Expand module contracts for references and normalizer LLM access

internal/framework/pipeline/module_test.go

@@ -7,19 +7,117 @@ import (
 	"gitea.maximumdirect.net/eric/notarius/internal/framework/contracts"
 )
 
-func TestValidateModuleSpecRejectsReferenceSlotsForNonExtractors(t *testing.T) {
-	err := validateModuleSpec("chunker", StageChunk, ModuleSpec{
-		Key:   "generic",
-		Stage: StageChunk,
-		ReferenceSlots: []contracts.ReferenceSlot{
-			{Name: "roster"},
-		},
-	})
-
-	if err == nil {
-		t.Fatal("validateModuleSpec() error = nil, want error")
+func TestValidateModuleSpecAllowsReferenceSlotsForEligibleStages(t *testing.T) {
+	tests := []struct {
+		name  string
+		kind  string
+		stage ModuleStage
+	}{
+		{name: "chunker", kind: "chunker", stage: StageChunk},
+		{name: "extractor", kind: "extractor", stage: StageExtract},
+		{name: "normalizer", kind: "normalizer", stage: StageNormalize},
 	}
-	if !strings.Contains(err.Error(), "reference slots") {
-		t.Fatalf("validateModuleSpec() error = %q, want reference slots context", err.Error())
+
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			spec := normalizeModuleSpec(ModuleSpec{
+				Key:   "module",
+				Stage: test.stage,
+				ReferenceSlots: []contracts.ReferenceSlot{
+					{Name: "roster", Description: "Character roster", MaxBytes: 1024},
+				},
+			})
+			err := validateModuleSpec(test.kind, test.stage, spec)
+			if err != nil {
+				t.Fatalf("validateModuleSpec() error = %v, want nil", err)
+			}
+		})
+	}
+}
+
+func TestValidateModuleSpecRejectsReferenceSlotsForIneligibleStages(t *testing.T) {
+	tests := []struct {
+		name  string
+		kind  string
+		stage ModuleStage
+	}{
+		{name: "input", kind: "input adapter", stage: StageInput},
+		{name: "merge", kind: "merger", stage: StageMerge},
+		{name: "validate", kind: "validator", stage: StageValidate},
+		{name: "output", kind: "output encoder", stage: StageOutput},
+	}
+
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			spec := normalizeModuleSpec(ModuleSpec{
+				Key:   "module",
+				Stage: test.stage,
+				ReferenceSlots: []contracts.ReferenceSlot{
+					{Name: "roster"},
+				},
+			})
+			err := validateModuleSpec(test.kind, test.stage, spec)
+			if err == nil {
+				t.Fatal("validateModuleSpec() error = nil, want error")
+			}
+			if !strings.Contains(err.Error(), "reference slots") {
+				t.Fatalf("validateModuleSpec() error = %q, want reference slots context", err.Error())
+			}
+		})
+	}
+}
+
+func TestValidateModuleSpecRejectsInvalidReferenceSlotsForEligibleStages(t *testing.T) {
+	invalidSlots := []struct {
+		name  string
+		slots []contracts.ReferenceSlot
+		want  string
+	}{
+		{
+			name:  "empty name",
+			slots: []contracts.ReferenceSlot{{Name: " "}},
+			want:  "name",
+		},
+		{
+			name: "duplicate name after trim",
+			slots: []contracts.ReferenceSlot{
+				{Name: "roster"},
+				{Name: " roster "},
+			},
+			want: "duplicated",
+		},
+		{
+			name:  "negative max bytes",
+			slots: []contracts.ReferenceSlot{{Name: "roster", MaxBytes: -1}},
+			want:  "max_bytes",
+		},
+	}
+	eligibleStages := []struct {
+		name  string
+		kind  string
+		stage ModuleStage
+	}{
+		{name: "chunk", kind: "chunker", stage: StageChunk},
+		{name: "extract", kind: "extractor", stage: StageExtract},
+		{name: "normalize", kind: "normalizer", stage: StageNormalize},
+	}
+
+	for _, stage := range eligibleStages {
+		for _, invalid := range invalidSlots {
+			t.Run(stage.name+"/"+invalid.name, func(t *testing.T) {
+				spec := normalizeModuleSpec(ModuleSpec{
+					Key:            "module",
+					Stage:          stage.stage,
+					ReferenceSlots: invalid.slots,
+				})
+				err := validateModuleSpec(stage.kind, stage.stage, spec)
+				if err == nil {
+					t.Fatal("validateModuleSpec() error = nil, want error")
+				}
+				if !strings.Contains(err.Error(), invalid.want) {
+					t.Fatalf("validateModuleSpec() error = %q, want %q", err.Error(), invalid.want)
+				}
+			})
+		}
 	}
 }