Compare commits

..

1 Commits

Author SHA1 Message Date
Rodin c1c8e61e9d feat: load personas from target repo .review-bot/personas/
CI / test (pull_request) Successful in 9m30s
CI / review (anthropic--claude-4.6-sonnet, sonnet, SONNET_REVIEW_TOKEN) (pull_request) Successful in 9m50s
CI / review (gpt-5, gpt, GPT_REVIEW_TOKEN) (pull_request) Successful in 10m19s
CI / review (gpt-5, security, SECURITY_REVIEW.md, SECURITY_REVIEW_TOKEN) (pull_request) Successful in 10m36s
- Add RepoContentFetcher interface for fetching repo files
- Add LoadRepoPersonas() to load custom personas from repo
- Add LoadPersonaWithFallback() to check repo then built-in
- Add ListAllPersonas() to merge repo + built-in persona names
- Repo personas take precedence over built-ins with same name

Closes #60
2026-05-10 19:01:54 -07:00
17 changed files with 397 additions and 2132 deletions
+2 -4
View File
@@ -38,8 +38,6 @@ jobs:
- name: security
token_secret: SECURITY_REVIEW_TOKEN
model: gpt-5
patterns_repo: rodin/security-patterns
patterns_files: "."
system_prompt_file: SECURITY_REVIEW.md
steps:
- uses: actions/checkout@v4
@@ -62,8 +60,8 @@ jobs:
AICORE_API_URL: ${{ secrets.AICORE_API_URL }}
AICORE_RESOURCE_GROUP: ${{ secrets.AICORE_RESOURCE_GROUP }}
CONVENTIONS_FILE: "CONVENTIONS.md"
PATTERNS_REPO: ${{ matrix.patterns_repo || 'rodin/go-patterns' }}
PATTERNS_FILES: ${{ matrix.patterns_files || 'README.md,patterns/' }}
PATTERNS_REPO: "rodin/go-patterns"
PATTERNS_FILES: "README.md,patterns/"
LLM_TIMEOUT: "600"
SYSTEM_PROMPT_FILE: ${{ matrix.system_prompt_file }}
run: ./review-bot
-200
View File
@@ -1,200 +0,0 @@
# This composite action is designed for Gitea Actions runners.
# Gitea Actions supports GitHub Actions syntax including $GITHUB_OUTPUT,
# actions/cache, and actions/checkout.
# Requirements: python3, sha256sum, curl (all present on ubuntu-* runners).
name: 'AI Code Review'
description: 'Run AI-powered code review on a pull request using review-bot'
inputs:
gitea-url:
description: 'Gitea instance URL (defaults to server_url)'
required: false
default: ''
repo:
description: 'Repository (owner/name, defaults to current)'
required: false
default: ''
pr-number:
description: 'Pull request number (defaults to current PR)'
required: false
default: ''
reviewer-token:
description: 'Gitea token for posting the review'
required: true
reviewer-name:
description: 'Display name for the reviewer'
required: false
default: ''
llm-base-url:
description: 'OpenAI-compatible LLM API base URL (not required for aicore provider)'
required: false
default: ''
llm-api-key:
description: 'LLM API key (not required for aicore provider)'
required: false
default: ''
llm-model:
description: 'LLM model name'
required: true
llm-provider:
description: 'LLM API provider: openai, anthropic, or aicore (default openai)'
required: false
default: 'openai'
aicore-client-id:
description: 'SAP AI Core client ID (required for aicore provider)'
required: false
default: ''
aicore-client-secret:
description: 'SAP AI Core client secret (required for aicore provider)'
required: false
default: ''
aicore-auth-url:
description: 'SAP AI Core authentication URL (required for aicore provider)'
required: false
default: ''
aicore-api-url:
description: 'SAP AI Core API URL (required for aicore provider)'
required: false
default: ''
aicore-resource-group:
description: 'SAP AI Core resource group (default: default)'
required: false
default: 'default'
conventions-file:
description: 'Path to conventions file in the repo (e.g. CLAUDE.md)'
required: false
default: ''
patterns-repo:
description: 'Comma-separated repos with language patterns (e.g. rodin/elixir-patterns,rodin/phoenix-conventions)'
required: false
default: ''
patterns-files:
description: 'Comma-separated file paths or directories to fetch from patterns repos'
required: false
default: 'README.md'
temperature:
description: 'LLM temperature (0 = server default)'
required: false
default: '0'
timeout:
description: 'LLM request timeout in seconds (default 300)'
required: false
default: '300'
version:
description: 'review-bot version to install (e.g. v0.1.0, defaults to latest)'
required: false
default: 'latest'
dry-run:
description: 'Print review to stdout instead of posting'
required: false
default: 'false'
update-existing:
description: 'Delete previous review from same bot after posting new one. Accepts: true/1/yes or false/0/no (default true)'
required: false
default: 'true'
system-prompt-file:
description: 'Local file with additional system prompt instructions (e.g. security review focus)'
required: false
default: ''
persona:
description: 'Built-in persona name (security, architect, docs)'
required: false
default: ''
persona-file:
description: 'Path to custom persona JSON file'
required: false
default: ''
runs:
using: 'composite'
steps:
- name: Determine version
id: version
shell: bash
run: |
GITEA_URL="${{ inputs.gitea-url || github.server_url }}"
REPO="${{ inputs.repo || 'rodin/review-bot' }}"
if [ "${{ inputs.version }}" = "latest" ]; then
VERSION=$(curl -sSf "${GITEA_URL}/api/v1/repos/${REPO}/releases?limit=1" \
| python3 -c "import sys, json; releases = json.load(sys.stdin); print(releases[0]['tag_name'] if releases else '')")
if [ -z "$VERSION" ]; then
echo "Failed to determine latest version" >&2
exit 1
fi
else
VERSION="${{ inputs.version }}"
fi
echo "version=${VERSION}" >> "$GITHUB_OUTPUT"
- name: Cache review-bot binary
id: cache
uses: actions/cache@v4
with:
path: ${{ runner.temp }}/review-bot
key: review-bot-linux-amd64-${{ steps.version.outputs.version }}
- name: Install review-bot
if: steps.cache.outputs.cache-hit != 'true'
shell: bash
run: |
GITEA_URL="${{ inputs.gitea-url || github.server_url }}"
REPO="${{ inputs.repo || 'rodin/review-bot' }}"
VERSION="${{ steps.version.outputs.version }}"
BINARY="review-bot-linux-amd64"
curl -sSfL "${GITEA_URL}/${REPO}/releases/download/${VERSION}/${BINARY}" \
-o "${{ runner.temp }}/review-bot"
curl -sSfL "${GITEA_URL}/${REPO}/releases/download/${VERSION}/checksums.txt" \
-o "${{ runner.temp }}/checksums.txt"
# Verify SHA-256 checksum
cd "${{ runner.temp }}"
EXPECTED=$(grep "${BINARY}" checksums.txt | awk '{print $1}')
ACTUAL=$(sha256sum review-bot | awk '{print $1}')
if [ -z "$EXPECTED" ]; then
echo "Error: no checksum found for ${BINARY}" >&2
exit 1
fi
if [ "$EXPECTED" != "$ACTUAL" ]; then
echo "Error: checksum mismatch!" >&2
echo " Expected: $EXPECTED" >&2
echo " Actual: $ACTUAL" >&2
exit 1
fi
chmod +x "${{ runner.temp }}/review-bot"
echo "Installed review-bot ${VERSION} (checksum verified)"
- name: Run review
shell: bash
env:
GITHUB_SERVER_URL: ${{ inputs.gitea-url || github.server_url }}
GITHUB_REPOSITORY: ${{ inputs.repo || github.repository }}
PR_NUMBER: ${{ inputs.pr-number || github.event.pull_request.number }}
REVIEWER_TOKEN: ${{ inputs.reviewer-token }}
REVIEWER_NAME: ${{ inputs.reviewer-name }}
LLM_BASE_URL: ${{ inputs.llm-base-url }}
LLM_API_KEY: ${{ inputs.llm-api-key }}
LLM_MODEL: ${{ inputs.llm-model }}
CONVENTIONS_FILE: ${{ inputs.conventions-file }}
PATTERNS_REPO: ${{ inputs.patterns-repo }}
PATTERNS_FILES: ${{ inputs.patterns-files }}
LLM_TEMPERATURE: ${{ inputs.temperature }}
LLM_TIMEOUT: ${{ inputs.timeout }}
LLM_PROVIDER: ${{ inputs.llm-provider }}
UPDATE_EXISTING: ${{ inputs.update-existing }}
SYSTEM_PROMPT_FILE: ${{ inputs.system-prompt-file }}
PERSONA: ${{ inputs.persona }}
PERSONA_FILE: ${{ inputs.persona-file }}
AICORE_CLIENT_ID: ${{ inputs.aicore-client-id }}
AICORE_CLIENT_SECRET: ${{ inputs.aicore-client-secret }}
AICORE_AUTH_URL: ${{ inputs.aicore-auth-url }}
AICORE_API_URL: ${{ inputs.aicore-api-url }}
AICORE_RESOURCE_GROUP: ${{ inputs.aicore-resource-group }}
run: |
ARGS=""
if [ "${{ inputs.dry-run }}" = "true" ]; then
ARGS="--dry-run"
fi
${{ runner.temp }}/review-bot $ARGS
-69
View File
@@ -1,69 +0,0 @@
name: CI
on:
push:
branches: [main]
pull_request:
types: [opened, synchronize]
jobs:
test:
runs-on: ubuntu-24.04
steps:
- uses: actions/checkout@v4
- uses: actions/setup-go@v5
with:
go-version: '1.26'
- run: go test ./...
- run: go vet ./...
- run: go build -o review-bot ./cmd/review-bot
# Self-review using native SAP AI Core provider
# Models must match SAP AI Core deployments
# Available models: gpt-5, anthropic--claude-4.6-sonnet, anthropic--claude-4.6-opus
# Removed gpt-4.1, gpt-5-mini, gpt-4.1-mini - not deployed on AI Core
review:
runs-on: ubuntu-24.04
if: github.event_name == 'pull_request'
needs: test
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
- name: security
token_secret: SECURITY_REVIEW_TOKEN
model: gpt-5
patterns_repo: rodin/security-patterns
patterns_files: "."
system_prompt_file: SECURITY_REVIEW.md
steps:
- uses: actions/checkout@v4
- uses: actions/setup-go@v5
with:
go-version: '1.26'
- run: go build -o review-bot ./cmd/review-bot
- name: Run ${{ matrix.name }} review
env:
GITHUB_SERVER_URL: ${{ github.server_url }}
GITHUB_REPOSITORY: ${{ github.repository }}
PR_NUMBER: ${{ github.event.pull_request.number }}
REVIEWER_TOKEN: ${{ secrets[matrix.token_secret] }}
REVIEWER_NAME: ${{ matrix.name }}
LLM_PROVIDER: aicore
LLM_MODEL: ${{ matrix.model }}
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: ${{ matrix.patterns_repo || 'rodin/go-patterns' }}
PATTERNS_FILES: ${{ matrix.patterns_files || 'README.md,patterns/' }}
LLM_TIMEOUT: "600"
SYSTEM_PROMPT_FILE: ${{ matrix.system_prompt_file }}
run: ./review-bot
-38
View File
@@ -1,38 +0,0 @@
name: PR Ready Gate
on:
pull_request:
types: [synchronize]
jobs:
clear-labels:
runs-on: ubuntu-24.04
# Always run - curl commands are safe if labels don't exist
steps:
- name: Remove ready and self-reviewed labels, reassign to author
env:
GITEA_TOKEN: ${{ secrets.RODIN_TOKEN }}
run: |
PR_NUMBER=${{ github.event.pull_request.number }}
AUTHOR=${{ github.event.pull_request.user.login }}
READY_LABEL_ID=38
SELF_REVIEWED_LABEL_ID=37
# Remove ready label if present
curl -sS -X DELETE \
-H "Authorization: token $GITEA_TOKEN" \
"https://gitea.weiker.me/api/v1/repos/${{ github.repository }}/issues/${PR_NUMBER}/labels/${READY_LABEL_ID}" || true
# Remove self-reviewed label if present
curl -sS -X DELETE \
-H "Authorization: token $GITEA_TOKEN" \
"https://gitea.weiker.me/api/v1/repos/${{ github.repository }}/issues/${PR_NUMBER}/labels/${SELF_REVIEWED_LABEL_ID}" || true
# Reassign to author
curl -sS -X PATCH \
-H "Authorization: token $GITEA_TOKEN" \
-H "Content-Type: application/json" \
-d "{\"assignees\": [\"${AUTHOR}\"]}" \
"https://gitea.weiker.me/api/v1/repos/${{ github.repository }}/pulls/${PR_NUMBER}"
echo "Cleared ready/self-reviewed labels and reassigned PR #${PR_NUMBER} to ${AUTHOR}"
-97
View File
@@ -1,97 +0,0 @@
name: Release
on:
push:
tags:
- 'v*'
jobs:
release:
runs-on: ubuntu-24.04
steps:
- uses: actions/checkout@v4
- uses: actions/setup-go@v5
with:
go-version: '1.26'
- name: Run tests
run: |
go vet ./...
go test ./...
- name: Build binaries
run: |
VERSION=${GITHUB_REF_NAME}
mkdir -p dist
GOOS=linux GOARCH=amd64 go build -ldflags "-s -w -X main.version=${VERSION}" -o dist/review-bot-linux-amd64 ./cmd/review-bot
GOOS=linux GOARCH=arm64 go build -ldflags "-s -w -X main.version=${VERSION}" -o dist/review-bot-linux-arm64 ./cmd/review-bot
GOOS=darwin GOARCH=amd64 go build -ldflags "-s -w -X main.version=${VERSION}" -o dist/review-bot-darwin-amd64 ./cmd/review-bot
GOOS=darwin GOARCH=arm64 go build -ldflags "-s -w -X main.version=${VERSION}" -o dist/review-bot-darwin-arm64 ./cmd/review-bot
cd dist && sha256sum * > checksums.txt
- name: Create release and upload assets
env:
GITEA_TOKEN: ${{ secrets.RELEASE_TOKEN }}
run: |
VERSION=${GITHUB_REF_NAME}
GITEA_URL="${{ github.server_url }}"
REPO="${{ github.repository }}"
# Create release (or find existing one for this tag)
HTTP_CODE=$(curl -s -o /tmp/release_response.json -w "%{http_code}" -X POST \
-H "Authorization: token ${GITEA_TOKEN}" \
-H "Content-Type: application/json" \
"${GITEA_URL}/api/v1/repos/${REPO}/releases" \
-d "{\"tag_name\": \"${VERSION}\", \"name\": \"${VERSION}\", \"body\": \"Release ${VERSION}\", \"draft\": false, \"prerelease\": false}")
if [ "$HTTP_CODE" = "409" ]; then
echo "Release for ${VERSION} already exists, fetching existing..."
curl -sSf -o /tmp/release_response.json \
-H "Authorization: token ${GITEA_TOKEN}" \
"${GITEA_URL}/api/v1/repos/${REPO}/releases/tags/${VERSION}"
elif [ "$HTTP_CODE" != "201" ]; then
echo "Failed to create release (HTTP ${HTTP_CODE})" >&2
cat /tmp/release_response.json >&2
exit 1
fi
# Parse release ID (python3 available on ubuntu-24.04 runners)
RELEASE_ID=$(python3 -c "import json; print(json.load(open('/tmp/release_response.json'))['id'])")
if [ -z "$RELEASE_ID" ]; then
echo "Failed to parse release ID" >&2
cat /tmp/release_response.json >&2
exit 1
fi
echo "Release ID: ${RELEASE_ID}"
# Upload each asset (idempotent: delete existing asset with same name first)
for file in dist/*; do
filename=$(basename "$file")
echo "Uploading ${filename}..."
# Check if asset already exists and delete it
EXISTING_ID=$(export ASSET_NAME="${filename}"; curl -sS \
-H "Authorization: token ${GITEA_TOKEN}" \
"${GITEA_URL}/api/v1/repos/${REPO}/releases/${RELEASE_ID}/assets" \
| python3 -c "import json,sys,os; name=os.environ['ASSET_NAME']; assets=json.load(sys.stdin); print(next((str(a['id']) for a in assets if a['name']==name),''))" 2>/dev/null)
if [ -n "$EXISTING_ID" ]; then
echo " Asset ${filename} already exists (id=${EXISTING_ID}), deleting..."
curl -sSf -X DELETE \
-H "Authorization: token ${GITEA_TOKEN}" \
"${GITEA_URL}/api/v1/repos/${REPO}/releases/${RELEASE_ID}/assets/${EXISTING_ID}"
fi
curl -sSf -X POST \
-H "Authorization: token ${GITEA_TOKEN}" \
-H "Content-Type: application/octet-stream" \
"${GITEA_URL}/api/v1/repos/${REPO}/releases/${RELEASE_ID}/assets?name=$(printf '%s' "${filename}" | jq -sRr @uri)" \
--data-binary "@${file}"
done
echo "Release ${VERSION} created with assets"
+2 -3
View File
@@ -329,12 +329,11 @@ All flags have environment variable equivalents:
### Token Scopes Required
| Scope | Purpose |
|-------|--------|
|-------|---------|
| `write:issue` | Post and delete reviews |
| `write:repository` | Read PR diffs, file content, commit statuses |
| `read:user` | Self-request as reviewer (optional but recommended) |
Without `read:user`, the bot still works but cannot add itself to the PR's reviewer list.
No `read:user` scope needed — the bot identifies itself from the review response.
## Development
+26 -83
View File
@@ -54,8 +54,8 @@ func main() {
logFormat := flag.String("log-format", envOrDefault("LOG_FORMAT", "text"), "Log output format: text or json")
verbosity := flag.String("verbosity", envOrDefault("LOG_VERBOSITY", "info"), "Log verbosity: debug, info, warn, error")
// CLI flags
giteaURL := flag.String("gitea-url", envOrDefault("GITEA_URL", envOrDefault("GITHUB_SERVER_URL", "")), "Gitea instance URL")
repo := flag.String("repo", envOrDefault("GITEA_REPO", envOrDefault("GITHUB_REPOSITORY", "")), "Repository (owner/name)")
giteaURL := flag.String("gitea-url", envOrDefault("GITEA_URL", ""), "Gitea instance URL")
repo := flag.String("repo", envOrDefault("GITEA_REPO", ""), "Repository (owner/name)")
prNum := flag.String("pr", envOrDefault("PR_NUMBER", ""), "Pull request number")
reviewerName := flag.String("reviewer-name", envOrDefault("REVIEWER_NAME", ""), "Reviewer display name")
reviewerToken := flag.String("reviewer-token", envOrDefault("REVIEWER_TOKEN", ""), "Gitea token for posting review")
@@ -79,6 +79,7 @@ func main() {
aicoreAPIURL := flag.String("aicore-api-url", envOrDefault("AICORE_API_URL", ""), "SAP AI Core API URL (for provider=aicore)")
aicoreResourceGroup := flag.String("aicore-resource-group", envOrDefault("AICORE_RESOURCE_GROUP", "default"), "SAP AI Core resource group (for provider=aicore)")
flag.Parse()
flag.Parse()
if *versionFlag {
@@ -115,7 +116,29 @@ func main() {
os.Exit(1)
}
// NOTE: Persona loading deferred until after Gitea client init to support repo personas
// Load persona if specified
var persona *review.Persona
if *personaName != "" {
var err error
persona, err = review.LoadBuiltinPersona(*personaName)
if err != nil {
slog.Error("failed to load persona", "persona", *personaName, "error", err)
os.Exit(1)
}
slog.Info("loaded built-in persona", "persona", persona.Name, "display", persona.DisplayName)
} else if *personaFile != "" {
resolvedPath, err := validateWorkspacePath(*personaFile, "persona-file")
if err != nil {
slog.Error("invalid persona-file path", "error", err)
os.Exit(1)
}
persona, err = review.LoadPersona(resolvedPath)
if err != nil {
slog.Error("failed to load persona file", "file", *personaFile, "error", err)
os.Exit(1)
}
slog.Info("loaded persona from file", "file", *personaFile, "persona", persona.Name)
}
// Validate reviewer-name: only safe characters allowed in sentinel
if err := validateReviewerName(*reviewerName); err != nil {
@@ -173,43 +196,6 @@ func main() {
ctx, cancel := context.WithTimeout(context.Background(), overallTimeout)
defer cancel()
// Load persona if specified (after Gitea client init to support repo personas)
var persona *review.Persona
if *personaName != "" {
// Try loading from repo first, then fall back to built-in
repoPersonas, err := review.LoadRepoPersonas(ctx, newGiteaClientAdapter(giteaClient), owner, repoName)
if err != nil {
slog.Warn("could not load repo personas", "repo", owner+"/"+repoName, "error", err)
// Continue with built-in personas only.
// NOTE: repoPersonas is nil here, but map indexing on a nil map is safe in Go
// (returns the zero value), so the fallback to built-in below works correctly.
