its-magic 0.1.2-9 → 0.1.2
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +1602 -755
- package/bin/its-magic.js +121 -11
- package/bin/postinstall.js +21 -0
- package/installer.ps1 +759 -0
- package/installer.py +981 -0
- package/installer.sh +649 -0
- package/package.json +18 -14
- package/scripts/check_intake_template_parity.py +284 -0
- package/scripts/doc_profile_lib.py +415 -0
- package/scripts/guard_installer_publish.py +88 -0
- package/scripts/intake_bug_routing_guard.py +67 -0
- package/scripts/intake_evidence_lib.py +802 -0
- package/scripts/intake_evidence_validate.py +73 -0
- package/scripts/materialize_codebase_map.py +184 -0
- package/scripts/remote_config_summary.py +243 -0
- package/template/.cursor/agents/curator.mdc +35 -0
- package/template/.cursor/agents/dev.mdc +29 -0
- package/template/.cursor/agents/po.mdc +141 -0
- package/template/.cursor/agents/qa.mdc +28 -0
- package/template/.cursor/agents/release.mdc +28 -0
- package/template/.cursor/agents/security.mdc +98 -0
- package/template/.cursor/agents/tech-lead.mdc +57 -0
- package/template/.cursor/commands/architecture.md +127 -0
- package/template/.cursor/commands/ask.md +55 -0
- package/template/.cursor/commands/auto.md +533 -0
- package/template/.cursor/commands/discovery.md +47 -0
- package/template/.cursor/commands/execute.md +343 -0
- package/template/.cursor/commands/intake.md +323 -0
- package/template/.cursor/commands/map-codebase.md +46 -0
- package/template/.cursor/commands/memory-audit.md +175 -0
- package/template/.cursor/commands/milestone-complete.md +51 -0
- package/template/.cursor/commands/milestone-start.md +59 -0
- package/template/.cursor/commands/pause.md +64 -0
- package/{.cursor/commands/gsd-phase-context.md → template/.cursor/commands/phase-context.md} +6 -2
- package/template/.cursor/commands/plan-verify.md +34 -0
- package/template/.cursor/commands/qa.md +226 -0
- package/template/.cursor/commands/quick.md +41 -0
- package/template/.cursor/commands/refresh-context.md +82 -0
- package/template/.cursor/commands/release.md +505 -0
- package/template/.cursor/commands/research.md +49 -0
- package/template/.cursor/commands/resume.md +67 -0
- package/template/.cursor/commands/security-review.md +81 -0
- package/template/.cursor/commands/sprint-plan.md +103 -0
- package/template/.cursor/commands/status-reconcile.md +95 -0
- package/template/.cursor/commands/verify-work.md +152 -0
- package/template/.cursor/dev-environment.json.example +22 -0
- package/{.cursor → template/.cursor}/hooks/README.md +3 -2
- package/{.cursor/hooks/gsd-hook.py → template/.cursor/hooks/hook.py} +15 -6
- package/template/.cursor/hooks.json +26 -0
- package/template/.cursor/remote.json +31 -0
- package/template/.cursor/rules/caveman.mdc +184 -0
- package/template/.cursor/rules/coding-standards.mdc +39 -0
- package/template/.cursor/rules/core.mdc +111 -0
- package/template/.cursor/rules/handoffs.mdc +27 -0
- package/template/.cursor/rules/quality.mdc +49 -0
- package/template/.cursor/scratchpad.local.example.md +323 -0
- package/template/.cursor/scratchpad.md +324 -0
- package/{.cursor/skills/gsd-team → template/.cursor/skills/its-magic}/SKILL.md +2 -2
- package/template/.cursorignore +6 -0
- package/template/.env.example +28 -0
- package/template/.github/workflows/ci.yml +194 -0
- package/{.github → template/.github}/workflows/deploy.yml +5 -2
- package/template/.its-magic-version +1 -0
- package/template/README.md +1602 -0
- package/template/decisions/DEC-0001.md +11 -0
- package/template/decisions/DEC-0002.md +11 -0
- package/template/docs/developer/README.md +44 -0
- package/template/docs/engineering/architecture.md +9 -0
- package/template/docs/engineering/artifact-ordering-policy.md +48 -0
- package/template/docs/engineering/artifact-ownership-policy.md +57 -0
- package/template/docs/engineering/auto-orchestration-reference.md +1211 -0
- package/{docs → template/docs}/engineering/codebase-map.md +0 -5
- package/template/docs/engineering/compatibility-report.md +20 -0
- package/template/docs/engineering/compatibility-signals.md +7 -0
- package/template/docs/engineering/component-scope-report.md +16 -0
- package/template/docs/engineering/component-scope.md +19 -0
- package/template/docs/engineering/context/installer-owned-paths.manifest +96 -0
- package/template/docs/engineering/context/readme-section-affinity.json +30 -0
- package/template/docs/engineering/decisions.md +16 -0
- package/template/docs/engineering/legacy-drift-audit.md +21 -0
- package/template/docs/engineering/manifests/components/api-gateway.manifest.yaml +12 -0
- package/template/docs/engineering/manifests/registry.manifest.yaml +20 -0
- package/template/docs/engineering/manifests/repo.manifest.yaml +11 -0
- package/template/docs/engineering/phase-context.md +16 -0
- package/template/docs/engineering/release-targets.json +123 -0
- package/template/docs/engineering/research.md +29 -0
- package/template/docs/engineering/runbook.md +2320 -0
- package/template/docs/engineering/runtime-connectivity.md +81 -0
- package/template/docs/engineering/security-review.md +33 -0
- package/template/docs/engineering/spec-pack/README.md +20 -0
- package/template/docs/engineering/state-archive/README.md +15 -0
- package/template/docs/engineering/state.md +20 -0
- package/template/docs/engineering/status-normalization-report.md +19 -0
- package/template/docs/engineering/token-cost-parity-manifest.md +16 -0
- package/template/docs/engineering/us-0084-remote-e2e.md +44 -0
- package/template/docs/product/acceptance.md +1 -0
- package/template/docs/product/backlog.md +5 -0
- package/template/docs/product/vision.md +11 -0
- package/template/docs/user-guides/README.md +40 -0
- package/{handoffs → template/handoffs}/dev_to_qa.md +0 -3
- package/{handoffs → template/handoffs}/po_to_tl.md +0 -3
- package/{handoffs → template/handoffs}/qa_to_dev.md +1 -2
- package/template/handoffs/release_notes.md +51 -0
- package/template/handoffs/release_queue.md +47 -0
- package/template/handoffs/release_to_dev.md +31 -0
- package/template/handoffs/releases/Sxxxx-release-notes.md +62 -0
- package/template/handoffs/resume_brief.md +14 -0
- package/{handoffs → template/handoffs}/tl_to_dev.md +0 -2
- package/template/handoffs/token_cost_runs/README.md +26 -0
- package/template/its_magic/.its-magic-version +1 -0
- package/template/its_magic/README.md +9 -0
- package/template/scripts/auto_outer_driver.py +521 -0
- package/template/scripts/caveman_compress_input.py +903 -0
- package/template/scripts/check_downstream_ci_guard.py +67 -0
- package/template/scripts/check_intake_template_parity.py +284 -0
- package/template/scripts/check_token_cost_parity.py +69 -0
- package/template/scripts/dev_environment_lib.py +463 -0
- package/template/scripts/doc_profile_lib.py +415 -0
- package/template/scripts/downstream_ci_guard_lib.py +222 -0
