refactor: deduplicate BFS impact traversal and centralize config loading (#463)

carlos-alm · web-flow · commit f0770f5379c1 · 2026-03-16T05:22:01.000-06:00
* refactor: deduplicate BFS impact traversal and centralize config loading

Extract shared bfsTransitiveCallers() into domain/analysis/impact.js,
replacing 4 near-identical BFS loops across audit, check, and impact
modules. The onVisit callback handles site-specific tracking (edges,
affected sets) without duplicating the core traversal.

Make feature functions (audit, check, manifesto, complexity, diff-impact)
accept opts.config to reuse the config already loaded at CLI entry,
falling back to loadConfig() for programmatic API callers.

Impact: 16 functions changed, 37 affected

* fix: filter minConfidence for Repository path and simplify alias

Impact: 7 functions changed, 3 affected

* test: add InMemoryRepository tests for dependency builder and document minConfidence trade-off

Impact: 1 functions changed, 11 affected

* docs: tighten bfsTransitiveCallers db param type to better-sqlite3 Database

* docs: document opts.config cwd vs db-root trade-off in checkData

Impact: 1 functions changed, 2 affected
diff --git a/src/cli/commands/audit.js b/src/cli/commands/audit.js
@@ -41,6 +41,7 @@ export const command = {
       kind: opts.kind,
       noTests: ctx.resolveNoTests(opts),
       json: opts.json,
+      config: ctx.config,
     });
   },
 };
diff --git a/src/cli/commands/check.js b/src/cli/commands/check.js
@@ -41,6 +41,7 @@ export const command = {
         limit: opts.limit ? parseInt(opts.limit, 10) : undefined,
         offset: opts.offset ? parseInt(opts.offset, 10) : undefined,
         ndjson: opts.ndjson,
+        config: ctx.config,
       });
       return;
     }
@@ -56,6 +57,7 @@ export const command = {
       depth: opts.depth ? parseInt(opts.depth, 10) : undefined,
       noTests: ctx.resolveNoTests(opts),
       json: opts.json,
+      config: ctx.config,
     });
 
     if (opts.rules) {
@@ -73,6 +75,7 @@ export const command = {
         limit: opts.limit ? parseInt(opts.limit, 10) : undefined,
         offset: opts.offset ? parseInt(opts.offset, 10) : undefined,
         ndjson: opts.ndjson,
+        config: ctx.config,
       });
     }
   },
diff --git a/src/cli/commands/complexity.js b/src/cli/commands/complexity.js
@@ -40,6 +40,7 @@ export const command = {
       noTests: ctx.resolveNoTests(opts),
       json: opts.json,
       ndjson: opts.ndjson,
+      config: ctx.config,
     });
   },
 };
diff --git a/src/cli/commands/diff-impact.js b/src/cli/commands/diff-impact.js
@@ -25,6 +25,7 @@ export const command = {
       limit: opts.limit ? parseInt(opts.limit, 10) : undefined,
       offset: opts.offset ? parseInt(opts.offset, 10) : undefined,
       ndjson: opts.ndjson,
+      config: ctx.config,
     });
   },
 };
diff --git a/src/db/repository/base.js b/src/db/repository/base.js
@@ -163,7 +163,7 @@ export class Repository {
     throw new Error('not implemented');
   }
 
-  /** @returns {{ source_id: number, target_id: number }[]} */
+  /** @returns {{ source_id: number, target_id: number, confidence: number|null }[]} */
   getCallEdges() {
     throw new Error('not implemented');
   }
diff --git a/src/db/repository/graph-read.js b/src/db/repository/graph-read.js
@@ -25,13 +25,13 @@ export function getCallableNodes(db) {
 /**
  * Get all 'calls' edges.
  * @param {object} db
- * @returns {{ source_id: number, target_id: number }[]}
+ * @returns {{ source_id: number, target_id: number, confidence: number|null }[]}
  */
 export function getCallEdges(db) {
   return cachedStmt(
     _getCallEdgesStmt,
     db,
-    "SELECT source_id, target_id FROM edges WHERE kind = 'calls'",
+    "SELECT source_id, target_id, confidence FROM edges WHERE kind = 'calls'",
   ).all();
 }
 
