mirror of
https://github.com/diegosouzapw/OmniRoute.git
synced 2026-11-16 17:09:09 +00:00
fix(nvidia): replace retired Nemotron 3 Super with Nemotron 3.5 Super VL (#17928)
Replace retired Nemotron 3 Super with Nemotron 3.5 Super VL. Evidence: focused tests (tests/unit/antigravity-bridge-routing.test.ts, tests/unit/catalog-updates-v3x.test.ts, tests/unit/nvidia-eol-catalog.test.ts, tests/unit/nvidia-nim-registry-6108.test.ts); validated in a combined board (B3) of non-overlapping PRs on origin/release/v3.8.53: 413/419 (the 6 failures: 1 from #18140, ejected; 4 in tests/integration/mcp-origin-host-e2e.test.ts from a Turbopack cache panic in the board worktree — the file passes 4/4 on #17273 alone and paired with every other PR of the board; 1 compression worker-pool timing flake that passes isolated) focused tests; ESLint, typecheck:core, check:open-sse-typecheck, API-route typecheck and check-deps clean; file-size OK; changelog integrity OK against origin/release/v3.8.53. ⚠️ base-red inherited: #17219
This commit is contained in:
@@ -99,17 +99,17 @@ const MODEL_ROUTING_MAP = {
|
||||
// Official OmniRoute Auto Groups
|
||||
"auto/best-fast": "groq/openai/gpt-oss-120b",
|
||||
"auto/best-coding": "mistral/codestral-latest",
|
||||
"auto/best-reasoning": "nvidia/nvidia/nemotron-3-super-120b-a12b",
|
||||
"auto/best-reasoning": "nvidia/nvidia/nemotron-3.5-super-vl-120b-a12b",
|
||||
"auto/best-free": "groq/qwen/qwen3.8-27b",
|
||||
"auto/best-vision": "nvidia/meta/llama-3.2-90b-vision-instruct",
|
||||
"auto/coding:pro": "mistral/codestral-latest",
|
||||
"auto/coding:fast": "groq/openai/gpt-oss-120b",
|
||||
"auto/coding:free": "groq/qwen/qwen3.8-27b",
|
||||
"auto/coding:reliable": "mistral/codestral-latest",
|
||||
"auto/reasoning:pro": "nvidia/nvidia/nemotron-3-super-120b-a12b",
|
||||
"auto/smart": "nvidia/nvidia/nemotron-3-super-120b-a12b",
|
||||
"auto/reasoning:pro": "nvidia/nvidia/nemotron-3.5-super-vl-120b-a12b",
|
||||
"auto/smart": "nvidia/nvidia/nemotron-3.5-super-vl-120b-a12b",
|
||||
"auto/claude-sonnet": "mistral/codestral-latest",
|
||||
"auto/claude-opus": "nvidia/nvidia/nemotron-3-super-120b-a12b",
|
||||
"auto/claude-opus": "nvidia/nvidia/nemotron-3.5-super-vl-120b-a12b",
|
||||
"auto/gemini": "gemini/gemini-2.5-flash",
|
||||
"auto/llama": "groq/openai/gpt-oss-120b",
|
||||
"auto/gemma": "groq/qwen/qwen3.8-27b",
|
||||
@@ -117,22 +117,24 @@ const MODEL_ROUTING_MAP = {
|
||||
// Human-readable Display Names (in case CLI sends displayName in envelope)
|
||||
"Auto: Best Fast (OmniRoute)": "groq/openai/gpt-oss-120b",
|
||||
"Auto: Best Coding (OmniRoute)": "mistral/codestral-latest",
|
||||
"Auto: Best Reasoning (OmniRoute)": "nvidia/nvidia/nemotron-3-super-120b-a12b",
|
||||
"Auto: Best Reasoning (OmniRoute)": "nvidia/nvidia/nemotron-3.5-super-vl-120b-a12b",
|
||||
