.gitea/actions/review/action.yml

@@ -74,6 +74,14 @@ inputs:
     description: 'Local file with additional system prompt instructions (e.g. security review focus)'
     required: false
     default: ''
+  persona:
+    description: 'Built-in persona name (security, architect, docs)'
+    required: false
+    default: ''
+  persona-file:
+    description: 'Path to custom persona JSON file'
+    required: false
+    default: ''
 
 runs:
   using: 'composite'
@@ -155,6 +163,8 @@ runs:
         LLM_PROVIDER: ${{ inputs.llm-provider }}
         UPDATE_EXISTING: ${{ inputs.update-existing }}
         SYSTEM_PROMPT_FILE: ${{ inputs.system-prompt-file }}
+        PERSONA: ${{ inputs.persona }}
+        PERSONA_FILE: ${{ inputs.persona-file }}
       run: |
         ARGS=""
         if [ "${{ inputs.dry-run }}" = "true" ]; then

README.md

@@ -182,6 +182,8 @@ Prints the review to CI logs without posting to the PR. Useful for testing promp
 | `patterns-repo` | No | `""` | Comma-separated repos with language patterns (e.g. `rodin/go-patterns`) |
 | `patterns-files` | No | `README.md` | Files/directories to fetch from pattern repos |
 | `system-prompt-file` | No | `""` | Local file with additional system prompt instructions |
+| `persona` | No | `""` | Built-in persona name (security, architect, docs) |
+| `persona-file` | No | `""` | Path to persona JSON file with custom review focus |
 | `temperature` | No | `0` | LLM temperature (0 = server default) |
 | `timeout` | No | `300` | LLM request timeout in seconds |
 | `dry-run` | No | `false` | Print review to stdout instead of posting |
@@ -329,3 +331,103 @@ budget/             Token estimation + context trimming
 ## License
 
 MIT
+
+## Review Personas
+
+Personas provide role-based review specialization. Instead of generic code review, each persona focuses on a specific domain (security, architecture, documentation) with tailored prompts and severity calibration.
+
+### Built-in Personas
+
+| Persona | Focus |
+|---------|-------|
+| `security` | Vulnerabilities, auth bypass, secrets exposure, injection attacks |
+| `architect` | Design patterns, code organization, API contracts, testability |
+| `docs` | Documentation quality, API clarity, error messages |
+
+### Using Built-in Personas
+
+```yaml
+- uses: rodin/review-bot/.gitea/actions/review@v1
+  with:
+    reviewer-name: security
+    persona: security
+    llm-model: claude-opus-4-20250514  # Security benefits from strong reasoning
+    ...
+```
+
+### Multiple Personas in Parallel
+
+```yaml
+jobs:
+  review:
+    strategy:
+      matrix:
+        include:
+          - name: security
+            persona: security
+          - name: architect
+            persona: architect
+    steps:
+      - uses: rodin/review-bot/.gitea/actions/review@v1
+        with:
+          reviewer-name: ${{ matrix.name }}
+          persona: ${{ matrix.persona }}
+          ...
+```
+
+Each persona posts independently with its own sentinel, so reviews don't interfere.
+
+
+### Custom Personas
+
+Create a JSON file with your domain-specific review focus:
+
+```json
+// .review/personas/trading.json
+{
+  "name": "trading",
+  "display_name": "Trading Domain Expert",
+  "identity": "You are a trading systems expert reviewing code for correctness.\n\nYour expertise:\n- Order lifecycle and state machines\n- Fill handling and partial fills\n- Position tracking and P&L calculations\n- Event sourcing invariants",
+  "focus": [
+    "Order state machine correctness",
+    "Fill handling edge cases (partial, overfill)",
+    "Position and P&L calculation accuracy",
+    "Event replay determinism",
+    "Decimal precision for money"
+  ],
+  "ignore": [
+    "Code style",
+    "General performance",
+    "Documentation formatting"
+  ],
+  "severity": {
+    "major": "Bugs that cause incorrect positions, fills, or money calculations",
+    "minor": "Edge cases that could cause issues under unusual conditions",
+    "nit": "Clarity improvements for domain logic"
+  }
+}
+```
+
+Use it in CI:
+
+```yaml
+- uses: rodin/review-bot/.gitea/actions/review@v1
+  with:
+    reviewer-name: trading
+    persona-file: .review/personas/trading.json
+    ...
+```
+
+
+### Persona vs system-prompt-file
+
+| Feature | `persona` / `persona-file` | `system-prompt-file` |
+|---------|---------------------------|----------------------|
+| Replaces base prompt | Yes | No (appends) |
+| Structured format | Yes (JSON) | No (freeform) |
+| Focus/ignore lists | Yes | Manual |
+| Severity calibration | Yes | Manual |
+| Header display name | Yes | No |
+| Built-in options | Yes | No |
+
+Use personas for domain-specialized reviews. Use `system-prompt-file` for minor tweaks to the generic review.

cmd/review-bot/main.go

@@ -70,6 +70,8 @@ func main() {
 	llmTemp := flag.Float64("llm-temperature", envOrDefaultFloat("LLM_TEMPERATURE", 0), "LLM temperature (0 = server default)")
 	llmTimeout := flag.Int("llm-timeout", envOrDefaultInt("LLM_TIMEOUT", 300), "LLM request timeout in seconds (default 300)")
 	llmProvider := flag.String("llm-provider", envOrDefault("LLM_PROVIDER", "openai"), "LLM API provider: openai or anthropic")
+	personaName := flag.String("persona", envOrDefault("PERSONA", ""), "Built-in persona name (security, architect, docs)")
+	personaFile := flag.String("persona-file", envOrDefault("PERSONA_FILE", ""), "Path to persona JSON file")
 
 	flag.Parse()
 
