@tduyng/pi-devos 0.0.0-stage → 0.14.0

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.
Files changed (109) hide show
  1. package/CHANGELOG.md +1421 -0
  2. package/LICENSE +201 -0
  3. package/README.md +206 -2
  4. package/package.json +44 -4
  5. package/plugins/devos/agents/reader.md +27 -0
  6. package/plugins/devos/agents/verifier.md +155 -0
  7. package/plugins/devos/pi/extension/devos.ts +605 -0
  8. package/plugins/devos/scripts/check-evidence-router.sh +140 -0
  9. package/plugins/devos/scripts/evidence-router.py +254 -0
  10. package/plugins/devos/scripts/gates/check-dod-core.sh +285 -0
  11. package/plugins/devos/scripts/gates/check-dod.sh +38 -0
  12. package/plugins/devos/scripts/gates/check-implementation-boundary.sh +99 -0
  13. package/plugins/devos/scripts/gates/check-port-source.sh +134 -0
  14. package/plugins/devos/scripts/gates/check-report-locations.sh +148 -0
  15. package/plugins/devos/scripts/gates/check-scenario-coverage.sh +104 -0
  16. package/plugins/devos/scripts/gates/gate-check.mjs +204 -0
  17. package/plugins/devos/scripts/gates/phase-gate.sh +208 -0
  18. package/plugins/devos/scripts/gates/plan-template-check.py +141 -0
  19. package/plugins/devos/scripts/gates/run-gate.sh +148 -0
  20. package/plugins/devos/scripts/gates/spec-contract.sh +19 -0
  21. package/plugins/devos/scripts/gates/spec-template-check.py +152 -0
  22. package/plugins/devos/scripts/gates/suite/01-dod.sh +485 -0
  23. package/plugins/devos/scripts/gates/suite/02-integrity.sh +310 -0
  24. package/plugins/devos/scripts/gates/suite/03-archetype.sh +255 -0
  25. package/plugins/devos/scripts/gates/suite/04-spec-validator.sh +183 -0
  26. package/plugins/devos/scripts/gates/suite/05-requires.sh +360 -0
  27. package/plugins/devos/scripts/gates/suite/06-clarify-adapters.sh +435 -0
  28. package/plugins/devos/scripts/gates/suite/07-lint-evals.sh +350 -0
  29. package/plugins/devos/scripts/gates/suite/08-converge.sh +591 -0
  30. package/plugins/devos/scripts/gates/suite/09-quality.sh +516 -0
  31. package/plugins/devos/scripts/gates/suite/10-eval-harness.sh +679 -0
  32. package/plugins/devos/scripts/gates/test-gates.sh +76 -0
  33. package/plugins/devos/scripts/gates/test-integrity-rubric.sh +152 -0
  34. package/plugins/devos/scripts/gates/test-phase-gate.sh +116 -0
  35. package/plugins/devos/skills/absorb/SKILL.md +75 -0
  36. package/plugins/devos/skills/absorb/references/distill.md +67 -0
  37. package/plugins/devos/skills/absorb/scripts/check-refs.sh +108 -0
  38. package/plugins/devos/skills/absorb/scripts/knowledge.py +258 -0
  39. package/plugins/devos/skills/build/SKILL.md +71 -0
  40. package/plugins/devos/skills/build/references/advanced-routing.md +19 -0
  41. package/plugins/devos/skills/build/references/defect.md +17 -0
  42. package/plugins/devos/skills/build/references/exposure.md +28 -0
  43. package/plugins/devos/skills/build/references/hard.md +39 -0
  44. package/plugins/devos/skills/build/references/refactor.md +66 -0
  45. package/plugins/devos/skills/build/references/routes.md +56 -0
  46. package/plugins/devos/skills/build/references/scale.md +84 -0
  47. package/plugins/devos/skills/build/references/spike.md +19 -0
  48. package/plugins/devos/skills/build/scripts/construct-census.py +204 -0
  49. package/plugins/devos/skills/build/scripts/dep-order.py +297 -0
  50. package/plugins/devos/skills/build/scripts/ledger.sh +228 -0
  51. package/plugins/devos/skills/build/scripts/route.sh +5 -0
  52. package/plugins/devos/skills/build/scripts/secret-scan.sh +121 -0
  53. package/plugins/devos/skills/build/scripts/toolchain-preflight.py +302 -0
  54. package/plugins/devos/skills/frame/SKILL.md +54 -0
  55. package/plugins/devos/skills/frame/references/template.md +115 -0
  56. package/plugins/devos/skills/frame/scripts/survey.sh +44 -0
  57. package/plugins/devos/skills/implement/SKILL.md +36 -0
  58. package/plugins/devos/skills/implement/references/conditional-plan.md +17 -0
