feat(github): implement PRReader + FileReader client (#80)

Implement the GitHub API client with PRReader and FileReader interface
conformance for both github.com and GitHub Enterprise.

New files:
- github/client.go: Client struct, NewClient with configurable base URL,
  HTTP helpers with 429 retry and Retry-After support
- github/pr.go: GetPullRequest, GetPullRequestDiff (per-request Accept
  header), GetPullRequestFiles (paginated, populates Patch field),
  GetFileContentAtRef (base64 decode), GetCommitStatuses (merges commit
  statuses + check runs with conclusion mapping)
- github/files.go: GetFileContent (delegates to GetFileContentAtRef),
  ListContents, escapePath, decodeBase64Content helpers

Type changes:
- vcs/types.go: Add Patch field to ChangedFile struct

Tests cover: happy path, 404, 401, 429+retry, malformed response,
pagination, binary files, check run conclusion mapping, base64 decoding.

Compile-time checks:
  var _ vcs.PRReader = (*Client)(nil)
  var _ vcs.FileReader = (*Client)(nil)

Exit criteria met:
- go test ./github/... passes (all methods)
- NewClient with empty baseURL uses https://api.github.com
- NewClient with GHE URL targets correctly
- GetFileContent delegates to GetFileContentAtRef with empty ref
- GetPullRequestFiles paginates and populates Patch field
- GetCommitStatuses merges both commit statuses and check-runs

.github/actions/review/action.yml

@@ -0,0 +1,200 @@
+# 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

.github/workflows/ci.yml

@@ -0,0 +1,69 @@
+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

.github/workflows/pr-ready-gate.yml

@@ -0,0 +1,38 @@
+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}"

.github/workflows/release.yml

@@ -0,0 +1,97 @@
+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"

CONVENTIONS.md

@@ -9,7 +9,7 @@
 
 | 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 |
 
 **Any import not in this table or the Go standard library is forbidden.**

cmd/review-bot/integration_test.go

@@ -130,7 +130,7 @@ func TestIntegration_PostAndCleanup(t *testing.T) {
 	// Post a test review
 	sentinel := "<!-- review-bot:integration-test -->"
 	testBody := "# Integration Test Review\n\nThis is a test review.\n\n" + sentinel
-	posted, err := giteaClient.PostReview(ctx, owner, repoName, prNumber, "COMMENT", testBody, "", nil)
+	posted, err := giteaClient.PostReview(ctx, owner, repoName, prNumber, "COMMENT", testBody, nil)
 	if err != nil {
 		t.Fatalf("PostReview: %v", err)
 	}

cmd/review-bot/main.go

@@ -15,6 +15,7 @@ import (
 	"gitea.weiker.me/rodin/review-bot/gitea"
 	"gitea.weiker.me/rodin/review-bot/llm"
 	"gitea.weiker.me/rodin/review-bot/review"
+	"gitea.weiker.me/rodin/review-bot/vcs"
 )
 
 var version = "dev"
@@ -54,8 +55,8 @@ 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", ""), "Gitea instance URL")
-	repo := flag.String("repo", envOrDefault("GITEA_REPO", ""), "Repository (owner/name)")
+	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)")
 	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")
@@ -65,7 +66,7 @@ func main() {
 	conventionsFile := flag.String("conventions-file", envOrDefault("CONVENTIONS_FILE", ""), "Conventions file path in repo (e.g. CLAUDE.md)")
 	systemPromptFile := flag.String("system-prompt-file", envOrDefault("SYSTEM_PROMPT_FILE", ""), "Local file with additional system prompt instructions")
 	patternsRepo := flag.String("patterns-repo", envOrDefault("PATTERNS_REPO", ""), "Repo with language patterns (e.g. rodin/elixir-patterns)")
-	patternsFiles := flag.String("patterns-files", envOrDefault("PATTERNS_FILES", ""), "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")
 	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)")
@@ -444,7 +445,7 @@ func main() {
 
 	// POST new review
 	slog.Info("posting review", "event", event, "pr", prNumber)
-	posted, err := giteaClient.PostReview(ctx, owner, repoName, prNumber, event, reviewBody, evaluatedSHA, inlineComments)
+	posted, err := giteaClient.PostReview(ctx, owner, repoName, prNumber, event, reviewBody, inlineComments)
 	if err != nil {
 		slog.Error("failed to post review", "pr", prNumber, "event", event, "error", err)
 		os.Exit(1)
@@ -523,25 +524,11 @@ func fetchFileContext(ctx context.Context, client *gitea.Client, owner, repo, re
 // patternsRepo is comma-separated list of owner/name repos.
 // patternsFiles is comma-separated list of file paths or directories.
 // If a path ends with / or is a directory, all files within it are fetched recursively.
-// If patternsFiles is empty, all files from the repo root are fetched.
 func fetchPatterns(ctx context.Context, client *gitea.Client, patternsRepo, patternsFiles string) string {
 	var sb strings.Builder
 
 	repos := strings.Split(patternsRepo, ",")
-
-	// 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)
-			}
-		}
-	}
+	paths := strings.Split(patternsFiles, ",")
 
 	for _, repoRef := range repos {
 		if ctx.Err() != nil {
@@ -562,6 +549,11 @@ func fetchPatterns(ctx context.Context, client *gitea.Client, patternsRepo, patt
 		var repoSkippedFiles []string
 
 		for _, path := range paths {
+			path = strings.TrimSpace(path)
+			if path == "" {
+				continue
+			}
+
 			files, err := client.GetAllFilesInPath(ctx, owner, repo, path)
 			if err != nil {
 				slog.Warn("could not fetch patterns", "path", path, "repo", repoRef, "error", err)
@@ -821,7 +813,7 @@ func shouldSkipStaleReview(evaluatedSHA, currentSHA string) bool {
 	return evaluatedSHA != currentSHA
 }
 
