File size: 11,723 Bytes
aef804e | 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 | """
Shared fixtures for workflow integration tests.
Provides database sessions, mock LLM providers, mock WebSocket managers,
and sample workflow/episode data for integration testing.
Key principles:
- Real database (SQLite in-memory) for persistence testing
- Mocked external services (LLM providers, WebSocket) to prevent flakiness
- Transaction rollback after each test for isolation
"""
import os
import pytest
import tempfile
import uuid
from datetime import datetime, timedelta
from unittest.mock import AsyncMock, MagicMock
from sqlalchemy import create_engine
from sqlalchemy.orm import Session, sessionmaker
# Set TESTING environment variable BEFORE any imports
os.environ["TESTING"] = "1"
# Add parent directory to path for imports
import sys
from pathlib import Path
sys.path.insert(0, str(Path(__file__).parent.parent.parent.parent))
from core.database import Base
from core.models import (
WorkflowExecution, WorkflowExecutionStatus,
AgentEpisode, EpisodeSegment, EpisodeOutcome,
ChatSession, CanvasAudit, AgentFeedback
)
@pytest.fixture(scope="function")
def db_session():
"""
Create a fresh in-memory database for each test.
Uses SQLite in-memory database with transaction rollback for test isolation.
All tables are created before the test and cleaned up after.
"""
# Use in-memory SQLite for tests
engine = create_engine(
"sqlite:///:memory:",
connect_args={"check_same_thread": False},
echo=False
)
# Create all tables
try:
Base.metadata.create_all(engine, checkfirst=True)
except Exception as e:
# If create_all fails, create tables individually
for table in Base.metadata.tables.values():
try:
table.create(engine, checkfirst=True)
except Exception:
continue
# Create session
TestingSessionLocal = sessionmaker(autocommit=False, autoflush=False, bind=engine)
session = TestingSessionLocal()
yield session
# Cleanup
session.close()
engine.dispose()
@pytest.fixture(scope="function")
def mock_llm_provider():
"""
AsyncMock for LLM provider calls.
Mocks both call_llm() and stream_llm() methods to prevent
external API calls during testing.
"""
mock_provider = AsyncMock()
# Mock call_llm to return success response
async def mock_call_llm(*args, **kwargs):
return {
"result": "success",
"content": "Mock LLM response",
"usage": {
"prompt_tokens": 10,
"completion_tokens": 20,
"total_tokens": 30
}
}
# Mock stream_llm to return async generator
async def mock_stream_llm(*args, **kwargs):
chunks = [
{"choices": [{"delta": {"content": "Mock "}, "finish_reason": None}], "usage": None},
{"choices": [{"delta": {"content": "streaming "}, "finish_reason": None}], "usage": None},
{"choices": [{"delta": {"content": "response"}, "finish_reason": None}], "usage": None},
{"choices": [{"delta": {}, "finish_reason": "stop"}],
"usage": {"prompt_tokens": 10, "completion_tokens": 20, "total_tokens": 30}}
]
for chunk in chunks:
yield chunk
mock_provider.call_llm = mock_call_llm
mock_provider.stream_llm = mock_stream_llm
return mock_provider
@pytest.fixture(scope="function")
def mock_websocket_manager():
"""
MagicMock for WebSocket notifications.
Tracks all WebSocket calls for verification in tests.
"""
mock_ws = MagicMock()
# Mock notification methods
mock_ws.notify_workflow_status = AsyncMock()
mock_ws.broadcast_message = AsyncMock()
mock_ws.send_message = AsyncMock()
# Track calls for verification
mock_ws.reset_mock()
return mock_ws
@pytest.fixture(scope="function")
def sample_workflow():
"""
Valid workflow definitions for tests.
