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>
67 lines
4.0 KiB
TypeScript
67 lines
4.0 KiB
TypeScript
// A scripted OpenAI-compatible server. Each request takes the next scripted response.
|
|
export type Scripted =
|
|
| { status: number; body: string }
|
|
| { chunks: unknown[]; done?: boolean; raw?: string; gapMs?: number }
|
|
|
|
export interface Fake {
|
|
url: string
|
|
requests: any[]
|
|
/** Path (with query) and headers of each request, in order. */
|
|
calls: { path: string; headers: Record<string, string> }[]
|
|
stop(): void
|
|
}
|
|
|
|
/** `route`: another fake that answers for a model (by the id in the request), as one LLeMbas server
|
|
* serves models from several backends — the request is passed to it whole, and recorded there. */
|
|
/** `served`: what GET /v1/models lists, as a LLeMbas server lists its models (default two
|
|
* placeholders). Any other GET — the instance's own description, its personalization — is a 404,
|
|
* which a client reads as "this server does not have it". */
|
|
export function fakeProvider(script: Scripted[], opts: { route?: (model: string) => Fake | undefined; served?: Record<string, unknown>[] } = {}): Fake {
|
|
const requests: any[] = []
|
|
const calls: { path: string; headers: Record<string, string> }[] = []
|
|
let i = 0
|
|
const server = Bun.serve({
|
|
port: 0,
|
|
async fetch(req) {
|
|
const url = new URL(req.url)
|
|
if (req.method !== "POST" || url.pathname.endsWith("/unload")) calls.push({ path: url.pathname + url.search, headers: Object.fromEntries(req.headers.entries()) })
|
|
if (url.pathname.endsWith("/models")) return Response.json({ data: opts.served ?? [{ id: "m1", meta: { n_ctx: 32768 } }, { id: "m2", max_model_len: 8192 }] })
|
|
if (url.pathname.endsWith("/props")) return url.pathname.includes("/upstream/swapped/") ? Response.json({ default_generation_settings: { n_ctx: 16384 } }) : new Response("no", { status: 404 })
|
|
if (url.pathname.endsWith("/unload")) return new Response("ok")
|
|
if (req.method === "GET") return new Response("not found", { status: 404 })
|
|
const body = (await req.json()) as any
|
|
const to = typeof body?.model === "string" ? opts.route?.(body.model) : undefined
|
|
if (to) return fetch(to.url.replace(/\/v1$/, "") + url.pathname + url.search, { method: "POST", headers: req.headers, body: JSON.stringify(body) })
|
|
requests.push(body)
|
|
calls.push({ path: url.pathname + url.search, headers: Object.fromEntries(req.headers.entries()) })
|
|
const r = script[i++]
|
|
if (!r) return new Response("script exhausted", { status: 500 })
|
|
if ("status" in r) return new Response(r.body, { status: r.status })
|
|
// gapMs: a pause between chunks, to look at the screen mid-stream.
|
|
if (r.gapMs && !r.raw) {
|
|
const gap = r.gapMs
|
|
const parts = [...r.chunks.map((c) => `data: ${JSON.stringify(c)}\n\n`), ...(r.done === false ? [] : ["data: [DONE]\n\n"])]
|
|
const stream = new ReadableStream({
|
|
async start(ctl) {
|
|
for (const [n, part] of parts.entries()) {
|
|
if (n) await Bun.sleep(gap)
|
|
ctl.enqueue(new TextEncoder().encode(part))
|
|
}
|
|
ctl.close()
|
|
},
|
|
})
|
|
return new Response(stream, { headers: { "content-type": "text/event-stream" } })
|
|
}
|
|
const text = r.raw ?? r.chunks.map((c) => `data: ${JSON.stringify(c)}\n\n`).join("") + (r.done === false ? "" : "data: [DONE]\n\n")
|
|
return new Response(text, { headers: { "content-type": "text/event-stream" } })
|
|
},
|
|
})
|
|
return { url: `http://127.0.0.1:${server.port}/v1`, requests, calls, stop: () => server.stop(true) }
|
|
}
|
|
|
|
/** Chunk helpers in the OpenAI shape. */
|
|
export const delta = (d: Record<string, unknown>, finish: string | null = null) => ({ choices: [{ index: 0, delta: d, finish_reason: finish }] })
|
|
export const usage = (p: number, c: number) => ({ choices: [], usage: { prompt_tokens: p, completion_tokens: c } })
|
|
export const toolCall = (index: number | undefined, id: string | undefined, name: string | undefined, args: unknown) =>
|
|
delta({ tool_calls: [{ ...(index === undefined ? {} : { index }), ...(id ? { id } : {}), function: { ...(name ? { name } : {}), arguments: args } }] })
|