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>

src/session/capacity.ts

@@ -19,8 +19,8 @@ export function capacityRefusal(main: ResolvedModel, helper: ResolvedModel): str
   }
   const shared = groupOf(main)
   if (shared !== undefined && shared === groupOf(helper)) {
-    const where = main.spec.group !== undefined ? `${main.ref}'s server (group ${main.spec.group})` : main.connectionName
-    return `${where} holds one model at a time (${main.spec.group !== undefined ? "group" : "one_model_at_a_time"}), so a subagent on ${helper.ref} would unload ${main.ref}, and this session's cached prompt with it, while its turn waits.`
+    const where = `${main.ref}'s server (group ${main.spec.group})`
+    return `${where} holds one model at a time, so a subagent on ${helper.ref} would unload ${main.ref}, and this session's cached prompt with it, while its turn waits.`
   }
   return ""
 }
@@ -35,15 +35,14 @@ export function capacityBeside(running: ResolvedModel, helper: ResolvedModel): s
   }
   const shared = groupOf(running)
   if (shared !== undefined && shared === groupOf(helper)) {
-    const where = running.spec.group !== undefined ? `${running.ref}'s server (group ${running.spec.group})` : running.connectionName
+    const where = `${running.ref}'s server (group ${running.spec.group})`
     return `${where} holds one model at a time, and a subagent is already running on ${running.ref} there; one on ${helper.ref} would unload it.`
   }
   return ""
 }
 
-/** Which one-model-at-a-time server a model is on: its own `group`, else its connection when the
- *  connection sets one_model_at_a_time, else none. The spec's capacity.group. */
+/** Which one-model-at-a-time server a model is on, as the LLeMbas server says (`capacity.group`,
+ *  the spec's), or none. */
 function groupOf(m: ResolvedModel): string | undefined {
-  if (m.spec.group !== undefined) return `group:${m.spec.group}`
-  return m.connection.one_model_at_a_time ? `connection:${m.connectionName}` : undefined
+  return m.spec.group !== undefined ? `group:${m.spec.group}` : undefined
 }