{
  "created_at_utc": "2026-10-03T17:16:19.416417+00:00",
  "base_url": "http://127.0.0.1:8131",
  "dataset": "evals\\knowledge_retrieval_project.jsonl",
  "indexing": {
    "semantic_indexed_documents": 1,
    "documents": 1,
    "embedding_models": [
      "granite-embedding:278m"
    ]
  },
  "metrics": {
    "cases": 1,
    "hit_at_1": 1.0,
    "hit_at_3": 1.0,
    "mean_reciprocal_rank": 1.0,
    "evidence_rate": 1.0
  },
  "results": [
    {
      "id": "project-skill-tool-filter",
      "query": "How is a tool call blocked when it is outside the selected skill permissions?",
      "expected_document": "fixture_main.py",
      "expected_evidence": "tool_name not in selected_skill.allowed_tools",
      "rank": 1,
      "top_paths": [
        "fixture_main.py"
      ],
      "expected_document_chunks": [
        102,
        99,
        100,
        79,
        85,
        84,
        98
      ],
      "evidence_found": true,
      "search_mode": "hybrid",
      "agent_answer": "لم يتم العثور على معلومات حول كيفية حظر استدعاء الأداة عندما يكون خارج أذونات المهارات المحددة.\n\nالمقاطع المسترجعة لا تتضمن إجابة مباشرة على هذا السؤال.",
      "agent_tool": "search_knowledge",
      "agent_files": [
        "fixture_main.py"
      ],
      "agent_steps": [
        {
          "tool": "search_knowledge",
          "status": "completed"
        }
      ],
      "human_rating": null
    }
  ],
  "note": "Small deterministic fixture set. Retrieval metrics cover source ranking and evidence presence, not general RAG quality. Optional agent answers are retained for human review and are not auto-scored."
}