@ryuenn3123/agentic-senior-core 2.0.4 → 2.0.5

package/mcp.json

@@ -1,92 +1,92 @@
-{
-  "$schema": "https://modelcontextprotocol.io/schemas/mcp.json",
-  "version": "1.0",
-  "name": "agentic-senior-core",
-  "description": "MCP configuration for governance-aware diagnostics and self-healing workflows with full knowledge injection.",
-  "knowledgeLayers": {
-    "enabled": true,
-    "description": "8-layer unified knowledge injection for AI agents",
-    "layers": {
-      "rules": {
-        "path": ".agent-context/rules",
-        "count": 14,
-        "autoLoad": true
-      },
-      "stacks": {
-        "path": ".agent-context/stacks",
-        "count": 10,
-        "autoLoad": true
-      },
-      "blueprints": {
-        "path": ".agent-context/blueprints",
-        "count": 14,
-        "autoLoad": true
-      },
-      "skills": {
-        "path": ".agent-context/skills",
-        "count": 6,
-        "autoLoad": true,
-        "packs": ["backend", "frontend", "cli", "distribution", "fullstack", "review-quality"]
-      },
-      "prompts": {
-        "path": ".agent-context/prompts",
-        "count": 3,
-        "autoLoad": true,
-        "templates": ["init-project", "refactor", "review-code"]
-      },
-      "profiles": {
-        "path": ".agent-context/profiles",
-        "count": 3,
-        "autoLoad": true,
-        "governance": ["platform", "regulated", "startup"]
-      },
-      "state": {
-        "path": ".agent-context/state",
-        "count": 6,
-        "autoLoad": true
-      },
-      "policies": {
-        "path": ".agent-context/policies",
-        "count": 1,
-        "autoLoad": true
-      }
-    }
-  },
-  "servers": {
-    "lint": {
-      "command": "node",
-      "args": ["./scripts/validate.mjs"],
-      "transport": "stdio"
-    },
-    "test": {
-      "command": "node",
-      "args": ["--test", "./tests/cli-smoke.test.mjs", "./tests/llm-judge.test.mjs"],
-      "transport": "stdio"
-    }
-  },
-  "workflows": {
-    "self-heal-on-failure": {
-      "trigger": ["ci.failure", "lint.failure"],
-      "steps": [
-        "collect_logs",
-        "map_violation_to_rule",
-        "propose_patch",
-        "run_checklist_review"
-      ]
-    },
-    "full-knowledge-injection": {
-      "trigger": ["workspace.initialize", "agent.start"],
-      "steps": [
-        "load_all_knowledge_layers",
-        "inject_rules",
-        "inject_stacks",
-        "inject_blueprints",
-        "inject_skills",
-        "inject_prompts",
-        "inject_profiles",
-        "inject_state",
-        "inject_policies"
-      ]
-    }
-  }
-}
+{
+  "$schema": "https://modelcontextprotocol.io/schemas/mcp.json",
+  "version": "1.0",
+  "name": "agentic-senior-core",
+  "description": "MCP configuration for governance-aware diagnostics and self-healing workflows with full knowledge injection.",
+  "knowledgeLayers": {
+    "enabled": true,
+    "description": "8-layer unified knowledge injection for AI agents",
+    "layers": {
+      "rules": {
+        "path": ".agent-context/rules",
+        "count": 14,
+        "autoLoad": true
+      },
+      "stacks": {
+        "path": ".agent-context/stacks",
+        "count": 10,
+        "autoLoad": true
+      },
+      "blueprints": {
+        "path": ".agent-context/blueprints",
+        "count": 14,
+        "autoLoad": true
+      },
+      "skills": {
+        "path": ".agent-context/skills",
+        "count": 6,
+        "autoLoad": true,
