--- /dev/null
+name: AI review (issues)
+
+on:
+ issues:
+ types: [opened]
+
+jobs:
+ find-duplicates:
+ if: github.event.action == 'opened'
+ runs-on: [self-hosted, opencode]
+
+ permissions:
+ contents: read
+ issues: write
+
+ steps:
+ - name: Checkout repository
+ uses: actions/checkout@v6
+ with:
+ fetch-depth: 1
+
+ - name: Find duplicates
+ env:
+ GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+ OPENCODE_PERMISSION: |
+ {
+ "bash": {
+ "*": "deny",
+ "gh issue*": "allow"
+ },
+ "webfetch": "deny"
+ }
+ run: |
+ opencode run -m llama.cpp-dgx/gpt-oss-120b-hf-low "A new issue has been created:
+
+ Issue number: ${{ github.event.issue.number }}
+
+ Lookup this issue with gh issue view ${{ github.event.issue.number }}.
+
+ Perform the following task and then post a SINGLE comment (if needed).
+
+ ---
+
+ TASK : DUPLICATE CHECK
+
+ Search through existing issues (excluding #${{ github.event.issue.number }}) to find potential duplicates.
+ Consider:
+ 1. Similar titles or descriptions
+ 2. Same error messages or symptoms
+ 3. Related functionality or components
+ 4. Similar feature requests
+
+ ---
+
+ POSTING YOUR COMMENT:
+
+ Based on your findings, post a SINGLE comment on issue #${{ github.event.issue.number }}. Build the comment as follows:
+
+ If no duplicates were found, do NOT comment at all.
+
+ If duplicates were found, include a section about potential duplicates with links using the following format:
+
+ [comment]
+ This issue might be a duplicate of:
+ - #[issue_number]: [brief description of similarity]
+
+ _This comment was auto-generated locally using **$GA_ENGINE** on **$GA_MACHINE**_
+ [/comment]
+
+ Remember: Do not include the comment tags in your actual comment. Post at most ONE comment combining all findings. If everything is fine, post nothing.
+ "