dsh-super-code 0.3.3 → 0.3.5

package/README.md

@@ -4,9 +4,9 @@
 
 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 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)
+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 **44.4%**，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 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)
+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 **44.4% fewer model calls**, with **54% passing versus 44%** for official minimal. [Full results and limitations](docs/EvaluationResults.md)
 
 # 1 版本与更新 · Versions and Updates
 
@@ -14,15 +14,27 @@ On the same SWE-bench Pro hard-100 set, the evaluation candidate for 0.3.0 uses
 
 Extensive testing and regression checks are needed to verify each release's effectiveness. This takes time, so release cycles may be longer.
 
-版本号采用 **主版本.效果优化版本.维护版本**，例如 `0.3.3`：
+版本号采用 **主版本.效果优化版本.维护版本**，例如 `0.3.5`：
 
-Version numbers follow **major.performance-improvement.maintenance**, for example `0.3.3`:
+Version numbers follow **major.performance-improvement.maintenance**, for example `0.3.5`:
 
 | 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. |
+| 第三位 / Third (`5`) | 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. |
+
+## 0.3.5 · What's New
+
+适配 Harness `0.2.1-rc.2`，修复 v4 会话日志升级后旧任务记录不可见的问题。[更新详情](docs/Changelog.md)
+
+Supports Harness `0.2.1-rc.2` and restores legacy task records after v4 session-log upgrades. [Changelog](docs/Changelog.md)
+
+## 0.3.4 · What's New
+
+补充官方预设评测结果，新增致谢表格与详细来源说明。[更新详情](docs/Changelog.md)
+
+Adds official preset evaluation results, an acknowledgements table, and detailed source attribution. [Changelog](docs/Changelog.md)
 
 ## 0.3.3 · What's New
 
@@ -50,17 +62,17 @@ Adds batched tool calls and parallel reads to reduce model round trips. [Changel
 
 # 2 开始使用 · Get Started
 
-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。
+支持 Harness `0.1.5-alpha.1` 至 `0.2.1-rc.2`，按所用客户端选择安装方式；[各版本与客户端的验证范围](docs/Compatibility.md)。
 
-Use a [verified Harness version](docs/Compatibility.md) and choose the installation method for your client.
+Supports Harness `0.1.5-alpha.1` through `0.2.1-rc.2`. Choose the installation method for your client; see [validation coverage by version and client](docs/Compatibility.md).
 
 ## 2.1 安装 · Install
 
 ### 官方桌面版 · Official Desktop
 
-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。
+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**。新版安装完成后点击 **立即启用**；其他版本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。
 
-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.
+Open **Plugins → Add plugin**, enter `dsh-super-code` in “Package name or address”, and click **Install**. On newer hosts, click **Enable now** when installation finishes; on other versions, reload or restart if prompted. The desktop app includes its runtime; no separate Node.js installation is needed.
 
