Auto-resumes dsh sessions whose turn was left mid-flight by a web process restart or by a transient upstream failure, by injecting a 「继续（自动）」 ("continue (auto)") user message so the agent picks up exa

by dongsheng123132

Offline content-addressed proof for supplied DSH workflow duty separation

by itchenshi

DeepSeek Harness plugin: declares the OpenCode Go route wire protocol, auto-adds DeepSeek V4.1 models, and attaches the x-opencode-session header

Folds streaming reasoning and tool calls into collapsed step bars and collapses each finished turn into a single summary bar; step bars show native tool icons, filenames, edited line counts, and failu

by Rycbartbad

Manage multiple API keys per provider in Settings → API Key: keep a pool of keys with notes, switch the active key with one click, and the switch really takes effect on the next model call.

Multi-provider LLM API balances under the chat input, with presets for DeepSeek, OpenRouter and SiliconFlow.

by scientisbo

Codex Usage · Subscription Quota & DeepSeek Balance Aggregation (DeepSeek Harness host plugin) | Codex subscription quota & DeepSeek balance aggregator for DeepSeek Harness

by Missher12

Independent Missher plugin: current source, installable bundle and documentation.；For the desktop entry and other plugins, see the homepage links.

by lurejewel

Lightweight, native sidebar usage panel for DeepSeek Harness: official balance + token usage history from session logs.

by DragonHorizon-xtihc

把本机所有 WorkBuddy 登录账号聚合成一个模型池：账号自动发现、签到、积分与到期、临期提醒、自动签到、模型与倍率，并可在输入框下方切换账号与查看剩余总积分。

by xiaomao49

DeepSeek Harness plugin to audit and correct llm-pi-ai model capability declarations by probing the endpoint itself: out-of-range maxTokens, contextWindow, reasoning levels, image input.

by YYfather

DeepSeek Harness Balance and Cost Plugin: The status bar displays DeepSeek/MiMo balance and per-request billing costs (this session/this active period/last request/previous conversation), supports multiple models + peak-valley pricing and spending threshold alerts

Metadata-first runtime profiler for DSH agents: turn/step traces, model and tool wall-time timelines, provider usage, retries, errors, and live or historical sessions.

DeepSeek Harness plugin: use your own Claude and ChatGPT/Codex subscriptions as model providers, over each vendor OAuth flow

Per-Session OpenRouter routing: a loopback relay writes `service_tier`, `provider.sort` and the `:floor` variant into each request from one of nine presets picked on the composer chip, with a pinned b

by uio-o

Unified model control for DeepSeek Harness: model picker + model management (channels, per-model capabilities) + reasoning-effort advisory, in one seat and one settings page.

by kongshan-zhuyu

A plugin that can configure balance, monitor model monitoring status, and configure model multimodal settings

Connects ChatGPT accounts through OAuth, switches among them manually or automatically, and adds Codex models with usage limits to DeepSeek Harness.

by dongsheng123132

Content-addressed proof that DSH authorization decisions and recorded effects agree

by Zn-Dk

Zhipu BigModel/GLM provider toolkit for DeepSeek Harness: dual-endpoint model catalog (Coding Plan + ordinary API), verified thinking-level mapping, live model discovery, Web settings card

by icyaaaww

Deterministic per-turn adaptive model routing for DeepSeek Harness

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.

by RGarrido03

Use your Zed AI subscription (Pro / Student) from DeepSeek Harness: registers the zed-agent route with Claude + GPT models, an editable Models-page card and a model chooser.

by d3vmeh

DeepSeek Harness plugin: keep a local model's context at a size your GPU handles well (measured prefill speed, hard ceiling, early compaction)