Recently, Large Language Models (LLMs) have gained attention for their ability to handle a broad range of tasks, including unit test generation. Despite their success, LLMs may exhibit hallucinations when generating unit tests for focal methods or functions due to their lack of awareness regarding the project’s global context. While many studies have explored the role of context, they often extract fixed patterns of context for different models and focal methods, which may not be suitable for all generation processes (e.g., excessive irrelevant context could lead to redundancy, preventing the model from focusing on essential information). To overcome this limitation, we propose RATester, which integrates the language server gopls to provide dynamic definition lookup to assist the LLM. When RATester encounters an unfamiliar identifier, it first leverages gopls to fetch relevant definitions and documentation comments, and then uses this global knowledge to guide the LLM. We evaluate the effectiveness and efficiency of RATester compared to baseline approaches by constructing a new Golang dataset from real-world projects. On our dataset, RATester achieves an average line coverage of 26.25%, representing an improvement of 16.30% to 165.69% over the baselines. Furthermore, RATester shows superior performance in mutation testing, successfully killing 25 to 147 more mutants than the baseline approaches.