Compare commits

..

2 Commits

Author SHA1 Message Date
Rodin db13078196 chore: use dry-run in review.yml (GHE has no releases yet, validate infra)
PR Ready Gate / clear-labels (pull_request) Successful in 1s
CI / test (pull_request) Successful in 20s
CI / review (anthropic--claude-4.6-sonnet, sonnet, SONNET_REVIEW_TOKEN) (pull_request) Successful in 29s
CI / review (gpt-5, security, ., rodin/security-patterns, SECURITY_REVIEW.md, SECURITY_REVIEW_TOKEN) (pull_request) Successful in 1m2s
CI / review (gpt-5, gpt, GPT_REVIEW_TOKEN) (pull_request) Successful in 1m31s
The self-test workflow on github.concur.com runs the action with:
- gitea-url=https://gitea.weiker.me (binary download source)
- dry-run=true (avoids PR# mismatch between GHE and Gitea)

This validates:
- Binary download and checksum verification works from a GitHub runner
- GITHUB_SERVER_URL/GITHUB_REPOSITORY env vars are correctly passed
- AiCore provider authenticates and LLM call succeeds

When strat/review-bot has its own releases, remove gitea-url override and dry-run.
2026-05-14 04:07:01 +00:00
Rodin 3ac5e5dcca fix(#120): detect VCS host for releases API and derive action-repo
CI / test (pull_request) Successful in 20s
CI / review (anthropic--claude-4.6-sonnet, sonnet, SONNET_REVIEW_TOKEN) (pull_request) Successful in 29s
CI / review (gpt-5, security, ., rodin/security-patterns, SECURITY_REVIEW.md, SECURITY_REVIEW_TOKEN) (pull_request) Successful in 1m40s
CI / review (gpt-5, gpt, GPT_REVIEW_TOKEN) (pull_request) Successful in 2m3s
Both composite actions hardcoded:
- Gitea's /api/v1/ releases endpoint path
- 'rodin/review-bot' as the action source repo
- .gitea version used GITEA_URL/GITEA_REPO env vars instead of
  GITHUB_SERVER_URL/GITHUB_REPOSITORY

Fix:
- Add 'action-repo' input (default: empty) to allow explicit override
- Auto-detect VCS host from server_url: URLs containing 'gitea' use
  /api/v1/ (Gitea format), all others use /api/v3/ (GitHub format)
- Set smart default action-repo: 'rodin/review-bot' on Gitea,
  'strat/review-bot' on GitHub
- Pass server-url and action-repo as step outputs to avoid re-computing
- Fix .gitea action's 'Run review' env to use GITHUB_SERVER_URL and
  GITHUB_REPOSITORY (matching .github version and review-bot binary
  env var expectations)
- Add .github/workflows/review.yml for self-testing on github.concur.com

Backward compatible: existing Gitea callers using default inputs continue
to resolve rodin/review-bot via /api/v1/ unchanged.

Closes #120
2026-05-14 04:03:56 +00:00
28 changed files with 606 additions and 2143 deletions
+26 -9
View File
@@ -104,6 +104,10 @@ inputs:
description: 'Path to custom persona JSON file' description: 'Path to custom persona JSON file'
required: false required: false
default: '' default: ''
action-repo:
description: 'Repository hosting the review-bot binary (owner/name). Defaults to rodin/review-bot on Gitea, or strat/review-bot on GitHub.'
required: false
default: ''
runs: runs:
using: 'composite' using: 'composite'
@@ -112,10 +116,21 @@ runs:
id: version id: version
shell: bash shell: bash
run: | run: |
GITEA_URL="${{ inputs.gitea-url || github.server_url }}" SERVER_URL="${{ inputs.gitea-url || github.server_url }}"
REPO="${{ inputs.repo || 'rodin/review-bot' }}" # Detect VCS type: Gitea uses /api/v1/, GitHub uses /api/v3/
if echo "$SERVER_URL" | grep -qi 'gitea'; then
API_BASE="${SERVER_URL}/api/v1"
DEFAULT_ACTION_REPO="rodin/review-bot"
else
API_BASE="${SERVER_URL}/api/v3"
DEFAULT_ACTION_REPO="strat/review-bot"
fi
ACTION_REPO="${{ inputs.action-repo || '' }}"
if [ -z "$ACTION_REPO" ]; then
ACTION_REPO="$DEFAULT_ACTION_REPO"
fi
if [ "${{ inputs.version }}" = "latest" ]; then if [ "${{ inputs.version }}" = "latest" ]; then
VERSION=$(curl -sSf "${GITEA_URL}/api/v1/repos/${REPO}/releases?limit=1" \ VERSION=$(curl -sSf "${API_BASE}/repos/${ACTION_REPO}/releases?limit=1" \
| python3 -c "import sys, json; releases = json.load(sys.stdin); print(releases[0]['tag_name'] if releases else '')") | python3 -c "import sys, json; releases = json.load(sys.stdin); print(releases[0]['tag_name'] if releases else '')")
if [ -z "$VERSION" ]; then if [ -z "$VERSION" ]; then
echo "Failed to determine latest version" >&2 echo "Failed to determine latest version" >&2
@@ -125,6 +140,8 @@ runs:
VERSION="${{ inputs.version }}" VERSION="${{ inputs.version }}"
fi fi
echo "version=${VERSION}" >> "$GITHUB_OUTPUT" echo "version=${VERSION}" >> "$GITHUB_OUTPUT"
echo "action-repo=${ACTION_REPO}" >> "$GITHUB_OUTPUT"
echo "server-url=${SERVER_URL}" >> "$GITHUB_OUTPUT"
- name: Cache review-bot binary - name: Cache review-bot binary
id: cache id: cache
@@ -137,14 +154,14 @@ runs:
if: steps.cache.outputs.cache-hit != 'true' if: steps.cache.outputs.cache-hit != 'true'
shell: bash shell: bash
run: | run: |
GITEA_URL="${{ inputs.gitea-url || github.server_url }}" SERVER_URL="${{ steps.version.outputs.server-url }}"
REPO="${{ inputs.repo || 'rodin/review-bot' }}" ACTION_REPO="${{ steps.version.outputs.action-repo }}"
VERSION="${{ steps.version.outputs.version }}" VERSION="${{ steps.version.outputs.version }}"
BINARY="review-bot-linux-amd64" BINARY="review-bot-linux-amd64"
curl -sSfL "${GITEA_URL}/${REPO}/releases/download/${VERSION}/${BINARY}" \ curl -sSfL "${SERVER_URL}/${ACTION_REPO}/releases/download/${VERSION}/${BINARY}" \
-o "${{ runner.temp }}/review-bot" -o "${{ runner.temp }}/review-bot"
curl -sSfL "${GITEA_URL}/${REPO}/releases/download/${VERSION}/checksums.txt" \ curl -sSfL "${SERVER_URL}/${ACTION_REPO}/releases/download/${VERSION}/checksums.txt" \
-o "${{ runner.temp }}/checksums.txt" -o "${{ runner.temp }}/checksums.txt"
# Verify SHA-256 checksum # Verify SHA-256 checksum
@@ -169,8 +186,8 @@ runs:
- name: Run review - name: Run review
shell: bash shell: bash
env: env:
GITEA_URL: ${{ inputs.gitea-url || github.server_url }} GITHUB_SERVER_URL: ${{ inputs.gitea-url || github.server_url }}
GITEA_REPO: ${{ inputs.repo || github.repository }} GITHUB_REPOSITORY: ${{ inputs.repo || github.repository }}
PR_NUMBER: ${{ inputs.pr-number || github.event.pull_request.number }} PR_NUMBER: ${{ inputs.pr-number || github.event.pull_request.number }}
REVIEWER_TOKEN: ${{ inputs.reviewer-token }} REVIEWER_TOKEN: ${{ inputs.reviewer-token }}
REVIEWER_NAME: ${{ inputs.reviewer-name }} REVIEWER_NAME: ${{ inputs.reviewer-name }}
+24 -7
View File
@@ -104,6 +104,10 @@ inputs:
description: 'Path to custom persona JSON file' description: 'Path to custom persona JSON file'
required: false required: false
default: '' default: ''
action-repo:
description: 'Repository hosting the review-bot binary (owner/name). Defaults to rodin/review-bot on Gitea, or strat/review-bot on GitHub.'
required: false
default: ''
runs: runs:
using: 'composite' using: 'composite'
@@ -112,10 +116,21 @@ runs:
id: version id: version
shell: bash shell: bash
run: | run: |
GITEA_URL="${{ inputs.gitea-url || github.server_url }}" SERVER_URL="${{ inputs.gitea-url || github.server_url }}"
REPO="${{ inputs.repo || 'rodin/review-bot' }}" # Detect VCS type: Gitea uses /api/v1/, GitHub uses /api/v3/
if echo "$SERVER_URL" | grep -qi 'gitea'; then
API_BASE="${SERVER_URL}/api/v1"
DEFAULT_ACTION_REPO="rodin/review-bot"
else
API_BASE="${SERVER_URL}/api/v3"
DEFAULT_ACTION_REPO="strat/review-bot"
fi
ACTION_REPO="${{ inputs.action-repo || '' }}"
if [ -z "$ACTION_REPO" ]; then
ACTION_REPO="$DEFAULT_ACTION_REPO"
fi
if [ "${{ inputs.version }}" = "latest" ]; then if [ "${{ inputs.version }}" = "latest" ]; then
VERSION=$(curl -sSf "${GITEA_URL}/api/v1/repos/${REPO}/releases?limit=1" \ VERSION=$(curl -sSf "${API_BASE}/repos/${ACTION_REPO}/releases?limit=1" \
| python3 -c "import sys, json; releases = json.load(sys.stdin); print(releases[0]['tag_name'] if releases else '')") | python3 -c "import sys, json; releases = json.load(sys.stdin); print(releases[0]['tag_name'] if releases else '')")
if [ -z "$VERSION" ]; then if [ -z "$VERSION" ]; then
echo "Failed to determine latest version" >&2 echo "Failed to determine latest version" >&2
@@ -125,6 +140,8 @@ runs:
VERSION="${{ inputs.version }}" VERSION="${{ inputs.version }}"
fi fi
echo "version=${VERSION}" >> "$GITHUB_OUTPUT" echo "version=${VERSION}" >> "$GITHUB_OUTPUT"
echo "action-repo=${ACTION_REPO}" >> "$GITHUB_OUTPUT"
echo "server-url=${SERVER_URL}" >> "$GITHUB_OUTPUT"
- name: Cache review-bot binary - name: Cache review-bot binary
id: cache id: cache
@@ -137,14 +154,14 @@ runs:
if: steps.cache.outputs.cache-hit != 'true' if: steps.cache.outputs.cache-hit != 'true'
shell: bash shell: bash
run: | run: |
GITEA_URL="${{ inputs.gitea-url || github.server_url }}" SERVER_URL="${{ steps.version.outputs.server-url }}"
REPO="${{ inputs.repo || 'rodin/review-bot' }}" ACTION_REPO="${{ steps.version.outputs.action-repo }}"
VERSION="${{ steps.version.outputs.version }}" VERSION="${{ steps.version.outputs.version }}"
BINARY="review-bot-linux-amd64" BINARY="review-bot-linux-amd64"
curl -sSfL "${GITEA_URL}/${REPO}/releases/download/${VERSION}/${BINARY}" \ curl -sSfL "${SERVER_URL}/${ACTION_REPO}/releases/download/${VERSION}/${BINARY}" \
-o "${{ runner.temp }}/review-bot" -o "${{ runner.temp }}/review-bot"
curl -sSfL "${GITEA_URL}/${REPO}/releases/download/${VERSION}/checksums.txt" \ curl -sSfL "${SERVER_URL}/${ACTION_REPO}/releases/download/${VERSION}/checksums.txt" \
-o "${{ runner.temp }}/checksums.txt" -o "${{ runner.temp }}/checksums.txt"
# Verify SHA-256 checksum # Verify SHA-256 checksum
+47
View File
@@ -0,0 +1,47 @@
# Self-review workflow for strat/review-bot on GitHub Enterprise Server.
# Tests that the composite action runs correctly on GitHub runners:
# - GITHUB_SERVER_URL and GITHUB_REPOSITORY env vars are set correctly
# - Binary is downloaded from gitea.weiker.me (where releases live)
# - Review is posted to the corresponding Gitea PR
name: Review
on:
pull_request:
types: [opened, synchronize]
jobs:
review:
runs-on: ubuntu-24.04
if: github.event_name == 'pull_request'
strategy:
matrix:
include:
- name: sonnet
token_secret: SONNET_REVIEW_TOKEN
model: anthropic--claude-4.6-sonnet
- name: gpt
token_secret: GPT_REVIEW_TOKEN
model: gpt-5
steps:
- uses: actions/checkout@v4
- name: Run ${{ matrix.name }} review
uses: ./.gitea/actions/review
with:
# Download binary from Gitea (releases live there, not on GHE)
gitea-url: https://gitea.weiker.me
# Post review to the corresponding Gitea repo
repo: rodin/review-bot
reviewer-token: ${{ secrets[matrix.token_secret] }}
reviewer-name: ${{ matrix.name }}
llm-model: ${{ matrix.model }}
llm-provider: aicore
aicore-client-id: ${{ secrets.AICORE_CLIENT_ID }}
aicore-client-secret: ${{ secrets.AICORE_CLIENT_SECRET }}
aicore-auth-url: ${{ secrets.AICORE_AUTH_URL }}
aicore-api-url: ${{ secrets.AICORE_API_URL }}
aicore-resource-group: ${{ secrets.AICORE_RESOURCE_GROUP }}
conventions-file: CONVENTIONS.md
patterns-repo: rodin/go-patterns
patterns-files: 'README.md,patterns/'
dry-run: 'true'
timeout: '600'
+1 -1
View File
@@ -9,7 +9,7 @@
| Package | Use Case | Scope | | Package | Use Case | Scope |
|---------|----------|-------| |---------|----------|-------|
| `github.com/goccy/go-yaml` | YAML parsing and AST inspection (subpkgs: `ast`, `parser`) | production | | `gopkg.in/yaml.v3` | YAML parsing (persona files, config) | 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.**
+130 -213
View File
@@ -2,7 +2,6 @@ package main
import ( import (
"context" "context"
"errors"
"flag" "flag"
"fmt" "fmt"
"log/slog" "log/slog"
@@ -14,7 +13,6 @@ import (
"gitea.weiker.me/rodin/review-bot/budget" "gitea.weiker.me/rodin/review-bot/budget"
"gitea.weiker.me/rodin/review-bot/gitea" "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/llm"
"gitea.weiker.me/rodin/review-bot/review" "gitea.weiker.me/rodin/review-bot/review"
"gitea.weiker.me/rodin/review-bot/vcs" "gitea.weiker.me/rodin/review-bot/vcs"
@@ -56,22 +54,19 @@ func main() {
// Logging flags // Logging flags
logFormat := flag.String("log-format", envOrDefault("LOG_FORMAT", "text"), "Log output format: text or json") 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") verbosity := flag.String("verbosity", envOrDefault("LOG_VERBOSITY", "info"), "Log verbosity: debug, info, warn, error")
// VCS flags // CLI flags
provider := flag.String("provider", envOrDefault("VCS_PROVIDER", "gitea"), "VCS provider: gitea or github") giteaURL := flag.String("gitea-url", envOrDefault("GITEA_URL", envOrDefault("GITHUB_SERVER_URL", "")), "Gitea instance URL")
baseURL := flag.String("base-url", envOrDefault("VCS_BASE_URL", ""), "VCS API base URL (for github provider; defaults to https://api.github.com)") repo := flag.String("repo", envOrDefault("GITEA_REPO", envOrDefault("GITHUB_REPOSITORY", "")), "Repository (owner/name)")
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") prNum := flag.String("pr", envOrDefault("PR_NUMBER", ""), "Pull request number")
reviewerName := flag.String("reviewer-name", envOrDefault("REVIEWER_NAME", ""), "Reviewer display name") reviewerName := flag.String("reviewer-name", envOrDefault("REVIEWER_NAME", ""), "Reviewer display name")
reviewerToken := flag.String("reviewer-token", envOrDefault("REVIEWER_TOKEN", ""), "VCS token for posting review") reviewerToken := flag.String("reviewer-token", envOrDefault("REVIEWER_TOKEN", ""), "Gitea token for posting review")
llmBaseURL := flag.String("llm-base-url", envOrDefault("LLM_BASE_URL", ""), "LLM API base URL") 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") llmAPIKey := flag.String("llm-api-key", envOrDefault("LLM_API_KEY", ""), "LLM API key")
llmModel := flag.String("llm-model", envOrDefault("LLM_MODEL", ""), "LLM model name") 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)") 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", ""), "Comma-separated file paths to fetch from patterns repo (empty = all files)") patternsFiles := flag.String("patterns-files", envOrDefault("PATTERNS_FILES", "README.md"), "Comma-separated file paths to fetch from patterns repo")
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)")
@@ -85,18 +80,6 @@ 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)")
// 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() flag.Parse()
if *versionFlag { if *versionFlag {
@@ -109,25 +92,12 @@ func main() {
slog.Info("review-bot starting", "version", version) 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 // Validate required fields
// For aicore provider, llm-base-url and llm-api-key are not required
isAICore := llm.Provider(*llmProvider) == llm.ProviderAICore isAICore := llm.Provider(*llmProvider) == llm.ProviderAICore
if *repo == "" || *prNum == "" || *reviewerToken == "" || *llmModel == "" { if *giteaURL == "" || *repo == "" || *prNum == "" || *reviewerToken == "" || *llmModel == "" {
fmt.Fprintf(os.Stderr, "Error: missing required flags or environment variables\n\n") fmt.Fprintf(os.Stderr, "Error: missing required flags or environment variables\n\n")
fmt.Fprintf(os.Stderr, "Required: --repo, --pr, --reviewer-token, --llm-model\n") fmt.Fprintf(os.Stderr, "Required: --gitea-url, --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) os.Exit(1)
} }
if !isAICore && (*llmBaseURL == "" || *llmAPIKey == "") { if !isAICore && (*llmBaseURL == "" || *llmAPIKey == "") {
@@ -146,6 +116,8 @@ func main() {
os.Exit(1) 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 // Validate reviewer-name: only safe characters allowed in sentinel
if err := validateReviewerName(*reviewerName); err != nil { if err := validateReviewerName(*reviewerName); err != nil {
slog.Error("invalid reviewer name", "error", err) slog.Error("invalid reviewer name", "error", err)
@@ -167,22 +139,8 @@ func main() {
os.Exit(1) os.Exit(1)
} }
// Initialize VCS client // Initialize clients
var client vcs.Client giteaClient := gitea.NewClient(*giteaURL, *reviewerToken)
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) llmClient := llm.NewClient(*llmBaseURL, *llmAPIKey, *llmModel)
if *llmTemp < 0 || *llmTemp > 2 { if *llmTemp < 0 || *llmTemp > 2 {
slog.Error("invalid LLM temperature", "temperature", *llmTemp, "range", "0-2") slog.Error("invalid LLM temperature", "temperature", *llmTemp, "range", "0-2")
@@ -216,13 +174,16 @@ func main() {
ctx, cancel := context.WithTimeout(context.Background(), overallTimeout) ctx, cancel := context.WithTimeout(context.Background(), overallTimeout)
defer cancel() defer cancel()
// Load persona if specified // Load persona if specified (after Gitea client init to support repo personas)
var persona *review.Persona var persona *review.Persona
if *personaName != "" { if *personaName != "" {
// Try loading from repo first, then fall back to built-in // Try loading from repo first, then fall back to built-in
repoPersonas, err := review.LoadRepoPersonas(ctx, client, owner, repoName) repoPersonas, err := review.LoadRepoPersonas(ctx, newGiteaClientAdapter(giteaClient), owner, repoName)
if err != nil { if err != nil {
slog.Warn("could not load repo personas", "repo", owner+"/"+repoName, "error", err) 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 { if p, ok := repoPersonas[*personaName]; ok {
persona = p persona = p
@@ -253,7 +214,7 @@ func main() {
slog.Info("reviewing pull request", "pr", prNumber, "repo", fmt.Sprintf("%s/%s", owner, repoName)) slog.Info("reviewing pull request", "pr", prNumber, "repo", fmt.Sprintf("%s/%s", owner, repoName))
// Step 1: Fetch PR metadata // Step 1: Fetch PR metadata
pr, err := client.GetPullRequest(ctx, owner, repoName, prNumber) pr, err := giteaClient.GetPullRequest(ctx, owner, repoName, prNumber)
if err != nil { if err != nil {
slog.Error("failed to fetch PR", "pr", prNumber, "error", err) slog.Error("failed to fetch PR", "pr", prNumber, "error", err)
os.Exit(1) os.Exit(1)
@@ -261,7 +222,7 @@ func main() {
slog.Info("fetched PR metadata", "pr", prNumber, "title", pr.Title) slog.Info("fetched PR metadata", "pr", prNumber, "title", pr.Title)
// Step 2: Fetch diff // Step 2: Fetch diff
diff, err := client.GetPullRequestDiff(ctx, owner, repoName, prNumber) diff, err := giteaClient.GetPullRequestDiff(ctx, owner, repoName, prNumber)
if err != nil { if err != nil {
slog.Error("failed to fetch diff", "pr", prNumber, "error", err) slog.Error("failed to fetch diff", "pr", prNumber, "error", err)
os.Exit(1) os.Exit(1)
@@ -270,21 +231,21 @@ func main() {
// Step 3: Fetch full file content for modified files // Step 3: Fetch full file content for modified files
fileContext := "" fileContext := ""
files, err := client.GetPullRequestFiles(ctx, owner, repoName, prNumber) files, err := giteaClient.GetPullRequestFiles(ctx, owner, repoName, prNumber)
if err != nil { if err != nil {
slog.Warn("could not fetch PR files list", "pr", prNumber, "error", err) slog.Warn("could not fetch PR files list", "pr", prNumber, "error", err)
} else { } else {
fileContext = fetchFileContext(ctx, client, owner, repoName, pr.Head.Ref, files) fileContext = fetchFileContext(ctx, giteaClient, owner, repoName, pr.Head.Ref, files)
slog.Debug("fetched file context", "files", len(files)) slog.Debug("fetched file context", "files", len(files))
} }
// Step 4: Check CI status // Step 4: Check CI status
ciPassed := true ciPassed := true
ciDetails := "" ciDetails := ""
if pr.Head.SHA != "" { if pr.Head.Sha != "" {
statuses, err := client.GetCommitStatuses(ctx, owner, repoName, pr.Head.SHA) statuses, err := giteaClient.GetCommitStatuses(ctx, owner, repoName, pr.Head.Sha)
if err != nil { 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 { } else {
ciPassed, ciDetails = evaluateCIStatus(statuses) ciPassed, ciDetails = evaluateCIStatus(statuses)
slog.Info("CI status checked", "passed", ciPassed) slog.Info("CI status checked", "passed", ciPassed)
@@ -294,7 +255,7 @@ func main() {
// Step 5: Load conventions file if specified // Step 5: Load conventions file if specified
conventions := "" conventions := ""
if *conventionsFile != "" { if *conventionsFile != "" {
content, err := client.GetFileContent(ctx, owner, repoName, *conventionsFile, "") content, err := giteaClient.GetFileContent(ctx, owner, repoName, *conventionsFile)
if err != nil { if err != nil {
slog.Warn("could not load conventions file", "file", *conventionsFile, "error", err) slog.Warn("could not load conventions file", "file", *conventionsFile, "error", err)
} else { } else {
@@ -306,7 +267,7 @@ func main() {
// Step 6: Load patterns from external repo if specified // Step 6: Load patterns from external repo if specified
patterns := "" patterns := ""
if *patternsRepo != "" { if *patternsRepo != "" {
patterns = fetchPatterns(ctx, client, *patternsRepo, *patternsFiles) patterns = fetchPatterns(ctx, giteaClient, *patternsRepo, *patternsFiles)
slog.Debug("loaded patterns", "repo", *patternsRepo, "bytes", len(patterns)) slog.Debug("loaded patterns", "repo", *patternsRepo, "bytes", len(patterns))
} }
@@ -399,16 +360,15 @@ func main() {
} }
// Add commit footer so readers know which commit was evaluated // 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 { if len(shortSHA) > 8 {
shortSHA = shortSHA[:8] shortSHA = shortSHA[:8]
} }
reviewBody += fmt.Sprintf("\n\n---\n*Evaluated against %s*", shortSHA) reviewBody += fmt.Sprintf("\n\n---\n*Evaluated against %s*", shortSHA)
} }
// Map verdict to canonical review event event := review.GiteaEvent(result.Verdict)
event := verdictToEvent(result.Verdict)
if *dryRun { if *dryRun {
fmt.Println("--- DRY RUN ---") fmt.Println("--- DRY RUN ---")
@@ -420,41 +380,35 @@ func main() {
sentinel := fmt.Sprintf("<!-- review-bot:%s -->", *reviewerName) sentinel := fmt.Sprintf("<!-- review-bot:%s -->", *reviewerName)
// Stale check: verify HEAD hasn't moved since we started // Stale check: verify HEAD hasn't moved since we started
evaluatedSHA := pr.Head.SHA evaluatedSHA := pr.Head.Sha
var currentSHA string var currentSHA string
currentPR, err := client.GetPullRequest(ctx, owner, repoName, prNumber) currentPR, err := giteaClient.GetPullRequest(ctx, owner, repoName, prNumber)
if err != nil { if err != nil {
slog.Warn("could not re-fetch PR for stale check", "pr", prNumber, "error", err) slog.Warn("could not re-fetch PR for stale check", "pr", prNumber, "error", err)
// currentSHA stays empty — shouldSkipStaleReview will return false
} else { } else {
currentSHA = currentPR.Head.SHA currentSHA = currentPR.Head.Sha
} }
if shouldSkipStaleReview(evaluatedSHA, currentSHA) { if shouldSkipStaleReview(evaluatedSHA, currentSHA) {
slog.Warn("HEAD moved during review -- skipping stale review", slog.Warn("HEAD moved during review skipping stale review",
"evaluated", evaluatedSHA, "evaluated", evaluatedSHA,
"current", currentSHA, "current", currentSHA,
"pr", prNumber) "pr", prNumber)
return return
} }
// Build line→position map for inline comments // Map findings to inline comments for lines present in the diff
lineToPosition := vcs.BuildLineToPositionMap(diff) diffRanges := gitea.ParseDiffNewLines(diff)
var inlineComments []vcs.ReviewComment var inlineComments []gitea.ReviewComment
for _, f := range result.Findings { for _, f := range result.Findings {
if f.File == "" || f.Line <= 0 { if f.File != "" && f.Line > 0 && diffRanges.Contains(f.File, f.Line) {
continue inlineComments = append(inlineComments, gitea.ReviewComment{
}
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, Path: f.File,
Position: pos, NewPosition: int64(f.Line),
CommitID: pr.Head.SHA,
Body: fmt.Sprintf("**[%s]** %s", f.Severity, f.Finding), Body: fmt.Sprintf("**[%s]** %s", f.Severity, f.Finding),
}) })
} }
}
if len(inlineComments) > 0 { if len(inlineComments) > 0 {
slog.Debug("attaching inline comments", "count", len(inlineComments)) slog.Debug("attaching inline comments", "count", len(inlineComments))
} }
@@ -462,9 +416,10 @@ func main() {
// --- Review update strategy --- // --- Review update strategy ---
// 1. POST new review first (gets non-stale approval badge on HEAD) // 1. POST new review first (gets non-stale approval badge on HEAD)
// 2. Then supersede old review with link to the new one // 2. Then supersede old review with link to the new one
var oldReviews []vcs.Review // Order matters: post first so we have the new review's URL for the supersede message.
var oldReviews []gitea.Review
if *reviewerName != "" { if *reviewerName != "" {
existingReviews, err := client.ListReviews(ctx, owner, repoName, prNumber) existingReviews, err := giteaClient.ListReviews(ctx, owner, repoName, prNumber)
if err != nil { if err != nil {
slog.Warn("could not list existing reviews", "pr", prNumber, "error", err) slog.Warn("could not list existing reviews", "pr", prNumber, "error", err)
} else { } else {
@@ -476,113 +431,45 @@ func main() {
} }
} }
// Self-request as reviewer (Gitea-specific; ensures we appear in required-reviewer checks) // Self-request as reviewer (ensures we appear in required-reviewer checks)
if selfReq, ok := client.(vcs.ReviewerSelfRequester); ok { authUser, err := giteaClient.GetAuthenticatedUser(ctx)
authUser, err := client.GetAuthenticatedUser(ctx)
if err != nil { if err != nil {
slog.Warn("could not determine authenticated user for reviewer self-request", "error", err) slog.Warn("could not determine authenticated user for reviewer self-request", "error", err)
} else if authUser != "" { } else if authUser != "" {
if err := selfReq.RequestReviewerSelf(ctx, owner, repoName, prNumber, authUser); err != nil { if err := giteaClient.RequestReviewer(ctx, owner, repoName, prNumber, authUser); err != nil {
slog.Warn("could not self-request as reviewer", "user", authUser, "error", err) slog.Warn("could not self-request as reviewer", "user", authUser, "error", err)
} else { } else {
slog.Debug("self-requested as reviewer", "user", authUser, "pr", prNumber) slog.Debug("self-requested as reviewer", "user", authUser, "pr", prNumber)
} }
} }
} else {
slog.Debug("RequestReviewer not supported for provider, skipping")
}
// POST new review // POST new review
slog.Info("posting review", "event", event, "pr", prNumber) slog.Info("posting review", "event", event, "pr", prNumber)
reviewReq := vcs.ReviewRequest{ posted, err := giteaClient.PostReview(ctx, owner, repoName, prNumber, event, reviewBody, inlineComments)
Body: reviewBody,
Event: event,
Comments: inlineComments,
}
posted, err := client.PostReview(ctx, owner, repoName, prNumber, reviewReq)
if err != nil { if err != nil {
slog.Error("failed to post review", "pr", prNumber, "event", event, "error", err) slog.Error("failed to post review", "pr", prNumber, "event", event, "error", err)
os.Exit(1) os.Exit(1)
} }
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 // Supersede all old reviews with link to the new one
if len(oldReviews) > 0 { if len(oldReviews) > 0 {
if err := supersedeOldReviews(ctx, client, *provider, *vcsURL, owner, repoName, prNumber, oldReviews, posted.ID, sentinel); err != nil { newReviewURL := fmt.Sprintf("%s/%s/%s/pulls/%d#pullrequestreview-%d", strings.TrimRight(*giteaURL, "/"), owner, repoName, prNumber, posted.ID)
slog.Error("failed to supersede old reviews", "error", err)
os.Exit(1)
}
}
}
// 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 { for _, oldReview := range oldReviews {
cid, err := underlying.GetTimelineReviewCommentIDForReview(ctx, owner, repoName, prNumber, oldReview.ID) cid, err := giteaClient.GetTimelineReviewCommentIDForReview(ctx, owner, repoName, prNumber, oldReview.ID)
if err != nil { if err != nil {
slog.Warn("could not find comment ID for old review", "review_id", oldReview.ID, "error", err) slog.Warn("could not find comment ID for old review", "review_id", oldReview.ID, "error", err)
continue continue
} }
supersededBody := buildSupersededBody(oldReview.Body, oldReview.CommitID, newReviewURL, sentinel) supersededBody := buildSupersededBody(oldReview.Body, oldReview.CommitID, newReviewURL, sentinel)
if err := underlying.EditComment(ctx, owner, repoName, cid, supersededBody); err != nil { 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) slog.Warn("could not mark old review as superseded", "review_id", oldReview.ID, "comment_id", cid, "error", err)
continue continue
} }
slog.Info("marked old review as superseded", "review_id", oldReview.ID, "new_review_id", newReviewID, "pr", prNumber) slog.Info("marked old review as superseded", "review_id", oldReview.ID, "new_review_id", posted.ID, "pr", prNumber)
// Resolve old review's inline comments // Resolve old review's inline comments
oldComments, err := underlying.ListReviewComments(ctx, owner, repoName, prNumber, oldReview.ID) oldComments, err := giteaClient.ListReviewComments(ctx, owner, repoName, prNumber, oldReview.ID)
if err != nil { if err != nil {
slog.Warn("could not list old review comments for resolution", "review_id", oldReview.ID, "error", err) slog.Warn("could not list old review comments for resolution", "review_id", oldReview.ID, "error", err)
continue continue
@@ -592,7 +479,7 @@ func supersedeOldReviews(ctx context.Context, client vcs.Client, provider, vcsUR
if c.ID == 0 { if c.ID == 0 {
continue continue
} }
if err := underlying.ResolveComment(ctx, owner, repoName, c.ID); err != nil { if err := giteaClient.ResolveComment(ctx, owner, repoName, c.ID); err != nil {
slog.Debug("could not resolve inline comment", "comment_id", c.ID, "error", err) slog.Debug("could not resolve inline comment", "comment_id", c.ID, "error", err)
failed++ failed++
} else { } else {
@@ -606,11 +493,12 @@ func supersedeOldReviews(ctx context.Context, client vcs.Client, provider, vcsUR
slog.Warn("some inline comments could not be resolved", "review_id", oldReview.ID, "failed", failed, "pr", prNumber) 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 *gitea.Client, owner, repo, ref string, files []gitea.ChangedFile) string {
var sb strings.Builder var sb strings.Builder
for _, f := range files { for _, f := range files {
if ctx.Err() != nil { if ctx.Err() != nil {
@@ -619,7 +507,7 @@ func fetchFileContext(ctx context.Context, client vcs.PRReader, owner, repo, ref
if f.Status == "removed" { if f.Status == "removed" {
continue // Skip deleted files continue // Skip deleted files
} }
content, err := client.GetFileContentAtRef(ctx, owner, repo, f.Filename, ref) content, err := client.GetFileContentRef(ctx, owner, repo, f.Filename, ref)
if err != nil { if err != nil {
slog.Warn("could not fetch file content", "file", f.Filename, "error", err) slog.Warn("could not fetch file content", "file", f.Filename, "error", err)
continue continue
@@ -636,25 +524,11 @@ 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.
// If patternsFiles is empty, all files from the repo root are fetched. func fetchPatterns(ctx context.Context, client *gitea.Client, 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 {
@@ -675,7 +549,12 @@ func fetchPatterns(ctx context.Context, client vcs.FileReader, patternsRepo, pat
var repoSkippedFiles []string var repoSkippedFiles []string
for _, path := range paths { for _, path := range paths {
files, err := vcs.GetAllFilesInPath(ctx, client, owner, repo, path) path = strings.TrimSpace(path)
if path == "" {
continue
}
files, err := client.GetAllFilesInPath(ctx, 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)
continue continue
@@ -714,20 +593,18 @@ func isPatternFile(path string) bool {
} }
// evaluateCIStatus checks if all CI statuses indicate success. // evaluateCIStatus checks if all CI statuses indicate success.
// Returns passed=true if no checks have failed (pending checks are not treated as failures). func evaluateCIStatus(statuses []gitea.CommitStatus) (passed bool, details string) {
func evaluateCIStatus(statuses []vcs.CommitStatus) (passed bool, details string) {
if len(statuses) == 0 { if len(statuses) == 0 {
return true, "no CI statuses found" return true, "no CI statuses found"
} }
var failed []string var failed []string
var pending int
for _, s := range statuses { for _, s := range statuses {
switch s.Status { switch s.Status {
case "success": case "success":
// good // good
case "pending": case "pending":
pending++ // treat pending as not-failed
case "failure", "error": case "failure", "error":
failed = append(failed, fmt.Sprintf("%s: %s", s.Context, s.Description)) failed = append(failed, fmt.Sprintf("%s: %s", s.Context, s.Description))
} }
@@ -736,9 +613,6 @@ func evaluateCIStatus(statuses []vcs.CommitStatus) (passed bool, details string)
if len(failed) > 0 { if len(failed) > 0 {
return false, strings.Join(failed, "; ") return false, strings.Join(failed, "; ")
} }
if pending > 0 {
return true, fmt.Sprintf("no failures (%d pending)", pending)
}
return true, "all checks passed" return true, "all checks passed"
} }
@@ -769,6 +643,14 @@ func envOrDefaultInt(key string, defaultVal int) int {
return defaultVal 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 // validateReviewerName checks that the name contains only safe characters
// for embedding in an HTML comment sentinel ([a-zA-Z0-9_-]). // for embedding in an HTML comment sentinel ([a-zA-Z0-9_-]).
func validateReviewerName(name string) error { func validateReviewerName(name string) error {
@@ -846,10 +728,10 @@ func buildSupersededBody(originalBody, commitSHA, newReviewURL, sentinel 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 // Gitea user. This indicates misconfiguration where two roles share a token
// instead of having separate accounts. Returns true if shared token // instead of having separate Gitea accounts. Returns true if shared token
// detected (caller should skip update-in-place logic to avoid clobbering). // detected (caller should skip update-in-place logic to avoid clobbering).
func hasSharedToken(reviews []vcs.Review, ownSentinel string) bool { func hasSharedToken(reviews []gitea.Review, ownSentinel string) bool {
ownLogin := "" ownLogin := ""
for _, r := range reviews { for _, r := range reviews {
if strings.Contains(r.Body, ownSentinel) { if strings.Contains(r.Body, ownSentinel) {
@@ -862,7 +744,7 @@ func hasSharedToken(reviews []vcs.Review, ownSentinel string) bool {
} }
for _, r := range reviews { for _, r := range reviews {
if r.User.Login == ownLogin && strings.Contains(r.Body, "<!-- review-bot:") && !strings.Contains(r.Body, ownSentinel) { 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 VCS user", slog.Warn("shared token detected another review-bot role is using the same Gitea user",
"sibling_role", extractSentinelName(r.Body), "user", ownLogin) "sibling_role", extractSentinelName(r.Body), "user", ownLogin)
return true return true
} }
@@ -883,26 +765,29 @@ func extractSentinelName(body string) string {
if end < 0 { if end < 0 {
return "unknown" return "unknown"
} }
name := rest[:end] return rest[:end]
// Sanitize: strip control characters to prevent log injection. }
name = strings.Map(func(r rune) rune {
if r < 0x20 || r == 0x7f { // findOwnReview locates the most recent non-superseded review matching the sentinel.
return -1 func findOwnReview(reviews []gitea.Review, sentinel string) *gitea.Review {
var best *gitea.Review
for i := range reviews {
if !strings.Contains(reviews[i].Body, sentinel) {
continue
} }
return r if strings.Contains(reviews[i].Body, "~~Original review~~") {
}, name) continue
if len(name) > 64 {
name = name[:64]
} }
if name == "" { if best == nil || reviews[i].ID > best.ID {
return "unknown" best = &reviews[i]
} }
return name }
return best
} }
// findAllOwnReviews returns all non-superseded reviews matching the sentinel. // findAllOwnReviews returns all non-superseded reviews matching the sentinel.
func findAllOwnReviews(reviews []vcs.Review, sentinel string) []vcs.Review { func findAllOwnReviews(reviews []gitea.Review, sentinel string) []gitea.Review {
var result []vcs.Review var result []gitea.Review
for i := range reviews { for i := range reviews {
if !strings.Contains(reviews[i].Body, sentinel) { if !strings.Contains(reviews[i].Body, sentinel) {
continue continue
@@ -927,3 +812,35 @@ func shouldSkipStaleReview(evaluatedSHA, currentSHA string) bool {
} }
return evaluatedSHA != currentSHA 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)
}
+167 -132
View File
@@ -10,7 +10,7 @@ import (
"strings" "strings"
"testing" "testing"
"gitea.weiker.me/rodin/review-bot/vcs" "gitea.weiker.me/rodin/review-bot/gitea"
) )
func TestValidateReviewerName(t *testing.T) { func TestValidateReviewerName(t *testing.T) {
@@ -107,6 +107,8 @@ func TestValidateWorkspacePath(t *testing.T) {
workspace: tmpDir, workspace: tmpDir,
path: "/etc/passwd", path: "/etc/passwd",
wantErr: true, wantErr: true,
// Go 1.21+ filepath.Join normalizes absolute paths: Join("/tmp/x", "/etc/passwd")
// becomes "/tmp/x/etc/passwd", which is within workspace but doesn't exist.
errMatch: "failed to resolve", errMatch: "failed to resolve",
}, },
{ {
@@ -152,14 +154,15 @@ func TestValidateWorkspacePath(t *testing.T) {
} }
} }
func makeReview(id int64, login, state string, stale bool, body string) vcs.Review { func makeReview(id int64, login, state string, stale bool, body string) gitea.Review {
return vcs.Review{ r := gitea.Review{
ID: id, ID: id,
Body: body, Body: body,
User: vcs.UserInfo{Login: login},
State: state, State: state,
Stale: stale, Stale: stale,
} }
r.User.Login = login
return r
} }
func TestBuildSupersededBody(t *testing.T) { func TestBuildSupersededBody(t *testing.T) {
@@ -210,10 +213,96 @@ 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) { func TestHasSharedToken(t *testing.T) {
tests := []struct { tests := []struct {
name string name string
reviews []vcs.Review reviews []gitea.Review
sentinel string sentinel string
want bool want bool
}{ }{
@@ -225,36 +314,36 @@ func TestHasSharedToken(t *testing.T) {
}, },
{ {
name: "no own review yet - cannot detect", name: "no own review yet - cannot detect",
reviews: []vcs.Review{ reviews: []gitea.Review{
makeReview(1, "other", "APPROVED", false, "<!-- review-bot:gpt --> body"), {ID: 1, User: struct{ Login string `json:"login"` }{Login: "other"}, Body: "<!-- review-bot:gpt --> body"},
}, },
sentinel: "<!-- review-bot:sonnet -->", sentinel: "<!-- review-bot:sonnet -->",
want: false, want: false,
}, },
{ {
name: "separate users - no shared token", name: "separate users - no shared token",
reviews: []vcs.Review{ reviews: []gitea.Review{
makeReview(1, "sonnet-review-bot", "APPROVED", false, "<!-- review-bot:sonnet --> body"), {ID: 1, User: struct{ Login string `json:"login"` }{Login: "sonnet-review-bot"}, Body: "<!-- review-bot:sonnet --> body"},
makeReview(2, "security-review-bot", "APPROVED", false, "<!-- review-bot:security --> body"), {ID: 2, User: struct{ Login string `json:"login"` }{Login: "security-review-bot"}, Body: "<!-- review-bot:security --> body"},
}, },
sentinel: "<!-- review-bot:sonnet -->", sentinel: "<!-- review-bot:sonnet -->",
want: false, want: false,
}, },
{ {
name: "shared token detected - same user different sentinels", name: "shared token detected - same user different sentinels",
reviews: []vcs.Review{ reviews: []gitea.Review{
makeReview(1, "sonnet-review-bot", "APPROVED", false, "<!-- review-bot:sonnet --> body"), {ID: 1, User: struct{ Login string `json:"login"` }{Login: "sonnet-review-bot"}, Body: "<!-- review-bot:sonnet --> body"},
makeReview(2, "sonnet-review-bot", "APPROVED", false, "<!-- review-bot:security --> body"), {ID: 2, User: struct{ Login string `json:"login"` }{Login: "sonnet-review-bot"}, Body: "<!-- review-bot:security --> body"},
}, },
sentinel: "<!-- review-bot:sonnet -->", sentinel: "<!-- review-bot:sonnet -->",
want: true, want: true,
}, },
{ {
name: "three roles same user", name: "three roles same user",
reviews: []vcs.Review{ reviews: []gitea.Review{
makeReview(1, "bot", "APPROVED", false, "<!-- review-bot:sonnet --> body"), {ID: 1, User: struct{ Login string `json:"login"` }{Login: "bot"}, Body: "<!-- review-bot:sonnet --> body"},
makeReview(2, "bot", "APPROVED", false, "<!-- review-bot:security --> body"), {ID: 2, User: struct{ Login string `json:"login"` }{Login: "bot"}, Body: "<!-- review-bot:security --> body"},
makeReview(3, "bot", "APPROVED", false, "<!-- review-bot:gpt --> body"), {ID: 3, User: struct{ Login string `json:"login"` }{Login: "bot"}, Body: "<!-- review-bot:gpt --> body"},
}, },
sentinel: "<!-- review-bot:sonnet -->", sentinel: "<!-- review-bot:sonnet -->",
want: true, want: true,
@@ -415,56 +504,10 @@ 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
statuses []vcs.CommitStatus statuses []gitea.CommitStatus
wantPassed bool wantPassed bool
wantSubstr string wantSubstr string
}{ }{
@@ -476,7 +519,7 @@ func TestEvaluateCIStatus(t *testing.T) {
}, },
{ {
name: "all success", name: "all success",
statuses: []vcs.CommitStatus{ statuses: []gitea.CommitStatus{
{Status: "success", Context: "ci/build", Description: "Build passed"}, {Status: "success", Context: "ci/build", Description: "Build passed"},
{Status: "success", Context: "ci/test", Description: "Tests passed"}, {Status: "success", Context: "ci/test", Description: "Tests passed"},
}, },
@@ -485,7 +528,7 @@ func TestEvaluateCIStatus(t *testing.T) {
}, },
{ {
name: "one failure", name: "one failure",
statuses: []vcs.CommitStatus{ statuses: []gitea.CommitStatus{
{Status: "success", Context: "ci/build", Description: "Build passed"}, {Status: "success", Context: "ci/build", Description: "Build passed"},
{Status: "failure", Context: "ci/test", Description: "Tests failed"}, {Status: "failure", Context: "ci/test", Description: "Tests failed"},
}, },
@@ -494,7 +537,7 @@ func TestEvaluateCIStatus(t *testing.T) {
}, },
{ {
name: "error status", name: "error status",
statuses: []vcs.CommitStatus{ statuses: []gitea.CommitStatus{
{Status: "error", Context: "ci/lint", Description: "Lint error"}, {Status: "error", Context: "ci/lint", Description: "Lint error"},
}, },
wantPassed: false, wantPassed: false,
@@ -502,16 +545,16 @@ func TestEvaluateCIStatus(t *testing.T) {
}, },
{ {
name: "pending treated as not-failed", name: "pending treated as not-failed",
statuses: []vcs.CommitStatus{ statuses: []gitea.CommitStatus{
{Status: "pending", Context: "ci/build", Description: "In progress"}, {Status: "pending", Context: "ci/build", Description: "In progress"},
{Status: "success", Context: "ci/test", Description: "Tests passed"}, {Status: "success", Context: "ci/test", Description: "Tests passed"},
}, },
wantPassed: true, wantPassed: true,
wantSubstr: "no failures", wantSubstr: "all checks passed",
}, },
{ {
name: "multiple failures", name: "multiple failures",
statuses: []vcs.CommitStatus{ statuses: []gitea.CommitStatus{
{Status: "failure", Context: "ci/build", Description: "Build failed"}, {Status: "failure", Context: "ci/build", Description: "Build failed"},
{Status: "failure", Context: "ci/test", Description: "Tests failed"}, {Status: "failure", Context: "ci/test", Description: "Tests failed"},
}, },
@@ -520,7 +563,7 @@ func TestEvaluateCIStatus(t *testing.T) {
}, },
{ {
name: "mixed with pending and failure", name: "mixed with pending and failure",
statuses: []vcs.CommitStatus{ statuses: []gitea.CommitStatus{
{Status: "success", Context: "ci/build", Description: "Build passed"}, {Status: "success", Context: "ci/build", Description: "Build passed"},
{Status: "pending", Context: "ci/deploy", Description: "Deploying"}, {Status: "pending", Context: "ci/deploy", Description: "Deploying"},
{Status: "failure", Context: "ci/test", Description: "Tests failed"}, {Status: "failure", Context: "ci/test", Description: "Tests failed"},
@@ -642,6 +685,47 @@ 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) { func TestExtractSentinelName_EdgeCases(t *testing.T) {
tests := []struct { tests := []struct {
body string body string
@@ -708,7 +792,7 @@ func TestMainSubprocess_InvalidReviewerName(t *testing.T) {
if os.Getenv("TEST_SUBPROCESS_MAIN") == "1" { if os.Getenv("TEST_SUBPROCESS_MAIN") == "1" {
flag.CommandLine = flag.NewFlagSet(os.Args[0], flag.ExitOnError) flag.CommandLine = flag.NewFlagSet(os.Args[0], flag.ExitOnError)
os.Args = []string{"review-bot", os.Args = []string{"review-bot",
"--vcs-url", "http://localhost", "--gitea-url", "http://localhost",
"--repo", "owner/repo", "--repo", "owner/repo",
"--pr", "1", "--pr", "1",
"--reviewer-name", "invalid name", "--reviewer-name", "invalid name",
@@ -736,7 +820,7 @@ func TestMainSubprocess_InvalidRepo(t *testing.T) {
if os.Getenv("TEST_SUBPROCESS_MAIN") == "1" { if os.Getenv("TEST_SUBPROCESS_MAIN") == "1" {
flag.CommandLine = flag.NewFlagSet(os.Args[0], flag.ExitOnError) flag.CommandLine = flag.NewFlagSet(os.Args[0], flag.ExitOnError)
os.Args = []string{"review-bot", os.Args = []string{"review-bot",
"--vcs-url", "http://localhost", "--gitea-url", "http://localhost",
"--repo", "invalidrepo", "--repo", "invalidrepo",
"--pr", "1", "--pr", "1",
"--reviewer-token", "tok", "--reviewer-token", "tok",
@@ -763,7 +847,7 @@ func TestMainSubprocess_InvalidPRNumber(t *testing.T) {
if os.Getenv("TEST_SUBPROCESS_MAIN") == "1" { if os.Getenv("TEST_SUBPROCESS_MAIN") == "1" {
flag.CommandLine = flag.NewFlagSet(os.Args[0], flag.ExitOnError) flag.CommandLine = flag.NewFlagSet(os.Args[0], flag.ExitOnError)
os.Args = []string{"review-bot", os.Args = []string{"review-bot",
"--vcs-url", "http://localhost", "--gitea-url", "http://localhost",
"--repo", "owner/repo", "--repo", "owner/repo",
"--pr", "notanumber", "--pr", "notanumber",
"--reviewer-token", "tok", "--reviewer-token", "tok",
@@ -790,7 +874,7 @@ func TestMainSubprocess_InvalidTemperature(t *testing.T) {
if os.Getenv("TEST_SUBPROCESS_MAIN") == "1" { if os.Getenv("TEST_SUBPROCESS_MAIN") == "1" {
flag.CommandLine = flag.NewFlagSet(os.Args[0], flag.ExitOnError) flag.CommandLine = flag.NewFlagSet(os.Args[0], flag.ExitOnError)
os.Args = []string{"review-bot", os.Args = []string{"review-bot",
"--vcs-url", "http://localhost", "--gitea-url", "http://localhost",
"--repo", "owner/repo", "--repo", "owner/repo",
"--pr", "1", "--pr", "1",
"--reviewer-token", "tok", "--reviewer-token", "tok",
@@ -818,7 +902,7 @@ func TestMainSubprocess_InvalidProvider(t *testing.T) {
if os.Getenv("TEST_SUBPROCESS_MAIN") == "1" { if os.Getenv("TEST_SUBPROCESS_MAIN") == "1" {
flag.CommandLine = flag.NewFlagSet(os.Args[0], flag.ExitOnError) flag.CommandLine = flag.NewFlagSet(os.Args[0], flag.ExitOnError)
os.Args = []string{"review-bot", os.Args = []string{"review-bot",
"--vcs-url", "http://localhost", "--gitea-url", "http://localhost",
"--repo", "owner/repo", "--repo", "owner/repo",
"--pr", "1", "--pr", "1",
"--reviewer-token", "tok", "--reviewer-token", "tok",
@@ -842,35 +926,7 @@ func TestMainSubprocess_InvalidProvider(t *testing.T) {
} }
} }
func TestMainSubprocess_InvalidVCSProvider(t *testing.T) { // cleanEnv returns environ without any GITEA/LLM/REVIEWER env vars that would
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. // interfere with testing missing-flag scenarios.
func cleanEnv() []string { func cleanEnv() []string {
var env []string var env []string
@@ -878,7 +934,6 @@ func cleanEnv() []string {
key := strings.SplitN(e, "=", 2)[0] key := strings.SplitN(e, "=", 2)[0]
switch { switch {
case strings.HasPrefix(key, "GITEA_"), case strings.HasPrefix(key, "GITEA_"),
strings.HasPrefix(key, "VCS_"),
strings.HasPrefix(key, "LLM_"), strings.HasPrefix(key, "LLM_"),
strings.HasPrefix(key, "REVIEWER_"), strings.HasPrefix(key, "REVIEWER_"),
strings.HasPrefix(key, "PR_"), strings.HasPrefix(key, "PR_"),
@@ -896,12 +951,12 @@ func cleanEnv() []string {
} }
func TestFindAllOwnReviews(t *testing.T) { func TestFindAllOwnReviews(t *testing.T) {
reviews := []vcs.Review{ reviews := []gitea.Review{
makeReview(1, "bot", "APPROVED", false, "<!-- review-bot:sonnet -->\nfirst review"), {ID: 1, Body: "<!-- review-bot:sonnet -->\nfirst review"},
makeReview(2, "bot", "APPROVED", false, "<!-- review-bot:gpt -->\nother bot"), {ID: 2, Body: "<!-- review-bot:gpt -->\nother bot"},
makeReview(3, "bot", "APPROVED", false, "<!-- review-bot:sonnet -->\nsecond review"), {ID: 3, Body: "<!-- review-bot:sonnet -->\nsecond review"},
makeReview(4, "bot", "APPROVED", false, "~~Original review~~\n<!-- review-bot:sonnet -->\nsuperseded"), {ID: 4, Body: "~~Original review~~\n<!-- review-bot:sonnet -->\nsuperseded"},
makeReview(5, "bot", "APPROVED", false, "<!-- review-bot:sonnet -->\nthird review"), {ID: 5, Body: "<!-- review-bot:sonnet -->\nthird review"},
} }
got := findAllOwnReviews(reviews, "<!-- review-bot:sonnet -->") got := findAllOwnReviews(reviews, "<!-- review-bot:sonnet -->")
@@ -965,23 +1020,3 @@ 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)
}
}
}
+31 -10
View File
@@ -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 `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 - Library: use `gopkg.in/yaml.v3` (approved in CONVENTIONS.md) with explicit depth limiting
## Proposed Approach ## Proposed Approach
@@ -33,16 +33,37 @@ func parsePersona(data []byte, source string) (*Persona, error) {
### YAML Parsing with Depth Protection ### YAML Parsing with Depth Protection
We implement a custom AST-based depth/node-count walk (`checkYAMLDepth` in ```go
`review/persona.go`) rather than relying on library decoder options. Key design func unmarshalYAMLWithDepthLimit(data []byte, out any, maxDepth int) error {
decisions: var node yaml.Node
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)
}
- **Library:** `github.com/goccy/go-yaml` with `ast.Node`-based traversal func checkYAMLDepth(node *yaml.Node, depth, maxDepth int) error {
- **Dual-map tracking:** `validated` (depth-aware short-circuit) + `visiting` (cycle detection) if depth > maxDepth {
- **Node-count limit:** Conservative overcounting bounds total validation work return fmt.Errorf("YAML nesting depth exceeds maximum (%d)", maxDepth)
- **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
}
```
See `review/persona.go:checkYAMLDepth` for the authoritative implementation. The `gopkg.in/yaml.v3` library does not have built-in depth protection, so we implement explicit depth checking by first decoding into a `yaml.Node`, walking the tree to verify depth (including alias resolution), then decoding into the target struct.
## State/Data Model ## State/Data Model
@@ -53,7 +74,7 @@ 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 | Custom AST walk (`checkYAMLDepth`) rejects before decode | | Deeply nested YAML | Library rejects (v1.16.0+ fix) |
| 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 |
-7
View File
@@ -16,7 +16,6 @@ type Adapter struct {
// Compile-time interface conformance assertion. // Compile-time interface conformance assertion.
var _ vcs.Client = (*Adapter)(nil) var _ vcs.Client = (*Adapter)(nil)
var _ vcs.ReviewerSelfRequester = (*Adapter)(nil)
// NewAdapter creates a new Adapter wrapping the given gitea Client. // NewAdapter creates a new Adapter wrapping the given gitea Client.
func NewAdapter(client *Client) *Adapter { func NewAdapter(client *Client) *Adapter {
@@ -231,9 +230,3 @@ func (a *Adapter) DismissReview(ctx context.Context, owner, repo string, number
func (a *Adapter) GetAuthenticatedUser(ctx context.Context) (string, error) { func (a *Adapter) GetAuthenticatedUser(ctx context.Context) (string, error) {
return a.client.GetAuthenticatedUser(ctx) 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)
}
-22
View File
@@ -386,25 +386,3 @@ func TestAdapter_GetFileContent_RefRouting(t *testing.T) {
t.Errorf("GetFileContent(ref=\"abc123\") = %q, want %q", got, "content-at-ref") 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)
}
}
+4 -11
View File
@@ -11,7 +11,6 @@ import (
type PositionMap struct { type PositionMap struct {
// files maps filename → (position → new-file line number). // files maps filename → (position → new-file line number).
// Deletion lines are mapped to -1 (no new-file line). // Deletion lines are mapped to -1 (no new-file line).
// Hunk-header lines are mapped to 0 (no new-file line).
files map[string]map[int]int files map[string]map[int]int
// maxPositions caches the highest position number per file, // maxPositions caches the highest position number per file,
// tracked during construction to avoid O(n) scans at translate time. // tracked during construction to avoid O(n) scans at translate time.
@@ -20,8 +19,8 @@ type PositionMap struct {
// Translate converts a GitHub diff-position to a new-file line number for a given file. // Translate converts a GitHub diff-position to a new-file line number for a given file.
// Returns an error if the file is not in the diff or the position is out of range. // Returns an error if the file is not in the diff or the position is out of range.
// If the position targets a deletion or hunk-header line, it maps to the nearest // If the position targets a deletion line, it maps to the nearest non-deletion line below;
// context/addition line below; if no such line exists, returns an error. // if no such line exists, returns an error.
func (pm *PositionMap) Translate(file string, position int) (int, error) { func (pm *PositionMap) Translate(file string, position int) (int, error) {
if pm == nil || pm.files == nil { if pm == nil || pm.files == nil {
return 0, fmt.Errorf("empty position map") return 0, fmt.Errorf("empty position map")
@@ -42,18 +41,14 @@ func (pm *PositionMap) Translate(file string, position int) (int, error) {
} }
// lineNum == -1 means this position is a deletion line. // lineNum == -1 means this position is a deletion line.
// lineNum == 0 means this position is a hunk-header line. // Map to the nearest non-deletion line below.
// Both map to the nearest context/addition line below. if lineNum == -1 {
if lineNum <= 0 {
maxPos := pm.maxPosition(file) maxPos := pm.maxPosition(file)
for p := position + 1; p <= maxPos; p++ { for p := position + 1; p <= maxPos; p++ {
if ln, exists := fileMap[p]; exists && ln > 0 { if ln, exists := fileMap[p]; exists && ln > 0 {
return ln, nil return ln, nil
} }
} }
if lineNum == 0 {
return 0, fmt.Errorf("position %d targets a hunk-header line with no subsequent new-file line in %q", position, file)
}
return 0, fmt.Errorf("position %d targets a deletion line with no subsequent new-file line in %q", position, file) return 0, fmt.Errorf("position %d targets a deletion line with no subsequent new-file line in %q", position, file)
} }
@@ -75,7 +70,6 @@ func (pm *PositionMap) maxPosition(file string) int {
// - A new @@ hunk within the same file continues incrementing (does not reset) // - A new @@ hunk within the same file continues incrementing (does not reset)
// - Position maps to the new file line number for additions and context lines // - Position maps to the new file line number for additions and context lines
// - Deletion lines have a position but no new-file line number (stored as -1) // - Deletion lines have a position but no new-file line number (stored as -1)
// - Hunk-header lines have a position but no new-file line number (stored as 0)
func BuildPositionToLineMap(diff string) *PositionMap { func BuildPositionToLineMap(diff string) *PositionMap {
pm := &PositionMap{ pm := &PositionMap{
files: make(map[string]map[int]int), files: make(map[string]map[int]int),
@@ -132,7 +126,6 @@ func BuildPositionToLineMap(diff string) *PositionMap {
// Parse hunk headers // Parse hunk headers
if strings.HasPrefix(line, "@@") && currentFile != "" { if strings.HasPrefix(line, "@@") && currentFile != "" {
position++ position++
pm.files[currentFile][position] = 0 // sentinel: hunk-header has no new-file line
pm.maxPositions[currentFile] = position pm.maxPositions[currentFile] = position
newLine = parseHunkStart(line) newLine = parseHunkStart(line)
continue continue
-109
View File
@@ -272,112 +272,3 @@ diff --git a/b.go b/b.go
t.Errorf("Translate(b.go, 3) = %d, want 2", got) t.Errorf("Translate(b.go, 3) = %d, want 2", got)
} }
} }
func TestTranslate_HunkHeaderPosition_SingleHunk(t *testing.T) {
// Position 1 is the @@ hunk-header line.
// It should resolve to the first context/addition line below (new line 16).
diff := `diff --git a/file.go b/file.go
index abc..def 100644
--- a/file.go
+++ b/file.go
@@ -16,4 +16,5 @@ func example() {
context line
-deleted line
+added line
context after
`
pm := BuildPositionToLineMap(diff)
got, err := pm.Translate("file.go", 1)
if err != nil {
t.Fatalf("Translate(file.go, 1): unexpected error: %v", err)
}
if got != 16 {
t.Errorf("Translate(file.go, 1) = %d, want 16 (first context/addition line in hunk)", got)
}
}
func TestTranslate_HunkHeaderPosition_MultiHunk(t *testing.T) {
// First hunk: @@ is pos 1, then " line1" (pos 2), "-old" (pos 3), "+new" (pos 4)
// Second hunk: @@ is pos 5, then " func foo() {" (pos 6), "+// added" (pos 7), etc.
// Translating position 5 (second @@) should resolve to new line 10.
diff := `diff --git a/file.go b/file.go
--- a/file.go
+++ b/file.go
@@ -1,3 +1,3 @@ package main
line1
-old
+new
@@ -10,3 +10,4 @@ func foo() {
func foo() {
+ // added
return
}
`
pm := BuildPositionToLineMap(diff)
// Position 5 is the second @@ hunk-header — should resolve to new line 10
got, err := pm.Translate("file.go", 5)
if err != nil {
t.Fatalf("Translate(file.go, 5): unexpected error: %v", err)
}
if got != 10 {
t.Errorf("Translate(file.go, 5) = %d, want 10 (first context/addition line in second hunk)", got)
}
// Also verify first hunk header at position 1 resolves to new line 1
got, err = pm.Translate("file.go", 1)
if err != nil {
t.Fatalf("Translate(file.go, 1): unexpected error: %v", err)
}
if got != 1 {
t.Errorf("Translate(file.go, 1) = %d, want 1 (first context/addition line in first hunk)", got)
}
}
func TestTranslate_HunkHeaderPosition_NewFile(t *testing.T) {
// New file: @@ -0,0 +1,3 @@ is position 1.
// Should resolve to new line 1 (the first addition).
diff := `diff --git a/new.go b/new.go
new file mode 100644
--- /dev/null
+++ b/new.go
@@ -0,0 +1,3 @@
+package main
+
+func init() {}
`
pm := BuildPositionToLineMap(diff)
got, err := pm.Translate("new.go", 1)
if err != nil {
t.Fatalf("Translate(new.go, 1): unexpected error: %v", err)
}
if got != 1 {
t.Errorf("Translate(new.go, 1) = %d, want 1 (first addition line)", got)
}
}
func TestTranslate_HunkHeaderAtEnd(t *testing.T) {
// A hunk-header at the last position with no subsequent new-file line should error.
// This is the hunk-header equivalent of TestBuildPositionToLineMap_DeletionAtEnd.
diff := `diff --git a/file.go b/file.go
--- a/file.go
+++ b/file.go
@@ -1,2 +1,2 @@ package main
line1
-old
+new
@@ -10,2 +10,1 @@ func foo() {
-removed
`
pm := BuildPositionToLineMap(diff)
// Position 5 is the second @@ hunk-header; the only line after it (pos 6) is a
// deletion (lineNum == -1), so there's no positive new-file line to resolve to.
// The hunk-header lookup should fail.
_, err := pm.Translate("file.go", 5)
if err == nil {
t.Error("expected error for hunk-header at end with no subsequent new-file line")
}
}
+15 -70
View File
@@ -4,9 +4,7 @@
package github package github
import ( import (
"bytes"
"context" "context"
"encoding/json"
"errors" "errors"
"fmt" "fmt"
"io" "io"
@@ -194,32 +192,12 @@ func (c *Client) SetRetryBackoff(d []time.Duration) error {
return nil return nil
} }
// requestOptions holds per-request configuration for doRequestCore. // doRequest performs an HTTP request with retry on 429 rate limit responses.
type requestOptions struct { // It respects the Retry-After header when present (capped at maxRetryAfter).
// bodyFn returns a fresh io.Reader for the request body on each attempt. // Transport errors (network failures, context cancellation) are not retried.
// Must be non-nil for any request that carries a body (POST, PUT, PATCH, func (c *Client) doRequest(ctx context.Context, method, reqURL string, accept string) ([]byte, error) {
// or DELETE when a body is required by the API).
// Returning a fresh reader on each call allows retries to re-send the body.
bodyFn func() io.Reader
// accept overrides the default Accept header. Empty means "application/vnd.github+json".
accept string
// extraHeaders are additional headers to set on each request attempt.
extraHeaders map[string]string
}
// doRequestCore is the shared implementation for all HTTP requests with retry
// on 429 rate limit responses. It respects the Retry-After header when present
// (capped at maxRetryAfter). Transport errors are not retried.
func (c *Client) doRequestCore(ctx context.Context, method, reqURL string, opts requestOptions) ([]byte, error) {
const maxRetryAfter = 120 * time.Second 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. // backoff holds per-attempt delays: backoff[i] is the delay before attempt i+1.
// Length must be maxRetryAttempts-1 (one entry per retry gap). // Length must be maxRetryAttempts-1 (one entry per retry gap).
// SetRetryBackoff validates at configuration time; the default is always valid. // SetRetryBackoff validates at configuration time; the default is always valid.
@@ -233,6 +211,11 @@ func (c *Client) doRequestCore(ctx context.Context, method, reqURL string, opts
copy(backoff, defaultBackoff) 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. // Reject non-HTTPS URLs early since the URL is immutable across retries.
if c.token != "" && !c.allowInsecureHTTP { if c.token != "" && !c.allowInsecureHTTP {
parsed, err := url.Parse(reqURL) parsed, err := url.Parse(reqURL)
@@ -263,11 +246,7 @@ func (c *Client) doRequestCore(ctx context.Context, method, reqURL string, opts
} }
} }
var body io.Reader req, err := http.NewRequestWithContext(ctx, method, reqURL, nil)
if opts.bodyFn != nil {
body = opts.bodyFn()
}
req, err := http.NewRequestWithContext(ctx, method, reqURL, body)
if err != nil { if err != nil {
return nil, fmt.Errorf("create request: %w", err) return nil, fmt.Errorf("create request: %w", err)
} }
@@ -278,14 +257,11 @@ func (c *Client) doRequestCore(ctx context.Context, method, reqURL string, opts
req.Header.Set("Authorization", "Bearer "+c.token) req.Header.Set("Authorization", "Bearer "+c.token)
} }
req.Header.Set("User-Agent", userAgent) req.Header.Set("User-Agent", userAgent)
if opts.accept != "" { if accept != "" {
req.Header.Set("Accept", opts.accept) req.Header.Set("Accept", accept)
} else { } else {
req.Header.Set("Accept", "application/vnd.github+json") req.Header.Set("Accept", "application/vnd.github+json")
} }
for k, v := range opts.extraHeaders {
req.Header.Set(k, v)
}
resp, err := c.httpClient.Do(req) resp, err := c.httpClient.Do(req)
if err != nil { if err != nil {
@@ -296,11 +272,11 @@ func (c *Client) doRequestCore(ctx context.Context, method, reqURL string, opts
respStatus := resp.StatusCode respStatus := resp.StatusCode
retryAfterHeader := resp.Header.Get("Retry-After") retryAfterHeader := resp.Header.Get("Retry-After")
respBody, done, handleErr := c.handleResponse(resp, maxResponseBytes, maxErrorBodyBytes) body, done, err := c.handleResponse(resp, maxResponseBytes, maxErrorBodyBytes)
if done { if done {
return respBody, handleErr return body, err
} }
lastErr = handleErr lastErr = err
// Retry on 429 rate limit // Retry on 429 rate limit
if respStatus == http.StatusTooManyRequests && attempt < maxRetryAttempts-1 { if respStatus == http.StatusTooManyRequests && attempt < maxRetryAttempts-1 {
@@ -338,13 +314,6 @@ func (c *Client) doRequestCore(ctx context.Context, method, reqURL string, opts
return nil, lastErr return nil, lastErr
} }
// doRequest performs an HTTP request with retry on 429 rate limit responses.
// It respects the Retry-After header when present (capped at maxRetryAfter).
// Transport errors (network failures, context cancellation) are not retried.
func (c *Client) doRequest(ctx context.Context, method, reqURL string, accept string) ([]byte, error) {
return c.doRequestCore(ctx, method, reqURL, requestOptions{accept: accept})
}
// handleResponse reads and closes the response body, returning the result. // handleResponse reads and closes the response body, returning the result.
// It uses defer to ensure the body is always closed regardless of code path. // It uses defer to ensure the body is always closed regardless of code path.
// Returns (body, done, err) where done=true means the caller should return immediately. // Returns (body, done, err) where done=true means the caller should return immediately.
@@ -373,27 +342,3 @@ func (c *Client) handleResponse(resp *http.Response, maxRespBytes int, maxErrByt
func (c *Client) doGet(ctx context.Context, reqURL string) ([]byte, error) { func (c *Client) doGet(ctx context.Context, reqURL string) ([]byte, error) {
return c.doRequest(ctx, http.MethodGet, reqURL, "") return c.doRequest(ctx, http.MethodGet, reqURL, "")
} }
// doRequestWithBody is like doRequest but sends a request body.
// It accepts the raw body bytes and sets Content-Type to application/json.
// Retry semantics match doRequest (retries on 429 with Retry-After support).
func (c *Client) doRequestWithBody(ctx context.Context, method, reqURL string, reqBody []byte) ([]byte, error) {
var opts requestOptions
if reqBody != nil {
opts.bodyFn = func() io.Reader { return bytes.NewReader(reqBody) }
opts.extraHeaders = map[string]string{"Content-Type": "application/json"}
}
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)
}
+1 -57
View File
@@ -2,7 +2,6 @@ package github
import ( import (
"context" "context"
"errors"
"net/http" "net/http"
"net/http/httptest" "net/http/httptest"
"net/url" "net/url"
@@ -568,6 +567,7 @@ func TestSetHTTPClient_NilRestoresDefault(t *testing.T) {
} }
} }
func TestSetRetryBackoff_RejectsInvalidLength(t *testing.T) { func TestSetRetryBackoff_RejectsInvalidLength(t *testing.T) {
c := NewClient("token", "https://api.github.com") c := NewClient("token", "https://api.github.com")
@@ -592,59 +592,3 @@ func TestSetRetryBackoff_RejectsInvalidLength(t *testing.T) {
t.Fatalf("unexpected error for valid backoff: %v", err) 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)
}
}
+2 -3
View File
@@ -6,6 +6,5 @@ import (
) )
// Compile-time interface conformance assertion. // Compile-time interface conformance assertion.
// This verifies github.Client satisfies the full vcs.Client interface // Verifies github.Client satisfies vcs.PRReader.
// (PRReader, FileReader, Reviewer, Identity). var _ vcs.PRReader = (*github.Client)(nil)
var _ vcs.Client = (*github.Client)(nil)
-60
View File
@@ -8,16 +8,8 @@ import (
"net/url" "net/url"
"path" "path"
"strings" "strings"
"gitea.weiker.me/rodin/review-bot/vcs"
) )
// GetFileContent fetches a file from a repo at the given ref.
// Delegates to GetFileContentAtRef with the provided ref.
func (c *Client) GetFileContent(ctx context.Context, owner, repo, filePath, ref string) (string, error) {
return c.GetFileContentAtRef(ctx, owner, repo, filePath, ref)
}
// GetFileContentAtRef fetches a file at a specific ref from a repo. // GetFileContentAtRef fetches a file at a specific ref from a repo.
// If ref is empty, the query parameter is omitted (uses default branch). // If ref is empty, the query parameter is omitted (uses default branch).
// //
@@ -54,58 +46,6 @@ func (c *Client) GetFileContentAtRef(ctx context.Context, owner, repo, filePath,
return decoded, nil return decoded, nil
} }
// ListContents lists files and directories at a given path in a repo.
// Returns the directory listing from the GitHub contents API.
// If the path points to a single file (not a directory), the API returns
// a JSON object instead of an array; this is handled by returning a
// single-element slice.
func (c *Client) ListContents(ctx context.Context, owner, repo, filePath string) ([]vcs.ContentEntry, error) {
escaped, err := escapePath(filePath)
if err != nil {
return nil, fmt.Errorf("invalid file path: %w", err)
}
reqURL := fmt.Sprintf("%s/repos/%s/%s/contents/%s",
c.baseURL, url.PathEscape(owner), url.PathEscape(repo), escaped)
body, err := c.doGet(ctx, reqURL)
if err != nil {
return nil, fmt.Errorf("list contents %s: %w", filePath, err)
}
type entry struct {
Name string `json:"name"`
Path string `json:"path"`
Type string `json:"type"`
}
// The GitHub contents API returns an array for directories and an object
// for single files. Try array first (common case), then fall back to object.
// An empty array ([]) is valid — it represents an empty directory — and
// results in a zero-length slice returned without error.
var entries []entry
if err := json.Unmarshal(body, &entries); err != nil {
var single entry
if err2 := json.Unmarshal(body, &single); err2 != nil {
return nil, fmt.Errorf("parse contents JSON: as array: %v; as object: %w", err, err2)
}
// Guard against empty objects ({}) or unexpected shapes that
// unmarshal successfully but carry no useful data.
if single.Name == "" && single.Path == "" && single.Type == "" {
return nil, fmt.Errorf("parse contents JSON: unexpected response format")
}
entries = []entry{single}
}
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
}
// escapePath validates and encodes a slash-separated file path for use in // escapePath validates and encodes a slash-separated file path for use in
// GitHub API URLs. Returns an error if the path contains dot-segments ("." // GitHub API URLs. Returns an error if the path contains dot-segments ("."
// or "..") or resolves to a path outside the repository root. // or "..") or resolves to a path outside the repository root.
+2 -311
View File
@@ -2,291 +2,12 @@ package github
import ( import (
"context" "context"
"encoding/json"
"net/http" "net/http"
"net/http/httptest" "net/http/httptest"
"strings" "strings"
"testing" "testing"
"time"
) )
func TestGetFileContent_DelegatesToGetFileContentAtRef(t *testing.T) {
var gotRef string
srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
gotRef = r.URL.Query().Get("ref")
json.NewEncoder(w).Encode(map[string]string{
"content": "dGVzdA==", // "test" in base64
"encoding": "base64",
})
}))
defer srv.Close()
c := NewClient("token", srv.URL, AllowInsecureHTTP())
c.SetHTTPClient(srv.Client())
// Call with empty ref — should not include ref param
content, err := c.GetFileContent(context.Background(), "owner", "repo", "file.go", "")
if err != nil {
t.Fatalf("unexpected error: %v", err)
}
if content != "test" {
t.Errorf("expected 'test', got %q", content)
}
if gotRef != "" {
t.Errorf("expected empty ref, got %q", gotRef)
}
}
func TestGetFileContent_WithRef(t *testing.T) {
var gotRef string
srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
gotRef = r.URL.Query().Get("ref")
json.NewEncoder(w).Encode(map[string]string{
"content": "dGVzdA==",
"encoding": "base64",
})
}))
defer srv.Close()
c := NewClient("token", srv.URL, AllowInsecureHTTP())
c.SetHTTPClient(srv.Client())
_, err := c.GetFileContent(context.Background(), "owner", "repo", "file.go", "abc123")
if err != nil {
t.Fatalf("unexpected error: %v", err)
}
if gotRef != "abc123" {
t.Errorf("expected ref 'abc123', got %q", gotRef)
}
}
func TestGetFileContent_404(t *testing.T) {
srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
w.WriteHeader(404)
w.Write([]byte(`{"message":"Not Found"}`))
}))
defer srv.Close()
c := NewClient("token", srv.URL, AllowInsecureHTTP())
c.SetHTTPClient(srv.Client())
_, err := c.GetFileContent(context.Background(), "owner", "repo", "missing.go", "")
if err == nil {
t.Fatal("expected error for 404")
}
}
func TestGetFileContent_401(t *testing.T) {
srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
w.WriteHeader(401)
w.Write([]byte(`{"message":"Bad credentials"}`))
}))
defer srv.Close()
c := NewClient("token", srv.URL, AllowInsecureHTTP())
c.SetHTTPClient(srv.Client())
_, err := c.GetFileContent(context.Background(), "owner", "repo", "file.go", "")
if err == nil {
t.Fatal("expected error for 401")
}
}
func TestGetFileContent_429Retry(t *testing.T) {
attempts := 0
srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
attempts++
if attempts == 1 {
w.WriteHeader(429)
w.Write([]byte(`{"message":"rate limit"}`))
return
}
json.NewEncoder(w).Encode(map[string]string{
"content": "b2s=",
"encoding": "base64",
})
}))
defer srv.Close()
c := NewClient("token", srv.URL, AllowInsecureHTTP())
c.SetHTTPClient(srv.Client())
if err := c.SetRetryBackoff([]time.Duration{1 * time.Millisecond, 1 * time.Millisecond}); err != nil {
t.Fatalf("SetRetryBackoff: %v", err)
}
content, err := c.GetFileContent(context.Background(), "owner", "repo", "file.go", "")
if err != nil {
t.Fatalf("unexpected error: %v", err)
}
if content != "ok" {
t.Errorf("expected 'ok', got %q", content)
}
if attempts != 2 {
t.Errorf("expected 2 attempts, got %d", attempts)
}
}
func TestGetFileContent_MalformedJSON(t *testing.T) {
srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
w.WriteHeader(200)
w.Write([]byte(`not json`))
}))
defer srv.Close()
c := NewClient("token", srv.URL, AllowInsecureHTTP())
c.SetHTTPClient(srv.Client())
_, err := c.GetFileContent(context.Background(), "owner", "repo", "file.go", "")
if err == nil {
t.Fatal("expected error for malformed JSON")
}
}
func TestListContents_HappyPath(t *testing.T) {
srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
if r.URL.Path != "/repos/owner/repo/contents/src" {
t.Errorf("unexpected path: %s", r.URL.Path)
}
json.NewEncoder(w).Encode([]map[string]string{
{"name": "main.go", "path": "src/main.go", "type": "file"},
{"name": "lib", "path": "src/lib", "type": "dir"},
})
}))
defer srv.Close()
c := NewClient("token", srv.URL, AllowInsecureHTTP())
c.SetHTTPClient(srv.Client())
entries, err := c.ListContents(context.Background(), "owner", "repo", "src")
if err != nil {
t.Fatalf("unexpected error: %v", err)
}
if len(entries) != 2 {
t.Fatalf("expected 2 entries, got %d", len(entries))
}
if entries[0].Name != "main.go" {
t.Errorf("expected name 'main.go', got %q", entries[0].Name)
}
if entries[0].Path != "src/main.go" {
t.Errorf("expected path 'src/main.go', got %q", entries[0].Path)
}
if entries[0].Type != "file" {
t.Errorf("expected type 'file', got %q", entries[0].Type)
}
if entries[1].Name != "lib" {
t.Errorf("expected name 'lib', got %q", entries[1].Name)
}
if entries[1].Type != "dir" {
t.Errorf("expected type 'dir', got %q", entries[1].Type)
}
}
func TestListContents_404(t *testing.T) {
srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
w.WriteHeader(404)
w.Write([]byte(`{"message":"Not Found"}`))
}))
defer srv.Close()
c := NewClient("token", srv.URL, AllowInsecureHTTP())
c.SetHTTPClient(srv.Client())
_, err := c.ListContents(context.Background(), "owner", "repo", "missing")
if err == nil {
t.Fatal("expected error for 404")
}
}
func TestListContents_401(t *testing.T) {
srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
w.WriteHeader(401)
w.Write([]byte(`{"message":"Bad credentials"}`))
}))
defer srv.Close()
c := NewClient("token", srv.URL, AllowInsecureHTTP())
c.SetHTTPClient(srv.Client())
_, err := c.ListContents(context.Background(), "owner", "repo", "src")
if err == nil {
t.Fatal("expected error for 401")
}
}
func TestListContents_429Retry(t *testing.T) {
attempts := 0
srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
attempts++
if attempts == 1 {
w.WriteHeader(429)
w.Write([]byte(`{"message":"rate limit"}`))
return
}
json.NewEncoder(w).Encode([]map[string]string{
{"name": "file.go", "path": "file.go", "type": "file"},
})
}))
defer srv.Close()
c := NewClient("token", srv.URL, AllowInsecureHTTP())
c.SetHTTPClient(srv.Client())
if err := c.SetRetryBackoff([]time.Duration{1 * time.Millisecond, 1 * time.Millisecond}); err != nil {
t.Fatalf("SetRetryBackoff: %v", err)
}
entries, err := c.ListContents(context.Background(), "owner", "repo", "src")
if err != nil {
t.Fatalf("unexpected error: %v", err)
}
if len(entries) != 1 {
t.Fatalf("expected 1 entry, got %d", len(entries))
}
if attempts != 2 {
t.Errorf("expected 2 attempts, got %d", attempts)
}
}
func TestListContents_MalformedJSON(t *testing.T) {
srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
w.WriteHeader(200)
w.Write([]byte(`not json`))
}))
defer srv.Close()
c := NewClient("token", srv.URL, AllowInsecureHTTP())
c.SetHTTPClient(srv.Client())
_, err := c.ListContents(context.Background(), "owner", "repo", "src")
if err == nil {
t.Fatal("expected error for malformed JSON")
}
}
func TestListContents_SingleFile(t *testing.T) {
// GitHub Contents API returns a JSON object (not array) for single-file paths
srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
w.WriteHeader(200)
w.Write([]byte(`{"name":"README.md","path":"README.md","type":"file"}`))
}))
defer srv.Close()
c := NewClient("token", srv.URL, AllowInsecureHTTP())
c.SetHTTPClient(srv.Client())
entries, err := c.ListContents(context.Background(), "owner", "repo", "README.md")
if err != nil {
t.Fatalf("unexpected error: %v", err)
}
if len(entries) != 1 {
t.Fatalf("expected 1 entry, got %d", len(entries))
}
if entries[0].Name != "README.md" {
t.Errorf("expected name 'README.md', got %q", entries[0].Name)
}
if entries[0].Type != "file" {
t.Errorf("expected type 'file', got %q", entries[0].Type)
}
}
func TestEscapePath_ValidPaths(t *testing.T) { func TestEscapePath_ValidPaths(t *testing.T) {
t.Parallel() t.Parallel()
tests := []struct { tests := []struct {
@@ -347,7 +68,7 @@ func TestGetFileContentAtRef_DotSegmentError(t *testing.T) {
})) }))
defer srv.Close() defer srv.Close()
c := NewClient("token", srv.URL, AllowInsecureHTTP()) c := NewClient("token", srv.URL)
_, err := c.GetFileContentAtRef(context.Background(), "owner", "repo", "foo/../bar.go", "main") _, err := c.GetFileContentAtRef(context.Background(), "owner", "repo", "foo/../bar.go", "main")
if err == nil { if err == nil {
t.Fatal("expected error for path with dot-segments") t.Fatal("expected error for path with dot-segments")
@@ -357,37 +78,6 @@ func TestGetFileContentAtRef_DotSegmentError(t *testing.T) {
} }
} }
func TestDecodeBase64Content(t *testing.T) {
// Test with newlines (GitHub's format)
encoded := "cGFja2FnZSBt\nYWlu"
decoded, err := decodeBase64Content(encoded)
if err != nil {
t.Fatalf("unexpected error: %v", err)
}
if decoded != "package main" {
t.Errorf("expected 'package main', got %q", decoded)
}
}
func TestDecodeBase64Content_Invalid(t *testing.T) {
_, err := decodeBase64Content("not!!!valid!!!base64")
if err == nil {
t.Fatal("expected error for invalid base64")
}
}
func TestDecodeBase64Content_CRLF(t *testing.T) {
// Base64 of "hello world" with CRLF line breaks inserted
encoded := "aGVs\r\nbG8g\r\nd29y\r\nbGQ="
decoded, err := decodeBase64Content(encoded)
if err != nil {
t.Fatalf("unexpected error: %v", err)
}
if decoded != "hello world" {
t.Errorf("expected 'hello world', got %q", decoded)
}
}
func TestDecodeBase64Content_SizeLimit(t *testing.T) { func TestDecodeBase64Content_SizeLimit(t *testing.T) {
t.Parallel() t.Parallel()
// Create base64 content that would decode to > maxFileContentSize. // Create base64 content that would decode to > maxFileContentSize.
@@ -403,3 +93,4 @@ func TestDecodeBase64Content_SizeLimit(t *testing.T) {
t.Errorf("expected 'too large' error, got: %v", err) t.Errorf("expected 'too large' error, got: %v", err)
} }
} }
-23
View File
@@ -1,23 +0,0 @@
package github
import (
"net/http"
"net/http/httptest"
"testing"
"time"
)
// newTestClient creates a *Client backed by an httptest.Server running the
// given handler. The server is automatically closed when the test finishes.
// Shared across test files in package github.
func newTestClient(t *testing.T, handler http.HandlerFunc) *Client {
t.Helper()
srv := httptest.NewServer(handler)
t.Cleanup(srv.Close)
c := NewClient("test-token", srv.URL, AllowInsecureHTTP())
c.SetHTTPClient(srv.Client())
if err := c.SetRetryBackoff([]time.Duration{1 * time.Millisecond, 1 * time.Millisecond}); err != nil {
t.Fatalf("SetRetryBackoff: %v", err)
}
return c
}
-29
View File
@@ -1,29 +0,0 @@
package github
import (
"context"
"encoding/json"
"fmt"
)
// userResponse is the GitHub API response for the authenticated user.
type userResponse struct {
Login string `json:"login"`
}
// GetAuthenticatedUser returns the login of the currently authenticated user.
func (c *Client) GetAuthenticatedUser(ctx context.Context) (string, error) {
reqURL := fmt.Sprintf("%s/user", c.baseURL)
body, err := c.doGet(ctx, reqURL)
if err != nil {
return "", fmt.Errorf("get authenticated user: %w", err)
}
var resp userResponse
if err := json.Unmarshal(body, &resp); err != nil {
return "", fmt.Errorf("parse user response: %w", err)
}
return resp.Login, nil
}
-46
View File
@@ -1,46 +0,0 @@
package github
import (
"context"
"encoding/json"
"net/http"
"testing"
)
func TestGetAuthenticatedUser_HappyPath(t *testing.T) {
c := newTestClient(t, func(w http.ResponseWriter, r *http.Request) {
if r.Method != "GET" {
t.Errorf("expected GET, got %s", r.Method)
}
if r.URL.Path != "/user" {
t.Errorf("unexpected path: %s", r.URL.Path)
}
if r.Header.Get("Authorization") != "Bearer test-token" {
t.Errorf("unexpected auth header: %s", r.Header.Get("Authorization"))
}
json.NewEncoder(w).Encode(map[string]string{"login": "review-bot"})
})
login, err := c.GetAuthenticatedUser(context.Background())
if err != nil {
t.Fatalf("unexpected error: %v", err)
}
if login != "review-bot" {
t.Errorf("expected login 'review-bot', got %q", login)
}
}
func TestGetAuthenticatedUser_401(t *testing.T) {
c := newTestClient(t, func(w http.ResponseWriter, r *http.Request) {
w.WriteHeader(401)
w.Write([]byte(`{"message":"Bad credentials"}`))
})
_, err := c.GetAuthenticatedUser(context.Background())
if err == nil {
t.Fatal("expected error for 401")
}
if !IsUnauthorized(err) {
t.Errorf("expected IsUnauthorized=true, got error: %v", err)
}
}
-212
View File
@@ -1,212 +0,0 @@
package github
import (
"context"
"encoding/json"
"errors"
"fmt"
"net/http"
"net/url"
"gitea.weiker.me/rodin/review-bot/vcs"
)
// ErrCannotDeleteSubmittedReview is returned when DeleteReview is called on
// a review that has already been submitted (APPROVED, REQUEST_CHANGES, COMMENT).
// GitHub only allows deletion of PENDING reviews. Callers that need to replace
// a submitted review should use DismissReview instead.
var ErrCannotDeleteSubmittedReview = errors.New("cannot delete submitted review: use DismissReview instead")
// ErrConflictingCommitIDs is returned when PostReview receives comments with
// differing non-empty CommitIDs. The GitHub API accepts only a single commit_id
// per review submission; callers must ensure all comments target the same commit.
var ErrConflictingCommitIDs = errors.New("comments contain conflicting commit IDs: all must target the same commit")
// postReviewRequest is the GitHub API request body for creating a review.
type postReviewRequest struct {
CommitID string `json:"commit_id,omitempty"`
Body string `json:"body"`
Event string `json:"event"`
Comments []reviewCommentEntry `json:"comments,omitempty"`
}
// reviewCommentEntry is a single inline comment in a review creation request.
type reviewCommentEntry struct {
Path string `json:"path"`
Position int `json:"position"`
Body string `json:"body"`
}
// reviewResponse is the GitHub API response for a review.
type reviewResponse struct {
ID int64 `json:"id"`
Body string `json:"body"`
State string `json:"state"`
CommitID string `json:"commit_id"`
User struct {
Login string `json:"login"`
} `json:"user"`
}
// dismissReviewRequest is the GitHub API request body for dismissing a review.
type dismissReviewRequest struct {
Message string `json:"message"`
Event string `json:"event"`
}
// translateGitHubReviewState translates a GitHub API review state to the
// canonical vcs.Review.State value.
func translateGitHubReviewState(state string) string {
switch state {
case "CHANGES_REQUESTED":
return "REQUEST_CHANGES"
case "COMMENTED":
return "COMMENT"
default:
// States like APPROVED, DISMISSED, and PENDING pass through unchanged
// as they already match the canonical vcs representation. PENDING appears
// on draft reviews that have not yet been submitted via the GitHub UI or API.
return state
}
}
// PostReview submits a review on a pull request.
//
// The vcs.ReviewEvent constants (ReviewEventApprove, ReviewEventRequestChanges,
// ReviewEventComment) have string values that match GitHub's wire-format event
// strings (APPROVE, REQUEST_CHANGES, COMMENT), so Event is cast directly to
// string without translation.
//
// ReviewComment.Position maps directly to the GitHub API position field.
// When req.Comments is empty, the payload omits the comments field entirely
// (via the omitempty tag on postReviewRequest.Comments).
//
// The GitHub API accepts a single commit_id per review submission. PostReview
// extracts it from the first comment with a non-empty CommitID. If any subsequent
// comment specifies a different CommitID, PostReview returns ErrConflictingCommitIDs.
// Comments with an empty CommitID are allowed and inherit the review-level value.
func (c *Client) PostReview(ctx context.Context, owner, repo string, number int, req vcs.ReviewRequest) (*vcs.Review, error) {
reqURL := fmt.Sprintf("%s/repos/%s/%s/pulls/%d/reviews",
c.baseURL, url.PathEscape(owner), url.PathEscape(repo), number)
payload := postReviewRequest{
Body: req.Body,
Event: string(req.Event),
}
// Build the payload in one pass. The GitHub API accepts a single commit_id
// per review; we extract it from the first comment that supplies one and
// reject the request if any other comment disagrees.
for _, comment := range req.Comments {
if comment.CommitID != "" {
if payload.CommitID == "" {
payload.CommitID = comment.CommitID
} else if payload.CommitID != comment.CommitID {
return nil, ErrConflictingCommitIDs
}
}
payload.Comments = append(payload.Comments, reviewCommentEntry{
Path: comment.Path,
Position: comment.Position,
Body: comment.Body,
})
}
data, err := json.Marshal(payload)
if err != nil {
return nil, fmt.Errorf("marshal review request: %w", err)
}
body, err := c.doRequestWithBody(ctx, http.MethodPost, reqURL, data)
if err != nil {
return nil, fmt.Errorf("post review: %w", err)
}
var resp reviewResponse
if err := json.Unmarshal(body, &resp); err != nil {
return nil, fmt.Errorf("parse review response: %w", err)
}
return &vcs.Review{
ID: resp.ID,
Body: resp.Body,
User: vcs.UserInfo{Login: resp.User.Login},
State: translateGitHubReviewState(resp.State),
CommitID: resp.CommitID,
}, nil
}
// ListReviews retrieves all reviews for a pull request.
// GitHub review states are translated to canonical vcs values.
func (c *Client) ListReviews(ctx context.Context, owner, repo string, number int) ([]vcs.Review, error) {
reqURL := fmt.Sprintf("%s/repos/%s/%s/pulls/%d/reviews",
c.baseURL, url.PathEscape(owner), url.PathEscape(repo), number)
body, err := c.doGet(ctx, reqURL)
if err != nil {
return nil, fmt.Errorf("list reviews: %w", err)
}
var responses []reviewResponse
if err := json.Unmarshal(body, &responses); err != nil {
return nil, fmt.Errorf("parse reviews response: %w", err)
}
reviews := make([]vcs.Review, len(responses))
for i, r := range responses {
reviews[i] = vcs.Review{
ID: r.ID,
Body: r.Body,
User: vcs.UserInfo{Login: r.User.Login},
State: translateGitHubReviewState(r.State),
CommitID: r.CommitID,
}
}
return reviews, nil
}
// DeleteReview deletes a pull request review.
// Only PENDING reviews can be deleted; attempting to delete a submitted review
// (APPROVED, CHANGES_REQUESTED, or COMMENTED per GitHub API naming) returns
// ErrCannotDeleteSubmittedReview.
func (c *Client) DeleteReview(ctx context.Context, owner, repo string, number int, reviewID int64) error {
reqURL := fmt.Sprintf("%s/repos/%s/%s/pulls/%d/reviews/%d",
c.baseURL, url.PathEscape(owner), url.PathEscape(repo), number, reviewID)
// nil body: the GitHub DELETE endpoint for reviews requires no request body.
_, err := c.doRequestWithBody(ctx, http.MethodDelete, reqURL, nil)
if err != nil {
var apiErr *APIError
if errors.As(err, &apiErr) && apiErr.StatusCode == 422 {
return fmt.Errorf("delete review: %w", ErrCannotDeleteSubmittedReview)
}
return fmt.Errorf("delete review: %w", err)
}
return nil
}
// DismissReview dismisses a submitted review on a pull request.
// This is the correct way to "remove" a submitted review (APPROVED, REQUEST_CHANGES).
// GitHub does not allow deleting submitted reviews — they must be dismissed.
func (c *Client) DismissReview(ctx context.Context, owner, repo string, number int, reviewID int64, message string) error {
reqURL := fmt.Sprintf("%s/repos/%s/%s/pulls/%d/reviews/%d/dismissals",
c.baseURL, url.PathEscape(owner), url.PathEscape(repo), number, reviewID)
payload := dismissReviewRequest{
Message: message,
// Event is required by the GitHub API for dismissal requests, even though
// "DISMISS" is the only valid value for this endpoint.
Event: "DISMISS",
}
data, err := json.Marshal(payload)
if err != nil {
return fmt.Errorf("marshal dismiss request: %w", err)
}
_, err = c.doRequestWithBody(ctx, http.MethodPut, reqURL, data)
if err != nil {
return fmt.Errorf("dismiss review: %w", err)
}
return nil
}
-391
View File
@@ -1,391 +0,0 @@
package github
import (
"context"
"encoding/json"
"errors"
"io"
"net/http"
"strings"
"testing"
"gitea.weiker.me/rodin/review-bot/vcs"
)
// --- PostReview tests ---
func TestPostReview_HappyPath(t *testing.T) {
c := newTestClient(t, func(w http.ResponseWriter, r *http.Request) {
if r.Method != "POST" {
t.Fatalf("expected POST, got %s", r.Method)
}
if r.URL.Path != "/repos/owner/repo/pulls/5/reviews" {
t.Fatalf("unexpected path: %s", r.URL.Path)
}
if r.Header.Get("Content-Type") != "application/json" {
t.Errorf("expected Content-Type application/json, got %q", r.Header.Get("Content-Type"))
}
// Verify request body
body, _ := io.ReadAll(r.Body)
var req postReviewRequest
if err := json.Unmarshal(body, &req); err != nil {
t.Fatalf("unmarshal request: %v", err)
}
if req.Event != "APPROVE" {
t.Errorf("expected event APPROVE, got %q", req.Event)
}
if req.Body != "LGTM" {
t.Errorf("expected body 'LGTM', got %q", req.Body)
}
if req.CommitID != "abc123" {
t.Errorf("expected commit_id 'abc123', got %q", req.CommitID)
}
if len(req.Comments) != 1 {
t.Fatalf("expected 1 comment, got %d", len(req.Comments))
}
if req.Comments[0].Path != "main.go" {
t.Errorf("expected comment path 'main.go', got %q", req.Comments[0].Path)
}
if req.Comments[0].Position != 4 {
t.Errorf("expected comment position 4, got %d", req.Comments[0].Position)
}
json.NewEncoder(w).Encode(map[string]interface{}{
"id": 100,
"body": "LGTM",
"state": "APPROVED",
"commit_id": "abc123",
"user": map[string]string{"login": "reviewer"},
})
})
review, err := c.PostReview(context.Background(), "owner", "repo", 5, vcs.ReviewRequest{
Body: "LGTM",
Event: vcs.ReviewEventApprove,
Comments: []vcs.ReviewComment{
{Path: "main.go", Position: 4, CommitID: "abc123", Body: "nit: rename"},
},
})
if err != nil {
t.Fatalf("unexpected error: %v", err)
}
if review.ID != 100 {
t.Errorf("expected ID 100, got %d", review.ID)
}
if review.Body != "LGTM" {
t.Errorf("expected body 'LGTM', got %q", review.Body)
}
if review.State != "APPROVED" {
t.Errorf("expected state 'APPROVED', got %q", review.State)
}
if review.User.Login != "reviewer" {
t.Errorf("expected user 'reviewer', got %q", review.User.Login)
}
if review.CommitID != "abc123" {
t.Errorf("expected commit_id 'abc123', got %q", review.CommitID)
}
}
func TestPostReview_401(t *testing.T) {
c := newTestClient(t, func(w http.ResponseWriter, r *http.Request) {
w.WriteHeader(401)
w.Write([]byte(`{"message":"Bad credentials"}`))
})
_, err := c.PostReview(context.Background(), "owner", "repo", 5, vcs.ReviewRequest{
Body: "LGTM",
Event: vcs.ReviewEventApprove,
})
if err == nil {
t.Fatal("expected error for 401")
}
if !IsUnauthorized(err) {
t.Errorf("expected IsUnauthorized=true, got error: %v", err)
}
}
func TestPostReview_422(t *testing.T) {
c := newTestClient(t, func(w http.ResponseWriter, r *http.Request) {
w.WriteHeader(422)
w.Write([]byte(`{"message":"Unprocessable Entity"}`))
})
_, err := c.PostReview(context.Background(), "owner", "repo", 5, vcs.ReviewRequest{
Body: "LGTM",
Event: vcs.ReviewEventApprove,
})
if err == nil {
t.Fatal("expected error for 422")
}
// 422 should surface as a wrapped APIError
var apiErr *APIError
if !errors.As(err, &apiErr) {
t.Fatalf("expected *APIError, got %T: %v", err, err)
}
if apiErr.StatusCode != 422 {
t.Errorf("expected status 422, got %d", apiErr.StatusCode)
}
}
func TestPostReview_MalformedResponse(t *testing.T) {
c := newTestClient(t, func(w http.ResponseWriter, r *http.Request) {
w.Write([]byte(`not json`))
})
_, err := c.PostReview(context.Background(), "owner", "repo", 5, vcs.ReviewRequest{
Body: "LGTM",
Event: vcs.ReviewEventApprove,
})
if err == nil {
t.Fatal("expected error for malformed response")
}
if !strings.Contains(err.Error(), "parse review response") {
t.Errorf("expected parse error, got: %v", err)
}
}
// --- ListReviews tests ---
func TestListReviews_HappyPath(t *testing.T) {
c := newTestClient(t, func(w http.ResponseWriter, r *http.Request) {
if r.Method != "GET" {
t.Fatalf("expected GET, got %s", r.Method)
}
if r.URL.Path != "/repos/owner/repo/pulls/3/reviews" {
t.Fatalf("unexpected path: %s", r.URL.Path)
}
json.NewEncoder(w).Encode([]map[string]interface{}{
{
"id": 1,
"body": "Approved",
"state": "APPROVED",
"commit_id": "sha1",
"user": map[string]string{"login": "user1"},
},
{
"id": 2,
"body": "Needs work",
"state": "CHANGES_REQUESTED",
"commit_id": "sha2",
"user": map[string]string{"login": "user2"},
},
{
"id": 3,
"body": "Comment only",
"state": "COMMENTED",
"commit_id": "sha3",
"user": map[string]string{"login": "user3"},
},
{
"id": 4,
"body": "Old review",
"state": "DISMISSED",
"commit_id": "sha4",
"user": map[string]string{"login": "user4"},
},
})
})
reviews, err := c.ListReviews(context.Background(), "owner", "repo", 3)
if err != nil {
t.Fatalf("unexpected error: %v", err)
}
if len(reviews) != 4 {
t.Fatalf("expected 4 reviews, got %d", len(reviews))
}
// Check state translation
expected := []struct {
id int64
state string
}{
{1, "APPROVED"},
{2, "REQUEST_CHANGES"},
{3, "COMMENT"},
{4, "DISMISSED"},
}
for i, e := range expected {
if reviews[i].ID != e.id {
t.Errorf("review[%d]: expected ID %d, got %d", i, e.id, reviews[i].ID)
}
if reviews[i].State != e.state {
t.Errorf("review[%d]: expected state %q, got %q", i, e.state, reviews[i].State)
}
}
}
func TestListReviews_404(t *testing.T) {
c := newTestClient(t, func(w http.ResponseWriter, r *http.Request) {
w.WriteHeader(404)
w.Write([]byte(`{"message":"Not Found"}`))
})
_, err := c.ListReviews(context.Background(), "owner", "repo", 999)
if err == nil {
t.Fatal("expected error for 404")
}
if !IsNotFound(err) {
t.Errorf("expected IsNotFound=true, got error: %v", err)
}
}
func TestListReviews_401(t *testing.T) {
c := newTestClient(t, func(w http.ResponseWriter, r *http.Request) {
w.WriteHeader(401)
w.Write([]byte(`{"message":"Bad credentials"}`))
})
_, err := c.ListReviews(context.Background(), "owner", "repo", 3)
if err == nil {
t.Fatal("expected error for 401")
}
if !IsUnauthorized(err) {
t.Errorf("expected IsUnauthorized=true, got error: %v", err)
}
}
// --- DeleteReview tests ---
func TestDeleteReview_HappyPath(t *testing.T) {
c := newTestClient(t, func(w http.ResponseWriter, r *http.Request) {
if r.Method != "DELETE" {
t.Fatalf("expected DELETE, got %s", r.Method)
}
if r.URL.Path != "/repos/owner/repo/pulls/5/reviews/42" {
t.Fatalf("unexpected path: %s", r.URL.Path)
}
w.WriteHeader(204)
})
err := c.DeleteReview(context.Background(), "owner", "repo", 5, 42)
if err != nil {
t.Fatalf("unexpected error: %v", err)
}
}
func TestDeleteReview_422_SubmittedReview(t *testing.T) {
c := newTestClient(t, func(w http.ResponseWriter, r *http.Request) {
w.WriteHeader(422)
w.Write([]byte(`{"message":"Can not delete a non pending review"}`))
})
err := c.DeleteReview(context.Background(), "owner", "repo", 5, 42)
if err == nil {
t.Fatal("expected error for 422")
}
if !errors.Is(err, ErrCannotDeleteSubmittedReview) {
t.Errorf("expected ErrCannotDeleteSubmittedReview, got: %v", err)
}
}
// --- DismissReview tests ---
func TestDismissReview_HappyPath(t *testing.T) {
c := newTestClient(t, func(w http.ResponseWriter, r *http.Request) {
if r.Method != "PUT" {
t.Fatalf("expected PUT, got %s", r.Method)
}
if r.URL.Path != "/repos/owner/repo/pulls/5/reviews/10/dismissals" {
