dongarandClaude Opus 5.5
3cf4cefacd
Architecture L9's role names, for the two roles with a direct counterpart: the delegation role is now 'helper' and the ask_expert role 'expert', in RoleMap, configuration (roles.helper, roles.expert), recorded events and tests. 'planner' and 'executor' stay distinct for now; they become 'driver' when the new loop merges them (Development Plan M2.3). Configurations must rename their keys: nisse-dev.example.yaml and tests/integration/nisse-test.yaml are updated here. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01PPQ14L3LikyefCMFBqEbKE
55 lines
1.7 KiB
Python
55 lines
1.7 KiB
Python
"""A real consult over the normalized route (L9).
|
|
|
|
The point is the prompt-level contract: a live model must produce something
|
|
that parses against our local schema, since no API-level enforcement exists.
|
|
"""
|
|
|
|
import io
|
|
from pathlib import Path
|
|
|
|
import pytest
|
|
|
|
from nisse_dev.evals import collect
|
|
from nisse_dev.expert import BudgetExhausted, ExpertDesk
|
|
from nisse_dev.llm import LiteLLMClient, RoleMap
|
|
from nisse_dev.oplog import OpLog
|
|
from nisse_dev.state import StateStore
|
|
|
|
pytestmark = pytest.mark.integration
|
|
|
|
|
|
@pytest.fixture
|
|
def desk(tmp_path: Path, litellm: LiteLLMClient, live_model: str):
|
|
def make(budget: int = 2) -> tuple[ExpertDesk, StateStore]:
|
|
model = live_model
|
|
roles = RoleMap(executor=model, planner=model, helper=model, expert=model)
|
|
store = StateStore(
|
|
tmp_path / "state.db", oplog=OpLog("nisse-dev", io.StringIO())
|
|
)
|
|
return ExpertDesk(litellm, store, roles, budget=budget), store
|
|
|
|
return make
|
|
|
|
|
|
def test_live_consult_parses_against_the_local_schema(desk) -> None:
|
|
expert, store = desk()
|
|
|
|
answer = expert.ask(
|
|
"For a single-process agent storing a few thousand rows of task state, "
|
|
"is SQLite sufficient, or is PostgreSQL warranted? Answer briefly."
|
|
)
|
|
|
|
assert answer.confidence in {"high", "medium", "low"}
|
|
assert len(answer.answer) > 20
|
|
# The consult is captured for L9 without any extra bookkeeping.
|
|
[record] = collect(store)
|
|
assert record.role == "expert"
|
|
assert record.exit_status == "answered"
|
|
|
|
|
|
def test_live_budget_stops_a_circling_caller(desk) -> None:
|
|
expert, _ = desk(budget=1)
|
|
expert.ask("Name one advantage of WAL mode in SQLite. Be brief.")
|
|
with pytest.raises(BudgetExhausted):
|
|
expert.ask("And another?")
|