-// giteaClientAdapter adapts gitea.Client to review.GiteaClient interface.
+// giteaClientAdapter adapts gitea.Client to vcs.FileReader interface.
 type giteaClientAdapter struct {
 	client *gitea.Client
 }
@@ -830,14 +822,14 @@ func newGiteaClientAdapter(c *gitea.Client) *giteaClientAdapter {
 	return &giteaClientAdapter{client: c}
 }
 
-func (a *giteaClientAdapter) ListContents(ctx context.Context, owner, repo, path string) ([]review.ContentEntry, error) {
+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([]review.ContentEntry, len(entries))
+	result := make([]vcs.ContentEntry, len(entries))
 	for i, e := range entries {
-		result[i] = review.ContentEntry{
+		result[i] = vcs.ContentEntry{
 			Name: e.Name,
 			Path: e.Path,
 			Type: e.Type,
@@ -846,6 +838,9 @@ func (a *giteaClientAdapter) ListContents(ctx context.Context, owner, repo, path
 	return result, nil
 }
 
-func (a *giteaClientAdapter) GetFileContent(ctx context.Context, owner, repo, filepath string) (string, error) {
-	return a.client.GetFileContent(ctx, owner, repo, filepath)
+func (a *giteaClientAdapter) GetFileContent(ctx context.Context, owner, repo, filePath, ref string) (string, error) {
+	if ref != "" {
+		return a.client.GetFileContentRef(ctx, owner, repo, filePath, ref)
+	}
+	return a.client.GetFileContent(ctx, owner, repo, filePath)
 }

cmd/review-bot/main_test.go

@@ -504,52 +504,6 @@ func TestIsPatternFile(t *testing.T) {
 	}
 }
 
-// TestBuildPatternPaths verifies the path-building logic for fetchPatterns.
-// Empty patternsFiles means "fetch all from root" (represented as [""]).
-func TestBuildPatternPaths(t *testing.T) {
-	buildPaths := func(patternsFiles string) []string {
-		if patternsFiles == "" {
-			return []string{""}
-		}
-		var paths []string
-		for _, p := range strings.Split(patternsFiles, ",") {
-			p = strings.TrimSpace(p)
-			if p != "" {
-				paths = append(paths, p)
-			}
-		}
-		return paths
-	}
-
-	tests := []struct {
-		name  string
-		input string
-		want  []string
-	}{
-		{"empty fetches root", "", []string{""}},
-		{"single file", "README.md", []string{"README.md"}},
-		{"multiple files", "README.md,PATTERNS.md", []string{"README.md", "PATTERNS.md"}},
-		{"trims whitespace", " foo.md , bar.md ", []string{"foo.md", "bar.md"}},
-		{"skips empty between commas", "foo.md,,bar.md", []string{"foo.md", "bar.md"}},
-		{"directory path", "patterns/", []string{"patterns/"}},
-	}
-
-	for _, tc := range tests {
-		t.Run(tc.name, func(t *testing.T) {
-			got := buildPaths(tc.input)
-			if len(got) != len(tc.want) {
-				t.Errorf("buildPaths(%q) = %v, want %v", tc.input, got, tc.want)
-				return
-			}
-			for i := range got {
-				if got[i] != tc.want[i] {
-					t.Errorf("buildPaths(%q)[%d] = %q, want %q", tc.input, i, got[i], tc.want[i])
-				}
-			}
-		})
-	}
-}
-
 func TestEvaluateCIStatus(t *testing.T) {
 	tests := []struct {
 		name       string

docs/DESIGN-57-yaml-persona.md

@@ -9,7 +9,7 @@ JSON is awkward for persona files that contain multi-line text (identity, severi
 - Backwards compatibility: existing JSON personas must continue to work
 - Security: protect against DoS via deeply nested YAML (AIKIDO-2024-10486)
 - Consistency: use `.yaml` extension (not `.yml`)
-- Library: use `github.com/goccy/go-yaml` v1.16.0+ (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
 
@@ -33,16 +33,37 @@ func parsePersona(data []byte, source string) (*Persona, error) {
 
 ### YAML Parsing with Depth Protection
 
-We implement a custom AST-based depth/node-count walk (`checkYAMLDepth` in
-`review/persona.go`) rather than relying on library decoder options. Key design
-decisions:
+```go
+func unmarshalYAMLWithDepthLimit(data []byte, out any, maxDepth int) error {
+    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
-- **Dual-map tracking:** `validated` (depth-aware short-circuit) + `visiting` (cycle detection)
-- **Node-count limit:** Conservative overcounting bounds total validation work
-- **Alias-aware depth:** Aliases increment depth and are re-checked when encountered at greater depths
+func checkYAMLDepth(node *yaml.Node, depth, maxDepth int) error {
+    if depth > maxDepth {
+        return fmt.Errorf("YAML nesting depth exceeds maximum (%d)", maxDepth)
+    }
+    // Handle alias nodes by following the Alias pointer
+    if node.Kind == yaml.AliasNode && node.Alias != nil {
+        return checkYAMLDepth(node.Alias, depth, maxDepth)
+    }
+    for _, child := range node.Content {
+        if err := checkYAMLDepth(child, depth+1, maxDepth); err != nil {
+            return err
+        }
+    }
+    return nil
+}
+```
 
