docs: add read:user to required token scopes

The read:user scope is needed for the bot to self-request as a
reviewer on PRs. Without it, the bot still functions but cannot
add itself to the reviewer list.

Closes #66

README.md

@@ -9,7 +9,7 @@ AI-powered code review bot for Gitea pull requests. Fetches diff + context, send
 - **Smart budget**: Automatically trims context to fit model token limits
 - **Idempotent reviews**: Posts new review, then cleans up stale ones (one review per bot)
 - **Custom prompts**: Load additional instructions from a file (e.g. security-focused review)
-- **Zero dependencies**: Go stdlib only
+- **Minimal dependencies**: Go stdlib + `gopkg.in/yaml.v3` only
 
 ## Quick Start: Composite Action
 
@@ -329,11 +329,12 @@ All flags have environment variable equivalents:
 ### Token Scopes Required
 
 | Scope | Purpose |
-|-------|---------|
+|-------|--------|
 | `write:issue` | Post and delete reviews |
 | `write:repository` | Read PR diffs, file content, commit statuses |
+| `read:user` | Self-request as reviewer (optional but recommended) |
 
-No `read:user` scope needed — the bot identifies itself from the review response.
+Without `read:user`, the bot still works but cannot add itself to the PR's reviewer list.
 
 ## Development
 

cmd/review-bot/main.go

@@ -79,7 +79,6 @@ func main() {
 	aicoreAPIURL := flag.String("aicore-api-url", envOrDefault("AICORE_API_URL", ""), "SAP AI Core API URL (for provider=aicore)")
 	aicoreResourceGroup := flag.String("aicore-resource-group", envOrDefault("AICORE_RESOURCE_GROUP", "default"), "SAP AI Core resource group (for provider=aicore)")
 
-	flag.Parse()
 	flag.Parse()
 
 	if *versionFlag {
@@ -116,29 +115,7 @@ func main() {
 		os.Exit(1)
 	}
 
-	// Load persona if specified
+	// NOTE: Persona loading deferred until after Gitea client init to support repo personas
-	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 {
@@ -196,6 +173,43 @@ func main() {
 	ctx, cancel := context.WithTimeout(context.Background(), overallTimeout)
 	defer cancel()
 
+	// Load persona if specified (after Gitea client init to support repo personas)
+	var persona *review.Persona
+	if *personaName != "" {
+		// Try loading from repo first, then fall back to built-in
+		repoPersonas, err := review.LoadRepoPersonas(ctx, newGiteaClientAdapter(giteaClient), owner, repoName)
+		if err != nil {
+			slog.Warn("could not load repo personas", "repo", owner+"/"+repoName, "error", err)
+			// Continue with built-in personas only.
+			// NOTE: repoPersonas is nil here, but map indexing on a nil map is safe in Go
+			// (returns the zero value), so the fallback to built-in below works correctly.
+		}
+		if p, ok := repoPersonas[*personaName]; ok {
+			persona = p
+			slog.Info("loaded repo persona", "persona", persona.Name, "display", persona.DisplayName, "repo", owner+"/"+repoName)
+		} else {
+			// Fall back to built-in
+			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)
+	}
+
 	slog.Info("reviewing pull request", "pr", prNumber, "repo", fmt.Sprintf("%s/%s", owner, repoName))
 
 	// Step 1: Fetch PR metadata
@@ -783,3 +797,32 @@ func shouldSkipStaleReview(evaluatedSHA, currentSHA string) bool {
 	}
 	return evaluatedSHA != currentSHA
 }
+
+// giteaClientAdapter adapts gitea.Client to review.GiteaClient interface.
+type giteaClientAdapter struct {
+	client *gitea.Client
+}
+
+func newGiteaClientAdapter(c *gitea.Client) *giteaClientAdapter {
+	return &giteaClientAdapter{client: c}
+}
+
+func (a *giteaClientAdapter) ListContents(ctx context.Context, owner, repo, path string) ([]review.ContentEntry, error) {
+	entries, err := a.client.ListContents(ctx, owner, repo, path)
+	if err != nil {
+		return nil, err
+	}
+	result := make([]review.ContentEntry, len(entries))
+	for i, e := range entries {
+		result[i] = review.ContentEntry{
+			Name: e.Name,
+			Path: e.Path,
+			Type: e.Type,
+		}
+	}
+	return result, nil
+}
+
+func (a *giteaClientAdapter) GetFileContent(ctx context.Context, owner, repo, filepath string) (string, error) {
+	return a.client.GetFileContent(ctx, owner, repo, filepath)
+}

docs/DESIGN-57-yaml-persona.md

@@ -9,7 +9,7 @@ JSON is awkward for persona files that contain multi-line text (identity, severi
 - Backwards compatibility: existing JSON personas must continue to work
 - Security: protect against DoS via deeply nested YAML (AIKIDO-2024-10486)
 - Consistency: use `.yaml` extension (not `.yml`)
-- Library: use `github.com/goccy/go-yaml` v1.16.0+ (actively maintained, security fix applied)
+- Library: use `gopkg.in/yaml.v3` (approved in CONVENTIONS.md) with explicit depth limiting
 
