test_work_graph_plan.py
18.7 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
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
"""U-011 tests: c_work_graph_plan, mocked at the subprocess boundary (CLAUDE.md
Testing constraint). Real-call coverage is in src/test_work_graph_plan_e2e.py
(RUN_REAL_AGENT_E2E=1) -- that real call is what proved --json-schema doesn't
constrain output when --agent is set, which is why these mocks return
free-form ```json-fenced text in `result`, not `structured_output`.
Run: python3 -m unittest src.test_work_graph_plan -v
"""
import json
import subprocess
import unittest
from unittest.mock import patch
from src import schema, work_graph_execute, work_graph_orchestrate, work_graph_plan
_MANIFEST = {
"nodes": [
{"node_id": "n1", "artifact_type": "brd", "depends_on": []},
{"node_id": "n2", "artifact_type": "prd", "depends_on": ["n1"]},
{"node_id": "n3", "artifact_type": "sdd", "depends_on": ["n2"]},
{"node_id": "n4", "artifact_type": "benchmark", "depends_on": ["n3"]},
],
"edges": [
{"from": "n1", "to": "n2", "edge_type": "needs_judgment"},
{"from": "n2", "to": "n3", "edge_type": "needs_judgment"},
{"from": "n3", "to": "n4", "edge_type": "needs_judgment"},
],
}
def _completed_process(returncode=0, stdout_obj=None, stderr=""):
stdout = json.dumps(stdout_obj) if stdout_obj is not None else ""
return subprocess.CompletedProcess(args=["claude"], returncode=returncode, stdout=stdout, stderr=stderr)
def _fenced_result(manifest, wrapper_key=None):
body = {wrapper_key: manifest} if wrapper_key else manifest
return "Here is my plan:\n\n```json\n" + json.dumps(body) + "\n```\n\nDone."
class PlanWorkGraphTestBase(unittest.TestCase):
def setUp(self):
# check_same_thread=False: GenericPathEndToEndViaRunGraphTest below
# drives a real multi-node concurrent layer through run_graph()
# (G), which calls into this conn from ThreadPoolExecutor worker
# threads via _LockedConn -- see test_work_graph_orchestrate.py's
# RunGraphTestBase for the same reasoning.
self.conn = schema.connect(":memory:", check_same_thread=False)
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', '实现贪吃蛇游戏', 'goal', 'queued', 'planner')"
)
self.conn.commit()
def tearDown(self):
self.conn.close()
class ExtractGraphManifestTest(unittest.TestCase):
def test_bare_json_result(self):
self.assertEqual(work_graph_plan._extract_graph_manifest(json.dumps(_MANIFEST)), _MANIFEST)
def test_fenced_json_block_with_prose_around_it(self):
self.assertEqual(work_graph_plan._extract_graph_manifest(_fenced_result(_MANIFEST)), _MANIFEST)
def test_fenced_json_wrapped_under_graph_manifest_key(self):
text = _fenced_result(_MANIFEST, wrapper_key="graph_manifest")
self.assertEqual(work_graph_plan._extract_graph_manifest(text), _MANIFEST)
def test_no_json_anywhere_returns_none(self):
self.assertIsNone(work_graph_plan._extract_graph_manifest("sorry, I can't do that"))
class NormalizeGraphManifestTest(unittest.TestCase):
"""U-031 regression: a real Planner call (2026-08-01) came back using
`id` instead of the documented `node_id`, and never populated any
node's own `depends_on` -- dependencies existed only as `edges`. This
is a real, observed deviation, not a hypothetical one; the fixture
below is the actual shape captured from that call (fields trimmed to
what normalization touches)."""
