test_e2e_pipeline.py
14.1 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
"""U-014 tests: end-to-end orchestration wiring, mocked at the subprocess
boundary (CLAUDE.md Testing constraint) -- these test that plan_documents/
implement_code/validate_implementation/run_end_to_end call the right things
in the right order and wire artifact lineage/task-status transitions
correctly, not what a real Planner/Coder/Validator would actually produce.
Real coverage (as much of it as is safe/affordable to run) is in
src/test_e2e_pipeline_e2e.py (RUN_REAL_AGENT_E2E=1).
**Rewired 2026-08-01 (U-031 regression audit)**: plan_documents/
implement_code now go through work_graph_plan.plan_work_graph +
work_graph_orchestrate.run_graph (which calls work_graph_execute.
execute_work_graph per node) instead of a flat org_node_trigger.
trigger_org_node call -- see e2e_pipeline.py's module docstring for why.
plan_work_graph is mocked at its own subprocess boundary (same pattern as
test_work_graph_plan.py) so its real graph_manifest-parsing logic and its
real work_graph_run INSERT both still run for real; execute_work_graph is
mocked directly (one level higher than its own subprocess boundary) since
this file's job is testing e2e_pipeline's wiring, not re-proving
execute_work_graph's own mechanics (covered in test_work_graph_execute.py)
or work_graph_orchestrate's own mechanics (test_work_graph_orchestrate.py).
Run: python3 -m unittest src.test_e2e_pipeline -v
"""
import json
import subprocess
import tempfile
import unittest
from unittest.mock import patch
from src import e2e_pipeline, org_node_trigger, project_scaffold, schema, work_graph_execute
_FAKE_DOCS = {"brd": "# BRD\nfake", "prd": "# PRD\nfake", "sdd": "# SDD\nfake", "benchmark": "# Benchmark\nfake"}
_FAKE_GRAPH_MANIFEST = {
"nodes": [
{"node_id": "brd", "artifact_type": "brd", "depends_on": []},
{"node_id": "prd", "artifact_type": "prd", "depends_on": ["brd"]},
{"node_id": "sdd", "artifact_type": "sdd", "depends_on": ["prd"]},
{"node_id": "benchmark", "artifact_type": "benchmark", "depends_on": ["sdd"]},
],
"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"},
],
}
def _fake_plan_subprocess_run(*args, **kwargs):
payload = {"is_error": False, "result": "```json\n" + json.dumps(_FAKE_GRAPH_MANIFEST) + "\n```"}
return subprocess.CompletedProcess(args=["claude"], returncode=0, stdout=json.dumps(payload), stderr="")
def _fake_ready_trigger(org_node, prompt, target_folder_path, timeout=300):
assert prompt == e2e_pipeline._READY_PROMPT
return "Ready."
class PipelineTestBase(unittest.TestCase):
def setUp(self):
self.tmp = tempfile.TemporaryDirectory()
self.addCleanup(self.tmp.cleanup)
subprocess.run(["git", "init"], cwd=self.tmp.name, check=True, capture_output=True)
self.conn = schema.connect(":memory:")
schema.create_schema(self.conn)
project_scaffold.create_project(self.conn, self.tmp.name, init_git_if_missing=False)
def tearDown(self):
self.conn.close()
class PlanDocumentsTest(PipelineTestBase):
def test_produces_four_artifacts_with_correct_lineage(self):
self.conn.execute(
"INSERT INTO task (task_id, project_id, goal_text, task_type, status, assigned_org_node) "
"VALUES ('task-1', (SELECT project_id FROM project), '实现贪吃蛇游戏', 'goal', "
"'planning_brd_prd_sdd', 'planner')"
)
self.conn.commit()
with patch("src.work_graph_plan.subprocess.run", side_effect=_fake_plan_subprocess_run), \
patch.object(work_graph_execute, "write_workflow_script"), \
