Stricter JSON schema validation broke a test. Test was fixed in
https://github.com/langchain-ai/langchain/pull/32145. Core release runs
old tests (i.e., last released version of langchain-anthropic) against
new core. So we bypass anthropic for release. Will revert after.
As part of core releases we run tests on the last released version of
some packages (including langchain-openai) using the new version of
langchain-core. We run langchain-openai's test suite as it was when it
was last released.
Our test for computer use started raising 500 error at some point during
the day today (test passed as part of scheduled test job in the
morning):
> InternalServerError: Error code: 500 - {'error': {'message': 'An error
occurred while processing your request. You can retry your request, or
contact us through our help center at help.openai.com if the error
persists.
Will revert this change after we release langchain-core.
As part of core releases we run tests on the last released version of
some packages (including langchain-openai) using the new version of
langchain-core. We run langchain-openai's test suite as it was when it
was last released.
OpenAI has since updated their API— relaxing constraints on what schemas
are supported when `strict=True`— causing these tests to break. They
have since been fixed. But the old tests will continue to fail.
Will revert this change after we release OpenAI today.
On core releases, we check out the latest published package for
langchain-openai and langchain-anthropic and run their tests against the
candidate version of langchain-core.
Because these packages have a local install of langchain-tests, we also
need to check out the previous version of langchain-tests.
Perplexity's importance in the space has been growing, so we think it's
time to add an official integration!
Note: following the release of `langchain-perplexity` to `pypi`, we
should be able to add `perplexity` as an extra in
`libs/langchain/pyproject.toml`, but we're blocked by a circular import
for now.
---------
Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
Co-authored-by: Chester Curme <chester.curme@gmail.com>
Here we add a job to the release workflow that, when releasing
`langchain-core`, tests prior published versions of select packages
against the new version of core. We limit the testing to the most recent
published versions of langchain-anthropic and langchain-openai.
This is designed to catch backward-incompatible updates to core. We
sometimes update core and downstream packages simultaneously, so there
may not be any commit in the history at which tests would fail. So
although core and latest downstream packages could be consistent, we can
benefit from testing prior versions of downstream packages against core.
I tested the workflow by simulating a [breaking
change](d7287248cf)
in core and running it with publishing steps disabled:
https://github.com/langchain-ai/langchain/actions/runs/13741876345. The
workflow correctly caught the issue.
