add MCP tool to get functions log tool

[taeold]

Includes small refactor in the existing API to fetch logs from Cloud Logging to support pagination.

[gemini-code-assist]

Summary of Changes

Hello @taeold, 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 significantly enhances the log retrieval capabilities within the Managed Control Plane by introducing a dedicated tool for Cloud Functions. It enables users to query and analyze function logs with greater flexibility through advanced filtering, sorting, and pagination. The underlying Cloud Logging API integration was updated to support these features, ensuring a robust and scalable solution for log management.

Highlights

• New MCP Tool for Cloud Functions Logs: Introduced a new Managed Control Plane (MCP) tool, get_logs, specifically designed for retrieving log entries from Cloud Functions. This tool provides advanced filtering, sorting, and pagination capabilities for function logs.
• Cloud Logging API Refactor for Pagination: The core cloudlogging.listEntries API has been refactored to support pagination. It now returns an object containing both the log entries and a nextPageToken, allowing for efficient retrieval of large log datasets.
• Enhanced Log Formatting and Error Handling: New utility files (formatter.ts and errors.ts) were added to provide structured formatting for log entries, including summarization, message truncation, and stack trace extraction. Additionally, improved error messages for Cloud Logging API failures are now provided, offering actionable advice for common issues like permissions or API enablement.
• Integration with Existing Log Commands: Existing commands that utilize the cloudlogging.listEntries API, such as functions:log and fetchServiceLogs for Cloud Run, have been updated to correctly handle the new paginated response format.

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 new MCP tool for retrieving Cloud Functions logs and refactors the Cloud Logging API client to support pagination. The changes are well-structured, with new functionality being properly typed, validated, and tested. The refactoring for pagination is applied consistently across all call sites. I have a couple of suggestions to simplify the implementation of the new get_logs tool by removing some redundant validation logic, which will improve maintainability.

[taeold]

/gemini review

[gemini-code-assist]

Code Review

This pull request introduces a new MCP tool for fetching Cloud Functions logs and refactors the listEntries API to support pagination. The changes are well-organized, adding new tools, formatters, and error handlers for the functions feature. The refactoring of listEntries is consistently applied throughout the codebase. I've identified a couple of areas in the new log formatting logic where payload extraction could be more robust to handle all possible data types correctly. My specific comments include suggestions to address these points.

[joehan]

Pretty much LGTM with minor fixes. Can you also throw up a screenshot/video of Gemini using this tool as a sanity check?