feat: Add experimental integration tests with cached providers #2176
+127
−2
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
derekhiggins
requested review from
ashwinb,
yanxi0830,
hardikjshah,
dltn,
raghotham,
dineshyv,
vladimirivic,
sixianyi0721,
ehhuang,
terrytangyuan,
SLR722 and
leseb
as code owners
facebook-github-bot
added
the
CLA Signed
|
The experimental jobs failed, as expected as there was no cache or tokens configured See https://github.com/derekhiggins/llama-stack/actions/runs/15042046690/job/42275834971 |
derekhiggins
force-pushed
the
agent-test
branch
2 times, most recently
from
4f1c7ec to
c859469
Compare
gpt-4o needs a hint to use get_boiling_point for fictional liquids. Signed-off-by: Derek Higgins <[email protected]>
Introduce a new workflow to run integration and agent tests against the OpenAI provider, and a subset of inference tests against Fireworks AI. Responses from inference providers are cached and reused in subsequent jobs, reducing API quota usage, speeding up test runs, and improving reliability by avoiding server-side errors. (see https://github.com/derekhiggins/cachemeifyoucan for caching code) The cache is updated on successful job completion. To prevent the cache from diverging or growing indefinitely, periodically refresh or manually update the cache by running this job without a cache(will do as a follow on if this merges). Any updates to integration tests that change the request to the provider will use provider quota and update the cache (if they fail), so need to be careful not to repeatedly run failing PR's Signed-off-by: Derek Higgins <[email protected]>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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?
Introduce a new workflow to run integration and agent tests
against the OpenAI provider, and a subset of inference tests
against Fireworks AI.
Responses from inference providers are cached and reused in
subsequent jobs, reducing API quota usage, speeding up test runs,
and improving reliability by avoiding server-side errors.
(see https://github.com/derekhiggins/cachemeifyoucan for caching code)
The cache is updated on successful job completion.
To prevent the cache from diverging or growing indefinitely,
periodically refresh or manually update the cache by running
this job without a cache(will do as a follow on if this merges).
Any updates to integration tests that change the request to the
provider will use provider quota and update the cache (if they
fail), so need to be careful not to repeatedly run failing PR's
Related: #2017