@aiready/pattern-detect 0.16.18 → 0.16.19

package/dist/analyzer-entry.mjs

@@ -0,0 +1,12 @@
+import {
+  analyzePatterns,
+  generateSummary,
+  getSmartDefaults
+} from "./chunk-WMOGJFME.mjs";
+import "./chunk-THF4RW63.mjs";
+import "./chunk-I6ETJC7L.mjs";
+export {
+  analyzePatterns,
+  generateSummary,
+  getSmartDefaults
+};

package/dist/chunk-I6ETJC7L.mjs

@@ -0,0 +1,179 @@
+// src/context-rules.ts
+import { Severity } from "@aiready/core";
+var CONTEXT_RULES = [
+  // Test Fixtures - Intentional duplication for test isolation
+  {
+    name: "test-fixtures",
+    detect: (file, code) => {
+      const isTestFile = file.includes(".test.") || file.includes(".spec.") || file.includes("__tests__") || file.includes("/test/") || file.includes("/tests/");
+      const hasTestFixtures = code.includes("beforeAll") || code.includes("afterAll") || code.includes("beforeEach") || code.includes("afterEach") || code.includes("setUp") || code.includes("tearDown");
+      return isTestFile && hasTestFixtures;
+    },
+    severity: Severity.Info,
+    reason: "Test fixture duplication is intentional for test isolation",
+    suggestion: "Consider if shared test setup would improve maintainability without coupling tests"
+  },
+  // Email/Document Templates - Often intentionally similar for consistency
+  {
+    name: "templates",
+    detect: (file, code) => {
+      const isTemplate = file.includes("/templates/") || file.includes("-template") || file.includes("/email-templates/") || file.includes("/emails/");
+      const hasTemplateContent = (code.includes("return") || code.includes("export")) && (code.includes("html") || code.includes("subject") || code.includes("body"));
+      return isTemplate && hasTemplateContent;
+    },
+    severity: Severity.Minor,
+    reason: "Template duplication may be intentional for maintainability and branding consistency",
+    suggestion: "Extract shared structure only if templates become hard to maintain"
+  },
+  // E2E/Integration Test Page Objects - Test independence
+  {
+    name: "e2e-page-objects",
+    detect: (file, code) => {
+      const isE2ETest = file.includes("e2e/") || file.includes("/e2e/") || file.includes(".e2e.") || file.includes("/playwright/") || file.includes("playwright/") || file.includes("/cypress/") || file.includes("cypress/") || file.includes("/integration/") || file.includes("integration/");
+      const hasPageObjectPatterns = code.includes("page.") || code.includes("await page") || code.includes("locator") || code.includes("getBy") || code.includes("selector") || code.includes("click(") || code.includes("fill(");
+      return isE2ETest && hasPageObjectPatterns;
+    },
+    severity: Severity.Minor,
+    reason: "E2E test duplication ensures test independence and reduces coupling",
+    suggestion: "Consider page object pattern only if duplication causes maintenance issues"
+  },
+  // Configuration Files - Often necessarily similar by design
+  {
+    name: "config-files",
+    detect: (file) => {
+      return file.endsWith(".config.ts") || file.endsWith(".config.js") || file.includes("jest.config") || file.includes("vite.config") || file.includes("webpack.config") || file.includes("rollup.config") || file.includes("tsconfig");
+    },
+    severity: Severity.Minor,
+    reason: "Configuration files often have similar structure by design",
+    suggestion: "Consider shared config base only if configurations become hard to maintain"
+  },
+  // Type Definitions - Duplication for type safety and module independence
+  {
+    name: "type-definitions",
+    detect: (file, code) => {
+      const isTypeFile = file.endsWith(".d.ts") || file.includes("/types/");
+      const hasTypeDefinitions = code.includes("interface ") || code.includes("type ") || code.includes("enum ");