diff --git a/src/db/repository/in-memory-repository.js b/src/db/repository/in-memory-repository.js
@@ -489,7 +489,7 @@ export class InMemoryRepository extends Repository {
   getCallEdges() {
     return [...this.#edges.values()]
       .filter((e) => e.kind === 'calls')
-      .map((e) => ({ source_id: e.source_id, target_id: e.target_id }));
+      .map((e) => ({ source_id: e.source_id, target_id: e.target_id, confidence: e.confidence }));
   }
 
   getFileNodesAll() {
diff --git a/src/domain/analysis/impact.js b/src/domain/analysis/impact.js
@@ -18,6 +18,42 @@ import { normalizeSymbol } from '../../shared/normalize.js';
 import { paginateResult } from '../../shared/paginate.js';
 import { findMatchingNodes } from './symbol-lookup.js';
 
+// ─── Shared BFS: transitive callers ────────────────────────────────────
+
+/**
+ * BFS traversal to find transitive callers of a node.
+ *
+ * @param {import('better-sqlite3').Database} db - Open read-only SQLite database handle (not a Repository)
+ * @param {number} startId - Starting node ID
+ * @param {{ noTests?: boolean, maxDepth?: number, onVisit?: (caller: object, parentId: number, depth: number) => void }} options
+ * @returns {{ totalDependents: number, levels: Record<number, Array<{name:string, kind:string, file:string, line:number}>> }}
+ */
+export function bfsTransitiveCallers(db, startId, { noTests = false, maxDepth = 3, onVisit } = {}) {
+  const visited = new Set([startId]);
+  const levels = {};
+  let frontier = [startId];
+
+  for (let d = 1; d <= maxDepth; d++) {
+    const nextFrontier = [];
+    for (const fid of frontier) {
+      const callers = findDistinctCallers(db, fid);
+      for (const c of callers) {
+        if (!visited.has(c.id) && (!noTests || !isTestFile(c.file))) {
+          visited.add(c.id);
+          nextFrontier.push(c.id);
+          if (!levels[d]) levels[d] = [];
+          levels[d].push({ name: c.name, kind: c.kind, file: c.file, line: c.line });
+          if (onVisit) onVisit(c, fid, d);
+        }
+      }
+    }
+    frontier = nextFrontier;
+    if (frontier.length === 0) break;
+  }
+
+  return { totalDependents: visited.size - 1, levels };
+}
+
 export function impactAnalysisData(file, customDbPath, opts = {}) {
   const db = openReadonlyOrFail(customDbPath);
   try {
@@ -82,31 +118,11 @@ export function fnImpactData(name, customDbPath, opts = {}) {
     }
 
     const results = nodes.map((node) => {
-      const visited = new Set([node.id]);
-      const levels = {};
-      let frontier = [node.id];
-
-      for (let d = 1; d <= maxDepth; d++) {
-        const nextFrontier = [];
-        for (const fid of frontier) {
-          const callers = findDistinctCallers(db, fid);
-          for (const c of callers) {
-            if (!visited.has(c.id) && (!noTests || !isTestFile(c.file))) {
-              visited.add(c.id);
-              nextFrontier.push(c.id);
-              if (!levels[d]) levels[d] = [];
-              levels[d].push({ name: c.name, kind: c.kind, file: c.file, line: c.line });
-            }
-          }
-        }
-        frontier = nextFrontier;
-        if (frontier.length === 0) break;
-      }
-
+      const { levels, totalDependents } = bfsTransitiveCallers(db, node.id, { noTests, maxDepth });
       return {
         ...normalizeSymbol(node, db, hc),
         levels,
-        totalDependents: visited.size - 1,
+        totalDependents,
       };
     });
 
