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.

Adds Claude, Gemini, and a local Ollama model to DSH's native model picker, using your existing Claude Code / Antigravity CLI logins instead of a metered API key, with a working reasoning-effort selec

Live per-task token cost widget: peak/valley pricing windows, projected post-hike costs, sortable per-task cost table, multi-currency (COP/USD/CNY + ~40 more) with FX rates, and one-click streamed LLM

Adds Tako chat models to the official llm-pi-ai provider list from Tako's public catalog, with live refresh, context windows from size tags, and browser one-click sign-in writing a cr_ key into DSH cr

Text-to-image and image-to-image for a model that cannot draw, through any OpenAI-compatible image API, with multiple providers and an automatic fallback model.

Registers a `deepseek-web` provider that drives your own signed-in chat.deepseek.com account as an extra model in DSH, so no Open Platform API key is needed: the sidebar footer lists your Web conversa

DSH plugin: matches a model you declared on a custom gateway to the capability metadata it should have — context window, output cap, reasoning levels and image support — by looking the bare model name

by GooDAnDReaDY

Normalizes malformed token-usage samples so broken session histories remain loadable.

by chengzhicao

Web UI for capturing and reviewing raw LLM requests, streamed responses, token usage and tool calls.

Connects a locally-signed-in Cursor desktop app to dsh as a native LlmAdapter — reads the Cursor login token from state.vscdb or auth.json, drives the private agent.v1.AgentService/Run HTTP/2 bidi str

Reasoning-effort gear presets for third-party models: 16 vendor/model presets with per-mode custom wire values, written into dsh-llm-pi-ai with pre-write validation and per-rule rejection; per-model s

by GooDAnDReaDY

Ollama Cloud LLM provider plugin for DeepSeek Harness (dsh).

No description yet

Expose every free model from a local opencode serve catalog — all providers, including your own custom ones — to DeepSeek Harness's model picker, with OpenCode's native tools denied so execution stays

Routes DeepSeek Harness model API requests through a system, custom or SOCKS proxy; requests outside the configured domains stay direct.

Brings WorkBuddy's free and paid models (domestic and international) into DSH without the WorkBuddy desktop app; published as @bushizhanghan/dsh-workmate, installable on dsh 0.2.0-rc.2 through 0.2.1 i

by n0pe-sled

dsh plugin: manage dsh skills and MCP servers from Settings > Skills & MCP, hot-reloaded without restarting the GUI

Flash-only reasoning-effort routing for DeepSeek Harness, setting the DeepSeek flash model reasoning effort per step. The model never changes; effort max is opt-in.

Stops compaction summaries and session titles from burning their output budget on reasoning, by lowering the thinking level and raising the token floor for auxiliary calls only.

DeepSeek Harness plugin: query AI subscription quotas & balances (Codex, Kimi, DeepSeek, 302.AI, OpenCode Go) as a model tool and a Settings page

by andregoncalves

Provider-aware account balance chip for the DSH sidebar, showing the active model provider balance for DeepSeek, OpenRouter, Moonshot/Kimi, Zhipu/GLM, and MiniMax, plus DeepSeek peak/off-peak status.

Declares image input on relay routes whose endpoint omits modality metadata, so models that can see photos stop being rejected as text-only. This also overrides routes that are explicitly declared tex

macOS Keychain credential provider that replaces the local-file provider and uses a signed, notarized universal helper.

Aggregates all local Trae accounts into one auto-failover model provider, with manual and automated daily check-in, credits and expiry monitoring, and a model selection settings card.