Spaces:
Sleeping
Sleeping
File size: 14,212 Bytes
e4f6727 910ae58 e4f6727 910ae58 e4f6727 910ae58 e4f6727 910ae58 e4f6727 910ae58 e4f6727 910ae58 e4f6727 910ae58 e4f6727 910ae58 e4f6727 910ae58 e4f6727 3d648f2 e4f6727 910ae58 e4f6727 910ae58 e4f6727 910ae58 e4f6727 910ae58 98ada6c 910ae58 98ada6c 910ae58 98ada6c 910ae58 e4f6727 910ae58 98ada6c e4f6727 910ae58 e4f6727 910ae58 e4f6727 910ae58 e4f6727 910ae58 e4f6727 910ae58 e4f6727 910ae58 e4f6727 910ae58 e4f6727 910ae58 3d648f2 910ae58 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 |
from args import Args
from graph import State, Nodes, Edges
from graph_builder import GraphBuilder
import unittest
class TestAlfredAgent(unittest.TestCase):
"""Test suite for the Alfred agent"""
def setUp(self):
"""Set up test fixtures"""
self.nodes = Nodes()
self.edges = Edges()
self.builder = GraphBuilder()
self.graph = self.builder.build_agent_graph()
def test_manager_node(self):
"""
Test the manager node functionality.
Orchestrates the workflow by delegating tasks to specialized nodes and integrating their outputs
"""
nodes = Nodes()
# Create a test state
test_state: State = {
"initial_query": "query",
"messages": ["query"], # Manager's context
"task_progress": [], # Solver's context
"audit_interval": 2,
"manager_queries": 0,
"solver_queries": 0,
"max_interactions": 4,
"max_solving_effort": 4,
"final_response": None
}
# Test the node function
print(f"Testing 'manager' node...")
nodes.manager_node(test_state)
# Assert that manager_queries has been incremented
self.assertEqual(test_state["manager_queries"], 1, "Manager queries should be incremented from 0 to 1")
# Assert that a new message has been added to the messages list
self.assertEqual(len(test_state["messages"]), 2, "Messages list should contain 2 items: the initial query and a new message from the manager node")
# Test audit interval behaviour
test_state = nodes.manager_node(test_state)
# Assert that manager_queries has been incremented
self.assertEqual(test_state["manager_queries"], 2, "Manager queries should be incremented from 1 to 2")
# Assert that a new message has been added to the messages list
self.assertEqual(len(test_state["messages"]), 2, "Messages list should contain 2 items: the initial 2 messages and no additional message as it is the audit interval")
already_tested_messages = test_state["messages"]
expected_state: State = {
"initial_query": "query",
"messages": already_tested_messages, # Manager's context
"task_progress": [test_state["messages"][-1]], # Solver's context
"audit_interval": 2,
"manager_queries": 2,
"solver_queries": 0,
"max_interactions": 4,
"max_solving_effort": 4,
"final_response": None
}
self.assertEqual(test_state, expected_state, "The state after manager node execution should match the expected state with manager_queries=2 and no additional messages added during audit interval")
print(f"State after node execution: {test_state}")
def test_final_answer_node(self):
"""
Test the final_answer node functionality.
Formats and delivers the final response to the user
"""
nodes = Nodes()
# Prepare a state with messages and required fields
test_state: State = {
"initial_query": "What is the capital of France?",
"messages": ["What is the capital of France?", "The capital of France is Paris."],
"task_progress": [],
"audit_interval": 2,
"manager_queries": 2,
"solver_queries": 0,
"max_interactions": 4,
"max_solving_effort": 4,
"final_response": None
}
print(f"Testing 'final_answer' node...")
nodes.final_answer_node(test_state)
# The last message should be the instruction
self.assertIn("Formulate a definitive final answer", test_state["messages"][-1])
# The final_response should be set and not None
self.assertIsNotNone(test_state["final_response"])
print(f"State after node execution: {test_state}")
def test_auditor_node(self):
"""
Test the auditor node functionality.