"Auto: Best Free (OmniRoute)": "groq/qwen/qwen3.8-27b",
|
||||
"Auto: Best Vision (OmniRoute)": "nvidia/meta/llama-3.2-90b-vision-instruct",
|
||||
"Auto: Coding Pro (OmniRoute)": "mistral/codestral-latest",
|
||||
"Auto: Coding Fast (OmniRoute)": "groq/openai/gpt-oss-120b",
|
||||
"Auto: Coding Free (OmniRoute)": "groq/qwen/qwen3.8-27b",
|
||||
"Auto: Coding Reliable (OmniRoute)": "mistral/codestral-latest",
|
||||
"Auto: Reasoning Pro (OmniRoute)": "nvidia/nvidia/nemotron-3-super-120b-a12b",
|
||||
"Auto: Smart (OmniRoute)": "nvidia/nvidia/nemotron-3-super-120b-a12b",
|
||||
"Auto: Reasoning Pro (OmniRoute)": "nvidia/nvidia/nemotron-3.5-super-vl-120b-a12b",
|
||||
"Auto: Smart (OmniRoute)": "nvidia/nvidia/nemotron-3.5-super-vl-120b-a12b",
|
||||
"Auto: Claude Sonnet (OmniRoute)": "mistral/codestral-latest",
|
||||
"Auto: Claude Opus (OmniRoute)": "nvidia/nvidia/nemotron-3-super-120b-a12b",
|
||||
"Auto: Claude Opus (OmniRoute)": "nvidia/nvidia/nemotron-3.5-super-vl-120b-a12b",
|
||||
"Auto: Gemini (OmniRoute)": "gemini/gemini-2.5-flash",
|
||||
"Auto: Llama (OmniRoute)": "groq/openai/gpt-oss-120b",
|
||||
"Auto: Gemma (OmniRoute)": "groq/qwen/qwen3.8-27b",
|
||||
|
||||
// Fail-safe self-healing for dead/retired models
|
||||
"nvidia/nvidia/nemotron-3-super-120b-a12b": "nvidia/nvidia/nemotron-3.5-super-vl-120b-a12b",
|
||||
"nvidia/nemotron-3-super-120b-a12b": "nvidia/nvidia/nemotron-3.5-super-vl-120b-a12b",
|
||||
"nvidia/deepseek-ai/deepseek-v4-pro-0813": "groq/openai/gpt-oss-120b",
|
||||
"deepseek-ai/deepseek-v4-pro-0813": "groq/openai/gpt-oss-120b",
|
||||
"NVIDIA: DeepSeek V4 Pro": "groq/openai/gpt-oss-120b",
|
||||
@@ -262,9 +264,9 @@ const OMNIROUTE_BUILTIN_GROUPS = [
|
||||
descriptionText: "Mistral flagship frontier code reasoning model",
|
||||
},
|
||||
{
|
||||
id: "nvidia/nvidia/nemotron-3-super-120b-a12b",
|
||||
displayName: "NVIDIA: Nemotron 3 Super 120B",
|
||||
descriptionText: "Nemotron 3 Super 120B Deep Reasoning model on NVIDIA NIM",
|
||||
id: "nvidia/nvidia/nemotron-3.5-super-vl-120b-a12b",
|
||||
displayName: "NVIDIA: Nemotron 3.5 Super VL 120B",
|
||||
descriptionText: "Nemotron 3.5 Super VL 120B reasoning model on NVIDIA NIM",
|
||||
},
|
||||
{
|
||||
id: "gemini/gemini-2.5-flash",
|
||||
|
||||
1
changelog.d/fixes/17928-nvidia-retired-nemotron-super.md
Normal file
1
changelog.d/fixes/17928-nvidia-retired-nemotron-super.md
Normal file
@@ -0,0 +1 @@
|
||||
- **fix(nvidia):** Replace the retired `nvidia/nemotron-3-super-120b-a12b` (404 since 2026-10-20) with its replacement `nvidia/nemotron-3.5-super-vl-120b-a12b` in the NVIDIA catalog and Antigravity bridge auto groups ([#17928](https://github.com/diegosouzapw/OmniRoute/pull/17928)) — thanks @DeadY2J
|
||||
@@ -654,7 +654,7 @@ For the full environment variable reference, see the [README](../README.md).
