dsh-super-code 0.3.6 → 0.3.7

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 **44.4%**，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 **46% 提高到 56%**。[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 **44.4% 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 **56% passing versus 46%** for official minimal. [Full results and limitations](docs/EvaluationResults.md)
 
 # 1 版本与更新 · Versions and Updates
 
@@ -14,15 +14,21 @@ 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 `0.3.6`：
+版本号采用 **主版本.效果优化版本.维护版本**，例如 `0.3.7`：
 
-Version numbers follow **major.performance-improvement.maintenance**, for example `0.3.6`:
+Version numbers follow **major.performance-improvement.maintenance**, for example `0.3.7`:
 
 | 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 (`6`) | 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 (`7`) | 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. |
+
+## 0.3.7 · What's New
+
+新增默认宽松的三档删除保护，以及全展开、虚拟滚动的任务状态侧栏。[更新详情](docs/Changelog.md)
+
+Adds three deletion-protection modes, defaulting to Relaxed, and a fully expanded task-status sidebar with virtual scrolling. [Changelog](docs/Changelog.md)
 
 ## 0.3.6 · What's New
 
@@ -36,35 +42,7 @@ Adds configurable budgets and restores the older, better-performing budgets with
 
 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
-
-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)
-
-## 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)
-
-## 0.3.1 · What's New
-
-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)
-
-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
-
-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)
+[查看完整版本记录 · Full changelog](docs/Changelog.md)
 
