# Virtual LLMs A **virtual LLM** is an `Llm` row in mcpd that's *registered by an mcplocal client* rather than created by hand with `mcpctl create llm`. Inference for a virtual LLM is relayed back through the publishing mcplocal's SSE control channel — **mcpd never needs to know the local URL or hold its API key**. When the publishing mcplocal goes away (or the user shuts down their laptop) the row decays: `active → inactive` after 90 s without a heartbeat, then deleted after 4 h of inactivity. A reconnecting mcplocal adopts the same row using a sticky `providerSessionId` it persisted at first publish. ## When to use this - **Local model on a developer laptop** that you want everyone on the team to be able to chat with via `mcpctl chat-llm `. The model doesn't need to be reachable from mcpd's k8s pods — only the user's mcplocal does (which is already the case because mcplocal pulls projects from mcpd over HTTPS). - **Hibernating models** that wake on demand (v2 — see "Roadmap"). - **Pool of identical models** distributed across user laptops, eligible for load balancing (v4). If your model is reachable from mcpd's k8s pods over LAN/VPN, you don't need a virtual LLM — just `mcpctl create llm --type openai --url …` and you're done. ## Publishing a local provider mcplocal's local config (`~/.mcpctl/config.json`) gains a `publish: true` opt-in per provider: ```json { "llm": { "providers": [ { "name": "vllm-local", "type": "openai", "model": "Qwen/Qwen2.5-7B-Instruct-AWQ", "url": "http://127.0.0.1:8000/v1", "tier": "fast", "publish": true } ] } } ``` Restart mcplocal: ```fish systemctl --user restart mcplocal ``` The registrar: 1. Reads `~/.mcpctl/credentials` for `mcpdUrl` + bearer token. 2. POSTs to `/api/v1/llms/_provider-register` with the publishable set. 3. Persists the returned `providerSessionId` to `~/.mcpctl/provider-session` so the next restart adopts the same mcpd row. 4. Opens the SSE channel at `/api/v1/llms/_provider-stream`. 5. Heartbeats every 30 s. 6. Listens for `event: task` frames and runs them against the local `LlmProvider`. If `~/.mcpctl/credentials` doesn't exist (e.g. you haven't run `mcpctl auth login`), the registrar logs a warning and skips — publishing is a best-effort feature, not a boot blocker. ## Verifying ```fish $ mcpctl get llm NAME KIND STATUS TYPE MODEL TIER KEY ID qwen3-thinking public active openai qwen3-thinking fast secret://litellm-key/API_KEY cmofx8y7u… vllm-local virtual active openai Qwen/Qwen2.5-7B-Instruct-AWQ fast - cmoxz12ab… $ mcpctl chat-llm vllm-local ───────────────────────────────────────────────────────── LLM: vllm-local openai → Qwen/Qwen2.5-7B-Instruct-AWQ Kind: virtual Status: active ───────────────────────────────────────────────────────── > hello? Hi! … ``` You can also chat with public LLMs the same way: ```fish $ mcpctl chat-llm qwen3-thinking ``` The CLI doesn't care about `kind` — mcpd's `/api/v1/llms//infer` route branches on it server-side. ## Lifecycle in detail | State | What it means | |----------------|---------------------------------------------------------------------------------| | `active` | Heartbeat received within the last 90 s and the SSE channel is open. | | `inactive` | Either the SSE closed or the heartbeat watchdog tripped. Inference returns 503. | | `hibernating` | Publisher is online but the backend is asleep; the next inference triggers a `wake` task before relaying. | Two timers on mcpd run the GC sweep: - **90 s** without a heartbeat → flip `active` → `inactive`. - **4 h** in `inactive` → delete the row entirely. A reconnecting mcplocal with the same `providerSessionId` revives every inactive row it owns; it only orphans rows that fell past the 4-h cutoff. ## Inference relay When mcpd receives `POST /api/v1/llms//infer`: 1. Look up the row, see `kind=virtual` + `status=active`. 2. Find the open SSE session for that `providerSessionId`. Missing session → 503. 