Repository navigation
Conversation
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
|
Important Draft PR not reviewedDraft PRs are not automatically reviewed by default.
To automatically review draft PRs, update your CodeRabbit configuration: reviews:
auto_review:
drafts: true
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
Owner
Author
This branch was successfully deployed
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Stacked on Persist and restore workspace-scoped ACP sessions (#136). Adds native PNG/JPEG/WebP prompt images when the selected model advertises vision, plus embedded text and binary context. Binary inputs are validated and stored by content hash for future turns; images use Penguin's existing image_paths path. Embedded text is labeled untrusted context, binaries remain inert references, and no remote resource is automatically fetched.
Limits: 10 MiB per binary, 20 MiB aggregate attachments, 40 million image pixels. Invalid base64, mismatched media type, invalid image data and unsafe asset destinations fail before model execution. Attachments remain in native session storage after closing a session for continuation. This does not add audio or media conversion.
Validation: 35 aggregate ACP tests pass, including image data preservation, native model input, invalid/oversize inputs, embedded text/binary, and subprocess wire embedded context. Scoped Ruff and diff checks pass. Live provider/editor still not claimed.