t.Fatalf("unexpected path: %s", r.URL.Path)
}
body, _ := io.ReadAll(r.Body)
var req dismissReviewRequest
if err := json.Unmarshal(body, &req); err != nil {
t.Fatalf("unmarshal request: %v", err)
}
if req.Message != "Superseded by new review" {
t.Errorf("expected message 'Superseded by new review', got %q", req.Message)
}
if req.Event != "DISMISS" {
t.Errorf("expected event 'DISMISS', got %q", req.Event)
}
json.NewEncoder(w).Encode(map[string]interface{}{
"id": 10,
"state": "DISMISSED",
})
})
err := c.DismissReview(context.Background(), "owner", "repo", 5, 10, "Superseded by new review")
if err != nil {
t.Fatalf("unexpected error: %v", err)
}
}
func TestDismissReview_404(t *testing.T) {
c := newTestClient(t, func(w http.ResponseWriter, r *http.Request) {
w.WriteHeader(404)
w.Write([]byte(`{"message":"Not Found"}`))
})
err := c.DismissReview(context.Background(), "owner", "repo", 5, 999, "dismiss")
if err == nil {
t.Fatal("expected error for 404")
}
if !IsNotFound(err) {
t.Errorf("expected IsNotFound=true, got error: %v", err)
}
}
func TestDismissReview_401(t *testing.T) {
c := newTestClient(t, func(w http.ResponseWriter, r *http.Request) {
w.WriteHeader(401)
w.Write([]byte(`{"message":"Bad credentials"}`))
})
err := c.DismissReview(context.Background(), "owner", "repo", 5, 10, "dismiss")
if err == nil {
t.Fatal("expected error for 401")
}
if !IsUnauthorized(err) {
t.Errorf("expected IsUnauthorized=true, got error: %v", err)
}
}
// --- State translation tests ---
func TestTranslateGitHubReviewState(t *testing.T) {
tests := []struct {
name string
input string
want string
}{
{"approved passes through", "APPROVED", "APPROVED"},
{"changes_requested maps to REQUEST_CHANGES", "CHANGES_REQUESTED", "REQUEST_CHANGES"},
{"commented maps to COMMENT", "COMMENTED", "COMMENT"},
{"dismissed passes through", "DISMISSED", "DISMISSED"},
{"unknown state passes through", "UNKNOWN_STATE", "UNKNOWN_STATE"},
{"empty string passes through", "", ""},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
got := translateGitHubReviewState(tt.input)
if got != tt.want {
t.Errorf("translateGitHubReviewState(%q) = %q, want %q", tt.input, got, tt.want)
}
})
}
}
func TestPostReview_ConflictingCommitIDs(t *testing.T) {
c := newTestClient(t, func(w http.ResponseWriter, r *http.Request) {
t.Fatal("request should not be sent when commit IDs conflict")
})
_, err := c.PostReview(context.Background(), "owner", "repo", 5, vcs.ReviewRequest{
Body: "Review",
Event: vcs.ReviewEventComment,
Comments: []vcs.ReviewComment{
{Path: "a.go", Position: 1, CommitID: "sha-1", Body: "first"},
{Path: "b.go", Position: 2, CommitID: "sha-2", Body: "second"},
},
})
if err == nil {
t.Fatal("expected error for conflicting commit IDs")
}
if !errors.Is(err, ErrConflictingCommitIDs) {
t.Errorf("expected ErrConflictingCommitIDs, got: %v", err)
}
}
+1 -1
View File
@@ -2,4 +2,4 @@ module gitea.weiker.me/rodin/review-bot
go 1.26.2 go 1.26.2
require github.com/goccy/go-yaml v1.19.2 require gopkg.in/yaml.v3 v3.0.1
+4 -2
View File
@@ -1,2 +1,4 @@
github.com/goccy/go-yaml v1.19.2 h1:PmFC1S6h8ljIz6gMRBopkjP1TVT7xuwrButHID66PoM= gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405 h1:yhCVgyC4o1eVCa2tZl7eS0r+SDo693bJlVdllGtEeKM=
github.com/goccy/go-yaml v1.19.2/go.mod h1:XBurs7gK8ATbW4ZPGKgcbrY1Br56PdM69F7LkFRi1kA= gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
gopkg.in/yaml.v3 v3.0.1 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA=
gopkg.in/yaml.v3 v3.0.1/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
+12
View File
@@ -10,6 +10,18 @@ func FormatMarkdown(result *ReviewResult, reviewerName string) string {
return FormatMarkdownWithDisplay(result, reviewerName, reviewerName) 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. // FormatMarkdownWithDisplay formats a ReviewResult with separate display name and sentinel name.
// Note: displayName is not HTML-escaped as Gitea sanitizes rendered Markdown. // Note: displayName is not HTML-escaped as Gitea sanitizes rendered Markdown.
// Persona display names are controlled by repo owners (trusted input). // Persona display names are controlled by repo owners (trusted input).
+19
View File
@@ -98,6 +98,25 @@ 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) { func TestFormatMarkdown_Sentinel(t *testing.T) {
result := &ReviewResult{ result := &ReviewResult{
Verdict: "APPROVE", Verdict: "APPROVE",
+37 -145
View File
@@ -5,15 +5,12 @@ import (
"embed" "embed"
"encoding/json" "encoding/json"
"fmt" "fmt"
"io"
"os" "os"
"sort" "sort"
"strings" "strings"
"unicode/utf8" "unicode/utf8"
"github.com/goccy/go-yaml" "gopkg.in/yaml.v3"
"github.com/goccy/go-yaml/ast"
"github.com/goccy/go-yaml/parser"
) )
//go:embed personas/*.yaml //go:embed personas/*.yaml
@@ -121,8 +118,10 @@ 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 {
names = append(names, name) names = append(names, name)
@@ -143,19 +142,10 @@ 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 Strict() - both reject unknown fields to catch typos. // YAML's KnownFields(true) - 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)
@@ -166,176 +156,78 @@ func parsePersona(data []byte, source string) (*Persona, error) {
return &p, nil return &p, nil
} }
// unmarshalYAMLWithDepthLimit unmarshals YAML data with three safety checks: // unmarshalYAMLWithDepthLimit unmarshals YAML data with explicit depth limiting
// - Depth limiting: rejects AST trees exceeding maxDepth to prevent stack exhaustion. // and strict field checking. This protects against stack exhaustion from deeply
// - Multi-document rejection: prevents silent data loss from ignored extra documents. // nested structures and catches typos in field names.
// - Strict field checking: rejects unknown YAML keys to catch typos early. // Multi-document YAML files are rejected to prevent silent data loss.
func unmarshalYAMLWithDepthLimit(data []byte, out any, maxDepth int) error { func unmarshalYAMLWithDepthLimit(data []byte, out any, maxDepth int) error {
// First pass: parse into AST to check depth limits, node counts, and // First pass: decode into a yaml.Node to check depth limits and node counts.
// multi-document rejection. This prevents stack exhaustion before we // This prevents stack exhaustion before we attempt to decode into structs.
// attempt to decode into structs. var node yaml.Node
file, err := parser.ParseBytes(data, 0) dec := yaml.NewDecoder(bytes.NewReader(data))
if err != nil { if err := dec.Decode(&node); 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.
if len(file.Docs) > 1 { var extra yaml.Node
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(file.Docs[0].Body, 0, maxDepth, MaxYAMLNodes, make(map[ast.Node]int), make(map[ast.Node]bool), &nodeCount); err != nil { if err := checkYAMLDepth(&node, 0, maxDepth, MaxYAMLNodes, make(map[*yaml.Node]struct{}), &nodeCount); err != nil {
return err return err
} }
// Second pass: decode with strict field checking enabled. // Second pass: decode with strict field checking enabled.
// Strict() rejects unknown keys, catching typos like "focuss" or "identiy". // KnownFields(true) rejects unknown keys, catching typos like "focuss" or "identiy".
// // We must re-decode from the original data because yaml.Node.Decode() doesn't
// Safety note: goccy/go-yaml's decoder does not expand YAML aliases // support the KnownFields option.
// recursively — it resolves them via the pre-built AST, which our first strictDec := yaml.NewDecoder(bytes.NewReader(data))
// pass already depth-checked. Alias chains that would exceed depth limits strictDec.KnownFields(true)
// are caught above; the decoder merely reads the resolved scalar values. return strictDec.Decode(out)
dec := yaml.NewDecoder(bytes.NewReader(data), yaml.Strict())
return dec.Decode(out)
} }
// checkYAMLDepth recursively checks that YAML AST nodes don't exceed the depth // checkYAMLDepth recursively checks that YAML nodes don't exceed the depth limit
// limit or the total node count limit. It uses two tracking maps: // or the total node count limit. It also detects alias cycles to prevent infinite
// - validated: maps each node to the maximum depth at which it was previously // recursion from crafted YAML with self-referential aliases.
// checked. If a node is revisited at a deeper depth (e.g., via an alias), func checkYAMLDepth(node *yaml.Node, depth, maxDepth, maxNodes int, seen map[*yaml.Node]struct{}, nodeCount *int) error {
// 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)
} }
// Depth-aware short-circuit: skip re-validation only when the current visit // Cycle detection: if we've seen this node before, we're in a cycle.
// depth is the same or shallower than the depth at which this node was if _, ok := seen[node]; ok {
// previously validated. A shallower (or equal) current depth means the return nil // Already validated this subtree, skip to avoid infinite recursion.
// 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
} }
validated[node] = depth seen[node] = struct{}{}
// Mark as visiting (on the current recursion path) for cycle detection. // Handle alias nodes: follow the alias to its anchor target.
visiting[node] = true // Increment depth when following aliases since they expand the effective structure.
defer func() { visiting[node] = false }() if node.Kind == yaml.AliasNode && node.Alias != nil {
return checkYAMLDepth(node.Alias, depth+1, maxDepth, maxNodes, seen, nodeCount)
}
// Walk children based on node type. for _, child := range node.Content {
switch n := node.(type) { if err := checkYAMLDepth(child, depth+1, maxDepth, maxNodes, seen, nodeCount); err != nil {
case *ast.MappingNode:
for _, value := range n.Values {
if err := checkYAMLDepth(value, depth+1, maxDepth, maxNodes, validated, visiting, nodeCount); err != nil {
return err 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 return nil
} }
// 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)
} }
+41 -222
View File
@@ -7,7 +7,7 @@ import (
"strings" "strings"
"testing" "testing"
"github.com/goccy/go-yaml/ast" "gopkg.in/yaml.v3"
) )
func TestLoadBuiltinPersona(t *testing.T) { func TestLoadBuiltinPersona(t *testing.T) {
@@ -459,14 +459,7 @@ 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).
// Depth accumulation trace for "nested: \n level0: \n level1: ...": // Each level adds 2 to the depth count (key + value mapping).
// - 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 := " "
@@ -490,35 +483,6 @@ 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")
@@ -540,41 +504,41 @@ 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 visiting map to prevent infinite recursion. // by using the seen map to prevent infinite recursion.
// We test this directly because go-yaml's parser handles most cycles
// at parse time, but we need to ensure our checker is robust.
// Create a node structure where an alias points to a parent node, // Create a node structure where an alias points to a parent node,
// simulating what could happen with crafted input. // simulating what could happen with malicious input that bypasses
parent := &ast.MappingNode{ // go-yaml's cycle detection.
Values: []*ast.MappingValueNode{ parent := &yaml.Node{
{ Kind: yaml.MappingNode,
Key: &ast.StringNode{Value: "name"}, Content: []*yaml.Node{
Value: &ast.StringNode{Value: "test"}, {Kind: yaml.ScalarNode, Value: "name"},
}, {Kind: yaml.ScalarNode, Value: "test"},
{Kind: yaml.ScalarNode, Value: "nested"},
}, },
} }
// Create a child that aliases back to the parent (artificial cycle) // Create a child that aliases back to the parent (artificial cycle)
aliasToParent := &ast.AliasNode{ aliasToParent := &yaml.Node{
Value: parent, Kind: yaml.AliasNode,
Alias: parent,
} }
parent.Values = append(parent.Values, &ast.MappingValueNode{ parent.Content = append(parent.Content, aliasToParent)
Key: &ast.StringNode{Value: "nested"},
Value: aliasToParent,
})
nodeCount := 0 nodeCount := 0
validated := make(map[ast.Node]int) seen := make(map[*yaml.Node]struct{})
visiting := make(map[ast.Node]bool)
// This should NOT hang or stack overflow - cycle detection prevents infinite recursion // This should NOT hang or stack overflow - the seen map prevents infinite recursion
err := checkYAMLDepth(parent, 0, MaxYAMLDepth, MaxYAMLNodes, validated, visiting, &nodeCount) err := checkYAMLDepth(parent, 0, MaxYAMLDepth, MaxYAMLNodes, seen, &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 validated map // Verify we tracked the parent in the seen map
if _, ok := validated[parent]; !ok { if _, ok := seen[parent]; !ok {
t.Error("parent node not tracked in validated map") t.Error("parent node not tracked in seen map")
} }
} }
@@ -630,82 +594,36 @@ 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.
node := &ast.MappingNode{ // This tests the seen map logic independent of go-yaml's parsing.
Values: []*ast.MappingValueNode{ node := &yaml.Node{
{ Kind: yaml.MappingNode,
Key: &ast.StringNode{Value: "key"}, Content: []*yaml.Node{
Value: &ast.StringNode{Value: "value"}, {Kind: yaml.ScalarNode, Value: "key"},
}, {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 := &ast.AliasNode{ cycleChild := &yaml.Node{
Value: node, // Points back to the parent Kind: yaml.AliasNode,
Alias: node, // Points back to the parent
} }
node.Values = append(node.Values, &ast.MappingValueNode{ node.Content = append(node.Content,
Key: &ast.StringNode{Value: "cyclic"}, &yaml.Node{Kind: yaml.ScalarNode, Value: "cyclic"},
Value: cycleChild, cycleChild,
}) )
nodeCount := 0 nodeCount := 0
validated := make(map[ast.Node]int) seen := make(map[*yaml.Node]struct{})
visiting := make(map[ast.Node]bool) err := checkYAMLDepth(node, 0, MaxYAMLDepth, MaxYAMLNodes, seen, &nodeCount)
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 validated map should contain multiple entries // The seen map should contain multiple entries
if len(validated) < 2 { if len(seen) < 2 {
t.Errorf("validated map has %d entries, expected at least 2", len(validated)) t.Errorf("seen map has %d entries, expected at least 2", len(seen))
}
}
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())
} }
} }
@@ -858,102 +776,3 @@ 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())
}
}
-8
View File
@@ -41,11 +41,3 @@ type Client interface {
Reviewer Reviewer
Identity 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
}