source/tests/test_fleet_campaign.py

import copy
from datetime import datetime, timezone
import hashlib
import json
import io
import math
from pathlib import Path
import tempfile
import time
import unittest
from unittest.mock import patch, MagicMock
from selection import SELECTION_METRIC, validation_selection

from scripts.fleet_campaign import (choose_candidate, checksum, copy_evidence, identity,
                                    snapshot_candidate, validate_plan, validation_score,
                                    verify_candidate, verify_correctness, verify_compatibility,
                                    verify_candidate_dataset, verify_selected_dataset, PROTECTED_SPLITS,
                                    deploy, stop_candidate, ROOT)


def predictions(logit=1.0):
    normalizer = math.log1p(math.exp(-logit))
    logs = [-normalizer, -logit-normalizer]
    return [{'id':f'{family}-{index}','group':f'{family}-{index}','family':family,
             'choices':['yes','no'],'target':0,'logits':[logit,0.0],
             'log_probabilities':logs[:],'probabilities':[math.exp(v) for v in logs]}
            for family in ('arc','banking','boolq','snli') for index in range(128)]


def artifact(rows, model):
    from training_model import ADAPTER_VERSION, PROMPT_VERSION
    dataset = Path(model).parent/'dataset'
    dataset.mkdir(exist_ok=True)
    (dataset/'validation.jsonl').write_text('frozen opaque bytes')
    hashes = {'validation':checksum(dataset/'validation.jsonl')}
    (dataset/'manifest.json').write_text(json.dumps({'split_sha256':hashes}))
    signature = hashlib.sha256(json.dumps({'data':hashes,'model':{'revision':'pinned'},
        'implementation':checksum(ROOT/'training_model.py'),'max_tokens':512},sort_keys=True).encode()).hexdigest()
    return {'format':'opensysone-adapter-v1','step':40,'trainable_state':{'head':'fake CPU test tensor'},
            'best_validation_macro_nll':validation_score(rows,rows)['macro_nll'],
            'selection_metric':SELECTION_METRIC,'best_validation_selection_score':validation_selection(rows)['score'],
            'source_commit':'abc123','model_provenance':{'revision':'pinned'},'data_signature':signature,
            'adapter_version':ADAPTER_VERSION,'prompt_version':PROMPT_VERSION,
            'config':{'validation_per_family':128,'model':str(model),'dataset':str(dataset),'max_tokens':512}}


def correctness(directory):
    checks = {key:0.0 for key in ('branch_chunks_1_probability_max_abs','branch_chunks_2_probability_max_abs',
              'branch_chunks_4_probability_max_abs','question_isolation_probability_max_abs',
              'candidate_permutation_probability_max_abs','repeat_probability_max_abs')}
    checks['tolerance_probability_abs'] = 1e-4
    (directory/'correctness_initial.json').write_text(json.dumps(checks))
    return checks


def dataset_variant(directory, train='original training'):
    directory.mkdir()
    hashes = {}
    for split in ('train', *PROTECTED_SPLITS):
        path = directory/f'{split}.jsonl'
        path.write_text(train if split == 'train' else 'opaque frozen ' + split)
        hashes[split] = checksum(path)
    (directory/'manifest.json').write_text(json.dumps({'split_sha256':hashes}))
    return directory


class FleetCampaignTests(unittest.TestCase):
    def test_dataset_override_requires_explicit_matching_registration_and_protected_bytes(self):
        with tempfile.TemporaryDirectory() as directory:
            root = Path(directory)
            baseline = dataset_variant(root/'v1')
            expanded = dataset_variant(root/'v2', 'original plus additional training')
            candidate = {'name':'expanded','host':'local','dataset':str(expanded),
                         'project':'/project','python':'/python','campaign':'/campaign','training':'/training'}
            plan = {'dataset':str(baseline),'candidates':[candidate], 'reference_predictions':'/reference.json',
                    'selection_cutoff':'2026-09-17T16:00:00Z','final_deadline':'2026-09-17T18:16:10Z'}
            proof = verify_candidate_dataset(candidate, plan, expanded)
            self.assertEqual(set(proof['protected_split_sha256']),set(PROTECTED_SPLITS))
            self.assertNotEqual(checksum(baseline/'train.jsonl'),checksum(expanded/'train.jsonl'))
            self.assertLess(*validate_plan(plan, datetime(2026,9,17,6,tzinfo=timezone.utc).timestamp()))
            selected = {'name':'expanded','config':{'dataset':str(expanded)}}
            self.assertEqual(verify_selected_dataset(selected,plan),proof)
            without_override = {key:value for key,value in candidate.items() if key != 'dataset'}
            self.assertIsNone(verify_candidate_dataset(without_override,plan,baseline))
            for entry,actual in ((without_override,expanded),(candidate,baseline),
                                 ({**candidate,'dataset':'relative'},expanded)):
                with self.assertRaises(ValueError):
                    verify_candidate_dataset(entry,plan,actual)
            with self.assertRaisesRegex(ValueError,'not uniquely registered'):
                verify_selected_dataset({**selected,'name':'unregistered'},plan)

