Skip to content

feat(openai): Add Agents API instrumentation #762

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
Abhijeet Prasad (AbhiPrasad) merged 2 commits into from
Sep 14, 2026
Merged

feat(openai): Add Agents API instrumentation #762

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
37800a4
feat(openai): Add Agents API instrumentation
AbhiPrasad Sep 11, 2026
8f046bb
handle streams better
AbhiPrasad Sep 14, 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
2 changes: 1 addition & 1 deletion py/pyproject.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -377,7 +377,7 @@ latest = "ai[openai]==0.5.2"
"0.4.0" = "ai[openai]==0.4.0"

[tool.braintrust.matrix.openai]
latest = "openai==3.8.0"
latest = "openai==3.13.0"

@realark Andrew Kent (realark) Sep 14, 2026

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

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

I assume the goal here is to just keep bumping up latest and if/when we hit some kind of major compat issue only then do we add a new entry to the matrix

@AbhiPrasad Abhijeet Prasad (AbhiPrasad) Sep 14, 2026

Copy link
Copy Markdown
Member Author

Choose a reason for hiding this comment

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

yup exactly. Every week we have a weekly job to update it. We still prefer fixed version numbers over just saying whatever is latest to prevent supply chain attacks.

"1.92.0" = "openai==1.92.0"
"1.77.0" = "openai==1.77.0"
"1.71.0" = "openai==1.71.0"
Expand Down
17 changes: 13 additions & 4 deletions py/src/braintrust/integrations/auto_test_scripts/test_auto_openai.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,18 +8,27 @@
from wrapt import FunctionWrapper


def _is_braintrust_wrapped() -> bool:
attr = inspect.getattr_static(openai.resources.chat.completions.Completions, "create", None)
def _is_braintrust_wrapped(resource) -> bool:
attr = inspect.getattr_static(resource, "create", None)
return isinstance(attr, FunctionWrapper)


resources = [openai.resources.chat.completions.Completions]
try:
from openai.resources.beta.agents.sessions.sessions import Sessions

resources.append(Sessions)
except ImportError:
pass


# 1. Verify not patched initially
assert not _is_braintrust_wrapped()
assert all(not _is_braintrust_wrapped(resource) for resource in resources)

# 2. Instrument
results = auto_instrument()
assert results.get("openai") == True
assert _is_braintrust_wrapped()
assert all(_is_braintrust_wrapped(resource) for resource in resources)

# 3. Idempotent
results2 = auto_instrument()
Expand Down
155 changes: 155 additions & 0 deletions ...ntrust/integrations/openai/cassettes/latest/test_openai_agents_session_stream[async].yaml
View file
Open in desktop

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

Loading