linyp/dsh-plugin-langfuse
Langfuse 对 DeepSeek Harness (dsh) 的可观测性支持:将代理会话作为 OpenTelemetry 跟踪树(GenAI semconv)导出到 Langfuse 的 OTLP 端点。
Project Overview项目介绍
This is a community-built native plugin for DeepSeek Harness (DSH) that enables Langfuse-based observability for DSH agent sessions. It is not part of the official DSH repository, but is fully compatible with the current DSH release. It exports every conversational turn as an OpenTelemetry trace, mapping model generation steps to dedicated spans and tool calls to their own separate spans, grouping all turns under the correct session identifier. It also records session comments and user message ratings as Langfuse Scores, preserves the full lineage of forked sessions and sub-agents, and implements DSH’s public telemetry seam as an alternative backend to the official OTLP logs exporter.
To install the plugin, you first need to have the DSH CLI installed on your machine, then run the command dsh plugin --profile web add dsh-plugin-langfuse to add it to your web profile. After installation completes, you need to set three environment variables: LANGFUSE_PUBLIC_KEY, LANGFUSE_SECRET_KEY, and optionally LANGFUSE_HOST if you are not using the default EU Langfuse cloud instance. Once you have set the variables, restart your DSH instance to activate the plugin, and you can also manually edit the cordis.yml file to add custom configuration for tracing modes and privacy settings.
The plugin is released under the open-source MIT license, so it is free to use, modify, and distribute for any purpose. There are several known limitations to note: message ratings are stored only as session-level scores, there is no persistent outbox for unflushed trace data so a process crash can lose pending data, and you can only run one observability backend per DSH context. Before using the plugin for production workflows, you should review these limitations to confirm they align with your observability requirements.
这是一个专为 DeepSeek Harness (DSH) 开发的原生社区插件,用于接入 Langfuse 可观测性平台。它会将会话中的每一轮交互导出为 OpenTelemetry 追踪,把模型生成步骤、工具调用分别对应到不同追踪 span,按会话分组追踪数据,同时将会话备注和消息评分记录为 Langfuse 分数,还保留了分叉与子代理的谱系关系。它基于 DSH 官方公开的可观测性接口开发,是官方 OTLP 日志导出器的替代后端。
用户可以通过 DSH CLI 直接安装该插件,安装后需要配置环境变量填入 Langfuse 的项目公钥、私钥,还可以根据自己使用的 Langfuse 区域修改 LANGFUSE_HOST 地址。安装完成后重启 DSH 即可生效,也支持手动在 cordis.yml 中添加配置项自定义模式、隐私控制等参数。适合需要对 DSH 会话进行可观测性分析、留存追踪数据的开发用户。
该插件遵循 MIT 许可证开源,免费使用。目前存在一些已知限制,比如消息评分仅作为会话级分数存储,不会关联到单独的 Langfuse 观测项,没有持久化保证,进程崩溃可能丢失未刷新的数据,同一上下文只能运行一个可观测性后端。使用前需要确认这些限制符合自己的使用需求。
请帮我安装这个 DSH 插件。安装前先完成【兼容性检查 + 安全性检查】,检查通过再动手。
插件:dsh-plugin-langfuse(linyp/dsh-plugin-langfuse)
仓库:https://github.com/linyp/dsh-plugin-langfuse
本站详情页:https://www.yhbd.top/plugins/linyp-dsh-plugin-langfuse/
本站登记:类型 plugin · 归类 原生 DSH 插件 · 许可证 MIT · ⭐ 13 · 最近提交 2026-09-24 · 主语言 TypeScript
按下面顺序执行,每步先把结论告诉我,再进入下一步:
【1 兼容性检查】
① 我这边:DSH 版本、Node 版本、操作系统、当前 profile(web / desktop)。
② 读它的 README、package.json、插件 manifest,列出它要求的 DSH 版本 / Node 版本 / 操作系统 / 外部依赖 / 需要另外先装的运行时。
③ 逐条比对,结论只写「满足 / 不满足 / 未知」三种;不满足的给出可行替代方案。
④ 检查是否和我已装的插件冲突:命令名重复、skill / tool 重名、端口占用、重复注册的 MCP server。
【2 安全性检查】
① 仓库可信度:和上面「本站登记」是否一致;star / fork 数、创建时间、最近提交,是否归档或长期停更。
② 安装脚本:逐行看 package.json 的 preinstall / install / postinstall,以及 install.sh、setup.ps1 之类脚本。出现 curl|bash、下载后直接执行、混淆代码、访问与插件功能无关的域名,立刻停下来告诉我,不要继续装。
③ 依赖:列出新增依赖,标出无人维护、或与知名包拼写近似的可疑包(typosquatting)。
④ 权限与副作用:它会读写哪些目录、访问哪些域名、需要哪些 DSH 权限(filesystem / network / shell / clipboard 等),以及怎么卸载和回滚。
⑤ 如果它要求 sudo / 管理员权限,或权限明显超出功能所需,先停下来问我。
【3 安装】
上面两步没有「不满足」和「高危项」时才执行;用官方推荐方式安装,不要自行提权。
【4 汇报】
用表格输出:检查项 / 结论 / 依据 / 是否需要我决策。拿不准的一律写「未知」并说明要我怎么确认——不要猜,也不要替我决定。
Send this message to DSH in your current session: it verifies compatibility and security first (answering met / not met / unknown item by item) and only installs once everything checks out — it will stop and ask you if it finds a high-risk item. The box scrolls; the copy is the full prompt. CLI install commands may not be accurate across systems, so DSH is the safer route.把上面这条消息直接发给当前会话里的 DSH:它会先核对兼容性与安全性(逐条给「满足 / 不满足 / 未知」),确认没问题再安装,有高危项会停下来问你。框内可滚动,复制到的是完整提示词;安装命令不一定准确,发给 DSH 更稳。
