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>
61 lines
3.1 KiB
TypeScript
61 lines
3.1 KiB
TypeScript
// The capacity rule (harness spec, after LLeMbas services/helpers.py): a subagent is not started
|
|
// where its server would unload the session's model, or push the session's cached prompt out.
|
|
import { afterEach, expect, test } from "bun:test"
|
|
import { mkdirSync, mkdtempSync, writeFileSync } from "node:fs"
|
|
import { tmpdir } from "node:os"
|
|
import { join } from "node:path"
|
|
import { createApp } from "../src/app.ts"
|
|
import type { AskReply } from "../src/bus/index.ts"
|
|
import { paths } from "../src/config/paths.ts"
|
|
import type { ResolvedModel } from "../src/provider/types.ts"
|
|
import { capacityRefusal } from "../src/session/capacity.ts"
|
|
import { delta, fakeProvider, toolCall, type Fake } from "./fake-provider.ts"
|
|
|
|
let fake: Fake | undefined
|
|
afterEach(() => fake?.stop())
|
|
|
|
const model = (conn: string, id: string, o: { single?: boolean } = {}): ResolvedModel => ({
|
|
ref: `${conn}/${id}`,
|
|
connectionName: "ai",
|
|
connection: { base_url: "http://x/v1", models: {} },
|
|
id: `${conn}/${id}`,
|
|
spec: o.single ? { single_session: true } : {},
|
|
})
|
|
|
|
test("a model's group (the server's capacity.group): another model of the same GPU is refused, the session's own is not", () => {
|
|
const grouped = (id: string, group?: string): ResolvedModel => ({ ...model("ai", id), spec: group ? { group } : {} })
|
|
const main = grouped("qwen", "gpu")
|
|
expect(capacityRefusal(main, grouped("gemma", "gpu"))).toContain("holds one model at a time")
|
|
// Another server behind the same connection, or a model with no group: free to run beside it.
|
|
expect(capacityRefusal(main, grouped("big", "cloud"))).toBe("")
|
|
expect(capacityRefusal(main, grouped("api"))).toBe("")
|
|
expect(capacityRefusal(main, main)).toBe("")
|
|
})
|
|
|
|
test("one request at a time: the model cannot be its own subagent; another can", () => {
|
|
const main = model("srv", "m", { single: true })
|
|
expect(capacityRefusal(main, main)).toContain("serves one request at a time")
|
|
expect(capacityRefusal(main, model("other", "n"))).toBe("")
|
|
})
|
|
|
|
test("task on a model the server cannot hold beside the session's is refused, and nothing runs", async () => {
|
|
fake = fakeProvider([
|
|
{ chunks: [toolCall(0, "t1", "task", JSON.stringify({ description: "second opinion", prompt: "look at it", model: "f/other" }))] },
|
|
{ chunks: [delta({ content: "I will do it myself." })] },
|
|
])
|
|
mkdirSync(paths.config, { recursive: true })
|
|
writeFileSync(
|
|
join(paths.config, "connections.yaml"),
|
|
`connections:\n f:\n type: webui\n url: ${fake.url}\n models: { f/m: { group: gpu }, f/other: { group: gpu } }\n`,
|
|
{ mode: 0o600 },
|
|
)
|
|
writeFileSync(join(paths.config, "config.yaml"), "model: f/m\n")
|
|
const a = createApp({ cwd: mkdtempSync(join(tmpdir(), "ph-cap-")), mode: "edit", store: false, asker: { ask: async (): Promise<AskReply> => ({ kind: "once" }) } })
|
|
await a.engine.prompt("get a second opinion")
|
|
// Two requests: the session's, then its next step — never one for f/other.
|
|
expect(fake.requests.map((r: any) => r.model)).toEqual(["f/m", "f/m"])
|
|
const result = fake.requests[1].messages.at(-1).content as string
|
|
expect(result).toContain("holds one model at a time")
|
|
expect(result).toContain("Do this part yourself")
|
|
})
|