Skip to content

[product-manager-impersonator] Configurable previous-findings fetch depth #1086

Description

@github-actions

Feature Idea

Summary: Add a previous-findings-limit input to scheduled workflows so maintainers can increase dedupe history depth beyond the current hardcoded 100 issues.

Why a Customer Would Want This

Teams running many scheduled detectors over long periods want low-noise issue filing. With a fixed 100-item history window, older findings can fall out of dedupe scope and be re-filed, creating avoidable operational noise.

Rough Implementation Sketch

  • Add previous-findings-limit (default 100) to .github/workflows/gh-aw-scheduled-audit.md and .github/workflows/gh-aw-scheduled-fix.md workflow_call inputs.
  • Wire that input into the gh issue list --limit ... step that writes /tmp/previous-findings.json.
  • Mirror the same input/usage in .github/workflows/gh-aw-fragments/previous-findings.md guidance.
  • Document when to raise this value in gh-agent-workflows/scheduled-audit/README.md and gh-agent-workflows/scheduled-fix/README.md.

Why It Won't Be That Hard

The change is small and localized: existing dedupe plumbing already exists in scheduled workflows and fragment guidance, and this only parameterizes a hardcoded limit plus docs.

Evidence

  • .github/workflows/gh-aw-scheduled-audit.md lines 86-99: previous findings query is hardcoded to --limit 100.
  • .github/workflows/gh-aw-scheduled-fix.md lines 88-100: same hardcoded --limit 100 pattern.
  • .github/workflows/gh-aw-fragments/previous-findings.md lines 3-15: shared previous-findings fetch also hardcoded to --limit 100.
  • gh-agent-workflows/README.md lines 67-80: many continuous-improvement scheduled workflows are commonly installed, increasing dedupe-history needs over time.
  • Related (not duplicate): open issue #987 proposes fail-closed behavior when previous-findings fetch fails; it does not address configurable history depth.

Note

🔒 Integrity filter blocked 37 items

The following items were blocked because they don't meet the GitHub integrity level.

  • #937 search_pull_requests: has lower integrity than agent requires. The agent cannot read data with integrity below "approved".
  • #1067 search_issues: has lower integrity than agent requires. The agent cannot read data with integrity below "approved".
  • #359 search_issues: has lower integrity than agent requires. The agent cannot read data with integrity below "approved".
  • Mint Ephemeral Tokens #1067 list_issues: has lower integrity than agent requires. The agent cannot read data with integrity below "approved".
  • Issue Fixer can use Ephemeral Token #1025 list_issues: has lower integrity than agent requires. The agent cannot read data with integrity below "approved".
  • #704 search_issues: has lower integrity than agent requires. The agent cannot read data with integrity below "approved".
  • #694 search_issues: has lower integrity than agent requires. The agent cannot read data with integrity below "approved".
  • #684 search_issues: has lower integrity than agent requires. The agent cannot read data with integrity below "approved".
  • #875 search_issues: has lower integrity than agent requires. The agent cannot read data with integrity below "approved".
  • #676 search_issues: has lower integrity than agent requires. The agent cannot read data with integrity below "approved".
  • #140 search_issues: has lower integrity than agent requires. The agent cannot read data with integrity below "approved".
  • #478 search_issues: has lower integrity than agent requires. The agent cannot read data with integrity below "approved".
  • #444 search_issues: has lower integrity than agent requires. The agent cannot read data with integrity below "approved".
  • #437 search_issues: has lower integrity than agent requires. The agent cannot read data with integrity below "approved".
  • #245 search_issues: has lower integrity than agent requires. The agent cannot read data with integrity below "approved".
  • #505 search_issues: has lower integrity than agent requires. The agent cannot read data with integrity below "approved".
  • ... and 21 more items

To allow these resources, lower min-integrity in your GitHub frontmatter:

tools:
  github:
    min-integrity: approved  # merged | approved | unapproved | none

What is this? | From workflow: Trigger Product Manager Impersonator

Give us feedback! React with 🚀 if perfect, 👍 if helpful, 👎 if not.

Activity

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions