headroom/plugins/openclaw/test/engine.test.ts
Sergei Baikin 6576ef639c
fix(openclaw-plugin): circuit breaker + per-request timeout for proxy resilience (#639)
## Description

This change adds bounded timeout and circuit-breaker behavior so
OpenClaw can degrade safely when Headroom or the upstream stream stalls,
while returning structured proxy errors instead of hanging.

Closes #638 by improving OpenClaw/proxy resilience when the Headroom
proxy stalls or Anthropic resets a stream. The PR adds proxy-side
handling for `httpx.RemoteProtocolError`, returns structured 502
responses for otherwise unhandled proxy middleware errors, and adds
OpenClaw plugin timeout/circuit-breaker fallback behavior.

## Type of Change

- [x] Bug fix
- [ ] New feature
- [x] Documentation
- [ ] Refactor
- [x] Tests only

## Changes Made

- Added OpenClaw plugin per-request compression timeout and circuit
breaker fallback.
- Cleared timeout timers after successful or failed compression so
successful calls do not leave pending timers.
- Added a focused Vitest regression for timeout cleanup.
- Added `contracts.tools` for `headroom_retrieve` without whole-file
manifest reformatting.
- Added proxy handling for mid-stream `httpx.RemoteProtocolError` and
structured 502 fallback behavior.
- Documented the new OpenClaw resilience configuration fields.

## Testing

- [x] Unit tests
- [x] Integration-style proxy tests
- [x] Typecheck/build
- [ ] Manual testing

### Test Output

```text
cd plugins/openclaw && npm test
Test Files 6 passed (6), Tests 55 passed (55)

cd plugins/openclaw && npm run typecheck
passed

cd plugins/openclaw && npm run build
Build success

UV_SKIP_WHEEL_FILENAME_CHECK=1 uv run --with pytest --with pytest-asyncio --with fastapi --with httpx --with uvicorn --with h2 python -m pytest tests/test_proxy_streaming_resilience.py -q
24 passed in 2.16s
```

## Real Behavior Proof

- Environment: Windows 11, Node/npm from local plugin worktree, Python
3.13.3, focused local worktree for PR #639.
- Exact command / steps: Installed plugin dependencies, ran OpenClaw
plugin tests/typecheck/build, and ran the proxy streaming resilience
suite with required async/FastAPI/httpx extras.
- Observed result: Plugin tests, typecheck, build, and proxy resilience
tests all passed.
- Not tested: Live OpenClaw gateway session in this pass; original
reporter previously verified patched files in a container and OpenClaw
degraded/recovered cleanly.

## Review Readiness

- [x] I have performed a self-review
- [x] This PR is ready for human review

---------

Co-authored-by: Sergei Baikin <sergei.baikin@fotograf.de>
Co-authored-by: JerrettDavis <mxjerrett@gmail.com>
Co-authored-by: JD Davis <jd@jds-macbook-air.tail2a279.ts.net>
2026-08-13 11:52:01 -05:00

