コーディングエージェントアノテーション

agentic:
  enabled: true
  trace_converter: claude_code
  display_type: coding_trace
 
  coding_trace_display:
    # Diff rendering
    diff_style: unified          # "unified" or "side_by_side"
    diff_context_lines: 3        # lines of context around changes
    syntax_highlight: true       # language-aware highlighting
    show_line_numbers: true
 
    # Terminal output
    terminal_theme: dark         # "dark" or "light"
    terminal_max_lines: 80       # auto-collapse after this many lines
    show_exit_codes: true
 
    # File reads
    file_read_max_lines: 100     # auto-collapse file reads longer than this
    show_file_path: true
    show_line_range: true        # display "lines 42-87" when partial reads
 
    # File tree sidebar
    file_tree:
      enabled: true
      position: left             # "left" or "right"
      show_operation_icons: true # icons for read/edit/create/delete
      group_by_directory: true
      click_to_navigate: true    # click a file to jump to its operations
 
    # Collapsible sections
    auto_collapse_threshold: 500 # characters before auto-collapsing
    collapse_file_reads: true
    collapse_terminal_output: true

agentic:
  trace_converter: claude_code    # or aider, swe_agent_trajectory, auto

# Convert Claude Code traces
python -m potato.trace_converter \
  -i traces.json \
  -f claude_code \
  -o data/converted.jsonl
 
# Convert Aider chat logs
python -m potato.trace_converter \
  -i aider_chat_history/ \
  -f aider \
  -o data/aider_converted.jsonl
 
# Convert SWE-Agent trajectories
python -m potato.trace_converter \
  -i trajectories/ \
  -f swe_agent_trajectory \
  -o data/swe_converted.jsonl
 
# Auto-detect format
python -m potato.trace_converter \
  -i mixed_traces/ \
  -f auto \
  -o data/auto_converted.jsonl

# Filter by file extension
python -m potato.trace_converter \
  -i traces/ -f claude_code -o data/out.jsonl \
  --include "*.json"
 
# Add metadata fields from a CSV
python -m potato.trace_converter \
  -i traces/ -f claude_code -o data/out.jsonl \
  --metadata metadata.csv --join-key trace_id
 
# Validate output without writing
python -m potato.trace_converter \
  -i traces.json -f claude_code --validate

{
  "id": "trace_001",
  "task_description": "Fix the failing test in test_parser.py",
  "repository": "myproject",
  "structured_turns": [
    {
      "type": "file_read",
      "tool": "Read",
      "file_path": "src/parser.py",
      "content": "def parse(input_str):\n    tokens = tokenize(input_str)\n    ...",
      "line_start": 1,
      "line_end": 45
    },
    {
      "type": "edit",
      "tool": "Edit",
      "file_path": "src/parser.py",
      "old_content": "    if len(tokens) == 0:\n        return None",
      "new_content": "    if len(tokens) == 0:\n        raise ParseError('Empty input')",
      "line_start": 12,
      "line_end": 13
    },
    {
      "type": "terminal",
      "tool": "Bash",
      "command": "python -m pytest test_parser.py -v",
      "output": "test_parser.py::test_empty_input PASSED\ntest_parser.py::test_valid_input PASSED\n\n2 passed in 0.34s",
      "exit_code": 0
    },
    {
      "type": "file_write",
      "tool": "Write",
      "file_path": "src/parser.py",
      "content": "...",
      "is_new_file": false
    }
  ],
  "metadata": {
    "agent": "claude_code",
    "model": "claude-sonnet-4-20250514",
    "total_tokens": 15234,
    "duration_seconds": 42
  }
}

task_name: "Coding Agent Evaluation"
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: 3
    syntax_highlight: true
    show_line_numbers: true
    terminal_theme: dark
    terminal_max_lines: 80
    show_exit_codes: true
    file_read_max_lines: 100
    file_tree:
      enabled: true
      position: left
      show_operation_icons: true
      group_by_directory: true
      click_to_navigate: true
    auto_collapse_threshold: 500
 
annotation_schemes:
  # Did the agent complete the task?
  - annotation_type: radio
    name: task_completion
    description: "Did the agent successfully complete the task?"
    labels:
      - "Fully Complete"
      - "Partially Complete"
      - "Failed"
      - "Made Things Worse"
 
  # Per-step correctness
  - annotation_type: per_turn_rating
    name: step_quality
    description: "Rate this step"
    target: agentic_steps
    rating_type: radio
    labels:
      - "Good"
      - "Acceptable"
      - "Unnecessary"
      - "Incorrect"
 
  # Code quality rating
  - annotation_type: likert
    name: code_quality
    description: "Rate the quality of the code changes"
    min: 1
    max: 5
    labels:
      1: "Very Poor"
      2: "Poor"
      3: "Acceptable"
      4: "Good"
      5: "Excellent"
 
  # Free-text notes
  - annotation_type: text
    name: notes
    description: "Any additional observations about the coding trace"
    label_requirement:
      required: false
 
output_annotation_dir: "output/"
output_annotation_format: "jsonl"

# Clone the repository
git clone https://github.com/davidjurgens/potato.git
cd potato
 
# Run the Claude Code trace evaluation example
potato start example/coding_agent_eval/config.yaml -p 8000
 
# Run the SWE-bench evaluation example
potato start example/swe_bench_eval/config.yaml -p 8000
 
# Run the multi-agent comparison example
potato start example/coding_agent_comparison/config.yaml -p 8000