-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
 
@@ -53,7 +74,7 @@ No new state. Same `Persona` struct, just different parsing.
 | Error | Handling |
 |-------|----------|
 | 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 |
 | Missing required fields | Validation rejects after parse |
 

docs/DESIGN-vcs-abstraction.md

@@ -0,0 +1,268 @@
+# 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.

gitea/client.go

@@ -11,7 +11,6 @@ import (
 	"fmt"
 	"io"
 	"log/slog"
-	"math"
 	"net"
 	"net/http"
 	"net/url"
@@ -48,12 +47,6 @@ func IsServerError(err error) bool {
 	return errors.As(err, &apiErr) && apiErr.StatusCode >= 500 && apiErr.StatusCode < 600
 }
 
-// DefaultMaxDiffSize is the default maximum diff size in bytes (10 MB).
-const DefaultMaxDiffSize = 10 * 1024 * 1024
-
-// ErrDiffTooLarge is returned when a PR diff exceeds the configured MaxDiffSize.
-var ErrDiffTooLarge = errors.New("diff size exceeds maximum allowed size")
-
 // Client interacts with the Gitea API.
 // A Client is safe for concurrent use by multiple goroutines.
 type Client struct {
@@ -68,42 +61,6 @@ type Client struct {
 	// This field must be configured before the first request is made.
 	// Modifying it while requests are in flight is not safe.
 	RetryBackoff []time.Duration
-
-	// MaxDiffSize is the maximum number of bytes allowed when fetching a PR diff.
-	// If zero, defaults to DefaultMaxDiffSize (10 MB). Set to any negative value
-	// (or math.MaxInt64) to disable the limit.
-	//
-	// This field must be configured before the first request is made.
-	// Modifying it while requests are in flight is not safe.
-	MaxDiffSize int64
-}
-
-// defaultCheckRedirect is the redirect policy used by NewClient.
-// NOTE: This function is intentionally duplicated in github/client.go (and vice versa)
-// because the packages are separate. Changes here must be mirrored there.
-// It rejects HTTPS->HTTP protocol downgrades (to prevent plaintext leakage)
-// and cross-host redirects (to prevent following responses from untrusted
-// endpoints). Same-host, same-or-upgraded-scheme redirects are allowed.
-func defaultCheckRedirect(req *http.Request, via []*http.Request) error {
-	if len(via) >= 10 {
-		return fmt.Errorf("stopped after 10 redirects")
-	}
-	// Guard for direct invocation in tests and any future callers;
-	// net/http guarantees len(via) >= 1 during actual redirects.
-	if len(via) == 0 {
-		return nil
-	}
-	prev := via[len(via)-1]
-	// Reject protocol downgrade: HTTPS->HTTP leaks request metadata over plaintext.
-	if prev.URL.Scheme == "https" && req.URL.Scheme == "http" {
-		return fmt.Errorf("refusing redirect: HTTPS to HTTP downgrade (%s -> %s)", prev.URL.Host, req.URL.Host)
-	}
-	// Reject cross-host redirect entirely to avoid consuming responses
-	// from untrusted endpoints.
-	if req.URL.Host != prev.URL.Host {
-		return fmt.Errorf("refusing redirect: cross-host (%s -> %s)", prev.URL.Host, req.URL.Host)
-	}
-	return nil
 }
 
 // NewClient creates a new Gitea API client.
@@ -111,30 +68,13 @@ func NewClient(baseURL, token string) *Client {
 	return &Client{
 		baseURL: strings.TrimRight(baseURL, "/"),
 		token:   token,
-		http: &http.Client{
-			Timeout:       30 * time.Second,
-			CheckRedirect: defaultCheckRedirect,
-		},
+		http:    &http.Client{Timeout: 30 * time.Second},
 	}
 }
 
 // SetHTTPClient sets the underlying HTTP client used for requests.
-// This is intended for test setup only to inject mock transports; it must be
-// called before any goroutines issue requests.
-//
-// Passing nil restores the default client (30s timeout + redirect-rejecting
-// CheckRedirect policy matching NewClient).
-//
-// Callers providing a non-nil client are responsible for configuring a safe
-// CheckRedirect policy. Without one, the default net/http behavior will follow
-// redirects and may forward the Authorization header to untrusted hosts.
+// This is intended for testing to inject mock transports.
 func (c *Client) SetHTTPClient(hc *http.Client) {
-	if hc == nil {
-		hc = &http.Client{
-			Timeout:       30 * time.Second,
-			CheckRedirect: defaultCheckRedirect,
-		}
-	}
 	c.http = hc
 }
 
@@ -185,28 +125,9 @@ func (c *Client) GetPullRequest(ctx context.Context, owner, repo string, number
 }
 
 // GetPullRequestDiff fetches the unified diff for a PR.
-// It enforces MaxDiffSize to prevent unbounded memory allocation.
-// Returns ErrDiffTooLarge if the diff exceeds the configured limit.
 func (c *Client) GetPullRequestDiff(ctx context.Context, owner, repo string, number int) (string, error) {
 	reqURL := fmt.Sprintf("%s/api/v1/repos/%s/%s/pulls/%d.diff", c.baseURL, url.PathEscape(owner), url.PathEscape(repo), number)
-
-	maxSize := c.MaxDiffSize
-	if maxSize == 0 {
-		maxSize = DefaultMaxDiffSize
-	}
-
-	// When the limit is disabled (negative) or set to math.MaxInt64 (which
-	// would overflow the +1 detection and silently disable enforcement),
-	// use the standard unlimited doGet path.
-	if maxSize < 0 || maxSize == math.MaxInt64 {
-		body, err := c.doGet(ctx, reqURL)
-		if err != nil {
-			return "", fmt.Errorf("fetch diff: %w", err)
-		}
-		return string(body), nil
-	}
-
-	body, err := c.doGetLimited(ctx, reqURL, maxSize)
+	body, err := c.doGet(ctx, reqURL)
 	if err != nil {
 		return "", fmt.Errorf("fetch diff: %w", err)
 	}
@@ -262,22 +183,18 @@ func (c *Client) GetFileContentRef(ctx context.Context, owner, repo, filepath, r
 }
 
 // PostReview submits a review to a PR and returns the created review.
-// event should be one of "APPROVED", "REQUEST_CHANGES", or "COMMENT".
-// commitID anchors the review to a specific commit SHA. If empty, Gitea
-// defaults to the current PR head.
+// event should be "APPROVED" or "REQUEST_CHANGES".
 // comments are optional inline comments attached to specific lines.
-func (c *Client) PostReview(ctx context.Context, owner, repo string, number int, event, body, commitID string, comments []ReviewComment) (*Review, error) {
+func (c *Client) PostReview(ctx context.Context, owner, repo string, number int, event, body string, comments []ReviewComment) (*Review, error) {
 	reqURL := fmt.Sprintf("%s/api/v1/repos/%s/%s/pulls/%d/reviews", c.baseURL, url.PathEscape(owner), url.PathEscape(repo), number)
 
 	payload := struct {
 		Body     string          `json:"body"`
 		Event    string          `json:"event"`
-		CommitID string          `json:"commit_id,omitempty"`
 		Comments []ReviewComment `json:"comments,omitempty"`
 	}{
 		Body:     body,
 		Event:    event,
-		CommitID: commitID,
 		Comments: comments,
 	}
 
@@ -375,9 +292,9 @@ func isRetriableSyscallError(err error) bool {
 	return true
 }
 
-// redactURL strips query parameters and userinfo credentials from a URL for
-// safe logging. This prevents accidental exposure of sensitive data (tokens in
-// query strings, or user:pass in the authority) in log output.
+// 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 {
@@ -385,9 +302,6 @@ func redactURL(rawURL string) string {
 		// potentially logging something sensitive.
 		return "[invalid URL]"
 	}
-	if parsed.User != nil {
-		parsed.User = url.User("REDACTED")
-	}
 	if parsed.RawQuery != "" {
 		parsed.RawQuery = "[redacted]"
 	}
@@ -408,12 +322,10 @@ func sanitizeErrorForLog(err error) string {
 	return err.Error()
 }
 
-// doGetWithReader 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).
-// The readBody function is called with the response body on success (2xx) and
-// is responsible for reading and closing it.
-func (c *Client) doGetWithReader(ctx context.Context, reqURL string, readBody func(io.ReadCloser) ([]byte, error)) ([]byte, 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.
@@ -478,7 +390,12 @@ func (c *Client) doGetWithReader(ctx context.Context, reqURL string, readBody fu
 			return nil, lastErr
 		}
 		if resp.StatusCode >= 200 && resp.StatusCode < 300 {
-			return readBody(resp.Body)
+			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
@@ -496,39 +413,6 @@ func (c *Client) doGetWithReader(ctx context.Context, reqURL string, readBody fu
 	return nil, lastErr
 }
 
-// doGet performs an HTTP GET request with retry, reading the full response body.
-func (c *Client) doGet(ctx context.Context, reqURL string) ([]byte, error) {
-	return c.doGetWithReader(ctx, reqURL, func(body io.ReadCloser) ([]byte, error) {
-		defer body.Close()
-		return io.ReadAll(body)
-	})
-}
-
-// doGetLimited performs an HTTP GET request with retry but enforces a maximum
-// response body size. Returns ErrDiffTooLarge if the response exceeds maxBytes.
-// It reads maxBytes+1 (clamped to avoid overflow) to detect truncation without
-// buffering the entire body.
-func (c *Client) doGetLimited(ctx context.Context, reqURL string, maxBytes int64) ([]byte, error) {
-	return c.doGetWithReader(ctx, reqURL, func(body io.ReadCloser) ([]byte, error) {
-		defer body.Close()
-		// Read up to maxBytes+1 to detect overflow.
-		// Clamp to prevent integer overflow when maxBytes == math.MaxInt64.
-		limitBytes := maxBytes + 1
-		if limitBytes <= 0 {
-			limitBytes = math.MaxInt64
-		}
-		limited := io.LimitReader(body, limitBytes)
-		data, err := io.ReadAll(limited)
-		if err != nil {
-			return nil, err
-		}
-		if int64(len(data)) > maxBytes {
-			return nil, fmt.Errorf("%w: response exceeds %d bytes", ErrDiffTooLarge, maxBytes)
-		}
-		return data, nil
-	})
-}
-
 // escapePath escapes each segment of a relative file path for use in URLs.
 // Slashes are preserved as path separators; other special characters are escaped.
 // Input should be a relative path (no leading slash). Already-encoded segments
@@ -947,3 +831,15 @@ func (c *Client) ResolveComment(ctx context.Context, owner, repo string, comment
 	}
 	return nil
 }
+
+// DismissReview dismisses a review on a pull request.
+// This is a stub for the vcs.Reviewer interface; full implementation is Phase 2.
+func (c *Client) DismissReview(ctx context.Context, owner, repo string, number int, reviewID int64, message string) error {
+	return fmt.Errorf("dismiss review %d on %s/%s#%d: %w", reviewID, owner, repo, number, errors.ErrUnsupported)
+}
+
+// GetFileContentAtRef fetches a file at a specific ref from a repo.
+// This delegates to GetFileContentRef for the Gitea implementation.
+func (c *Client) GetFileContentAtRef(ctx context.Context, owner, repo, path, ref string) (string, error) {
+	return c.GetFileContentRef(ctx, owner, repo, path, ref)
+}

