कोड रिव्यू एनोटेशन

annotation_schemes:
  - name: inline_comments
    annotation_type: code_review_comments
    description: "Click any diff line to add an inline comment"
 
    inline_comments:
      # Comment categories
      categories:
        - value: bug
          display: "Bug"
          color: "#ef4444"
          icon: "bug"
        - value: logic
          display: "Logic Error"
          color: "#f97316"
          icon: "alert-triangle"
        - value: security
          display: "Security"
          color: "#dc2626"
          icon: "shield-alert"
        - value: performance
          display: "Performance"
          color: "#eab308"
          icon: "zap"
        - value: style
          display: "Style"
          color: "#6b7280"
          icon: "palette"
        - value: suggestion
          display: "Suggestion"
          color: "#3b82f6"
          icon: "lightbulb"
        - value: question
          display: "Question"
          color: "#8b5cf6"
          icon: "help-circle"
        - value: praise
          display: "Praise"
          color: "#22c55e"
          icon: "thumbs-up"
 
      # Severity levels (optional)
      severity:
        enabled: true
        levels:
          - value: critical
            display: "Critical"
          - value: major
            display: "Major"
          - value: minor
            display: "Minor"
          - value: nit
            display: "Nit"
 
      # Behavior
      require_category: true
      require_severity: false
      allow_multi_line: true       # comments can span a range of lines
      allow_suggestions: true      # annotator can write suggested replacement code
      min_comments: 0              # minimum comments required before submission

# In inline comment output:
{
  "file": "src/parser.py",
  "line_start": 42,
  "line_end": 44,
  "category": "bug",
  "severity": "critical",
  "comment": "Off-by-one error: range should be inclusive of end",
  "suggestion": "for i in range(start, end + 1):\n    process(tokens[i])"
}

annotation_schemes:
  - name: file_ratings
    annotation_type: code_review_file_ratings
    description: "Rate each modified file"
 
    file_ratings:
      dimensions:
        - name: correctness
          display: "Correctness"
          description: "Are the changes to this file functionally correct?"
          scale:
            min: 1
            max: 5
            labels:
              1: "Broken -- introduces bugs or breaks existing functionality"
              2: "Mostly broken -- significant functional issues"
              3: "Partially correct -- works but has edge cases or minor bugs"
              4: "Mostly correct -- minor issues only"
              5: "Fully correct -- changes work as intended"
 
        - name: quality
          display: "Code Quality"
          description: "How well-written are the changes to this file?"
          scale:
            min: 1
            max: 5
            labels:
              1: "Very poor -- unreadable, no structure"
              2: "Poor -- hard to follow, inconsistent style"
              3: "Acceptable -- works but could be cleaner"
              4: "Good -- clean, idiomatic, well-structured"
              5: "Excellent -- exemplary code, would merge as-is"
 
      # Files to rate
      include_unchanged: false     # only rate files the agent modified
      include_new_files: true      # include files the agent created
      include_deleted_files: true  # include files the agent deleted
 
      # Behavior
      require_all_files: true      # must rate every modified file

{
  "file_ratings": {
    "src/parser.py": {
      "correctness": 4,
      "quality": 3
    },
    "tests/test_parser.py": {
      "correctness": 5,
      "quality": 4
    },
    "src/utils.py": {
      "correctness": 2,
      "quality": 2
    }
  }
}

annotation_schemes:
  - name: verdict
    annotation_type: code_review_verdict
    description: "Give an overall verdict on the code changes"
 
    verdict:
      options:
        - value: approve
          display: "Approve"
          description: "Changes are correct and ready to merge"
          color: "#22c55e"
          icon: "check-circle"
        - value: request_changes
          display: "Request Changes"
          description: "Changes need fixes before merging"
          color: "#ef4444"
          icon: "x-circle"
        - value: comment_only
          display: "Comment Only"
          description: "Leaving feedback without a verdict"
          color: "#6b7280"
          icon: "message-circle"
 
      # Optional summary text
      require_summary: true
      summary_placeholder: "Summarize your review..."
      summary_min_length: 20

task_name: "Coding Agent Code Review"
task_dir: "."
 
