import asyncio import threading import pytest from app.errors import QueueFull, QueueTimeout, SynthesisTimeout from app.work_queue import WorkQueue from tests.conftest import HEADERS, body pytestmark = pytest.mark.anyio async def _wait_until(predicate, timeout=3.0): loop = asyncio.get_running_loop() end = loop.time() + timeout while not predicate(): if loop.time() > end: raise AssertionError("condição não atingida") await asyncio.sleep(0.01) async def test_concurrency_limit_and_queue_full(): gate = threading.Event() queue = WorkQueue(max_concurrency=1, max_queue_per_key=1, queue_timeout_s=5, run_timeout_s=5) running = asyncio.create_task(queue.run(lambda: gate.wait(5), owner="a")) await _wait_until(lambda: queue.running == 1) waiting = asyncio.create_task(queue.run(lambda: "segundo", owner="a")) await _wait_until(lambda: queue.waiting == 1) with pytest.raises(QueueFull): await queue.run(lambda: "terceiro", owner="a") gate.set() assert await running is True assert await waiting == "segundo" queue.shutdown() async def test_queue_timeout(): gate = threading.Event() queue = WorkQueue(max_concurrency=1, max_queue_per_key=5, queue_timeout_s=0.2, run_timeout_s=5) running = asyncio.create_task(queue.run(lambda: gate.wait(5), owner="a")) await _wait_until(lambda: queue.running == 1) with pytest.raises(QueueTimeout): await queue.run(lambda: "nunca", owner="a") gate.set() await running queue.shutdown() async def test_synthesis_timeout_keeps_slot_until_thread_ends(): gate = threading.Event() queue = WorkQueue(max_concurrency=1, max_queue_per_key=5, queue_timeout_s=5, run_timeout_s=0.2) with pytest.raises(SynthesisTimeout): await queue.run(lambda: gate.wait(5), owner="a") # O cliente já recebeu timeout, mas a thread segue rodando: a vaga continua ocupada. assert queue.running == 1 gate.set() await _wait_until(lambda: queue.running == 0) assert await queue.run(lambda: "livre", owner="a") == "livre" queue.shutdown() async def test_http_queue_full_returns_503_with_retry_after(make_client, engine): engine.gate = threading.Event() async with make_client(max_concurrency=1, max_queue_per_key=1) as client: first = asyncio.create_task(client.post("/v1/synthesize", json=body("req-aaaaaaaa", text="um"), headers=HEADERS)) await _wait_until(lambda: engine.calls == 1) second = asyncio.create_task(client.post("/v1/synthesize", json=body("req-bbbbbbbb", text="dois"), headers=HEADERS)) await asyncio.sleep(0.1) third = await client.post("/v1/synthesize", json=body("req-cccccccc", text="três"), headers=HEADERS) engine.gate.set() assert (await first).status_code == 200 assert (await second).status_code == 200 assert third.status_code == 503 assert third.json()["error"]["code"] == "queue_full" assert third.headers["retry-after"] == "5" async def test_http_synthesis_timeout_is_504(make_client, engine): engine.gate = threading.Event() async with make_client(synth_timeout_s=0.2) as client: response = await client.post("/v1/synthesize", json=body(), headers=HEADERS) engine.gate.set() assert response.status_code == 504 assert response.json()["error"]["code"] == "synthesis_timeout" async def test_inflight_same_content_is_rendered_once(make_client, engine): engine.gate = threading.Event() async with make_client(max_concurrency=2) as client: a = asyncio.create_task(client.post("/v1/synthesize", json=body("req-aaaaaaaa"), headers=HEADERS)) await _wait_until(lambda: engine.calls == 1) b = asyncio.create_task(client.post("/v1/synthesize", json=body("req-bbbbbbbb"), headers=HEADERS)) await asyncio.sleep(0.1) engine.gate.set() ra, rb = await a, await b assert ra.status_code == rb.status_code == 200 assert ra.content == rb.content assert engine.calls == 1