model"):
model_name = agent._sentry_request_model

client_options = sentry_sdk.get_client().options

Expand Down
3 changes: 0 additions & 3 deletions sentry_sdk/integrations/openai_agents/utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -64,12 +64,9 @@ def _set_agent_data(
if agent.model_settings.max_tokens:
set_on_span(SPANDATA.GEN_AI_REQUEST_MAX_TOKENS, agent.model_settings.max_tokens)

# Get model name from agent.model or fall back to request model (for when agent.model is None/default)
model_name = None
if agent.model:
model_name = agent.model.model if hasattr(agent.model, "model") else agent.model
elif hasattr(agent, "_sentry_request_model"):
model_name = agent._sentry_request_model

@cursor cursor Bot Sep 7, 2026

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Request model lost for default models

Medium Severity

Removing _sentry_request_model drops the resolved request model when agent.model is unset. Agents that use the SDK default or a RunConfig model no longer get gen_ai.request.model, and chat spans are named chat None.

Additional Locations (2)
Fix in Cursor Fix in Web

Reviewed by Cursor Bugbot for commit 5bb18fd. Configure here.


if model_name:
set_on_span(SPANDATA.GEN_AI_REQUEST_MODEL, model_name)
Expand Down
Loading