Skip to main content

How to use dsh-llm-finish-reason-tolerance

A DeepSeek Harness host plugin that makes the agent tolerate OpenAI-compatible providers whose streaming responses end without a finish_reason. The canonical case is the Snowflake Cortex REST API gateway.

This article is auto-derived from indexed fields (wiki / faq / compatibility_json), not freshly AI-generated.

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

A DeepSeek Harness host plugin that makes the agent tolerate OpenAI-compatible providers whose streaming responses end without a finish_reason. The canonical case is the Snowflake Cortex REST API gateway.

— source: plugins.ai_summary

Install & verify

dsh plugin --profile web add github:michael-han-il/dsh-llm-finish-reason-tolerance

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

— source: plugins.install

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