@@ -91,6 +93,36 @@ func main() {
 		os.Exit(1)
 	}
 
+	// Validate persona flags are mutually exclusive
+	if *personaName != "" && *personaFile != "" {
+		slog.Error("--persona and --persona-file are mutually exclusive")
+		os.Exit(1)
+	}
+
+	// Load persona if specified
+	var persona *review.Persona
+	if *personaName != "" {
+		var err error
+		persona, err = review.LoadBuiltinPersona(*personaName)
+		if err != nil {
+			slog.Error("failed to load persona", "persona", *personaName, "error", err)
+			os.Exit(1)
+		}
+		slog.Info("loaded built-in persona", "persona", persona.Name, "display", persona.DisplayName)
+	} else if *personaFile != "" {
+		resolvedPath, err := validateWorkspacePath(*personaFile, "persona-file")
+		if err != nil {
+			slog.Error("invalid persona-file path", "error", err)
+			os.Exit(1)
+		}
+		persona, err = review.LoadPersona(resolvedPath)
+		if err != nil {
+			slog.Error("failed to load persona file", "file", *personaFile, "error", err)
+			os.Exit(1)
+		}
+		slog.Info("loaded persona from file", "file", *personaFile, "persona", persona.Name)
+	}
+
 	// Validate reviewer-name: only safe characters allowed in sentinel
 	if err := validateReviewerName(*reviewerName); err != nil {
 		slog.Error("invalid reviewer name", "error", err)
@@ -201,34 +233,14 @@ func main() {
 	// Step 6b: Load additional system prompt if specified
 	additionalPrompt := ""
 	if *systemPromptFile != "" {
-		workspace := os.Getenv("GITHUB_WORKSPACE")
-		if workspace == "" {
-			workspace, _ = os.Getwd()
-		}
-		absWorkspace, err := filepath.Abs(workspace)
+		resolvedPath, err := validateWorkspacePath(*systemPromptFile, "system-prompt-file")
 		if err != nil {
-			slog.Error("failed to resolve workspace path", "error", err)
-			os.Exit(1)
-		}
-		promptPath := filepath.Join(absWorkspace, *systemPromptFile)
-		promptPath = filepath.Clean(promptPath)
-		if !strings.HasPrefix(promptPath, absWorkspace+string(filepath.Separator)) && promptPath != absWorkspace {
-			slog.Error("system-prompt-file resolves outside workspace", "path", promptPath, "workspace", absWorkspace)
-			os.Exit(1)
-		}
-		// Resolve symlinks and re-validate to prevent symlink traversal
-		resolvedPath, err := filepath.EvalSymlinks(promptPath)
-		if err != nil {
-			slog.Error("failed to resolve system prompt file", "path", promptPath, "error", err)
-			os.Exit(1)
-		}
-		if !strings.HasPrefix(resolvedPath, absWorkspace+string(filepath.Separator)) && resolvedPath != absWorkspace {
-			slog.Error("system-prompt-file symlink resolves outside workspace", "resolved", resolvedPath, "workspace", absWorkspace)
+			slog.Error("invalid system-prompt-file path", "error", err)
 			os.Exit(1)
 		}
 		data, err := os.ReadFile(resolvedPath)
 		if err != nil {
-			slog.Error("failed to read system prompt file", "path", promptPath, "error", err)
+			slog.Error("failed to read system prompt file", "path", *systemPromptFile, "error", err)
 			os.Exit(1)
 		}
 		additionalPrompt = string(data)
@@ -236,7 +248,13 @@ func main() {
 	}
 
 	// Step 7: Budget-aware prompt assembly
-	systemBase := review.BuildSystemBase()
+	var systemBase string
+	if persona != nil {
+		systemBase = review.BuildPersonaSystemPrompt(persona)
+		slog.Debug("using persona system prompt", "persona", persona.Name)
+	} else {
+		systemBase = review.BuildSystemBase()
+	}
 	if additionalPrompt != "" {
 		systemBase += "\n\n## Additional Review Instructions\n\n" + additionalPrompt
 	}
@@ -293,7 +311,12 @@ func main() {
 	slog.Info("review parsed", "verdict", result.Verdict, "findings", len(result.Findings))
 
 	// Step 10: Format and post review
-	reviewBody := review.FormatMarkdown(result, *reviewerName)
+	var reviewBody string
+	if persona != nil && persona.DisplayName != "" {
+		reviewBody = review.FormatMarkdownWithDisplay(result, persona.DisplayName, *reviewerName)
+	} else {
+		reviewBody = review.FormatMarkdown(result, *reviewerName)
+	}
 
 	// Add commit footer so readers know which commit was evaluated
 	if pr.Head.Sha != "" {
@@ -587,6 +610,43 @@ func validateReviewerName(name string) error {
 	return nil
 }
 
+// validateWorkspacePath ensures a file path is within the workspace and resolves
+// symlinks to prevent traversal attacks. Returns the resolved absolute path or
+// an error if the path is outside the workspace.
+func validateWorkspacePath(path, pathName string) (string, error) {
+	workspace := os.Getenv("GITHUB_WORKSPACE")
+	if workspace == "" {
+		workspace, _ = os.Getwd()
+	}
+	absWorkspace, err := filepath.Abs(workspace)
+	if err != nil {
+		return "", fmt.Errorf("failed to resolve workspace path: %w", err)
+	}
+
+	// Join and clean the path
+	fullPath := filepath.Join(absWorkspace, path)
+	fullPath = filepath.Clean(fullPath)
+
+	// Check path is within workspace using filepath.Rel (more robust than HasPrefix)
+	rel, err := filepath.Rel(absWorkspace, fullPath)
+	if err != nil || strings.HasPrefix(rel, "..") {
+		return "", fmt.Errorf("%s resolves outside workspace: path=%s workspace=%s", pathName, fullPath, absWorkspace)
+	}
+
+	// Resolve symlinks and re-validate to prevent symlink traversal
+	resolvedPath, err := filepath.EvalSymlinks(fullPath)
+	if err != nil {
+		return "", fmt.Errorf("failed to resolve %s: %w", pathName, err)
+	}
+
+	relResolved, err := filepath.Rel(absWorkspace, resolvedPath)
+	if err != nil || strings.HasPrefix(relResolved, "..") {
+		return "", fmt.Errorf("%s symlink resolves outside workspace: resolved=%s workspace=%s", pathName, resolvedPath, absWorkspace)
+	}
+
+	return resolvedPath, nil
+}
+
 // buildSupersededBody creates the body for a superseded review: struck-through banner
 // with collapsed original content and the commit it was evaluated against.
 func buildSupersededBody(originalBody, commitSHA, newReviewURL, sentinel string) string {

cmd/review-bot/main_test.go

@@ -6,6 +6,7 @@ import (
 	"log/slog"
 	"os"
 	"os/exec"
+	"path/filepath"
 	"strings"
 	"testing"
 
