見る、止める、巻き戻す：Potatoのライブコーディングエージェント観察

# Install Ollama
curl -fsSL https://ollama.ai/install.sh | sh
 
# Pull a coding-capable model
ollama pull qwen2.5-coder:32b
 
# Verify the model is available
ollama list

# config.yaml
annotation_task_name: "Live Agent Observation - Ollama"
port: 8000
 
live_coding_agent:
  backend_type: ollama_tool_use
  ai_config:
    model: "qwen2.5-coder:32b"
    base_url: "http://localhost:11434"
    temperature: 0.2
    max_tokens: 4096
  working_dir: ./workspace       # Agent's working directory
  max_turns: 50
  sandbox_mode: container        # container (default) | bubblewrap | trusted
  sandbox_image: "python:3.11-slim"

# Set your API key
export ANTHROPIC_API_KEY="sk-ant-..."

# config.yaml
annotation_task_name: "Live Agent Observation - Claude"
port: 8000
 
live_coding_agent:
  backend_type: anthropic_tool_use
  ai_config:
    model: "claude-sonnet-4-20250514"
    max_tokens: 8192
    temperature: 0.1
  system_prompt: >
    You are a coding agent. You will be given a task description and
    access to a codebase. Use the provided tools to read files, make
    edits, and run commands to complete the task. Think step by step
    and verify your changes by running tests.
  working_dir: ./workspace
  max_turns: 50
  sandbox_mode: container
  sandbox_image: "python:3.11-slim"

# Install the Claude Agent SDK
pip install claude-agent-sdk

# config.yaml
annotation_task_name: "Live Agent Observation - Claude Agent SDK"
port: 8000
 
live_coding_agent:
  backend_type: claude_sdk
  ai_config:
    model: "claude-sonnet-4-20250514"
  working_dir: ./workspace
  max_turns: 50                  # Maximum number of agent turns
  sandbox_mode: container
  sandbox_image: "node:20-slim"

# Start the server
potato start config.yaml -p 8000

# You can inspect checkpoints directly with git
cd workspace/
git log --oneline
 
# Output:
# f8a2c1d [potato-checkpoint] Step 12: Edit tests/test_parser.py
# 3b7e9f0 [potato-checkpoint] Step 10: Edit src/parser.py
# a1c4d8e [potato-checkpoint] Step 8: Edit src/parser.py
# 9e2f6b3 [potato-checkpoint] Step 5: Edit src/config.py
# 7d0a3c1 [potato-checkpoint] Step 0: Initial state

python -m potato.export \
  -c config.yaml \
  -f trajectory_correction \
  -o ./training_data/

{
  "session_id": "session_001",
  "branch": "branch-A",
  "task": "Fix the failing test in tests/test_parser.py",
  "steps": [
    {"step_idx": 0, "type": "file_read", "path": "tests/test_parser.py", "...": "..."},
    {"step_idx": 1, "type": "thinking", "content": "The test expects..."},
    {"step_idx": 2, "type": "file_edit", "path": "src/parser.py", "diff": "..."},
    {"step_idx": 3, "type": "bash_command", "command": "pytest tests/test_parser.py"}
  ],
  "human_interventions": [
    {"after_step": 2, "type": "instruction", "content": "Use a migration instead"}
  ],
  "rollback_from_step": null,
  "outcome": "resolved"
}

python -m potato.export \
  -c config.yaml \
  -f trajectory_correction \
  -o ./training_data/

{
  "session_id": "session_001",
  "task": "Fix the failing test in tests/test_parser.py",
  "branch_point_step": 2,
  "branch_point_reason": "Agent started modifying the wrong file",
  "rejected_branch": "branch-A",
  "rejected_steps": [
    {"step_idx": 3, "type": "file_edit", "path": "src/wrong_file.py", "...": "..."},
    {"step_idx": 4, "type": "bash_command", "command": "pytest", "exit_code": 1}
  ],
  "chosen_branch": "branch-B",
  "chosen_steps": [
    {"step_idx": 3, "type": "file_edit", "path": "src/parser.py", "...": "..."},
    {"step_idx": 4, "type": "bash_command", "command": "pytest", "exit_code": 0}
  ]
}

python -m potato.export \
  -c config.yaml \
  -f coding_eval \
  -o ./training_data/ \
  --option types=prm

python -m potato.export \
  -c config.yaml \
  -f coding_eval \
  -o ./training_data/ \
  --option types=code_review

# 1. Install Potato with live agent support
pip install potato-annotation[live-agents]
 
# 2. Install and start Ollama
curl -fsSL https://ollama.ai/install.sh | sh
ollama pull qwen2.5-coder:32b
 
# 3. Set up a workspace with a repo to work on
mkdir -p workspace/
git clone https://github.com/example/test-project workspace/repo
 
# 4. Create the config file
cat > config.yaml << 'YAML'
annotation_task_name: "Live Agent Observation"
port: 8000
 
live_coding_agent:
  backend_type: ollama_tool_use
  ai_config:
    model: "qwen2.5-coder:32b"
    base_url: "http://localhost:11434"
    temperature: 0.2
  working_dir: ./workspace/repo
  max_turns: 50
  sandbox_mode: trusted
 
annotation_schemes:
  - annotation_type: radio
    name: outcome
    description: "Final outcome"
    labels:
      - name: "resolved"
        text: "Task Fully Resolved"
      - name: "partial"
        text: "Partially Resolved"
      - name: "failed"
        text: "Failed"
 
  - annotation_type: text
    name: notes
    description: "Session Notes"
    placeholder: "Key observations about agent behavior..."
    label_requirement:
      required: false
 
output_annotation_dir: "./output/"
export_annotation_format: jsonl
 
user_config:
  allow_all_users: false
  users:
    - "observer1"
YAML
 
# 5. Start Potato
potato start config.yaml -p 8000
 
# 6. Open http://localhost:8000 in your browser