  59. package/plugins/devos/skills/implement/references/debug-loop.md +7 -0
  60. package/plugins/devos/skills/implement/references/dod.md +37 -0
  61. package/plugins/devos/skills/implement/references/implement.md +54 -0
  62. package/plugins/devos/skills/implement/references/manual-gates.md +16 -0
  63. package/plugins/devos/skills/implement/references/plan.md +142 -0
  64. package/plugins/devos/skills/implement/references/resume.md +9 -0
  65. package/plugins/devos/skills/implement/references/scale.md +86 -0
  66. package/plugins/devos/skills/implement/references/verify-close.md +62 -0
  67. package/plugins/devos/skills/implement/references/visual-verification.md +7 -0
  68. package/plugins/devos/skills/implement/scripts/check-converge.sh +147 -0
  69. package/plugins/devos/skills/implement/scripts/equivalence-check.sh +140 -0
  70. package/plugins/devos/skills/implement/scripts/manifest-queue.sh +185 -0
  71. package/plugins/devos/skills/implement/scripts/ops-log.sh +58 -0
  72. package/plugins/devos/skills/implement/scripts/pilot-consistency.py +173 -0
  73. package/plugins/devos/skills/implement/scripts/validate-spec.sh +220 -0
  74. package/plugins/devos/skills/init/SKILL.md +100 -0
  75. package/plugins/devos/skills/init/references/archetype-sections.md +15 -0
  76. package/plugins/devos/skills/init/references/context.md +42 -0
  77. package/plugins/devos/skills/init/references/conventions-template.md +153 -0
  78. package/plugins/devos/skills/init/references/reverse-engineer.md +3 -0
  79. package/plugins/devos/skills/init/references/rule-format.md +58 -0
  80. package/plugins/devos/skills/init/references/shape-model.md +29 -0
  81. package/plugins/devos/skills/init/scripts/detect-archetype.py +461 -0
  82. package/plugins/devos/skills/init/scripts/render-rule.py +114 -0
  83. package/plugins/devos/skills/init/scripts/reverse-engineer.sh +162 -0
  84. package/plugins/devos/skills/learn/SKILL.md +29 -0
  85. package/plugins/devos/skills/learn/references/destinations.md +43 -0
  86. package/plugins/devos/skills/learn/references/scoring.md +26 -0
  87. package/plugins/devos/skills/review/SKILL.md +54 -0
  88. package/plugins/devos/skills/review/references/comments.md +13 -0
  89. package/plugins/devos/skills/review/references/gaps.md +26 -0
  90. package/plugins/devos/skills/review/references/reviewer.md +124 -0
  91. package/plugins/devos/skills/review/references/routing.md +35 -0
  92. package/plugins/devos/skills/review/scripts/__pycache__/prepare.cpython-313.pyc +0 -0
  93. package/plugins/devos/skills/review/scripts/prepare.py +763 -0
  94. package/plugins/devos/skills/spec/SKILL.md +57 -0
  95. package/plugins/devos/skills/spec/references/prototype.md +21 -0
  96. package/plugins/devos/skills/spec/references/question-craft.md +47 -0
  97. package/plugins/devos/skills/spec/references/roadmap-link.md +5 -0
  98. package/plugins/devos/skills/spec/references/write-spec.md +128 -0
  99. package/plugins/devos/skills/spec/scripts/clarify.sh +173 -0
  100. package/plugins/devos/skills/status/SKILL.md +67 -0
  101. package/plugins/devos/skills/status/references/cost.md +38 -0
  102. package/plugins/devos/skills/status/scripts/artifact-budgets.sh +88 -0
  103. package/plugins/devos/skills/status/scripts/check-requires.py +556 -0
  104. package/plugins/devos/skills/status/scripts/context-cost.sh +89 -0
  105. package/plugins/devos/skills/status/scripts/convention-usage.sh +184 -0
  106. package/plugins/devos/skills/status/scripts/findings-summary.sh +112 -0
  107. package/plugins/devos/skills/status/scripts/quality-correlation.sh +259 -0
  108. package/plugins/devos/skills/status/scripts/sizing-calibration.sh +71 -0
  109. package/plugins/devos/skills/status/scripts/spec-diff.sh +137 -0
@@ -0,0 +1,148 @@
1
+ #!/bin/bash
2
+ # One dispatcher for every tool hook shim. Usage: run-gate.sh --agent <tool>
3
+ # <test-integrity|dod>.
4
+ #
5
+ # Per-tool differences (jq field paths, the rubric --format flag, the JSON
6
+ # response contract) live in the case branches below, one arm per tool that
7
+ # has a hook: claude, cursor, copilot, codex. Adding a tool that supports hooks is
8
+ # adding a case arm here.
9
+ #
10
+ # Hand-maintained since 0.11.9: the generator that used to emit this file was
11
+ # removed with the per-tool agent translations.
12
+ #
13
+ # Unparseable input allows rather than blocks: a broken adapter must never
14
+ # brick every edit in the session.
15
+ set -u
16
+ GATES="$(cd "$(dirname "${BASH_SOURCE[0]}")" 2>/dev/null && pwd)"
17
+
18
+ AGENT=""
19
+ GATE=""
20
+ while [[ $# -gt 0 ]]; do
21
+ case "$1" in
22
+ --agent)
23
+ [[ $# -ge 2 ]] || break
24
+ AGENT="$2"; shift 2
25
+ ;;
26
+ test-integrity|dod) GATE="$1"; shift;;
27
+ *) shift;;
28
+ esac
29
+ done
30
+ if [[ -z "$AGENT" || -z "$GATE" ]]; then
31
+ echo "run-gate.sh: usage: --agent <tool> <test-integrity|dod>" >&2
32
+ exit 0
33
+ fi
34
+
35
+ TI_FILE="" TI_CONTENT="" TI_NEW="" TI_OLD="" TI_FORMAT="" TI_ALLOW=""
36
+ DOD_TRANSCRIPT="" DOD_ALLOW="" DOD_DENY=""
37
+ case "$AGENT" in
38
+ cursor)
39
+ TI_FILE='.tool_input.path // .tool_input.file_path // .tool_input.target_file // empty'
40
+ TI_CONTENT='.tool_input.content // empty'
41
+ TI_NEW='.tool_input.new_string // .tool_input.new_content // empty'
42
+ TI_OLD='.tool_input.old_string // empty'
43
+ TI_FORMAT='cursor'
44
+ TI_ALLOW='{"permission":"allow"}'
45
+ DOD_TRANSCRIPT=''
46
+ DOD_ALLOW=''
47
+ DOD_DENY=''
48
+ ;;
49
+ copilot)
50
+ TI_FILE='.toolArgs.path // .toolArgs.file_path // .toolArgs.target_file // empty'
51
+ TI_CONTENT='.toolArgs.content // empty'
52
+ TI_NEW='.toolArgs.new_string // .toolArgs.new_content // empty'
53
+ TI_OLD='.toolArgs.old_string // empty'
54
+ TI_FORMAT='copilot'
55
+ TI_ALLOW='{"permissionDecision":"allow"}'
56
+ DOD_TRANSCRIPT='.transcriptPath // empty'
57
+ DOD_ALLOW='{"decision":"allow"}'
58
+ DOD_DENY='{"decision":"block","reason":"%s"}'
59
+ ;;
60
+ codex)
61
+ TI_FILE='.tool_input.path // .tool_input.file_path // .tool_input.target_file // empty'
62
+ TI_CONTENT='.tool_input.content // empty'
63
+ TI_NEW='.tool_input.new_string // .tool_input.new_content // empty'
64
+ TI_OLD='.tool_input.old_string // empty'
65
+ TI_FORMAT='codex'
66
+ TI_ALLOW='{"permissionDecision":"allow"}'
67
+ DOD_TRANSCRIPT='.transcript_path // empty'
68
+ DOD_ALLOW='{"continue":true}'
69
+ DOD_DENY='{"continue":false,"stopReason":"%s"}'
70
+ ;;
71
+ claude)
72
+ TI_FILE='.tool_input.file_path // empty'
73
+ TI_CONTENT='.tool_input.content // empty'
74
+ TI_NEW='.tool_input.new_string // empty'
75
+ TI_OLD='.tool_input.old_string // empty'
76
+ TI_FORMAT=''
77
+ TI_ALLOW=''
78
+ DOD_TRANSCRIPT=''
79
+ DOD_ALLOW=''
80
+ DOD_DENY=''
81
+ ;;
82
+ *)
83
+ exit 0
84
+ ;;
85
+ esac
86
+
87
+ if [[ "$GATE" == "test-integrity" ]]; then
88
+ command -v jq >/dev/null 2>&1 || { [[ -n "$TI_ALLOW" ]] && echo "$TI_ALLOW"; exit 0; }
89
+ # An unreachable rubric (moved clone, missing gate script) must allow, not
90
+ # exit 127 with no decision emitted.
91
+ [[ -x "$GATES/test-integrity-rubric.sh" ]] || { [[ -n "$TI_ALLOW" ]] && echo "$TI_ALLOW"; exit 0; }
92
+ input=$(cat)
93
+ file=$(printf '%s' "$input" | jq -r "$TI_FILE" 2>/dev/null)
94
+ content=$(printf '%s' "$input" | jq -r "$TI_CONTENT" 2>/dev/null)
95
+ new_string=$(printf '%s' "$input" | jq -r "$TI_NEW" 2>/dev/null)
96
+ old_string=$(printf '%s' "$input" | jq -r "$TI_OLD" 2>/dev/null)
97
+ if [[ -z "$file" ]]; then
98
+ if printf '%s' "$input" | jq -e 'has("tool_input") or has("toolArgs")' >/dev/null 2>&1; then
99
+ echo "run-gate.sh: test-integrity could not read file path from payload (field renamed?); allowing (fail-open)" >&2
100
+ fi
101
+ [[ -n "$TI_ALLOW" ]] && echo "$TI_ALLOW"
102
+ exit 0
103
+ fi
104
+ old_tmp=$(mktemp)
105
+ new_tmp=$(mktemp)
106
+ trap 'rm -f "$old_tmp" "$new_tmp"' EXIT
107
+ write=0
108
+ if [[ -n "$content" ]]; then
109
+ [[ -f "$file" ]] && cp "$file" "$old_tmp"
110
+ printf '%s' "$content" > "$new_tmp"
111
+ write=1
112
+ else
113
+ printf '%s' "$old_string" > "$old_tmp"
114
+ printf '%s' "$new_string" > "$new_tmp"
115
+ fi
116
+ if [[ -n "$TI_FORMAT" ]]; then
117
+ gate_args=(--format "$TI_FORMAT" --file "$file" --old "$old_tmp" --new "$new_tmp")
118
+ else
119
+ gate_args=(--file "$file" --old "$old_tmp" --new "$new_tmp")
120
+ fi
121
+ [[ "$write" -eq 1 ]] && gate_args+=(--write)
122
+ "$GATES/test-integrity-rubric.sh" "${gate_args[@]}"
123
+ status=$?
124
+ rm -f "$old_tmp" "$new_tmp"
125
+ exit "$status"
126
+ elif [[ "$GATE" == "dod" ]]; then
127
+ command -v jq >/dev/null 2>&1 || { [[ -n "$DOD_ALLOW" ]] && echo "$DOD_ALLOW"; exit 0; }
128
+ input=$(cat)
129
+ transcript=$(printf '%s' "$input" | jq -r "$DOD_TRANSCRIPT" 2>/dev/null)
130
+ if [[ -z "$transcript" || ! -x "$GATES/check-dod-core.sh" ]]; then
131
+ [[ -n "$DOD_ALLOW" ]] && echo "$DOD_ALLOW"
132
+ exit 0
133
+ fi
134
+ reason=$("$GATES/check-dod-core.sh" "$transcript" 2>&1)
135
+ status=$?
136
+ if [[ $status -eq 2 ]]; then
137
+ escaped=$(printf '%s' "$reason" | sed 's/"/\\"/g' | tr '\n' ' ')
138
+ if [[ -n "$DOD_DENY" ]]; then
139
+ printf "$DOD_DENY" "$escaped"
140
+ else
141
+ echo "$reason" >&2
142
+ exit 2
143
+ fi
144
+ else
145
+ [[ -n "$DOD_ALLOW" ]] && echo "$DOD_ALLOW"
146
+ fi
147
+ exit 0
148
+ fi
@@ -0,0 +1,19 @@
1
+ #!/bin/bash
2
+ # spec-contract.sh <spec-dir>: print the contract sections of spec.md (Goal,
3
+ # Scenarios, Functionality, Behavior delta, Invariant, Functional constraints,
4
+ # Out of scope) plus any Requires: line. Exit 1 with no output when spec.md is missing.
5
+ # spec-contract.sh --has-plan <spec-dir>: exit 0 when spec.md carries an Implementation Plan.