@@ -45,6 +46,114 @@ func TestValidateReviewerName(t *testing.T) {
 	}
 }
 
+func TestValidateWorkspacePath(t *testing.T) {
+	// Create a temp directory as our workspace
+	tmpDir := t.TempDir()
+
+	// Create a valid file inside the workspace
+	validFile := filepath.Join(tmpDir, "valid.json")
+	if err := os.WriteFile(validFile, []byte("{}"), 0644); err != nil {
+		t.Fatalf("failed to create test file: %v", err)
+	}
+
+	// Create a subdirectory with a file
+	subDir := filepath.Join(tmpDir, "subdir")
+	if err := os.MkdirAll(subDir, 0755); err != nil {
+		t.Fatalf("failed to create subdir: %v", err)
+	}
+	nestedFile := filepath.Join(subDir, "nested.json")
+	if err := os.WriteFile(nestedFile, []byte("{}"), 0644); err != nil {
+		t.Fatalf("failed to create nested file: %v", err)
+	}
+
+	// Create a symlink pointing outside the workspace
+	symlinkPath := filepath.Join(tmpDir, "evil-symlink.json")
+	if err := os.Symlink("/etc/passwd", symlinkPath); err != nil {
+		t.Fatalf("failed to create symlink: %v", err)
+	}
+
+	// Save and restore GITHUB_WORKSPACE
+	origWorkspace := os.Getenv("GITHUB_WORKSPACE")
+	defer os.Setenv("GITHUB_WORKSPACE", origWorkspace)
+
+	tests := []struct {
+		name      string
+		workspace string
+		path      string
+		wantErr   bool
+		errMatch  string
+	}{
+		{
+			name:      "valid relative path",
+			workspace: tmpDir,
+			path:      "valid.json",
+			wantErr:   false,
+		},
+		{
+			name:      "valid nested path",
+			workspace: tmpDir,
+			path:      "subdir/nested.json",
+			wantErr:   false,
+		},
+		{
+			name:      "path traversal attempt",
+			workspace: tmpDir,
+			path:      "../../../etc/passwd",
+			wantErr:   true,
+			errMatch:  "resolves outside workspace",
+		},
+		{
+			name:      "absolute path normalized to workspace-relative",
+			workspace: tmpDir,
+			path:      "/etc/passwd",
+			wantErr:   true,
+			// Go 1.21+ filepath.Join normalizes absolute paths: Join("/tmp/x", "/etc/passwd")
+			// becomes "/tmp/x/etc/passwd", which is within workspace but doesn't exist.
+			errMatch: "failed to resolve",
+		},
+		{
+			name:      "nonexistent file",
+			workspace: tmpDir,
+			path:      "nonexistent.json",
+			wantErr:   true,
+			errMatch:  "failed to resolve",
+		},
+		{
+			name:      "symlink escaping workspace",
+			workspace: tmpDir,
+			path:      "evil-symlink.json",
+			wantErr:   true,
+			errMatch:  "symlink resolves outside workspace",
+		},
+	}
+
+	for _, tc := range tests {
+		t.Run(tc.name, func(t *testing.T) {
+			os.Setenv("GITHUB_WORKSPACE", tc.workspace)
+			resolved, err := validateWorkspacePath(tc.path, "test-file")
+
+			if tc.wantErr {
+				if err == nil {
+					t.Errorf("expected error for %q, got nil", tc.path)
+				} else if tc.errMatch != "" && !strings.Contains(err.Error(), tc.errMatch) {
+					t.Errorf("error %q should contain %q", err.Error(), tc.errMatch)
+				}
+			} else {
+				if err != nil {
+					t.Errorf("expected no error for %q, got %v", tc.path, err)
+				}
+				if resolved == "" {
+					t.Error("expected non-empty resolved path")
+				}
+				// Verify resolved path is within workspace
+				if !strings.HasPrefix(resolved, tc.workspace) {
+					t.Errorf("resolved path %q not within workspace %q", resolved, tc.workspace)
+				}
+			}
+		})
+	}
+}
+
 func makeReview(id int64, login, state string, stale bool, body string) gitea.Review {
 	r := gitea.Review{
 		ID:    id,
@@ -56,7 +165,6 @@ func makeReview(id int64, login, state string, stale bool, body string) gitea.Re
 	return r
 }
 
-
 func TestBuildSupersededBody(t *testing.T) {
 	original := "# Review\n\nLooks good.\n\n<!-- review-bot:sonnet -->"
 	sentinel := "<!-- review-bot:sonnet -->"
@@ -626,8 +734,8 @@ func TestExtractSentinelName_EdgeCases(t *testing.T) {
 		{"<!-- review-bot:sonnet --> rest", "sonnet"},
 		{"<!-- review-bot:gpt-review --> rest", "gpt-review"},
 		{"no sentinel here", "unknown"},
-		{"<!-- review-bot:", "unknown"},       // prefix but no suffix
-		{"prefix <!-- review-bot:abc --> end", "abc"}, // embedded in text
+		{"<!-- review-bot:", "unknown"},                   // prefix but no suffix
+		{"prefix <!-- review-bot:abc --> end", "abc"},     // embedded in text
 	}
 
