ContextModule: Improving Code Completion via Repository-level Contextual Information

TL;DR

ContextModule tackles the gap where LLM-based code completion relies only on the current file by integrating repository-wide signals. It retrieves three context types—user behavior code, similar code, and symbol definitions via a Code Knowledge Graph—and fuses them with the active file content to form prompts for an LLM. The approach is supported by caching, incremental parsing, and a fast CK G-driven symbol retrieval strategy, achieving substantial online improvements in acceptance rates and completion accuracy in production. This work demonstrates that combining cross-file signals with efficient retrieval and symbol context significantly enhances code completion in real-world development environments.

Abstract

Large Language Models (LLMs) have demonstrated impressive capabilities in code completion tasks, where they assist developers by predicting and generating new code in real-time. However, existing LLM-based code completion systems primarily rely on the immediate context of the file being edited, often missing valuable repository-level information, user behaviour and edit history that could improve suggestion accuracy. Additionally, challenges such as efficiently retrieving relevant code snippets from large repositories, incorporating user behavior, and balancing accuracy with low-latency requirements in production environments remain unresolved. In this paper, we propose ContextModule, a framework designed to enhance LLM-based code completion by retrieving and integrating three types of contextual information from the repository: user behavior-based code, similar code snippets, and critical symbol definitions. By capturing user interactions across files and leveraging repository-wide static analysis, ContextModule improves the relevance and precision of generated code. We implement performance optimizations, such as index caching, to ensure the system meets the latency constraints of real-world coding environments. Experimental results and industrial practise demonstrate that ContextModule significantly improves code completion accuracy and user acceptance rates.

Figures (10)

• Figure 1: FrameWork of ContextModule
• Figure 2: User Behavior Code Retrieval Process
• Figure 3: Cache Strategy for Similar Code Retrieval
• Figure 4: CKG-based Symbol Retrieval Process
• Figure 5: CKG Case 1