test_work_graph_orchestrate.py
19.8 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
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
"""U-031 tests: work_graph_orchestrate.py -- the graph_manifest -> per-node
execution bridge closed during the REQ-01~14 regression audit. Real sqlite,
run_fn mocked at the claude subprocess boundary (execute_work_graph is
tested for real elsewhere, in test_work_graph_execute.py / the 2026-08-01
spike -- this module's own job is orchestration, not re-proving that).
Run: python3 -m unittest src.test_work_graph_orchestrate -v
"""
import json
import os
import tempfile
import unittest
from unittest.mock import patch
from src import execution_log, paths, schema, work_graph_execute, work_graph_orchestrate as wgo, work_node_run
class TopologicalOrderTest(unittest.TestCase):
def test_linear_chain_via_depends_on(self):
manifest = {
"nodes": [
{"node_id": "brd", "depends_on": []},
{"node_id": "prd", "depends_on": ["brd"]},
{"node_id": "sdd", "depends_on": ["prd"]},
],
"edges": [],
}
self.assertEqual([n["node_id"] for n in wgo.topological_order(manifest)], ["brd", "prd", "sdd"])
def test_linear_chain_via_edges_only(self):
# real LLM output might populate edges but not each node's own
# depends_on -- must still order correctly
manifest = {
"nodes": [{"node_id": "a"}, {"node_id": "b"}, {"node_id": "c"}],
"edges": [{"from": "a", "to": "b"}, {"from": "b", "to": "c"}],
}
self.assertEqual([n["node_id"] for n in wgo.topological_order(manifest)], ["a", "b", "c"])
def test_diamond_fan_out_fan_in(self):
manifest = {
"nodes": [
{"node_id": "n1", "depends_on": []},
{"node_id": "n2", "depends_on": ["n1"]},
{"node_id": "n3", "depends_on": ["n1"]},
{"node_id": "n4", "depends_on": ["n2", "n3"]},
],
"edges": [],
}
order = [n["node_id"] for n in wgo.topological_order(manifest)]
self.assertEqual(order[0], "n1")
self.assertEqual(order[-1], "n4")
self.assertEqual(set(order[1:3]), {"n2", "n3"})
def test_cycle_raises(self):
manifest = {
"nodes": [{"node_id": "x", "depends_on": ["y"]}, {"node_id": "y", "depends_on": ["x"]}],
"edges": [],
}
with self.assertRaises(ValueError):
wgo.topological_order(manifest)
def test_independent_nodes_ordered_deterministically(self):
manifest = {"nodes": [{"node_id": "b"}, {"node_id": "a"}], "edges": []}
self.assertEqual([n["node_id"] for n in wgo.topological_order(manifest)], ["a", "b"])
class RunGraphTestBase(unittest.TestCase):
def setUp(self):