 	for _, tc := range tests {

docs/DESIGN-51-personas.md

@@ -0,0 +1,334 @@
+# Design: Role-based Review Personas (Issue #51)
+
+> **Note:** This design was revised during implementation to use JSON instead of YAML
+> to maintain the repository's zero-external-dependencies convention. All persona
+> files use JSON format. See "Design Revision" section at the end for details.
+
+## Problem
+
+Current review-bot performs generic code review. Every reviewer (regardless of `reviewer-name`) uses the same base prompt and evaluates the same concerns. This leads to:
+
+1. **Redundancy** — Two reviewers (e.g., GPT + Claude twins) often flag identical issues
+2. **Gaps** — Generic reviewers miss specialized concerns (security, domain logic, architecture)
+3. **Noise** — NITs about style mixed with critical security findings
+4. **No ownership** — Findings lack clear domain attribution
+
+## Constraints
+
+- Must work with existing CLI flags and CI workflow patterns
+- Must not break backwards compatibility (existing configs still work)
+- Must integrate cleanly with the budget system (personas add to context)
+- Multiple personas running in parallel must not interfere with each other
+- Each persona must have clear scope boundaries (no duplication)
+
+## Proposed Approach
+
+### 1. Persona Definition
+
+A persona is a named review role with:
+- **Identity** — Who am I? What's my expertise?
+- **Focus** — What do I look for?
+- **Scope boundaries** — What do I explicitly NOT comment on?
+- **Severity calibration** — What counts as MAJOR/MINOR/NIT for MY domain?
+
+Personas are defined in JSON files that can live:
+1. In the pattern repos (shared across projects)
+2. In the target repo (project-specific personas)
+3. Inline via a new `--persona-file` flag (JSON format)
+
+### 2. Persona File Format
+
+```json
+# .review/personas/security.yaml
+name: security
+display_name: Security Specialist
+model_preference: opus  # optional hint for expensive analysis
+
+identity: |
+  You are a security specialist reviewing code for vulnerabilities.
+  Your expertise: OWASP Top 10, injection attacks, auth/authz, secrets management,
+  event sourcing security (replay attacks, event injection).
+
+focus:
+  - Injection attacks (SQL, command, path traversal, template)
+  - Authentication and authorization gaps
+  - Secrets exposure (hardcoded credentials, tokens in logs)
+  - Input validation (unsanitized input, unsafe deserialization)
+  - Race conditions with security implications
+  - Event sourcing attack vectors
+
+ignore:
+  - Code style and naming conventions
+  - Performance (unless security-related)
+  - Documentation
+  - General code quality
+  - Test coverage
+
+severity:
+  critical: "Remote code execution, auth bypass, data exfiltration"
+  major: "Privilege escalation, information disclosure, DoS"
+  minor: "Missing rate limiting, verbose errors"
+  nit: "Theoretical risk with low exploitability"
+
+output_format: |
+  For each finding:
+  - Severity: [CRITICAL|MAJOR|MINOR|NIT]
+  - Attack vector: How could this be exploited?
+  - Evidence: Code snippet showing the vulnerability
+  - Recommendation: Specific fix
+```
+
+### 3. New CLI Flags
+
+```
+--persona-file PATH      Path to persona JSON file (local or in repo)
+--persona NAME           Built-in persona name (security, architect, domain)
+```
+
+Either flag sets the persona. If neither is provided, behavior is unchanged (generic review).
+
+### 4. Prompt Assembly
+
+Current flow:
+```
+SystemBase → Patterns → Conventions → [LLM]
+```
+
+New flow with persona:
+```
+PersonaPrompt (from YAML) → Patterns (filtered?) → Conventions → [LLM]
+```
+
+The persona's identity/focus/ignore/severity sections become the system prompt, replacing the generic "You are an expert code reviewer" base.
+
+### 5. Built-in Personas
+
+Ship with these built-in personas (loadable via `--persona NAME`):
+
+| Name | Focus |
+|------|-------|
+| `security` | Vulnerabilities, auth, secrets |
+| `architect` | Patterns, consistency, design |
+| `domain` | Business logic (requires repo-specific config) |
+| `docs` | Documentation, API clarity |
+
+Built-in personas live in `review/personas/` as embedded Go assets or YAML shipped with the binary.
+
+### 6. CI Workflow Integration
+
+Single persona:
+```yaml
+- uses: rodin/review-bot/.gitea/actions/review@v1
+  with:
+    reviewer-name: security
+    persona: security
+    ...
+```
+
+Multiple personas (parallel jobs):
+```yaml
+jobs:
+  review:
+    strategy:
+      matrix:
+        include:
+          - name: security
+            persona: security
+          - name: architect
+            persona: architect
+    steps:
+      - uses: rodin/review-bot/.gitea/actions/review@v1
+        with:
+          reviewer-name: ${{ matrix.name }}
+          persona: ${{ matrix.persona }}
+```
+
+Custom persona from repo:
+```yaml
+- uses: rodin/review-bot/.gitea/actions/review@v1
+  with:
+    reviewer-name: trading
+    persona-file: .review/personas/trading.yaml
+```
+
+### 7. Persona + Patterns Interaction
+
+Some personas benefit from filtered patterns:
+- Security → only security-related patterns
+- Architect → all patterns (structural focus)
+- Domain → domain docs, not language patterns
+
+For v1, keep it simple: all patterns are included regardless of persona. Future enhancement could add `patterns_filter` to persona YAML.
+
+### 8. Output Format Changes
+
+Persona name appears in the review header:
+```markdown
+# Security Review
+
+## Summary
+No critical vulnerabilities found in this change.
+
+## Findings
+| # | Severity | File | Line | Finding |
+...
+
+## Recommendation
+**APPROVE** — No security-relevant issues detected.
+
+---
+*Review by security*
+<!-- review-bot:security -->
+```
+
+## State/Data Model
+
+### Persona struct
+
+```go
+// review/persona.go
+type Persona struct {
+    Name          string   `yaml:"name"`
+    DisplayName   string   `yaml:"display_name"`
+    ModelPref     string   `yaml:"model_preference,omitempty"`
+    Identity      string   `yaml:"identity"`
+    Focus         []string `yaml:"focus"`
+    Ignore        []string `yaml:"ignore"`
+    Severity      Severity `yaml:"severity"`
+    OutputFormat  string   `yaml:"output_format,omitempty"`
+}
+
+type Severity struct {
+    Critical string `yaml:"critical"`
+    Major    string `yaml:"major"`
+    Minor    string `yaml:"minor"`
+    Nit      string `yaml:"nit"`
+}
+```
+
+### Loading precedence
+
+1. `--persona-file PATH` → load from local file system
+2. `--persona NAME` → load from embedded built-ins
+3. Neither → use generic system prompt (current behavior)
+
+## Error Cases
+
+| Error | Handling |
+|-------|----------|
+| Persona file not found | Fatal exit with clear message |
+| Invalid YAML in persona file | Fatal exit with parse error |
+| Both `--persona` and `--persona-file` specified | Fatal exit: mutually exclusive |
+| Unknown built-in persona name | Fatal exit with list of valid names |
+| Empty identity in persona | Warning, fall back to generic prompt |
+
+## Edge Cases
+
+- **Empty focus list**: Valid — persona relies on identity alone
+- **Empty ignore list**: Valid — no explicit scope exclusions
+- **No severity section**: Use default MAJOR/MINOR/NIT definitions
+- **Model preference set but budget insufficient**: Ignore preference, log warning
+- **Persona file in pattern repo**: Fetch like other pattern files
+
+## Testing Strategy
+
+### Unit tests
+- `persona_test.go`: Parse valid/invalid YAML, validate required fields
+- `prompt_test.go`: Verify persona prompt assembly
+- Integration with budget: persona prompts count toward token limit
+
+### Integration tests
+- End-to-end with `--persona security` (built-in)
+- End-to-end with `--persona-file custom.yaml`
+- Backwards compatibility: no flags = generic behavior
+
+### Manual verification
+- Run security persona on a PR with obvious vulnerability
+- Verify security persona ignores style issues
+- Verify non-security persona doesn't flag security issues
+
+## Implementation Phases
+
+### Phase 1: Persona types and loading
+- [ ] `review/persona.go`: Persona struct + YAML parsing
+- [ ] `review/persona_test.go`: Unit tests
+- [ ] Embed built-in personas in binary
+- [ ] Compiles clean, tests pass
+
+### Phase 2: Prompt generation
+- [ ] `review/prompt.go`: `BuildPersonaPrompt(p Persona) string`
+- [ ] Modify `BuildSystemBase()` to accept optional persona
+- [ ] Integrate persona prompt with budget system
+- [ ] Tests for prompt assembly
+
+### Phase 3: CLI integration
+- [ ] Add `--persona` and `--persona-file` flags
+- [ ] Flag validation (mutually exclusive, valid names)
+- [ ] Load persona based on flags
+- [ ] Pass persona to prompt builder
+
+### Phase 4: Action integration
+- [ ] Add `persona` and `persona-file` inputs to action.yml
+- [ ] Update README with persona examples
+- [ ] End-to-end CI test
+
+### Phase 5: Built-in personas
+- [ ] `security.yaml` built-in
+- [ ] `architect.yaml` built-in
+- [ ] `docs.yaml` built-in
+- [ ] Document each persona's focus
+
+## Open Questions
+
+1. **Persona file location in repo**: Should we support `--persona-file .review/security.yaml` where the file is fetched from the PR's repo (like conventions)? This adds complexity but enables project-specific personas without action changes.
+
+2. **Model preference enforcement**: If persona specifies `model_preference: opus` but the action uses a different model, should we warn? Override? Ignore? Current thinking: log warning, use the specified model (user controls model via action input).
+
+3. **Severity override output**: If persona defines custom severity levels (CRITICAL), should the JSON output include them, or map back to standard MAJOR/MINOR/NIT? Current thinking: keep standard output format, use severity calibration only for prompt guidance.
+
+## Completion Checklist
+
+1. Persona struct matches YAML schema exactly?
+2. Built-in personas embedded in binary (not external files)?
+3. `--persona` and `--persona-file` are mutually exclusive?
+4. Unknown persona name produces clear error with valid options?
+5. Empty persona file fields have sensible defaults?
+6. Persona prompt integrates with budget system (token counting)?
+7. Backwards compatibility: no flags = current behavior?
+8. Review header shows persona display name?
+9. Sentinel still uses reviewer-name (not persona name)?
+10. Unit tests cover parse errors, missing fields, valid YAML?
+
+## Design Review Findings (Self-Review)
+
+### Finding 1: Severity Mapping
+The persona YAML allows `critical` severity, but the LLM output parser (`review/parser.go`) only accepts MAJOR/MINOR/NIT. 
+
+**Resolution:** Keep standard output format. Persona severity section is ONLY for calibrating the LLM's judgment (prompt guidance). Output must still use MAJOR/MINOR/NIT. Document this clearly in persona format docs.
+
+### Finding 2: Embedding Built-in Personas
+Go doesn't natively embed YAML. Must use `//go:embed` directive (Go 1.16+).
+
+**Resolution:** Create `review/personas/` directory with YAML files and use:
+```go
+//go:embed personas/*.yaml
+var embeddedPersonas embed.FS
+```
+
+### Finding 3: display_name vs reviewer-name
+Design says header shows "persona display name" but sentinel uses "reviewer-name". This is correct - they serve different purposes:
+- `display_name` → human-readable header ("Security Specialist Review")
+- `reviewer-name` → machine sentinel for cleanup (`<!-- review-bot:security -->`)
+
+When persona is used, `display_name` takes precedence for the header title, but `reviewer-name` (CLI flag) is still used for the sentinel.
+
+## Design Revision: YAML with gopkg.in/yaml.v3
+
+**Decision:** Add `gopkg.in/yaml.v3` as a dependency.
+
+YAML is preferred over JSON for persona files because:
+- Multi-line strings are cleaner (no escaping quotes in identity/focus text)
+- Comments are supported for documentation
+- More human-readable for complex persona definitions
+
+The implementation supports both YAML (`.yaml`, `.yml`) and JSON (`.json`) for backwards compatibility, with YAML as the default for built-in personas.

