Release 2.0.0 with Sol-led escalation and evidence adjudication

2026-09-15 21:17:41 +08:00
parent 7969489b7e
commit dc0360cefb
12 changed files with 300 additions and 3 deletions
@@ -0,0 +1,69 @@
+import copy
+import importlib.util
+import json
+from pathlib import Path
+import unittest
+
+ROOT = Path(__file__).resolve().parents[1]
+spec = importlib.util.spec_from_file_location("decision", ROOT / "skills/codex-subagent-router/scripts/validate_decision_record.py")
+module = importlib.util.module_from_spec(spec)
+spec.loader.exec_module(module)
+
+
+class DecisionTests(unittest.TestCase):
+    def setUp(self):
+        self.record = json.loads((ROOT / "examples/decisions/resolved.json").read_text())
+
+    def test_valid_resolution(self):
+        self.assertEqual(module.validate(self.record), [])
+
+    def test_counter_survives_continuation(self):
+        previous = copy.deepcopy(self.record)
+        self.record["same_class_failures"] = 0
+        self.assertTrue(module.validate(self.record, previous))
+
+    def test_reassessment_required(self):
+        self.record["reassessment"] = ""
+        self.assertTrue(module.validate(self.record))
+
+    def test_unresolved_counterexample_blocks_resolution(self):
+        self.record["unresolved"] = ["reproducible contrary result"]
+        self.assertTrue(module.validate(self.record))
+
+    def test_stale_baseline_blocks_resolution(self):
+        self.record["verification"]["baseline"] = "old"
+        self.assertTrue(module.validate(self.record))
+
+    def test_parent_must_understand(self):
+        self.record["verification"]["parent_understands"] = False
+        self.assertTrue(module.validate(self.record))
+
+    def test_environment_and_authority_do_not_escalate_to_astra(self):
+        for category in ("environment", "authority"):
+            self.record["failure_class"] = category
+            self.record["escalation"]["target"] = "astra"
+            self.assertTrue(module.validate(self.record))
+
+    def test_extra_consultation_needs_basis(self):
+        self.record["escalation"]["expert_consultations"] = 2
+        self.assertTrue(module.validate(self.record))
+        self.record["escalation"]["followup_basis"] = "new discriminator result"
+        self.assertEqual(module.validate(self.record), [])
+
+    def test_recovery_required(self):
+        self.record["recovery_route"] = ""
+        self.assertTrue(module.validate(self.record))
+
+    def test_bad_shapes_and_boolean_counters(self):
+        for value in (None, [], True):
+            self.assertTrue(module.validate(value))
+        self.record["same_class_failures"] = True
+        self.assertTrue(module.validate(self.record))
+
+    def test_unhashable_enum_fields_are_rejected(self):
+        for key in ("failure_class", "status"):
+            record = copy.deepcopy(self.record)
+            record[key] = []
+            self.assertTrue(module.validate(record))
+        self.record["escalation"]["target"] = {}
+        self.assertTrue(module.validate(self.record))