feat: add YAML support for persona files (#57)

- Add github.com/goccy/go-yaml dependency (v1.19.2)
- Update parsePersona to detect format by file extension
- Support both .yaml and .yml extensions (case-insensitive)
- Convert built-in personas to YAML format
- Add comprehensive tests for YAML parsing
- Update README with YAML examples and documentation

YAML provides cleaner multi-line strings via literal block scalars
and supports comments, making persona definitions more readable.
JSON remains supported for backwards compatibility.

Closes #57

review/persona.go

@@ -7,32 +7,35 @@ import (
 	"os"
 	"strings"
 	"unicode/utf8"
+
+	"github.com/goccy/go-yaml"
 )
 
-//go:embed personas/*.json
+//go:embed personas/*.yaml
 var embeddedPersonas embed.FS
 
 // Persona defines a specialized review role with focused expertise.
 type Persona struct {
-	Name         string   `json:"name"`
-	DisplayName  string   `json:"display_name"`
-	ModelPref    string   `json:"model_preference,omitempty"`
-	Identity     string   `json:"identity"`
-	Focus        []string `json:"focus"`
-	Ignore       []string `json:"ignore"`
-	Severity     Severity `json:"severity"`
-	OutputFormat string   `json:"output_format,omitempty"`
+	Name         string   `json:"name" yaml:"name"`
+	DisplayName  string   `json:"display_name" yaml:"display_name"`
+	ModelPref    string   `json:"model_preference,omitempty" yaml:"model_preference,omitempty"`
+	Identity     string   `json:"identity" yaml:"identity"`
+	Focus        []string `json:"focus" yaml:"focus"`
+	Ignore       []string `json:"ignore" yaml:"ignore"`
+	Severity     Severity `json:"severity" yaml:"severity"`
+	OutputFormat string   `json:"output_format,omitempty" yaml:"output_format,omitempty"`
 }
 
 // Severity defines what constitutes each severity level for this persona.
 // These are prompt guidance for the LLM, not output format changes.
 type Severity struct {
-	Major string `json:"major"`
-	Minor string `json:"minor"`
-	Nit   string `json:"nit"`
+	Major string `json:"major" yaml:"major"`
+	Minor string `json:"minor" yaml:"minor"`
+	Nit   string `json:"nit" yaml:"nit"`
 }
 
-// LoadPersona loads a persona from a JSON file path.
+// LoadPersona loads a persona from a JSON or YAML file path.
+// Format is detected by file extension: .yaml/.yml for YAML, .json or other for JSON.
 func LoadPersona(path string) (*Persona, error) {
 	data, err := os.ReadFile(path)
 	if err != nil {
@@ -43,14 +46,23 @@ func LoadPersona(path string) (*Persona, error) {
 
 // LoadBuiltinPersona loads a built-in persona by name.
 // Returns an error if the persona doesn't exist.
+// Built-in personas are stored in YAML format.
 func LoadBuiltinPersona(name string) (*Persona, error) {
-	filename := name + ".json"
-	data, err := embeddedPersonas.ReadFile("personas/" + filename) // embed.FS paths use forward slashes per io/fs spec
+	// Try YAML first (preferred format)
+	yamlFile := name + ".yaml"
+	data, err := embeddedPersonas.ReadFile("personas/" + yamlFile)
+	if err == nil {
+		return parsePersona(data, "builtin:"+yamlFile)
+	}
+
+	// Fall back to JSON for backwards compatibility
+	jsonFile := name + ".json"
+	data, err = embeddedPersonas.ReadFile("personas/" + jsonFile)
 	if err != nil {
 		available := ListBuiltinPersonas()
 		return nil, fmt.Errorf("unknown built-in persona %q (available: %s)", name, strings.Join(available, ", "))
 	}
-	return parsePersona(data, "builtin:"+name)
+	return parsePersona(data, "builtin:"+jsonFile)
 }
 
 // ListBuiltinPersonas returns the names of all built-in personas.
@@ -60,22 +72,50 @@ func ListBuiltinPersonas() []string {
 	if err != nil {
 		return []string{}
 	}
-	var names []string
+	seen := make(map[string]bool)
 	for _, e := range entries {
 		if e.IsDir() {
 			continue
 		}
 		name := e.Name()
-		if strings.HasSuffix(name, ".json") {
-			names = append(names, strings.TrimSuffix(name, ".json"))
+		// Strip extension to get persona name
+		var personaName string
+		switch {
+		case strings.HasSuffix(name, ".yaml"):
+			personaName = strings.TrimSuffix(name, ".yaml")
+		case strings.HasSuffix(name, ".yml"):
+			personaName = strings.TrimSuffix(name, ".yml")
+		case strings.HasSuffix(name, ".json"):
+			personaName = strings.TrimSuffix(name, ".json")
+		default:
+			continue
 		}
+		if !seen[personaName] {
+			seen[personaName] = true
+		}
+	}
+	var names []string
+	for name := range seen {
+		names = append(names, name)
 	}
 	return names
 }
 
