@optave/codegraph 3.1.5 → 3.2.0

package/src/domain/analysis/module-map.js

@@ -1,5 +1,6 @@
 import path from 'node:path';
 import { openReadonlyOrFail, testFilterSQL } from '../../db/index.js';
+import { debug } from '../../infrastructure/logger.js';
 import { isTestFile } from '../../infrastructure/test-filter.js';
 import { findCycles } from '../graph/cycles.js';
 import { LANGUAGE_REGISTRY } from '../parser.js';
@@ -36,6 +37,241 @@ export const FALSE_POSITIVE_NAMES = new Set([
 ]);
 export const FALSE_POSITIVE_CALLER_THRESHOLD = 20;
 
+// ---------------------------------------------------------------------------
+// Section helpers
+// ---------------------------------------------------------------------------
+
+function buildTestFileIds(db) {
+  const allFileNodes = db.prepare("SELECT id, file FROM nodes WHERE kind = 'file'").all();
+  const testFileIds = new Set();
+  const testFiles = new Set();
+  for (const n of allFileNodes) {
+    if (isTestFile(n.file)) {
+      testFileIds.add(n.id);
+      testFiles.add(n.file);
+    }
+  }
+  const allNodes = db.prepare('SELECT id, file FROM nodes').all();
+  for (const n of allNodes) {
+    if (testFiles.has(n.file)) testFileIds.add(n.id);
+  }
+  return testFileIds;
+}
+
+function countNodesByKind(db, testFileIds) {
+  let nodeRows;
+  if (testFileIds) {
+    const allNodes = db.prepare('SELECT id, kind, file FROM nodes').all();
+    const filtered = allNodes.filter((n) => !testFileIds.has(n.id));
+    const counts = {};
+    for (const n of filtered) counts[n.kind] = (counts[n.kind] || 0) + 1;
+    nodeRows = Object.entries(counts).map(([kind, c]) => ({ kind, c }));
+  } else {
+    nodeRows = db.prepare('SELECT kind, COUNT(*) as c FROM nodes GROUP BY kind').all();
+  }
+  const byKind = {};
+  let total = 0;
+  for (const r of nodeRows) {
+    byKind[r.kind] = r.c;
+    total += r.c;
+  }
+  return { total, byKind };
+}
+
+function countEdgesByKind(db, testFileIds) {
+  let edgeRows;
+  if (testFileIds) {
+    const allEdges = db.prepare('SELECT source_id, target_id, kind FROM edges').all();
+    const filtered = allEdges.filter(
+      (e) => !testFileIds.has(e.source_id) && !testFileIds.has(e.target_id),
+    );
+    const counts = {};
+    for (const e of filtered) counts[e.kind] = (counts[e.kind] || 0) + 1;
+    edgeRows = Object.entries(counts).map(([kind, c]) => ({ kind, c }));
+  } else {
+    edgeRows = db.prepare('SELECT kind, COUNT(*) as c FROM edges GROUP BY kind').all();
+  }
+  const byKind = {};
+  let total = 0;
+  for (const r of edgeRows) {
+    byKind[r.kind] = r.c;
+    total += r.c;
+  }
+  return { total, byKind };
+}
+
+function countFilesByLanguage(db, noTests) {
+  const extToLang = new Map();
+  for (const entry of LANGUAGE_REGISTRY) {
+    for (const ext of entry.extensions) {
+      extToLang.set(ext, entry.id);
+    }
+  }
+  let fileNodes = db.prepare("SELECT file FROM nodes WHERE kind = 'file'").all();
+  if (noTests) fileNodes = fileNodes.filter((n) => !isTestFile(n.file));
+  const byLanguage = {};
+  for (const row of fileNodes) {
+    const ext = path.extname(row.file).toLowerCase();
+    const lang = extToLang.get(ext) || 'other';
+    byLanguage[lang] = (byLanguage[lang] || 0) + 1;
+  }
+  return { total: fileNodes.length, languages: Object.keys(byLanguage).length, byLanguage };
+}
+
+function findHotspots(db, noTests, limit) {
+  const testFilter = testFilterSQL('n.file', noTests);
+  const hotspotRows = db
+    .prepare(`
+      SELECT n.file,
+        (SELECT COUNT(*) FROM edges WHERE target_id = n.id) as fan_in,
+        (SELECT COUNT(*) FROM edges WHERE source_id = n.id) as fan_out
+      FROM nodes n
+      WHERE n.kind = 'file' ${testFilter}
+      ORDER BY (SELECT COUNT(*) FROM edges WHERE target_id = n.id)
+             + (SELECT COUNT(*) FROM edges WHERE source_id = n.id) DESC
+    `)
+    .all();
+  const filtered = noTests ? hotspotRows.filter((r) => !isTestFile(r.file)) : hotspotRows;
+  return filtered.slice(0, limit).map((r) => ({
+    file: r.file,
+    fanIn: r.fan_in,
+    fanOut: r.fan_out,
+  }));
+}
+
+function getEmbeddingsInfo(db) {
+  try {
+    const count = db.prepare('SELECT COUNT(*) as c FROM embeddings').get();
+    if (count && count.c > 0) {
+      const meta = {};
+      const metaRows = db.prepare('SELECT key, value FROM embedding_meta').all();
+      for (const r of metaRows) meta[r.key] = r.value;
+      return {
+        count: count.c,
+        model: meta.model || null,
+        dim: meta.dim ? parseInt(meta.dim, 10) : null,
+        builtAt: meta.built_at || null,
+      };
+    }
+  } catch (e) {
+    debug(`embeddings lookup skipped: ${e.message}`);
+  }
+  return null;
+}
+
+function computeQualityMetrics(db, testFilter) {
+  const qualityTestFilter = testFilter.replace(/n\.file/g, 'file');
+
+  const totalCallable = db
+    .prepare(
+      `SELECT COUNT(*) as c FROM nodes WHERE kind IN ('function', 'method') ${qualityTestFilter}`,
+    )
+    .get().c;
+  const callableWithCallers = db
+    .prepare(`
+      SELECT COUNT(DISTINCT e.target_id) as c FROM edges e
+      JOIN nodes n ON e.target_id = n.id
+      WHERE e.kind = 'calls' AND n.kind IN ('function', 'method') ${testFilter}
+    `)
+    .get().c;
+  const callerCoverage = totalCallable > 0 ? callableWithCallers / totalCallable : 0;
+
+  const totalCallEdges = db.prepare("SELECT COUNT(*) as c FROM edges WHERE kind = 'calls'").get().c;
+  const highConfCallEdges = db
+    .prepare("SELECT COUNT(*) as c FROM edges WHERE kind = 'calls' AND confidence >= 0.7")
+    .get().c;
+  const callConfidence = totalCallEdges > 0 ? highConfCallEdges / totalCallEdges : 0;
+
+  const fpRows = db
+    .prepare(`
+      SELECT n.name, n.file, n.line, COUNT(e.source_id) as caller_count
+      FROM nodes n
+      LEFT JOIN edges e ON n.id = e.target_id AND e.kind = 'calls'
+      WHERE n.kind IN ('function', 'method')
+      GROUP BY n.id
+      HAVING caller_count > ?
+      ORDER BY caller_count DESC
+    `)
+    .all(FALSE_POSITIVE_CALLER_THRESHOLD);
+  const falsePositiveWarnings = fpRows
+    .filter((r) =>
+      FALSE_POSITIVE_NAMES.has(r.name.includes('.') ? r.name.split('.').pop() : r.name),
+    )
+    .map((r) => ({ name: r.name, file: r.file, line: r.line, callerCount: r.caller_count }));
+
+  let fpEdgeCount = 0;
+  for (const fp of falsePositiveWarnings) fpEdgeCount += fp.callerCount;
+  const falsePositiveRatio = totalCallEdges > 0 ? fpEdgeCount / totalCallEdges : 0;
+
+  const score = Math.round(
+    callerCoverage * 40 + callConfidence * 40 + (1 - falsePositiveRatio) * 20,
+  );
+
+  return {
+    score,
+    callerCoverage: {
+      ratio: callerCoverage,
+      covered: callableWithCallers,
+      total: totalCallable,
+    },
+    callConfidence: {
+      ratio: callConfidence,
+      highConf: highConfCallEdges,
+      total: totalCallEdges,
+    },
+    falsePositiveWarnings,
+  };
+}
+
+function countRoles(db, noTests) {
+  let roleRows;
+  if (noTests) {
+    const allRoleNodes = db.prepare('SELECT role, file FROM nodes WHERE role IS NOT NULL').all();
+    const filtered = allRoleNodes.filter((n) => !isTestFile(n.file));
+    const counts = {};
+    for (const n of filtered) counts[n.role] = (counts[n.role] || 0) + 1;
+    roleRows = Object.entries(counts).map(([role, c]) => ({ role, c }));
+  } else {
+    roleRows = db
+      .prepare('SELECT role, COUNT(*) as c FROM nodes WHERE role IS NOT NULL GROUP BY role')
+      .all();
+  }
+  const roles = {};
+  for (const r of roleRows) roles[r.role] = r.c;
+  return roles;
+}
+
+function getComplexitySummary(db, testFilter) {
+  try {
+    const cRows = db
+      .prepare(
+        `SELECT fc.cognitive, fc.cyclomatic, fc.max_nesting, fc.maintainability_index
+         FROM function_complexity fc JOIN nodes n ON fc.node_id = n.id
+         WHERE n.kind IN ('function','method') ${testFilter}`,
+      )
+      .all();
+    if (cRows.length > 0) {
+      const miValues = cRows.map((r) => r.maintainability_index || 0);
+      return {
+        analyzed: cRows.length,
+        avgCognitive: +(cRows.reduce((s, r) => s + r.cognitive, 0) / cRows.length).toFixed(1),
+        avgCyclomatic: +(cRows.reduce((s, r) => s + r.cyclomatic, 0) / cRows.length).toFixed(1),
+        maxCognitive: Math.max(...cRows.map((r) => r.cognitive)),
+        maxCyclomatic: Math.max(...cRows.map((r) => r.cyclomatic)),
+        avgMI: +(miValues.reduce((s, v) => s + v, 0) / miValues.length).toFixed(1),
+        minMI: +Math.min(...miValues).toFixed(1),
+      };
+    }
+  } catch (e) {
+    debug(`complexity summary skipped: ${e.message}`);
+  }
+  return null;
+}
+
+// ---------------------------------------------------------------------------
+// Public API
+// ---------------------------------------------------------------------------
+
 export function moduleMapData(customDbPath, limit = 20, opts = {}) {
   const db = openReadonlyOrFail(customDbPath);
   try {
@@ -78,237 +314,27 @@ export function statsData(customDbPath, opts = {}) {
   const db = openReadonlyOrFail(customDbPath);
   try {
     const noTests = opts.noTests || false;
+    const testFilter = testFilterSQL('n.file', noTests);
 