}
if p, ok := repoPersonas[*personaName]; ok {
persona = p
slog.Info("loaded repo persona", "persona", persona.Name, "display", persona.DisplayName, "repo", owner+"/"+repoName)
} else {
// Fall back to built-in
persona, err = review.LoadBuiltinPersona(*personaName)
if err != nil {
slog.Error("failed to load persona", "persona", *personaName, "error", err)
os.Exit(1)
}
slog.Info("loaded built-in persona", "persona", persona.Name, "display", persona.DisplayName)
}
} else if *personaFile != "" {
resolvedPath, err := validateWorkspacePath(*personaFile, "persona-file")
if err != nil {
slog.Error("invalid persona-file path", "error", err)
os.Exit(1)
}
persona, err = review.LoadPersona(resolvedPath)
if err != nil {
slog.Error("failed to load persona file", "file", *personaFile, "error", err)
os.Exit(1)
}
slog.Info("loaded persona from file", "file", *personaFile, "persona", persona.Name)
}
slog.Info("reviewing pull request", "pr", prNumber, "repo", fmt.Sprintf("%s/%s", owner, repoName))
// Step 1: Fetch PR metadata
@@ -544,9 +530,6 @@ func fetchPatterns(ctx context.Context, client *gitea.Client, patternsRepo, patt
}
owner, repo := parts[0], parts[1]
var repoLoadedFiles []string
var repoSkippedFiles []string
for _, path := range paths {
path = strings.TrimSpace(path)
if path == "" {
@@ -562,22 +545,11 @@ func fetchPatterns(ctx context.Context, client *gitea.Client, patternsRepo, patt
for filePath, content := range files {
// Only include markdown and text files as patterns
if !isPatternFile(filePath) {
repoSkippedFiles = append(repoSkippedFiles, filePath)
continue
}
repoLoadedFiles = append(repoLoadedFiles, filePath)
sb.WriteString(fmt.Sprintf("### %s/%s\n\n%s\n\n", repoRef, filePath, content))
}
}
if len(repoLoadedFiles) > 0 {
slog.Info("loaded pattern files", "repo", repoRef, "count", len(repoLoadedFiles), "files", repoLoadedFiles)
} else {
slog.Warn("no pattern files loaded", "repo", repoRef, "paths", paths)
}
if len(repoSkippedFiles) > 0 {
slog.Debug("skipped non-pattern files", "repo", repoRef, "count", len(repoSkippedFiles), "files", repoSkippedFiles)
}
}
return sb.String()
}
@@ -811,32 +783,3 @@ func shouldSkipStaleReview(evaluatedSHA, currentSHA string) bool {
}
return evaluatedSHA != currentSHA
}
// giteaClientAdapter adapts gitea.Client to review.GiteaClient interface.
type giteaClientAdapter struct {
client *gitea.Client
}
func newGiteaClientAdapter(c *gitea.Client) *giteaClientAdapter {
return &giteaClientAdapter{client: c}
}
func (a *giteaClientAdapter) ListContents(ctx context.Context, owner, repo, path string) ([]review.ContentEntry, error) {
entries, err := a.client.ListContents(ctx, owner, repo, path)
if err != nil {
return nil, err
}
result := make([]review.ContentEntry, len(entries))
for i, e := range entries {
result[i] = review.ContentEntry{
Name: e.Name,
Path: e.Path,
Type: e.Type,
}
}
return result, nil
}
func (a *giteaClientAdapter) GetFileContent(ctx context.Context, owner, repo, filepath string) (string, error) {
return a.client.GetFileContent(ctx, owner, repo, filepath)
}
-268
View File
@@ -1,268 +0,0 @@
# GitHub Support for review-bot
## Goal
AI code reviews on GitHub PRs using SAP AI Core as the LLM provider.
## Non-Goals
- Auto-detection of platform (explicit `--provider` flag is fine)
- Unifying into one abstraction layer for its own sake
## Constraints
1. **Same features on both platforms** — anything review-bot does on Gitea should work on GitHub
2. **Testable** — small interfaces, dependency injection, no global state
3. **Interface from working code** — extract from gitea/, don't invent in vacuum
---
## Part 1: Feature Inventory
What does review-bot actually do?
### Core Review Flow
| Feature | Description |
|---------|-------------|
| Get PR metadata | Title, body, head SHA, base ref |
| Get PR diff | Unified diff format |
| Get PR files | List of changed files with status |
| Get file content | Raw file at ref |
| List directory | Enumerate files in path |
| Post review | Body + inline comments + verdict |
### Review Management
| Feature | Description |
|---------|-------------|
| List reviews | Get existing reviews on PR |
| Delete review | Remove old review before re-posting |
| Get authenticated user | Who am I? |
### Platform-Specific (not in shared interface)
| Feature | Gitea | GitHub |
|---------|-------|--------|
| Resolve comment | Yes | No equivalent |
| Timeline API | Yes | No equivalent |
These stay on gitea.Client directly. Callers that need them type-assert.
---
## Part 2: GitHub API Mapping
| Feature | Gitea API | GitHub API |
|---------|-----------|------------|
| Get PR | `GET /api/v1/repos/.../pulls/{n}` | `GET /repos/.../pulls/{n}` |
| Get diff | `.diff` suffix | `Accept: application/vnd.github.diff` header |
| Get files | `GET .../pulls/{n}/files` | Same |
| Get file content | `GET .../raw/{path}?ref=` | `GET .../contents/{path}?ref=` + base64 decode |
| List directory | `GET .../contents/{path}` | Same |
| Post review | `POST .../pulls/{n}/reviews` | Same (adapter handles comment schema) |
| List reviews | `GET .../pulls/{n}/reviews` | Same |
| Delete review | `DELETE .../pulls/{n}/reviews/{id}` | Same |
| Get user | `GET /api/v1/user` | `GET /user` |
---
## Part 3: Interface Design
**Principle:** Extract from working gitea/ code. The interface is discovered, not invented.
### Small, role-based interfaces
```go
// vcs/interfaces.go
type PRReader interface {
GetPullRequest(ctx context.Context, owner, repo string, number int) (*PullRequest, error)
GetPullRequestDiff(ctx context.Context, owner, repo string, number int) (string, error)
GetPullRequestFiles(ctx context.Context, owner, repo string, number int) ([]ChangedFile, error)
}
type FileReader interface {
GetFileContent(ctx context.Context, owner, repo, path, ref string) (string, error)
ListContents(ctx context.Context, owner, repo, path string) ([]ContentEntry, error)
}
type Reviewer interface {
PostReview(ctx context.Context, owner, repo string, number int, req ReviewRequest) (*Review, error)
ListReviews(ctx context.Context, owner, repo string, number int) ([]Review, error)
DeleteReview(ctx context.Context, owner, repo string, number int, reviewID int64) error
}
type Identity interface {
GetAuthenticatedUser(ctx context.Context) (string, error)
}
// Client combines all for callers that need everything
type Client interface {
PRReader
FileReader
Reviewer
Identity
}
```
### Types
Use what gitea/ already has. Move to vcs/types.go or re-export.
```go
type PullRequest struct { ... } // from gitea.PullRequest
type ChangedFile struct { ... } // from gitea.ChangedFile
type ContentEntry struct { ... } // from gitea.ContentEntry
type Review struct { ... } // from gitea.Review
type ReviewRequest struct { ... } // new, for PostReview input
type ReviewComment struct { ... } // from gitea.ReviewComment
```
### Adapter responsibilities
Each adapter (gitea, github) handles:
- API URL construction
- Auth header format (`token` vs `Bearer`)
- Request/response mapping
- Comment schema translation (line numbers, commit IDs, etc.)
---
## Part 4: Test Plan
### Unit Tests (mock HTTP)
```
github/
pr_test.go # TestGetPullRequest, TestGetDiff, TestGetFiles
files_test.go # TestGetFileContent, TestListContents
review_test.go # TestPostReview, TestListReviews, TestDeleteReview
identity_test.go # TestGetAuthenticatedUser
```
Per method: happy path, 404, 401, 429, malformed response.
### Integration Tests
Against github.com/aweiker/ai-core-review-bot:
- Fetch real PR
- Fetch real file
- Post + delete review (clean up)
### End-to-End
Open PR on test repo, run full review-bot, verify review appears.
---
## Part 5: Implementation Phases
### Phase 1: Extract interfaces from gitea/
**Work:**
- Create `vcs/interfaces.go` with interfaces extracted from gitea/client.go signatures
- Create `vcs/types.go` — move or alias types from gitea/
- Verify gitea.Client satisfies vcs.Client (compile-time check)
**Exit criteria:** `var _ vcs.Client = (*gitea.Client)(nil)` compiles.
---
### Phase 2: Gitea adapter (if needed)
**Work:**
- If gitea.Client method signatures don't match exactly, create wrapper
- Keep gitea/ working exactly as before
**Exit criteria:** Existing tests pass. No behavior change.
---
### Phase 3: GitHub client — PRReader
**Work:**
- `github/client.go` — struct, constructor, HTTP helpers
- `github/pr.go` — GetPullRequest, GetPullRequestDiff, GetPullRequestFiles
- Unit tests
**Exit criteria:** `go test ./github/...` passes for PR methods.
---
### Phase 4: GitHub client — FileReader
**Work:**
- `github/files.go` — GetFileContent, ListContents
- Unit tests
**Exit criteria:** Unit tests pass.
---
### Phase 5: GitHub client — Reviewer + Identity
**Work:**
- `github/review.go` — PostReview, ListReviews, DeleteReview
- `github/identity.go` — GetAuthenticatedUser
- Unit tests
**Exit criteria:** Unit tests pass.
---
### Phase 6: Integration tests
**Work:**
- `integration/github_test.go`
- Test against real GitHub
**Exit criteria:** All integration tests pass.
---
### Phase 7: Wire into cmd/review-bot
**Work:**
- Add `--provider github|gitea` flag (default: gitea for backward compat)
- Select client based on flag
- Update to use vcs interfaces where it makes sense
**Exit criteria:**
- `./review-bot --provider github ...` works
- `./review-bot --provider gitea ...` works (same as before)
- Existing Gitea workflows unchanged
---
### Phase 8: GitHub Actions workflow + releases
**Work:**
- `.github/workflows/ci.yml` — test on PR
- `.github/workflows/release.yml` — publish binary to GitHub releases
- `.github/actions/review/action.yml` — composite action
- Action downloads binary from github.com/aweiker/ai-core-review-bot releases
**Exit criteria:**
- CI runs on github.com/aweiker/ai-core-review-bot
- Release creates downloadable binary
- Review action posts review successfully
---
## Part 6: Decisions
| Question | Decision |
|----------|----------|
| Auth token | Workflow `GITHUB_TOKEN` (automatic) |
| Binary distribution | GitHub releases on aweiker/ai-core-review-bot |
| Comment schema | Adapter's job — translate ReviewComment to platform format |
| Default provider | `gitea` for backward compatibility |
| Shared types | vcs/types.go (extracted from gitea/) |
| Platform-specific features | Stay on concrete client, not interface |
---
## Summary
8 phases. Start by extracting interfaces from working gitea/ code, not inventing them. GitHub implements the same interfaces. Each phase has clear exit criteria.
+17 -215
View File
@@ -11,11 +11,9 @@ import (
"fmt"
"io"
"log/slog"
"net"
"net/http"
"net/url"
"strings"
"syscall"
"time"
)
@@ -41,26 +39,12 @@ func IsNotFound(err error) bool {
return errors.As(err, &apiErr) && apiErr.StatusCode == http.StatusNotFound
}
// IsServerError reports whether an error is an API 5xx response.
func IsServerError(err error) bool {
var apiErr *APIError
return errors.As(err, &apiErr) && apiErr.StatusCode >= 500 && apiErr.StatusCode < 600
}
// Client interacts with the Gitea API.
// A Client is safe for concurrent use by multiple goroutines.
type Client struct {
baseURL string
token string
http *http.Client
// RetryBackoff defines the delays between retry attempts.
// RetryBackoff[i] is the delay before attempt i+1 (after attempt i fails).
// If nil, defaults to {1s, 2s}. Set to shorter durations in tests.
//
// This field must be configured before the first request is made.
// Modifying it while requests are in flight is not safe.
RetryBackoff []time.Duration
}
// NewClient creates a new Gitea API client.