    def test_dataset_override_rejects_each_changed_missing_or_unhashed_protected_split(self):
        for split in PROTECTED_SPLITS:
            for damage in ('changed','missing_checksum','missing_file','stale_checksum'):
                with self.subTest(split=split,damage=damage), tempfile.TemporaryDirectory() as directory:
                    root = Path(directory)
                    baseline = dataset_variant(root/'v1')
                    expanded = dataset_variant(root/'v2','expanded training')
                    manifest = json.loads((expanded/'manifest.json').read_text())
                    if damage in ('changed','stale_checksum'):
                        (expanded/f'{split}.jsonl').write_text('different reserved bytes')
                        if damage == 'changed':
                            manifest['split_sha256'][split] = checksum(expanded/f'{split}.jsonl')
                    elif damage == 'missing_checksum':
                        del manifest['split_sha256'][split]
                    else:
                        (expanded/f'{split}.jsonl').unlink()
                    (expanded/'manifest.json').write_text(json.dumps(manifest))
                    with self.assertRaisesRegex(ValueError,'[Pp]rotected split'):
                        verify_candidate_dataset({'dataset':str(expanded)}, {'dataset':str(baseline)}, expanded)

    def test_fresh_finalization_uses_verified_selected_dataset_variant(self):
        with tempfile.TemporaryDirectory() as directory:
            root = Path(directory)
            baseline = dataset_variant(root/'v1')
            expanded = dataset_variant(root/'v2','expanded training')
            campaign = root/'campaign'
            campaign.mkdir()
            selected = {'name':'expanded','checkpoint':'/verified/best.pt','config':{'dataset':str(expanded)}}
            plan = {'dataset':str(baseline),'candidates':[{'name':'expanded','dataset':str(expanded)}]}
            verify_selected_dataset(selected,plan)
            deadline = time.time()+7200
            with patch('scripts.fleet_campaign.stage',side_effect=RuntimeError('CPU fixture stops before execution')) as stage:
                with self.assertRaisesRegex(RuntimeError,'CPU fixture'):
                    deploy(campaign,{},plan,selected,deadline)
            self.assertEqual(stage.call_args.args[2],'evaluation')
            command = stage.call_args.args[3]
            self.assertEqual(command[command.index('--dataset')+1],str(expanded))
            self.assertEqual(stage.call_args.args[4],deadline-120)

    def test_natural_exit_between_inspection_and_stop_requires_fresh_stopped_status(self):
        running = {'supervisor_running':True,'child_running':True,'api_running':False}
        stopped = {'supervisor_running':False,'child_running':False,'api_running':False}
        for followup in (stopped,running):
            with self.subTest(followup=followup), patch('scripts.fleet_campaign.candidate_status',
                    side_effect=[running,RuntimeError('No recorded process remains'),followup]) as status:
                if followup is stopped:
                    self.assertEqual(stop_candidate({'name':'gx10'}),stopped)
                else:
                    with self.assertRaisesRegex(RuntimeError,'No recorded process'):
                        stop_candidate({'name':'gx10'})
                self.assertEqual(status.call_count,3)
                self.assertEqual(status.call_args_list[1].kwargs,{'stop':True})
                self.assertEqual(status.call_args_list[2].kwargs,{})

    def test_validation_identity_probabilities_and_durable_score_are_required(self):
        rows = predictions()
        with tempfile.TemporaryDirectory() as directory:
            saved = artifact(rows,Path(directory)/'model')
        self.assertAlmostEqual(verify_candidate(saved,rows,rows)['macro_nll'],math.log1p(math.exp(-1)))
        self.assertEqual(verify_candidate(saved,list(reversed(rows)),rows)['accuracy'],1)
        changed = copy.deepcopy(rows)
        changed[0]['id'] = 'different-id'
        with self.assertRaisesRegex(ValueError,'identical 512'):
            verify_candidate(saved,changed,rows)
        changed = copy.deepcopy(rows)
        changed[0]['group'] = 'different-source-group'
        with self.assertRaises(ValueError):
            verify_candidate(saved,changed,rows)
        changed = copy.deepcopy(rows)
        changed[0]['probabilities'] = [0.5,0.5]
        with self.assertRaisesRegex(ValueError,'disagree with logits'):
            verify_candidate(saved,changed,rows)
        changed = copy.deepcopy(rows)
        changed[0]['logits'][0] = float('nan')
        with self.assertRaisesRegex(ValueError,'Non-finite'):
            verify_candidate(saved,changed,rows)
        with self.assertRaisesRegex(ValueError,'durable best'):
            verify_candidate({**saved,'best_validation_macro_nll':0.01},rows,rows)
        with self.assertRaisesRegex(ValueError,'durable trained artifact'):
            verify_candidate({**saved,'trainable_state':{}},rows,rows)
        with self.assertRaisesRegex(ValueError,'raw validation'):
            verify_candidate({**saved,'temperature':2},rows,rows)
        with self.assertRaisesRegex(ValueError,'selection policy'):
            verify_candidate({**saved,'selection_metric':'raw_nll'},rows,rows)
        with self.assertRaisesRegex(ValueError,'Crossfit selection score'):
            verify_candidate({**saved,'best_validation_selection_score':0.2},rows,rows)
        with self.assertRaises(ValueError):
            verify_candidate(saved,rows[:-1],rows)
        duplicate = copy.deepcopy(rows)
        duplicate[-1] = duplicate[0]
        with self.assertRaisesRegex(ValueError,'Duplicate'):
            identity(duplicate)

