Open-source platform for 3D AI agents. Turn text or a photo into a rigged, animated GLB avatar, give it an LLM brain, memory and a wallet, and embed it anywhere with one web component. Remote MCP server, x402 payments, Three.js, browser-native.
JavaScript 3d-generationai-agentsanimationavatardigital-humangenerative-aiglbgltfimage-to-3dllmmcpmcp-servermodel-context-protocolsolanatext-to-3dthreejsweb-componentswebglwebxrx402
fix(vision): restore the image judge with a free OpenRouter rung after all three lanes died
nirholasabf076b087ef
diff --git a/api/_lib/seed-quality.js b/api/_lib/seed-quality.jsindex 06f2e18cf..1a907febd 100644--- a/api/_lib/seed-quality.js+++ b/api/_lib/seed-quality.js@@ -5,10 +5,10 @@// asset enters the public catalog:// • api/cron/forge-seed-cron.js — the per-minute trickle, in-process on// Cloud Run (Vertex reachable via the attached service account).-// • the bulk batch runner (gcp-credits campaign, work order 05 task 5, still-// open: not in the tree yet) - driven from a workstation with no GCP-// credentials, so it routes render + judge through the production HTTP-// surfaces instead.+// • scripts/gcp/seed-avatars.mjs - the bulk batch runner, driven from a+// workstation with no GCP credentials, so it routes render (and by default+// the judge too) through the production HTTP surfaces instead. It has no+// 70 s function wall, so unlike the cron it runs BOTH stages below.//// Two stages, cheapest first://@@ -192,9 +192,8 @@ export const SEED_WATCHLIST = Object.freeze([* @param {{ origin: string, fetchImpl?: typeof fetch, timeoutMs?: number }} opts*/export function remoteTransport({ origin, fetchImpl = fetch, timeoutMs = 120_000 }) {- const base = String(origin || '').replace(/\/+$/, '');-async function visionAsk({ png, prompt }) {+ const base = String(origin || '').replace(/\/+$/, '');const res = await fetchImpl(`${base}/api/vision`, {method: 'POST',headers: { 'content-type': 'application/json' },@@ -209,9 +208,81 @@ export function remoteTransport({ origin, fetchImpl = fetch, timeoutMs = 120_000if (!res.ok) throw new Error(`vision ${res.status}: ${JSON.stringify(data).slice(0, 300)}`);return String(data?.text || '');}+ return buildTransport({ name: 'remote', origin, fetchImpl, timeoutMs, visionAsk });+}++/**+ * Same gate as remoteTransport, with the judge running IN THIS PROCESS against+ * api/_lib/vision.js's provider chain instead of the deployed POST /api/vision.+ * Rendering still goes to `origin`, because the renderer is a GPU service with+ * no in-process equivalent; only the judge moves.+ *+ * This is how a vision-chain change is measured before it ships. A fix to the+ * chain cannot be exercised through the deployed endpoint until the deploy+ * lands, so a bulk run that needs the fixed chain points its judge here and+ * keeps its accept rate honest in the meantime. Same prompts, same parser, same+ * verdict maths as remoteTransport; the only difference is which process calls+ * the model, so the numbers are comparable across the two.+ *+ * Needs whatever credentials that chain reads (OPENROUTER_API_KEY, NVIDIA_API_KEY,+ * or GCP application-default credentials for the Vertex anchor) in this process.+ *+ * @param {{ origin: string, fetchImpl?: typeof fetch, timeoutMs?: number }} opts+ */+export function localJudgeTransport({ origin, fetchImpl = fetch, timeoutMs = 120_000 }) {+ async function visionAsk({ png, prompt }) {+ const { describeImage } = await import('./vision.js');+ const out = await describeImage({+ imageBase64: png.toString('base64'),+ prompt,+ maxTokens: 700,+ timeoutMs,+ });+ return String(out?.text || '');+ }+ return buildTransport({ name: 'local-judge', origin, fetchImpl, timeoutMs, visionAsk });+}++/**+ * Shared transport body: the renderer call and the two judge calls, over an+ * injected `visionAsk`. Both transports differ only in that function, and the+ * prompts and parsing must stay identical between them or their accept rates+ * stop being comparable, which is why they are written once here.+ */+function buildTransport({ name, origin, fetchImpl, timeoutMs, visionAsk }) {+ const base = String(origin || '').replace(/\/+$/, '');++ /**+ * Ask for a JSON verdict, and give a model that answered in prose exactly one+ * more chance with the instruction restated as the last thing it reads.