 ## Proposed Approach
 
@@ -34,21 +34,36 @@ func parsePersona(data []byte, source string) (*Persona, error) {
 ### YAML Parsing with Depth Protection
 
 ```go
-func parseYAML(data []byte, source string) (*Persona, error) {
+func unmarshalYAMLWithDepthLimit(data []byte, out any, maxDepth int) error {
-    var p Persona
+    var node yaml.Node
-    // go-yaml has built-in protection against deeply nested structures
+    dec := yaml.NewDecoder(bytes.NewReader(data))
-    // but we add explicit decoder options for defense in depth
+    if err := dec.Decode(&node); err != nil {
-    if err := yaml.Unmarshal(data, &p); err != nil {
+        return err
-        return nil, fmt.Errorf("parse persona %s: %w", source, err)
     }
-    if err := validatePersona(&p, source); err != nil {
+    if err := checkYAMLDepth(&node, 0, maxDepth); err != nil {
-        return nil, err
+        return err
     }
-    return &p, nil
+    return node.Decode(out)
+}
+
+func checkYAMLDepth(node *yaml.Node, depth, maxDepth int) error {
+    if depth > maxDepth {
+        return fmt.Errorf("YAML nesting depth exceeds maximum (%d)", maxDepth)
+    }
+    // Handle alias nodes by following the Alias pointer
+    if node.Kind == yaml.AliasNode && node.Alias != nil {
+        return checkYAMLDepth(node.Alias, depth, maxDepth)
+    }
+    for _, child := range node.Content {
+        if err := checkYAMLDepth(child, depth+1, maxDepth); err != nil {
+            return err
+        }
+    }
+    return nil
 }
 ```
 
-The `goccy/go-yaml` library since v1.16.0 limits nesting depth by default.
+The `gopkg.in/yaml.v3` library does not have built-in depth protection, so we implement explicit depth checking by first decoding into a `yaml.Node`, walking the tree to verify depth (including alias resolution), then decoding into the target struct.
 
 ## State/Data Model
 

review/persona.go

@@ -1,10 +1,12 @@
 package review
 
 import (
+	"bytes"
 	"embed"
 	"encoding/json"
 	"fmt"
 	"os"
+	"sort"
 	"strings"
 	"unicode/utf8"
 
@@ -14,6 +16,18 @@ import (
 //go:embed personas/*.yaml
 var embeddedPersonas embed.FS
 
+// MaxPersonaFileSize is the maximum size for persona files (64 KB).
+// This prevents denial-of-service via excessively large files.
+const MaxPersonaFileSize = 64 * 1024
+
+// MaxYAMLDepth is the maximum nesting depth allowed in YAML persona files.
+// This prevents stack exhaustion from deeply nested structures.
+const MaxYAMLDepth = 20
+
+// MaxYAMLNodes is the maximum number of YAML nodes allowed in persona files.
+// This prevents DoS via wide-but-shallow structures that bypass depth limits.
+const MaxYAMLNodes = 1000
+
 // Persona defines a specialized review role with focused expertise.
 type Persona struct {
 	Name         string   `json:"name" yaml:"name"`
@@ -36,36 +50,50 @@ type Severity struct {
 
 // 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.
+// Files larger than MaxPersonaFileSize are rejected.
+//
+// Symlinks are supported: os.Stat follows symlinks, so a symlink pointing to
+// a regular file will pass the IsRegular() check. Symlinks to non-regular files
+// (directories, FIFOs, devices) are still rejected.
 func LoadPersona(path string) (*Persona, error) {
+	// os.Stat follows symlinks, so symlinks to regular files are supported.
+	// The IsRegular() check operates on the target, not the symlink itself.
+	info, err := os.Stat(path)
+	if err != nil {
+		return nil, fmt.Errorf("read persona file %s: %w", path, err)
+	}
+	if !info.Mode().IsRegular() {
+		return nil, fmt.Errorf("persona file %s is not a regular file", path)
+	}
+	if info.Size() > MaxPersonaFileSize {
+		return nil, fmt.Errorf("persona file %s exceeds maximum size (%d bytes)", path, MaxPersonaFileSize)
+	}
 	data, err := os.ReadFile(path)
 	if err != nil {
 		return nil, fmt.Errorf("read persona file %s: %w", path, err)
 	}
+	// Re-check size after read to defend against TOCTOU races where file
+	// grows between stat and read (e.g., appending process, replaced file).
+	if len(data) > MaxPersonaFileSize {
+		return nil, fmt.Errorf("persona file %s exceeds maximum size (%d bytes)", path, MaxPersonaFileSize)
+	}
 	return parsePersona(data, path)
 }
 
 // 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.
+// Built-in personas are stored in YAML format only (see embed directive).
 func LoadBuiltinPersona(name string) (*Persona, error) {
-	// 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:"+jsonFile)
+	return parsePersona(data, "builtin:"+yamlFile)
 }
 
-// ListBuiltinPersonas returns the names of all built-in personas.
+// ListBuiltinPersonas returns the names of all built-in personas in sorted order.
 // Returns an empty slice if the embedded directory cannot be read.
 func ListBuiltinPersonas() []string {
 	entries, err := embeddedPersonas.ReadDir("personas")
@@ -94,10 +122,11 @@ func ListBuiltinPersonas() []string {
 			seen[personaName] = true
 		}
 	}
-	var names []string
+	names := make([]string, 0, len(seen))
 	for name := range seen {
 		names = append(names, name)
 	}
+	sort.Strings(names)
 	return names
 }
 
@@ -110,10 +139,13 @@ func parsePersona(data []byte, source string) (*Persona, error) {
 	var p Persona
 	var err error
 	if isYAML {
-		// go-yaml v1.16.0+ has built-in protection against deeply nested structures
+		err = unmarshalYAMLWithDepthLimit(data, &p, MaxYAMLDepth)
-		err = yaml.Unmarshal(data, &p)
 	} else {
-		err = json.Unmarshal(data, &p)
+		// Use json.Decoder with DisallowUnknownFields for consistency with
+		// YAML's KnownFields(true) - both reject unknown fields to catch typos.
+		dec := json.NewDecoder(bytes.NewReader(data))
+		dec.DisallowUnknownFields()
+		err = dec.Decode(&p)
 	}
 	if err != nil {
 		return nil, fmt.Errorf("parse persona %s: %w", source, err)
@@ -124,6 +156,81 @@ func parsePersona(data []byte, source string) (*Persona, error) {
 	return &p, nil
 }
 
+// unmarshalYAMLWithDepthLimit unmarshals YAML data with explicit depth limiting
+// and strict field checking. This protects against stack exhaustion from deeply
+// nested structures and catches typos in field names.
+// Multi-document YAML files are rejected to prevent silent data loss.
+func unmarshalYAMLWithDepthLimit(data []byte, out any, maxDepth int) error {
+	// First pass: decode into a yaml.Node to check depth limits and node counts.
+	// This prevents stack exhaustion before we attempt to decode into structs.
+	var node yaml.Node
+	dec := yaml.NewDecoder(bytes.NewReader(data))
+	if err := dec.Decode(&node); err != nil {
+		return err
+	}
+
+	// Reject multi-document YAML files - silently ignoring additional documents
+	// could lead to confusing behavior where users think their changes take effect.
+	var extra yaml.Node
+	if dec.Decode(&extra) == nil {
+		return fmt.Errorf("multi-document YAML is not supported; only single-document files are allowed")
+	}
+
+	nodeCount := 0
+	if err := checkYAMLDepth(&node, 0, maxDepth, MaxYAMLNodes, make(map[*yaml.Node]struct{}), &nodeCount); err != nil {
+		return err
+	}
+
+	// Second pass: decode with strict field checking enabled.
+	// KnownFields(true) rejects unknown keys, catching typos like "focuss" or "identiy".
+	// We must re-decode from the original data because yaml.Node.Decode() doesn't
+	// support the KnownFields option.
+	strictDec := yaml.NewDecoder(bytes.NewReader(data))
+	strictDec.KnownFields(true)
+	return strictDec.Decode(out)
+}
+
+// checkYAMLDepth recursively checks that YAML nodes don't exceed the depth limit
+// or the total node count limit. It also detects alias cycles to prevent infinite
+// recursion from crafted YAML with self-referential aliases.
+func checkYAMLDepth(node *yaml.Node, depth, maxDepth, maxNodes int, seen map[*yaml.Node]struct{}, nodeCount *int) error {
+	if depth > maxDepth {
+		return fmt.Errorf("YAML nesting depth exceeds maximum (%d)", maxDepth)
+	}
+
+	// Track total nodes visited as defense-in-depth against wide-but-shallow attacks.
+	*nodeCount++
+	if *nodeCount > maxNodes {
+		return fmt.Errorf("YAML node count exceeds maximum (%d)", maxNodes)
+	}
+
+	// Cycle detection: if we've seen this node before, we're in a cycle.
+	if _, ok := seen[node]; ok {
+		return nil // Already validated this subtree, skip to avoid infinite recursion.
+	}
+	seen[node] = struct{}{}
+
+	// Handle alias nodes: follow the alias to its anchor target.
+	// Increment depth when following aliases since they expand the effective structure.
+	if node.Kind == yaml.AliasNode && node.Alias != nil {
+		return checkYAMLDepth(node.Alias, depth+1, maxDepth, maxNodes, seen, nodeCount)
+	}
+
+	for _, child := range node.Content {
+		if err := checkYAMLDepth(child, depth+1, maxDepth, maxNodes, seen, nodeCount); err != nil {
+			return err
+		}
+	}
+	return nil
+}
+
+// ParsePersonaBytes parses persona data from bytes with a source label for errors.
+// This is useful for parsing personas fetched from external sources (e.g., Gitea API)
+// without requiring filesystem access. Format is detected by source extension.
+func ParsePersonaBytes(data []byte, source string) (*Persona, error) {
+	return parsePersona(data, source)
+}
+
 func validatePersona(p *Persona, source string) error {
 	if p.Name == "" {
 		return fmt.Errorf("persona %s: name is required", source)

review/persona_test.go

@@ -1,10 +1,13 @@
 package review
 
 import (
+	"fmt"
 	"os"
 	"path/filepath"
 	"strings"
 	"testing"
+
+	"gopkg.in/yaml.v3"
 )
 
 func TestLoadBuiltinPersona(t *testing.T) {
@@ -173,6 +176,7 @@ func TestLoadPersonaFromJSONFile(t *testing.T) {
 		"display_name": "Test Persona",
 		"identity": "You are a test persona.\nMulti-line identity works.",
 		"focus": ["testing", "validation"],
+
 		"ignore": ["nothing"],
 		"severity": {
 			"major": "Big problems",
@@ -449,3 +453,326 @@ severity:
 		t.Errorf("Focus[0] = %q, want %q", p.Focus[0], "item")
 	}
 }
+
+func TestYAMLDeeplyNestedRejection(t *testing.T) {
+	dir := t.TempDir()
+	path := filepath.Join(dir, "deeply-nested.yaml")
+
+	// Build a deeply nested YAML structure that exceeds MaxYAMLDepth (20).
+	// Each level adds 2 to the depth count (key + value mapping).
+	var sb strings.Builder
+	sb.WriteString("name: test\nidentity: test\nnested:\n")
+	indent := "  "
+	for i := 0; i < 25; i++ {
+		sb.WriteString(strings.Repeat(indent, i+1))
+		sb.WriteString(fmt.Sprintf("level%d:\n", i))
+	}
+	sb.WriteString(strings.Repeat(indent, 26))
+	sb.WriteString("value: too-deep\n")
+
+	if err := os.WriteFile(path, []byte(sb.String()), 0644); err != nil {
+		t.Fatalf("failed to write test file: %v", err)
+	}
+
+	_, err := LoadPersona(path)
+	if err == nil {
+		t.Error("expected error for deeply nested YAML, got nil")
+	}
+	if !strings.Contains(err.Error(), "nesting depth exceeds") {
+		t.Errorf("error = %q, want containing 'nesting depth exceeds'", err.Error())
+	}
+}
+
+func TestYAMLFileSizeLimit(t *testing.T) {
+	dir := t.TempDir()
+	path := filepath.Join(dir, "huge.yaml")
+
+	// Create a file larger than MaxPersonaFileSize (64 KB)
+	content := "name: test\nidentity: " + strings.Repeat("x", MaxPersonaFileSize+1) + "\n"
+	if err := os.WriteFile(path, []byte(content), 0644); err != nil {
+		t.Fatalf("failed to write test file: %v", err)
+	}
+
+	_, err := LoadPersona(path)
+	if err == nil {
+		t.Error("expected error for oversized file, got nil")
+	}
+	if !strings.Contains(err.Error(), "exceeds maximum size") {
+		t.Errorf("error = %q, want containing 'exceeds maximum size'", err.Error())
+	}
+}
+
+func TestYAMLAliasCycleDetection(t *testing.T) {
+	// Test that our checkYAMLDepth function handles alias cycles gracefully
+	// by using the seen map to prevent infinite recursion.
+	// We test this directly because go-yaml's parser handles most cycles
+	// at parse time, but we need to ensure our checker is robust.
+
+	// Create a node structure where an alias points to a parent node,
+	// simulating what could happen with malicious input that bypasses
+	// go-yaml's cycle detection.
+	parent := &yaml.Node{
+		Kind: yaml.MappingNode,
+		Content: []*yaml.Node{
+			{Kind: yaml.ScalarNode, Value: "name"},
+			{Kind: yaml.ScalarNode, Value: "test"},
+			{Kind: yaml.ScalarNode, Value: "nested"},
+		},
+	}
+
+	// Create a child that aliases back to the parent (artificial cycle)
+	aliasToParent := &yaml.Node{
+		Kind:  yaml.AliasNode,
+		Alias: parent,
+	}
+	parent.Content = append(parent.Content, aliasToParent)
+
+	nodeCount := 0
+	seen := make(map[*yaml.Node]struct{})
+
+	// This should NOT hang or stack overflow - the seen map prevents infinite recursion
+	err := checkYAMLDepth(parent, 0, MaxYAMLDepth, MaxYAMLNodes, seen, &nodeCount)
+	if err != nil {
+		t.Errorf("unexpected error traversing cyclic structure: %v", err)
+	}
+
+	// Verify we tracked the parent in the seen map
+	if _, ok := seen[parent]; !ok {
+		t.Error("parent node not tracked in seen map")
+	}
+}
+
+func TestYAMLMultiDocumentRejection(t *testing.T) {
+	dir := t.TempDir()
+	path := filepath.Join(dir, "multi.yaml")
+
+	// Multi-document YAML (documents separated by ---)
+	content := `name: first
+identity: first document
+---
+name: second
+identity: second document
+`
+	if err := os.WriteFile(path, []byte(content), 0644); err != nil {
+		t.Fatalf("failed to write test file: %v", err)
+	}
+
+	_, err := LoadPersona(path)
+	if err == nil {
+		t.Error("expected error for multi-document YAML, got nil")
+	}
+	if !strings.Contains(err.Error(), "multi-document") {
+		t.Errorf("error = %q, want containing 'multi-document'", err.Error())
+	}
+}
+
+func TestYAMLNodeCountLimit(t *testing.T) {
+	dir := t.TempDir()
+	path := filepath.Join(dir, "wide.yaml")
+
+	// Build a YAML structure that's shallow but wide - many keys at the same level
+	// to test the node count limit (should exceed MaxYAMLNodes = 1000)
+	var sb strings.Builder
+	sb.WriteString("name: test\nidentity: test\n")
+	for i := 0; i < 600; i++ {
+		sb.WriteString(fmt.Sprintf("key%d: value%d\n", i, i))
+	}
+
+	if err := os.WriteFile(path, []byte(sb.String()), 0644); err != nil {
+		t.Fatalf("failed to write test file: %v", err)
+	}
+
+	_, err := LoadPersona(path)