 # 2 开始使用 · Get Started
 
@@ -99,7 +77,7 @@ 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-0.3.6.tgz
+dsh plugin --profile web add ./dsh-super-code-0.3.7.tgz
 ```
 
 </details>
@@ -122,9 +100,9 @@ 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 **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)
+右侧 **Super Code** 页面依次展示任务状态、协作执行和记忆库，默认展开任务状态，点击标题切换。任务、步骤和已加载动作直接展开，虚拟滚动保持长列表流畅；保留圆圈 Agent 执行树及记忆的查看、新增、编辑和删除。任务状态只读取现有记录，不改变提示词或模型行为。[界面与记忆说明](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)
+The **Super Code** sidebar contains Task status, Agent execution, and Memory library, with Task status open by default. Tasks, steps, and loaded activity stay expanded in a virtualized list. The circular Agent graph and memory browsing, creation, editing, and deletion remain available. Task status reads existing records without changing prompts or model behavior. [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)
 
@@ -136,48 +114,98 @@ Current iterations are optimized on **33 valid difficult tasks selected from the
 
 ## 3.1 各版本成绩 · Version Results
 
-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。
+五组均使用 **DSH `0.1.5-rc.2`**、**`deepseek-v4.1-flash`** 和 `high` 思考等级，完成同一批 100 题；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 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.
+All five runs used **DSH `0.1.5-rc.2`**, **`deepseek-v4.1-flash`**, and `high` reasoning on the same 100 tasks. 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 + 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** |
+| 通过 / Passed | 46/100 | 50/100 | 53/100 | 54/100 | **56/100** |
 | 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** |
 
+五组均按相同规则复核。通过数已包含实际测试全部通过、仅因测试名称差异被误判的记录；用量和耗时保持原作答数据。修正依据见[评测说明](docs/EvaluationResults.md)。
+
+All five runs were reviewed under the same rules. Pass counts include verified cases where every test passed but test-name differences caused a grading mismatch. Original usage and timing are unchanged. See the [evaluation report](docs/EvaluationResults.md) for correction evidence.
+
 ## 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。
+本表使用 **DSH `0.1.5-rc.2`** 和 **`deepseek-v4.1-flash`**，思考等级按列标明；成绩包含后续原补丁复评与测试名称修正。各列只统计有效结果，未满 100 题的列不参与完整 100 题排名。
+
+This table uses **DSH `0.1.5-rc.2`** and **`deepseek-v4.1-flash`**, with reasoning effort shown per column. Scores include subsequent original-patch regrades and verified test-name corrections. Each column uses valid scores only; incomplete columns are excluded from full 100-task rankings.
+
+| 指标 / Metric | 极简 minimal + high | 极简 minimal + max | 标准 standard + high | PTC + high | 创造 creative + high | 标准 standard + max |
+|---|---:|---:|---:|---:|---:|---:|
+| 有效进度 / Valid scores | 100/100 | 100/100 | 100/100 | 100/100 | 100/100 | 99/100 |
+| 通过/有效 / Passed / valid | 46/100 | 50/100 | 51/100 | 47/100 | 49/100 | 49/99 |
+| 待环境复评 / Pending regrades | 0 | 0 | 0 | 0 | 0 | 0 |
+| 原始分钟/题 / Original minutes | 25.685 | 32.529 | 20.683 | 17.302 | 19.856 | 20.452 |
+| 净分钟/题 / Net minutes | 25.122 | 32.009 | 18.826 | 15.122 | 18.714 | 19.561 |
+| 模型调用/题 / Model calls | 124.660 | 138.920 | 92.370 | 71.160 | 93.600 | 101.061 |
+| 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 | 11,526,872.192 |
+| 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 | 11,349,317.818 |
+| 非缓存输入 token/题 / Uncached input | 73,068.830 | 79,357.380 | 58,114.810 | 61,668.140 | 60,262.050 | 68,006.202 |
+| 输出 token/题 / Output | 100,876.950 | 116,599.720 | 82,820.870 | 77,499.860 | 87,662.110 | 109,548.172 |
+| 缺少用量的请求 / Requests without usage | 3 | 11 | 4 | 5 | 2 | 0 |
+
+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。复评分保留原作答的用量和耗时；有效题目范围变化时，均值会随之变化。未返回的用量不估算，数字不等于完整账单。
+
+Net time excludes failed requests and retry waits in the final valid answer; both time measures exclude grading. Call counts exclude logged failed requests. Total tokens = cached input + uncached input + output, including reasoning. Regrading preserves each answer's original usage and timing; means change when the valid subset changes. Missing usage is not estimated, so these figures are not a complete bill.
+
+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。极简 + high 复用历史基线，宿主修订与本轮不同，不能把差异完全归因于思考等级。
+
+Creative retains the official preset and tools; evaluation isolation blocks host-side dynamic execution through `cordis_run`, while read-only inspection remains available. Minimal + high reuses a historical baseline with different Harness revisions, so the results do not isolate reasoning effort.
+
+## 3.3 跨模型迁移 · Cross-Model Transfer
+
+将模型换为 **`glm-5.3-flash`**，思考等级统一为 **`max`**，仍使用同一批 hard-100。两组均完成 100 题：Super Code 使用 **DSH `0.1.5-rc.2` + 插件 `0.3.4`**；对照使用完整原生 **ZCode Desktop `3.14.4` / CLI `0.16.9`**，没有抽取部分源码模拟 Agent。
