Files
creator/backend/tests/test_race.py
2026-07-05 15:26:22 +02:00

104 lines
4.0 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
"""_race-Hedging: Stall-Slots bekommen einen parallelen Zwilling statt den Timeout-Cap
abzuwarten (gemessen: 4 Panel-Stalls à 160230 s pro Lauf auf dem kritischen Pfad)."""
import asyncio
import pipeline
def _slot(payload=lambda r: r[1]):
return {"key": "k1", "prompt": "p", "role": "judge", "capabilities": "none", "payload": payload}
async def test_hedge_zwilling_rettet_stall(monkeypatch):
"""Original stallt → nach HEDGE_NACH_S startet der Zwilling (key -h), sein Ergebnis
gewinnt, das hängende Original wird gekillt."""
calls, killed = [], []
async def fake_agent(key, prompt, timeout, **kw):
calls.append(key)
if key.endswith("-h"):
return (0, "zwilling", "")
await asyncio.sleep(30) # Stall — würde sonst den ganzen Cap verbrennen
return (0, "original", "")
monkeypatch.setattr(pipeline, "run_agent", fake_agent)
monkeypatch.setattr(pipeline, "kill_process", lambda k: killed.append(k))
monkeypatch.setattr(pipeline, "_HEDGE_NACH_S", 0.05)
res = await pipeline._race("t", "Test", [_slot()], 1, 0.1, "claude")
assert res == ["zwilling"]
assert calls == ["k1", "k1-h"]
assert "k1" in killed # das hängende Original läuft nicht weiter
async def test_hedge_original_gewinnt_zwilling_wird_gekillt(monkeypatch):
"""Kommt das Original doch noch vor dem Zwilling an, wird der Zwilling gekillt
und sein spätes Ergebnis nicht gewertet."""
killed = []
async def fake_agent(key, prompt, timeout, **kw):
await asyncio.sleep(0.3 if key.endswith("-h") else 0.15)
return (0, key, "")
monkeypatch.setattr(pipeline, "run_agent", fake_agent)
monkeypatch.setattr(pipeline, "kill_process", lambda k: killed.append(k))
monkeypatch.setattr(pipeline, "_HEDGE_NACH_S", 0.05)
res = await pipeline._race("t", "Test", [_slot()], 1, 0.1, "claude")
assert res == ["k1"]
assert "k1-h" in killed
async def test_hedge_aus_bei_null(monkeypatch):
"""HEDGE_NACH_S=0 → kein Zwilling, Verhalten wie zuvor."""
calls = []
async def fake_agent(key, prompt, timeout, **kw):
calls.append(key)
await asyncio.sleep(0.1)
return (0, "ok", "")
monkeypatch.setattr(pipeline, "run_agent", fake_agent)
monkeypatch.setattr(pipeline, "_HEDGE_NACH_S", 0)
res = await pipeline._race("t", "Test", [_slot()], 1, 0.1, "claude")
assert res == ["ok"]
assert calls == ["k1"]
async def test_hedge_schwelle_skaliert_mit_timeout(monkeypatch):
"""Die Schwelle ist max(HEDGE_NACH_S, timeout/2): ein gesunder Call, der länger als
die Untergrenze, aber kürzer als das halbe Timeout läuft, bekommt KEINEN Zwilling
(pauschale 90 s hedgten jeden normalen Fix-Call)."""
calls = []
async def fake_agent(key, prompt, timeout, **kw):
calls.append(key)
await asyncio.sleep(0.15) # > Untergrenze 0.05, < timeout/2 = 0.5
return (0, "ok", "")
monkeypatch.setattr(pipeline, "run_agent", fake_agent)
monkeypatch.setattr(pipeline, "_HEDGE_NACH_S", 0.05)
res = await pipeline._race("t", "Test", [_slot()], 1, 1.0, "claude")
assert res == ["ok"]
assert calls == ["k1"]
async def test_hedge_zwilling_ersetzt_restart(monkeypatch):
"""Scheitert das Original, während der Zwilling noch läuft, gibt es KEINEN
zusätzlichen Restart — der Zwilling ist der Retry."""
calls = []
async def fake_agent(key, prompt, timeout, **kw):
calls.append(key)
if key.endswith("-h"):
await asyncio.sleep(0.2)
return (0, "zwilling", "")
await asyncio.sleep(0.1)
return (1, "", "kaputt") # Fehler NACH dem Hedge-Start
monkeypatch.setattr(pipeline, "run_agent", fake_agent)
monkeypatch.setattr(pipeline, "kill_process", lambda k: None)
monkeypatch.setattr(pipeline, "_HEDGE_NACH_S", 0.05)
res = await pipeline._race("t", "Test", [_slot()], 1, 0.1, "claude")
assert res == ["zwilling"]
assert calls == ["k1", "k1-h"] # kein dritter Spawn