test(telemetry): Telemetry Tests #3805
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
iamemilio
requested review from
ashwinb,
bbrowning,
ehhuang,
franciscojavierarceo,
hardikjshah,
leseb,
mattf,
raghotham,
reluctantfuturist,
slekkala1,
terrytangyuan and
yanxi0830
as code owners
meta-cla
bot
added
the
CLA Signed
iamemilio
force-pushed
the
telemetry-coverage-tests
branch
from
bcb801e to
d057549
Compare
iamemilio
force-pushed
the
telemetry-coverage-tests
branch
from
d057549 to
94bcedd
Compare
iamemilio
changed the title
iamemilio
force-pushed
the
telemetry-coverage-tests
branch
2 times, most recently
from
da28bd0 to
86ec389
Compare
9 tasks
ehhuang
reviewed
Oct 14, 2025
Comment on lines
71
to
72
| # Verify token metrics in response | ||
| # Note: Llama Stack emits token metrics in the response JSON, not via OTel Metrics API |
There was a problem hiding this comment.
These shouldn't be in telemetry tests? should be responses tests instead?
|
|
||
| pytestmark = pytest.mark.skipif( | ||
| os.environ.get("LLAMA_STACK_TEST_STACK_CONFIG_TYPE") == "server", | ||
| reason="In-memory telemetry tests only work in library_client mode (server mode runs in separate process)", |
There was a problem hiding this comment.
I think it would be great to have the server tested as that's the main production path. We can have the server use in-memory collector and maybe write the collected results to file somehow, which the tests can then load and validate?
iamemilio
force-pushed
the
telemetry-coverage-tests
branch
from
8bbdadc to
862076f
Compare
iamemilio
force-pushed
the
telemetry-coverage-tests
branch
2 times, most recently
from
dd9f6d4 to
d82abf4
Compare
iamemilio
force-pushed
the
telemetry-coverage-tests
branch
2 times, most recently
from
de02a38 to
56d2bd2
Compare
iamemilio
force-pushed
the
telemetry-coverage-tests
branch
from
56d2bd2 to
2ca139d
Compare
ehhuang
reviewed
Oct 16, 2025
ehhuang
reviewed
Oct 16, 2025
ehhuang
reviewed
Oct 16, 2025
Comment on lines
52
to
59
| # Handle both dict and Pydantic model for usage | ||
| # This occurs do to the replay system returning a dict for usage, but the client returning a Pydantic model | ||
| # TODO: Fix this by making the replay system return a Pydantic model for usage |
iamemilio
force-pushed
the
telemetry-coverage-tests
branch
from
2ca139d to
73a7af0
Compare
ehhuang
approved these changes
Oct 16, 2025
| contains_model_id = True | ||
| assert args["model_id"] == text_model_id | ||
|
|
||
| assert contains_model_id |
There was a problem hiding this comment.
clearer to store logged_model_id directly in the loop above and assert logged_model_id == text_model_id here
…ma stack initializes
iamemilio
force-pushed
the
telemetry-coverage-tests
branch
from
73a7af0 to
4f82002
Compare
ehhuang
reviewed
Oct 17, 2025
| if "model_id" in args: | ||
| logged_model_id = args["model_id"] | ||
|
|
||
| assert logged_model_id is not None |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
What does this PR do?
Adds a test and a standardized way to build future tests out for telemetry in llama stack.
Contributes to #3806
Test Plan
This is the test plan 😎