The transcript channel only showed STT and LLM seconds. Add wall-clock start/end times and durations for listening, LLM and TTS so it's obvious what takes long; STT surfaces as the gap between listening end and LLM start. - bridge: emit llm_start_ms/llm_end_ms on meta and tts_*_ms on the end event - bot: capture the listening window, assemble full timing after the stream, and render a per-stage breakdown in the transcript message Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
101 lines
3.1 KiB
TypeScript
101 lines
3.1 KiB
TypeScript
import { test, expect } from "bun:test";
|
|
|
|
// bridge.ts imports the runtime `config`, which requires DISCORD_GUILD_ID.
|
|
// Set it before the dynamic import so the module loads without a real .env.
|
|
process.env.DISCORD_GUILD_ID ||= "test-guild";
|
|
const { ndjson, converseStream } = await import("./bridge.ts");
|
|
|
|
const enc = (s: string) => new TextEncoder().encode(s);
|
|
|
|
async function* chunked(...cs: string[]): AsyncGenerator<Uint8Array> {
|
|
for (const c of cs) yield enc(c);
|
|
}
|
|
|
|
test("ndjson yields one object per line even when chunks split mid-line", async () => {
|
|
const out: any[] = [];
|
|
for await (const o of ndjson(chunked('{"a":1}\n{"b":', '2}\n{"c":3}'))) out.push(o);
|
|
expect(out).toEqual([{ a: 1 }, { b: 2 }, { c: 3 }]);
|
|
});
|
|
|
|
test("ndjson skips blank lines and a trailing newline", async () => {
|
|
const out: any[] = [];
|
|
for await (const o of ndjson(chunked('{"a":1}\n\n{"b":2}\n'))) out.push(o);
|
|
expect(out).toEqual([{ a: 1 }, { b: 2 }]);
|
|
});
|
|
|
|
test("converseStream surfaces meta first, then plays each sentence clip in order", async () => {
|
|
const clipA = Buffer.from("clipA");
|
|
const clipB = Buffer.from("clipB");
|
|
const body =
|
|
[
|
|
JSON.stringify({
|
|
type: "meta",
|
|
transcript: "안녕",
|
|
reply: "안녕하세요. 반갑습니다!",
|
|
broadcast_action: "start",
|
|
llm_start_ms: 1000,
|
|
llm_end_ms: 2600,
|
|
}),
|
|
JSON.stringify({ type: "audio", seq: 0, audio_b64: clipA.toString("base64") }),
|
|
JSON.stringify({ type: "audio", seq: 1, audio_b64: clipB.toString("base64") }),
|
|
JSON.stringify({ type: "end", tts_sec: 0.9, tts_start_ms: 2600, tts_end_ms: 3500 }),
|
|
].join("\n") + "\n";
|
|
|
|
const orig = globalThis.fetch;
|
|
globalThis.fetch = (async () => ({
|
|
ok: true,
|
|
body: chunked(body),
|
|
text: async () => "",
|
|
})) as any;
|
|
|
|
try {
|
|
const events: string[] = [];
|
|
const clips: Buffer[] = [];
|
|
let meta: any;
|
|
let end: any;
|
|
await converseStream(Buffer.from("wav"), true, {
|
|
onMeta: (m) => {
|
|
meta = m;
|
|
events.push("meta");
|
|
},
|
|
onAudio: (c) => {
|
|
clips.push(c);
|
|
events.push("audio");
|
|
},
|
|
onEnd: (e) => {
|
|
end = e;
|
|
events.push("end");
|
|
},
|
|
});
|
|
|
|
expect(meta.transcript).toBe("안녕");
|
|
expect(meta.broadcast_action).toBe("start");
|
|
// LLM wall-clock window rides on the meta line.
|
|
expect(meta.llm_start_ms).toBe(1000);
|
|
expect(meta.llm_end_ms).toBe(2600);
|
|
// Meta must arrive before any audio, the end (with TTS timing) comes last,
|
|
// and clips stay in order.
|
|
expect(events).toEqual(["meta", "audio", "audio", "end"]);
|
|
expect(clips.map((c) => c.toString())).toEqual(["clipA", "clipB"]);
|
|
expect(end.tts_start_ms).toBe(2600);
|
|
expect(end.tts_end_ms).toBe(3500);
|
|
} finally {
|
|
globalThis.fetch = orig;
|
|
}
|
|
});
|
|
|
|
test("converseStream throws on a non-ok bridge response", async () => {
|
|
const orig = globalThis.fetch;
|
|
globalThis.fetch = (async () => ({
|
|
ok: false,
|
|
status: 500,
|
|
body: null,
|
|
text: async () => "boom",
|
|
})) as any;
|
|
try {
|
|
await expect(converseStream(Buffer.from("wav"), undefined, {})).rejects.toThrow("500");
|
|
} finally {
|
|
globalThis.fetch = orig;
|
|
}
|
|
});
|