6
+ if [[ "${1:-}" == "--has-plan" ]]; then
7
+ grep -q '^## Implementation Plan' "${2:-}/spec.md" 2>/dev/null
8
+ exit
9
+ fi
10
+ dir="${1:-}"
11
+ [[ -f "$dir/spec.md" ]] || exit 1
12
+ awk '
13
+ /^## / {
14
+ h = tolower($0); sub(/^##[ \t]*/, "", h); sub(/^[0-9]+[.)]?[ \t]*/, "", h)
15
+ keep = (h ~ /^(goal|scenarios|functionality|behavior delta|invariant|functional constraints|out of scope)/)
16
+ }
17
+ /^Requires:/ { print; next }
18
+ keep { print }
19
+ ' "$dir/spec.md"
@@ -0,0 +1,152 @@
1
+ #!/usr/bin/env python3
2
+ """Both spec shapes in write-spec.md must pass the gate.
3
+
4
+ An M change is a few files with clear behavior, and the router sends it to the
5
+ one-page shape as the whole specification. An L change is sent to the full
6
+ shape. Both are contracts in the same sense the plan.md template is one: if
7
+ either drifts from what validate-spec.sh reads, every spec the model writes
8
+ from it is rejected, and the first thing that shows it is a real run failing on
9
+ something nobody changed.
10
+
11
+ Each block is extracted, its placeholders filled, and the result run through the
12
+ gate. The REQUIRED pre-assert is one-directional on purpose: remove Out of scope
13
+ from a block and validate-spec rejects the specimen. Add a new requirement to
14
+ validate-spec.sh and a specimen fails because the block does not carry it. Both
15
+ directions were checked by hand before this shipped.
16
+ """
17
+ import re
18
+ import subprocess
19
+ import sys
20
+ import tempfile
21
+ from pathlib import Path
22
+
23
+ ROOT = Path(__file__).resolve().parents[4]
24
+ SKILLS = ROOT / "plugins/devos/skills"
25
+ WRITE_SPEC = SKILLS / "spec/references/write-spec.md"
26
+ VALIDATE = SKILLS / "implement/scripts/validate-spec.sh"
27
+
28
+ # The three things validate-spec.sh requires of a functional spec. Present as
29
+ # substrings because the block is a template, not a finished spec.
30
+ REQUIRED = [
31
+ "## Goal",
32
+ "## Scenarios",
33
+ "Scenario SC-1:",
34
+ "Scenario SC-2:",
35
+ "WHEN [condition] / THEN [observable outcome]",
36
+ "## Out of scope",
37
+ ]
38
+
39
+ FILL = [
40
+ (r"^# \[Feature Name\]$", "# Export invoices"),
41
+ (r"^\[1-2 sentences of business purpose\]$", "A user downloads their invoices."),
42
+ (r"^- Scenario SC-1: .*$",
43
+ "- Scenario SC-1: plain export / WHEN an account has 3 invoices "
44
+ "/ THEN a PDF with all 3 is downloaded"),
45
+ (r"^- Scenario SC-2: .*$",
46
+ "- Scenario SC-2: empty account / WHEN an account has no invoices "
47
+ "/ THEN the export is refused naming why"),
48
+ (r"^- \[Item 1 explicitly out of scope\]$", "- Scheduled exports"),
49
+ ]
50
+
51
+ # The full L shape. Same three requirements plus the two sections an L feature
52
+ # exists to produce, the Behavior delta and the Functional Constraints.
53
+ L_REQUIRED = REQUIRED + ["## Behavior delta", "## Functional constraints"]
54
+
55
+ L_FILL = FILL + [
56
+ (r"^- \[Rule 1\]$", "- one rule"),
57
+ (r"^\*\*Added\*\* \(capability: .*$", "**Added** (capability: `invoices`):"),
58
+ (r"^- \[New behavior, one line each\]$", "- a new behavior"),
59
+ (r"^- \[Current behavior, quoted\] → \[new behavior\]$", "- old -> new"),
60
+ (r"^\*\*Modified\*\* \(capability: .*$", "**Modified** (capability: `invoices`):"),
61
+ (r"^\*\*Removed:\*\* \(none\)$", "**Removed:** (none)"),
62
+ (r"^- \[Constraint 1, functional only\]$", "- functional only"),
63
+ (r"^\*\*Engineer overrides:\*\* .*$", "**Engineer overrides:** none"),
64
+ (r"^\*\*Open assumptions:\*\* .*$", "**Open assumptions:** none"),
65
+ (r"^Requires: .*$", "Requires: none"),
66
+ ]
67
+
68
+
69
+ def block(heading, required, fill):
70
+ body = WRITE_SPEC.read_text()
71
+ # Take the first fenced block after the heading rather than slicing to the
72
+ # next `## ` line: the block's own headings (`## Goal`, `## Out of
73
+ # scope`) are the same level, so a section boundary cannot find the end of
74
+ # it. Locating the fence by position survives renumbering the sections.
