How to use dsh-plugin-langfuse

This article is derived from the plugin's already-indexed fields (wiki / faq / compatibility_json / readme), not freshly generated by AI. Source field is noted at the end of each section.

Quick start

Langfuse observability for DeepSeek Harness (dsh): exports agent sessions as OpenTelemetry trace trees (GenAI semconv) to Langfuse's OTLP endpoint

— source: plugins.ai_summary

Install & verify

dsh plugin --profile web add dsh-plugin-langfuse

Run the command above in your DSH Web Profile. Then enable the plugin in the plugin list.

— source: plugins.install

Key points

• id: session-telemetry-langfuse
• sessionId defaults to the dsh session id, and the original dsh session id stays on each logical root as dsh.session.id — the pointer back into $DSH_HOME/sessions for local diagnosis.
• Static correlation values bypass the redaction waterfall: the waterfall transforms records, and these values never transit one.
• Delivery semantics are unchanged: correlation is identity, not dedup — duplicates remain possible (see decision 5).
• capture of everything model-visible — including subagent, workflow, compaction, and plugin events this package has never heard of;

— source: plugin_wiki.readme_en (fallback readme_raw)

Pitfalls

Review the upstream repo before installing. This guide is auto-derived from indexed fields and may lag the latest release. If anything contradicts the official docs, treat the upstream source as authoritative.

— source: general rule