Improve GitHub issue deduplication reliability by introducing a stage… (#11769)

…d two-pass Codex search strategy with deterministic fallback behavior,
and remove an obsolete prompt file that was no longer used.

### Changes
- Updated `workflows/issue-deduplicator.yml`:
- Added richer issue input fields (`state`, `updatedAt`, `labels`) for
model context.
  - Added two candidate pools:
    - `codex-existing-issues-all.json` (`--state all`)
    - `codex-existing-issues-open.json` (`--state open`)
- Added body truncation during JSON preparation to reduce prompt noise.
  - Added **Pass 1** Codex run over all issues.
  - Added normalization/validation step for Pass 1 output:
    - tolerant JSON parsing
    - self-issue filtering
    - deduplication
    - cap to 5 results
- Added **Pass 2 fallback** Codex run over open issues only, triggered
only when Pass 1 has no usable matches.
- Added normalization/validation step for Pass 2 output (same
filtering/dedup/cap behavior).
  - Added final deterministic selector:
    - prefer pass 2 if it finds matches
    - otherwise use pass 1
    - otherwise return no matches
  - Added observability logs:
    - pool sizes
    - per-pass parse/match status
    - final pass selected and final duplicate count
  - Kept public issue-comment format unchanged.
- Added comment documenting that prompt text now lives inline in
workflow.

- Deleted obsolete file:
  - `/prompts/issue-deduplicator.txt`

### Behavior Impact
- Better duplicate recall when broad search fails by retrying against
active issues only.
- More deterministic/noise-resistant output handling.
- No change to workflow trigger conditions, permissions, or issue
comment structure.
This commit is contained in:
Eric Traut
2026-02-13 12:01:07 -08:00
committed by GitHub
Unverified
parent e71760fc64
commit ffef5ce5de
2 changed files with 232 additions and 34 deletions
-18
View File
@@ -1,18 +0,0 @@
You are an assistant that triages new GitHub issues by identifying potential duplicates.
You will receive the following JSON files located in the current working directory:
- `codex-current-issue.json`: JSON object describing the newly created issue (fields: number, title, body).
- `codex-existing-issues.json`: JSON array of recent issues (each element includes number, title, body, createdAt).
Instructions:
- Load both files as JSON and review their contents carefully. The codex-existing-issues.json file is large, ensure you explore all of it.
- Compare the current issue against the existing issues to find up to five that appear to describe the same underlying problem or request.
- Only consider an issue a potential duplicate if there is a clear overlap in symptoms, feature requests, reproduction steps, or error messages.
- Prioritize newer issues when similarity is comparable.
- Ignore pull requests and issues whose similarity is tenuous.
- When unsure, prefer returning fewer matches.
Output requirements:
- Respond with a JSON array of issue numbers (integers), ordered from most likely duplicate to least.
- Include at most five numbers.
- If you find no plausible duplicates, respond with `[]`.