Harden M9: Ed25519 attestation, full SHA-256 integrity, locked-by-default, prompt improvements, registry verification

tests/test_prompt_optimizer.py

@@ -23,6 +23,21 @@ class TestTruncate:
 
 
 class TestGenerateVariations:
+    def test_mock_provider_never_calls_external_provider(self):
+        with patch("cmdforge.providers.call_provider") as call:
+            _get_strategies("Summarize the text", 2, provider="mock")
+        call.assert_not_called()
+
+    def test_selected_provider_is_honored(self):
+        from cmdforge.providers import ProviderResult
+        with patch(
+            "cmdforge.providers.call_provider",
+            return_value=ProviderResult(text="A materially clearer instruction", success=True),
+        ) as call:
+            result = _get_strategies("Summarize the text", 1, provider="chosen")
+        assert result[0][1] == "A materially clearer instruction"
+        assert call.call_args.args[0] == "chosen"
+
     def test_generates_for_prompt_steps(self, tmp_path):
         from cmdforge.tool import Tool, PromptStep
 
@@ -75,6 +90,29 @@ class TestGetStrategies:
 
 
 class TestOptimizeTool:
+    def test_structural_results_do_not_claim_a_best_prompt(self):
+        from cmdforge.tool import Tool, PromptStep
+        tool = Tool(
+            name="structural", steps=[PromptStep("Summarize", "mock", "out")],
+            output="{out}", input_schema={"type": "string"},
+            output_schema={"type": "string"},
+        )
+        result = optimize_tool(tool, count=2)
+        assert result.best is None
+        assert "cannot compare prompt semantics" in result.note
+
+    def test_behavioral_evaluator_selects_only_an_improvement(self):
+        from cmdforge.tool import Tool, PromptStep
+        tool = Tool(
+            name="behavioral", steps=[PromptStep("Do it", "mock", "out")],
+            output="{out}",
+        )
+        result = optimize_tool(
+            tool, count=3,
+            evaluator=lambda candidate: len(candidate.steps[0].prompt),
+        )
+        assert result.best is not None
+        assert result.scores[result.best_index] > result.baseline_score
     def test_baseline_score_recorded(self, tmp_path):
         from cmdforge.tool import Tool, PromptStep