+      return isTypeFile && hasTypeDefinitions;
+    },
+    severity: Severity.Info,
+    reason: "Type duplication may be intentional for module independence and type safety",
+    suggestion: "Extract to shared types package only if causing maintenance burden"
+  },
+  // Migration Scripts - One-off scripts that are similar by nature
+  {
+    name: "migration-scripts",
+    detect: (file) => {
+      return file.includes("/migrations/") || file.includes("/migrate/") || file.includes(".migration.");
+    },
+    severity: Severity.Info,
+    reason: "Migration scripts are typically one-off and intentionally similar",
+    suggestion: "Duplication is acceptable for migration scripts"
+  },
+  // Mock Data - Test data intentionally duplicated
+  {
+    name: "mock-data",
+    detect: (file, code) => {
+      const isMockFile = file.includes("/mocks/") || file.includes("/__mocks__/") || file.includes("/fixtures/") || file.includes(".mock.") || file.includes(".fixture.");
+      const hasMockData = code.includes("mock") || code.includes("Mock") || code.includes("fixture") || code.includes("stub") || code.includes("export const");
+      return isMockFile && hasMockData;
+    },
+    severity: Severity.Info,
+    reason: "Mock data duplication is expected for comprehensive test coverage",
+    suggestion: "Consider shared factories only for complex mock generation"
+  },
+  // Tool Implementations - Structural Boilerplate
+  {
+    name: "tool-implementations",
+    detect: (file, code) => {
+      const isToolFile = file.includes("/tools/") || file.endsWith(".tool.ts") || code.includes("toolDefinitions");
+      const hasToolStructure = code.includes("execute") && (code.includes("try") || code.includes("catch"));
+      return isToolFile && hasToolStructure;
+    },
+    severity: Severity.Info,
+    reason: "Tool implementations share structural boilerplate but have distinct business logic",
+    suggestion: "Tool duplication is acceptable for boilerplate interface wrappers"
+  }
+];
+function calculateSeverity(file1, file2, code, similarity, linesOfCode) {
+  for (const rule of CONTEXT_RULES) {
+    if (rule.detect(file1, code) || rule.detect(file2, code)) {
+      return {
+        severity: rule.severity,
+        reason: rule.reason,
+        suggestion: rule.suggestion,
+        matchedRule: rule.name
+      };
+    }
+  }
+  if (similarity >= 0.95 && linesOfCode >= 30) {
+    return {
+      severity: Severity.Critical,
+      reason: "Large nearly-identical code blocks waste tokens and create maintenance burden",
+      suggestion: "Extract to shared utility module immediately"
+    };
+  } else if (similarity >= 0.95 && linesOfCode >= 15) {
+    return {
+      severity: Severity.Major,
+      reason: "Nearly identical code should be consolidated",
+      suggestion: "Move to shared utility file"
+    };
+  } else if (similarity >= 0.85) {
+    return {
+      severity: Severity.Major,
+      reason: "High similarity indicates significant duplication",
+      suggestion: "Extract common logic to shared function"
+    };
+  } else if (similarity >= 0.7) {
+    return {
+      severity: Severity.Minor,
+      reason: "Moderate similarity detected",
+      suggestion: "Consider extracting shared patterns if code evolves together"
+    };
+  } else {
+    return {
+      severity: Severity.Minor,
+      reason: "Minor similarity detected",
+      suggestion: "Monitor but refactoring may not be worthwhile"
+    };
+  }
+}
+function getSeverityLabel(severity) {
+  const labels = {
+    [Severity.Critical]: "\u{1F534} CRITICAL",
+    [Severity.Major]: "\u{1F7E1} MAJOR",
+    [Severity.Minor]: "\u{1F535} MINOR",
+    [Severity.Info]: "\u2139\uFE0F  INFO"
+  };
+  return labels[severity];
+}
+function filterBySeverity(duplicates, minSeverity) {
