fix: address review feedback on PR #106

- Remove unused envOrDefaultBool function and its test (Sonnet #3266 NIT)
- Replace Unicode em dashes with ASCII in slog messages (GPT #3267 NIT)
- Add scheme validation for vcsURL before embedding in Markdown link
  (Security #3269 MINOR — defense-in-depth against unsafe schemes)
- Extract ReviewerSelfRequester interface to remove concrete gitea.Adapter
  dependency from main's self-reviewer path (Sonnet #3266 NIT)
- Add compile-time conformance assertion and test for Adapter.RequestReviewerSelf

CONVENTIONS.md

@@ -9,7 +9,7 @@
 
 | Package | Use Case | Scope |
 |---------|----------|-------|
-| `gopkg.in/yaml.v3` | YAML parsing (persona files, config) | production |
+| `github.com/goccy/go-yaml` | YAML parsing and AST inspection (subpkgs: `ast`, `parser`) | production |
 | `github.com/google/go-cmp` | Test comparisons (`cmp.Diff`) | test only |
 
 **Any import not in this table or the Go standard library is forbidden.**

cmd/review-bot/main.go

@@ -2,6 +2,7 @@ package main
 
 import (
 	"context"
+	"errors"
 	"flag"
 	"fmt"
 	"log/slog"
@@ -13,6 +14,7 @@ import (
 
 	"gitea.weiker.me/rodin/review-bot/budget"
 	"gitea.weiker.me/rodin/review-bot/gitea"
+	"gitea.weiker.me/rodin/review-bot/github"
 	"gitea.weiker.me/rodin/review-bot/llm"
 	"gitea.weiker.me/rodin/review-bot/review"
 	"gitea.weiker.me/rodin/review-bot/vcs"
@@ -54,19 +56,22 @@ func main() {
 	// Logging flags
 	logFormat := flag.String("log-format", envOrDefault("LOG_FORMAT", "text"), "Log output format: text or json")
 	verbosity := flag.String("verbosity", envOrDefault("LOG_VERBOSITY", "info"), "Log verbosity: debug, info, warn, error")
-	// CLI flags
+	// VCS flags
-	giteaURL := flag.String("gitea-url", envOrDefault("GITEA_URL", envOrDefault("GITHUB_SERVER_URL", "")), "Gitea instance URL")
+	provider := flag.String("provider", envOrDefault("VCS_PROVIDER", "gitea"), "VCS provider: gitea or github")
-	repo := flag.String("repo", envOrDefault("GITEA_REPO", envOrDefault("GITHUB_REPOSITORY", "")), "Repository (owner/name)")
+	baseURL := flag.String("base-url", envOrDefault("VCS_BASE_URL", ""), "VCS API base URL (for github provider; defaults to https://api.github.com)")
+	vcsURL := flag.String("vcs-url", envOrDefault("VCS_URL", envOrDefault("GITEA_URL", envOrDefault("GITHUB_SERVER_URL", ""))), "VCS instance URL (Gitea) [deprecated alias: --gitea-url]")
+	// Keep --gitea-url as backward-compatible alias (flag package doesn't support aliases natively, handle below)
+	repo := flag.String("repo", envOrDefault("VCS_REPO", envOrDefault("GITEA_REPO", envOrDefault("GITHUB_REPOSITORY", ""))), "Repository (owner/name)")
 	prNum := flag.String("pr", envOrDefault("PR_NUMBER", ""), "Pull request number")
 	reviewerName := flag.String("reviewer-name", envOrDefault("REVIEWER_NAME", ""), "Reviewer display name")
-	reviewerToken := flag.String("reviewer-token", envOrDefault("REVIEWER_TOKEN", ""), "Gitea token for posting review")
+	reviewerToken := flag.String("reviewer-token", envOrDefault("REVIEWER_TOKEN", ""), "VCS token for posting review")
 	llmBaseURL := flag.String("llm-base-url", envOrDefault("LLM_BASE_URL", ""), "LLM API base URL")
 	llmAPIKey := flag.String("llm-api-key", envOrDefault("LLM_API_KEY", ""), "LLM API key")
 	llmModel := flag.String("llm-model", envOrDefault("LLM_MODEL", ""), "LLM model name")
 	conventionsFile := flag.String("conventions-file", envOrDefault("CONVENTIONS_FILE", ""), "Conventions file path in repo (e.g. CLAUDE.md)")
 	systemPromptFile := flag.String("system-prompt-file", envOrDefault("SYSTEM_PROMPT_FILE", ""), "Local file with additional system prompt instructions")
 	patternsRepo := flag.String("patterns-repo", envOrDefault("PATTERNS_REPO", ""), "Repo with language patterns (e.g. rodin/elixir-patterns)")
-	patternsFiles := flag.String("patterns-files", envOrDefault("PATTERNS_FILES", "README.md"), "Comma-separated file paths to fetch from patterns repo")
+	patternsFiles := flag.String("patterns-files", envOrDefault("PATTERNS_FILES", ""), "Comma-separated file paths to fetch from patterns repo (empty = all files)")
 	dryRun := flag.Bool("dry-run", false, "Print review to stdout instead of posting")
 	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)")
@@ -80,6 +85,18 @@ 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)")
 
+	// Register --gitea-url as a backward-compatible alias for --vcs-url.
+	// StringVar shares the *string pointer with vcsURL, so whichever flag is
+	// set last by flag.Parse wins — both point to the same underlying value.
+	// NOTE: If a user passes both --vcs-url and --gitea-url, the last one on
+	// the command line takes effect (standard flag package behavior). This is
+	// acceptable since --gitea-url is deprecated and both serve the same purpose.
+	//
+	// ORDERING: This must remain AFTER vcsURL's flag.String declaration and BEFORE
+	// flag.Parse(). The *vcsURL dereference captures the env-var-resolved default
+	// at registration time; moving flag.Parse() above this line would break it.
+	flag.StringVar(vcsURL, "gitea-url", *vcsURL, "Deprecated: use --vcs-url instead")
+
 	flag.Parse()
 
 	if *versionFlag {
@@ -92,12 +109,25 @@ func main() {
 
 	slog.Info("review-bot starting", "version", version)
 
+	// Validate VCS provider
+	switch *provider {
+	case "gitea", "github":
+		// valid
+	default:
+		fmt.Fprintf(os.Stderr, "Error: invalid --provider %q (valid: gitea, github)\n", *provider)
+		os.Exit(1)
+	}
+
 	// Validate required fields
-	// For aicore provider, llm-base-url and llm-api-key are not required
 	isAICore := llm.Provider(*llmProvider) == llm.ProviderAICore
-	if *giteaURL == "" || *repo == "" || *prNum == "" || *reviewerToken == "" || *llmModel == "" {
+	if *repo == "" || *prNum == "" || *reviewerToken == "" || *llmModel == "" {
 		fmt.Fprintf(os.Stderr, "Error: missing required flags or environment variables\n\n")
-		fmt.Fprintf(os.Stderr, "Required: --gitea-url, --repo, --pr, --reviewer-token, --llm-model\n")
+		fmt.Fprintf(os.Stderr, "Required: --repo, --pr, --reviewer-token, --llm-model\n")
+		os.Exit(1)
+	}
+	// --vcs-url is required only for gitea provider
+	if *provider == "gitea" && *vcsURL == "" {
+		fmt.Fprintf(os.Stderr, "Error: --vcs-url (or --gitea-url) is required for provider=gitea\n")
 		os.Exit(1)
 	}
 	if !isAICore && (*llmBaseURL == "" || *llmAPIKey == "") {
@@ -116,8 +146,6 @@ func main() {
 		os.Exit(1)
 	}
 
-	// NOTE: Persona loading deferred until after Gitea client init to support repo personas
-
 	// Validate reviewer-name: only safe characters allowed in sentinel
 	if err := validateReviewerName(*reviewerName); err != nil {
 		slog.Error("invalid reviewer name", "error", err)
@@ -139,8 +167,22 @@ func main() {
 		os.Exit(1)
 	}
 
-	// Initialize clients
+	// Initialize VCS client
-	giteaClient := gitea.NewClient(*giteaURL, *reviewerToken)
+	var client vcs.Client
+	switch *provider {
+	case "gitea":
+		giteaClient := gitea.NewClient(*vcsURL, *reviewerToken)
+		client = gitea.NewAdapter(giteaClient)
+	case "github":
+		ghBaseURL := *baseURL
+		if ghBaseURL == "" {
+			ghBaseURL = "https://api.github.com"
+		}
+		client = github.NewClient(*reviewerToken, ghBaseURL)
+	}
+	slog.Info("VCS client initialized", "provider", *provider)
+
+	// Initialize LLM client
 	llmClient := llm.NewClient(*llmBaseURL, *llmAPIKey, *llmModel)
 	if *llmTemp < 0 || *llmTemp > 2 {
 		slog.Error("invalid LLM temperature", "temperature", *llmTemp, "range", "0-2")
@@ -174,16 +216,13 @@ func main() {
 	ctx, cancel := context.WithTimeout(context.Background(), overallTimeout)
 	defer cancel()
 
-	// Load persona if specified (after Gitea client init to support repo personas)
+	// Load persona if specified
 	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)
+		repoPersonas, err := review.LoadRepoPersonas(ctx, client, 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
@@ -214,7 +253,7 @@ func main() {
 	slog.Info("reviewing pull request", "pr", prNumber, "repo", fmt.Sprintf("%s/%s", owner, repoName))
 
 	// Step 1: Fetch PR metadata
-	pr, err := giteaClient.GetPullRequest(ctx, owner, repoName, prNumber)
+	pr, err := client.GetPullRequest(ctx, owner, repoName, prNumber)
 	if err != nil {
 		slog.Error("failed to fetch PR", "pr", prNumber, "error", err)
 		os.Exit(1)
@@ -222,7 +261,7 @@ func main() {
 	slog.Info("fetched PR metadata", "pr", prNumber, "title", pr.Title)
 
 	// Step 2: Fetch diff
-	diff, err := giteaClient.GetPullRequestDiff(ctx, owner, repoName, prNumber)
+	diff, err := client.GetPullRequestDiff(ctx, owner, repoName, prNumber)
 	if err != nil {
 		slog.Error("failed to fetch diff", "pr", prNumber, "error", err)
 		os.Exit(1)
@@ -231,21 +270,21 @@ func main() {
 
 	// Step 3: Fetch full file content for modified files
 	fileContext := ""
-	files, err := giteaClient.GetPullRequestFiles(ctx, owner, repoName, prNumber)
+	files, err := client.GetPullRequestFiles(ctx, owner, repoName, prNumber)
 	if err != nil {
 		slog.Warn("could not fetch PR files list", "pr", prNumber, "error", err)
 	} else {
-		fileContext = fetchFileContext(ctx, giteaClient, owner, repoName, pr.Head.Ref, files)
+		fileContext = fetchFileContext(ctx, client, owner, repoName, pr.Head.Ref, files)
 		slog.Debug("fetched file context", "files", len(files))
 	}
 