+// parsePersona parses persona data from JSON or YAML format.
+// Format is detected by the source file extension.
 func parsePersona(data []byte, source string) (*Persona, error) {
+	lowerSource := strings.ToLower(source)
+	isYAML := strings.HasSuffix(lowerSource, ".yaml") || strings.HasSuffix(lowerSource, ".yml")
+
 	var p Persona
-	if err := json.Unmarshal(data, &p); err != nil {
+	var err error
+	if isYAML {
+		// go-yaml v1.16.0+ has built-in protection against deeply nested structures
+		err = yaml.Unmarshal(data, &p)
+	} else {
+		err = json.Unmarshal(data, &p)
+	}
+	if err != nil {
 		return nil, fmt.Errorf("parse persona %s: %w", source, err)
 	}
 	if err := validatePersona(&p, source); err != nil {

review/persona_test.go

@@ -87,6 +87,83 @@ func TestListBuiltinPersonas(t *testing.T) {
 	}
 }
 
+func TestLoadPersonaFromYAMLFile(t *testing.T) {
+	dir := t.TempDir()
+	path := filepath.Join(dir, "test.yaml")
+
+	content := `# Test persona
+name: test
+display_name: Test Persona
+identity: |
+  You are a test persona.
+  Multi-line identity works.
+focus:
+  - testing
+  - validation
+ignore:
+  - nothing
+severity:
+  major: Big problems
+  minor: Small problems
+  nit: Tiny problems
+`
+
+	if err := os.WriteFile(path, []byte(content), 0644); err != nil {
+		t.Fatalf("failed to write test file: %v", err)
+	}
+
+	p, err := LoadPersona(path)
+	if err != nil {
+		t.Fatalf("LoadPersona failed: %v", err)
+	}
+
+	if p.Name != "test" {
+		t.Errorf("Name = %q, want %q", p.Name, "test")
+	}
+	if p.DisplayName != "Test Persona" {
+		t.Errorf("DisplayName = %q, want %q", p.DisplayName, "Test Persona")
+	}
+	if len(p.Focus) != 2 {
+		t.Errorf("Focus len = %d, want 2", len(p.Focus))
+	}
+	if !strings.Contains(p.Identity, "Multi-line") {
+		t.Error("Identity should contain multi-line content")
+	}
+}
+
+func TestLoadPersonaFromYMLFile(t *testing.T) {
+	dir := t.TempDir()
+	path := filepath.Join(dir, "test.yml")
+
+	content := `name: test
+display_name: Test YML
+identity: Test identity
+focus:
+  - testing
+ignore: []
+severity:
+  major: Big
+  minor: Small
+  nit: Tiny
+`
+
+	if err := os.WriteFile(path, []byte(content), 0644); err != nil {
+		t.Fatalf("failed to write test file: %v", err)
+	}
+
+	p, err := LoadPersona(path)
+	if err != nil {
+		t.Fatalf("LoadPersona failed: %v", err)
+	}
+
+	if p.Name != "test" {
+		t.Errorf("Name = %q, want %q", p.Name, "test")
+	}
+	if p.DisplayName != "Test YML" {
+		t.Errorf("DisplayName = %q, want %q", p.DisplayName, "Test YML")
+	}
+}
+
 func TestLoadPersonaFromJSONFile(t *testing.T) {
 	dir := t.TempDir()
 	path := filepath.Join(dir, "test.json")
@@ -130,22 +207,38 @@ func TestLoadPersonaFromJSONFile(t *testing.T) {
 func TestLoadPersonaValidation(t *testing.T) {
 	tests := []struct {
 		name    string
-		json    string
+		content string
+		ext     string
 		wantErr string
 	}{
 		{
-			name:    "missing name",
-			json:    `{"identity": "test"}`,
+			name:    "missing name yaml",
+			content: "identity: test\n",
+			ext:     ".yaml",
 			wantErr: "name is required",
 		},
 		{
-			name:    "missing identity",
-			json:    `{"name": "test"}`,
+			name:    "missing identity yaml",
+			content: "name: test\n",
+			ext:     ".yaml",
 			wantErr: "identity is required",
 		},
 		{
-			name: "display_name defaults to name",
-			json: `{"name": "test", "identity": "test identity"}`,
+			name:    "missing name json",
+			content: `{"identity": "test"}`,
+			ext:     ".json",
+			wantErr: "name is required",
+		},
+		{
+			name:    "missing identity json",
+			content: `{"name": "test"}`,
+			ext:     ".json",
+			wantErr: "identity is required",
+		},
+		{
+			name:    "display_name defaults to name",
+			content: "name: test\nidentity: test identity\n",
+			ext:     ".yaml",
 			// No error expected - should succeed
 		},
 	}
@@ -153,8 +246,8 @@ func TestLoadPersonaValidation(t *testing.T) {
 	for _, tt := range tests {
 		t.Run(tt.name, func(t *testing.T) {
 			dir := t.TempDir()
-			path := filepath.Join(dir, "test.json")
-			if err := os.WriteFile(path, []byte(tt.json), 0644); err != nil {
+			path := filepath.Join(dir, "test"+tt.ext)
+			if err := os.WriteFile(path, []byte(tt.content), 0644); err != nil {
 				t.Fatalf("failed to write test file: %v", err)
 			}
 
