chore: refine PR reviewer prompt guidance

[PeterDaveHello]

User description

Tighten scope to issues introduced by the PR and clarify what to flag.

Improve issue descriptions to be more concrete and actionable while allowing high-impact, lower-confidence risks when uncertainty is stated.

GitHub Copilot PR summary:

This pull request updates the PR reviewer prompt and related field descriptions to clarify the reviewer's focus, improve the quality and precision of review comments, and set clearer expectations for issue reporting. The changes emphasize actionable, concrete, and confident feedback, especially for critical issues, and provide more detailed guidance on how to structure review comments.

Prompt and Review Guidance Improvements:

• The PR reviewer prompt now explicitly instructs reviewers to focus only on issues introduced by the current PR, not on pre-existing code or general concerns.
• Expanded instructions clarify how to determine what to flag, emphasizing confidence, specificity, and actionable feedback—especially for bugs, security, and high-impact issues. Reviewers are advised to avoid speculation and to clearly communicate the severity and context of each issue.
• Added guidelines on constructing review comments: be direct, concise, matter-of-fact, and avoid filler or overly positive/negative language.

Field Description Refinements:

• The issue_content field in KeyIssuesComponentLink now requires a concise description of the issue, why it matters, and a specific scenario or input that triggers it, instead of a generic summary.
• The key_issues_to_review field in the Review model is updated to require only confident findings of bugs, security vulnerabilities, or significant performance concerns, with explicit instructions for handling limited-confidence/high-impact issues and requiring concrete, realistic trigger scenarios.

---

PR Type

Enhancement, Documentation

---

Description

• Clarify reviewer scope to focus only on issues introduced by the PR

• Expand guidance on determining what issues to flag with confidence levels

• Improve issue description requirements to include concrete trigger scenarios

• Refine comment construction guidelines for clarity and accuracy

---

Diagram Walkthrough

flowchart LR
  A["Reviewer Scope"] -->|"Focus on new code only"| B["Issues Introduced by PR"]
  C["Issue Determination"] -->|"Clear bugs & security"| D["Flag Thoroughly"]
  C -->|"Lower-severity concerns"| E["Flag Only if Confident"]
  C -->|"High-impact, low-confidence"| F["Flag with Uncertainty Note"]
  B --> G["Issue Description"]
  D --> G
  E --> G
  F --> G
  G -->|"Include concrete scenario"| H["Actionable Feedback"]
  I["Comment Construction"] -->|"Direct, concise, matter-of-fact"| H

Loading

File Walkthrough

Relevant files

Documentation

pr_reviewer_prompts.toml Enhance reviewer guidance with confidence and specificity standards pr_agent/settings/pr_reviewer_prompts.toml Clarified that review should focus only on issues introduced by the PR, not pre-existing code Added new "Determining what to flag" section with guidance on confidence levels for different issue types Added new "Constructing comments" section with guidelines for direct, accurate, and helpful feedback Updated issue_content field description to require concrete trigger scenarios and explanation of why issues matter Updated key_issues_to_review field description to emphasize confidence, allow high-impact uncertain issues with explicit notes, and require realistic trigger scenarios +18/-5

---

[qodo-free-for-open-source-projects]

PR Compliance Guide 🔍

Below is a summary of compliance checks for this PR:

Security Compliance
🟢	No security concerns identified No security vulnerabilities detected by AI analysis. Human verification advised for critical code.
Ticket Compliance
⚪	🎫 No ticket provided Create ticket/issue
Codebase Duplication Compliance
⚪	Codebase context is not defined Follow the guide to enable codebase context checks.
Custom Compliance
🟢	Consistent Naming Conventions Objective: All new variables, functions, and classes must follow the project's established naming standards Status: Passed
	No Dead or Commented-Out Code Objective: Keep the codebase clean by ensuring all submitted code is active and necessary Status: Passed
	Robust Error Handling Objective: Ensure potential errors and edge cases are anticipated and handled gracefully throughout the code Status: Passed
	Single Responsibility for Functions Objective: Each function should have a single, well-defined responsibility Status: Passed
	When relevant, utilize early return Objective: In a code snippet containing multiple logic conditions (such as 'if-else'), prefer an early return on edge cases than deep nesting Status: Passed

Compliance status legend

🟢 - Fully Compliant
🟡 - Partial Compliant
🔴 - Not Compliant
⚪ - Requires Further Human Verification
🏷️ - Compliance label

[qodo-free-for-open-source-projects]

PR Code Suggestions ✨

Explore these optional code suggestions:

Category	Suggestion	Impact
Possible issue	Fix default versus description in Field Correct the Pydantic Field definition by moving the descriptive text to the description keyword argument and setting the default value to ... to make the field required. pr_agent/settings/pr_reviewer_prompts.toml [132] -key_issues_to_review: List[KeyIssuesComponentLink] = Field("A concise list (0-{{ num_max_findings }} issues) of bugs, security vulnerabilities, or significant performance concerns introduced in this PR. Only include issues you are confident about. If confidence is limited but the potential impact is high (e.g., data loss, security), you may include it only if you explicitly note what remains uncertain. Each issue must identify a concrete problem with a realistic trigger scenario. An empty list is acceptable if no clear issues are found.") +key_issues_to_review: List[KeyIssuesComponentLink] = Field(..., description="A concise list (0-{{ num_max_findings }} issues) of bugs, security vulnerabilities, or significant performance concerns introduced in this PR. Only include issues you are confident about. If confidence is limited but the potential impact is high (e.g., data loss, security), you may include it only if you explicitly note what remains uncertain. Each issue must identify a concrete problem with a realistic trigger scenario. An empty list is acceptable if no clear issues are found.") Apply / Chat Suggestion importance[1-10]: 9 __ Why: The suggestion correctly identifies a misuse of Pydantic's Field, where a description string is improperly used as a default value. This would cause a runtime error, as the default str is incompatible with the List[KeyIssuesComponentLink] type hint.	High
More

• Author self-review: I have reviewed the PR code suggestions, and addressed the relevant ones.