@ryuenn3123/agentic-senior-core 2.0.24 → 2.0.25
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/.cursorrules
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
# AGENTIC-SENIOR-CORE DYNAMIC GOVERNANCE RULESET
|
|
2
2
|
|
|
3
|
-
Generated by Agentic-Senior-Core CLI v2.0.
|
|
3
|
+
Generated by Agentic-Senior-Core CLI v2.0.25
|
|
4
4
|
Timestamp: 2026-04-15T00:14:51.184Z
|
|
5
5
|
Selected profile: beginner
|
|
6
6
|
Selected policy file: .agent-context/policies/llm-judge-threshold.json
|
|
@@ -30,9 +30,16 @@ jobs:
|
|
|
30
30
|
node ./scripts/detection-benchmark.mjs > detection-benchmark-report.json
|
|
31
31
|
test -s detection-benchmark-report.json
|
|
32
32
|
|
|
33
|
+
- name: Run benchmark anti-regression gate
|
|
34
|
+
run: |
|
|
35
|
+
node ./scripts/benchmark-gate.mjs > benchmark-gate-report.json
|
|
36
|
+
test -s benchmark-gate-report.json
|
|
37
|
+
|
|
33
38
|
- name: Upload benchmark artifact
|
|
34
39
|
if: always()
|
|
35
40
|
uses: actions/upload-artifact@v4
|
|
36
41
|
with:
|
|
37
42
|
name: detection-benchmark-report
|
|
38
|
-
path:
|
|
43
|
+
path: |
|
|
44
|
+
detection-benchmark-report.json
|
|
45
|
+
benchmark-gate-report.json
|
package/.windsurfrules
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
# AGENTIC-SENIOR-CORE DYNAMIC GOVERNANCE RULESET
|
|
2
2
|
|
|
3
|
-
Generated by Agentic-Senior-Core CLI v2.0.
|
|
3
|
+
Generated by Agentic-Senior-Core CLI v2.0.25
|
|
4
4
|
Timestamp: 2026-04-15T00:14:51.184Z
|
|
5
5
|
Selected profile: beginner
|
|
6
6
|
Selected policy file: .agent-context/policies/llm-judge-threshold.json
|
|
@@ -184,7 +184,15 @@ export async function runProjectDiscovery(userInterface, options = {}) {
|
|
|
184
184
|
}
|
|
185
185
|
|
|
186
186
|
if (!projectName) {
|
|
187
|
-
|
|
187
|
+
const projectNamePrompt = defaultProjectName
|
|
188
|
+
? `Project name (press Enter to use folder name: ${defaultProjectName}): `
|
|
189
|
+
: 'Project name: ';
|
|
190
|
+
|
|
191
|
+
projectName = (await userInterface.question(projectNamePrompt)).trim();
|
|
192
|
+
|
|
193
|
+
if (!projectName && defaultProjectName) {
|
|
194
|
+
projectName = defaultProjectName;
|
|
195
|
+
}
|
|
188
196
|
}
|
|
189
197
|
|
|
190
198
|
if (!projectName) {
|
package/package.json
CHANGED
package/scripts/release-gate.mjs
CHANGED
|
@@ -36,6 +36,7 @@ const REQUIRED_FRONTEND_PARITY_SNIPPETS = [
|
|
|
36
36
|
'UX Narrative and Conversion Clarity',
|
|
37
37
|
'Release Evidence',
|
|
38
38
|
];
|
|
39
|
+
const BENCHMARK_GATE_SCRIPT_PATH = 'scripts/benchmark-gate.mjs';
|
|
39
40
|
|
|
40
41
|
function readText(relativeFilePath) {
|
|
41
42
|
const absolutePath = resolve(REPOSITORY_ROOT, relativeFilePath);
|
|
@@ -54,6 +55,46 @@ function pushResult(results, isPassed, checkName, details) {
|
|
|
54
55
|
});
|
|
55
56
|
}
|
|
56
57
|
|
|
58
|
+
function parseMachineReadableReport(rawOutput) {
|
|
59
|
+
if (typeof rawOutput !== 'string' || rawOutput.trim().length === 0) {
|
|
60
|
+
return null;
|
|
61
|
+
}
|
|
62
|
+
|
|
63
|
+
try {
|
|
64
|
+
return JSON.parse(rawOutput);
|
|
65
|
+
} catch {
|
|
66
|
+
return null;
|
|
67
|
+
}
|
|
68
|
+
}
|
|
69
|
+
|
|
70
|
+
function runMachineReadableScript(scriptRelativePath) {
|
|
71
|
+
try {
|
|
72
|
+
const rawOutput = execFileSync('node', [scriptRelativePath], {
|
|
73
|
+
cwd: REPOSITORY_ROOT,
|
|
74
|
+
encoding: 'utf8',
|
|
75
|
+
maxBuffer: 1024 * 1024,
|
|
76
|
+
});
|
|
77
|
+
|
|
78
|
+
return {
|
|
79
|
+
report: parseMachineReadableReport(rawOutput),
|
|
80
|
+
executionErrorMessage: null,
|
|
81
|
+
};
|
|
82
|
+
} catch (scriptExecutionError) {
|
|
83
|
+
