Compare commits
29 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
| e7efbe2204 | |||
| d9179c27ea | |||
| 8e3c31cce7 | |||
| e72bda0110 | |||
| 8eeab96364 | |||
| b7f108faf6 | |||
| 528d29b63d | |||
| 0e503357ed | |||
| f50920333f | |||
| b47bab08d6 | |||
| 550ba44354 | |||
| 6a3f63a726 | |||
| 0ea9c93af6 | |||
| bee4d98b8c | |||
| 691788833e | |||
| d8c8a743ed | |||
| 629e29806c | |||
| 787ac3b736 | |||
| 1200ef700d | |||
| 5e36547a1c | |||
| 0522cfe3cb | |||
| ee84c64151 | |||
| 3a1e5e443e | |||
| 9b1e93bfde | |||
| dbbc7bda6a | |||
| 93e2fbd58d | |||
| 6f4461b0f7 | |||
| 32c89330aa | |||
| 2036f57011 |
+1
-1
@@ -9,7 +9,7 @@
|
|||||||
|
|
||||||
| Package | Use Case | Scope |
|
| 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 |
|
| `github.com/google/go-cmp` | Test comparisons (`cmp.Diff`) | test only |
|
||||||
|
|
||||||
**Any import not in this table or the Go standard library is forbidden.**
|
**Any import not in this table or the Go standard library is forbidden.**
|
||||||
|
|||||||
+152
-29
@@ -2,6 +2,7 @@ package main
|
|||||||
|
|
||||||
import (
|
import (
|
||||||
"context"
|
"context"
|
||||||
|
"errors"
|
||||||
"flag"
|
"flag"
|
||||||
"fmt"
|
"fmt"
|
||||||
"log/slog"
|
"log/slog"
|
||||||
@@ -70,7 +71,7 @@ func main() {
|
|||||||
conventionsFile := flag.String("conventions-file", envOrDefault("CONVENTIONS_FILE", ""), "Conventions file path in repo (e.g. CLAUDE.md)")
|
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")
|
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)")
|
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")
|
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)")
|
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)")
|
llmTimeout := flag.Int("llm-timeout", envOrDefaultInt("LLM_TIMEOUT", 300), "LLM request timeout in seconds (default 300)")
|
||||||
@@ -84,9 +85,16 @@ func main() {
|
|||||||
aicoreAPIURL := flag.String("aicore-api-url", envOrDefault("AICORE_API_URL", ""), "SAP AI Core API URL (for provider=aicore)")
|
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)")
|
aicoreResourceGroup := flag.String("aicore-resource-group", envOrDefault("AICORE_RESOURCE_GROUP", "default"), "SAP AI Core resource group (for provider=aicore)")
|
||||||
|
|
||||||
// Backward-compatible alias: --gitea-url shares vcsURL's pointer (last flag wins).
|
// Register --gitea-url as a backward-compatible alias for --vcs-url.
|
||||||
// Must use *vcsURL as default: StringVar sets *p=value at registration, so empty
|
// StringVar shares the *string pointer with vcsURL, so whichever flag is
|
||||||
// string would overwrite the env-resolved value from the --vcs-url declaration.
