Files
tech-log-frontend/tests/unit/provider-sandbox-probe.test.ts
T
DongHyeonkaandClaude Opus 5 74281b0277 test: probe the provider sandbox instead of failing on it
The 16 sandboxed provider tests in `tests/unit/ci-artifact-contract.test.ts`
fail wherever unprivileged user namespaces are denied. bubblewrap is installed
and answers `--version`, but `bwrap --unshare-net … -- /bin/true` exits 1 with
`bwrap: loopback: Failed RTM_NEWADDR: Operation not permitted`, and it fails the
same way with no netns flag at all (`setting up uid map: Permission denied`), so
this is the whole nested-userns capability and not one option. Sixteen
assertion errors on every local run buried whatever else the file had to say.

`scripts/lib/provider-sandbox-probe.ts` now runs a trivial command under the
real isolation options — `runProviderInSandbox` spreads the same
`PROVIDER_SANDBOX_ISOLATION_ARGUMENTS`, and a test fails if an isolation option
is added to the run without the probe having to clear it. Capability is
measured, never inferred from the binary existing or from a version string;
both would pass here.

An unusable sandbox means two different things in two places, so the decision
is explicit. Locally it is an environment fact: the affected tests skip and
carry the bwrap diagnostic as their skip note, visible as `↓ … [reason]`. In CI
it is a regression — a security gate that silently stopped running is exactly
what these tests exist to catch — so the same probe result fails the run
through one guard test that says "the provider sandbox is unavailable" instead
of sixteen assertion errors.

CI is detected with `CI === "true"` via a new `isCiRun`, sharing the predicate
that already gates `ciBuildEnvironmentFailures`. The workflow sets it at the
top-level `env:` block, so it holds in every job; `CI_RUN_ID` and its
`GITEA_`/`GITHUB_` fallbacks are declared only by the release-tier provider
jobs and are absent from the merge gates that run this file, so keying on them
would have left the CI branch permanently dead.

The three `it.each` groups become `it.for` because only `.for` passes the test
context, which is what carries the skip note.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-18 12:55:56 +09:00

96 lines
4.0 KiB
TypeScript

import { chmod, mkdtemp, readFile, rm, writeFile } from "node:fs/promises";
import { tmpdir } from "node:os";
import path from "node:path";
import { afterEach, describe, expect, it } from "vitest";
import {
PROVIDER_SANDBOX_ISOLATION_ARGUMENTS,
PROVIDER_SANDBOX_UNAVAILABLE,
assertProviderSandboxUsable,
probeProviderSandbox,
providerSandboxDecision,
providerSandboxProbeArguments,
} from "../../scripts/lib/provider-sandbox-probe.ts";
const roots: string[] = [];
afterEach(async () => {
await Promise.all(roots.splice(0).map((root) => rm(root, { recursive: true, force: true })));
});
async function stubSandboxBinary(body: string): Promise<string> {
const root = await mkdtemp(path.join(tmpdir(), "sandbox-probe-"));
roots.push(root);
const binary = path.join(root, "bwrap");
await writeFile(binary, `#!/bin/sh\n${body}\n`);
await chmod(binary, 0o755);
return binary;
}
describe("provider sandbox probe", () => {
it("probes execution rather than the existence of the binary", async () => {
const refuses = await stubSandboxBinary(
'echo "bwrap: loopback: Failed RTM_NEWADDR: Operation not permitted" >&2\nexit 1',
);
const probe = probeProviderSandbox(refuses);
expect(probe.usable).toBe(false);
expect(probe.usable ? "" : probe.reason).toContain(
"bwrap: loopback: Failed RTM_NEWADDR: Operation not permitted",
);
expect(probeProviderSandbox(await stubSandboxBinary("exit 0"))).toEqual({ usable: true });
});
it("reports a missing sandbox binary as its own reason", async () => {
const missing = path.join(await mkdtemp(path.join(tmpdir(), "sandbox-absent-")), "bwrap");
roots.push(path.dirname(missing));
const probe = probeProviderSandbox(missing);
expect(probe.usable).toBe(false);
expect(probe.usable ? "" : probe.reason).toMatch(/is not installed/u);
});
it("probes with the same isolation options the real provider run applies", async () => {
const source = await readFile(
new URL("../../scripts/run-and-validate-provider.ts", import.meta.url),
"utf8",
);
// The run builds its bubblewrap vector from the shared constant and
// declares no isolation option of its own, so an option cannot be added to
// the run without the probe having to clear it as well.
expect(source).toContain("...PROVIDER_SANDBOX_ISOLATION_ARGUMENTS");
expect(source.match(/"(?:--unshare-[a-z]+|--as-pid-1|--new-session|--die-with-parent)"/gu))
.toBeNull();
expect(PROVIDER_SANDBOX_ISOLATION_ARGUMENTS).toEqual(
expect.arrayContaining([
"--unshare-pid", "--unshare-ipc", "--unshare-uts", "--unshare-net", "--as-pid-1",
]),
);
const probeArguments = providerSandboxProbeArguments();
expect(probeArguments.slice(0, PROVIDER_SANDBOX_ISOLATION_ARGUMENTS.length)).toEqual([
...PROVIDER_SANDBOX_ISOLATION_ARGUMENTS,
]);
expect(probeArguments.at(-1)).toBe("/bin/true");
});
it("skips locally and fails in CI on the same unusable sandbox", () => {
const probe = { usable: false, reason: "bwrap: setting up uid map: Permission denied" } as const;
expect(providerSandboxDecision(probe, {})).toEqual({
outcome: "skip",
reason: `${PROVIDER_SANDBOX_UNAVAILABLE}: bwrap: setting up uid map: Permission denied`,
});
expect(providerSandboxDecision(probe, { CI: "true" })).toEqual({
outcome: "fail",
reason: `${PROVIDER_SANDBOX_UNAVAILABLE}: bwrap: setting up uid map: Permission denied`,
});
expect(providerSandboxDecision({ usable: true }, { CI: "true" })).toEqual({ outcome: "run" });
});
it("asserts only the CI failure outcome", () => {
const probe = { usable: false, reason: "denied" } as const;
expect(() => assertProviderSandboxUsable(providerSandboxDecision(probe, { CI: "true" })))
.toThrow(new RegExp(PROVIDER_SANDBOX_UNAVAILABLE, "u"));
expect(() => assertProviderSandboxUsable(providerSandboxDecision(probe, {}))).not.toThrow();
expect(() => assertProviderSandboxUsable(providerSandboxDecision({ usable: true }, { CI: "true" })))
.not.toThrow();
});
});