Bugfixes and improved alignment with architecture blueprint

internal/profile/filesystem_repository.go

@@ -1,6 +1,7 @@
 package profile
 
 import (
+	"bytes"
 	"context"
 	"errors"
 	"fmt"
@@ -26,12 +27,22 @@ func NewFilesystemRepository(dir string) Repository {
 }
 
 func (r *filesystemRepository) GetProfile(ctx context.Context, id string, version string) (*domain.PromptProfile, error) {
+	if strings.TrimSpace(id) == "" {
+		return nil, fmt.Errorf("%w: profile id is required", ErrInvalidProfile)
+	}
+
 	files, err := os.ReadDir(r.dir)
 	if err != nil {
 		return nil, fmt.Errorf("failed to read profile directory: %w", err)
 	}
 
 	for _, file := range files {
+		select {
+		case <-ctx.Done():
+			return nil, ctx.Err()
+		default:
+		}
+
 		if file.IsDir() || (!strings.HasSuffix(file.Name(), ".yaml") && !strings.HasSuffix(file.Name(), ".yml")) {
 			continue
 		}
@@ -43,8 +54,10 @@ func (r *filesystemRepository) GetProfile(ctx context.Context, id string, versio
 		}
 
 		var prof domain.PromptProfile
-		if err := yaml.Unmarshal(data, &prof); err != nil {
-			if strings.Contains(file.Name(), id) {
+		decoder := yaml.NewDecoder(bytes.NewReader(data))
+		decoder.KnownFields(true)
+		if err := decoder.Decode(&prof); err != nil {
+			if strings.TrimSuffix(strings.TrimSuffix(file.Name(), ".yaml"), ".yml") == id {
 				return nil, fmt.Errorf("%w: %s: %v", ErrInvalidYAML, file.Name(), err)
 			}
 			continue
@@ -75,8 +88,8 @@ func validateProfile(p *domain.PromptProfile) error {
 		return errors.New("at least one prompt template message is required")
 	}
 	for i, t := range p.Templates {
-		if t.Role == "" {
-			return fmt.Errorf("template message %d is missing role", i)
+		if !isValidMessageRole(t.Role) {
+			return fmt.Errorf("template message %d has invalid role %q", i, t.Role)
 		}
 		if t.Content == "" {
 			return fmt.Errorf("template message %d is missing content", i)
@@ -88,6 +101,15 @@ func validateProfile(p *domain.PromptProfile) error {
 	if !isValidValidationMode(p.Validation.ValidationMode) {
 		return fmt.Errorf("invalid validation mode: %s", p.Validation.ValidationMode)
 	}
+	if p.Validation.RepairAttempts < 0 {
+		return errors.New("validation.repair_attempts must be greater than or equal to 0")
+	}
+	if p.Validation.ValidationMode == domain.ValidationJSONSchema && strings.TrimSpace(p.Validation.SchemaPath) == "" {
+		return errors.New("validation.schema_path is required when validation_mode is json_schema")
+	}
+	if p.Validation.Format != "" && p.Validation.Format != p.OutputFormat {
+		return fmt.Errorf("validation format %q does not match output format %q", p.Validation.Format, p.OutputFormat)
+	}
 	for i, input := range p.ExpectedInputs {
 		if strings.TrimSpace(input) == "" {
 			return fmt.Errorf("expected input %d has empty name", i)
@@ -111,3 +133,11 @@ func isValidValidationMode(m domain.ValidationMode) bool {
 	}
 	return false
 }
+
+func isValidMessageRole(role string) bool {
+	switch role {
+	case "system", "user", "assistant", "developer":
+		return true
+	}
+	return false
+}

internal/profile/repository_test.go

@@ -6,6 +6,8 @@ import (
 	"os"
 	"path/filepath"
 	"testing"
+
+	"gitea.maximumdirect.net/eric/scriptorium/internal/domain"
 )
 
 func TestFilesystemRepository_GetProfile(t *testing.T) {
@@ -44,6 +46,24 @@ func TestFilesystemRepository_GetProfile(t *testing.T) {
 		if p == nil || p.ID != "test-profile" {
 			t.Errorf("expected profile test-profile, got %v", p)
 		}
+		if p.Version != "1.0.0" {
+			t.Fatalf("expected version 1.0.0, got %q", p.Version)
+		}
+		if len(p.ExpectedInputs) != 2 || p.ExpectedInputs[0] != "transcript" || p.ExpectedInputs[1] != "glossary" {
+			t.Fatalf("unexpected expected_inputs: %#v", p.ExpectedInputs)
+		}
+		if len(p.Templates) != 2 {
+			t.Fatalf("expected 2 templates, got %d", len(p.Templates))
+		}
+		if p.Templates[0].Role != "system" || p.Templates[1].Role != "user" {
+			t.Fatalf("unexpected template roles: %#v", p.Templates)
+		}
+		if p.OutputFormat != domain.FormatMarkdown {
+			t.Fatalf("expected output format markdown, got %q", p.OutputFormat)
+		}
+		if p.Validation.ValidationMode != domain.ValidationBasic {
+			t.Fatalf("expected validation mode basic, got %q", p.Validation.ValidationMode)
+		}
 	})
 
 	t.Run("invalid YAML", func(t *testing.T) {
@@ -67,6 +87,13 @@ func TestFilesystemRepository_GetProfile(t *testing.T) {
 		}
 	})
 
+	t.Run("json schema mode missing schema path", func(t *testing.T) {
+		_, err := repo.GetProfile(ctx, "json-schema-missing-path", "")
+		if !errors.Is(err, ErrInvalidProfile) {
+			t.Errorf("expected ErrInvalidProfile for json_schema profile without schema_path, got %v", err)
+		}
+	})
+
 	t.Run("profile not found", func(t *testing.T) {
 		_, err := repo.GetProfile(ctx, "unknown", "")
 		if !errors.Is(err, ErrProfileNotFound) {

internal/profile/testdata/json_schema_missing_path.yaml

@@ -0,0 +1,8 @@
+id: json-schema-missing-path
+version: "1.0.0"
+templates:
+  - role: user
+    content: "Return JSON"
+output_format: json
+validation:
+  validation_mode: json_schema

internal/profile/testdata/valid.yaml

@@ -1,14 +1,14 @@
 id: test-profile
-version: 1.0.0
+version: "1.0.0"
 description: A valid test profile
 expected_inputs:
   - transcript
   - glossary
 templates:
   - role: system
-    content: You are a helpful assistant.
+    content: "You are a helpful assistant."
   - role: user
-    content: Analyze this: {{.transcript}}
+    content: 'Analyze this: {{input "transcript"}}'
 model_defaults:
   model: gpt-4o
   temperature: 0.7