dsh-run2skill 0.3.0 → 0.4.0

package/README.en.md

@@ -14,7 +14,11 @@ Have you run into any of these situations?
 
 Run2Skill does not let an agent silently create permanent rules for itself. Every draft shows its source, intended scope, and complete content before you decide whether to save or discard it. Only an approved draft is written to DSH's native Skill directory.
 
-> The current stable release is `0.3.0`. It supports DSH Web `0.1.1-rc.2` only.
+> The current stable release is [`0.4.0`](https://www.npmjs.com/package/dsh-run2skill/v/0.4.0). It supports DSH Web `0.1.2-rc.1` only.
+
+`0.4.0` uses the Remote/API Gateway and browser-authentication contracts from DSH `0.1.2-rc.1`, and adapts its Session, Storage/Profile, Settings, and plugin-lifecycle changes. It supports only the retained built-in `standard` preset. Continue using `dsh-run2skill@0.3.1` with the older DSH `0.1.1-rc.2` line.
+
+Low-noise learning status, **Synthesize this experience now**, revision requests that generate a new draft, and bounded preservation of important long-workflow evidence remain available. An immediate request still waits for the agent to stop and for complete facts, then follows the existing lookup, review, and publication safety gates. Internal batch counters are not shown in the settings page.
 
 ## See the complete flow
 
@@ -22,7 +26,8 @@ Run2Skill does not let an agent silently create permanent rules for itself. Ever
 
 1. **Find the draft** — Run2Skill only notifies you when action is required and places the draft under **Settings → Plugins → Run2Skill**.
 2. **Review its evidence and scope** — inspect the rationale, filtered conversation evidence, target scope, and the complete `SKILL.md` that would be written.
-3. **Save only after approval** — successful results appear under Recent activity and remain ordinary native DSH Skills.
+3. **Request a revision if needed** — leave one short instruction and Run2Skill generates a new complete draft; the old version is not published and the new one still needs review.
+4. **Save only after approval** — successful results appear under Recent activity and remain ordinary native DSH Skills.
 
 <details>
 <summary>View the three key screenshots</summary>
@@ -37,13 +42,13 @@ Run2Skill does not let an agent silently create permanent rules for itself. Ever
 
 ## Install
 
-First confirm that you use DSH Web `0.1.1-rc.2`, install Node.js `^22.19.0 || >=24.0.0`, and make sure both `dsh` and `pnpm` are available in your terminal. Then run:
+First confirm that you use DSH Web `0.1.2-rc.1`, install Node.js `^22.19.0 || >=24.0.0`, and make sure both `dsh` and `pnpm` are available in your terminal. Then run:
 
 ```bash
-dsh plugin --profile web add dsh-run2skill@0.3.0
+dsh plugin --profile web add dsh-run2skill@0.4.0
 ```
 
-Restart DSH Web. Open **Settings → Plugins**; the plugin is loaded when the **Run2Skill** tab appears.
+Restart DSH Web. Open **Settings → Plugins**; the plugin is loaded when the **Run2Skill** tab appears.
 
 Run2Skill does not need a separate model key. When it analyzes a Skill draft, it uses the model already selected for the current DSH session. If the session has no available model, learning stops and reports the reason instead of silently switching providers.
 
@@ -57,15 +62,17 @@ Save this workflow as a Skill so it can be reused later.
 
 You can also give an explicit correction, describe a durable constraint, or teach a reusable ordered workflow during ordinary work. You do not need to stop and manually reconstruct a `SKILL.md` file.
 
-Run2Skill performs a lightweight check after a conversation turn. It does not run a model retrospective on every turn; deeper analysis begins only after an explicit learning signal is found.
+After each conversation turn, Run2Skill records only low-cost observations; it does not call a model to review every turn. Batch detection runs at bounded batch boundaries, when the session becomes idle, or when you explicitly request saving or immediate synthesis. Only reusable experience proceeds to Skill lookup and draft generation.
 
 When something needs your attention, DSH shows one native notification. To review a draft:
 
 1. Open **Settings → Plugins → Run2Skill**.
 2. Review the draft, its intended scope, evidence, and complete content.
-3. Approve and save it, discard it, or retry a failed save.
+3. Approve and save it, request a revision, discard it, or retry a failed save.
 4. After a successful save, it is an ordinary native DSH Skill and remains usable even if Run2Skill is later uninstalled.
 
+If a draft is not right, submit one revision request of at most 2,048 UTF-8 bytes. The Host uses the current complete draft to generate a new immutable version, records the parent/child relationship, and invalidates the old approval. You must inspect and approve the new version. This is not a free-form editor and does not bypass lookup, human review, or safe publication.
+
 Drafts can target the current project (`PROJECT`) or the current user (`USER`). The current release writes only to DSH's default Skill storage. If you replace or disable that storage, Run2Skill stops safely instead of guessing a path.
 