# DU-01: run_fn now really calls execution_log.append_log(), which
# writes to paths.log_file_path() (default ~/.graphlemon/logs/...) --
# isolate that under a throwaway tempdir so real (non-mocked)
# run_work_node/run_fn calls in this test module never touch the
# developer's actual home directory, same pattern as test_paths.py.
self.home_tmp = tempfile.TemporaryDirectory()
self.addCleanup(self.home_tmp.cleanup)
self.old_graphlemon_home = os.environ.get("GRAPHLEMON_HOME")
os.environ["GRAPHLEMON_HOME"] = self.home_tmp.name
self.addCleanup(self._restore_graphlemon_home)
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', 'planner')"
)
self.conn.execute(
"INSERT INTO work_graph_run (run_id, task_id, org_node, graph_manifest, status) "
"VALUES ('run-1', 'task-1', 'planner', '{}', 'running')"
)
self.conn.commit()
def _restore_graphlemon_home(self):
if self.old_graphlemon_home is None:
os.environ.pop("GRAPHLEMON_HOME", None)
else:
os.environ["GRAPHLEMON_HOME"] = self.old_graphlemon_home
def tearDown(self):
self.conn.close()
_OUT_SCHEMA = {"type": "object", "required": ["content"]}
_IN_SCHEMA = {"type": "object", "required": ["node_id"]}
class RunGraphHappyPathTest(RunGraphTestBase):
def test_runs_nodes_in_order_and_returns_outputs(self):
manifest = {
"nodes": [
{"node_id": "brd", "artifact_type": "brd", "depends_on": []},
{"node_id": "prd", "artifact_type": "prd", "depends_on": ["brd"]},
],
"edges": [],
}
calls = []
def build_prompt(node, outputs):
calls.append((node["node_id"], dict(outputs)))
return "prompt for " + node["node_id"]
with patch.object(work_graph_execute, "write_workflow_script"), \
patch.object(work_graph_execute, "execute_work_graph") as mock_execute:
mock_execute.side_effect = [{"content": "brd text"}, {"content": "prd text"}]
outputs = wgo.run_graph(
self.conn, "run-1", "planner", "planner-doc-writing", "/tmp/proj-1", manifest,
build_prompt, _IN_SCHEMA, _OUT_SCHEMA,
)
self.assertEqual(outputs, {"brd": {"content": "brd text"}, "prd": {"content": "prd text"}})
self.assertEqual(calls[0], ("brd", {}))
self.assertEqual(calls[1], ("prd", {"brd": {"content": "brd text"}}))
def test_creates_work_node_execution_rows_and_placeholder_skill(self):
manifest = {"nodes": [{"node_id": "brd", "depends_on": []}], "edges": []}
with patch.object(work_graph_execute, "write_workflow_script"), \
patch.object(work_graph_execute, "execute_work_graph", return_value={"content": "x"}):
wgo.run_graph(
self.conn, "run-1", "planner", "planner-doc-writing", "/tmp/proj-1", manifest,
lambda node, outputs: "p", _IN_SCHEMA, _OUT_SCHEMA,
)
row = self.conn.execute(
"SELECT status, subagent_type, skill_ref FROM work_node_execution WHERE run_id = 'run-1' AND node_id = 'brd'"
).fetchone()
self.assertEqual(row, ("done", "planner", "planner-doc-writing"))
skill_row = self.conn.execute("SELECT owner_org_node FROM skill WHERE skill_id = 'planner-doc-writing'").fetchone()
self.assertEqual(skill_row[0], "planner")
def test_resumes_without_rerunning_done_nodes(self):
manifest = {
"nodes": [
{"node_id": "brd", "depends_on": []},
{"node_id": "prd", "depends_on": ["brd"]},
],
"edges": [],
}
calls = []
def build_prompt(node, outputs):
return "p-" + node["node_id"]
with patch.object(work_graph_execute, "write_workflow_script"), \
patch.object(work_graph_execute, "execute_work_graph") as mock_execute:
mock_execute.side_effect = lambda cwd, name, args, schema, timeout=600: calls.append(name) or {"content": "c-" + name}
wgo.run_graph(
self.conn, "run-1", "planner", "planner-doc-writing", "/tmp/proj-1", manifest,
build_prompt, _IN_SCHEMA, _OUT_SCHEMA,
)
self.assertEqual(len(calls), 2)
# simulate a restart: run_graph called again for the same run_id
with patch.object(work_graph_execute, "write_workflow_script"), \
