test_scheduler.py
16.7 KB
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
"""U-032 tests: the scheduler's own bookkeeping (loop-closing wiring + real
thread-level concurrency bookkeeping), mocked at the org_level_loop/
org_loop_route/run_goal_to_completion boundary -- this file is not about
re-proving e2e_pipeline/org_level_loop's own mechanics (covered in their own
test files), it's about proving finish_task_lifecycle applies the right
loop-closing step and run_scheduler_once actually runs goals concurrently
(not accidentally serially) while still collecting every result. Real
multi-Goal coverage (RUN_REAL_AGENT_E2E=1) is in src/test_scheduler_e2e.py.
Run: python3 -m unittest src.test_scheduler -v
"""
import os
import tempfile
import threading
import time
import unittest
from unittest.mock import patch
from src import org_level_loop, org_loop_route, schema, scheduler, settings_config, work_graph_execute, work_node_run
class FinishTaskLifecycleTestBase(unittest.TestCase):
def setUp(self):
self.conn = schema.connect(":memory:")
schema.create_schema(self.conn)
self.conn.execute(
"INSERT INTO project (project_id, name, target_folder_path, has_git_repo, status) "
"VALUES ('proj-1', 'P', '/tmp/proj-1', 1, 'active')"
)
self.conn.execute(
"INSERT INTO task (task_id, project_id, goal_text, task_type, status, loop_round, assigned_org_node) "
"VALUES ('task-1', 'proj-1', 'goal', 'goal', 'validating', 0, 'validator')"
)
self.conn.commit()
def tearDown(self):
self.conn.close()
class FinishTaskLifecyclePassTest(FinishTaskLifecycleTestBase):
def test_pass_verdict_closes_task_done(self):
run_result = {
"task_id": "task-1", "doc_artifact_ids": {}, "code_artifact_ids": {},
"verdict": {"verdict": "PASS", "raw_response": "VERDICT: PASS"},
}
result = scheduler.finish_task_lifecycle(self.conn, run_result, "/tmp/proj-1", "goal text")
self.assertEqual(result["final_status"], "done")
status = self.conn.execute("SELECT status FROM task WHERE task_id = 'task-1'").fetchone()[0]
self.assertEqual(status, "done")
class FinishTaskLifecycleFailTest(FinishTaskLifecycleTestBase):
def test_fail_verdict_runs_fix_loop(self):
run_result = {
"task_id": "task-1",
"doc_artifact_ids": {"benchmark": "artifact-b"},
"code_artifact_ids": {},
"verdict": {"verdict": "FAIL", "raw_response": "VERDICT: FAIL\nwall collision broken"},
}
with patch.object(scheduler.e2e_pipeline, "_read_artifact_content", return_value="benchmark content"), \
patch.object(org_level_loop, "run_fix_loop", return_value={"final_status": "done"}) as mock_fix:
result = scheduler.finish_task_lifecycle(self.conn, run_result, "/tmp/proj-1", "goal text")
self.assertEqual(result["final_status"], "done")
mock_fix.assert_called_once()
args, kwargs = mock_fix.call_args
self.assertEqual(args[0], self.conn)
self.assertEqual(args[1], "task-1")
self.assertEqual(args[2], "/tmp/proj-1")
class RunSchedulerOnceTest(unittest.TestCase):
def setUp(self):
self.tmp = tempfile.NamedTemporaryFile(suffix=".db", delete=False)
self.tmp.close()
self.db_path = self.tmp.name
conn = schema.connect(self.db_path)
schema.create_schema(conn)
conn.close()
self.addCleanup(lambda: os.path.exists(self.db_path) and os.remove(self.db_path))
def test_runs_all_goals_and_collects_results_in_order(self):
def fake_run(db_path, target_folder_path, goal_text):
return {"goal_text": goal_text, "final_status": "done"}
goals = [("/tmp/p", "goal-{}".format(i)) for i in range(4)]
with patch.object(scheduler, "run_goal_to_completion", side_effect=fake_run):