Returns a dict with three workflow variations:
- simple: 2-step linear execution
- branching: if/else conditional logic
- error_handling: try/catch error recovery
"""
return {
"simple": {
"id": "simple_workflow",
"nodes": [
{
"id": "step1",
"title": "First Step",
"type": "action",
"config": {
"action": "collect_data",
"service": "data_service",
"parameters": {"source": "api"}
}
},
{
"id": "step2",
"title": "Second Step",
"type": "action",
"config": {
"action": "process_data",
"service": "processing_service",
"parameters": {"mode": "batch"}
}
}
],
"connections": [
{"source": "step1", "target": "step2"}
]
},
"branching": {
"id": "branching_workflow",
"nodes": [
{
"id": "step1",
"title": "Evaluate Condition",
"type": "action",
"config": {
"action": "evaluate",
"service": "logic_service",
"parameters": {}
}
},
{
"id": "true_branch",
"title": "True Branch",
"type": "action",
"config": {
"action": "handle_true",
"service": "logic_service",
"parameters": {"branch": "true"}
}
},
{
"id": "false_branch",
"title": "False Branch",
"type": "action",
"config": {
"action": "handle_false",
"service": "logic_service",
"parameters": {"branch": "false"}
}
}
],
"connections": [
{"source": "step1", "target": "true_branch", "condition": "${step1.result} == true"},
{"source": "step1", "target": "false_branch", "condition": "${step1.result} == false"}
]
},
"error_handling": {
"id": "error_handling_workflow",
"nodes": [
{
"id": "step1",
"title": "Risky Step",
"type": "action",
"config": {
"action": "risky_operation",
"service": "risky_service",
"parameters": {"continue_on_error": True}
}
},
{
"id": "step2",
"title": "Recovery Step",
"type": "action",
"config": {
"action": "recover",
"service": "recovery_service",
"parameters": {}
}
}
],
"connections": [
{"source": "step1", "target": "step2"}
]
}
}
@pytest.fixture(scope="function")
def sample_episode_context(db_session: Session):
"""
Episode context for segmentation tests.
Creates a realistic episode context with:
- ChatSession with messages
- Canvas presentation events
- User feedback data
"""
# Create ChatSession with messages
chat_session = ChatSession(
id=str(uuid.uuid4()),
user_id="test_user",
title="Test Episode Session",
metadata_json={"agent_id": "test_agent"}
)
db_session.add(chat_session)
# Create sample canvas presentation
canvas_audit = CanvasAudit(
id=str(uuid.uuid4()),
canvas_id="test_canvas_123",
canvas_type="line_chart",
agent_id="test_agent",
user_id="test_user",
session_id=chat_session.id,
title="Sales Performance Chart",
config={"data": [1, 2, 3, 4, 5]},
status="presented"
)
db_session.add(canvas_audit)
# Create sample user feedback
agent_feedback = AgentFeedback(
id=str(uuid.uuid4()),
agent_id="test_agent",
user_id="test_user",
session_id=chat_session.id,
feedback_type="thumbs_up",
feedback_value=1.0,
comment="Great analysis!"
)
db_session.add(agent_feedback)
db_session.commit()
return {
"chat_session": chat_session,
"canvas_audit": canvas_audit,
"agent_feedback": agent_feedback,
"messages": [
{
"role": "user",
"content": "Show me the sales data",
"timestamp": datetime.utcnow() - timedelta(minutes=10)
},
{
"role": "assistant",
"content": "Here's the sales performance chart",
"timestamp": datetime.utcnow() - timedelta(minutes=9),
"canvas_id": canvas_audit.canvas_id
},
{
"role": "user",
"content": "Great analysis!",
"timestamp": datetime.utcnow() - timedelta(minutes=8),
"feedback_id": agent_feedback.id
}
]
}
@pytest.fixture(scope="function")
def sample_episode(db_session: Session):
"""
Create a sample AgentEpisode with segments for testing.
Returns an episode with 3 segments representing a simple workflow.
"""
episode_id = str(uuid.uuid4())
episode = AgentEpisode(
id=episode_id,
agent_id="test_agent",
user_id="test_user",
workflow_id="test_workflow",
outcome=EpisodeOutcome.SUCCESS,
title="Test Episode",
summary="Test episode with multiple segments",
start_time=datetime.utcnow() - timedelta(minutes=10),
end_time=datetime.utcnow()
)
db_session.add(episode)
# Create segments
segment1 = EpisodeSegment(
id=str(uuid.uuid4()),
episode_id=episode_id,
segment_type="action",
title="Data Collection",
content="Collected data from API",
start_time=datetime.utcnow() - timedelta(minutes=10),
end_time=datetime.utcnow() - timedelta(minutes=8),
metadata={"action": "collect_data", "source": "api"}
)
db_session.add(segment1)
segment2 = EpisodeSegment(
id=str(uuid.uuid4()),
episode_id=episode_id,
segment_type="action",
title="Data Processing",
content="Processed data in batch mode",
start_time=datetime.utcnow() - timedelta(minutes=8),
end_time=datetime.utcnow() - timedelta(minutes=5),
metadata={"action": "process_data", "mode": "batch"}
)
db_session.add(segment2)
segment3 = EpisodeSegment(
id=str(uuid.uuid4()),
episode_id=episode_id,
segment_type="result",
title="Result Presentation",
content="Presented results to user",
start_time=datetime.utcnow() - timedelta(minutes=5),
end_time=datetime.utcnow(),
metadata={"action": "present_results"}
)
db_session.add(segment3)
db_session.commit()
return {
"episode": episode,
"segments": [segment1, segment2, segment3]
}
|