Files
nisse/tests/integration/test_crash_durability.py
T
dongarandClaude Opus 5.5 6ae2375194
CI / checks (push) Skipped
CI / checks (pull_request) Successful in 2m16s
CI / e2e (pull_request) Successful in 10m51s
M2.8: switch over to the new loop
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
2026-10-08 03:12:58 +00:00

54 lines
1.7 KiB
Python

"""Integration: state written before an abrupt process death must be intact
and the in-flight intent visible on the next boot (architecture L8)."""
import subprocess
import sys
from pathlib import Path
import pytest
from nisse_dev.reconcile import reconcile_on_boot
from nisse_dev.state import StateStore
pytestmark = pytest.mark.integration
CRASH_SCRIPT = """
import os
import sys
from nisse_dev.canonical import UserMessage
from nisse_dev.state import StateStore
store = StateStore(sys.argv[1])
store.open_work_item("demo-1", title="t", scope="demo", position="RUNNING", data={"milestone": 2}, cause="test")
store.set_active("demo-1", cause="test")
store.begin_intent("push_branch", {"branch": "milestone-2"}, cause="test")
store.transcript("t", "operator").append(UserMessage(text="start milestone 2", source="m:1"))
os._exit(1) # die without closing anything, as a power cut would
"""
def test_state_survives_process_death(tmp_path: Path) -> None:
db = tmp_path / "state.db"
result = subprocess.run(
[sys.executable, "-c", CRASH_SCRIPT, str(db)],
capture_output=True,
text=True,
timeout=30,
check=False,
)
assert result.returncode == 1, result.stderr
with StateStore(db) as store:
item = store.active_item()
assert item is not None
assert item.position == "RUNNING"
assert item.data == {"milestone": 2}
report = reconcile_on_boot(store, {"push_branch": lambda intent: None})
assert report.action == "await_input"
[pending] = store.pending_intents()
assert pending.payload == {"branch": "milestone-2"}
[stored] = store.all_events()
assert stored.event.text == "start milestone 2"