|
// 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.StringVar(vcsURL, "gitea-url", *vcsURL, "Deprecated: use --vcs-url instead")
|
||||||
|
|
||||||
flag.Parse()
|
flag.Parse()
|
||||||
@@ -102,8 +110,10 @@ func main() {
|
|||||||
slog.Info("review-bot starting", "version", version)
|
slog.Info("review-bot starting", "version", version)
|
||||||
|
|
||||||
// Validate VCS provider
|
// Validate VCS provider
|
||||||
vcsProvider := vcs.VCSProvider(*provider)
|
switch *provider {
|
||||||
if !vcsProvider.Valid() {
|
case "gitea", "github":
|
||||||
|
// valid
|
||||||
|
default:
|
||||||
fmt.Fprintf(os.Stderr, "Error: invalid --provider %q (valid: gitea, github)\n", *provider)
|
fmt.Fprintf(os.Stderr, "Error: invalid --provider %q (valid: gitea, github)\n", *provider)
|
||||||
os.Exit(1)
|
os.Exit(1)
|
||||||
}
|
}
|
||||||
@@ -116,7 +126,7 @@ func main() {
|
|||||||
os.Exit(1)
|
os.Exit(1)
|
||||||
}
|
}
|
||||||
// --vcs-url is required only for gitea provider
|
// --vcs-url is required only for gitea provider
|
||||||
if vcsProvider == vcs.ProviderGitea && *vcsURL == "" {
|
if *provider == "gitea" && *vcsURL == "" {
|
||||||
fmt.Fprintf(os.Stderr, "Error: --vcs-url (or --gitea-url) is required for provider=gitea\n")
|
fmt.Fprintf(os.Stderr, "Error: --vcs-url (or --gitea-url) is required for provider=gitea\n")
|
||||||
os.Exit(1)
|
os.Exit(1)
|
||||||
}
|
}
|
||||||
@@ -159,16 +169,18 @@ func main() {
|
|||||||
|
|
||||||
// Initialize VCS client
|
// Initialize VCS client
|
||||||
var client vcs.Client
|
var client vcs.Client
|
||||||
switch vcsProvider {
|
switch *provider {
|
||||||
case vcs.ProviderGitea:
|
case "gitea":
|
||||||
giteaClient := gitea.NewClient(*vcsURL, *reviewerToken)
|
giteaClient := gitea.NewClient(*vcsURL, *reviewerToken)
|
||||||
client = gitea.NewAdapter(giteaClient)
|
client = gitea.NewAdapter(giteaClient)
|
||||||
case vcs.ProviderGitHub:
|
case "github":
|
||||||
client = github.NewClient(*reviewerToken, *baseURL)
|
ghBaseURL := *baseURL
|
||||||
default:
|
if ghBaseURL == "" {
|
||||||
panic("unreachable: provider validation should have caught " + vcsProvider.String())
|
ghBaseURL = "https://api.github.com"
|
||||||
|
}
|
||||||
|
client = github.NewClient(*reviewerToken, ghBaseURL)
|
||||||
}
|
}
|
||||||
slog.Info("VCS client initialized", "provider", vcsProvider)
|
slog.Info("VCS client initialized", "provider", *provider)
|
||||||
|
|
||||||
// Initialize LLM client
|
// Initialize LLM client
|
||||||
llmClient := llm.NewClient(*llmBaseURL, *llmAPIKey, *llmModel)
|
llmClient := llm.NewClient(*llmBaseURL, *llmAPIKey, *llmModel)
|
||||||
@@ -494,15 +506,11 @@ func main() {
|
|||||||
}
|
}
|
||||||
slog.Info("review posted", "review_id", posted.ID, "user", posted.User.Login, "pr", prNumber)
|
slog.Info("review posted", "review_id", posted.ID, "user", posted.User.Login, "pr", prNumber)
|
||||||
|
|
||||||
// Supersede all old reviews via optional interface
|
// Supersede all old reviews
|
||||||
if len(oldReviews) > 0 {
|
if len(oldReviews) > 0 {
|
||||||
if superseder, ok := client.(vcs.ReviewSuperseder); ok {
|
if err := supersedeOldReviews(ctx, client, *provider, *vcsURL, owner, repoName, prNumber, oldReviews, posted.ID, sentinel); err != nil {
|
||||||
if err := superseder.SupersedeReviews(ctx, owner, repoName, prNumber, oldReviews, posted.ID, *vcsURL, sentinel); err != nil {
|
slog.Error("failed to supersede old reviews", "error", err)
|
||||||
slog.Error("failed to supersede old reviews", "error", err)
|
os.Exit(1)
|
||||||
os.Exit(1)
|
|
||||||
}
|
|
||||||
} else {
|
|
||||||
slog.Error("provider does not support review superseding", "provider", vcsProvider)
|
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
@@ -519,6 +527,88 @@ func verdictToEvent(verdict string) vcs.ReviewEvent {
|
|||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
|
// 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.
|
// fetchFileContext fetches the full content of modified files from the PR branch.
|
||||||
func fetchFileContext(ctx context.Context, client vcs.PRReader, owner, repo, ref string, files []vcs.ChangedFile) string {
|
func fetchFileContext(ctx context.Context, client vcs.PRReader, owner, repo, ref string, files []vcs.ChangedFile) string {
|
||||||
var sb strings.Builder
|
var sb strings.Builder
|
||||||
@@ -546,12 +636,25 @@ func fetchFileContext(ctx context.Context, client vcs.PRReader, owner, repo, ref
|
|||||||
// patternsRepo is comma-separated list of owner/name repos.
|
// patternsRepo is comma-separated list of owner/name repos.
|
||||||
// patternsFiles is comma-separated list of file paths or directories.
|
// 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.
|
// If a path ends with / or is a directory, all files within it are fetched recursively.
|
||||||
// Empty entries in patternsFiles are skipped (no implicit repo-root fetch).
|
// If patternsFiles is empty, all files from the repo root are fetched.
|
||||||
func fetchPatterns(ctx context.Context, client vcs.FileReader, patternsRepo, patternsFiles string) string {
|
func fetchPatterns(ctx context.Context, client vcs.FileReader, patternsRepo, patternsFiles string) string {
|
||||||
var sb strings.Builder
|
var sb strings.Builder
|
||||||
|
|
||||||
repos := strings.Split(patternsRepo, ",")
|
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 {
|
for _, repoRef := range repos {
|
||||||
if ctx.Err() != nil {
|
if ctx.Err() != nil {
|
||||||
@@ -572,11 +675,6 @@ func fetchPatterns(ctx context.Context, client vcs.FileReader, patternsRepo, pat
|
|||||||
var repoSkippedFiles []string
|
var repoSkippedFiles []string
|
||||||
|
|
||||||
for _, path := range paths {
|
for _, path := range paths {
|
||||||
path = strings.TrimSpace(path)
|
|
||||||
if path == "" {
|
|
||||||
continue
|
|
||||||
}
|
|
||||||
|
|
||||||
files, err := vcs.GetAllFilesInPath(ctx, client, owner, repo, path)
|
files, err := vcs.GetAllFilesInPath(ctx, client, owner, repo, path)
|
||||||
if err != nil {
|
if err != nil {
|
||||||
slog.Warn("could not fetch patterns", "path", path, "repo", repoRef, "error", err)
|
slog.Warn("could not fetch patterns", "path", path, "repo", repoRef, "error", err)
|
||||||
@@ -722,6 +820,31 @@ func validateWorkspacePath(path, pathName string) (string, error) {
|
|||||||
return resolvedPath, nil
|
return resolvedPath, nil
|
||||||
}
|
}
|
||||||
|
|
||||||
|
// buildSupersededBody creates the body for a superseded review: struck-through banner
|
||||||
|
// with collapsed original content and the commit it was evaluated against.
|
||||||
|
func buildSupersededBody(originalBody, commitSHA, newReviewURL, sentinel string) string {
|
||||||
|
shortSHA := commitSHA
|
||||||
|
if len(shortSHA) > 8 {
|
||||||
|
shortSHA = shortSHA[:8]
|
||||||
|
}
|
||||||
|
var sb strings.Builder
|
||||||
|
sb.WriteString("~~Original review~~\n\n")
|
||||||
|
sb.WriteString("**Superseded** \u2014 [see current review](")
|
||||||
|
sb.WriteString(newReviewURL)
|
||||||
|
sb.WriteString(") for up-to-date findings.\n\n")
|
||||||
|
if shortSHA != "" {
|
||||||
|
sb.WriteString("<details><summary>Previous findings (commit ")
|
||||||
|
sb.WriteString(shortSHA)
|
||||||
|
sb.WriteString(")</summary>\n\n")
|
||||||
|
} else {
|
||||||
|
sb.WriteString("<details><summary>Previous findings</summary>\n\n")
|
||||||
|
}
|
||||||
|
sb.WriteString(originalBody)
|
||||||
|
sb.WriteString("\n\n</details>\n\n")
|
||||||
|
sb.WriteString(sentinel)
|
||||||
|
return sb.String()
|
||||||
|
}
|
||||||
|
|
||||||
// hasSharedToken detects if another review-bot role posted under the same
|
// hasSharedToken detects if another review-bot role posted under the same
|
||||||
// VCS 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 accounts. Returns true if shared token
|
// instead of having separate accounts. Returns true if shared token
|
||||||
|
|||||||
@@ -162,6 +162,54 @@ func makeReview(id int64, login, state string, stale bool, body string) vcs.Revi
|
|||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
|
func TestBuildSupersededBody(t *testing.T) {
|
||||||
|
original := "# Review\n\nLooks good.\n\n<!-- review-bot:sonnet -->"
|
||||||
|
sentinel := "<!-- review-bot:sonnet -->"
|
||||||
|
newURL := "https://gitea.example.com/owner/repo/pulls/1#pullrequestreview-99"
|
||||||
|
|
||||||
|
result := buildSupersededBody(original, "abcdef1234567890", newURL, sentinel)
|
||||||
|
|
||||||
|
// Should contain the struck-through banner
|
||||||
|
if !strings.Contains(result, "~~Original review~~") {
|
||||||
|
t.Error("missing struck-through banner")
|
||||||
|
}
|
||||||