def test_already_well_formed_manifest_untouched(self):
manifest = {
"nodes": [
{"node_id": "brd", "artifact_type": "brd", "depends_on": []},
{"node_id": "prd", "artifact_type": "prd", "depends_on": ["brd"]},
],
"edges": [{"from": "brd", "to": "prd", "edge_type": "needs_judgment"}],
}
result = work_graph_plan._normalize_graph_manifest(manifest)
self.assertEqual(result["nodes"][1]["depends_on"], ["brd"])
def test_id_key_normalized_to_node_id(self):
manifest = {
"nodes": [{"id": "brd", "artifact_type": "brd"}, {"id": "prd", "artifact_type": "prd"}],
"edges": [{"from": "brd", "to": "prd", "edge_type": "needs_judgment"}],
}
result = work_graph_plan._normalize_graph_manifest(manifest)
self.assertEqual([n["node_id"] for n in result["nodes"]], ["brd", "prd"])
def test_depends_on_derived_from_edges_when_absent(self):
manifest = {
"nodes": [{"id": "brd"}, {"id": "prd"}, {"id": "sdd"}, {"id": "benchmark"}],
"edges": [
{"from": "brd", "to": "prd", "edge_type": "needs_judgment"},
{"from": "prd", "to": "sdd", "edge_type": "needs_judgment"},
{"from": "sdd", "to": "benchmark", "edge_type": "needs_judgment"},
],
}
result = work_graph_plan._normalize_graph_manifest(manifest)
by_id = {n["node_id"]: n for n in result["nodes"]}
self.assertEqual(by_id["brd"]["depends_on"], [])
self.assertEqual(by_id["prd"]["depends_on"], ["brd"])
self.assertEqual(by_id["sdd"]["depends_on"], ["prd"])
self.assertEqual(by_id["benchmark"]["depends_on"], ["sdd"])
def test_does_not_duplicate_dependency_already_present(self):
manifest = {
"nodes": [{"node_id": "brd", "depends_on": []}, {"node_id": "prd", "depends_on": ["brd"]}],
"edges": [{"from": "brd", "to": "prd", "edge_type": "needs_judgment"}],
}
result = work_graph_plan._normalize_graph_manifest(manifest)
self.assertEqual(result["nodes"][1]["depends_on"], ["brd"])
def test_edge_referencing_unknown_node_id_ignored(self):
manifest = {"nodes": [{"id": "brd"}], "edges": [{"from": "brd", "to": "no-such-node"}]}
result = work_graph_plan._normalize_graph_manifest(manifest)
self.assertEqual(result["nodes"][0]["depends_on"], [])
def test_canonical_doc_chain_enforced_even_with_zero_dependency_info(self):
# 2026-08-03 regression: a real call omitted depends_on AND edges
# entirely -- worse than test_depends_on_derived_from_edges_when_absent,
# which at least had edges to derive from. With nothing to
# normalize, topological_order() scheduled 'benchmark' before 'sdd'
# (alphabetically first among zero-in-degree nodes), and
# e2e_pipeline's build_prompt() crashed formatting a template that
# needed sdd's not-yet-produced output.
manifest = {
"nodes": [
{"node_id": "brd", "artifact_type": "brd"},
{"node_id": "prd", "artifact_type": "prd"},
{"node_id": "sdd", "artifact_type": "sdd"},
{"node_id": "benchmark", "artifact_type": "benchmark"},
{"node_id": "test_dataset", "artifact_type": "test_dataset"},
{"node_id": "test_script", "artifact_type": "test_script"},
],
"edges": [],
}
result = work_graph_plan._normalize_graph_manifest(manifest)
by_type = {n["artifact_type"]: n for n in result["nodes"]}
self.assertEqual(by_type["brd"]["depends_on"], [])
self.assertEqual(by_type["prd"]["depends_on"], ["brd"])
self.assertEqual(by_type["sdd"]["depends_on"], ["prd"])
self.assertEqual(by_type["benchmark"]["depends_on"], ["sdd"])
self.assertEqual(by_type["test_dataset"]["depends_on"], ["benchmark"])
# test_script needs both -- its own prompt references
# {benchmark_content} directly, not just what survives into
# test_dataset_content (see work_graph_plan._normalize_graph_manifest).
self.assertEqual(by_type["test_script"]["depends_on"], ["test_dataset", "benchmark"])
def test_canonical_chain_enforcement_uses_real_node_ids_not_artifact_types(self):
# node_id and artifact_type can differ (e.g. real LLM output naming
# nodes "n1"/"n2"/... while still setting artifact_type correctly) --
# the enforced dependency must reference the real node_id.
manifest = {
"nodes": [
{"node_id": "step-1", "artifact_type": "brd"},
{"node_id": "step-2", "artifact_type": "prd"},
{"node_id": "step-3", "artifact_type": "sdd"},
{"node_id": "step-4", "artifact_type": "benchmark"},
{"node_id": "step-5", "artifact_type": "test_dataset"},
{"node_id": "step-6", "artifact_type": "test_script"},
],
"edges": [],
}
result = work_graph_plan._normalize_graph_manifest(manifest)
by_type = {n["artifact_type"]: n for n in result["nodes"]}
self.assertEqual(by_type["prd"]["depends_on"], ["step-1"])
self.assertEqual(by_type["sdd"]["depends_on"], ["step-2"])
self.assertEqual(by_type["benchmark"]["depends_on"], ["step-3"])
self.assertEqual(by_type["test_dataset"]["depends_on"], ["step-4"])
self.assertEqual(by_type["test_script"]["depends_on"], ["step-5", "step-4"])
def test_partial_canonical_set_does_not_trigger_enforcement(self):