 ### Web / 命令行版 · Web / CLI
 
@@ -81,7 +93,7 @@ dsh plugin --profile web add dsh-super-code
 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
+dsh plugin --profile web add ./dsh-super-code-0.3.5.tgz
 ```
 
 </details>
@@ -118,19 +130,72 @@ Current iterations are optimized on **33 valid difficult tasks selected from the
 
 ## 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。
+五组均完成同一批 100 题，使用 `high` 思考等级；评分环境异常已用原补丁复核。0.2.0 和 0.3.0 对应已评测的候选，耗时保留历史原始作答口径。
 
-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.
+All five runs completed the same 100 tasks with `high` reasoning. Grading anomalies were rechecked with the original patches. Versions 0.2.0 and 0.3.0 refer to evaluated candidates; times retain the historical response-time convention.
 
-| 指标 / Metric | 官方 minimal | 0.0.9 | 0.1.2 | 0.2.0 | 0.3.0 |
+| 指标 / Metric | 官方 minimal + high | 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** |
+| 平均耗时（历史）/ Original minutes per task | 25.685 | 16.458 | 16.011 | 15.148 | **13.461** |
+| 平均总 token / Total tokens per task | 11,578,046.900 | 9,623,216.520 | 9,938,176.210 | 9,299,093.840 | **6,381,968.850** |
+| 缓存输入 token/题 / Cached input | 11,404,101.120 | 9,461,981.440 | 9,775,799.040 | 9,142,005.760 | 6,231,823.360 |
+| 模型调用/题 / Model calls | 124.660 | 92.780 | 99.780 | 93.830 | **69.290** |
+
+## 3.2 官方预设成绩 · Official Preset Results
+
+截至 **2026-10-15 08:38（UTC+8）**，下表五组均已完成同一批 100 题。极简 + high 的净耗时和调用次数已按原始会话核算。
+
+As of **October 15, 2026, 08:38 (UTC+8)**, all five runs below have completed the same 100 tasks. Minimal + high's net time and call counts have been audited against the original sessions.
+
+| 指标 / Metric | 极简 minimal + high | 极简 minimal + max | 标准 standard + high | PTC + high | 创造 creative + high |
+|---|---:|---:|---:|---:| ---: |
+| 有效进度 / Valid scores | 100/100 | 100/100 | 100/100 | 100/100 | 100/100 |
+| 通过/有效 / Passed / valid | 44/100 | 48/100 | 49/100 | 44/100 | 46/100 |
+| 原始分钟/题 / Original minutes | 25.685 | 32.529 | 20.683 | 17.302 | 19.856 |
+| 净分钟/题 / Net minutes | 25.122 | 32.009 | 18.826 | 15.122 | 18.714 |
+| 模型调用/题 / Model calls | 124.660 | 138.920 | 92.370 | 71.160 | 93.600 |
+| 总 token/题 / Total tokens | 11,578,046.900 | 14,966,097.260 | 8,854,513.910 | 6,238,434.510 | 9,292,949.400 |
+| 缓存输入 token/题 / Cached input | 11,404,101.120 | 14,770,140.160 | 8,713,578.230 | 6,099,266.510 | 9,145,025.240 |
+| 非缓存输入 token/题 / Uncached input | 73,068.830 | 79,357.380 | 58,114.810 | 61,668.140 | 60,262.050 |
+| 输出 token/题 / Output | 100,876.950 | 116,599.720 | 82,820.870 | 77,499.860 | 87,662.110 |
+| 缺少用量的请求 / Requests without usage | 3 | 11 | 4 | 5 | 2 |
+
+标准 + max 已暂停（2 个有效结果，0 题通过），暂不纳入完整 100 题比较。
+
+Standard + max is paused, with 2 valid results and 0 passes, and is excluded from the completed 100-task comparison.
+
+创造保留官方预设与工具定义；评测隔离禁止 `cordis_run` 在宿主上执行动态代码，只读检查仍可使用。
+
+Creative retains the official preset and tool definitions. Evaluation isolation blocks host-side dynamic execution through `cordis_run`; read-only inspection remains available.
+
+净耗时扣除最终有效作答中的失败请求和重试等待；两种耗时均不含官方评分。调用次数排除已记录的失败请求。总 token = 缓存输入 + 非缓存输入 + 输出，输出含思考 token。未返回的用量不估算，表中数字不等于完整账单。历史宿主版本也有差异。
+
+Net time excludes failed requests and retry waits within the final valid answer; neither time measure includes grading. Call counts exclude logged failed requests. Total tokens = cached input + uncached input + output, including reasoning. Missing usage is not estimated, so these figures are not a complete bill. Historical Harness revisions also differ.
 
 [多维指标、逐题证据与统计口径](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)
+
+# 4 致谢 · Acknowledgements
+
+本项目认可 [LINUX DO](https://linux.do) 社区。
+
+This project recognizes the [LINUX DO](https://linux.do) community.
+
+感谢以下项目与资料。具体贡献、借鉴范围和许可证说明见[详细致谢文档](docs/Acknowledgements.md)。
+
+Thanks to the projects and resources below. See the [detailed acknowledgements](docs/Acknowledgements.md) for contributions, design references, and license notes.
+
+| 项目 / Reference | 类型与许可证 / Type and license | 贡献与借鉴 / Contribution and influence |
+| --- | --- | --- |
+| [DeepSeek Harness](https://github.com/deepseek-ai/deepseek-harness) | 宿主 / Harness，MIT | Agent、会话、工具、PTC、Skill 与 Web / 桌面扩展接口 / Agents, sessions, tools, PTC, Skills, Web and desktop APIs |
+| [ZCode](https://github.com/zai-org/ZCode) | UI 设计参考 / UI reference，Apache-2.0 | 紧凑布局、视觉层级、设置分组与交互状态 / Compact layouts, hierarchy, settings groups, interaction states |
+| [Agent Skills](https://agentskills.io/specification) | 开放规范 / Open specification，Apache-2.0 | SKILL.md、元数据、参考目录与按需加载 / SKILL.md, metadata, resource directories, progressive disclosure |
+| [Apple Human Interface Guidelines](https://developer.apple.com/design/human-interface-guidelines) | 设计指南，官方文档条款 / Design guidance, documentation terms | 前端 Skill 的布局、操作负担与反馈原则 / Layout, ergonomic controls, feedback guidance for the frontend Skill |
+| [W3C WCAG 2.2](https://www.w3.org/TR/WCAG22/) | Web 无障碍标准，W3C 文档条款 / Accessibility standard, W3C document terms | 操作目标尺寸、间距与浏览器验证 / Target size, spacing, browser validation |
+| [SWE-bench](https://github.com/SWE-bench/SWE-bench) | 评测代码 MIT；数据另见条款 / MIT code; separate data terms | dev 集有效困难 33 题的来源与评分基础 / Source and grading foundation for the 33 valid difficult dev tasks |
+| [SWE-bench Pro](https://github.com/scaleapi/SWE-bench_Pro-os) | 评测代码 MIT；数据另见条款 / MIT code; separate data terms | 冻结候选的 hard-100 评测与 bug 排查 / Frozen-candidate hard-100 evaluation and bug investigation |
+| [js-yaml](https://github.com/nodeca/js-yaml) / [Zod](https://github.com/colinhacks/zod) | 运行依赖 / Runtime dependencies，MIT | YAML 解析与数据校验 / YAML parsing and data validation |

package/client/index.js

@@ -1057,7 +1057,7 @@ function detailRecord(entry, t = key => zh[key] || key) {
   }
   if (event.type === 'tool/result') {
     const blocks = (data.message?.content || []).filter(block => block.type === 'tool-result')
-    // Older journals store a direct tool message; newer ones nest its content.
+    // Harness journals use both direct tool messages (v4) and nested results.
     const direct = data.message?.role === 'tool'
     if (!blocks.length && !direct) return { kind: 'skip' }
     const failed = direct ? data.message.isError : blocks.some(block => block.isError)

package/cordis.patch.yml

@@ -17,7 +17,7 @@
           - id: super-code
             name: dsh-super-code/super-code
             config:
-              presetVersion: 0.3.3
+              presetVersion: 0.3.5
               presetInstallation: bundle:dsh-super-code
           - id: compaction
             name: cordis:group

package/docs/Acknowledgements.md

@@ -0,0 +1,105 @@
+# 致谢与借鉴 · Acknowledgements and Design References
+
+感谢为 Super Code 提供运行基础、设计启发、开放规范和评测资源的项目与维护者。本文展开 [README 致谢表格](../README.md#4-致谢--acknowledgements)中的具体贡献，范围为当前 `0.3.4` 主干及其已有研究记录。
+
+We thank the projects and maintainers who provide Super Code's runtime foundation, design references, open specifications, and evaluation resources. This document expands the [README acknowledgements](../README.md#4-致谢--acknowledgements), covering the current `0.3.4` main branch and its recorded design studies.
+
+## DeepSeek Harness
+
+**[项目与源码](https://github.com/deepseek-ai/deepseek-harness) · [MIT 许可证](https://github.com/deepseek-ai/deepseek-harness/blob/master/LICENSE)**
+
+DeepSeek Harness 是本插件的运行基础。Super Code 复用宿主的 Agent、模型路由、会话、工具、权限、取消、持久化、子 Agent 和用量记录；批量调用与独立读取通过宿主原生 PTC 调度。预设组合沿用官方的 compaction、文件、搜索、终端、网页、子 Agent 与 Skill 插件。
+
+DeepSeek Harness is the runtime foundation. Super Code uses its Agents, model routing, sessions, tools, permissions, cancellation, persistence, subagents, and usage records. Native PTC schedules batched calls and independent reads. Preset compositions use the official compaction, file, search, shell, Web, subagent, and Skill plugins.
+
+Web 与桌面界面依托 Harness 的 React、主题变量、Remote、设置页、侧栏和会话投影接口。对话式 Agent 详情也参考宿主的消息与工具调用呈现。Cordis 的插件生命周期和组合机制、Schemastery 的配置机制同样来自宿主提供的基础设施。
