From be38e6a8dc17ba5f37b683599b63fd41d08daf1f Mon Sep 17 00:00:00 2001 From: tzhouam Date: Tue, 6 Oct 2026 03:16:09 +0800 Subject: [PATCH] Stabilize objective coordinator positive test cohort --- test/test_autonomous_evolution.py | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/test/test_autonomous_evolution.py b/test/test_autonomous_evolution.py index 4b3492c4..23a818f0 100644 --- a/test/test_autonomous_evolution.py +++ b/test/test_autonomous_evolution.py @@ -403,6 +403,15 @@ def test_objective_coordinator_never_calls_legacy_dual_model_forensics(autonomou from infermatrix_copilot.improve import coordinator from infermatrix_copilot.engine.steps import improve st, store, model, worker = autonomous + # Keep this large-effect routing test's positive cohort above the + # coordinator's replenishment floor, including after its eight holdouts + # are consumed. Negative controls are independently asserted above. + objectives.prepare(st, store, workflow=objectives.ENGINE) + path = objectives.data_root(st) / objectives.ENGINE / 'dataset.json' + manifest = json.loads(path.read_text()) + manifest['items'] = [r for r in manifest['items'] if not r['objective'].get('negative')] + artifacts.atomic_json(path, manifest) + assert sum(r['split'] == 'holdout' for r in manifest['items']) >= 88 def forbidden(*args, **kwargs): raise AssertionError('legacy model or human benchmark requested') monkeypatch.setattr(improve, '_forensics', forbidden) result = coordinator.run(st, store, workflow=objectives.ENGINE, llm=model, sandbox=worker)