Skip to content

Conversation

@dlarocque
Copy link
Contributor

  • Updates the prompt templates integration tests to use the default endpoint rather than the STAGING_URL.
    The integration tests were originally written to run against staging. Now that this feature is in prod, we should test against the prod endpoint.
  • Added a new set of test configs promptTemplatesTestConfigs which are used for the server prompt templates integration tests. These configs don't define a model, since those aren't defined in the client when using server prompt templates. The tests now run only once per endpoint (twice, for Google AI then Vertex AI), rather than once per endpoint for each model (Google AI gemini-2.0-flash, Google AI gemini-2.5-flash, ...).

The integration tests were originally written to run against staging.
Now that this feature is in prod, we should test against the prod
endpoint.
@dlarocque dlarocque requested a review from a team as a code owner November 17, 2025 18:00
@changeset-bot

This comment was marked as resolved.

@gemini-code-assist

This comment was marked as resolved.

gemini-code-assist[bot]

This comment was marked as resolved.

@google-oss-bot

This comment was marked as resolved.

@google-oss-bot
Copy link
Contributor

google-oss-bot commented Nov 17, 2025

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants