Merge pull request #75 from colbymchenry/fix/python-resolution-and-context-relevance

feat: Improve Java/Python resolution, context relevance, and multi-symbol aggregation
This commit is contained in:
Colby Mchenry
2026-04-03 12:31:37 -05:00
committed by GitHub
11 changed files with 399 additions and 63 deletions
+2 -2
View File
@@ -1,12 +1,12 @@
{
"name": "@colbymchenry/codegraph",
"version": "0.6.6",
"version": "0.6.8",
"lockfileVersion": 3,
"requires": true,
"packages": {
"": {
"name": "@colbymchenry/codegraph",
"version": "0.6.6",
"version": "0.6.8",
"hasInstallScript": true,
"license": "MIT",
"dependencies": {
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "@colbymchenry/codegraph",
"version": "0.6.6",
"version": "0.6.8",
"description": "Supercharge Claude Code with semantic code intelligence. 30% fewer tokens, 25% fewer tool calls, 100% local.",
"main": "dist/index.js",
"types": "dist/index.d.ts",
+12
View File
@@ -25,6 +25,7 @@ import { VectorManager } from '../vectors';
import { formatContextAsMarkdown, formatContextAsJson } from './formatter';
import { logDebug, logWarn } from '../errors';
import { validatePathWithinRoot } from '../utils';
import { isTestFile } from '../search/query-utils';
/**
* Extract likely symbol names from a natural language query
@@ -334,6 +335,17 @@ export class ContextBuilder {
// Limit total results
searchResults = searchResults.slice(0, opts.searchLimit * 2);
// Deprioritize test files unless the query is about tests
const queryLower = query.toLowerCase();
const isTestQuery = queryLower.includes('test') || queryLower.includes('spec');
if (!isTestQuery) {
searchResults = searchResults.map(r => ({
...r,
score: isTestFile(r.node.filePath) ? r.score * 0.3 : r.score,
}));
searchResults.sort((a, b) => b.score - a.score);
}
// Filter by minimum score
let filteredResults = searchResults.filter((r) => r.score >= opts.minScore);
+17
View File
@@ -926,6 +926,23 @@ export class QueryBuilder {
this.db.prepare(`DELETE FROM unresolved_refs WHERE from_node_id IN (${placeholders})`).run(...fromNodeIds);
}
/**
* Delete specific resolved references by (fromNodeId, referenceName, referenceKind) tuples.
* More precise than deleteResolvedReferences — only removes refs that were actually resolved.
*/
deleteSpecificResolvedReferences(refs: Array<{ fromNodeId: string; referenceName: string; referenceKind: string }>): void {
if (refs.length === 0) return;
const stmt = this.db.prepare(
'DELETE FROM unresolved_refs WHERE from_node_id = ? AND reference_name = ? AND reference_kind = ?'
);
const deleteMany = this.db.transaction((items: typeof refs) => {
for (const ref of items) {
stmt.run(ref.fromNodeId, ref.referenceName, ref.referenceKind);
}
});
deleteMany(refs);
}
// ===========================================================================
// Statistics
// ===========================================================================
+68 -27
View File
@@ -1325,10 +1325,14 @@ export class TreeSitterExtractor {
let kind: NodeKind = 'interface';
if (this.language === 'rust') kind = 'trait';
this.createNode(kind, name, node, {
const interfaceNode = this.createNode(kind, name, node, {
docstring,
isExported,
});
if (!interfaceNode) return;
// Extract extends (interface inheritance)
this.extractInheritance(node, interfaceNode.id);
}
/**
@@ -1754,6 +1758,19 @@ export class TreeSitterExtractor {
signature: importText,
});
}
// Create unresolved reference for import resolution before returning
if (moduleName && this.nodeStack.length > 0) {
const parentId = this.nodeStack[this.nodeStack.length - 1];
if (parentId) {
this.unresolvedReferences.push({
fromNodeId: parentId,
referenceName: moduleName,
referenceKind: 'imports',
line: node.startPosition.row + 1,
column: node.startPosition.column,
});
}
}
return; // Java handled completely above
} else if (this.language === 'csharp') {