+  const severityOrder = [
+    Severity.Info,
+    Severity.Minor,
+    Severity.Major,
+    Severity.Critical
+  ];
+  const minIndex = severityOrder.indexOf(minSeverity);
+  if (minIndex === -1) return duplicates;
+  return duplicates.filter((dup) => {
+    const dupIndex = severityOrder.indexOf(dup.severity);
+    return dupIndex >= minIndex;
+  });
+}
+function getSeverityThreshold(severity) {
+  const thresholds = {
+    [Severity.Critical]: 0.95,
+    [Severity.Major]: 0.85,
+    [Severity.Minor]: 0.5,
+    [Severity.Info]: 0
+  };
+  return thresholds[severity] || 0;
+}
+
+export {
+  CONTEXT_RULES,
+  calculateSeverity,
+  getSeverityLabel,
+  filterBySeverity,
+  getSeverityThreshold
+};

package/dist/chunk-THF4RW63.mjs

@@ -0,0 +1,254 @@
+import {
+  calculateSeverity
+} from "./chunk-I6ETJC7L.mjs";
+
+// src/detector.ts
+import { estimateTokens } from "@aiready/core";
+function normalizeCode(code, isPython = false) {
+  let normalized = code;
+  if (isPython) {
+    normalized = normalized.replace(/#.*/g, "");
+  } else {
+    normalized = normalized.replace(/\/\/.*/g, "").replace(/\/\*[\s\S]*?\*\//g, "");
+  }
+  return normalized.replace(/['"`]/g, '"').replace(/\s+/g, " ").trim().toLowerCase();
+}
+function extractBlocks(file, content) {
+  const isPython = file.toLowerCase().endsWith(".py");
+  if (isPython) {
+    return extractBlocksPython(file, content);
+  }
+  const blocks = [];
+  const lines = content.split("\n");
+  const blockRegex = /^\s*(?:export\s+)?(?:async\s+)?(?:public\s+|private\s+|protected\s+|internal\s+|static\s+|readonly\s+|virtual\s+|abstract\s+|override\s+)*(function|class|interface|type|enum|record|struct|void|func|[a-zA-Z0-9_<>[]]+)\s+([a-zA-Z0-9_]+)(?:\s*\(|(?:\s+extends|\s+implements|\s+where)?\s*\{)|^\s*(?:export\s+)?const\s+([a-zA-Z0-9_]+)\s*=\s*[a-zA-Z0-9_.]+\.object\(|^\s*(app\.(?:get|post|put|delete|patch|use))\(/gm;
+  let match;
+  while ((match = blockRegex.exec(content)) !== null) {
+    const startLine = content.substring(0, match.index).split("\n").length;
+    let type;
+    let name;
+    if (match[1]) {
+      type = match[1];
+      name = match[2];
+    } else if (match[3]) {
+      type = "const";
+      name = match[3];
+    } else {
+      type = "handler";
+      name = match[4];
+    }
+    let endLine = -1;
+    let openBraces = 0;
+    let foundStart = false;
+    for (let i = match.index; i < content.length; i++) {
+      if (content[i] === "{") {
+        openBraces++;
+        foundStart = true;
+      } else if (content[i] === "}") {
+        openBraces--;
+      }
+      if (foundStart && openBraces === 0) {
+        endLine = content.substring(0, i + 1).split("\n").length;
+        break;
+      }
+    }
+    if (endLine === -1) {
+      const remaining = content.slice(match.index);
+      const nextLineMatch = remaining.indexOf("\n");
+      if (nextLineMatch !== -1) {
+        endLine = startLine;
+      } else {
+        endLine = lines.length;
+      }
+    }
+    endLine = Math.max(startLine, endLine);
+    const blockCode = lines.slice(startLine - 1, endLine).join("\n");
+    const tokens = estimateTokens(blockCode);
+    blocks.push({
+      file,
+      startLine,
+      endLine,
+      code: blockCode,
+      tokens,
+      patternType: inferPatternType(type, name)
+    });
+  }
+  return blocks;
+}
+function extractBlocksPython(file, content) {
+  const blocks = [];
+  const lines = content.split("\n");
+  const blockRegex = /^\s*(?:async\s+)?(def|class)\s+([a-zA-Z0-9_]+)/gm;
+  let match;
+  while ((match = blockRegex.exec(content)) !== null) {
+    const startLinePos = content.substring(0, match.index).split("\n").length;
+    const startLineIdx = startLinePos - 1;
+    const initialIndent = lines[startLineIdx].search(/\S/);
