Spaces:
Sleeping
Sleeping
File size: 7,595 Bytes
225a75e |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 |
#!/usr/bin/env python3
"""
Integration test for GAIA Agents
Tests Web Researcher, File Processor, and Reasoning agents
"""
import os
import sys
import time
import tempfile
from pathlib import Path
# Add src to path for imports
sys.path.insert(0, str(Path(__file__).parent))
from agents.state import GAIAAgentState, QuestionType
from agents.web_researcher import WebResearchAgent
from agents.file_processor_agent import FileProcessorAgent
from agents.reasoning_agent import ReasoningAgent
from models.qwen_client import QwenClient
def test_agents():
"""Test all implemented agents"""
print("🤖 GAIA Agents Integration Test")
print("=" * 50)
# Initialize LLM client
try:
llm_client = QwenClient()
except Exception as e:
print(f"❌ Failed to initialize LLM client: {e}")
return False
results = []
start_time = time.time()
# Test 1: Web Research Agent
print("\n🌐 Testing Web Research Agent...")
web_agent = WebResearchAgent(llm_client)
web_test_cases = [
{
"question": "What is the capital of France?",
"question_type": QuestionType.WIKIPEDIA,
"complexity": "simple"
},
{
"question": "Find information about Python programming language",
"question_type": QuestionType.WEB_RESEARCH,
"complexity": "medium"
}
]
for i, test_case in enumerate(web_test_cases, 1):
state = GAIAAgentState()
state.question = test_case["question"]
state.question_type = test_case["question_type"]
state.complexity_assessment = test_case["complexity"]
try:
result_state = web_agent.process(state)
success = len(result_state.agent_results) > 0 and list(result_state.agent_results.values())[-1].success
results.append(('Web Research', f'Test {i}', success, list(result_state.agent_results.values())[-1].processing_time if result_state.agent_results else 0))
status = "✅ PASS" if success else "❌ FAIL"
print(f" Test {i}: {status}")
except Exception as e:
results.append(('Web Research', f'Test {i}', False, 0))
print(f" Test {i}: ❌ FAIL ({e})")
# Test 2: File Processor Agent
print("\n📁 Testing File Processor Agent...")
file_agent = FileProcessorAgent(llm_client)
# Create test files
with tempfile.TemporaryDirectory() as temp_dir:
# Create CSV test file
csv_path = os.path.join(temp_dir, "test.csv")
with open(csv_path, 'w') as f:
f.write("name,age,salary\nAlice,25,50000\nBob,30,60000\nCharlie,35,70000")
# Create Python test file
py_path = os.path.join(temp_dir, "test.py")
with open(py_path, 'w') as f:
f.write("def calculate_sum(a, b):\n return a + b\n\nresult = calculate_sum(5, 3)")
file_test_cases = [
{
"question": "What is the average salary in this data?",
"file_path": csv_path,
"question_type": QuestionType.FILE_PROCESSING,
"complexity": "medium"
},
{
"question": "What does this Python code do?",
"file_path": py_path,
"question_type": QuestionType.FILE_PROCESSING,
"complexity": "simple"
}
]
for i, test_case in enumerate(file_test_cases, 1):
state = GAIAAgentState()
state.question = test_case["question"]
state.file_path = test_case["file_path"]
state.question_type = test_case["question_type"]
state.complexity_assessment = test_case["complexity"]
try:
result_state = file_agent.process(state)
success = len(result_state.agent_results) > 0 and list(result_state.agent_results.values())[-1].success
results.append(('File Processor', f'Test {i}', success, list(result_state.agent_results.values())[-1].processing_time if result_state.agent_results else 0))
status = "✅ PASS" if success else "❌ FAIL"
print(f" Test {i}: {status}")
except Exception as e:
results.append(('File Processor', f'Test {i}', False, 0))
print(f" Test {i}: ❌ FAIL ({e})")
# Test 3: Reasoning Agent
print("\n🧠 Testing Reasoning Agent...")
reasoning_agent = ReasoningAgent(llm_client)
reasoning_test_cases = [
{
"question": "Calculate 15% of 200",
"question_type": QuestionType.REASONING,
"complexity": "simple"
},
{
"question": "Convert 100 celsius to fahrenheit",
"question_type": QuestionType.REASONING,
"complexity": "simple"
},
{
"question": "What is the average of 10, 15, 20, 25, 30?",
"question_type": QuestionType.REASONING,
"complexity": "medium"
}
]
for i, test_case in enumerate(reasoning_test_cases, 1):
state = GAIAAgentState()
state.question = test_case["question"]
state.question_type = test_case["question_type"]
state.complexity_assessment = test_case["complexity"]
try:
result_state = reasoning_agent.process(state)
success = len(result_state.agent_results) > 0 and list(result_state.agent_results.values())[-1].success
results.append(('Reasoning', f'Test {i}', success, list(result_state.agent_results.values())[-1].processing_time if result_state.agent_results else 0))
status = "✅ PASS" if success else "❌ FAIL"
print(f" Test {i}: {status}")
except Exception as e:
results.append(('Reasoning', f'Test {i}', False, 0))
print(f" Test {i}: ❌ FAIL ({e})")
# Summary
total_time = time.time() - start_time
passed_tests = sum(1 for _, _, success, _ in results if success)
total_tests = len(results)
print("\n" + "=" * 50)
print("📊 AGENT TEST RESULTS")
print("=" * 50)
# Results by agent
agents = {}
for agent, test, success, exec_time in results:
if agent not in agents:
agents[agent] = {'passed': 0, 'total': 0, 'time': 0}
agents[agent]['total'] += 1
agents[agent]['time'] += exec_time
if success:
agents[agent]['passed'] += 1
for agent, stats in agents.items():
pass_rate = (stats['passed'] / stats['total']) * 100
avg_time = stats['time'] / stats['total']
status = "✅" if pass_rate == 100 else "⚠️" if pass_rate >= 80 else "❌"
print(f"{status} {agent:15}: {stats['passed']}/{stats['total']} ({pass_rate:5.1f}%) - Avg: {avg_time:.3f}s")
# Overall results
overall_pass_rate = (passed_tests / total_tests) * 100
print(f"\n🎯 OVERALL: {passed_tests}/{total_tests} tests passed ({overall_pass_rate:.1f}%)")
print(f"⏱️ TOTAL TIME: {total_time:.2f} seconds")
# Success criteria
if overall_pass_rate >= 80:
print("🚀 AGENTS READY! Multi-agent system is working correctly!")
return True
else:
print("⚠️ ISSUES FOUND! Check individual agent failures above")
return False
if __name__ == "__main__":
success = test_agents()
sys.exit(0 if success else 1) |