 	// Step 4: Check CI status
 	ciPassed := true
 	ciDetails := ""
-	if pr.Head.Sha != "" {
+	if pr.Head.SHA != "" {
-		statuses, err := giteaClient.GetCommitStatuses(ctx, owner, repoName, pr.Head.Sha)
+		statuses, err := client.GetCommitStatuses(ctx, owner, repoName, pr.Head.SHA)
 		if err != nil {
-			slog.Warn("could not fetch CI status", "sha", pr.Head.Sha, "error", err)
+			slog.Warn("could not fetch CI status", "sha", pr.Head.SHA, "error", err)
 		} else {
 			ciPassed, ciDetails = evaluateCIStatus(statuses)
 			slog.Info("CI status checked", "passed", ciPassed)
@@ -255,7 +294,7 @@ func main() {
 	// Step 5: Load conventions file if specified
 	conventions := ""
 	if *conventionsFile != "" {
-		content, err := giteaClient.GetFileContent(ctx, owner, repoName, *conventionsFile)
+		content, err := client.GetFileContent(ctx, owner, repoName, *conventionsFile, "")
 		if err != nil {
 			slog.Warn("could not load conventions file", "file", *conventionsFile, "error", err)
 		} else {
@@ -267,7 +306,7 @@ func main() {
 	// Step 6: Load patterns from external repo if specified
 	patterns := ""
 	if *patternsRepo != "" {
-		patterns = fetchPatterns(ctx, giteaClient, *patternsRepo, *patternsFiles)
+		patterns = fetchPatterns(ctx, client, *patternsRepo, *patternsFiles)
 		slog.Debug("loaded patterns", "repo", *patternsRepo, "bytes", len(patterns))
 	}
 
@@ -360,15 +399,16 @@ func main() {
 	}
 
 	// Add commit footer so readers know which commit was evaluated
-	if pr.Head.Sha != "" {
+	if pr.Head.SHA != "" {
-		shortSHA := pr.Head.Sha
+		shortSHA := pr.Head.SHA
 		if len(shortSHA) > 8 {
 			shortSHA = shortSHA[:8]
 		}
 		reviewBody += fmt.Sprintf("\n\n---\n*Evaluated against %s*", shortSHA)
 	}
 
-	event := review.GiteaEvent(result.Verdict)
+	// Map verdict to canonical review event
+	event := verdictToEvent(result.Verdict)
 
 	if *dryRun {
 		fmt.Println("--- DRY RUN ---")
@@ -380,34 +420,40 @@ func main() {
 	sentinel := fmt.Sprintf("<!-- review-bot:%s -->", *reviewerName)
 
 	// Stale check: verify HEAD hasn't moved since we started
-	evaluatedSHA := pr.Head.Sha
+	evaluatedSHA := pr.Head.SHA
 	var currentSHA string
-	currentPR, err := giteaClient.GetPullRequest(ctx, owner, repoName, prNumber)
+	currentPR, err := client.GetPullRequest(ctx, owner, repoName, prNumber)
 	if err != nil {
 		slog.Warn("could not re-fetch PR for stale check", "pr", prNumber, "error", err)
-		// currentSHA stays empty — shouldSkipStaleReview will return false
 	} else {
-		currentSHA = currentPR.Head.Sha
+		currentSHA = currentPR.Head.SHA
 	}
 	if shouldSkipStaleReview(evaluatedSHA, currentSHA) {
-		slog.Warn("HEAD moved during review — skipping stale review",
+		slog.Warn("HEAD moved during review -- skipping stale review",
 			"evaluated", evaluatedSHA,
 			"current", currentSHA,
 			"pr", prNumber)
 		return
 	}
 
-	// Map findings to inline comments for lines present in the diff
+	// Build line→position map for inline comments
-	diffRanges := gitea.ParseDiffNewLines(diff)
+	lineToPosition := vcs.BuildLineToPositionMap(diff)
-	var inlineComments []gitea.ReviewComment
+	var inlineComments []vcs.ReviewComment
 	for _, f := range result.Findings {
-		if f.File != "" && f.Line > 0 && diffRanges.Contains(f.File, f.Line) {
+		if f.File == "" || f.Line <= 0 {
-			inlineComments = append(inlineComments, gitea.ReviewComment{
+			continue
-				Path:        f.File,
-				NewPosition: int64(f.Line),
-				Body:        fmt.Sprintf("**[%s]** %s", f.Severity, f.Finding),
-			})
 		}
+		pos, ok := lineToPosition[f.File][f.Line]
+		if !ok {
+			slog.Warn("line not in diff, skipping comment", "file", f.File, "line", f.Line)
+			continue
+		}
+		inlineComments = append(inlineComments, vcs.ReviewComment{
+			Path:     f.File,
+			Position: pos,
+			CommitID: pr.Head.SHA,
+			Body:     fmt.Sprintf("**[%s]** %s", f.Severity, f.Finding),
+		})
 	}
 	if len(inlineComments) > 0 {
 		slog.Debug("attaching inline comments", "count", len(inlineComments))
@@ -416,10 +462,9 @@ func main() {
 	// --- Review update strategy ---
 	// 1. POST new review first (gets non-stale approval badge on HEAD)
 	// 2. Then supersede old review with link to the new one
-	// Order matters: post first so we have the new review's URL for the supersede message.
+	var oldReviews []vcs.Review
-	var oldReviews []gitea.Review
 	if *reviewerName != "" {
-		existingReviews, err := giteaClient.ListReviews(ctx, owner, repoName, prNumber)
+		existingReviews, err := client.ListReviews(ctx, owner, repoName, prNumber)
 		if err != nil {
 			slog.Warn("could not list existing reviews", "pr", prNumber, "error", err)
 		} else {
@@ -431,74 +476,141 @@ func main() {
 		}
 	}
 
-	// Self-request as reviewer (ensures we appear in required-reviewer checks)
+	// Self-request as reviewer (Gitea-specific; ensures we appear in required-reviewer checks)
-	authUser, err := giteaClient.GetAuthenticatedUser(ctx)
+	if selfReq, ok := client.(vcs.ReviewerSelfRequester); ok {
-	if err != nil {
+		authUser, err := client.GetAuthenticatedUser(ctx)
-		slog.Warn("could not determine authenticated user for reviewer self-request", "error", err)
+		if err != nil {
-	} else if authUser != "" {
+			slog.Warn("could not determine authenticated user for reviewer self-request", "error", err)
-		if err := giteaClient.RequestReviewer(ctx, owner, repoName, prNumber, authUser); err != nil {
+		} else if authUser != "" {
-			slog.Warn("could not self-request as reviewer", "user", authUser, "error", err)
+			if err := selfReq.RequestReviewerSelf(ctx, owner, repoName, prNumber, authUser); err != nil {
-		} else {
+				slog.Warn("could not self-request as reviewer", "user", authUser, "error", err)
-			slog.Debug("self-requested as reviewer", "user", authUser, "pr", prNumber)
+			} else {
+				slog.Debug("self-requested as reviewer", "user", authUser, "pr", prNumber)
+			}
 		}
+	} else {
+		slog.Debug("RequestReviewer not supported for provider, skipping")
 	}
 
 	// POST new review
 	slog.Info("posting review", "event", event, "pr", prNumber)
-	posted, err := giteaClient.PostReview(ctx, owner, repoName, prNumber, event, reviewBody, inlineComments)
+	reviewReq := vcs.ReviewRequest{
+		Body:     reviewBody,
+		Event:    event,
+		Comments: inlineComments,
+	}
+	posted, err := client.PostReview(ctx, owner, repoName, prNumber, reviewReq)
 	if err != nil {
 		slog.Error("failed to post review", "pr", prNumber, "event", event, "error", err)
 		os.Exit(1)
 	}
 	slog.Info("review posted", "review_id", posted.ID, "user", posted.User.Login, "pr", prNumber)
 
-	// Supersede all old reviews with link to the new one
+	// Supersede all old reviews
 	if len(oldReviews) > 0 {
-		newReviewURL := fmt.Sprintf("%s/%s/%s/pulls/%d#pullrequestreview-%d", strings.TrimRight(*giteaURL, "/"), owner, repoName, prNumber, posted.ID)
+		if err := supersedeOldReviews(ctx, client, *provider, *vcsURL, owner, repoName, prNumber, oldReviews, posted.ID, sentinel); err != nil {
-		for _, oldReview := range oldReviews {
+			slog.Error("failed to supersede old reviews", "error", err)
-			cid, err := giteaClient.GetTimelineReviewCommentIDForReview(ctx, owner, repoName, prNumber, oldReview.ID)
+			os.Exit(1)
-			if err != nil {
-				slog.Warn("could not find comment ID for old review", "review_id", oldReview.ID, "error", err)
-				continue
-			}
-			supersededBody := buildSupersededBody(oldReview.Body, oldReview.CommitID, newReviewURL, sentinel)
-			if err := giteaClient.EditComment(ctx, owner, repoName, cid, supersededBody); err != nil {
-				slog.Warn("could not mark old review as superseded", "review_id", oldReview.ID, "comment_id", cid, "error", err)
-				continue
-			}
-			slog.Info("marked old review as superseded", "review_id", oldReview.ID, "new_review_id", posted.ID, "pr", prNumber)
-
-			// Resolve old review's inline comments
-			oldComments, err := giteaClient.ListReviewComments(ctx, owner, repoName, prNumber, oldReview.ID)
-			if err != nil {
-				slog.Warn("could not list old review comments for resolution", "review_id", oldReview.ID, "error", err)
-				continue
-			}
-			resolved, failed := 0, 0
-			for _, c := range oldComments {
-				if c.ID == 0 {
-					continue
-				}
-				if err := giteaClient.ResolveComment(ctx, owner, repoName, c.ID); err != nil {
-					slog.Debug("could not resolve inline comment", "comment_id", c.ID, "error", err)
-					failed++
-				} else {
-					resolved++
-				}
-			}
-			if resolved > 0 {
-				slog.Info("resolved old inline comments", "review_id", oldReview.ID, "count", resolved, "pr", prNumber)
-			}
-			if failed > 0 {
-				slog.Warn("some inline comments could not be resolved", "review_id", oldReview.ID, "failed", failed, "pr", prNumber)
-			}
 		}
 	}
+}
 
