In Line with Context: Repository-Level Code Generation via Context Inlining

TL;DR

InlineCoder is a novel framework that improves repository-level code generation by inline-contextualizing functions within call graphs, enabling better understanding of complex dependencies.

Contribution

It introduces a new inlining-based approach that enhances repository understanding for code generation, surpassing surface-level similarity methods.

Findings

Enables more accurate repository-level code generation.

Uses inlining to incorporate upstream and downstream context.

Provides a confidence estimate for generated code.

Abstract

Repository-level code generation has attracted growing attention in recent years. Unlike function-level code generation, it requires the model to understand the entire repository, reasoning over complex dependencies across functions, classes, and modules. However, existing approaches such as retrieval-augmented generation (RAG) or context-based function selection often fall short: they primarily rely on surface-level similarity and struggle to capture the rich dependencies that govern repository-level semantics. In this paper, we introduce InlineCoder, a novel framework for repository-level code generation. InlineCoder enhances the understanding of repository context by inlining the unfinished function into its call graph, thereby reframing the challenging repository understanding as an easier function-level coding task. Given a function signature, InlineCoder first generates a draft completion, termed an anchor, which approximates downstream dependencies and enables perplexity-based confidence estimation. This anchor drives a bidirectional inlining process: (i) Upstream Inlining, which embeds the anchor into its callers to capture diverse usage scenarios; and (ii) Downstream Retrieval, which integrates the anchor's callees into the prompt to provide precise dependency context. The enriched context, combining draft completion with upstream and downstream perspectives, equips the LLM with a comprehensive repository view.