+
+The Web and desktop interfaces use Harness-provided React, theme variables, Remotes, settings pages, sidebars, and session projections. Chat-style Agent details also draw on its message and tool-call presentation. Cordis supplies plugin lifecycles and composition, while Schemastery supplies configuration facilities through the host.
+
+实现对应：[预设组合](../presets/super-code/agent.cordis.yml)、[声明式预设](../cordis.patch.yml)、[宿主接入](https://github.com/ArtlexYoung/dsh-super-code/blob/main/src/dsh/index.ts)、[客户端](../client/index.js)。
+
+Implementation: [preset composition](../presets/super-code/agent.cordis.yml), [declarative preset](../cordis.patch.yml), [host integration](https://github.com/ArtlexYoung/dsh-super-code/blob/main/src/dsh/index.ts), and [client](../client/index.js).
+
+## ZCode
+
+**[项目与源码](https://github.com/zai-org/ZCode) · [Apache-2.0 许可证](https://github.com/zai-org/ZCode/blob/main/LICENSE)**
+
+0.3.2 界面设计阶段研究了 ZCode 的 [DESIGN.md](https://github.com/zai-org/ZCode/blob/main/DESIGN.md)、语义主题与字号、Button / Input、设置资源分组、分段切换、搜索框、确认对话框和 WorkflowAgentPill。感谢这些可供阅读的设计与组件实现，它们帮助梳理紧凑布局、清晰层级、分组操作和交互状态。
+
+During the 0.3.2 UI design work, we studied ZCode's [DESIGN.md](https://github.com/zai-org/ZCode/blob/main/DESIGN.md), semantic themes and typography, Button / Input components, settings resource groups, segmented tabs, search fields, confirmation dialogs, and WorkflowAgentPill. These design documents and component implementations informed compact layouts, clear hierarchy, grouped actions, and interaction states.
+
+Super Code 的界面接入仍采用 Harness 的公开接口与主题变量。ZCode 在这里是设计参考，没有作为插件依赖引入；执行树保留 Super Code 的圆形节点与运行反馈。
+
+Super Code implements its interface through Harness's public APIs and theme variables. ZCode is a design reference rather than a package dependency; the execution tree keeps Super Code's circular nodes and running feedback.
+
+## Agent Skills
+
+**[格式规范](https://agentskills.io/specification) · [规范仓库与许可证](https://github.com/agentskills/agentskills)**
+
+内嵌前端 Skill 采用 Agent Skills 的目录格式：SKILL.md、YAML 元数据和 references/ 资源目录。宿主先提供名称与短描述，匹配任务后再加载正文和相关参考文件。感谢这套开放约定，使指导内容可以保持简短入口、按需展开，并与项目和用户自己的 Skill 共存。
+
+The bundled frontend Skill follows Agent Skills conventions: SKILL.md, YAML metadata, and a references/ resource directory. The host exposes a name and short description first, then loads the body and relevant resources when needed. This open format supports a short entry point, progressive disclosure, and coexistence with project and user Skills.
+
+实现对应：[super-code-frontend](../presets/super-code/skills/super-code-frontend/SKILL.md)。格式与内容加载复用 Harness 的原生 Skill 能力。
+
+Implementation: [super-code-frontend](../presets/super-code/skills/super-code-frontend/SKILL.md). Parsing and content loading use Harness's native Skill facilities.
+
+## 前端设计与无障碍资料 · Frontend Design and Accessibility
+
+### Apple Human Interface Guidelines
+
+**[布局](https://developer.apple.com/design/human-interface-guidelines/layout) · [无障碍](https://developer.apple.com/design/human-interface-guidelines/accessibility) · [按钮](https://developer.apple.com/design/human-interface-guidelines/buttons) · [反馈](https://developer.apple.com/design/human-interface-guidelines/feedback)**
+
+前端 Skill 的补充研究阅读了上述官方指南，采纳对齐表达关系、布局适应容器与字体、控制尺寸与间隔降低操作负担、交互可预测、反馈就近且适度等原则。这些原则被整理进视觉设计、交互状态和浏览器验证三份按需参考，感谢指南对具体交互问题的细致说明。
+
+The frontend Skill study used these official guides for alignment, layouts that adapt to containers and typography, control size and spacing, predictable interaction, and timely, proportionate feedback. These principles inform the Skill's visual-design, interaction-state, and browser-validation references.
+
+采纳范围是可迁移的交互原则；产品仍沿用自己的视觉语言。原生平台尺寸单位不直接换成 Web 的 CSS pixel，材质、字体和图标也不作为统一模板。资料适用条款见 [Apple Developer 条款](https://developer.apple.com/support/terms/)。
+
+The reference concerns transferable interaction principles, applied within each product's visual language. Native platform units are not treated as CSS pixels, and platform materials, typography, and icons are not prescribed as a template. See [Apple Developer terms](https://developer.apple.com/support/terms/) for applicable documentation terms.
+
+### W3C WCAG 2.2
+
+**[WCAG 2.2](https://www.w3.org/TR/WCAG22/) · [2.5.8 Target Size (Minimum) 说明](https://www.w3.org/WAI/WCAG22/Understanding/target-size-minimum.html)**
+
+感谢 W3C Web Accessibility Initiative 对操作目标尺寸、间距和例外条件的公开说明。前端 Skill 使用 WCAG 2.2 AA 2.5.8 的 24 × 24 CSS pixel 尺寸及间距等例外作为 Web 检查依据，并要求通过实际命中、键盘操作和内容验证检查可用性。数字检查通过不等于整个界面已满足无障碍要求。
+
+We thank the W3C Web Accessibility Initiative for its target-size, spacing, and exception guidance. The frontend Skill uses WCAG 2.2 AA 2.5.8's 24 × 24 CSS pixel criterion and its exceptions when checking Web controls, alongside real hit-area, keyboard, and content checks. Passing numeric checks does not establish accessibility compliance for the whole interface.
+
+实现对应：[交互状态参考](../presets/super-code/skills/super-code-frontend/references/interaction-states.md)、[浏览器验证参考](../presets/super-code/skills/super-code-frontend/references/browser-validation.md)。版权与使用条件见各 W3C 文档随附声明。
+
+Implementation: [interaction-state guidance](../presets/super-code/skills/super-code-frontend/references/interaction-states.md) and [browser-validation guidance](../presets/super-code/skills/super-code-frontend/references/browser-validation.md). Copyright and usage conditions are recorded in the respective W3C documents.
+
+## 评测项目 · Evaluation Projects
+
+### SWE-bench
+
+**[项目与评分工具](https://github.com/SWE-bench/SWE-bench) · [数据集](https://huggingface.co/datasets/princeton-nlp/SWE-bench) · [代码许可证](https://github.com/SWE-bench/SWE-bench/blob/main/LICENSE)**
+
+感谢 SWE-bench 提供真实软件工程任务、任务环境和可复现的评分基础。当前版本迭代使用从官方 dev 集中筛选并验证有效的 33 道困难题进行效果优化与开发验证。这 33 题是本项目的筛选集合。
+
+We thank SWE-bench for real software-engineering tasks, task environments, and reproducible grading infrastructure. Current iterations use 33 valid difficult tasks selected from the official dev split for performance improvement and development checks. This is a project-selected subset.
+
+### SWE-bench Pro
+
+**[项目与评分工具](https://github.com/scaleapi/SWE-bench_Pro-os) · [数据集](https://huggingface.co/datasets/ScaleAI/SWE-bench_Pro) · [代码许可证](https://github.com/scaleapi/SWE-bench_Pro-os/blob/main/LICENSE)**
+
+感谢 Scale AI 与 SWE-bench Pro 的维护者提供长流程软件工程任务及评分工具。本项目固定的 hard-100 用于候选冻结后的效果评测和 bug 排查，不参与效果调优；“hard-100”是本项目的集合名称，不代表官方认定的最难 100 题。
+
+We thank Scale AI and the SWE-bench Pro maintainers for long-horizon software-engineering tasks and grading tools. The project's frozen hard-100 set is used to evaluate frozen candidates and investigate bugs, not for performance tuning. “hard-100” is this project's selection name, rather than an official hardest-100 designation.
+
+评测口径、限制和逐题证据见[评测文档](EvaluationResults.md)。两项评测项目的代码许可证均为 MIT；数据集、被测仓库、镜像与其他资产保留各自条款，代码许可证不统一覆盖这些内容。
+
+See the [evaluation report](EvaluationResults.md) for methodology, limitations, and per-task evidence. Both evaluation code repositories use MIT licenses. Datasets, tested repositories, images, and other assets retain their own terms, which are not replaced by the evaluation code licenses.
+
+## 运行依赖 · Runtime Dependencies
+
+感谢 [js-yaml](https://github.com/nodeca/js-yaml) 与 [Zod](https://github.com/colinhacks/zod) 的维护者。前者提供 YAML 解析，后者提供数据结构与输入校验；两者均以 MIT 许可证发布，是本插件的直接运行依赖。完整直接依赖及宿主 peer dependencies 见 [package.json](../package.json)，版本锁定见 [package-lock.json](https://github.com/ArtlexYoung/dsh-super-code/blob/main/package-lock.json)。
+
+We thank the maintainers of [js-yaml](https://github.com/nodeca/js-yaml) and [Zod](https://github.com/colinhacks/zod). They provide YAML parsing and schema/input validation, respectively. Both are direct runtime dependencies under MIT licenses. See [package.json](../package.json) for direct and host peer dependencies, and [package-lock.json](https://github.com/ArtlexYoung/dsh-super-code/blob/main/package-lock.json) for locked versions.