+// verdictToEvent maps a verdict string from the LLM response to a canonical vcs.ReviewEvent.
+func verdictToEvent(verdict string) vcs.ReviewEvent {
+	switch verdict {
+	case "APPROVE":
+		return vcs.ReviewEventApprove
+	case "REQUEST_CHANGES":
+		return vcs.ReviewEventRequestChanges
+	default:
+		return vcs.ReviewEventComment
+	}
+}
+
+// supersedeOldReviews marks prior reviews as superseded so only the latest review is visible.
+// For GitHub: dismisses old reviews (vcsURL is unused in this path).
+// For Gitea: edits the review body with a link to the new review and resolves inline comments.
+//
+// The vcsURL parameter is only used in the Gitea path to construct review permalink URLs;
+// it is accepted unconditionally to keep the function signature uniform across providers.
+func supersedeOldReviews(ctx context.Context, client vcs.Client, provider, vcsURL, owner, repoName string, prNumber int, oldReviews []vcs.Review, newReviewID int64, sentinel string) error {
+	switch provider {
+	case "github":
+		// Best-effort dismissal: attempt all reviews, join any errors.
+		var errs []error
+		for _, old := range oldReviews {
+			if err := client.DismissReview(ctx, owner, repoName, prNumber, old.ID, "Superseded by new review"); err != nil {
+				slog.Warn("failed to dismiss review", "id", old.ID, "error", err)
+				errs = append(errs, fmt.Errorf("dismiss review %d: %w", old.ID, err))
+			} else {
+				slog.Info("dismissed old review", "review_id", old.ID, "new_review_id", newReviewID, "pr", prNumber)
+			}
+		}
+		return errors.Join(errs...)
+	case "gitea":
+		// Continue to Gitea-specific logic below the switch.
+	default:
+		return fmt.Errorf("supersedeOldReviews: unsupported provider %q", provider)
+	}
+
+	// The type assertion below is guaranteed to succeed: the caller's provider switch
+	// ensures we only reach this point when provider == "gitea", and the gitea provider
+	// always constructs a *gitea.Adapter. The !ok branch guards against future refactors
+	// (e.g. wrapping the adapter in a decorator) that would silently break this path.
+	giteaAdapter, ok := client.(*gitea.Adapter)
+	if !ok {
+		return fmt.Errorf("expected gitea.Adapter for gitea provider, got %T", client)
+	}
+	underlying := giteaAdapter.Underlying()
+
+	// Validate vcsURL scheme before embedding in Markdown link (defense-in-depth).
+	if !strings.HasPrefix(vcsURL, "http://") && !strings.HasPrefix(vcsURL, "https://") {
+		return fmt.Errorf("supersedeOldReviews: vcsURL must have http or https scheme, got %q", vcsURL)
+	}
+	newReviewURL := fmt.Sprintf("%s/%s/%s/pulls/%d#pullrequestreview-%d", strings.TrimRight(vcsURL, "/"), owner, repoName, prNumber, newReviewID)
+	for _, oldReview := range oldReviews {
+		cid, err := underlying.GetTimelineReviewCommentIDForReview(ctx, owner, repoName, prNumber, oldReview.ID)
+		if err != nil {
+			slog.Warn("could not find comment ID for old review", "review_id", oldReview.ID, "error", err)
+			continue
+		}
+		supersededBody := buildSupersededBody(oldReview.Body, oldReview.CommitID, newReviewURL, sentinel)
+		if err := underlying.EditComment(ctx, owner, repoName, cid, supersededBody); err != nil {
+			slog.Warn("could not mark old review as superseded", "review_id", oldReview.ID, "comment_id", cid, "error", err)
+			continue
+		}
+		slog.Info("marked old review as superseded", "review_id", oldReview.ID, "new_review_id", newReviewID, "pr", prNumber)
+
+		// Resolve old review's inline comments
+		oldComments, err := underlying.ListReviewComments(ctx, owner, repoName, prNumber, oldReview.ID)
+		if err != nil {
+			slog.Warn("could not list old review comments for resolution", "review_id", oldReview.ID, "error", err)
+			continue
+		}
+		resolved, failed := 0, 0
+		for _, c := range oldComments {
+			if c.ID == 0 {
+				continue
+			}
+			if err := underlying.ResolveComment(ctx, owner, repoName, c.ID); err != nil {
+				slog.Debug("could not resolve inline comment", "comment_id", c.ID, "error", err)
+				failed++
+			} else {
+				resolved++
+			}
+		}
+		if resolved > 0 {
+			slog.Info("resolved old inline comments", "review_id", oldReview.ID, "count", resolved, "pr", prNumber)
+		}
+		if failed > 0 {
+			slog.Warn("some inline comments could not be resolved", "review_id", oldReview.ID, "failed", failed, "pr", prNumber)
+		}
+	}
+	return nil
 }
 
 // fetchFileContext fetches the full content of modified files from the PR branch.
-func fetchFileContext(ctx context.Context, client *gitea.Client, owner, repo, ref string, files []gitea.ChangedFile) string {
+func fetchFileContext(ctx context.Context, client vcs.PRReader, owner, repo, ref string, files []vcs.ChangedFile) string {
 	var sb strings.Builder
 	for _, f := range files {
 		if ctx.Err() != nil {
@@ -507,7 +619,7 @@ func fetchFileContext(ctx context.Context, client *gitea.Client, owner, repo, re
 		if f.Status == "removed" {
 			continue // Skip deleted files
 		}
-		content, err := client.GetFileContentRef(ctx, owner, repo, f.Filename, ref)
+		content, err := client.GetFileContentAtRef(ctx, owner, repo, f.Filename, ref)
 		if err != nil {
 			slog.Warn("could not fetch file content", "file", f.Filename, "error", err)
 			continue
@@ -524,11 +636,25 @@ func fetchFileContext(ctx context.Context, client *gitea.Client, owner, repo, re
 // patternsRepo is comma-separated list of owner/name repos.
 // patternsFiles is comma-separated list of file paths or directories.
 // If a path ends with / or is a directory, all files within it are fetched recursively.
-func fetchPatterns(ctx context.Context, client *gitea.Client, patternsRepo, patternsFiles string) string {
+// If patternsFiles is empty, all files from the repo root are fetched.
+func fetchPatterns(ctx context.Context, client vcs.FileReader, patternsRepo, patternsFiles string) string {
 	var sb strings.Builder
 
 	repos := strings.Split(patternsRepo, ",")
-	paths := strings.Split(patternsFiles, ",")
+
+	// Build the list of paths to fetch
+	var paths []string
+	if patternsFiles == "" {
+		// Empty patternsFiles means "fetch all files from repo root"
+		paths = []string{""}
+	} else {
+		for _, p := range strings.Split(patternsFiles, ",") {
+			p = strings.TrimSpace(p)
+			if p != "" {
+				paths = append(paths, p)
+			}
+		}
+	}
 
 	for _, repoRef := range repos {
 		if ctx.Err() != nil {
@@ -549,12 +675,7 @@ func fetchPatterns(ctx context.Context, client *gitea.Client, patternsRepo, patt
 		var repoSkippedFiles []string
 
 		for _, path := range paths {
-			path = strings.TrimSpace(path)
+			files, err := vcs.GetAllFilesInPath(ctx, client, owner, repo, path)
-			if path == "" {
-				continue
-			}
-
-			files, err := client.GetAllFilesInPath(ctx, owner, repo, path)
 			if err != nil {
 				slog.Warn("could not fetch patterns", "path", path, "repo", repoRef, "error", err)
 				continue
@@ -593,18 +714,20 @@ func isPatternFile(path string) bool {
 }
 
 // evaluateCIStatus checks if all CI statuses indicate success.
-func evaluateCIStatus(statuses []gitea.CommitStatus) (passed bool, details string) {
+// Returns passed=true if no checks have failed (pending checks are not treated as failures).
+func evaluateCIStatus(statuses []vcs.CommitStatus) (passed bool, details string) {
 	if len(statuses) == 0 {
 		return true, "no CI statuses found"
 	}
 
 	var failed []string
+	var pending int
 	for _, s := range statuses {
 		switch s.Status {
 		case "success":
 			// good
 		case "pending":
-			// treat pending as not-failed
+			pending++
 		case "failure", "error":
 			failed = append(failed, fmt.Sprintf("%s: %s", s.Context, s.Description))
 		}
@@ -613,6 +736,9 @@ func evaluateCIStatus(statuses []gitea.CommitStatus) (passed bool, details strin
 	if len(failed) > 0 {
 		return false, strings.Join(failed, "; ")
 	}
+	if pending > 0 {
+		return true, fmt.Sprintf("no failures (%d pending)", pending)
+	}
 	return true, "all checks passed"
 }
 
@@ -643,14 +769,6 @@ func envOrDefaultInt(key string, defaultVal int) int {
 	return defaultVal
 }
 
-func envOrDefaultBool(key string, defaultVal bool) bool {
-	v := strings.TrimSpace(strings.ToLower(os.Getenv(key)))
-	if v == "" {
-		return defaultVal
-	}
-	return v == "true" || v == "1" || v == "yes"
-}
-
 // validateReviewerName checks that the name contains only safe characters
 // for embedding in an HTML comment sentinel ([a-zA-Z0-9_-]).
 func validateReviewerName(name string) error {
@@ -728,10 +846,10 @@ func buildSupersededBody(originalBody, commitSHA, newReviewURL, sentinel string)
 }
 
 // hasSharedToken detects if another review-bot role posted under the same
-// Gitea user. This indicates misconfiguration where two roles share a token
+// VCS user. This indicates misconfiguration where two roles share a token
-// instead of having separate Gitea accounts. Returns true if shared token
+// instead of having separate accounts. Returns true if shared token
 // detected (caller should skip update-in-place logic to avoid clobbering).
-func hasSharedToken(reviews []gitea.Review, ownSentinel string) bool {
+func hasSharedToken(reviews []vcs.Review, ownSentinel string) bool {
 	ownLogin := ""
 	for _, r := range reviews {
 		if strings.Contains(r.Body, ownSentinel) {
@@ -744,7 +862,7 @@ func hasSharedToken(reviews []gitea.Review, ownSentinel string) bool {
 	}
 	for _, r := range reviews {
 		if r.User.Login == ownLogin && strings.Contains(r.Body, "<!-- review-bot:") && !strings.Contains(r.Body, ownSentinel) {
-			slog.Warn("shared token detected — another review-bot role is using the same Gitea user",
+			slog.Warn("shared token detected -- another review-bot role is using the same VCS user",
 				"sibling_role", extractSentinelName(r.Body), "user", ownLogin)
 			return true
 		}
@@ -765,29 +883,26 @@ func extractSentinelName(body string) string {
 	if end < 0 {
 		return "unknown"
 	}
-	return rest[:end]
+	name := rest[:end]
-}
+	// Sanitize: strip control characters to prevent log injection.
-
+	name = strings.Map(func(r rune) rune {
-// findOwnReview locates the most recent non-superseded review matching the sentinel.
+		if r < 0x20 || r == 0x7f {
-func findOwnReview(reviews []gitea.Review, sentinel string) *gitea.Review {
+			return -1
-	var best *gitea.Review
-	for i := range reviews {
-		if !strings.Contains(reviews[i].Body, sentinel) {
-			continue
-		}
-		if strings.Contains(reviews[i].Body, "~~Original review~~") {
-			continue
-		}
-		if best == nil || reviews[i].ID > best.ID {
-			best = &reviews[i]
 		}
+		return r
+	}, name)
+	if len(name) > 64 {
+		name = name[:64]
 	}
-	return best
+	if name == "" {
+		return "unknown"
+	}
+	return name
 }
 
 // findAllOwnReviews returns all non-superseded reviews matching the sentinel.
-func findAllOwnReviews(reviews []gitea.Review, sentinel string) []gitea.Review {
+func findAllOwnReviews(reviews []vcs.Review, sentinel string) []vcs.Review {
-	var result []gitea.Review
+	var result []vcs.Review
 	for i := range reviews {
 		if !strings.Contains(reviews[i].Body, sentinel) {
 			continue
@@ -812,35 +927,3 @@ func shouldSkipStaleReview(evaluatedSHA, currentSHA string) bool {
 	}
 	return evaluatedSHA != currentSHA
 }
-
-// giteaClientAdapter adapts gitea.Client to vcs.FileReader 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) ([]vcs.ContentEntry, error) {
-	entries, err := a.client.ListContents(ctx, owner, repo, path)
-	if err != nil {
-		return nil, err
-	}
-	result := make([]vcs.ContentEntry, len(entries))
-	for i, e := range entries {
-		result[i] = vcs.ContentEntry{
-			Name: e.Name,
-			Path: e.Path,
-			Type: e.Type,
-		}
-	}
-	return result, nil
-}
-
-func (a *giteaClientAdapter) GetFileContent(ctx context.Context, owner, repo, filePath, ref string) (string, error) {
-	if ref != "" {
-		return a.client.GetFileContentRef(ctx, owner, repo, filePath, ref)
-	}
-	return a.client.GetFileContent(ctx, owner, repo, filePath)
-}

cmd/review-bot/main_test.go

@@ -10,7 +10,7 @@ import (
 	"strings"
 	"testing"
 