- package/template/scripts/enforce-triad-hot-surface.py +753 -0
- package/template/scripts/guard_installer_publish.py +88 -0
- package/template/scripts/intake_bug_resume_brief_refresh.py +303 -0
- package/template/scripts/intake_bug_routing_guard.py +67 -0
- package/template/scripts/intake_evidence_lib.py +802 -0
- package/template/scripts/intake_evidence_validate.py +73 -0
- package/template/scripts/materialize_codebase_map.py +184 -0
- package/template/scripts/pack_json_validate.py +130 -0
- package/template/scripts/project_readme_coverage_lib.py +417 -0
- package/template/scripts/readme_feature_coverage_lib.py +608 -0
- package/template/scripts/remote_config_summary.py +243 -0
- package/template/scripts/sync_push_gates.py +198 -0
- package/template/scripts/token_cost_compare.py +40 -0
- package/template/scripts/token_cost_lib.py +108 -0
- package/template/scripts/uat_probe_lib.py +868 -0
- package/template/scripts/validate-and-push.ps1 +280 -0
- package/template/scripts/validate-and-push.sh +243 -0
- package/template/scripts/validate_doc_profile.py +103 -0
- package/template/scripts/validate_project_readme_coverage.py +151 -0
- package/template/scripts/validate_readme_feature_coverage.py +140 -0
- package/template/sprints/S0001/progress.md +1 -0
- package/template/sprints/S0001/qa-findings.md +9 -0
- package/template/sprints/S0001/release-findings.md +24 -0
- package/template/sprints/S0001/sprint.md +9 -0
- package/template/sprints/S0001/summary.md +7 -0
- package/template/sprints/S0001/tasks.md +1 -0
- package/template/sprints/S0001/uat.json +6 -0
- package/template/sprints/S0001/uat.md +5 -0
- package/template/sprints/quick/Q0001/summary.md +1 -0
- package/{sprints → template/sprints}/quick/Q0001/task.json +0 -1
- package/.cursor/agents/curator.mdc +0 -21
- package/.cursor/agents/dev.mdc +0 -20
- package/.cursor/agents/po.mdc +0 -19
- package/.cursor/agents/qa.mdc +0 -19
- package/.cursor/agents/release.mdc +0 -19
- package/.cursor/agents/tech-lead.mdc +0 -21
- package/.cursor/commands/gsd-architecture.md +0 -29
- package/.cursor/commands/gsd-auto.md +0 -27
- package/.cursor/commands/gsd-discovery.md +0 -27
- package/.cursor/commands/gsd-execute.md +0 -32
- package/.cursor/commands/gsd-intake.md +0 -28
- package/.cursor/commands/gsd-map-codebase.md +0 -25
- package/.cursor/commands/gsd-milestone-complete.md +0 -24
- package/.cursor/commands/gsd-milestone-start.md +0 -26
- package/.cursor/commands/gsd-pause.md +0 -25
- package/.cursor/commands/gsd-plan-verify.md +0 -26
- package/.cursor/commands/gsd-qa.md +0 -28
- package/.cursor/commands/gsd-quick.md +0 -24
- package/.cursor/commands/gsd-refresh-context.md +0 -26
- package/.cursor/commands/gsd-release.md +0 -29
- package/.cursor/commands/gsd-research.md +0 -28
- package/.cursor/commands/gsd-resume.md +0 -26
- package/.cursor/commands/gsd-sprint-plan.md +0 -30
- package/.cursor/commands/gsd-verify-work.md +0 -25
- package/.cursor/hooks.json +0 -26
- package/.cursor/plans/cursor-gsd-team-kit_8cfee9b8.plan.md +0 -57
- package/.cursor/remote.json +0 -18
- package/.cursor/rules/gsd-core.mdc +0 -18
- package/.cursor/rules/gsd-handoffs.mdc +0 -10
- package/.cursor/rules/gsd-quality.mdc +0 -15
- package/.cursor/scratchpad.md +0 -34
- package/.github/workflows/ci.yml +0 -47
- package/decisions/DEC-0001.md +0 -21
- package/decisions/DEC-0002.md +0 -21
- package/docs/engineering/architecture.md +0 -354
- package/docs/engineering/decisions.md +0 -6
- package/docs/engineering/research.md +0 -11
- package/docs/engineering/runbook.md +0 -32
- package/docs/engineering/state.md +0 -33
- package/docs/product/acceptance.md +0 -6
- package/docs/product/backlog.md +0 -7
- package/docs/product/vision.md +0 -46
- package/gsd-installer.ps1 +0 -189
- package/gsd-installer.py +0 -195
- package/gsd-installer.sh +0 -201
- package/handoffs/release_notes.md +0 -14
- package/handoffs/resume_brief.md +0 -8
- package/milestones/M0001/milestone.json +0 -7
- package/milestones/M0001/phases.json +0 -9
- package/milestones/M0001/progress.md +0 -3
- package/milestones/M0001/summary.md +0 -3
- package/scripts/generate-release-notes.ps1 +0 -74
- package/scripts/generate-release-notes.sh +0 -63
- package/scripts/release-all.ps1 +0 -423
- package/scripts/release-all.sh +0 -226
- package/sprints/S0001/progress.md +0 -4
- package/sprints/S0001/qa-findings.md +0 -113
- package/sprints/S0001/sprint.md +0 -70
- package/sprints/S0001/summary.md +0 -46
- package/sprints/S0001/tasks.md +0 -35
- package/sprints/S0001/uat.json +0 -8
- package/sprints/S0001/uat.md +0 -8
- package/sprints/quick/Q0001/summary.md +0 -3
- /package/{.cursor/rules/gsd-escalation.mdc → template/.cursor/rules/escalation.mdc} +0 -0
- /package/{.cursor/skills/gsd-team → template/.cursor/skills/its-magic}/templates/acceptance.json +0 -0
- /package/{.cursor/skills/gsd-team → template/.cursor/skills/its-magic}/templates/acceptance.md +0 -0
- /package/{.cursor/skills/gsd-team → template/.cursor/skills/its-magic}/templates/architecture.json +0 -0
- /package/{.cursor/skills/gsd-team → template/.cursor/skills/its-magic}/templates/architecture.md +0 -0
- /package/{.cursor/skills/gsd-team → template/.cursor/skills/its-magic}/templates/decision.json +0 -0
- /package/{.cursor/skills/gsd-team → template/.cursor/skills/its-magic}/templates/decision.md +0 -0
- /package/{.cursor/skills/gsd-team → template/.cursor/skills/its-magic}/templates/handoff.json +0 -0
- /package/{.cursor/skills/gsd-team → template/.cursor/skills/its-magic}/templates/handoff.md +0 -0
- /package/{.cursor/skills/gsd-team → template/.cursor/skills/its-magic}/templates/milestone.json +0 -0
- /package/{.cursor/skills/gsd-team → template/.cursor/skills/its-magic}/templates/phase-context.json +0 -0
- /package/{.cursor/skills/gsd-team → template/.cursor/skills/its-magic}/templates/plan-verify.json +0 -0
- /package/{.cursor/skills/gsd-team → template/.cursor/skills/its-magic}/templates/sprint.json +0 -0
- /package/{.cursor/skills/gsd-team → template/.cursor/skills/its-magic}/templates/sprint.md +0 -0
- /package/{.cursor/skills/gsd-team → template/.cursor/skills/its-magic}/templates/story.json +0 -0
- /package/{.cursor/skills/gsd-team → template/.cursor/skills/its-magic}/templates/story.md +0 -0
- /package/{.cursor/skills/gsd-team → template/.cursor/skills/its-magic}/templates/uat.json +0 -0
- /package/{docs → template/docs}/engineering/context/phase-template.json +0 -0
- /package/{docs → template/docs}/engineering/dependencies.json +0 -0
- /package/{sprints → template/sprints}/S0001/plan-verify.json +0 -0
|
@@ -0,0 +1,868 @@
|
|
|
1
|
+
#!/usr/bin/env python3
|
|
2
|
+
"""
|
|
3
|
+
UAT probe resolver (US-0092 / DEC-0078; US-0093 / DEC-0079).
|
|
4
|
+
|
|
5
|
+
Shared by /verify-work and /qa for self-verify acceptance steps.
|
|
6
|
+
Fail-closed — no silent PASS. Lib never invokes browser MCP (BUG-0006).
