From 3830825500d98ff13ed8008395f8ab5029f3595c Mon Sep 17 00:00:00 2001 From: "jinli.yl" Date: Fri, 16 Oct 2026 12:48:19 +0800 Subject: [PATCH] docs: pin matched-input results links --- docs/en/context_compaction.md | 2 +- docs/zh/context_compaction.md | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/docs/en/context_compaction.md b/docs/en/context_compaction.md index 1f7cc8fd..5dc24662 100644 --- a/docs/en/context_compaction.md +++ b/docs/en/context_compaction.md @@ -119,7 +119,7 @@ latency and total cost alongside token reduction. ReMe does not automatically su ## Compaction strategy comparison -The [benchmark protocol and results](https://github.com/jinliyl/ReMe/blob/feat/decision-model-compaction/benchmark/compaction/RESULTS.md) use one four-row table: Full context, Jev, Summary and Jev + Summary. +The [benchmark protocol and results](https://github.com/jinliyl/ReMe/blob/de6f80bd1a4b3e83a5e694ccbdf944413936561d/benchmark/compaction/RESULTS.md) use one four-row table: Full context, Jev, Summary and Jev + Summary. All compressed methods share a **3,300-token complete input ceiling**, including the original system prompt, task, compressed evidence, evaluation question and message framing. Full context preserves the original history as an explicitly over-budget reference. diff --git a/docs/zh/context_compaction.md b/docs/zh/context_compaction.md index 76e5b847..ccd54e3c 100644 --- a/docs/zh/context_compaction.md +++ b/docs/zh/context_compaction.md @@ -110,7 +110,7 @@ ReMe 不会自动生成摘要或写入长期记忆。 ## 压缩策略对比 -[Benchmark 方案与结果](https://github.com/jinliyl/ReMe/blob/feat/decision-model-compaction/benchmark/compaction/RESULTS.md)统一比较 Full context、Jev、Summary 和 Jev + Summary，结果用一张四行表呈现。 +[Benchmark 方案与结果](https://github.com/jinliyl/ReMe/blob/de6f80bd1a4b3e83a5e694ccbdf944413936561d/benchmark/compaction/RESULTS.md)统一比较 Full context、Jev、Summary 和 Jev + Summary，结果用一张四行表呈现。 三个压缩组使用相同的 **3300-token 完整输入上限**，包含原始 system、任务、压缩内容、评测提示和消息封装； Full context 保留原始历史，作为允许超限的参考组。