sage-mem 2.0.0 → 2.1.0

package/README.md

@@ -12,7 +12,7 @@
 
 **Cross-session memory for DeepSeek Harness — plain markdown files, no database, no worker.**
 
-**Current release: `2.0.0`** — the npm badge above is the dynamic source of truth. **Contract baseline: `1.0.0`** — the first stable release, whose public commitments, the capability boundaries and the list of things it explicitly cannot do are frozen in the
+**Current release: `2.1.0`** — the npm badge above is the dynamic source of truth. **Contract baseline: `1.0.0`** — the first stable release, whose public commitments, the capability boundaries and the list of things it explicitly cannot do are frozen in the
 [frozen contract](https://github.com/gezi-wen/sage-mem/blob/main/docs/1.0.0-contract.md).
 
 If it is useful to you, a Star is the most direct feedback.
@@ -70,7 +70,7 @@ Most memory schemes take the "SQLite + a long-running worker" route: once memori
 | Feature | Description |
 |---|---|
 | **File-based storage** | One `.md` per memory: frontmatter holds metadata, the body holds content. No database, no hidden format |
-| **Automatic injection** | Every turn automatically scans the memory directory and picks the most relevant few by relevance to inject into context. The model "recalls" on the first turn, without having to go and read files itself |
+| **Automatic injection** | Every new question rescans the memory directory and re-picks the most relevant few for that question, injecting them into context before the model speaks — no file reading needed |
 | **The model can look things up too** | Two retrieval tools are also given to the model (`search_memory` / `read_memory`), so it can go through memories on its own and read the original text by line |
 | **Writes are not overwritten** | While you are editing and the model is changing things at the same time, the later write does not silently clobber the earlier one; the conflict is left as a pending record for you to decide which side to keep |
 | **Zero extra services** | No worker, no SQLite, no port, no long-running process, and no extra API key or cloud service (the only runtime dependency is the ordinary npm library `zod`) |
@@ -116,7 +116,7 @@ Then **open a new session** and try three steps:
 
 1. Tell the model "remember: my cat is called Zhima, and it likes sunbathing" — it writes this into the memory directory by its rules
 2. Open another **new session** and ask "what is my cat called"
-3. It should answer "Zhima" on the first turn — the memory was retrieved and injected automatically by the plugin; the model did not go and read files itself
+3. Its first reply should answer "Zhima" — the memory was retrieved and injected automatically by the plugin; the model did not go and read files itself
 
 <details>
 <summary>Manual install (if you do not want the CLI, or want to install a local development build)</summary>
@@ -164,7 +164,7 @@ The state directory (configuration, ledger, rollback points, conflict queue) def
 
 Every image below is **rendered from the UI code in this repository** (the same CSS, the same component tree; the data is demo data for illustration, not a real memory directory).
 
-Since 1.9.0 the memory-management surface follows the harness language (**Settings → General → Language**); memory content itself stays in whatever language it was written in, and the remaining panels (autodream, archive, starmap, audit) are still Chinese until the next i18n batch.
+Since 1.9.0 the memory-management surface follows the harness language (**Settings → General → Language**); memory content itself stays in whatever language it was written in, 2.1.0 extends it to the **Autodream** (run / settings / records) and **Auto-archive** screens; the star map is the only panel still Chinese until the next i18n batch.
 
 ![File list: one Markdown file per memory, greyed rows are archived](https://raw.githubusercontent.com/gezi-wen/sage-mem/main/docs/images/files-list.png)
 
@@ -415,7 +415,7 @@ The two things are moved **differently**, spelled out:
 | `SAGE_MEM_MAX_BASELINE` | `8` (1–50) | number of `baseline` slots |
 | `SAGE_MEM_STALE_DAYS` | `1` (0–365) | threshold for marking a heading 「保存于 N 天前」(saved N days ago); 0 = mark every one |
 | `SAGE_MEM_TASK_ID` | empty | scope of task checkpoints; empty falls back to the session id |
-| `SAGE_MEM_DEBUG` | off | debug logging; when on, the panel's **工具 ▾ → 注入调试** shows the last 8 injection attempts (read-only, never written to disk) |
+| `SAGE_MEM_DEBUG` | off | debug logging; when on, the panel's **工具 ▾ → 注入调试** shows the last 8 injection attempts (read-only, never written to disk; it also lists any memory kept out of the body by an expired `invalid_at` or an unresolved contradiction, with the reason and the conflict id) |
 | `SAGE_MEM_VALIDITY` | on | master switch for invalidity filtering and contradiction suppression. **Only `0` / `false` / `off` turn it off** (empty or misspelled values count as on); off restores the 1.9.x injection behaviour |
 
 Value semantics: **out-of-range values are clamped to the boundary, illegal values (including pure whitespace) fall back to the default.**

package/README.zh.md

@@ -14,7 +14,7 @@
 
 > File-based cross-session memory for DeepSeek Harness — every memory is a plain markdown file you can open, edit and delete. No database, no worker, no port.
 
