Add self-scoping assessment comparison

tests/test_cli.py

@@ -131,3 +131,26 @@ def test_export_assessment_cli_writes_completed_run_artifact(tmp_path):
     assert artifact["execution"]["analysis_run_id"] == summary.analysis_run.id
     assert artifact["assessment"]["role"] == "challenger"
     assert artifact["generated_tree"]["abilities"]
+
+
+def test_compare_assessment_cli_writes_markdown_report(tmp_path):
+    output_path = tmp_path / "comparison.md"
+
+    exit_code = main(
+        [
+            "compare-assessment",
+            "--golden",
+            "docs/self-scoping/golden/repo-scoping-golden-profile.v1.json",
+            "--assessment",
+            "docs/self-scoping/assessments/repo-scoping-known-bad-2026-05-15-run-39.json",
+            "--output",
+            str(output_path),
+            "--format",
+            "markdown",
+        ]
+    )
+
+    report = output_path.read_text(encoding="utf-8")
+    assert exit_code == 0
+    assert "Status: `regression`" in report
+    assert "Route LLM Requests Across Providers" in report