@@ -184,12 +277,25 @@ func TestLoadPersonaValidation(t *testing.T) {
 }
 
 func TestLoadPersonaFileNotFound(t *testing.T) {
-	_, err := LoadPersona("/nonexistent/path/persona.json")
+	_, err := LoadPersona("/nonexistent/path/persona.yaml")
 	if err == nil {
 		t.Error("expected error for nonexistent file")
 	}
 }
 
+func TestLoadPersonaInvalidYAML(t *testing.T) {
+	dir := t.TempDir()
+	path := filepath.Join(dir, "invalid.yaml")
+	if err := os.WriteFile(path, []byte("not valid yaml:\n  - [broken"), 0644); err != nil {
+		t.Fatalf("failed to write test file: %v", err)
+	}
+
+	_, err := LoadPersona(path)
+	if err == nil {
+		t.Error("expected error for invalid YAML")
+	}
+}
+
 func TestLoadPersonaInvalidJSON(t *testing.T) {
 	dir := t.TempDir()
 	path := filepath.Join(dir, "invalid.json")
@@ -203,6 +309,38 @@ func TestLoadPersonaInvalidJSON(t *testing.T) {
 	}
 }
 
+func TestLoadPersonaCaseInsensitiveExtension(t *testing.T) {
+	tests := []struct {
+		name string
+		ext  string
+	}{
+		{"lowercase yaml", ".yaml"},
+		{"uppercase YAML", ".YAML"},
+		{"mixed case Yaml", ".Yaml"},
+		{"lowercase yml", ".yml"},
+		{"uppercase YML", ".YML"},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			dir := t.TempDir()
+			path := filepath.Join(dir, "test"+tt.ext)
+			content := "name: test\nidentity: test identity\n"
+			if err := os.WriteFile(path, []byte(content), 0644); err != nil {
+				t.Fatalf("failed to write test file: %v", err)
+			}
+
+			p, err := LoadPersona(path)
+			if err != nil {
+				t.Fatalf("LoadPersona failed for extension %s: %v", tt.ext, err)
+			}
+			if p.Name != "test" {
+				t.Errorf("Name = %q, want %q", p.Name, "test")
+			}
+		})
+	}
+}
+
 func TestCapitalizeFirst(t *testing.T) {
 	tests := []struct {
 		input string
@@ -237,3 +375,77 @@ func TestListBuiltinPersonasReturnsEmptySlice(t *testing.T) {
 		t.Error("ListBuiltinPersonas should return empty slice, not nil")
 	}
 }
+
+func TestYAMLMultilineStrings(t *testing.T) {
+	dir := t.TempDir()
+	path := filepath.Join(dir, "multiline.yaml")
+
+	// Test literal block scalar (|) which preserves newlines
+	content := `name: multiline
+display_name: Multiline Test
+identity: |
+  First line.
+  Second line.
+  Third line.
+focus:
+  - item one
+ignore: []
+severity:
+  major: Major issue
+  minor: Minor issue
+  nit: Nit
+`
+
+	if err := os.WriteFile(path, []byte(content), 0644); err != nil {
+		t.Fatalf("failed to write test file: %v", err)
+	}
+
+	p, err := LoadPersona(path)
+	if err != nil {
+		t.Fatalf("LoadPersona failed: %v", err)
+	}
+
+	// Literal block scalar preserves newlines
+	if !strings.Contains(p.Identity, "\n") {
+		t.Error("Identity should contain newlines from literal block scalar")
+	}
+	if !strings.Contains(p.Identity, "Second line") {
+		t.Error("Identity should contain 'Second line'")
+	}
+}
+
+func TestYAMLComments(t *testing.T) {
+	dir := t.TempDir()
+	path := filepath.Join(dir, "comments.yaml")
+
+	content := `# This is a comment
+name: commented  # inline comment
+display_name: Commented Persona
+# Another comment
+identity: Test identity
+focus:
+  - item  # comment after item
+ignore: []
+severity:
+  major: Major
+  minor: Minor
+  nit: Nit
+`
+
+	if err := os.WriteFile(path, []byte(content), 0644); err != nil {
+		t.Fatalf("failed to write test file: %v", err)
+	}
+
+	p, err := LoadPersona(path)
+	if err != nil {
+		t.Fatalf("LoadPersona failed: %v", err)
+	}
+
+	// Comments should be ignored
+	if p.Name != "commented" {
+		t.Errorf("Name = %q, want %q", p.Name, "commented")
+	}
+	if p.Focus[0] != "item" {
+		t.Errorf("Focus[0] = %q, want %q", p.Focus[0], "item")
+	}
+}