|
|
7
|
+
"""
|
|
8
|
+
|
|
9
|
+
from __future__ import annotations
|
|
10
|
+
|
|
11
|
+
import json
|
|
12
|
+
import os
|
|
13
|
+
import re
|
|
14
|
+
import subprocess
|
|
15
|
+
import sys
|
|
16
|
+
import time
|
|
17
|
+
import urllib.error
|
|
18
|
+
import urllib.request
|
|
19
|
+
from pathlib import Path
|
|
20
|
+
|
|
21
|
+
UAT_PROBE_UNRESOLVED = "UAT_PROBE_UNRESOLVED"
|
|
22
|
+
UAT_STACK_PROFILE_UNKNOWN = "UAT_STACK_PROFILE_UNKNOWN"
|
|
23
|
+
UAT_PROBE_TIMEOUT = "UAT_PROBE_TIMEOUT"
|
|
24
|
+
UAT_PROBE_FAILED = "UAT_PROBE_FAILED"
|
|
25
|
+
UAT_PROBE_FORBIDDEN = "UAT_PROBE_FORBIDDEN"
|
|
26
|
+
UAT_PROBE_PASS = "UAT_PROBE_PASS"
|
|
27
|
+
UAT_BROWSER_UNAVAILABLE = "UAT_BROWSER_UNAVAILABLE"
|
|
28
|
+
UAT_BROWSER_PROBE_FAILED = "UAT_BROWSER_PROBE_FAILED"
|
|
29
|
+
UAT_BROWSER_PROBE_TIMEOUT = "UAT_BROWSER_PROBE_TIMEOUT"
|
|
30
|
+
|
|
31
|
+
PROBE_KINDS = (
|
|
32
|
+
"build",
|
|
33
|
+
"test",
|
|
34
|
+
"api_health",
|
|
35
|
+
"process_health",
|
|
36
|
+
"browser_smoke",
|
|
37
|
+
"cli_smoke",
|
|
38
|
+
"manual_operator",
|
|
39
|
+
)
|
|
40
|
+
|
|
41
|
+
FORBIDDEN_PATH_TOKENS = (".env", "intake_evidence", "handoffs/intake_evidence")
|
|
42
|
+
SECRET_FORBIDDEN_TOKENS = ("password", "credential", "api key")
|
|
43
|
+
|
|
44
|
+
JUDGMENT_DENY_TOKENS = (
|
|
45
|
+
"visually",
|
|
46
|
+
"aesthetically",
|
|
47
|
+
"operator confirms",
|
|
48
|
+
"subjective",
|
|
49
|
+
"human judgment",
|
|
50
|
+
"eyeball",
|
|
51
|
+
"manually verify appearance",
|
|
52
|
+
"approve layout",
|
|
53
|
+
)
|
|
54
|
+
|
|
55
|
+
AUTOMATABLE_UI_TOKENS = (
|
|
56
|
+
"click",
|
|
57
|
+
"fill",
|
|
58
|
+
"navigate",
|
|
59
|
+
"smoke",
|
|
60
|
+
"form",
|
|
61
|
+
"submit",
|
|
62
|
+
"button",
|
|
63
|
+
"page load",
|
|
64
|
+
"scroll",
|
|
65
|
+
"type into",
|
|
66
|
+
"select",
|
|
67
|
+
"checkbox",
|
|
68
|
+
"dropdown",
|
|
69
|
+
"ui",
|
|
70
|
+
"browser",
|
|
71
|
+
)
|
|
72
|
+
|
|
73
|
+
BROWSER_PROBE_MODES = ("cursor", "http_fallback", "playwright_fallback")
|
|
74
|
+
|
|
75
|
+
DEFAULT_PROBE_TIMEOUT = 120
|
|
76
|
+
DEFAULT_POLL_SECONDS = 60
|
|
77
|
+
DEFAULT_POLL_INTERVAL = 2
|
|
78
|
+
MAX_SCREENSHOTS = 5
|
|
79
|
+
|
|
80
|
+
|
|
81
|
+
def _merge_scratchpad(repo: Path) -> dict[str, str]:
|
|
82
|
+
values: dict[str, str] = {}
|
|
83
|
+
for name in (".cursor/scratchpad.md", ".cursor/scratchpad.local.md"):
|
|
84
|
+
path = repo / name
|
|
85
|
+
if not path.is_file():
|
|
86
|
+
continue
|
|
87
|
+
for line in path.read_text(encoding="utf-8").splitlines():
|
|
88
|
+
stripped = line.strip()
|
|
89
|
+
if not stripped or stripped.startswith("#"):
|
|
90
|
+
continue
|
|
91
|
+
if "=" in stripped:
|
|
92
|
+
key, _, val = stripped.partition("=")
|
|
93
|
+
values[key.strip()] = val.strip()
|
|
94
|
+
return values
|
|
95
|
+
|
|
96
|
+
|
|
97
|
+
def _read_int(merged: dict[str, str], key: str, default: int) -> int:
|
|
98
|
+
raw = merged.get(key, "")
|
|
99
|
+
if not raw:
|
|
100
|
+
return default
|
|
101
|
+
try:
|
|
102
|
+
return max(1, int(raw))
|
|
103
|
+
except ValueError:
|
|
104
|
+
return default
|
|
105
|
+
|
|
106
|
+
|
|
107
|
+
def read_browser_probe_mode(repo: Path) -> str:
|
|
108
|
+
merged = _merge_scratchpad(repo)
|
|
109
|
+
mode = merged.get("UAT_BROWSER_PROBE_MODE", "cursor").strip()
|
|
110
|
+
return mode if mode in BROWSER_PROBE_MODES else "cursor"
|
|
111
|
+
|
|
112
|
+
|
|
113
|
+
def read_fallback_chain(repo: Path) -> bool:
|
|
114
|
+
merged = _merge_scratchpad(repo)
|
|
115
|
+
raw = merged.get("UAT_BROWSER_FALLBACK_CHAIN", "1").strip()
|
|
116
|
+
if raw in ("0", "1"):
|
|
117
|
+
return raw == "1"
|
|
118
|
+
return True
|
|
119
|
+
|
|
120
|
+
|
|
121
|
+
def read_poll_settings(repo: Path) -> tuple[int, int]:
|
|
122
|
+
merged = _merge_scratchpad(repo)
|
|
123
|
+
cap = _read_int(merged, "UAT_PROCESS_HEALTH_POLL_SECONDS", DEFAULT_POLL_SECONDS)
|
|
124
|
+
interval = _read_int(
|
|
125
|
+
merged, "UAT_PROCESS_HEALTH_POLL_INTERVAL_SECONDS", DEFAULT_POLL_INTERVAL
|
|
126
|
+
)
|
|
127
|
+
return cap, interval
|
|
128
|
+
|
|
129
|
+
|
|
130
|
+
def detect_stack_profile(repo: Path) -> str | None:
|
|
131
|
+
if (repo / "package.json").is_file():
|
|
132
|
+
return "node"
|
|
133
|
+
if (repo / "pyproject.toml").is_file() or (repo / "setup.py").is_file():
|
|
134
|
+
return "python"
|
|
135
|
+
if (repo / "go.mod").is_file():
|
|
136
|
+
return "go"
|
|
137
|
+
if list(repo.glob("*.csproj")):
|
|
138
|
+
return "dotnet"
|
|
139
|
+
if (repo / "pom.xml").is_file():
|
|
140
|
+
return "java"
|
|
141
|
+
readme = repo / "README.md"
|
|
142
|
+
if readme.is_file() and "generated" in readme.read_text(encoding="utf-8").lower():
|
|
143
|
+
return "generated"
|
|
144
|
+
return None
|
|
145
|
+
|
|
146
|
+
|
|
147
|
+
def _forbidden(step_text: str) -> bool:
|
|
148
|
+
lower = step_text.lower()
|
|
149
|
+
if any(tok in lower for tok in FORBIDDEN_PATH_TOKENS):
|
|
150
|
+
return True
|
|
151
|
+
return any(tok in lower for tok in SECRET_FORBIDDEN_TOKENS)
|
|
152
|
+
|
|
153
|
+
|
|
154
|
+
def _has_judgment_deny(lower: str) -> bool:
|
|
155
|
+
return any(tok in lower for tok in JUDGMENT_DENY_TOKENS)
|
|
156
|
+
|
|
157
|
+
|
|
158
|
+
def _has_automatable_ui(lower: str) -> bool:
|
|
159
|
+
return any(tok in lower for tok in AUTOMATABLE_UI_TOKENS)
|
|
160
|
+
|
|
161
|
+
|
|
162
|
+
def _read_test_command(repo: Path) -> str | None:
|
|
163
|
+
runbook = repo / "docs" / "engineering" / "runbook.md"
|
|
164
|
+
if runbook.is_file():
|
|
165
|
+
m = re.search(r"^TEST_COMMAND:\s*(.+)$", runbook.read_text(encoding="utf-8"), re.M)
