feat: forward ACP prompt content to Muse - #3
Merged
Merged
Conversation
This was referenced Sep 1, 2026
puncsky
marked this pull request as ready for review
September 12, 2026 08:44
This was referenced Sep 12, 2026
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
ACP images now reach both backends: ordered inline MSP image parts for the default SDK, and private temporary files for legacy exec. PNG, JPEG, GIF and WebP are supported; malformed base64, audio and embedded resources fail before execution. Exec requires accompanying text or a resource link.
Updated against the SDK migration while retaining current resource-link encoding, cancellation, model selection and host checks. Turn admission remains reserved through staging and cleanup.
Validation: 166 contract tests, lint/format/build, packed-install smoke, and real Muse loopback suites. Real-host image coverage asserts that the provider receives the image bytes and user prompt. Paid-provider vision acceptance remains opt-in.