    def test_selection_ignores_incomplete_better_scores(self):
        candidates = [{'name':'incomplete','eligible':False,'metrics':{'selection_score':0.01}},
                      {'name':'gx10','eligible':True,'metrics':{'macro_nll':0.3,'selection_score':0.4}},
                      {'name':'spark','eligible':True,'metrics':{'macro_nll':0.5,'selection_score':0.3}}]
        self.assertEqual(choose_candidate(candidates)['name'],'spark')
        self.assertEqual(choose_candidate(candidates[:2])['name'],'gx10')
        with self.assertRaisesRegex(RuntimeError,'No verified durable'):
            choose_candidate(candidates[:1])

    def test_deadlines_timezone_paths_and_fallback(self):
        now = datetime(2026,9,16,20,tzinfo=timezone.utc).timestamp()
        plan = {'selection_cutoff':'2026-09-17T16:00:00Z','final_deadline':'2026-09-17T18:16:10Z',
                'dataset':'/frozen/data','reference_predictions':'/reference.json',
                'candidates':[{'name':'gx10','host':'local','project':'/project','python':'/python',
                               'campaign':'/campaign','training':'/campaign/training'}]}
        self.assertLess(*validate_plan(plan,now))
        for change in ({'final_deadline':'2026-09-17T17:00:00Z'},
                       {'final_deadline':'2026-09-17T18:16:10'},
                       {'final_deadline':'2026-09-18T18:16:10Z'},
                       {'reference_predictions':'relative'},
                       {'candidates':[{**plan['candidates'][0],'host':'192.168.8.111'}]}):
            with self.assertRaises(ValueError):
                validate_plan({**plan,**change},now)

    def test_snapshot_loads_durable_best_and_never_copies_test_predictions(self):
        import torch
        with tempfile.TemporaryDirectory() as directory:
            root = Path(directory)
            training = root/'training'
            training.mkdir()
            model = root/'model'
            model.mkdir()
            rows = predictions()
            saved = artifact(rows,model)
            (model/'opensysone-provenance.json').write_text(json.dumps(saved['model_provenance']))
            torch.save(saved,training/'best.pt')
            correctness(training)
            (training/'best_validation_predictions.json').write_text(json.dumps(rows))
            (training/'test_predictions.json').write_text('MUST NOT COPY')
            (training/'calibration_predictions.json').write_text('MUST NOT COPY')
            (training/'holdout_predictions.json').write_text('MUST NOT COPY')
            (training/'checkpoint.pt').write_text('MUST NOT COPY OPTIMIZER')
            candidate = {'name':'gx10','host':'local','training':str(training),'campaign':'/campaign'}
            record = snapshot_candidate(candidate,root/'snapshot',rows)
            self.assertTrue(record['eligible'])
            self.assertEqual(record['checkpoint_sha256'],checksum(training/'best.pt'))
            copied = {p.name for p in (root/'snapshot/training').iterdir()}
            self.assertEqual(copied,{'best.pt','best_validation_predictions.json','correctness_initial.json'})
            (training/'best_validation_predictions.json').unlink()
            with self.assertRaisesRegex(ValueError,'no matching complete validation'):
                snapshot_candidate(candidate,root/'missing-evidence',rows)

    def test_snapshot_accepts_inherited_pilot_evidence_and_rejects_transfer_change(self):
        import torch
        with tempfile.TemporaryDirectory() as directory:
            root = Path(directory)
            training,pilot,model = root/'training',root/'pilot',root/'model'
            for path in (training,pilot,model):
                path.mkdir()
            rows = predictions()
            torch.save(artifact(rows,model),training/'best.pt')
            (model/'opensysone-provenance.json').write_text(json.dumps({'revision':'pinned'}))
            correctness(training)
            (pilot/'validation_step_000040_predictions.json').write_text(json.dumps(rows))
            candidate = {'name':'gx10','host':'local','training':str(training),'campaign':'/campaign',
                         'evidence_dirs':[str(pilot)]}
            record = snapshot_candidate(candidate,root/'snapshot',rows)
            self.assertTrue(record['eligible'])
            with patch('scripts.fleet_campaign.command_on',side_effect=['first-sha best.pt','changed-sha best.pt']):
                with self.assertRaisesRegex(ValueError,'changed during snapshot'):
                    snapshot_candidate(candidate,root/'changed-snapshot',rows)