review/personas/architect.json

@@ -1,26 +0,0 @@
-{
-  "name": "architect",
-  "display_name": "Software Architect",
-  "identity": "You are a software architect reviewing code for design quality.\n\nYour expertise:\n- Design patterns and anti-patterns\n- Code organization and module boundaries\n- API design and contracts\n- Testability and dependency injection\n- Consistency with existing architecture\n- Technical debt identification",
-  "focus": [
-    "Design pattern violations or misuse",
-    "Module boundary violations (inappropriate coupling)",
-    "API design issues (unclear contracts, leaky abstractions)",
-    "Testability problems (hidden dependencies, god objects)",
-    "Inconsistency with existing codebase patterns",
-    "Unnecessary complexity or over-engineering",
-    "Missing abstractions or premature abstraction"
-  ],
-  "ignore": [
-    "Security vulnerabilities (security persona handles these)",
-    "Performance micro-optimizations",
-    "Code style and formatting",
-    "Documentation typos",
-    "Test implementation details"
-  ],
-  "severity": {
-    "major": "Architectural violations that will cause maintenance problems or make the codebase harder to evolve",
-    "minor": "Design issues that reduce clarity or testability but don't block progress",
-    "nit": "Minor pattern deviations or style preferences"
-  }
-}

review/personas/architect.yaml

@@ -0,0 +1,37 @@
+# Software Architect Persona
+# Focuses on design quality, patterns, and code organization
+
+name: architect
+display_name: Software Architect
+
+identity: |
+  You are a software architect reviewing code for design quality.
+
+  Your expertise:
+  - Design patterns and anti-patterns
+  - Code organization and module boundaries
+  - API design and contracts
+  - Testability and dependency injection
+  - Consistency with existing architecture
+  - Technical debt identification
+
+focus:
+  - Design pattern violations or misuse
+  - Module boundary violations (inappropriate coupling)
+  - API design issues (unclear contracts, leaky abstractions)
+  - Testability problems (hidden dependencies, god objects)
+  - Inconsistency with existing codebase patterns
+  - Unnecessary complexity or over-engineering
+  - Missing abstractions or premature abstraction
+
+ignore:
+  - Security vulnerabilities (security persona handles these)
+  - Performance micro-optimizations
+  - Code style and formatting
+  - Documentation typos
+  - Test implementation details
+
+severity:
+  major: "Architectural violations that will cause maintenance problems or make the codebase harder to evolve"
+  minor: "Design issues that reduce clarity or testability but don't block progress"
+  nit: "Minor pattern deviations or style preferences"

review/personas/docs.json

@@ -1,26 +0,0 @@
-{
-  "name": "docs",
-  "display_name": "Documentation Reviewer",
-  "identity": "You are a documentation specialist reviewing code for clarity and documentation quality.\n\nYour expertise:\n- API documentation and examples\n- Code comments and their accuracy\n- Error message clarity\n- README and guide quality\n- Naming clarity and self-documenting code",
-  "focus": [
-    "Missing or outdated documentation",
-    "Unclear or misleading comments",
-    "Poor error messages (cryptic, unhelpful, missing context)",
-    "Confusing naming (functions, variables, types)",
-    "Missing examples for complex APIs",
-    "Inconsistent terminology",
-    "Documentation that contradicts the code"
-  ],
-  "ignore": [
-    "Security vulnerabilities",
-    "Performance issues",
-    "Design patterns",
-    "Test coverage",
-    "Code style (unless it affects readability)"
-  ],
-  "severity": {
-    "major": "Documentation that actively misleads or missing docs for critical functionality",
-    "minor": "Unclear documentation or poor error messages that will confuse users",
-    "nit": "Minor clarity improvements or typo fixes"
-  }
-}

