File size: 10,082 Bytes
4c0b7eb e7b4937 4c0b7eb 59f3cce 4c0b7eb |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 |
"""
LLM Integration Tests - Stage 3 Validation
Author: @mangubee
Date: 2026-01-02
Tests for Stage 3 LLM integration:
- Planning with LLM
- Tool selection via function calling
- Answer synthesis from evidence
- Full workflow with mocked LLM responses
"""
import pytest
from unittest.mock import patch, MagicMock
from src.agent.llm_client import (
plan_question,
select_tools_with_function_calling,
synthesize_answer
)
from src.tools import TOOLS
class TestPlanningFunction:
"""Test LLM-based planning function."""
@patch('src.agent.llm_client.Anthropic')
def test_plan_question_basic(self, mock_anthropic):
"""Test planning with simple question."""
# Mock LLM response
mock_client = MagicMock()
mock_response = MagicMock()
mock_response.content = [MagicMock(text="1. Search for information\n2. Analyze results")]
mock_client.messages.create.return_value = mock_response
mock_anthropic.return_value = mock_client
# Test planning
plan = plan_question(
question="What is the capital of France?",
available_tools=TOOLS
)
assert isinstance(plan, str)
assert len(plan) > 0
print(f"✓ Generated plan: {plan[:50]}...")
@patch('src.agent.llm_client.Anthropic')
def test_plan_with_files(self, mock_anthropic):
"""Test planning with file context."""
# Mock LLM response
mock_client = MagicMock()
mock_response = MagicMock()
mock_response.content = [MagicMock(text="1. Parse file\n2. Extract data\n3. Calculate answer")]
mock_client.messages.create.return_value = mock_response
mock_anthropic.return_value = mock_client
# Test planning with files
plan = plan_question(
question="What is the total in the spreadsheet?",
available_tools=TOOLS,
file_paths=["data.xlsx"]
)
assert isinstance(plan, str)
assert len(plan) > 0
print(f"✓ Generated plan with files: {plan[:50]}...")
class TestToolSelection:
"""Test LLM function calling for tool selection."""
@patch('src.agent.llm_client.Anthropic')
def test_select_single_tool(self, mock_anthropic):
"""Test selecting single tool with parameters."""
# Mock LLM response with function call
mock_client = MagicMock()
mock_response = MagicMock()
# Mock tool_use content block
mock_tool_use = MagicMock()
mock_tool_use.type = "tool_use"
mock_tool_use.name = "search"
mock_tool_use.input = {"query": "capital of France"}
mock_tool_use.id = "call_001"
mock_response.content = [mock_tool_use]
mock_client.messages.create.return_value = mock_response
mock_anthropic.return_value = mock_client
# Test tool selection
tool_calls = select_tools_with_function_calling(
question="What is the capital of France?",
plan="1. Search for capital of France",
available_tools=TOOLS
)
assert isinstance(tool_calls, list)
assert len(tool_calls) == 1
assert tool_calls[0]["tool"] == "search"
assert "query" in tool_calls[0]["params"]
print(f"✓ Selected tool: {tool_calls[0]}")
@patch('src.agent.llm_client.Anthropic')
def test_select_multiple_tools(self, mock_anthropic):
"""Test selecting multiple tools in sequence."""
# Mock LLM response with multiple function calls
mock_client = MagicMock()
mock_response = MagicMock()
# Mock multiple tool_use blocks
mock_tool1 = MagicMock()
mock_tool1.type = "tool_use"
mock_tool1.name = "parse_file"
mock_tool1.input = {"file_path": "data.xlsx"}
mock_tool1.id = "call_001"
mock_tool2 = MagicMock()
mock_tool2.type = "tool_use"
mock_tool2.name = "safe_eval"
mock_tool2.input = {"expression": "sum(values)"}
mock_tool2.id = "call_002"
mock_response.content = [mock_tool1, mock_tool2]
mock_client.messages.create.return_value = mock_response
mock_anthropic.return_value = mock_client
# Test tool selection
tool_calls = select_tools_with_function_calling(
question="What is the sum in data.xlsx?",
plan="1. Parse file\n2. Calculate sum",
available_tools=TOOLS
)
assert isinstance(tool_calls, list)
assert len(tool_calls) == 2
assert tool_calls[0]["tool"] == "parse_file"
assert tool_calls[1]["tool"] == "safe_eval"
print(f"✓ Selected {len(tool_calls)} tools")
class TestAnswerSynthesis:
"""Test LLM-based answer synthesis."""
@patch('src.agent.llm_client.Anthropic')
def test_synthesize_simple_answer(self, mock_anthropic):
"""Test synthesizing answer from single evidence."""
