Configure model input capabilities and reasoning efforts for DeepSeek Harness

Per-model capability declarations (image input and reasoning efforts) for custom pi-ai providers, edited in place on the Models settings cards; writes the official llm-pi-ai settings namespace, no DSH source changes.

DSH plugin: auto-detect and configure model capabilities (reasoningEfforts + input modalities) for llm-pi-ai. Successor to dsh-reasoning-efforts.

Auto-complete missing model display name, context window, max output tokens, and reasoning efforts in the llm-pi-ai settings namespace.

DeepSeek Harness LLM adapter plugin for locally deployed Qwen models behind a vLLM OpenAI-compatible endpoint: per-model multimodal switch, fully configurable reasoning efforts, and a web settings page (client plugin) for editing the deployment from the f

DeepSeek Harness plugin: the Models+ settings page — a fully plugin-owned model/provider UI with per-model extension fields (reasoning efforts, input modalities, compat flags) and models.dev metadata prefill

DSH plugin: auto-detect thinking levels (reasoningEfforts) for custom models in llm-pi-ai settings.

DSH plugin: when a provider's model sync returns only ids, automatically fill display name, context window, max output tokens, reasoning efforts, and input modalities from the models.dev catalog (cached, TTL-refreshed), and surface a settings page with to

Declare per-model reasoning efforts, image input, and openai-completions dialect on hand-declared llm-pi-ai routes. Writes the official namespace; does not intercept llm/stream or replace the Models page.

Unified ModelID routing for DeepSeek Harness: one logical model id over multiple providers, first-token failover with cooldown, health-aware ranking, fallback reasoning efforts, purpose-based simple/complex task split, per-tier reasoning effort, and a set

DSH Web GUI 模型能力配置：在「设置 → 模型」的模型目录编辑器内，为每个已配置的模型直接设置是否支持图像与思考等级（reasoning efforts），写入 llm-pi-ai 设置命名空间。

Apollo Federation internal utilities

Storybook for SvelteKit: Develop, document, and test UI components in isolation

Grammar parsing support for cspell

SOTA NPM module for agentic processes using local or cloud LLMs.

The **[Alibaba provider](https://ai-sdk.dev/providers/ai-sdk-providers/alibaba)** for the [AI SDK](https://ai-sdk.dev/docs) contains language model, embedding model, and video model support for [Alibaba Cloud Model Studio](https://modelstudio.console.alib

[](https://www.npmjs.com/package/@agentclientprotocol/codex-acp)

Smoothly Model Reasoning (Smoothly MR) — 思磨力提供方参数: external DeepSeek Harness web client plugin — a Settings page managing llm-pi-ai provider-route parameters (retry & backoff, timeouts, transport, caching, budgets, capacities) plus per-model reasoning eff

Presentation-complete Agent Client Protocol server for deepseek-harness: streaming text, reasoning, tool cards, inline diffs, plans, usage, commands, permission prompts, and resumable sessions

Playwright Tools for MCP