+    let endLineIdx = startLineIdx;
+    for (let i = startLineIdx + 1; i < lines.length; i++) {
+      const line = lines[i];
+      if (line.trim().length === 0) {
+        endLineIdx = i;
+        continue;
+      }
+      const currentIndent = line.search(/\S/);
+      if (currentIndent <= initialIndent) {
+        break;
+      }
+      endLineIdx = i;
+    }
+    while (endLineIdx > startLineIdx && lines[endLineIdx].trim().length === 0) {
+      endLineIdx--;
+    }
+    const blockCode = lines.slice(startLineIdx, endLineIdx + 1).join("\n");
+    const tokens = estimateTokens(blockCode);
+    blocks.push({
+      file,
+      startLine: startLinePos,
+      endLine: endLineIdx + 1,
+      code: blockCode,
+      tokens,
+      patternType: inferPatternType(match[1], match[2])
+    });
+  }
+  return blocks;
+}
+function inferPatternType(keyword, name) {
+  const n = name.toLowerCase();
+  if (keyword === "handler" || n.includes("handler") || n.includes("controller") || n.startsWith("app.")) {
+    return "api-handler";
+  }
+  if (n.includes("validate") || n.includes("schema")) return "validator";
+  if (n.includes("util") || n.includes("helper")) return "utility";
+  if (keyword === "class") return "class-method";
+  if (n.match(/^[A-Z]/)) return "component";
+  if (keyword === "function") return "function";
+  return "unknown";
+}
+function calculateSimilarity(a, b) {
+  if (a === b) return 1;
+  const tokensA = a.split(/[^a-zA-Z0-9]+/).filter((t) => t.length > 0);
+  const tokensB = b.split(/[^a-zA-Z0-9]+/).filter((t) => t.length > 0);
+  if (tokensA.length === 0 || tokensB.length === 0) return 0;
+  const setA = new Set(tokensA);
+  const setB = new Set(tokensB);
+  const intersection = new Set([...setA].filter((x) => setB.has(x)));
+  const union = /* @__PURE__ */ new Set([...setA, ...setB]);
+  return intersection.size / union.size;
+}
+function calculateConfidence(similarity, tokens, lines) {
+  let confidence = similarity;
+  if (lines > 20) confidence += 0.05;
+  if (tokens > 200) confidence += 0.05;
+  if (lines < 5) confidence -= 0.1;
+  return Math.max(0, Math.min(1, confidence));
+}
+async function detectDuplicatePatterns(fileContents, options) {
+  const {
+    minSimilarity,
+    minLines,
+    streamResults,
+    onProgress,
+    excludePatterns = [],
+    confidenceThreshold = 0,
+    ignoreWhitelist = []
+  } = options;
+  const allBlocks = [];
+  const excludeRegexes = excludePatterns.map((p) => new RegExp(p, "i"));
+  for (const { file, content } of fileContents) {
+    const blocks = extractBlocks(file, content);
+    for (const b of blocks) {
+      if (b.endLine - b.startLine + 1 < minLines) continue;
+      const isExcluded = excludeRegexes.some((regex) => regex.test(b.code));
+      if (isExcluded) continue;
+      allBlocks.push(b);
+    }
+  }
+  const duplicates = [];
+  const totalBlocks = allBlocks.length;
+  let comparisons = 0;
+  const totalComparisons = totalBlocks * (totalBlocks - 1) / 2;
+  if (onProgress) {
+    onProgress(
+      0,
+      totalComparisons,
+      `Starting duplicate detection on ${totalBlocks} blocks...`
+    );
+  }
+  for (let i = 0; i < allBlocks.length; i++) {
+    if (i % 50 === 0 && i > 0) {
+      await new Promise((resolve) => setImmediate(resolve));
+      if (onProgress) {
+        onProgress(
+          comparisons,
+          totalComparisons,
+          `Analyzing blocks (${i}/${totalBlocks})...`
+        );
+      }
+    }
+    const b1 = allBlocks[i];
+    const isPython1 = b1.file.toLowerCase().endsWith(".py");
+    const norm1 = normalizeCode(b1.code, isPython1);
+    for (let j = i + 1; j < allBlocks.length; j++) {
+      comparisons++;
+      const b2 = allBlocks[j];
+      if (b1.file === b2.file) continue;
+      const isWhitelisted = ignoreWhitelist.some((pattern) => {
