stratagate-dsh 0.2.93 → 0.2.94

package/CHANGELOG.md

@@ -1,5 +1,11 @@
 # Changelog
 
+## 0.2.94 - Unreleased
+
+- Simplify the DSH main-agent memory protocol by removing tool-level batch, citation, and memory-merge details while retaining the six Block layers, evidence-gated use, adopted-evidence reinforcement, and Profile consent boundaries.
+- Clarify when to search history outside the visible conversation, Event/Graph responsibilities, automatic memory versus explicit retrieval, evidence sufficiency, and targeted follow-up retrieval without repeating failed searches.
+- Verify the complete approved protocol in assembled system prompts, including session-scoped and activated-memory contexts. Tool descriptions, runtime behavior, and WorkBuddy remain unchanged.
+
 ## 0.2.93 - Unreleased
 
 - Support the complete DeepSeek Harness `0.2.0` version family: all Alpha, Beta, RC, and stable releases (`>=0.2.0-0 <0.2.1-0`), without listing individual prereleases as installation requirements. Preserve the previously supported DSH versions.

package/README.md

@@ -122,7 +122,7 @@ Each fully processed Block contains these views:
 | L4 | Near-verbatim dialogue without internal messages | Remove system messages; only trim outer whitespace and add role labels to user and assistant text; retain names and summaries for recognized tool records |
 | L5 | Source messages and tool records | Verify provenance and specific details |
 
-The model summarizes L0–L2. Fixed rules prune fillers, repeated content, and tool records for L3/L4. Short-term decay advances with subsequent ready Blocks, not elapsed days.
+The model summarizes L0–L2. Fixed rules generate L3/L4: L3 removes standalone fillers and repeated long content, while L4 stays near-verbatim; both compact recognized tool records. Short-term decay advances with subsequent ready Blocks, not elapsed days.
 
 <details>
 <summary>Exact pruning rules, decay formula, and level thresholds</summary>

package/README.zh-CN.md

@@ -123,7 +123,7 @@ DeepSeek Harness 插件默认每 **6 轮**完整对话封存一个 Block，一
 | L4 | 去除内部记录的近原文对话 | 过滤 system 消息；用户和助手正文只裁剪首尾空白并添加角色标签；可识别的工具记录保留名称和结果摘要 |
 | L5 | 原始消息与工具记录 | 查证来源及具体细节 |
 
-L0–L2 由模型概括；L3/L4 按固定规则删减寒暄、重复内容和工具记录，具体规则见下方。短期衰减按后续就绪 Block 的数量推进，不按现实中经过的天数计算。
+L0–L2 由模型概括；L3/L4 由固定规则生成：L3 删除独立寒暄和重复长文本，L4 则尽量保留原话；两者都会精简可识别的工具记录。具体规则见下方。短期衰减按后续就绪 Block 的数量推进，不按现实中经过的天数计算。
 
 <details>
 <summary>具体精简规则、衰减公式与层级阈值</summary>