# Mock LLM response
mock_client = MagicMock()
mock_response = MagicMock()
mock_response.content = [MagicMock(text="Paris")]
mock_client.messages.create.return_value = mock_response
mock_anthropic.return_value = mock_client
# Test answer synthesis
answer = synthesize_answer(
question="What is the capital of France?",
evidence=["[search] Paris is the capital and most populous city of France"]
)
assert isinstance(answer, str)
assert len(answer) > 0
assert answer == "Paris"
print(f"✓ Synthesized answer: {answer}")
@patch('src.agent.llm_client.Anthropic')
def test_synthesize_from_multiple_evidence(self, mock_anthropic):
"""Test synthesizing answer from multiple evidence sources."""
# Mock LLM response
mock_client = MagicMock()
mock_response = MagicMock()
mock_response.content = [MagicMock(text="42")]
mock_client.messages.create.return_value = mock_response
mock_anthropic.return_value = mock_client
# Test answer synthesis with multiple evidence
answer = synthesize_answer(
question="What is the answer?",
evidence=[
"[search] The answer to life is 42",
"[safe_eval] 6 * 7 = 42",
"[parse_file] Result: 42"
]
)
assert isinstance(answer, str)
assert answer == "42"
print(f"✓ Synthesized answer from {3} evidence items: {answer}")
@patch('src.agent.llm_client.Anthropic')
def test_synthesize_with_conflicts(self, mock_anthropic):
"""Test synthesizing answer when evidence conflicts."""
# Mock LLM response - should resolve conflict
mock_client = MagicMock()
mock_response = MagicMock()
mock_response.content = [MagicMock(text="Paris")]
mock_client.messages.create.return_value = mock_response
mock_anthropic.return_value = mock_client
# Test answer synthesis with conflicting evidence
answer = synthesize_answer(
question="What is the capital of France?",
evidence=[
"[search] Paris is the capital of France (source: Wikipedia, 2024)",
"[search] Lyon was briefly capital during revolution (source: old text, 1793)"
]
)
assert isinstance(answer, str)
assert answer == "Paris" # Should pick more recent/credible source
print(f"✓ Resolved conflict, answer: {answer}")
class TestEndToEndWorkflow:
"""Test full agent workflow with mocked LLM."""
@patch('src.agent.llm_client.Anthropic')
@patch('src.tools.web_search.tavily_search')
def test_full_search_workflow(self, mock_tavily, mock_anthropic):
"""Test complete workflow: plan → search → answer."""
from src.agent import GAIAAgent
# Mock tool execution
mock_tavily.return_value = "Paris is the capital and most populous city of France"
# Mock LLM responses
mock_client = MagicMock()
# Response 1: Planning
# Response 2: Tool selection (function calling)
# Response 3: Answer synthesis
mock_plan_response = MagicMock()
mock_plan_response.content = [MagicMock(text="1. Search for capital of France")]
mock_tool_response = MagicMock()
mock_tool_use = MagicMock()
mock_tool_use.type = "tool_use"
mock_tool_use.name = "web_search"
mock_tool_use.input = {"query": "capital of France"}
mock_tool_use.id = "call_001"
mock_tool_response.content = [mock_tool_use]
mock_answer_response = MagicMock()
mock_answer_response.content = [MagicMock(text="Paris")]
# Set up mock to return different responses for each call
mock_client.messages.create.side_effect = [
mock_plan_response,
mock_tool_response,
mock_answer_response
]
mock_anthropic.return_value = mock_client
# Test full workflow
agent = GAIAAgent()
answer = agent("What is the capital of France?")
assert isinstance(answer, str)
assert answer == "Paris"
print(f"✓ Full workflow completed, answer: {answer}")
if __name__ == "__main__":
print("\n" + "="*70)
print("GAIA Agent - Stage 3 LLM Integration Tests")
print("="*70 + "\n")
# Run tests manually for quick validation
test_plan = TestPlanningFunction()
test_plan.test_plan_question_basic()
test_plan.test_plan_with_files()
test_tools = TestToolSelection()
test_tools.test_select_single_tool()
test_tools.test_select_multiple_tools()
test_answer = TestAnswerSynthesis()
test_answer.test_synthesize_simple_answer()
test_answer.test_synthesize_from_multiple_evidence()
test_answer.test_synthesize_with_conflicts()
test_e2e = TestEndToEndWorkflow()
test_e2e.test_full_search_workflow()
print("\n" + "="*70)
print("✓ All Stage 3 LLM integration tests passed!")
print("="*70 + "\n")
|