@@ -72,12 +56,6 @@ func NewClient(baseURL, token string) *Client {
}
}
// SetHTTPClient sets the underlying HTTP client used for requests.
// This is intended for testing to inject mock transports.
func (c *Client) SetHTTPClient(hc *http.Client) {
c.http = hc
}
// PullRequest holds relevant PR metadata.
type PullRequest struct {
Title string `json:"title"`
@@ -232,185 +210,24 @@ func (c *Client) PostReview(ctx context.Context, owner, repo string, number int,
return &review, nil
}
// isTemporaryNetError reports whether err is a temporary network error worth retrying.
// This includes connection refused, network unreachable, connection reset, and DNS
// timeouts. It explicitly excludes permanent errors like permission denied or
// "no such host" DNS failures.
func isTemporaryNetError(err error) bool {
if err == nil {
return false
}
// Check for OpError and inspect the underlying syscall error.
// Not all OpErrors are transient — permission denied, for example, is permanent.
var opErr *net.OpError
if errors.As(err, &opErr) {
return isRetriableSyscallError(opErr.Err)
}
// DNS errors: only retry on timeout, not on "no such host" which is permanent.
var dnsErr *net.DNSError
if errors.As(err, &dnsErr) {
return dnsErr.IsTimeout
}
// Check for net.Error with Timeout() (Temporary is deprecated)
var netErr net.Error
if errors.As(err, &netErr) {
return netErr.Timeout()
}
return false
}
// isRetriableSyscallError reports whether the underlying error from a net.OpError
// is a transient syscall error worth retrying.
func isRetriableSyscallError(err error) bool {
if err == nil {
return false
}
// Check for syscall.Errno directly or wrapped
var errno syscall.Errno
if errors.As(err, &errno) {
switch errno {
case syscall.ECONNREFUSED, // connection refused — server not listening
syscall.ECONNRESET, // connection reset by peer
syscall.ENETUNREACH, // network unreachable
syscall.EHOSTUNREACH, // host unreachable
syscall.ETIMEDOUT: // connection timed out
return true
default:
// EACCES, EPERM, etc. are permanent — don't retry
return false
}
}
// If we can't identify the specific syscall error, be conservative and retry.
// This handles wrapped errors or platform-specific error types.
// The retry count is limited, so erring on the side of retrying is safe.
return true
}
// redactURL strips query parameters from a URL for safe logging.
// This prevents accidental exposure of sensitive data that future callers
// might pass via query strings.
func redactURL(rawURL string) string {
parsed, err := url.Parse(rawURL)
if err != nil {
// If we cannot parse it, return a safe placeholder rather than
// potentially logging something sensitive.
return "[invalid URL]"
}
if parsed.RawQuery != "" {
parsed.RawQuery = "[redacted]"
}
return parsed.String()
}
// sanitizeErrorForLog returns a loggable version of an error that omits
// potentially sensitive content like response bodies. For APIError, only
// the status code is included; for other errors, the type is preserved.
func sanitizeErrorForLog(err error) string {
if err == nil {
return "<nil>"
}
var apiErr *APIError
if errors.As(err, &apiErr) {
return fmt.Sprintf("HTTP %d", apiErr.StatusCode)
}
return err.Error()
}
// doGet performs an HTTP GET request with retry on 5xx errors and temporary
// network errors. Retries up to 3 times with exponential backoff (1s, 2s delays
// by default; configurable via Client.RetryBackoff for testing).
func (c *Client) doGet(ctx context.Context, reqURL string) ([]byte, error) {
const maxAttempts = 3
// backoff[i] is the delay before attempt i+1 (i.e., after attempt i fails).
// First attempt (i=0) has no delay; retries wait 1s then 2s by default.
backoff := c.RetryBackoff
if backoff == nil {
backoff = []time.Duration{1 * time.Second, 2 * time.Second}
req, err := http.NewRequestWithContext(ctx, http.MethodGet, reqURL, nil)
if err != nil {
return nil, err
}
req.Header.Set("Authorization", "token "+c.token)
// maxErrorBodyBytes limits how much of an error response body we read
// to protect against malicious servers sending unbounded data.
const maxErrorBodyBytes = 64 * 1024 // 64 KB
var lastErr error
for attempt := 0; attempt < maxAttempts; attempt++ {
if attempt > 0 {
// Determine delay: use backoff slice if available, otherwise retry immediately.
// An empty RetryBackoff slice means "retry without delay" — this is intentional
// as the caller explicitly configured no delays.
var delay time.Duration
if attempt-1 < len(backoff) {
delay = backoff[attempt-1]
}
if delay > 0 {
slog.Warn("retrying request after error",
"attempt", attempt+1,
"url", redactURL(reqURL),
"delay", delay.String(),
"lastError", sanitizeErrorForLog(lastErr))
timer := time.NewTimer(delay)
select {
case <-timer.C:
case <-ctx.Done():
timer.Stop()
return nil, ctx.Err()
}
}
}
req, err := http.NewRequestWithContext(ctx, http.MethodGet, reqURL, nil)
if err != nil {
return nil, err
}
req.Header.Set("Authorization", "token "+c.token)
resp, err := c.http.Do(req)
if err != nil {
// Always capture the error for consistent return at loop end.
// This ensures both network errors and HTTP 5xx return lastErr.
lastErr = err
// Only retry temporary network errors when attempts remain.
if attempt < maxAttempts-1 && isTemporaryNetError(err) {
slog.Warn("temporary network error, will retry",
"attempt", attempt+1,
"url", redactURL(reqURL),
"error", err)
continue
}
// Non-retryable network error or final attempt exhausted.
return nil, lastErr
}
if resp.StatusCode >= 200 && resp.StatusCode < 300 {
body, err := io.ReadAll(resp.Body)
resp.Body.Close()
if err != nil {
return nil, err
}
return body, nil
}
// Error path: limit how much we read from potentially malicious server
errBody, _ := io.ReadAll(io.LimitReader(resp.Body, maxErrorBodyBytes))
resp.Body.Close()
lastErr = &APIError{StatusCode: resp.StatusCode, Body: string(errBody)}
// Only retry on 5xx server errors
if resp.StatusCode < 500 || resp.StatusCode >= 600 {
return nil, lastErr
}
resp, err := c.http.Do(req)
if err != nil {
return nil, err
}
defer resp.Body.Close()
return nil, lastErr
if resp.StatusCode < 200 || resp.StatusCode >= 300 {
body, _ := io.ReadAll(resp.Body)
return nil, &APIError{StatusCode: resp.StatusCode, Body: string(body)}
}
return io.ReadAll(resp.Body)
}
// escapePath escapes each segment of a relative file path for use in URLs.
@@ -434,13 +251,7 @@ type ContentEntry struct {
// ListContents lists files and directories at a given path in a repo.
// Pass an empty path to list the repository root.
// If the path points to a file (not a directory), Gitea returns a single
// object instead of an array; this method normalizes both cases to a slice.
func (c *Client) ListContents(ctx context.Context, owner, repo, path string) ([]ContentEntry, error) {
// Normalize "." to empty string — Gitea API rejects "." with 500
if path == "." {
path = ""
}
var reqURL string
if path == "" {
reqURL = fmt.Sprintf("%s/api/v1/repos/%s/%s/contents", c.baseURL, url.PathEscape(owner), url.PathEscape(repo))
@@ -453,16 +264,7 @@ func (c *Client) ListContents(ctx context.Context, owner, repo, path string) ([]
}
var entries []ContentEntry
if err := json.Unmarshal(body, &entries); err != nil {
// Gitea returns a single object (not an array) when path is a file
var single ContentEntry
if err2 := json.Unmarshal(body, &single); err2 != nil {
return nil, fmt.Errorf("parse contents JSON: %w", err)
}
// Guard against empty/malformed responses
if single.Name == "" && single.Path == "" {
return nil, fmt.Errorf("parse contents JSON: empty response for path %q", path)
}
entries = []ContentEntry{single}
return nil, fmt.Errorf("parse contents JSON: %w", err)
}
return entries, nil
}
@@ -515,9 +317,9 @@ func (c *Client) GetAllFilesInPath(ctx context.Context, owner, repo, path string
// Review represents a pull request review from the Gitea API.
type Review struct {
ID int64 `json:"id"`
Body string `json:"body"`
User struct {
ID int64 `json:"id"`
Body string `json:"body"`
User struct {
Login string `json:"login"`
} `json:"user"`
State string `json:"state"`
+5 -406
View File
@@ -6,14 +6,10 @@ import (
"errors"
"fmt"
"io"
"net"
"net/http"
"net/http/httptest"
"strings"
"sync/atomic"
"syscall"
"testing"
"time"
)
func TestGetPullRequest(t *testing.T) {
@@ -280,64 +276,11 @@ func TestListContents(t *testing.T) {
}
}
func TestListContents_DotPath(t *testing.T) {
server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
// "." should be normalized to empty path, which hits the root contents endpoint
if r.URL.Path != "/api/v1/repos/owner/repo/contents" {
t.Errorf("expected root contents path, got: %s", r.URL.Path)
}
w.Header().Set("Content-Type", "application/json")
fmt.Fprintf(w, `[{"name":"README.md","path":"README.md","type":"file"}]`)
}))
defer server.Close()
client := NewClient(server.URL, "test-token")
entries, err := client.ListContents(context.Background(), "owner", "repo", ".")
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 README.md, got %s", entries[0].Name)
}
}
func TestListContents_FilePath(t *testing.T) {
// Gitea returns a single object (not an array) when path is a file
server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
if r.URL.Path != "/api/v1/repos/owner/repo/contents/README.md" {
t.Errorf("unexpected path: %s", r.URL.Path)
}
w.Header().Set("Content-Type", "application/json")
// Single object, not an array
fmt.Fprintf(w, `{"name":"README.md","path":"README.md","type":"file"}`)
}))
defer server.Close()
client := NewClient(server.URL, "test-token")
entries, err := client.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 README.md, got %s", entries[0].Name)
}
if entries[0].Type != "file" {
t.Errorf("expected type file, got %s", entries[0].Type)
}
}
func TestGetAllFilesInPath_File(t *testing.T) {
server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
if r.URL.Path == "/api/v1/repos/owner/repo/contents/README.md" {
// Gitea returns a single object (not array) when path is a file
w.Header().Set("Content-Type", "application/json")
fmt.Fprintf(w, `{"name":"README.md","path":"README.md","type":"file"}`)
// Gitea returns 404 for contents API on files (it's not a dir)
http.NotFound(w, r)
return
}
if r.URL.Path == "/api/v1/repos/owner/repo/raw/README.md" {
@@ -641,9 +584,9 @@ func TestGetAllFilesInPath_403Propagates(t *testing.T) {
func TestIsNotFound(t *testing.T) {
tests := []struct {
name string
err error
want bool
name string
err error
want bool
}{
{"nil error", nil, false},
{"non-API error", fmt.Errorf("network timeout"), false},
@@ -800,347 +743,3 @@ func TestResolveComment_Error(t *testing.T) {
t.Fatal("expected error for 404 response")
}
}
func TestIsServerError(t *testing.T) {
tests := []struct {
name string
err error
want bool
}{
{"nil error", nil, false},
{"non-API error", fmt.Errorf("network timeout"), false},
{"404 APIError", &APIError{StatusCode: 404, Body: "not found"}, false},
{"500 APIError", &APIError{StatusCode: 500, Body: "server error"}, true},
{"502 APIError", &APIError{StatusCode: 502, Body: "bad gateway"}, true},
{"503 APIError", &APIError{StatusCode: 503, Body: "unavailable"}, true},
{"599 APIError", &APIError{StatusCode: 599, Body: "edge case"}, true},
{"600 not server error", &APIError{StatusCode: 600, Body: "edge"}, false},
{"400 not server error", &APIError{StatusCode: 400, Body: "bad request"}, false},
{"wrapped 500", fmt.Errorf("fetch: %w", &APIError{StatusCode: 500, Body: "err"}), true},
{"wrapped 404", fmt.Errorf("fetch: %w", &APIError{StatusCode: 404, Body: "err"}), false},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
got := IsServerError(tt.err)
if got != tt.want {
t.Errorf("IsServerError(%v) = %v, want %v", tt.err, got, tt.want)
}
})
}
}
func TestDoGet_RetriesOn500(t *testing.T) {
attempts := 0
server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
attempts++
if attempts < 3 {
w.WriteHeader(http.StatusInternalServerError)
w.Write([]byte(`{"message":"transient error"}`))
return
}
w.WriteHeader(http.StatusOK)
w.Write([]byte(`{"data":"success"}`))
}))
defer server.Close()
client := NewClient(server.URL, "test-token")
// Use short backoff for fast tests
client.RetryBackoff = []time.Duration{1 * time.Millisecond, 1 * time.Millisecond}
body, err := client.doGet(context.Background(), server.URL+"/test")
if err != nil {
t.Fatalf("expected success after retry, got error: %v", err)
}
if string(body) != `{"data":"success"}` {
t.Errorf("body = %q, want %q", string(body), `{"data":"success"}`)
}
if attempts != 3 {
t.Errorf("attempts = %d, want 3", attempts)
}
}
func TestDoGet_FailsAfterMaxRetries(t *testing.T) {
attempts := 0
server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
attempts++
w.WriteHeader(http.StatusInternalServerError)
w.Write([]byte(`{"message":"persistent error"}`))
}))
defer server.Close()
client := NewClient(server.URL, "test-token")
// Use short backoff for fast tests
client.RetryBackoff = []time.Duration{1 * time.Millisecond, 1 * time.Millisecond}
_, err := client.doGet(context.Background(), server.URL+"/test")
if err == nil {
t.Fatal("expected error after max retries")
}
var apiErr *APIError
if !errors.As(err, &apiErr) {
t.Fatalf("expected APIError, got: %v", err)
}
if apiErr.StatusCode != http.StatusInternalServerError {
t.Errorf("status = %d, want 500", apiErr.StatusCode)
}
if attempts != 3 {
t.Errorf("attempts = %d, want 3 (max retries)", attempts)
}
}
func TestDoGet_NoRetryOn4xx(t *testing.T) {
attempts := 0
server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
attempts++
w.WriteHeader(http.StatusForbidden)
w.Write([]byte(`{"message":"forbidden"}`))
}))
defer server.Close()
client := NewClient(server.URL, "test-token")
_, err := client.doGet(context.Background(), server.URL+"/test")
if err == nil {
t.Fatal("expected error for 403")
}
var apiErr *APIError
if !errors.As(err, &apiErr) {
t.Fatalf("expected APIError, got: %v", err)
}
if apiErr.StatusCode != http.StatusForbidden {
t.Errorf("status = %d, want 403", apiErr.StatusCode)
}
if attempts != 1 {
t.Errorf("attempts = %d, want 1 (no retry on 4xx)", attempts)
}
}
func TestDoGet_RespectsContextCancellation(t *testing.T) {
attempts := 0
server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
attempts++
w.WriteHeader(http.StatusInternalServerError)
w.Write([]byte(`{"message":"error"}`))
}))
defer server.Close()
ctx, cancel := context.WithCancel(context.Background())
client := NewClient(server.URL, "test-token")
// Use longer backoff to give us time to cancel during the wait
client.RetryBackoff = []time.Duration{100 * time.Millisecond, 100 * time.Millisecond}
// Cancel after first attempt returns and retry begins
go func() {
time.Sleep(20 * time.Millisecond)
cancel()
}()
_, err := client.doGet(ctx, server.URL+"/test")
if err == nil {
t.Fatal("expected error on context cancellation")
}
// Should have made 1 attempt, then context cancelled during backoff
if attempts != 1 {
t.Errorf("attempts = %d, expected 1 before context cancel during backoff", attempts)
}
}
// mockTransport is a test helper that returns errors for the first N calls,
// then delegates to a real server.
type mockTransport struct {
failCount int32 // number of failures remaining (atomic)
failErr error // error to return on failure
realServer *httptest.Server
attemptsMade atomic.Int32 // tracks total attempts
}
func (m *mockTransport) RoundTrip(req *http.Request) (*http.Response, error) {
m.attemptsMade.Add(1)
remaining := atomic.AddInt32(&m.failCount, -1)
if remaining >= 0 {
// Still have failures to return
return nil, m.failErr
}
// Redirect to real server
req.URL.Host = m.realServer.Listener.Addr().String()
req.URL.Scheme = "http"
return http.DefaultTransport.RoundTrip(req)
}
func TestDoGet_RetriesOnTemporaryNetError(t *testing.T) {
// Real server that will handle successful requests
server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
w.WriteHeader(http.StatusOK)
w.Write([]byte(`{"status":"ok"}`))
}))
defer server.Close()
// Mock transport: fail twice with ECONNREFUSED, then succeed
mt := &mockTransport{
failCount: 2,
failErr: &net.OpError{Op: "dial", Net: "tcp", Err: syscall.ECONNREFUSED},
realServer: server,
}
client := NewClient("http://fake-host/", "test-token")
client.SetHTTPClient(&http.Client{Transport: mt})
client.RetryBackoff = []time.Duration{1 * time.Millisecond, 1 * time.Millisecond}
body, err := client.doGet(context.Background(), "http://fake-host/test")
if err != nil {
t.Fatalf("expected success after retries, got error: %v", err)
}
if string(body) != `{"status":"ok"}` {
t.Errorf("body = %q, want %q", string(body), `{"status":"ok"}`)
}
// Should have made exactly 3 attempts: 2 failures + 1 success
if got := mt.attemptsMade.Load(); got != 3 {
t.Errorf("attempts = %d, want 3 (2 failures + 1 success)", got)
}
}
func TestIsTemporaryNetError(t *testing.T) {
tests := []struct {
name string
err error
want bool
}{
{"nil error", nil, false},
{"plain error", fmt.Errorf("some error"), false},
// OpError with retriable syscall errors
{"OpError ECONNREFUSED", &net.OpError{Op: "dial", Err: syscall.ECONNREFUSED}, true},
{"OpError ECONNRESET", &net.OpError{Op: "read", Err: syscall.ECONNRESET}, true},
{"OpError ENETUNREACH", &net.OpError{Op: "dial", Err: syscall.ENETUNREACH}, true},
{"OpError EHOSTUNREACH", &net.OpError{Op: "dial", Err: syscall.EHOSTUNREACH}, true},
{"OpError ETIMEDOUT", &net.OpError{Op: "dial", Err: syscall.ETIMEDOUT}, true},
// OpError with permanent syscall errors — should NOT retry
{"OpError EACCES", &net.OpError{Op: "dial", Err: syscall.EACCES}, false},
{"OpError EPERM", &net.OpError{Op: "dial", Err: syscall.EPERM}, false},
// OpError with unknown inner error — conservative retry
{"OpError unknown inner", &net.OpError{Op: "dial", Err: fmt.Errorf("unknown")}, true},
// DNS errors
{"DNS timeout", &net.DNSError{IsTimeout: true}, true},
{"DNS no such host", &net.DNSError{IsTimeout: false, Name: "bad.host"}, false},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
got := isTemporaryNetError(tt.err)
if got != tt.want {
t.Errorf("isTemporaryNetError(%v) = %v, want %v", tt.err, got, tt.want)
}
})
}
}
func TestIsRetriableSyscallError(t *testing.T) {
tests := []struct {
name string
err error
want bool
}{
{"nil", nil, false},
{"ECONNREFUSED", syscall.ECONNREFUSED, true},
{"ECONNRESET", syscall.ECONNRESET, true},
{"ENETUNREACH", syscall.ENETUNREACH, true},
{"EHOSTUNREACH", syscall.EHOSTUNREACH, true},
{"ETIMEDOUT", syscall.ETIMEDOUT, true},
{"EACCES (permanent)", syscall.EACCES, false},
{"EPERM (permanent)", syscall.EPERM, false},
{"ENOENT (permanent)", syscall.ENOENT, false},
{"unknown error", fmt.Errorf("something"), true}, // conservative retry
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
got := isRetriableSyscallError(tt.err)
if got != tt.want {
t.Errorf("isRetriableSyscallError(%v) = %v, want %v", tt.err, got, tt.want)
}
})
}
}
func TestRedactURL(t *testing.T) {
tests := []struct {
name string
input string
want string
}{
{
name: "no query params",
input: "https://gitea.example.com/api/v1/repos/owner/repo/pulls/1",
want: "https://gitea.example.com/api/v1/repos/owner/repo/pulls/1",
},
{
name: "with query params - redacts",
input: "https://gitea.example.com/api/v1/repos/owner/repo/raw/file?ref=main",
want: "https://gitea.example.com/api/v1/repos/owner/repo/raw/file?[redacted]",
},
{
name: "multiple query params",
input: "https://example.com/path?token=secret&page=1",
want: "https://example.com/path?[redacted]",
},
{
name: "invalid URL",
input: "://invalid",
want: "[invalid URL]",
},
{
name: "empty string",
input: "",
want: "",
},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
got := redactURL(tt.input)
if got != tt.want {
t.Errorf("redactURL(%q) = %q, want %q", tt.input, got, tt.want)
}
})
}
}
func TestSanitizeErrorForLog(t *testing.T) {
tests := []struct {
name string
err error
want string
}{
{
name: "nil error",
err: nil,
want: "<nil>",
},
{
name: "APIError omits body",
err: &APIError{StatusCode: 500, Body: "internal error: database connection failed"},
want: "HTTP 500",
},
{
name: "APIError with large body still only shows status",
err: &APIError{StatusCode: 502, Body: strings.Repeat("x", 1000)},
want: "HTTP 502",
},
{
name: "non-API error preserved",
err: fmt.Errorf("connection refused"),
want: "connection refused",
},
{
name: "wrapped APIError",
err: fmt.Errorf("request failed: %w", &APIError{StatusCode: 503, Body: "service unavailable"}),
want: "HTTP 503",
},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
got := sanitizeErrorForLog(tt.err)
if got != tt.want {
t.Errorf("sanitizeErrorForLog() = %q, want %q", got, tt.want)
}
})
}
}
+105 -7
View File
@@ -2,10 +2,12 @@ package review
import (
"bytes"
"context"
"embed"
"encoding/json"
"fmt"
"os"
"path/filepath"
"sort"
"strings"
"unicode/utf8"
@@ -28,6 +30,9 @@ const MaxYAMLDepth = 20
// This prevents DoS via wide-but-shallow structures that bypass depth limits.
const MaxYAMLNodes = 1000
// RepoPersonasPath is the path within a repository where custom personas are stored.
const RepoPersonasPath = ".review-bot/personas"
// Persona defines a specialized review role with focused expertise.
type Persona struct {
Name string `json:"name" yaml:"name"`
@@ -48,6 +53,20 @@ type Severity struct {
Nit string `json:"nit" yaml:"nit"`
}
// RepoContentFetcher is an interface for fetching file content from a repository.
// This allows LoadRepoPersonas to work with any client that can list and fetch files.
type RepoContentFetcher interface {
ListContents(ctx context.Context, owner, repo, path string) ([]ContentEntry, error)
GetFileContent(ctx context.Context, owner, repo, filepath string) (string, error)
}
// ContentEntry represents a file or directory entry (mirrors gitea.ContentEntry).
type ContentEntry struct {
Name string `json:"name"`
Path string `json:"path"`
Type string `json:"type"` // "file" or "dir"
}
// LoadPersona loads a persona from a JSON or YAML file path.
// Format is detected by file extension: .yaml/.yml for YAML, .json or other for JSON.
// Files larger than MaxPersonaFileSize are rejected.
@@ -130,6 +149,92 @@ func ListBuiltinPersonas() []string {
return names
}
// LoadRepoPersonas loads custom personas from a repository's .review-bot/personas/ directory.
// Returns an empty map if the directory doesn't exist or is empty.
// Repo personas take precedence over built-in personas with the same name.
func LoadRepoPersonas(ctx context.Context, client RepoContentFetcher, owner, repo string) (map[string]*Persona, error) {
personas := make(map[string]*Persona)
entries, err := client.ListContents(ctx, owner, repo, RepoPersonasPath)
if err != nil {
// Directory doesn't exist — not an error, just no custom personas
return personas, nil
}
for _, entry := range entries {
if entry.Type != "file" {
continue
}
// Only load YAML files
ext := strings.ToLower(filepath.Ext(entry.Name))
if ext != ".yaml" && ext != ".yml" {
continue
}
content, err := client.GetFileContent(ctx, owner, repo, entry.Path)
if err != nil {
// Log but don't fail — one bad persona shouldn't break the whole review
continue
}
// Validate file size
if len(content) > MaxPersonaFileSize {
continue
}
persona, err := parsePersona([]byte(content), "repo:"+entry.Path)
if err != nil {
// Log but don't fail
continue
}
personas[persona.Name] = persona
}
return personas, nil
}
// LoadPersonaWithFallback loads a persona by name, checking the repo first, then built-ins.
// This is the primary entry point for loading personas during a review.
func LoadPersonaWithFallback(ctx context.Context, client RepoContentFetcher, owner, repo, name string) (*Persona, error) {
// Try repo personas first
repoPersonas, err := LoadRepoPersonas(ctx, client, owner, repo)
if err == nil {
if p, ok := repoPersonas[name]; ok {
return p, nil
}
}
// Fall back to built-in
return LoadBuiltinPersona(name)
}
// ListAllPersonas returns a merged list of available personas (repo + built-in).
// Repo personas take precedence over built-ins with the same name.
func ListAllPersonas(ctx context.Context, client RepoContentFetcher, owner, repo string) []string {
seen := make(map[string]bool)
// Built-ins first
for _, name := range ListBuiltinPersonas() {
seen[name] = true
}
// Repo personas override
repoPersonas, err := LoadRepoPersonas(ctx, client, owner, repo)
if err == nil {
for name := range repoPersonas {
seen[name] = true
}
}
names := make([]string, 0, len(seen))
for name := range seen {
names = append(names, name)
}
sort.Strings(names)
return names
}
// parsePersona parses persona data from JSON or YAML format.
// Format is detected by the source file extension.
func parsePersona(data []byte, source string) (*Persona, error) {
@@ -224,13 +329,6 @@ func checkYAMLDepth(node *yaml.Node, depth, maxDepth, maxNodes int, seen map[*ya
return nil
}
// ParsePersonaBytes parses persona data from bytes with a source label for errors.
// This is useful for parsing personas fetched from external sources (e.g., Gitea API)
// without requiring filesystem access. Format is detected by source extension.
func ParsePersonaBytes(data []byte, source string) (*Persona, error) {
return parsePersona(data, source)
}
func validatePersona(p *Persona, source string) error {
if p.Name == "" {
return fmt.Errorf("persona %s: name is required", source)
+240
View File
@@ -1,6 +1,7 @@
package review
import (
"context"
"fmt"
"os"
"path/filepath"
@@ -776,3 +777,242 @@ identity: test identity
t.Errorf("Name = %q, want %q", p.Name, "test")
}
}
// MockRepoFetcher is a mock implementation of RepoContentFetcher for testing.
type MockRepoFetcher struct {
Contents map[string][]ContentEntry // path -> entries
Files map[string]string // path -> content
}
func (m *MockRepoFetcher) ListContents(ctx context.Context, owner, repo, path string) ([]ContentEntry, error) {
key := fmt.Sprintf("%s/%s/%s", owner, repo, path)
entries, ok := m.Contents[key]
if !ok {
return nil, fmt.Errorf("path not found: %s", path)
}
return entries, nil
}
func (m *MockRepoFetcher) GetFileContent(ctx context.Context, owner, repo, filepath string) (string, error) {
key := fmt.Sprintf("%s/%s/%s", owner, repo, filepath)
content, ok := m.Files[key]
if !ok {
return "", fmt.Errorf("file not found: %s", filepath)
}
return content, nil
}
func TestLoadRepoPersonas(t *testing.T) {
validPersona := `name: custom-security
display_name: Custom Security
identity: |
You are a custom security reviewer.
focus:
- SQL injection
- XSS attacks
ignore:
- Code style
severity:
major: Critical vulnerabilities
minor: Potential issues
nit: Suggestions
`
tests := []struct {
name string
fetcher *MockRepoFetcher
wantCount int
wantNames []string
}{
{
name: "no personas directory",
fetcher: &MockRepoFetcher{
Contents: map[string][]ContentEntry{},
Files: map[string]string{},
},
wantCount: 0,
},
{
name: "empty personas directory",
fetcher: &MockRepoFetcher{
Contents: map[string][]ContentEntry{
"owner/repo/.review-bot/personas": {},
},
Files: map[string]string{},
},
wantCount: 0,
},
{
name: "one valid persona",
fetcher: &MockRepoFetcher{
Contents: map[string][]ContentEntry{
"owner/repo/.review-bot/personas": {
{Name: "custom-security.yaml", Path: ".review-bot/personas/custom-security.yaml", Type: "file"},
},
},
Files: map[string]string{
"owner/repo/.review-bot/personas/custom-security.yaml": validPersona,
},
},
wantCount: 1,
wantNames: []string{"custom-security"},
},
{
name: "skip non-yaml files",
fetcher: &MockRepoFetcher{
Contents: map[string][]ContentEntry{
"owner/repo/.review-bot/personas": {
{Name: "custom-security.yaml", Path: ".review-bot/personas/custom-security.yaml", Type: "file"},
{Name: "readme.md", Path: ".review-bot/personas/readme.md", Type: "file"},
{Name: "subdir", Path: ".review-bot/personas/subdir", Type: "dir"},
},
},
Files: map[string]string{
"owner/repo/.review-bot/personas/custom-security.yaml": validPersona,
},
},
wantCount: 1,
wantNames: []string{"custom-security"},
},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
ctx := context.Background()
personas, err := LoadRepoPersonas(ctx, tt.fetcher, "owner", "repo")
if err != nil {
t.Fatalf("unexpected error: %v", err)
}
if len(personas) != tt.wantCount {
t.Errorf("got %d personas, want %d", len(personas), tt.wantCount)
}
for _, name := range tt.wantNames {
if _, ok := personas[name]; !ok {
t.Errorf("missing expected persona %q", name)
}
}
})
}
}
func TestLoadPersonaWithFallback(t *testing.T) {
customSecurity := `name: security
display_name: Custom Security Override
identity: |
Custom security reviewer for this repo.
focus:
- Repo-specific security
ignore:
- General stuff
severity:
major: Critical
minor: Warning
nit: Info
`
tests := []struct {
name string
fetcher *MockRepoFetcher
personaName string
wantDisplayName string
wantErr bool
}{
{
name: "repo persona overrides builtin",
fetcher: &MockRepoFetcher{
Contents: map[string][]ContentEntry{
"owner/repo/.review-bot/personas": {
{Name: "security.yaml", Path: ".review-bot/personas/security.yaml", Type: "file"},
},
},
Files: map[string]string{
"owner/repo/.review-bot/personas/security.yaml": customSecurity,
},
},
personaName: "security",
wantDisplayName: "Custom Security Override",
},
{
name: "fallback to builtin when repo has no override",
fetcher: &MockRepoFetcher{
Contents: map[string][]ContentEntry{},
Files: map[string]string{},
},
personaName: "security",
wantDisplayName: "Security Specialist",
},
{
name: "unknown persona",
fetcher: &MockRepoFetcher{
Contents: map[string][]ContentEntry{},
Files: map[string]string{},
},
personaName: "nonexistent",
wantErr: true,
},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
ctx := context.Background()
p, err := LoadPersonaWithFallback(ctx, tt.fetcher, "owner", "repo", tt.personaName)
if tt.wantErr {
if err == nil {
t.Error("expected error, got nil")
}
return
}
if err != nil {
t.Fatalf("unexpected error: %v", err)
}
if p.DisplayName != tt.wantDisplayName {
t.Errorf("DisplayName = %q, want %q", p.DisplayName, tt.wantDisplayName)
}
})
}
}
func TestListAllPersonas(t *testing.T) {
customPersona := `name: repo-specific
display_name: Repo Specific
identity: A repo-specific reviewer.
focus: []
ignore: []
severity:
major: Major
minor: Minor
nit: Nit
`
fetcher := &MockRepoFetcher{
Contents: map[string][]ContentEntry{
"owner/repo/.review-bot/personas": {
{Name: "repo-specific.yaml", Path: ".review-bot/personas/repo-specific.yaml", Type: "file"},
},
},
Files: map[string]string{
"owner/repo/.review-bot/personas/repo-specific.yaml": customPersona,
},
}
ctx := context.Background()
names := ListAllPersonas(ctx, fetcher, "owner", "repo")
// Should include both built-ins and repo-specific
builtins := ListBuiltinPersonas()
if len(names) <= len(builtins) {
t.Error("expected more personas than just built-ins")
}
// Check repo-specific is included
found := false
for _, name := range names {
if name == "repo-specific" {
found = true
break
}
}
if !found {
t.Error("repo-specific persona not found in list")
}
}
-150
View File
@@ -1,150 +0,0 @@
package review
import (
"context"
"log/slog"
"strings"
)
// RepoPersonaPath is the directory path where repo-specific personas are stored.
const RepoPersonaPath = ".review-bot/personas"
// GiteaClient defines the subset of gitea.Client methods needed for loading repo personas.