gitea/client_test.go

@@ -9,7 +9,6 @@ import (
 	"net"
 	"net/http"
 	"net/http/httptest"
-	"net/url"
 	"strings"
 	"sync/atomic"
 	"syscall"
@@ -117,9 +116,8 @@ func TestPostReview(t *testing.T) {
 		}
 
 		var payload struct {
-			Body     string `json:"body"`
-			Event    string `json:"event"`
-			CommitID string `json:"commit_id"`
+			Body  string `json:"body"`
+			Event string `json:"event"`
 		}
 		if err := json.NewDecoder(r.Body).Decode(&payload); err != nil {
 			t.Fatalf("failed to decode payload: %v", err)
@@ -130,16 +128,14 @@ func TestPostReview(t *testing.T) {
 		if payload.Event != "APPROVED" {
 			t.Errorf("expected event %q, got %q", "APPROVED", payload.Event)
 		}
-		if payload.CommitID != "abc123def" {
-			t.Errorf("expected commit_id %q, got %q", "abc123def", payload.CommitID)
-		}
+
 		w.WriteHeader(http.StatusOK)
 		w.Write([]byte(`{"id":100,"user":{"login":"review-bot"},"state":"APPROVED","stale":false}`))
 	}))
 	defer server.Close()
 
 	client := NewClient(server.URL, "test-token")
-	review, err := client.PostReview(context.Background(), "owner", "repo", 3, "APPROVED", "LGTM", "abc123def", nil)
+	review, err := client.PostReview(context.Background(), "owner", "repo", 3, "APPROVED", "LGTM", nil)
 	if err != nil {
 		t.Fatalf("unexpected error: %v", err)
 	}
@@ -186,35 +182,12 @@ func TestPostReview_Non200(t *testing.T) {
 	defer server.Close()
 
 	client := NewClient(server.URL, "test-token")
-	_, err := client.PostReview(context.Background(), "owner", "repo", 1, "APPROVED", "test", "", nil)
+	_, err := client.PostReview(context.Background(), "owner", "repo", 1, "APPROVED", "test", nil)
 	if err == nil {
 		t.Fatal("expected error for 403, got nil")
 	}
 }
 
-func TestPostReview_EmptyCommitID_OmittedFromPayload(t *testing.T) {
-	server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
-		body, _ := io.ReadAll(r.Body)
-		var raw map[string]interface{}
-		if err := json.Unmarshal(body, &raw); err != nil {
-			t.Fatalf("failed to decode payload: %v", err)
-		}
-		if _, exists := raw["commit_id"]; exists {
-			t.Errorf("expected commit_id to be omitted from payload when empty, but it was present")
-		}
-
-		w.WriteHeader(http.StatusOK)
-		w.Write([]byte(`{"id":200,"user":{"login":"bot"},"state":"APPROVED","stale":false}`))
-	}))
-	defer server.Close()
-
-	client := NewClient(server.URL, "test-token")
-	_, err := client.PostReview(context.Background(), "owner", "repo", 1, "APPROVED", "ok", "", nil)
-	if err != nil {
-		t.Fatalf("unexpected error: %v", err)
-	}
-}
-
 func TestGetFileContent(t *testing.T) {
 	expected := "# Conventions\n- Be nice\n"
 
