Repository navigation
fix(migrations): read documents already waiting to be transcribed - #278
Merged
Merged
Conversation
Runs of documents and images queued before the read step existed still waited at transcribe for a speech model. An upgrade step rewrites what those runs have left to read the file, and reruns ones that failed at transcribe, so nobody has to rerun them by hand. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01R52DQopnWr6KKw8MiuQ7bi
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01R52DQopnWr6KKw8MiuQ7bi
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Requested by Adeel · project thread
Description
Before: after #265, documents and images queued before the upgrade still sat at "transcribe" waiting for a speech model, and ones that had failed there stayed failed, so they never reached analyze or the graph until someone reran them.
After: an upgrade step (
document-read-step) runs once on start. What those runs have left reads the file instead (transcribe becomes read, diarize is dropped), and a run that failed at transcribe is queued again unless a newer run of the same file is already queued. Audio and video runs are untouched.Motivation and Context
Follow-up to #265, so nobody has to rerun stuck documents by hand.
Types of changes
Checklist:
🤖 Generated with Claude Code
https://claude.ai/code/session_01R52DQopnWr6KKw8MiuQ7bi
Generated by Claude Code