+
+Both runs completed the same hard-100 set using **`glm-5.3-flash`** with **`max`** reasoning. Super Code ran on **DSH `0.1.5-rc.2` + plugin `0.3.4`**; the comparison used the complete native **ZCode Desktop `3.14.4` / CLI `0.16.9`**, rather than an extracted Agent implementation.
+
+| 指标 / Metric | DSH + Super Code 0.3.4 | 原生 ZCode / Native ZCode |
+|---|---:|---:|
+| 通过 / Passed | 44/100 | 28/100 |
+| 净分钟/题 / Net minutes | 32.896 | 52.320 |
+| 模型调用/题 / Model calls | 66.890 | 64.310 |
+| 总 token/题 / Total tokens | 5,499,154.470 | 3,609,511.930 |
+| 缓存输入 token/题 / Cached input | 5,302,796.160 | 3,356,862.720 |
+| 缺少用量的请求 / Requests without usage | 29 | 120 |
+
+这轮 Super Code 通过率高 **16 个百分点**，平均净耗时更少，但 token 更多。这说明方案可在 GLM 上运行并取得有效结果；对照比较的是两套完整系统，不能据此分离插件的贡献，也不能推及所有模型。缺失用量未估算。[测试脚本与记录](eval/glm/README.md)
+
+Super Code passed **16 percentage points** more tasks and used less net time, but more tokens. This demonstrates working transfer to GLM in this run. The comparison covers two complete systems, so it neither isolates the plugin's contribution nor establishes gains across all models. Missing usage is not estimated. [Scripts and records](eval/glm/README.md)
+
+## 3.4 新版 DSH 与预算 · New DSH and Budgets
 
-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.
+以下四组均使用 **DSH `0.2.1-rc.2`**、新模型 **`deepseek-v4.1-flash-1017`**（调用标识 `deepseek/deepseek-flash`）和 **`high`** 思考，完成同一批 100 题。这里只展示官方预设与正式插件版本。
 
-| 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 |
+All four runs completed the same 100 tasks on **DSH `0.2.1-rc.2`**, using the newer **`deepseek-v4.1-flash-1017`** model (API ID: `deepseek/deepseek-flash`) with **`high`** reasoning. Only official presets and released plugin versions are shown here.
 
-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。
+| 指标 / Metric | 标准 / Standard · 默认 / Default | Super Code 0.3.4 · 默认 / Default | 标准 / Standard · 旧预算 / Legacy | Super Code 0.3.5 · 旧预算 / Legacy |
+|---|---:|---:|---:|---:|
+| 通过/有效 / Passed / valid | 45/100 | 40/99 | 46/100 | 48/99 |
+| 待核查 / Pending review | 0 | 1 | 0 | 1 |
+| 净分钟/题 / Net minutes | 17.875 | 20.458 | 20.870 | 16.486 |
+| 模型调用/题 / Model calls | 85.050 | 69.051 | 91.980 | 68.616 |
+| 总 token/题 / Total tokens | 6,832,805.820 | 5,125,240.424 | 7,806,295.960 | 5,131,724.556 |
+| 缓存输入 token/题 / Cached input | 6,710,566.400 | 5,008,071.111 | 7,679,298.560 | 5,016,822.909 |
+| 缺少用量的请求 / Requests without usage | 0 | 0 | 0 | 1 |
 
-Standard + max is paused, with 2 valid results and 0 passes, and is excluded from the completed 100-task comparison.
+两组 Super Code 各有一条 NodeBB 环境异常待核查，暂不计入有效评分和均值。npm 依赖已离线打包，但参考答案仍遇到初始化超时；原答案、判分记录和用量保留。
 
-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。
+Each Super Code run has one NodeBB environment issue pending review, excluded from valid-score counts and means. npm dependencies are bundled offline, but reference setup still times out; original answers, verdicts, and usage are retained.
 
-Creative retains the official preset and tool definitions. Evaluation isolation blocks host-side dynamic execution through `cordis_run`; read-only inspection remains available.
+- **新版组合出现退化。** 相比旧 DSH / 旧模型，标准通过数从 51 降到 45，Super Code 从 0.3.0 候选的 56 降到 0.3.4 的 40；这同时涉及宿主、模型和插件版本变化。
+- **预算是已定位的影响因素。** 新版更早压缩上下文、保留更少原文，PTC 执行时限也有变化。恢复旧预算后，Super Code 从 40 回升至 48，标准从 45 到 46。**0.3.6 已默认恢复旧预算**；表中验证组实际是 **0.3.5 + 显式旧预算**，不是另跑的 0.3.6 成绩。
+- **结果仍有波动。** v4.1 的多轮实验中，同一道题存在一轮通过、另一轮失败的情况。后续版本会尝试改善这种不稳定性；各轮配置也有变化，本轮回升不代表已消除波动，也不能证明全部退化都由预算造成。
 
-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。
+- **The newer combination regressed.** Standard fell from 51 passes on the older host/model to 45; Super Code fell from 56 for the 0.3.0 candidate to 40 for 0.3.4. Host, model, and plugin versions changed together.
+- **Budgets are one identified factor.** The newer host compresses earlier, retains less verbatim context, and changes PTC execution deadlines. Restoring the older budgets raised Super Code from 40 to 48 and standard from 45 to 46. **Version 0.3.6 restores these defaults.** The measured row is **0.3.5 with explicit legacy budgets**, not a separate 0.3.6 run.
+- **Run-to-run variation remains.** Across v4.1 experiments, the same task has both passed and failed. Future versions will aim to reduce this variability. Configurations also changed between runs; the recovery does not establish stability or attribute the entire regression to budgets.
 
-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.
+[预算诊断、逐题记录与限制 · Budget diagnosis, per-task records, and limitations](docs/EvaluationResults.md#新版-dsh-与预算--new-dsh-and-budgets)
 
 [多维指标、逐题证据与统计口径](docs/EvaluationResults.md)