Modern large language model (LLM) agents do not simply need longer contexts; they need decision-relevant evidence at the moment of action. We study decision-aware context selection: ranking retrieved files, tests, traces, rules, and memories by their expected effect on an agent's next action rather than by semantic similarity alone. We present the Counterfactual-Inspired Context Layer (CICL), which builds an instance context graph, estimates decision-oriented utility for candidate units, and compresses selected evidence into typed memory cards. The same schema can be instantiated with hosted LLM judges, local surrogates, or lightweight rankers, making the selection protocol auditable across model choices. On 50 SWE-bench Verified file-retrieval instances, Qwen3.6-Plus reranking of BM25 top-50 candidates improves hit@1 from 0.58 to 0.78 and MRR@10 from 0.634 to 0.790, with all 2,500 judgments parseable. Controlled diagnostics show that CICL identifies action-critical evidence: removing the top-utility semantic unit reduces F1 from 0.245 to 0.000. In selected-then-compressed mode, memory cards save 44.93 tokens per query while preserving selected evidence. CICL provides a practical layer for measuring, ranking, and compressing decision-critical context for tool-using agents. Code is available at https://github.com/stephen-guan-researcher/CICL.

翻译：现代大语言模型（LLM）代理不仅需要更长的上下文，还需要在行动时刻获取与决策相关的证据。我们研究决策感知的上下文选择：根据候选内容对代理下一步行动的预期影响（而非仅基于语义相似性）对检索到的文件、测试用例、追踪记录、规则和记忆进行排序。我们提出反事实启发上下文层（CICL），该方法构建实例上下文图，评估候选单元的决策导向效用，并将选中的证据压缩为类型化记忆卡。该方案可通过托管LLM裁判、本地代理模型或轻量级排序器实例化，使选择协议在不同模型选择下均具备可审计性。在50个SWE-bench验证文件检索实例上，Qwen3.6-Plus对BM25前50候选的重排序将命中率@1从0.58提升至0.78，MRR@10从0.634提升至0.790，且全部2500个判断均可解析。受控诊断表明CICL能识别行动关键证据：移除最高效用语义单元后F1得分从0.245骤降至0.000。在选择后压缩模式下，记忆卡每查询可节省44.93个token同时保留选中证据。CICL为工具使用代理提供了一种实用层，用于测量、排序和压缩决策关键上下文。代码已开源至https://github.com/stephen-guan-researcher/CICL。