-    // Build set of test file IDs for filtering nodes and edges
-    let testFileIds = null;
-    if (noTests) {
-      const allFileNodes = db.prepare("SELECT id, file FROM nodes WHERE kind = 'file'").all();
-      testFileIds = new Set();
-      const testFiles = new Set();
-      for (const n of allFileNodes) {
-        if (isTestFile(n.file)) {
-          testFileIds.add(n.id);
-          testFiles.add(n.file);
-        }
-      }
-
-      // Also collect non-file node IDs that belong to test files
-      const allNodes = db.prepare('SELECT id, file FROM nodes').all();
-      for (const n of allNodes) {
-        if (testFiles.has(n.file)) testFileIds.add(n.id);
-      }
-    }
-
-    // Node breakdown by kind
-    let nodeRows;
-    if (noTests) {
-      const allNodes = db.prepare('SELECT id, kind, file FROM nodes').all();
-      const filtered = allNodes.filter((n) => !testFileIds.has(n.id));
-      const counts = {};
-      for (const n of filtered) counts[n.kind] = (counts[n.kind] || 0) + 1;
-      nodeRows = Object.entries(counts).map(([kind, c]) => ({ kind, c }));
-    } else {
-      nodeRows = db.prepare('SELECT kind, COUNT(*) as c FROM nodes GROUP BY kind').all();
-    }
-    const nodesByKind = {};
-    let totalNodes = 0;
-    for (const r of nodeRows) {
-      nodesByKind[r.kind] = r.c;
-      totalNodes += r.c;
-    }
-
-    // Edge breakdown by kind
-    let edgeRows;
-    if (noTests) {
-      const allEdges = db.prepare('SELECT source_id, target_id, kind FROM edges').all();
-      const filtered = allEdges.filter(
-        (e) => !testFileIds.has(e.source_id) && !testFileIds.has(e.target_id),
-      );
-      const counts = {};
-      for (const e of filtered) counts[e.kind] = (counts[e.kind] || 0) + 1;
-      edgeRows = Object.entries(counts).map(([kind, c]) => ({ kind, c }));
-    } else {
-      edgeRows = db.prepare('SELECT kind, COUNT(*) as c FROM edges GROUP BY kind').all();
-    }
-    const edgesByKind = {};
-    let totalEdges = 0;
-    for (const r of edgeRows) {
-      edgesByKind[r.kind] = r.c;
-      totalEdges += r.c;
-    }
+    const testFileIds = noTests ? buildTestFileIds(db) : null;
 