-	"gitea.weiker.me/rodin/review-bot/gitea"
+	"gitea.weiker.me/rodin/review-bot/vcs"
 )
 
 func TestValidateReviewerName(t *testing.T) {
@@ -107,9 +107,7 @@ func TestValidateWorkspacePath(t *testing.T) {
 			workspace: tmpDir,
 			path:      "/etc/passwd",
 			wantErr:   true,
-			// Go 1.21+ filepath.Join normalizes absolute paths: Join("/tmp/x", "/etc/passwd")
+			errMatch:  "failed to resolve",
-			// becomes "/tmp/x/etc/passwd", which is within workspace but doesn't exist.
-			errMatch: "failed to resolve",
 		},
 		{
 			name:      "nonexistent file",
@@ -154,15 +152,14 @@ func TestValidateWorkspacePath(t *testing.T) {
 	}
 }
 
-func makeReview(id int64, login, state string, stale bool, body string) gitea.Review {
+func makeReview(id int64, login, state string, stale bool, body string) vcs.Review {
-	r := gitea.Review{
+	return vcs.Review{
 		ID:    id,
 		Body:  body,
+		User:  vcs.UserInfo{Login: login},
 		State: state,
 		Stale: stale,
 	}
-	r.User.Login = login
-	return r
 }
 
 func TestBuildSupersededBody(t *testing.T) {
@@ -213,96 +210,10 @@ func TestBuildSupersededBodyShortSHA(t *testing.T) {
 	}
 }
 
-func TestFindOwnReview(t *testing.T) {
-	tests := []struct {
-		name     string
-		reviews  []gitea.Review
-		sentinel string
-		wantID   int64
-		wantNil  bool
-	}{
-		{
-			name:     "no reviews",
-			reviews:  nil,
-			sentinel: "<!-- review-bot:sonnet -->",
-			wantNil:  true,
-		},
-		{
-			name: "found by sentinel",
-			reviews: []gitea.Review{
-				makeReview(42, "bot", "APPROVED", false, "review body\n<!-- review-bot:sonnet -->"),
-			},
-			sentinel: "<!-- review-bot:sonnet -->",
-			wantID:   42,
-		},
-		{
-			name: "wrong sentinel",
-			reviews: []gitea.Review{
-				makeReview(42, "bot", "APPROVED", false, "body\n<!-- review-bot:gpt -->"),
-			},
-			sentinel: "<!-- review-bot:sonnet -->",
-			wantNil:  true,
-		},
-		{
-			name: "multiple reviews, returns first match",
-			reviews: []gitea.Review{
-				makeReview(10, "bot", "APPROVED", false, "old\n<!-- review-bot:gpt -->"),
-				makeReview(20, "bot", "APPROVED", false, "new\n<!-- review-bot:sonnet -->"),
-			},
-			sentinel: "<!-- review-bot:sonnet -->",
-			wantID:   20,
-		},
-		{
-			name: "skips superseded review",
-			reviews: []gitea.Review{
-				makeReview(10, "bot", "APPROVED", false, "~~Original review~~\n\n**Superseded**\n<!-- review-bot:sonnet -->"),
-				makeReview(20, "bot", "APPROVED", false, "fresh review\n<!-- review-bot:sonnet -->"),
-			},
-			sentinel: "<!-- review-bot:sonnet -->",
-			wantID:   20,
-		},
-		{
-			name: "only superseded reviews exist",
-			reviews: []gitea.Review{
-				makeReview(10, "bot", "APPROVED", false, "~~Original review~~\n\n<!-- review-bot:sonnet -->"),
-			},
-			sentinel: "<!-- review-bot:sonnet -->",
-			wantNil:  true,
-		},
-		{
-			name: "picks highest ID among matches",
-			reviews: []gitea.Review{
-				makeReview(50, "bot", "APPROVED", false, "v1\n<!-- review-bot:sonnet -->"),
-				makeReview(30, "bot", "APPROVED", false, "v0\n<!-- review-bot:sonnet -->"),
-			},
-			sentinel: "<!-- review-bot:sonnet -->",
-			wantID:   50,
-		},
-	}
-
-	for _, tc := range tests {
-		t.Run(tc.name, func(t *testing.T) {
-			got := findOwnReview(tc.reviews, tc.sentinel)
-			if tc.wantNil {
-				if got != nil {
-					t.Errorf("findOwnReview() = %v, want nil", got)
-				}
-			} else {
-				if got == nil {
-					t.Fatal("findOwnReview() = nil, want non-nil")
-				}
-				if got.ID != tc.wantID {
-					t.Errorf("findOwnReview().ID = %d, want %d", got.ID, tc.wantID)
-				}
-			}
-		})
-	}
-}
-
 func TestHasSharedToken(t *testing.T) {
 	tests := []struct {
 		name     string
-		reviews  []gitea.Review
+		reviews  []vcs.Review
 		sentinel string
 		want     bool
 	}{
@@ -314,36 +225,36 @@ func TestHasSharedToken(t *testing.T) {
 		},
 		{
 			name: "no own review yet - cannot detect",
-			reviews: []gitea.Review{
+			reviews: []vcs.Review{
-				{ID: 1, User: struct{ Login string `json:"login"` }{Login: "other"}, Body: "<!-- review-bot:gpt --> body"},
+				makeReview(1, "other", "APPROVED", false, "<!-- review-bot:gpt --> body"),
 			},
 			sentinel: "<!-- review-bot:sonnet -->",
 			want:     false,
 		},
 		{
 			name: "separate users - no shared token",
-			reviews: []gitea.Review{
+			reviews: []vcs.Review{
-				{ID: 1, User: struct{ Login string `json:"login"` }{Login: "sonnet-review-bot"}, Body: "<!-- review-bot:sonnet --> body"},
+				makeReview(1, "sonnet-review-bot", "APPROVED", false, "<!-- review-bot:sonnet --> body"),
-				{ID: 2, User: struct{ Login string `json:"login"` }{Login: "security-review-bot"}, Body: "<!-- review-bot:security --> body"},
+				makeReview(2, "security-review-bot", "APPROVED", false, "<!-- review-bot:security --> body"),
 			},
 			sentinel: "<!-- review-bot:sonnet -->",
 			want:     false,
 		},
 		{
 			name: "shared token detected - same user different sentinels",
-			reviews: []gitea.Review{
+			reviews: []vcs.Review{
-				{ID: 1, User: struct{ Login string `json:"login"` }{Login: "sonnet-review-bot"}, Body: "<!-- review-bot:sonnet --> body"},
+				makeReview(1, "sonnet-review-bot", "APPROVED", false, "<!-- review-bot:sonnet --> body"),
-				{ID: 2, User: struct{ Login string `json:"login"` }{Login: "sonnet-review-bot"}, Body: "<!-- review-bot:security --> body"},
+				makeReview(2, "sonnet-review-bot", "APPROVED", false, "<!-- review-bot:security --> body"),
 			},
 			sentinel: "<!-- review-bot:sonnet -->",
 			want:     true,
 		},
 		{
 			name: "three roles same user",
-			reviews: []gitea.Review{
+			reviews: []vcs.Review{
-				{ID: 1, User: struct{ Login string `json:"login"` }{Login: "bot"}, Body: "<!-- review-bot:sonnet --> body"},
+				makeReview(1, "bot", "APPROVED", false, "<!-- review-bot:sonnet --> body"),
-				{ID: 2, User: struct{ Login string `json:"login"` }{Login: "bot"}, Body: "<!-- review-bot:security --> body"},
+				makeReview(2, "bot", "APPROVED", false, "<!-- review-bot:security --> body"),
-				{ID: 3, User: struct{ Login string `json:"login"` }{Login: "bot"}, Body: "<!-- review-bot:gpt --> body"},
+				makeReview(3, "bot", "APPROVED", false, "<!-- review-bot:gpt --> body"),
 			},
 			sentinel: "<!-- review-bot:sonnet -->",
 			want:     true,
@@ -504,10 +415,56 @@ func TestIsPatternFile(t *testing.T) {
 	}
 }
 
+// TestBuildPatternPaths verifies the path-building logic for fetchPatterns.
+// Empty patternsFiles means "fetch all from root" (represented as [""]).
+func TestBuildPatternPaths(t *testing.T) {
+	buildPaths := func(patternsFiles string) []string {
+		if patternsFiles == "" {
+			return []string{""}
+		}
+		var paths []string
+		for _, p := range strings.Split(patternsFiles, ",") {
+			p = strings.TrimSpace(p)
+			if p != "" {
+				paths = append(paths, p)
+			}
+		}
+		return paths
+	}
+
+	tests := []struct {
+		name  string
+		input string
+		want  []string
+	}{
+		{"empty fetches root", "", []string{""}},
+		{"single file", "README.md", []string{"README.md"}},
+		{"multiple files", "README.md,PATTERNS.md", []string{"README.md", "PATTERNS.md"}},
+		{"trims whitespace", " foo.md , bar.md ", []string{"foo.md", "bar.md"}},
+		{"skips empty between commas", "foo.md,,bar.md", []string{"foo.md", "bar.md"}},
+		{"directory path", "patterns/", []string{"patterns/"}},
+	}
+
+	for _, tc := range tests {
+		t.Run(tc.name, func(t *testing.T) {
+			got := buildPaths(tc.input)
+			if len(got) != len(tc.want) {
+				t.Errorf("buildPaths(%q) = %v, want %v", tc.input, got, tc.want)
+				return
+			}
+			for i := range got {
+				if got[i] != tc.want[i] {
+					t.Errorf("buildPaths(%q)[%d] = %q, want %q", tc.input, i, got[i], tc.want[i])
+				}
+			}
+		})
+	}
+}
+
 func TestEvaluateCIStatus(t *testing.T) {
 	tests := []struct {
 		name       string
-		statuses   []gitea.CommitStatus
+		statuses   []vcs.CommitStatus
 		wantPassed bool
 		wantSubstr string
 	}{
@@ -519,7 +476,7 @@ func TestEvaluateCIStatus(t *testing.T) {
 		},
 		{
 			name: "all success",
-			statuses: []gitea.CommitStatus{
+			statuses: []vcs.CommitStatus{
 				{Status: "success", Context: "ci/build", Description: "Build passed"},
 				{Status: "success", Context: "ci/test", Description: "Tests passed"},
 			},
@@ -528,7 +485,7 @@ func TestEvaluateCIStatus(t *testing.T) {
 		},
 		{
 			name: "one failure",
-			statuses: []gitea.CommitStatus{
+			statuses: []vcs.CommitStatus{
 				{Status: "success", Context: "ci/build", Description: "Build passed"},
 				{Status: "failure", Context: "ci/test", Description: "Tests failed"},
 			},
@@ -537,7 +494,7 @@ func TestEvaluateCIStatus(t *testing.T) {
 		},
 		{
 			name: "error status",
-			statuses: []gitea.CommitStatus{
+			statuses: []vcs.CommitStatus{
 				{Status: "error", Context: "ci/lint", Description: "Lint error"},
 			},
 			wantPassed: false,
@@ -545,16 +502,16 @@ func TestEvaluateCIStatus(t *testing.T) {
 		},
 		{
 			name: "pending treated as not-failed",
-			statuses: []gitea.CommitStatus{
+			statuses: []vcs.CommitStatus{
 				{Status: "pending", Context: "ci/build", Description: "In progress"},
 				{Status: "success", Context: "ci/test", Description: "Tests passed"},
 			},
 			wantPassed: true,
-			wantSubstr: "all checks passed",
+			wantSubstr: "no failures",
 		},
 		{
 			name: "multiple failures",
-			statuses: []gitea.CommitStatus{
+			statuses: []vcs.CommitStatus{
 				{Status: "failure", Context: "ci/build", Description: "Build failed"},
 				{Status: "failure", Context: "ci/test", Description: "Tests failed"},
 			},
@@ -563,7 +520,7 @@ func TestEvaluateCIStatus(t *testing.T) {
 		},
 		{
 			name: "mixed with pending and failure",
-			statuses: []gitea.CommitStatus{
+			statuses: []vcs.CommitStatus{
 				{Status: "success", Context: "ci/build", Description: "Build passed"},
 				{Status: "pending", Context: "ci/deploy", Description: "Deploying"},
 				{Status: "failure", Context: "ci/test", Description: "Tests failed"},
@@ -685,47 +642,6 @@ func TestEnvOrDefaultInt(t *testing.T) {
 	}
 }
 
