dsh-memory-dba 0.1.2 → 0.1.4

package/CHANGELOG.md

@@ -1,5 +1,27 @@
 # Changelog
 
+## 0.1.4 — 2026-10-26
+
+Documentation-only revision. No runtime source file, API, or behavior changed.
+
+- Corrected an inverted research claim. `0.1.2`/`0.1.3` said the v4 state decoder's
+  no-state loss was better than its true-state loss. The recorded run says the
+  opposite: on dev (1,779 cases) true-state token loss was **1.185**, against
+  **1.575** with no state and **1.260** with a mismatched state. The decoder fails
+  on joint multi-label extraction (all-slot exact 0/1779, content-slot accuracy
+  1.6%), not because the frozen state carries no signal; per-label linear probes
+  on the same pooled features reach AUC 0.98.
+- `README.zh-CN.md` now carries the same corrected numbers.
+
+## 0.1.3 — 2026-10-26
+
+Documentation-only revision. No runtime source file, API, or behavior changed.
+
+- Corrected the release history: `0.1.0` was the first functional release; `0.1.1`
+  only added `repository`/`homepage`/`bugs` metadata.
+- README release section renamed to "Release notes" so it no longer hardcodes the
+  version it documents.
+
 ## 0.1.2 — 2026-10-26
 
 Documentation-only revision. No runtime source file, API, or behavior changed.
@@ -20,18 +42,20 @@ Documentation-only revision. No runtime source file, API, or behavior changed.
   failures without retry; and the default memory directory differing from the old
   Python DBA, which requires an explicit `home` to reuse an existing library.
 - Corrected the research status: state-decoder training on frozen RWKV features was performed (v4, 5,000 steps)
-  but did not meet acceptance (dev all-slot exact 0/1779, no-state loss better than
-  true-state, Not qualified, no final test). It is not described as untrained.
+  but did not meet acceptance (dev all-slot exact 0/1779, Not qualified, no final
+  test). It is not described as untrained. This entry originally also claimed the
+  no-state loss beat the true-state loss; that was wrong and is superseded by 0.1.4.
 
 ## 0.1.1 — 2026-10-26
 
-- Published the file-memory plugin: three-layer store, two-section prompt
-  injection, BM25 with CJK bigrams, optional Ollama/bge-m3 semantic recall, DSH
-  session-event integration, CLI, and tests.
+- Package metadata only: added `repository`, `homepage`, and `bugs` so the npm
+  page links back to the GitHub source. No source file, API, or behavior changed.
 
 ## 0.1.0 — 2026-10-26
 
-- Initial release.
+- First functional release: three-layer store, two-section prompt injection, BM25
+  with CJK bigrams, optional Ollama/bge-m3 semantic recall, DSH session-event
+  integration, CLI, and 40 tests.
 
 ## 0.0.0-stage — 2026-10-26
 

package/README.md

@@ -46,7 +46,7 @@ These are real capabilities of the original Python system, not hypothetical futu
 
 | Research item | Actual state |
 |---|---|
-| Decoding RWKV state into reliable slots or memory codes | State-decoder training experiments were performed on frozen RWKV features, but they did not reach the acceptance standard. The v4 decoder run completed 5,000 steps; on dev, all-slot exact matches were 0/1779, and the final no-state loss was better than the true-state loss. It was judged **Not qualified** and never entered the final test. There is no usable state-to-slot decoder today. |
+| Decoding RWKV state into reliable slots or memory codes | State-decoder training experiments were performed on frozen RWKV features, but they did not reach the acceptance standard. The v4 decoder run completed 5,000 steps; on dev (1,779 cases) all-slot exact matches were **0/1779** and content-slot accuracy was 1.6%. The state itself was not useless: true-state token loss 1.185 beat no-state 1.575 and wrong-state 1.260, and per-label linear probes on the same pooled features reached AUC 0.98 — the information is present, the joint multi-label decode is what fails. It was judged **Not qualified** and never entered the final test. There is no usable state-to-slot decoder today. |
 | Cross-model consumption of state | Cloud models consume text summaries and retrieved text, not RWKV state tensors or dedicated memory codes. The interface is not built. |
 | A genuinely resident service | RWKV runs through a local runner/bridge. Continuity across turns is not the same as an accepted always-on service; no resident deployment has been accepted. |
 