review/formatter.go

@@ -7,10 +7,37 @@ import (
 
 // FormatMarkdown formats a ReviewResult into the markdown body for a Gitea review.
 func FormatMarkdown(result *ReviewResult, reviewerName string) string {
+	return FormatMarkdownWithDisplay(result, reviewerName, reviewerName)
+}
+
+// GiteaEvent converts the verdict to the Gitea API event string.
+func GiteaEvent(verdict string) string {
+	switch verdict {
+	case "APPROVE":
+		return "APPROVED"
+	case "REQUEST_CHANGES":
+		return "REQUEST_CHANGES"
+	default:
+		return "COMMENT"
+	}
+}
+
+// FormatMarkdownWithDisplay formats a ReviewResult with separate display name and sentinel name.
+// Note: displayName is not HTML-escaped as Gitea sanitizes rendered Markdown.
+// Persona display names are controlled by repo owners (trusted input).
+// displayName is used for the header title, sentinelName is used for the cleanup sentinel.
+// If displayName is empty, sentinelName is used for both.
+func FormatMarkdownWithDisplay(result *ReviewResult, displayName, sentinelName string) string {
 	var sb strings.Builder
 
-	if reviewerName != "" {
-		title := strings.ToUpper(reviewerName[:1]) + reviewerName[1:]
+	// Use display name for header, or fall back to sentinel name
+	headerName := displayName
+	if headerName == "" {
+		headerName = sentinelName
+	}
+
+	if headerName != "" {
+		title := CapitalizeFirst(headerName)
 		sb.WriteString(fmt.Sprintf("# %s Review\n\n", title))
 	}
 
@@ -33,23 +60,11 @@ func FormatMarkdown(result *ReviewResult, reviewerName string) string {
 	sb.WriteString("## Recommendation\n\n")
 	sb.WriteString(fmt.Sprintf("**%s** — %s\n", result.Verdict, result.Recommendation))
 
-	if reviewerName != "" {
-		sb.WriteString(fmt.Sprintf("\n---\n*Review by %s*\n", reviewerName))
+	if sentinelName != "" {
+		sb.WriteString(fmt.Sprintf("\n---\n*Review by %s*\n", headerName))
 		// Hidden sentinel for identifying this bot's reviews during cleanup
-		sb.WriteString(fmt.Sprintf("\n<!-- review-bot:%s -->\n", reviewerName))
+		sb.WriteString(fmt.Sprintf("\n<!-- review-bot:%s -->\n", sentinelName))
 	}
 
 	return sb.String()
 }
-
-// GiteaEvent converts the verdict to the Gitea API event string.
-func GiteaEvent(verdict string) string {
-	switch verdict {
-	case "APPROVE":
-		return "APPROVED"
-	case "REQUEST_CHANGES":
-		return "REQUEST_CHANGES"
-	default:
-		return "COMMENT"
-	}
-}

review/formatter_test.go

@@ -159,3 +159,58 @@ func TestFormatMarkdown_RoleTitle(t *testing.T) {
 		t.Error("should not contain role title header when reviewer name is empty")
 	}
 }
+
+func TestFormatMarkdownWithDisplay(t *testing.T) {
+	result := &ReviewResult{
+		Verdict:        "APPROVE",
+		Summary:        "Test summary",
+		Findings:       nil,
+		Recommendation: "Test recommendation",
+	}
+
+	t.Run("with display name", func(t *testing.T) {
+		body := FormatMarkdownWithDisplay(result, "Security Specialist", "security")
+
+		// Header should use display name
+		if !strings.Contains(body, "# Security Specialist Review") {
+			t.Error("header should use display name")
+		}
+
+		// Sentinel should use sentinel name
+		if !strings.Contains(body, "<!-- review-bot:security -->") {
+			t.Error("sentinel should use sentinel name")
+		}
+
+		// Footer "Review by" should use display name
+		if !strings.Contains(body, "*Review by Security Specialist*") {
+			t.Error("footer should use display name")
+		}
+	})
+
+	t.Run("without display name", func(t *testing.T) {
+		body := FormatMarkdownWithDisplay(result, "", "reviewer")
+
+		// Should fall back to sentinel name for header
+		if !strings.Contains(body, "# Reviewer Review") {
+			t.Error("header should fall back to sentinel name")
+		}
+
+		if !strings.Contains(body, "<!-- review-bot:reviewer -->") {
+			t.Error("sentinel should use sentinel name")
+		}
+	})
+
+	t.Run("empty both names", func(t *testing.T) {
+		body := FormatMarkdownWithDisplay(result, "", "")
+
+		// Should not have header
+		if strings.Contains(body, "# ") && strings.Contains(body, " Review") {
+			t.Error("should not have header when both names empty")
+		}
+
+		// Should not have sentinel
+		if strings.Contains(body, "<!-- review-bot:") {
+			t.Error("should not have sentinel when sentinel name empty")
+		}
+	})
+}

