feat: support native installed Claude CLI detection

[DragonFSKY]

Summary

Add automatic detection for Claude CLI installed via native methods that may not be in PATH:

• curl https://claude.ai/install.sh | bash → ~/.local/bin/claude
• brew install --cask claude-code → /opt/homebrew/bin/claude (Apple Silicon) or /usr/local/bin/claude (Intel)

When claude is not found in PATH, the script checks these paths in order and adds the first found to PATH.

Changes

• Added multi-path detection logic in check_claude_cli_integration() function
• Checks paths: ~/.local/bin, /opt/homebrew/bin, /usr/local/bin
• Informative log messages showing which path was found and added

Test plan

• [x] Tested with simulated native install scenario
• [x] Verified log messages display correctly
• [x] Verified subsequent claude commands work after PATH modification
• [x] Confirmed paths match official installation methods

References

• Homebrew cask info
• Issue #10970 confirms Homebrew creates /opt/homebrew/bin/claude

Closes #303

[gemini-code-assist[bot]]

Summary of Changes

Hello @DragonFSKY, 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 enhances the 'run-server.sh' script by implementing automatic detection for the Claude CLI when it's installed via its native method. This ensures that users who have installed Claude in the default '~/.local/bin' location will have the CLI correctly recognized and added to their session's PATH, even if '~/.local/bin' is not pre-configured in their environment, thereby improving usability and reducing setup friction.

Highlights

• Native Claude CLI Detection: The script now automatically detects the Claude CLI when installed via its native installer.
• Default Install Location: The native installer places the 'claude' executable at '~/.local/bin/claude', which is often not included in the system's default PATH.
• PATH Modification: If the Claude CLI is not found in the system's PATH, the script now checks for its presence in '~/.local/bin/claude' and, if found, adds '~/.local/bin' to the current session's PATH.

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.

[guidedways]

@codex review

[chatgpt-codex-connector[bot]]

Codex Review: Didn't find any major issues. Hooray!

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

• Open a pull request for review
• Mark a draft as ready
• Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".