// This interface allows for easier testing and decouples the review package from gitea.
type GiteaClient interface {
ListContents(ctx context.Context, owner, repo, path string) ([]ContentEntry, error)
GetFileContent(ctx context.Context, owner, repo, filepath string) (string, error)
}
// ContentEntry represents a file or directory entry from the contents API.
// This mirrors gitea.ContentEntry to avoid import cycles.
type ContentEntry struct {
Name string `json:"name"`
Path string `json:"path"`
Type string `json:"type"` // "file" or "dir"
}
// LoadRepoPersonas fetches personas from a repository's .review-bot/personas/ directory.
// Returns an empty map (not nil) if the directory doesn't exist or is empty.
// Individual parse failures are logged and skipped; the remaining personas are still returned.
// Auth errors and other non-404 errors are propagated.
// Files exceeding MaxPersonaFileSize are rejected to prevent resource exhaustion.
func LoadRepoPersonas(ctx context.Context, client GiteaClient, owner, repo string) (map[string]*Persona, error) {
result := make(map[string]*Persona)
entries, err := client.ListContents(ctx, owner, repo, RepoPersonaPath)
if err != nil {
// Check if this is a 404 (directory doesn't exist) - expected case
if isNotFoundError(err) {
slog.Debug("no repo personas directory found", "repo", owner+"/"+repo)
return result, nil
}
// Other errors (auth, server) should propagate
return nil, err
}
if len(entries) == 0 {
slog.Debug("repo personas directory is empty", "repo", owner+"/"+repo)
return result, nil
}
for _, entry := range entries {
if entry.Type != "file" {
continue
}
// Only process YAML files
if !isYAMLFile(entry.Name) {
continue
}
content, err := client.GetFileContent(ctx, owner, repo, entry.Path)
if err != nil {
slog.Warn("could not fetch repo persona file",
"file", entry.Path,
"repo", owner+"/"+repo,
"error", err)
continue
}
// Enforce size limit before parsing to prevent resource exhaustion
if len(content) > MaxPersonaFileSize {
slog.Warn("repo persona file exceeds maximum size",
"file", entry.Path,
"repo", owner+"/"+repo,
"size", len(content),
"max", MaxPersonaFileSize)
continue
}
persona, err := ParsePersonaBytes([]byte(content), entry.Path)
if err != nil {
slog.Warn("could not parse repo persona file",
"file", entry.Path,
"repo", owner+"/"+repo,
"error", err)
continue
}
result[persona.Name] = persona
slog.Debug("loaded repo persona",
"name", persona.Name,
"file", entry.Path,
"repo", owner+"/"+repo)
}
return result, nil
}
// MergePersonas combines built-in personas with repo personas.
// Repo personas take precedence on name collision.
// Returns a new map; inputs are not modified.
func MergePersonas(builtin, repo map[string]*Persona) map[string]*Persona {
result := make(map[string]*Persona, len(builtin)+len(repo))
// Copy built-in personas first
for name, p := range builtin {
result[name] = p
}
// Overlay repo personas (override on collision)
for name, p := range repo {
if _, exists := result[name]; exists {
slog.Debug("repo persona overrides built-in", "name", name)
}
result[name] = p
}
return result
}
// GetBuiltinPersonasMap returns all built-in personas as a map keyed by name.
// Returns an empty map (not nil) if loading fails.
func GetBuiltinPersonasMap() map[string]*Persona {
result := make(map[string]*Persona)
for _, name := range ListBuiltinPersonas() {
p, err := LoadBuiltinPersona(name)
if err != nil {
slog.Warn("could not load built-in persona", "name", name, "error", err)
continue
}
result[name] = p
}
return result
}
// isYAMLFile checks if a filename has a YAML extension.
func isYAMLFile(name string) bool {
lower := strings.ToLower(name)
return strings.HasSuffix(lower, ".yaml") || strings.HasSuffix(lower, ".yml")
}
// isNotFoundError checks if an error represents a 404 response.
// This uses a specific "HTTP 404" substring match rather than a generic "not found"
// match to avoid masking authentication failures or transport errors that might
// contain "not found" in their message.
func isNotFoundError(err error) bool {
if err == nil {
return false
}
return strings.Contains(err.Error(), "HTTP 404")
}
-443
View File
@@ -1,443 +0,0 @@
package review
import (
"context"
"errors"
"strings"
"testing"
)
func TestParsePersonaBytes(t *testing.T) {
tests := []struct {
name string
data string
source string
wantName string
wantErr string
}{
{
name: "valid yaml",
data: `name: test
identity: test identity
focus:
- testing
`,
source: "test.yaml",
wantName: "test",
},
{
name: "missing name",
data: "identity: test\n",
source: "test.yaml",
wantErr: "name is required",
},
{
name: "invalid yaml",
data: "not: valid:\n yaml: [broken",
source: "test.yaml",
wantErr: "parse",
},
{
name: "json format by extension",
data: `{"name": "jsontest", "identity": "json identity"}`,
source: "test.json",
wantName: "jsontest",
},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
p, err := ParsePersonaBytes([]byte(tt.data), tt.source)
if tt.wantErr != "" {
if err == nil {
t.Fatalf("expected error containing %q, got nil", tt.wantErr)
}
if !strings.Contains(err.Error(), tt.wantErr) {
t.Errorf("error = %q, want containing %q", err.Error(), tt.wantErr)
}
return
}
if err != nil {
t.Fatalf("unexpected error: %v", err)
}
if p.Name != tt.wantName {
t.Errorf("Name = %q, want %q", p.Name, tt.wantName)
}
})
}
}
// mockGiteaClient implements GiteaClient for testing.
type mockGiteaClient struct {
contents map[string][]ContentEntry // path -> entries
files map[string]string // path -> content
listErr error
fileErr map[string]error // path -> error
}
func (m *mockGiteaClient) ListContents(ctx context.Context, owner, repo, path string) ([]ContentEntry, error) {
if m.listErr != nil {
return nil, m.listErr
}
entries, ok := m.contents[path]
if !ok {
return nil, errors.New("list contents .review-bot/personas: HTTP 404: not found")
}
return entries, nil
}
func (m *mockGiteaClient) GetFileContent(ctx context.Context, owner, repo, filepath string) (string, error) {
if m.fileErr != nil {
if err, ok := m.fileErr[filepath]; ok {
return "", err
}
}
content, ok := m.files[filepath]
if !ok {
return "", errors.New("HTTP 404: file not found")
}
return content, nil
}
func TestLoadRepoPersonas(t *testing.T) {
ctx := context.Background()
t.Run("directory not found returns empty map", func(t *testing.T) {
client := &mockGiteaClient{} // No contents configured -> 404
personas, err := LoadRepoPersonas(ctx, client, "owner", "repo")
if err != nil {
t.Fatalf("unexpected error: %v", err)
}
if personas == nil {
t.Error("expected empty map, got nil")
}
if len(personas) != 0 {
t.Errorf("expected 0 personas, got %d", len(personas))
}
})
t.Run("empty directory returns empty map", func(t *testing.T) {
client := &mockGiteaClient{
contents: map[string][]ContentEntry{
RepoPersonaPath: {},
},
}
personas, err := LoadRepoPersonas(ctx, client, "owner", "repo")
if err != nil {
t.Fatalf("unexpected error: %v", err)
}
if len(personas) != 0 {
t.Errorf("expected 0 personas, got %d", len(personas))
}
})
t.Run("loads valid personas", func(t *testing.T) {
client := &mockGiteaClient{
contents: map[string][]ContentEntry{
RepoPersonaPath: {
{Name: "trading.yaml", Path: ".review-bot/personas/trading.yaml", Type: "file"},
{Name: "crypto.yaml", Path: ".review-bot/personas/crypto.yaml", Type: "file"},
},
},
files: map[string]string{
".review-bot/personas/trading.yaml": `name: trading
display_name: Trading Expert
identity: You are a trading expert.
focus:
- order handling
- risk management
`,
".review-bot/personas/crypto.yaml": `name: crypto
display_name: Crypto Expert
identity: You are a cryptography expert.
