dsh-super-code 0.3.2 → 0.3.3

package/README.md

@@ -4,66 +4,99 @@
 
 A faster, more efficient coding plugin for DeepSeek Harness. It handles straightforward tasks directly, brings in specialist Agents when useful, and keeps sourced knowledge available for later conversations.
 
-在同一组 SWE-bench Pro hard-100 中，0.3.0 采用的 Batch.3 候选相比官方 minimal，平均回答耗时减少 **48%**、每题总 token 减少 **45%**、模型调用次数减少 **44.5%**，通过率从 **44% 提高到 54%**。[完整结果与限制](docs/EvaluationResults.md)
+在同一组 SWE-bench Pro hard-100 中，0.3.0 的评测候选相比官方 minimal，平均回答耗时减少 **48%**、每题总 token 减少 **45%**、模型调用次数减少 **44.5%**，通过率从 **44% 提高到 54%**。[完整结果与限制](docs/EvaluationResults.md)
 
-On the same SWE-bench Pro hard-100 set, the Batch.3 candidate adopted for 0.3.0 uses **48% less response time**, **45% fewer total tokens**, and **44.5% fewer model calls**, with **54% passing versus 44%** for official minimal. [Full results and limitations](docs/EvaluationResults.md)
+On the same SWE-bench Pro hard-100 set, the evaluation candidate for 0.3.0 uses **48% less response time**, **45% fewer total tokens**, and **44.5% fewer model calls**, with **54% passing versus 44%** for official minimal. [Full results and limitations](docs/EvaluationResults.md)
 
-## 0.3.2 · What's New
+# 1 版本与更新 · Versions and Updates
 
-- **更紧凑的执行树：** 保留圆形节点，顶部操作集中一行；“已收起”和“自动整理”显示名称，所有插件按钮的名称气泡位于上方，历史筛选使用自定义下拉菜单。
-  **Compact Agent tree:** Retains circular nodes and puts actions in one row, with visible Collapsed/Organize labels, above-button name bubbles, and custom history dropdowns.
-- **对话式详情与主题记忆库：** 用户消息、Agent 回复和可展开的真实工具记录分别呈现；顶部用量摘要保持紧凑。记忆可按主题浏览、搜索，并查看同主题条目、来源和版本。
-  **Chat details and topic library:** Separates user messages, Agent replies, and expandable journal tool records beneath a compact usage header. Browse and search memory topics, related entries, sources, and versions.
+为保证版本效果，发布前需要进行大量测试和回归验证，耗时较久，因此更新周期可能较长。
 
-安装、确认重装、归属校验及恢复备份沿用 0.3.1；[本次验证范围](docs/Compatibility.md)单独记录。
+Extensive testing and regression checks are needed to verify each release's effectiveness. This takes time, so release cycles may be longer.
 
-Installation, confirmed reinstallation, ownership checks, and recovery backups retain the 0.3.1 behavior; [this release's validation scope](docs/Compatibility.md) is recorded separately.
+版本号采用 **主版本.效果优化版本.维护版本**，例如 `0.3.3`：
 
-## 0.3.1 · What's New
+Version numbers follow **major.performance-improvement.maintenance**, for example `0.3.3`:
+
+| 位置 / Position | 含义 / Meaning |
+|---|---|
+| 第一位 / First (`0`) | 主版本，仅在大范围重构时调整。 / Major version; changes only for extensive refactoring. |
+| 第二位 / Second (`3`) | 效果优化版本，记录编码效果、效率等方面的优化。 / Performance-improvement version; tracks improvements to coding results, efficiency, and related capabilities. |
+| 第三位 / Third (`3`) | 维护版本，记录问题修复、UI 优化、兼容性适配等更新。 / Maintenance version; tracks bug fixes, UI improvements, compatibility updates, and similar changes. |
+
+## 0.3.3 · What's New
+
+统一执行树与记忆库侧栏，支持直接管理记忆，并改善执行树动画与布局。[更新详情](docs/Changelog.md)
+
+Unifies the Agent tree and memory library in one sidebar, adds direct memory management, and improves tree animation and spacing. [Changelog](docs/Changelog.md)
 