patch.object(work_graph_execute, "execute_work_graph") as mock_execute2:
mock_execute2.side_effect = AssertionError("should not be called -- both nodes are already done")
outputs = wgo.run_graph(
self.conn, "run-1", "planner", "planner-doc-writing", "/tmp/proj-1", manifest,
build_prompt, _IN_SCHEMA, _OUT_SCHEMA,
)
self.assertEqual(set(outputs.keys()), {"brd", "prd"})
class RunGraphUsageLimitTest(RunGraphTestBase):
def test_usage_limit_reached_translates_to_quota_wait(self):
manifest = {"nodes": [{"node_id": "brd", "depends_on": []}], "edges": []}
attempts = {"n": 0}
def fake_execute(cwd, name, args, output_schema, timeout=600):
attempts["n"] += 1
if attempts["n"] == 1:
raise work_graph_execute.UsageLimitReachedError("hit your session limit", "session")
return {"content": "recovered"}
sleeps = []
with patch.object(work_graph_execute, "write_workflow_script"), \
patch.object(work_graph_execute, "execute_work_graph", side_effect=fake_execute):
outputs = wgo.run_graph(
self.conn, "run-1", "planner", "planner-doc-writing", "/tmp/proj-1", manifest,
lambda node, outputs: "p", _IN_SCHEMA, _OUT_SCHEMA,
sleep=lambda s: sleeps.append(s), now=lambda: 0.0,
)
self.assertEqual(outputs["brd"], {"content": "recovered"})
self.assertEqual(sleeps, [5 * 60])
class RunGraphClassifierBlockedTest(RunGraphTestBase):
def test_classifier_blocked_marks_node_blocked_and_propagates(self):
manifest = {"nodes": [{"node_id": "brd", "depends_on": []}], "edges": []}
with patch.object(work_graph_execute, "write_workflow_script"), \
patch.object(
work_graph_execute, "execute_work_graph",
side_effect=work_graph_execute.ClassifierBlockedError("blocked by classifier"),
):
with self.assertRaises(work_graph_execute.ClassifierBlockedError):
wgo.run_graph(
self.conn, "run-1", "planner", "planner-doc-writing", "/tmp/proj-1", manifest,
lambda node, outputs: "p", _IN_SCHEMA, _OUT_SCHEMA,
)
node_exec_id = self.conn.execute(
"SELECT node_exec_id FROM work_node_execution WHERE run_id = 'run-1' AND node_id = 'brd'"
).fetchone()[0]
status = self.conn.execute(
"SELECT status FROM work_node_execution WHERE node_exec_id = ?", (node_exec_id,)
).fetchone()[0]
self.assertEqual(status, "blocked")
class VerifyFnTest(RunGraphTestBase):
"""REQ-02 boundary: verify_fn intercepts a bad node output before it
propagates downstream, via one regeneration attempt."""
def test_verify_fn_passing_immediately_does_not_regenerate(self):
manifest = {"nodes": [{"node_id": "prd", "depends_on": []}], "edges": []}
with patch.object(work_graph_execute, "write_workflow_script"), \
patch.object(work_graph_execute, "execute_work_graph", return_value={"content": "consistent prd"}) as mock_execute:
outputs = wgo.run_graph(
self.conn, "run-1", "planner", "planner-doc-writing", "/tmp/proj-1", manifest,
lambda node, outputs: "p", _IN_SCHEMA, _OUT_SCHEMA,
verify_fn=lambda node, output: (True, None),
)
self.assertEqual(outputs["prd"], {"content": "consistent prd"})
self.assertEqual(mock_execute.call_count, 1)
run_status = self.conn.execute("SELECT status FROM work_graph_run WHERE run_id = 'run-1'").fetchone()[0]
self.assertEqual(run_status, "running") # untouched -- verify_fn never failed
def test_verify_fn_failing_once_regenerates_and_succeeds(self):
manifest = {"nodes": [{"node_id": "prd", "depends_on": []}], "edges": []}
contents = iter(["contradictory prd", "fixed prd"])
checked = []
def verify_fn(node, output):
checked.append(output["content"])
return output["content"] == "fixed prd", ["scenario A contradicts scenario B"]
with patch.object(work_graph_execute, "write_workflow_script"), \
patch.object(work_graph_execute, "execute_work_graph", side_effect=lambda *a, **k: {"content": next(contents)}):
outputs = wgo.run_graph(
