智慧體標註

agentic:
  enabled: true
  trace_converter: react
  trace_file: "data/agent_traces.jsonl"

agentic:
  enabled: true
  trace_converter: multi_agent
  trace_file: "data/multi_agent_traces.jsonl"
  multi_agent:
    agent_converters:
      planner: react
      coder: anthropic
      reviewer: openai

agentic:
  enabled: true
  trace_converter: auto
  trace_file: "data/traces.jsonl"

# converters/my_converter.py
from potato.agentic.base_converter import BaseTraceConverter
 
class MyConverter(BaseTraceConverter):
    name = "my_framework"
 
    def convert(self, raw_trace: dict) -> dict:
        steps = []
        for entry in raw_trace["log"]:
            steps.append({
                "type": entry.get("kind", "action"),
                "content": entry["text"],
                "timestamp": entry.get("ts"),
                "metadata": entry.get("extra", {}),
            })
        return {"steps": steps}

agentic:
  trace_converter: custom
  custom_converter: "converters/my_converter.py:MyConverter"

agentic:
  enabled: true
  trace_converter: openai
  display_type: agent_trace
 
  agent_trace_display:
    # Color coding for step types
    colors:
      thought: "#6E56CF"
      action: "#3b82f6"
      observation: "#22c55e"
      error: "#ef4444"
      system: "#6b7280"
 
    # Collapsible sections
    collapse_observations: true
    collapse_threshold: 500    # characters before auto-collapsing
 
    # Step numbering
    show_step_numbers: true
    show_timestamps: true
 
    # Tool call rendering
    render_json: true          # pretty-print JSON arguments
    syntax_highlight: true     # highlight code in observations

agentic:
  enabled: true
  trace_converter: webarena
  display_type: web_agent
 
  web_agent_display:
    # Screenshot rendering
    screenshot_max_width: 900
    screenshot_quality: 85
 
    # SVG overlay for agent actions
    overlay:
      enabled: true
      click_marker: "circle"       # circle, crosshair, or arrow
      click_color: "#ef4444"
      click_radius: 20
      type_highlight: "#3b82f6"    # highlight for text input fields
      scroll_indicator: true
 
    # Filmstrip view
    filmstrip:
      enabled: true
      thumbnail_width: 150
      show_action_labels: true
 
    # DOM snapshot display
    show_dom_snapshot: false        # optional raw DOM view
    show_url_bar: true
    show_action_description: true

agentic:
  enabled: true
  display_type: interactive_chat
 
  interactive_chat_display:
    mode: trace_review         # or "live_chat"
 
    # Trace review settings
    trace_review:
      show_system_prompt: false
      show_token_counts: true
      show_latency: true
      message_grouping: turn    # "turn" or "message"
 
    # Live chat settings (when mode: live_chat)
    live_chat:
      proxy: openai             # agent proxy to use
      max_turns: 20
      timeout_seconds: 60
      show_typing_indicator: true
      allow_regenerate: true
 
    # Common settings
    show_role_labels: true
    role_colors:
      user: "#3b82f6"
      assistant: "#6E56CF"
      system: "#6b7280"
      tool: "#22c55e"

agentic:
  enabled: true
  trace_converter: claude_code
  display_type: coding_trace
 
  coding_trace_display:
    diff_style: unified           # unified or split
    terminal_theme: dark
    show_file_tree: true
    collapse_long_output: true
    collapse_threshold: 50        # lines
    show_line_numbers: true
    syntax_highlight: true

agentic:
  enabled: true
  display_type: live_agent

annotation_schemes:
  - annotation_type: trajectory_eval
    name: step_eval
    error_types:
      reasoning:
        - logical_error
        - incorrect_assumption
      action:
        - wrong_tool
        - wrong_arguments
        - premature_termination

annotation_schemes:
  - annotation_type: rubric_eval
    name: agent_rubric
    criteria:
      - name: correctness
        description: "Did the agent produce the correct result?"
      - name: efficiency
        description: "Did the agent take an efficient path?"
      - name: safety
        description: "Did the agent avoid unsafe actions?"
    scale_points: 5
    scale_labels:
      1: "Very Poor"
      3: "Acceptable"
      5: "Excellent"

annotation_schemes:
  - annotation_type: pairwise
    name: agent_comparison
    mode: multi_dimension
    allow_tie: true

annotation_schemes:
  - annotation_type: process_reward
    name: prm
    mode: first_error    # or per_step

annotation_schemes:
  # Overall trace rating
  - annotation_type: likert
    name: overall_quality
    description: "Rate the overall quality of this agent trace"
    labels:
      1: "Very Poor"
      5: "Excellent"
 
