Enhance Slack integration and database backup workflows#21
Merged
Conversation
… database backups
|
ℹ️ Recent review info⚙️ Run configurationConfiguration used: defaults Review profile: CHILL Plan: Pro Run ID: 📒 Files selected for processing (2)
✅ Files skipped from review due to trivial changes (1)
🚧 Files skipped from review as they are similar to previous changes (1)
📝 WalkthroughWalkthroughAdds startup Slack-status enqueueing at process boot and converts the GitHub Actions DB backup to a staging/production matrix that uploads environment-scoped dumps to gs://insights-db-backups/paperscout//; documentation and tests updated accordingly. ChangesStartup Status Notification
Database Backup Parallelization
Sequence Diagram(s)sequenceDiagram
participant Main as __main__
participant MQ as MessageQueue
participant Scout as scout
participant Slack as NOTIFICATION_CHANNEL
Main->>Scout: enqueue_startup_status(mq, state, paper_count_fn)
Scout->>Scout: format_status_message(...)
Scout->>MQ: enqueue(message)
MQ->>Slack: post formatted status
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~20 minutes Possibly related PRs
Suggested labels
Poem
🚥 Pre-merge checks | ✅ 4 | ❌ 1❌ Failed checks (1 warning)
✅ Passed checks (4 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches🧪 Generate unit tests (beta)
Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 2
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In @.github/workflows/db-backup.yml:
- Around line 27-33: The STAMP/DUMP/DEST naming is too coarse and can collide;
change how STAMP, DUMP and DEST are constructed so they include the environment
(matrix.environment) plus a unique run identifier (e.g. GITHUB_RUN_ID or
GITHUB_RUN_NUMBER) and/or a random suffix or use a safe temporary filename
generator for DUMP (instead of fixed /tmp/paperscout-${STAMP}.dump). Update the
DUMP variable (used by sudo -u postgres pg_dump) to use that unique temp name
and update DEST (gs://.../paperscout/${{ matrix.environment }}/...) to include
the same unique run id so uploaded object keys are unique per run and per
environment.
In `@deploy/SERVER_SETUP.md`:
- Around line 240-243: The pg_restore invocation shown for restoring paperscout
omits the --no-owner flag; update the pg_restore command (the line containing
"pg_restore -U paperscout -h localhost -d paperscout -c /tmp/paperscout.dump")
to include --no-owner (i.e., add the --no-owner option alongside -c) so the
restore mirrors the earlier examples and avoids ownership-related failures.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: defaults
Review profile: CHILL
Plan: Pro
Run ID: de02fba6-fb94-4a0a-bb0b-5b320053720a
📒 Files selected for processing (9)
.github/workflows/db-backup.yml.gitignoreCHANGELOG.mdREADME.mddeploy/SERVER_SETUP.mddocs/onboarding.mdsrc/paperscout/__main__.pysrc/paperscout/scout.pytests/test_scout.py
… keys and improved restore instructions
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In @.github/workflows/db-backup.yml:
- Around line 26-34: The script may leave the temporary dump file if a command
fails because set -e skips the final rm; ensure cleanup always runs by
installing an EXIT trap immediately after defining DUMP that removes the file
(use a safe conditional that checks the DUMP variable exists before removing),
e.g. set the trap right after the DUMP assignment so any early failures invoke
the trap and remove the artifact; keep the existing rm -f "$DUMP" at the end
(harmless) and ensure the trap runs only once (or is idempotent).
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: defaults
Review profile: CHILL
Plan: Pro
Run ID: 4c8fa1ca-a950-420d-806d-eaf056e6ca64
📒 Files selected for processing (4)
.github/workflows/db-backup.ymlCHANGELOG.mdREADME.mddeploy/SERVER_SETUP.md
✅ Files skipped from review due to trivial changes (2)
- README.md
- deploy/SERVER_SETUP.md
…porary dump files on failure; update documentation for clarity on backup processes.
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
1 participant
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.
Summary by CodeRabbit
New Features
Documentation
Tests
Chores