Implement retry limits to prevent ingestion pipeline blockage#161
Draft
Implement retry limits to prevent ingestion pipeline blockage#161
Conversation
|
The latest updates on your projects. Learn more about Vercel for GitHub. 1 Skipped Deployment
|
Co-authored-by: vbuch <5102057+vbuch@users.noreply.github.com>
Co-authored-by: vbuch <5102057+vbuch@users.noreply.github.com>
Copilot
AI
changed the title
[WIP] Fix blockable ingestion by limiting message retry attempts
Implement retry limits to prevent ingestion pipeline blockage
Feb 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Sequential ingestion gets stuck indefinitely on a single bad message, blocking all subsequent sources from processing.
Changes
Schema
retryCount?: numbertoInternalMessageSchemato track failed ingestion attemptsIngestion logic (
from-sources.ts)MAX_RETRY_ATTEMPTS = 3- sources exceeding this limit are skippedgetAlreadyIngestedSet()now returns{ alreadyIngestedIds, maxRetriesReachedIds }for filteringincrementRetryCount()updates Firestore on actual failures (excludes boundary/filter outcomes)maxRetriesReachedto summary loggingExample flow
Configuration
shared/from lint-staged (schema-only package, no eslint config needed)Original prompt
✨ Let Copilot coding agent set things up for you — coding agent works faster and does higher quality work when set up for your repo.