|
||||
|
||||
**Cohere (`cohere/`)** — RAG-focused: `cohere/command-a-reasoning-08-2025`, `cohere/command-a-vision-07-2025`, `cohere/command-a-03-2025`, `cohere/command-r-08-2024`
|
||||
|
||||
**NVIDIA NIM (`nvidia/`)** — Enterprise: `nvidia/z-ai/glm-5.1`, `nvidia/minimaxai/minimax-m2.7`, `nvidia/google/gemma-4-31b-it`, `nvidia/mistralai/mistral-small-4-119b-2603`, `nvidia/mistralai/mistral-large-3-675b-instruct-2512`, `nvidia/qwen/qwen3.5-397b-a17b`, `nvidia/deepseek-ai/deepseek-v4-pro`, `nvidia/openai/gpt-oss-120b`, `nvidia/nvidia/nemotron-3-super-120b-a12b`
|
||||
**NVIDIA NIM (`nvidia/`)** — Enterprise: `nvidia/z-ai/glm-5.1`, `nvidia/minimaxai/minimax-m2.7`, `nvidia/google/gemma-4-31b-it`, `nvidia/mistralai/mistral-small-4-119b-2603`, `nvidia/mistralai/mistral-large-3-675b-instruct-2512`, `nvidia/qwen/qwen3.5-397b-a17b`, `nvidia/deepseek-ai/deepseek-v4-pro`, `nvidia/openai/gpt-oss-120b`, `nvidia/nvidia/nemotron-3.5-super-vl-120b-a12b`
|
||||
|
||||
**Baidu Qianfan (`qianfan/`)** — ERNIE: `qianfan/ernie-5.1`, `qianfan/ernie-5.0-thinking-latest`, `qianfan/ernie-x1.1`
|
||||
|
||||
|
||||
@@ -314,7 +314,7 @@ export const FREE_MODEL_BUDGETS: FreeModelBudget[] = [
|
||||
{ provider: "nscale", modelId: "meta-llama/Llama-4-Scout-17B-16E-Instruct", displayName: "meta-llama/Llama-4-Scout-17B-16E-Instruct", monthlyTokens: 0, creditTokens: 5000000, freeType: "one-time-initial", poolKey: "nscale", tos: "caution" },
|
||||
{ provider: "nscale", modelId: "meta-llama/Llama-3.3-70B-Instruct", displayName: "meta-llama/Llama-3.3-70B-Instruct", monthlyTokens: 0, creditTokens: 5000000, freeType: "one-time-initial", poolKey: "nscale", tos: "caution" },
|
||||
{ provider: "nvidia", modelId: "google/gemma-4-31b-it", displayName: "Gemma 4 31B", monthlyTokens: 0, creditTokens: 0, freeType: "one-time-initial", poolKey: "nvidia", tos: "caution" },
|
||||
{ provider: "nvidia", modelId: "nvidia/nemotron-3-super-120b-a12b", displayName: "Nemotron 3 Super 120B A12B", monthlyTokens: 0, creditTokens: 0, freeType: "one-time-initial", poolKey: "nvidia", tos: "caution" },
|
||||
{ provider: "nvidia", modelId: "nvidia/nemotron-3.5-super-vl-120b-a12b", displayName: "Nemotron 3.5 Super VL 120B A12B", monthlyTokens: 0, creditTokens: 0, freeType: "one-time-initial", poolKey: "nvidia", tos: "caution" },
|
||||
{ provider: "nvidia", modelId: "openai/gpt-oss-120b", displayName: "GPT OSS 120B", monthlyTokens: 0, creditTokens: 0, freeType: "one-time-initial", poolKey: "nvidia", tos: "caution" },
|
||||
// evidence: public-page https://ollama.com/pricing (2026-09-02) — Free plan: "Starter usage credits
|
||||
// included · Includes access to starter models · Add credits to unlock all models"; docs.ollama.com/cloud:
|
||||
|
||||
@@ -7,7 +7,7 @@
|
||||
"google/gemma-4-31b-it",
|
||||
"google/diffusiongemma-26b-a4b-it",
|
||||
"nvidia/nemotron-3-ultra-550b-a55b",
|
||||
"nvidia/nemotron-3-super-120b-a12b",
|
||||
"nvidia/nemotron-3.5-super-vl-120b-a12b",
|
||||
"nvidia/nemotron-3.5-lightning-30b-a3b",
|
||||
"nvidia/nemotron-3-nano-omni-30b-a3b-reasoning",
|
||||
"openai/gpt-oss-120b"
|
||||
|
||||
@@ -33,7 +33,13 @@ export const nvidiaProvider: RegistryEntry = {
|
||||
{ id: "google/gemma-4-31b-it", name: "Gemma 4 31B" },
|
||||
{ id: "google/diffusiongemma-26b-a4b-it", name: "DiffusionGemma 26B A4B IT" },
|
||||
{ id: "nvidia/nemotron-3-ultra-550b-a55b", name: "Nemotron 3 Ultra 550B A55B" },
|
||||
{ id: "nvidia/nemotron-3-super-120b-a12b", name: "Nemotron 3 Super 120B A12B" },
|
||||
// Nemotron 3 Super 120B A12B was retired by NVIDIA on 2026-10-20 (404 "Function not found");
|
||||
// Nemotron 3.5 Super VL is NVIDIA's announced replacement (NVIDIA/NemoClaw#13536).
