examples: refactor test-simulator.sh for better readability

Extract repeating question string into TEST_QUESTION variable and
create make_request() helper function to reduce code duplication.
Add proper error handling for error responses.

examples/llama-eval/test-simulator.sh

@@ -1,10 +1,13 @@
 #!/bin/bash
 
+set -e
+
 echo "=== llama-server-simulator Test Script ==="
 echo ""
 
 PORT=8033
 SUCCESS_RATE=0.8
+TEST_PORT=8034
 
 echo "Starting simulator on port $PORT with success rate $SUCCESS_RATE..."
 source venv/bin/activate
@@ -14,74 +17,61 @@ SIMULATOR_PID=$!
 echo "Waiting for simulator to start..."
 sleep 5
 
-echo ""
+# Helper function to make a request and extract the answer
-echo "=== Test 1: Basic Request with Known Question ==="
+make_request() {
-echo "Sending request with AIME question..."
+  local question="$1"
-curl -s -X POST http://localhost:$PORT/v1/chat/completions \
+  curl -s -X POST http://localhost:$PORT/v1/chat/completions \
-  -H "Content-Type: application/json" \
+    -H "Content-Type: application/json" \
-  -d '{
+    -d "{
-    "model": "llama",
+      \"model\": \"llama\",
-    "messages": [
+      \"messages\": [
-      {"role": "user", "content": "Quadratic polynomials P(x) and Q(x) have leading coefficients 2 and -2, respectively. The graphs of both polynomials pass through the two points (16,54) and (20,53). Find P(0) + Q(0)."}
+        {\"role\": \"user\", \"content\": \"$question\"}
-    ],
+      ],
-    "temperature": 0,
+      \"temperature\": 0,
-    "max_tokens": 2048
+      \"max_tokens\": 2048
-  }' | python3 -c "import sys, json; data = json.load(sys.stdin); print('Answer:', data['choices'][0]['message']['content'])"
+    }" | python3 -c "import sys, json; data = json.load(sys.stdin); print(data.get('choices', [{}])[0].get('message', {}).get('content', data.get('error', 'No response')))"
+}
+
+# Test question (repeated in multiple tests)
+TEST_QUESTION="Quadratic polynomials P(x) and Q(x) have leading coefficients 2 and -2, respectively. The graphs of both polynomials pass through the two points (16,54) and (20,53). Find P(0) + Q(0)."
 
 echo ""
-echo ""
+echo "=== Test 1: Correct Answer ==="
-echo "=== Test 2: Request with Different Question ==="
+echo "Sending request with known question..."
-echo "Sending request with another AIME question..."
+answer=$(make_request "$TEST_QUESTION")
-curl -s -X POST http://localhost:$PORT/v1/chat/completions \
+echo "Answer: $answer"
-  -H "Content-Type: application/json" \
+echo "Expected: 116"
-  -d '{
+echo "Correct: $([ "$answer" == "116" ] && echo "Yes" || echo "No")"
-    "model": "llama",
-    "messages": [
-      {"role": "user", "content": "Compute the value of 2^10 + 3^10."}
-    ],
-    "temperature": 0,
-    "max_tokens": 2048
-  }' | python3 -c "import sys, json; data = json.load(sys.stdin); print('Answer:', data['choices'][0]['message']['content'])"
 
 echo ""
+echo "=== Test 2: Wrong Answer ==="
+echo "Sending request with known question (success rate 0.0)..."
+answer=$(make_request "$TEST_QUESTION")
+echo "Answer: $answer"
+echo "Expected: 116"
+echo "Correct: $([ "$answer" == "116" ] && echo "Yes" || echo "No")"
+
 echo ""
-echo "=== Test 3: Request with No Matching Question ==="
+echo "=== Test 3: No Matching Question ==="
 echo "Sending request with non-matching text..."
-curl -s -X POST http://localhost:$PORT/v1/chat/completions \
+response=$(make_request "What is the capital of France?")
-  -H "Content-Type: application/json" \
+echo "Response: $response"
-  -d '{
+echo "Expected: No matching question found"
-    "model": "llama",
+echo "Correct: $([ "$response" == "No matching question found" ] && echo "Yes" || echo "No")"
-    "messages": [
-      {"role": "user", "content": "What is the capital of France?"}
-    ],
-    "temperature": 0,
-    "max_tokens": 2048
-  }' | python3 -c "import sys, json; data = json.load(sys.stdin); print('Response:', data.get('error', 'No error'))"
 
 echo ""
-echo ""
+echo "=== Test 4: Success Rate Verification ==="
-echo "=== Test 4: Multiple Requests to Test Success Rate ==="
 echo "Sending 10 requests to test success rate..."
 correct_count=0
 for i in {1..10}; do
-  echo "Request $i:"
+  answer=$(make_request "$TEST_QUESTION")
-  response=$(curl -s -X POST http://localhost:$PORT/v1/chat/completions \
-    -H "Content-Type: application/json" \
-    -d '{
-      "model": "llama",
-      "messages": [
-        {"role": "user", "content": "Quadratic polynomials P(x) and Q(x) have leading coefficients 2 and -2, respectively. The graphs of both polynomials pass through the two points (16,54) and (20,53). Find P(0) + Q(0)."}
-      ],
-      "temperature": 0,
-      "max_tokens": 2048
-    }')
-  answer=$(echo $response | python3 -c "import sys, json; data = json.load(sys.stdin); print(data['choices'][0]['message']['content'])")
   if [ "$answer" == "116" ]; then
     correct_count=$((correct_count + 1))
   fi
-  echo "  Answer: $answer"
+  echo "  Request $i: Answer = $answer"
 done
 echo "Correct answers: $correct_count/10"
+echo "Expected: ~8/10 (80% success rate)"
 echo "Success rate: $(echo "scale=1; $correct_count * 10" | bc)%"
 
 echo ""