"""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_conversation_isolation,
    shared_instance_conversation_bleed,
    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_conversation_across_projects() -> None:
    ids = [p.id for p in load_reference_projects()]
    assert len(ids) >= 2  # need >=2 projects to show cross-run bleed (portfolio grew via SC1)
    seen = await shared_instance_conversation_bleed(ids)
    # Reusing ONE built workflow accumulates the MAF thread across runs: each run's
    # participant receives the EARLIER projects' prompts too (genuine G2/B7 bleed),
    # measured by message CONTENT — not a call counter.
    assert seen[0] == [ids[0]]  # first run is clean — nothing prior to bleed
    assert set(seen[-1]) == set(ids)  # last run saw every project's prompt
    # Strictly monotonic growth = conversation history accumulating, not coincidence.
    assert all(set(seen[i]) < set(seen[i + 1]) for i in range(len(seen) - 1))


async def test_fresh_instance_isolates_conversation_across_projects() -> None:
    ids = [p.id for p in load_reference_projects()]
    seen = await fresh_instance_conversation_isolation(ids)
    # A fresh instance per project gives each run a clean thread -> a participant sees
    # ONLY its own project -> zero cross-run contamination (the B7 mitigation works).
    assert seen == [[pid] for pid in ids]