review/persona.go

@@ -0,0 +1,112 @@
+package review
+
+import (
+	"embed"
+	"encoding/json"
+	"fmt"
+	"os"
+	"strings"
+	"unicode/utf8"
+)
+
+//go:embed personas/*.json
+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"`
+}
+
+// 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"`
+}
+
+// LoadPersona loads a persona from a JSON file path.
+func LoadPersona(path string) (*Persona, error) {
+	data, err := os.ReadFile(path)
+	if err != nil {
+		return nil, fmt.Errorf("read persona file %s: %w", path, err)
+	}
+	return parsePersona(data, path)
+}
+
+// LoadBuiltinPersona loads a built-in persona by name.
+// Returns an error if the persona doesn't exist.
+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
+	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)
+}
+
+// ListBuiltinPersonas returns the names of all built-in personas.
+// Returns an empty slice if the embedded directory cannot be read.
+func ListBuiltinPersonas() []string {
+	entries, err := embeddedPersonas.ReadDir("personas")
+	if err != nil {
+		return []string{}
+	}
+	var names []string
+	for _, e := range entries {
+		if e.IsDir() {
+			continue
+		}
+		name := e.Name()
+		if strings.HasSuffix(name, ".json") {
+			names = append(names, strings.TrimSuffix(name, ".json"))
+		}
+	}
+	return names
+}
+
+func parsePersona(data []byte, source string) (*Persona, error) {
+	var p Persona
+	if err := json.Unmarshal(data, &p); err != nil {
+		return nil, fmt.Errorf("parse persona %s: %w", source, err)
+	}
+	if err := validatePersona(&p, source); err != nil {
+		return nil, err
+	}
+	return &p, nil
+}
+
+func validatePersona(p *Persona, source string) error {
+	if p.Name == "" {
+		return fmt.Errorf("persona %s: name is required", source)
+	}
+	if p.Identity == "" {
+		return fmt.Errorf("persona %s: identity is required", source)
+	}
+	// DisplayName defaults to Name if not set
+	if p.DisplayName == "" {
+		p.DisplayName = p.Name
+	}
+	return nil
+}
+
+// CapitalizeFirst capitalizes the first rune of a string in a Unicode-safe way.
+// Returns the original string if it's empty.
+func CapitalizeFirst(s string) string {
+	if s == "" {
+		return s
+	}
+	r, size := utf8.DecodeRuneInString(s)
+	if r == utf8.RuneError {
+		return s
+	}
+	return strings.ToUpper(string(r)) + s[size:]
+}

review/persona_prompt.go

@@ -0,0 +1,104 @@
+package review
+
+import (
+	"fmt"
+	"strings"
+)
+
+// BuildPersonaSystemPrompt constructs a system prompt from a persona definition.
+// This replaces BuildSystemBase when a persona is provided.
+func BuildPersonaSystemPrompt(p *Persona) string {
+	var sb strings.Builder
+
+	// Identity section
+	sb.WriteString(p.Identity)
+	sb.WriteString("\n\n")
+
+	// Focus section
+	if len(p.Focus) > 0 {
+		sb.WriteString("## Focus Areas\n\n")
+		sb.WriteString("Concentrate your review on:\n")
+		for _, f := range p.Focus {
+			sb.WriteString(fmt.Sprintf("- %s\n", f))
+		}
+		sb.WriteString("\n")
+	}
+
+	// Ignore section
+	if len(p.Ignore) > 0 {
+		sb.WriteString("## Explicitly Out of Scope\n\n")
+		sb.WriteString("Do NOT comment on:\n")
+		for _, i := range p.Ignore {
+			sb.WriteString(fmt.Sprintf("- %s\n", i))
+		}
+		sb.WriteString("\n")
+	}
+
+	// Severity calibration
+	if p.Severity.Major != "" || p.Severity.Minor != "" || p.Severity.Nit != "" {
+		sb.WriteString("## Severity Calibration\n\n")
+		sb.WriteString("Use these severity definitions for YOUR domain:\n")
+		if p.Severity.Major != "" {
+			sb.WriteString(fmt.Sprintf("- **MAJOR**: %s\n", p.Severity.Major))
+		}
+		if p.Severity.Minor != "" {
+			sb.WriteString(fmt.Sprintf("- **MINOR**: %s\n", p.Severity.Minor))
+		}
+		if p.Severity.Nit != "" {
+			sb.WriteString(fmt.Sprintf("- **NIT**: %s\n", p.Severity.Nit))
+		}
+		sb.WriteString("\n")
+	}
+
+	// Output format instructions (shared schema from prompt.go)
+	sb.WriteString("## Review Instructions\n\n")
+	sb.WriteString("CONTEXT:\n")
+	sb.WriteString("- You will receive the full content of modified files for reference, followed by the diff showing what changed.\n")
+	sb.WriteString("- The diff shows ONLY what was added/removed. The full file content provides complete context.\n")
+	sb.WriteString("- Focus your review on the CHANGES (the diff), using the full files for context.\n\n")
+	sb.WriteString("Your task:\n")
+	sb.WriteString("1. Review the diff for issues within YOUR focus areas only.\n")
+	sb.WriteString("2. Consider the CI status — if CI has failed, that is an automatic REQUEST_CHANGES regardless of code quality.\n")
+	sb.WriteString("3. Output your review as structured JSON (and ONLY JSON, no markdown fences or other text).\n\n")
+	sb.WriteString("Output format:\n")
+	sb.WriteString(outputSchemaJSON)
+	sb.WriteString("\n\n")
+	sb.WriteString(verdictRules)
+	sb.WriteString("\n- Only report findings within your focus areas. Ignore everything else.\n")
+	sb.WriteString("- Line numbers should reference the new file line numbers from the diff headers.\n")
+	sb.WriteString("- If the diff has no changes relevant to your focus areas, APPROVE with no findings.\n")
+
+	// Custom output format if provided
+	if p.OutputFormat != "" {
+		sb.WriteString("\n\n## Additional Output Guidelines\n\n")
+		sb.WriteString(p.OutputFormat)
+	}
+
+	return sb.String()
+}
+
+// BuildSystemPromptWithPersona constructs the full system prompt, using either
+// a persona or the default generic prompt. This is a convenience wrapper that
+// combines BuildPersonaSystemPrompt (or BuildSystemBase) with patterns and conventions.
+// It is exported for use by callers who want one-shot prompt assembly.
+func BuildSystemPromptWithPersona(persona *Persona, conventions, patterns string) string {
+	var base string
+	if persona != nil {
+		base = BuildPersonaSystemPrompt(persona)
+	} else {
+		base = BuildSystemBase()
+	}
+
+	var sb strings.Builder
+	sb.WriteString(base)
+
+	if patterns != "" {
+		sb.WriteString(fmt.Sprintf("\n\n## Language Patterns & Idioms\n\nUse the following patterns as review criteria. Code that violates these established patterns is a finding:\n\n%s\n", patterns))
+	}
+
+	if conventions != "" {
+		sb.WriteString(fmt.Sprintf("\n\n## Repository Conventions\n\nThe repository has the following coding conventions that must be respected:\n\n%s\n", conventions))
+	}
+
+	return sb.String()
+}