|
|
166
|
+
if m:
|
|
167
|
+
cmd = m.group(1).strip()
|
|
168
|
+
if cmd and "not configured" not in cmd.lower():
|
|
169
|
+
return cmd
|
|
170
|
+
merged = _merge_scratchpad(repo)
|
|
171
|
+
return merged.get("TEST_COMMAND") or None
|
|
172
|
+
|
|
173
|
+
|
|
174
|
+
def _read_build_command(repo: Path, profile: str | None) -> str | None:
|
|
175
|
+
if profile == "node" and (repo / "package.json").is_file():
|
|
176
|
+
try:
|
|
177
|
+
pkg = json.loads((repo / "package.json").read_text(encoding="utf-8"))
|
|
178
|
+
scripts = pkg.get("scripts", {})
|
|
179
|
+
if "build" in scripts:
|
|
180
|
+
return "npm run build"
|
|
181
|
+
except (json.JSONDecodeError, OSError):
|
|
182
|
+
pass
|
|
183
|
+
if profile == "python" and (repo / "pyproject.toml").is_file():
|
|
184
|
+
return "python -m build"
|
|
185
|
+
return None
|
|
186
|
+
|
|
187
|
+
|
|
188
|
+
def _read_health_url(repo: Path) -> str | None:
|
|
189
|
+
rc = repo / "docs" / "engineering" / "runtime-connectivity.md"
|
|
190
|
+
if rc.is_file():
|
|
191
|
+
m = re.search(r"https?://[^\s\)]+", rc.read_text(encoding="utf-8"))
|
|
192
|
+
if m:
|
|
193
|
+
return m.group(0).rstrip(".,)")
|
|
194
|
+
return None
|
|
195
|
+
|
|
196
|
+
|
|
197
|
+
def resolve_browser_url(repo: Path) -> str | None:
|
|
198
|
+
url = _read_health_url(repo)
|
|
199
|
+
if url:
|
|
200
|
+
return url
|
|
201
|
+
merged = _merge_scratchpad(repo)
|
|
202
|
+
port = merged.get("DEV_SERVER_PORT", "").strip()
|
|
203
|
+
if port:
|
|
204
|
+
return f"http://localhost:{port}/"
|
|
205
|
+
if (repo / "package.json").is_file():
|
|
206
|
+
try:
|
|
207
|
+
pkg = json.loads((repo / "package.json").read_text(encoding="utf-8"))
|
|
208
|
+
if pkg.get("scripts", {}).get("start") or pkg.get("scripts", {}).get("dev"):
|
|
209
|
+
default_port = port or "3000"
|
|
210
|
+
return f"http://localhost:{default_port}/"
|
|
211
|
+
except (json.JSONDecodeError, OSError):
|
|
212
|
+
pass
|
|
213
|
+
return None
|
|
214
|
+
|
|
215
|
+
|
|
216
|
+
def is_mcp_unavailable() -> bool:
|
|
217
|
+
ci = os.environ.get("CI", "").lower()
|
|
218
|
+
if ci in ("1", "true", "yes"):
|
|
219
|
+
return True
|
|
220
|
+
return os.environ.get("GITHUB_ACTIONS", "").lower() == "true"
|
|
221
|
+
|
|
222
|
+
|
|
223
|
+
def classify_step(step_text: str, repo: Path) -> tuple[str | None, str]:
|
|
224
|
+
if _forbidden(step_text):
|
|
225
|
+
return None, UAT_PROBE_FORBIDDEN
|
|
226
|
+
lower = step_text.lower()
|
|
227
|
+
profile = detect_stack_profile(repo)
|
|
228
|
+
|
|
229
|
+
if _has_judgment_deny(lower):
|
|
230
|
+
return "manual_operator", UAT_PROBE_UNRESOLVED
|
|
231
|
+
|
|
232
|
+
if any(w in lower for w in ("build", "compile", "bundle")):
|
|
233
|
+
if _read_build_command(repo, profile):
|
|
234
|
+
return "build", ""
|
|
235
|
+
return None, UAT_PROBE_UNRESOLVED
|
|
236
|
+
|
|
237
|
+
if any(w in lower for w in ("test", "pytest", "unit test", "integration test")):
|
|
238
|
+
if _read_test_command(repo) or profile in ("python", "node", "go", "generated"):
|
|
239
|
+
return "test", ""
|
|
240
|
+
return None, UAT_PROBE_UNRESOLVED
|
|
241
|
+
|
|
242
|
+
if any(w in lower for w in ("api", "health", "endpoint", "http", "rest")):
|
|
243
|
+
if _read_health_url(repo):
|
|
244
|
+
return "api_health", ""
|
|
245
|
+
return None, UAT_PROBE_UNRESOLVED
|
|
246
|
+
|
|
247
|
+
if any(w in lower for w in ("process", "startup", "server start", "readiness")):
|
|
248
|
+
if _extract_startup_command(step_text, repo) and (
|
|
249
|
+
_read_health_url(repo) or resolve_browser_url(repo)
|
|
250
|
+
):
|
|
251
|
+
return "process_health", ""
|
|
252
|
+
return "process_health", UAT_PROBE_UNRESOLVED
|
|
253
|
+
|
|
254
|
+
if _has_automatable_ui(lower):
|
|
255
|
+
if resolve_browser_url(repo):
|
|
256
|
+
return "browser_smoke", ""
|
|
257
|
+
return None, UAT_PROBE_UNRESOLVED
|
|
258
|
+
|
|
259
|
+
if any(w in lower for w in ("browser", "playwright", "smoke", "ui")):
|
|
260
|
+
if resolve_browser_url(repo):
|
|
261
|
+
return "browser_smoke", ""
|
|
262
|
+
return None, UAT_PROBE_UNRESOLVED
|
|
263
|
+
|
|
264
|
+
if any(w in lower for w in ("cli", "command line", "exit code")):
|
|
265
|
+
if _extract_backtick_command(step_text):
|
|
266
|
+
return "cli_smoke", ""
|
|
267
|
+
return "cli_smoke", UAT_PROBE_UNRESOLVED
|
|
268
|
+
|
|
269
|
+
if any(w in lower for w in ("manual", "operator", "human", "judgment")):
|
|
270
|
+
return "manual_operator", UAT_PROBE_UNRESOLVED
|
|
271
|
+
|
|
272
|
+
if profile is None:
|
|
273
|
+
return None, UAT_STACK_PROFILE_UNKNOWN
|
|
274
|
+
return None, UAT_PROBE_UNRESOLVED
|
|
275
|
+
|
|
276
|
+
|
|
277
|
+
def _extract_backtick_command(text: str) -> str | None:
|
|
278
|
+
m = re.search(r"`([^`]+)`", text)
|
|
279
|
+
return m.group(1).strip() if m else None
|
|
280
|
+
|
|
281
|
+
|
|
282
|
+
def _extract_stdout_expectation(text: str) -> str | None:
|
|
283
|
+
m = re.search(r'expect\s+"([^"]+)"', text, re.I)
|
|
284
|
+
if m:
|
|
285
|
+
return m.group(1)
|
|
286
|
+
m = re.search(r'output contains\s+"([^"]+)"', text, re.I)
|
|
287
|
+
return m.group(1) if m else None
|
|
288
|
+
|
|
289
|
+
|
|
290
|
+
def _extract_startup_command(step_text: str, repo: Path) -> str | None:
|
|
291
|
+
merged = _merge_scratchpad(repo)
|
|
292
|
+
override = merged.get("DEV_SERVER_COMMAND", "").strip()
|
|
293
|
+
if override:
|
|
294
|
+
return override
|
|
295
|
+
cmd = _extract_backtick_command(step_text)
|
|
296
|
+
if cmd:
|
|
297
|
+
return cmd
|
|
298
|
+
