test_work_node_run.py
14.3 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
"""U-013 tests: c_work_node_run's contract (schema validation, retry state
machine, quota-wait, execution_log_file lifecycle) with a fake `run_fn`, plus
real git worktree isolation + merge -- REQ-03's boundary case (two independent
nodes, separate worktrees, merge without conflict) needs no LLM call at all,
so it's tested for real here, not mocked.
Run: python3 -m unittest src.test_work_node_run -v
"""
import json
import os
import subprocess
import tempfile
import unittest
from src import schema, work_node_run
_IN_SCHEMA = {"type": "object", "required": ["goal"]}
_OUT_SCHEMA = {"type": "object", "required": ["value"]}
def _init_git_repo(path):
subprocess.run(["git", "init"], cwd=path, check=True, capture_output=True)
with open(os.path.join(path, "README.md"), "w") as f:
f.write("seed\n")
subprocess.run(["git", "add", "README.md"], cwd=path, check=True, capture_output=True)
subprocess.run(
["git"] + work_node_run._GIT_IDENTITY + ["commit", "-m", "seed"],
cwd=path, check=True, capture_output=True,
)
class WorkNodeRunTestBase(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, assigned_org_node) "
"VALUES ('task-1', 'proj-1', 'goal', 'goal', 'coding', 'coder')"
)
self.conn.execute(
"INSERT INTO work_graph_run (run_id, task_id, org_node, graph_manifest, status) "
"VALUES ('run-1', 'task-1', 'coder', '{}', 'running')"
)
self.conn.execute(
"INSERT INTO skill (skill_id, owner_org_node, file_path, current_git_commit_sha, source, status) "
"VALUES ('skill-1', 'coder', 'skills/skill-1/', 'sha', 'new', 'active')"
)
self.conn.execute(
"INSERT INTO work_node_execution (node_exec_id, run_id, node_id, subagent_type, skill_ref, "
"input_schema_ref, output_schema_ref, input_payload, status) "
"VALUES ('node-1', 'run-1', 'n1', 'coder', 'skill-1', 'in.json', 'out.json', '{}', 'pending')"
)
self.conn.commit()
def tearDown(self):
self.conn.close()
class InputValidationTest(WorkNodeRunTestBase):
def test_invalid_input_rejected_before_execution_starts(self):
with self.assertRaises(work_node_run.InvalidInputError):
work_node_run.run_work_node(
self.conn, "node-1", {}, _IN_SCHEMA, _OUT_SCHEMA, run_fn=lambda cwd, model=None: {"value": 1}
)
status = self.conn.execute("SELECT status FROM work_node_execution WHERE node_exec_id = 'node-1'").fetchone()[0]
self.assertEqual(status, "pending")
count = self.conn.execute("SELECT COUNT(*) FROM execution_log_file").fetchone()[0]
self.assertEqual(count, 0)
class HappyPathTest(WorkNodeRunTestBase):
def test_valid_output_marks_node_done(self):
output = work_node_run.run_work_node(
self.conn, "node-1", {"goal": "x"}, _IN_SCHEMA, _OUT_SCHEMA, run_fn=lambda cwd, model=None: {"value": 42}
)
self.assertEqual(output, {"value": 42})
row = self.conn.execute(
"SELECT status, output_payload, retry_count FROM work_node_execution WHERE node_exec_id = 'node-1'"
).fetchone()
self.assertEqual(row[0], "done")
self.assertEqual(json.loads(row[1]), {"value": 42})
self.assertEqual(row[2], 0)
def test_execution_log_file_created_active_then_closed(self):
seen_status_during_run = []
def run_fn(cwd, model=None):
seen_status_during_run.append(
self.conn.execute("SELECT status FROM execution_log_file").fetchone()[0]
)
return {"value": 1}
work_node_run.run_work_node(self.conn, "node-1", {"goal": "x"}, _IN_SCHEMA, _OUT_SCHEMA, run_fn=run_fn)
self.assertEqual(seen_status_during_run, ["active"])
final_status = self.conn.execute("SELECT status FROM execution_log_file").fetchone()[0]
self.assertEqual(final_status, "closed")
def test_log_file_closed_even_when_run_fn_raises(self):
def boom(cwd, model=None):
raise RuntimeError("node blew up")
with self.assertRaises(RuntimeError):
work_node_run.run_work_node(self.conn, "node-1", {"goal": "x"}, _IN_SCHEMA, _OUT_SCHEMA, run_fn=boom)
final_status = self.conn.execute("SELECT status FROM execution_log_file").fetchone()[0]
self.assertEqual(final_status, "closed")
class RetryOnSchemaFailureTest(WorkNodeRunTestBase):
