yuanzonghao
e88e988de3
Three transport-only optimizations that cut per-session Vercel FOT by ~50-60%: P0 — Server strips voice.referenceAudioBase64 from already-known characters in /api/scene and /api/insert-beat responses (defense-in-depth). P1 — Client strips all voice data from session before sending to /api/scene, /api/vision, and /api/insert-beat. Voices are retained locally and re-merged from responses via mergeCharactersPreserveVoice(). The engine only needs character names + visualDescriptions for scene generation. P3 — /api/beat-audio returns binary audio (Response with Content-Type) instead of JSON-wrapped base64, saving ~33% encoding overhead. Client converts to blob URLs; PlayCanvas accepts a single audioSrc prop. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
51 lines
1.7 KiB
TypeScript
51 lines
1.7 KiB
TypeScript
import { requestScene } from "@infiplot/engine";
|
||
import type { Character, SceneRequest } from "@infiplot/types";
|
||
import { NextResponse } from "next/server";
|
||
import { loadEngineConfig } from "@/lib/config";
|
||
|
||
function stripKnownVoices(
|
||
characters: Character[],
|
||
knownNames: Set<string>,
|
||
): Character[] {
|
||
return characters.map((c) =>
|
||
knownNames.has(c.name) ? { ...c, voice: undefined } : c,
|
||
);
|
||
}
|
||
|
||
export const runtime = "nodejs";
|
||
// Capped at 60 for Vercel Hobby (300 allowed on Pro). The scene pipeline is
|
||
// Writer + CharDesigner×N + Cinematographer + Painter — happy path 9–12s; the
|
||
// tail (cold provider, multiple new characters) can push 30–45s, so 60 is a
|
||
// reasonable headroom on Hobby.
|
||
export const maxDuration = 60;
|
||
|
||
export async function POST(req: Request) {
|
||
let body: SceneRequest;
|
||
try {
|
||
body = (await req.json()) as SceneRequest;
|
||
} catch {
|
||
return NextResponse.json({ error: "Invalid JSON" }, { status: 400 });
|
||
}
|
||
|
||
if (!body.session) {
|
||
return NextResponse.json({ error: "session is required" }, { status: 400 });
|
||
}
|
||
|
||
try {
|
||
const base = loadEngineConfig(req.headers);
|
||
// See StartRequest.clientTts — BYO clients synth in-browser, so drop server TTS.
|
||
const config = body.clientTts === true ? { ...base, tts: undefined } : base;
|
||
const result = await requestScene(config, body);
|
||
const knownNames = new Set(
|
||
(body.session.characters ?? []).map((c) => c.name),
|
||
);
|
||
return NextResponse.json({
|
||
...result,
|
||
characters: stripKnownVoices(result.characters, knownNames),
|
||
});
|
||
} catch (err) {
|
||
const message = err instanceof Error ? err.message : "Unknown error";
|
||
return NextResponse.json({ error: message }, { status: 500 });
|
||
}
|
||
}
|