Skip to content

Worktrunk is a CLI for Git worktree management, designed for parallel AI agent workflows

ci: change review-reviewers from nightly to hourly (#1291)

worktrunk-bot881813f87b52
diff --git a/.github/workflows/claude-nightly-review-reviewers.yaml b/.github/workflows/claude-hourly-review-reviewers.yaml
similarity index 70%
rename from .github/workflows/claude-nightly-review-reviewers.yaml
rename to .github/workflows/claude-hourly-review-reviewers.yaml
index dda5ecf4b..50f4dbb74 100644
--- a/.github/workflows/claude-nightly-review-reviewers.yaml
+++ b/.github/workflows/claude-hourly-review-reviewers.yaml
@@ -1,12 +1,12 @@
-name: claude-nightly-review-reviewers
+name: claude-hourly-review-reviewers
# Runner versions pinned; see ci.yaml header comment for rationale.
-# Nightly analysis of Claude CI session logs — identifies behavioral problems,
+# Hourly analysis of Claude CI session logs — identifies behavioral problems,
# skill gaps, and workflow issues across all Claude-powered CI runs.
on:
schedule:
- # Run at 5:47 AM UTC daily (off-peak minute, after nightly-benchmark at 4:17)
- - cron: '47 5 * * *'
+ # Run at :47 past every hour (off-peak minute)
+ - cron: '47 * * * *'
workflow_dispatch:
# Consistent with ci.yaml for cache compatibility
@@ -50,19 +50,19 @@ jobs:
actions: read
prompt: |
- You are running as a nightly job that reviews the behavior of all Claude-powered CI workflows from the past 24 hours. Your goal is to identify behavioral problems, skill gaps, and workflow issues — then create issues and/or PRs to fix them.
+ You are running as an hourly job that reviews the behavior of all Claude-powered CI workflows from the past hour. Your goal is to identify behavioral problems, skill gaps, and workflow issues — then create issues and/or PRs to fix them.
## Step 1: Find recent Claude CI runs
- Use `gh run list` to find all runs from Claude workflows in the past 24 hours:
+ Use `gh run list` to find all runs from Claude workflows in the past hour:
```
- for wf in claude-review claude-ci-fix claude-issue-triage claude-mention claude-renovate claude-nightly-review-reviewers claude-nightly-cleaner; do
- gh run list --workflow "${wf}.yaml" --created ">=$(date -d '24 hours ago' +%Y-%m-%dT%H:%M:%S)" --json databaseId,conclusion,createdAt --limit 50
+ for wf in claude-review claude-ci-fix claude-issue-triage claude-mention claude-renovate claude-hourly-review-reviewers claude-nightly-cleaner; do
+ gh run list --workflow "${wf}.yaml" --created ">=$(date -d '1 hour ago' +%Y-%m-%dT%H:%M:%S)" --json databaseId,conclusion,createdAt --limit 50
done
```
- If no Claude CI runs occurred in the past 24 hours, report "no runs to review" and exit.
+ If no Claude CI runs occurred in the past hour, report "no runs to review" and exit.
## Step 2: Download session logs
@@ -98,16 +98,27 @@ jobs:
This is the strongest signal — it shows what the reviewer actually missed, not just whether it followed process.
+ **Important**: Although you only look at runs from the past hour, always pull in the **full context** of the PR or issue when assessing a session. Read the complete PR description, all comments, all reviews, and all commits — not just the ones from the past hour. You need the full history to judge whether the bot's response was appropriate.
+
## Step 5: Identify problems
Compare each session against CLAUDE.md and project conventions. Flag anything where Claude's behavior diverged from the guidelines or produced a poor outcome. Include findings from the cross-check in Step 4.
- ## Step 6: Check for existing issues
+ ## Step 6: Check for existing issues and PRs (deduplication)
+
+ Because this job runs hourly, deduplication is critical. Before creating any new issue or PR, thoroughly check for existing ones that cover the same problem:
+
+ ```
+ gh issue list --state open --label claude-behavior --json number,title,body
+ gh issue list --state open --json number,title,body
+ gh pr list --state open --json number,title,headRefName,body
+ ```
+
+ For each finding, search issue titles AND bodies for related keywords. If an existing issue or PR already covers the same behavioral problem — even partially or with different wording — do NOT create a duplicate. Instead, add a comment to the existing issue with any new evidence or context from this run.
- Before creating any new issues or PRs, check for duplicates:
+ Also check recently closed issues (past 7 days) to avoid re-filing problems that were already addressed:
```
- gh issue list --state open --json number,title
- gh pr list --state open --json number,title,headRefName
+ gh issue list --state closed --label claude-behavior --json number,title,closedAt --limit 30
```
## Step 7: Report findings
@@ -119,7 +130,7 @@ jobs:
- Use `gh issue create`
2. **For actionable fixes** (skill edits, workflow tweaks, CLAUDE.md updates):
- - Create a branch: `git checkout -b nightly/review-${{ github.run_id }}`
+ - Create a branch: `git checkout -b hourly/review-${{ github.run_id }}`
- Make the changes
- Commit and push
- Create a PR referencing the issue
diff --git a/.github/workflows/claude-nightly-cleaner.yaml b/.github/workflows/claude-nightly-cleaner.yaml
index 4b89db762..9904f2478 100644
--- a/.github/workflows/claude-nightly-cleaner.yaml
+++ b/.github/workflows/claude-nightly-cleaner.yaml
@@ -6,7 +6,7 @@ name: claude-nightly-cleaner
# open issues that have been resolved by recent (or earlier unlinked) merges.
on:
schedule:
- # Run at 6:17 AM UTC daily (off-peak minute, 30 min after review-reviewers)
+ # Run at 6:17 AM UTC daily (off-peak minute)
- cron: '17 6 * * *'
workflow_dispatch: