Normalize report-format guidance across non-compliant agentic workflows#41728
Merged
pelikhan merged 2 commits intoJun 26, 2026
Merged
Conversation
Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com>
Copilot
AI
changed the title
[WIP] Normalize report formatting for non-compliant workflows
Normalize report-format guidance across non-compliant agentic workflows
Jun 26, 2026
pelikhan
marked this pull request as ready for review
June 26, 2026 15:54
Contributor
There was a problem hiding this comment.
Pull request overview
Aligns several gh-aw agentic workflow prompts with the repository’s report-format guidance by adjusting markdown header levels in report/example sections and adding progressive-disclosure blocks, then regenerating compiled .lock.yml artifacts to keep runtime outputs in sync.
Changes:
- Normalized select report/example section headers from
##to###across multiple workflows. - Added
<details>progressive-disclosure blocks to previously non-collapsible example/report guidance. - Regenerated the corresponding
.lock.ymlcompiled outputs to match updated workflow sources.
Show a summary per file
| File | Description |
|---|---|
| .github/workflows/test-quality-sentinel.md | Adjusted step/report section header levels (note: current changes introduce heading-hierarchy inconsistencies for step sections). |
| .github/workflows/test-quality-sentinel.lock.yml | Regenerated compiled artifact metadata hashes to match updated source. |
| .github/workflows/pr-sous-chef.md | Normalized a report-related section header level. |
| .github/workflows/pr-sous-chef.lock.yml | Regenerated compiled artifact metadata hashes to match updated source. |
| .github/workflows/plan.md | Added a <details> block to the example issue body to model progressive disclosure. |
| .github/workflows/plan.lock.yml | Regenerated compiled artifact metadata hashes to match updated source. |
| .github/workflows/mattpocock-skills-reviewer.md | Normalized report/comment guidance section headers from ## to ###. |
| .github/workflows/mattpocock-skills-reviewer.lock.yml | Regenerated compiled artifact metadata hashes to match updated source. |
| .github/workflows/draft-pr-cleanup.md | Normalized section header levels in guidance near the report/example area (note: current changes flatten parent/child heading hierarchy). |
| .github/workflows/draft-pr-cleanup.lock.yml | Regenerated compiled artifact metadata hashes to match updated source. |
| .github/workflows/designer-drift-audit.md | Updated report template heading level and wrapped drift details guidance in a <details> block. |
| .github/workflows/designer-drift-audit.lock.yml | Regenerated compiled artifact metadata hashes to match updated source. |
| .github/workflows/daily-syntax-error-quality.md | Normalized selected phase headers (note: current changes break phase/subsection heading nesting). |
| .github/workflows/daily-syntax-error-quality.lock.yml | Regenerated compiled artifact metadata hashes to match updated source. |
| .github/workflows/auto-triage-issues.md | Normalized the scheduled-run report section header level. |
| .github/workflows/auto-triage-issues.lock.yml | Regenerated compiled artifact metadata hashes to match updated source. |
Review details
Tip
Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
- Files reviewed: 16/16 changed files
- Comments generated: 8
- Review effort level: Low
| Otherwise, collect the list of changed test files and their diffs. | ||
|
|
||
| ## Step 2: Extract Test Functions | ||
| ### Step 2: Extract Test Functions |
| ``` | ||
|
|
||
| ## Step 3: AST-Assisted Structural Analysis | ||
| ### Step 3: AST-Assisted Structural Analysis |
| - **Legitimate mocking targets**: external I/O (`fs`, `path`), GitHub Actions runtime (`global.core`, `process.stderr`), and HTTP clients are acceptable mock targets. Flag only when mocking internal business-logic functions that have no external side-effects. | ||
|
|
||
| ## Step 4: AI Quality Review of Each Test | ||
| ### Step 4: AI Quality Review of Each Test |
| 2. Complex workflow (> 300 lines, many tools/features) | ||
|
|
||
| ## Phase 2: Generate Syntax Errors | ||
| ### Phase 2: Generate Syntax Errors |
| ``` | ||
|
|
||
| ## Phase 3: Run Compiler and Capture Output | ||
| ### Phase 3: Run Compiler and Capture Output |
| Collect key strengths (1–2 bullets) and improvement suggestions (1–2 bullets) per test. Do **not** reproduce the full compiler output in your report — reference file:line only. | ||
|
|
||
| ## Phase 6: Create Issue with Suggestions | ||
| ### Phase 6: Create Issue with Suggestions |
Comment on lines
+211
to
213
| ### Important Guidelines | ||
|
|
||
| ### Fair and Transparent |
| - **Bot-created PRs**: Apply same rules, but consider if bot is still active | ||
|
|
||
| ## Success Metrics | ||
| ### Success Metrics |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Daily workflow-style review flagged eight active workflows with report instructions that violated markdown output conventions (report headers at
##level and missing progressive-disclosure blocks). This change aligns those workflow prompts with the project’s report-style contract without broad prompt rewrites.##→###in report/example sections)auto-triage-issues.mddaily-syntax-error-quality.mddraft-pr-cleanup.mdmattpocock-skills-reviewer.mdpr-sous-chef.mdtest-quality-sentinel.mddesigner-drift-audit.md: wrapped drift-item detail guidance in a<details>block.plan.md: added a<details>block in the example issue body to model collapsible implementation detail..lock.ymlfiles for all eight updated workflow sources so runtime artifacts match prompt-source changes.