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/library.test.ts

@@ -96,10 +96,13 @@ test("an OpenAI-shaped /embeddings: in order, unit length", async () => {
       return Response.json({ data: input.map((_, i) => ({ index: i, embedding: [3, 4] })).reverse() })
     },
   })
-  const e = embedderFor({ connections: { emb: { dialect: "openai-chat", base_url: `http://127.0.0.1:${server.port}/v1`, models: {} } } } as never, "emb/nomic")!
+  // The server's embedding model, by its served id.
+  const loaded = { connections: { emb: { base_url: `http://127.0.0.1:${server.port}/v1`, models: {}, webui: { url: `http://127.0.0.1:${server.port}`, embeddings: ["llama/nomic"] } } }, refs: [] } as never
+  const e = embedderFor(loaded, "llama/nomic")!
   const [v] = await e.embed(["x", "y"])
   expect(Array.from(v!)).toEqual([0.6000000238418579, 0.800000011920929])
-  expect(() => embedderFor({ connections: { a: { dialect: "anthropic", base_url: "http://x", models: {} } } } as never, "a/b")).toThrow("no embeddings")
+  // Not logged in: said.
+  expect(() => embedderFor({ connections: {}, refs: [] } as never, "llama/nomic")).toThrow("not logged in")
 })
 
 test("ingest: text and code; HTML as markdown; binaries skipped; long text cut and said; links out of the directory ignored", async () => {
@@ -135,7 +138,7 @@ test("the tools: knowledge_search is offered only with something to search; a pr
     { chunks: [delta({ content: "ok" }, "stop")] },
   ])
   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: {} }\n`, { mode: 0o600 })
+  writeFileSync(join(paths.config, "connections.yaml"), `connections:\n  f:\n    type: webui\n    url: ${fake.url}\n    models: { f/m: {} }\n`, { mode: 0o600 })
   writeFileSync(join(paths.config, "config.yaml"), "model: f/m\ntitles: prompt\n")
   const cwd = mkdtempSync(join(tmpdir(), "ph-libtools-"))
   mkdirSync(join(cwd, ".agent"))