@@ -971,6 +944,8 @@ func TestDoGet_RespectsContextCancellation(t *testing.T) {
 		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 {
@@ -1117,21 +1092,6 @@ func TestRedactURL(t *testing.T) {
 			input: "",
 			want:  "",
 		},
-		{
-			name:  "with userinfo - redacts credentials",
-			input: "https://admin:secret@gitea.example.com/api/v1/repos",
-			want:  "https://REDACTED@gitea.example.com/api/v1/repos",
-		},
-		{
-			name:  "with userinfo and query params",
-			input: "https://user:pass@example.com/path?token=abc",
-			want:  "https://REDACTED@example.com/path?[redacted]",
-		},
-		{
-			name:  "username only - no password",
-			input: "https://user@example.com/path",
-			want:  "https://REDACTED@example.com/path",
-		},
 	}
 	for _, tt := range tests {
 		t.Run(tt.name, func(t *testing.T) {
@@ -1184,104 +1144,3 @@ func TestSanitizeErrorForLog(t *testing.T) {
 		})
 	}
 }
-
-func TestNewClient_HasCheckRedirect(t *testing.T) {
-	c := NewClient("https://gitea.example.com", "token")
-	if c.http.CheckRedirect == nil {
-		t.Fatal("expected CheckRedirect to be set")
-	}
-}
-
-func TestDefaultCheckRedirect_RejectsHTTPSToHTTP(t *testing.T) {
-	prev := &http.Request{URL: &url.URL{Scheme: "https", Host: "gitea.example.com", Path: "/foo"}}
-	req := &http.Request{
-		URL:    &url.URL{Scheme: "http", Host: "gitea.example.com", Path: "/foo"},
-		Header: http.Header{"Authorization": []string{"token abc"}},
-	}
-	err := defaultCheckRedirect(req, []*http.Request{prev})
-	if err == nil {
-		t.Fatal("expected error on HTTPS->HTTP redirect")
-	}
-	if !strings.Contains(err.Error(), "HTTPS to HTTP downgrade") {
-		t.Errorf("unexpected error message: %v", err)
-	}
-}
-
-func TestDefaultCheckRedirect_RejectsCrossHost(t *testing.T) {
-	prev := &http.Request{URL: &url.URL{Scheme: "https", Host: "gitea.example.com", Path: "/foo"}}
-	req := &http.Request{
-		URL:    &url.URL{Scheme: "https", Host: "cdn.example.com", Path: "/bar"},
-		Header: http.Header{"Authorization": []string{"token abc"}},
-	}
-	err := defaultCheckRedirect(req, []*http.Request{prev})
-	if err == nil {
-		t.Fatal("expected error on cross-host redirect")
-	}
-	if !strings.Contains(err.Error(), "cross-host") {
-		t.Errorf("unexpected error message: %v", err)
-	}
-}
-
-func TestDefaultCheckRedirect_AllowsSameHost(t *testing.T) {
-	prev := &http.Request{URL: &url.URL{Scheme: "https", Host: "gitea.example.com", Path: "/foo"}}
-	req := &http.Request{
-		URL:    &url.URL{Scheme: "https", Host: "gitea.example.com", Path: "/bar"},
-		Header: http.Header{"Authorization": []string{"token abc"}},
-	}
-	err := defaultCheckRedirect(req, []*http.Request{prev})
-	if err != nil {
-		t.Fatalf("unexpected error: %v", err)
-	}
-	if auth := req.Header.Get("Authorization"); auth != "token abc" {
-		t.Errorf("expected Authorization to be preserved, got %q", auth)
-	}
-}
-
-func TestDefaultCheckRedirect_AllowsSameHostHTTPToHTTP(t *testing.T) {
-	prev := &http.Request{URL: &url.URL{Scheme: "http", Host: "localhost:3000", Path: "/foo"}}
-	req := &http.Request{
-		URL:    &url.URL{Scheme: "http", Host: "localhost:3000", Path: "/bar"},
-		Header: http.Header{},
-	}
-	err := defaultCheckRedirect(req, []*http.Request{prev})
-	if err != nil {
-		t.Fatalf("unexpected error: %v", err)
-	}
-}
-
-func TestDefaultCheckRedirect_RejectsTooManyRedirects(t *testing.T) {
-	via := make([]*http.Request, 10)
-	for i := range via {
-		via[i] = &http.Request{URL: &url.URL{Scheme: "https", Host: "gitea.example.com", Path: "/"}}
-	}
-	req := &http.Request{URL: &url.URL{Scheme: "https", Host: "gitea.example.com", Path: "/final"}}
-	err := defaultCheckRedirect(req, via)
-	if err == nil {
-		t.Fatal("expected error after 10 redirects")
-	}
-	if !strings.Contains(err.Error(), "10 redirects") {
-		t.Errorf("unexpected error message: %v", err)
-	}
-}
-
-func TestDefaultCheckRedirect_EmptyViaAllowed(t *testing.T) {
-	req := &http.Request{URL: &url.URL{Scheme: "https", Host: "gitea.example.com", Path: "/foo"}}
-	err := defaultCheckRedirect(req, nil)
-	if err != nil {
-		t.Fatalf("unexpected error with empty via: %v", err)
-	}
-}
-
-func TestSetHTTPClient_NilRestoresDefault(t *testing.T) {
-	c := NewClient("https://gitea.example.com", "token")
-	c.SetHTTPClient(nil)
-	if c.http == nil {
-		t.Fatal("expected non-nil http client after SetHTTPClient(nil)")
-	}
-	if c.http.Timeout != 30*time.Second {
-		t.Errorf("expected 30s timeout, got %v", c.http.Timeout)
-	}
-	if c.http.CheckRedirect == nil {
-		t.Fatal("expected CheckRedirect policy after SetHTTPClient(nil)")
-	}
-}

gitea/conformance_test.go

@@ -0,0 +1,25 @@
+//go:build phase2
+
+package gitea_test
+
+import (
+	"gitea.weiker.me/rodin/review-bot/gitea"
+	"gitea.weiker.me/rodin/review-bot/vcs"
+)
+
+// Compile-time interface conformance assertions.
+// These will verify gitea.Client satisfies vcs interfaces once the Phase 2
+// adapter bridges the method signature gaps:
+//
+//   - PRReader: GetPullRequest returns *gitea.PullRequest (needs *vcs.PullRequest)
+//   - PRReader: GetPullRequestFiles returns []gitea.ChangedFile (needs []vcs.ChangedFile)
+//   - FileReader: GetFileContent lacks ref parameter
+//   - Reviewer: PostReview uses (event, body, comments) instead of vcs.ReviewRequest
+//
+// Remove the phase2 build tag once the adapter is complete.
+var (
+	_ vcs.PRReader   = (*gitea.Client)(nil)
+	_ vcs.FileReader = (*gitea.Client)(nil)
+	_ vcs.Reviewer   = (*gitea.Client)(nil)
+	_ vcs.Identity   = (*gitea.Client)(nil)
+)

