Files
OmniRoute/tests/unit/router-eval-e2e-chain.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

136 lines
3.7 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 searchScript = "scripts/router-eval/search.ts";
const checkScript = "scripts/check/check-router-eval-regression.ts";
function writeObservation(file: string, configId: string, latencyMs: number, costUsd: number) {
writeFileSync(
file,
`${JSON.stringify({
sampleId: `${configId}-sample`,
configId,
selectedModel: "gpt-4.1",
expectedModel: "gpt-4.1",
latencyMs,
costUsd,
success: true,
})}\n`
);
}
function runSearch(
baseline: string,
candidateName: string,
candidate: string,
artifactDir: string,
runId: string
): string {
const result = spawnSync(
process.execPath,
[
"--import",
"tsx",
searchScript,
"--baseline",
baseline,
"--candidate",
`${candidateName}=${candidate}`,
"--artifact-dir",
artifactDir,
"--run-id",
runId,
"--objective",
"quality",
],
{ encoding: "utf8" }
);
assert.equal(result.status, 0);
const patch = join(artifactDir, runId, "router-config.patch.json");
assert.ok(readFileSync(patch, "utf8").includes("router-config-patch"));
return patch;
}
test("router eval retained chain runs search patches through the check wrapper gate", () => {
const dir = mkdtempSync(join(tmpdir(), "router-eval-e2e-chain-"));
const baseline = join(dir, "baseline.ndjson");
const oldCandidate = join(dir, "old.ndjson");
const newCandidate = join(dir, "new.ndjson");
const searchArtifacts = join(dir, "search-artifacts");
const gateArtifacts = join(dir, "gate-artifacts");
const runId = "chain-001";
writeObservation(baseline, "baseline", 150, 0.004);
writeObservation(oldCandidate, "old-router", 130, 0.004);
writeObservation(newCandidate, "new-router", 100, 0.003);
try {
const baselinePatch = runSearch(
baseline,
"old-router",
oldCandidate,
searchArtifacts,
"old-search"
);
const candidatePatch = runSearch(
baseline,
"new-router",
newCandidate,
searchArtifacts,
"new-search"
);
const result = spawnSync(
process.execPath,
[
"--import",
"tsx",
checkScript,
"--baseline",
baseline,
"--candidate",
newCandidate,
"--baseline-patch",
baselinePatch,
"--candidate-patch",
candidatePatch,
"--artifact-dir",
gateArtifacts,
"--run-id",
runId,
],
{ encoding: "utf8" }
);
assert.equal(result.status, 0);
const runDir = join(gateArtifacts, runId);
assert.ok(
readFileSync(join(runDir, "router-eval.json"), "utf8").includes("router-eval-comparison")
);
assert.ok(
readFileSync(join(runDir, "patch-comparison.json"), "utf8").includes(
"router-config-patch-comparison"
)
);
assert.ok(
readFileSync(join(runDir, "inputs", "baseline.patch.json"), "utf8").includes("old-router")
);
assert.ok(
readFileSync(join(runDir, "inputs", "candidate.patch.json"), "utf8").includes("new-router")
);
const manifest = JSON.parse(readFileSync(join(runDir, "manifest.json"), "utf8")) as {
kind?: string;
result?: { status?: number };
outputs?: { patchJson?: string };
};
assert.equal(manifest.kind, "router-eval-gate-run");
assert.equal(manifest.result?.status, 0);
assert.equal(manifest.outputs?.patchJson, "patch-comparison.json");
} finally {
rmSync(dir, { recursive: true, force: true, maxRetries: 5, retryDelay: 100 });
}
});