{
  "generated_at": "2026-08-15T22:25:13.203224+00:00",
  "status": "complete",
  "configuration": {
    "questions_file": "/home/janko/DP/zp-agent/evaluation/json_files/questions.json",
    "overrides_file": "/home/janko/DP/zp-agent/evaluation/json_files/rag_answer_overrides.json",
    "applied_override_ids": [
      "q0010"
    ],
    "split": "dev",
    "selected_question_count": 1,
    "requested_model": "model120-fast",
    "openwebui_url": "https://ui.tukekemt.xyz/api/chat/completions",
    "rag_url": "http://localhost:8000/rag",
    "timeout": 180,
    "delay": 0.0
  },
  "summary": {
    "total": 1,
    "completed": 1,
    "errors": 0,
    "tool_call_rate": 1.0,
    "answer_contains_score": 1.0,
    "source_url_score": 1.0,
    "should_answer_score": 1.0,
    "overall_score": 1.0,
    "strict_pass_count": 1,
    "strict_pass_rate": 1.0,
    "mean_latency_seconds": 5.838173,
    "prompt_tokens": 3223,
    "completion_tokens": 145,
    "total_tokens": 3368,
    "by_category": {
      "adversarial_year": {
        "total": 1,
        "completed": 1,
        "errors": 0,
        "tool_call_rate": 1.0,
        "answer_contains_score": 1.0,
        "source_url_score": 1.0,
        "should_answer_score": 1.0,
        "overall_score": 1.0,
        "strict_pass_count": 1,
        "strict_pass_rate": 1.0,
        "mean_latency_seconds": 5.838173,
        "prompt_tokens": 3223,
        "completion_tokens": 145,
        "total_tokens": 3368
      }
    },
    "by_difficulty": {
      "hard": {
        "total": 1,
        "completed": 1,
        "errors": 0,
        "tool_call_rate": 1.0,
        "answer_contains_score": 1.0,
        "source_url_score": 1.0,
        "should_answer_score": 1.0,
        "overall_score": 1.0,
        "strict_pass_count": 1,
        "strict_pass_rate": 1.0,
        "mean_latency_seconds": 5.838173,
        "prompt_tokens": 3223,
        "completion_tokens": 145,
        "total_tokens": 3368
      }
    }
  },
  "results": [
    {
      "id": "q0010",
      "split": "dev",
      "category": "adversarial_year",
      "difficulty": "hard",
      "question": "Je rok 2016 rokom diplomovej práce Jána Holpa? Ak nie, čo rok 2016 označuje a v ktorom roku je uvedená jeho diplomová práca?",
      "override_applied": true,
      "requested_model": "model120-fast",
      "expected_documents": [
        "pages/students/2016/jan_holp/README.md"
      ],
      "expected_source_urls": [
        "https://zp.kemt.fei.tuke.sk/students/2016/jan_holp"
      ],
      "expected_answer_contains": [
        "2016",
        "2021"
      ],
      "should_answer": true,
      "note": "Model má vysvetliť, že prvý rok je rok začiatku štúdia, ak to zdroj tak uvádza.",
      "answer": "Rok 2016 nie je rokom diplomovej práce Jána Holpa, ale označuje rok začiatku jeho štúdia. Jeho diplomová práca s názvom „Systém získavania informácií v slovenskom jazyku\" je uvedená v roku 2021.\n\nZdroj: https://zp.kemt.fei.tuke.sk/students/2016/jan_holp",
      "tool_called": true,
      "tool_call_count": 1,
      "tool_calls": [
        {
          "name": "retrieve_zpwiki_context",
          "arguments": {
            "query": "Ján Holp diplomová práca rok",
            "limit": 5
          },
          "latency_seconds": 0.039992,
          "source_urls": [
            "https://zp.kemt.fei.tuke.sk/students/2016/jan_holp"
          ]
        }
      ],
      "rag_source_urls": [
        "https://zp.kemt.fei.tuke.sk/students/2016/jan_holp"
      ],
      "first_model_latency_seconds": 1.785037,
      "tool_latency_seconds": 0.039992,
      "final_model_latency_seconds": 4.012958,
      "total_latency_seconds": 5.838173,
      "usage": {
        "prompt_tokens": 3223,
        "completion_tokens": 145,
        "total_tokens": 3368
      },
      "response_model": "Qwen3.5-122B-A10B-Q4_K_M",
      "answer_matches": [
        true,
        true
      ],
      "answer_contains_score": 1.0,
      "source_matches": [
        true
      ],
      "source_url_score": 1.0,
      "should_answer_ok": true,
      "should_answer_score": 1.0,
      "returned_no_answer": false,
      "tool_score": 1.0,
      "overall_score": 1.0,
      "strict_pass": true,
      "error": null
    }
  ]
}