by zuojinxin

Provider on/off switches, model search, and inline provider renaming for DeepSeek Harness.

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

by dongsheng123132

Offline content-addressed proof of pseudonymous authority binding across DSH execution surfaces

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.

No description yet

Image generation workbench and agent tool for DSH: one tool (ark9_generate_image) paints text-to-image and image-to-image via any OpenAI-compatible API. Channels are entirely user-configured - no bund

Bing-backed web search provider for the built-in web_search tool: scrapes the public cn.bing.com HTML results page with no API key, reachable from mainland China, and keeps searches off the model's ow

DeepSeek Harness Subagent Model Management and Jev Intelligent Routing Plugin (merged from vitas/dsh-jev-subagent-dispatch and ringoage/dsh-subagent-model-picker)

by mervyn-teo

No project description is available for this repository yet.

Connects the OpenCode Zen anonymous free lane to DeepSeek Harness: refresh the model list from upstream, tick which models the opencode provider exposes, test any of them with a real request that ends

by HandsYe

DeepSeek Harness bundle for MotoMoto's OpenAI-compatible endpoint: pi-ai provider route + Settings status card

Live remaining balance for the current API key from Sub2API, New API, or official DeepSeek, plus actual spend when the site publishes it, not a local token estimate.

by dongsheng123132

Offline content-addressed proof that a supplied change event chain stayed inside one declared maintenance window

Shows Provider/Model in the DSH Web composer model selector trigger; the dropdown list and its search are unchanged.

Per-model input type and thinking level declarations on the model settings page — input type checkboxes on every provider card, and a thinking level field in the provider edit dialog. Writes the official pi-ai input and r

by knyazev741

Adds the KnyazevAI API provider and its DeepSeek, GLM, Kimi, and MiniMax model catalog to DeepSeek Harness.

Real-time cost tracking for the current DSH conversation: a composer-dock line showing the running token usage and DeepSeek official price estimate (base and peak/valley pricing).

by guhanfei-ai

Wraps globalThis.fetch to route chosen domains through one or more named HTTP/SOCKS proxies (exact host or *.suffix rules, per-card enable), with global direct rules that override every proxy; unmatch

Cumulative token usage tracking for DeepSeek Harness, with per-model and per-day breakdowns, a settings-page dashboard and an online-changeable data directory.

Shows the selected model provider's account balance next to the composer's model seat once a model and reasoning effort are selected.

Connects the locally signed-in WPS Comate desktop account to DeepSeek Harness as a model provider, via a secure loopback shim.

Shows real-time token and cost savings from the Headroom compression proxy in the DSH web UI: a Settings dashboard plus a persistent stats line under the composer.

by marsma-101

Bring Trae CN desktop-app models into DeepSeek Harness: decrypt the local sign-in, translate the remote-session protocol behind a loopback OpenAI-compatible shim, register a Trae model group.

Adds the official Google Antigravity ACP agent as a DeepSeek Harness model provider, with tool execution and approval kept in DSH, Node 22.19+ and a signed-in Antigravity account required, a per-model