|
// Should contain superseded notice with link
|
||||||
|
if !strings.Contains(result, "**Superseded**") {
|
||||||
|
t.Error("missing superseded notice")
|
||||||
|
}
|
||||||
|
if !strings.Contains(result, "[see current review]("+newURL+")") {
|
||||||
|
t.Error("missing link to new review")
|
||||||
|
}
|
||||||
|
// Should contain collapsed original
|
||||||
|
if !strings.Contains(result, "<details>") {
|
||||||
|
t.Error("missing details/collapse")
|
||||||
|
}
|
||||||
|
// Should contain short commit SHA
|
||||||
|
if !strings.Contains(result, "abcdef12") {
|
||||||
|
t.Error("missing short SHA")
|
||||||
|
}
|
||||||
|
// Should NOT contain full SHA
|
||||||
|
if strings.Contains(result, "abcdef1234567890") {
|
||||||
|
t.Error("should truncate SHA to 8 chars")
|
||||||
|
}
|
||||||
|
// Should contain the original body inside details
|
||||||
|
if !strings.Contains(result, original) {
|
||||||
|
t.Error("original body not preserved in collapsed section")
|
||||||
|
}
|
||||||
|
// Should end with sentinel
|
||||||
|
if !strings.Contains(result, sentinel) {
|
||||||
|
t.Error("missing sentinel")
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
func TestBuildSupersededBodyShortSHA(t *testing.T) {
|
||||||
|
// Short SHA should pass through without panic
|
||||||
|
result := buildSupersededBody("body", "abc", "https://example.com/review", "<!-- review-bot:x -->")
|
||||||
|
if !strings.Contains(result, "abc") {
|
||||||
|
t.Error("short SHA not preserved")
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
func TestHasSharedToken(t *testing.T) {
|
func TestHasSharedToken(t *testing.T) {
|
||||||
tests := []struct {
|
tests := []struct {
|
||||||
name string
|
name string
|
||||||
@@ -367,6 +415,52 @@ 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) {
|
func TestEvaluateCIStatus(t *testing.T) {
|
||||||
tests := []struct {
|
tests := []struct {
|
||||||
name string
|
name string
|
||||||
|
|||||||
@@ -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
|
- Backwards compatibility: existing JSON personas must continue to work
|
||||||
- Security: protect against DoS via deeply nested YAML (AIKIDO-2024-10486)
|
- Security: protect against DoS via deeply nested YAML (AIKIDO-2024-10486)
|
||||||
- Consistency: use `.yaml` extension (not `.yml`)
|
- 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
|
## Proposed Approach
|
||||||
|
|
||||||
@@ -33,37 +33,16 @@ func parsePersona(data []byte, source string) (*Persona, error) {
|
|||||||
|
|
||||||
### YAML Parsing with Depth Protection
|
### 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
|
## State/Data Model
|
||||||
|
|
||||||
@@ -74,7 +53,7 @@ No new state. Same `Persona` struct, just different parsing.
|
|||||||
| Error | Handling |
|
| Error | Handling |
|
||||||
|-------|----------|
|
|-------|----------|
|
||||||
| Invalid YAML syntax | Return parse error with source file |
|
| 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 |
|
| Unknown extension | Fall back to JSON parsing |
|
||||||
| Missing required fields | Validation rejects after parse |
|
| Missing required fields | Validation rejects after parse |
|
||||||
|
|
||||||
|
|||||||
@@ -3,8 +3,6 @@ package gitea
|
|||||||
import (
|
import (
|
||||||
"context"
|
"context"
|
||||||
"fmt"
|
"fmt"
|
||||||
"log/slog"
|
|
||||||
"strings"
|
|
||||||
|
|
||||||
"gitea.weiker.me/rodin/review-bot/vcs"
|
"gitea.weiker.me/rodin/review-bot/vcs"
|
||||||
)
|
)
|
||||||
@@ -239,78 +237,3 @@ func (a *Adapter) GetAuthenticatedUser(ctx context.Context) (string, error) {
|
|||||||
func (a *Adapter) RequestReviewerSelf(ctx context.Context, owner, repo string, number int, user string) error {
|
func (a *Adapter) RequestReviewerSelf(ctx context.Context, owner, repo string, number int, user string) error {
|
||||||
return a.client.RequestReviewer(ctx, owner, repo, number, user)
|
return a.client.RequestReviewer(ctx, owner, repo, number, user)
|
||||||
}
|
}
|
||||||
|
|
||||||
// Compile-time interface conformance assertion for ReviewSuperseder.