-func TestEnvOrDefaultBool(t *testing.T) {
-	tests := []struct {
-		name       string
-		envVal     string
-		setEnv     bool
-		defaultVal bool
-		want       bool
-	}{
-		{"unset returns default true", "", false, true, true},
-		{"unset returns default false", "", false, false, false},
-		{"true", "true", true, false, true},
-		{"TRUE", "TRUE", true, false, true},
-		{"True", "True", true, false, true},
-		{"1", "1", true, false, true},
-		{"yes", "yes", true, false, true},
-		{"YES", "YES", true, false, true},
-		{"false", "false", true, true, false},
-		{"0", "0", true, true, false},
-		{"no", "no", true, true, false},
-		{"random string", "random", true, true, false},
-		{"empty string returns default", "", true, true, true},
-		{"whitespace true", "  true  ", true, false, true},
-	}
-
-	for _, tc := range tests {
-		t.Run(tc.name, func(t *testing.T) {
-			envKey := "TEST_ENV_BOOL_" + strings.ReplaceAll(tc.name, " ", "_")
-			if tc.setEnv {
-				os.Setenv(envKey, tc.envVal)
-				defer os.Unsetenv(envKey)
-			} else {
-				os.Unsetenv(envKey)
-			}
-			got := envOrDefaultBool(envKey, tc.defaultVal)
-			if got != tc.want {
-				t.Errorf("envOrDefaultBool(%q, %v) = %v, want %v", tc.envVal, tc.defaultVal, got, tc.want)
-			}
-		})
-	}
-}
-
 func TestExtractSentinelName_EdgeCases(t *testing.T) {
 	tests := []struct {
 		body string
@@ -734,8 +650,8 @@ 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
+		{"<!-- review-bot:", "unknown"},               // prefix but no suffix
-		{"prefix <!-- review-bot:abc --> end", "abc"},     // embedded in text
+		{"prefix <!-- review-bot:abc --> end", "abc"}, // embedded in text
 	}
 
 	for _, tc := range tests {
@@ -792,7 +708,7 @@ func TestMainSubprocess_InvalidReviewerName(t *testing.T) {
 	if os.Getenv("TEST_SUBPROCESS_MAIN") == "1" {
 		flag.CommandLine = flag.NewFlagSet(os.Args[0], flag.ExitOnError)
 		os.Args = []string{"review-bot",
-			"--gitea-url", "http://localhost",
+			"--vcs-url", "http://localhost",
 			"--repo", "owner/repo",
 			"--pr", "1",
 			"--reviewer-name", "invalid name",
@@ -820,7 +736,7 @@ func TestMainSubprocess_InvalidRepo(t *testing.T) {
 	if os.Getenv("TEST_SUBPROCESS_MAIN") == "1" {
 		flag.CommandLine = flag.NewFlagSet(os.Args[0], flag.ExitOnError)
 		os.Args = []string{"review-bot",
-			"--gitea-url", "http://localhost",
+			"--vcs-url", "http://localhost",
 			"--repo", "invalidrepo",
 			"--pr", "1",
 			"--reviewer-token", "tok",
@@ -847,7 +763,7 @@ func TestMainSubprocess_InvalidPRNumber(t *testing.T) {
 	if os.Getenv("TEST_SUBPROCESS_MAIN") == "1" {
 		flag.CommandLine = flag.NewFlagSet(os.Args[0], flag.ExitOnError)
 		os.Args = []string{"review-bot",
-			"--gitea-url", "http://localhost",
+			"--vcs-url", "http://localhost",
 			"--repo", "owner/repo",
 			"--pr", "notanumber",
 			"--reviewer-token", "tok",
@@ -874,7 +790,7 @@ func TestMainSubprocess_InvalidTemperature(t *testing.T) {
 	if os.Getenv("TEST_SUBPROCESS_MAIN") == "1" {
 		flag.CommandLine = flag.NewFlagSet(os.Args[0], flag.ExitOnError)
 		os.Args = []string{"review-bot",
-			"--gitea-url", "http://localhost",
+			"--vcs-url", "http://localhost",
 			"--repo", "owner/repo",
 			"--pr", "1",
 			"--reviewer-token", "tok",
@@ -902,7 +818,7 @@ func TestMainSubprocess_InvalidProvider(t *testing.T) {
 	if os.Getenv("TEST_SUBPROCESS_MAIN") == "1" {
 		flag.CommandLine = flag.NewFlagSet(os.Args[0], flag.ExitOnError)
 		os.Args = []string{"review-bot",
-			"--gitea-url", "http://localhost",
+			"--vcs-url", "http://localhost",
 			"--repo", "owner/repo",
 			"--pr", "1",
 			"--reviewer-token", "tok",
@@ -926,7 +842,35 @@ func TestMainSubprocess_InvalidProvider(t *testing.T) {
 	}
 }
 
-// cleanEnv returns environ without any GITEA/LLM/REVIEWER env vars that would
+func TestMainSubprocess_InvalidVCSProvider(t *testing.T) {
+	if os.Getenv("TEST_SUBPROCESS_MAIN") == "1" {
+		flag.CommandLine = flag.NewFlagSet(os.Args[0], flag.ExitOnError)
+		os.Args = []string{"review-bot",
+			"--provider", "invalid",
+			"--vcs-url", "http://localhost",
+			"--repo", "owner/repo",
+			"--pr", "1",
+			"--reviewer-token", "tok",
+			"--llm-base-url", "http://localhost",
+			"--llm-api-key", "key",
+			"--llm-model", "model",
+		}
+		main()
+		return
+	}
+
+	cmd := exec.Command(os.Args[0], "-test.run=TestMainSubprocess_InvalidVCSProvider")
+	cmd.Env = append(cleanEnv(), "TEST_SUBPROCESS_MAIN=1")
+	out, err := cmd.CombinedOutput()
+	if err == nil {
+		t.Fatal("expected non-zero exit with invalid VCS provider")
+	}
+	if !strings.Contains(string(out), "invalid --provider") {
+		t.Errorf("expected error about invalid --provider, got: %s", out)
+	}
+}
+
+// cleanEnv returns environ without any GITEA/LLM/REVIEWER/VCS env vars that would
 // interfere with testing missing-flag scenarios.
 func cleanEnv() []string {
 	var env []string
@@ -934,6 +878,7 @@ func cleanEnv() []string {
 		key := strings.SplitN(e, "=", 2)[0]
 		switch {
 		case strings.HasPrefix(key, "GITEA_"),
+			strings.HasPrefix(key, "VCS_"),
 			strings.HasPrefix(key, "LLM_"),
 			strings.HasPrefix(key, "REVIEWER_"),
 			strings.HasPrefix(key, "PR_"),
@@ -951,12 +896,12 @@ func cleanEnv() []string {
 }
 
 func TestFindAllOwnReviews(t *testing.T) {
-	reviews := []gitea.Review{
+	reviews := []vcs.Review{
-		{ID: 1, Body: "<!-- review-bot:sonnet -->\nfirst review"},
+		makeReview(1, "bot", "APPROVED", false, "<!-- review-bot:sonnet -->\nfirst review"),
-		{ID: 2, Body: "<!-- review-bot:gpt -->\nother bot"},
+		makeReview(2, "bot", "APPROVED", false, "<!-- review-bot:gpt -->\nother bot"),
-		{ID: 3, Body: "<!-- review-bot:sonnet -->\nsecond review"},
+		makeReview(3, "bot", "APPROVED", false, "<!-- review-bot:sonnet -->\nsecond review"),
-		{ID: 4, Body: "~~Original review~~\n<!-- review-bot:sonnet -->\nsuperseded"},
+		makeReview(4, "bot", "APPROVED", false, "~~Original review~~\n<!-- review-bot:sonnet -->\nsuperseded"),
-		{ID: 5, Body: "<!-- review-bot:sonnet -->\nthird review"},
+		makeReview(5, "bot", "APPROVED", false, "<!-- review-bot:sonnet -->\nthird review"),
 	}
 
 	got := findAllOwnReviews(reviews, "<!-- review-bot:sonnet -->")
@@ -1020,3 +965,23 @@ func TestShouldSkipStaleReview(t *testing.T) {
 		})
 	}
 }
+
+func TestVerdictToEvent(t *testing.T) {
+	tests := []struct {
+		verdict string
+		want    vcs.ReviewEvent
+	}{
+		{"APPROVE", vcs.ReviewEventApprove},
+		{"REQUEST_CHANGES", vcs.ReviewEventRequestChanges},
+		{"COMMENT", vcs.ReviewEventComment},
+		{"other", vcs.ReviewEventComment},
+		{"", vcs.ReviewEventComment},
+	}
+
+	for _, tc := range tests {
+		got := verdictToEvent(tc.verdict)
+		if got != tc.want {
+			t.Errorf("verdictToEvent(%q) = %q, want %q", tc.verdict, got, tc.want)
+		}
+	}
+}

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 `gopkg.in/yaml.v3` (approved in CONVENTIONS.md) with explicit depth limiting
+- Library: use `github.com/goccy/go-yaml` v1.16.0+ (approved in CONVENTIONS.md); we implement custom AST-based depth/node-count checks for precise alias-aware validation
 
 ## Proposed Approach
 
@@ -33,37 +33,16 @@ func parsePersona(data []byte, source string) (*Persona, error) {
 
 ### YAML Parsing with Depth Protection
 
-```go
+We implement a custom AST-based depth/node-count walk (`checkYAMLDepth` in
-func unmarshalYAMLWithDepthLimit(data []byte, out any, maxDepth int) error {
+`review/persona.go`) rather than relying on library decoder options. Key design
-    var node yaml.Node
+decisions:
-    dec := yaml.NewDecoder(bytes.NewReader(data))
-    if err := dec.Decode(&node); err != nil {
-        return err
-    }
-    if err := checkYAMLDepth(&node, 0, maxDepth); err != nil {
-        return err
-    }
-    return node.Decode(out)
-}
 
-func checkYAMLDepth(node *yaml.Node, depth, maxDepth int) error {
+- **Library:** `github.com/goccy/go-yaml` with `ast.Node`-based traversal
-    if depth > maxDepth {
+- **Dual-map tracking:** `validated` (depth-aware short-circuit) + `visiting` (cycle detection)
-        return fmt.Errorf("YAML nesting depth exceeds maximum (%d)", maxDepth)
+- **Node-count limit:** Conservative overcounting bounds total validation work
-    }
+- **Alias-aware depth:** Aliases increment depth and are re-checked when encountered at greater depths
-    // 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 `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.
+See `review/persona.go:checkYAMLDepth` for the authoritative implementation.
 
