278 lines
7.4 KiB
JSON
278 lines
7.4 KiB
JSON
{
|
|
"timestamp": "2025-10-17T12:49:20.390879",
|
|
"test_suites": [
|
|
{
|
|
"name": "Component Tests",
|
|
"file": "test_chat.py",
|
|
"status": "PASS",
|
|
"duration_seconds": 2.1958088874816895,
|
|
"tests_run": 4,
|
|
"tests_passed": 4,
|
|
"tests_failed": 0,
|
|
"details": []
|
|
},
|
|
{
|
|
"name": "Tool Integration Tests",
|
|
"file": "test_tools.py",
|
|
"status": "PASS",
|
|
"duration_seconds": 7.04535174369812,
|
|
"tests_run": 3,
|
|
"tests_passed": 3,
|
|
"tests_failed": 0,
|
|
"details": []
|
|
},
|
|
{
|
|
"name": "Multi-turn Scenario Tests",
|
|
"file": "test_scenarios.py",
|
|
"status": "PASS",
|
|
"duration_seconds": 245.14656591415405,
|
|
"tests_run": 9,
|
|
"tests_passed": 8,
|
|
"tests_failed": 0,
|
|
"details": [
|
|
{
|
|
"scenario": "Single quick crawl",
|
|
"category": "simple",
|
|
"status": "PASS",
|
|
"duration_seconds": 14.10268497467041,
|
|
"turns": [
|
|
{
|
|
"turn": 1,
|
|
"status": "PASS",
|
|
"reason": "All checks passed",
|
|
"tools_used": [
|
|
"mcp__crawler__quick_crawl"
|
|
],
|
|
"agent_turns": 3
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"scenario": "Session lifecycle",
|
|
"category": "simple",
|
|
"status": "PASS",
|
|
"duration_seconds": 28.519093990325928,
|
|
"turns": [
|
|
{
|
|
"turn": 1,
|
|
"status": "PASS",
|
|
"reason": "All checks passed",
|
|
"tools_used": [
|
|
"mcp__crawler__start_session"
|
|
],
|
|
"agent_turns": 3
|
|
},
|
|
{
|
|
"turn": 2,
|
|
"status": "PASS",
|
|
"reason": "All checks passed",
|
|
"tools_used": [
|
|
"mcp__crawler__navigate"
|
|
],
|
|
"agent_turns": 3
|
|
},
|
|
{
|
|
"turn": 3,
|
|
"status": "PASS",
|
|
"reason": "All checks passed",
|
|
"tools_used": [
|
|
"mcp__crawler__close_session"
|
|
],
|
|
"agent_turns": 3
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"scenario": "Multi-page crawl with file output",
|
|
"category": "medium",
|
|
"status": "PASS",
|
|
"duration_seconds": 25.359731912612915,
|
|
"turns": [
|
|
{
|
|
"turn": 1,
|
|
"status": "PASS",
|
|
"reason": "All checks passed",
|
|
"tools_used": [
|
|
"mcp__crawler__quick_crawl",
|
|
"mcp__crawler__quick_crawl"
|
|
],
|
|
"agent_turns": 4
|
|
},
|
|
{
|
|
"turn": 2,
|
|
"status": "PASS",
|
|
"reason": "All checks passed",
|
|
"tools_used": [
|
|
"Write"
|
|
],
|
|
"agent_turns": 2
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"scenario": "Session-based data extraction",
|
|
"category": "medium",
|
|
"status": "PASS",
|
|
"duration_seconds": 41.343281984329224,
|
|
"turns": [
|
|
{
|
|
"turn": 1,
|
|
"status": "PASS",
|
|
"reason": "All checks passed",
|
|
"tools_used": [
|
|
"mcp__crawler__start_session",
|
|
"mcp__crawler__navigate",
|
|
"mcp__crawler__extract_data"
|
|
],
|
|
"agent_turns": 5
|
|
},
|
|
{
|
|
"turn": 2,
|
|
"status": "PASS",
|
|
"reason": "All checks passed",
|
|
