RepoScope: Leveraging Call Chain-Aware Multi-View Context for Repository-Level Code Generation

TL;DR

RepoScope introduces a novel approach for repository-level code generation by leveraging call chain-aware multi-view context and structural semantics, significantly improving the relevance and accuracy of generated code without additional training.

Contribution

It proposes a call chain prediction method and a structure-preserving serialization algorithm, utilizing static analysis to enhance context retrieval and prompt construction for code generation.

Findings

Achieves up to 36.35% relative improvement in pass@1 scores on benchmarks.

Outperforms state-of-the-art methods in repository-level code generation.

Demonstrates effectiveness across multiple tasks and integration with existing approaches.

Abstract

Repository-level code generation aims to generate code within the context of a specified repository. Existing approaches typically employ retrieval-augmented generation (RAG) techniques to provide LLMs with relevant contextual information extracted from the repository. However, these approaches often struggle with effectively identifying truly relevant contexts that capture the rich semantics of the repository, and their contextual perspectives remains narrow. Moreover, most approaches fail to account for the structural relationships in the retrieved code during prompt construction, hindering the LLM's ability to accurately interpret the context. To address these issues, we propose RepoScope, which leverages call chain-aware multi-view context for repository-level code generation. RepoScope constructs a Repository Structural Semantic Graph (RSSG) and retrieves a comprehensive four-view context, integrating both structural and similarity-based contexts. We propose a novel call chain prediction method that utilizes the repository's structural semantics to improve the identification of callees in the target function. Additionally, we present a structure-preserving serialization algorithm for prompt construction, ensuring the coherence of the context for the LLM. Notably, RepoScope relies solely on static analysis, eliminating the need for additional training or multiple LLM queries, thus ensuring both efficiency and generalizability. Evaluation on widely-used repository-level code generation benchmarks (CoderEval and DevEval) demonstrates that RepoScope outperforms state-of-the-art methods, achieving up to a 36.35% relative improvement in pass@1 scores. Further experiments emphasize RepoScope's potential to improve code generation across different tasks and its ability to integrate effectively with existing approaches.