Reviews manager's outputs for accuracy, safety, and quality
"""
nodes = Nodes()
test_state: State = {
"initial_query": "What is the capital of France?",
"messages": ["What is the capital of France?", "The capital of France is Paris."],
"task_progress": [],
"audit_interval": 2,
"manager_queries": 2,
"solver_queries": 0,
"max_interactions": 4,
"max_solving_effort": 4,
"final_response": None
}
print(f"Testing 'auditor' node...")
nodes.auditor_node(test_state)
# Auditor appends a message
self.assertGreaterEqual(len(test_state["messages"]), 3)
print(f"State after node execution: {test_state}")
def test_solver_node(self):
"""
Test the solver node functionality.
Central problem-solving node that coordinates with specialized experts based on task requirements
"""
nodes = Nodes()
test_state: State = {
"initial_query": "What is the capital of France?",
"messages": ["What is the capital of France?"],
"task_progress": ["Solve: What is the capital of France?"],
"audit_interval": 2,
"manager_queries": 1,
"solver_queries": 0,
"max_interactions": 4,
"max_solving_effort": 4,
"final_response": None
}
print(f"Testing 'solver' node...")
nodes.solver_node(test_state)
# Solver appends to task_progress
self.assertGreaterEqual(len(test_state["task_progress"]), 2)
print(f"State after node execution: {test_state}")
def test_researcher_node(self):
"""
Test the researcher node functionality.
Retrieves and synthesizes information from various sources to answer knowledge-based questions
"""
nodes = Nodes()
test_state: State = {
"initial_query": "What are the latest news headlines about artificial intelligence published this week?",
"messages": ["What are the latest news headlines about artificial intelligence published this week?"],
"task_progress": ["What are the latest news headlines about artificial intelligence published this week?"],
"audit_interval": 2,
"manager_queries": 1,
"solver_queries": 0,
"max_interactions": 4,
"max_solving_effort": 4,
"final_response": None
}
print(f"Testing 'researcher' node...")
nodes.researcher_node(test_state)
self.assertGreaterEqual(len(test_state["task_progress"]), 2)
print(f"State after node execution: {test_state}")
def test_reasoner_node(self):
"""
Test the reasoner node functionality.
Performs logical reasoning, inference, and step-by-step problem-solving
"""
nodes = Nodes()
test_state: State = {
"initial_query": "What is the capital of France?",
"messages": ["What is the capital of France?"],
"task_progress": ["Reason: What is the capital of France?"],
"audit_interval": 2,
"manager_queries": 1,
"solver_queries": 0,
"max_interactions": 4,
"max_solving_effort": 4,
"final_response": None
}
print(f"Testing 'reasoner' node...")
nodes.reasoner_node(test_state)
self.assertGreaterEqual(len(test_state["task_progress"]), 2)
print(f"State after node execution: {test_state}")
def test_viewer_node(self):
"""
Test the viewer node functionality.
Processes, analyzes, and generates vision related information
"""
nodes = Nodes()
test_state: State = {
"initial_query": "Describe the image.",
"messages": ["Describe the image."],
"task_progress": ["View: Describe the image."],
"audit_interval": 2,
"manager_queries": 1,
"solver_queries": 0,
"max_interactions": 4,
"max_solving_effort": 4,
"final_response": None
}
print(f"Testing 'image_handler' node...")
nodes.viewer_node(test_state)
self.assertGreaterEqual(len(test_state["task_progress"]), 2)
print(f"State after node execution: {test_state}")
def test_manager_edge(self):
"""
Test the conditional edge for manager node.
