Skip to content

Reduce duplicate issue creation between DeepReport and Code Quality task-mining workflows #47998

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
pelikhan merged 2 commits into from
Jul 25, 2026
+24 −10
Merged

Reduce duplicate issue creation between DeepReport and Code Quality task-mining workflows #47998

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
fd112bb
Initial plan
Copilot Jul 25, 2026
62543c3
Add duplicate guards to DeepReport and task-miner issue filing
Copilot Jul 25, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 5 additions & 5 deletions .github/workflows/deep-report.lock.yml
View file
Open in desktop

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

9 changes: 9 additions & 0 deletions .github/workflows/deep-report.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -59,6 +59,7 @@ safe-outputs:
create-issue:
expires: 2d
title-prefix: "[deep-report] "
deduplicate-by-title: 28
labels: [automation, improvement, quick-win, cookie]
max: 7
group: true
Expand Down Expand Up @@ -244,6 +245,14 @@ For each task, **CREATE A GITHUB ISSUE** using the safe-outputs create-issue cap

**Maximum: 7 issues.** Choose the most impactful tasks.

**Dedup gate (required before every create-issue call):**
1. Search open issues for similar work using title keywords, component/file names, and key terms from the candidate task.
2. Treat a candidate as duplicate when both are true:
- Title is exact/near match (wording differences allowed), or same component + same fix intent.
- Scope overlaps materially (same root cause or same target files/components).
3. If duplicate is found, do **not** create a new issue. Prefer the existing canonical issue and cite it in the report task list.
4. Keep creating unique tasks until you either produce 7 non-duplicate issues or run out of high-value tasks.

#### Report Structure

{{#if experiments.output_format == 'executive_brief'}}
Expand Down
10 changes: 5 additions & 5 deletions .github/workflows/discussion-task-miner.lock.yml
View file
Open in desktop

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

5 changes: 5 additions & 0 deletions .github/workflows/discussion-task-miner.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -28,6 +28,7 @@ safe-outputs:
create-issue:
expires: 1d
group: true
deduplicate-by-title: 28
labels:
- code-quality
- automation
Expand Down Expand Up @@ -175,6 +176,10 @@ From all identified tasks, select the **top 5 highest-value tasks** based on:
- Check processed-discussions.json to avoid re-extracting from same discussion
- Check extracted-tasks.json to avoid creating duplicate issues
- Search existing GitHub issues to ensure task isn't already tracked
- Before every create-issue call, run a title/topic similarity check against open issues:
- Compare candidate title against open issue titles for near matches.
- Compare component/file paths and fix intent to detect same-topic overlaps even when wording differs.
- If an open issue already covers the same fix topic, skip creating a duplicate and reference the canonical issue in your run summary.

### Step 5: Create GitHub Issues

Expand Down