focus:
- key management
- encryption
`,
},
}
personas, err := LoadRepoPersonas(ctx, client, "owner", "repo")
if err != nil {
t.Fatalf("unexpected error: %v", err)
}
if len(personas) != 2 {
t.Fatalf("expected 2 personas, got %d", len(personas))
}
if personas["trading"] == nil {
t.Error("expected trading persona")
}
if personas["crypto"] == nil {
t.Error("expected crypto persona")
}
if personas["trading"].DisplayName != "Trading Expert" {
t.Errorf("trading display name = %q, want %q", personas["trading"].DisplayName, "Trading Expert")
}
})
t.Run("skips invalid persona files", func(t *testing.T) {
client := &mockGiteaClient{
contents: map[string][]ContentEntry{
RepoPersonaPath: {
{Name: "valid.yaml", Path: ".review-bot/personas/valid.yaml", Type: "file"},
{Name: "invalid.yaml", Path: ".review-bot/personas/invalid.yaml", Type: "file"},
},
},
files: map[string]string{
".review-bot/personas/valid.yaml": `name: valid
identity: Valid persona
`,
".review-bot/personas/invalid.yaml": "not valid yaml: [broken",
},
}
personas, err := LoadRepoPersonas(ctx, client, "owner", "repo")
if err != nil {
t.Fatalf("unexpected error: %v", err)
}
// Should have the valid one, skip the invalid
if len(personas) != 1 {
t.Fatalf("expected 1 persona (skipped invalid), got %d", len(personas))
}
if personas["valid"] == nil {
t.Error("expected valid persona")
}
})
t.Run("skips non-yaml files", func(t *testing.T) {
client := &mockGiteaClient{
contents: map[string][]ContentEntry{
RepoPersonaPath: {
{Name: "persona.yaml", Path: ".review-bot/personas/persona.yaml", Type: "file"},
{Name: "README.md", Path: ".review-bot/personas/README.md", Type: "file"},
{Name: "notes.txt", Path: ".review-bot/personas/notes.txt", Type: "file"},
},
},
files: map[string]string{
".review-bot/personas/persona.yaml": `name: test
identity: Test persona
`,
".review-bot/personas/README.md": "# Personas\n\nPut your personas here.",
},
}
personas, err := LoadRepoPersonas(ctx, client, "owner", "repo")
if err != nil {
t.Fatalf("unexpected error: %v", err)
}
if len(personas) != 1 {
t.Fatalf("expected 1 persona (yaml only), got %d", len(personas))
}
})
t.Run("skips subdirectories", func(t *testing.T) {
client := &mockGiteaClient{
contents: map[string][]ContentEntry{
RepoPersonaPath: {
{Name: "persona.yaml", Path: ".review-bot/personas/persona.yaml", Type: "file"},
{Name: "subdir", Path: ".review-bot/personas/subdir", Type: "dir"},
},
},
files: map[string]string{
".review-bot/personas/persona.yaml": `name: test
identity: Test persona
`,
},
}
personas, err := LoadRepoPersonas(ctx, client, "owner", "repo")
if err != nil {
t.Fatalf("unexpected error: %v", err)
}
if len(personas) != 1 {
t.Fatalf("expected 1 persona (files only), got %d", len(personas))
}
})
t.Run("propagates auth errors", func(t *testing.T) {
client := &mockGiteaClient{
listErr: errors.New("HTTP 401: unauthorized"),
}
_, err := LoadRepoPersonas(ctx, client, "owner", "repo")
if err == nil {
t.Fatal("expected error for auth failure")
}
if !strings.Contains(err.Error(), "401") {
t.Errorf("error = %q, want containing '401'", err.Error())
}
})
t.Run("skips files that fail to fetch", func(t *testing.T) {
client := &mockGiteaClient{
contents: map[string][]ContentEntry{
RepoPersonaPath: {
{Name: "good.yaml", Path: ".review-bot/personas/good.yaml", Type: "file"},
{Name: "bad.yaml", Path: ".review-bot/personas/bad.yaml", Type: "file"},
},
},
files: map[string]string{
".review-bot/personas/good.yaml": `name: good
identity: Good persona
`,
},
fileErr: map[string]error{
".review-bot/personas/bad.yaml": errors.New("HTTP 500: internal server error"),
},
}
personas, err := LoadRepoPersonas(ctx, client, "owner", "repo")
if err != nil {
t.Fatalf("unexpected error: %v", err)
}
if len(personas) != 1 {
t.Fatalf("expected 1 persona (skipped failed fetch), got %d", len(personas))
}
})
t.Run("skips oversized files", func(t *testing.T) {
// Create a content string that exceeds MaxPersonaFileSize (64KB)
oversizedContent := strings.Repeat("a", MaxPersonaFileSize+1)
client := &mockGiteaClient{
contents: map[string][]ContentEntry{
RepoPersonaPath: {
{Name: "normal.yaml", Path: ".review-bot/personas/normal.yaml", Type: "file"},
{Name: "huge.yaml", Path: ".review-bot/personas/huge.yaml", Type: "file"},
},
},
files: map[string]string{
".review-bot/personas/normal.yaml": `name: normal
identity: Normal sized persona
`,
".review-bot/personas/huge.yaml": oversizedContent,
},
}
personas, err := LoadRepoPersonas(ctx, client, "owner", "repo")
if err != nil {
t.Fatalf("unexpected error: %v", err)
}
// Should have the normal one, skip the oversized
if len(personas) != 1 {
t.Fatalf("expected 1 persona (skipped oversized), got %d", len(personas))
}
if personas["normal"] == nil {
t.Error("expected normal persona")
}
})
}
func TestMergePersonas(t *testing.T) {
builtin := map[string]*Persona{
"security": {Name: "security", Identity: "Built-in security"},
"docs": {Name: "docs", Identity: "Built-in docs"},
}
repo := map[string]*Persona{
"security": {Name: "security", Identity: "Repo security override"},
"trading": {Name: "trading", Identity: "Repo trading"},
}
merged := MergePersonas(builtin, repo)
t.Run("repo overrides builtin on collision", func(t *testing.T) {
if merged["security"].Identity != "Repo security override" {
t.Errorf("security identity = %q, want repo override", merged["security"].Identity)
}
})
t.Run("builtin preserved when no collision", func(t *testing.T) {
if merged["docs"].Identity != "Built-in docs" {
t.Errorf("docs identity = %q, want built-in", merged["docs"].Identity)
}
})
t.Run("repo-only persona added", func(t *testing.T) {
if merged["trading"] == nil {
t.Error("expected trading persona from repo")
}
if merged["trading"].Identity != "Repo trading" {
t.Errorf("trading identity = %q, want repo", merged["trading"].Identity)
}
})
t.Run("original maps not modified", func(t *testing.T) {
if builtin["trading"] != nil {
t.Error("builtin map was modified")
}
if len(repo) != 2 {
t.Error("repo map was modified")
}
})
}
func TestGetBuiltinPersonasMap(t *testing.T) {
personas := GetBuiltinPersonasMap()
if len(personas) == 0 {
t.Fatal("expected at least one built-in persona")
}
// Verify expected personas exist
expected := []string{"security", "architect", "docs"}
for _, name := range expected {
if personas[name] == nil {
t.Errorf("expected built-in persona %q", name)
}
}
// Verify personas are valid
for name, p := range personas {
if p.Name != name {
t.Errorf("persona %q has mismatched name %q", name, p.Name)
}
if p.Identity == "" {
t.Errorf("persona %q has empty identity", name)
}
}
}
func TestIsYAMLFile(t *testing.T) {
tests := []struct {
name string
want bool
}{
{"test.yaml", true},
{"test.yml", true},
{"test.YAML", true},
{"test.YML", true},
{"test.json", false},
{"test.md", false},
{"test.txt", false},
{"yaml", false},
{"yaml.md", false},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
if got := isYAMLFile(tt.name); got != tt.want {
t.Errorf("isYAMLFile(%q) = %v, want %v", tt.name, got, tt.want)
}
})
}
}
func TestIsNotFoundError(t *testing.T) {
tests := []struct {
err error
want bool
}{
{nil, false},
{errors.New("HTTP 404: not found"), true},
{errors.New("HTTP 404"), true},
// Intentionally false: generic "not found" could mask auth/transport errors.
// Only explicit HTTP 404 responses should be treated as "directory doesn't exist".
{errors.New("something not found"), false},
{errors.New("HTTP 401: unauthorized"), false},
{errors.New("connection refused"), false},
}
for _, tt := range tests {
name := "nil"
if tt.err != nil {
name = tt.err.Error()
}
t.Run(name, func(t *testing.T) {
if got := isNotFoundError(tt.err); got != tt.want {
t.Errorf("isNotFoundError(%v) = %v, want %v", tt.err, got, tt.want)
}
})
}
}
-27
View File
@@ -1,27 +0,0 @@
//go:build phase2
package vcs_test
import (
"gitea.weiker.me/rodin/review-bot/gitea"
"gitea.weiker.me/rodin/review-bot/vcs"
)
// Compile-time assertion: documents the gap between gitea.Client and vcs.Client.
// Guarded by the "phase2" build tag — enable once the Gitea adapter bridges these gaps:
//
// 1. PostReview signature mismatch:
// gitea.Client: PostReview(ctx, owner, repo, number, event, body string, comments []gitea.ReviewComment)
// vcs.Reviewer: PostReview(ctx, owner, repo, number, req vcs.ReviewRequest)
//
// 2. GetFileContent signature mismatch:
// gitea.Client: GetFileContent(ctx, owner, repo, filepath string) [no ref; uses default branch]
// vcs.FileReader: GetFileContent(ctx, owner, repo, path, ref string)
// (gitea.Client has GetFileContentRef for the ref variant)
//
// 3. ReviewComment type mismatch:
// gitea.ReviewComment uses NewPosition int64 (Gitea line-number convention)
// vcs.ReviewComment uses Position int (GitHub diff-position convention)
//
// The Gitea adapter (Phase 2) will wrap gitea.Client to bridge these gaps.
var _ vcs.Client = (*gitea.Client)(nil)
-40
View File
@@ -1,40 +0,0 @@
// Package vcs defines the shared VCS client interface and supporting types.
// Platform adapters (gitea, github) implement these interfaces so the core
// review logic can work with any VCS platform without platform-specific code.
package vcs
import "context"
// PRReader can fetch pull request metadata, diffs, and changed files.
type PRReader interface {
GetPullRequest(ctx context.Context, owner, repo string, number int) (*PullRequest, error)
GetPullRequestDiff(ctx context.Context, owner, repo string, number int) (string, error)
GetPullRequestFiles(ctx context.Context, owner, repo string, number int) ([]ChangedFile, error)
}
// FileReader can fetch file contents and list directory entries.
type FileReader interface {
GetFileContent(ctx context.Context, owner, repo, path, ref string) (string, error)
ListContents(ctx context.Context, owner, repo, path string) ([]ContentEntry, error)
}
// Reviewer can post, list, and delete pull request reviews.
type Reviewer interface {
PostReview(ctx context.Context, owner, repo string, number int, req ReviewRequest) (*Review, error)
ListReviews(ctx context.Context, owner, repo string, number int) ([]Review, error)
DeleteReview(ctx context.Context, owner, repo string, number int, reviewID int64) error
}
// Identity can report who the authenticated user is.
type Identity interface {
GetAuthenticatedUser(ctx context.Context) (string, error)
}
// Client is the full VCS interface: PR reads, file reads, review management, and identity.
// Platform adapters (gitea, github) implement this interface.
type Client interface {
PRReader
FileReader
Reviewer
Identity
}
-82
View File
@@ -1,82 +0,0 @@
package vcs
// ReviewEvent is the event type for a pull request review action.
// Adapters must translate these action constants to/from platform-native values.
// For example, Gitea uses "APPROVED" as both action and state, while GitHub
// uses "APPROVE" for the action and returns "approved" as the state.
type ReviewEvent string
const (
// ReviewEventApprove approves the pull request.
ReviewEventApprove ReviewEvent = "APPROVE"
// ReviewEventRequestChanges requests changes to the pull request.
ReviewEventRequestChanges ReviewEvent = "REQUEST_CHANGES"
// ReviewEventComment posts a review comment without approval or rejection.
ReviewEventComment ReviewEvent = "COMMENT"
)
// HeadRef identifies the source branch and latest commit of a pull request.
type HeadRef struct {
SHA string `json:"sha"`
Ref string `json:"ref"`
}
// UserInfo identifies a user by login name.
type UserInfo struct {
Login string `json:"login"`
}
// PullRequest holds relevant PR metadata.
type PullRequest struct {
Title string `json:"title"`
Body string `json:"body"`
Head HeadRef `json:"head"`
}
// ChangedFile represents a file modified in a PR.
type ChangedFile struct {
Filename string `json:"filename"`
Status string `json:"status"`
}
// ContentEntry represents a file or directory entry from the contents API.
type ContentEntry struct {
Name string `json:"name"`
Path string `json:"path"`
Type string `json:"type"` // "file" or "dir"
}
// Review represents a pull request review.
type Review struct {
ID int64 `json:"id"`
Body string `json:"body"`
User UserInfo `json:"user"`
State string `json:"state"`
Stale bool `json:"stale"`
CommitID string `json:"commit_id"`
}
// ReviewComment represents an inline comment in a review.
// All adapters use GitHub diff-position convention:
// - Position is a 1-indexed offset from the @@ hunk line in the unified diff.
// - CommitID identifies the commit the comment is anchored to.
// It is optional; omit (empty string) for review-level comments that are
// not attached to a specific commit.
//
// Adapters are responsible for translating to/from platform-native formats
// (e.g. Gitea uses line numbers; GitHub uses diff positions natively).
type ReviewComment struct {
Path string `json:"path"`
Position int `json:"position"` // diff-position: 1-indexed offset from @@ hunk line
CommitID string `json:"commit_id"`
Body string `json:"body"`
}
// ReviewRequest is the payload for posting a review.
type ReviewRequest struct {
// Body is the top-level review comment.
Body string `json:"body"`
// Event is the review action (approve, request changes, or comment).
Event ReviewEvent `json:"event"`
Comments []ReviewComment `json:"comments,omitempty"`
}