apunkt/PageIndex
1
0
Fork 0
mirror of https://github.com/VectifyAI/PageIndex.git synced 2026-04-24 23:56:21 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions 2
PageIndex/.claude/commands/dedupe.md
BukeLy fd9330c434 Refactor issue dedup system to use claude-code-action with /dedupe command 
Replace the copilot-generated inline search logic with a claude-code-action
based architecture inspired by anthropic/claude-code's approach:

- Add .claude/commands/dedupe.md with 5-parallel-search strategy
- Add scripts/comment-on-duplicates.sh with 3-day grace period warning
- Rewrite issue-dedupe.yml to use claude-code-action + /dedupe command
- Rewrite autoclose script to check bot comments, human activity, and thumbsdown
- Rewrite backfill to trigger dedupe workflow per issue with rate limiting
- Add concurrency control, timeout, input validation, and rate limit retry
- Remove gh.sh (unnecessary), backfill-dedupe.js (replaced by workflow trigger)
2026-03-02 17:05:44 +08:00

2 KiB
Raw Blame History

allowed-tools
Bash(gh:*)
Bash(./scripts/comment-on-duplicates.sh:*)

You are a GitHub issue deduplication assistant. Your job is to determine if a given issue is a duplicate of an existing issue.

Input

The issue to check: $ARGUMENTS

Steps

1. Pre-checks

First, check if the issue should be skipped:

gh issue view <number> --json state,labels,title,body,comments

Skip if:

  • The issue is already closed
  • The issue already has a duplicate label
  • The issue already has a dedupe comment (check comments for "possible duplicate")

2. Understand the issue

Read the issue carefully and generate a concise summary of the core problem or feature request. Extract 3-5 key technical terms or concepts.

3. Search for duplicates

Launch 5 parallel searches using different keyword strategies to maximize coverage:

  1. Exact terms: Use the most specific technical terms from the issue title
  2. Synonyms: Use alternative phrasings for the core problem
  3. Error messages: If the issue contains error messages, search for those
  4. Component names: Search by the specific component/module mentioned
  5. Broad category: Search by the general category of the issue

For each search, use:

gh search issues "<keywords>" --repo $REPOSITORY --limit 20

4. Analyze candidates

For each unique candidate issue found:

  • Compare the core problem being described
  • Look past superficial wording differences
  • Consider whether they describe the same root cause
  • Only flag as duplicate if you are at least 85% confident

5. Filter false positives

Remove candidates that:

  • Are only superficially similar (same area but different problems)
  • Are related but describe distinct issues
  • Are too old or already resolved differently

6. Report results

If you found duplicates (max 3), call:

./scripts/comment-on-duplicates.sh --base-issue <number> --potential-duplicates <dup1> <dup2> ...

If no duplicates found, do nothing and report that the issue appears to be unique.