gitea/diff_size_test.go

@@ -1,97 +0,0 @@
-package gitea
-
-import (
-	"context"
-	"errors"
-	"math"
-	"net/http"
-	"net/http/httptest"
-	"strings"
-	"testing"
-	"time"
-)
-
-func TestGetPullRequestDiff_SizeLimits(t *testing.T) {
-	tests := []struct {
-		name        string
-		diff        string
-		maxDiffSize int64
-		wantErr     error
-		wantDiff    string
-	}{
-		{
-			name:        "exceeds max size",
-			diff:        strings.Repeat("+ added line\n", 1000), // ~13 KB
-			maxDiffSize: 100,
-			wantErr:     ErrDiffTooLarge,
-		},
-		{
-			name:        "within max size",
-			diff:        "diff --git a/f.go b/f.go\n--- a/f.go\n+++ b/f.go\n@@ -1 +1 @@\n-old\n+new\n",
-			maxDiffSize: 1024,
-			wantDiff:    "diff --git a/f.go b/f.go\n--- a/f.go\n+++ b/f.go\n@@ -1 +1 @@\n-old\n+new\n",
-		},
-		{
-			name:        "exactly at limit",
-			diff:        strings.Repeat("x", 50),
-			maxDiffSize: 50,
-			wantDiff:    strings.Repeat("x", 50),
-		},
-		{
-			name:        "one byte over limit",
-			diff:        strings.Repeat("x", 51),
-			maxDiffSize: 50,
-			wantErr:     ErrDiffTooLarge,
-		},
-		{
-			name:        "disabled limit",
-			diff:        strings.Repeat("x", 10000),
-			maxDiffSize: -1,
-			wantDiff:    strings.Repeat("x", 10000),
-		},
-		{
-			name:        "math.MaxInt64 treated as disabled",
-			diff:        strings.Repeat("x", 10000),
-			maxDiffSize: math.MaxInt64,
-			wantDiff:    strings.Repeat("x", 10000),
-		},
-		{
-			name:        "default limit",
-			diff:        "diff content",
-			maxDiffSize: 0, // zero means use DefaultMaxDiffSize
-			wantDiff:    "diff content",
-		},
-	}
-
-	for _, tt := range tests {
-		t.Run(tt.name, func(t *testing.T) {
-			server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
-				w.Write([]byte(tt.diff)) //nolint:errcheck // test handler
-			}))
-			defer server.Close()
-
-			client := NewClient(server.URL, "test-token")
-			client.MaxDiffSize = tt.maxDiffSize
-			client.RetryBackoff = []time.Duration{}
-
-			got, err := client.GetPullRequestDiff(context.Background(), "owner", "repo", 1)
-
-			if tt.wantErr != nil {
-				if err == nil {
-					t.Fatal("expected error, got nil")
-				}
-				if !errors.Is(err, tt.wantErr) {
-					t.Errorf("expected %v, got: %v", tt.wantErr, err)
-				}
-				return
-			}
-
-			if err != nil {
-				t.Fatalf("unexpected error: %v", err)
-			}
-			if got != tt.wantDiff {
-				t.Errorf("diff mismatch: got length %d, want length %d", len(got), len(tt.wantDiff))
-			}
-		})
-	}
-}

gitea/post_review_comments_test.go

@@ -37,7 +37,7 @@ func TestPostReview_WithComments(t *testing.T) {
 		{Path: "util.go", NewPosition: 10, Body: "[MINOR] Style issue"},
 	}
 
-	_, err := client.PostReview(context.Background(), "owner", "repo", 1, "REQUEST_CHANGES", "summary", "", comments)
+	_, err := client.PostReview(context.Background(), "owner", "repo", 1, "REQUEST_CHANGES", "summary", comments)
 	if err != nil {
 		t.Fatalf("unexpected error: %v", err)
 	}
@@ -72,7 +72,7 @@ func TestPostReview_NilComments(t *testing.T) {
 	defer server.Close()
 
 	client := NewClient(server.URL, "test-token")
-	_, err := client.PostReview(context.Background(), "owner", "repo", 1, "APPROVED", "all good", "", nil)
+	_, err := client.PostReview(context.Background(), "owner", "repo", 1, "APPROVED", "all good", nil)
 	if err != nil {
 		t.Fatalf("unexpected error: %v", err)
 	}

github/client.go

@@ -14,33 +14,11 @@ import (
 	"time"
 )
 
-const (
-	defaultBaseURL = "https://api.github.com"
-
-	// maxRetryAttempts is the number of times doRequest will attempt a request.
-	maxRetryAttempts = 3
-
-	// maxRetryAfter caps the maximum delay from a Retry-After header to prevent
-	// a server from stalling the client indefinitely.
-	maxRetryAfter = 60 * time.Second
-
-	// maxErrorBodyBytes limits how much of an error response body we read
-	// to protect against malicious servers sending unbounded data.
-	maxErrorBodyBytes = 64 * 1024 // 64 KB
-
-	// maxResponseBodyBytes limits how much of a successful response body we read
-	// for defense-in-depth against servers returning excessively large payloads.
-	maxResponseBodyBytes = 10 * 1024 * 1024 // 10 MB
-)
+const defaultBaseURL = "https://api.github.com"
 
 // APIError represents an HTTP error response from the GitHub API.
 // It carries the status code so callers can distinguish between
 // different failure modes (e.g. 404 vs 500).
-//
-// The Body field stores up to 64 KiB of the raw response for programmatic
-// inspection. Error() truncates to 200 bytes for safe logging, but callers
-// should avoid logging or propagating Body directly in production since it may
-// contain sensitive details from the upstream server.
 type APIError struct {
 	StatusCode int
 	Body       string
@@ -51,9 +29,6 @@ func (e *APIError) Error() string {
 	if len(body) > 200 {
 		body = body[:200] + "...(truncated)"
 	}
-	// Sanitize newlines to prevent log injection from upstream response bodies.
-	body = strings.ReplaceAll(body, "\n", " ")
-	body = strings.ReplaceAll(body, "\r", " ")
 	return fmt.Sprintf("HTTP %d: %s", e.StatusCode, body)
 }
 