+
+## 版权与许可证 · Copyright and Licenses
+
+Super Code 使用 [Apache License 2.0](../LICENSE)。上述项目、规范、设计资料和数据保留各自版权、许可证或文档条款；具体内容以对应上游的 LICENSE、NOTICE、数据说明和版权声明为准。本页记录贡献与借鉴范围，设计参考本身不表示运行依赖、上游背书或功能等价。
+
+Super Code uses the [Apache License 2.0](../LICENSE). Referenced projects, specifications, design resources, and datasets retain their own copyrights, licenses, or documentation terms, as stated by their upstream LICENSE, NOTICE, dataset documentation, and copyright notices. This page records contributions and design influence; a design reference does not imply a runtime dependency, upstream endorsement, or feature equivalence.

package/docs/Changelog.md

@@ -1,5 +1,11 @@
 # 版本记录 · Changelog
 
+- **0.3.5 · 2026-10-18**：适配 Harness `0.2.1-rc.2`，修复 v4 日志迁移后旧任务记录不可见的问题，保留 `0.1.5-alpha.1` 起的兼容性，并补齐官方桌面安装说明。[验证范围](Compatibility.md)
+  **0.3.5 · 2026-10-18**: Supports Harness `0.2.1-rc.2`, restores legacy task records after v4 log migration, retains support from `0.1.5-alpha.1`, and clarifies official Desktop installation. [Validation coverage](Compatibility.md)
+
+- **0.3.4 · 2026-10-15**：补充官方预设在同一批 100 题上的成绩、用量与耗时核算说明；新增 README 致谢表格和[详细致谢文档](Acknowledgements.md)，说明宿主、界面设计、Skill、无障碍资料、评测项目与运行依赖的贡献和借鉴范围，并将文档纳入 npm 包。
+  **0.3.4 · 2026-10-15**: Adds official preset results on the same 100 tasks, with usage and timing methodology. Adds a README acknowledgements table and [detailed acknowledgements](Acknowledgements.md) covering the host, UI design, Skills, accessibility resources, evaluation projects, and runtime dependencies; includes the document in the npm package.
+
 - **0.3.3 · 2026-10-14**：执行树与记忆库合并为单个 Super Code 侧栏，默认展开执行区，两区互斥且始终保留一个展开；切换后保留树状态、筛选、搜索、阅读位置与草稿，记忆记录同页定位。记忆支持新增、编辑、取消、保存和确认删除，手动条目标明来源，只保留当前内容，失败保留输入并防止并发覆盖。保留圆形节点，增强运行环动画，修复节点光环、文字与连线重叠。内嵌按需加载的前端 Skill，覆盖布局对齐、操作舒适度、响应式、交互状态和浏览器验证；旧预设需要确认重装。整理双语安装、评测用途、版本规则及简短更新说明；[验证范围](Compatibility.md)。
   **0.3.3 · 2026-10-14**: Combines the Agent tree and memory library in one Super Code sidebar, with the tree open by default and exactly one section expanded. Switching preserves tree state, filters, search, reading position, and drafts; memory activity links open in the same page. Adds memory creation, editing, cancellation, saving, and confirmed deletion. Manual entries are labeled; only current content is stored, failed writes preserve input, and concurrent changes are protected. Retains circular nodes, makes running animation clearer, and fixes halo, label, and connector overlap. Bundles an on-demand frontend Skill for alignment, comfortable controls, responsive layout, interaction states, and browser validation; existing presets require confirmed reinstallation. Clarifies bilingual installation, evaluation methodology, version rules, and concise update notes; [validation scope](Compatibility.md).
 

package/docs/Compatibility.md

@@ -1,5 +1,59 @@
 # 宿主兼容性 · Host Compatibility
 
+## 0.3.5 · Harness 0.2.1-rc.2 · 2026-10-18
+
+兼容范围扩展至 `0.2.1-rc.2`，最低保持 `0.1.5-alpha.1`。本次基于主干 0.3.4，逐版固定并审计宿主依赖，在独立 profile 中真实安装和运行。现有 peer 依赖范围已覆盖这些预发布版本；补充 v4 日志迁移检查后，修复旧插件来源记录的识别及投影缓存失效，未增加依赖，发布版本为 0.3.5。
+
+Compatibility extends through `0.2.1-rc.2`, with the minimum remaining `0.1.5-alpha.1`. Based on main at plugin version 0.3.4, candidates were installed and run in isolated profiles, with each host's dependency graph pinned and audited. Existing peer ranges already cover these prereleases. Additional v4 migration checks identified and fixed legacy plugin-source recognition and projection-cache invalidation without adding dependencies. The release version is 0.3.5.
+
+| Harness | Web/CLI 与真实浏览器 / Web/CLI and real browser | 原生 Skill 加载 / Native Skill loading |
+|---|---|---|
+| `0.2.1-alpha.3` | 通过 / Pass | 组合与持久化 profile 均通过 / Bundle and persisted profile pass |
+| `0.2.1-alpha.4` | 通过 / Pass | 组合与持久化 profile 均通过 / Bundle and persisted profile pass |
+| `0.2.1-alpha.5` | 通过 / Pass | 组合与持久化 profile 均通过 / Bundle and persisted profile pass |
+| `0.2.1-rc.1` | 通过 / Pass | 组合与持久化 profile 均通过 / Bundle and persisted profile pass |
+| `0.2.1-rc.2` | 通过 / Pass | 组合与持久化 profile 均通过 / Bundle and persisted profile pass |
+
+五版均验证原生 PTC、主/子 Agent、任务记忆、项目/全局记忆与归属、跨工作区隔离及冷重启后无需恢复会话的历史读取。真实浏览器覆盖执行树运行/完成动画、节点间距、减弱动态效果、320/400/560px 与缩放、互斥侧栏及状态恢复、记忆新增/编辑/取消/保存/删除、详情页记忆定位、中英文和明暗主题切换。十条 Skill 路径覆盖摘要目录、按需正文与三份参考文件读取、用户/项目同名覆盖。
+
+All five passed native PTC, main/child Agents, task memory, project/global memory and attribution, workspace isolation, and historical reads after a cold restart without resuming the session. Real-browser checks cover running/completed tree animation, node spacing, reduced motion, 320/400/560px widths and zoom, exclusive sidebar sections and retained state, memory creation/editing/cancellation/saving/deletion, memory links from Agent details, and Chinese/English and light/dark switching. Ten Skill paths cover summary catalogs, on-demand content and three reference reads, and user/project overrides.
+
+最低版本 `0.1.5-alpha.1` 另通过同一候选包的目录预设安装、主/子 Agent、PTC、记忆归属/隔离/重启和真实浏览器回归。171 项测试、类型检查、构建、客户端语法检查通过。
+
+The minimum `0.1.5-alpha.1` also passed directory-preset installation, main/child Agents, PTC, memory attribution/isolation/restart, and real-browser regression with the same candidate. All 171 tests, type checking, build, and client syntax checks passed.
+
+官方 macOS arm64 Desktop `0.2.1-rc.2` 从[官方下载地址](https://download.deepseek.com/dsh-desk/bin/mac-arm64/deepseek-harness-0.2.1-rc.2-mac-arm64.zip)获取，并按官方更新源校验 SHA-512。在独立应用身份、DSH_HOME 和 userData 中，通过原生插件页安装并点击“立即启用”；设置页验证未安装预设的安装、重装确认/取消、从清单移除、按新标识符和中文名称重装、旧预设移除与恢复备份。真实原生主/子 Agent 的 PTC 和记忆流程、执行树动画、统一侧栏、记忆维护及中英文/明暗切换通过，保留截图；冷启动后确认改名预设、自定义名称与项目/全局记忆保留，历史子会话无需恢复即可读取记忆。正式应用和日常配置未修改。
+
+Official macOS arm64 Desktop `0.2.1-rc.2` was obtained from the [official download](https://download.deepseek.com/dsh-desk/bin/mac-arm64/deepseek-harness-0.2.1-rc.2-mac-arm64.zip) and SHA-512 verified against its update feed. In an isolated app identity, DSH_HOME, and userData, the native plugin page installed and enabled the plugin. Settings checks cover missing-preset installation, reinstall confirmation/cancellation, removing confirmation rows, reinstallation with a new identifier and Chinese name, removal of the old preset, and recovery backups. Real native main/child PTC and memory flows, tree animation, unified sections, memory maintenance, and Chinese/English and light/dark switching passed with screenshots. A cold start preserved the renamed preset, custom name, and project/global memory, with historical child memory readable without resuming the session. The official app and daily configuration were not changed.
+
+截至本次检查，官方 npm `latest` 为 `0.2.0-rc.2`、`alpha` 为 `0.2.1-alpha.5`、`next` 为 `0.2.1-rc.2`；桌面 nightly 同为 `0.2.1-rc.2`。[官方发布说明](https://github.com/deepseek-ai/deepseek-harness/releases/tag/dsh-v0.2.1-rc.2)。本次模型响应由本地确定性程序提供，没有调用外部模型、没有新增 SWE-bench 成绩，也不代表 Windows、macOS x64 或其他新增版本的原生桌面已复验；其他版本保留以下历史记录。
+
+At this check, official npm tags point to `latest: 0.2.0-rc.2`, `alpha: 0.2.1-alpha.5`, and `next: 0.2.1-rc.2`; Desktop nightly is also `0.2.1-rc.2`. [Official release notes](https://github.com/deepseek-ai/deepseek-harness/releases/tag/dsh-v0.2.1-rc.2). A local deterministic fixture supplied model responses, without external model calls or new SWE-bench scores. This does not establish native Desktop revalidation on Windows, macOS x64, or the other newly covered versions; earlier records remain below.
+
+### v4 会话日志补充验证 · 2026-10-18
+
+物理日志解压、格式迁移、分页与游标由 Harness 的 Session 和官方 journal API 处理；插件不直接解析用户的日志文件。v4 会把旧的 `{kind: "plugin", plugin: "…"}` 来源迁移为 `{kind: "plugin:…"}`。原读取器会跳过其中的任务记录，导致升级后的任务状态、历史与归档不可见。现已识别新旧包名对应的精确来源，同时保留原有直接来源和旧包装形式；任务投影版本由 1 提升到 2，使此前遗漏记录的缓存重新回放。无需为此依赖实验性的 plugin-record API，仍兼容旧宿主。
+
+Harness Session and official journal APIs own physical decompression, migration, pagination, and cursors; the plugin does not parse users' log files directly. V4 migrates `{kind: "plugin", plugin: "…"}` to `{kind: "plugin:…"}`. The previous reader skipped these task records, hiding task state, history, and archives after an upgrade. It now recognizes the exact current and legacy package sources while preserving direct sources and old wrappers. The task projection version increases from 1 to 2 to replay caches that previously missed those records. This does not require the experimental plugin-record API or remove older-host support.
+
+使用官方 rc.2 格式迁移器与真实 v3 会话（含历史子会话事实）验证直接来源、新包名旧包装、旧包名旧包装三条路径；对照原生 v4 日志，核对任务状态、11 对工具证据、9 条记忆使用记录、按模型用量和历史详情。另验证旧空缓存失效、全量重建及后续尾部回放，并增加任务保存、归档、聚焦与无关插件隔离回归；173 项测试、类型检查、构建和客户端语法检查通过。本补充不代表已遍历所有历史损坏或中断日志；上方五版和原生桌面界面记录来自首轮候选包。
+
+The official rc.2 format migrator restored real v3 sessions with historical child facts for direct sources and wrappers using both current and legacy package names. Comparisons with native v4 logs cover task state, 11 tool-evidence pairs, nine memory-usage rows, per-model usage, and historical details. Checks also cover invalidating stale empty caches, full replay, and subsequent tail replay. Added regressions cover task saving, archiving, focus, and unrelated-plugin isolation. All 173 tests, type checking, build, and client syntax checks passed. This supplement does not cover every damaged or interrupted historical log; the five-version and native Desktop UI records above used the initial candidate.
+
+修复后的安装包另在 `0.1.5-alpha.1` 和 `0.2.1-rc.2` 中通过真实安装、激活、主/子 Agent、PTC、记忆归属、工作区隔离和冷重启历史读取回归；实际安装的任务投影实现与候选包一致。本补充未重跑浏览器及原生桌面界面，客户端仅更正日志格式注释。
+
+The fixed package also passed real installation, activation, main/child Agents, PTC, memory attribution, workspace isolation, and historical reads after a cold restart on `0.1.5-alpha.1` and `0.2.1-rc.2`. The installed task projection matches the candidate. This supplement did not rerun browser or native Desktop UI checks; the client change only corrects a log-format comment.
+
+## 0.3.4 · 2026-10-15
+
+本次更新评测文档、公开结果快照与致谢，宿主依赖和运行行为不变。构建后 112 个运行文件与 0.3.3 发布包逐字节一致，两份预设组合仅将版本标记更新为 0.3.4；此前 0.3.3 的宿主验收记录继续适用，本轮未重跑 Web / 原生 Desktop 界面，也未新增模型效果评测。
+
+This release updates evaluation documentation, the public results snapshot, and acknowledgements, with unchanged host dependencies and runtime behavior. After building, 112 runtime files are byte-for-byte identical to the 0.3.3 release package; the two preset compositions only update their version marker to 0.3.4. The 0.3.3 host-validation records below remain applicable. Web/native Desktop UI checks and new model-quality evaluations were not rerun for this release.
+
+171 项测试、类型检查、构建及客户端语法检查通过；另核对评测快照汇总、文档链接、版本一致性和打包范围。
+
+All 171 tests, type checking, build, and client syntax checks passed. Additional checks cover evaluation-snapshot aggregates, documentation links, version consistency, and package contents.
+
 ## 0.3.3 · 2026-10-14
 
 支持下限保持 `0.1.5-alpha.1`，依赖范围不变。本次核对官方 npm `latest`/`next` 为 `0.2.0-rc.2`，`alpha` 为 `0.2.1-alpha.2`。以下三个宿主使用固定并审计的依赖和隔离 profile，真实安装 0.3.3 组合候选包；其他版本保留此前逐版记录，本次没有全部重测。

package/docs/EvaluationResults.md

@@ -1,40 +1,97 @@
 # SWE-bench Pro hard-100 · 校正结果 / Corrected Results
 
-截至 2026-10-09，下面五组都完成了同一批 100 题的官方评分。0.2.0 使用冻结的分层记忆候选，0.3.0 使用冻结的 Batch.3 候选成绩；本页不混入其他实验方案。
+截至 2026-10-09，版本对比中的五组都完成了同一批 100 题的官方评分。0.2.0 使用冻结的分层记忆候选，0.3.0 使用冻结的 Batch.3 候选成绩。官方预设对比另列于下方，截至 2026-10-15，极简、标准、PTC 和创造的五组均已完成。
 
-As of October 9, 2026, all five runs have official scores for the same 100 tasks. Version 0.2.0 refers to the frozen memory-hierarchy candidate; 0.3.0 reports the frozen Batch.3 candidate. Other experiments are not included.
+As of October 9, 2026, all five version-comparison runs have official scores for the same 100 tasks. Version 0.2.0 refers to the frozen memory-hierarchy candidate; 0.3.0 reports the frozen Batch.3 candidate. The official-preset comparison appears separately below. As of October 15, 2026, all five minimal, standard, PTC, and creative runs are complete.
 
 ## 版本对比 · Version Comparison
 
-| 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 + high | 0.0.9 | 0.1.2 | 0.2.0 分层记忆 | 0.3.0 Batch.3 |
 |---|---:|---:|---:|---:|---:|
 | 有效评分 / Valid scores | 100 | 100 | 100 | 100 | 100 |
 | 通过题数 / Passed | 44 | 48 | 52 | 52 | 54 |
-| 平均回答耗时 / Mean minutes | 25.69 | 16.46 | 16.01 | 15.15 | 13.46 |
-| 耗时中位数 / Median minutes | 26.14 | 14.40 | 13.74 | 13.51 | 12.20 |
-| 耗时 P90 / P90 minutes | 43.70 | 28.82 | 29.36 | 24.14 | 21.38 |
-| 模型调用/题 / Model calls per task | 124.85 | 92.78 | 99.78 | 93.83 | 69.29 |
-| 顶层工具调用/题 / Top-level tool calls per task | 127.36 | 116.55 | 123.34 | 119.16 | 69.73 |
-| 总输入 token/题 / Input tokens per task | 11,477,170 | 9,525,316 | 9,840,383 | 9,202,574 | 6,290,407 |
-| 缓存输入 token/题 / Cached input per task | 11,404,101 | 9,461,981 | 9,775,799 | 9,142,006 | 6,231,823 |
-| 非缓存输入 token/题 / Uncached input per task | 73,069 | 63,334 | 64,584 | 60,569 | 58,584 |
-| 输出 token/题 / Output tokens per task | 100,877 | 97,901 | 97,793 | 96,520 | 91,562 |
-| 总 token/题 / Total tokens per task | 11,578,047 | 9,623,217 | 9,938,176 | 9,299,094 | 6,381,969 |
+| 平均回答耗时（历史）/ Original mean minutes | 25.685 | 16.458 | 16.011 | 15.148 | 13.461 |
+| 耗时中位数 / Median minutes | 26.138 | 14.398 | 13.736 | 13.510 | 12.197 |
+| 耗时 P90 / P90 minutes | 43.696 | 28.816 | 29.360 | 24.145 | 21.381 |
+| 模型调用/题 / Model calls per task | 124.660 | 92.780 | 99.780 | 93.830 | 69.290 |
+| 顶层工具调用/题 / Top-level tool calls per task | 127.360 | 116.550 | 123.340 | 119.160 | 69.730 |
+| 总输入 token/题 / Input tokens per task | 11,477,169.950 | 9,525,315.530 | 9,840,382.730 | 9,202,574.270 | 6,290,407.000 |
+| 缓存输入 token/题 / Cached input per task | 11,404,101.120 | 9,461,981.440 | 9,775,799.040 | 9,142,005.760 | 6,231,823.360 |
+| 非缓存输入 token/题 / Uncached input per task | 73,068.830 | 63,334.090 | 64,583.690 | 60,568.510 | 58,583.640 |
+| 输出 token/题 / Output tokens per task | 100,876.950 | 97,900.990 | 97,793.480 | 96,519.570 | 91,561.850 |
+| 总 token/题 / Total tokens per task | 11,578,046.900 | 9,623,216.520 | 9,938,176.210 | 9,299,093.840 | 6,381,968.850 |
 | 输入缓存率 / Input cache hit rate | 99.363% | 99.335% | 99.344% | 99.342% | 99.069% |
-| 缺少用量的请求 / Requests without usage | 7 | 8 | 1 | 1 | 0 |
+| 缺少用量的请求 / Requests without usage | 3 | 8 | 1 | 1 | 0 |
 
 工具次数按宿主 `tool/call` 统计。一次 PTC 调用内部可以执行多个操作，因此这列不能用来比较实际执行了多少次文件读取或命令。
 
 Tool counts use host `tool/call` events. One PTC call can execute several operations, so this column does not compare the number of underlying file reads or commands.
 
+## 官方预设对比 · Official Preset Comparison
+
+截至 **2026-10-15 08:38（UTC+8）**，以下五组均已完成同一批 100 题。标准 + max 已暂停，部分成绩另列，未完成题不算错。
+
+As of **October 15, 2026, 08:38 (UTC+8)**, all five runs below have completed the same 100 tasks. The paused standard + max run is listed separately; pending tasks are not counted as failures.
+
+| 指标 / Metric | 极简 minimal + high | 极简 minimal + max | 标准 standard + high | PTC + high | 创造 creative + high |
+|---|---:|---:|---:|---:| ---: |
+| 有效进度 / Valid scores | 100/100 | 100/100 | 100/100 | 100/100 | 100/100 |
+| 通过/有效 / Passed / valid | 44/100 | 48/100 | 49/100 | 44/100 | 46/100 |
+| 原始分钟/题 / Original minutes | 25.685 | 32.529 | 20.683 | 17.302 | 19.856 |
+| 净分钟/题 / Net minutes | 25.122 | 32.009 | 18.826 | 15.122 | 18.714 |
+| 净耗时中位数 / Median net minutes | 25.598 | 32.167 | 16.639 | 13.455 | 16.452 |
+| 净耗时 P90 / P90 net minutes | 41.658 | 45.179 | 36.681 | 25.031 | 30.104 |
+| 模型调用/题 / Model calls | 124.660 | 138.920 | 92.370 | 71.160 | 93.600 |
+| 顶层工具调用/题 / Top-level tool calls | 127.360 | 150.070 | 110.480 | 70.990 | 113.780 |
+| 总输入 token/题 / Input tokens | 11,477,169.950 | 14,849,497.540 | 8,771,693.040 | 6,160,934.650 | 9,205,287.290 |
+| 总 token/题 / Total tokens | 11,578,046.900 | 14,966,097.260 | 8,854,513.910 | 6,238,434.510 | 9,292,949.400 |