  # Per-turn ratings
  - annotation_type: trajectory_eval
    name: step_correctness
    description: "Was this step correct?"
    steps_key: agentic_steps        # binds to trace steps
    correctness_options:
      - "Correct"
      - "Partially Correct"
      - "Incorrect"
      - "Unnecessary"
 
  - annotation_type: trajectory_eval
    name: step_explanation
    description: "Explain any issues with this step"
    steps_key: agentic_steps

{
  "id": "trace_042",
  "annotations": {
    "overall_quality": 3,
    "step_correctness": {
      "0": "Correct",
      "1": "Correct",
      "2": "Incorrect",
      "3": "Correct"
    },
    "step_explanation": {
      "2": "The agent searched for the wrong product name"
    }
  }
}

agentic:
  enabled: true
  display_type: interactive_chat
 
  agent_proxy:
    type: openai                 # openai, http, or echo
 
    # OpenAI proxy
    openai:
      model: "gpt-4o"
      api_key: ${OPENAI_API_KEY}
      system_prompt: "You are a helpful customer service agent."
      temperature: 0.7
      max_tokens: 1024

agent_proxy:
  type: openai
  openai:
    model: "gpt-4o"
    api_key: ${OPENAI_API_KEY}
    system_prompt: "You are a helpful assistant."
    temperature: 0.7

agent_proxy:
  type: http
  http:
    url: "https://my-agent.example.com/chat"
    method: POST
    headers:
      Authorization: "Bearer ${AGENT_API_KEY}"
    request_template:
      messages: "{{messages}}"
      session_id: "{{session_id}}"
    response_path: "response.content"
    timeout_seconds: 30

agent_proxy:
  type: echo
  echo:
    prefix: "[Echo] "
    delay_ms: 500

annotation_schemes:
  - preset: agent_task_success
  - preset: agent_step_correctness
  - preset: agent_error_taxonomy

annotation_schemes:
  - preset: agent_task_success
  - preset: agent_step_correctness
 
  # Custom schema alongside presets
  - annotation_type: text
    name: evaluator_notes
    description: "Any additional observations about this agent trace"
    label_requirement:
      required: false

# project config
task_name: "ReAct Agent Evaluation"
task_dir: "."
 
data_files:
  - "data/react_traces.jsonl"
 
item_properties:
  id_key: trace_id
  text_key: task_description
 
agentic:
  enabled: true
  trace_converter: react
  display_type: agent_trace
 
  agent_trace_display:
    colors:
      thought: "#6E56CF"
      action: "#3b82f6"
      observation: "#22c55e"
      error: "#ef4444"
    collapse_observations: true
    collapse_threshold: 300
    show_step_numbers: true
    render_json: true
 
annotation_schemes:
  - preset: agent_task_success
  - preset: agent_step_correctness
  - preset: agent_efficiency
 
  - annotation_type: text
    name: failure_reason
    description: "If the agent failed, describe what went wrong"
    label_requirement:
      required: false
 
output_annotation_dir: "output/"
output_annotation_format: "jsonl"

{
  "trace_id": "react_001",
  "task_description": "Find the population of Tokyo and compare it to New York City",
  "trace": [
    {"type": "thought", "content": "I need to find the population of both cities. Let me search for Tokyo first."},
    {"type": "action", "content": "search", "action_input": "Tokyo population 2024"},
    {"type": "observation", "content": "Tokyo has a population of approximately 13.96 million in the city proper..."},
    {"type": "thought", "content": "Now I need to find New York City's population."},
    {"type": "action", "content": "search", "action_input": "New York City population 2024"},
    {"type": "observation", "content": "New York City has a population of approximately 8.34 million..."},
    {"type": "thought", "content": "Tokyo (13.96M) has about 67% more people than NYC (8.34M)."},
    {"type": "action", "content": "finish", "action_input": "Tokyo has ~13.96 million people vs NYC's ~8.34 million, making Tokyo about 67% larger by population."}
  ]
}

potato start config.yaml -p 8000