- 13 stars - an early-stage project星标 13,属于早期项目
DSH walks through these 9 checksDSH 会逐条核对这 9 项
Compatibility兼容性
- DSH, Node, OS and profile requirementsDSH 版本 / Node 版本 / 操作系统 / profile 是否满足要求
- External dependencies and runtimes (Electron / Python / Docker, ...)外部依赖与运行时(Electron / Python / Docker 等)是否齐备
- Conflicts with installed plugins: command names, skill / tool names, ports, duplicate MCP registration与已装插件是否冲突:命令名、skill / tool 重名、端口占用、重复 MCP 注册
Security安全性
- Repo matches the facts registered here; archived or abandoned?仓库是否与页面登记一致,是否归档或长期停更
- Safety of preinstall / install / postinstall and install.sh / setup.ps1preinstall / install / postinstall 与 install.sh、setup.ps1 是否安全
- curl|bash, download-then-execute, obfuscation, unrelated domains → stop immediatelycurl|bash、下载即执行、混淆代码、无关域名 → 立刻停止
- Typosquatting or unmaintained packages among the new dependencies新增依赖里有没有 typosquatting 或无人维护的包
- Requested permissions vs. what the feature actually needs申请了哪些权限、是否超出功能所需(filesystem / network / shell / clipboard)
- Any sudo / admin requirement, plus uninstall and rollback是否要求 sudo / 管理员权限,以及卸载与回滚方式
Anything uncertain must be marked unknown with a note on how to confirm it. This site's signal screen is a static snapshot, not a security audit.拿不准的必须标「未知」并说明要我怎么确认。本站的信号筛查是静态快照,不能替代安全审计。
Or use CLI install (for developers)或使用命令行安装(适合开发者)
CLI Install命令行安装
dsh plugin --profile web add dsh-plugin-langfuse
把 linyp/dsh-plugin-langfuse 加入你的 DSH 配置(web profile)即可启用。
READMEREADME
dsh-plugin-langfuse
English | 中文
Langfuse observability for DeepSeek Harness (dsh): exports each turn as an OpenTelemetry trace — model step → generation, tool call → tool span — groups turns by session, records session remarks and message ratings as Langfuse Scores, and preserves fork/subagent lineage.
This is a community plugin (dsh-plugin topic), not part of the official repository. It implements the harness's public telemetry seam (@deepseek-ai/dsh-session-telemetry) as an alternative backend to the official OTLP-logs exporter.
Install
The commands below assume the installed dsh CLI. Running the official harness from a source checkout instead? Run each of them as pnpm dsh … from the checkout root (after its pnpm run build) — same commands, same web profile.
As a profile bundle (the package ships a cordis.patch.yml patch layer):
dsh plugin --profile web add dsh-plugin-langfuse
export LANGFUSE_PUBLIC_KEY=pk-lf-…
export LANGFUSE_SECRET_KEY=sk-lf-…
# optional, defaults to https://cloud.langfuse.com (EU region); note the plugin
# reads LANGFUSE_HOST, not the Langfuse SDK's LANGFUSE_BASE_URL
export LANGFUSE_HOST=https://us.cloud.langfuse.com
dsh web # alias for: dsh --profile web
The bundled patch disables the base profile's session-telemetry-otel row (the telemetry seam accepts exactly one backend per context; a duplicate load throws) and mounts this backend in FULL mode when a Langfuse key is present, DISABLED otherwise. It also enables feedback Scores when both project keys are present. LANGFUSE_TELEMETRY_MODE=FEEDBACK_ONLY narrows sharing to feedback-gated release.
Both the bundle layer and the env vars are read at boot: an already-running instance must be restarted after installing, from a shell that has the variables set. dsh --profile web --dump-config shows the composed result without booting — a # == dsh-plugin-langfuse layer that patches the base telemetry row and adds session-telemetry-langfuse with its env-driven mode. After the next turn, traces appear in the Langfuse console of the region LANGFUSE_HOST points at — keys are region-scoped, so a US project shows nothing on the EU console. dsh plugin --profile web remove dsh-plugin-langfuse removes both the dependency and the layer.
Showing the opening section of the README — the full document lives in the repository以上为 README 开头摘要,完整文档在仓库内 · View the full README on GitHub →在 GitHub 查看完整 README →
extracurricular-ai/dsh-filesnap
SenmuuuuW/dsh-whale-report
SnowCrescenter-tech/dsh-milestone
PerryLink/dsh-checkpoint-rewind
XieZongChen/dsh-md-notes
TencentCloud/tencentcloud-agentobs-sdk-dsh