 ## State/Data Model
 
@@ -74,7 +53,7 @@ No new state. Same `Persona` struct, just different parsing.
 | Error | Handling |
 |-------|----------|
 | Invalid YAML syntax | Return parse error with source file |
-| Deeply nested YAML | Library rejects (v1.16.0+ fix) |
+| Deeply nested YAML | Custom AST walk (`checkYAMLDepth`) rejects before decode |
 | Unknown extension | Fall back to JSON parsing |
 | Missing required fields | Validation rejects after parse |
 

gitea/adapter.go

@@ -16,6 +16,7 @@ type Adapter struct {
 
 // Compile-time interface conformance assertion.
 var _ vcs.Client = (*Adapter)(nil)
+var _ vcs.ReviewerSelfRequester = (*Adapter)(nil)
 
 // NewAdapter creates a new Adapter wrapping the given gitea Client.
 func NewAdapter(client *Client) *Adapter {
@@ -230,3 +231,9 @@ func (a *Adapter) DismissReview(ctx context.Context, owner, repo string, number
 func (a *Adapter) GetAuthenticatedUser(ctx context.Context) (string, error) {
 	return a.client.GetAuthenticatedUser(ctx)
 }
+
+// RequestReviewerSelf adds the given user as a requested reviewer on a pull request.
+// This implements vcs.ReviewerSelfRequester for the Gitea adapter.
+func (a *Adapter) RequestReviewerSelf(ctx context.Context, owner, repo string, number int, user string) error {
+	return a.client.RequestReviewer(ctx, owner, repo, number, user)
+}

gitea/adapter_test.go

@@ -386,3 +386,25 @@ func TestAdapter_GetFileContent_RefRouting(t *testing.T) {
 		t.Errorf("GetFileContent(ref=\"abc123\") = %q, want %q", got, "content-at-ref")
 	}
 }
+
+func TestAdapter_RequestReviewerSelf(t *testing.T) {
+	server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		if r.Method != http.MethodPost {
+			t.Errorf("expected POST, got %s", r.Method)
+		}
+		expected := "/api/v1/repos/owner/repo/pulls/5/requested_reviewers"
+		if r.URL.Path != expected {
+			t.Errorf("path = %q, want %q", r.URL.Path, expected)
+		}
+		w.WriteHeader(http.StatusCreated)
+	}))
+	defer server.Close()
+
+	client := gitea.NewClient(server.URL, "token")
+	adapter := gitea.NewAdapter(client)
+
+	err := adapter.RequestReviewerSelf(context.Background(), "owner", "repo", 5, "bot-user")
+	if err != nil {
+		t.Fatalf("RequestReviewerSelf() error = %v", err)
+	}
+}

github/client.go

@@ -6,6 +6,7 @@ package github
 import (
 	"bytes"
 	"context"
+	"encoding/json"
 	"errors"
 	"fmt"
 	"io"
@@ -214,6 +215,11 @@ type requestOptions struct {
 func (c *Client) doRequestCore(ctx context.Context, method, reqURL string, opts requestOptions) ([]byte, error) {
 	const maxRetryAfter = 120 * time.Second
 
+	// maxErrorBodyBytes limits how much of an error response body is stored.
+	// Kept small (4 KiB) to reduce the risk of sensitive data leakage if callers
+	// log APIError.Body directly. Error() further truncates to 200 bytes.
+	const maxErrorBodyBytes = 4 * 1024
+
 	// backoff holds per-attempt delays: backoff[i] is the delay before attempt i+1.
 	// Length must be maxRetryAttempts-1 (one entry per retry gap).
 	// SetRetryBackoff validates at configuration time; the default is always valid.
@@ -227,11 +233,6 @@ func (c *Client) doRequestCore(ctx context.Context, method, reqURL string, opts
 		copy(backoff, defaultBackoff)
 	}
 
-	// maxErrorBodyBytes limits how much of an error response body is stored.
-	// Kept small (4 KiB) to reduce the risk of sensitive data leakage if callers
-	// log APIError.Body directly. Error() further truncates to 200 bytes.
-	const maxErrorBodyBytes = 4 * 1024
-
 	// Reject non-HTTPS URLs early since the URL is immutable across retries.
 	if c.token != "" && !c.allowInsecureHTTP {
 		parsed, err := url.Parse(reqURL)
@@ -384,3 +385,15 @@ func (c *Client) doRequestWithBody(ctx context.Context, method, reqURL string, r
 	}
 	return c.doRequestCore(ctx, method, reqURL, opts)
 }
+
+// doJSONRequest performs an HTTP request with a JSON body and returns the response body.
+// It delegates retry/backoff/429 handling to doRequestWithBody.
+// This is a general-purpose helper used by any method that needs to send JSON payloads
+// (e.g. PostReview, DismissReview).
+func (c *Client) doJSONRequest(ctx context.Context, method, reqURL string, payload any) ([]byte, error) {
+	jsonBody, err := json.Marshal(payload)
+	if err != nil {
+		return nil, fmt.Errorf("marshal request body: %w", err)
+	}
+	return c.doRequestWithBody(ctx, method, reqURL, jsonBody)
+}

github/client_test.go

@@ -2,6 +2,7 @@ package github
 
 import (
 	"context"
+	"errors"
 	"net/http"
 	"net/http/httptest"
 	"net/url"
@@ -567,7 +568,6 @@ func TestSetHTTPClient_NilRestoresDefault(t *testing.T) {
 	}
 }
 
-
 func TestSetRetryBackoff_RejectsInvalidLength(t *testing.T) {
 	c := NewClient("token", "https://api.github.com")
 
@@ -592,3 +592,59 @@ func TestSetRetryBackoff_RejectsInvalidLength(t *testing.T) {
 		t.Fatalf("unexpected error for valid backoff: %v", err)
 	}
 }
+
+func TestDoJSONRequest_429Retry(t *testing.T) {
+	attempts := 0
+	ts := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		attempts++
+		if attempts < 3 {
+			w.WriteHeader(429)
+			w.Write([]byte(`{"message":"rate limit exceeded"}`))
+			return
+		}
+		w.WriteHeader(200)
+		w.Write([]byte(`{"id":1}`))
+	}))
+	defer ts.Close()
+
+	c := NewClient("token", ts.URL, AllowInsecureHTTP())
+	if err := c.SetRetryBackoff([]time.Duration{1 * time.Millisecond, 1 * time.Millisecond}); err != nil {
+		t.Fatalf("SetRetryBackoff: %v", err)
+	}
+
+	body, err := c.doJSONRequest(context.Background(), http.MethodPost, ts.URL+"/test", map[string]string{"key": "val"})
+	if err != nil {
+		t.Fatalf("unexpected error: %v", err)
+	}
+	if attempts != 3 {
+		t.Errorf("expected 3 attempts, got %d", attempts)
+	}
+	if string(body) != `{"id":1}` {
+		t.Errorf("unexpected body: %s", body)
+	}
+}
+
+func TestDoJSONRequest_429ExhaustsRetries(t *testing.T) {
+	ts := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		w.WriteHeader(429)
+		w.Write([]byte(`{"message":"rate limit"}`))
+	}))
+	defer ts.Close()
+
+	c := NewClient("token", ts.URL, AllowInsecureHTTP())
+	if err := c.SetRetryBackoff([]time.Duration{1 * time.Millisecond, 1 * time.Millisecond}); err != nil {
+		t.Fatalf("SetRetryBackoff: %v", err)
+	}
+
+	_, err := c.doJSONRequest(context.Background(), http.MethodPost, ts.URL+"/test", map[string]string{"key": "val"})
+	if err == nil {
+		t.Fatal("expected error after exhausting retries")
+	}
+	var apiErr *APIError
+	if !errors.As(err, &apiErr) {
+		t.Fatalf("expected APIError, got %T: %v", err, err)
+	}
+	if apiErr.StatusCode != 429 {
+		t.Errorf("expected 429, got %d", apiErr.StatusCode)
+	}
+}

go.mod

@@ -2,4 +2,4 @@ module gitea.weiker.me/rodin/review-bot
 
 go 1.26.2
 
-require gopkg.in/yaml.v3 v3.0.1
+require github.com/goccy/go-yaml v1.19.2

go.sum

@@ -1,4 +1,2 @@
-gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405 h1:yhCVgyC4o1eVCa2tZl7eS0r+SDo693bJlVdllGtEeKM=
+github.com/goccy/go-yaml v1.19.2 h1:PmFC1S6h8ljIz6gMRBopkjP1TVT7xuwrButHID66PoM=
-gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
+github.com/goccy/go-yaml v1.19.2/go.mod h1:XBurs7gK8ATbW4ZPGKgcbrY1Br56PdM69F7LkFRi1kA=
-gopkg.in/yaml.v3 v3.0.1 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA=
-gopkg.in/yaml.v3 v3.0.1/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=

review/formatter.go

@@ -10,18 +10,6 @@ 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).

review/formatter_test.go

@@ -98,25 +98,6 @@ func TestFormatMarkdown_SpecialChars(t *testing.T) {
 	}
 }
 
-func TestGiteaEvent(t *testing.T) {
-	tests := []struct {
-		verdict  string
-		expected string
-	}{
-		{"APPROVE", "APPROVED"},
-		{"REQUEST_CHANGES", "REQUEST_CHANGES"},
-		{"UNKNOWN", "COMMENT"},
-		{"", "COMMENT"},
-	}
-
-	for _, tc := range tests {
-		got := GiteaEvent(tc.verdict)
-		if got != tc.expected {
-			t.Errorf("GiteaEvent(%q) = %q, want %q", tc.verdict, got, tc.expected)
-		}
-	}
-}
-
 func TestFormatMarkdown_Sentinel(t *testing.T) {
 	result := &ReviewResult{
 		Verdict:        "APPROVE",

review/persona.go

@@ -5,12 +5,15 @@ import (
 	"embed"
 	"encoding/json"
 	"fmt"
+	"io"
 	"os"
 	"sort"
 	"strings"
 	"unicode/utf8"
 
-	"gopkg.in/yaml.v3"
+	"github.com/goccy/go-yaml"
+	"github.com/goccy/go-yaml/ast"
+	"github.com/goccy/go-yaml/parser"
 )
 
 //go:embed personas/*.yaml
@@ -118,9 +121,7 @@ func ListBuiltinPersonas() []string {
 		default:
 			continue
 		}
-		if !seen[personaName] {
+		seen[personaName] = true
-			seen[personaName] = true
-		}
 	}
 	names := make([]string, 0, len(seen))
 	for name := range seen {
@@ -142,10 +143,19 @@ func parsePersona(data []byte, source string) (*Persona, error) {
 		err = unmarshalYAMLWithDepthLimit(data, &p, MaxYAMLDepth)
 	} else {
 		// Use json.Decoder with DisallowUnknownFields for consistency with
-		// YAML's KnownFields(true) - both reject unknown fields to catch typos.
+		// YAML's Strict() - both reject unknown fields to catch typos.
 		dec := json.NewDecoder(bytes.NewReader(data))
 		dec.DisallowUnknownFields()
 		err = dec.Decode(&p)
+		if err == nil {
+			// Reject trailing content after the first valid JSON object.
+			// Without this check, input like `{"name":"x"}garbage` would
+			// silently succeed because Decoder stops after one object.
+			var dummy json.RawMessage
+			if err2 := dec.Decode(&dummy); err2 != io.EOF {
+				err = fmt.Errorf("unexpected trailing content after JSON object")
+			}
+		}
 	}
 	if err != nil {
 		return nil, fmt.Errorf("parse persona %s: %w", source, err)
@@ -156,70 +166,164 @@ func parsePersona(data []byte, source string) (*Persona, error) {
 	return &p, nil
 }
 