-设置页始终展开，显示插件与当前预设的独立版本，并提示版本不一致或旧预设未记录版本。目录式和 DSH NEXT 等声明式宿主均提供安装、确认重装、改名及恢复备份，默认名称和描述跟随中英文切换。[版本检查与更新](docs/UsageGuide.md#查看预设版本--checking-the-preset-version)
+## 0.3.2 · What's New
+
+美化插件界面，提供更紧凑的执行树、对话式 Agent 详情和按主题组织的记忆库。[更新详情](docs/Changelog.md)
+
+Refreshes the plugin UI with a compact Agent tree, chat-style Agent details, and a topic-based memory library. [Changelog](docs/Changelog.md)
 
-The settings page stays expanded, shows independent plugin and preset versions, and flags mismatched or unrecorded versions. Directory and declarative hosts such as DSH NEXT support installation, confirmed reinstallation, renaming and recovery backups. Default names and descriptions follow Chinese/English language changes. [Version checks and updates](docs/UsageGuide.md#查看预设版本--checking-the-preset-version)
+## 0.3.1 · What's New
 
-0.3.1 已逐版验证 Harness `0.1.5-alpha.1`～`0.2.1-alpha.2` 的 15 个官方 Web/CLI 版本；原生桌面范围和限制见[兼容矩阵](docs/Compatibility.md)。
+完善预设安装与重装，新增版本提示，并让默认名称和描述跟随中英文切换。[更新详情](docs/Changelog.md)
 
-Version 0.3.1 verified 15 official Web/CLI versions from Harness `0.1.5-alpha.1` through `0.2.1-alpha.2`; see the [matrix](docs/Compatibility.md) for native Desktop coverage and limits.
+Improves preset installation and reinstallation, adds version notices, and keeps default names and descriptions in sync with Chinese/English settings. [Changelog](docs/Changelog.md)
 
 ## 0.3.0 · What's New
 
-- **批量工具调用：** 用 Harness 原生 PTC 在一次模型调用中组合多个操作，减少来回；独立读取可以并行，写入、测试和有依赖的操作依次执行，不用额外配置。
-  **Batched tool calls:** Uses Harness-native PTC to compose several operations in one model call. Independent reads can overlap; writes, tests, and dependent operations run in order. No extra setup is needed.
-- **保留记忆与界面：** 延续任务、项目和全局三层记忆、右侧执行树及记忆库；已适配 Harness `0.1.5-alpha.1`～`0.2.1-alpha.1`。具体版本和验收范围见[兼容矩阵](docs/Compatibility.md)。
-  **Memory and interface:** Retains task, project, and global memory, the Agent tree, and the memory library, with adaptations for Harness `0.1.5-alpha.1`–`0.2.1-alpha.1`. See the [verified versions and scope](docs/Compatibility.md).
+支持批量工具调用和并行读取，减少模型往返。[更新详情](docs/Changelog.md)
+
+Adds batched tool calls and parallel reads to reduce model round trips. [Changelog](docs/Changelog.md)
+
+# 2 开始使用 · Get Started
 
-效果数据来自已完成 100 题评分的冻结 Batch.3 候选；整合后的 0.3.0 发布包另做功能回归，没有重新跑这 100 次模型任务。
+请使用[已验证的 Harness 版本](docs/Compatibility.md)，按所用客户端选择安装方式。
 
-Quality results come from the frozen Batch.3 candidate, which has scores for all 100 tasks. The integrated 0.3.0 package receives separate functional regression checks, not a fresh 100-task model run.
+Use a [verified Harness version](docs/Compatibility.md) and choose the installation method for your client.
 