self.conn, "run-1", "planner", "planner-doc-writing", "/tmp/proj-1", manifest,
lambda node, outputs: "p", _IN_SCHEMA, _OUT_SCHEMA, verify_fn=verify_fn,
)
self.assertEqual(outputs["prd"], {"content": "fixed prd"})
self.assertEqual(checked, ["contradictory prd", "fixed prd"])
run_status = self.conn.execute("SELECT status FROM work_graph_run WHERE run_id = 'run-1'").fetchone()[0]
self.assertEqual(run_status, "verifying")
reflect_row = self.conn.execute(
"SELECT status FROM work_node_execution WHERE run_id = 'run-1' AND node_id = 'prd-reflect'"
).fetchone()
self.assertEqual(reflect_row[0], "done")
def test_verify_fn_failing_twice_raises_and_blocks_run(self):
manifest = {"nodes": [{"node_id": "prd", "depends_on": []}], "edges": []}
with patch.object(work_graph_execute, "write_workflow_script"), \
patch.object(work_graph_execute, "execute_work_graph", return_value={"content": "still contradictory"}):
with self.assertRaises(wgo.ConsistencyCheckFailedError):
wgo.run_graph(
self.conn, "run-1", "planner", "planner-doc-writing", "/tmp/proj-1", manifest,
lambda node, outputs: "p", _IN_SCHEMA, _OUT_SCHEMA,
verify_fn=lambda node, output: (False, ["still broken"]),
)
run_status = self.conn.execute("SELECT status FROM work_graph_run WHERE run_id = 'run-1'").fetchone()[0]
self.assertEqual(run_status, "blocked")
class SelfTargetForcesWorktreeTest(RunGraphTestBase):
"""U-035 (05 §5.8): self-target unconditionally forces needs_worktree=True,
regardless of what the caller passed. run_work_node itself is mocked here
(not just execute_work_graph) so this only asserts what needs_worktree
value run_graph computes and passes down -- it doesn't exercise real git
worktree commands against this actual checkout."""
def test_self_target_forces_worktree_even_when_caller_passed_false(self):
manifest = {"nodes": [{"node_id": "brd", "depends_on": []}], "edges": []}
self.conn.execute(
"UPDATE project SET target_folder_path = ? WHERE project_id = 'proj-1'", (paths.repo_root(),)
)
self.conn.commit()
with patch.object(work_graph_execute, "write_workflow_script"), \
patch.object(work_node_run, "run_work_node", return_value={"content": "x"}) as mock_run:
wgo.run_graph(
self.conn, "run-1", "planner", "planner-doc-writing", paths.repo_root(), manifest,
lambda node, outputs: "p", _IN_SCHEMA, _OUT_SCHEMA, needs_worktree=False,
)
self.assertTrue(mock_run.call_args.kwargs["needs_worktree"])
def test_non_self_target_respects_caller_supplied_false(self):
manifest = {"nodes": [{"node_id": "brd", "depends_on": []}], "edges": []}
with patch.object(work_graph_execute, "write_workflow_script"), \
patch.object(work_node_run, "run_work_node", return_value={"content": "x"}) as mock_run:
wgo.run_graph(
self.conn, "run-1", "planner", "planner-doc-writing", "/tmp/proj-1", manifest,
lambda node, outputs: "p", _IN_SCHEMA, _OUT_SCHEMA, needs_worktree=False,
)
self.assertFalse(mock_run.call_args.kwargs["needs_worktree"])
def test_non_self_target_still_respects_caller_supplied_true(self):
manifest = {"nodes": [{"node_id": "brd", "depends_on": []}], "edges": []}
with patch.object(work_graph_execute, "write_workflow_script"), \
patch.object(work_node_run, "run_work_node", return_value={"content": "x"}) as mock_run:
wgo.run_graph(
self.conn, "run-1", "planner", "planner-doc-writing", "/tmp/proj-1", manifest,
lambda node, outputs: "p", _IN_SCHEMA, _OUT_SCHEMA, needs_worktree=True,
)
self.assertTrue(mock_run.call_args.kwargs["needs_worktree"])
class RunFnLogsExecutionEventsTest(RunGraphTestBase):
"""DU-01 (bug A1/A2 root cause): `_make_run_fn()`'s `run_fn` closure must
actually call `execution_log.append_log()` around the real
`execute_work_graph()` call, so `execution_log_file`'s backing file on
disk genuinely has content -- not just a DB row tracking its lifecycle."""