m = re.search(r'"([^"]+(?:start|dev|serve)[^"]*)"', step_text, re.I)
|
|
299
|
+
if m:
|
|
300
|
+
return m.group(1)
|
|
301
|
+
m = re.search(
|
|
302
|
+
r"(npm\s+(?:run\s+)?(?:start|dev)|yarn\s+(?:start|dev)|python\s+-m\s+\w+)",
|
|
303
|
+
step_text,
|
|
304
|
+
re.I,
|
|
305
|
+
)
|
|
306
|
+
if m:
|
|
307
|
+
return m.group(1)
|
|
308
|
+
profile = detect_stack_profile(repo)
|
|
309
|
+
if profile == "node" and (repo / "package.json").is_file():
|
|
310
|
+
try:
|
|
311
|
+
pkg = json.loads((repo / "package.json").read_text(encoding="utf-8"))
|
|
312
|
+
scripts = pkg.get("scripts", {})
|
|
313
|
+
if "dev" in scripts:
|
|
314
|
+
return "npm run dev"
|
|
315
|
+
if "start" in scripts:
|
|
316
|
+
return "npm run start"
|
|
317
|
+
except (json.JSONDecodeError, OSError):
|
|
318
|
+
pass
|
|
319
|
+
return None
|
|
320
|
+
|
|
321
|
+
|
|
322
|
+
def _http_get_probe(url: str, timeout: int) -> tuple[bool, str, dict[str, object]]:
|
|
323
|
+
meta: dict[str, object] = {"url": url}
|
|
324
|
+
try:
|
|
325
|
+
req = urllib.request.Request(url, method="GET")
|
|
326
|
+
with urllib.request.urlopen(req, timeout=min(timeout, 30)) as resp:
|
|
327
|
+
meta["status_code"] = resp.status
|
|
328
|
+
if 200 <= resp.status < 400:
|
|
329
|
+
return True, UAT_PROBE_PASS, meta
|
|
330
|
+
return False, UAT_BROWSER_PROBE_FAILED, meta
|
|
331
|
+
except urllib.error.URLError as exc:
|
|
332
|
+
meta["error"] = type(exc).__name__
|
|
333
|
+
return False, UAT_BROWSER_PROBE_FAILED, meta
|
|
334
|
+
except TimeoutError:
|
|
335
|
+
return False, UAT_BROWSER_PROBE_TIMEOUT, meta
|
|
336
|
+
|
|
337
|
+
|
|
338
|
+
def _playwright_probe(url: str, timeout: int) -> tuple[bool, str, dict[str, object]]:
|
|
339
|
+
meta: dict[str, object] = {"url": url}
|
|
340
|
+
script = (
|
|
341
|
+
"const { chromium } = require('playwright');"
|
|
342
|
+
"(async () => {"
|
|
343
|
+
f" const b = await chromium.launch(); const p = await b.newPage();"
|
|
344
|
+
f" await p.goto({json.dumps(url)}, {{ timeout: {min(timeout, 30) * 1000} }});"
|
|
345
|
+
" await b.close(); process.exit(0);"
|
|
346
|
+
"})().catch(() => process.exit(1));"
|
|
347
|
+
)
|
|
348
|
+
try:
|
|
349
|
+
proc = subprocess.run(
|
|
350
|
+
["node", "-e", script],
|
|
351
|
+
capture_output=True,
|
|
352
|
+
text=True,
|
|
353
|
+
timeout=min(timeout, 60),
|
|
354
|
+
)
|
|
355
|
+
meta["exit_code"] = proc.returncode
|
|
356
|
+
if proc.returncode == 0:
|
|
357
|
+
return True, UAT_PROBE_PASS, meta
|
|
358
|
+
return False, UAT_BROWSER_PROBE_FAILED, meta
|
|
359
|
+
except subprocess.TimeoutExpired:
|
|
360
|
+
return False, UAT_BROWSER_PROBE_TIMEOUT, meta
|
|
361
|
+
except OSError as exc:
|
|
362
|
+
meta["error"] = str(exc)
|
|
363
|
+
return False, UAT_BROWSER_UNAVAILABLE, meta
|
|
364
|
+
|
|
365
|
+
|
|
366
|
+
def _run_fallback_chain(
|
|
367
|
+
url: str,
|
|
368
|
+
repo: Path,
|
|
369
|
+
timeout: int,
|
|
370
|
+
*,
|
|
371
|
+
dom_interaction: bool = False,
|
|
372
|
+
) -> tuple[bool, str, dict[str, object], str]:
|
|
373
|
+
mode = read_browser_probe_mode(repo)
|
|
374
|
+
chain = read_fallback_chain(repo)
|
|
375
|
+
details: dict[str, object] = {"url": url, "execution_tier": "stdlib"}
|
|
376
|
+
|
|
377
|
+
if mode == "http_fallback":
|
|
378
|
+
ok, code, meta = _http_get_probe(url, timeout)
|
|
379
|
+
details.update(meta)
|
|
380
|
+
return ok, code, details, "http_fallback"
|
|
381
|
+
|
|
382
|
+
if mode == "playwright_fallback":
|
|
383
|
+
ok, code, meta = _playwright_probe(url, timeout)
|
|
384
|
+
details.update(meta)
|
|
385
|
+
if ok:
|
|
386
|
+
return ok, code, details, "playwright_fallback"
|
|
387
|
+
if chain:
|
|
388
|
+
ok, code, meta = _http_get_probe(url, timeout)
|
|
389
|
+
details.update(meta)
|
|
390
|
+
details["fallback_from"] = "playwright_fallback"
|
|
391
|
+
return ok, code, details, "http_fallback"
|
|
392
|
+
return ok, UAT_BROWSER_UNAVAILABLE, details, "playwright_fallback"
|
|
393
|
+
|
|
394
|
+
if dom_interaction and chain:
|
|
395
|
+
ok, code, meta = _playwright_probe(url, timeout)
|
|
396
|
+
if ok:
|
|
397
|
+
details.update(meta)
|
|
398
|
+
return ok, code, details, "playwright_fallback"
|
|
399
|
+
|
|
400
|
+
ok, code, meta = _http_get_probe(url, timeout)
|
|
401
|
+
details.update(meta)
|
|
402
|
+
if ok:
|
|
403
|
+
return ok, code, details, "http_fallback"
|
|
404
|
+
if chain and dom_interaction:
|
|
405
|
+
ok, code, meta = _playwright_probe(url, timeout)
|
|
406
|
+
details.update(meta)
|
|
407
|
+
details["fallback_from"] = "http_fallback"
|
|
408
|
+
return ok, code, details, "playwright_fallback"
|
|
409
|
+
return ok, code, details, "http_fallback"
|
|
410
|
+
|
|
411
|
+
|
|
412
|
+
def execute_browser_smoke(
|
|
413
|
+
step_text: str,
|
|
414
|
+
repo: Path,
|
|
415
|
+
*,
|
|
416
|
+
timeout: int = DEFAULT_PROBE_TIMEOUT,
|
|
417
|
+
) -> dict[str, object]:
|
|
418
|
+
mode = read_browser_probe_mode(repo)
|
|
419
|
+
url = resolve_browser_url(repo)
|
|
420
|
+
dom_interaction = _has_automatable_ui(step_text.lower())
|
|
421
|
+
result: dict[str, object] = {
|
|
422
|
+
"probe_kind": "browser_smoke",
|
|
423
|
+
"step": step_text[:200],
|
|
424
|
+
"stack_profile": detect_stack_profile(repo) or "unknown",
|
|
425
|
+
"probe_mode": mode,
|
|
426
|
+
"passed": False,
|
|
427
|
+
"reason_code": UAT_PROBE_UNRESOLVED,
|
|
428
|
+
"target_url": url,
|
|
429
|
+
}
|
|
430
|
+
|
|
431
|
+
if not url:
|
|
432
|
+
result["reason_code"] = UAT_PROBE_UNRESOLVED
|
|
433
|
+
return result
|
|
434
|
+
|
|
435
|
+
if mode == "cursor":
|
|
436
|
+
if is_mcp_unavailable():
|
|
437
|
+