+| 缓存输入 token/题 / Cached input | 11,404,101.120 | 14,770,140.160 | 8,713,578.230 | 6,099,266.510 | 9,145,025.240 |
+| 非缓存输入 token/题 / Uncached input | 73,068.830 | 79,357.380 | 58,114.810 | 61,668.140 | 60,262.050 |
+| 输出 token/题 / Output | 100,876.950 | 116,599.720 | 82,820.870 | 77,499.860 | 87,662.110 |
+| 输入缓存率 / Input cache hit rate | 99.363% | 99.466% | 99.337% | 98.999% | 99.345% |
+| 扣除重试分钟（全组）/ Retry minutes excluded, total | 56.323 | 51.936 | 185.717 | 217.996 | 114.226 |
+| 缺少用量的请求 / Requests without usage | 3 | 11 | 4 | 5 | 2 |
+
+| 方案 / Mode | 状态 / Status | 有效进度 / Valid scores | 通过 / Passed | 净分钟/题 / Net minutes | 模型调用/题 / Model calls | 总 token/题 / Total tokens |
+|---|---|---:|---:|---:|---:|---:|
+| 标准 standard + max | 已暂停 / Paused | 2/100 | 0/2 | 18.273 | 110.500 | 14,100,705.000 |
+
+标准 + max 的均值只覆盖其 2 道有效完成题，不参与完整 100 题排名。
+
+Standard + max means cover its two valid completed tasks and are excluded from the completed 100-task ranking.
+
+极简 + high 复用历史基线，其宿主修订与本轮不同，不能把差异完全归因于思考等级。极简 + max、标准 + high、PTC + high 和创造 + high 使用同一冻结 Harness 修订和原生 Web RPC，插件未加载。各组均使用同一固定 100 题和官方评分器。
+
+Minimal + high reuses the historical baseline, whose host revision differs from this run; reasoning effort alone cannot explain the difference. Minimal + max, standard + high, PTC + high, and creative + high use the same frozen Harness revision and native Web RPC, without the plugin. All modes target the same frozen 100 tasks and official grader.
+
+创造保留官方预设与工具定义；评测隔离禁止 `cordis_run` 在宿主上执行动态代码，只读检查仍可使用。
+
+Creative retains the official preset and tool definitions. Evaluation isolation blocks host-side dynamic execution through `cordis_run`; read-only inspection remains available.
+
+“原始分钟”是最终有效作答的 Web RPC 耗时，不含镜像准备和官方评分。“净分钟”进一步扣除该次作答中的失败模型请求与重试等待，不扣除正常思考、工具或测试时间。
+
+Original minutes measure Web RPC time for the final valid answer, excluding image preparation and grading. Net minutes additionally remove failed model requests and retry waits within that answer, while retaining normal reasoning, tool calls, and tests.
+
+本次逐题核对了极简 + high 的全部 100 份原始证据、补丁及会话日志。已记录 29 次失败请求，扣除失败请求及等待共 **56.323 分钟**，净耗时为 **25.122 分钟/题**。旧调用统计已排除其中 10 次，但仍多计 19 次，本次修正后为 **124.660 次/题**；这 19 次没有有效用量，Token 总量不变。旧统计的 7 次缺失用量中，4 次属于失败请求，剩余 **3 次**发生在预算结束时，日志未返回 usage，无法补齐。版本表同步修正极简的调用数和缺失用量数，历史 JSON 保留原貌。
+
+This audit checked all 100 original minimal + high receipts, patches, and session logs. It identified 29 failed requests and excluded **56.323 minutes** of failed-request and retry time, giving **25.122 net minutes per task**. The old call count had already excluded ten failures but still included 19; the corrected count is **124.660 calls per task**. Those 19 requests added no valid usage, so token totals are unchanged. Four of the seven previously unknown-usage requests were failures. The remaining **three** occurred at the budget cutoff and have no recorded usage to recover. The version table uses the corrected minimal call and unknown-usage counts; historical JSON remains unchanged.
+
+标准 + high、PTC + high、极简 + max 和创造 + high 的净计时已覆盖全部有效题。其余缺失用量也已检查原始结算和流记录，未找到可恢复的 usage；这些缺失不会被估算成零费用。调用数排除已记录的失败请求，预算结束时尚未结算用量的请求仍计入次数并单列为缺失用量。总 token = 缓存输入 + 非缓存输入 + 输出，输出含思考 token，不再次叠加。数字保留三位小数，独立舍入可能造成末位差异。
+
+Net timing covers every valid task for standard + high, PTC + high, minimal + max, and creative + high. Original settlement and stream records were also checked for the remaining missing usage, with no recoverable usage found; this does not imply zero cost. Call counts exclude logged failed requests. Requests interrupted at the budget cutoff remain counted and are marked as unknown usage. Total tokens = cached input + uncached input + output, which already includes reasoning. Do not add reasoning again. Values use three decimal places; independent rounding can produce a last-digit difference.
+
+[官方预设逐题快照](../eval/results/swebench-pro-final-100/OfficialPresetResults.json)保留全部 **502 个有效结果**（五组各 100 题、标准 + max 2 题）的成绩、用量、原始 / 净耗时、核算说明与证据哈希。README 和本表来自同一快照。
+
+The [official-preset snapshot](../eval/results/swebench-pro-final-100/OfficialPresetResults.json) contains all **502 valid results**—100 for each of the five completed modes and 2 for standard + max—with usage, raw/net timing, audit notes, and evidence hashes. README and this table use the same snapshot.
+
 ## 相比官方 minimal · Relative to Official minimal
 
 | 版本 / Version | 通过率变化 / Pass-rate change | 平均耗时 / Mean time | 总 token / Total tokens | 新通过 / Gains | 回退 / Regressions |
 |---|---:|---:|---:|---:|---:|
-| 0.0.9 | +4 pp | -35.9% | -16.9% | 7 | 3 |
-| 0.1.2 | +8 pp | -37.7% | -14.2% | 10 | 2 |
-| 0.2.0 | +8 pp | -41.0% | -19.7% | 11 | 3 |
-| 0.3.0 Batch.3 | +10 pp | -47.6% | -44.9% | 13 | 3 |
+| 0.0.9 | +4.000 pp | -35.923% | -16.884% | 7 | 3 |
+| 0.1.2 | +8.000 pp | -37.663% | -14.164% | 10 | 2 |
+| 0.2.0 | +8.000 pp | -41.025% | -19.683% | 11 | 3 |
+| 0.3.0 Batch.3 | +10.000 pp | -47.593% | -44.879% | 13 | 3 |
 
 Batch.3 相比 0.2.0 平均耗时减少 11.1%、总 token 减少 31.4%、模型调用减少 26.2%，通过数从 52 增至 54；逐题新通过 8 题、回退 6 题。这是同题单轮结果，2 题的净增不能据此认定为稳定的质量提升。
 
@@ -57,9 +114,9 @@ Both 0.2.0 and 0.1.2 pass 52 tasks. Version 0.2.0 uses 5.4% less time and 6.4% f
 
 Sixteen grading records had anomalies such as the ConfigFileTest 500 ms timeout or a killed Jest worker. Each was regraded with the **original patch**, requiring two matching results without that anomaly—not selecting the best result from retries. Twelve recovered to a pass and four remained failures. Regrading added no model calls; the original scores, usage, and patches are preserved.
 
-[四版本逐题数据](../eval/results/swebench-pro-final-100/CorrectedFourVersions.json)包含全部 400 条评分、调用数、token、耗时、补丁与证据哈希，以及逐条修正原因。历史 JSON 保留原貌，以这份校正汇总为当前展示口径；结果文件留在仓库，不重复放进 npm 包。
+[四版本逐题数据](../eval/results/swebench-pro-final-100/CorrectedFourVersions.json)包含全部 400 条评分、调用数、token、耗时、补丁与证据哈希，以及逐条修正原因。历史 JSON 保留原貌；极简的调用数和缺失用量数采用上述原会话核算，其余版本指标来自这份校正汇总。结果文件留在仓库，不重复放进 npm 包。
 
-The [four-version per-task data](../eval/results/swebench-pro-final-100/CorrectedFourVersions.json) contains all 400 scores, call counts, tokens, times, patch/evidence hashes, and individual correction reasons. Historical JSON is unchanged; the corrected summary is the current reporting source. Result files remain in the repository rather than the npm package.
+The [four-version per-task data](../eval/results/swebench-pro-final-100/CorrectedFourVersions.json) contains all 400 scores, call counts, tokens, times, patch/evidence hashes, and individual correction reasons. Historical JSON is unchanged. Minimal call and unknown-usage counts use the session audit above; other version metrics come from the corrected summary. Result files remain in the repository rather than the npm package.
 
 [Batch.3 逐题数据](../eval/results/swebench-pro-final-100/Batch3Results.json)另存 100 条成绩、用量、耗时和原始证据及补丁哈希，汇总数字已逐题复算，并核对与上述基线使用同一批任务。Batch.3 的评分异常同样用原补丁复核，不把作废尝试的调用和用量加到最终结果中；这些数据也不进入 npm 包。
 
@@ -67,12 +124,12 @@ The separate [Batch.3 per-task data](../eval/results/swebench-pro-final-100/Batc
 
 ## 如何理解 · How to Read These Results
 
-- **同题比较：** 固定题集标识为 `swebench-pro-hard-100-ddd22492f1c38839`，使用同一开发测试模型、`high` 思考等级、原生 DSH Web RPC 和官方评分器。这 100 题按既有难度方法选出，并非官方认定的“最难 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。版本迭代的效果优化使用从 SWE-bench 官方 dev 集筛选的 33 道有效困难题。
-  **Same tasks:** The frozen selection is `swebench-pro-hard-100-ddd22492f1c38839`, using the same development test model, `high` reasoning, native DSH Web RPC, and the official grader. These 100 tasks were selected using the existing difficulty-ranking method, rather than an official hardest-100 designation. They are used to evaluate frozen candidates and investigate bugs, not for performance tuning. Version iterations use 33 valid difficult tasks selected from the official SWE-bench dev split for optimization.
-- **时间：** 统一采用每题 Web RPC 回答耗时，不计官方评分、下载镜像和复评分；中位数取第 50、51 项均值，P90 取排序后的第 90 项。旧文档 0.0.9 的 16.27 分钟使用不同口径，现统一为 16.46 分钟。