def _node_exec_id(self, node_id="brd"):
return self.conn.execute(
"SELECT node_exec_id FROM work_node_execution WHERE run_id = 'run-1' AND node_id = ?", (node_id,)
).fetchone()[0]
def _log_lines(self, node_exec_id):
content = execution_log.get_log(self.conn, node_exec_id)["content"]
return [json.loads(line) for line in content.splitlines() if line]
def test_success_writes_node_start_then_node_completed(self):
manifest = {"nodes": [{"node_id": "brd", "depends_on": []}], "edges": []}
with patch.object(work_graph_execute, "write_workflow_script"), \
patch.object(work_graph_execute, "execute_work_graph", return_value={"content": "brd text"}):
wgo.run_graph(
self.conn, "run-1", "planner", "planner-doc-writing", "/tmp/proj-1", manifest,
lambda node, outputs: "p", _IN_SCHEMA, _OUT_SCHEMA,
)
events = self._log_lines(self._node_exec_id())
self.assertEqual([e["event"] for e in events], ["node_start", "node_completed"])
self.assertEqual(events[1]["output"], {"content": "brd text"})
# also exercise the real HTTP-facing read path end to end (not just
# the module function) -- an empty file was exactly bug A1.
row = self.conn.execute(
"SELECT size_bytes FROM execution_log_file WHERE node_exec_id = ?", (self._node_exec_id(),)
).fetchone()
self.assertGreater(row[0], 0)
def test_classifier_blocked_writes_node_failed_and_still_propagates(self):
manifest = {"nodes": [{"node_id": "brd", "depends_on": []}], "edges": []}
with patch.object(work_graph_execute, "write_workflow_script"), \
patch.object(
work_graph_execute, "execute_work_graph",
side_effect=work_graph_execute.ClassifierBlockedError("blocked by classifier"),
):
with self.assertRaises(work_graph_execute.ClassifierBlockedError):
wgo.run_graph(
self.conn, "run-1", "planner", "planner-doc-writing", "/tmp/proj-1", manifest,
lambda node, outputs: "p", _IN_SCHEMA, _OUT_SCHEMA,
)
events = self._log_lines(self._node_exec_id())
self.assertEqual([e["event"] for e in events], ["node_start", "node_failed"])
self.assertIn("blocked by classifier", events[1]["error"])
def test_usage_limit_writes_quota_limit_then_retries(self):
manifest = {"nodes": [{"node_id": "brd", "depends_on": []}], "edges": []}
attempts = {"n": 0}
def fake_execute(cwd, name, args, output_schema, timeout=600):
attempts["n"] += 1
if attempts["n"] == 1:
raise work_graph_execute.UsageLimitReachedError("hit your session limit", "session")
return {"content": "recovered"}
with patch.object(work_graph_execute, "write_workflow_script"), \
patch.object(work_graph_execute, "execute_work_graph", side_effect=fake_execute):
outputs = wgo.run_graph(
self.conn, "run-1", "planner", "planner-doc-writing", "/tmp/proj-1", manifest,
lambda node, outputs: "p", _IN_SCHEMA, _OUT_SCHEMA,
sleep=lambda s: None, now=lambda: 0.0,
)
self.assertEqual(outputs["brd"], {"content": "recovered"})
events = self._log_lines(self._node_exec_id())
self.assertEqual(
[e["event"] for e in events], ["node_start", "quota_limit", "node_start", "node_completed"]
)
self.assertEqual(events[1]["quota_limit_type"], "session")
if __name__ == "__main__":
unittest.main()