Spaces:
Sleeping
Sleeping
File size: 10,919 Bytes
baa1efb |
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 |
"""
Test Task Decomposer
Comprehensive tests for task decomposition
"""
import sys
import os
ROOT = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
sys.path.append(ROOT)
import asyncio
from app.decomposition.task_decomposer import TaskDecomposer
from app.orchestrator.models import TaskClassification, TaskType, ComplexityLevel, OutputFormat
from app.orchestrator.parameter_models import (
ExtractedParameters,
DataSource,
FilterCondition,
AggregationSpec,
VisualizationRequirement,
OutputRequirement
)
from app.core.logging import setup_logging, get_logger
setup_logging()
logger = get_logger(__name__)
def test_simple_task_no_decomposition():
"""Test that simple tasks don't get decomposed"""
print("\n" + "=" * 60)
print("Test 1: Simple Task (No Decomposition)")
print("=" * 60)
decomposer = TaskDecomposer()
# Simple task
classification = TaskClassification(
primary_task=TaskType.WEB_SCRAPING,
secondary_tasks=[],
complexity=ComplexityLevel.SIMPLE,
estimated_steps=1,
output_format=OutputFormat.CSV,
confidence=0.9,
reasoning="Simple scraping"
)
parameters = ExtractedParameters(
data_sources=[
DataSource(
type='url',
location='https://example.com',
format='html',
description='Test page'
)
]
)
task_description = "Scrape data from example.com"
print(f"\n📋 Task: {task_description}")
print(f"Complexity: {classification.complexity.value}")
print(f"Estimated steps: {classification.estimated_steps}")
print("-" * 60)
# Decompose
result = decomposer.decompose(classification, parameters, task_description)
print(f"\n✅ Decomposition Result:")
print(f" Subtasks: {len(result.subtasks)}")
print(f" Strategy: {result.execution_strategy}")
print(f" Needs decomposition: {result.metadata.get('decomposed', True)}")
assert len(result.subtasks) == 1, "Simple task should have 1 subtask"
assert result.execution_strategy == 'single', "Should use single strategy"
print("\n✓ Simple task correctly identified (no decomposition)")
def test_complex_task_sequential():
"""Test complex task with sequential decomposition"""
print("\n" + "=" * 60)
print("Test 2: Complex Task (Sequential Decomposition)")
print("=" * 60)
decomposer = TaskDecomposer()
# Complex task
classification = TaskClassification(
primary_task=TaskType.ML_ANALYSIS,
secondary_tasks=[TaskType.VISUALIZATION],
complexity=ComplexityLevel.COMPLEX,
estimated_steps=5,
output_format=OutputFormat.CSV,
confidence=0.85,
reasoning="Complex analysis with multiple steps"
)
parameters = ExtractedParameters(
data_sources=[
DataSource(
type='url',
location='https://example.com/data.csv',
format='csv',
description='Sales data'
)
],
filters=[
FilterCondition(
field='region',
operator='equals',
value='North',
description='Filter North region'
)
],
aggregations=[
AggregationSpec(
function='avg',
field='sales',
group_by=['category'],
description='Average sales by category'
)
],
visualizations=[
VisualizationRequirement(
type='chart',
chart_type='bar',
description='Bar chart'
)
],
output=OutputRequirement(
format='csv',
description='Export results'
)
)
task_description = "Analyze sales data, filter, aggregate, visualize, and export"
print(f"\n📋 Task: {task_description}")
print(f"Complexity: {classification.complexity.value}")
print(f"Has filters: {len(parameters.filters)}")
print(f"Has aggregations: {len(parameters.aggregations)}")
print(f"Has visualizations: {len(parameters.visualizations)}")
print("-" * 60)
# Decompose
result = decomposer.decompose(classification, parameters, task_description)
print(f"\n✅ Decomposition Result:")
print(f" Subtasks: {len(result.subtasks)}")
print(f" Strategy: {result.execution_strategy}")
print(f" Can parallelize: {result.can_parallelize}")
print(f" Complexity score: {result.complexity_score}")
print(f" Estimated duration: {result.estimated_total_duration}s")
print(f"\n📝 Subtasks:")
for i, subtask in enumerate(result.subtasks, 1):
print(f" {i}. {subtask.name} ({subtask.type.value})")
print(f" ID: {subtask.id}")
print(f" Depends on: {subtask.depends_on if subtask.depends_on else 'None'}")
print(f" Priority: {subtask.priority}")
print(f" Duration: {subtask.estimated_duration}s")
print(f"\n🔗 Dependencies:")
for dep in result.dependencies:
print(f" {dep.subtask_id} depends on {dep.depends_on}")