result["reason_code"] = UAT_BROWSER_UNAVAILABLE
|
|
438
|
+
result["execution_tier"] = "stdlib"
|
|
439
|
+
if read_fallback_chain(repo):
|
|
440
|
+
ok, code, meta, fb_mode = _run_fallback_chain(
|
|
441
|
+
url, repo, timeout, dom_interaction=dom_interaction
|
|
442
|
+
)
|
|
443
|
+
result.update(meta)
|
|
444
|
+
result["probe_mode"] = fb_mode
|
|
445
|
+
result["passed"] = ok
|
|
446
|
+
result["reason_code"] = code if ok else UAT_BROWSER_PROBE_FAILED
|
|
447
|
+
if not ok and code == UAT_BROWSER_UNAVAILABLE:
|
|
448
|
+
result["reason_code"] = UAT_BROWSER_UNAVAILABLE
|
|
449
|
+
return result
|
|
450
|
+
result["execution_tier"] = "agent"
|
|
451
|
+
result["reason_code"] = UAT_PROBE_UNRESOLVED
|
|
452
|
+
result["agent_plan"] = {
|
|
453
|
+
"sequence": "browser_navigate → interact → screenshot → console/network → evidence",
|
|
454
|
+
"evidence_dir": "sprints/Sxxxx/evidence/browser/",
|
|
455
|
+
}
|
|
456
|
+
return result
|
|
457
|
+
|
|
458
|
+
result["execution_tier"] = "stdlib"
|
|
459
|
+
ok, code, meta, fb_mode = _run_fallback_chain(
|
|
460
|
+
url, repo, timeout, dom_interaction=dom_interaction
|
|
461
|
+
)
|
|
462
|
+
result.update(meta)
|
|
463
|
+
result["probe_mode"] = fb_mode
|
|
464
|
+
result["passed"] = ok
|
|
465
|
+
result["reason_code"] = code
|
|
466
|
+
return result
|
|
467
|
+
|
|
468
|
+
|
|
469
|
+
def execute_process_health(
|
|
470
|
+
step_text: str,
|
|
471
|
+
repo: Path,
|
|
472
|
+
*,
|
|
473
|
+
timeout: int = DEFAULT_PROBE_TIMEOUT,
|
|
474
|
+
poll_cap: int | None = None,
|
|
475
|
+
poll_interval: int | None = None,
|
|
476
|
+
) -> dict[str, object]:
|
|
477
|
+
cap, interval = read_poll_settings(repo)
|
|
478
|
+
if poll_cap is not None:
|
|
479
|
+
cap = poll_cap
|
|
480
|
+
if poll_interval is not None:
|
|
481
|
+
interval = poll_interval
|
|
482
|
+
|
|
483
|
+
startup = _extract_startup_command(step_text, repo)
|
|
484
|
+
health_url = _read_health_url(repo) or resolve_browser_url(repo)
|
|
485
|
+
result: dict[str, object] = {
|
|
486
|
+
"probe_kind": "process_health",
|
|
487
|
+
"step": step_text[:200],
|
|
488
|
+
"stack_profile": detect_stack_profile(repo) or "unknown",
|
|
489
|
+
"execution_tier": "stdlib",
|
|
490
|
+
"passed": False,
|
|
491
|
+
"reason_code": UAT_PROBE_UNRESOLVED,
|
|
492
|
+
}
|
|
493
|
+
|
|
494
|
+
if not startup or not health_url:
|
|
495
|
+
return result
|
|
496
|
+
|
|
497
|
+
result["startup_command"] = startup
|
|
498
|
+
result["health_url"] = health_url
|
|
499
|
+
proc: subprocess.Popen[str] | None = None
|
|
500
|
+
try:
|
|
501
|
+
proc = subprocess.Popen(
|
|
502
|
+
startup,
|
|
503
|
+
shell=True,
|
|
504
|
+
cwd=str(repo),
|
|
505
|
+
stdout=subprocess.DEVNULL,
|
|
506
|
+
stderr=subprocess.DEVNULL,
|
|
507
|
+
)
|
|
508
|
+
deadline = time.monotonic() + cap
|
|
509
|
+
while time.monotonic() < deadline:
|
|
510
|
+
ok, code, meta = _http_get_probe(health_url, min(timeout, interval + 2))
|
|
511
|
+
if ok:
|
|
512
|
+
result.update(meta)
|
|
513
|
+
result["passed"] = True
|
|
514
|
+
result["reason_code"] = UAT_PROBE_PASS
|
|
515
|
+
return result
|
|
516
|
+
time.sleep(interval)
|
|
517
|
+
result["reason_code"] = UAT_PROBE_TIMEOUT
|
|
518
|
+
except OSError as exc:
|
|
519
|
+
result["reason_code"] = UAT_PROBE_FAILED
|
|
520
|
+
result["error"] = str(exc)
|
|
521
|
+
finally:
|
|
522
|
+
if proc is not None:
|
|
523
|
+
proc.terminate()
|
|
524
|
+
try:
|
|
525
|
+
proc.wait(timeout=5)
|
|
526
|
+
except subprocess.TimeoutExpired:
|
|
527
|
+
proc.kill()
|
|
528
|
+
return result
|
|
529
|
+
|
|
530
|
+
|
|
531
|
+
def execute_cli_smoke(
|
|
532
|
+
step_text: str,
|
|
533
|
+
repo: Path,
|
|
534
|
+
*,
|
|
535
|
+
timeout: int = DEFAULT_PROBE_TIMEOUT,
|
|
536
|
+
) -> dict[str, object]:
|
|
537
|
+
cmd = _extract_backtick_command(step_text)
|
|
538
|
+
expect_out = _extract_stdout_expectation(step_text)
|
|
539
|
+
result: dict[str, object] = {
|
|
540
|
+
"probe_kind": "cli_smoke",
|
|
541
|
+
"step": step_text[:200],
|
|
542
|
+
"stack_profile": detect_stack_profile(repo) or "unknown",
|
|
543
|
+
"execution_tier": "stdlib",
|
|
544
|
+
"passed": False,
|
|
545
|
+
"reason_code": UAT_PROBE_UNRESOLVED,
|
|
546
|
+
}
|
|
547
|
+
if not cmd:
|
|
548
|
+
return result
|
|
549
|
+
result["command"] = cmd
|
|
550
|
+
try:
|
|
551
|
+
proc = subprocess.run(
|
|
552
|
+
cmd,
|
|
553
|
+
shell=True,
|
|
554
|
+
cwd=str(repo),
|
|
555
|
+
timeout=timeout,
|
|
556
|
+
capture_output=True,
|
|
557
|
+
text=True,
|
|
558
|
+
)
|
|
559
|
+
result["exit_code"] = proc.returncode
|
|
560
|
+
if proc.returncode != 0:
|
|
561
|
+
result["reason_code"] = UAT_PROBE_FAILED
|
|
562
|
+
return result
|
|
563
|
+
if expect_out and expect_out not in proc.stdout:
|
|
564
|
+
result["reason_code"] = UAT_PROBE_FAILED
|
|
565
|
+
return result
|
|
566
|
+
result["reason_code"] = UAT_PROBE_PASS
|
|
567
|
+
result["passed"] = True
|
|
568
|
+
except subprocess.TimeoutExpired:
|
|
569
|
+
result["reason_code"] = UAT_PROBE_TIMEOUT
|
|
570
|
+
except OSError as exc:
|
|
571
|
+
result["reason_code"] = UAT_PROBE_FAILED
|
|
572
|
+
result["error"] = str(exc)
|
|
573
|
+
return result
|
|
574
|
+
|
|
575
|
+
|
|
576
|
+
def validate_browser_evidence(result: dict[str, object], mode: str) -> dict[str, object]:
|
|
577
|
+
out = dict(result)
|
|
578
|
+
if not out.get("passed"):
|
|
579
|
+
return out
|
|
580
|
+
if mode != "cursor":
|
|
581
|
+
return out
|
|
582
|
+
refs = out.get("browser_evidence_refs")
|
|
583
|
+
if not isinstance(refs, dict):
|
|
584
|
+
out["passed"] = False
|
|
585
|
