32 lines
2.5 KiB
JSON
32 lines
2.5 KiB
JSON
{
|
|
"context_window": {
|
|
"conversation_history": [
|
|
{
|
|
"content": "You are G3, a general-purpose AI agent. Your goal is to analyze and solve problems by writing code.\n\n# Tool Call Format\n\nWhen you need to execute a tool, write ONLY the JSON tool call on a new line:\n\n{\"tool\": \"tool_name\", \"args\": {\"param\": \"value\"}}\n\nThe tool will execute immediately and you'll receive the result (success or error) to continue with.\n\n# Available Tools\n\n- **shell**: Execute shell commands\n - Format: {\"tool\": \"shell\", \"args\": {\"command\": \"your_command_here\"}}\n - Example: {\"tool\": \"shell\", \"args\": {\"command\": \"ls ~/Downloads\"}}\n\n- **final_output**: Signal task completion with a detailed summary of work done in markdown format\n - Format: {\"tool\": \"final_output\", \"args\": {\"summary\": \"what_was_accomplished\"}}\n\n# Instructions\n\n1. Analyze the request and break down into smaller tasks if appropriate\n2. Execute ONE tool at a time\n3. STOP when the original request was satisfied\n4. Call the final_output tool when done\n\n# Response Guidelines\n\n- Use Markdown formatting for all responses except tool calls.\n- Whenever taking actions, use the pronoun 'I'\n\n",
|
|
"role": "system"
|
|
},
|
|
{
|
|
"content": "Task: hello test",
|
|
"role": "user"
|
|
},
|
|
{
|
|
"content": "1. Understanding the task, it seems simple enough. The goal is to output the message \"hello\" for this test.\n2. I will execute the following tool call to print the message \"hello\" to the console:\n\n```json\n\n{\"tool\": \"shell\", \"args\": {\"command\":\"echo hello\"}}",
|
|
"role": "assistant"
|
|
},
|
|
{
|
|
"content": "Tool result: hello",
|
|
"role": "user"
|
|
},
|
|
{
|
|
"content": "1. Understanding the task, it seems simple enough. The goal is to output the message \"hello\" for this test.\n2. I will execute the following tool call to print the message \"hello\" to the console:\n\n```json\n\nTool executed: shell -> hello\n\n1. The shell tool call was successful, and it has printed the message \"hello\" as requested.\n2. I am now ready to call the final_output tool to signal task completion and provide a summary of the work done.\n\n```json\n\n=> Printed the message 'hello' as requested.",
|
|
"role": "assistant"
|
|
}
|
|
],
|
|
"percentage_used": 1.06201171875,
|
|
"total_tokens": 32768,
|
|
"used_tokens": 348
|
|
},
|
|
"session_id": "hello_test_a63e133911916b31",
|
|
"status": "completed",
|
|
"timestamp": 1757968007
|
|
} |