Add wtf_transcribe link for WTF transcription#131
Conversation
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
There was a problem hiding this comment.
Cursor Bugbot has reviewed your changes and found 1 potential issue.
Bugbot Free Tier Details
Your team is on the Bugbot Free tier. On this plan, Bugbot will review limited PRs each billing cycle for each member of your team.
To receive Bugbot reviews on all of your PRs, visit the Cursor dashboard to activate Pro and start your 14-day free trial.
Bugbot Autofix is OFF. To automatically fix reported issues with cloud agents, enable autofix in the Cursor dashboard.
Comment @cursor review or bugbot run to trigger another review on this PR
| # Send audio to vfun server | ||
| files = {"file": (filename, audio_content, mimetype)} | ||
| data = { | ||
| "diarize": str(opts.get("diarize", True)), |
There was a problem hiding this comment.
str(True) produces "True" not "true" for API
Medium Severity
Python's str(True) returns "True" (capital T), not "true". The diarize form field sent to the vfun server will be "True" instead of the expected lowercase "true". Note that the adjacent block field on line 284 correctly uses the lowercase string literal "true", making this inconsistency especially likely to cause issues. Most HTTP APIs parse boolean strings as lowercase, so diarization may silently fail to activate.


Note
Medium Risk
Adds a new link that fetches/decodes audio (including
file://and remote URLs) and sends it to an external transcription service, then persists derived analysis back to Redis; failures or misconfiguration could impact processing and introduces new outbound network/file access paths.Overview
Adds a new
wtf_transcribelink that scans vCon dialogs, extracts audio frombody(base64/base64url) orurl(includingfile:///HTTP), POSTs it to a configurable vfun/transcribeendpoint (optional bearerapi-key,diarize,timeout), and writes back a generated WTF-compliantwtf_transcriptionanalysis entry per dialog.The link skips non-
recordingdialogs, dialogs belowmin-duration, and dialogs already containing awtf_transcription, and includes documentation for configuration, chain usage, and expected output format.Written by Cursor Bugbot for commit 950bc3c. Configure here.