+        "packs": ["backend", "frontend", "cli", "distribution", "fullstack", "review-quality"]
+      },
+      "prompts": {
+        "path": ".agent-context/prompts",
+        "count": 3,
+        "autoLoad": true,
+        "templates": ["init-project", "refactor", "review-code"]
+      },
+      "profiles": {
+        "path": ".agent-context/profiles",
+        "count": 3,
+        "autoLoad": true,
+        "governance": ["platform", "regulated", "startup"]
+      },
+      "state": {
+        "path": ".agent-context/state",
+        "count": 6,
+        "autoLoad": true
+      },
+      "policies": {
+        "path": ".agent-context/policies",
+        "count": 1,
+        "autoLoad": true
+      }
+    }
+  },
+  "servers": {
+    "lint": {
+      "command": "node",
+      "args": ["./scripts/validate.mjs"],
+      "transport": "stdio"
+    },
+    "test": {
+      "command": "node",
+      "args": ["--test", "./tests/cli-smoke.test.mjs", "./tests/llm-judge.test.mjs"],
+      "transport": "stdio"
+    }
+  },
+  "workflows": {
+    "self-heal-on-failure": {
+      "trigger": ["ci.failure", "lint.failure"],
+      "steps": [
+        "collect_logs",
+        "map_violation_to_rule",
+        "propose_patch",
+        "run_checklist_review"
+      ]
+    },
+    "full-knowledge-injection": {
+      "trigger": ["workspace.initialize", "agent.start"],
+      "steps": [
+        "load_all_knowledge_layers",
+        "inject_rules",
+        "inject_stacks",
+        "inject_blueprints",
+        "inject_skills",
+        "inject_prompts",
+        "inject_profiles",
+        "inject_state",
+        "inject_policies"
+      ]
+    }
+  }
+}

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@ryuenn3123/agentic-senior-core",
-  "version": "2.0.4",
+  "version": "2.0.5",
   "type": "module",
   "description": "Force your AI Agent to code like a Staff Engineer, not a Junior.",
   "bin": {
@@ -50,6 +50,7 @@
     "benchmark:token": "node ./scripts/token-optimization-benchmark.mjs",
     "benchmark:gate": "node ./scripts/benchmark-gate.mjs",
     "benchmark:intelligence": "node ./scripts/benchmark-intelligence.mjs",
+    "report:quality-trend": "node ./scripts/quality-trend-report.mjs",
     "validate": "node ./scripts/validate.mjs",
     "test": "node --test ./tests/cli-smoke.test.mjs ./tests/llm-judge.test.mjs ./tests/enterprise-ops.test.mjs ./tests/skill-tier-gate.test.mjs"
   }

package/scripts/benchmark-gate.mjs

@@ -1,121 +1,121 @@
-#!/usr/bin/env node
-
-/**
- * benchmark-gate.mjs
- *
- * Anti-regression gate for benchmark quality signals.
- * Fails when benchmark metrics drop below configured thresholds.
- */
-
-import { existsSync, readFileSync } from 'node:fs';
-import { dirname, join, resolve } from 'node:path';
-import { fileURLToPath } from 'node:url';
-import { execFileSync } from 'node:child_process';
-
-const SCRIPT_FILE_PATH = fileURLToPath(import.meta.url);
-const SCRIPT_DIR = dirname(SCRIPT_FILE_PATH);
-const REPOSITORY_ROOT = resolve(SCRIPT_DIR, '..');
-const BENCHMARK_THRESHOLD_PATH = join(REPOSITORY_ROOT, '.agent-context', 'state', 'benchmark-thresholds.json');
-const DETECTION_BENCHMARK_PATH = join(REPOSITORY_ROOT, 'scripts', 'detection-benchmark.mjs');
-
-function readThresholdConfiguration() {
-  if (!existsSync(BENCHMARK_THRESHOLD_PATH)) {
-    return {
-      minimumTop1Accuracy: 0.9,
-      maximumManualCorrectionRate: 0.12,
-      maximumTop1AccuracyDrop: 0.02,
-      maximumManualCorrectionIncrease: 0.03,
-      previousReleaseBaseline: {
