Files
OmniRoute/tests/unit/synced-effort-suffix-learned-validation.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
3.2 KiB
TypeScript

/**
* C1 — the `-<tier>` suffix resolver validates against the EFFECTIVE tier set
* (learned ?? sync), not raw synced metadata. Without this, the catalog
* advertises <alias>/<model>-max (learned set) but dispatch refuses to strip
* `-max` because sync metadata lacks the tier — dead-on-arrival variant.
* Harness mirrors deepseek-thinking-efforts.test.ts (custom provider +
* persistDiscoveredModels + async getModelInfo).
*/
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-c1-effort-dispatch-"));
process.env.DATA_DIR = TEST_DATA_DIR;
process.env.API_KEY_SECRET = process.env.API_KEY_SECRET || "c1-test-secret";
const core = await import("../../src/lib/db/core.ts");
const providersDb = await import("../../src/lib/db/providers.ts");
const modelDiscovery = await import("../../src/lib/providerModels/modelDiscovery.ts");
const { getModelInfo } = await import("../../src/sse/services/model.ts");
const { recordLearnedReasoningEffort, __test_resetLearnedReasoningEffortCaps } =
await import("@omniroute/open-sse/services/learnedReasoningEffortCaps.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 });
}
const PROVIDER = "c1prov";
const MODEL_ID = "c1-model";
async function seed() {
const connection = await providersDb.createProviderConnection({
provider: PROVIDER,
authType: "apikey",
name: "c1-runtime-efforts",
apiKey: `${PROVIDER}-key`,
isActive: true,
testStatus: "active",
});
// Sync tiers deliberately EXCLUDE max — only the learned set will vouch for it.
await modelDiscovery.persistDiscoveredModels(PROVIDER, connection.id, [
{ id: MODEL_ID, reasoning: { supported_efforts: ["none", "low", "medium", "high"] } },
]);
}
test.beforeEach(async () => {
__test_resetLearnedReasoningEffortCaps();
await resetStorage();
await seed();
});
test.after(async () => {
core.resetDbInstance();
fs.rmSync(TEST_DATA_DIR, { recursive: true, force: true, maxRetries: 5, retryDelay: 100 });
});
test("-max resolves once the learned set advertises it (sync metadata does not)", async () => {
// Real record path, executor-style CONNECTION key — NOT the provider alias.
recordLearnedReasoningEffort("openai-compatible-chat-eaff6869", MODEL_ID, ["low", "high", "max"]);
const info = await getModelInfo(`${PROVIDER}/${MODEL_ID}-max`);
assert.equal(info.provider, PROVIDER);
assert.equal(info.model, MODEL_ID);
assert.equal(info.resolvedThinkingEffort, "max");
});
test("-medium still resolves via sync tiers even before anything is learned", async () => {
const info = await getModelInfo(`${PROVIDER}/${MODEL_ID}-medium`);
assert.equal(info.model, MODEL_ID);
assert.equal(info.resolvedThinkingEffort, "medium");
});
test("a tier neither learned nor synced is left untouched (literal id)", async () => {
recordLearnedReasoningEffort("conn-a", MODEL_ID, ["low"]);
const info = await getModelInfo(`${PROVIDER}/${MODEL_ID}-ultra`);
assert.equal(info.resolvedThinkingEffort, undefined);
});