def test_retries_then_succeeds(self):
attempts = {"n": 0}
def run_fn(cwd, model=None):
attempts["n"] += 1
if attempts["n"] < 3:
return {"wrong_key": True}
return {"value": "ok"}
output = work_node_run.run_work_node(
self.conn, "node-1", {"goal": "x"}, _IN_SCHEMA, _OUT_SCHEMA, run_fn=run_fn, max_retries=2
)
self.assertEqual(output, {"value": "ok"})
row = self.conn.execute(
"SELECT status, retry_count FROM work_node_execution WHERE node_exec_id = 'node-1'"
).fetchone()
self.assertEqual(row, ("done", 2))
def test_exceeding_max_retries_blocks_the_node(self):
with self.assertRaises(work_node_run.SchemaValidationFailedError):
work_node_run.run_work_node(
self.conn, "node-1", {"goal": "x"}, _IN_SCHEMA, _OUT_SCHEMA,
run_fn=lambda cwd, model=None: {"wrong_key": True}, max_retries=2,
)
row = self.conn.execute(
"SELECT status, retry_count FROM work_node_execution WHERE node_exec_id = 'node-1'"
).fetchone()
self.assertEqual(row, ("blocked", 3))
class UsageLimitWaitTest(WorkNodeRunTestBase):
def setUp(self):
super().setUp()
self.sleeps = []
self.clock = [0.0]
def _sleep(self, seconds):
self.sleeps.append(seconds)
self.clock[0] += seconds
def _now(self):
return self.clock[0]
def test_session_limit_then_recovers(self):
attempts = {"n": 0}
def run_fn(cwd, model=None):
attempts["n"] += 1
if attempts["n"] == 1:
work_node_run.raise_if_usage_limited("Error: You've hit your session limit")
return {"value": "recovered"}
output = work_node_run.run_work_node(
self.conn, "node-1", {"goal": "x"}, _IN_SCHEMA, _OUT_SCHEMA, run_fn=run_fn,
sleep=self._sleep, now=self._now,
)
self.assertEqual(output, {"value": "recovered"})
self.assertEqual(self.sleeps, [5 * 60])
row = self.conn.execute(
"SELECT quota_limit_type FROM work_node_execution WHERE node_exec_id = 'node-1'"
).fetchone()
self.assertEqual(row[0], "session")
event = self.conn.execute(
"SELECT event_type FROM execution_event WHERE node_exec_id = 'node-1'"
).fetchone()
self.assertEqual(event[0], "quota_wait_started")
def test_opus_quota_retries_immediately_on_downgraded_model_no_backoff(self):
# REQ-14 boundary: "不走退避轮询，直接降级到非 Opus 模型重试" -- an actual
# retry with a different model, not just detect-and-fail.
calls = []
def run_fn(cwd, model=None):
calls.append(model)
if len(calls) == 1:
work_node_run.raise_if_usage_limited("You've hit your Opus limit")
return {"value": "recovered on " + str(model)}
output = work_node_run.run_work_node(
self.conn, "node-1", {"goal": "x"}, _IN_SCHEMA, _OUT_SCHEMA, run_fn=run_fn,
sleep=self._sleep, now=self._now,
)
self.assertEqual(calls, [None, "claude-sonnet-5"])
self.assertEqual(output, {"value": "recovered on claude-sonnet-5"})
self.assertEqual(self.sleeps, []) # no backoff wait for opus
status = self.conn.execute("SELECT status FROM work_node_execution WHERE node_exec_id = 'node-1'").fetchone()[0]
self.assertEqual(status, "done")
def test_opus_quota_custom_downgrade_model_is_used(self):
calls = []
def run_fn(cwd, model=None):
calls.append(model)
if len(calls) == 1:
work_node_run.raise_if_usage_limited("You've hit your Opus limit")
return {"value": "ok"}
work_node_run.run_work_node(
self.conn, "node-1", {"goal": "x"}, _IN_SCHEMA, _OUT_SCHEMA, run_fn=run_fn,
sleep=self._sleep, now=self._now, opus_downgrade_model="claude-fable-5",
)
self.assertEqual(calls, [None, "claude-fable-5"])
def test_opus_quota_persisting_after_downgrade_raises_timeout(self):
# a non-opus model shouldn't hit an opus-specific quota again -- if it
# somehow does, this doesn't loop forever chasing it
def run_fn(cwd, model=None):
work_node_run.raise_if_usage_limited("You've hit your Opus limit")
with self.assertRaises(work_node_run.UsageLimitWaitTimeoutError):
work_node_run.run_work_node(
self.conn, "node-1", {"goal": "x"}, _IN_SCHEMA, _OUT_SCHEMA, run_fn=run_fn,
sleep=self._sleep, now=self._now,
)
self.assertEqual(self.sleeps, [])
def test_session_timeout_after_8_hours_blocks_node(self):
def run_fn(cwd, model=None):