// C# using directives: using System, using System.Collections.Generic, using static X, using Alias = X
@@ -1960,20 +1977,36 @@ export class TreeSitterExtractor {
// Get the function/method being called
let calleeName = '';
const func = getChildByField(node, 'function') || node.namedChild(0);
if (func) {
if (func.type === 'member_expression' || func.type === 'attribute') {
// Method call: obj.method()
const property = getChildByField(func, 'property') || func.namedChild(1);
if (property) {
calleeName = getNodeText(property, this.source);
// Java/Kotlin method_invocation has 'object' + 'name' fields instead of 'function'
const nameField = getChildByField(node, 'name');
const objectField = getChildByField(node, 'object');
if (nameField && objectField && node.type === 'method_invocation') {
// Java-style method call: receiver.method()
const methodName = getNodeText(nameField, this.source);
const receiverName = getNodeText(objectField, this.source);
if (methodName) {
// Emit receiver.method form for qualified resolution
calleeName = `${receiverName}.${methodName}`;
}
} else {
const func = getChildByField(node, 'function') || node.namedChild(0);
if (func) {
if (func.type === 'member_expression' || func.type === 'attribute') {
// Method call: obj.method()
const property = getChildByField(func, 'property') || func.namedChild(1);
if (property) {
calleeName = getNodeText(property, this.source);
}
} else if (func.type === 'scoped_identifier' || func.type === 'scoped_call_expression') {
// Scoped call: Module::function()
calleeName = getNodeText(func, this.source);
} else {
calleeName = getNodeText(func, this.source);
}
} else if (func.type === 'scoped_identifier' || func.type === 'scoped_call_expression') {
// Scoped call: Module::function()
calleeName = getNodeText(func, this.source);
} else {
calleeName = getNodeText(func, this.source);
}
}
@@ -2023,30 +2056,38 @@ export class TreeSitterExtractor {
if (
child.type === 'extends_clause' ||
child.type === 'class_heritage' ||
child.type === 'superclass'
child.type === 'superclass' ||
child.type === 'extends_interfaces' // Java interface extends
) {
// Extract parent class name
const superclass = child.namedChild(0);
if (superclass) {
const name = getNodeText(superclass, this.source);
this.unresolvedReferences.push({
fromNodeId: classId,
referenceName: name,
referenceKind: 'extends',
line: child.startPosition.row + 1,
column: child.startPosition.column,
});
// Extract parent class/interface names
// Java uses type_list wrapper: superclass -> type_identifier, extends_interfaces -> type_list -> type_identifier
const typeList = child.namedChildren.find((c: SyntaxNode) => c.type === 'type_list');
const targets = typeList ? typeList.namedChildren : [child.namedChild(0)];
for (const target of targets) {
if (target) {
const name = getNodeText(target, this.source);
this.unresolvedReferences.push({
fromNodeId: classId,
referenceName: name,
referenceKind: 'extends',
line: target.startPosition.row + 1,
column: target.startPosition.column,
});
}
}
}
if (
child.type === 'implements_clause' ||
child.type === 'class_interface_clause' ||
child.type === 'super_interfaces' || // Java class implements
child.type === 'interfaces' // Dart
) {
// Extract implemented interfaces
for (let j = 0; j < child.namedChildCount; j++) {
const iface = child.namedChild(j);
// Java uses type_list wrapper: super_interfaces -> type_list -> type_identifier
const typeList = child.namedChildren.find((c: SyntaxNode) => c.type === 'type_list');
const targets = typeList ? typeList.namedChildren : child.namedChildren;
for (const iface of targets) {
if (iface) {
const name = getNodeText(iface, this.source);
this.unresolvedReferences.push({
+19
View File
@@ -483,6 +483,25 @@ export class GraphTraverser {
}
visited.add(nodeId);
// For container nodes (classes, interfaces, structs, etc.), also traverse