3. Push a `{ kind: "infer", taskId, llmName, request, streaming }` task frame onto the SSE. 4. mcplocal pulls, calls `LlmProvider.complete(...)`, and POSTs the result back to `/api/v1/llms/_provider-task//result`: - non-streaming: `{ status: 200, body: }` - streaming: per-chunk `{ chunk: { data, done? } }` - failure: `{ error: "..." }` 5. mcpd forwards the result/chunks out to the original caller. **v1 caveat — streaming granularity**: `LlmProvider.complete()` returns a finalized `CompletionResult`, not a token stream. Streaming requests therefore arrive at the caller as a single delta + `[DONE]`. Real per-token streaming is a v2 concern. ## Wake-on-demand (v2) A provider whose backend hibernates (a vLLM instance that suspends when idle, an Ollama daemon that exits when nothing's connected, …) can declare a **wake recipe** in mcplocal config. When that provider's `isAvailable()` returns false at registrar startup, the row is published as `status=hibernating`. The next inference request that hits the row triggers the recipe and waits for the backend to come up before relaying. Two recipe types: ```jsonc // HTTP — POST to a "wake controller" that starts the backend out of band. { "name": "vllm-local", "type": "openai", "model": "...", "publish": true, "wake": { "type": "http", "url": "http://10.0.0.50:9090/wake/vllm", "method": "POST", "headers": { "Authorization": "Bearer ..." }, "maxWaitSeconds": 60 } } ``` ```jsonc // command — spawn a local process (systemd, wakeonlan, custom script). { "name": "vllm-local", "type": "openai", "model": "...", "publish": true, "wake": { "type": "command", "command": "/usr/local/bin/start-vllm", "args": ["--profile", "qwen3"], "maxWaitSeconds": 120 } } ``` How a request flows when the row is `hibernating`: ``` client → mcpd POST /api/v1/llms//infer mcpd: status === hibernating → push wake task on SSE mcplocal: receive wake task → run recipe → poll isAvailable() → heartbeat each tick → POST { ok: true } back mcpd: flip row → active, push the original infer task mcplocal: run inference → POST result back mcpd → client (forwards the inference result) ``` Concurrent infers for the same hibernating Llm share a single wake task — only the first request triggers the recipe; later ones await the same in-flight wake promise. After the wake settles, every queued infer dispatches in order. If the recipe fails (HTTP non-2xx, command exits non-zero, or the provider doesn't come up within `maxWaitSeconds`), every queued infer is rejected with a clear error and the row stays `hibernating` — the next request gets a fresh wake attempt. ## Roadmap (later stages) - **v3 — Virtual agents**: mcplocal publishes its local agent configs (model + system prompt + sampling defaults) into mcpd's `Agent` table. - **v4 — LB pool by model**: agents can target a model name instead of a specific Llm; mcpd picks the healthiest pool member per request. - **v5 — Task queue**: persisted requests for hibernating/saturated pools. Workers pull tasks of their model when they come online. ## API surface (v1) ``` POST /api/v1/llms/_provider-register → returns { providerSessionId, llms[] } GET /api/v1/llms/_provider-stream → SSE channel; require x-mcpctl-provider-session header POST /api/v1/llms/_provider-heartbeat → { providerSessionId } POST /api/v1/llms/_provider-task/:id/result → one of: { error: "msg" } { chunk: { data, done? } } { status, body } GET /api/v1/llms → list (now includes kind, status, lastHeartbeatAt, inactiveSince) POST /api/v1/llms//infer → routes through the SSE relay DELETE /api/v1/llms/ → delete unconditionally (also runs GC's job) ``` RBAC piggybacks on `view/edit/create:llms` — no new resource. Publishing a virtual LLM is morally a `create:llms` operation. ## See also - [agents.md](./agents.md) — what an Agent is and how it pins to an LLM. - [chat.md](./chat.md) — `mcpctl chat ` (full agent flow). - The CLI: `mcpctl chat-llm ` (this doc) is the stateless counterpart for raw LLM chat.