مراقبة وكيل البرمجة المباشر

# Install Ollama
curl -fsSL https://ollama.com/install.sh | sh
 
# Pull a coding-capable model
ollama pull qwen2.5-coder:7b
 
# Or a larger model for better performance
ollama pull deepseek-coder-v2:16b

agentic:
  enabled: true
  display_type: coding_trace
  live_agent:
    enabled: true
    backend: ollama
    model: qwen2.5-coder:7b
 
    ollama:
      host: "http://localhost:11434"    # Ollama server URL
      temperature: 0.2
      num_ctx: 8192                     # context window size
      num_predict: 2048                 # max tokens per response
      keep_alive: "5m"                  # keep model loaded in memory
 
    # Agent capabilities
    tools:
      - read_file
      - edit_file
      - write_file
      - bash
      - glob
      - grep
    max_steps: 50
    step_timeout_seconds: 60

# Set your API key
export ANTHROPIC_API_KEY="sk-ant-..."
 
# Or add to .env file
echo "ANTHROPIC_API_KEY=sk-ant-..." >> .env

agentic:
  enabled: true
  display_type: coding_trace
  live_agent:
    enabled: true
    backend: anthropic
    model: claude-sonnet-4-20250514
 
    anthropic:
      api_key: ${ANTHROPIC_API_KEY}
      max_tokens: 4096
      temperature: 0.2
      system_prompt: |
        You are a coding assistant working on a software project.
        Read files before editing them. Run tests after making changes.
        Explain your reasoning before each action.
 
    # Agent capabilities
    tools:
      - read_file
      - edit_file
      - write_file
      - bash
      - glob
      - grep
    max_steps: 100
    step_timeout_seconds: 120

# Install the Claude Agent SDK
pip install claude-agent-sdk
 
# Set your API key
export ANTHROPIC_API_KEY="sk-ant-..."

agentic:
  enabled: true
  display_type: coding_trace
  live_agent:
    enabled: true
    backend: claude_agent_sdk
 
    claude_agent_sdk:
      api_key: ${ANTHROPIC_API_KEY}
      model: claude-sonnet-4-20250514
      max_turns: 100
      permission_mode: auto           # auto-approve tool use
      enable_thinking: true           # show extended thinking
 
    max_steps: 100
    step_timeout_seconds: 180

live_agent:
  controls:
    pause_resume:
      enabled: true
      auto_pause_on_error: true      # pause when a command fails
      auto_pause_after_steps: 0      # pause after N steps (0 = disabled)
      keyboard_shortcut: "Space"

live_agent:
  controls:
    send_instructions:
      enabled: true
      placeholder: "Type instructions for the agent..."
      inject_as: system_message      # "system_message" or "user_message"
      keyboard_shortcut: "Enter"
      presets:
        - "Try a different approach"
        - "Read the error message more carefully"
        - "Check the test file for expected behavior"
        - "Revert your last change and try again"

live_agent:
  controls:
    rollback:
      enabled: true
      show_checkpoint_diff: true     # show what will be undone
      require_confirmation: true     # "Are you sure?" dialog
      keyboard_shortcut: "Ctrl+Z"

live_agent:
  controls:
    branch:
      enabled: true
      max_branches: 5                # maximum branches from any checkpoint
      branch_naming: auto            # "auto" or "manual"
      compare_view: true             # side-by-side branch comparison
      keyboard_shortcut: "Ctrl+B"

live_agent:
  git_checkpoints:
    enabled: true
    branch_prefix: "potato-session"
    commit_message_format: "Step {step}: {tool} {file_path}"
    auto_commit: true
    cleanup_on_complete: false       # delete session branches when done
    require_clean_working_dir: true  # fail if there are uncommitted changes

# List all Potato session branches
git branch | grep potato-session
 
# View checkpoints for a session
git log potato-session-abc123 --oneline
 
# Clean up old session branches
python -m potato.cleanup_sessions --older-than 7d

{
  "id": "task_001",
  "task_description": "Fix the bug in src/parser.py where empty input causes a crash",
  "project_dir": "/path/to/project",
  "start_file": "src/parser.py",
  "test_command": "python -m pytest tests/test_parser.py -v",
  "context_files": [
    "src/parser.py",
    "tests/test_parser.py"
  ]
}

task_name: "Live Coding Agent Observation"
task_dir: "."
 