+	if err == nil {
+		t.Error("expected error for wide YAML exceeding node count, got nil")
+	}
+	if !strings.Contains(err.Error(), "node count exceeds") {
+		t.Errorf("error = %q, want containing 'node count exceeds'", err.Error())
+	}
+}
+
+func TestCheckYAMLDepthCycleDetectionDirect(t *testing.T) {
+	// Direct test of cycle detection in checkYAMLDepth by creating
+	// a node structure with an artificial cycle.
+	// This tests the seen map logic independent of go-yaml's parsing.
+	node := &yaml.Node{
+		Kind: yaml.MappingNode,
+		Content: []*yaml.Node{
+			{Kind: yaml.ScalarNode, Value: "key"},
+			{Kind: yaml.ScalarNode, Value: "value"},
+		},
+	}
+
+	// Create a cycle by making a child reference the parent
+	cycleChild := &yaml.Node{
+		Kind:  yaml.AliasNode,
+		Alias: node, // Points back to the parent
+	}
+	node.Content = append(node.Content,
+		&yaml.Node{Kind: yaml.ScalarNode, Value: "cyclic"},
+		cycleChild,
+	)
+
+	nodeCount := 0
+	seen := make(map[*yaml.Node]struct{})
+	err := checkYAMLDepth(node, 0, MaxYAMLDepth, MaxYAMLNodes, seen, &nodeCount)
+
+	// Should complete without infinite recursion due to cycle detection
+	if err != nil {
+		t.Errorf("unexpected error: %v", err)
+	}
+	// The seen map should contain multiple entries
+	if len(seen) < 2 {
+		t.Errorf("seen map has %d entries, expected at least 2", len(seen))
+	}
+}
+
+func TestListBuiltinPersonasSortedOrder(t *testing.T) {
+	names := ListBuiltinPersonas()
+	if len(names) < 2 {
+		t.Skip("need at least 2 personas to test ordering")
+	}
+
+	// Verify the list is sorted
+	for i := 1; i < len(names); i++ {
+		if names[i-1] > names[i] {
+			t.Errorf("ListBuiltinPersonas not sorted: %q > %q", names[i-1], names[i])
+		}
+	}
+}
+
+func TestYAMLUnknownFieldsRejected(t *testing.T) {
+	tests := []struct {
+		name    string
+		content string
+		wantErr string
+	}{
+		{
+			name: "unknown top-level field",
+			content: `name: test
+identity: test identity
+unknown_field: should fail
+`,
+			wantErr: "unknown_field",
+		},
+		{
+			name: "typo in field name",
+			content: `name: test
+identiy: typo should fail
+`,
+			wantErr: "identiy",
+		},
+		{
+			name: "unknown field in severity",
+			content: `name: test
+identity: test
+severity:
+  major: Major
+  minro: typo
+`,
+			wantErr: "minro",
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			dir := t.TempDir()
+			path := filepath.Join(dir, "unknown.yaml")
+			if err := os.WriteFile(path, []byte(tt.content), 0644); err != nil {
+				t.Fatalf("failed to write test file: %v", err)
+			}
+
+			_, err := LoadPersona(path)
+			if err == nil {
+				t.Errorf("expected error for unknown field %q, got nil", tt.wantErr)
+				return
+			}
+			if !strings.Contains(err.Error(), tt.wantErr) {
+				t.Errorf("error = %q, want containing %q", err.Error(), tt.wantErr)
+			}
+		})
+	}
+}
+
+func TestJSONUnknownFieldsRejected(t *testing.T) {
+	tests := []struct {
+		name    string
+		content string
+		wantErr string
+	}{
+		{
+			name: "unknown top-level field",
+			content: `{
+				"name": "test",
+				"identity": "test identity",
+				"unknown_field": "should fail"
+			}`,
+			wantErr: "unknown_field",
+		},
+		{
+			name: "typo in field name",
+			content: `{
+				"name": "test",
+				"identiy": "typo should fail"
+			}`,
+			wantErr: "identiy",
+		},
+		{
+			name: "unknown field in severity",
+			content: `{
+				"name": "test",
+				"identity": "test",
+				"severity": {
+					"major": "ok",
+					"miner": "typo"
+				}
+			}`,
+			wantErr: "miner",
+		},
+	}
+
+	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.content), 0644); err != nil {
+				t.Fatalf("failed to write test file: %v", err)
+			}
+
+			_, err := LoadPersona(path)
+			if err == nil {
+				t.Fatal("expected error for unknown field, got nil")
+			}
+			if !strings.Contains(err.Error(), tt.wantErr) {
+				t.Errorf("error = %q, want to contain %q", err.Error(), tt.wantErr)
+			}
+		})
+	}
+}
+
+func TestLoadPersonaSymlink(t *testing.T) {
+	// Create a regular persona file
+	dir := t.TempDir()
+	realFile := filepath.Join(dir, "real.yaml")
+	content := `name: test
+identity: test identity
+`
+	if err := os.WriteFile(realFile, []byte(content), 0644); err != nil {
+		t.Fatalf("failed to write test file: %v", err)
+	}
+
+	// Create a symlink to it
+	symlink := filepath.Join(dir, "link.yaml")
+	if err := os.Symlink(realFile, symlink); err != nil {
+		t.Fatalf("failed to create symlink: %v", err)
+	}
+
+	// LoadPersona should work via symlink
+	p, err := LoadPersona(symlink)
+	if err != nil {
+		t.Fatalf("LoadPersona via symlink failed: %v", err)
+	}
+	if p.Name != "test" {
+		t.Errorf("Name = %q, want %q", p.Name, "test")
+	}
+}

