Add execution-model decision handoff and Jev AALC research
This commit is contained in:
@@ -77,9 +77,9 @@ class AgentRuntimeTest(unittest.TestCase):
|
|||||||
self.kernel.CreateMutexW.return_value = 12345
|
self.kernel.CreateMutexW.return_value = 12345
|
||||||
self.kernel.GetLastError.return_value = 0
|
self.kernel.GetLastError.return_value = 0
|
||||||
|
|
||||||
def run_agent(self, bridge, extra_args=(), constructor_error=None):
|
def run_agent(self, bridge, extra_args=(), constructor_error=None, fixed=True, executor_decider=None):
|
||||||
output = io.StringIO()
|
output = io.StringIO()
|
||||||
environment = dict(os.environ, LC_FIXED_FALLBACK='1')
|
environment = dict(os.environ, LC_FIXED_FALLBACK='1' if fixed else '0')
|
||||||
environment.pop('OPENCODE_API_KEY', None)
|
environment.pop('OPENCODE_API_KEY', None)
|
||||||
with mock.patch.object(agent, 'RUNTIME_HOME', self.home), \
|
with mock.patch.object(agent, 'RUNTIME_HOME', self.home), \
|
||||||
mock.patch.object(agent, 'STOP_FILE', self.home / 'JEV_STOP'), \
|
mock.patch.object(agent, 'STOP_FILE', self.home / 'JEV_STOP'), \
|
||||||
@@ -90,8 +90,8 @@ class AgentRuntimeTest(unittest.TestCase):
|
|||||||
mock.patch.object(agent.time, 'sleep'), \
|
mock.patch.object(agent.time, 'sleep'), \
|
||||||
mock.patch.object(agent, 'button_enabled', return_value=False), \
|
mock.patch.object(agent, 'button_enabled', return_value=False), \
|
||||||
contextlib.redirect_stdout(output):
|
contextlib.redirect_stdout(output):
|
||||||
agent.main()
|
agent.main(executor_decider=executor_decider)
|
||||||
status = json.loads((self.home / 'jev_mirror_status.json').read_text())
|
status = json.loads((self.home / 'jev_mirror_status.json').read_text(encoding='utf-8'))
|
||||||
return status, factory
|
return status, factory
|
||||||
|
|
||||||
def test_old_claim_context_does_not_complete_new_run_at_lobby(self):
|
def test_old_claim_context_does_not_complete_new_run_at_lobby(self):
|
||||||
@@ -151,6 +151,59 @@ class AgentRuntimeTest(unittest.TestCase):
|
|||||||
self.run_agent(bridge)
|
self.run_agent(bridge)
|
||||||
self.assertEqual(self.kernel.CloseHandle.call_count, 1)
|
self.assertEqual(self.kernel.CloseHandle.call_count, 1)
|
||||||
|
|
||||||
|
def test_no_jev_config_publishes_execution_model_request_without_input(self):
|
||||||
|
bridge = mock.Mock()
|
||||||
|
bridge.call.return_value = {'ok': True, 'items': [{'text': '路线', 'score': 1}]}
|
||||||
|
options = {
|
||||||
|
'wait': {'description': 'wait', 'action': {'tool': 'wait', 'args': {'seconds': .7}}},
|
||||||
|
'requires_analysis': {'description': 'inspect', 'action': {'tool': 'requires_analysis', 'args': {}}},
|
||||||
|
'route_w': {'description': 'event above', 'action': {'tool': 'route', 'args': {'key': 'w'}}},
|
||||||
|
}
|
||||||
|
with mock.patch.object(agent, 'candidates', return_value=options), mock.patch.object(agent, 'decide') as decide:
|
||||||
|
status, _ = self.run_agent(bridge, fixed=False)
|
||||||
|
self.assertEqual(status['state'], 'requires_decision')
|
||||||
|
self.assertEqual(status['decision_request']['reason'], 'no_jev_model')
|
||||||
|
self.assertEqual(bridge.call.call_args_list, [mock.call('get_state')])
|
||||||
|
decide.assert_not_called()
|
||||||
|
bridge.close.assert_called_once()
|
||||||
|
self.assertEqual(self.kernel.CloseHandle.call_count, 1)
|
||||||
|
pending = json.loads((self.home / 'decision_request.json').read_text(encoding='utf-8'))
|
||||||
|
run = json.loads((self.home / 'mirror_current_run.json').read_text())
|
||||||
|
self.assertEqual(pending['run_id'], run['run_id'])
|
||||||
|
self.assertEqual(run['status'], 'requires_decision')
|
||||||
|
|
||||||
|
def test_pending_execution_model_decision_can_resume_same_run(self):
|
||||||
|
save_json(self.home / 'mirror_current_run.json', {
|
||||||
|
'run_id': 'pending-run', 'start_utc': '2026-10-02T00:00:00+00:00',
|
||||||
|
'status': 'requires_decision', 'dungeon_completed': False, 'final_reward_claimed': False})
|
||||||
|
save_json(self.home / 'jev_shop_context.json', {'run_id': 'pending-run', 'floor': 3})
|
||||||
|
bridge = mock.Mock()
|
||||||
|
bridge.call.return_value = {'ok': True, 'items': []}
|
||||||
|
status, _ = self.run_agent(bridge, extra_args=['--resume'])
|
||||||
|
self.assertEqual(status['state'], 'stopped')
|
||||||
|
self.assertEqual(status['run_id'], 'pending-run')
|
||||||
|
|
||||||
|
def test_embedded_execution_model_selects_and_executes_without_jev(self):
|
||||||
|
bridge = mock.Mock()
|
||||||
|
bridge.call.return_value = {'ok': True, 'items': [{'text': '路线', 'score': 1}]}
|
||||||
|
options = {
|
||||||
|
'wait': {'description': 'wait', 'action': {'tool': 'wait', 'args': {'seconds': .7}}},
|
||||||
|
'requires_analysis': {'description': 'inspect', 'action': {'tool': 'requires_analysis', 'args': {}}},
|
||||||
|
'route_w': {'description': 'event above', 'action': {'tool': 'route', 'args': {'key': 'w'}}},
|
||||||
|
}
|
||||||
|
executor = mock.Mock(side_effect=lambda request: {'request_id': request['request_id'], 'choice': 'route_w'})
|
||||||
|
with mock.patch.object(agent, 'candidates', return_value=options), mock.patch.object(agent, 'decide') as decide:
|
||||||
|
status, _ = self.run_agent(bridge, fixed=False, executor_decider=executor)
|
||||||
|
self.assertEqual(status['state'], 'stopped')
|
||||||
|
executor.assert_called_once()
|
||||||
|
decide.assert_not_called()
|
||||||
|
self.assertEqual(bridge.call.call_args_list, [mock.call('get_state'),
|
||||||
|
mock.call('keypress', {'key': 'w'}), mock.call('keypress', {'key': 'enter'}),
|
||||||
|
mock.call('keypress', {'key': 'enter'})])
|
||||||
|
rows = [json.loads(line) for line in (self.home / 'jev_mirror_log.jsonl').read_text(encoding='utf-8').splitlines()]
|
||||||
|
self.assertEqual(rows[-1]['decision_engine'], 'executor')
|
||||||
|
self.assertEqual(rows[-1]['jev_ms'], 0)
|
||||||
|
|
||||||
|
|
||||||
if __name__ == '__main__':
|
if __name__ == '__main__':
|
||||||
unittest.main()
|
unittest.main()
|
||||||
|
|||||||
Reference in New Issue
Block a user