michael-han-il/dsh-llm-finish-reason-tolerance

这是一个DeepSeek Harness主机插件,使智能体能够容忍那些流式响应结束时未提供finish_reason的兼容OpenAI的提供商。典型情况是Snowflake Cortex REST API网关。

Project Overview项目介绍

This is a DSH host plugin for OpenAI-compatible providers whose streaming responses end without finish_reason, such as Snowflake Cortex. It hooks llm/stream and, only when content was delivered and pi-ai raises “Stream ended without finish_reason,” rewrites the terminal result to stop or tool-calls; other errors pass through unchanged. Use it when delivered content is wrongly marked as a transport failure. It must be installed in a profile, mounted at host level, and requires a restart.

这是一个 DSH 宿主插件,用于兼容流式响应缺少 finish_reason 的 OpenAI 兼容提供商(如 Snowflake Cortex)。它监听 llm/stream,仅在已收到内容且出现“Stream ended without finish_reason”终止错误时,将结果改写为 stop 或 tool-calls;其他错误原样透传。适用于内容已返回却被判为传输失败的场景。注意:需装在 profile 并由宿主组合挂载,安装后须重启。

Pre-install check安装前体检Compatibility · Security兼容性 · 安全性 1 warning1 项注意
  • Only 2 stars - very few users, little community feedback星标只有 2,几乎没人在用,遇到问题缺少社区反馈
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 github:michael-han-il/dsh-llm-finish-reason-tolerance

把 michael-han-il/dsh-llm-finish-reason-tolerance 加入你的 DSH 配置(web profile)即可启用。

READMEREADME

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 gateway (*.snowflakecomputing.com/api/v2/cortex/v1): its Chat Completions SSE streams content deltas and a terminal data: [DONE] but never sends a finish_reason — not for plain text, not for tool calls (non-streaming responses return finish_reason: ""). The harness's model client (pi-ai) treats that as a truncated stream (Stream ended without finish_reason), and the harness maps it to a TRANSPORT error finish. Every request delivers content and then fails the turn.

This plugin rewrites only that specific terminal error into the successful finish the content already deserves.

How it works

The plugin listens on the harness's llm/stream waterfall (registered globally and prepended, so its returned iterable is the one consumers iterate) and wraps every model stream:

  • a tool-call block was delivered → the terminal finish becomes { kind: 'tool-calls' }
  • text content was delivered → the terminal finish becomes { kind: 'stop' }
  • nothing was delivered, or the error is anything else → passed through untouched

The rewrite is gated on both the exact pi-ai message (Stream ended without finish_reason) and on delivered content, so genuine mid-stream truncations (which surface as different pi-ai errors) are never masked.

No changes to pi-ai, dsh-llm, or dsh-llm-pi-ai are required.

Requirements

  • DeepSeek Harness (any recent deployment; @deepseek-ai/cordis ≥ 4 and @deepseek-ai/schemastery ≥ 3 are already present)
  • Node ≥ 20
  • The plugin must be installed into a profile (e.g. web) and mounted in the host composition — it is host-level and single-instance. Do not mount it inside an agent preset.

Install

The package is shipped as a profile bundle: it carries its own cordis.patch.yml layer (declared via dsh.bundle.patch in package.json), so installing it mounts the plugin with no manual composition editing.

Bundle install (recommended)

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 →

← 上一个 Prev dsh-billing-glass 下一个 Next dsh-specify-lite →