mirror of
https://github.com/diegosouzapw/OmniRoute.git
synced 2026-08-12 02:02:13 +03:00
* fix(deps): bump nanoid, dompurify for 2 new Dependabot alerts (#189, #190) Bumps: nanoid ^3.3.17 (was transitive, now overridden), dompurify ^3.4.13 (with monaco-editor scoped override). Closes Dependabot #189, #190. Remaining #182-#188 (js-yaml + mermaid) already closed by #9651 merge — awaiting Dependabot re-scan. npm audit → 0 vulnerabilities. * fix(repo): harden .gitignore to also ignore a _tasks symlink (/_tasks) _tasks is a SEPARATE nested git repo (gitignored). The pattern _tasks/ (trailing slash) ignores only a directory, not a SYMLINK named _tasks. A self-referential _tasks symlink can slip in via git add -A and, once pulled, checkout materializes it over the real _tasks repo (destroying plans/specs/hands-off). Anchored /_tasks ignores the symlink too, preventing re-capture. * fix(services): stop embedded-service supervisor retry loop when binary cannot spawn A non-spawnable supervised binary (ENOENT/EACCES, or an ELF on Windows where spawn() throws EFTYPE synchronously) left the supervisor in 'starting' forever while the HealthChecker polled the dead port every healthIntervalMs. Each failed probe fired a full ProxyFetch dispatcher+native fetch pair, burning CPU and eventually collapsing the server (observed: 24 warns/min against 127.0.0.1:8317 for 2 days). - handle synchronous spawn() throws and the child 'error' event: stop the poller and transition to an explicit error state - transition to error and stop polling when FAILURE_THRESHOLD consecutive health probes fail, including during startup - waitForHealthy re-checks the state after its deadline so a mid-startup error surfaces as a rejection instead of being overwritten by 'running' --------- Co-authored-by: diegosouzapw <diegosouzapw@users.noreply.github.com> Co-authored-by: Diego Rodrigues de Sa e Souza <diegosouza.pw@outlook.com> Co-authored-by: diegosouzapw <diegosouza.pw@gmail.com> Co-authored-by: herjarsa <herjarsa@users.noreply.github.com>
96 lines
3.8 KiB
TypeScript
96 lines
3.8 KiB
TypeScript
/**
|
||
* Regression tests for the embedded-services supervisor (ServiceSupervisor).
|
||
*
|
||
* Bug: when the supervised binary cannot be spawned (ENOENT / EACCES, or a
|
||
* non-executable binary such as an ELF on Windows — EFTYPE), the child emits
|
||
* the 'error' event — NOT 'exit' — and on Windows spawn() can even throw
|
||
* synchronously. The supervisor had no 'error' handler, so it stayed in
|
||
* "starting" forever while the HealthChecker kept polling the dead port every
|
||
* healthIntervalMs (each probe firing a full ProxyFetch dispatcher+native
|
||
* fetch pair, e.g. against a CLIProxyAPI port that will never answer on this
|
||
* platform).
|
||
*
|
||
* Fix under test: the supervisor now (1) handles synchronous spawn() throws
|
||
* and the child 'error' event → stops the poller and transitions to "error",
|
||
* and (2) transitions to "error" and stops the poller once the health checker
|
||
* reports FAILURE_THRESHOLD consecutive failures, including during startup,
|
||
* instead of polling the dead endpoint forever.
|
||
*
|
||
* Run: node --import tsx/esm --import ./open-sse/utils/setupPolyfill.ts --import ./tests/_setup/isolateDataDir.ts --test tests/unit/services/serviceSupervisorSpawnError.test.ts
|
||
*/
|
||
import { describe, it } from "node:test";
|
||
import assert from "node:assert/strict";
|
||
import { mkdtemp, writeFile, rm } from "node:fs/promises";
|
||
import { tmpdir } from "node:os";
|
||
import { join } from "node:path";
|
||
|
||
import { ServiceSupervisor } from "../../../src/lib/services/ServiceSupervisor.ts";
|
||
import type { ServiceConfig } from "../../../src/lib/services/types.ts";
|
||
|
||
function baseConfig(overrides: Partial<ServiceConfig> = {}): ServiceConfig {
|
||
return {
|
||
tool: "cliproxy",
|
||
port: 0,
|
||
spawnArgs: () => ({
|
||
command: process.execPath,
|
||
args: ["-e", "setTimeout(() => {}, 30_000)"],
|
||
env: process.env,
|
||
cwd: tmpdir(),
|
||
}),
|
||
healthUrl: () => "http://127.0.0.1:1/v1/models",
|
||
healthIntervalMs: 50,
|
||
stopTimeoutMs: 1_000,
|
||
logsBufferBytes: 4_096,
|
||
...overrides,
|
||
};
|
||
}
|
||
|
||
describe("ServiceSupervisor spawn-failure handling", () => {
|
||
it("transitions to error and stops polling when the binary cannot be spawned", async () => {
|
||
// A plain text file is not an executable: on Windows spawn() throws
|
||
// synchronously (EFTYPE/EINVAL); on POSIX the child emits 'error'
|
||
// (ENOENT/EACCES). Both paths must land in an explicit error state.
|
||
const dir = await mkdtemp(join(tmpdir(), "svc-sup-spawn-"));
|
||
const badBinary = join(dir, "not-an-executable.txt");
|
||
await writeFile(badBinary, "this is not a runnable binary\n", "utf8");
|
||
|
||
const supervisor = new ServiceSupervisor(
|
||
baseConfig({
|
||
spawnArgs: () => ({
|
||
command: badBinary,
|
||
args: [],
|
||
env: process.env,
|
||
cwd: dir,
|
||
}),
|
||
})
|
||
);
|
||
|
||
try {
|
||
const status = await supervisor.start();
|
||
assert.equal(status.state, "error");
|
||
assert.ok(status.lastError, "lastError should describe the spawn failure");
|
||
assert.match(
|
||
status.lastError!,
|
||
/ENOENT|EACCES|EINVAL|EFTYPE|not recognized|spawn|%1|Win32/i
|
||
);
|
||
} finally {
|
||
await rm(dir, { recursive: true, force: true });
|
||
}
|
||
});
|
||
|
||
it("transitions to error after consecutive health failures instead of polling forever", async () => {
|
||
const supervisor = new ServiceSupervisor(baseConfig());
|
||
try {
|
||
// The child runs but never opens a server on the health URL: the
|
||
// HealthChecker reaches FAILURE_THRESHOLD (3 × 50ms) and the supervisor
|
||
// must surface an explicit error instead of staying "running" with an
|
||
// endless poller.
|
||
await assert.rejects(supervisor.start(), /Health probe failed|Service failed to start/i);
|
||
assert.equal(supervisor.getStatus().state, "error");
|
||
assert.ok(supervisor.getStatus().lastError);
|
||
} finally {
|
||
await supervisor.stop();
|
||
}
|
||
});
|
||
});
|