mirror of https://github.com/microsoft/PowerToys.git synced 2026-04-03 09:46:54 +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

2.8 KiB

Raw Blame History

agent: 'agent' model: GPT-5.1-Codex-Max description: "Execute the fix for a GitHub issue using the previously generated implementation plan. Apply code & tests directly in the repo. Output only a PR description (and optional manual steps)."

DEPENDENCY

Source review prompt (for generating the implementation plan if missing):

.github/prompts/review-issue.prompt.md

Required plan file (single source of truth):

Generated Files/issueReview/{{issue_number}}/implementation-plan.md

Dependency Handling

If implementation-plan.md exists → proceed.
If missing → run the review prompt:
- Invoke: .github/prompts/review-issue.prompt.md
- Pass: issue_number={{issue_number}}
- Then re-check for implementation-plan.md.
If still missing → stop and generate:
- Generated Files/issueFix/{{issue_number}}/manual-steps.md containing: “implementation-plan.md not found; please run .github/prompts/review-issue.prompt.md for #{{issue_number}}.”

GOAL

For #{{issue_number}}:

Use implementation-plan.md as the single authority.
Apply code and test changes directly in the repository.
Produce a PR-ready description.

OUTPUT FILES

Generated Files/issueFix/{{issue_number}}/pr-description.md
Generated Files/issueFix/{{issue_number}}/manual-steps.md # only if human interaction or external setup is required

EXECUTION RULES

Read implementation-plan.md and execute:
- Layers & Files → edit/create as listed
- Pattern Choices → follow repository conventions
- Fundamentals (perf, security, compatibility, accessibility)
- Logging & Exceptions
- Telemetry (only if explicitly included in the plan)
- Risks & Mitigations
- Tests to Add
Locate affected files via rg or git grep.
Add/update tests to enforce the fixed behavior.
If any ambiguity exists, add: // TODO(Human input needed):
Verify locally: build & tests run successfully.

pr-description.md should include:

Title: Fix: <short summary> (#{{issue_number}})
What changed and why the fix works
Files or modules touched
Risks & mitigations (implemented)
Tests added/updated and how to run them
Telemetry behavior (if applicable)
Validation / reproduction steps
Closes #{{issue_number}}

manual-steps.md (only if needed)

List required human actions: secrets, config, approvals, missing info, or code comments requiring human decisions.

IMPORTANT

Apply code and tests directly; do not produce patch files.
Follow implementation-plan.md as the source of truth.
Insert comments for human review where a decision or input is required.
Use repository conventions and deterministic, minimal changes.

FINALIZE

Write pr-description.md
Write manual-steps.md only if needed
Print concise success message or note items requiring human interaction

2.8 KiB Raw Blame History