feat(cli): add native drag-and-drop and Cmd+V clipboard image pasting

[pedrogoiania]

What does this PR do?

This PR brings visual multimodal parity to Gemini CLI by adding first-class terminal drag-and-drop and native Cmd+V / Ctrl+V clipboard image pasting inside standard terminal emulators.

This addresses the long-standing limitation discussed in closed/stale issues #15532 and #5316, making the workflow incredibly fast and polished.

Detailed Changes:

1. Background Clipboard Image Synchronizer:
   • Implemented a background observer loop inside InputPrompt.tsx that polls the clipboard for raw image buffers (e.g. screenshots).
   • When a new raw image is detected, it automatically saves it to the secure local project temporary directory (~/.gemini/tmp/gemini-cli/images/clipboard-xxx.png) and writes the workspace-relative path text (@.gemini-clipboard/clipboard-xxx.png ) back to the system clipboard.
   • This makes standard Cmd+V paste the file reference natively!
2. Workspace-Relative Path Resolution:
   • Updated parsePastedPaths in clipboardUtils.ts to accept an optional targetDir parameter.
   • If a dropped/pasted file path is inside the active workspace, it automatically resolves to a clean relative path (e.g., @src/image.png) instead of a long absolute path.
3. Pasting / Drop Status Toast:
   • Updated the text-buffer.ts input handler to pass the active workspace directory and emit a clean, non-intrusive status toast (e.g. Added logo.png to prompt context) when files are dropped or pasted.
4. Unit Tests:
   • Added robust tests inside clipboardUtils.test.ts verifying path resolution both inside and outside of the workspace directory.

Closes #27855

[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 enhances the Gemini CLI by introducing native drag-and-drop and clipboard image pasting capabilities. By implementing a background clipboard watcher and improving path resolution logic, the PR streamlines the workflow for adding local files and images to the prompt, providing a more polished and intuitive terminal experience.

Highlights

• Clipboard Image Synchronization: Implemented a background observer in InputPrompt.tsx that detects raw images in the clipboard, saves them to a temporary directory, and writes a workspace-relative path back to the clipboard for native Cmd+V/Ctrl+V support.
• Workspace-Relative Path Resolution: Updated parsePastedPaths to support target directory resolution, ensuring dropped or pasted file paths are converted to clean, workspace-relative references.
• User Feedback: Added non-intrusive status toasts in the text-buffer input handler to confirm when files are successfully dropped or pasted into the prompt context.

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 the 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 counterproductive. 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.

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. ↩

[github-actions]

📊 PR Size: size/L

• Lines changed: 260
• Additions: +222
• Deletions: -38
• Files changed: 6

[google-cla]

Thanks for your pull request! It looks like this may be your first contribution to a Google open source project. Before we can look at your pull request, you'll need to sign a Contributor License Agreement (CLA).

View this failed invocation of the CLA check for more information.

For the most up to date status, view the checks section at the bottom of the pull request.

[gemini-code-assist]

Code Review

This pull request introduces a background clipboard image watcher that automatically converts copied raw images into temporary files and writes their relative paths back to the clipboard. It also updates path pasting to resolve paths relatively within the target directory and adds toast notifications when files are added to the prompt context. Feedback on these changes highlights a critical command injection vulnerability in the Windows clipboard writing function, potential path traversal issues due to simple string prefix checks, and a bug where file paths containing spaces are incorrectly split when generating toast notifications.