Image Support
Images give an agent visual evidence that is difficult to express in text: a clipped panel, a design mockup, an error dialog, or the exact arrangement you want to reproduce. Include a short explanation of what the agent should notice and what outcome you want.
Add images to the next message
Click the attachment button near Send to open Choose Files, then select one or more images. You can also paste an image from the clipboard or drop files anywhere in the Agent Mode pane. Drop files to attach marks the drop target. Plain text and web links remain editor content rather than becoming file attachments. RepoPrompt prepares supported image input and shows attachments above the editor.
Review the attachment previews before sending. Remove an image with its attachment removal control if it belongs to another task or contains information you do not intend to share. Attachments are staged for the next turn; they are not sent merely because you select or paste them.
Attach files when the chat is idle. If the agent is working, wait for it to finish. Finish or cancel any pending submission or rewrite before changing attachments. If you switch sessions or workspaces, check the active tab and reattach the files if needed.
Image support varies by provider and model; see Providers & Models. Grok Build sessions do not support attachments.
Preview an image
Click an image thumbnail in the composer or transcript to open its preview and optionally reveal it in the Finder.
Saved images and privacy
A session’s attachment folder is capped at 200 MiB, with older retained files removed to make room and forks and handoffs make independently owned image copies. Images over 20 MiB are candidates for downscaling so keep originals elsewhere when long-term access or exact pixels matter. Successfully deleting a saved session removes its managed attachment folder.
Review images for credentials and secrets before attaching them!
Include other files when useful
The file picker also accepts files beyond images. Acceptance and delivery depend on the connection and file type; choosing a file does not make every provider able to read it. Keep the task text explicit about what each attachment contributes, and inspect any unsupported-file or size-limit message before resubmitting.
For a separate Oracle consultation, images, UTF-8 text files, and PDFs on supported routes can be supplied through Oracle attachments. Oracle has its own attachment validation and does not automatically receive everything attached to the coding session.
Explain how to use the image
A useful message identifies the relevant part and the requested change: “The Save button is clipped at the bottom of this screenshot. Fix the layout while keeping the form keyboard-accessible.” If you attach several images, describe their relationship, such as current behavior versus intended design.
Images can show text, code, and instructions that belong to the material being analyzed. State your task in the message and identify which visual details matter. For documentation work, explain whether a screenshot is the current interface or an example from an older build.
Images, selected files, and desktop interaction
An image attachment is visual input for the message's execution provider. It is separate from the repository file selection in Context Builder. Selecting source files helps the agent connect the visual issue to implementation, but attaching a screenshot does not select those source files automatically.
Re-prompt and automatic routing have narrower inputs: image attachments are not automatically forwarded as visual input to their draft-rewriting or decision requests. The execution provider receives the supported attachments with the submitted task. Review the image for private information before sending.
To let an eligible session interact with desktop applications rather than analyze a static image, see Computer Use.