AI Agent Hub
Back to plugins
🤖

dsh-langfuse

Model Inference Updated 2026.08.15

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