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/acp-v2.test.ts

@@ -40,7 +40,7 @@ function pair(): [Transport, Transport] {
 
 function config(url: string, extra = "", model = "{}") {
   mkdirSync(paths.config, { recursive: true })
-  writeFileSync(join(paths.config, "connections.yaml"), `connections:\n  f:\n    dialect: openai-chat\n    base_url: ${url}\n    models: { m: ${model} }\n`, { mode: 0o600 })
+  writeFileSync(join(paths.config, "connections.yaml"), `connections:\n  f:\n    type: webui\n    url: ${url}\n    models: { f/m: ${model} }\n`, { mode: 0o600 })
   writeFileSync(join(paths.config, "config.yaml"), `model: f/m\n${extra}`)
 }
 
@@ -535,7 +535,7 @@ test("answered at the terminal first: the web UI's card is settled", async () =>
 test("the model event: said whenever the model or effort changes, forwarded to LLeMbas", async () => {
   fake = fakeProvider([])
   mkdirSync(paths.config, { recursive: true })
-  writeFileSync(join(paths.config, "connections.yaml"), `connections:\n  example:\n    dialect: openai-chat\n    base_url: ${fake.url}\n    models: { a: { efforts: [low, high] }, b: {} }\n`, { mode: 0o600 })
+  writeFileSync(join(paths.config, "connections.yaml"), `connections:\n  example:\n    type: webui\n    url: ${fake.url}\n    models: { example/a: { efforts: [low, high] }, example/b: {} }\n`, { mode: 0o600 })
   writeFileSync(join(paths.config, "config.yaml"), "model: example/a\n")
   const root = project()
   const { c, events } = await client(limitsFor(root), { instance: "example" })
@@ -771,13 +771,13 @@ test("a command's mode from the web is clamped to remote.max_mode in a terminal
 test("a command naming a model gives the session its model and its effort back afterwards", async () => {
   fake = fakeProvider([{ chunks: [delta({ content: "ok" })] }])
   mkdirSync(paths.config, { recursive: true })
-  writeFileSync(join(paths.config, "connections.yaml"), `connections:\n  f:\n    dialect: openai-chat\n    base_url: ${fake.url}\n    models: { m: { efforts: [low, high], effort: low }, other: {} }\n`, { mode: 0o600 })
+  writeFileSync(join(paths.config, "connections.yaml"), `connections:\n  f:\n    type: webui\n    url: ${fake.url}\n    models: { f/m: { efforts: [low, high], effort: low }, f/other: {} }\n`, { mode: 0o600 })
   writeFileSync(join(paths.config, "config.yaml"), "model: f/m\n")
   const root = project({ ".agent/config.yaml": "", ".agent/commands/quick.md": "---\nmodel: f/other\n---\nQuick." })
   const { c } = await client(limitsFor(root))
   const s: any = await c.request("session/new", { cwd: root, _meta: { effort: "high" } })
   await c.request("session/prompt", { sessionId: s.sessionId, prompt: [{ type: "text", text: "/quick" }] })
-  expect(fake.requests[0].model).toBe("other")
+  expect(fake.requests[0].model).toBe("f/other")
   expect(await c.request<any>("_lembas/configure", { sessionId: s.sessionId })).toEqual({ model: "f/m", effort: "high" })
 })