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/tui/setup.test.tsx

@@ -31,16 +31,16 @@ test("no model yet: the sign-in is first and focused; ctrl+r opens the session o
     return setup!.captureCharFrame()
   }
   let f = await frame()
-  expect(f).toContain("no model to talk to yet")
+  // 2.0: the server's models or none — the screen is the sign-in, and nothing else to fill in.
+  expect(f).toContain("not logged in to a LLeMbas server")
   expect(f).toContain("Log in to a LLeMbas instance")
-  // Before the file instructions: the screen opens on the sign-in.
-  expect(f.indexOf("Log in to a LLeMbas instance")).toBeLessThan(f.indexOf("connections.yaml"))
+  expect(f).not.toContain("connections.yaml")
   // Focused: what is typed is the address, without pressing l first.
   await setup.mockInput.typeText("ai.example")
   f = await frame()
   expect(f).toContain("Address: ai.example")
   // A model added meanwhile: ctrl+r, a letter-free key, opens the session.
-  writeFileSync(join(paths.config, "connections.yaml"), `connections:\n  fake:\n    dialect: openai-chat\n    base_url: ${fake.url}\n    models: { m: {} }\n`, { mode: 0o600 })
+  writeFileSync(join(paths.config, "connections.yaml"), `connections:\n  fake:\n    type: webui\n    url: ${fake.url}\n    models: { fake/m: {} }\n`, { mode: 0o600 })
   writeFileSync(join(paths.config, "config.yaml"), "model: fake/m\n")
   setup.mockInput.pressKey("r", { ctrl: true })
   f = await frame()