This edge should return one of: "solver", "auditor", "final_answer"
"""
edges = Edges()
# Test for final_answer by FINAL ANSWER in last message
test_state: State = {
"initial_query": "Q",
"messages": ["Q", "FINAL ANSWER: Paris"],
"task_progress": [],
"audit_interval": 2,
"manager_queries": 2,
"solver_queries": 0,
"max_interactions": 4,
"max_solving_effort": 4,
"final_response": None
}
print(f"Testing 'manager' conditional edge...")
result = edges.manager_edge(test_state)
self.assertEqual(result, "final_answer")
# Test for final_answer by max_interactions
test_state2: State = {
"initial_query": "Q",
"messages": ["Q", "Some message"],
"task_progress": [],
"audit_interval": 2,
"manager_queries": 4,
"solver_queries": 0,
"max_interactions": 4,
"max_solving_effort": 4,
"final_response": None
}
result2 = edges.manager_edge(test_state2)
self.assertEqual(result2, "final_answer")
# Test for auditor
test_state3: State = {
"initial_query": "Q",
"messages": ["Q", "Some message"],
"task_progress": [],
"audit_interval": 2,
"manager_queries": 2,
"solver_queries": 0,
"max_interactions": 4,
"max_solving_effort": 4,
"final_response": None
}
result3 = edges.manager_edge(test_state3)
self.assertEqual(result3, "auditor")
# Test for solver
test_state4: State = {
"initial_query": "Q",
"messages": ["Q", "Some message"],
"task_progress": [],
"audit_interval": 2,
"manager_queries": 1,
"solver_queries": 0,
"max_interactions": 4,
"max_solving_effort": 4,
"final_response": None
}
result4 = edges.manager_edge(test_state4)
self.assertEqual(result4, "solver")
print(f"Edge decision: {result4}")
def test_solver_edge(self):
"""
Test the conditional edge for solver node.
This edge should return one of: "manager", "researcher", "reasoner", "viewer"
"""
edges = Edges()
# researcher
test_state: State = {
"initial_query": "Q",
"messages": ["Q"],
"task_progress": ["to: researcher"],
"audit_interval": 2,
"manager_queries": 1,
"solver_queries": 0,
"max_interactions": 4,
"max_solving_effort": 4,
"final_response": None
}
result = edges.solver_edge(test_state)
self.assertEqual(result, "researcher")
# reasoner
test_state2: State = {
"initial_query": "Q",
"messages": ["Q"],
"task_progress": ["to: reasoner"],
"audit_interval": 2,
"manager_queries": 1,
"solver_queries": 0,
"max_interactions": 4,
"max_solving_effort": 4,
"final_response": None
}
result2 = edges.solver_edge(test_state2)
self.assertEqual(result2, "reasoner")
# viewer
test_state3: State = {
"initial_query": "Q",
"messages": ["Q"],
"task_progress": ["to: viewer"],
"audit_interval": 2,
"manager_queries": 1,
"solver_queries": 0,
"max_interactions": 4,
"max_solving_effort": 4,
"final_response": None
}
result3 = edges.solver_edge(test_state3)
self.assertEqual(result3, "viewer")
# manager
test_state4: State = {
"initial_query": "Q",
"messages": ["Q"],
"task_progress": ["to: manager"],
"audit_interval": 2,
"manager_queries": 1,
"solver_queries": 0,
"max_interactions": 4,
"max_solving_effort": 4,
"final_response": None
}
result4 = edges.solver_edge(test_state4)
self.assertEqual(result4, "manager")
# unspecified (should append instruction and return manager)
test_state5: State = {
"initial_query": "Q",
"messages": ["Q"],
"task_progress": ["no receiver"],
"audit_interval": 2,
"manager_queries": 1,
"solver_queries": 0,
"max_interactions": 4,
"max_solving_effort": 4,
"final_response": None
}
result5 = edges.solver_edge(test_state5)
self.assertEqual(result5, "manager")
print(f"Edge decision: {result5}")
def test_full_workflow(self):
"""
Test the Alfred agent full workflow.
"""
# This is a placeholder for a full workflow test.
# For a real test, you would simulate the entire agent graph.
print("Testing Alfred complete workflow...")
# Example test (pseudo, as actual invoke may require more setup)
# result = self.graph.invoke({"input": "Test input"})
# self.assertIsNotNone(result)
# print(f"Workflow result: {result}")
if __name__ == "__main__":
# test = TestAlfredAgent()
# test.test_researcher_node()
unittest.main() |