 ## What it learns
@@ -130,6 +137,7 @@ Report problems through [GitHub Issues](https://github.com/qkycir-123/dsh-run2sk
 - [Storage and upgrades](docs/storage-and-upgrades.md)
 - [Product requirements](docs/product/prd.md)
 - [Architecture baseline](docs/architecture/baseline.md)
+- [Design document index](docs/design/README.md)
 - [Single-owner design for one Skill-save intent](docs/design/single-owner-skill-save.md)
 - [Contributing](CONTRIBUTING.md)
 - [Maintainer compatibility probes](probes/README.md)

package/README.md

@@ -16,7 +16,11 @@
 
 它不会让 Agent 偷偷给自己立规矩。每份技能草稿都可以先看来源、适用范围和完整内容，然后由你决定确认保存还是放弃草稿。只有确认后，它才会写入 DSH 的原生 Skill 目录。
 
-> 当前稳定版为 `0.3.0`。目前仅支持 DSH Web `0.1.1-rc.2`。
+> 当前稳定版为 [`0.4.0`](https://www.npmjs.com/package/dsh-run2skill/v/0.4.0)。目前仅支持 DSH Web `0.1.2-rc.1`。
+
+`0.4.0` 改用 DSH `0.1.2-rc.1` 的 Remote/API Gateway 与浏览器认证契约，并适配 Session、Storage/Profile、Settings 和插件生命周期变化。它只支持 RC1 保留的内置 `standard` preset；使用旧 DSH `0.1.1-rc.2` 时请继续安装 `dsh-run2skill@0.3.1`。
+
+低噪声整理状态、“立即整理本次经验”、按意见生成新版草稿，以及长工作流关键证据保留继续保留。“立即整理”仍会等待 Agent 停止运行和事实完整，并继续经过查重、审核与发布安全门；设置页不会展示内部批次计数。
 
 ## 看一遍完整流程
 
@@ -24,7 +28,8 @@
 
 1. **发现技能草稿**：Run2Skill 只在有事项需要处理时提醒你，并把草稿放在 **设置 → 插件 → Run2Skill**。
 2. **核对来源与范围**：查看生成理由、经过过滤的对话证据、保存范围以及将要写入的完整 `SKILL.md`。
-3. **确认后才保存**：成功结果会进入“最近活动”；保存下来的内容是普通的 DSH 原生 Skill。
+3. **不满意就要求修改**：写一条简短意见，Run2Skill 会生成新的完整草稿；旧版本不会直接发布，新版本仍需你审核。
+4. **确认后才保存**：成功结果会进入“最近活动”；保存下来的内容是普通的 DSH 原生 Skill。
 
 <details>
 <summary>查看三张关键界面截图</summary>
@@ -39,13 +44,13 @@
 
 ## 安装
 
-先确认你使用 DSH Web `0.1.1-rc.2`，已经安装 Node.js `^22.19.0 || >=24.0.0`，并能在终端运行 `dsh` 和 `pnpm`。然后执行：
+先确认你使用 DSH Web `0.1.2-rc.1`，已经安装 Node.js `^22.19.0 || >=24.0.0`，并能在终端运行 `dsh` 和 `pnpm`。然后执行：
 
 ```bash
-dsh plugin --profile web add dsh-run2skill@0.3.0
+dsh plugin --profile web add dsh-run2skill@0.4.0
 ```
 
-重启 DSH Web。打开 **Settings → Plugins**，看到 **run2skill** 卡片就说明插件已加载。
+重启 DSH Web。打开 **Settings → Plugins**，看到 **run2skill** 卡片就说明插件已加载。
 
 run2skill 不需要单独填写模型密钥。需要分析技能草稿时，它沿用当前 DSH 会话已经选择的模型；如果当前会话没有可用模型，学习会停止并显示原因，不会偷偷换用其他模型。
 
@@ -59,15 +64,17 @@ run2skill 不需要单独填写模型密钥。需要分析技能草稿时，它
 
 你也可以在正常工作中明确纠正做法、说明长期约束，或给出有顺序的可复用流程。不用为了“教它”停下当前任务，也不用自己打开 `SKILL.md` 边回忆边编辑。
 
-run2skill 会在一轮对话完成后做轻量检查。它不是每轮都拉着模型开复盘会；只有命中明确的学习信号后，才会进入后续分析。
+run2skill 会在每轮对话完成后只做低成本记录，不会每轮调用模型复盘。到达有界批次边界、会话进入空闲，或你明确请求保存/立即整理时，才会触发一次批次检测；只有检测到可复用经验，才继续查重和技能草稿生成。
 
 当有需要你处理的事项时，DSH 会显示一条原生通知；平时页面顶部不会常驻 run2skill 状态框。处理技能草稿时：
 
 1. 打开 **Settings → Plugins → run2skill**。
 2. 在待处理列表中查看技能草稿、适用范围和内容差异。
-3. 选择确认并保存、放弃草稿，或在保存失败后重试。
+3. 选择确认并保存、要求修改、放弃草稿，或在保存失败后重试。
 4. 保存成功后，结果就是普通的 DSH 原生 Skill；即使以后卸载 run2skill，它仍然可以被 DSH 使用。
 
+如果草稿不合适，可以先写一条不超过 2048 UTF-8 字节的修改意见。Host 会基于当前完整草稿生成新的不可变版本，保留父子版本关系并让旧批准失效；你必须重新查看并确认新版本。这个入口不是自由编辑器，也不会绕过查重、人工审核或安全发布。
+
 技能草稿可以保存到当前项目（`PROJECT`）或当前用户（`USER`）范围。当前版本只会写入 DSH 默认的 Skill 存储目录；如果你改过 Skill 的存储方式或关闭了默认目录，run2skill 会停止保存，不会猜测写入位置。
 
 ## 它会学什么
@@ -134,6 +141,7 @@ dsh plugin --profile web remove dsh-run2skill
 - [数据存储与升级](docs/storage-and-upgrades.md)
 - [产品需求](docs/product/prd.md)
 - [架构基线](docs/architecture/baseline.md)
+- [设计文档索引](docs/design/README.md)
 - [同一 Skill 保存意图的单一生成所有者设计](docs/design/single-owner-skill-save.md)
 - [贡献指南](CONTRIBUTING.md)
 - [维护者兼容性探针](probes/README.md)