관찰, 일시정지, 되감기: Potato의 실시간 코딩 에이전트 관찰

# 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
project_name: "Live Agent Observation - Ollama"
port: 8000
 
live_coding_agent:
  enabled: true
  backend: "ollama"
  ollama:
    model: "qwen2.5-coder:32b"
    host: "http://localhost:11434"
    temperature: 0.2
    max_tokens: 4096
    num_ctx: 32768               # Context window size
  sandbox:
    type: "docker"               # "docker" or "local"
    image: "python:3.11-slim"    # Base image for sandboxed execution
    workspace: "./workspace/"    # Agent's working directory
    timeout: 600                 # Max seconds per agent session
  streaming:
    update_interval_ms: 100      # How often to push updates to the UI
    buffer_output: true          # Buffer terminal output for smoother rendering
  checkpoints:
    enabled: true
    strategy: "git"              # Git-based checkpoints
    auto_commit_on_file_change: true
    commit_message_prefix: "[potato-checkpoint]"

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

# config.yaml
project_name: "Live Agent Observation - Claude"
port: 8000
 
live_coding_agent:
  enabled: true
  backend: "anthropic"
  anthropic:
    model: "claude-sonnet-4-20250514"
    api_key_env: "ANTHROPIC_API_KEY"
    max_tokens: 8192
    temperature: 0.1
    tools:
      - "file_read"
      - "file_edit"
      - "bash_command"
      - "directory_list"
      - "file_search"
    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.
  sandbox:
    type: "docker"
    image: "python:3.11-slim"
    workspace: "./workspace/"
    timeout: 900
    allowed_commands:             # Whitelist for bash commands
      - "python"
      - "pip"
      - "pytest"
      - "git"
      - "ls"
      - "cat"
      - "find"
      - "grep"
  streaming:
    update_interval_ms: 50
    show_thinking: true           # Show Claude's thinking in real time
  checkpoints:
    enabled: true
    strategy: "git"
    auto_commit_on_file_change: true

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

# config.yaml
project_name: "Live Agent Observation - Claude Agent SDK"
port: 8000
 
live_coding_agent:
  enabled: true
  backend: "claude_agent_sdk"
  claude_agent_sdk:
    api_key_env: "ANTHROPIC_API_KEY"
    model: "claude-sonnet-4-20250514"
    max_turns: 50                # Maximum number of agent turns
    permission_mode: "auto"      # "auto", "ask", or "restricted"
    allowed_tools:
      - "Read"
      - "Edit"
      - "Write"
      - "Bash"
      - "Glob"
      - "Grep"
    restricted_commands:          # Bash commands to block
      - "rm -rf /"
      - "sudo"
      - "curl"
      - "wget"
  sandbox:
    type: "docker"
    image: "node:20-slim"
    workspace: "./workspace/"
    timeout: 1200
    mount_volumes:
      - "./test-repo:/workspace/repo"
  streaming:
    update_interval_ms: 50
    show_thinking: true
    show_tool_inputs: true
  checkpoints:
    enabled: true
    strategy: "git"
    auto_commit_on_file_change: true
    max_checkpoints: 100

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

# Control bar configuration
live_coding_agent:
  controls:
    pause_enabled: true
    instruction_enabled: true
    stop_enabled: true
    rollback_enabled: true
    branch_enabled: true
    pause_keyboard_shortcut: "Space"
    instruction_keyboard_shortcut: "i"

# 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

# Branching configuration
live_coding_agent:
  branching:
    enabled: true
    max_branches_per_session: 10
    auto_name_branches: true     # "branch-A", "branch-B", etc.
    require_reason_on_rollback: true  # Annotator must explain why they rolled back
    compare_branches_view: true  # Side-by-side view of branch outcomes

potato export \
  --format trajectories \
  --project ./output/ \
  --output ./training_data/trajectories.jsonl \
  --flatten_branches true

{
  "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"
}

potato export \
  --format branch_preferences \
  --project ./output/ \
  --output ./training_data/branch_preferences.jsonl

{
  "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}
  ]
}

potato export \
  --format prm_from_branches \
  --project ./output/ \
  --output ./training_data/prm_live.jsonl

potato export \
  --format code_review \
  --project ./output/ \
  --output ./training_data/code_review.jsonl

# 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'
project_name: "Live Agent Observation"
port: 8000
 
live_coding_agent:
  enabled: true
  backend: "ollama"
  ollama:
    model: "qwen2.5-coder:32b"
    host: "http://localhost:11434"
    temperature: 0.2
    num_ctx: 32768
  sandbox:
    type: "local"
    workspace: "./workspace/repo"
    timeout: 600
  streaming:
    update_interval_ms: 100
  checkpoints:
    enabled: true
    strategy: "git"
    auto_commit_on_file_change: true
  controls:
    pause_enabled: true
    instruction_enabled: true
    rollback_enabled: true
    branch_enabled: true
  branching:
    enabled: true
    max_branches_per_session: 5
    require_reason_on_rollback: true
 
annotation_schemes:
  - annotation_type: radio
    name: outcome
    label: "Final outcome"
    options:
      - value: "resolved"
        text: "Task Fully Resolved"
      - value: "partial"
        text: "Partially Resolved"
      - value: "failed"
        text: "Failed"
 
  - annotation_type: text_input
    name: notes
    label: "Session Notes"
    placeholder: "Key observations about agent behavior..."
    required: false
 
output:
  path: "./output/"
  format: "jsonl"
  export_formats:
    - "trajectories"
    - "branch_preferences"
    - "prm_from_branches"
 
annotators:
  - username: "observer1"
    password: "observer_pw_1"
YAML
 
# 5. Start Potato
potato start config.yaml -p 8000
 
# 6. Open http://localhost:8000 in your browser