|
|
||||||
var _ vcs.ReviewSuperseder = (*Adapter)(nil)
|
|
||||||
|
|
||||||
// SupersedeReviews marks prior reviews as superseded by editing their body with a
|
|
||||||
// link to the new review and resolving their inline comments. This is Gitea-specific
|
|
||||||
// behavior that has no GitHub equivalent (GitHub uses DismissReview instead).
|
|
||||||
//
|
|
||||||
// baseURL is the Gitea instance URL used to construct review permalink URLs.
|
|
||||||
// sentinel is the HTML comment sentinel that identifies reviews belonging to this reviewer.
|
|
||||||
func (a *Adapter) SupersedeReviews(ctx context.Context, owner, repo string, prNumber int, oldReviews []vcs.Review, newReviewID int64, baseURL, sentinel string) error {
|
|
||||||
// Validate baseURL scheme before embedding in Markdown link (defense-in-depth).
|
|
||||||
if !strings.HasPrefix(baseURL, "http://") && !strings.HasPrefix(baseURL, "https://") {
|
|
||||||
return fmt.Errorf("SupersedeReviews: baseURL must have http or https scheme, got %q", baseURL)
|
|
||||||
}
|
|
||||||
|
|
||||||
underlying := a.client
|
|
||||||
|
|
||||||
newReviewURL := fmt.Sprintf("%s/%s/%s/pulls/%d#pullrequestreview-%d",
|
|
||||||
strings.TrimRight(baseURL, "/"), owner, repo, prNumber, newReviewID)
|
|
||||||
|
|
||||||
for _, oldReview := range oldReviews {
|
|
||||||
cid, err := underlying.GetTimelineReviewCommentIDForReview(ctx, owner, repo, 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, repo, cid, supersededBody); err != nil {
|
|
||||||
slog.Warn("could not mark old review as superseded", "review_id", oldReview.ID, "error", err)
|
|
||||||
continue
|
|
||||||
}
|
|
||||||
|
|
||||||
// Resolve old review's inline comments
|
|
||||||
oldComments, err := underlying.ListReviewComments(ctx, owner, repo, prNumber, oldReview.ID)
|
|
||||||
if err != nil {
|
|
||||||
slog.Warn("could not list old review comments for resolution", "review_id", oldReview.ID, "error", err)
|
|
||||||
continue
|
|
||||||
}
|
|
||||||
for _, c := range oldComments {
|
|
||||||
if c.ID == 0 {
|
|
||||||
continue
|
|
||||||
}
|
|
||||||
if err := underlying.ResolveComment(ctx, owner, repo, c.ID); err != nil {
|
|
||||||
slog.Debug("could not resolve inline comment", "comment_id", c.ID, "error", err)
|
|
||||||
}
|
|
||||||
}
|
|
||||||
}
|
|
||||||
return nil
|
|
||||||
}
|
|
||||||
|
|
||||||
// buildSupersededBody creates the body for a superseded review: struck-through banner
|
|
||||||
// with collapsed original content and the commit it was evaluated against.