# only brd/prd/sdd present, no benchmark -- not a recognized
# canonical 4-node doc chain, must not guess at a shape.
manifest = {
"nodes": [
{"node_id": "brd", "artifact_type": "brd"},
{"node_id": "prd", "artifact_type": "prd"},
{"node_id": "sdd", "artifact_type": "sdd"},
],
"edges": [],
}
result = work_graph_plan._normalize_graph_manifest(manifest)
for node in result["nodes"]:
self.assertEqual(node["depends_on"], [])
class HappyPathTest(PlanWorkGraphTestBase):
def test_returns_run_id_and_graph_manifest(self):
with patch("src.work_graph_plan.subprocess.run") as run:
run.return_value = _completed_process(
stdout_obj={"is_error": False, "result": _fenced_result(_MANIFEST)}
)
result = work_graph_plan.plan_work_graph(
self.conn, "planner", "task-1", "实现贪吃蛇游戏", "/tmp/proj-1"
)
self.assertEqual(result["graph_manifest"], _MANIFEST)
self.assertTrue(result["run_id"])
def test_creates_work_graph_run_row_in_planning_status(self):
with patch("src.work_graph_plan.subprocess.run") as run:
run.return_value = _completed_process(
stdout_obj={"is_error": False, "result": _fenced_result(_MANIFEST)}
)
result = work_graph_plan.plan_work_graph(
self.conn, "planner", "task-1", "实现贪吃蛇游戏", "/tmp/proj-1"
)
row = self.conn.execute(
"SELECT task_id, org_node, status, graph_manifest FROM work_graph_run WHERE run_id = ?",
(result["run_id"],),
).fetchone()
self.assertEqual(row[0], "task-1")
self.assertEqual(row[1], "planner")
self.assertEqual(row[2], "planning")
self.assertEqual(json.loads(row[3]), _MANIFEST)
def test_invokes_claude_with_expected_args(self):
with patch("src.work_graph_plan.subprocess.run") as run:
run.return_value = _completed_process(
stdout_obj={"is_error": False, "result": _fenced_result(_MANIFEST)}
)
work_graph_plan.plan_work_graph(self.conn, "planner", "task-1", "goal", "/tmp/proj-1")
args, kwargs = run.call_args
argv = args[0]
self.assertEqual(argv[:3], ["claude", "--agent", "planner"])
self.assertIn("--permission-mode", argv)
self.assertIn("auto", argv)
self.assertNotIn("--bare", argv)
# --json-schema deliberately dropped -- confirmed for real it's a no-op
# when combined with --agent (see module docstring)
self.assertNotIn("--json-schema", argv)
self.assertEqual(kwargs["cwd"], "/tmp/proj-1")
self.assertEqual(kwargs["stdin"], subprocess.DEVNULL)
class FailureTest(PlanWorkGraphTestBase):
def test_nonzero_exit_raises_planning_failed(self):
with patch("src.work_graph_plan.subprocess.run") as run:
run.return_value = _completed_process(returncode=1, stdout_obj=None, stderr="boom")
with self.assertRaises(work_graph_plan.PlanningFailedError):
work_graph_plan.plan_work_graph(self.conn, "planner", "task-1", "goal", "/tmp/proj-1")
def test_is_error_true_raises_planning_failed(self):
with patch("src.work_graph_plan.subprocess.run") as run:
run.return_value = _completed_process(stdout_obj={"is_error": True})
with self.assertRaises(work_graph_plan.PlanningFailedError):
work_graph_plan.plan_work_graph(self.conn, "planner", "task-1", "goal", "/tmp/proj-1")
def test_unparseable_result_raises_planning_failed(self):
with patch("src.work_graph_plan.subprocess.run") as run:
run.return_value = _completed_process(stdout_obj={"is_error": False, "result": "no json here"})
with self.assertRaises(work_graph_plan.PlanningFailedError):
work_graph_plan.plan_work_graph(self.conn, "planner", "task-1", "goal", "/tmp/proj-1")
self.assertEqual(self.conn.execute("SELECT COUNT(*) FROM work_graph_run").fetchone()[0], 0)