review/personas/docs.yaml

@@ -0,0 +1,36 @@
+# Documentation Reviewer Persona
+# Focuses on clarity, documentation quality, and self-documenting code
+
+name: docs
+display_name: Documentation Reviewer
+
+identity: |
+  You are a documentation specialist reviewing code for clarity and documentation quality.
+
+  Your expertise:
+  - API documentation and examples
+  - Code comments and their accuracy
+  - Error message clarity
+  - README and guide quality
+  - Naming clarity and self-documenting code
+
+focus:
+  - Missing or outdated documentation
+  - Unclear or misleading comments
+  - Poor error messages (cryptic, unhelpful, missing context)
+  - Confusing naming (functions, variables, types)
+  - Missing examples for complex APIs
+  - Inconsistent terminology
+  - Documentation that contradicts the code
+
+ignore:
+  - Security vulnerabilities
+  - Performance issues
+  - Design patterns
+  - Test coverage
+  - Code style (unless it affects readability)
+
+severity:
+  major: "Documentation that actively misleads or missing docs for critical functionality"
+  minor: "Unclear documentation or poor error messages that will confuse users"
+  nit: "Minor clarity improvements or typo fixes"

review/personas/security.json

@@ -1,26 +0,0 @@
-{
-  "name": "security",
-  "display_name": "Security Specialist",
-  "identity": "You are a security specialist reviewing code for vulnerabilities.\n\nYour expertise:\n- OWASP Top 10 vulnerabilities\n- Injection attacks (SQL, command, path traversal, template)\n- Authentication and authorization patterns\n- Secrets management and exposure risks\n- Race conditions with security implications\n- Event sourcing attack vectors (replay attacks, event injection)",
-  "focus": [
-    "Injection attacks (SQL, command, path traversal, template injection)",
-    "Authentication and authorization gaps or bypasses",
-    "Secrets exposure (hardcoded credentials, tokens in logs, config leaks)",
-    "Input validation failures (unsanitized input, unsafe deserialization)",
-    "Race conditions that could be exploited",
-    "Cryptographic weaknesses (weak algorithms, improper key handling)",
-    "Information disclosure through error messages or logs"
-  ],
-  "ignore": [
-    "Code style and naming conventions",
-    "Performance optimizations (unless security-related)",
-    "Documentation quality",
-    "General code quality or readability",
-    "Test coverage"
-  ],
-  "severity": {
-    "major": "Exploitable vulnerabilities: auth bypass, injection, data exfiltration, privilege escalation, RCE",
-    "minor": "Defense-in-depth issues: missing rate limiting, verbose errors, weak input validation",
-    "nit": "Theoretical risks with low exploitability or impact"
-  }
-}

review/personas/security.yaml

@@ -0,0 +1,37 @@
+# Security Specialist Persona
+# Focuses on vulnerabilities, auth issues, and security best practices
+
+name: security
+display_name: Security Specialist
+
+identity: |
+  You are a security specialist reviewing code for vulnerabilities.
+
+  Your expertise:
+  - OWASP Top 10 vulnerabilities
+  - Injection attacks (SQL, command, path traversal, template)
+  - Authentication and authorization patterns
+  - Secrets management and exposure risks
+  - Race conditions with security implications
+  - Event sourcing attack vectors (replay attacks, event injection)
+
+focus:
+  - Injection attacks (SQL, command, path traversal, template injection)
+  - Authentication and authorization gaps or bypasses
+  - Secrets exposure (hardcoded credentials, tokens in logs, config leaks)
+  - Input validation failures (unsanitized input, unsafe deserialization)
+  - Race conditions that could be exploited
+  - Cryptographic weaknesses (weak algorithms, improper key handling)
+  - Information disclosure through error messages or logs
+
+ignore:
+  - Code style and naming conventions
+  - Performance optimizations (unless security-related)
+  - Documentation quality
+  - General code quality or readability
+  - Test coverage
+
+severity:
+  major: "Exploitable vulnerabilities: auth bypass, injection, data exfiltration, privilege escalation, RCE"
+  minor: "Defense-in-depth issues: missing rate limiting, verbose errors, weak input validation"
+  nit: "Theoretical risks with low exploitability or impact"