dsh-langfuse
Run the following command in DeepSeek Harness:
dsh plugin install TtTRz/dsh-langfuse
Paste the following prompt into your AI chat to install this plugin:
Install this plugin in DeepSeek Harness by running dsh plugin install TtTRz/dsh-langfuse. Source: https://github.com/TtTRz/dsh-langfuse
About this plugin
When building complex LLM applications, developers often struggle with unclear session flows, difficulty tracking token consumption, and blind spots in sub-agent interactions. The dsh-langfuse plugin addresses this by transforming every agent session in DeepSeek Harness into a standard OpenTelemetry trace tree, achieving full-link visualization from model generation to tool calls, while automatically capturing time-to-first-token and error states.
Use Cases
- Trace LLM sessions and tool call chains
- Monitor token usage and generation costs
- Analyze subagent hierarchies and feedback data
Best For
- Developers building agents with DeepSeek Harness
- Teams needing fine-grained control over token costs and performance
- Enterprise users requiring auditability and debugging of AI interactions
Related Plugins
ModLens is a vision plugin for DeepSeek Harness that gives text-only models sight by reading images pasted directly into chat, with zero-config setup and multiple vision engines.
On-demand vision for text-only DeepSeek Harness agents: built-in free keyless vision chain and 14 vision tools, routing image turns as tool calls to vision models with pixel fidelity, no Python needed, one-command install.
Give text-only models in DeepSeek Harness eyes, enabling image Q&A, long-screenshot OCR, UI restoration, and GUI visual tasks.
An armor-breaking plugin for DeepSeek: rewrites instruction priority, expands refusal-blocked phrases, persists across sessions, and shows a green active indicator.