// into their children so that callers of contained methods appear in impact
const focalNode = this.queries.getNodeById(nodeId);
if (focalNode) {
const containerKinds = new Set(['class', 'interface', 'struct', 'trait', 'protocol', 'module', 'enum']);
if (containerKinds.has(focalNode.kind)) {
const containsEdges = this.queries.getOutgoingEdges(nodeId, ['contains']);
for (const edge of containsEdges) {
const childNode = this.queries.getNodeById(edge.target);
if (childNode && !visited.has(childNode.id)) {
nodes.set(childNode.id, childNode);
edges.push(edge);
// Recurse into children at the same depth (they're part of the same symbol)
this.getImpactRecursive(childNode.id, maxDepth, currentDepth, nodes, edges, visited);
}
}
}
}
// Get all incoming edges (things that depend on this node)
const incomingEdges = this.queries.getIncomingEdges(nodeId);
+87 -21
View File
@@ -5,7 +5,7 @@
*/
import CodeGraph, { findNearestCodeGraphRoot } from '../index';
import type { Node, SearchResult, Subgraph, TaskContext, NodeKind } from '../types';
import type { Node, Edge, SearchResult, Subgraph, TaskContext, NodeKind } from '../types';
import { createHash } from 'crypto';
import { writeFileSync } from 'fs';
import { clamp } from '../utils';
@@ -475,19 +475,28 @@ export class ToolHandler {
const cg = this.getCodeGraph(args.projectPath as string | undefined);
const limit = clamp((args.limit as number) || 20, 1, 100);
const match = this.findSymbol(cg, symbol);
if (!match) {
const allMatches = this.findAllSymbols(cg, symbol);
if (allMatches.nodes.length === 0) {
return this.textResult(`Symbol "${symbol}" not found in the codebase`);
}
const callers = cg.getCallers(match.node.id);
if (callers.length === 0) {
return this.textResult(`No callers found for "${symbol}"${match.note}`);
// Aggregate callers across all matching symbols
const seen = new Set<string>();
const allCallers: Node[] = [];
for (const node of allMatches.nodes) {
for (const c of cg.getCallers(node.id)) {
if (!seen.has(c.node.id)) {
seen.add(c.node.id);
allCallers.push(c.node);
}
}
}
const callerNodes = callers.slice(0, limit).map(c => c.node);
const formatted = this.formatNodeList(callerNodes, `Callers of ${symbol}`) + match.note;
if (allCallers.length === 0) {
return this.textResult(`No callers found for "${symbol}"${allMatches.note}`);
}
const formatted = this.formatNodeList(allCallers.slice(0, limit), `Callers of ${symbol}`) + allMatches.note;
return this.textResult(this.truncateOutput(formatted));
}
@@ -501,19 +510,28 @@ export class ToolHandler {
const cg = this.getCodeGraph(args.projectPath as string | undefined);
const limit = clamp((args.limit as number) || 20, 1, 100);
const match = this.findSymbol(cg, symbol);
if (!match) {
const allMatches = this.findAllSymbols(cg, symbol);
if (allMatches.nodes.length === 0) {
return this.textResult(`Symbol "${symbol}" not found in the codebase`);
}
const callees = cg.getCallees(match.node.id);
if (callees.length === 0) {
return this.textResult(`No callees found for "${symbol}"${match.note}`);
// Aggregate callees across all matching symbols
const seen = new Set<string>();
const allCallees: Node[] = [];
for (const node of allMatches.nodes) {
for (const c of cg.getCallees(node.id)) {
if (!seen.has(c.node.id)) {
seen.add(c.node.id);
allCallees.push(c.node);
}
}
}
const calleeNodes = callees.slice(0, limit).map(c => c.node);
const formatted = this.formatNodeList(calleeNodes, `Callees of ${symbol}`) + match.note;
if (allCallees.length === 0) {
return this.textResult(`No callees found for "${symbol}"${allMatches.note}`);
}
const formatted = this.formatNodeList(allCallees.slice(0, limit), `Callees of ${symbol}`) + allMatches.note;
return this.textResult(this.truncateOutput(formatted));
}
@@ -527,14 +545,37 @@ export class ToolHandler {
const cg = this.getCodeGraph(args.projectPath as string | undefined);
