PowerToys/.github/prompts/create-pr-summary.prompt.md at 961a65f4704b6e0c2cd5c7f928855877ee0c732b

mirror of https://github.com/microsoft/PowerToys.git synced 2026-04-09 04:37:30 +02:00

Files

Gordon Lam 961a65f470 Update VSCode task for streamline build + fix prompts syntax error (#44605 )

<!-- Enter a brief description/summary of your PR here. What does it
fix/what does it change/how was it tested (even manually, if necessary)?
-->
## Summary of the Pull Request
This pull request introduces several improvements and updates across the
repository, focusing on build tooling, prompt configuration for AI
agents, and documentation clarity. The most significant changes include
the addition of new VSCode build tasks, updates to prompt files to use a
newer AI model, enhancements to the build script for flexibility, and
refinements to documentation and style rules.

### Enabled scenario
* On any active files in VSCode, do "Ctrl + Shift + B" just build
correctly for you.
* The Run Task (no matter from Terminal or Ctrl + Shift + P), we can see
the build option:
<img width="1210" height="253" alt="image"
src="https://github.com/user-attachments/assets/09fbef16-55ce-42d5-a9ec-74111be83472"
/>

**Build tooling and automation:**

* Added a new `.vscode/tasks.json` file with configurable build tasks
for PowerToys, supporting quick and customizable builds with platform
and configuration selection.
* Enhanced `tools/build/build.ps1` to support an optional `-Path`
parameter for building projects in a specified directory, updated
parameter documentation, and improved logic to resolve the working
directory.
[[1]](diffhunk://#diff-7a444242b2a6d9c642341bd2ef45f51ba5698ad7827e5136e85eb483863967a7R14-R16)
[[2]](diffhunk://#diff-7a444242b2a6d9c642341bd2ef45f51ba5698ad7827e5136e85eb483863967a7R27-R30)
[[3]](diffhunk://#diff-7a444242b2a6d9c642341bd2ef45f51ba5698ad7827e5136e85eb483863967a7R51)
[[4]](diffhunk://#diff-7a444242b2a6d9c642341bd2ef45f51ba5698ad7827e5136e85eb483863967a7L81-R93)


**AI agent prompt configuration:**

* Updated all prompt files in `.github/prompts/` to use the
`GPT-5.1-Codex-Max` model instead of older models, and standardized the
agent field format.
[[1]](diffhunk://#diff-7a5c9b18594ff83fda2c191fd5a401ca01b74451e8949dc09e14eabee15de165L1-R2)
[[2]](diffhunk://#diff-f48674f7557a6c623bb48120c41b4546b20b32f741cc13d82076b0f4b2375d98L1-R2)
[[3]](diffhunk://#diff-a6831d9c98a26487c89c39532ec54d26f8987a8bdc88c5becb9368e9d7e589b9L1-R2)
[[4]](diffhunk://#diff-60e145ef3296b0cb4bec35363cc8afbfe0b6b7bd0c7785fe16a11d98e38c6f29L1-R2)
[[5]](diffhunk://#diff-6a7664740d6984e73a33254333a302a7e258c638a17134921c53967b4965a304L1-R3)
[[6]](diffhunk://#diff-7b246ee6421c503c22d7994406b822ede18d7d0c791b7667a55fcd50524fb0b0L1-R2)
* Improved clarity and consistency in the description and instructions
within the `review-issue.prompt.md` file.

**Documentation and style rules:**

* Updated `.github/copilot-instructions.md` to clarify that C++ and C#
style analyzers and formatters are now enforced from the `src/`
directory, not the repo root, and made the C++ formatting rule more
precise.

## PR Checklist
- [N/A] Closes: #xxx
- [N/A] **Tests:** Added/updated and all pass

## Validation Steps Performed
- Not run (config/docs/build-script changes only).

2026-01-08 15:41:51 +08:00

1.9 KiB

Raw Blame History

agent: 'agent' model: GPT-5.1-Codex-Max description: 'Generate a PowerToys-ready pull request description from the local diff.'

Goal: Produce a ready-to-paste PR title and description that follows PowerToys conventions by comparing the current branch against a user-selected target branch.

Repo guardrails:

Treat .github/pull_request_template.md as the single source of truth; load it at runtime instead of embedding hardcoded content in this prompt.
Preserve section order from the template but only surface checklist lines that are relevant for the detected changes, filling them with [x]/[ ] as appropriate.
Cite touched paths with inline backticks, matching the guidance in .github/copilot-instructions.md.
Call out test coverage explicitly: list automated tests run (unit/UI) or state why they are not applicable.

Workflow:

Determine the target branch from user context; default to main when no branch is supplied.
Run git status --short once to surface uncommitted files that may influence the summary.
Run git diff <target-branch>...HEAD a single time to review the detailed changes. Only when confidence stays low dig deeper with focused calls such as git diff <target-branch>...HEAD -- <path>.
From the diff, capture impacted areas, key file changes, behavioral risks, migrations, and noteworthy edge cases.
Confirm validation: list tests executed with results or state why tests were skipped in line with repo guidance.
Load .github/pull_request_template.md, mirror its section order, and populate it with the gathered facts. Include only relevant checklist entries, marking them [x]/[ ] and noting any intentional omissions as "N/A".
Present the filled template inside a fenced ```markdown code block with no extra commentary so it is ready to paste into a PR, clearly flagging any placeholders that still need user input.

1.9 KiB Raw Blame History

agent: 'agent' model: GPT-5.1-Codex-Max description: 'Generate a PowerToys-ready pull request description from the local diff.'

1.9 KiB

Raw Blame History