DeepSeek Harness Plugin Hub

Publish and manage complete Harness Profiles. Discover Plugins for your next setup.

Explore

PluginsPresetsDocsNews

Community

Publish a pluginContactReport an issue

Resources

Plugin Hub on GitHubDeepSeek HarnessSystem statusPrivacy notice
© 2026 DeepSeek Harness Plugin HubPowered byPaxTech

Independent and unofficial. Not affiliated with, authorized by, or endorsed by DeepSeek.

Llm Capture — DSH Plugin for DeepSeek Harness
DeepSeek Harness Plugin Hub
ProfilesPluginsCategoriesNewsDocsSign inManage Profiles
ProfilesPluginsCategoriesNewsDocsSign in
← Plugins
L

dsh-llm-capture

Llm Capture

Inspect raw LLM requests and responses in DeepSeek Harness Web

The plugin will be installed here. Keep web if you are unsure.

npx -y @deepseek-ai/dsh plugin --profile web add github:chengzhicao/llm-capture#cd3d737ff3f350c7bc67d6fdae5a4d2e0d352676
READMECompatibilityVersions
LLM Capture 界面

Compatibility and provenance

Llm Capture is published as dsh-llm-capture and currently resolves to version 0.1.0. The Hub verifies its manifest and preserves the exact installation source for reproducible installs.

DSH compatibility
*
Runtime surfaces
web
Release source
github
Registry updated
9/9/2026

Versions

0.1.0stable
9/9/2026

Related plugins

Loading related plugins…

Latest
0.1.0
DSH
*
HMR
Process restart
Tree shaking
Safe tree shaking not declared
Unpacked size
Unavailable
Files
Unavailable
Surface
web
License
Not declared
Source
github
GitHub
★ 0
Weekly downloads
0
Last push
9/9/2026
View source ↗
README badge

Click the badge to copy Markdown for your README.

Do you maintain this Plugin?Claim benefit · Priority security scan

Verify the GitHub repository declared in package.json to manage this listing. After you claim it, Hub will prioritize a security scan of the current version and publish the result when it passes.

Claim this Plugin →
Report an issue

Related plugins

More verified plugins in models-usage.

Usage@linxin666/dsh-usageUsage statistics plugin for the dsh web GUI: per-provider balance and coding-plan quota detection plus a live token usage ledger, with the current session provider's today usage on the sidebar entryWhale Widgetdsh-whale-widgetDeepSeek balance whale widget in the bottom-right corner of the DSH Web interface: balance/today’s usage/peak-off-peak pricing, customizable bubble click sequence (text/balance/today/peak-off-peak/image/random phrases and parallel weighted selection), per-line styles and fonts, floating quick editinCommandcode Provider@mars-sea/dsh-commandcode-providerUnofficial DeepSeek Harness LLM provider plugin for Command Code, ported from pi-commandcode-provider (MIT). Registers the 'commandcode' provider route with a Models-page card and live model catalog.Codex Connectdsh-codex-connectChatGPT OAuth and Codex models for DeepSeek Harness.

README

LLM Capture

LLM Capture 是 DeepSeek Harness Web 的调用日志插件。它在会话页面增加独立的 LLM Capture 标签页,用于查看模型请求、消息、返回内容、Token 用量、耗时和工具调用。

LLM Capture 界面

功能

  • 按 Session 记录完整的 LLM 请求与响应。
  • 展示模型、Provider、耗时、Token 用量和完成原因。
  • 支持请求、消息、返回和原文四种详情视图。
  • 支持全文搜索、手动刷新和清空当前 Session 的日志。
  • 每个 Session 独立编号,新 Session 从 #1 开始。
  • 日志持久化到本地,重启 DSH 后仍可查看。

安装

LLM Capture 需要 DeepSeek Harness Web 和 Node.js ^22.19.0 || >=24.0.0。

dsh plugin --profile web add github:chengzhicao/llm-capture

安装完成后启动 Web:

dsh web

需要卸载时执行:

dsh plugin --profile web remove dsh-llm-capture

使用

  1. 打开或创建一个会话并发起模型调用。
  2. 点击会话顶部的 LLM Capture 标签页。
  3. 在左侧选择一次调用,在右侧查看请求、消息、返回或原文。
  4. 使用搜索框过滤当前 Session 的请求和返回内容。
  5. 点击“清空”会清除当前 Session 的内存记录,并将对应日志文件覆盖为空数组;其他 Session 不受影响。

日志存储

日志默认保存在启动 DSH 时的工作目录下:

tmp/llm-capture-data/

每个 Session 对应一个 JSON 文件。日志文件包含完整提示词、消息、工具参数和模型返回,请勿提交到版本库或发送给不受信任的第三方。

可以在 $DSH_HOME/cordis.patch.yml 中覆盖存储配置:

- id: llm-capture
  config:
    directory: tmp/llm-capture-data
    capacity: 500
    flushDelayMs: 400
配置项默认值说明
directorytmp/llm-capture-data日志目录;相对路径基于 DSH 的工作目录解析
capacity500每个 Session 在内存和磁盘中保留的最大记录数
flushDelayMs400合并连续磁盘写入的等待时间,单位为毫秒

修改配置后重启 DSH 生效。插件不会自动迁移自定义目录中的旧日志。

工作方式

Host 插件监听 llm/stream,在不改变模型输出的前提下收集请求和流式返回,并按 Session 写入 JSON 文件。Web Client 通过 llmLog Remote 接口读取和清空记录,不直接访问主机文件系统。