39 lines
1.6 KiB
Python
39 lines
1.6 KiB
Python
"""Spike B tests — Magentic unbounded footgun (G1/B4) + fan-out state isolation (G2/B7).
|
|
|
|
These drive the real GA builders with the fake client (no endpoint), de-risked by the
|
|
Step 2 builder smoke. Pattern: tests/test_backends.py.
|
|
"""
|
|
|
|
from portfolio_optimiser.reference_domain import load_reference_projects
|
|
from spikes.b_footguns import (
|
|
bounded_magentic_terminates,
|
|
fresh_instance_call_counts,
|
|
shared_instance_max_calls,
|
|
unbounded_magentic_self_terminates,
|
|
)
|
|
|
|
|
|
async def test_unbounded_magentic_does_not_self_terminate() -> None:
|
|
# max_round_count=None never finalizes — only the external guard stops it (B4).
|
|
self_terminated = await unbounded_magentic_self_terminates(guard_rounds=8)
|
|
assert self_terminated is False # the guard fired, not a natural stop
|
|
|
|
|
|
async def test_bounded_magentic_terminates_within_limit() -> None:
|
|
# An explicit max_round_count makes the same never-satisfied manager stop cleanly.
|
|
assert await bounded_magentic_terminates(max_round_count=2) is True
|
|
|
|
|
|
async def test_shared_instance_bleeds_state_across_projects() -> None:
|
|
ids = [p.id for p in load_reference_projects()]
|
|
assert len(ids) == 3
|
|
bled = await shared_instance_max_calls(ids)
|
|
# One shared instance reused across all 3 projects -> calls accumulate -> bleed.
|
|
assert bled == len(ids)
|
|
|
|
|
|
async def test_fresh_instance_zero_bleed_across_projects() -> None:
|
|
ids = [p.id for p in load_reference_projects()]
|
|
counts = await fresh_instance_call_counts(ids)
|
|
# A fresh instance per project -> each run sees exactly one call -> zero bleed.
|
|
assert counts == [1, 1, 1]
|