+
out["reason_code"] = UAT_BROWSER_PROBE_FAILED
|
|
586
|
+
return out
|
|
587
|
+
nav = str(refs.get("navigation_url") or "").strip()
|
|
588
|
+
screenshots = refs.get("screenshots")
|
|
589
|
+
if not isinstance(screenshots, list):
|
|
590
|
+
screenshots = []
|
|
591
|
+
console = refs.get("console_summary")
|
|
592
|
+
network = refs.get("network_summary")
|
|
593
|
+
console_path = ""
|
|
594
|
+
network_path = ""
|
|
595
|
+
if isinstance(console, dict):
|
|
596
|
+
console_path = str(console.get("summary_path") or "")
|
|
597
|
+
if isinstance(network, dict):
|
|
598
|
+
network_path = str(network.get("summary_path") or "")
|
|
599
|
+
has_evidence = bool(nav) and (
|
|
600
|
+
bool(screenshots) or bool(console_path) or bool(network_path)
|
|
601
|
+
)
|
|
602
|
+
if len(screenshots) > MAX_SCREENSHOTS:
|
|
603
|
+
has_evidence = False
|
|
604
|
+
if not has_evidence:
|
|
605
|
+
out["passed"] = False
|
|
606
|
+
out["reason_code"] = UAT_BROWSER_PROBE_FAILED
|
|
607
|
+
return out
|
|
608
|
+
|
|
609
|
+
|
|
610
|
+
def merge_result_fragment(fragment: dict[str, object], repo: Path) -> dict[str, object]:
|
|
611
|
+
mode = read_browser_probe_mode(repo)
|
|
612
|
+
if "probe_mode" not in fragment:
|
|
613
|
+
fragment = dict(fragment)
|
|
614
|
+
fragment["probe_mode"] = mode
|
|
615
|
+
return validate_browser_evidence(fragment, mode)
|
|
616
|
+
|
|
617
|
+
|
|
618
|
+
def execute_probe(
|
|
619
|
+
kind: str,
|
|
620
|
+
step_text: str,
|
|
621
|
+
repo: Path,
|
|
622
|
+
*,
|
|
623
|
+
timeout: int = DEFAULT_PROBE_TIMEOUT,
|
|
624
|
+
) -> dict[str, object]:
|
|
625
|
+
profile = detect_stack_profile(repo)
|
|
626
|
+
result: dict[str, object] = {
|
|
627
|
+
"probe_kind": kind,
|
|
628
|
+
"step": step_text[:200],
|
|
629
|
+
"stack_profile": profile or "unknown",
|
|
630
|
+
"reason_code": UAT_PROBE_UNRESOLVED,
|
|
631
|
+
"passed": False,
|
|
632
|
+
}
|
|
633
|
+
|
|
634
|
+
if kind == "manual_operator":
|
|
635
|
+
result["reason_code"] = UAT_PROBE_UNRESOLVED
|
|
636
|
+
return result
|
|
637
|
+
|
|
638
|
+
if kind == "build":
|
|
639
|
+
cmd = _read_build_command(repo, profile)
|
|
640
|
+
if not cmd:
|
|
641
|
+
result["reason_code"] = UAT_PROBE_UNRESOLVED
|
|
642
|
+
return result
|
|
643
|
+
result["execution_tier"] = "stdlib"
|
|
644
|
+
return _run_subprocess(cmd, repo, timeout, result)
|
|
645
|
+
|
|
646
|
+
if kind == "test":
|
|
647
|
+
cmd = _read_test_command(repo)
|
|
648
|
+
if not cmd:
|
|
649
|
+
if profile == "python":
|
|
650
|
+
cmd = "python -m pytest -q"
|
|
651
|
+
elif profile == "node":
|
|
652
|
+
cmd = "npm test"
|
|
653
|
+
elif profile == "generated":
|
|
654
|
+
cmd = "python -m pytest -q"
|
|
655
|
+
else:
|
|
656
|
+
result["reason_code"] = UAT_PROBE_UNRESOLVED
|
|
657
|
+
return result
|
|
658
|
+
result["execution_tier"] = "stdlib"
|
|
659
|
+
return _run_subprocess(cmd, repo, timeout, result)
|
|
660
|
+
|
|
661
|
+
if kind == "api_health":
|
|
662
|
+
url = _read_health_url(repo)
|
|
663
|
+
if not url:
|
|
664
|
+
result["reason_code"] = UAT_PROBE_UNRESOLVED
|
|
665
|
+
return result
|
|
666
|
+
result["execution_tier"] = "stdlib"
|
|
667
|
+
ok, code, meta = _http_get_probe(url, timeout)
|
|
668
|
+
result.update(meta)
|
|
669
|
+
result["passed"] = ok
|
|
670
|
+
result["reason_code"] = code if ok else UAT_PROBE_FAILED
|
|
671
|
+
return result
|
|
672
|
+
|
|
673
|
+
if kind == "process_health":
|
|
674
|
+
return execute_process_health(step_text, repo, timeout=timeout)
|
|
675
|
+
|
|
676
|
+
if kind == "browser_smoke":
|
|
677
|
+
return execute_browser_smoke(step_text, repo, timeout=timeout)
|
|
678
|
+
|
|
679
|
+
if kind == "cli_smoke":
|
|
680
|
+
return execute_cli_smoke(step_text, repo, timeout=timeout)
|
|
681
|
+
|
|
682
|
+
result["reason_code"] = UAT_PROBE_UNRESOLVED
|
|
683
|
+
return result
|
|
684
|
+
|
|
685
|
+
|
|
686
|
+
def _run_subprocess(
|
|
687
|
+
cmd: str,
|
|
688
|
+
repo: Path,
|
|
689
|
+
timeout: int,
|
|
690
|
+
result: dict[str, object],
|
|
691
|
+
) -> dict[str, object]:
|
|
692
|
+
result["command"] = cmd
|
|
693
|
+
try:
|
|
694
|
+
proc = subprocess.run(
|
|
695
|
+
cmd,
|
|
696
|
+
shell=True,
|
|
697
|
+
cwd=str(repo),
|
|
698
|
+
timeout=timeout,
|
|
699
|
+
capture_output=True,
|
|
700
|
+
text=True,
|
|
701
|
+
)
|
|
702
|
+
result["exit_code"] = proc.returncode
|
|
703
|
+
if proc.returncode == 0:
|
|
704
|
+
result["reason_code"] = UAT_PROBE_PASS
|
|
705
|
+
result["passed"] = True
|
|
706
|
+
else:
|
|
707
|
+
result["reason_code"] = UAT_PROBE_FAILED
|
|
708
|
+
except subprocess.TimeoutExpired:
|
|
709
|
+
result["reason_code"] = UAT_PROBE_TIMEOUT
|
|
710
|
+
except OSError as exc:
|
|
711
|
+
result["reason_code"] = UAT_PROBE_FAILED
|
|
712
|
+
result["error"] = str(exc)
|
|
713
|
+
return result
|
|
714
|
+
|
|
715
|
+
|
|
716
|
+
def resolve_and_probe(step_text: str, repo: Path) -> dict[str, object]:
|
|
717
|
+
kind, pre_reason = classify_step(step_text, Path(repo))
|
|
718
|
+
if kind is None:
|
|
719
|
+
return {
|
|
720
|
+
"probe_kind": None,
|
|
721
|
+
"reason_code": pre_reason or UAT_PROBE_UNRESOLVED,
|
|
722
|
+
"passed": False,
|
|
723
|
+
}
|
|
724
|
+
if pre_reason == UAT_PROBE_FORBIDDEN:
|
|
725
|
+
return {"probe_kind": kind, "reason_code": UAT_PROBE_FORBIDDEN, "passed": False}
|
|
726
|
+
if pre_reason == UAT_PROBE_UNRESOLVED and kind in ("manual_operator",):
|
|
727
|
+
return {
|
|
728
|
+
"probe_kind": kind,
|
|
729
|
+
"reason_code": UAT_PROBE_UNRESOLVED,
|
|
730
|
+
"passed": False,
|
|
731
|
+
}
|
|
732
|
+