-    // File/language distribution — map extensions via LANGUAGE_REGISTRY
-    const extToLang = new Map();
-    for (const entry of LANGUAGE_REGISTRY) {
-      for (const ext of entry.extensions) {
-        extToLang.set(ext, entry.id);
-      }
-    }
-    let fileNodes = db.prepare("SELECT file FROM nodes WHERE kind = 'file'").all();
-    if (noTests) fileNodes = fileNodes.filter((n) => !isTestFile(n.file));
-    const byLanguage = {};
-    for (const row of fileNodes) {
-      const ext = path.extname(row.file).toLowerCase();
-      const lang = extToLang.get(ext) || 'other';
-      byLanguage[lang] = (byLanguage[lang] || 0) + 1;
-    }
-    const langCount = Object.keys(byLanguage).length;
+    const { total: totalNodes, byKind: nodesByKind } = countNodesByKind(db, testFileIds);
+    const { total: totalEdges, byKind: edgesByKind } = countEdgesByKind(db, testFileIds);
+    const files = countFilesByLanguage(db, noTests);
 
-    // Cycles
     const fileCycles = findCycles(db, { fileLevel: true, noTests });
     const fnCycles = findCycles(db, { fileLevel: false, noTests });
 
-    // Top 5 coupling hotspots (fan-in + fan-out, file nodes)
-    const testFilter = testFilterSQL('n.file', noTests);
-    const hotspotRows = db
-      .prepare(`
-      SELECT n.file,
-        (SELECT COUNT(*) FROM edges WHERE target_id = n.id) as fan_in,
-        (SELECT COUNT(*) FROM edges WHERE source_id = n.id) as fan_out
-      FROM nodes n
-      WHERE n.kind = 'file' ${testFilter}
-      ORDER BY (SELECT COUNT(*) FROM edges WHERE target_id = n.id)
-             + (SELECT COUNT(*) FROM edges WHERE source_id = n.id) DESC
-    `)
-      .all();
-    const filteredHotspots = noTests ? hotspotRows.filter((r) => !isTestFile(r.file)) : hotspotRows;
-    const hotspots = filteredHotspots.slice(0, 5).map((r) => ({
-      file: r.file,
-      fanIn: r.fan_in,
-      fanOut: r.fan_out,
-    }));
-
-    // Embeddings metadata
-    let embeddings = null;
-    try {
-      const count = db.prepare('SELECT COUNT(*) as c FROM embeddings').get();
-      if (count && count.c > 0) {
-        const meta = {};
-        const metaRows = db.prepare('SELECT key, value FROM embedding_meta').all();
-        for (const r of metaRows) meta[r.key] = r.value;
-        embeddings = {
-          count: count.c,
-          model: meta.model || null,
-          dim: meta.dim ? parseInt(meta.dim, 10) : null,
-          builtAt: meta.built_at || null,
-        };
-      }
-    } catch {
-      /* embeddings table may not exist */
-    }
-
-    // Graph quality metrics
-    const qualityTestFilter = testFilter.replace(/n\.file/g, 'file');
-    const totalCallable = db
-      .prepare(
-        `SELECT COUNT(*) as c FROM nodes WHERE kind IN ('function', 'method') ${qualityTestFilter}`,
-      )
-      .get().c;
-    const callableWithCallers = db
-      .prepare(`
-        SELECT COUNT(DISTINCT e.target_id) as c FROM edges e
-        JOIN nodes n ON e.target_id = n.id
-        WHERE e.kind = 'calls' AND n.kind IN ('function', 'method') ${testFilter}
-      `)
-      .get().c;
-    const callerCoverage = totalCallable > 0 ? callableWithCallers / totalCallable : 0;
-
-    const totalCallEdges = db
-      .prepare("SELECT COUNT(*) as c FROM edges WHERE kind = 'calls'")
-      .get().c;
-    const highConfCallEdges = db
-      .prepare("SELECT COUNT(*) as c FROM edges WHERE kind = 'calls' AND confidence >= 0.7")
-      .get().c;
-    const callConfidence = totalCallEdges > 0 ? highConfCallEdges / totalCallEdges : 0;