data_files:
  - "data/coding_traces.jsonl"
 
item_properties:
  id_key: id
  text_key: task_description
 
agentic:
  enabled: true
  trace_converter: claude_code
  display_type: coding_trace
 
  coding_trace_display:
    diff_style: unified
    diff_context_lines: 5
    syntax_highlight: true
    show_line_numbers: true
    terminal_theme: dark
    file_tree:
      enabled: true
      position: left
      show_operation_icons: true
      click_to_navigate: true
 
annotation_schemes:
  # Inline comments on diff lines
  - name: inline_comments
    annotation_type: code_review_comments
    inline_comments:
      categories:
        - { value: bug, display: "Bug", color: "#ef4444" }
        - { value: logic, display: "Logic Error", color: "#f97316" }
        - { value: security, display: "Security", color: "#dc2626" }
        - { value: performance, display: "Performance", color: "#eab308" }
        - { value: style, display: "Style", color: "#6b7280" }
        - { value: suggestion, display: "Suggestion", color: "#3b82f6" }
        - { value: question, display: "Question", color: "#8b5cf6" }
        - { value: praise, display: "Praise", color: "#22c55e" }
      severity:
        enabled: true
        levels:
          - { value: critical, display: "Critical" }
          - { value: major, display: "Major" }
          - { value: minor, display: "Minor" }
          - { value: nit, display: "Nit" }
      require_category: true
      allow_multi_line: true
      allow_suggestions: true
 
  # File-level correctness and quality
  - name: file_ratings
    annotation_type: code_review_file_ratings
    file_ratings:
      dimensions:
        - name: correctness
          display: "Correctness"
          scale: { min: 1, max: 5 }
        - name: quality
          display: "Code Quality"
          scale: { min: 1, max: 5 }
      require_all_files: true
 
  # Overall verdict
  - name: verdict
    annotation_type: code_review_verdict
    verdict:
      options:
        - { value: approve, display: "Approve", color: "#22c55e" }
        - { value: request_changes, display: "Request Changes", color: "#ef4444" }
        - { value: comment_only, display: "Comment Only", color: "#6b7280" }
      require_summary: true
      summary_min_length: 20
 
output_annotation_dir: "output/"
output_annotation_format: "jsonl"

{
  "id": "trace_042",
  "annotator": "reviewer_01",
  "timestamp": "2025-01-15T14:30:00Z",
  "annotations": {
    "inline_comments": [
      {
        "file": "src/parser.py",
        "line_start": 42,
        "line_end": 42,
        "category": "bug",
        "severity": "critical",
        "comment": "This will throw IndexError when tokens list is empty",
        "suggestion": "if tokens:\n    return tokens[0]\nreturn None"
      },
      {
        "file": "src/parser.py",
        "line_start": 15,
        "line_end": 15,
        "category": "style",
        "severity": "nit",
        "comment": "Variable name 'x' is not descriptive"
      },
      {
        "file": "tests/test_parser.py",
        "line_start": 28,
        "line_end": 30,
        "category": "praise",
        "comment": "Good edge case coverage for empty input"
      }
    ],
    "file_ratings": {
      "src/parser.py": { "correctness": 3, "quality": 2 },
      "tests/test_parser.py": { "correctness": 5, "quality": 4 }
    },
    "verdict": {
      "decision": "request_changes",
      "summary": "The core fix is on the right track but has an edge case bug with empty input. The test coverage is good. Fix the IndexError and clean up variable naming."
    }
  }
}

# Export as structured code review JSON
python -m potato.export \
  -i output/ \
  -f code_review \
  -o results/reviews.jsonl
 
# Export inline comments only (for training code comment models)
python -m potato.export \
  -i output/ \
  -f code_review_comments \
  -o results/comments.jsonl
 
# Export file ratings as a CSV (for analysis)
python -m potato.export \
  -i output/ \
  -f code_review_file_ratings \
  -o results/file_ratings.csv
 
# Export verdict distribution summary
python -m potato.export \
  -i output/ \
  -f code_review_verdicts \
  -o results/verdicts.json