-**当前发布版本：`2.0.0`** —— 顶部 npm 徽章是动态权威。**契约基线：`1.0.0`** —— 第一个稳定版，公开承诺、能力边界与「明确做不到」的清单冻结在
+**当前发布版本：`2.1.0`** —— 顶部 npm 徽章是动态权威。**契约基线：`1.0.0`** —— 第一个稳定版，公开承诺、能力边界与「明确做不到」的清单冻结在
 [契约冻结](https://github.com/gezi-wen/sage-mem/blob/main/docs/1.0.0-contract.md)。
 
 如果它对你有用，给个 Star 是最直接的反馈。
@@ -72,7 +72,7 @@ sage-mem 补上这一层，做法是：**把该记住的事写成一张张卡片
 | 特性 | 说明 |
 |---|---|
 | **文件式存储** | 每条记忆一个 `.md`：frontmatter 存元数据，正文存内容。无数据库、无隐藏格式 |
-| **自动注入** | 每轮提问自动扫记忆目录、按相关度挑出最相关的几条注入上下文。模型第一轮就「想起来」，不需要它自己去翻文件 |
+| **自动注入** | 每条新问题都会重新扫一遍记忆目录，按这条问题挑出最相关的几条，在模型开口之前拼进上下文 —— 不用模型自己去翻文件 |
 | **模型也能自己查** | 另给模型两个检索工具（`search_memory` / `read_memory`），它可以主动翻记忆、按行读原文 |
 | **写入不被覆盖** | 你正在编辑、模型同时在改的时候，后写的不会静默盖掉先写的；冲突留成待处理记录，由你决定保留哪边 |
 | **零额外服务** | 无 worker、无 SQLite、无端口、无常驻进程，不需要额外的 API key 或云服务（运行时唯一的依赖是普通 npm 库 `zod`） |
@@ -116,7 +116,7 @@ dsh plugin --profile web list
 
 1. 跟模型说「记住：我的猫叫芝麻，它喜欢晒太阳」—— 它按规则把这条写进记忆目录
 2. 再开一个**新会话**，问「我的猫叫什么」
-3. 第一轮就该答出「芝麻」—— 记忆由插件自动检索并注入，模型没有主动去翻文件
+3. 它的第一个回答就该答出「芝麻」—— 记忆由插件自动检索并注入，模型没有主动去翻文件
 
 <details>
 <summary>手动安装（不想用 CLI，或要装本地开发版本）</summary>
@@ -164,7 +164,7 @@ SAGE_MEM_DIR=/path/to/your/memory
 
 下面每张图都是**从仓库里的界面代码渲染出来的**（同一份 CSS、同一棵组件树；数据是演示用的假数据，不是真实记忆目录）。
 
-1.9.0 起，记忆管理这一块跟随宿主语言（**设置 → 通用 → 语言**）；记忆内容本身保持它被写下时的语言，其余面板（自动做梦、自动归档、记忆星图、体检）仍是中文，等下一批 i18n。
+1.9.0 起，记忆管理这一块跟随宿主语言（**设置 → 通用 → 语言**）；记忆内容本身保持它被写下时的语言，2.1.0 起扩展到**自动做梦**（运行 / 设置 / 记录）与**自动归档**两屏；只剩记忆星图仍是中文，等下一批 i18n。
 
 ![文件列表：每条记忆一个 Markdown 文件，灰底的是已归档](https://raw.githubusercontent.com/gezi-wen/sage-mem/main/docs/images/files-list.png)
 
@@ -415,7 +415,7 @@ sage-mem 给记忆目录的写入加了**版本守卫**：写入前记下当前
 | `SAGE_MEM_MAX_BASELINE` | `8`（1–50） | `baseline` 名额 |
 | `SAGE_MEM_STALE_DAYS` | `1`（0–365） | 标题标「保存于 N 天前」的门槛；0 = 每条都标 |
 | `SAGE_MEM_TASK_ID` | 空 | 任务检查点的作用域；空则回落会话 id |
-| `SAGE_MEM_DEBUG` | 关 | 调试日志；打开后面板「工具 ▾ → 注入调试」显示最近 8 次注入的账（只读、不落盘） |
+| `SAGE_MEM_DEBUG` | 关 | 调试日志；打开后面板「工具 ▾ → 注入调试」显示最近 8 次注入的账（只读、不落盘；同时列出被已失效标注 / 未裁决矛盾挡在正文外的记忆与理由，矛盾还带冲突 id） |
 | `SAGE_MEM_VALIDITY` | 开 | 失效过滤与矛盾抑制的总开关。**只认 `0` / `false` / `off` 为关闭**（空值、拼错都按开启）；关掉后回到 1.9.x 的注入行为 |
 
 取值语义：**越界夹到边界，非法值（含纯空格）回落默认。**