patch.object(work_graph_execute, "execute_work_graph") as mock_execute:
mock_execute.side_effect = [
{"content": _FAKE_DOCS["brd"]}, {"content": _FAKE_DOCS["prd"]},
{"consistent": True, "issues": []}, # PRD consistency check (REQ-02 boundary)
{"content": _FAKE_DOCS["sdd"]}, {"content": _FAKE_DOCS["benchmark"]},
]
plan_result = e2e_pipeline.plan_documents(self.conn, "task-1", "实现贪吃蛇游戏", self.tmp.name)
artifact_ids = plan_result["artifact_ids"]
self.assertEqual(set(artifact_ids), {"brd", "prd", "sdd", "benchmark"})
prd_deps = json.loads(
self.conn.execute(
"SELECT depends_on_artifact_ids FROM artifact WHERE artifact_id = ?", (artifact_ids["prd"],)
).fetchone()[0]
)
self.assertEqual(prd_deps, [artifact_ids["brd"]])
sdd_deps = json.loads(
self.conn.execute(
"SELECT depends_on_artifact_ids FROM artifact WHERE artifact_id = ?", (artifact_ids["sdd"],)
).fetchone()[0]
)
self.assertEqual(sdd_deps, [artifact_ids["prd"]])
# plan_work_graph's own real work_graph_run INSERT actually ran (not bypassed)
run_row = self.conn.execute(
"SELECT org_node, status FROM work_graph_run WHERE run_id = ?", (plan_result["run_id"],)
).fetchone()
self.assertEqual(run_row, ("planner", "planning"))
class RunEndToEndTest(PipelineTestBase):
def test_full_pipeline_wiring(self):
with patch("src.org_node_lifecycle.trigger_org_node", side_effect=_fake_ready_trigger), \
patch("src.work_graph_plan.subprocess.run", side_effect=_fake_plan_subprocess_run), \
patch.object(work_graph_execute, "write_workflow_script"), \
patch.object(work_graph_execute, "execute_work_graph") as mock_execute, \
patch.object(org_node_trigger, "trigger_org_node", return_value="VERDICT: PASS\nAll scenarios pass."):
mock_execute.side_effect = [
{"content": _FAKE_DOCS["brd"]}, {"content": _FAKE_DOCS["prd"]},
{"consistent": True, "issues": []}, # PRD consistency check (REQ-02 boundary)
{"content": _FAKE_DOCS["sdd"]}, {"content": _FAKE_DOCS["benchmark"]},
{"response": "Implemented. Ran `pytest`: 3 passed."},
]
result = e2e_pipeline.run_end_to_end(self.conn, self.tmp.name, "实现贪吃蛇游戏")
self.assertEqual(result["verdict"]["verdict"], "PASS")
self.assertEqual(set(result["doc_artifact_ids"]), {"brd", "prd", "sdd", "benchmark"})
self.assertEqual(set(result["code_artifact_ids"]), {"code_diff", "test_report"})
task_row = self.conn.execute(
"SELECT status FROM task WHERE task_id = ?", (result["task_id"],)
).fetchone()
self.assertEqual(task_row[0], "validating")
all_artifacts = self.conn.execute(
"SELECT COUNT(*) FROM artifact WHERE task_id = ?", (result["task_id"],)
).fetchone()[0]
self.assertEqual(all_artifacts, 6) # brd, prd, sdd, benchmark, code_diff, test_report
# planner and coder each got their own work_graph_run (not sharing one)
run_org_nodes = {
row[0] for row in self.conn.execute(
"SELECT org_node FROM work_graph_run WHERE task_id = ?", (result["task_id"],)
).fetchall()
}
self.assertEqual(run_org_nodes, {"planner", "coder"})
class PrdConsistencyVerifyFnTest(unittest.TestCase):
"""REQ-02 boundary: only the PRD node gets the consistency check."""
def test_non_prd_node_passes_through_without_a_call(self):
node_artifact_types = {"brd": "brd"}
verify_fn = e2e_pipeline._prd_consistency_verify_fn(node_artifact_types, "/tmp/proj-1")
with patch.object(work_graph_execute, "execute_work_graph") as mock_execute:
ok, feedback = verify_fn({"node_id": "brd"}, {"content": "brd text"})
self.assertTrue(ok)
self.assertIsNone(feedback)
mock_execute.assert_not_called()
def test_string_false_from_a_real_call_is_not_treated_as_truthy(self):