-
-    // False-positive warnings: generic names with > threshold callers
-    const fpRows = db
-      .prepare(`
-        SELECT n.name, n.file, n.line, COUNT(e.source_id) as caller_count
-        FROM nodes n
-        LEFT JOIN edges e ON n.id = e.target_id AND e.kind = 'calls'
-        WHERE n.kind IN ('function', 'method')
-        GROUP BY n.id
-        HAVING caller_count > ?
-        ORDER BY caller_count DESC
-      `)
-      .all(FALSE_POSITIVE_CALLER_THRESHOLD);
-    const falsePositiveWarnings = fpRows
-      .filter((r) =>
-        FALSE_POSITIVE_NAMES.has(r.name.includes('.') ? r.name.split('.').pop() : r.name),
-      )
-      .map((r) => ({ name: r.name, file: r.file, line: r.line, callerCount: r.caller_count }));
-
-    // Edges from suspicious nodes
-    let fpEdgeCount = 0;
-    for (const fp of falsePositiveWarnings) fpEdgeCount += fp.callerCount;
-    const falsePositiveRatio = totalCallEdges > 0 ? fpEdgeCount / totalCallEdges : 0;
-
-    const score = Math.round(
-      callerCoverage * 40 + callConfidence * 40 + (1 - falsePositiveRatio) * 20,
-    );
-
-    const quality = {
-      score,
-      callerCoverage: {
-        ratio: callerCoverage,
-        covered: callableWithCallers,
-        total: totalCallable,
-      },
-      callConfidence: {
-        ratio: callConfidence,
-        highConf: highConfCallEdges,
-        total: totalCallEdges,
-      },
-      falsePositiveWarnings,
-    };
-
-    // Role distribution
-    let roleRows;
-    if (noTests) {
-      const allRoleNodes = db.prepare('SELECT role, file FROM nodes WHERE role IS NOT NULL').all();
-      const filtered = allRoleNodes.filter((n) => !isTestFile(n.file));
-      const counts = {};
-      for (const n of filtered) counts[n.role] = (counts[n.role] || 0) + 1;
-      roleRows = Object.entries(counts).map(([role, c]) => ({ role, c }));
-    } else {
-      roleRows = db
-        .prepare('SELECT role, COUNT(*) as c FROM nodes WHERE role IS NOT NULL GROUP BY role')
-        .all();
-    }
-    const roles = {};
-    for (const r of roleRows) roles[r.role] = r.c;
-
-    // Complexity summary
-    let complexity = null;
-    try {
-      const cRows = db
-        .prepare(
-          `SELECT fc.cognitive, fc.cyclomatic, fc.max_nesting, fc.maintainability_index
-         FROM function_complexity fc JOIN nodes n ON fc.node_id = n.id
-         WHERE n.kind IN ('function','method') ${testFilter}`,
-        )
-        .all();
-      if (cRows.length > 0) {
-        const miValues = cRows.map((r) => r.maintainability_index || 0);
-        complexity = {
-          analyzed: cRows.length,
-          avgCognitive: +(cRows.reduce((s, r) => s + r.cognitive, 0) / cRows.length).toFixed(1),
-          avgCyclomatic: +(cRows.reduce((s, r) => s + r.cyclomatic, 0) / cRows.length).toFixed(1),
-          maxCognitive: Math.max(...cRows.map((r) => r.cognitive)),
-          maxCyclomatic: Math.max(...cRows.map((r) => r.cyclomatic)),
-          avgMI: +(miValues.reduce((s, v) => s + v, 0) / miValues.length).toFixed(1),
-          minMI: +Math.min(...miValues).toFixed(1),
-        };
-      }
-    } catch {
-      /* table may not exist in older DBs */
-    }
+    const hotspots = findHotspots(db, noTests, 5);
+    const embeddings = getEmbeddingsInfo(db);
+    const quality = computeQualityMetrics(db, testFilter);
+    const roles = countRoles(db, noTests);
+    const complexity = getComplexitySummary(db, testFilter);
 