-        top1Accuracy: 0.9167,
-        manualCorrectionRate: 0.0833,
-      },
-    };
-  }
-
-  return JSON.parse(readFileSync(BENCHMARK_THRESHOLD_PATH, 'utf8'));
-}
-
-function runDetectionBenchmark() {
-  const benchmarkRawOutput = execFileSync('node', [DETECTION_BENCHMARK_PATH], {
-    cwd: REPOSITORY_ROOT,
-    encoding: 'utf8',
-  });
-
-  return JSON.parse(benchmarkRawOutput);
-}
-
-function buildCheckResult(checkName, passed, details) {
-  return {
-    checkName,
-    passed,
-    details,
-  };
-}
-
-function runBenchmarkGate() {
-  const thresholdConfiguration = readThresholdConfiguration();
-  const benchmarkResult = runDetectionBenchmark();
-  const benchmarkChecks = [];
-
-  const top1AccuracyPassed = benchmarkResult.top1Accuracy >= thresholdConfiguration.minimumTop1Accuracy;
-  benchmarkChecks.push(
-    buildCheckResult(
-      'minimum-top1-accuracy',
-      top1AccuracyPassed,
-      `top1Accuracy=${benchmarkResult.top1Accuracy} minimum=${thresholdConfiguration.minimumTop1Accuracy}`,
-    ),
-  );
-
-  const manualCorrectionPassed = benchmarkResult.manualCorrectionRate <= thresholdConfiguration.maximumManualCorrectionRate;
-  benchmarkChecks.push(
-    buildCheckResult(
-      'maximum-manual-correction-rate',
-      manualCorrectionPassed,
-      `manualCorrectionRate=${benchmarkResult.manualCorrectionRate} maximum=${thresholdConfiguration.maximumManualCorrectionRate}`,
-    ),
-  );
-
-  const previousReleaseBaseline = thresholdConfiguration.previousReleaseBaseline;
-  if (previousReleaseBaseline && typeof previousReleaseBaseline === 'object') {
-    const top1AccuracyDrop = Number((previousReleaseBaseline.top1Accuracy - benchmarkResult.top1Accuracy).toFixed(4));
-    const manualCorrectionIncrease = Number((benchmarkResult.manualCorrectionRate - previousReleaseBaseline.manualCorrectionRate).toFixed(4));
-
-    const top1AccuracyDropPassed = top1AccuracyDrop <= thresholdConfiguration.maximumTop1AccuracyDrop;
-    benchmarkChecks.push(
-      buildCheckResult(
-        'maximum-top1-accuracy-drop',
-        top1AccuracyDropPassed,
-        `drop=${top1AccuracyDrop} maximum=${thresholdConfiguration.maximumTop1AccuracyDrop}`,
-      ),
-    );
-
-    const manualCorrectionIncreasePassed = manualCorrectionIncrease <= thresholdConfiguration.maximumManualCorrectionIncrease;
-    benchmarkChecks.push(
-      buildCheckResult(
-        'maximum-manual-correction-increase',
-        manualCorrectionIncreasePassed,
-        `increase=${manualCorrectionIncrease} maximum=${thresholdConfiguration.maximumManualCorrectionIncrease}`,
-      ),
-    );
-  }
-
-  const failedCheckCount = benchmarkChecks.filter((benchmarkCheck) => !benchmarkCheck.passed).length;
-  const benchmarkGateReport = {
-    generatedAt: new Date().toISOString(),
-    gateName: 'benchmark-gate',
-    passed: failedCheckCount === 0,
-    failureCount: failedCheckCount,
-    benchmarkResult: {
-      fixtureCount: benchmarkResult.fixtureCount,
-      top1Accuracy: benchmarkResult.top1Accuracy,
-      manualCorrectionRate: benchmarkResult.manualCorrectionRate,
-    },
-    thresholds: thresholdConfiguration,
-    results: benchmarkChecks,
-  };
-
-  console.log(JSON.stringify(benchmarkGateReport, null, 2));
-  process.exit(benchmarkGateReport.passed ? 0 : 1);
-}
-
-runBenchmarkGate();
+#!/usr/bin/env node
+
+/**
+ * benchmark-gate.mjs
+ *
+ * Anti-regression gate for benchmark quality signals.
+ * Fails when benchmark metrics drop below configured thresholds.