# regression: a real call (2026-08-02) returned "consistent": "false"
# as a JSON string, not a boolean -- `if "false":` is truthy in
# Python, silently inverting the check until a real test caught it.
node_artifact_types = {"prd": "prd"}
verify_fn = e2e_pipeline._prd_consistency_verify_fn(node_artifact_types, "/tmp/proj-1")
with patch.object(work_graph_execute, "write_workflow_script"), \
patch.object(
work_graph_execute, "execute_work_graph",
return_value={"consistent": "false", "issues": ["contradiction found"]},
):
ok, feedback = verify_fn({"node_id": "prd"}, {"content": "contradictory prd"})
self.assertFalse(ok)
def test_string_true_from_a_real_call_is_treated_as_consistent(self):
node_artifact_types = {"prd": "prd"}
verify_fn = e2e_pipeline._prd_consistency_verify_fn(node_artifact_types, "/tmp/proj-1")
with patch.object(work_graph_execute, "write_workflow_script"), \
patch.object(
work_graph_execute, "execute_work_graph",
return_value={"consistent": "true", "issues": []},
):
ok, feedback = verify_fn({"node_id": "prd"}, {"content": "consistent prd"})
self.assertTrue(ok)
def test_prd_node_triggers_a_real_check_call(self):
node_artifact_types = {"prd": "prd"}
verify_fn = e2e_pipeline._prd_consistency_verify_fn(node_artifact_types, "/tmp/proj-1")
with patch.object(work_graph_execute, "write_workflow_script"), \
patch.object(
work_graph_execute, "execute_work_graph",
return_value={"consistent": False, "issues": ["contradiction found"]},
) as mock_execute:
ok, feedback = verify_fn({"node_id": "prd"}, {"content": "contradictory prd"})
self.assertFalse(ok)
self.assertEqual(feedback, ["contradiction found"])
mock_execute.assert_called_once()
args = mock_execute.call_args[0]
self.assertEqual(args[0], "/tmp/proj-1")
class PrdConsistencySelfTargetWorktreeTest(unittest.TestCase):
"""2026-08-03 regression: a real self-hosting run showed _check_prd_
consistency() calling execute_work_graph() directly against
target_folder_path, bypassing worktree isolation entirely -- when
self-targeting, its own agentType='planner'+memory:project call writes
a real, uncommitted change straight to the main checkout's
.claude/agent-memory/planner/MEMORY.md, which then made the NEXT
node's own (correctly worktree-isolated) merge fail with "local
changes would be overwritten by merge". This call must isolate the
same way work_node_run.run_work_node() already does for every other
self-target call."""
def test_self_target_isolates_the_check_in_its_own_worktree(self):
node_artifact_types = {"prd": "prd"}
verify_fn = e2e_pipeline._prd_consistency_verify_fn(node_artifact_types, "/repo")
with patch.object(e2e_pipeline.paths, "is_self_target", return_value=True), \
patch.object(e2e_pipeline.work_node_run, "create_worktree", return_value="/repo/.graphlemon-worktrees/x") as mock_create, \
patch.object(e2e_pipeline.work_node_run, "ensure_worktree_committed") as mock_ensure, \
patch.object(e2e_pipeline.work_node_run, "merge_worktree") as mock_merge, \
patch.object(e2e_pipeline.work_node_run, "remove_worktree") as mock_remove, \
patch.object(work_graph_execute, "write_workflow_script") as mock_write, \
patch.object(
work_graph_execute, "execute_work_graph",
return_value={"consistent": True, "issues": []},
) as mock_execute:
ok, feedback = verify_fn({"node_id": "prd"}, {"content": "some prd"})
self.assertTrue(ok)
mock_create.assert_called_once_with("/repo", unittest.mock.ANY)
# both the script write and the real execute call must use the
# WORKTREE path as cwd, never the main checkout, when self-targeting
self.assertEqual(mock_write.call_args[0][0], "/repo/.graphlemon-worktrees/x")
self.assertEqual(mock_execute.call_args[0][0], "/repo/.graphlemon-worktrees/x")
mock_ensure.assert_called_once()
mock_merge.assert_called_once()
mock_remove.assert_called_once()
def test_non_self_target_does_not_use_a_worktree_at_all(self):
node_artifact_types = {"prd": "prd"}
verify_fn = e2e_pipeline._prd_consistency_verify_fn(node_artifact_types, "/tmp/proj-1")
with patch.object(e2e_pipeline.paths, "is_self_target", return_value=False), \
patch.object(e2e_pipeline.work_node_run, "create_worktree") as mock_create, \
patch.object(work_graph_execute, "write_workflow_script") as mock_write, \
patch.object(
work_graph_execute, "execute_work_graph",
return_value={"consistent": True, "issues": []},
) as mock_execute:
verify_fn({"node_id": "prd"}, {"content": "some prd"})
mock_create.assert_not_called()
self.assertEqual(mock_write.call_args[0][0], "/tmp/proj-1")
self.assertEqual(mock_execute.call_args[0][0], "/tmp/proj-1")
class ValidateImplementationTest(unittest.TestCase):
def test_parses_pass_verdict(self):
with patch("src.org_node_trigger.trigger_org_node", return_value="VERDICT: PASS\nlooks good"):
result = e2e_pipeline.validate_implementation("task-1", "benchmark content", "goal", "/tmp/p")
self.assertEqual(result["verdict"], "PASS")
def test_parses_fail_verdict(self):
with patch("src.org_node_trigger.trigger_org_node", return_value="VERDICT: FAIL\nwall collision broken"):
result = e2e_pipeline.validate_implementation("task-1", "benchmark content", "goal", "/tmp/p")
self.assertEqual(result["verdict"], "FAIL")
def test_no_verdict_line_defaults_to_inconclusive(self):
with patch("src.org_node_trigger.trigger_org_node", return_value="I'm not sure what happened."):
result = e2e_pipeline.validate_implementation("task-1", "benchmark content", "goal", "/tmp/p")
self.assertEqual(result["verdict"], "INCONCLUSIVE")
if __name__ == "__main__":
unittest.main()