[product-manager-impersonator] Manual persona overrides in trigger workflow

Start with gh-agent-workflows/product-manager-impersonator/example.yml#L2-L16 and compare its dispatch setup with .github/workflows/gh-aw-product-manager-impersonator.lock.yml#L72-L112. Check the existing input descriptions in gh-agent-workflows/product-manager-impersonator/README.md#L30-L37. Done means manual runs expose persona, idea-size, and title-prefix overrides while scheduled runs retain their defaults, with a README example.

Feature Idea

Summary: Add workflow_dispatch inputs to the Product Manager Impersonator trigger template so operators can override persona, idea-size, and title-prefix at run time without editing YAML.

Why a Customer Would Want This

Teams running this workflow often want ad-hoc idea generation from different perspectives (for example, SRE vs. security) or a one-off medium idea run. Today, the shipped trigger template supports manual dispatch but exposes no form inputs, so users must change the workflow file and open a PR just to tune one run.

Rough Implementation Sketch

• Add workflow_dispatch.inputs for persona, idea-size, and title-prefix in gh-agent-workflows/product-manager-impersonator/example.yml.
• Pass those values into jobs.run.with so manual runs can override defaults while scheduled runs remain unchanged.
• Keep defaults aligned with the reusable workflow contract ("", "small", and "[product-manager-impersonator]").
• Update gh-agent-workflows/product-manager-impersonator/README.md with a manual-run example using dispatch-time overrides.

Why It Won't Be That Hard

The reusable workflow already supports these inputs; this is mostly wiring and docs. No runtime engine changes are needed, and the scope is a single trigger template plus its README.

Evidence

• gh-agent-workflows/product-manager-impersonator/example.yml#L2-L16 defines workflow_dispatch but no dispatch inputs and no with: passthrough.
• gh-agent-workflows/product-manager-impersonator/README.md#L30-L37 documents persona, idea-size, and title-prefix as supported inputs.
• .github/workflows/gh-aw-product-manager-impersonator.lock.yml#L72-L112 already declares those inputs in the reusable workflow.
• Open-issue duplicate checks found no matching request:
  • repo:elastic/ai-github-actions is:issue is:open "product-manager-impersonator" "workflow_dispatch" persona → 0 results
  • repo:elastic/ai-github-actions is:issue is:open "persona" "idea-size" "product-manager-impersonator" → 0 results
  • repo:elastic/ai-github-actions is:issue in:title "[product-manager-impersonator]" "persona" → 0 results
• /tmp/previous-findings.json contains prior PM ideas (run names, quick-setup flags, scaffold generator, etc.) but no dispatch-time persona override proposal.

[!NOTE]

🔒 Integrity filter blocked 33 items

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

• #1175 list_pull_requests: 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".
• #1175 search_pull_requests: has lower integrity than agent requires. The agent cannot read data with integrity below "approved".
• #1128 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".
• #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".
• #235 search_issues: has lower integrity than agent requires. The agent cannot read data with integrity below "approved".
• #139 search_issues: has lower integrity than agent requires. The agent cannot read data with integrity below "approved".
• #1025 search_issues: has lower integrity than agent requires. The agent cannot read data with integrity below "approved".
• #336 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".
• #354 search_issues: has lower integrity than agent requires. The agent cannot read data with integrity below "approved".
• #321 search_issues: has lower integrity than agent requires. The agent cannot read data with integrity below "approved".
• #248 search_issues: has lower integrity than agent requires. The agent cannot read data with integrity below "approved".
• elastic/ai-github-actions#1067 list_issues: has lower integrity than agent requires. The agent cannot read data with integrity below "approved".
• ... and 17 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.