dongarandClaude Opus 5.5
6ae2375194
nisse-dev now runs only the conversational loop. The gated state machine it was built alongside is gone: - Removed control.py, planner.py, executor.py, approvals.py, gates.py (command_form moves to loop/reader.py), publish.py and poller.py, the old assembly in agent.py (its shared helpers move to loop/build.py), the store's state-machine view (get_state, transition), their tests, the old end-to-end and live planning/milestone/gate tests, and specs/orchestrator.qnt with its scenarios. - Roles are driver, helper, expert and classifier; driver is required. loop:, roles.planner, roles.executor and tuning.executor are refused with what to use instead; tuning.driver takes the turn cap and failure limit. - The benchmark and the capability matrix measure the driver: the loop's own system prompt and tools, the task's plan as the agreed restatement. Task plans end with finish_milestone, so earlier runs show as (old); stored runs' executor tuning reads as the driver's. - A delegation on the loop records what its helper's alias resolved to (L9), as the old path's did. - The dump shows a work item's revision and what it waits for. - Behaviour the old tests covered and the loop shares stays covered: driver runs that fail on a model call, stop mid-turn, reset the failure count; go-aheads ignoring case and punctuation; a request too big to fit is never sent; the assembly tests, now on build_loop_agent. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01PPQ14L3LikyefCMFBqEbKE
59 lines
1.8 KiB
Python
59 lines
1.8 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(driver=model, helper=model, expert=model)
|
|
store = StateStore(
|
|
tmp_path / "state.db", oplog=OpLog("nisse-dev", io.StringIO())
|
|
)
|
|
return ExpertDesk(litellm, roles, budget=budget), store
|
|
|
|
return make
|
|
|
|
|
|
def test_live_consult_parses_against_the_local_schema(desk) -> None:
|
|
expert, store = desk()
|
|
|
|
answer = expert.ask(
|
|
store.transcript("t", "expert"),
|
|
"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, store = desk(budget=1)
|
|
expert.ask(
|
|
store.transcript("t", "expert"),
|
|
"Name one advantage of WAL mode in SQLite. Be brief.",
|
|
)
|
|
with pytest.raises(BudgetExhausted):
|
|
expert.ask(store.transcript("t", "expert"), "And another?")
|