軌跡の形式

{
  "conversations": [ ... ],
  "timestamp": "2026-03-30T14:22:31.456789",
  "model": "anthropic/claude-sonnet-4.6",
  "completed": true
}

{
  "prompt_index": 42,
  "conversations": [ ... ],
  "metadata": { "prompt_source": "gsm8k", "difficulty": "hard" },
  "completed": true,
  "partial": false,
  "api_calls": 7,
  "toolsets_used": ["code_tools", "file_tools"],
  "tool_stats": {
    "terminal": {"count": 3, "success": 3, "failure": 0},
    "read_file": {"count": 2, "success": 2, "failure": 0},
    "write_file": {"count": 0, "success": 0, "failure": 0}
  },
  "tool_error_counts": {
    "terminal": 0,
    "read_file": 0,
    "write_file": 0
  }
}

{
  "conversations": [
    {
      "from": "system",
      "value": "You are a function calling AI model. You are provided with function signatures within <tools> </tools> XML tags. You may call one or more functions to assist with the user query. If available tools are not relevant in assisting with user query, just respond in natural conversational language. Don't make assumptions about what values to plug into functions. After calling & executing the functions, you will be provided with function results within <tool_response> </tool_response> XML tags. Here are the available tools:\n<tools>\n[{\"name\": \"terminal\", \"description\": \"Execute shell commands\", \"parameters\": {\"type\": \"object\", \"properties\": {\"command\": {\"type\": \"string\"}}}, \"required\": null}]\n</tools>\nFor each function call return a JSON object, with the following pydantic model json schema for each:\n{'title': 'FunctionCall', 'type': 'object', 'properties': {'name': {'title': 'Name', 'type': 'string'}, 'arguments': {'title': 'Arguments', 'type': 'object'}}, 'required': ['name', 'arguments']}\nEach function call should be enclosed within <tool_call> </tool_call> XML tags.\nExample:\n<tool_call>\n{'name': <function-name>,'arguments': <args-dict>}\n</tool_call>"
    },
    {
      "from": "human",
      "value": "What Python version is installed?"
    },
    {
      "from": "gpt",
      "value": "<think>\nThe user wants to know the Python version. I should run python3 --version.\n</think>\n<tool_call>\n{\"name\": \"terminal\", \"arguments\": {\"command\": \"python3 --version\"}}\n</tool_call>"
    },
    {
      "from": "tool",
      "value": "<tool_response>\n{\"tool_call_id\": \"call_abc123\", \"name\": \"terminal\", \"content\": \"Python 3.11.6\"}\n</tool_response>"
    },
    {
      "from": "gpt",
      "value": "<think>\nGot the version. I can now answer the user.\n</think>\nPython 3.11.6 is installed on this system."
    }
  ],
  "timestamp": "2026-03-30T14:22:31.456789",
  "model": "anthropic/claude-sonnet-4.6",
  "completed": true
}

<tool_call>
{"name": "terminal", "arguments": {"command": "ls -la"}}
</tool_call>

<tool_response>
{"tool_call_id": "call_abc123", "name": "terminal", "content": "output here"}
</tool_response>

def load_trajectories(path: str):
    """Load trajectory entries from a JSONL file."""
    entries = []
    with open(path, "r", encoding="utf-8") as f:
        for line in f:
            line = line.strip()
            if line:
                entries.append(json.loads(line))
    return entries

# Filter to successful completions only
successful = [e for e in load_trajectories("trajectory_samples.jsonl")
              if e.get("completed")]

# Extract just the conversations for training
training_data = [e["conversations"] for e in successful]

from datasets import load_dataset

ds = load_dataset("json", data_files="trajectory_samples.jsonl")

python run_agent.py --save_trajectories --query='your question here'