pjandro/OmniRoute
1
0
Fork 0
mirror of https://github.com/diegosouzapw/OmniRoute.git synced 2026-08-11 01:32:22 +03:00
Code Issues Packages Projects Releases Wiki Activity

fix(providers): remove retired NVIDIA NIM catalog entries

Browse Source
This commit is contained in:
Zartharas
2026-08-08 16:48:13 -05:00
committed by diegosouzapw
parent 918647af69
commit d84c811a8a
4 changed files with 54 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
open-sse/config/freeModelCatalog.data.ts
View File

@@ -311,7 +311,6 @@ export const FREE_MODEL_BUDGETS: FreeModelBudget[] = [
{ provider: "nscale", modelId: "openai/gpt-oss-20b", displayName: "openai/gpt-oss-20b", monthlyTokens: 0, creditTokens: 5000000, freeType: "one-time-initial", poolKey: "nscale", tos: "caution" },
{ 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: "z-ai/glm-5.1", displayName: "GLM 5.1", monthlyTokens: 0, creditTokens: 0, freeType: "one-time-initial", poolKey: "nvidia", tos: "caution" },
{ provider: "nvidia", modelId: "z-ai/glm-5.2", displayName: "GLM 5.2", monthlyTokens: 0, creditTokens: 0, freeType: "one-time-initial", poolKey: "nvidia", tos: "caution" },
{ provider: "nvidia", modelId: "minimaxai/minimax-m2.7", displayName: "MiniMax M2.7", monthlyTokens: 0, creditTokens: 0, freeType: "one-time-initial", poolKey: "nvidia", 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" },
@@ -321,7 +320,6 @@ export const FREE_MODEL_BUDGETS: FreeModelBudget[] = [
{ provider: "nvidia", modelId: "qwen/qwen3.5-397b-a17b", displayName: "Qwen3.5-397B-A17B", monthlyTokens: 0, creditTokens: 0, freeType: "one-time-initial", poolKey: "nvidia", tos: "caution" },
{ provider: "nvidia", modelId: "qwen/qwen3.5-122b-a10b", displayName: "Qwen3.5-122B-A10B", monthlyTokens: 0, creditTokens: 0, freeType: "one-time-initial", poolKey: "nvidia", tos: "caution" },
{ provider: "nvidia", modelId: "stepfun-ai/step-3.5-flash", displayName: "Step 3.5 Flash", monthlyTokens: 0, creditTokens: 0, freeType: "one-time-initial", poolKey: "nvidia", tos: "caution" },
{ provider: "nvidia", modelId: "deepseek-ai/deepseek-v4-pro", displayName: "DeepSeek V4 Pro", 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" },
{ provider: "nvidia", modelId: "openai/gpt-oss-20b", displayName: "GPT OSS 20B", 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" },

2
open-sse/config/nvidiaHostedModels.snapshot.json
View File

@@ -1,5 +1,4 @@
[
"deepseek-ai/deepseek-v4-pro",
"google/gemma-4-31b-it",
"minimaxai/minimax-m2.7",
"mistralai/devstral-2-123b-instruct-2512",
@@ -13,6 +12,5 @@
"qwen/qwen3.5-397b-a17b",
"stepfun-ai/step-3.5-flash",
"thinkingmachines/inkling",
"z-ai/glm-5.1",
"z-ai/glm-5.2"
]

2
open-sse/config/providers/registry/nvidia/index.ts
View File

@@ -32,8 +32,6 @@ export const nvidiaProvider: RegistryEntry = {
{ id: "qwen/qwen3.5-122b-a10b", name: "Qwen3.5-122B-A10B" },
{ id: "stepfun-ai/step-3.5-flash", name: "Step 3.5 Flash" },
{ id: "stepfun-ai/step-3.7-flash", name: "Step 3.7 Flash" },
{ id: "deepseek-ai/deepseek-v4-pro", name: "DeepSeek V4 Pro", supportsReasoning: true },
{ id: "deepseek-ai/deepseek-v4-flash", name: "DeepSeek V4 Flash", supportsReasoning: true },
// Sweep 2026-06-19: verified present in the live NVIDIA NIM /v1/models catalog.
{ id: "moonshotai/kimi-k2.6", name: "Kimi K2.6" },
{ id: "openai/gpt-oss-120b", name: "GPT OSS 120B", toolCalling: false },

54
tests/unit/nvidia-eol-catalog.test.ts Normal file
View File

@@ -0,0 +1,54 @@
import test from "node:test";
import assert from "node:assert/strict";
import { FREE_MODEL_BUDGETS } from "../../open-sse/config/freeModelCatalog.data.ts";
import reviewedLiveIds from "../../open-sse/config/nvidiaHostedModels.snapshot.json" with { type: "json" };
import { nvidiaProvider } from "../../open-sse/config/providers/registry/nvidia/index.ts";
const registryIds = new Set(nvidiaProvider.models.map((model) => model.id));
const documentedFreeIds = new Set(
FREE_MODEL_BUDGETS.filter((model) => model.provider === "nvidia").map((model) => model.modelId)
);
const reviewedIds = new Set(reviewedLiveIds);
test("NVIDIA registry excludes retired DeepSeek V4 models", () => {
assert.ok(
!registryIds.has("deepseek-ai/deepseek-v4-pro"),
"retired deepseek-ai/deepseek-v4-pro must not be advertised"
);
assert.ok(
!registryIds.has("deepseek-ai/deepseek-v4-flash"),
"retired deepseek-ai/deepseek-v4-flash must not be advertised"
);
});
test("NVIDIA static lifecycle metadata excludes known EOL models", () => {
for (const modelId of ["z-ai/glm-5.1", "deepseek-ai/deepseek-v4-pro"]) {
assert.ok(
!reviewedIds.has(modelId),
`${modelId} must not remain in the reviewed NVIDIA hosted-model snapshot`
);
assert.ok(
!documentedFreeIds.has(modelId),
`${modelId} must not remain in the NVIDIA free-model catalog`
);
}
});
test("NVIDIA cleanup preserves the healthy GLM replacement", () => {
assert.ok(registryIds.has("z-ai/glm-5.2"), "z-ai/glm-5.2 must remain in the NVIDIA registry");
assert.ok(
reviewedIds.has("z-ai/glm-5.2"),
"z-ai/glm-5.2 must remain in the reviewed NVIDIA hosted-model snapshot"
);
assert.ok(
documentedFreeIds.has("z-ai/glm-5.2"),
"z-ai/glm-5.2 must remain in the NVIDIA free-model catalog"
);
});