     return {
       nodes: { total: totalNodes, byKind: nodesByKind },
       edges: { total: totalEdges, byKind: edgesByKind },
-      files: { total: fileNodes.length, languages: langCount, byLanguage },
+      files,
       cycles: { fileLevel: fileCycles.length, functionLevel: fnCycles.length },
       hotspots,
       embeddings,

package/src/domain/analysis/roles.js

@@ -1,4 +1,5 @@
 import { openReadonlyOrFail } from '../../db/index.js';
+import { buildFileConditionSQL } from '../../db/query-builder.js';
 import { isTestFile } from '../../infrastructure/test-filter.js';
 import { normalizeSymbol } from '../../shared/normalize.js';
 import { paginateResult } from '../../shared/paginate.js';
@@ -8,8 +9,6 @@ export function rolesData(customDbPath, opts = {}) {
   try {
     const noTests = opts.noTests || false;
     const filterRole = opts.role || null;
-    const filterFile = opts.file || null;
-
     const conditions = ['role IS NOT NULL'];
     const params = [];
 
@@ -17,9 +16,13 @@ export function rolesData(customDbPath, opts = {}) {
       conditions.push('role = ?');
       params.push(filterRole);
     }
-    if (filterFile) {
-      conditions.push('file LIKE ?');
-      params.push(`%${filterFile}%`);
+    {
+      const fc = buildFileConditionSQL(opts.file, 'file');
+      if (fc.sql) {
+        // Strip leading ' AND ' since we're using conditions array
+        conditions.push(fc.sql.replace(/^ AND /, ''));
+        params.push(...fc.params);
+      }
     }
 
     let rows = db

package/src/domain/analysis/symbol-lookup.js

@@ -14,12 +14,13 @@ import {
   openReadonlyOrFail,
   Repository,
 } from '../../db/index.js';
+import { debug } from '../../infrastructure/logger.js';
 import { isTestFile } from '../../infrastructure/test-filter.js';
-import { ALL_SYMBOL_KINDS } from '../../shared/kinds.js';
+import { EVERY_SYMBOL_KIND } from '../../shared/kinds.js';
 import { getFileHash, normalizeSymbol } from '../../shared/normalize.js';
 import { paginateResult } from '../../shared/paginate.js';
 
-const FUNCTION_KINDS = ['function', 'method', 'class'];
+const FUNCTION_KINDS = ['function', 'method', 'class', 'constant'];
 
 /**
  * Find nodes matching a name query, ranked by relevance.
@@ -109,12 +110,12 @@ export function queryNameData(name, customDbPath, opts = {}) {
 }
 
 function whereSymbolImpl(db, target, noTests) {
-  const placeholders = ALL_SYMBOL_KINDS.map(() => '?').join(', ');
+  const placeholders = EVERY_SYMBOL_KIND.map(() => '?').join(', ');
   let nodes = db
     .prepare(
       `SELECT * FROM nodes WHERE name LIKE ? AND kind IN (${placeholders}) ORDER BY file, line`,
     )
-    .all(`%${target}%`, ...ALL_SYMBOL_KINDS);
+    .all(`%${target}%`, ...EVERY_SYMBOL_KIND);
   if (noTests) nodes = nodes.filter((n) => !isTestFile(n.file));
 
   const hc = new Map();
@@ -206,7 +207,8 @@ export function childrenData(name, customDbPath, opts = {}) {
       let children;
       try {
         children = findNodeChildren(db, node.id);
-      } catch {
+      } catch (e) {
+        debug(`findNodeChildren failed for node ${node.id}: ${e.message}`);
         children = [];
       }
       if (noTests) children = children.filter((c) => !isTestFile(c.file || node.file));

package/src/domain/graph/builder/helpers.js

@@ -179,7 +179,7 @@ export function purgeFilesFromGraph(db, files, options = {}) {
 }
 
 /** Batch INSERT chunk size for multi-value INSERTs. */
-export const BATCH_CHUNK = 200;
+const BATCH_CHUNK = 200;
 
 /**
  * Batch-insert node rows via multi-value INSERT statements.