-// unmarshalYAMLWithDepthLimit unmarshals YAML data with explicit depth limiting
+// unmarshalYAMLWithDepthLimit unmarshals YAML data with three safety checks:
-// and strict field checking. This protects against stack exhaustion from deeply
+//   - Depth limiting: rejects AST trees exceeding maxDepth to prevent stack exhaustion.
-// nested structures and catches typos in field names.
+//   - Multi-document rejection: prevents silent data loss from ignored extra documents.
-// Multi-document YAML files are rejected to prevent silent data loss.
+//   - Strict field checking: rejects unknown YAML keys to catch typos early.
 func unmarshalYAMLWithDepthLimit(data []byte, out any, maxDepth int) error {
-	// First pass: decode into a yaml.Node to check depth limits and node counts.
+	// First pass: parse into AST to check depth limits, node counts, and
-	// This prevents stack exhaustion before we attempt to decode into structs.
+	// multi-document rejection. This prevents stack exhaustion before we
-	var node yaml.Node
+	// attempt to decode into structs.
-	dec := yaml.NewDecoder(bytes.NewReader(data))
+	file, err := parser.ParseBytes(data, 0)
-	if err := dec.Decode(&node); err != nil {
+	if err != nil {
 		return err
 	}
 
+	// Reject empty YAML input (whitespace-only, comment-only, or truly empty files).
+	// The parser returns a single doc with nil body for these cases.
+	if len(file.Docs) == 0 || file.Docs[0].Body == nil {
+		return fmt.Errorf("empty YAML document")
+	}
+
 	// 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 len(file.Docs) > 1 {
-	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 {
+	if err := checkYAMLDepth(file.Docs[0].Body, 0, maxDepth, MaxYAMLNodes, make(map[ast.Node]int), make(map[ast.Node]bool), &nodeCount); err != nil {
 		return err
 	}
 
 	// Second pass: decode with strict field checking enabled.
-	// KnownFields(true) rejects unknown keys, catching typos like "focuss" or "identiy".
+	// Strict() 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.
+	// Safety note: goccy/go-yaml's decoder does not expand YAML aliases
-	strictDec := yaml.NewDecoder(bytes.NewReader(data))
+	// recursively — it resolves them via the pre-built AST, which our first
-	strictDec.KnownFields(true)
+	// pass already depth-checked. Alias chains that would exceed depth limits
-	return strictDec.Decode(out)
+	// are caught above; the decoder merely reads the resolved scalar values.
+	dec := yaml.NewDecoder(bytes.NewReader(data), yaml.Strict())
+	return dec.Decode(out)
 }
 
-// checkYAMLDepth recursively checks that YAML nodes don't exceed the depth limit
+// checkYAMLDepth recursively checks that YAML AST nodes don't exceed the depth
-// or the total node count limit. It also detects alias cycles to prevent infinite
+// limit or the total node count limit. It uses two tracking maps:
-// recursion from crafted YAML with self-referential aliases.
+//   - validated: maps each node to the maximum depth at which it was previously
-func checkYAMLDepth(node *yaml.Node, depth, maxDepth, maxNodes int, seen map[*yaml.Node]struct{}, nodeCount *int) error {
+//     checked. If a node is revisited at a deeper depth (e.g., via an alias),
+//     we re-check it to ensure the combined effective depth doesn't exceed limits.
+//   - visiting: per-path recursion stack for true cycle detection. A node on the
+//     current path is a cycle (alias loop); we return nil to avoid infinite recursion.
+//
+// This design prevents the alias depth bypass where an anchored subtree validated
+// at a shallow depth could be referenced via alias at a greater depth, effectively
+// exceeding MaxYAMLDepth.
+func checkYAMLDepth(node ast.Node, depth, maxDepth, maxNodes int, validated map[ast.Node]int, visiting map[ast.Node]bool, nodeCount *int) error {
+	if node == nil {
+		return nil
+	}
+
 	if depth > maxDepth {
 		return fmt.Errorf("YAML nesting depth exceeds maximum (%d)", maxDepth)
 	}
 
+	// Cycle detection: if we're currently visiting this node on the current
+	// recursion path, it's a cycle (e.g., alias pointing to an ancestor).
+	// Return nil to break the cycle without error — cycles are a structural
+	// property, not a depth violation.
+	if visiting[node] {
+		return nil
+	}
+
 	// Track total nodes visited as defense-in-depth against wide-but-shallow attacks.
+	// Placed after cycle detection but before the depth-aware short-circuit. This means
+	// nodes revisited at shallower depths (via aliases) are counted each time they are
+	// encountered — intentional conservative overcounting. This bounds the total work
+	// performed during validation rather than tracking unique nodes, which is the safer
+	// security posture for untrusted YAML input.
 	*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.
+	// Depth-aware short-circuit: skip re-validation only when the current visit
-	if _, ok := seen[node]; ok {
+	// depth is the same or shallower than the depth at which this node was
-		return nil // Already validated this subtree, skip to avoid infinite recursion.
+	// previously validated. A shallower (or equal) current depth means the
+	// prior, deeper validation already covered any subtree depth violations.
+	// If the current depth exceeds the previous validation depth (e.g., an alias
+	// references this node deeper in the tree), we must re-traverse to ensure
+	// the combined effective depth doesn't exceed maxDepth.
+	//
+	// Note: using ast.Node (interface) as map key relies on pointer identity,
+	// which is correct because all goccy/go-yaml AST node types are pointer
+	// receivers (*MappingNode, *SequenceNode, etc.), never value types.
+	if prevDepth, ok := validated[node]; ok && depth <= prevDepth {
+		return nil
 	}
-	seen[node] = struct{}{}
+	validated[node] = depth
 
-	// Handle alias nodes: follow the alias to its anchor target.
+	// Mark as visiting (on the current recursion path) for cycle detection.
-	// Increment depth when following aliases since they expand the effective structure.
+	visiting[node] = true
-	if node.Kind == yaml.AliasNode && node.Alias != nil {
+	defer func() { visiting[node] = false }()
-		return checkYAMLDepth(node.Alias, depth+1, maxDepth, maxNodes, seen, nodeCount)
-	}
 
-	for _, child := range node.Content {
+	// Walk children based on node type.
-		if err := checkYAMLDepth(child, depth+1, maxDepth, maxNodes, seen, nodeCount); err != nil {
+	switch n := node.(type) {
+	case *ast.MappingNode:
+		for _, value := range n.Values {
+			if err := checkYAMLDepth(value, depth+1, maxDepth, maxNodes, validated, visiting, nodeCount); err != nil {
+				return err
+			}
+		}
+	case *ast.MappingValueNode:
+		// Both Key and Value are visited at depth+1 relative to this
+		// MappingValueNode. Since MappingNode visits its MappingValueNode
+		// children at depth+1 as well, keys and values end up at depth+2
+		// from the parent MappingNode. This is intentional: it mirrors the
+		// actual nesting structure (mapping → key-value pair → key/value).
+		if err := checkYAMLDepth(n.Key, depth+1, maxDepth, maxNodes, validated, visiting, nodeCount); err != nil {
 			return err
 		}
+		if err := checkYAMLDepth(n.Value, depth+1, maxDepth, maxNodes, validated, visiting, nodeCount); err != nil {
+			return err
+		}
+	case *ast.SequenceNode:
+		for _, value := range n.Values {
+			if err := checkYAMLDepth(value, depth+1, maxDepth, maxNodes, validated, visiting, nodeCount); err != nil {
+				return err
+			}
+		}
+	case *ast.AliasNode:
+		// Follow alias to its target, incrementing depth since aliases expand
+		// the effective structure.
+		if err := checkYAMLDepth(n.Value, depth+1, maxDepth, maxNodes, validated, visiting, nodeCount); err != nil {
+			return err
+		}
+	case *ast.AnchorNode:
+		// Increment depth for anchor values as a conservative measure: the
+		// anchor definition itself is structural, and treating it as a depth
+		// level ensures that deeply nested anchors are caught at definition
+		// time rather than only when referenced via alias. This +1 is
+		// asymmetric with alias (which also increments) — by design, the
+		// effective depth budget for anchored-then-aliased content is reduced
+		// because both the definition site and the reference site each consume
+		// a level, making deeply nested anchor/alias pairs hit the limit sooner.
+		if err := checkYAMLDepth(n.Value, depth+1, maxDepth, maxNodes, validated, visiting, nodeCount); err != nil {
+			return err
+		}
+	case *ast.TagNode:
+		if err := checkYAMLDepth(n.Value, depth+1, maxDepth, maxNodes, validated, visiting, nodeCount); err != nil {
+			return err
+		}
+	case *ast.MergeKeyNode:
+		// MergeKeyNode represents the literal "<<" merge key token. It has no
+		// child nodes — the value side of a merge (e.g., *alias) lives in the
+		// parent MappingValueNode.Value, which is already recursed into above.
+		// Explicitly listed here (rather than in the default case) to prevent
+		// future library changes from silently bypassing depth checks.
+	default:
+		// Scalar leaf nodes (StringNode, IntegerNode, FloatNode, BoolNode,
+		// NullNode, InfinityNode, NanNode, LiteralNode) have no children to
+		// recurse into.
 	}
 	return nil
 }
@@ -227,7 +331,11 @@ func checkYAMLDepth(node *yaml.Node, depth, maxDepth, maxNodes int, seen map[*ya
 // 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.
+// Input is bounded by MaxPersonaFileSize to prevent resource exhaustion.
 func ParsePersonaBytes(data []byte, source string) (*Persona, error) {
+	if len(data) > MaxPersonaFileSize {
+		return nil, fmt.Errorf("persona data from %s exceeds maximum size (%d bytes, limit %d)", source, len(data), MaxPersonaFileSize)
+	}
 	return parsePersona(data, source)
 }
 

review/persona_test.go

@@ -7,7 +7,7 @@ import (
 	"strings"
 	"testing"
 
-	"gopkg.in/yaml.v3"
+	"github.com/goccy/go-yaml/ast"
 )
 
 func TestLoadBuiltinPersona(t *testing.T) {
@@ -355,7 +355,7 @@ func TestCapitalizeFirst(t *testing.T) {
 		{"HELLO", "HELLO"},
 		{"a", "A"},
 		{"", ""},
-		{"日本語", "日本語"}, // Non-ASCII: Japanese doesn't have case
+		{"日本語", "日本語"},     // Non-ASCII: Japanese doesn't have case
 		{"über", "Über"},   // German umlaut
 		{"élève", "Élève"}, // French accent
 	}
@@ -459,7 +459,14 @@ func TestYAMLDeeplyNestedRejection(t *testing.T) {
 	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).
+	// Depth accumulation trace for "nested: \n  level0: \n    level1: ...":
+	//   - Document root parsed at depth 0
+	//   - Root MappingNode children (MappingValueNodes) visited at depth 1
+	//   - "nested" MappingValueNode: key at depth 2, value at depth 2
+	//   - Each levelN adds depth via MappingValueNode traversal (key + value)
+	//   - Exact depth per level depends on AST structure (MappingNode wrapping),
+	//     but 25 levels reliably exceeds MaxYAMLDepth (20) with comfortable margin.
+	// The test uses 25 levels rather than exactly 21 to avoid brittleness.
 	var sb strings.Builder
 	sb.WriteString("name: test\nidentity: test\nnested:\n")
 	indent := "  "
@@ -483,6 +490,35 @@ func TestYAMLDeeplyNestedRejection(t *testing.T) {
 	}
 }
 
