feat: media and image support#13
Draft
dodaa08 wants to merge 1 commit into
Draft
Conversation
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Media & Image Support
Attachment classification — extracts and categorizes attached files (image, audio, video, document, or unknown) from Rocket.Chat messages, handling both uploaded files and URL-based attachments
File download materialization — downloads private/local-hosted attachments (blocked by SSRF otherwise) to a local temp directory before passing them to the agent, so image analysis works without external URLs
File upload to Rocket.Chat — sends files back from the agent to Rocket.Chat rooms with thread support
Agent media context — private URLs are injected as
MediaPath(local file), public URLs passthrough asMediaUrl, with MIME type info so the agent knows what it's looking atAttachment-aware message handling — messages with only attachments and no text are no longer skipped; outbound replies with files use the upload path instead of plain text
Config — added vision-capable models (Llama 3.2 Vision, Phi-4 Multimodal) with
input: ["text", "image"]and animageModelagent default