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): floor the lane timeout so the fallback rung can send at all
nirholasbdea4fc55044
diff --git a/api/_lib/vision.js b/api/_lib/vision.jsindex cef48e976..6b9bf8b73 100644--- a/api/_lib/vision.js+++ b/api/_lib/vision.js@@ -44,12 +44,17 @@ import {vertexGeminiHeaders,} from './vertex-gemini.js';-// Free NIM vision lanes, in order. nemotron-nano carries the smallest image-// token footprint (~281 prompt tokens for a tiny image vs ~1600 for llama-90B);-// llama-3.2-11b is a different model family, so its failure modes are-// independent — a real second lane, not a re-roll of the first.+// Free NIM vision lanes, in order.+//+// `nvidia/nemotron-nano-12b-v2-vl` used to lead here for its small image token+// footprint. NVIDIA retired it: the host answers every request for it with a+// hard 410 ("has reached its end of life on 2026-08-26T09:00:00Z"), verified+// against production on 2026-09-08. A 410 never recovers, so leaving it in the+// list only spent the first, largest slice of every vision request's deadline+// on a model that cannot answer. Adding a replacement free NIM VLM needs a live+// NVIDIA_API_KEY to probe the catalog against, which is why this is a removal+// rather than a swap.const NVIDIA_VISION_MODELS = [- 'nvidia/nemotron-nano-12b-v2-vl','meta/llama-3.2-11b-vision-instruct',];// Paid last-resort tail. gpt-5.4-nano is vision-capable and already priced in@@ -76,11 +81,11 @@ const OPENAI_VISION_MODEL = 'gpt-5.4-nano';// remaining budget across the lanes that are still to come guarantees// every rung a real attempt, which is the only reason a chain exists.//-// The two free NIM rungs share one host, so a transport failure or a 429 there-// is a statement about the HOST, not the model: cooling only the model that-// happened to be asked would send the very next request to its twin on the same-// sick host. Model-specific rejections (a 404 for a retired model id, a 400)-// cool just that lane.+// Free NIM rungs share one host, so a transport failure or a 429 there is a+// statement about the HOST, not the model: cooling only the model that happened+// to be asked would send the very next request to a sibling on the same sick+// host. Model-specific rejections (a 404 for a retired model id, a 400) cool+// just that lane, and a 410 parks it for the long window (see below).const VISION_LANE_COOLDOWN_SECONDS = 45;// Below this a lane cannot complete a VLM call, so handing it a smaller slice// only burns budget the next rung could have used.@@ -132,7 +137,16 @@ export function laneAttemptTimeout(remainingMs, lanesLeft, timeoutMs) {const share = remainingMs / Math.max(1, lanesLeft);// The floor may exceed the share when the budget is nearly spent; capping it// by what is actually left keeps the attempt inside the deadline either way.- return Math.max(1, Math.min(timeoutMs, remainingMs, Math.max(MIN_LANE_ATTEMPT_MS, share)));+ //+ // Math.floor is load-bearing, not cosmetic: this value is handed straight to+ // AbortSignal.timeout(), which rejects a non-integer delay with+ // ERR_OUT_OF_RANGE. The division above produces an integer only when the+ // remaining budget happens to divide evenly by the lane count, so in+ // production the fallback rung usually threw before it sent a single byte+ // and was recorded as "unreachable" ("The value of \"delay\" is out of range.+ // It must be an integer. Received 7924.333333333333"). That silently cost the+ // chain the very rung it exists for, on every request that reached it.+ return Math.floor(Math.max(1, Math.min(timeoutMs, remainingMs, Math.max(MIN_LANE_ATTEMPT_MS, share))));}/**@@ -465,7 +479,11 @@ export async function describeImage({// every rung sharing it. Anything else (a 404 for a retired model id, a// 400) is specific to this model and cools this lane alone.const st = upstream.status;- const authFault = st === 401 || st === 403 || st === 402;+ // 410 Gone is how NIM reports a retired model id. Unlike a 404 or a 500 it+ // is a permanent verdict about this model, so it parks the lane for the+ // long window instead of being re-probed (and re-charged a slice of the+ // deadline) on every request until someone notices.+ const authFault = st === 401 || st === 403 || st === 402 || st === 410;// A 429 is the one verdict that is unambiguously about the HOST and the// account behind it: every model served there is throttled by the same// quota, so both the bench and the in-request skip cover every siblingdiff --git a/tests/api/vision-lane-health.test.js b/tests/api/vision-lane-health.test.jsindex ef93f3e5a..6867b47df 100644--- a/tests/api/vision-lane-health.test.js+++ b/tests/api/vision-lane-health.test.js@@ -16,7 +16,6 @@ const ENV_KEYS = ['NVIDIA_API_KEY', 'OPENAI_API_KEY', 'GOOGLE_CLOUD_PROJECT'];const ORIGINAL_ENV = Object.fromEntries(ENV_KEYS.map((k) => [k, process.env[k]]));const LANE_KEYS = [- 'vision:nvidia:nvidia/nemotron-nano-12b-v2-vl','vision:nvidia:meta/llama-3.2-11b-vision-instruct','vision:openai:gpt-5.4-nano',];@@ -75,6 +74,23 @@ describe('laneAttemptTimeout', () => {it('leaves the caller timeout alone when there is no deadline', () => {expect(laneAttemptTimeout(Infinity, 3, 20_000)).toBe(20_000);});+ it('always returns an integer AbortSignal.timeout will accept', () => {+ // Every case above divides evenly, which is how a fractional return value+ // shipped: AbortSignal.timeout() throws ERR_OUT_OF_RANGE on a non-integer+ // delay, so the lane threw before sending a byte and the chain lost its+ // fallback rung. 23_474/3 is the shape production actually produced.+ const split = laneAttemptTimeout(23_474, 3, 20_000);+ expect(Number.isInteger(split)).toBe(true);+ expect(split).toBe(7_824);+ expect(() => AbortSignal.timeout(split)).not.toThrow();+ for (const remaining of [23_474, 9_999, 12_345, 7_001]) {+ for (const lanes of [1, 2, 3, 4, 7]) {+ const ms = laneAttemptTimeout(remaining, lanes, 20_000);+ expect(Number.isInteger(ms)).toBe(true);+ expect(() => AbortSignal.timeout(ms)).not.toThrow();+ }+ }+ });});describe('inlineImageBudget', () => {@@ -98,8 +114,8 @@ describe('vision lane cooldowns', () => {const a = await describeImage({ prompt: 'p', imageBase64: 'AAAA', mimeType: 'image/png' });expect(a.provider).toBe('openai');// 429 is the one verdict that is unambiguously about the host and its- // quota, so the sibling rung is skipped inside this very request: one- // throttled attempt is paid, not one per model the host serves.+ // quota, so every rung sharing that host is skipped inside this very+ // request: one throttled attempt is paid, not one per model it serves.expect(first.filter((c) => c.url.includes('nvidia')).length).toBe(1);const second = stubFetch([@@ -112,32 +128,39 @@ describe('vision lane cooldowns', () => {expect(second[0].url).toContain('openai.com');});- it('keeps trying the twin rung on a transport failure, which may be one slow model', async () => {- let nimCalls = 0;+ it('fails a transport error over to the backstop rather than giving up', async () => {const calls = stubFetch([- ['integrate.api.nvidia.com', () => {- if (++nimCalls === 1) throw Object.assign(new Error('aborted'), { name: 'TimeoutError' });- return chatOk('twin answered');- }],+ ['integrate.api.nvidia.com', () => { throw Object.assign(new Error('aborted'), { name: 'TimeoutError' }); }],+ ['api.openai.com', () => chatOk('backstop answered')],]);const r = await describeImage({ prompt: 'p', imageBase64: 'AAAA', mimeType: 'image/png' });- expect(r.text).toBe('twin answered');- expect(calls.filter((c) => c.url.includes('nvidia')).length).toBe(2);+ expect(r.text).toBe('backstop answered');+ expect(r.provider).toBe('openai');+ // The NIM rung was really attempted before the failover: a chain that skips+ // its free lane and bills the paid one is the regression worth catching.+ expect(calls.filter((c) => c.url.includes('nvidia')).length).toBe(1);});- it('benches only the failing model on a 5xx, keeping its twin on the same host', async () => {- let nimCalls = 0;+ it('parks a 410 lane for the long window instead of re-probing a retired model', async () => {+ // NVIDIA answers a retired model id with 410 Gone. That verdict never+ // reverses, so the lane must be benched for the auth-length window, not the+ // 45s health one, or every request keeps paying it a slice of the deadline.stubFetch([- ['integrate.api.nvidia.com', () => (++nimCalls === 1 ? httpErr(500, 'boom') : chatOk('twin'))],+ ['integrate.api.nvidia.com', () => httpErr(410, "model has reached its end of life")],+ ['api.openai.com', () => chatOk('backstop')],]);const a = await describeImage({ prompt: 'p', imageBase64: 'AAAA', mimeType: 'image/png' });- expect(a.provider).toBe('nvidia');+ expect(a.provider).toBe('openai');- // Next request still leads with a NIM lane, because a model-level 500 is no- // evidence against the host or against the sibling model.- const next = stubFetch([['integrate.api.nvidia.com', () => chatOk('ok')]]);- await describeImage({ prompt: 'p', imageBase64: 'AAAA', mimeType: 'image/png' });- expect(next[0].url).toContain('integrate.api.nvidia.com');+ // The retired lane is now behind the healthy one, so the next request does+ // not lead with it.+ const next = stubFetch([+ ['integrate.api.nvidia.com', () => httpErr(410, 'gone')],+ ['api.openai.com', () => chatOk('backstop again')],+ ]);+ const b = await describeImage({ prompt: 'p', imageBase64: 'AAAA', mimeType: 'image/png' });+ expect(b.provider).toBe('openai');+ expect(next[0].url).toContain('openai.com');});it('clears a lane cooldown as soon as that lane serves a real request', async () => {