@@ -232,40 +248,27 @@ export function diffImpactData(customDbPath, opts = {}) {
 
     const allAffected = new Set();
     const functionResults = affectedFunctions.map((fn) => {
-      const visited = new Set([fn.id]);
-      let frontier = [fn.id];
-      let totalCallers = 0;
-      const levels = {};
       const edges = [];
       const idToKey = new Map();
       idToKey.set(fn.id, `${fn.file}::${fn.name}:${fn.line}`);
-      for (let d = 1; d <= maxDepth; d++) {
-        const nextFrontier = [];
-        for (const fid of frontier) {
-          const callers = findDistinctCallers(db, fid);
-          for (const c of callers) {
-            if (!visited.has(c.id) && (!noTests || !isTestFile(c.file))) {
-              visited.add(c.id);
-              nextFrontier.push(c.id);
-              allAffected.add(`${c.file}:${c.name}`);
-              const callerKey = `${c.file}::${c.name}:${c.line}`;
-              idToKey.set(c.id, callerKey);
-              if (!levels[d]) levels[d] = [];
-              levels[d].push({ name: c.name, kind: c.kind, file: c.file, line: c.line });
-              edges.push({ from: idToKey.get(fid), to: callerKey });
-              totalCallers++;
-            }
-          }
-        }
-        frontier = nextFrontier;
-        if (frontier.length === 0) break;
-      }
+
+      const { levels, totalDependents } = bfsTransitiveCallers(db, fn.id, {
+        noTests,
+        maxDepth,
+        onVisit(c, parentId) {
+          allAffected.add(`${c.file}:${c.name}`);
+          const callerKey = `${c.file}::${c.name}:${c.line}`;
+          idToKey.set(c.id, callerKey);
+          edges.push({ from: idToKey.get(parentId), to: callerKey });
+        },
+      });
+
       return {
         name: fn.name,
         kind: fn.kind,
         file: fn.file,
         line: fn.line,
-        transitiveCallers: totalCallers,
+        transitiveCallers: totalDependents,
         levels,
         edges,
       };
@@ -310,8 +313,8 @@ export function diffImpactData(customDbPath, opts = {}) {
     let boundaryViolations = [];
     let boundaryViolationCount = 0;
     try {
-      const config = loadConfig(repoRoot);
-      const boundaryConfig = config.manifesto?.boundaries;
+      const cfg = opts.config || loadConfig(repoRoot);
+      const boundaryConfig = cfg.manifesto?.boundaries;
       if (boundaryConfig) {
         const result = evaluateBoundaries(db, boundaryConfig, {
           scopeFiles: [...changedRanges.keys()],
diff --git a/src/features/audit.js b/src/features/audit.js
@@ -8,6 +8,7 @@
 
 import path from 'node:path';
 import { openReadonlyOrFail } from '../db/index.js';
+import { bfsTransitiveCallers } from '../domain/analysis/impact.js';
 import { explainData } from '../domain/queries.js';
 import { loadConfig } from '../infrastructure/config.js';
 import { isTestFile } from '../infrastructure/test-filter.js';
@@ -17,11 +18,15 @@ import { RULE_DEFS } from './manifesto.js';
 
 const FUNCTION_RULES = RULE_DEFS.filter((d) => d.level === 'function');
 
-function resolveThresholds(customDbPath) {
+function resolveThresholds(customDbPath, config) {
   try {
-    const dbDir = path.dirname(customDbPath);
-    const repoRoot = path.resolve(dbDir, '..');
-    const cfg = loadConfig(repoRoot);
+    const cfg =
+      config ||
+      (() => {
+        const dbDir = path.dirname(customDbPath);
+        const repoRoot = path.resolve(dbDir, '..');
+        return loadConfig(repoRoot);
+      })();
     const userRules = cfg.manifesto || {};
     const resolved = {};
     for (const def of FUNCTION_RULES) {
@@ -70,39 +75,6 @@ function checkBreaches(row, thresholds) {
   return breaches;
 }
 