results = scheduler.run_scheduler_once(self.db_path, goals, max_workers=2)
self.assertEqual([r["goal_text"] for r in results], [g[1] for g in goals])
self.assertTrue(all("result" in r for r in results))
def test_one_goal_raising_does_not_stop_the_others(self):
def fake_run(db_path, target_folder_path, goal_text):
if goal_text == "goal-bad":
raise RuntimeError("boom")
return {"goal_text": goal_text, "final_status": "done"}
goals = [("/tmp/p", "goal-ok-1"), ("/tmp/p", "goal-bad"), ("/tmp/p", "goal-ok-2")]
with patch.object(scheduler, "run_goal_to_completion", side_effect=fake_run):
results = scheduler.run_scheduler_once(self.db_path, goals, max_workers=3)
self.assertIn("result", results[0])
self.assertIn("error", results[1])
self.assertEqual(results[1]["error"], "boom")
self.assertIn("result", results[2])
def test_max_workers_bounds_real_concurrency(self):
current = [0]
peak = [0]
lock = threading.Lock()
def fake_run(db_path, target_folder_path, goal_text):
with lock:
current[0] += 1
peak[0] = max(peak[0], current[0])
time.sleep(0.05)
with lock:
current[0] -= 1
return {"goal_text": goal_text, "final_status": "done"}
goals = [("/tmp/p", "goal-{}".format(i)) for i in range(6)]
with patch.object(scheduler, "run_goal_to_completion", side_effect=fake_run):
results = scheduler.run_scheduler_once(self.db_path, goals, max_workers=2)
self.assertEqual(len(results), 6)
self.assertLessEqual(peak[0], 2)
self.assertEqual(peak[0], 2, "expected real parallelism up to the max_workers bound, not accidental serial execution")
def test_defaults_max_workers_to_org_concurrency_config(self):
conn = schema.connect(self.db_path)
settings_config.upsert_concurrency_config(conn, max_concurrent_goals=3, updated_by="test")
conn.close()
current = [0]
peak = [0]
lock = threading.Lock()
def fake_run(db_path, target_folder_path, goal_text):
with lock:
current[0] += 1
peak[0] = max(peak[0], current[0])
time.sleep(0.05)
with lock:
current[0] -= 1
return {"goal_text": goal_text, "final_status": "done"}
goals = [("/tmp/p", "goal-{}".format(i)) for i in range(6)]
with patch.object(scheduler, "run_goal_to_completion", side_effect=fake_run):
scheduler.run_scheduler_once(self.db_path, goals, max_workers=None)
self.assertEqual(peak[0], 3)
class ConcurrentSqliteWritesStressTest(unittest.TestCase):
"""Not gated behind RUN_REAL_AGENT_E2E -- doesn't call the real Claude
API, but DOES exercise the actual novel risk in this module's design
(see module docstring's "Threading model" note): multiple threads, each
holding its OWN sqlite connection, writing concurrently to the SAME db
file. e2e_pipeline.run_end_to_end is faked (no real API calls) but
finish_task_lifecycle's own close_task_done still runs for real against
a real connection, so this is a genuine concurrent-write stress test,
not a fully mocked one."""
def setUp(self):
self.tmp = tempfile.NamedTemporaryFile(suffix=".db", delete=False)
self.tmp.close()
self.db_path = self.tmp.name
conn = schema.connect(self.db_path)
schema.create_schema(conn)
conn.execute(
"INSERT INTO project (project_id, name, target_folder_path, has_git_repo, status) "
"VALUES ('proj-1', 'P', '/tmp/proj-1', 1, 'active')"
)
conn.commit()
conn.close()
self.addCleanup(lambda: os.path.exists(self.db_path) and os.remove(self.db_path))
def test_many_concurrent_goals_write_to_the_same_db_file_without_locking_errors(self):
def fake_run_task_lifecycle(conn, task_id, target_folder_path, goal_text):