|
|
||||||
func buildSupersededBody(originalBody, commitSHA, newReviewURL, sentinel string) string {
|
|
||||||
shortSHA := commitSHA
|
|
||||||
if len(shortSHA) > 8 {
|
|
||||||
shortSHA = shortSHA[:8]
|
|
||||||
}
|
|
||||||
var sb strings.Builder
|
|
||||||
sb.WriteString("~~Original review~~\n\n")
|
|
||||||
sb.WriteString("**Superseded** \u2014 [see current review](")
|
|
||||||
sb.WriteString(newReviewURL)
|
|
||||||
sb.WriteString(") for up-to-date findings.\n\n")
|
|
||||||
if shortSHA != "" {
|
|
||||||
sb.WriteString("<details><summary>Previous findings (commit ")
|
|
||||||
sb.WriteString(shortSHA)
|
|
||||||
sb.WriteString(")</summary>\n\n")
|
|
||||||
} else {
|
|
||||||
sb.WriteString("<details><summary>Previous findings</summary>\n\n")
|
|
||||||
}
|
|
||||||
sb.WriteString(originalBody)
|
|
||||||
sb.WriteString("\n\n</details>\n\n")
|
|
||||||
sb.WriteString(sentinel)
|
|
||||||
return sb.String()
|
|
||||||
}
|
|
||||||
|
|||||||
@@ -1,54 +0,0 @@
|
|||||||
package gitea
|
|
||||||
|
|
||||||
import (
|
|
||||||
"strings"
|
|
||||||
"testing"
|
|
||||||
)
|
|
||||||
|
|
||||||
func TestBuildSupersededBody(t *testing.T) {
|
|
||||||
original := "# Review\n\nLooks good.\n\n<!-- review-bot:sonnet -->"
|
|
||||||
sentinel := "<!-- review-bot:sonnet -->"
|
|
||||||
newURL := "https://gitea.example.com/owner/repo/pulls/1#pullrequestreview-99"
|
|
||||||
|
|
||||||
result := buildSupersededBody(original, "abcdef1234567890", newURL, sentinel)
|
|
||||||
|
|
||||||
// Should contain the struck-through banner
|
|
||||||
if !strings.Contains(result, "~~Original review~~") {
|
|
||||||
t.Error("missing struck-through banner")
|
|
||||||
}
|
|
||||||
// Should contain superseded notice with link
|
|
||||||
if !strings.Contains(result, "**Superseded**") {
|
|
||||||
t.Error("missing superseded notice")
|
|
||||||
}
|
|
||||||
if !strings.Contains(result, "[see current review]("+newURL+")") {
|
|
||||||
t.Error("missing link to new review")
|
|
||||||
}
|
|
||||||
// Should contain collapsed original
|
|
||||||
if !strings.Contains(result, "<details>") {
|
|
||||||
t.Error("missing details/collapse")
|
|
||||||
}
|
|
||||||
// Should contain short commit SHA
|
|
||||||
if !strings.Contains(result, "abcdef12") {
|
|
||||||
t.Error("missing short SHA")
|
|
||||||
}
|
|
||||||
// Should NOT contain full SHA in summary (it's truncated to 8)
|
|
||||||
if strings.Contains(result, "abcdef1234567890") {
|
|
||||||
t.Error("should truncate SHA to 8 chars")
|
|
||||||
}
|
|
||||||
// Should contain the original body inside details
|
|
||||||
if !strings.Contains(result, original) {
|
|
||||||
t.Error("original body not preserved in collapsed section")
|
|
||||||
}
|
|
||||||
// Should end with sentinel
|
|
||||||
if !strings.Contains(result, sentinel) {
|
|
||||||
t.Error("missing sentinel")
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
func TestBuildSupersededBodyShortSHA(t *testing.T) {
|
|
||||||
// Short SHA should pass through without panic
|
|
||||||
result := buildSupersededBody("body", "abc", "https://example.com/review", "<!-- review-bot:x -->")
|
|
||||||
if !strings.Contains(result, "abc") {
|
|
||||||
t.Error("short SHA not preserved")
|
|
||||||
}
|
|
||||||
}
|
|
||||||
@@ -9,6 +9,3 @@ import (
|
|||||||
// This verifies github.Client satisfies the full vcs.Client interface
|
// This verifies github.Client satisfies the full vcs.Client interface
|
||||||
// (PRReader, FileReader, Reviewer, Identity).
|
// (PRReader, FileReader, Reviewer, Identity).
|
||||||
var _ vcs.Client = (*github.Client)(nil)
|
var _ vcs.Client = (*github.Client)(nil)
|
||||||
|
|
||||||
// Verify github.Client implements ReviewSuperseder.
|
|
||||||
var _ vcs.ReviewSuperseder = (*github.Client)(nil)
|
|
||||||
|
|||||||
@@ -210,16 +210,3 @@ func (c *Client) DismissReview(ctx context.Context, owner, repo string, number i
|
|||||||
}
|
}
|
||||||
return nil
|
return nil
|
||||||
}
|
}
|
||||||
|
|
||||||
// SupersedeReviews marks prior reviews as superseded by dismissing them.
|
|
||||||
// This implements vcs.ReviewSuperseder for the GitHub adapter.
|
|
||||||
// The baseURL and sentinel parameters are unused for GitHub (dismissal is the mechanism).