assert len(result.subtasks) > 1, "Complex task should have multiple subtasks"
print("\n✓ Complex task correctly decomposed")
def test_parallel_decomposition():
"""Test parallel decomposition with multiple data sources"""
print("\n" + "=" * 60)
print("Test 3: Parallel Decomposition (Multiple Sources)")
print("=" * 60)
decomposer = TaskDecomposer()
# Task with multiple data sources
classification = TaskClassification(
primary_task=TaskType.WEB_SCRAPING,
secondary_tasks=[],
complexity=ComplexityLevel.MEDIUM,
estimated_steps=3,
output_format=OutputFormat.JSON,
confidence=0.88,
reasoning="Multi-source data fetching"
)
parameters = ExtractedParameters(
data_sources=[
DataSource(
type='url',
location='https://source1.com/data',
format='json',
description='Source 1'
),
DataSource(
type='url',
location='https://source2.com/data',
format='json',
description='Source 2'
),
DataSource(
type='url',
location='https://source3.com/data',
format='json',
description='Source 3'
)
]
)
task_description = "Fetch data from 3 different sources"
print(f"\n📋 Task: {task_description}")
print(f"Data sources: {len(parameters.data_sources)}")
print("-" * 60)
# Decompose
result = decomposer.decompose(classification, parameters, task_description)
print(f"\n✅ Decomposition Result:")
print(f" Subtasks: {len(result.subtasks)}")
print(f" Strategy: {result.execution_strategy}")
print(f" Can parallelize: {result.can_parallelize}")
print(f"\n📝 Subtasks:")
for subtask in result.subtasks:
parallel_indicator = "🔀" if subtask.can_run_parallel else "➡️"
print(f" {parallel_indicator} {subtask.name}")
print(f" Can run parallel: {subtask.can_run_parallel}")
print(f" Depends on: {subtask.depends_on if subtask.depends_on else 'None'}")
print(f"\n📊 Execution Order (Batches):")
batches = result.get_execution_order()
for i, batch in enumerate(batches, 1):
print(f" Batch {i}: {batch}")
if len(batch) > 1:
print(f" ↳ Can execute in parallel")
assert result.can_parallelize, "Should support parallel execution"
assert result.execution_strategy == 'parallel', "Should use parallel strategy"
print("\n✓ Parallel decomposition working correctly")
def test_execution_order():
"""Test execution order calculation"""
print("\n" + "=" * 60)
print("Test 4: Execution Order Calculation")
print("=" * 60)
decomposer = TaskDecomposer()
# Complex task with dependencies
classification = TaskClassification(
primary_task=TaskType.ML_ANALYSIS,
secondary_tasks=[TaskType.VISUALIZATION],
complexity=ComplexityLevel.COMPLEX,
estimated_steps=4,
output_format=OutputFormat.CSV,
confidence=0.9,
reasoning="Test execution order"
)
parameters = ExtractedParameters(
data_sources=[
DataSource(
type='url',
location='https://example.com/data.csv',
format='csv',
description='Data'
)
],
filters=[FilterCondition(field='status', operator='equals', value='active', description='Active only')],
visualizations=[VisualizationRequirement(type='chart', chart_type='line', description='Line chart')],
output=OutputRequirement(format='csv', description='Export')
)
# Decompose
result = decomposer.decompose(classification, parameters, "Complex task")
print(f"\n📊 Execution Order:")
batches = result.get_execution_order()
for i, batch in enumerate(batches, 1):
print(f"\nBatch {i}:")
for subtask_id in batch:
subtask = result.get_subtask(subtask_id)
print(f" - {subtask.name} (ID: {subtask_id})")
print(f"\n✓ Total batches: {len(batches)}")
print(f"✓ All subtasks covered: {sum(len(b) for b in batches) == len(result.subtasks)}")
def run_all_tests():
"""Run all decomposer tests"""
print("\n" + "=" * 80)
print(" " * 20 + "TASK DECOMPOSER TEST SUITE")
print("=" * 80)
try:
test_simple_task_no_decomposition()
test_complex_task_sequential()
test_parallel_decomposition()
test_execution_order()
print("\n" + "=" * 80)
print(" " * 30 + "ALL TESTS PASSED")
print("=" * 80)
print("\n✅ Task decomposer tests complete!")
print("\n📊 Summary:")
print(" ✓ Simple tasks not decomposed")
print(" ✓ Complex tasks decomposed sequentially")
print(" ✓ Multiple sources decomposed in parallel")
print(" ✓ Execution order calculated correctly")
print(" ✓ Dependencies tracked properly")
except AssertionError as e:
print(f"\n❌ Assertion failed: {e}")
logger.error("Test assertion failed", exc_info=True)
raise
except Exception as e:
print(f"\n❌ Test failed: {e}")
logger.error("Test suite failed", exc_info=True)
raise
if __name__ == "__main__":
run_all_tests()
|