Plugins

gopkg fork：接入 WorkBuddy / WorkBuddy AI 模型，支持按模型选择上下文窗口与桌面客户端请求格式。WorkBuddy models for DSH with selectable context windows.

Automatic tier-based model routing for DeepSeek Harness: a virtual `smart` model classifies each request by difficulty (hard / normal / easy) and by vision need, then delegates it to the models you already configured. 三级难度 + 视觉自动路由，虚拟 smart 模型零配置接入。

Anchored Standard preset with GPT Patch mode: task-aware first-request anchors using the bundled OpenAI Codex apply_patch instead of edit/write. Built for GPT/Codex models.

OpenRouter free-models browser plugin (dual-face): fetch OpenRouter models, filter the free ones (price 0 or :free), list them newest-first in a Settings tab with local search and full model info, and create a ready-to-use DSH model config (settings.yaml

Digests the images in a prompt with a vision model before admission, so any model — a text-only one included — can read them without the session ever switching models, and adds a describe_image tool for image paths.

Search and select models in the DeepSeek Harness WebUI with a native settings card.

Declares per-model reasoning-effort ladders for third-party providers in the llm-pi-ai settings section, so DSH's stock thinking-intensity selector works on models the pi-ai catalog does not describe.

Connect DeepSeek Harness to ChatGPT models through the Codex app-server

Adds per-route context window and compaction threshold fields to the Models settings page and a vendor-aware thinking-effort picker to the composer, writing llm-pi-ai capacities, reasoningEfforts, and a compaction-basic patch row.

LiveBench leaderboard for DSH — discovers the release the official site currently publishes, then reads its CSV and category JSON, and renders model rankings in an isolated same-origin iframe opened from a button beside the composer. Search, organization / open-weight / reasoning filters, per-category sorting, task-level detail, up to four models side by side, CSV export; refreshes every 60 s by default (configurable 30–3600) and caches only to the plugin's own .cache/rankings.json.

Per-provider request headers in the DeepSeek Harness Models settings page, with per-conversation ${sessionId} expansion.

PK 2-10 models on the same prompt, files, and tools in DeepSeek Harness.

DeepSeek Harness plugin: expensive models plan and review, cheap models implement, a program loop keeps the factory inside budget.

Auto-switch DeepSeek models: routes every request to the vision model when images are present, to the pro model for complex tasks, and to the fast model otherwise; includes a switch_model tool for manual overrides.

Model switching, model capability configuration, fixed compaction models, subagent routing, and input history enhancement.

Consult multiple expert advisor models in a retro CRT chat-group card: one ask_advisors call runs an auto-deepen pipeline (driver deep-question, advisor relay, synthesis conclusion) with SSE streaming, 26 provider presets, a configurable daily quota, stop/resume, and optional advisor tool calling.

Keeps every model request inside a per-provider allow-list, enforced at the agent/request waterfall: disallowed models are redirected to a fallback or refused; subagents stop inheriting stale creation-time routes; warns when consecutive requests would make a --models-max 1 llama.cpp router reload models. A one-entry list is a global single-model mode.

Task Runner mode for DeepSeek Harness: the main agent decomposes large tasks into independent subtasks, dispatches them to subagents (default local model) in fresh short contexts, and synthesizes results; concurrency and worker/orchestrator models are configurable in the settings panel.

Vision bridge for text-only DeepSeek models: transcribes attached images with deepseek-v4-flash-vision-exp before they reach deepseek-v4-pro, with no third-party dependencies.

Apple on-device Vision tools for text-only dsh models: local OCR (zh-Hans + 30 langs), image classification, face detection, document layout, and a combined describe — 100% offline, no API key, tall-screenshot slicing.

Deterministic Reasoning Engine (DRE) for dsh: dre__* tools for knowledge verification (three-stage discrimination), deterministic cognition loops, constraint solving, mental models and synapse memory - strengthens information certainty.

Codex-shaped coding tools and agent presets for GPT models on DeepSeek Harness: exec_command, write_stdin, apply_patch and view_image, plus OpenAI Chat Completions and Responses API routes, bridged to DSH-native plan, ask, approval and compaction. Long-running commands become DSH background jobs with bounded head/tail output readable through job_output, and each subagent type can be pinned to its own preset, provider, model and reasoning effort.

Add missing reasoning-effort declarations to custom pi-ai models through DSH settings, enabling the native effort picker and handling models added later.

Bring OpenCode Zen free models to DSH: 8 live-discovered providers with zero config, no API key; includes persistent quota tracker with rate-limit detection and reset countdown.