[ISSUE #2069]💫Optimize auto approve pull requests github action #2070
Conversation
WalkthroughThe pull request modifies the GitHub Actions workflow for auto-approving pull requests by reducing the maximum number of retries from 20 to 15 when polling for required status checks. This change subtly adjusts the workflow's retry mechanism while maintaining the core logic of the auto-approval process. Changes
Assessment against linked issues
Possibly related PRs
Suggested labels
Suggested reviewers
Poem
Thank you for using CodeRabbit. We offer it for free to the OSS community and would appreciate your support in helping us grow. If you find it useful, would you consider giving us a shout-out on your favorite social media? 🪧 TipsChatThere are 3 ways to chat with CodeRabbit:
Note: Be mindful of the bot's finite context window. It's strongly recommended to break down tasks such as reading entire modules into smaller chunks. For a focused discussion, use review comments to chat about specific files and their changes, instead of using the PR comments. CodeRabbit Commands (Invoked using PR comments)
Other keywords and placeholders
Documentation and Community
|
|
🔊@flydream-ylgw 🚀Thanks for your contribution🎉！ 💡CodeRabbit(AI) will review your code first🔥！ Note 🚨The code review suggestions from CodeRabbit are to be used as a reference only, and the PR submitter can decide whether to make changes based on their own judgment. Ultimately, the project management personnel will conduct the final code review💥. |
rocketmq-rust-bot
added
AI review first
rocketmq-rust-bot
requested review from
rocketmq-rust-bot,
SpaceXCN and
TeslaRustor
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 0
🧹 Nitpick comments (2)
.github/workflows/auto_approve_pull_requests.yml (2)
Line range hint
84-92: Consider adding retry count to workflow outputs.To help monitor the impact of this change, consider adding the retry count as a workflow output. This would help track if PRs are timing out more frequently with the reduced retry limit.
const maxRetries = 15; const retryInterval = 30 * 1000; // 30 seconds +let actualRetries = 0; for (let i = 0; i < maxRetries; i++) { const allChecksPassed = await checkRequiredStatusChecks(); if (allChecksPassed) { + core.setOutput('retries_used', actualRetries); return true; } + actualRetries = i + 1; console.log(`Retrying in ${retryInterval / 1000} seconds... (${i + 1}/${maxRetries})`); await new Promise(resolve => setTimeout(resolve, retryInterval)); } +core.setOutput('retries_used', actualRetries);
Line range hint
1-92: Document the timeout configuration in workflow comments.Consider adding documentation in the workflow file explaining:
- The initial delay (300s)
- The retry interval (30s)
- The maximum retries (15)
- The total maximum wait time (750s)
Add this documentation at the top of the workflow:
name: Auto Approve Pull Requests + +# Timeout Configuration: +# - Initial delay: 300 seconds +# - Retry interval: 30 seconds +# - Maximum retries: 15 +# - Maximum total wait time: 750 seconds (12.5 minutes) on: pull_request_target:
📜 Review details
Configuration used: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (1)
.github/workflows/auto_approve_pull_requests.yml(1 hunks)
🔇 Additional comments (1)
.github/workflows/auto_approve_pull_requests.yml (1)
84-84: Please justify the reduction in retry attempts.The change reduces the maximum retry attempts from 20 to 15, effectively reducing the total wait time from 15 minutes to 12.5 minutes (including the initial 300s delay). This could potentially impact pull requests with longer-running checks.
Could you please:
- Provide data supporting this optimization
- Confirm that all required checks typically complete within the new timeout window
Run this script to analyze historical check completion times:
✅ Verification successful
Reducing maxRetries is safe based on historical check completion times
Based on the analysis of historical check completion times:
- The longest-running check is "auto-approve" with max duration of ~5.08 minutes
- All build checks complete within 3.6 minutes
- Test checks complete within 2.3 minutes
- Other checks complete within seconds
The new timeout of 12.5 minutes (750s = 300s initial delay + 15 retries * 30s) provides more than enough buffer:
- It's about 2.5x longer than the slowest observed check duration
- Provides ~7.4 minutes of buffer after the longest recorded check
🏁 Scripts executed
The following scripts were executed for the analysis:
Script:
#!/bin/bash # Description: Analyze the duration of status checks in recent PRs gh api graphql -f query=' query($owner: String!, $name: String!) { repository(owner: $owner, name: $name) { pullRequests(last: 50, states: [OPEN, MERGED]) { nodes { number commits(last: 1) { nodes { commit { statusCheckRollup { state contexts(last: 100) { nodes { ... on StatusContext { context state } ... on CheckRun { name completedAt startedAt } } } } } } } } } } }' -F owner="$(dirname "$(git remote get-url origin)" | xargs basename)" -F name="$(basename -s .git "$(git remote get-url origin)")" | jq -r ' .data.repository.pullRequests.nodes[] | select(.commits.nodes[0].commit.statusCheckRollup != null) | .number as $pr | .commits.nodes[0].commit.statusCheckRollup.contexts.nodes[] | select(.completedAt != null and .startedAt != null) | { pr: $pr, check: .name, duration: (((.completedAt | fromdateiso8601) - (.startedAt | fromdateiso8601)) / 60) } ' | jq -s 'group_by(.check) | map({ check: .[0].check, avg_duration: (map(.duration) | add / length), max_duration: (map(.duration) | max) })'Length of output: 3578
Codecov ReportAll modified and coverable lines are covered by tests ✅
Additional details and impacted files@@ Coverage Diff @@
## main #2070 +/- ##
=======================================
Coverage 28.44% 28.44%
=======================================
Files 489 489
Lines 69312 69312
=======================================
Hits 19713 19713
Misses 49599 49599 ☔ View full report in Codecov by Sentry. |
Which Issue(s) This PR Fixes(Closes)
Fixes #2069
Brief Description
How Did You Test This Change?
Summary by CodeRabbit