dsh-apply-model-all

Apply the current session's model to every session in one click: a compact control next to the composer's model picker that writes the active provider/model into the per-session model selection of every session that can hold one. 适合需要快速统一多个会话的模型及供应商配置的用户。

Productivity

Package: dsh-apply-model-all
Compatibility: Unverified
Harness peer range: >=0.2.0-rc.1 <0.3.0-0
Version: 0.1.0
License: MIT
Last updated: Oct 4, 2026

Install

$npx -p @deepseek-ai/dsh dsh plugin --profile web add github:SYXliuliuliu/dsh-apply-model-all

README

Read the full README ↗

Configuration

None. There are two host routes and no settings surface:

POST /apply-model-all/start    {provider, model, reasoningEffort?}  → {runId}
GET  /apply-model-all/status                                        → {run: {…}}

Only one run may be active at a time; a second request returns 409 with the in-flight progress. Failures are grouped by reason in the response rather than repeated per session, and failure detail is capped at 50 entries.