review/repo_persona.go

@@ -0,0 +1,150 @@
+package review
+
+import (
+	"context"
+	"log/slog"
+	"strings"
+)
+
+// RepoPersonaPath is the directory path where repo-specific personas are stored.
+const RepoPersonaPath = ".review-bot/personas"
+
+// GiteaClient defines the subset of gitea.Client methods needed for loading repo personas.
+// This interface allows for easier testing and decouples the review package from gitea.
+type GiteaClient interface {
+	ListContents(ctx context.Context, owner, repo, path string) ([]ContentEntry, error)
+	GetFileContent(ctx context.Context, owner, repo, filepath string) (string, error)
+}
+
+// ContentEntry represents a file or directory entry from the contents API.
+// This mirrors gitea.ContentEntry to avoid import cycles.
+type ContentEntry struct {
+	Name string `json:"name"`
+	Path string `json:"path"`
+	Type string `json:"type"` // "file" or "dir"
+}
+
+// LoadRepoPersonas fetches personas from a repository's .review-bot/personas/ directory.
+// Returns an empty map (not nil) if the directory doesn't exist or is empty.
+// Individual parse failures are logged and skipped; the remaining personas are still returned.
+// Auth errors and other non-404 errors are propagated.
+// Files exceeding MaxPersonaFileSize are rejected to prevent resource exhaustion.
+func LoadRepoPersonas(ctx context.Context, client GiteaClient, owner, repo string) (map[string]*Persona, error) {
+	result := make(map[string]*Persona)
+
+	entries, err := client.ListContents(ctx, owner, repo, RepoPersonaPath)
+	if err != nil {
+		// Check if this is a 404 (directory doesn't exist) - expected case
+		if isNotFoundError(err) {
+			slog.Debug("no repo personas directory found", "repo", owner+"/"+repo)
+			return result, nil
+		}
+		// Other errors (auth, server) should propagate
+		return nil, err
+	}
+
+	if len(entries) == 0 {
+		slog.Debug("repo personas directory is empty", "repo", owner+"/"+repo)
+		return result, nil
+	}
+
+	for _, entry := range entries {
+		if entry.Type != "file" {
+			continue
+		}
+		// Only process YAML files
+		if !isYAMLFile(entry.Name) {
+			continue
+		}
+
+		content, err := client.GetFileContent(ctx, owner, repo, entry.Path)
+		if err != nil {
+			slog.Warn("could not fetch repo persona file",
+				"file", entry.Path,
+				"repo", owner+"/"+repo,
+				"error", err)
+			continue
+		}
+
+		// Enforce size limit before parsing to prevent resource exhaustion
+		if len(content) > MaxPersonaFileSize {
+			slog.Warn("repo persona file exceeds maximum size",
+				"file", entry.Path,
+				"repo", owner+"/"+repo,
+				"size", len(content),
+				"max", MaxPersonaFileSize)
+			continue
+		}
+
+		persona, err := ParsePersonaBytes([]byte(content), entry.Path)
+		if err != nil {
+			slog.Warn("could not parse repo persona file",
+				"file", entry.Path,
+				"repo", owner+"/"+repo,
+				"error", err)
+			continue
+		}
+
+		result[persona.Name] = persona
+		slog.Debug("loaded repo persona",
+			"name", persona.Name,
+			"file", entry.Path,
+			"repo", owner+"/"+repo)
+	}
+
+	return result, nil
+}
+
+// MergePersonas combines built-in personas with repo personas.
+// Repo personas take precedence on name collision.
+// Returns a new map; inputs are not modified.
+func MergePersonas(builtin, repo map[string]*Persona) map[string]*Persona {
+	result := make(map[string]*Persona, len(builtin)+len(repo))
+
+	// Copy built-in personas first
+	for name, p := range builtin {
+		result[name] = p
+	}
+
+	// Overlay repo personas (override on collision)
+	for name, p := range repo {
+		if _, exists := result[name]; exists {
+			slog.Debug("repo persona overrides built-in", "name", name)
+		}
+		result[name] = p
+	}
+
+	return result
+}
+
+// GetBuiltinPersonasMap returns all built-in personas as a map keyed by name.
+// Returns an empty map (not nil) if loading fails.
+func GetBuiltinPersonasMap() map[string]*Persona {
+	result := make(map[string]*Persona)
+	for _, name := range ListBuiltinPersonas() {
+		p, err := LoadBuiltinPersona(name)
+		if err != nil {
+			slog.Warn("could not load built-in persona", "name", name, "error", err)
+			continue
+		}
+		result[name] = p
+	}
+	return result
+}
+
+// isYAMLFile checks if a filename has a YAML extension.
+func isYAMLFile(name string) bool {
+	lower := strings.ToLower(name)
+	return strings.HasSuffix(lower, ".yaml") || strings.HasSuffix(lower, ".yml")
+}
+
+// isNotFoundError checks if an error represents a 404 response.
+// This uses a specific "HTTP 404" substring match rather than a generic "not found"
+// match to avoid masking authentication failures or transport errors that might
+// contain "not found" in their message.
+func isNotFoundError(err error) bool {
+	if err == nil {
+		return false
+	}
+	return strings.Contains(err.Error(), "HTTP 404")
+}