75
+ start = re.search(rf"^## \d+\. {re.escape(heading)}$", body, re.M)
76
+ if not start:
77
+ raise SystemExit(f"FAIL spec-template: write-spec.md has no '{heading}' section")
78
+ fenced = re.search(r"```markdown\n(.*?)\n```", body[start.end():], re.S)
79
+ if not fenced:
80
+ raise SystemExit(f"FAIL spec-template: the {heading} section carries no ```markdown block")
81
+ raw = fenced.group(1)
82
+ absent = [t for t in required if t not in raw]
83
+ if absent:
84
+ raise SystemExit(
85
+ f"FAIL spec-template: the {heading} block no longer carries what "
86
+ "validate-spec.sh requires, so every spec written from it is rejected. "
87
+ "Missing:\n " + "\n ".join(absent))
88
+ spec = raw
89
+ for pattern, value in fill:
90
+ spec = re.sub(pattern, value, spec, flags=re.M)
91
+ # Ask the drift question against the RAW block: a raw line carrying a
92
+ # bracket that no FILL rule matches is a placeholder this specimen does not
93
+ # fill, so it is testing an older shape than the file holds. Asking it
94
+ # against the substituted text instead is wrong, because a replacement value
95
+ # may itself contain brackets, which is exactly what `- [ ] Criterion 1`
96
+ # does.
97
+ unfilled = [l.strip() for l in raw.splitlines()
98
+ if "[" in l and l.strip() != "["
99
+ and not any(re.search(p, l, re.M) for p, _ in fill)]
100
+ if unfilled:
101
+ raise SystemExit(
102
+ f"FAIL spec-template: the FILL list no longer covers the {heading} block, "
103
+ "so this check is testing an older shape than the file holds. Unfilled:\n "
104
+ + "\n ".join(unfilled[:6]))
105
+ # Guidance inside the form lands in the artifact. Two real specs in this
106
+ # repo still carry a template note that told the writer where technical
107
+ # constraints belong, because it was a line of the form rather than of the
108
+ # instructions. A short bracketed line is a field placeholder the author
109
+ # overwrites; a long one is a paragraph of advice nobody overwrites.
110
+ paras = [l.strip() for l in raw.splitlines()
111
+ if len(l.strip()) > 60 and l.strip().startswith("[") and l.strip().endswith("]")]
112
+ if paras:
113
+ raise SystemExit(
114
+ f"FAIL spec-template: the {heading} block carries guidance a model will "
115
+ "paste into the spec instead of a field it will fill:\n "
116
+ + "\n ".join(p[:70] for p in paras[:4])
117
+ + "\n fix: move it above the fence, into the section's prose")
118
+ return spec.rstrip() + "\n"
119
+
120
+
121
+ def m_block():
122
+ return block("M: one page", REQUIRED, FILL)
123
+
124
+
125
+ def l_block():
126
+ return block("L: the full shape", L_REQUIRED, L_FILL)
127
+
128
+
129
+ def main():
130
+ failures = []
131
+ for label, shape in (("M: one page", m_block), ("L: the full shape", l_block)):
132
+ spec = shape()
133
+ with tempfile.TemporaryDirectory() as tmp:
134
+ d = Path(tmp) / "spec"
135
+ d.mkdir()
136
+ (d / "spec.md").write_text(spec)
137
+ r = subprocess.run(["bash", str(VALIDATE), str(d)],
138
+ capture_output=True, text=True)
139
+ if r.returncode != 0:
140
+ failures.append((label, r.stdout + r.stderr))
141
+ if failures:
142
+ for label, out in failures:
143
+ print(f"FAIL the {label} shape in write-spec.md does not pass "
144
+ "validate-spec, so every spec the model writes from it is "
145
+ "rejected:", file=sys.stderr)
146
+ print(out, file=sys.stderr)
147
+ return 1
148
+ print("PASS both spec shapes in write-spec.md pass validate-spec")
149
+ return 0
150
+
151
+
152
+ sys.exit(main())