File size: 7,641 Bytes
7e9a520
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
"""Generate a release-readiness gate report for AtlasOps.

The goal is to provide a single command that validates core shipping evidence
before hackathon submission and emits a human-readable markdown report.
"""

from __future__ import annotations

import argparse
from dataclasses import dataclass
from pathlib import Path
import sys


ROOT = Path(__file__).resolve().parents[1]
DEFAULT_OUTPUT = ROOT / "docs" / "RELEASE_READINESS.md"


@dataclass
class CheckResult:
    name: str
    status: str  # PASS | FAIL | WARN
    details: str
    critical: bool = True


def _exists(path: Path) -> bool:
    return path.exists()


def _read_text(path: Path) -> str:
    return path.read_text(encoding="utf-8") if path.exists() else ""


def check_artifact_presence() -> list[CheckResult]:
    required = [
        ROOT / "docs" / "AMD_FINAL_DELIVERY_SCORECARD_AND_REWARD_SPEC.md",
        ROOT / "docs" / "MI300X_EVIDENCE.md",
        ROOT / "bench" / "results" / "comparison_table.md",
        ROOT / "tests" / "test_app_endpoints.py",
        ROOT / "tests" / "test_bench_runner.py",
        ROOT / "tests" / "test_chaos_manifests.py",
    ]
    missing = [str(p.relative_to(ROOT)) for p in required if not _exists(p)]
    if missing:
        return [CheckResult("Required artifacts", "FAIL", f"Missing: {', '.join(missing)}", True)]
    return [CheckResult("Required artifacts", "PASS", "All required docs/results/tests present.", True)]


def check_chaos_manifest_inventory() -> list[CheckResult]:
    expected = {
        "single_fault": 8,
        "cascade": 5,
        "multi_fault": 5,
        "named_replays": 10,
    }
    results: list[CheckResult] = []
    for tier, count in expected.items():
        actual = len(list((ROOT / "bench" / "chaos_manifests" / tier).glob("*.yaml")))
        if actual != count:
            results.append(
                CheckResult(
                    f"Chaos manifest count ({tier})",
                    "FAIL",
                    f"Expected {count}, found {actual}.",
                    True,
                )
            )
        else:
            results.append(
                CheckResult(
                    f"Chaos manifest count ({tier})",
                    "PASS",
                    f"Expected {count}, found {actual}.",
                    True,
                )
            )
    return results


def check_runtime_tiers() -> list[CheckResult]:
    runtime_text = _read_text(ROOT / "config" / "runtime.py")
    expected_tiers = ["warmup", "single_fault", "cascade", "multi_fault", "adversarial"]
    missing_from_speed = [t for t in expected_tiers if f'"{t}"' not in runtime_text]
    base = []
    if missing_from_speed:
        base.append(
            CheckResult(
                "Difficulty tiers declared",
                "FAIL",
                "Missing tier labels in runtime config: " + ", ".join(missing_from_speed),
                True,
            )
        )
    else:
        base.append(
            CheckResult(
                "Difficulty tiers declared",
                "PASS",
                "All five required tiers are declared in runtime config.",
                True,
            )
        )

    # Advisory: warmup/adversarial scenario pools are often omitted accidentally.
    advisory_missing = [
        t for t in ("warmup", "adversarial") if f'SCENARIOS_BY_TIER = {{' in runtime_text and f'"{t}":' not in runtime_text
    ]
    if advisory_missing:
        base.append(
            CheckResult(
                "Tier scenario pool coverage",
                "WARN",
                "No explicit SCENARIOS_BY_TIER entries for: " + ", ".join(advisory_missing),
                False,
            )
        )
    else:
        base.append(
            CheckResult(
                "Tier scenario pool coverage",
                "PASS",
                "Scenario pools include all required tiers or intentionally map tiers elsewhere.",
                False,
            )
        )
    return base


def check_ui_runtime_config() -> list[CheckResult]:
    app_text = _read_text(ROOT / "app.py")
    static_text = _read_text(ROOT / "static" / "index.html")
    checks = [
        ("/config endpoint", '@app.get("/config")' in app_text),
        ("Static UI dynamic config", "fetch('/config'" in static_text),
    ]
    out: list[CheckResult] = []
    for name, ok in checks:
        out.append(
            CheckResult(
                name,
                "PASS" if ok else "FAIL",
                "Configured correctly." if ok else "Missing expected runtime-config wiring.",
                True,
            )
        )
    return out


def check_benchmark_columns() -> list[CheckResult]:
    table = _read_text(ROOT / "bench" / "results" / "comparison_table.md")
    if not table:
        return [CheckResult("Benchmark output sanity", "FAIL", "comparison_table.md missing or empty.", True)]
    expected_tokens = ["avg_reward_contract", "avg_penalty", "unsafe_actions", "false_resolution", "hallucinated_evidence"]
    missing = [t for t in expected_tokens if t not in table]
    if missing:
        return [
            CheckResult(
                "Benchmark output sanity",
                "WARN",
                "Missing newer anti-gaming columns: " + ", ".join(missing),
                False,
            )
        ]
    return [CheckResult("Benchmark output sanity", "PASS", "Anti-gaming benchmark columns present.", False)]


def run_checks() -> list[CheckResult]:
    results: list[CheckResult] = []
    results.extend(check_artifact_presence())
    results.extend(check_chaos_manifest_inventory())
    results.extend(check_runtime_tiers())
    results.extend(check_ui_runtime_config())
    results.extend(check_benchmark_columns())
    return results


def render_report(results: list[CheckResult]) -> str:
    critical_failures = [r for r in results if r.critical and r.status == "FAIL"]
    warnings = [r for r in results if r.status == "WARN"]
    overall = "PASS" if not critical_failures else "FAIL"
    lines = [
        "# AtlasOps Release Readiness",
        "",
        f"- Overall: **{overall}**",
        f"- Critical failures: **{len(critical_failures)}**",
        f"- Warnings: **{len(warnings)}**",
        "",
        "## Checks",
    ]
    for r in results:
        icon = "PASS" if r.status == "PASS" else ("FAIL" if r.status == "FAIL" else "WARN")
        gate = "critical" if r.critical else "advisory"
        lines.append(f"- [{icon}] `{r.name}` ({gate}) - {r.details}")
    lines.append("")
    if critical_failures:
        lines.append("## Blockers")
        for r in critical_failures:
            lines.append(f"- `{r.name}` - {r.details}")
        lines.append("")
    return "\n".join(lines) + "\n"


def main() -> int:
    parser = argparse.ArgumentParser(description="Run AtlasOps release readiness gate.")
    parser.add_argument("--output", default=str(DEFAULT_OUTPUT), help="Markdown report output path.")
    parser.add_argument("--strict", action="store_true", help="Return non-zero on critical failures.")
    args = parser.parse_args()

    results = run_checks()
    report = render_report(results)
    output_path = Path(args.output)
    output_path.parent.mkdir(parents=True, exist_ok=True)
    output_path.write_text(report, encoding="utf-8")
    print(f"Wrote release readiness report: {output_path}")
    critical_failures = [r for r in results if r.critical and r.status == "FAIL"]
    if args.strict and critical_failures:
        print("Release gate failed (critical checks).", file=sys.stderr)
        return 1
    return 0


if __name__ == "__main__":
    raise SystemExit(main())