const depth = clamp((args.depth as number) || 2, 1, 10);
const match = this.findSymbol(cg, symbol);
if (!match) {
const allMatches = this.findAllSymbols(cg, symbol);
if (allMatches.nodes.length === 0) {
return this.textResult(`Symbol "${symbol}" not found in the codebase`);
}
const impact = cg.getImpactRadius(match.node.id, depth);
// Aggregate impact across all matching symbols
const mergedNodes = new Map<string, Node>();
const mergedEdges: Edge[] = [];
const seenEdges = new Set<string>();
const formatted = this.formatImpact(symbol, impact) + match.note;
for (const node of allMatches.nodes) {
const impact = cg.getImpactRadius(node.id, depth);
for (const [id, n] of impact.nodes) {
mergedNodes.set(id, n);
}
for (const e of impact.edges) {
const key = `${e.source}->${e.target}:${e.kind}`;
if (!seenEdges.has(key)) {
seenEdges.add(key);
mergedEdges.push(e);
}
}
}
const mergedImpact = {
nodes: mergedNodes,
edges: mergedEdges,
roots: allMatches.nodes.map(n => n.id),
};
const formatted = this.formatImpact(symbol, mergedImpact) + allMatches.note;
return this.textResult(this.truncateOutput(formatted));
}
@@ -822,6 +863,31 @@ export class ToolHandler {
return { node: results[0]!.node, note: '' };
}
/**
* Find ALL symbols matching a name. Used by callers/callees/impact to aggregate
* results across all matching symbols (e.g., multiple classes with an `execute` method).
*/
private findAllSymbols(cg: CodeGraph, symbol: string): { nodes: Node[]; note: string } {
const results = cg.searchNodes(symbol, { limit: 50 });
if (results.length === 0) {
return { nodes: [], note: '' };
}
const exactMatches = results.filter(r => r.node.name === symbol);
if (exactMatches.length <= 1) {
const node = exactMatches[0]?.node ?? results[0]!.node;
return { nodes: [node], note: '' };
}
const locations = exactMatches.map(r =>
`${r.node.kind} at ${r.node.filePath}:${r.node.startLine}`
);
const note = `\n\n> **Note:** Aggregated results across ${exactMatches.length} symbols named "${symbol}": ${locations.join(', ')}`;
return { nodes: exactMatches.map(r => r.node), note };
}
/**
* Truncate output if it exceeds the maximum length
*/
+42
View File
@@ -375,6 +375,17 @@ export class ReferenceResolver {
this.queries.insertEdges(edges);
}
// Clean up resolved refs from unresolved_refs table so metrics are accurate
if (result.resolved.length > 0) {
this.queries.deleteSpecificResolvedReferences(
result.resolved.map((r) => ({
fromNodeId: r.original.fromNodeId,
referenceName: r.original.referenceName,
referenceKind: r.original.referenceKind,
}))
);
}
return result;
}
@@ -426,6 +437,37 @@ export class ReferenceResolver {
return true;
}
// Python built-in method calls (e.g., list.extend, dict.update, self.xxx)
if (ref.language === 'python') {
const dotIdx = name.indexOf('.');
if (dotIdx > 0) {
const receiver = name.substring(0, dotIdx);
// self.method and cls.method are internal calls, not built-in — let them resolve
// But receiver types that are built-in types should be filtered
const pythonBuiltInTypes = new Set([
'list', 'dict', 'set', 'tuple', 'str', 'int', 'float', 'bool',
'bytes', 'bytearray', 'frozenset', 'object', 'super',
]);
if (pythonBuiltInTypes.has(receiver)) {
return true;
}
}
// Also filter bare method names that are common Python built-in methods
// These get extracted as unresolved refs when called on arbitrary objects
const pythonBuiltInMethods = new Set([
'append', 'extend', 'insert', 'remove', 'pop', 'clear', 'sort', 'reverse', 'copy',
'update', 'keys', 'values', 'items', 'get',
'add', 'discard', 'union', 'intersection', 'difference',
'split', 'join', 'strip', 'lstrip', 'rstrip', 'replace', 'lower', 'upper',
'startswith', 'endswith', 'find', 'index', 'count', 'encode', 'decode',
'format', 'isdigit', 'isalpha', 'isalnum',
'read', 'write', 'readline', 'readlines', 'close', 'flush', 'seek',
]);
if (pythonBuiltInMethods.has(name)) {
