dsh-model-health-probe
Manual model probe for DeepSeek Harness: a session-view tab where you pick provider, API type, model and route, then send one real raw HTTP request over openai-completions, openai-responses or anthropic-messages — streaming or not — and read latency, TTFT, HTTP status, token usage and a three-layer diagnosis chain (API request / model response / strict check) on one screen, with errors in plain language.
DSH 模型健康检查：会话视图页签内按「供应商 → API 类型 → 模型 → 路由」选定目标，手动发一条真实裸 HTTP 请求（支持 openai-completions / openai-responses / anthropic-messages 三协议，流式可切），一屏看清耗时、TTFT、HTTP 状态、token 用量与三层诊断链（API 请求 / 模型响应 / 严格校验），错误全部人话化。
How to install
dsh plugin add dsh-model-health-probe About
dsh-model-health-probe DSH（DeepSeek Harness）插件：在**会话视图**内新增「**模型健康检查**」页签。手动选定一条「供应商 → API 类型 → 模型 → 路由」，点一下发送**一条真实的裸 HTTP 测试请求**，一屏看清：耗时、TTFT、HTTP 状态、token 用量、响应内容，以及**三层诊断链**（API 请求 / 模型响应 / 严格校验）到底卡在哪一层。 **这是一个手动探针，不是监控系统。** 不轮询、不监控、不告警、不做历史趋势、不落盘。它提供的是**用户显式启动、成功即停的有限重试会话**（见下文「自动重试」）——那**不是**后台常驻监控：单例运行、成功即停、结束不自动重启。 **包名**：dsh-model-health-probe。源码目录、包名、origin 仓库三者同名。 它解决什么问题 DSH 的模型配置里，同一个供应商可能同时挂多种协议，而 baseURL 的 /v1 后缀规则在两种协议下**恰好相反**： | 协议 | 路径 | baseURL 是否自带 /v1 | | --- | --- | --- | | openai-completions | /chat/completions | **必须自带** | | openai-responses | /responses | **必须自带** | |…
Recommendation signals
Meta
- License
- MIT
- Language
- JavaScript
- GitHub stars
- 0
- mo. downloads
- –
- Last push
- 2026-09-18
- Created
- 2026-09-18
Basic safety check
- Findings
- None
- Sources
- curated:awesome-dsh-plugin.com, curated:awesome-dsh-plugin/awesome-dsh-plugin
- Topics
- dsh-plugin
Related plugins
langfuse
langfuse/langfuse
🪢 Open source agent evals & observability: Trace, evaluate, and improve LLM applications with one open platform.
claude-code-templates
davila7/claude-code-templates
CLI tool for configuring and monitoring Claude Code
cc-safety-net
kenryu42/claude-code-safety-net
A pre-execution guard for AI coding agents. It blocks destructive Git and file system commands, plus common attempts to access sensitive files, before a tool call runs. Supports Amp Code, Antigravity CLI, Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot CLI, Grok Build, Hermes Agent, Kimi Code, OpenClaw, OpenCode, and Pi.
loki-mode
asklokesh/claudeskill-loki-mode
Multi-agent autonomous SDLC framework. Spec to deployed app. PRD, GitHub issue, OpenAPI/JSON/YAML, or one-line brief. 5 AI providers, 8 quality gates.