# E (2026-08-06): cross-Org-Agent dynamic planning path -- org_node != 'planner'
# gets _GENERIC_PROMPT_TEMPLATE instead of the fixed doc-chain prompt, and each
# node carries its own task_prompt instead of a fixed artifact_type.
_CODER_THREE_MODULE_MANIFEST = {
"nodes": [
{"node_id": "test-module-a", "depends_on": [], "task_prompt": "Write unit tests for module_a.py."},
{"node_id": "test-module-b", "depends_on": [], "task_prompt": "Write unit tests for module_b.py."},
{"node_id": "test-module-c", "depends_on": [], "task_prompt": "Write unit tests for module_c.py."},
],
"edges": [],
}
class GenericPlanningPromptTest(PlanWorkGraphTestBase):
def test_planner_still_gets_fixed_doc_chain_template(self):
with patch("src.work_graph_plan.subprocess.run") as run:
run.return_value = _completed_process(
stdout_obj={"is_error": False, "result": _fenced_result(_MANIFEST)}
)
work_graph_plan.plan_work_graph(self.conn, "planner", "task-1", "goal", "/tmp/proj-1")
prompt = run.call_args.args[0][run.call_args.args[0].index("-p") + 1]
self.assertIn("BRD, PRD, SDD, Benchmark", prompt)
self.assertNotIn("design-dynamic-work-graph", prompt)
def test_coder_gets_generic_template_referencing_the_skill(self):
with patch("src.work_graph_plan.subprocess.run") as run:
run.return_value = _completed_process(
stdout_obj={"is_error": False, "result": _fenced_result(_CODER_THREE_MODULE_MANIFEST)}
)
work_graph_plan.plan_work_graph(self.conn, "coder", "task-1", "goal", "/tmp/proj-1")
prompt = run.call_args.args[0][run.call_args.args[0].index("-p") + 1]
self.assertIn("design-dynamic-work-graph", prompt)
self.assertNotIn("BRD, PRD, SDD, Benchmark", prompt)
self.assertIn("task_prompt", prompt)
class CoderThreeIndependentModulesScenarioTest(PlanWorkGraphTestBase):
"""E acceptance criterion 1: a Coder scenario that naturally splits into
2-3 independent sub-tasks produces a graph_manifest via the new generic
path (not the old single trigger_org_node call), correctly marking those
nodes as mutually independent."""
def test_three_independent_modules_produce_correctly_shaped_manifest(self):
with patch("src.work_graph_plan.subprocess.run") as run:
run.return_value = _completed_process(
stdout_obj={"is_error": False, "result": _fenced_result(_CODER_THREE_MODULE_MANIFEST)}
)
result = work_graph_plan.plan_work_graph(self.conn, "coder", "task-1", "goal", "/tmp/proj-1")
manifest = result["graph_manifest"]
self.assertEqual(len(manifest["nodes"]), 3)
for node in manifest["nodes"]:
self.assertEqual(node["depends_on"], [])
self.assertIn("task_prompt", node)
# E's whole point ties directly into G: independence is expressed
# structurally (empty depends_on), so topological_layers() must put
# all three in ONE concurrent layer, not three serial ones.
layers = work_graph_orchestrate.topological_layers(manifest)
self.assertEqual(len(layers), 1)
self.assertEqual({n["node_id"] for n in layers[0]}, {"test-module-a", "test-module-b", "test-module-c"})
class GenericNodePromptBuilderTest(unittest.TestCase):
def test_returns_the_node_own_task_prompt(self):
node = {"node_id": "test-module-a", "task_prompt": "Write unit tests for module_a.py."}
self.assertEqual(
work_graph_plan.generic_node_prompt_builder(node, {}), "Write unit tests for module_a.py."
)
class GenericPathEndToEndViaRunGraphTest(PlanWorkGraphTestBase):
"""E acceptance criterion (FR-5): the generated graph_manifest, driven by
generic_node_prompt_builder, actually runs to completion through
run_graph() -- not just a standalone parsing/shape check."""
def test_three_independent_nodes_execute_and_return_outputs(self):
with patch("src.work_graph_plan.subprocess.run") as run:
run.return_value = _completed_process(
stdout_obj={"is_error": False, "result": _fenced_result(_CODER_THREE_MODULE_MANIFEST)}
)
plan_result = work_graph_plan.plan_work_graph(self.conn, "coder", "task-1", "goal", "/tmp/proj-1")
# plan_work_graph() already inserted the work_graph_run row
# (status='planning') -- run_graph() doesn't require any particular
# status on it, so nothing more to set up here.
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: {"content": "done: " + name}
outputs = work_graph_orchestrate.run_graph(
self.conn, plan_result["run_id"], "coder", "coder-implementation", "/tmp/proj-1",
plan_result["graph_manifest"], work_graph_plan.generic_node_prompt_builder,
{"type": "object", "required": ["node_id"]}, {"type": "object", "required": ["content"]},
)
self.assertEqual(set(outputs.keys()), {"test-module-a", "test-module-b", "test-module-c"})
self.assertEqual(mock_execute.call_count, 3)
if __name__ == "__main__":
unittest.main()