-// ─── BFS impact (inline, same algorithm as fnImpactData) ────────────
-
-function computeImpact(db, nodeId, noTests, maxDepth) {
-  const visited = new Set([nodeId]);
-  const levels = {};
-  let frontier = [nodeId];
-
-  for (let d = 1; d <= maxDepth; d++) {
-    const nextFrontier = [];
-    for (const fid of frontier) {
-      const callers = db
-        .prepare(
-          `SELECT DISTINCT n.id, n.name, n.kind, n.file, n.line
-           FROM edges e JOIN nodes n ON e.source_id = n.id
-           WHERE e.target_id = ? AND e.kind = 'calls'`,
-        )
-        .all(fid);
-      for (const c of callers) {
-        if (!visited.has(c.id) && (!noTests || !isTestFile(c.file))) {
-          visited.add(c.id);
-          nextFrontier.push(c.id);
-          if (!levels[d]) levels[d] = [];
-          levels[d].push({ name: c.name, kind: c.kind, file: c.file, line: c.line });
-        }
-      }
-    }
-    frontier = nextFrontier;
-    if (frontier.length === 0) break;
-  }
-
-  return { totalDependents: visited.size - 1, levels };
-}
-
 // ─── Phase 4.4 fields (graceful null fallback) ─────────────────────
 
 function readPhase44(db, nodeId) {
@@ -147,7 +119,7 @@ export function auditData(target, customDbPath, opts = {}) {
 
   // 2. Open DB for enrichment
   const db = openReadonlyOrFail(customDbPath);
-  const thresholds = resolveThresholds(customDbPath);
+  const thresholds = resolveThresholds(customDbPath, opts.config);
 
   let functions;
   try {
@@ -189,7 +161,7 @@ function enrichFunction(db, r, noTests, maxDepth, thresholds) {
   const nodeId = nodeRow?.id;
   const health = nodeId ? buildHealth(db, nodeId, thresholds) : defaultHealth();
   const impact = nodeId
-    ? computeImpact(db, nodeId, noTests, maxDepth)
+    ? bfsTransitiveCallers(db, nodeId, { noTests, maxDepth })
     : { totalDependents: 0, levels: {} };
   const phase44 = nodeId
     ? readPhase44(db, nodeId)
@@ -260,7 +232,7 @@ function enrichSymbol(db, sym, file, noTests, maxDepth, thresholds) {
 
   const health = nodeId ? buildHealth(db, nodeId, thresholds) : defaultHealth();
   const impact = nodeId
-    ? computeImpact(db, nodeId, noTests, maxDepth)
+    ? bfsTransitiveCallers(db, nodeId, { noTests, maxDepth })
     : { totalDependents: 0, levels: {} };
   const phase44 = nodeId
     ? readPhase44(db, nodeId)
diff --git a/src/features/check.js b/src/features/check.js
@@ -2,6 +2,7 @@ import { execFileSync } from 'node:child_process';
 import fs from 'node:fs';
 import path from 'node:path';
 import { findDbPath, openReadonlyOrFail } from '../db/index.js';
+import { bfsTransitiveCallers } from '../domain/analysis/impact.js';
 import { findCycles } from '../domain/graph/cycles.js';
 import { loadConfig } from '../infrastructure/config.js';
 import { isTestFile } from '../infrastructure/test-filter.js';
@@ -96,31 +97,10 @@ export function checkMaxBlastRadius(db, changedRanges, threshold, noTests, maxDe
       }
       if (!overlaps) continue;
 