+ *+ * The free vision lanes obey "reply with only JSON" most of the time and+ * occasionally open with "The image shows..." instead. Treating that as an+ * infrastructure failure loses the whole asset: it is recorded as ungated,+ * so the run learns nothing about that prompt and re-spends GPU time on it+ * at the next resume. One retry is cheap next to a regeneration, and it is+ * NOT a quality shortcut: the retry only re-asks for the format, never+ * relaxes the verdict, and a second prose reply still fails the gate.+ */+ async function askJson({ png, prompt }) {+ const first = await visionAsk({ png, prompt });+ try {+ return parseJsonReply(first);+ } catch (err) {+ const retry = await visionAsk({+ png,+ prompt: `${prompt}\n\nYour previous reply was prose and could not be parsed. Reply with ONLY the JSON object, starting with { and ending with }. No prose, no markdown fence.`,+ });+ try {+ return parseJsonReply(retry);+ } catch {+ throw err;+ }+ }+ }return {- name: 'remote',+ name,async render({ glbUrl, width = 768, height = 768, theta = 0, phi = 78 }) {const res = await fetchImpl(`${base}/api/render/avatar-clip`, {method: 'POST',@@ -233,7 +304,7 @@ export function remoteTransport({ origin, fetchImpl = fetch, timeoutMs = 120_000},async judgeRealism({ png, prompt, viewLabel }) {const { buildJudgePrompt } = await import('./quality-bench.js');- const text = await visionAsk({+ const parsed = await askJson({png,prompt: buildJudgePrompt({prompt,@@ -242,7 +313,6 @@ export function remoteTransport({ origin, fetchImpl = fetch, timeoutMs = 120_000viewLabel,}),});- const parsed = parseJsonReply(text);const out = {};for (const k of ['photorealism', 'geometryIntegrity', 'textureFidelity', 'promptAdherence']) {const n = Number(parsed[k]);@@ -253,8 +323,7 @@ export function remoteTransport({ origin, fetchImpl = fetch, timeoutMs = 120_000return out;},async judgeRigReadiness({ png, prompt, category }) {- const text = await visionAsk({ png, prompt: buildRigReadinessPrompt({ prompt, category }) });- return normalizeRigReadiness(parseJsonReply(text));+ return normalizeRigReadiness(await askJson({ png, prompt: buildRigReadinessPrompt({ prompt, category }) }));},};}diff --git a/api/_lib/vision.js b/api/_lib/vision.jsindex 6b9bf8b73..ac31723af 100644--- a/api/_lib/vision.js+++ b/api/_lib/vision.js@@ -57,6 +57,34 @@ import {const NVIDIA_VISION_MODELS = ['meta/llama-3.2-11b-vision-instruct',];+// Free OpenRouter vision lanes, in order.+//+// The text chain (llm.js providerChain) has carried an OpenRouter rung for a+// long time; vision never did, and that gap took the whole endpoint down on+// 2026-09-09: NVIDIA answered 500, the paid OpenAI backstop answered 429+// `billing_not_active`, and Vertex answered 403 `Lightning dunning decision is+// deny for project` (a project-level billing hold that denies Vertex AND the+// AI-Studio Gemini endpoint on the same key, so both Google rungs die together).+// Three rungs, one dead chain, and every consumer that judges an image with it+// (catalog seeding's quality gate, forge validation, alt text) went dark.+//+// Only the `:free` suffix is used here. llm-pricing.js prices OpenRouter by+// exactly that suffix (isOpenRouterFreeModel), so a `:free` route is metered at+// zero and the spend ledger stays truthful; OpenRouter's `openrouter/free`+// router meta-model answers fine but would be metered as paid, so it is+// deliberately not in this list.+//+// Verified against the live platform key on 2026-09-09: nemotron-omni answered+// 3/3 in a median 1.5 s with clean parseable JSON, which is what the seed judge+// needs (api/_lib/seed-quality.js parses every reply as JSON). The two Gemma+// routes were saturated (429) in the same probe and are kept behind it as spare+// capacity: a 429 falls through in ~150 ms and, unlike the 410 that retired the+// NIM model above, it recovers when the shared free pool drains.