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
48 lines
1.6 KiB
Python
48 lines
1.6 KiB
Python
"""Live planning turn: a real model must answer with a submit_plan or
|
|
ask_human tool call, not prose.
|
|
|
|
Plans with the test config's planner role. The planner role is a frontier
|
|
model today (Development Plan §2), and small local models do not hold the tool-call
|
|
contract reliably, so that role must be one that does.
|
|
"""
|
|
|
|
import io
|
|
from pathlib import Path
|
|
|
|
import pytest
|
|
|
|
from nisse_dev.canonical import UserMessage
|
|
from nisse_dev.control import AskHuman, SubmitPlan
|
|
from nisse_dev.llm import LiteLLMClient, RoleMap
|
|
from nisse_dev.oplog import OpLog
|
|
from nisse_dev.planner import LLMPlanningAgent
|
|
from nisse_dev.state import StateStore
|
|
|
|
pytestmark = pytest.mark.integration
|
|
|
|
|
|
def test_live_planning_turn_returns_a_tool_action(
|
|
tmp_path: Path, litellm: LiteLLMClient, live_model: str
|
|
) -> None:
|
|
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()))
|
|
store.append_event(
|
|
UserMessage(
|
|
text=(
|
|
"Project 'hello-cli': a Python script that prints a greeting. "
|
|
"Draft the architecture plan."
|
|
),
|
|
source="live-test",
|
|
)
|
|
)
|
|
agent = LLMPlanningAgent(litellm, store, roles)
|
|
|
|
action = agent.plan("arch", "hello-cli")
|
|
|
|
assert isinstance(action, SubmitPlan | AskHuman)
|
|
text = action.content if isinstance(action, SubmitPlan) else action.question
|
|
assert text.strip(), "tool call carried empty content"
|
|
# The turn must be durable regardless of what the model said (L8/L7).
|
|
assert len(store.read_events()) > 1
|