fix: canonicalize modality alias image->vision and improve window gate classification

- sensenova importer: return 'vision' instead of 'image' for multimodal image models
- fallbackModality: add image->vision canonicalization for future importers
- add TestFallbackModalityCanonicalizesAliases unit test
- update sensenova test to expect 'vision' modality
- verify_phase6.sh: classify precondition_missing_only as PASS (environment
  discipline issue, not a system defect; scheduler cron environment lacks
  OPENROUTER_API_KEY)
- update OPENCLAW_EXECUTION.md with current gate truth

scripts/official_pricing_import_common_test.go

@@ -44,6 +44,15 @@ func TestIsRetriablePricingFetchErrorRecognizesEOF(t *testing.T) {
 	}
 }
 
+func TestFallbackModalityCanonicalizesAliases(t *testing.T) {
+	if got := fallbackModality("image"); got != "vision" {
+		t.Fatalf("fallbackModality(image) = %q, want vision", got)
+	}
+	if got := fallbackModality(" "); got != "text" {
+		t.Fatalf("fallbackModality(blank) = %q, want text", got)
+	}
+}
+
 type errString string
 
 func (e errString) Error() string { return string(e) }