review/repo_persona_test.go

@@ -0,0 +1,443 @@
+package review
+
+import (
+	"context"
+	"errors"
+	"strings"
+	"testing"
+)
+
+func TestParsePersonaBytes(t *testing.T) {
+	tests := []struct {
+		name       string
+		data       string
+		source     string
+		wantName   string
+		wantErr    string
+	}{
+		{
+			name: "valid yaml",
+			data: `name: test
+identity: test identity
+focus:
+  - testing
+`,
+			source:   "test.yaml",
+			wantName: "test",
+		},
+		{
+			name:    "missing name",
+			data:    "identity: test\n",
+			source:  "test.yaml",
+			wantErr: "name is required",
+		},
+		{
+			name:    "invalid yaml",
+			data:    "not: valid:\n  yaml: [broken",
+			source:  "test.yaml",
+			wantErr: "parse",
+		},
+		{
+			name: "json format by extension",
+			data: `{"name": "jsontest", "identity": "json identity"}`,
+			source:   "test.json",
+			wantName: "jsontest",
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			p, err := ParsePersonaBytes([]byte(tt.data), tt.source)
+			if tt.wantErr != "" {
+				if err == nil {
+					t.Fatalf("expected error containing %q, got nil", tt.wantErr)
+				}
+				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)
+			}
+			if p.Name != tt.wantName {
+				t.Errorf("Name = %q, want %q", p.Name, tt.wantName)
+			}
+		})
+	}
+}
+
+// mockGiteaClient implements GiteaClient for testing.
+type mockGiteaClient struct {
+	contents map[string][]ContentEntry // path -> entries
+	files    map[string]string         // path -> content
+	listErr  error
+	fileErr  map[string]error // path -> error
+}
+
+func (m *mockGiteaClient) ListContents(ctx context.Context, owner, repo, path string) ([]ContentEntry, error) {
+	if m.listErr != nil {
+		return nil, m.listErr
+	}
+	entries, ok := m.contents[path]
+	if !ok {
+		return nil, errors.New("list contents .review-bot/personas: HTTP 404: not found")
+	}
+	return entries, nil
+}
+
+func (m *mockGiteaClient) GetFileContent(ctx context.Context, owner, repo, filepath string) (string, error) {
+	if m.fileErr != nil {
+		if err, ok := m.fileErr[filepath]; ok {
+			return "", err
+		}
+	}
+	content, ok := m.files[filepath]
+	if !ok {
+		return "", errors.New("HTTP 404: file not found")
+	}
+	return content, nil
+}
+
+func TestLoadRepoPersonas(t *testing.T) {
+	ctx := context.Background()
+
+	t.Run("directory not found returns empty map", func(t *testing.T) {
+		client := &mockGiteaClient{} // No contents configured -> 404
+		personas, err := LoadRepoPersonas(ctx, client, "owner", "repo")
+		if err != nil {
+			t.Fatalf("unexpected error: %v", err)
+		}
+		if personas == nil {
+			t.Error("expected empty map, got nil")
+		}
+		if len(personas) != 0 {
+			t.Errorf("expected 0 personas, got %d", len(personas))
+		}
+	})
+
+	t.Run("empty directory returns empty map", func(t *testing.T) {
+		client := &mockGiteaClient{
+			contents: map[string][]ContentEntry{
+				RepoPersonaPath: {},
+			},
+		}
+		personas, err := LoadRepoPersonas(ctx, client, "owner", "repo")
+		if err != nil {
+			t.Fatalf("unexpected error: %v", err)
+		}
+		if len(personas) != 0 {
+			t.Errorf("expected 0 personas, got %d", len(personas))
+		}
+	})
+
+	t.Run("loads valid personas", func(t *testing.T) {
+		client := &mockGiteaClient{
+			contents: map[string][]ContentEntry{
+				RepoPersonaPath: {
+					{Name: "trading.yaml", Path: ".review-bot/personas/trading.yaml", Type: "file"},
+					{Name: "crypto.yaml", Path: ".review-bot/personas/crypto.yaml", Type: "file"},
+				},
+			},
+			files: map[string]string{
+				".review-bot/personas/trading.yaml": `name: trading
+display_name: Trading Expert
+identity: You are a trading expert.
+focus:
+  - order handling
+  - risk management
+`,
+				".review-bot/personas/crypto.yaml": `name: crypto
+display_name: Crypto Expert
+identity: You are a cryptography expert.
+focus:
+  - key management
+  - encryption
+`,
+			},
+		}
+		personas, err := LoadRepoPersonas(ctx, client, "owner", "repo")
+		if err != nil {
+			t.Fatalf("unexpected error: %v", err)
+		}
+		if len(personas) != 2 {
+			t.Fatalf("expected 2 personas, got %d", len(personas))
+		}
+		if personas["trading"] == nil {
+			t.Error("expected trading persona")
+		}
+		if personas["crypto"] == nil {
+			t.Error("expected crypto persona")
+		}
+		if personas["trading"].DisplayName != "Trading Expert" {
+			t.Errorf("trading display name = %q, want %q", personas["trading"].DisplayName, "Trading Expert")
+		}
+	})
+
+	t.Run("skips invalid persona files", func(t *testing.T) {
+		client := &mockGiteaClient{
+			contents: map[string][]ContentEntry{
+				RepoPersonaPath: {
+					{Name: "valid.yaml", Path: ".review-bot/personas/valid.yaml", Type: "file"},
+					{Name: "invalid.yaml", Path: ".review-bot/personas/invalid.yaml", Type: "file"},
+				},
+			},
+			files: map[string]string{
+				".review-bot/personas/valid.yaml": `name: valid
+identity: Valid persona
+`,
+				".review-bot/personas/invalid.yaml": "not valid yaml: [broken",
+			},
+		}
+		personas, err := LoadRepoPersonas(ctx, client, "owner", "repo")
+		if err != nil {
+			t.Fatalf("unexpected error: %v", err)
+		}
+		// Should have the valid one, skip the invalid
+		if len(personas) != 1 {
+			t.Fatalf("expected 1 persona (skipped invalid), got %d", len(personas))
+		}
+		if personas["valid"] == nil {
+			t.Error("expected valid persona")
+		}
+	})
+
+	t.Run("skips non-yaml files", func(t *testing.T) {
+		client := &mockGiteaClient{
+			contents: map[string][]ContentEntry{
+				RepoPersonaPath: {
+					{Name: "persona.yaml", Path: ".review-bot/personas/persona.yaml", Type: "file"},
+					{Name: "README.md", Path: ".review-bot/personas/README.md", Type: "file"},
+					{Name: "notes.txt", Path: ".review-bot/personas/notes.txt", Type: "file"},
+				},
+			},
+			files: map[string]string{
+				".review-bot/personas/persona.yaml": `name: test
+identity: Test persona
+`,
+				".review-bot/personas/README.md": "# Personas\n\nPut your personas here.",
+			},
+		}
+		personas, err := LoadRepoPersonas(ctx, client, "owner", "repo")
+		if err != nil {
+			t.Fatalf("unexpected error: %v", err)
+		}
+		if len(personas) != 1 {
+			t.Fatalf("expected 1 persona (yaml only), got %d", len(personas))
+		}
+	})
+
