HomerandClaude Opus 5.5
28ff205ed0
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>
53 lines
2.9 KiB
TypeScript
53 lines
2.9 KiB
TypeScript
import { findRef, modelRefs } from "./refs.ts"
|
|
import type { Loaded } from "../config/load.ts"
|
|
import { OpenAIChatClient } from "./openai-chat.ts"
|
|
import type { Client, ResolvedModel } from "./types.ts"
|
|
|
|
export class ModelError extends Error {}
|
|
|
|
/** What a start without a login says: LLeMbas CLI 2.0 has no model of its own, only the server's. */
|
|
export const NOT_LOGGED_IN = "Not logged in to a LLeMbas server. LLeMbas CLI uses the models of the server it is logged in to: lembas login <address> (e.g. lembas login ai.example.org)."
|
|
|
|
/** A model of the server this machine is logged in to, by its served id (`deepseek/deepseek-flash`)
|
|
* or an older form of its name (refs.ts). Without a ref: config.yaml's `model`, else the server's
|
|
* default for the account, else its first. */
|
|
export function resolveModel(loaded: Loaded, ref: string | undefined): ResolvedModel {
|
|
const refs = loaded.refs ?? modelRefs(loaded.connections)
|
|
const [name, connection] = Object.entries(loaded.connections)[0] ?? []
|
|
if (!name || !connection) {
|
|
const why = Object.values(loaded.broken ?? {})[0]
|
|
throw new ModelError(why ? `The LLeMbas login is unusable: ${why}` : NOT_LOGGED_IN)
|
|
}
|
|
if (loaded.broken?.[name]) throw new ModelError(`The LLeMbas login ${name} is unusable: ${loaded.broken[name]}`)
|
|
if (!ref) ref = connection.webui?.default && connection.models[connection.webui.default] ? connection.webui.default : refs[0]?.ref
|
|
if (!ref) throw new ModelError(`${name} serves no model to this account yet. lembas login ${connection.webui?.url ?? ""} again once it does.`.replace(" ", " "))
|
|
const known = findRef(loaded.connections, refs, ref)
|
|
if (known) return { ref: known.ref, connectionName: name, connection, id: known.id, spec: connection.models[known.id] ?? {} }
|
|
// A model the server serves that its list did not have when it was read: the server decides
|
|
// which models exist, so it is asked for rather than refused here. The login's own name in front
|
|
// of it (an older form) is taken off.
|
|
const id = ref.startsWith(`${name}/`) ? ref.slice(name.length + 1) : ref
|
|
return { ref: id, connectionName: name, connection, id, spec: {} }
|
|
}
|
|
|
|
export function clientFor(m: ResolvedModel): Client {
|
|
return new OpenAIChatClient(m)
|
|
}
|
|
|
|
/** Which prompt family a model gets when the server does not say: anthropic, gpt, gemini, or
|
|
* local — every open-weight or unknown model, which gets Hermes' act-don't-describe guidance. */
|
|
export function familyOf(m: ResolvedModel): string {
|
|
if (m.spec.family) return m.spec.family
|
|
const id = m.id.toLowerCase()
|
|
if (id.includes("claude")) return "anthropic"
|
|
if (id.includes("gemini")) return "gemini"
|
|
if (/\bgpt|^o[134]\b|^o[134]-|codex/.test(id)) return "gpt"
|
|
return "local"
|
|
}
|
|
|
|
/** The window to plan with, as the server gives it; undefined when it does not say (no percentage,
|
|
* no automatic compaction). */
|
|
export function contextWindow(m: ResolvedModel): number | undefined {
|
|
return m.spec.context || undefined
|
|
}
|