review/persona_prompt_test.go

@@ -0,0 +1,157 @@
+package review
+
+import (
+	"strings"
+	"testing"
+)
+
+func TestBuildPersonaSystemPrompt(t *testing.T) {
+	p := &Persona{
+		Name:        "security",
+		DisplayName: "Security Specialist",
+		Identity:    "You are a security specialist.",
+		Focus:       []string{"injection attacks", "auth bypass"},
+		Ignore:      []string{"code style", "performance"},
+		Severity: Severity{
+			Major: "exploitable vulnerabilities",
+			Minor: "defense in depth",
+			Nit:   "theoretical risks",
+		},
+	}
+
+	prompt := BuildPersonaSystemPrompt(p)
+
+	// Check identity is included
+	if !strings.Contains(prompt, "You are a security specialist.") {
+		t.Error("prompt should contain identity")
+	}
+
+	// Check focus areas
+	if !strings.Contains(prompt, "Focus Areas") {
+		t.Error("prompt should contain Focus Areas section")
+	}
+	if !strings.Contains(prompt, "injection attacks") {
+		t.Error("prompt should contain focus item")
+	}
+
+	// Check ignore section
+	if !strings.Contains(prompt, "Out of Scope") {
+		t.Error("prompt should contain Out of Scope section")
+	}
+	if !strings.Contains(prompt, "code style") {
+		t.Error("prompt should contain ignore item")
+	}
+
+	// Check severity calibration
+	if !strings.Contains(prompt, "Severity Calibration") {
+		t.Error("prompt should contain Severity Calibration section")
+	}
+	if !strings.Contains(prompt, "exploitable vulnerabilities") {
+		t.Error("prompt should contain major severity definition")
+	}
+
+	// Check JSON output format is included
+	if !strings.Contains(prompt, `"verdict"`) {
+		t.Error("prompt should contain JSON output format")
+	}
+	if !strings.Contains(prompt, "APPROVE") {
+		t.Error("prompt should mention APPROVE verdict")
+	}
+}
+
+func TestBuildPersonaSystemPromptMinimal(t *testing.T) {
+	// Minimal persona with only required fields
+	p := &Persona{
+		Name:     "minimal",
+		Identity: "You are a minimal reviewer.",
+	}
+
+	prompt := BuildPersonaSystemPrompt(p)
+
+	// Should still work without optional fields
+	if !strings.Contains(prompt, "You are a minimal reviewer.") {
+		t.Error("prompt should contain identity")
+	}
+
+	// Should not have empty sections
+	if strings.Contains(prompt, "Focus Areas") && !strings.Contains(prompt, "Concentrate your review on:") {
+		t.Error("should not have Focus Areas header without content")
+	}
+}
+
+func TestBuildSystemPromptWithPersona(t *testing.T) {
+	t.Run("with persona", func(t *testing.T) {
+		p := &Persona{
+			Name:     "test",
+			Identity: "Test persona identity.",
+			Focus:    []string{"testing"},
+		}
+
+		prompt := BuildSystemPromptWithPersona(p, "test conventions", "test patterns")
+
+		if !strings.Contains(prompt, "Test persona identity.") {
+			t.Error("should contain persona identity")
+		}
+		if !strings.Contains(prompt, "test conventions") {
+			t.Error("should contain conventions")
+		}
+		if !strings.Contains(prompt, "test patterns") {
+			t.Error("should contain patterns")
+		}
+	})
+
+	t.Run("without persona", func(t *testing.T) {
+		prompt := BuildSystemPromptWithPersona(nil, "test conventions", "test patterns")
+
+		// Should use default system base
+		if !strings.Contains(prompt, "expert code reviewer") {
+			t.Error("should contain default system base when no persona")
+		}
+		if !strings.Contains(prompt, "test conventions") {
+			t.Error("should contain conventions")
+		}
+	})
+
+	t.Run("empty conventions and patterns", func(t *testing.T) {
+		p := &Persona{
+			Name:     "test",
+			Identity: "Test identity.",
+		}
+
+		prompt := BuildSystemPromptWithPersona(p, "", "")
+
+		if strings.Contains(prompt, "Language Patterns") {
+			t.Error("should not contain patterns section when empty")
+		}
+		if strings.Contains(prompt, "Repository Conventions") {
+			t.Error("should not contain conventions section when empty")
+		}
+	})
+}
+
+func TestPersonaPromptContainsOutputRules(t *testing.T) {
+	p := &Persona{
+		Name:     "test",
+		Identity: "Test.",
+	}
+
+	prompt := BuildPersonaSystemPrompt(p)
+
+	// Must contain the critical output rules
+	requiredStrings := []string{
+		"APPROVE",
+		"REQUEST_CHANGES",
+		"MAJOR",
+		"MINOR",
+		"NIT",
+		"verdict",
+		"findings",
+		"CI",
+	}
+
+	for _, s := range requiredStrings {
+		if !strings.Contains(prompt, s) {
+			t.Errorf("prompt should contain %q", s)
+		}
+	}
+}

