Files
OmniRoute/tests/unit/provider-models-token-limits.test.ts
Diego Rodrigues de Sa e Souza 3d4f3e4960 test(infra): retry recursive temp-dir removal instead of failing a shard on ENOTEMPTY (#11966) (#11968)
* test(infra): retry recursive temp-dir removal instead of failing a shard on ENOTEMPTY (#11966)

Two shards on release/v3.8.51 went red in one day with the same signature —
"ENOTEMPTY, Directory not empty: /tmp/omniroute-<test>-XXXXXX" — from
combo-same-provider-cascade (Unit Tests fast-path 4/4, on a PR that touches only
.github/) and auth-policy-embeddings-webfetch-7785 (the 20k-test TIA step). Both pass
alone and on re-run: the cleanup races something still writing into the directory
(SQLite WAL/-shm checkpoint, a worker, the backup) and under a loaded hosted runner
the window opens. 1154 test files do their own cleanup with
fs.rmSync(dir, { recursive: true, force: true }); 57 already asked for retries.

One-shot codemod (scripts/ad-hoc/codemod-rm-maxretries.mjs, kept for the record):
every rm / rmSync / rmdirSync option object with `recursive: true` and no
`maxRetries` gains `maxRetries: 5, retryDelay: 100` — Node itself then retries
ENOTEMPTY/EBUSY/EPERM for up to ~0.5 s before giving up. 2243 call sites in 1292
files under tests/, the shared tests/_setup/isolateDataDir.ts exit hook included.
Only the option object changes: no call site, assertion or import is touched.

Validation: prettier and ESLint (with the frozen suppressions) clean on all 1292
files; a random 20-file sample runs green (quota-redis-store hangs identically on
the untouched tree — it needs a Redis on localhost, an environment matter). The
four unit shards on this PR are the full run.

* fix(quality): let check-forgotten-sibling-tests read a 1,000-file diff

The gate shells out to `git diff` through execFileSync with Node's default 1 MB
maxBuffer; the 1,292-file codemod in this PR is the first diff large enough to
overflow it, and the gate died with `spawnSync git ENOBUFS` before comparing
anything. 64 MB is far above any real PR and costs nothing when unused.
2026-08-29 01:17:40 -03:00

81 lines
2.8 KiB
TypeScript

import test from "node:test";
import assert from "node:assert/strict";
import fs from "node:fs";
import os from "node:os";
import path from "node:path";
const TEST_DATA_DIR = fs.mkdtempSync(
path.join(os.tmpdir(), "omniroute-provider-model-token-limits-")
);
process.env.DATA_DIR = TEST_DATA_DIR;
const core = await import("../../src/lib/db/core.ts");
const modelsDb = await import("../../src/lib/db/models.ts");
const providerModelsRoute = await import("../../src/app/api/provider-models/route.ts");
async function resetStorage() {
core.resetDbInstance();
fs.rmSync(TEST_DATA_DIR, { recursive: true, force: true, maxRetries: 5, retryDelay: 100 });
fs.mkdirSync(TEST_DATA_DIR, { recursive: true });
}
function buildPostRequest(body) {
return new Request("http://localhost/api/provider-models", {
method: "POST",
headers: { "Content-Type": "application/json" },
body: JSON.stringify(body),
});
}
test.beforeEach(async () => {
await resetStorage();
});
test.after(async () => {
core.resetDbInstance();
fs.rmSync(TEST_DATA_DIR, { recursive: true, force: true, maxRetries: 5, retryDelay: 100 });
});
// #1294: POST /api/provider-models must persist max_input_tokens / max_output_tokens
// (stored as inputTokenLimit / outputTokenLimit) so the token limits set in the
// "add custom model" form survive into the catalog round-trip.
test("POST persists max_input_tokens / max_output_tokens as inputTokenLimit / outputTokenLimit", async () => {
const response = await providerModelsRoute.POST(
buildPostRequest({
provider: "openai-compatible-demo",
modelId: "custom-long-context",
modelName: "Custom Long Context",
max_input_tokens: 200000,
max_output_tokens: 16384,
})
);
const body = (await response.json()) as any;
assert.equal(response.status, 200);
assert.equal(body.model?.id, "custom-long-context");
assert.equal(body.model?.inputTokenLimit, 200000);
assert.equal(body.model?.outputTokenLimit, 16384);
const stored = await modelsDb.getCustomModels("openai-compatible-demo");
const persisted = stored.find((model) => model.id === "custom-long-context");
assert.ok(persisted, "custom model should be persisted");
assert.equal(persisted.inputTokenLimit, 200000);
assert.equal(persisted.outputTokenLimit, 16384);
});
test("POST omits token limits when they are not provided", async () => {
const response = await providerModelsRoute.POST(
buildPostRequest({
provider: "openai-compatible-demo",
modelId: "custom-no-limits",
modelName: "Custom No Limits",
})
);
const body = (await response.json()) as any;
assert.equal(response.status, 200);
assert.equal(body.model?.id, "custom-no-limits");
assert.equal("inputTokenLimit" in body.model, false);
assert.equal("outputTokenLimit" in body.model, false);
});