    def test_correctness_requires_complete_finite_gate_and_does_not_hide_final_failure(self):
        with tempfile.TemporaryDirectory() as directory:
            directory = Path(directory)
            with self.assertRaisesRegex(ValueError,'lacks'):
                verify_correctness(directory)
            checks = correctness(directory)
            self.assertEqual(verify_correctness(directory).name,'correctness_initial.json')
            checks['repeat_probability_max_abs'] = float('nan')
            (directory/'correctness_final.json').write_text(json.dumps(checks))
            with self.assertRaisesRegex(ValueError,'failed'):
                verify_correctness(directory)
            checks['repeat_probability_max_abs'] = 0.0
            checks['tolerance_probability_abs'] = 0.02
            (directory/'correctness_final.json').write_text(json.dumps(checks))
            with self.assertRaisesRegex(ValueError,'weakened'):
                verify_correctness(directory)

    def test_compatibility_checks_versions_and_actual_frozen_source_bytes(self):
        with tempfile.TemporaryDirectory() as directory:
            saved = artifact(predictions(),Path(directory)/'model')
            verify_compatibility(saved)
            for change in ({'prompt_version':'other'}, {'adapter_version':'other'}, {'data_signature':'other'}):
                with self.assertRaisesRegex(ValueError,'incompatible'):
                    verify_compatibility({**saved,**change})
            (Path(saved['config']['dataset'])/'validation.jsonl').write_text('modified')
            with self.assertRaisesRegex(ValueError,'source hash mismatch'):
                verify_compatibility(saved)

    def test_deployment_pointer_requires_completed_eval_and_actual_http_probe(self):
        for succeeds in (False,True):
            with self.subTest(succeeds=succeeds), tempfile.TemporaryDirectory() as directory:
                root = Path(directory)
                campaign = root/'campaign'
                evaluation = campaign/'evaluation'
                evaluation.mkdir(parents=True)
                model = evaluation/'model.pt'
                model.write_bytes(b'durable final artifact')
                (evaluation/'metrics.json').write_text(json.dumps({'status':'complete','model_sha256':checksum(model)}))
                (evaluation/'manifest.json').write_text(json.dumps({'checkpoint_sha256':'selected-sha',
                    'data_signature':'frozen-data','source_sha256':{name:checksum(ROOT/name)
                      for name in ('experiment.py','training_model.py')}}))
                selected = {'checkpoint_sha256':'selected-sha','data_signature':'frozen-data'}
                api = MagicMock(pid=987654321)
                api.poll.return_value = None
                responses = [io.BytesIO(json.dumps({'status':'ready','checkpoint':str(model),'model':'opensysone'}).encode()),
                             io.BytesIO(b'{"response":"HTTP probe"}')]
                def validate(payload,result):
                    self.assertFalse((root/'ai/opensysone/deploy/current.json').exists())
                    self.assertEqual(result,{'response':'HTTP probe'})
                    if not succeeds:
                        raise ValueError('invalid actual HTTP response')
                state = {}
                with patch('scripts.fleet_campaign.runner.STOP',False), \
                     patch('scripts.fleet_campaign.stage') as stage_mock, \
                     patch('scripts.fleet_campaign.subprocess.Popen',return_value=api), \
                     patch('scripts.fleet_campaign.urllib.request.urlopen',side_effect=responses) as http, \
                     patch('scripts.fleet_campaign.Path.home',return_value=root), \
                     patch('jev_harness.validate_response',side_effect=validate):
                    if succeeds:
                        deploy(campaign,state,{'port':18081},selected,time.time()+120)
                        pointer = json.loads((root/'ai/opensysone/deploy/current.json').read_text())
                        self.assertEqual(pointer['sha256'],checksum(model))
                        self.assertEqual(state['status'],'complete')
                        api.terminate.assert_not_called()
                    else:
                        with self.assertRaisesRegex(ValueError,'invalid actual HTTP'):
                            deploy(campaign,state,{'port':18081},selected,time.time()+120)
                        self.assertFalse((root/'ai/opensysone/deploy/current.json').exists())
                        api.terminate.assert_called_once()
                    self.assertEqual(stage_mock.call_args.args[2],'harness_check')
                    self.assertEqual(http.call_args.args[0].method,'POST')


if __name__ == '__main__':
    unittest.main()