mirror of
https://github.com/diegosouzapw/OmniRoute.git
synced 2026-09-14 10:52:17 +03:00
3d4f3e4960
* 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.
84 lines
2.2 KiB
TypeScript
84 lines
2.2 KiB
TypeScript
import test from "node:test";
|
|
import assert from "node:assert/strict";
|
|
import { mkdtempSync, readFileSync, rmSync, writeFileSync } from "node:fs";
|
|
import { tmpdir } from "node:os";
|
|
import { join } from "node:path";
|
|
import { spawnSync } from "node:child_process";
|
|
|
|
const compareScript = "scripts/router-eval/compare.ts";
|
|
|
|
test("router eval compare retains named comparison artifacts", () => {
|
|
const dir = mkdtempSync(join(tmpdir(), "router-eval-compare-"));
|
|
const baseline = join(dir, "baseline.ndjson");
|
|
const candidate = join(dir, "candidate.ndjson");
|
|
const artifactDir = join(dir, "artifacts");
|
|
const runId = "policy-a-vs-policy-b";
|
|
|
|
writeFileSync(
|
|
baseline,
|
|
JSON.stringify({
|
|
sampleId: "b1",
|
|
configId: "policy-a",
|
|
selectedModel: "gpt-4.1",
|
|
expectedModel: "gpt-4.1",
|
|
latencyMs: 140,
|
|
costUsd: 0.004,
|
|
success: true,
|
|
})
|
|
);
|
|
writeFileSync(
|
|
candidate,
|
|
JSON.stringify({
|
|
sampleId: "c1",
|
|
configId: "policy-b",
|
|
selectedModel: "gpt-4.1",
|
|
expectedModel: "gpt-4.1",
|
|
latencyMs: 130,
|
|
costUsd: 0.004,
|
|
success: true,
|
|
})
|
|
);
|
|
|
|
const result = spawnSync(
|
|
process.execPath,
|
|
[
|
|
"--import",
|
|
"tsx",
|
|
compareScript,
|
|
"--baseline",
|
|
baseline,
|
|
"--candidate",
|
|
candidate,
|
|
"--baseline-name",
|
|
"policy-a",
|
|
"--candidate-name",
|
|
"policy-b",
|
|
"--artifact-dir",
|
|
artifactDir,
|
|
"--run-id",
|
|
runId,
|
|
],
|
|
{ encoding: "utf8" }
|
|
);
|
|
|
|
try {
|
|
assert.equal(result.status, 0);
|
|
assert.ok((result.stdout ?? "").includes("Router Eval Comparison"));
|
|
const runDir = join(artifactDir, runId);
|
|
assert.ok(
|
|
readFileSync(join(runDir, "router-eval.md"), "utf8").includes("Router Eval Comparison")
|
|
);
|
|
assert.ok(
|
|
readFileSync(join(runDir, "router-eval.json"), "utf8").includes("router-eval-comparison")
|
|
);
|
|
const comparison = JSON.parse(readFileSync(join(runDir, "comparison.json"), "utf8")) as Record<
|
|
string,
|
|
unknown
|
|
>;
|
|
assert.equal(comparison.baselineName, "policy-a");
|
|
assert.equal(comparison.candidateName, "policy-b");
|
|
} finally {
|
|
rmSync(dir, { recursive: true, force: true, maxRetries: 5, retryDelay: 100 });
|
|
}
|
|
});
|