|
||||
{
|
||||
id: "nvidia/nemotron-3.5-super-vl-120b-a12b",
|
||||
name: "Nemotron 3.5 Super VL 120B A12B",
|
||||
supportsVision: true,
|
||||
},
|
||||
{
|
||||
id: "nvidia/nemotron-3.5-lightning-30b-a3b",
|
||||
name: "Nemotron 3.5 Lightning 30B A3B",
|
||||
|
||||
@@ -68,13 +68,21 @@ test("resolveTargetModel correctly maps OmniRoute auto groups to active provider
|
||||
assert.equal(resolveTargetModel("Auto: Best Coding (OmniRoute)"), "mistral/codestral-latest");
|
||||
assert.equal(
|
||||
resolveTargetModel("auto/best-reasoning"),
|
||||
"nvidia/nvidia/nemotron-3-super-120b-a12b"
|
||||
"nvidia/nvidia/nemotron-3.5-super-vl-120b-a12b"
|
||||
);
|
||||
assert.equal(resolveTargetModel("auto/best-free"), "groq/qwen/qwen3.8-27b");
|
||||
});
|
||||
|
||||
test("resolveTargetModel self-heals retired models and prevents upstream 410 crashes", () => {
|
||||
// Deprecated/retired on NVIDIA NIM
|
||||
assert.equal(
|
||||
resolveTargetModel("nvidia/nvidia/nemotron-3-super-120b-a12b"),
|
||||
"nvidia/nvidia/nemotron-3.5-super-vl-120b-a12b"
|
||||
);
|
||||
assert.equal(
|
||||
resolveTargetModel("nvidia/nemotron-3-super-120b-a12b"),
|
||||
"nvidia/nvidia/nemotron-3.5-super-vl-120b-a12b"
|
||||
);
|
||||
assert.equal(
|
||||
resolveTargetModel("nvidia/deepseek-ai/deepseek-v4-pro-0813"),
|
||||
"groq/openai/gpt-oss-120b"
|
||||
|
||||
@@ -33,7 +33,7 @@ test("NVIDIA catalog includes the current hosted models and GPT OSS 120B alias r
|
||||
assert.ok(ids.has("meta/muse-glimmer-30b"));
|
||||
assert.ok(ids.has("google/diffusiongemma-26b-a4b-it"));
|
||||
assert.ok(ids.has("openai/gpt-oss-120b"));
|
||||
assert.ok(ids.has("nvidia/nemotron-3-super-120b-a12b"));
|
||||
assert.ok(ids.has("nvidia/nemotron-3.5-super-vl-120b-a12b"));
|
||||
|
||||
assert.deepEqual(resolveCanonicalProviderModel("nvidia", "gpt-oss-120b"), {
|
||||
provider: "nvidia",
|
||||
|
||||
@@ -20,6 +20,7 @@ test("NVIDIA static catalog metadata excludes superseded model ids", () => {
|
||||
"deepseek-ai/deepseek-v4-pro",
|
||||
"deepseek-ai/deepseek-v4-flash",
|
||||
"minimaxai/minimax-m2.7",
|
||||
"nvidia/nemotron-3-super-120b-a12b",
|
||||
]) {
|
||||
assert.ok(!registryIds.has(modelId), `${modelId} must not remain in the NVIDIA registry`);
|
||||
assert.ok(
|
||||
|
||||
@@ -12,7 +12,7 @@ const EXPECTED_MODEL_IDS = [
|
||||
"google/gemma-4-31b-it",
|
||||
"google/diffusiongemma-26b-a4b-it",
|
||||
"nvidia/nemotron-3-ultra-550b-a55b",
|
||||
"nvidia/nemotron-3-super-120b-a12b",
|
||||
"nvidia/nemotron-3.5-super-vl-120b-a12b",
|
||||
"nvidia/nemotron-3.5-lightning-30b-a3b",
|
||||
"nvidia/nemotron-3-nano-omni-30b-a3b-reasoning",
|
||||
"openai/gpt-oss-120b",
|
||||
|
||||
Reference in New Issue
Block a user