TypeScript Repository Indexing for Code Agent Retrieval

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Pu, Junsong, Li, Yichen, Chen, Zhuangbin
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913051815444480
author Pu, Junsong
Li, Yichen
Chen, Zhuangbin
author_facet Pu, Junsong
Li, Yichen
Chen, Zhuangbin
contents Graph-based code indexing can improve context retrieval for LLM-based code agents by preserving call chains and dependency relationships that keyword search and similarity retrieval often miss. ABCoder is an open-source framework that parses codebases into a function-level code index called UniAST. Its existing parsers combine lightweight AST parsers for syntactic analysis with language servers for semantic resolution, but because LSP-based resolution requires a JSON-RPC call for each symbol lookup, these per-symbol calls become a bottleneck on large TypeScript repositories. We present abcoder-ts-parser, a TypeScript parser built on the TypeScript Compiler API that works directly with the compiler's AST, semantic information, and module resolution logic. We evaluate the parser on three open-source TypeScript projects with up to 1.2 million lines of code and find that it produces reliable indexes significantly more efficiently than the existing architecture. For a live demonstration, watch: https://youtu.be/ryssr7ouvdE
format Preprint
id arxiv_https___arxiv_org_abs_2604_18413
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle TypeScript Repository Indexing for Code Agent Retrieval
Pu, Junsong
Li, Yichen
Chen, Zhuangbin
Software Engineering
Graph-based code indexing can improve context retrieval for LLM-based code agents by preserving call chains and dependency relationships that keyword search and similarity retrieval often miss. ABCoder is an open-source framework that parses codebases into a function-level code index called UniAST. Its existing parsers combine lightweight AST parsers for syntactic analysis with language servers for semantic resolution, but because LSP-based resolution requires a JSON-RPC call for each symbol lookup, these per-symbol calls become a bottleneck on large TypeScript repositories. We present abcoder-ts-parser, a TypeScript parser built on the TypeScript Compiler API that works directly with the compiler's AST, semantic information, and module resolution logic. We evaluate the parser on three open-source TypeScript projects with up to 1.2 million lines of code and find that it produces reliable indexes significantly more efficiently than the existing architecture. For a live demonstration, watch: https://youtu.be/ryssr7ouvdE
title TypeScript Repository Indexing for Code Agent Retrieval
topic Software Engineering
url https://arxiv.org/abs/2604.18413