work_node_run.raise_if_usage_limited("You've hit your session limit")
with self.assertRaises(work_node_run.UsageLimitWaitTimeoutError):
work_node_run.run_work_node(
self.conn, "node-1", {"goal": "x"}, _IN_SCHEMA, _OUT_SCHEMA, run_fn=run_fn,
sleep=self._sleep, now=self._now,
)
self.assertGreaterEqual(self.clock[0], 8 * 3600)
status = self.conn.execute("SELECT status FROM work_node_execution WHERE node_exec_id = 'node-1'").fetchone()[0]
self.assertEqual(status, "blocked")
def test_weekly_limit_then_recovers(self):
# previously untested quota_limit_type -- session/opus were covered,
# weekly wasn't, even though the detection regex and timeout table
# both already supported it
attempts = {"n": 0}
def run_fn(cwd, model=None):
attempts["n"] += 1
if attempts["n"] == 1:
work_node_run.raise_if_usage_limited("Error: You've hit your weekly limit")
return {"value": "recovered"}
work_node_run.run_work_node(
self.conn, "node-1", {"goal": "x"}, _IN_SCHEMA, _OUT_SCHEMA, run_fn=run_fn,
sleep=self._sleep, now=self._now,
)
quota_type = self.conn.execute(
"SELECT quota_limit_type FROM work_node_execution WHERE node_exec_id = 'node-1'"
).fetchone()[0]
self.assertEqual(quota_type, "weekly")
def test_weekly_timeout_after_9_days_blocks_node(self):
def run_fn(cwd, model=None):
work_node_run.raise_if_usage_limited("You've hit your weekly limit")
with self.assertRaises(work_node_run.UsageLimitWaitTimeoutError):
work_node_run.run_work_node(
self.conn, "node-1", {"goal": "x"}, _IN_SCHEMA, _OUT_SCHEMA, run_fn=run_fn,
sleep=self._sleep, now=self._now,
)
self.assertGreaterEqual(self.clock[0], 9 * 24 * 3600)
status = self.conn.execute("SELECT status FROM work_node_execution WHERE node_exec_id = 'node-1'").fetchone()[0]
self.assertEqual(status, "blocked")
class RealGitWorktreeIsolationTest(WorkNodeRunTestBase):
"""REQ-03 boundary: two independent nodes, each in its own git worktree,
merged back with no conflict. Real git, no LLM call needed."""
def setUp(self):
super().setUp()
self.tmp = tempfile.TemporaryDirectory()
self.addCleanup(self.tmp.cleanup)
_init_git_repo(self.tmp.name)
self.conn.execute(
"INSERT INTO work_node_execution (node_exec_id, run_id, node_id, subagent_type, skill_ref, "
"input_schema_ref, output_schema_ref, input_payload, status) "
"VALUES ('node-2', 'run-1', 'n2', 'coder', 'skill-1', 'in.json', 'out.json', '{}', 'pending')"
)
self.conn.commit()
def _write_file_run_fn(self, filename, content):
def run_fn(cwd, model=None):
with open(os.path.join(cwd, filename), "w") as f:
f.write(content)
subprocess.run(["git", "add", filename], cwd=cwd, check=True, capture_output=True)
subprocess.run(
["git"] + work_node_run._GIT_IDENTITY + ["commit", "-m", "add " + filename],
cwd=cwd, check=True, capture_output=True,
)
return {"value": filename}
return run_fn
def test_two_independent_nodes_isolated_and_merged_without_conflict(self):
work_node_run.run_work_node(
self.conn, "node-1", {"goal": "x"}, _IN_SCHEMA, _OUT_SCHEMA,
run_fn=self._write_file_run_fn("module_a.txt", "module a content"),
needs_worktree=True, repo_path=self.tmp.name,
)
work_node_run.run_work_node(
self.conn, "node-2", {"goal": "x"}, _IN_SCHEMA, _OUT_SCHEMA,
run_fn=self._write_file_run_fn("module_b.txt", "module b content"),
needs_worktree=True, repo_path=self.tmp.name,
)
self.assertTrue(os.path.isfile(os.path.join(self.tmp.name, "module_a.txt")))
self.assertTrue(os.path.isfile(os.path.join(self.tmp.name, "module_b.txt")))
row1 = self.conn.execute(
"SELECT git_worktree_ref FROM work_node_execution WHERE node_exec_id = 'node-1'"
).fetchone()[0]
row2 = self.conn.execute(
"SELECT git_worktree_ref FROM work_node_execution WHERE node_exec_id = 'node-2'"
).fetchone()[0]
self.assertNotEqual(row1, row2)
self.assertIn("node-1", row1)
self.assertIn("node-2", row2)
log = subprocess.run(
["git", "log", "--oneline"], cwd=self.tmp.name, check=True, capture_output=True, text=True
)
self.assertIn("module_a.txt", log.stdout)
self.assertIn("module_b.txt", log.stdout)
if __name__ == "__main__":
unittest.main()