@davidgallo/dsh-llm-subscription
适用于 Claude Code / Antigravity CLI 订阅的原生 DeepSeek Harness LLM 适配器——在模型选择器中使用 Claude 和 Gemini，无需 API 密钥
插件会安装到这里；不确定时保持 web。
npx -y @deepseek-ai/dsh plugin --profile web add github:DavidRm1911/dsh-llm-subscription#a265331a3163e116a5bdedb3ba313c66bead925aLlm Subscription 以 @davidgallo/dsh-llm-subscription 发布，当前版本为 0.1.0。Plugin Hub 会校验它的 manifest，并保存精确安装来源，便于复现安装结果。
A native DeepSeek Harness LLM adapter that puts Claude and Gemini in the model picker — real entries, right next to DeepSeek, with a working reasoning-effort selector — using your existing Claude Code / Antigravity subscriptions instead of a metered API key.
If you've seen dsh-subscription-gateway, this is the same idea done properly: that one is an HTTP bridge you point DSH's Custom Provider at. This one is an actual dsh.bundle plugin registered against DSH's own dsh-llm seam (ctx.llm.registerAdapter) — same mechanism dsh-llm-deepseek uses internally. No Custom Provider screen, no separate process to keep running; it's just there once installed.
claude, haiku, sonnet, opus, fable — each with a native reasoning-effort selector (Low → Max), because Claude's own --effort flag supports that independently of which model you pick.Flash Low/Medium/High, Pro Low/High) — Gemini bakes its intensity into the model name itself, so there's no separate effort control for it.via <real-model-id> line — claude --model sonnet is an alias, and Claude Code sometimes uses a small internal model alongside it for things like session titling. This picks out whichever model actually wrote the visible text (the one with the most output tokens) so you're not left guessing whether you got Sonnet or something else.Inside a DSH profile:
dsh plugin --profile web add @davidgallo/dsh-llm-subscription
Requires the claude CLI (logged in via claude login) and/or agy (Antigravity CLI, logged in) already on PATH. Missing one just means that provider's models won't show up.
Each request shells out to claude -p or agy -p in headless/JSON mode and reshapes the result into the StreamChunk sequence DSH's LLM seam expects (block-start → text-delta → block-end → usage → finish). Neither CLI streams token-by-token in headless mode, so the whole response arrives as one delta — functionally fine, just not incremental.
The Claude call always passes --strict-mcp-config. Without it, the subprocess quietly inherits whatever MCP servers are configured in your regular Claude Code setup, which leaked unrelated tools into responses that were supposed to be clean completions — a real bug hit while building this, not a guess.
0.1.1-rc.2. This whole plugin surface (cordis, the dsh-llm seam) is developer preview and can change without warning.MIT — see LICENSE.