59 lines
2.4 KiB
Python
59 lines
2.4 KiB
Python
"""Step 9 tests — fresh_workflow isolation + maker-checker round cap (FakeChatClient, no LLM).
|
|
|
|
Isolation is asserted on received-message CONTENT (not a call counter — the Fase 1 round-2
|
|
fix): a fresh workflow per run gives each run a clean thread, so a participant sees ONLY its
|
|
own project. The round cap is pinned to the EXACT observed count (retiring the 1-turn=1-round
|
|
off-by-one assumption). Pattern: tests/spikes/test_b_footguns.py + tests/spikes/test_harness.py.
|
|
"""
|
|
|
|
from collections.abc import Callable
|
|
|
|
from agent_framework import BaseChatClient
|
|
from spikes._harness import FakeChatClient
|
|
|
|
from portfolio_optimiser.reference_domain import load_reference_projects
|
|
from portfolio_optimiser.workflow import fresh_workflow
|
|
|
|
|
|
def _recording_factory(created: list[FakeChatClient]) -> Callable[[str], BaseChatClient]:
|
|
def factory(role: str) -> BaseChatClient:
|
|
client = FakeChatClient(default_reply=f"{role} view")
|
|
created.append(client)
|
|
return client
|
|
|
|
return factory
|
|
|
|
|
|
async def test_participant_sees_only_its_own_project() -> None:
|
|
ids = [p.id for p in load_reference_projects()]
|
|
seen_per_run: list[list[str]] = []
|
|
for pid in ids:
|
|
created: list[FakeChatClient] = []
|
|
wf = fresh_workflow(_recording_factory(created), max_rounds=2)
|
|
await wf.run(f"Evaluate project {pid}.")
|
|
blob = " ".join(t for c in created for call in c.received_texts for t in call)
|
|
seen_per_run.append([q for q in ids if q in blob])
|
|
# A fresh instance per run -> each participant sees ONLY its own project (B7 mitigation).
|
|
assert seen_per_run == [[pid] for pid in ids]
|
|
|
|
|
|
async def test_never_converging_debate_halts_at_exactly_max_rounds() -> None:
|
|
created: list[FakeChatClient] = []
|
|
|
|
def factory(role: str) -> BaseChatClient:
|
|
client = FakeChatClient(default_reply="still disagreeing, keep debating")
|
|
created.append(client)
|
|
return client
|
|
|
|
wf = fresh_workflow(factory, max_rounds=3)
|
|
await wf.run("Debate a never-ending question.")
|
|
# with_max_rounds(3) is the hard cap; the debate halts at EXACTLY 3 turns, not <=.
|
|
assert sum(c.call_count for c in created) == 3
|
|
|
|
|
|
def test_layer1_hitl_option_builds() -> None:
|
|
def factory(role: str) -> BaseChatClient:
|
|
return FakeChatClient(default_reply="ok")
|
|
|
|
wf = fresh_workflow(factory, max_rounds=2, enable_layer1_hitl=True)
|
|
assert wf is not None
|