return execute_probe(kind, step_text, Path(repo))
|
|
733
|
+
|
|
734
|
+
|
|
735
|
+
def probe_steps(steps: list[str], repo: Path) -> list[dict[str, object]]:
|
|
736
|
+
return [resolve_and_probe(step, repo) for step in steps]
|
|
737
|
+
|
|
738
|
+
|
|
739
|
+
def self_test() -> None:
|
|
740
|
+
repo = Path(__file__).resolve().parents[1]
|
|
741
|
+
assert "build" in PROBE_KINDS
|
|
742
|
+
|
|
743
|
+
r = classify_step("run unit tests", repo)
|
|
744
|
+
assert r[0] == "test" or r[1] in (UAT_PROBE_UNRESOLVED, "")
|
|
745
|
+
|
|
746
|
+
r2 = classify_step("read secrets from .env file", repo)
|
|
747
|
+
assert r2[1] == UAT_PROBE_FORBIDDEN
|
|
748
|
+
|
|
749
|
+
r3 = classify_step("enter password in login form", repo)
|
|
750
|
+
assert r3[1] == UAT_PROBE_FORBIDDEN
|
|
751
|
+
|
|
752
|
+
r4 = classify_step("operator visually confirms button click", repo)
|
|
753
|
+
assert r4[0] == "manual_operator"
|
|
754
|
+
assert r4[1] == UAT_PROBE_UNRESOLVED
|
|
755
|
+
|
|
756
|
+
r5 = classify_step("click submit button on home page", repo)
|
|
757
|
+
assert r5[0] == "browser_smoke" or r5[1] == UAT_PROBE_UNRESOLVED
|
|
758
|
+
|
|
759
|
+
r6 = classify_step("operator verifies compliance manually", repo)
|
|
760
|
+
assert r6[0] == "manual_operator"
|
|
761
|
+
|
|
762
|
+
mode = read_browser_probe_mode(repo)
|
|
763
|
+
assert mode in BROWSER_PROBE_MODES
|
|
764
|
+
|
|
765
|
+
bs = execute_browser_smoke("browser smoke test ui", repo)
|
|
766
|
+
assert bs.get("probe_mode") == "cursor"
|
|
767
|
+
assert bs["passed"] is False
|
|
768
|
+
if bs.get("target_url"):
|
|
769
|
+
assert bs.get("execution_tier") == "agent"
|
|
770
|
+
assert bs["reason_code"] == UAT_PROBE_UNRESOLVED
|
|
771
|
+
else:
|
|
772
|
+
assert bs["reason_code"] == UAT_PROBE_UNRESOLVED
|
|
773
|
+
|
|
774
|
+
bad_pass = validate_browser_evidence(
|
|
775
|
+
{"passed": True, "reason_code": UAT_PROBE_PASS},
|
|
776
|
+
"cursor",
|
|
777
|
+
)
|
|
778
|
+
assert bad_pass["passed"] is False
|
|
779
|
+
assert bad_pass["reason_code"] == UAT_BROWSER_PROBE_FAILED
|
|
780
|
+
|
|
781
|
+
good_pass = validate_browser_evidence(
|
|
782
|
+
{
|
|
783
|
+
"passed": True,
|
|
784
|
+
"reason_code": UAT_PROBE_PASS,
|
|
785
|
+
"browser_evidence_refs": {
|
|
786
|
+
"navigation_url": "http://localhost:3000/",
|
|
787
|
+
"screenshots": ["sprints/S0082/evidence/browser/pr-01.png"],
|
|
788
|
+
},
|
|
789
|
+
},
|
|
790
|
+
"cursor",
|
|
791
|
+
)
|
|
792
|
+
assert good_pass["passed"] is True
|
|
793
|
+
|
|
794
|
+
cli = execute_cli_smoke('run CLI `python -c "import sys; sys.exit(0)"` exit code 0', repo)
|
|
795
|
+
assert cli["passed"] is True
|
|
796
|
+
assert cli["reason_code"] == UAT_PROBE_PASS
|
|
797
|
+
|
|
798
|
+
ph = execute_process_health(
|
|
799
|
+
"wait for server startup readiness",
|
|
800
|
+
repo,
|
|
801
|
+
poll_cap=1,
|
|
802
|
+
poll_interval=1,
|
|
803
|
+
)
|
|
804
|
+
assert ph["reason_code"] in (UAT_PROBE_UNRESOLVED, UAT_PROBE_TIMEOUT, UAT_PROBE_FAILED)
|
|
805
|
+
|
|
806
|
+
merged = merge_result_fragment(
|
|
807
|
+
{"passed": True, "probe_kind": "browser_smoke"},
|
|
808
|
+
repo,
|
|
809
|
+
)
|
|
810
|
+
assert merged["passed"] is False
|
|
811
|
+
|
|
812
|
+
assert detect_stack_profile(repo) in ("python", "node", None, "generated")
|
|
813
|
+
|
|
814
|
+
|
|
815
|
+
def main() -> int:
|
|
816
|
+
import argparse
|
|
817
|
+
|
|
818
|
+
parser = argparse.ArgumentParser(description="UAT probe resolver (US-0092 / US-0093).")
|
|
819
|
+
parser.add_argument("--repo", default=".")
|
|
820
|
+
parser.add_argument("--step", action="append", default=[], help="Acceptance step text.")
|
|
821
|
+
parser.add_argument("--self-test", action="store_true")
|
|
822
|
+
parser.add_argument("--report", action="store_true", help="JSON probe results to stdout.")
|
|
823
|
+
parser.add_argument(
|
|
824
|
+
"--merge-result",
|
|
825
|
+
metavar="FRAGMENT.json",
|
|
826
|
+
help="Validate browser evidence fragment JSON (US-0093).",
|
|
827
|
+
)
|
|
828
|
+
args = parser.parse_args()
|
|
829
|
+
repo = Path(args.repo).resolve()
|
|
830
|
+
|
|
831
|
+
if args.self_test:
|
|
832
|
+
try:
|
|
833
|
+
self_test()
|
|
834
|
+
except AssertionError as exc:
|
|
835
|
+
print(f"self-test failed: {exc}", file=sys.stderr)
|
|
836
|
+
return 2
|
|
837
|
+
print("[UAT_PROBE_LIB_SELF_TEST_OK]")
|
|
838
|
+
return 0
|
|
839
|
+
|
|
840
|
+
if args.merge_result:
|
|
841
|
+
frag_path = Path(args.merge_result)
|
|
842
|
+
if not frag_path.is_file():
|
|
843
|
+
print(f"merge-result: file not found: {frag_path}", file=sys.stderr)
|
|
844
|
+
return 2
|
|
845
|
+
try:
|
|
846
|
+
fragment = json.loads(frag_path.read_text(encoding="utf-8"))
|
|
847
|
+
except json.JSONDecodeError as exc:
|
|
848
|
+
print(f"merge-result: invalid JSON: {exc}", file=sys.stderr)
|
|
849
|
+
return 2
|
|
850
|
+
validated = merge_result_fragment(fragment, repo)
|
|
851
|
+
print(json.dumps(validated, sort_keys=True, separators=(",", ":")))
|
|
852
|
+
return 0 if validated.get("passed") else 1
|
|
853
|
+
|
|
854
|
+
if args.report or args.step:
|
|
855
|
+
results = probe_steps(args.step or ["run tests"], repo)
|
|
856
|
+
print(json.dumps(results, sort_keys=True, separators=(",", ":")))
|
|
857
|
+
if any(r.get("reason_code") == UAT_PROBE_UNRESOLVED for r in results):
|
|
858
|
+
return 1
|
|
859
|
+
if any(not r.get("passed") for r in results):
|
|
860
|
+
return 1
|
|
861
|
+
return 0
|
|
862
|
+
|
|
863
|
+
parser.print_help()
|
|
864
|
+
return 2
|
|
865
|
+
|
|
866
|
+
|
|
867
|
+
if __name__ == "__main__":
|
|
868
|
+
sys.exit(main())
|