const rawOutput = scriptExecutionError && typeof scriptExecutionError === 'object' && 'stdout' in scriptExecutionError
|
|
84
|
+
? String(scriptExecutionError.stdout ?? '')
|
|
85
|
+
: '';
|
|
86
|
+
const parsedReport = parseMachineReadableReport(rawOutput);
|
|
87
|
+
const executionErrorMessage = scriptExecutionError instanceof Error
|
|
88
|
+
? scriptExecutionError.message
|
|
89
|
+
: 'Unknown execution error';
|
|
90
|
+
|
|
91
|
+
return {
|
|
92
|
+
report: parsedReport,
|
|
93
|
+
executionErrorMessage,
|
|
94
|
+
};
|
|
95
|
+
}
|
|
96
|
+
}
|
|
97
|
+
|
|
57
98
|
function validateCompatibilityManifestShape(parsedManifest, skillDomainName) {
|
|
58
99
|
const validationErrors = [];
|
|
59
100
|
|
|
@@ -82,6 +123,7 @@ function validateCompatibilityManifestShape(parsedManifest, skillDomainName) {
|
|
|
82
123
|
|
|
83
124
|
function runReleaseGate() {
|
|
84
125
|
const results = [];
|
|
126
|
+
const diagnostics = {};
|
|
85
127
|
const packageJsonPath = 'package.json';
|
|
86
128
|
const changelogPath = 'CHANGELOG.md';
|
|
87
129
|
const roadmapPath = 'docs/roadmap.md';
|
|
@@ -245,12 +287,48 @@ function runReleaseGate() {
|
|
|
245
287
|
pushResult(results, false, 'frontend-usability-audit', `Failed to execute frontend usability audit: ${frontendAuditErrorMessage}`);
|
|
246
288
|
}
|
|
247
289
|
|
|
290
|
+
const benchmarkGateExecution = runMachineReadableScript(BENCHMARK_GATE_SCRIPT_PATH);
|
|
291
|
+
if (!benchmarkGateExecution.report) {
|
|
292
|
+
const failureDetails = benchmarkGateExecution.executionErrorMessage
|
|
293
|
+
? `Benchmark gate execution failed before producing a machine-readable report: ${benchmarkGateExecution.executionErrorMessage}`
|
|
294
|
+
: 'Benchmark gate did not produce machine-readable JSON output';
|
|
295
|
+
pushResult(results, false, 'benchmark-threshold-gate', failureDetails);
|
|
296
|
+
} else {
|
|
297
|
+
diagnostics.benchmarkGate = benchmarkGateExecution.report;
|
|
298
|
+
pushResult(
|
|
299
|
+
results,
|
|
300
|
+
true,
|
|
301
|
+
'benchmark-threshold-gate',
|
|
302
|
+
`Benchmark threshold gate executed (passed=${benchmarkGateExecution.report.passed}, failures=${benchmarkGateExecution.report.failureCount})`
|
|
303
|
+
);
|
|
304
|
+
|
|
305
|
+
if (benchmarkGateExecution.report.passed === true) {
|
|
306
|
+
pushResult(results, true, 'benchmark-regression-block', 'Benchmark thresholds are healthy; release remains eligible');
|
|
307
|
+
} else {
|
|
308
|
+
const failedBenchmarkChecks = Array.isArray(benchmarkGateExecution.report.results)
|
|
309
|
+
? benchmarkGateExecution.report.results
|
|
310
|
+
.filter((benchmarkCheckResult) => !benchmarkCheckResult.passed)
|
|
311
|
+
.map((benchmarkCheckResult) => `${benchmarkCheckResult.checkName}: ${benchmarkCheckResult.details}`)
|
|
312
|
+
: [];
|
|
313
|
+
const failureSummary = failedBenchmarkChecks.length > 0
|
|
314
|
+
? failedBenchmarkChecks.join('; ')
|
|
315
|
+
: 'Benchmark gate failed but did not report individual failed checks';
|
|
316
|
+
pushResult(
|
|
317
|
+
results,
|
|
318
|
+
false,
|
|
319
|
+
'benchmark-regression-block',
|
|
320
|
+
`Benchmark threshold regression detected. ${failureSummary}`
|
|
321
|
+
);
|
|
322
|
+
}
|
|
323
|
+
}
|
|
324
|
+
|
|
248
325
|
const failureCount = results.filter((checkResult) => !checkResult.passed).length;
|
|
249
326
|
const releaseGateReport = {
|
|
250
327
|
generatedAt: new Date().toISOString(),
|
|
251
328
|
gateName: 'release-gate',
|
|
252
329
|
passed: failureCount === 0,
|
|
253
330
|
failureCount,
|
|
331
|
+
diagnostics,
|
|
254
332
|
results,
|
|
255
333
|
};
|
|
256
334
|
|