-      // BFS transitive callers
-      const visited = new Set([def.id]);
-      let frontier = [def.id];
-      let totalCallers = 0;
-      for (let d = 1; d <= maxDepth; d++) {
-        const nextFrontier = [];
-        for (const fid of frontier) {
-          const callers = db
-            .prepare(
-              `SELECT DISTINCT n.id, n.name, n.kind, n.file, n.line
-               FROM edges e JOIN nodes n ON e.source_id = n.id
-               WHERE e.target_id = ? AND e.kind = 'calls'`,
-            )
-            .all(fid);
-          for (const c of callers) {
-            if (!visited.has(c.id) && (!noTests || !isTestFile(c.file))) {
-              visited.add(c.id);
-              nextFrontier.push(c.id);
-              totalCallers++;
-            }
-          }
-        }
-        frontier = nextFrontier;
-        if (frontier.length === 0) break;
-      }
+      const { totalDependents: totalCallers } = bfsTransitiveCallers(db, def.id, {
+        noTests,
+        maxDepth,
+      });
 
       if (totalCallers > maxFound) maxFound = totalCallers;
       if (totalCallers > threshold) {
@@ -240,7 +220,10 @@ export function checkData(customDbPath, opts = {}) {
     const maxDepth = opts.depth || 3;
 
     // Load config defaults for check predicates
-    const config = loadConfig(repoRoot);
+    // NOTE: opts.config is loaded from process.cwd() at startup (via CLI context),
+    // which may differ from the DB's parent repo root when --db points to an external
+    // project. This is an acceptable trade-off to avoid duplicate I/O on the hot path.
+    const config = opts.config || loadConfig(repoRoot);
     const checkConfig = config.check || {};
 
     // Resolve which predicates are enabled: CLI flags ?? config ?? built-in defaults
diff --git a/src/features/complexity.js b/src/features/complexity.js
@@ -524,7 +524,7 @@ export function complexityData(customDbPath, opts = {}) {
     const kindFilter = opts.kind || null;
 
     // Load thresholds from config
-    const config = loadConfig(process.cwd());
+    const config = opts.config || loadConfig(process.cwd());
     const thresholds = config.manifesto?.rules || {
       cognitive: { warn: 15, fail: null },
       cyclomatic: { warn: 10, fail: null },
diff --git a/src/features/manifesto.js b/src/features/manifesto.js
@@ -395,7 +395,7 @@ export function manifestoData(customDbPath, opts = {}) {
   const db = openReadonlyOrFail(customDbPath);
 
   try {
-    const config = loadConfig(process.cwd());
+    const config = opts.config || loadConfig(process.cwd());
     const rules = resolveRules(config.manifesto?.rules);
 
     const violations = [];
diff --git a/src/graph/builders/dependency.js b/src/graph/builders/dependency.js
diff --git a/tests/graph/builders/dependency.test.js b/tests/graph/builders/dependency.test.js

Original file line number	Diff line number	Diff line change
`@@ -163,7 +163,7 @@ export class Repository {`
`163`	`163`	`throw new Error('not implemented');`
`164`	`164`	`}`
`165`	`165`
`166`		`- /** @returns {{ source_id: number, target_id: number }[]} */`
	`166`	`+ /** @returns {{ source_id: number, target_id: number, confidence: number\|null }[]} */`
`167`	`167`	`getCallEdges() {`
`168`	`168`	`throw new Error('not implemented');`
`169`	`169`	`}`
Original file line number	Diff line number	Diff line change
`@@ -489,7 +489,7 @@ export class InMemoryRepository extends Repository {`
`489`	`489`	`getCallEdges() {`
`490`	`490`	`return [...this.#edges.values()]`
`491`	`491`	`.filter((e) => e.kind === 'calls')`
`492`		`- .map((e) => ({ source_id: e.source_id, target_id: e.target_id }));`
	`492`	`+ .map((e) => ({ source_id: e.source_id, target_id: e.target_id, confidence: e.confidence }));`
`493`	`493`	`}`
`494`	`494`
`495`	`495`	`getFileNodesAll() {`