review/persona_test.go

@@ -0,0 +1,239 @@
+package review
+
+import (
+	"os"
+	"path/filepath"
+	"strings"
+	"testing"
+)
+
+func TestLoadBuiltinPersona(t *testing.T) {
+	tests := []struct {
+		name        string
+		personaName string
+		wantErr     bool
+		wantDisplay string
+	}{
+		{
+			name:        "security persona",
+			personaName: "security",
+			wantErr:     false,
+			wantDisplay: "Security Specialist",
+		},
+		{
+			name:        "architect persona",
+			personaName: "architect",
+			wantErr:     false,
+			wantDisplay: "Software Architect",
+		},
+		{
+			name:        "docs persona",
+			personaName: "docs",
+			wantErr:     false,
+			wantDisplay: "Documentation Reviewer",
+		},
+		{
+			name:        "unknown persona",
+			personaName: "nonexistent",
+			wantErr:     true,
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			p, err := LoadBuiltinPersona(tt.personaName)
+			if tt.wantErr {
+				if err == nil {
+					t.Error("expected error, got nil")
+				}
+				return
+			}
+			if err != nil {
+				t.Fatalf("unexpected error: %v", err)
+			}
+			if p.Name != tt.personaName {
+				t.Errorf("Name = %q, want %q", p.Name, tt.personaName)
+			}
+			if p.DisplayName != tt.wantDisplay {
+				t.Errorf("DisplayName = %q, want %q", p.DisplayName, tt.wantDisplay)
+			}
+			if p.Identity == "" {
+				t.Error("Identity should not be empty")
+			}
+			if len(p.Focus) == 0 {
+				t.Error("Focus should not be empty")
+			}
+		})
+	}
+}
+
+func TestListBuiltinPersonas(t *testing.T) {
+	names := ListBuiltinPersonas()
+	if len(names) == 0 {
+		t.Fatal("expected at least one built-in persona")
+	}
+
+	// Check for expected personas
+	expected := map[string]bool{"security": false, "architect": false, "docs": false}
+	for _, name := range names {
+		if _, ok := expected[name]; ok {
+			expected[name] = true
+		}
+	}
+	for name, found := range expected {
+		if !found {
+			t.Errorf("expected built-in persona %q not found", name)
+		}
+	}
+}
+
+func TestLoadPersonaFromJSONFile(t *testing.T) {
+	dir := t.TempDir()
+	path := filepath.Join(dir, "test.json")
+
+	content := `{
+		"name": "test",
+		"display_name": "Test Persona",
+		"identity": "You are a test persona.\nMulti-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 TestLoadPersonaValidation(t *testing.T) {
+	tests := []struct {
+		name    string
+		json    string
+		wantErr string
+	}{
+		{
+			name:    "missing name",
+			json:    `{"identity": "test"}`,
+			wantErr: "name is required",
+		},
+		{
+			name:    "missing identity",
+			json:    `{"name": "test"}`,
+			wantErr: "identity is required",
+		},
+		{
+			name: "display_name defaults to name",
+			json: `{"name": "test", "identity": "test identity"}`,
+			// No error expected - should succeed
+		},
+	}
+
+	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 {
+				t.Fatalf("failed to write test file: %v", err)
+			}
+
+			p, err := LoadPersona(path)
+			if tt.wantErr != "" {
+				if err == nil {
+					t.Errorf("expected error containing %q, got nil", tt.wantErr)
+					return
+				}
+				if !strings.Contains(err.Error(), tt.wantErr) {
+					t.Errorf("error = %q, want containing %q", err.Error(), tt.wantErr)
+				}
+				return
+			}
+			if err != nil {
+				t.Fatalf("unexpected error: %v", err)
+			}
+			// Check display_name defaulting
+			if p.DisplayName == "" {
+				t.Error("DisplayName should default to Name")
+			}
+			if p.DisplayName != p.Name {
+				t.Errorf("DisplayName should default to Name, got %q", p.DisplayName)
+			}
+		})
+	}
+}
+
+func TestLoadPersonaFileNotFound(t *testing.T) {
+	_, err := LoadPersona("/nonexistent/path/persona.json")
+	if err == nil {
+		t.Error("expected error for nonexistent file")
+	}
+}
+
+func TestLoadPersonaInvalidJSON(t *testing.T) {
+	dir := t.TempDir()
+	path := filepath.Join(dir, "invalid.json")
+	if err := os.WriteFile(path, []byte("not valid json {"), 0644); err != nil {
+		t.Fatalf("failed to write test file: %v", err)
+	}
+
+	_, err := LoadPersona(path)
+	if err == nil {
+		t.Error("expected error for invalid JSON")
+	}
+}
+
+func TestCapitalizeFirst(t *testing.T) {
+	tests := []struct {
+		input string
+		want  string
+	}{
+		{"hello", "Hello"},
+		{"Hello", "Hello"},
+		{"HELLO", "HELLO"},
+		{"a", "A"},
+		{"", ""},
+		{"日本語", "日本語"}, // Non-ASCII: Japanese doesn't have case
+		{"über", "Über"},   // German umlaut
+		{"élève", "Élève"}, // French accent
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.input, func(t *testing.T) {
+			got := CapitalizeFirst(tt.input)
+			if got != tt.want {
+				t.Errorf("CapitalizeFirst(%q) = %q, want %q", tt.input, got, tt.want)
+			}
+		})
+	}
+}
+
+func TestListBuiltinPersonasReturnsEmptySlice(t *testing.T) {
+	// ListBuiltinPersonas should return an empty slice (not nil) on error.
+	// We can't easily test the error case, but we can verify the success case
+	// returns a proper slice.
+	names := ListBuiltinPersonas()
+	if names == nil {
+		t.Error("ListBuiltinPersonas should return empty slice, not nil")
+	}
+}

review/personas/architect.json

@@ -0,0 +1,26 @@
+{
+  "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/docs.json

@@ -0,0 +1,26 @@
+{
+  "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/security.json

@@ -0,0 +1,26 @@
+{
+  "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/prompt.go

@@ -7,6 +7,28 @@ import (
 	"strings"
 )
 
+// outputSchemaJSON is the shared JSON output format specification used by both
+// the generic reviewer and persona-based reviewers.
+const outputSchemaJSON = `{
+  "verdict": "APPROVE" or "REQUEST_CHANGES",
+  "summary": "Brief overall assessment (1-3 sentences)",
+  "findings": [
+    {
+      "severity": "MAJOR" or "MINOR" or "NIT",
+      "file": "path/to/file",
+      "line": <line number from the diff>,
+      "finding": "Description of the issue"
+    }
+  ],
+  "recommendation": "Full recommendation text explaining your verdict"
+}`
+
+// verdictRules is the shared verdict determination rules.
+const verdictRules = `Rules:
+- If there are any MAJOR findings → verdict must be REQUEST_CHANGES
+- If there are no MAJOR findings → verdict should be APPROVE
+- If CI has failed → verdict must be REQUEST_CHANGES with a finding noting the CI failure`
+
 // BuildSystemBase returns the core system prompt instructions without
 // patterns or conventions. Used by the budget package to separate
 // trimmable from non-trimmable content.
@@ -23,24 +45,10 @@ func BuildSystemBase() string {
 	sb.WriteString("2. Consider the CI status — if CI has failed, that is an automatic REQUEST_CHANGES regardless of code quality.\n")
 	sb.WriteString("3. Output your review as structured JSON (and ONLY JSON, no markdown fences or other text).\n\n")
 	sb.WriteString("Output format:\n")
-	sb.WriteString("{\n")
-	sb.WriteString("  \"verdict\": \"APPROVE\" or \"REQUEST_CHANGES\",\n")
-	sb.WriteString("  \"summary\": \"Brief overall assessment (1-3 sentences)\",\n")
-	sb.WriteString("  \"findings\": [\n")
-	sb.WriteString("    {\n")
-	sb.WriteString("      \"severity\": \"MAJOR\" or \"MINOR\" or \"NIT\",\n")
-	sb.WriteString("      \"file\": \"path/to/file\",\n")
-	sb.WriteString("      \"line\": <line number from the diff>,\n")
-	sb.WriteString("      \"finding\": \"Description of the issue\"\n")
-	sb.WriteString("    }\n")
-	sb.WriteString("  ],\n")
-	sb.WriteString("  \"recommendation\": \"Full recommendation text explaining your verdict\"\n")
-	sb.WriteString("}\n\n")
-	sb.WriteString("Rules:\n")
-	sb.WriteString("- If there are any MAJOR findings → verdict must be REQUEST_CHANGES\n")
-	sb.WriteString("- If there are no MAJOR findings → verdict should be APPROVE\n")
-	sb.WriteString("- If CI has failed → verdict must be REQUEST_CHANGES with a finding noting the CI failure\n")
-	sb.WriteString("- Be thorough but fair. Don't nitpick style unless it impacts readability significantly.\n")
+	sb.WriteString(outputSchemaJSON)
+	sb.WriteString("\n\n")
+	sb.WriteString(verdictRules)
+	sb.WriteString("\n- Be thorough but fair. Don't nitpick style unless it impacts readability significantly.\n")
 	sb.WriteString("- Line numbers should reference the new file line numbers from the diff headers.\n")
 	sb.WriteString("- If the diff is empty or trivial (only formatting/whitespace), APPROVE with no findings.\n")