return true;
}
}
// Pascal/Delphi built-ins and standard library units
if (ref.language === 'pascal') {
// Standard RTL/VCL/FMX unit prefixes — these are external dependencies
+111 -8
View File
@@ -20,12 +20,13 @@ export function matchByExactName(
return null;
}
// If only one match, use it
// If only one match, use it — but penalize cross-language matches
if (candidates.length === 1) {
const isCrossLanguage = candidates[0]!.language !== ref.language;
return {
original: ref,
targetNodeId: candidates[0]!.id,
confidence: 0.9,
confidence: isCrossLanguage ? 0.5 : 0.9,
resolvedBy: 'exact-match',
};
}
@@ -108,12 +109,14 @@ export function matchMethodCall(
const [, objectOrClass, methodName] = match;
// Find the class/object first
// Strategy 1: Direct class name match (existing logic)
const classCandidates = context.getNodesByName(objectOrClass!);
for (const classNode of classCandidates) {
if (classNode.kind === 'class' || classNode.kind === 'struct' || classNode.kind === 'interface') {
// Look for method in the same file
// Skip cross-language class matches
if (classNode.language !== ref.language) continue;
const nodesInFile = context.getNodesInFile(classNode.filePath);
const methodNode = nodesInFile.find(
(n) =>
@@ -133,9 +136,102 @@ export function matchMethodCall(
}
}
// Strategy 2: Instance variable receiver - try capitalized form to find class
// e.g., "permissionEngine" → look for classes containing "PermissionEngine"
const capitalizedReceiver = objectOrClass!.charAt(0).toUpperCase() + objectOrClass!.slice(1);
if (capitalizedReceiver !== objectOrClass) {
const fuzzyClassCandidates = context.getNodesByName(capitalizedReceiver);
for (const classNode of fuzzyClassCandidates) {
if (classNode.kind === 'class' || classNode.kind === 'struct' || classNode.kind === 'interface') {
// Skip cross-language class matches
if (classNode.language !== ref.language) continue;
const nodesInFile = context.getNodesInFile(classNode.filePath);
const methodNode = nodesInFile.find(
(n) =>
n.kind === 'method' &&
n.name === methodName &&
n.qualifiedName.includes(classNode.name)
);
if (methodNode) {
return {
original: ref,
targetNodeId: methodNode.id,
confidence: 0.8,
resolvedBy: 'instance-method',
};
}
}
}
}
// Strategy 3: Find methods by name across the codebase, match by receiver
// name similarity with the containing class. Handles abbreviated variable
// names like permissionEngine → PermissionRuleEngine.
if (methodName) {
const methodCandidates = context.getNodesByName(methodName!);
const methods = methodCandidates.filter(
(n) => n.kind === 'method' && n.name === methodName
);
// Filter to same-language candidates first
const sameLanguageMethods = methods.filter(m => m.language === ref.language);
const targetMethods = sameLanguageMethods.length > 0 ? sameLanguageMethods : methods;
// If only one same-language method with this name exists, use it
if (targetMethods.length === 1 && targetMethods[0]!.language === ref.language) {
return {
original: ref,
targetNodeId: targetMethods[0]!.id,
confidence: 0.7,
resolvedBy: 'instance-method',
};
}
// Multiple methods: score by receiver name word overlap with class name
if (targetMethods.length > 1) {
const receiverWords = splitCamelCase(objectOrClass!);
let bestMatch: typeof targetMethods[0] | undefined;
let bestScore = 0;
for (const method of targetMethods) {
const classWords = splitCamelCase(method.qualifiedName);
let score = receiverWords.filter(w =>
classWords.some(cw => cw.toLowerCase() === w.toLowerCase())
).length;
// Bonus for same language
if (method.language === ref.language) score += 1;
if (score > bestScore) {
bestScore = score;
bestMatch = method;
}
}
if (bestMatch && bestScore >= 2) {
return {
original: ref,
targetNodeId: bestMatch.id,
confidence: 0.65,
resolvedBy: 'instance-method',
};
}
}
}
return null;
}
/**
* Split a camelCase or PascalCase string into words.