253 lines
8 KiB
TypeScript

import { afterEach, describe, expect, it, vi } from "vitest";
const mocked = vi.hoisted(() => ({
start: vi.fn(async () => "http://127.0.0.1:8787"),
stop: vi.fn(async () => undefined),
logger: {
debug: vi.fn(),
error: vi.fn(),
info: vi.fn(),
warn: vi.fn(),
},
}));
vi.mock("headroom-ai", () => ({
compress: vi.fn(),
}));
vi.mock("../src/proxy-manager.js", () => ({
ProxyManager: class {
start = mocked.start;
stop = mocked.stop;
},
defaultLogger: mocked.logger,
}));
import { HeadroomContextEngine } from "../src/engine.js";
import { compress } from "headroom-ai";
afterEach(() => {
vi.mocked(compress).mockReset();
mocked.start.mockReset();
mocked.start.mockResolvedValue("http://127.0.0.1:8787");
mocked.stop.mockClear();
mocked.logger.debug.mockClear();
mocked.logger.error.mockClear();
mocked.logger.info.mockClear();
mocked.logger.warn.mockClear();
});
describe("HeadroomContextEngine proxy startup helpers", () => {
it("bootstraps by scheduling proxy startup when enabled", async () => {
const engine = new HeadroomContextEngine();
await expect(
engine.bootstrap({
sessionId: "session-1",
sessionFile: "session.jsonl",
}),
).resolves.toEqual({
bootstrapped: true,
reason: "proxy startup scheduled",
});
expect(mocked.start).toHaveBeenCalledTimes(1);
});
it("removes unsubscribed proxy listeners before notifying readiness", async () => {
const engine = new HeadroomContextEngine();
const first = vi.fn();
const second = vi.fn();
const unsubscribeFirst = engine.onProxyReady(first);
engine.onProxyReady(second);
unsubscribeFirst();
engine.ensureProxyStarted();
await engine.ensureProxyUrl();
expect(first).not.toHaveBeenCalled();
expect(second).toHaveBeenCalledWith("http://127.0.0.1:8787");
});
it("returns the existing proxy URL without starting again", async () => {
const engine = new HeadroomContextEngine();
(engine as { proxyUrl: string | null }).proxyUrl = "http://127.0.0.1:8787";
await expect(engine.ensureProxyUrl()).resolves.toBe("http://127.0.0.1:8787");
expect(mocked.start).not.toHaveBeenCalled();
});
it("throws when proxy startup is disabled", async () => {
const engine = new HeadroomContextEngine({ enabled: false });
await expect(engine.ensureProxyUrl()).rejects.toThrow("Headroom proxy startup is disabled");
expect(mocked.start).not.toHaveBeenCalled();
});
it("does not emit an unhandledRejection when fire-and-forget startup fails", async () => {
mocked.start.mockReset();
mocked.start.mockRejectedValue(new Error("proxy boom"));
const engine = new HeadroomContextEngine();
const unhandled: unknown[] = [];
const onUnhandled = (reason: unknown) => unhandled.push(reason);
process.on("unhandledRejection", onUnhandled);
try {
// Fire-and-forget: caller intentionally does not await.
engine.ensureProxyStarted();
// Let the startup promise settle and any microtasks/macrotasks flush.
await new Promise((resolve) => setTimeout(resolve, 0));
expect(unhandled).toEqual([]);
expect(mocked.logger.warn).toHaveBeenCalledWith(
expect.stringContaining("Headroom proxy unavailable"),
);
} finally {
process.off("unhandledRejection", onUnhandled);
}
});
it("stores the startup failure in getProxyStartupError()", async () => {
const failure = new Error("proxy boom");
mocked.start.mockReset();
mocked.start.mockRejectedValue(failure);
const engine = new HeadroomContextEngine();
expect(engine.getProxyStartupError()).toBeNull();
engine.ensureProxyStarted();
await new Promise((resolve) => setTimeout(resolve, 0));
expect(engine.getProxyStartupError()).toBe(failure);
});
it("allows retrying startup after a failure", async () => {
mocked.start.mockReset();
mocked.start
.mockRejectedValueOnce(new Error("proxy boom"))
.mockResolvedValueOnce("http://127.0.0.1:8787");
const engine = new HeadroomContextEngine();
engine.ensureProxyStarted();
await new Promise((resolve) => setTimeout(resolve, 0));
expect(engine.getProxyStartupError()).toBeInstanceOf(Error);
// A second attempt is possible once the failed promise has cleared.
const url = await engine.ensureProxyUrl();
expect(url).toBe("http://127.0.0.1:8787");
expect(engine.getProxyStartupError()).toBeNull();
expect(mocked.start).toHaveBeenCalledTimes(2);
});
it("ensureProxyUrl rejects cleanly on startup failure without unhandledRejection", async () => {
const failure = new Error("proxy boom");
mocked.start.mockReset();
mocked.start.mockRejectedValue(failure);
const engine = new HeadroomContextEngine();
const unhandled: unknown[] = [];
const onUnhandled = (reason: unknown) => unhandled.push(reason);
process.on("unhandledRejection", onUnhandled);
try {
await expect(engine.ensureProxyUrl()).rejects.toBe(failure);
await new Promise((resolve) => setTimeout(resolve, 0));
expect(unhandled).toEqual([]);
} finally {
process.off("unhandledRejection", onUnhandled);
}
});
it("isolates and logs proxy-ready listener rejections", async () => {
const engine = new HeadroomContextEngine();
const failing = vi.fn(async () => {
throw new Error("listener boom");
});
const healthy = vi.fn();
engine.onProxyReady(failing);
engine.onProxyReady(healthy);
engine.ensureProxyStarted();
// ensureProxyUrl must still resolve despite the listener throwing.
await expect(engine.ensureProxyUrl()).resolves.toBe("http://127.0.0.1:8787");
expect(failing).toHaveBeenCalled();
expect(healthy).toHaveBeenCalledWith("http://127.0.0.1:8787");
expect(mocked.logger.warn).toHaveBeenCalledWith(
expect.stringContaining("Headroom proxy ready listener failed"),
);
expect(engine.getProxyStartupError()).toBeNull();
});
it("schedules startup and returns original messages when assembling before proxy readiness", async () => {
const engine = new HeadroomContextEngine();
const messages = [{ role: "user", content: "hello" }];
await expect(
engine.assemble({
sessionId: "session-1",
messages,
}),
).resolves.toEqual({
messages,
estimatedTokens: 0,
});
expect(mocked.start).toHaveBeenCalledTimes(1);
});
it("clears the request timeout after successful compression", async () => {
vi.useFakeTimers();
try {
vi.mocked(compress).mockResolvedValue({
compressed: false,
messages: [{ role: "user", content: "hello" }],
tokensBefore: 5,
tokensAfter: 5,
tokensSaved: 0,
});
const engine = new HeadroomContextEngine({ requestTimeoutMs: 30_000 });
(engine as { proxyUrl: string | null }).proxyUrl = "http://127.0.0.1:8787";
await expect(
engine.assemble({
sessionId: "session-1",
messages: [{ role: "user", content: "hello" }],
}),
).resolves.toEqual({
messages: [{ role: "user", content: "hello" }],
estimatedTokens: 5,
});
expect(vi.getTimerCount()).toBe(0);
} finally {
vi.useRealTimers();
}
});
it("opens the circuit after consecutive compression failures", async () => {
vi.mocked(compress).mockRejectedValue(new Error("proxy stalled"));
const messages = [{ role: "user", content: "hello" }];
const engine = new HeadroomContextEngine({
circuitBreakerThreshold: 2,
circuitBreakerCooldownMs: 60_000,
});
(engine as { proxyUrl: string | null }).proxyUrl = "http://127.0.0.1:8787";
await engine.assemble({ sessionId: "session-1", messages });
await engine.assemble({ sessionId: "session-1", messages });
await expect(engine.assemble({ sessionId: "session-1", messages })).resolves.toEqual({
messages,
estimatedTokens: 0,
});
expect(compress).toHaveBeenCalledTimes(2);
expect(mocked.logger.warn).toHaveBeenCalledWith(
expect.stringContaining("Circuit breaker opened"),
);
});
});