+	t.Run("skips subdirectories", func(t *testing.T) {
+		client := &mockGiteaClient{
+			contents: map[string][]ContentEntry{
+				RepoPersonaPath: {
+					{Name: "persona.yaml", Path: ".review-bot/personas/persona.yaml", Type: "file"},
+					{Name: "subdir", Path: ".review-bot/personas/subdir", Type: "dir"},
+				},
+			},
+			files: map[string]string{
+				".review-bot/personas/persona.yaml": `name: test
+identity: Test persona
+`,
+			},
+		}
+		personas, err := LoadRepoPersonas(ctx, client, "owner", "repo")
+		if err != nil {
+			t.Fatalf("unexpected error: %v", err)
+		}
+		if len(personas) != 1 {
+			t.Fatalf("expected 1 persona (files only), got %d", len(personas))
+		}
+	})
+
+	t.Run("propagates auth errors", func(t *testing.T) {
+		client := &mockGiteaClient{
+			listErr: errors.New("HTTP 401: unauthorized"),
+		}
+		_, err := LoadRepoPersonas(ctx, client, "owner", "repo")
+		if err == nil {
+			t.Fatal("expected error for auth failure")
+		}
+		if !strings.Contains(err.Error(), "401") {
+			t.Errorf("error = %q, want containing '401'", err.Error())
+		}
+	})
+
+	t.Run("skips files that fail to fetch", func(t *testing.T) {
+		client := &mockGiteaClient{
+			contents: map[string][]ContentEntry{
+				RepoPersonaPath: {
+					{Name: "good.yaml", Path: ".review-bot/personas/good.yaml", Type: "file"},
+					{Name: "bad.yaml", Path: ".review-bot/personas/bad.yaml", Type: "file"},
+				},
+			},
+			files: map[string]string{
+				".review-bot/personas/good.yaml": `name: good
+identity: Good persona
+`,
+			},
+			fileErr: map[string]error{
+				".review-bot/personas/bad.yaml": errors.New("HTTP 500: internal server error"),
+			},
+		}
+		personas, err := LoadRepoPersonas(ctx, client, "owner", "repo")
+		if err != nil {
+			t.Fatalf("unexpected error: %v", err)
+		}
+		if len(personas) != 1 {
+			t.Fatalf("expected 1 persona (skipped failed fetch), got %d", len(personas))
+		}
+	})
+
+	t.Run("skips oversized files", func(t *testing.T) {
+		// Create a content string that exceeds MaxPersonaFileSize (64KB)
+		oversizedContent := strings.Repeat("a", MaxPersonaFileSize+1)
+		client := &mockGiteaClient{
+			contents: map[string][]ContentEntry{
+				RepoPersonaPath: {
+					{Name: "normal.yaml", Path: ".review-bot/personas/normal.yaml", Type: "file"},
+					{Name: "huge.yaml", Path: ".review-bot/personas/huge.yaml", Type: "file"},
+				},
+			},
+			files: map[string]string{
+				".review-bot/personas/normal.yaml": `name: normal
+identity: Normal sized persona
+`,
+				".review-bot/personas/huge.yaml": oversizedContent,
+			},
+		}
+		personas, err := LoadRepoPersonas(ctx, client, "owner", "repo")
+		if err != nil {
+			t.Fatalf("unexpected error: %v", err)
+		}
+		// Should have the normal one, skip the oversized
+		if len(personas) != 1 {
+			t.Fatalf("expected 1 persona (skipped oversized), got %d", len(personas))
+		}
+		if personas["normal"] == nil {
+			t.Error("expected normal persona")
+		}
+	})
+}
+
+func TestMergePersonas(t *testing.T) {
+	builtin := map[string]*Persona{
+		"security": {Name: "security", Identity: "Built-in security"},
+		"docs":     {Name: "docs", Identity: "Built-in docs"},
+	}
+	repo := map[string]*Persona{
+		"security": {Name: "security", Identity: "Repo security override"},
+		"trading":  {Name: "trading", Identity: "Repo trading"},
+	}
+
+	merged := MergePersonas(builtin, repo)
+
+	t.Run("repo overrides builtin on collision", func(t *testing.T) {
+		if merged["security"].Identity != "Repo security override" {
+			t.Errorf("security identity = %q, want repo override", merged["security"].Identity)
+		}
+	})
+
+	t.Run("builtin preserved when no collision", func(t *testing.T) {
+		if merged["docs"].Identity != "Built-in docs" {
+			t.Errorf("docs identity = %q, want built-in", merged["docs"].Identity)
+		}
+	})
+
+	t.Run("repo-only persona added", func(t *testing.T) {
+		if merged["trading"] == nil {
+			t.Error("expected trading persona from repo")
+		}
+		if merged["trading"].Identity != "Repo trading" {
+			t.Errorf("trading identity = %q, want repo", merged["trading"].Identity)
+		}
+	})
+
+	t.Run("original maps not modified", func(t *testing.T) {
+		if builtin["trading"] != nil {
+			t.Error("builtin map was modified")
+		}
+		if len(repo) != 2 {
+			t.Error("repo map was modified")
+		}
+	})
+}
+
+func TestGetBuiltinPersonasMap(t *testing.T) {
+	personas := GetBuiltinPersonasMap()
+
+	if len(personas) == 0 {
+		t.Fatal("expected at least one built-in persona")
+	}
+
+	// Verify expected personas exist
+	expected := []string{"security", "architect", "docs"}
+	for _, name := range expected {
+		if personas[name] == nil {
+			t.Errorf("expected built-in persona %q", name)
+		}
+	}
+
+	// Verify personas are valid
+	for name, p := range personas {
+		if p.Name != name {
+			t.Errorf("persona %q has mismatched name %q", name, p.Name)
+		}
+		if p.Identity == "" {
+			t.Errorf("persona %q has empty identity", name)
+		}
+	}
+}
+
+func TestIsYAMLFile(t *testing.T) {
+	tests := []struct {
+		name string
+		want bool
+	}{
+		{"test.yaml", true},
+		{"test.yml", true},
+		{"test.YAML", true},
+		{"test.YML", true},
+		{"test.json", false},
+		{"test.md", false},
+		{"test.txt", false},
+		{"yaml", false},
+		{"yaml.md", false},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			if got := isYAMLFile(tt.name); got != tt.want {
+				t.Errorf("isYAMLFile(%q) = %v, want %v", tt.name, got, tt.want)
+			}
+		})
+	}
+}
+
+func TestIsNotFoundError(t *testing.T) {
+	tests := []struct {
+		err  error
+		want bool
+	}{
+		{nil, false},
+		{errors.New("HTTP 404: not found"), true},
+		{errors.New("HTTP 404"), true},
+		// Intentionally false: generic "not found" could mask auth/transport errors.
+		// Only explicit HTTP 404 responses should be treated as "directory doesn't exist".
+		{errors.New("something not found"), false},
+		{errors.New("HTTP 401: unauthorized"), false},
+		{errors.New("connection refused"), false},
+	}
+
+	for _, tt := range tests {
+		name := "nil"
+		if tt.err != nil {
+			name = tt.err.Error()
+		}
+		t.Run(name, func(t *testing.T) {
+			if got := isNotFoundError(tt.err); got != tt.want {
+				t.Errorf("isNotFoundError(%v) = %v, want %v", tt.err, got, tt.want)
+			}
+		})
+	}
+}