|
|
||||||
func (c *Client) SupersedeReviews(ctx context.Context, owner, repo string, prNumber int, oldReviews []vcs.Review, newReviewID int64, _, _ string) error {
|
|
||||||
var errs []error
|
|
||||||
for _, old := range oldReviews {
|
|
||||||
if err := c.DismissReview(ctx, owner, repo, prNumber, old.ID, "Superseded by new review"); err != nil {
|
|
||||||
errs = append(errs, fmt.Errorf("dismiss review %d: %w", old.ID, err))
|
|
||||||
}
|
|
||||||
}
|
|
||||||
return errors.Join(errs...)
|
|
||||||
}
|
|
||||||
|
|||||||
@@ -2,4 +2,4 @@ module gitea.weiker.me/rodin/review-bot
|
|||||||
|
|
||||||
go 1.26.2
|
go 1.26.2
|
||||||
|
|
||||||
require gopkg.in/yaml.v3 v3.0.1
|
require github.com/goccy/go-yaml v1.19.2
|
||||||
|
|||||||
@@ -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=
|
|
||||||
|
|||||||
+146
-38
@@ -5,12 +5,15 @@ import (
|
|||||||
"embed"
|
"embed"
|
||||||
"encoding/json"
|
"encoding/json"
|
||||||
"fmt"
|
"fmt"
|
||||||
|
"io"
|
||||||
"os"
|
"os"
|
||||||
"sort"
|
"sort"
|
||||||
"strings"
|
"strings"
|
||||||
"unicode/utf8"
|
"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
|
//go:embed personas/*.yaml
|
||||||
@@ -118,9 +121,7 @@ func ListBuiltinPersonas() []string {
|
|||||||
default:
|
default:
|
||||||
continue
|
continue
|
||||||
}
|
}
|
||||||
if !seen[personaName] {
|
seen[personaName] = true
|
||||||
seen[personaName] = true
|
|
||||||
}
|
|
||||||
}
|
}
|
||||||
names := make([]string, 0, len(seen))
|
names := make([]string, 0, len(seen))
|
||||||
for name := range seen {
|
for name := range seen {
|
||||||
@@ -142,10 +143,19 @@ func parsePersona(data []byte, source string) (*Persona, error) {
|
|||||||
err = unmarshalYAMLWithDepthLimit(data, &p, MaxYAMLDepth)
|
err = unmarshalYAMLWithDepthLimit(data, &p, MaxYAMLDepth)
|
||||||
} else {
|
} else {
|
||||||
// Use json.Decoder with DisallowUnknownFields for consistency with
|
// 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 := json.NewDecoder(bytes.NewReader(data))
|
||||||
dec.DisallowUnknownFields()
|
dec.DisallowUnknownFields()
|
||||||
err = dec.Decode(&p)
|
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 {
|
if err != nil {
|
||||||
return nil, fmt.Errorf("parse persona %s: %w", source, err)
|
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
|
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 {
|
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
|
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
|
// Reject multi-document YAML files - silently ignoring additional documents
|
||||||
// could lead to confusing behavior where users think their changes take effect.
|
// 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")
|
return fmt.Errorf("multi-document YAML is not supported; only single-document files are allowed")
|
||||||
}
|
}
|
||||||
|
|
||||||
nodeCount := 0
|
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
|
return err
|
||||||
}
|
}
|
||||||
|
|
||||||
// Second pass: decode with strict field checking enabled.
|
// 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 {
|
if depth > maxDepth {
|
||||||
return fmt.Errorf("YAML nesting depth exceeds maximum (%d)", 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.
|
// 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++
|
*nodeCount++
|
||||||
if *nodeCount > maxNodes {
|
if *nodeCount > maxNodes {
|
||||||
return fmt.Errorf("YAML node count exceeds maximum (%d)", 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
|
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
|
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.
|
// 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)
|
// This is useful for parsing personas fetched from external sources (e.g., Gitea API)
|
||||||
// without requiring filesystem access. Format is detected by source extension.