-  **Time:** Per-task Web RPC response time excludes grading, image downloads, and regrading. The median averages the 50th and 51st values; P90 is the 90th ordered value. The older 16.27-minute figure for 0.0.9 used a different timing convention; the consistent figure is 16.46 minutes.
-- **用量：** 纳入每题最终评分尝试的已记录调用，先逐题合计再对 100 题取平均。输入包含缓存读取；缓存率为全部缓存输入除以全部输入，而非逐题缓存率的平均。未返回用量的请求不估算，因此 token 不代表完整账单费用，也不包括先前被放弃的尝试成本。
-  **Usage:** Recorded calls from each task’s final scored attempt are summed per task, then averaged over 100 tasks. Input includes cache reads; the cache rate is total cached input divided by total input, not the mean per-task rate. Missing usage is not estimated, so tokens do not represent a complete bill or the cost of earlier abandoned attempts.
+- **同题比较：** 固定题集标识为 `swebench-pro-hard-100-ddd22492f1c38839`，使用同一开发测试模型、原生 DSH Web RPC 和官方评分器。版本表均为 `high` 思考等级，官方预设表的等级按列标明。这 100 题按既有难度方法选出，并非官方认定的“最难 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。
+  **Same tasks:** The frozen selection is `swebench-pro-hard-100-ddd22492f1c38839`, using the same development test model, native DSH Web RPC, and the official grader. All version-comparison runs use `high` reasoning; the official-preset table labels each effort level. These 100 tasks were selected using the existing difficulty-ranking method, rather than an official hardest-100 designation. They are used to evaluate frozen candidates and investigate bugs, not for performance tuning.
+- **时间：** 版本表保留每题最终有效作答的原始 Web RPC 耗时，不计官方评分、下载镜像和复评分，但未逐项扣除该次作答内部的失败请求与重试等待。中位数取第 50、51 项均值，P90 取排序后的第 90 项。0.0.9 的旧文档曾写 16.27 分钟，这里按历史统一口径为 16.458 分钟。官方预设表另列净耗时，两种口径不混用。
+  **Time:** The version table retains raw Web RPC time for each final valid answer, excluding grading, image downloads, and regrading, but without subtracting individual failed requests and retry waits within that answer. The median averages the 50th and 51st values; P90 is the 90th ordered value. An older 0.0.9 document reported 16.27 minutes; the historical convention gives 16.458 minutes. The official-preset table reports net time separately; the two measures must not be mixed.
+- **用量：** 纳入每题最终评分尝试的已记录调用，先逐题合计再对 100 题取平均。输入包含缓存读取，输出包含思考 token；缓存率为全部缓存输入除以全部输入，而非逐题缓存率的平均。未返回用量的请求不估算，因此 token 不代表完整账单费用，也不包括先前被放弃的尝试成本。
+  **Usage:** Recorded calls from each task’s final scored attempt are summed per task, then averaged over 100 tasks. Input includes cache reads and output includes reasoning tokens; the cache rate is total cached input divided by total input, not the mean per-task rate. Missing usage is not estimated, so tokens do not represent a complete bill or the cost of earlier abandoned attempts.
 - **候选身份：** 0.2.0 表示已评测的分层记忆候选，其实验包内部版本仍为 0.1.3，包 SHA-256 为 `164cc1b505c05288f01b6f12c0756af049dbde8f1a49bdb11f9a320a19c925f5`。新整合的记忆 UI 与兼容改动进行单测及真实宿主回归，未重新运行这 100 次模型任务。
   **Candidate identity:** The evaluated memory-hierarchy candidate is reported as 0.2.0; its experimental package still carried version 0.1.3 and SHA-256 `164cc1b505c05288f01b6f12c0756af049dbde8f1a49bdb11f9a320a19c925f5`. The integrated memory UI and compatibility changes undergo unit and real-host regression checks, not a fresh 100-task model run.
 - **0.3.0 来源：** 本页成绩属于内部版本 `0.3.0-batch.3` 的实际安装候选。整合时按冻结的运行模块逐文件核对，保留主干 0.2.1 的语言资源和兼容改动；发布包做类型、单测、打包及真实宿主回归，没有重新执行这 100 次模型任务。Batch.3 与分层记忆候选的 Harness 提交同为 `649bfcddf0e3532510a38380b9620570d8b13818`，仍不能分离提示词和工具呈现方式各自的作用。

package/lib/task-memory-projection.d.ts

@@ -28,7 +28,7 @@ declare module '@deepseek-ai/dsh-llm' {
         };
     }
 }
-/** Known host message vocabulary keeps external plugin records resumable. */
+/** V4 prefixes migrated plugin wrappers; native producer kinds remain unchanged. */
 export declare function taskMemoryEventOf(event: SessionEvent): {
     kind: 'record';
     record: TaskMemoryEvent;

package/lib/task-memory-projection.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"task-memory-projection.d.ts","sourceRoot":"","sources":["../src/task-memory-projection.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,oBAAoB,EAAE,MAAM,qCAAqC,CAAA;AAC/E,OAAO,KAAK,EAAE,YAAY,EAAE,MAAM,0BAA0B,CAAA;AAE5D,OAAO,KAAK,EAAE,eAAe,EAAE,eAAe,EAAE,MAAM,uBAAuB,CAAA;AAG7E,MAAM,WAAW,cAAc;IAC7B,KAAK,EAAE;QAAE,EAAE,EAAE,MAAM,CAAC;QAAC,KAAK,EAAE,MAAM,CAAC;QAAC,MAAM,EAAE,MAAM,CAAA;KAAE,EAAE,CAAA;IACtD,OAAO,EAAE;QAAE,IAAI,EAAE,MAAM,CAAA;KAAE,GAAG;QAAE,IAAI,EAAE,MAAM,CAAC;QAAC,EAAE,EAAE,MAAM,CAAC;QAAC,KAAK,EAAE,MAAM,CAAC;QAAC,IAAI,EAAE,MAAM,CAAC;QAAC,MAAM,EAAE,MAAM,CAAC;QAAC,IAAI,EAAE,MAAM,CAAA;KAAE,CAAA;CACpH;AAOD,qFAAqF;AACrF,wBAAgB,cAAc,CAAC,KAAK,EAAE,eAAe,GAAG,cAAc,CAOrE;AAED,eAAO,MAAM,kBAAkB,kCAAkC,CAAA;AACjE,OAAO,QAAQ,sBAAsB,CAAC;IACpC,UAAU,gBAAgB;QAAG,+BAA+B,EAAE;YAAE,IAAI,EAAE,+BAA+B,CAAA;SAAE,CAAA;KAAE;CAC1G;AAID,6EAA6E;AAC7E,wBAAgB,iBAAiB,CAAC,KAAK,EAAE,YAAY,GAAG;IAAE,IAAI,EAAE,QAAQ,CAAC;IAAC,MAAM,EAAE,eAAe,CAAA;CAAE,GAAG;IAAE,IAAI,EAAE,WAAW,CAAA;CAAE,CAQ1H;AACD,OAAO,QAAQ,2CAA2C,CAAC;IACzD,UAAU,yBAAyB;QAAG,cAAc,EAAE,eAAe,CAAA;KAAE;IACvE,UAAU,oBAAoB;QAAG,cAAc,EAAE,cAAc,CAAA;KAAE;CAClE;AAED,sFAAsF;AACtF,eAAO,MAAM,oBAAoB,EAAE,oBAAoB,CAAC,gBAAgB,EAAE,eAAe,CAAC,GAAG;IAC3F,IAAI,EAAE,WAAW,CAAC,oBAAoB,CAAC,gBAAgB,EAAE,eAAe,CAAC,CAAC,MAAM,CAAC,CAAC,CAAA;CAanF,CAAA"}
+{"version":3,"file":"task-memory-projection.d.ts","sourceRoot":"","sources":["../src/task-memory-projection.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,oBAAoB,EAAE,MAAM,qCAAqC,CAAA;AAC/E,OAAO,KAAK,EAAE,YAAY,EAAE,MAAM,0BAA0B,CAAA;AAE5D,OAAO,KAAK,EAAE,eAAe,EAAE,eAAe,EAAE,MAAM,uBAAuB,CAAA;AAG7E,MAAM,WAAW,cAAc;IAC7B,KAAK,EAAE;QAAE,EAAE,EAAE,MAAM,CAAC;QAAC,KAAK,EAAE,MAAM,CAAC;QAAC,MAAM,EAAE,MAAM,CAAA;KAAE,EAAE,CAAA;IACtD,OAAO,EAAE;QAAE,IAAI,EAAE,MAAM,CAAA;KAAE,GAAG;QAAE,IAAI,EAAE,MAAM,CAAC;QAAC,EAAE,EAAE,MAAM,CAAC;QAAC,KAAK,EAAE,MAAM,CAAC;QAAC,IAAI,EAAE,MAAM,CAAC;QAAC,MAAM,EAAE,MAAM,CAAC;QAAC,IAAI,EAAE,MAAM,CAAA;KAAE,CAAA;CACpH;AAOD,qFAAqF;AACrF,wBAAgB,cAAc,CAAC,KAAK,EAAE,eAAe,GAAG,cAAc,CAOrE;AAED,eAAO,MAAM,kBAAkB,kCAAkC,CAAA;AACjE,OAAO,QAAQ,sBAAsB,CAAC;IACpC,UAAU,gBAAgB;QAAG,+BAA+B,EAAE;YAAE,IAAI,EAAE,+BAA+B,CAAA;SAAE,CAAA;KAAE;CAC1G;AAKD,oFAAoF;AACpF,wBAAgB,iBAAiB,CAAC,KAAK,EAAE,YAAY,GAAG;IAAE,IAAI,EAAE,QAAQ,CAAC;IAAC,MAAM,EAAE,eAAe,CAAA;CAAE,GAAG;IAAE,IAAI,EAAE,WAAW,CAAA;CAAE,CAS1H;AACD,OAAO,QAAQ,2CAA2C,CAAC;IACzD,UAAU,yBAAyB;QAAG,cAAc,EAAE,eAAe,CAAA;KAAE;IACvE,UAAU,oBAAoB;QAAG,cAAc,EAAE,cAAc,CAAA;KAAE;CAClE;AAED,sFAAsF;AACtF,eAAO,MAAM,oBAAoB,EAAE,oBAAoB,CAAC,gBAAgB,EAAE,eAAe,CAAC,GAAG;IAC3F,IAAI,EAAE,WAAW,CAAC,oBAAoB,CAAC,gBAAgB,EAAE,eAAe,CAAC,CAAC,MAAM,CAAC,CAAC,CAAA;CAcnF,CAAA"}

package/lib/task-memory-projection.js

@@ -19,13 +19,15 @@ export function taskMemoryView(state) {
 export const TASK_MEMORY_SOURCE = 'dsh-super-code/task-memory/v1';
 // Persisted records from before the package rename must remain readable.
 const LEGACY_TASK_MEMORY_SOURCE = 'dsh-super-agent/task-memory/v1';
-/** Known host message vocabulary keeps external plugin records resumable. */
+const taskMemorySources = new Set([TASK_MEMORY_SOURCE, LEGACY_TASK_MEMORY_SOURCE]);
+/** V4 prefixes migrated plugin wrappers; native producer kinds remain unchanged. */
 export function taskMemoryEventOf(event) {
     if (event.type !== 'user/message')
         return { kind: 'unrelated' };
     const source = event.data.source;
-    if (![TASK_MEMORY_SOURCE, LEGACY_TASK_MEMORY_SOURCE].includes(source.kind)
-        && !(source.kind === 'plugin' && [TASK_MEMORY_SOURCE, LEGACY_TASK_MEMORY_SOURCE].includes(source.plugin ?? '')))
+    const producer = source.kind === 'plugin' ? source.plugin ?? ''
+        : source.kind.startsWith('plugin:') ? source.kind.slice('plugin:'.length) : source.kind;
+    if (!taskMemorySources.has(producer))
         return { kind: 'unrelated' };
     const content = event.data.content;
     if (content.length !== 1 || content[0]?.type !== 'text')
@@ -34,7 +36,8 @@ export function taskMemoryEventOf(event) {
 }
 /** Host checkpoints restore the bounded working set without summarizing summaries. */
