Files
shockbot/test/models-catalog.main.test.ts
T
Colin McDonnell 3c9799adda add models-bump cron + drop snapshot test
every 12h, scripts/find-newer-models.ts scans models.dev for newer GA
versions of every alias in action/models.ts and writes a focused
per-alias diff. .github/workflows/models-bump.yml short-circuits when
no candidates exist; otherwise hands the diff to pullfrog/pullfrog@main
to evaluate against the policy in wiki/model-resolution.md and open a
single living PR on the pullfrog/models-bump branch.

drops the brittle "latest model per provider" snapshot block in
action/test/models-catalog.main.test.ts (and its .snap file) — the cron
keeps the registry in sync with upstreams, and the remaining validity
tests act as the integrity gate on the bump PR.
2026-05-08 23:27:42 +00:00

115 lines
4.1 KiB
TypeScript

import { describe, expect, it } from "vitest";
import { modelAliases } from "../models.ts";
// ── catalog drift tests — main-only ─────────────────────────────────────────────
//
// these tests fetch models.dev and openrouter.ai to verify that every alias in
// models.ts still corresponds to a live, non-deprecated upstream model. upstream
// catalog drift (new model ships, old model deprecated, etc.) causes failures
// that are unrelated to any code change in the PR — so these run only on main.
//
// the registry is kept in sync with upstreams by the `models-bump` cron
// (`.github/workflows/models-bump.yml`), which scans models.dev every 12h and
// opens a PR bumping `resolve` / `openRouterResolve` for any alias whose
// upstream has shipped a newer GA version. these tests are the integrity gate
// for that PR — they catch typos, removed models, and openrouter mismatches.
//
// run locally with `pnpm test:catalog`.
// in CI, gated to push events on main.
type ModelsDevModel = {
name: string;
status?: string;
release_date?: string;
};
type ModelsDevProvider = {
name: string;
models: Record<string, ModelsDevModel>;
};
type ModelsDevApi = Record<string, ModelsDevProvider>;
const api = fetch("https://models.dev/api.json").then((r) => r.json() as Promise<ModelsDevApi>);
function parseResolve(resolve: string): { provider: string; modelId: string } {
const idx = resolve.indexOf("/");
return { provider: resolve.slice(0, idx), modelId: resolve.slice(idx + 1) };
}
describe("models.dev validity", async () => {
const data = await api;
for (const alias of modelAliases) {
const parsed = parseResolve(alias.resolve);
it(`${alias.resolve} exists on models.dev`, () => {
const providerData = data[parsed.provider];
expect(providerData, `provider "${parsed.provider}" not found on models.dev`).toBeDefined();
const model = providerData.models[parsed.modelId];
expect(
model,
`model "${parsed.modelId}" not found under ${parsed.provider} on models.dev`
).toBeDefined();
});
if (!alias.fallback) {
it(`${alias.resolve} is not deprecated`, () => {
const model = data[parsed.provider]?.models[parsed.modelId];
if (!model) return; // covered by existence test above
expect(model.status, `${alias.resolve} is deprecated on models.dev`).not.toBe("deprecated");
});
}
}
});
describe("openRouterResolve models.dev validity", async () => {
const data = await api;
const seen = new Set<string>();
for (const alias of modelAliases) {
if (!alias.openRouterResolve) continue;
if (seen.has(alias.openRouterResolve)) continue;
seen.add(alias.openRouterResolve);
const parsed = parseResolve(alias.openRouterResolve);
it(`${alias.openRouterResolve} exists on models.dev`, () => {
const providerData = data[parsed.provider];
expect(providerData, `provider "${parsed.provider}" not found on models.dev`).toBeDefined();
const model = providerData.models[parsed.modelId];
expect(
model,
`model "${parsed.modelId}" not found under ${parsed.provider} on models.dev`
).toBeDefined();
});
}
});
type OpenRouterModel = { id: string };
type OpenRouterModelsResponse = { data: OpenRouterModel[] };
const openRouterApi = fetch("https://openrouter.ai/api/v1/models").then(
(r) => r.json() as Promise<OpenRouterModelsResponse>
);
describe("openRouterResolve OpenRouter API validity", async () => {
const orData = await openRouterApi;
const orModelIds = new Set(orData.data.map((m) => m.id));
const seen = new Set<string>();
for (const alias of modelAliases) {
if (!alias.openRouterResolve) continue;
const orModelId = alias.openRouterResolve.slice("openrouter/".length);
if (seen.has(orModelId)) continue;
seen.add(orModelId);
it(`${orModelId} exists on OpenRouter`, () => {
expect(
orModelIds.has(orModelId),
`model "${orModelId}" not found in OpenRouter API (/api/v1/models)`
).toBe(true);
});
}
});