# task_id already exists -- run_goal_to_completion creates it for
# real via task_create.create_task before calling this; stand in
# for org_node_lifecycle's real queued->...->validating march so
# finish_task_lifecycle's close_task_done (requires 'validating') works.
conn.execute("UPDATE task SET status = 'validating' WHERE task_id = ?", (task_id,))
conn.commit()
time.sleep(0.02) # widen the contention window
return {
"task_id": task_id, "doc_artifact_ids": {}, "code_artifact_ids": {},
"verdict": {"verdict": "PASS", "raw_response": "VERDICT: PASS"},
}
goals = [("/tmp/proj-1", "goal-{}".format(i)) for i in range(10)]
with patch.object(scheduler.e2e_pipeline, "run_task_lifecycle", side_effect=fake_run_task_lifecycle):
results = scheduler.run_scheduler_once(self.db_path, goals, max_workers=5)
self.assertTrue(all("result" in r for r in results), results)
conn = schema.connect(self.db_path)
done_count = conn.execute("SELECT COUNT(*) FROM task WHERE status = 'done'").fetchone()[0]
conn.close()
self.assertEqual(done_count, 10)
class RoutableExceptionTestBase(unittest.TestCase):
"""REQ-06/07/14 failure: work-node-level failures (CorruptPersistedState
/ClassifierBlocked/UsageLimitWaitTimeout) must actually reach
task.status='blocked_pending_human' with the matching blocked_reason --
found missing during the PH4-closure audit (2026-08-02): each exception
was correctly raised and correctly marked its own work_node_execution
'blocked', but nothing ever caught it to apply the task-level
consequence 06's own acceptance text names."""
def setUp(self):
self.tmp = tempfile.NamedTemporaryFile(suffix=".db", delete=False)
self.tmp.close()
self.db_path = self.tmp.name
conn = schema.connect(self.db_path)
schema.create_schema(conn)
conn.execute(
"INSERT INTO project (project_id, name, target_folder_path, has_git_repo, status) "
"VALUES ('proj-1', 'P', '/tmp/proj-1', 1, 'active')"
)
conn.commit()
conn.close()
self.addCleanup(lambda: os.path.exists(self.db_path) and os.remove(self.db_path))
def _run_with_raising_lifecycle(self, exc):
def fake_run_task_lifecycle(conn, task_id, target_folder_path, goal_text):
raise exc
with patch.object(scheduler.e2e_pipeline, "run_task_lifecycle", side_effect=fake_run_task_lifecycle):
result = scheduler.run_goal_to_completion(self.db_path, "/tmp/proj-1", "goal text")
return result
def _assert_task_blocked(self, task_id, blocked_reason):
conn = schema.connect(self.db_path)
row = conn.execute("SELECT status, blocked_reason FROM task WHERE task_id = ?", (task_id,)).fetchone()
event = conn.execute(
"SELECT event_type FROM execution_event WHERE task_id = ? ORDER BY rowid DESC LIMIT 1", (task_id,)
).fetchone()
conn.close()
self.assertEqual(row, ("blocked_pending_human", blocked_reason))
self.assertEqual(event[0], "task_status_changed")
class CorruptPersistedStateRoutingTest(RoutableExceptionTestBase):
def test_routes_to_blocked_pending_human(self):
result = self._run_with_raising_lifecycle(work_node_run.CorruptPersistedStateError("boom"))
self.assertEqual(result["final_status"], "blocked_pending_human")
self.assertEqual(result["blocked_reason"], "corrupt_persisted_state")
self._assert_task_blocked(result["task_id"], "corrupt_persisted_state")
class ClassifierBlockedRoutingTest(RoutableExceptionTestBase):
def test_routes_to_blocked_pending_human(self):
result = self._run_with_raising_lifecycle(work_graph_execute.ClassifierBlockedError("boom"))
self.assertEqual(result["final_status"], "blocked_pending_human")
self.assertEqual(result["blocked_reason"], "classifier_blocked")
self._assert_task_blocked(result["task_id"], "classifier_blocked")
class UsageLimitWaitTimeoutRoutingTest(RoutableExceptionTestBase):
def test_routes_to_blocked_pending_human(self):
result = self._run_with_raising_lifecycle(work_node_run.UsageLimitWaitTimeoutError("boom"))
self.assertEqual(result["final_status"], "blocked_pending_human")
self.assertEqual(result["blocked_reason"], "usage_limit_wait_timeout")
self._assert_task_blocked(result["task_id"], "usage_limit_wait_timeout")
class ConsistencyCheckFailedRoutingTest(RoutableExceptionTestBase):
def test_routes_to_blocked_pending_human(self):
result = self._run_with_raising_lifecycle(
scheduler.work_graph_orchestrate.ConsistencyCheckFailedError("boom")
)
self.assertEqual(result["final_status"], "blocked_pending_human")
self.assertEqual(result["blocked_reason"], "prd_consistency_check_failed")
self._assert_task_blocked(result["task_id"], "prd_consistency_check_failed")
class UnroutedExceptionStillPropagatesTest(RoutableExceptionTestBase):
def test_other_exceptions_are_not_swallowed(self):
with self.assertRaises(RuntimeError):
self._run_with_raising_lifecycle(RuntimeError("something else entirely"))
def _fix_loop_trigger(org_node, prompt, target_folder_path, timeout=300):
"""org_node_trigger.trigger_org_node fake for org_level_loop.run_fix_loop's
3 perspective calls (all agree 'coder') + fixer + verify -- verify always
fails, so route_org_loop keeps incrementing loop_round on retries."""
