llm 220

DeepSeek Harness plugin: provider sign-in, model catalog, and selection routing over a loopback-only /model-hub channel

Kimi K3 connector plugin for the DeepSeek Harness llm capability seam.

AI news & hot topics panel for DSH: LLM / Agent / AI creation trends / AI hot topics / AI short-drama (manju), powered by DeepSeek web search with on-demand AI summaries

Content-moderation rescue for dsh: a provider's content moderation (DeepSeek HTTP 400 'Content Exists Risk' / INVALID_REQUEST) rejects an entire request, and because the loop re-derives the whole conversation from the session log on every turn, one stored

DSH 双模型路由插件：主对话留在 DeepSeek，图片任务自动分发到显式配置的视觉模型，再把分析结果交回 DeepSeek 继续。

Ollama 监控与测评平台：node 半侧提供 DSH 工具，web 半侧提供设置页内的交互面板

CodeBuddy LLM provider bundle for the DeepSeek Harness web GUI: registers the `codebuddy` provider route, its Models-page card, and its model picker entries, authenticating against the machine's CodeBuddy desktop-app login, with per-model measured image i

The LLM debug console inside DeepSeek Harness — capture every model call, see everything, replay anything.

A dsh plugin that replaces the built-in llm-pi-ai and llm-deepseek adapters, the model selector and the Models settings page with self-maintained versions, tracks upstream @earendil-works/pi-ai, adds OAuth/device-code sign-in for subscription providers (C

Calendar todo plugin for the dsh web GUI: a sidebar entry plus a week/month calendar where you drag-select time ranges to create tasks, with Eisenhower urgency/importance quadrants, subtasks, pinned execution session + LLM provider, and host-authoritative

Memory plugin with built-in governance for DeepSeek Harness

Deterministic, zero-LLM, byte-budget context compaction for DeepSeek Harness, with byte-exact recall of compacted history.

OpenCode gateway provider for DeepSeek Harness: the Zen pay-as-you-go plan and the Go subscription, with their settings UI

OpenCode Go provider for DeepSeek Harness: live gateway catalog, per-conversation session header, usage

Plan Checkup for DeepSeek Harness: checks each step of a plan with Jev or a local LLM before you approve it, and marks the results on the plan review card.

Configurable DSH session title templates with semantic refinement, icons, and safe model fallback.

Content-free request and stream diagnostics for DeepSeek Harness

Keep DSH provider model catalogs current with the living models.dev catalog: refreshes each provider's models (new and existing) with updated modalities and thinking levels — automatically and from one refresh button in the Models page. / Utrzymuj żywy ka

Per-route API-key rotation + retry for dsh. When a provider request ends with a retryable failure (default: QUOTA, AUTH — the codes where waiting cannot help), this plugin (1) repoints the provider's credential reference (e.g. llm-deepseek's apiKeyEnv) to

TimeWeb Cloud AI provider for DeepSeek Harness — a "Time Web" section with "Добавить агента Time Web": auto-fetch models from the agent, one-click create of a correct provider, success toast, auto-close to Models.

DeepSeek Harness plugin for Readproof: stable readproof:// identity, freshness policy, snapshots, per-run manifests, diff, byte-exact replay, and evidence bundles as model-callable tools.

Use a Claude Pro or Max subscription as a DeepSeek Harness model provider, by driving the Claude Code CLI through the Agent SDK.

LLMTR AI gateway provider for the DeepSeek Harness LLM seam: 170+ chat models and Türkiye-hosted LLMs behind one OpenAI-compatible key

DeepSeek Harness compatibility plugin for third-party OpenAI-style gateways: tolerates SSE streams that close without the [DONE] sentinel after a complete reply.

A Models settings companion page listing every model's input modalities in one place, editable for both LLM adapter families

DSH 模型代理插件：按模型走代理（Clash 等）+ 失败自动重试 + 直连失败自动回退代理，设置页实时生效。

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。

Use ChatGPT (Codex) subscription as a DeepSeek Harness LLM provider via OAuth — standalone plugin, no upstream patching, proxy-aware.

CodeBuddy/WorkBuddy models bundle for DeepSeek Harness (dsh): reads the local desktop login and serves the CodeBuddy subscription as a native provider route in the model picker

Cordis-native Lead/Worker model routing for DeepSeek Harness: a replaceable `ctx.llm` provider route plus an observable, interceptable routing service.

A production-oriented llama.cpp LLM provider for DeepSeek Harness, with first-class Qwen reasoning support: streaming tool calls, adaptive inference policies, multi-endpoint reliability, capability-aware routing, discovery, observability, and diagnostics.

Bridge OpenCode CLI free models into dsh (no OpenCode login needed) via an llm adapter

Per-model reasoning effort declarations for GPT, Gemini and OpenAI-compatible providers in DeepSeek Harness

A searchable, sortable model picker for the DeepSeek Harness Web UI — provider groups, favorites, hidden-models blacklist, live per-task cost, prices and context windows, a refresh button that re-syncs every provider model list from its live API, and the

DeepSeek Harness (dsh) plugin that connects Sber GigaChat models: a built-in local OAuth proxy (client-credentials -> OpenAI-compatible endpoint, upstream serialization, legacy tool-calling translation) plus automatic provider-route bootstrap, so GigaChat

DeepSeek Harness plugin: LLM model selection & deployment analysis (deployability, VRAM, TTFT, latency, throughput, power for 38 models × 20 GPUs/NPUs)

用于 DeepSeek Harness 的模型配置插件，支持管理 llm-pi-ai 提供方、API 凭据、模型发现和单模型配置覆盖。仅提供增强模型配置，不修改官方模型配置页面

Brave Search API-backed web search provider for the DeepSeek Harness web capability seam (ctx.web)

Request image optimization, intelligent retention, and observability for DeepSeek Harness (DSH)

为 opencode go 设计的 API 池:根据余额热管理切换不同 API key,官方用量/余额查询 + 设置页图形化管理。

DeepSeek Harness plugin: adds the Ollama cloud chat-completions provider for LLM models.

Magpie gateway models for DeepSeek Harness (DSH): native dsh-llm adapter plugin with image + responses + thinking levels.

Neutralize tool calls with invalid JSON arguments on the wire, so one malformed model generation cannot brick a session against strict OpenAI-compatible servers (vLLM et al).

Extra LLM provider routes for DeepSeek Harness: OpenCode Go with per-session x-opencode-session routing, and OpenAI Codex over ChatGPT-subscription OAuth.

Describe images with a vision model so text-only DeepSeek Harness models can read them

Local-first DeepSeek Harness control center for balance monitoring, usage accounting, time-aware custom third-party API pricing, a 365-day local token ledger, Z.ai Coding Plan quotas, official pricing sync, encrypted multi-account switching, reminders, re

Explicit, evidence-first multi-model consultation for DeepSeek Harness

dsh plugin: persistent whole-machine LLM usage ledger with a markdown /llm-stats report (GFM tables + emoji: tokens, cache hit, model/tool time, per-day bars)

Active Context Pruning (ACP) for the DeepSeek Harness — model-driven context management as a CompactionEngine backend.

KoboldCpp for DeepSeek Harness - a tool plugin that lets the harness online model hand repetitive text and vision (OCR) labor to a local KoboldCpp (llama.cpp) server.