|
// 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) {
|
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)
|
return parsePersona(data, source)
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|||||||
+222
-41
@@ -7,7 +7,7 @@ import (
|
|||||||
"strings"
|
"strings"
|
||||||
"testing"
|
"testing"
|
||||||
|
|
||||||
"gopkg.in/yaml.v3"
|
"github.com/goccy/go-yaml/ast"
|
||||||
)
|
)
|
||||||
|
|
||||||
func TestLoadBuiltinPersona(t *testing.T) {
|
func TestLoadBuiltinPersona(t *testing.T) {
|
||||||
@@ -459,7 +459,14 @@ func TestYAMLDeeplyNestedRejection(t *testing.T) {
|
|||||||
path := filepath.Join(dir, "deeply-nested.yaml")
|
path := filepath.Join(dir, "deeply-nested.yaml")
|
||||||
|
|
||||||
// Build a deeply nested YAML structure that exceeds MaxYAMLDepth (20).
|
// 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
|
var sb strings.Builder
|
||||||
sb.WriteString("name: test\nidentity: test\nnested:\n")
|
sb.WriteString("name: test\nidentity: test\nnested:\n")
|
||||||
indent := " "
|
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) {
|
func TestYAMLFileSizeLimit(t *testing.T) {
|
||||||
dir := t.TempDir()
|
dir := t.TempDir()
|
||||||
path := filepath.Join(dir, "huge.yaml")
|
path := filepath.Join(dir, "huge.yaml")
|
||||||
@@ -504,41 +540,41 @@ func TestYAMLFileSizeLimit(t *testing.T) {
|
|||||||
|
|
||||||
func TestYAMLAliasCycleDetection(t *testing.T) {
|
func TestYAMLAliasCycleDetection(t *testing.T) {
|
||||||
// Test that our checkYAMLDepth function handles alias cycles gracefully
|
// 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,
|
// 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)
|
// 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
|
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 {
|
if err != nil {
|
||||||
t.Errorf("unexpected error traversing cyclic structure: %v", err)
|
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) {
|
func TestCheckYAMLDepthCycleDetectionDirect(t *testing.T) {
|
||||||
// Direct test of cycle detection in checkYAMLDepth by creating
|
// Direct test of cycle detection in checkYAMLDepth by creating
|
||||||
// a node structure with an artificial cycle.
|
// 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
|
// 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
|
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
|
// Should complete without infinite recursion due to cycle detection
|
||||||
if err != nil {
|
if err != nil {
|
||||||
t.Errorf("unexpected error: %v", err)
|
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")
|
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())
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|||||||
@@ -49,12 +49,3 @@ type Client interface {
|
|||||||
type ReviewerSelfRequester interface {
|
type ReviewerSelfRequester interface {
|
||||||
RequestReviewerSelf(ctx context.Context, owner, repo string, number int, user string) error
|
RequestReviewerSelf(ctx context.Context, owner, repo string, number int, user string) error
|
||||||
}
|
}
|
||||||
|
|
||||||
// ReviewSuperseder is an optional interface implemented by adapters that support
|
|
||||||
// marking old reviews as superseded. For Gitea this means editing the review body
|
|
||||||
// with a link to the new review and resolving inline comments. For GitHub this
|
|
||||||
// means dismissing old reviews.
|
|
||||||
// Consumers should use interface assertion: if rs, ok := client.(ReviewSuperseder); ok { ... }
|
|
||||||
type ReviewSuperseder interface {
|
|
||||||
SupersedeReviews(ctx context.Context, owner, repo string, prNumber int, oldReviews []Review, newReviewID int64, baseURL, sentinel string) error
|
|
||||||
}
|
|
||||||
|
|||||||
@@ -1,26 +0,0 @@
|
|||||||
package vcs
|
|
||||||
|
|
||||||
// VCSProvider identifies a VCS platform. Using a typed string instead of bare
|
|
||||||
// strings makes provider values compiler-checkable and prevents typos from
|
|
||||||
// silently passing validation.
|
|
||||||
type VCSProvider string
|
|
||||||
|
|
||||||
const (
|
|
||||||
ProviderGitea VCSProvider = "gitea"
|
|
||||||
ProviderGitHub VCSProvider = "github"
|
|
||||||
)
|
|
||||||
|
|
||||||
// Valid reports whether p is a known VCS provider.
|
|
||||||
func (p VCSProvider) Valid() bool {
|
|
||||||
switch p {
|
|
||||||
case ProviderGitea, ProviderGitHub:
|
|
||||||
return true
|
|
||||||
default:
|
|
||||||
return false
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
// String returns the string representation of the provider.
|
|
||||||
func (p VCSProvider) String() string {
|
|
||||||
return string(p)
|
|
||||||
}
|
|
||||||
Reference in New Issue
Block a user