Link protocol 3; a session the client opens runs on the chat's model or not at all

- LEMBAS_PROTOCOL, the device protocol and the protocols the CLI logs in to
  and links with are 3 alone (harness/acp.md *Versions*). A server listing
  only 1 and 2 is refused at login and at every dial — before anything is
  dialled — with its version and protocols and "update the server, or use
  LLeMbas CLI 1.x with it"; a newer one is told to update the CLI
  (ProtocolError). A 4400 stops the link with the same advice. The old
  downgrade to protocol 1 is gone.
- session/new's result says `instance`: whether the session's model is the
  link's instance's.
- `lembas_model` is the model, full stop: a device not logged in to the link's
  instance, a link with no instance (serve --stdio), or a model the instance
  does not serve to this device is -32602 with the reason, never a session on
  the device's own model. `_lembas/configure` naming such a model is refused
  likewise and the session keeps its model.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

tests/remote.test.ts

@@ -164,7 +164,7 @@ test("the service links with remote work off, says no roots and refuses everythi
       const u = new URL(req.url)
       const base = `http://${u.host}`
       if (u.pathname === "/.well-known/lembas.json")
-        return Response.json({ service: "lembas", version: "2.2.0", protocol: 1, protocols: [1, 2], harness_spec: "2.1.0", base_url: base, api: { openai: `${base}/v1` }, login: { device: { code: `${base}/c`, token: `${base}/t`, verify: `${base}/d` } } })
+        return Response.json({ service: "lembas", version: "2.0.0", protocol: 3, protocols: [3], harness_spec: "3.0.0", base_url: base, api: { openai: `${base}/v1` }, login: { device: { code: `${base}/c`, token: `${base}/t`, verify: `${base}/d` } } })
       if (u.pathname === "/api/devices/link" && srv.upgrade(req)) return
       return new Response("no", { status: 404 })
     },