+ */
+
+import { existsSync, readFileSync } from 'node:fs';
+import { dirname, join, resolve } from 'node:path';
+import { fileURLToPath } from 'node:url';
+import { execFileSync } from 'node:child_process';
+
+const SCRIPT_FILE_PATH = fileURLToPath(import.meta.url);
+const SCRIPT_DIR = dirname(SCRIPT_FILE_PATH);
+const REPOSITORY_ROOT = resolve(SCRIPT_DIR, '..');
+const BENCHMARK_THRESHOLD_PATH = join(REPOSITORY_ROOT, '.agent-context', 'state', 'benchmark-thresholds.json');
+const DETECTION_BENCHMARK_PATH = join(REPOSITORY_ROOT, 'scripts', 'detection-benchmark.mjs');
+
+function readThresholdConfiguration() {
+  if (!existsSync(BENCHMARK_THRESHOLD_PATH)) {
+    return {
+      minimumTop1Accuracy: 0.9,
+      maximumManualCorrectionRate: 0.12,
+      maximumTop1AccuracyDrop: 0.02,
+      maximumManualCorrectionIncrease: 0.03,
+      previousReleaseBaseline: {
+        top1Accuracy: 0.9167,
+        manualCorrectionRate: 0.0833,
+      },
+    };
+  }
+
+  return JSON.parse(readFileSync(BENCHMARK_THRESHOLD_PATH, 'utf8'));
+}
+
+function runDetectionBenchmark() {
+  const benchmarkRawOutput = execFileSync('node', [DETECTION_BENCHMARK_PATH], {
+    cwd: REPOSITORY_ROOT,
+    encoding: 'utf8',
+  });
+
+  return JSON.parse(benchmarkRawOutput);
+}
+
+function buildCheckResult(checkName, passed, details) {
+  return {
+    checkName,
+    passed,
+    details,
+  };
+}
+
+function runBenchmarkGate() {
+  const thresholdConfiguration = readThresholdConfiguration();
+  const benchmarkResult = runDetectionBenchmark();
+  const benchmarkChecks = [];
+
+  const top1AccuracyPassed = benchmarkResult.top1Accuracy >= thresholdConfiguration.minimumTop1Accuracy;
+  benchmarkChecks.push(
+    buildCheckResult(
+      'minimum-top1-accuracy',
+      top1AccuracyPassed,
+      `top1Accuracy=${benchmarkResult.top1Accuracy} minimum=${thresholdConfiguration.minimumTop1Accuracy}`,
+    ),
+  );
+
+  const manualCorrectionPassed = benchmarkResult.manualCorrectionRate <= thresholdConfiguration.maximumManualCorrectionRate;
+  benchmarkChecks.push(
+    buildCheckResult(
+      'maximum-manual-correction-rate',
+      manualCorrectionPassed,
+      `manualCorrectionRate=${benchmarkResult.manualCorrectionRate} maximum=${thresholdConfiguration.maximumManualCorrectionRate}`,
+    ),
+  );
+
+  const previousReleaseBaseline = thresholdConfiguration.previousReleaseBaseline;
+  if (previousReleaseBaseline && typeof previousReleaseBaseline === 'object') {
+    const top1AccuracyDrop = Number((previousReleaseBaseline.top1Accuracy - benchmarkResult.top1Accuracy).toFixed(4));
+    const manualCorrectionIncrease = Number((benchmarkResult.manualCorrectionRate - previousReleaseBaseline.manualCorrectionRate).toFixed(4));
+
+    const top1AccuracyDropPassed = top1AccuracyDrop <= thresholdConfiguration.maximumTop1AccuracyDrop;
+    benchmarkChecks.push(
+      buildCheckResult(
+        'maximum-top1-accuracy-drop',
+        top1AccuracyDropPassed,
+        `drop=${top1AccuracyDrop} maximum=${thresholdConfiguration.maximumTop1AccuracyDrop}`,
+      ),
+    );
+
+    const manualCorrectionIncreasePassed = manualCorrectionIncrease <= thresholdConfiguration.maximumManualCorrectionIncrease;
+    benchmarkChecks.push(
+      buildCheckResult(
+        'maximum-manual-correction-increase',
+        manualCorrectionIncreasePassed,
+        `increase=${manualCorrectionIncrease} maximum=${thresholdConfiguration.maximumManualCorrectionIncrease}`,
+      ),
+    );
+  }
+
+  const failedCheckCount = benchmarkChecks.filter((benchmarkCheck) => !benchmarkCheck.passed).length;
+  const benchmarkGateReport = {
+    generatedAt: new Date().toISOString(),
+    gateName: 'benchmark-gate',
+    passed: failedCheckCount === 0,
+    failureCount: failedCheckCount,
+    benchmarkResult: {
+      fixtureCount: benchmarkResult.fixtureCount,
+      top1Accuracy: benchmarkResult.top1Accuracy,
+      manualCorrectionRate: benchmarkResult.manualCorrectionRate,
+    },
+    thresholds: thresholdConfiguration,
+    results: benchmarkChecks,
+  };
+
+  console.log(JSON.stringify(benchmarkGateReport, null, 2));
+  process.exit(benchmarkGateReport.passed ? 0 : 1);
+}
+
+runBenchmarkGate();