 export const taskMemoryProjection = {
-    key: 'superCodeTasks', stateVersion: 1, stateSchema: taskMemoryStateSchema,
+    // Rebuild checkpoints that previously skipped v4 migrated plugin sources.
+    key: 'superCodeTasks', stateVersion: 2, stateSchema: taskMemoryStateSchema,
     init: () => emptyTaskMemory(),
     apply: (state, event) => {
         const record = taskMemoryEventOf(event);

package/lib/task-memory-projection.js.map

@@ -1 +1 @@
-{"version":3,"file":"task-memory-projection.js","sourceRoot":"","sources":["../src/task-memory-projection.ts"],"names":[],"mappings":"AAEA,OAAO,EAAE,eAAe,EAAE,cAAc,EAAE,qBAAqB,EAAE,qBAAqB,EAAE,MAAM,uBAAuB,CAAA;AAErH,OAAO,EAAE,CAAC,EAAE,MAAM,KAAK,CAAA;AAMvB,MAAM,UAAU,GAA8B,CAAC,CAAC,MAAM,CAAC;IACrD,KAAK,EAAE,CAAC,CAAC,KAAK,CAAC,CAAC,CAAC,MAAM,CAAC,EAAE,EAAE,EAAE,CAAC,CAAC,MAAM,EAAE,EAAE,KAAK,EAAE,CAAC,CAAC,MAAM,EAAE,EAAE,MAAM,EAAE,CAAC,CAAC,MAAM,EAAE,EAAE,CAAC,CAAC,MAAM,EAAE,CAAC;IAC5F,OAAO,EAAE,CAAC,CAAC,kBAAkB,CAAC,MAAM,EAAE,CAAC,CAAC,CAAC,MAAM,CAAC,EAAE,IAAI,EAAE,CAAC,CAAC,OAAO,CAAC,MAAM,CAAC,EAAE,CAAC,CAAC,MAAM,EAAE;QACnF,CAAC,CAAC,MAAM,CAAC,EAAE,IAAI,EAAE,CAAC,CAAC,OAAO,CAAC,MAAM,CAAC,EAAE,EAAE,EAAE,CAAC,CAAC,MAAM,EAAE,EAAE,KAAK,EAAE,CAAC,CAAC,MAAM,EAAE,EAAE,IAAI,EAAE,CAAC,CAAC,MAAM,EAAE,EAAE,MAAM,EAAE,CAAC,CAAC,MAAM,EAAE,EAAE,IAAI,EAAE,CAAC,CAAC,MAAM,EAAE,EAAE,CAAC,CAAC,MAAM,EAAE,CAAC,CAAC;CAC9I,CAAC,CAAC,MAAM,EAAE,CAAA;AAEX,qFAAqF;AACrF,MAAM,UAAU,cAAc,CAAC,KAAsB;IACnD,MAAM,KAAK,GAAG,MAAM,CAAC,MAAM,CAAC,KAAK,CAAC,KAAK,CAAC,CAAC,GAAG,CAAC,CAAC,EAAE,EAAE,EAAE,KAAK,EAAE,MAAM,EAAE,EAAE,EAAE,CAAC,CAAC,EAAE,EAAE,EAAE,KAAK,EAAE,MAAM,EAAE,CAAC,CAAC,CAAA;IAChG,IAAI,KAAK,CAAC,KAAK,CAAC,IAAI,KAAK,MAAM;QAAE,OAAO,EAAE,KAAK,EAAE,OAAO,EAAE,EAAE,IAAI,EAAE,MAAM,EAAE,EAAE,CAAA;IAC5E,MAAM,IAAI,GAAG,KAAK,CAAC,KAAK,CAAC,KAAK,CAAC,KAAK,CAAC,EAAE,CAAC,CAAA;IACxC,IAAI,CAAC,IAAI;QAAE,MAAM,IAAI,KAAK,CAAC,8BAA8B,CAAC,CAAA;IAC1D,MAAM,EAAE,EAAE,EAAE,KAAK,EAAE,IAAI,EAAE,MAAM,EAAE,IAAI,EAAE,GAAG,IAAI,CAAA;IAC9C,OAAO,EAAE,KAAK,EAAE,OAAO,EAAE,EAAE,IAAI,EAAE,MAAM,EAAE,EAAE,EAAE,KAAK,EAAE,IAAI,EAAE,MAAM,EAAE,IAAI,EAAE,EAAE,CAAA;AAC5E,CAAC;AAED,MAAM,CAAC,MAAM,kBAAkB,GAAG,+BAA+B,CAAA;AAIjE,yEAAyE;AACzE,MAAM,yBAAyB,GAAG,gCAAgC,CAAA;AAElE,6EAA6E;AAC7E,MAAM,UAAU,iBAAiB,CAAC,KAAmB;IACnD,IAAI,KAAK,CAAC,IAAI,KAAK,cAAc;QAAE,OAAO,EAAE,IAAI,EAAE,WAAW,EAAE,CAAA;IAC/D,MAAM,MAAM,GAAG,KAAK,CAAC,IAAI,CAAC,MAA2C,CAAA;IACrE,IAAI,CAAC,CAAC,kBAAkB,EAAE,yBAAyB,CAAC,CAAC,QAAQ,CAAC,MAAM,CAAC,IAAI,CAAC;WACrE,CAAC,CAAC,MAAM,CAAC,IAAI,KAAK,QAAQ,IAAI,CAAC,kBAAkB,EAAE,yBAAyB,CAAC,CAAC,QAAQ,CAAC,MAAM,CAAC,MAAM,IAAI,EAAE,CAAC,CAAC;QAAE,OAAO,EAAE,IAAI,EAAE,WAAW,EAAE,CAAA;IAC/I,MAAM,OAAO,GAAG,KAAK,CAAC,IAAI,CAAC,OAAO,CAAA;IAClC,IAAI,OAAO,CAAC,MAAM,KAAK,CAAC,IAAI,OAAO,CAAC,CAAC,CAAC,EAAE,IAAI,KAAK,MAAM;QAAE,MAAM,IAAI,KAAK,CAAC,8BAA8B,CAAC,CAAA;IACxG,OAAO,EAAE,IAAI,EAAE,QAAQ,EAAE,MAAM,EAAE,qBAAqB,CAAC,KAAK,CAAC,IAAI,CAAC,KAAK,CAAC,OAAO,CAAC,CAAC,CAAC,CAAC,IAAI,CAAC,CAAC,EAAE,CAAA;AAC7F,CAAC;AAMD,sFAAsF;AACtF,MAAM,CAAC,MAAM,oBAAoB,GAE7B;IACF,GAAG,EAAE,gBAAgB,EAAE,YAAY,EAAE,CAAC,EAAE,WAAW,EAAE,qBAAqB;IAC1E,IAAI,EAAE,GAAG,EAAE,CAAC,eAAe,EAAE;IAC7B,KAAK,EAAE,CAAC,KAAK,EAAE,KAAK,EAAE,EAAE;QACtB,MAAM,MAAM,GAAG,iBAAiB,CAAC,KAAK,CAAC,CAAA;QACvC,IAAI,MAAM,CAAC,IAAI,KAAK,QAAQ;YAAE,OAAO,cAAc,CAAC,KAAK,EAAE,MAAM,CAAC,MAAM,CAAC,CAAA;QACzE,IAAI,KAAK,CAAC,IAAI,KAAK,cAAc,IAAI,KAAK,CAAC,IAAI,CAAC,MAAM,CAAC,IAAI,KAAK,MAAM,EAAE,CAAC;YACvE,OAAO,EAAE,GAAG,KAAK,EAAE,aAAa,EAAE,CAAC,GAAG,KAAK,CAAC,aAAa,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,EAAE,KAAK,CAAC,GAAG,CAAC,EAAE,CAAA;QACnF,CAAC;QACD,OAAO,KAAK,CAAA;IACd,CAAC;IACD,IAAI,EAAE,EAAE,UAAU,EAAE,IAAI,EAAE,cAAc,EAAE;CAC3C,CAAA"}
+{"version":3,"file":"task-memory-projection.js","sourceRoot":"","sources":["../src/task-memory-projection.ts"],"names":[],"mappings":"AAEA,OAAO,EAAE,eAAe,EAAE,cAAc,EAAE,qBAAqB,EAAE,qBAAqB,EAAE,MAAM,uBAAuB,CAAA;AAErH,OAAO,EAAE,CAAC,EAAE,MAAM,KAAK,CAAA;AAMvB,MAAM,UAAU,GAA8B,CAAC,CAAC,MAAM,CAAC;IACrD,KAAK,EAAE,CAAC,CAAC,KAAK,CAAC,CAAC,CAAC,MAAM,CAAC,EAAE,EAAE,EAAE,CAAC,CAAC,MAAM,EAAE,EAAE,KAAK,EAAE,CAAC,CAAC,MAAM,EAAE,EAAE,MAAM,EAAE,CAAC,CAAC,MAAM,EAAE,EAAE,CAAC,CAAC,MAAM,EAAE,CAAC;IAC5F,OAAO,EAAE,CAAC,CAAC,kBAAkB,CAAC,MAAM,EAAE,CAAC,CAAC,CAAC,MAAM,CAAC,EAAE,IAAI,EAAE,CAAC,CAAC,OAAO,CAAC,MAAM,CAAC,EAAE,CAAC,CAAC,MAAM,EAAE;QACnF,CAAC,CAAC,MAAM,CAAC,EAAE,IAAI,EAAE,CAAC,CAAC,OAAO,CAAC,MAAM,CAAC,EAAE,EAAE,EAAE,CAAC,CAAC,MAAM,EAAE,EAAE,KAAK,EAAE,CAAC,CAAC,MAAM,EAAE,EAAE,IAAI,EAAE,CAAC,CAAC,MAAM,EAAE,EAAE,MAAM,EAAE,CAAC,CAAC,MAAM,EAAE,EAAE,IAAI,EAAE,CAAC,CAAC,MAAM,EAAE,EAAE,CAAC,CAAC,MAAM,EAAE,CAAC,CAAC;CAC9I,CAAC,CAAC,MAAM,EAAE,CAAA;AAEX,qFAAqF;AACrF,MAAM,UAAU,cAAc,CAAC,KAAsB;IACnD,MAAM,KAAK,GAAG,MAAM,CAAC,MAAM,CAAC,KAAK,CAAC,KAAK,CAAC,CAAC,GAAG,CAAC,CAAC,EAAE,EAAE,EAAE,KAAK,EAAE,MAAM,EAAE,EAAE,EAAE,CAAC,CAAC,EAAE,EAAE,EAAE,KAAK,EAAE,MAAM,EAAE,CAAC,CAAC,CAAA;IAChG,IAAI,KAAK,CAAC,KAAK,CAAC,IAAI,KAAK,MAAM;QAAE,OAAO,EAAE,KAAK,EAAE,OAAO,EAAE,EAAE,IAAI,EAAE,MAAM,EAAE,EAAE,CAAA;IAC5E,MAAM,IAAI,GAAG,KAAK,CAAC,KAAK,CAAC,KAAK,CAAC,KAAK,CAAC,EAAE,CAAC,CAAA;IACxC,IAAI,CAAC,IAAI;QAAE,MAAM,IAAI,KAAK,CAAC,8BAA8B,CAAC,CAAA;IAC1D,MAAM,EAAE,EAAE,EAAE,KAAK,EAAE,IAAI,EAAE,MAAM,EAAE,IAAI,EAAE,GAAG,IAAI,CAAA;IAC9C,OAAO,EAAE,KAAK,EAAE,OAAO,EAAE,EAAE,IAAI,EAAE,MAAM,EAAE,EAAE,EAAE,KAAK,EAAE,IAAI,EAAE,MAAM,EAAE,IAAI,EAAE,EAAE,CAAA;AAC5E,CAAC;AAED,MAAM,CAAC,MAAM,kBAAkB,GAAG,+BAA+B,CAAA;AAIjE,yEAAyE;AACzE,MAAM,yBAAyB,GAAG,gCAAgC,CAAA;AAClE,MAAM,iBAAiB,GAAG,IAAI,GAAG,CAAC,CAAC,kBAAkB,EAAE,yBAAyB,CAAC,CAAC,CAAA;AAElF,oFAAoF;AACpF,MAAM,UAAU,iBAAiB,CAAC,KAAmB;IACnD,IAAI,KAAK,CAAC,IAAI,KAAK,cAAc;QAAE,OAAO,EAAE,IAAI,EAAE,WAAW,EAAE,CAAA;IAC/D,MAAM,MAAM,GAAG,KAAK,CAAC,IAAI,CAAC,MAA2C,CAAA;IACrE,MAAM,QAAQ,GAAG,MAAM,CAAC,IAAI,KAAK,QAAQ,CAAC,CAAC,CAAC,MAAM,CAAC,MAAM,IAAI,EAAE;QAC7D,CAAC,CAAC,MAAM,CAAC,IAAI,CAAC,UAAU,CAAC,SAAS,CAAC,CAAC,CAAC,CAAC,MAAM,CAAC,IAAI,CAAC,KAAK,CAAC,SAAS,CAAC,MAAM,CAAC,CAAC,CAAC,CAAC,MAAM,CAAC,IAAI,CAAA;IACzF,IAAI,CAAC,iBAAiB,CAAC,GAAG,CAAC,QAAQ,CAAC;QAAE,OAAO,EAAE,IAAI,EAAE,WAAW,EAAE,CAAA;IAClE,MAAM,OAAO,GAAG,KAAK,CAAC,IAAI,CAAC,OAAO,CAAA;IAClC,IAAI,OAAO,CAAC,MAAM,KAAK,CAAC,IAAI,OAAO,CAAC,CAAC,CAAC,EAAE,IAAI,KAAK,MAAM;QAAE,MAAM,IAAI,KAAK,CAAC,8BAA8B,CAAC,CAAA;IACxG,OAAO,EAAE,IAAI,EAAE,QAAQ,EAAE,MAAM,EAAE,qBAAqB,CAAC,KAAK,CAAC,IAAI,CAAC,KAAK,CAAC,OAAO,CAAC,CAAC,CAAC,CAAC,IAAI,CAAC,CAAC,EAAE,CAAA;AAC7F,CAAC;AAMD,sFAAsF;AACtF,MAAM,CAAC,MAAM,oBAAoB,GAE7B;IACF,0EAA0E;IAC1E,GAAG,EAAE,gBAAgB,EAAE,YAAY,EAAE,CAAC,EAAE,WAAW,EAAE,qBAAqB;IAC1E,IAAI,EAAE,GAAG,EAAE,CAAC,eAAe,EAAE;IAC7B,KAAK,EAAE,CAAC,KAAK,EAAE,KAAK,EAAE,EAAE;QACtB,MAAM,MAAM,GAAG,iBAAiB,CAAC,KAAK,CAAC,CAAA;QACvC,IAAI,MAAM,CAAC,IAAI,KAAK,QAAQ;YAAE,OAAO,cAAc,CAAC,KAAK,EAAE,MAAM,CAAC,MAAM,CAAC,CAAA;QACzE,IAAI,KAAK,CAAC,IAAI,KAAK,cAAc,IAAI,KAAK,CAAC,IAAI,CAAC,MAAM,CAAC,IAAI,KAAK,MAAM,EAAE,CAAC;YACvE,OAAO,EAAE,GAAG,KAAK,EAAE,aAAa,EAAE,CAAC,GAAG,KAAK,CAAC,aAAa,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,EAAE,KAAK,CAAC,GAAG,CAAC,EAAE,CAAA;QACnF,CAAC;QACD,OAAO,KAAK,CAAA;IACd,CAAC;IACD,IAAI,EAAE,EAAE,UAAU,EAAE,IAAI,EAAE,cAAc,EAAE;CAC3C,CAAA"}

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "dsh-super-code",
-  "version": "0.3.3",
+  "version": "0.3.5",
   "description": "Task-focused coding, specialist teams, and durable task memory with directory and declarative presets for DeepSeek Harness.",
   "license": "Apache-2.0",
   "type": "module",
@@ -46,6 +46,7 @@
     "docs/Compatibility.md",
     "docs/UsageGuide.md",
     "docs/EvaluationResults.md",
+    "docs/Acknowledgements.md",
     "docs/images/agent-tree.png",
     "docs/images/agent-tree-preview.png",
     "docs/images/preset-settings.png",

package/presets/super-code/agent.cordis.yml

@@ -2,7 +2,7 @@
 - id: super-code
   name: dsh-super-code/super-code
   config:
-    presetVersion: 0.3.3
+    presetVersion: 0.3.5
 # Reuse the host backend in an agent-local realm, as shipped Harness presets do.
 # The token meter remains host-owned; each agent owns its compaction lifecycle.
 - id: compaction