+        return b1.file.includes(pattern) && b2.file.includes(pattern) || pattern === `${b1.file}::${b2.file}` || pattern === `${b2.file}::${b1.file}`;
+      });
+      if (isWhitelisted) continue;
+      const isPython2 = b2.file.toLowerCase().endsWith(".py");
+      const norm2 = normalizeCode(b2.code, isPython2);
+      const sim = calculateSimilarity(norm1, norm2);
+      if (sim >= minSimilarity) {
+        const confidence = calculateConfidence(
+          sim,
+          b1.tokens,
+          b1.endLine - b1.startLine + 1
+        );
+        if (confidence < confidenceThreshold) continue;
+        const { severity, reason, suggestion, matchedRule } = calculateSeverity(
+          b1.file,
+          b2.file,
+          b1.code,
+          sim,
+          b1.endLine - b1.startLine + 1
+        );
+        const dup = {
+          file1: b1.file,
+          line1: b1.startLine,
+          endLine1: b1.endLine,
+          file2: b2.file,
+          line2: b2.startLine,
+          endLine2: b2.endLine,
+          code1: b1.code,
+          code2: b2.code,
+          similarity: sim,
+          confidence,
+          patternType: b1.patternType,
+          tokenCost: b1.tokens + b2.tokens,
+          severity,
+          reason,
+          suggestion,
+          matchedRule
+        };
+        duplicates.push(dup);
+        if (streamResults)
+          console.log(
+            `[DUPLICATE] ${dup.file1}:${dup.line1} <-> ${dup.file2}:${dup.line2} (${Math.round(sim * 100)}%, conf: ${Math.round(confidence * 100)}%)`
+          );
+      }
+    }
+  }
+  if (onProgress) {
+    onProgress(
+      totalComparisons,
+      totalComparisons,
+      `Duplicate detection complete. Found ${duplicates.length} patterns.`
+    );
+  }
+  return duplicates.sort((a, b) => b.similarity - a.similarity);
+}
+
+export {
+  detectDuplicatePatterns
+};

package/dist/chunk-UB3CGOQ7.mjs

@@ -0,0 +1,64 @@
+import {
+  analyzePatterns
+} from "./chunk-WMOGJFME.mjs";
+import {
+  calculatePatternScore
+} from "./chunk-WBBO35SC.mjs";
+
+// src/index.ts
+import { ToolRegistry, Severity } from "@aiready/core";
+
+// src/provider.ts
+import {
+  ToolName,
+  SpokeOutputSchema,
+  GLOBAL_SCAN_OPTIONS
+} from "@aiready/core";
+var PatternDetectProvider = {
+  id: ToolName.PatternDetect,
+  alias: ["patterns", "duplicates", "duplication"],
+  async analyze(options) {
+    const results = await analyzePatterns(options);
+    return SpokeOutputSchema.parse({
+      results: results.results,
+      summary: {
+        totalFiles: results.files.length,
+        totalIssues: results.results.reduce(
+          (sum, r) => sum + r.issues.length,
+          0
+        ),
+        duplicates: results.duplicates,
+        // Keep the raw duplicates for score calculation
+        clusters: results.clusters,
+        config: Object.fromEntries(
+          Object.entries(results.config).filter(
+            ([key]) => !GLOBAL_SCAN_OPTIONS.includes(key) || key === "rootDir"
+          )
+        )
+      },
+      metadata: {
+        toolName: ToolName.PatternDetect,
+        version: "0.12.5",
+        timestamp: (/* @__PURE__ */ new Date()).toISOString()
+      }
+    });
+  },
+  score(output, options) {
+    const duplicates = output.summary.duplicates || [];
+    const totalFiles = output.summary.totalFiles || output.results.length;
+    return calculatePatternScore(
+      duplicates,
+      totalFiles,
+      options.costConfig
+    );
+  },
+  defaultWeight: 22
+};
+
+// src/index.ts
+ToolRegistry.register(PatternDetectProvider);
+
+export {
+  PatternDetectProvider,
+  Severity
+};

package/dist/chunk-WBBO35SC.mjs

@@ -0,0 +1,112 @@
+// src/scoring.ts
+import {
+  calculateMonthlyCost,
+  calculateProductivityImpact,
+  DEFAULT_COST_CONFIG,
