Custom connections are gone: the CLI talks to the LLeMbas server it is logged in to

LLeMbas CLI 2.0 is LLeMbas-server-specific (CLI rule 2). Removed: the
anthropic, gemini, ollama and responses clients, context discovery and
llama-swap unloading (discover.ts), the Connection schema with its dialect,
auth, key_cmd, discover, unload_url and one_model_at_a_time, the model
`fallback` (it only ever moved to another server), effort_map and cache, and
the multi-connection refs. Kept: openai-chat, http, sse, think, effort,
tokens and all of src/lembas.

- connections.yaml holds the login (`type: webui`, as lembas login writes
  it). A custom entry from 1.x is read past with a warning that says how to
  log in, so an old file still starts; with several logins left, the latest
  is used and the others named.
- A model's ref is the id the server serves it under; the older forms
  (`<login>/<id>`, `<login>/<model>`) still resolve and config.yaml is
  rewritten once. Without a login there is no model, and the error (and the
  first-run screen, now the sign-in alone) says `lembas login <address>`.
- A login to another server signs this machine out of the previous one.
- The window is the server's word (no discovery); a capacity group comes
  from the server's `capacity.group` alone; embeddings use the server's
  /v1/embeddings.
- `lembas models` lists the server's models; install.sh's starter files, the
  README and the JSON schemas say the same.

Tests: every fixture is a login now (the fake server lists models, answers
other GETs with 404, and can hand one model to another script, as a server
with several backends); the dialect suites and the cross-connection tests are
gone with their code.

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

tests/capacity.test.ts

@@ -14,24 +14,15 @@ import { delta, fakeProvider, toolCall, type Fake } from "./fake-provider.ts"
 let fake: Fake | undefined
 afterEach(() => fake?.stop())
 
-const model = (conn: string, id: string, o: { one?: boolean; single?: boolean } = {}): ResolvedModel => ({
+const model = (conn: string, id: string, o: { single?: boolean } = {}): ResolvedModel => ({
   ref: `${conn}/${id}`,
-  connectionName: conn,
-  connection: { dialect: "openai-chat", base_url: "http://x/v1", models: {}, ...(o.one ? { one_model_at_a_time: true } : {}) } as ResolvedModel["connection"],
-  id,
+  connectionName: "ai",
+  connection: { base_url: "http://x/v1", models: {} },
+  id: `${conn}/${id}`,
   spec: o.single ? { single_session: true } : {},
 })
 
-test("one model at a time: another model of the same server is refused, the session's own is not", () => {
-  const main = model("swap", "qwen", { one: true })
-  expect(capacityRefusal(main, model("swap", "gemma", { one: true }))).toContain("holds one model at a time")
-  expect(capacityRefusal(main, main)).toBe("")
-  expect(capacityRefusal(main, model("cloud", "big"))).toBe("")
-  // Without the flag, as before.
-  expect(capacityRefusal(model("swap", "qwen"), model("swap", "gemma"))).toBe("")
-})
-
-test("a model's group: models one connection serves from several servers are told apart", () => {
+test("a model's group (the server's capacity.group): another model of the same GPU is refused, the session's own is not", () => {
   const grouped = (id: string, group?: string): ResolvedModel => ({ ...model("ai", id), spec: group ? { group } : {} })
   const main = grouped("qwen", "gpu")
   expect(capacityRefusal(main, grouped("gemma", "gpu"))).toContain("holds one model at a time")
@@ -55,14 +46,14 @@ test("task on a model the server cannot hold beside the session's is refused, an
   mkdirSync(paths.config, { recursive: true })
   writeFileSync(
     join(paths.config, "connections.yaml"),
-    `connections:\n  f:\n    dialect: openai-chat\n    base_url: ${fake.url}\n    one_model_at_a_time: true\n    models: { m: {}, other: {} }\n`,
+    `connections:\n  f:\n    type: webui\n    url: ${fake.url}\n    models: { f/m: { group: gpu }, f/other: { group: gpu } }\n`,
     { mode: 0o600 },
   )
   writeFileSync(join(paths.config, "config.yaml"), "model: f/m\n")
   const a = createApp({ cwd: mkdtempSync(join(tmpdir(), "ph-cap-")), mode: "edit", store: false, asker: { ask: async (): Promise<AskReply> => ({ kind: "once" }) } })
   await a.engine.prompt("get a second opinion")
   // Two requests: the session's, then its next step — never one for f/other.
-  expect(fake.requests.map((r: any) => r.model)).toEqual(["m", "m"])
+  expect(fake.requests.map((r: any) => r.model)).toEqual(["f/m", "f/m"])
   const result = fake.requests[1].messages.at(-1).content as string
   expect(result).toContain("holds one model at a time")
   expect(result).toContain("Do this part yourself")