@@ -68,9 +68,9 @@ Read these before relying on the plugin as shared or historical memory.
 - **Failed writes are not retried.** A read-only or full disk still serves readable memory, but a failed turn append is logged (`[memory-dba] session event failed: …`) and the turn is lost; there is no outbox or retry queue in this package.
 - **The default memory directory is not the old Python DBA directory.** On Windows it is `%LOCALAPPDATA%\dsh-memory-dba`; elsewhere `~/.dsh-memory-dba`, unless `home` or `DSH_MEMORY_HOME` says otherwise. To reuse an existing Python DBA memory library, set `home` explicitly (for example `D:/AI/DBA/memory`).
 
-## Release 0.1.2
+## Release notes
 
-Documentation-only revision. No runtime source file or behavior changed in this release; the changes are the scope tables and the limits above, so that the npm page matches what is actually delivered. See `CHANGELOG.md` for the full history.
+`0.1.2` through `0.1.4` are documentation-only revisions. No runtime source file or behavior changed in either release; the changes are the scope tables, the limits above, and the corrected release history, so that the npm page matches what is actually delivered. See `CHANGELOG.md` for the full history.
 
 ## Install
 

package/README.zh-CN.md

@@ -1,10 +1,10 @@
 # dsh-memory-dba：功能范围
 
-[English README](README.md) · 版本 0.1.2
+[English README](README.md) · 版本 0.1.4
 
 本包是 DBA（Dual-Brain Architecture，双脑架构）的**文件记忆与检索插件**，不是完整双脑运行时。安装它不会同时安装 RWKV 小脑、连续状态后端或原 Python DBA 的可靠事件处理链。
 
-0.1.2 是说明文档修订版：明确交付范围和限制，没有新增运行时功能，也没有修复下列尚未实现的能力。
+0.1.2–0.1.4 是说明文档修订版：明确交付范围和限制、修正发布历史与一处写反的研究结论，没有新增运行时功能，也没有修复下列尚未实现的能力。
 
 ## 本 npm 包已实现
 
@@ -32,7 +32,7 @@
 
 ## 整体 DBA 仍在研究、未达验收标准
 
-- **RWKV 状态可靠解码为槽位或记忆码**：做过基于冻结 RWKV 特征的解码器训练实验。v4 完成 5000 步，但验证集全槽精确命中为 0/1779，未通过验收，也未进入最终测试；这不等于 RWKV 主干微调已成功或已有可用状态接口。
+- **RWKV 状态可靠解码为槽位或记忆码**：做过基于冻结 RWKV 特征的解码器训练实验。v4 完成 5000 步，验证集 1779 例里全槽精确命中 0/1779、内容槽准确率 1.6%，未通过验收，也未进入最终测试。但状态本身不是没用：真实状态 token loss 1.185 优于无状态 1.575、错配状态 1.260，同一池化特征上的逐标签线性探针 AUC 达 0.98 —— 信息在，失败的是联合多标签解码。这不等于 RWKV 主干微调已成功或已有可用状态接口。
 - **跨模型状态消费**：云端目前消费文本摘要与检索原文，不是直接接收 RWKV 状态张量或专用记忆码。
 - **经验证的模型常驻服务**：跨轮状态连续与进程/权重始终常驻是两回事，原系统也没有完成常驻部署验收。
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "dsh-memory-dba",
-  "version": "0.1.2",
+  "version": "0.1.4",
   "description": "File-based, git-portable long-term memory for DeepSeek Harness: core/stream/workspace layers, BM25 retrieval with CJK bigrams, two-section prompt injection",
   "license": "MIT",
   "repository": {