-## 开始使用 · Get Started
+## 2.1 安装 · Install
 
-需要 Node.js 22 或更高版本，以及[已验证的 Harness 版本](docs/Compatibility.md)。
+### 官方桌面版 · Official Desktop
 
-Use Node.js 22 or later and a [verified Harness version](docs/Compatibility.md).
+打开左侧 **插件 → 添加插件**，在“包名或地址”中输入 `dsh-super-code`，点击 **安装**，完成后按提示重新加载或重启。桌面版自带运行环境，无需另外安装 Node.js。
 
-1. **安装：** 在插件市场搜索 `dsh-super-code`，或运行以下命令安装 npm 已发布版。
+Open **Plugins → Add plugin**, enter `dsh-super-code` in “Package name or address”, and click **Install**. Reload or restart if prompted. The desktop app includes its runtime; no separate Node.js installation is needed.
 
-   **Install:** Search for `dsh-super-code` in the plugin marketplace, or install the published npm version:
+### Web / 命令行版 · Web / CLI
 
-   ```bash
-   dsh plugin --profile web add dsh-super-code
-   ```
+需要 Node.js 22 或更高版本。通过 npm 安装 Harness，再添加插件；已有 `dsh` 命令时跳过第一行。
 
-   GitHub Release 中的 0.3.2 安装包可用 `dsh plugin --profile web add ./dsh-super-code-0.3.2.tgz` 安装。
-   To install the 0.3.2 package from GitHub Releases, use `dsh plugin --profile web add ./dsh-super-code-0.3.2.tgz`.
+Requires Node.js 22 or later. Install Harness via npm, then add the plugin. Skip the first line if `dsh` is already installed.
 
-2. **选中预设：** 打开“设置”→“Agent 预设”，选择 `super-code`。
+```bash
+npm install -g @deepseek-ai/dsh
+dsh plugin --profile web add dsh-super-code
+```
 
-   **Select the preset:** Open “Settings” → “Agent Presets” and choose `super-code`.
+<details>
+<summary>使用 Release 安装包（可选） · Install a Release package (optional)</summary>
 
-3. **开始对话：** 新建会话，描述你要完成的编码任务。模型、推理等级、权限和工具沿用 Harness 的设置；子 Agent 默认继承父 Agent 的模型，不用另配模型池。
+从 [GitHub Releases](https://github.com/ArtlexYoung/dsh-super-code/releases) 下载 `.tgz` 包。桌面版在“包名或地址”中填入文件的完整路径；Web 版运行以下命令，将文件名替换为实际下载的版本。
 
-   **Start a conversation:** Open a new session and describe the task. Models, reasoning effort, permissions, and tools come from Harness; child Agents inherit the parent's model by default.
+Download a `.tgz` package from [GitHub Releases](https://github.com/ArtlexYoung/dsh-super-code/releases). On desktop, enter its full path in “Package name or address”. For Web, run the command below with the filename you downloaded.
+
+```bash
+dsh plugin --profile web add ./dsh-super-code-0.3.3.tgz
+```
+
+</details>
+
+## 2.2 选中预设 · Select the Preset
+
+打开 **设置 → Agent 预设**，选择 **Super Code 模式**（默认标识符 `super-code`）。
+
+Open **Settings → Agent Presets** and choose **Super Code** (default identifier: `super-code`).
+
+## 2.3 开始对话 · Start a Conversation
+
+新建会话，描述你要完成的编码任务。模型、推理等级、权限和工具沿用 Harness 的设置；子 Agent 默认继承父 Agent 的模型，不用另配模型池。
+
+Open a new session and describe the task. Models, reasoning effort, permissions, and tools come from Harness; child Agents inherit the parent's model by default.
 