data_files:
  - "data/coding_tasks.jsonl"
 
item_properties:
  id_key: id
  text_key: task_description
 
agentic:
  enabled: true
  display_type: coding_trace
 
  coding_trace_display:
    diff_style: unified
    diff_context_lines: 3
    syntax_highlight: true
    show_line_numbers: true
    terminal_theme: dark
    file_tree:
      enabled: true
      position: left
      click_to_navigate: true
 
  live_agent:
    enabled: true
    backend: anthropic
    model: claude-sonnet-4-20250514
 
    anthropic:
      api_key: ${ANTHROPIC_API_KEY}
      max_tokens: 4096
      temperature: 0.2
 
    tools:
      - read_file
      - edit_file
      - write_file
      - bash
      - glob
      - grep
 
    max_steps: 100
    step_timeout_seconds: 120
 
    controls:
      pause_resume:
        enabled: true
        auto_pause_on_error: true
        keyboard_shortcut: "Space"
      send_instructions:
        enabled: true
        inject_as: system_message
        presets:
          - "Try a different approach"
          - "Read the error message carefully"
          - "Run the tests first"
      rollback:
        enabled: true
        require_confirmation: true
      branch:
        enabled: true
        max_branches: 5
        compare_view: true
 
    git_checkpoints:
      enabled: true
      branch_prefix: "potato-session"
      auto_commit: true
      cleanup_on_complete: false
 
annotation_schemes:
  # Per-step ratings during observation
  - annotation_type: per_turn_rating
    name: step_quality
    description: "Rate each agent step as you observe it"
    target: agentic_steps
    rating_type: radio
    labels:
      - "Good"
      - "Acceptable"
      - "Unnecessary"
      - "Incorrect"
 
  # Overall task completion after agent finishes
  - annotation_type: radio
    name: task_completion
    description: "Did the agent complete the task?"
    labels:
      - "Fully Complete"
      - "Partially Complete"
      - "Failed"
 
  # Branch comparison (when branching is used)
  - annotation_type: radio
    name: branch_preference
    description: "Which branch produced a better result?"
    labels:
      - "Branch A"
      - "Branch B"
      - "Both Equal"
      - "Both Failed"
 
  # Notes on the observation
  - annotation_type: text
    name: observation_notes
    description: "Describe what you observed and any interventions you made"
    label_requirement:
      required: false
 
output_annotation_dir: "output/"
output_annotation_format: "jsonl"

{
  "id": "task_001",
  "annotator": "observer_01",
  "root_branch": {
    "branch_id": "main",
    "steps": [
      {"step": 0, "type": "file_read", "file": "src/parser.py", "rating": "Good"},
      {"step": 1, "type": "edit", "file": "src/parser.py", "rating": "Incorrect"}
    ],
    "children": [
      {
        "branch_id": "branch_1",
        "branch_point": 1,
        "instruction": "Try a different approach -- use a try/except block instead",
        "steps": [
          {"step": 2, "type": "edit", "file": "src/parser.py", "rating": "Good"},
          {"step": 3, "type": "terminal", "command": "pytest", "rating": "Good"}
        ],
        "outcome": "Fully Complete",
        "children": []
      },
      {
        "branch_id": "branch_2",
        "branch_point": 1,
        "instruction": "Read the test file first to understand expected behavior",
        "steps": [
          {"step": 2, "type": "file_read", "file": "tests/test_parser.py", "rating": "Good"},
          {"step": 3, "type": "edit", "file": "src/parser.py", "rating": "Good"},
          {"step": 4, "type": "terminal", "command": "pytest", "rating": "Good"}
        ],
        "outcome": "Fully Complete",
        "children": []
      }
    ]
  },
  "branch_preference": "Branch B",
  "observation_notes": "Both branches solved the problem, but branch B produced cleaner code by reading the tests first."
}

# Export as DPO preference pairs from branch comparisons
python -m potato.export \
  -i output/ \
  -f branching_dpo \
  -o results/branch_preferences.jsonl
 
# Export full trajectory trees
python -m potato.export \
  -i output/ \
  -f trajectory_tree \
  -o results/trajectory_trees.jsonl

# Restricted tool set for analysis-only tasks
live_agent:
  tools:
    - read_file
    - glob
    - grep
  # No edit_file, write_file, or bash

ollama serve

ollama list

export ANTHROPIC_API_KEY="sk-ant-..."

cd /path/to/project
git init
git add -A
git commit -m "Initial commit"

live_agent:
  loop_detection:
    enabled: true
    threshold: 3                     # pause after N identical consecutive steps
    action: pause                    # "pause" or "terminate"

# Remove branches older than 7 days
python -m potato.cleanup_sessions --older-than 7d
 
# Remove all session branches
python -m potato.cleanup_sessions --all
 
# Dry run (show what would be deleted)
python -m potato.cleanup_sessions --older-than 7d --dry-run