[Feat] Support audio requests across chat providers - #1173
Merged
Conversation
Contributor
|
No new code issues found. See task
Reviewed f2f73c2 |
Contributor
Author
|
Addressed the Teams file-download wrapper feedback in |
mrubens
marked this pull request as ready for review
August 8, 2026 03:46
mrubens
requested review from
brunobergher,
daniel-lxs and
mrubens
as code owners
August 8, 2026 03:46
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What changed
Added inbound audio and voice-note transcription for Telegram, Discord, and Teams. Each provider now recognizes audio-only task entries and follow-ups, downloads media through its authenticated bounded transport, and appends the shared transcript or actionable warning to the task prompt.
The shared transcription layer normalizes provider MIME metadata and owns consistent transcript, unsupported-model, oversized-media, and failure messages. Extension inference is limited to absent or generic MIME metadata so explicitly typed video and other non-audio attachments never enter audio transcription. Teams file-download wrappers use their nested content type, filename, or file type so uploaded audio is still recognized correctly. Telegram and Teams attachment downloads also enforce byte limits while streaming rather than buffering an unbounded response.
Why this change was made
Audio requests worked in Slack but were ignored or reduced to unusable attachment placeholders in the other chat providers. This makes voice-driven task entry consistent across supported communication surfaces without exposing provider credentials or signed attachment URLs to agents.
Impact
Users can start tasks and send active follow-ups with Telegram voice/audio messages, Discord audio attachments, and Teams audio attachments, including normal Teams file uploads. Unsupported models, media above 20 MiB, unsupported formats, and download failures remain actionable text instead of producing an empty request, while video uploads retain their explicit media classification.