+  ToolName
+} from "@aiready/core";
+function calculatePatternScore(duplicates, totalFilesAnalyzed, costConfig) {
+  const totalDuplicates = duplicates.length;
+  const totalTokenCost = duplicates.reduce((sum, d) => sum + d.tokenCost, 0);
+  const highImpactDuplicates = duplicates.filter(
+    (d) => d.tokenCost > 1e3 || d.similarity > 0.7
+  ).length;
+  if (totalFilesAnalyzed === 0) {
+    return {
+      toolName: ToolName.PatternDetect,
+      score: 100,
+      rawMetrics: {
+        totalDuplicates: 0,
+        totalTokenCost: 0,
+        highImpactDuplicates: 0,
+        totalFilesAnalyzed: 0
+      },
+      factors: [],
+      recommendations: []
+    };
+  }
+  const duplicatesPerFile = totalDuplicates / totalFilesAnalyzed * 100;
+  const tokenWastePerFile = totalTokenCost / totalFilesAnalyzed;
+  const duplicatesPenalty = Math.min(60, duplicatesPerFile * 0.6);
+  const tokenPenalty = Math.min(40, tokenWastePerFile / 125);
+  const highImpactPenalty = highImpactDuplicates > 0 ? Math.min(15, highImpactDuplicates * 2 - 5) : -5;
+  const score = 100 - duplicatesPenalty - tokenPenalty - highImpactPenalty;
+  const finalScore = Math.max(0, Math.min(100, Math.round(score)));
+  const factors = [
+    {
+      name: "Duplication Density",
+      impact: -Math.round(duplicatesPenalty),
+      description: `${duplicatesPerFile.toFixed(1)} duplicates per 100 files`
+    },
+    {
+      name: "Token Waste",
+      impact: -Math.round(tokenPenalty),
+      description: `${Math.round(tokenWastePerFile)} tokens wasted per file`
+    }
+  ];
+  if (highImpactDuplicates > 0) {
+    factors.push({
+      name: "High-Impact Patterns",
+      impact: -Math.round(highImpactPenalty),
+      description: `${highImpactDuplicates} high-impact duplicates (>1000 tokens or >70% similar)`
+    });
+  } else {
+    factors.push({
+      name: "No High-Impact Patterns",
+      impact: 5,
+      description: "No severe duplicates detected"
+    });
+  }
+  const recommendations = [];
+  if (highImpactDuplicates > 0) {
+    const estimatedImpact = Math.min(15, highImpactDuplicates * 3);
+    recommendations.push({
+      action: `Deduplicate ${highImpactDuplicates} high-impact pattern${highImpactDuplicates > 1 ? "s" : ""}`,
+      estimatedImpact,
+      priority: "high"
+    });
+  }
+  if (totalDuplicates > 10 && duplicatesPerFile > 20) {
+    const estimatedImpact = Math.min(10, Math.round(duplicatesPenalty * 0.3));
+    recommendations.push({
+      action: "Extract common patterns into shared utilities",
+      estimatedImpact,
+      priority: "medium"
+    });
+  }
+  if (tokenWastePerFile > 2e3) {
+    const estimatedImpact = Math.min(8, Math.round(tokenPenalty * 0.4));
+    recommendations.push({
+      action: "Consolidate duplicated logic to reduce AI context waste",
+      estimatedImpact,
+      priority: totalTokenCost > 1e4 ? "high" : "medium"
+    });
+  }
+  const cfg = { ...DEFAULT_COST_CONFIG, ...costConfig };
+  const estimatedMonthlyCost = calculateMonthlyCost(totalTokenCost, cfg);
+  const issues = duplicates.map((d) => ({
+    severity: d.severity === "critical" ? "critical" : d.severity === "major" ? "major" : "minor"
+  }));
+  const productivityImpact = calculateProductivityImpact(issues);
+  return {
+    toolName: "pattern-detect",
+    score: finalScore,
+    rawMetrics: {
+      totalDuplicates,
+      totalTokenCost,
+      highImpactDuplicates,
+      totalFilesAnalyzed,
+      duplicatesPerFile: Math.round(duplicatesPerFile * 10) / 10,
+      tokenWastePerFile: Math.round(tokenWastePerFile),
+      // Business value metrics
+      estimatedMonthlyCost,
+      estimatedDeveloperHours: productivityImpact.totalHours
+    },
+    factors,
+    recommendations
+  };
+}
+
+export {
+  calculatePatternScore
+};