+const OPENROUTER_VISION_MODELS = [+ 'nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free',+ 'google/gemma-4-31b-it:free',+ 'google/gemma-4-26b-a4b-it:free',+];// Paid last-resort tail. gpt-5.4-nano is vision-capable and already priced in// llm-pricing.js, keeping the backstop cheap and the spend ledger truthful.const OPENAI_VISION_MODEL = 'gpt-5.4-nano';@@ -164,7 +192,7 @@ export function inlineImageBudget(remainingMs, timeoutMs) {// a handler that *chose* to surface it can return 503 — but consumers should// generally catch it and degrade silently instead.export class VisionUnavailableError extends Error {- constructor(message = 'No vision provider available. Configure NVIDIA_API_KEY (free), GOOGLE_CLOUD_PROJECT (Vertex Gemini credits anchor), or OPENAI_API_KEY (paid backstop).') {+ constructor(message = 'No vision provider available. Configure NVIDIA_API_KEY or OPENROUTER_API_KEY (free), GOOGLE_CLOUD_PROJECT (Vertex Gemini credits anchor), or OPENAI_API_KEY (paid backstop).') {super(message);this.name = 'VisionUnavailableError';this.code = 'vision_unavailable';@@ -211,6 +239,21 @@ export function visionChain() {}));}}+ // Free OpenRouter routes, alongside the NIM lanes and ahead of the credits+ // anchor: same free tier, same zero meter, and they are the rungs that keep+ // vision answering when both NVIDIA and Google are down at once. Ordering+ // them here leaves the Vertex anchor exactly where it was in the chain+ // relative to the paid tail; nothing is evicted.+ if (env.OPENROUTER_API_KEY) {+ for (const model of OPENROUTER_VISION_MODELS) {+ chain.push(openaiCompatVisionProvider({+ name: 'openrouter',+ key: env.OPENROUTER_API_KEY,+ url: 'https://openrouter.ai/api/v1/chat/completions',+ model,+ }));+ }+ }// Vertex Gemini credits anchor: multimodal (Gemini Flash reads image_url// parts, data URIs included, through the same OpenAI-compatible endpoint),// keyless (OAuth token minted per request), billed to GCP credits. Sitsdiff --git a/scripts/gcp/seed-avatars.mjs b/scripts/gcp/seed-avatars.mjsindex f17632820..deb4968a6 100644--- a/scripts/gcp/seed-avatars.mjs+++ b/scripts/gcp/seed-avatars.mjs@@ -20,6 +20,7 @@* node scripts/gcp/seed-avatars.mjs --limit=500 --concurrency=4* node scripts/gcp/seed-avatars.mjs --categories=accessory* node scripts/gcp/seed-avatars.mjs --no-vision # mesh stage only+ * node scripts/gcp/seed-avatars.mjs --judge=local # judge in-process* node scripts/gcp/seed-avatars.mjs --report # checkpoint stats** RESUMABLE. Every decision is written to a checkpoint keyed by the bare prompt@@ -44,7 +45,7 @@ import { dirname, join, resolve } from 'node:path';import { fileURLToPath } from 'node:url';import { SEED_PROMPTS, composeSeedPrompt } from '../../api/_lib/seed-prompts.js';-import { evaluateSeedAsset, remoteTransport } from '../../api/_lib/seed-quality.js';+import { evaluateSeedAsset, remoteTransport, localJudgeTransport } from '../../api/_lib/seed-quality.js';import { isFreeBackend } from '../../api/_lib/forge-tiers.js';const __dirname = dirname(fileURLToPath(import.meta.url));@@ -66,6 +67,11 @@ const LIMIT = args.limit ? Number(args.limit) : 25;const CONCURRENCY = Math.max(1, Math.min(Number(args.concurrency) || 3, 8));const CATEGORIES = typeof args.categories === 'string' ? args.categories.split(',').map((s) => s.trim()) : null;const VISION = args['no-vision'] !== true;+// Where the vision judge runs. 'remote' (default) calls the deployed+// POST /api/vision; 'local' runs the same prompts against this process's own+// api/_lib/vision.js chain, which is the only way to measure a chain fix before+// its deploy lands. Rendering is remote either way (see seed-quality.js).+const JUDGE = args.judge === 'local' ? 'local' : 'remote';const REPORT_ONLY = !!args.report;const RETRY_REJECTS = !!args['retry-rejects'];@@ -289,12 +295,13 @@ async function main() {// Render + judge run through the live platform's own HTTP surfaces, so the// batch enforces the identical gate from a machine with no GCP credentials.- const transport = VISION ? remoteTransport({ origin: ORIGIN, timeoutMs: GATE_TIMEOUT_MS }) : null;+ const makeTransport = JUDGE === 'local' ? localJudgeTransport : remoteTransport;+ const transport = VISION ? makeTransport({ origin: ORIGIN, timeoutMs: GATE_TIMEOUT_MS }) : null;log('Seeding the avatar catalog from api/_lib/seed-prompts.js');log(` origin ${ORIGIN}`);log(` queue ${queue.length} prompt(s) of ${pool.length} (${Object.keys(state.prompts).length} already decided)`);- log(` gate mesh${VISION ? ' + vision judge (render + Vertex via /api/vision)' : ' only (--no-vision)'}`);+ log(` gate mesh${VISION ? ` + vision judge (remote render, ${JUDGE} judge)` : ' only (--no-vision)'}`);log(` concurrency ${CONCURRENCY}`);log('');