 没看到预设？在“设置”→ **Super Code** 查看状态；旧插件版本的入口在“插件配置”中。[安装与排查](docs/UsageGuide.md)
 
@@ -71,27 +104,33 @@ Can't find the preset? Open “Settings” → **Super Code**. Older plugin vers
 
 [![Super Code 配置入口 · Super Code settings](docs/images/preset-settings-preview.png)](docs/images/preset-settings.png)
 
-右侧执行树显示各 Agent 的状态、用量和缓存率。拖动平移、滚轮缩放；点节点查看详情，不切换主对话。右侧新标签页中的“记忆库”可以查看当前项目和全局偏好。[界面与记忆说明](docs/UsageGuide.md)
+右侧 **Super Code** 页面统一展示执行树与记忆库，默认展开执行区，点击标题切换。执行树显示各 Agent 的状态、用量和缓存率，支持平移、缩放和节点详情；记忆库可查看、新增、编辑和删除当前项目记忆及全局偏好。[界面与记忆说明](docs/UsageGuide.md)
 
-The Agent tree shows status, usage, and cache hit rate. Drag to pan, scroll to zoom, and click a node for details without leaving the main conversation. Open “Memory library” from the sidebar's new-tab page to view project knowledge and global preferences. [Interface and memory guide](docs/UsageGuide.md)
+The **Super Code** sidebar combines the Agent tree and memory library. The tree opens by default; click a section heading to switch. View Agent status, usage, and cache hit rate, pan and zoom, or open node details. Browse, add, edit, and delete project memories and global preferences in the library. [Interface and memory guide](docs/UsageGuide.md)
 
 [![Agent 执行树 · Agent execution tree](docs/images/agent-tree-preview.png)](docs/images/agent-tree.png)
 
-## 效果 · Results
+# 3 效果 · Results
+
+当前版本迭代的效果优化均使用从 SWE-bench 官方 dev 集中筛选出的 **33 道有效困难题**；SWE-bench Pro hard-100 的 100 题用于候选冻结后的效果评测及 bug 排查，不参与效果调优。详见[评测口径与限制](docs/EvaluationResults.md)。
+
+Current iterations are optimized on **33 valid difficult tasks selected from the official SWE-bench dev split**. The 100 SWE-bench Pro hard-100 tasks are used to evaluate frozen candidates and investigate bugs, not for performance tuning. See the [methodology and limitations](docs/EvaluationResults.md).
+
+## 3.1 各版本成绩 · Version Results
 
 同一组 100 题，均完成官方评分；评分环境异常已使用原补丁复核。时间不含官方评分，token 包含缓存输入，并不等于费用。
 
 All five runs received official scores for the same 100 tasks. Grading anomalies were rechecked with the original patches. Time excludes grading; tokens include cache reads and are not a monetary cost estimate.
 
-| 指标 / Metric | 官方 minimal | 0.0.9 | 0.1.2 | 0.2.0 分层记忆 | 0.3.0 Batch.3 |
+| 指标 / Metric | 官方 minimal | 0.0.9 | 0.1.2 | 0.2.0 | 0.3.0 |
 |---|---:|---:|---:|---:|---:|
 | 通过 / Passed | 44/100 | 48/100 | 52/100 | 52/100 | **54/100** |
 | 平均耗时 / Minutes per task | 25.69 | 16.46 | 16.01 | 15.15 | **13.46** |
 | 平均总 token / Tokens per task | 11,578,047 | 9,623,217 | 9,938,176 | 9,299,094 | **6,381,969** |
 | 模型调用/题 / Model calls | 124.85 | 92.78 | 99.78 | 93.83 | **69.29** |
 
-Batch.3 相比 0.2.0 新通过 8 题、回退 6 题，净增 2 题。这是已用于诊断的历史题集，各轮宿主版本也有差异，结果不能单独证明某一项改动的效果。[多维指标、逐题证据与统计口径](docs/EvaluationResults.md)
+[多维指标、逐题证据与统计口径](docs/EvaluationResults.md)
 
-Batch.3 gains eight tasks and regresses on six against 0.2.0, for a net gain of two. This is a historically exposed diagnostic set, and host revisions differ between some runs; the results do not isolate any single change. [Detailed metrics, per-task evidence, and methodology](docs/EvaluationResults.md)
+[Detailed metrics, per-task evidence, and methodology](docs/EvaluationResults.md)
 
 [使用说明 · Usage](docs/UsageGuide.md) · [兼容性 · Compatibility](docs/Compatibility.md) · [版本记录 · Changelog](docs/Changelog.md)