ci(evals): only run evals in CI if prompts or tools changed

[gundermanc]

Update the CI to require nightly evals to pass, but only when making changes to prompt and tools.

This change comes in the wake of an issue where the CI was blocked on evals this morning. I temporarily removed the block: #20870

I then investigated, and identified and fixed this regression, which caused the failure: #20890

Now that the tests are once again passing, I am making them required, but only for changes to prompts and tools, to minimize the impact of future failures.

[github-actions]

Size Change: -2 B (0%)

Total Size: 25.8 MB

ℹ️ View Unchanged

Filename	Size	Change
./bundle/gemini.js	25.3 MB	-2 B (0%)
./bundle/node_modules/@google/gemini-cli-devtools/dist/client/main.js	221 kB	0 B
./bundle/node_modules/@google/gemini-cli-devtools/dist/src/_client-assets.js	227 kB	0 B
./bundle/node_modules/@google/gemini-cli-devtools/dist/src/index.js	11.5 kB	0 B
./bundle/node_modules/@google/gemini-cli-devtools/dist/src/types.js	132 B	0 B
./bundle/sandbox-macos-permissive-open.sb	890 B	0 B
./bundle/sandbox-macos-permissive-proxied.sb	1.31 kB	0 B
./bundle/sandbox-macos-restrictive-open.sb	3.36 kB	0 B
./bundle/sandbox-macos-restrictive-proxied.sb	3.56 kB	0 B
./bundle/sandbox-macos-strict-open.sb	4.82 kB	0 B
./bundle/sandbox-macos-strict-proxied.sb	5.02 kB	0 B

_{compressed-size-action}

[gemini-code-assist]

Summary of Changes

Hello, I'm Gemini Code Assist¹! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request refines the continuous integration process by implementing a conditional execution strategy for nightly evaluation tests. The primary goal is to prevent unnecessary CI blockages by ensuring these resource-intensive tests only run when changes directly impacting prompts or tools are detected, thereby streamlining the development workflow and improving CI efficiency.

Highlights

• CI/CD Workflow Enhancement: Modified the CI process to conditionally execute nightly evaluation tests, aiming to reduce unnecessary CI blockages and improve efficiency.
• Conditional Evaluation Trigger: Evaluation tests will now only run if changes are detected within the packages/core/src/prompts/ or packages/core/src/tools/ directories.
• New Script for Change Detection: Introduced a new Node.js script, scripts/changed_prompt.js, responsible for determining whether evaluation tests should be triggered based on file changes.

Changelog

• scripts/changed_prompt.js
  • Added a new script that uses Git commands to identify changed files and determine if evaluation tests should be executed based on predefined file path prefixes.

Ignored Files

• Ignored by pattern: .github/workflows/** (1)
  • .github/workflows/chained_e2e.yml

Activity

• No human activity (comments, reviews) has occurred on this pull request yet.

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature	Command	Description
Code Review	/gemini review	Performs a code review for the current pull request in its current state.
Pull Request Summary	/gemini summary	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help	/gemini help	Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Footnotes

1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

[gemini-code-assist]

Code Review

This pull request introduces a script to conditionally run CI evaluations based on whether prompt or tool files have been modified. The logic is sound, defaulting to running evaluations if any error occurs. However, I've identified a potential issue where the script hardcodes the main branch for comparison, which could lead to incorrect behavior on PRs targeting other branches. My review includes a suggestion to make the script more robust by dynamically determining the target branch from CI environment variables.

[SandyTao520]

it looks like the code find the merge base with the target branch instead of main?

[SandyTao520]

consider adding the evals/ directory too

[gundermanc]

Ok, added. Note that as written, only the ALWAYS_PASSES evals will end up getting run during the CI. Breaking changes to USUALLY_PASSES ones will not.

I guess we could make it smart enough to compute the delta, but I'd rather aspire to stabilizing as many tests as possible and running them during the CI by default.