if "CATEGORY:" in prompt:
return "CATEGORY: coder\nDETAIL: because reasons"
if org_node == "coder":
return "Fixed it."
if org_node == "validator":
return "VERDICT: FAIL\nstill broken"
raise AssertionError("unexpected call: " + org_node)
class SchedulerContinuesPastBlockedTaskTest(unittest.TestCase):
"""REQ-05 failure / REQ-09 boundary, against the REAL scheduler (U-032) --
test_org_loop_route.py's own test for this literally says "no scheduler
exists yet to test against directly" (stale as of U-032). One Goal's
task is pre-seeded at loop_round=3 so its fix-loop attempt hits
org_loop_route.LoopLimitReachedError for real (route_org_loop's own real
blocked_pending_human write, not a mock) while the others complete via
close_task_done -- proving the scheduler doesn't stop serving the rest
of the batch."""
def setUp(self):
self.tmp = tempfile.NamedTemporaryFile(suffix=".db", delete=False)
self.tmp.close()
self.db_path = self.tmp.name
conn = schema.connect(self.db_path)
schema.create_schema(conn)
conn.execute(
"INSERT INTO project (project_id, name, target_folder_path, has_git_repo, status) "
"VALUES ('proj-1', 'P', '/tmp/proj-1', 1, 'active')"
)
conn.commit()
conn.close()
self.addCleanup(lambda: os.path.exists(self.db_path) and os.remove(self.db_path))
def test_one_task_hitting_loop_limit_does_not_block_the_others(self):
def fake_run_task_lifecycle(conn, task_id, target_folder_path, goal_text):
conn.execute("UPDATE task SET status = 'validating' WHERE task_id = ?", (task_id,))
conn.commit()
if goal_text == "goal-doomed":
conn.execute("UPDATE task SET loop_round = 3 WHERE task_id = ?", (task_id,))
conn.commit()
verdict = {"verdict": "FAIL", "raw_response": "VERDICT: FAIL\nstill broken"}
else:
verdict = {"verdict": "PASS", "raw_response": "VERDICT: PASS"}
return {
"task_id": task_id, "doc_artifact_ids": {"benchmark": "artifact-b"},
"code_artifact_ids": {}, "verdict": verdict,
}
goals = [("/tmp/proj-1", "goal-ok-1"), ("/tmp/proj-1", "goal-doomed"), ("/tmp/proj-1", "goal-ok-2")]
with patch.object(scheduler.e2e_pipeline, "run_task_lifecycle", side_effect=fake_run_task_lifecycle), \
patch.object(scheduler.e2e_pipeline, "_read_artifact_content", return_value="benchmark content"), \
patch("src.org_node_trigger.trigger_org_node", side_effect=_fix_loop_trigger):
results = scheduler.run_scheduler_once(self.db_path, goals, max_workers=3)
by_goal = {r["goal_text"]: r for r in results}
self.assertEqual(by_goal["goal-ok-1"]["result"]["final_status"], "done")
self.assertEqual(by_goal["goal-ok-2"]["result"]["final_status"], "done")
self.assertIn("error", by_goal["goal-doomed"])
conn = schema.connect(self.db_path)
doomed_status = conn.execute(
"SELECT status, blocked_reason FROM task WHERE goal_text = 'goal-doomed'"
).fetchone()
conn.close()
self.assertEqual(doomed_status, ("blocked_pending_human", "loop_limit_reached"))
if __name__ == "__main__":
unittest.main()