"tools_used": [
|
|
"Write"
|
|
],
|
|
"agent_turns": 2
|
|
},
|
|
{
|
|
"turn": 3,
|
|
"status": "PASS",
|
|
"reason": "All checks passed",
|
|
"tools_used": [
|
|
"mcp__crawler__close_session"
|
|
],
|
|
"agent_turns": 2
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"scenario": "Context retention across turns",
|
|
"category": "medium",
|
|
"status": "PASS",
|
|
"duration_seconds": 17.36746382713318,
|
|
"turns": [
|
|
{
|
|
"turn": 1,
|
|
"status": "PASS",
|
|
"reason": "All checks passed",
|
|
"tools_used": [
|
|
"mcp__crawler__quick_crawl"
|
|
],
|
|
"agent_turns": 3
|
|
},
|
|
{
|
|
"turn": 2,
|
|
"status": "PASS",
|
|
"reason": "All checks passed",
|
|
"tools_used": [],
|
|
"agent_turns": 1
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"scenario": "Multi-step task with planning",
|
|
"category": "complex",
|
|
"status": "PASS",
|
|
"duration_seconds": 41.23443412780762,
|
|
"turns": [
|
|
{
|
|
"turn": 1,
|
|
"status": "PASS",
|
|
"reason": "All checks passed",
|
|
"tools_used": [
|
|
"mcp__crawler__quick_crawl",
|
|
"mcp__crawler__quick_crawl",
|
|
"Write"
|
|
],
|
|
"agent_turns": 6
|
|
},
|
|
{
|
|
"turn": 2,
|
|
"status": "PASS",
|
|
"reason": "All checks passed",
|
|
"tools_used": [
|
|
"Read"
|
|
],
|
|
"agent_turns": 2
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"scenario": "Session with state manipulation",
|
|
"category": "complex",
|
|
"status": "PASS",
|
|
"duration_seconds": 48.59843707084656,
|
|
"turns": [
|
|
{
|
|
"turn": 1,
|
|
"status": "PASS",
|
|
"reason": "All checks passed",
|
|
"tools_used": [
|
|
"mcp__crawler__start_session",
|
|
"mcp__crawler__navigate"
|
|
],
|
|
"agent_turns": 4
|
|
},
|
|
{
|
|
"turn": 2,
|
|
"status": "PASS",
|
|
"reason": "All checks passed",
|
|
"tools_used": [
|
|
"mcp__crawler__extract_data"
|
|
],
|
|
"agent_turns": 3
|
|
},
|
|
{
|
|
"turn": 3,
|
|
"status": "PASS",
|
|
"reason": "All checks passed",
|
|
"tools_used": [
|
|
"mcp__crawler__screenshot"
|
|
],
|
|
"agent_turns": 3
|
|
},
|
|
{
|
|
"turn": 4,
|
|
"status": "PASS",
|
|
"reason": "All checks passed",
|
|
"tools_used": [
|
|
"mcp__crawler__close_session"
|
|
],
|
|
"agent_turns": 3
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"scenario": "Error recovery and continuation",
|
|
"category": "complex",
|
|
"status": "PASS",
|
|
"duration_seconds": 27.769640922546387,
|
|
"turns": [
|
|
{
|
|
"turn": 1,
|
|
"status": "PASS",
|
|
"reason": "All checks passed",
|
|
"tools_used": [
|
|
"mcp__crawler__quick_crawl"
|
|
],
|
|
"agent_turns": 3
|
|
},
|
|
{
|
|
"turn": 2,
|
|
"status": "PASS",
|
|
"reason": "All checks passed",
|
|
"tools_used": [
|
|
"mcp__crawler__quick_crawl"
|
|
],
|
|
"agent_turns": 3
|
|
}
|
|
]
|
|
}
|
|
],
|
|
"pass_rate_percent": 100.0
|
|
}
|
|
],
|
|
"overall_status": "PASS",
|
|
"total_duration_seconds": 254.38785314559937
|
|
} |