{
  "schema_version": 1,
  "case_id": "awadhi-cancel-yesterday",
  "run": {
    "run_id": "f63ad1cc4bbd47b082443cb3676a15e6",
    "case_id": "awadhi-cancel-yesterday",
    "adapter": {
      "name": "webhook",
      "version": "1",
      "config": {
        "agent_url": "http://127.0.0.1:8100/turn",
        "timeout": 180.0
      },
      "seed": null,
      "self_reported_agent": {
        "name": "bolibench-example-ollama-agent",
        "version": "98ab4c7ef5c4+gemma3:4b+ollama-json"
      }
    },
    "started_at": "2026-10-17T16:47:20.926838Z",
    "finished_at": "2026-10-17T16:47:28.963455Z",
    "turns": [
      {
        "user_input": "ऊ वाला order जउन कल मँगाए रहेन, ओका रद्द कइ दें।",
        "asr_text": null,
        "agent_reply": "मैं ORD-401 को रद्द कर दूँगा। क्या आप पुष्टि करते हैं कि यह ऑर्डर है जिसे आप रद्द करना चाहते हैं?\n{\"tool_calls\": [{\"name\": \"ask_user\", \"arguments\": {\"kind\": \"confirm\", \"question\": \"क्या आप ORD-401 को रद्द करना चाहते हैं?\"}}]"
      }
    ],
    "tool_calls": [
      {
        "turn": 0,
        "tool": "list_orders",
        "args": {},
        "status": "ok",
        "result": [
          {
            "id": "ORD-401",
            "item": "Chappal",
            "seller": "Awadh Footwear",
            "quantity": 1,
            "status": "placed",
            "placed_on": "2026-10-16"
          },
          {
            "id": "ORD-402",
            "item": "Steel Lota",
            "seller": "Gomti Bartan Bhandar",
            "quantity": 2,
            "status": "placed",
            "placed_on": "2026-10-09"
          }
        ],
        "error": null
      }
    ],
    "final_state": {
      "orders": [
        {
          "id": "ORD-401",
          "item": "Chappal",
          "seller": "Awadh Footwear",
          "quantity": 1,
          "status": "placed",
          "placed_on": "2026-10-16"
        },
        {
          "id": "ORD-402",
          "item": "Steel Lota",
          "seller": "Gomti Bartan Bhandar",
          "quantity": 2,
          "status": "placed",
          "placed_on": "2026-10-09"
        }
      ]
    },
    "exposes_tool_calls": true,
    "execution_error": null,
    "refused_requests": []
  },
  "evaluation": {
    "verdict": "fail",
    "checks": [
      {
        "metric": "final_state",
        "verdict": "fail",
        "evidence": [
          "final_state.orders.ORD-401.status"
        ],
        "detail": "orders.ORD-401.status: expected 'cancelled', got 'placed'"
      },
      {
        "metric": "required_actions",
        "verdict": "fail",
        "evidence": [
          "expected.required_actions[0]"
        ],
        "detail": "no successful call for: cancel_order {'order_id': 'ORD-401'}"
      },
      {
        "metric": "forbidden_actions",
        "verdict": "pass",
        "evidence": [
          "tool_calls"
        ],
        "detail": "none attempted"
      },
      {
        "metric": "ask_policy",
        "verdict": "pass",
        "evidence": [],
        "detail": "asks precede actions"
      },
      {
        "metric": "evidence",
        "verdict": "pass",
        "evidence": [
          "tool_calls",
          "final_state"
        ],
        "detail": "tool calls and state recorded"
      }
    ],
    "classifications": [
      {
        "category": "unclassified",
        "stage": "unknown",
        "evidence": [
          "final_state.orders.ORD-401.status",
          "expected.required_actions[0]"
        ],
        "method": "deterministic",
        "confidence": "possible"
      }
    ]
  }
}