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>
65 lines
3.9 KiB
TypeScript
65 lines
3.9 KiB
TypeScript
// Every call can say what it is for; the user sees that when asked. The tool never sees the
|
|
// added argument — an MCP server, which gets arguments as they are, least of all.
|
|
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 { z } from "zod"
|
|
import { createApp } from "../src/app.ts"
|
|
import type { AskReply } from "../src/bus/index.ts"
|
|
import { paths } from "../src/config/paths.ts"
|
|
import { BUILTIN_TOOLS } from "../src/tool/registry.ts"
|
|
import { splitPurpose, toSpec, type Tool } from "../src/tool/tool.ts"
|
|
import { delta, fakeProvider, toolCall, type Fake } from "./fake-provider.ts"
|
|
|
|
let fake: Fake | undefined
|
|
afterEach(() => fake?.stop())
|
|
|
|
const spec = (name: string) => toSpec(BUILTIN_TOOLS.find((t) => t.name === name)!).parameters as { properties: Record<string, { description?: string }> }
|
|
|
|
const mcpLike = (props: Record<string, unknown>, seen: unknown[]): Tool =>
|
|
({
|
|
name: "mcp__srv__do",
|
|
access: "mcp__srv__do",
|
|
description: "an MCP tool",
|
|
schema: z.looseObject({}),
|
|
jsonSchema: { type: "object", properties: props },
|
|
permission: () => ({ permission: "mcp__srv__do", class: "execute", patterns: ["*"] }),
|
|
run: async (args: unknown) => (seen.push(args), { output: "done" }),
|
|
}) as Tool
|
|
|
|
test("every tool that can ask takes a purpose; bash says it in description; tools that never ask do not", () => {
|
|
for (const name of ["edit", "write", "read", "web_fetch", "skill_manage", "task"]) expect(spec(name).properties.purpose?.description).toContain("what this call is for")
|
|
expect(spec("bash").properties.purpose).toBeUndefined()
|
|
expect(spec("bash").properties.description?.description).toContain("what this command is for")
|
|
for (const name of ["ask_user", "plan_write", "plan_update", "plan_submit", "job_output", "job_list", "job_stop", "job_send", "report", "notes_search", "note_view", "note_manage"]) expect(spec(name).properties.purpose).toBeUndefined()
|
|
})
|
|
|
|
test("split: taken out of the arguments; a server's own `purpose` stays its own", () => {
|
|
const seen: unknown[] = []
|
|
expect(splitPurpose(mcpLike({ q: {} }, seen), { q: 1, purpose: " find it " })).toEqual({ args: { q: 1 }, purpose: "find it" })
|
|
const own = mcpLike({ purpose: { type: "string" } }, seen)
|
|
expect(toSpec(own).parameters).toEqual({ type: "object", properties: { purpose: { type: "string" } } })
|
|
expect(splitPurpose(own, { purpose: "theirs" })).toEqual({ args: { purpose: "theirs" } })
|
|
const bash = BUILTIN_TOOLS.find((t) => t.name === "bash")!
|
|
expect(splitPurpose(bash, { command: "ls", description: "See what is here" })).toEqual({ args: { command: "ls", description: "See what is here" }, purpose: "See what is here" })
|
|
})
|
|
|
|
test("the asker is told the purpose, and the tool runs without it", async () => {
|
|
fake = fakeProvider([
|
|
{ chunks: [toolCall(0, "c1", "mcp__srv__do", JSON.stringify({ q: "x", purpose: "Check the ticket is still open before closing it" }))] },
|
|
{ chunks: [delta({ content: "ok" }, "stop")] },
|
|
])
|
|
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: {} }\n`, { mode: 0o600 })
|
|
writeFileSync(join(paths.config, "config.yaml"), "model: f/m\n")
|
|
const asked: (string | undefined)[] = []
|
|
const app = createApp({ cwd: mkdtempSync(join(tmpdir(), "ph-purpose-")), store: false, snapshots: false, asker: { ask: async (r): Promise<AskReply> => (asked.push(r.purpose), { kind: "once" }) } })
|
|
const seen: unknown[] = []
|
|
app.engine.o.tools.push(mcpLike({ q: { type: "string" } }, seen))
|
|
expect(await app.engine.prompt("go")).toBe("stop")
|
|
expect(asked).toEqual(["Check the ticket is still open before closing it"])
|
|
expect(seen).toEqual([{ q: "x" }])
|
|
expect(fake.requests[0].tools.find((t: any) => t.function.name === "mcp__srv__do").function.parameters.properties.purpose).toBeDefined()
|
|
})
|