*/
function splitCamelCase(str: string): string[] {
return str.replace(/([a-z])([A-Z])/g, '$1 $2')
.replace(/([A-Z]+)([A-Z][a-z])/g, '$1 $2')
.split(/[\s._:\/\\]+/)
.filter(w => w.length > 1);
}
/**
* Compute directory proximity between two file paths.
* Returns a score based on the number of shared directory segments.
@@ -187,9 +283,11 @@ function findBestMatch(
// Directory proximity bonus — strongly prefer same module/package
score += computePathProximity(ref.filePath, candidate.filePath);
// Same language bonus
// Language matching: strongly prefer same language, penalize cross-language
if (candidate.language === ref.language) {
score += 50;
} else {
score -= 80;
}
// For call references, prefer functions/methods
@@ -235,11 +333,16 @@ export function matchFuzzy(
const callableKinds = new Set(['function', 'method', 'class']);
const callableCandidates = candidates.filter((n) => callableKinds.has(n.kind));
if (callableCandidates.length === 1) {
// Prefer same-language matches
const sameLanguageCandidates = callableCandidates.filter(n => n.language === ref.language);
const finalCandidates = sameLanguageCandidates.length > 0 ? sameLanguageCandidates : callableCandidates;
if (finalCandidates.length === 1) {
const isCrossLanguage = finalCandidates[0]!.language !== ref.language;
return {
original: ref,
targetNodeId: callableCandidates[0]!.id,
confidence: 0.5,
targetNodeId: finalCandidates[0]!.id,
confidence: isCrossLanguage ? 0.3 : 0.5,
resolvedBy: 'fuzzy',
};
}
+1 -1
View File
@@ -39,7 +39,7 @@ export interface ResolvedRef {
/** Confidence score (0-1) */
confidence: number;
/** How it was resolved */
resolvedBy: 'exact-match' | 'import' | 'qualified-name' | 'framework' | 'fuzzy';
resolvedBy: 'exact-match' | 'import' | 'qualified-name' | 'framework' | 'fuzzy' | 'instance-method';
}
/**
+39 -3
View File
@@ -79,9 +79,45 @@ export function scorePathRelevance(filePath: string, query: string): number {
else if (pathLower.includes(term)) score += 3;
}
// Deprioritize test files unless the query is explicitly about tests
const queryLower = query.toLowerCase();
const isTestQuery = queryLower.includes('test') || queryLower.includes('spec');
if (!isTestQuery && isTestFile(filePath)) {
score -= 15;
}
return score;
}
/**
* Check if a file path looks like a test file
*/
export function isTestFile(filePath: string): boolean {
const lower = filePath.toLowerCase();
const fileName = path.basename(lower);
// Common test file patterns
return (
fileName.startsWith('test_') ||
fileName.startsWith('test.') ||
fileName.endsWith('.test.ts') ||
fileName.endsWith('.test.js') ||
fileName.endsWith('.test.tsx') ||
fileName.endsWith('.test.jsx') ||
fileName.endsWith('.spec.ts') ||
fileName.endsWith('.spec.js') ||
fileName.endsWith('_test.go') ||
fileName.endsWith('_test.py') ||
fileName.endsWith('_test.rs') ||
fileName.endsWith('Tests.java') ||
fileName.endsWith('Test.java') ||
lower.includes('/tests/') ||
lower.includes('/test/') ||
lower.includes('/__tests__/') ||
lower.includes('/spec/')
);
}
/**
* Kind-based bonus for search ranking
* Functions and classes are typically more relevant than variables/imports
@@ -91,10 +127,10 @@ export function kindBonus(kind: Node['kind']): number {
function: 10,
method: 10,
class: 8,
interface: 7,
interface: 9,
type_alias: 6,
struct: 6,
trait: 6,
trait: 9,
enum: 5,
component: 8,
route: 9,
@@ -108,7 +144,7 @@ export function kindBonus(kind: Node['kind']): number {
parameter: 0,
namespace: 4,
file: 0,
protocol: 6,
protocol: 9,
enum_member: 3,
};
return bonuses[kind] ?? 0;