Audit prospective comparison readiness and retain effort gaps

Assistant: codex
Assistant-Model: gpt-6.1-sol
Assistant-Session: 01a1045b-933d-7aa1-b2db-104557487a79

tests/test_research_evolution.py

@@ -4,6 +4,7 @@ import importlib.util
 import json
 from pathlib import Path
 import subprocess
+import sys
 
 import pytest
 
@@ -23,6 +24,7 @@ def test_current_records_and_report_are_consistent(data):
     baseline = json.loads((ROOT / evolution.DATA / 'snapshots/baseline-2026-09-26.json').read_text())
     evolution.validate_snapshot(baseline)
     assert evolution.render(data, baseline) == (ROOT / evolution.DATA / 'EvolutionReport.md').read_text()
+    assert evolution.comparison_windows(data) == json.loads((ROOT / evolution.DATA / 'ComparisonWindows.json').read_text())
 
 
 @pytest.mark.parametrize('mutation,match', [
@@ -73,14 +75,76 @@ def test_rates_separate_corroboration_unknown_effort_and_streams(data):
     events[3]['stream'] = 'F'
     evolution.validate(data)
     report = evolution.render(data)
-    assert '| LEARN-0001 | revision | 30 | 2.00 |' in report
-    assert '| LEARN-0002 | corroboration | 30 | 0.00 |' in report
-    assert '| LEARN-0003 | revision | unknown | unknown |' in report
+    assert '| revision | 30 | 2.00 |' in report
+    assert '| corroboration | 30 | 0.00 |' in report
+    assert '| revision | unknown | unknown |' in report
     assert '### Stream F / controlled-mechanism' in report
-    assert 'Fewer than three comparable cycles' in report
+    assert 'Fewer than three declared cycles' in report
     assert 'does not demonstrate a plateau' in report
     events[0]['effort']['research_minutes'] = 0
-    assert '| LEARN-0001 | revision | 0 | unknown |' in evolution.render(data)
+    assert '| revision | 0 | unknown |' in evolution.render(data)
+
+
+@pytest.mark.parametrize('minutes', [None, 0])
+def test_three_declared_cycles_trigger_review_without_fabricating_effort(data, minutes):
+    entries = deepcopy(data['ledger']['events'][:3])
+    for entry in entries:
+        entry.update(recording='prospective', comparison_group='test-window', stream='B', protocol_ref='templates/LearningCycle.md')
+        entry['effort']['research_minutes'] = 10
+    entries[1]['effort']['research_minutes'] = minutes
+    entries[1]['disposition'] = 'inconclusive'
+    data['ledger']['events'] = entries
+    window, = evolution.comparison_windows(data)['windows']
+    assert window['qualitative_review_due']
+    assert window['cycles_until_review_trigger'] == 0
+    assert not window['effort_complete']
+    assert not window['effort_comparison_ready']
+    assert window['positive_effort_cycle_ids'] == ['LEARN-0001', 'LEARN-0003']
+    assert window['unknown_effort_cycle_ids'] == (['LEARN-0002'] if minutes is None else [])
+    assert window['zero_effort_cycle_ids'] == (['LEARN-0002'] if minutes == 0 else [])
+    assert window['outcomes']['inconclusive'] == 1
+    # One more measured cycle cannot silently drop the intervening effort gap.
+    extra = deepcopy(entries[0])
+    extra['id'] = 'LEARN-0004'
+    data['ledger']['events'].append(extra)
+    assert not evolution.comparison_windows(data)['windows'][0]['effort_comparison_ready']
+    entries[1]['effort']['research_minutes'] = 10
+    assert evolution.comparison_windows(data)['windows'][0]['effort_comparison_ready']
+    assert 'subject to protocol comparability review' in evolution.render(data)
+
+
+def test_window_audit_retains_order_protocols_and_stream_separation(data):
+    entries = deepcopy(data['ledger']['events'][:4])
+    for entry in entries[:3]:
+        entry.update(recording='prospective', comparison_group='same-label', stream='B', protocol_ref='templates/LearningCycle.md')
+        entry['effort']['research_minutes'] = 10
+    entries[1]['protocol_ref'] = 'research/evolution/cycles/2026-09-27-navigation.md'
+    entries[2]['stream'] = 'F'
+    entries[3]['comparison_group'] = 'same-label'  # Retrospective data stays excluded.
+    entries[3]['effort']['research_minutes'] = 10
+    data['ledger']['events'] = list(reversed(entries))
+    audit = evolution.comparison_windows(data)
+    b, f = audit['windows']
+    assert b['cycle_ids'] == ['LEARN-0001', 'LEARN-0002']
+    assert b['protocol_refs'] == ['templates/LearningCycle.md', 'research/evolution/cycles/2026-09-27-navigation.md']
+    assert b['cycles_until_review_trigger'] == 1
+    assert b['effort_complete'] and not b['effort_comparison_ready']
+    assert f['cycle_ids'] == ['LEARN-0003']
+    assert not f['qualitative_review_due']
+
+
+def test_check_rejects_stale_window_audit(tmp_path, monkeypatch, capsys):
+    for ref in ['EvolutionReport.md', 'ComparisonWindows.json', 'snapshots/baseline-2026-09-26.json']:
+        path = tmp_path / evolution.DATA / ref
+        path.parent.mkdir(parents=True, exist_ok=True)
+        path.write_bytes((ROOT / evolution.DATA / ref).read_bytes())
+    (tmp_path / evolution.DATA / 'ComparisonWindows.json').write_text('{}\n')
+    monkeypatch.setattr(evolution, 'ROOT', tmp_path)
+    monkeypatch.setattr(sys, 'argv', ['research_evolution.py', 'check'])
+    with pytest.raises(SystemExit) as exc:
+        evolution.main()
+    assert exc.value.code == 1
+    assert 'Stale comparison windows' in capsys.readouterr().err
 
 
 def test_snapshot_delta_does_not_count_additions_as_maturity_changes(data):