#!/usr/bin/env bash
# Sample /run-eval request against a locally running ows-ai-eval-runner service.
#
# Start the service with `make trace-dev` (so Bedrock calls get traced).

set -euo pipefail

BASE_URL="http://localhost:5000"

curl -s -X POST "$BASE_URL/run-eval" \
  -H "Content-Type: application/json" \
  -d '{
    "mcp": {
      "name": "test-mcp",
      "endpoint": "http://localhost:8080/mcp",
      "auth_token": "dev-jwt"
    },
    "runs": 1,
    "pipeline": {"pipeline_name": "manual-test", "pipeline_id": "1"},
    "prompts": {
      "capital_check": {
        "prompt": "What is the capital of France? Answer in one word.",
        "expected_tools": [],
        "judges": [
          {"name": "mentions_paris", "instructions": "Does the answer correctly state that the capital of France is Paris?"}
        ]
      }
    }
  }' | python3 -m json.tool