Skip crashlytics from doing a server enablement check.
Currently feature check is done by making an API enablement check on GCP for the feature. Crashlytics while it uses the platform API, it uses it with the scope of the Firebase CLI project ID rather than the end user project ID. For the end user, this API is by default enabled as the Crashlytics service does not need this API by default. So the check consistently returns a failure.
Crashlytics does not have any reliable way at the moment to check if the Crashlytics integration is successfully enabled for the project. As that part is being worked on, this hack is mainly to skip the API enablement check for just Crashlytics.
Cons for now is that we will always show the Crashlytics tools/prompts. But, hoping to fix this asap.
Summary of Changes
Hello @visumickey, I'm Gemini Code Assist[^1]! 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 implements a temporary measure to bypass the server enablement check for specific features, starting with Crashlytics. By adding features to a new featureSkipServerCheck list, the system will now consider them active without performing the usual server-side verification. This change is explicitly noted as a short-term workaround until a more robust public API for integration verification becomes available.
Highlights
-
Feature Skip List: Introduced a new constant,
featureSkipServerCheck, which is an array designed to hold names of features for which the server enablement check should be bypassed. -
Crashlytics Bypass: Added 'crashlytics' to the
featureSkipServerChecklist, ensuring that Crashlytics will now skip the server enablement check. -
Conditional Feature Activation: Modified the
checkFeatureActivefunction to immediately returntrueif the requested feature is found within thefeatureSkipServerChecklist, effectively marking it as active without further server-side verification. -
Temporary Solution: Included a
TODOcomment indicating that this change is a short-term hack, intended to be replaced by a public API for verifying integration.
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 :thumbsup: and :thumbsdown: 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.
[^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.