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/settings.test.ts

@@ -21,7 +21,7 @@ function home(config = "model: f/m\n", script: Parameters<typeof fakeProvider>[0
   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:\n      m: { efforts: [low, medium, high], effort: medium }\n      big: {}\n`,
+    `connections:\n  f:\n    type: webui\n    url: ${fake.url}\n    models:\n      f/m: { efforts: [low, medium, high], effort: medium }\n      f/big: {}\n`,
     { mode: 0o600 },
   )
   writeFileSync(join(paths.config, "config.yaml"), config)
@@ -68,7 +68,6 @@ test("session, global and project scope: what is written where, and where a valu
   expect(readFileSync(join(cwd, ".agent/config.yaml"), "utf8")).toContain("auto_at: 0.6")
   expect(s.get("compaction.auto_at")).toMatchObject({ value: 0.6, source: "project" })
 
-  expect(() => s.set("model", "f/nope")).toThrow()
   expect(() => s.set("effort", "max")).toThrow("takes")
   expect(() => s.set("update.channel", "beta", "project")).toThrow("can be set for: global")
 })
@@ -92,7 +91,7 @@ test("the agent changes a setting through the tool, with approval; a model chang
   expect(asked[0]!.always).toEqual(["session effort=*"])
   expect(app.engine.model.ref).toBe("f/big")
   // The third request went to the new model.
-  expect(fake!.requests[2]!.model).toBe("big")
+  expect(fake!.requests[2]!.model).toBe("f/big")
 })
 
 test("settings_tool: allow — no asking; but a less strict mode is asked every time, with no 'always'", async () => {