+func TestYAMLEmptyFileRejection(t *testing.T) {
+	tests := []struct {
+		name    string
+		content string
+	}{
+		{"completely_empty", ""},
+		{"whitespace_only", "   \n\n  "},
+		{"comment_only", "# just a comment\n"},
+	}
+
+	for _, tc := range tests {
+		t.Run(tc.name, func(t *testing.T) {
+			dir := t.TempDir()
+			path := filepath.Join(dir, tc.name+".yaml")
+			if err := os.WriteFile(path, []byte(tc.content), 0644); err != nil {
+				t.Fatalf("failed to write test file: %v", err)
+			}
+
+			_, err := LoadPersona(path)
+			if err == nil {
+				t.Fatal("expected error for empty YAML input, got nil")
+			}
+			if !strings.Contains(err.Error(), "empty YAML document") {
+				t.Errorf("expected error containing %q, got: %v", "empty YAML document", err)
+			}
+		})
+	}
+}
+
 func TestYAMLFileSizeLimit(t *testing.T) {
 	dir := t.TempDir()
 	path := filepath.Join(dir, "huge.yaml")
@@ -504,41 +540,41 @@ func TestYAMLFileSizeLimit(t *testing.T) {
 
 func TestYAMLAliasCycleDetection(t *testing.T) {
 	// Test that our checkYAMLDepth function handles alias cycles gracefully
-	// by using the seen map to prevent infinite recursion.
+	// by using the visiting 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
+	// simulating what could happen with crafted input.
-	// go-yaml's cycle detection.
+	parent := &ast.MappingNode{
-	parent := &yaml.Node{
+		Values: []*ast.MappingValueNode{
-		Kind: yaml.MappingNode,
+			{
-		Content: []*yaml.Node{
+				Key:   &ast.StringNode{Value: "name"},
-			{Kind: yaml.ScalarNode, Value: "name"},
+				Value: &ast.StringNode{Value: "test"},
-			{Kind: yaml.ScalarNode, Value: "test"},
+			},
-			{Kind: yaml.ScalarNode, Value: "nested"},
 		},
 	}
 
 	// Create a child that aliases back to the parent (artificial cycle)
-	aliasToParent := &yaml.Node{
+	aliasToParent := &ast.AliasNode{
-		Kind:  yaml.AliasNode,
+		Value: parent,
-		Alias: parent,
 	}
-	parent.Content = append(parent.Content, aliasToParent)
+	parent.Values = append(parent.Values, &ast.MappingValueNode{
+		Key:   &ast.StringNode{Value: "nested"},
+		Value: aliasToParent,
+	})
 
 	nodeCount := 0
-	seen := make(map[*yaml.Node]struct{})
+	validated := make(map[ast.Node]int)
+	visiting := make(map[ast.Node]bool)
 
-	// This should NOT hang or stack overflow - the seen map prevents infinite recursion
+	// This should NOT hang or stack overflow - cycle detection prevents infinite recursion
-	err := checkYAMLDepth(parent, 0, MaxYAMLDepth, MaxYAMLNodes, seen, &nodeCount)
+	err := checkYAMLDepth(parent, 0, MaxYAMLDepth, MaxYAMLNodes, validated, visiting, &nodeCount)
 	if err != nil {
 		t.Errorf("unexpected error traversing cyclic structure: %v", err)
 	}
 
-	// Verify we tracked the parent in the seen map
+	// Verify we tracked the parent in the validated map
-	if _, ok := seen[parent]; !ok {
+	if _, ok := validated[parent]; !ok {
-		t.Error("parent node not tracked in seen map")
+		t.Error("parent node not tracked in validated map")
 	}
 }
 
@@ -594,36 +630,82 @@ func TestYAMLNodeCountLimit(t *testing.T) {
 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 := &ast.MappingNode{
-	node := &yaml.Node{
+		Values: []*ast.MappingValueNode{
-		Kind: yaml.MappingNode,
+			{
-		Content: []*yaml.Node{
+				Key:   &ast.StringNode{Value: "key"},
-			{Kind: yaml.ScalarNode, Value: "key"},
+				Value: &ast.StringNode{Value: "value"},
-			{Kind: yaml.ScalarNode, Value: "value"},
+			},
 		},
 	}
 
 	// Create a cycle by making a child reference the parent
-	cycleChild := &yaml.Node{
+	cycleChild := &ast.AliasNode{
-		Kind:  yaml.AliasNode,
+		Value: node, // Points back to the parent
-		Alias: node, // Points back to the parent
 	}
-	node.Content = append(node.Content,
+	node.Values = append(node.Values, &ast.MappingValueNode{
-		&yaml.Node{Kind: yaml.ScalarNode, Value: "cyclic"},
+		Key:   &ast.StringNode{Value: "cyclic"},
-		cycleChild,
+		Value: cycleChild,
-	)
+	})
 
 	nodeCount := 0
-	seen := make(map[*yaml.Node]struct{})
+	validated := make(map[ast.Node]int)
-	err := checkYAMLDepth(node, 0, MaxYAMLDepth, MaxYAMLNodes, seen, &nodeCount)
+	visiting := make(map[ast.Node]bool)
+	err := checkYAMLDepth(node, 0, MaxYAMLDepth, MaxYAMLNodes, validated, visiting, &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
+	// The validated map should contain multiple entries
-	if len(seen) < 2 {
+	if len(validated) < 2 {
-		t.Errorf("seen map has %d entries, expected at least 2", len(seen))
+		t.Errorf("validated map has %d entries, expected at least 2", len(validated))
+	}
+}
+
+func TestYAMLAliasDepthBypass(t *testing.T) {
+	// Test that an anchored subtree first validated at a shallow depth is
+	// re-checked when referenced via alias at a deeper position. Without the
+	// depth-aware validated map, the alias reference would skip re-checking
+	// and allow the effective nesting to exceed MaxYAMLDepth.
+
+	dir := t.TempDir()
+	path := filepath.Join(dir, "alias-depth-bypass.yaml")
+
+	// Build YAML with an anchor at shallow depth containing a subtree near the limit,
+	// then reference it via alias deep enough that effective depth exceeds MaxYAMLDepth.
+	var sb strings.Builder
+	sb.WriteString("name: test\nidentity: test\n")
+
+	// Create the anchored subtree at depth 1 (key level) that nests 15 levels deep.
+	sb.WriteString("anchor_key: &deep_anchor\n")
+	for i := 0; i < 15; i++ {
+		sb.WriteString(strings.Repeat("  ", i+1))
+		sb.WriteString(fmt.Sprintf("level%d:\n", i))
+	}
+	sb.WriteString(strings.Repeat("  ", 16))
+	sb.WriteString("leaf: value\n")
+
+	// Create a wrapper that nests 6 levels deep, then references the anchor.
+	// Effective depth at alias target = 6 (wrapper nesting) + 1 (alias) + 15 (subtree) = 22 > 20
+	sb.WriteString("wrapper:\n")
+	for i := 0; i < 6; i++ {
+		sb.WriteString(strings.Repeat("  ", i+1))
+		sb.WriteString(fmt.Sprintf("n%d:\n", i))
+	}
+	sb.WriteString(strings.Repeat("  ", 7))
+	sb.WriteString("alias_ref: *deep_anchor\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.Fatal("expected error for alias depth bypass, got nil")
+	}
+	if !strings.Contains(err.Error(), "nesting depth exceeds") {
+		t.Errorf("error = %q, want containing 'nesting depth exceeds'", err.Error())
 	}
 }
 
@@ -776,3 +858,102 @@ identity: test identity
 		t.Errorf("Name = %q, want %q", p.Name, "test")
 	}
 }
+
+func TestJSONTrailingContentRejected(t *testing.T) {
+	tests := []struct {
+		name    string
+		content string
+	}{
+		{
+			name:    "trailing garbage after object",
+			content: `{"name":"test","identity":"test identity"}garbage`,
+		},
+		{
+			name:    "two JSON objects",
+			content: `{"name":"test","identity":"test identity"}{"name":"other"}`,
+		},
+		{
+			name:    "trailing array",
+			content: `{"name":"test","identity":"test identity"}[]`,
+		},
+	}
+
+	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 trailing content, got nil")
+			}
+			if !strings.Contains(err.Error(), "trailing content") {
+				t.Errorf("error = %q, want to contain 'trailing content'", err.Error())
+			}
+		})
+	}
+}
+
+func TestParsePersonaBytesSizeLimit(t *testing.T) {
+	// ParsePersonaBytes should reject input exceeding MaxPersonaFileSize
+	oversized := make([]byte, MaxPersonaFileSize+1)
+	for i := range oversized {
+		oversized[i] = 'x'
+	}
+
+	_, err := ParsePersonaBytes(oversized, "oversized.yaml")
+	if err == nil {
+		t.Fatal("expected error for oversized input, got nil")
+	}
+	if !strings.Contains(err.Error(), "exceeds maximum size") {
+		t.Errorf("error = %q, want to contain 'exceeds maximum size'", err.Error())
+	}
+
+	// Just under the limit should not trigger size error (may fail parse, but not size)
+	underLimit := []byte("name: test\nidentity: test persona\n")
+	p, err := ParsePersonaBytes(underLimit, "valid.yaml")
+	if err != nil {
+		t.Fatalf("unexpected error for valid input: %v", err)
+	}
+	if p.Name != "test" {
+		t.Errorf("Name = %q, want %q", p.Name, "test")
+	}
+}
+
+func TestYAMLMergeKeyDepthCheck(t *testing.T) {
+	// Verify that YAML merge keys (<<: *alias) are properly handled by the
+	// depth checker. The merge key content is in the MappingValueNode.Value
+	// (an AliasNode), not in the MergeKeyNode itself.
+	p, err := ParsePersonaBytes([]byte("name: merge-test\nidentity: test\n"), "merge.yaml")
+	if err != nil {
+		t.Fatalf("basic parse failed: %v", err)
+	}
+	if p.Name != "merge-test" {
+		t.Errorf("Name = %q, want %q", p.Name, "merge-test")
+	}
+
+	// Test that deeply nested merge keys still hit depth limit.
+	// Build YAML with merge key content nested beyond MaxYAMLDepth.
+	var sb strings.Builder
+	sb.WriteString("name: deep-merge\nidentity: deep merge persona\n")
+	sb.WriteString("anchor: &deep\n")
+	indent := "  "
+	for i := 0; i < MaxYAMLDepth+5; i++ {
+		sb.WriteString(indent)
+		sb.WriteString(fmt.Sprintf("level%d:\n", i))
+		indent += "  "
+	}
+	sb.WriteString(indent + "leaf: value\n")
+	sb.WriteString("target:\n  <<: *deep\n")
+
+	_, err = ParsePersonaBytes([]byte(sb.String()), "deep-merge.yaml")
+	if err == nil {
+		t.Fatal("expected error for deeply nested merge key content, got nil")
+	}
+	if !strings.Contains(err.Error(), "depth") {
+		t.Errorf("error = %q, want to contain 'depth'", err.Error())
+	}
+}

vcs/interfaces.go

@@ -41,3 +41,11 @@ type Client interface {
 	Reviewer
 	Identity
 }
+
+// ReviewerSelfRequester is an optional interface implemented by adapters that support
+// requesting the authenticated user as a reviewer on a pull request. This is used for
+// Gitea-specific behavior (ensuring the bot appears in required-reviewer checks).
+// Consumers should use interface assertion: if sr, ok := client.(ReviewerSelfRequester); ok { ... }
+type ReviewerSelfRequester interface {
+	RequestReviewerSelf(ctx context.Context, owner, repo string, number int, user string) error
+}