@@ -86,53 +61,15 @@ func asAPIError(err error) (*APIError, bool) {
 
 // Client interacts with the GitHub API.
 // A Client is safe for concurrent use by multiple goroutines.
-// SetHTTPClient and SetRetryBackoff are intended for test setup only and must
-// be called before any goroutines issue requests; they have no synchronization.
 type Client struct {
-	// TODO: baseURL is populated by NewClient but not yet consumed by doRequest/doGet.
-	// Higher-level exported methods (GetPullRequest, etc.) will use it to
-	// construct request URLs; remove this field if those methods end up
-	// accepting full URLs instead.
 	baseURL string
 	token   string
-	httpClient *http.Client
+	http    *http.Client
 
-	// retryBackoff defines the delays between retry attempts for 429 responses.
-	// retryBackoff[i] is the delay before attempt i+1 (after attempt i fails).
-	// If nil, defaults to {1s, 2s}.
-	retryBackoff []time.Duration
-
-	// now returns the current time. Defaults to time.Now.
-	// Override in tests to control HTTP-date Retry-After calculations.
-	now func() time.Time
-}
-
-// defaultCheckRedirect is the redirect policy used by NewClient.
-// NOTE: This function is intentionally duplicated in gitea/client.go (and vice versa)
-// because the packages are separate. Changes here must be mirrored there.
-// It rejects HTTPS->HTTP protocol downgrades (to prevent plaintext leakage)
-// and cross-host redirects (to prevent following responses from untrusted
-// endpoints). Same-host, same-or-upgraded-scheme redirects are allowed.
-func defaultCheckRedirect(req *http.Request, via []*http.Request) error {
-	if len(via) >= 10 {
-		return fmt.Errorf("stopped after 10 redirects")
-	}
-	// Guard for direct invocation in tests and any future callers;
-	// net/http guarantees len(via) >= 1 during actual redirects.
-	if len(via) == 0 {
-		return nil
-	}
-	prev := via[len(via)-1]
-	// Reject protocol downgrade: HTTPS->HTTP leaks request metadata over plaintext.
-	if prev.URL.Scheme == "https" && req.URL.Scheme == "http" {
-		return fmt.Errorf("refusing redirect: HTTPS to HTTP downgrade (%s -> %s)", prev.URL.Host, req.URL.Host)
-	}
-	// Reject cross-host redirect entirely to avoid consuming responses
-	// from untrusted endpoints.
-	if req.URL.Host != prev.URL.Host {
-		return fmt.Errorf("refusing redirect: cross-host (%s -> %s)", prev.URL.Host, req.URL.Host)
-	}
-	return nil
+	// RetryBackoff defines the delays between retry attempts for 429 responses.
+	// 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.
+	RetryBackoff []time.Duration
 }
 
 // NewClient creates a new GitHub API client.
@@ -145,89 +82,29 @@ func NewClient(token, baseURL string) *Client {
 	return &Client{
 		baseURL: strings.TrimRight(baseURL, "/"),
 		token:   token,
-		httpClient: &http.Client{
-			Timeout:       30 * time.Second,
-			CheckRedirect: defaultCheckRedirect,
-		},
-		now: time.Now,
+		http:    &http.Client{Timeout: 30 * time.Second},
 	}
 }
 
 // SetHTTPClient sets the underlying HTTP client used for requests.
-// This is intended for test setup only to inject mock transports; it must be
-// called before any goroutines issue requests.
-//
-// Passing nil restores the default client (30s timeout + redirect-rejecting
-// CheckRedirect policy matching NewClient).
-//
-// Callers providing a non-nil client are responsible for configuring a safe
-// CheckRedirect policy. Without one, the default net/http behavior will follow
-// redirects and may forward the Authorization header to untrusted hosts.
+// This is intended for testing to inject mock transports.
 func (c *Client) SetHTTPClient(hc *http.Client) {
-	if hc == nil {
-		hc = &http.Client{
-			Timeout:       30 * time.Second,
-			CheckRedirect: defaultCheckRedirect,
-		}
-	}
-	c.httpClient = hc
-}
-
-// SetRetryBackoff sets the delays between retry attempts.
-// This is intended for testing to speed up retry tests.
-//
-// Note: if an empty non-nil slice is provided, Retry-After delays parsed from
-// server responses will be computed and capped but not applied (because
-// attempt < len(backoff) is always false). This is acceptable for the
-// test-only use case but callers should be aware of this edge case.
-func (c *Client) SetRetryBackoff(backoff []time.Duration) {
-	c.retryBackoff = backoff
-}
-
-// parseRetryAfter parses a Retry-After header value, supporting both integer
-// seconds (e.g. "120") and HTTP-date format (e.g. "Thu, 01 Dec 2025 16:00:00 GMT")
-// as specified in RFC 7231 §7.1.3.
-//
-// For integer values, it returns the duration directly.
-// For HTTP-date values, it computes the delay as the difference between the
-// parsed time and now. If the date is in the past, it returns 0.
-//
-// Returns (0, false) if the value cannot be parsed as either format.
-func (c *Client) parseRetryAfter(value string) (time.Duration, bool) {
-	value = strings.TrimSpace(value)
-
-	// Try integer seconds first (most common from GitHub).
-	// RFC 7231 allows delta-seconds of 0 to indicate immediate retry.
-	if seconds, err := strconv.Atoi(value); err == nil && seconds >= 0 {
-		return time.Duration(seconds) * time.Second, true
-	}
-
-	// Try HTTP-date format (RFC 7231 §7.1.3).
-	// http.ParseTime handles RFC 1123, RFC 850, and ASCTIME formats.
-	if retryAt, err := http.ParseTime(value); err == nil {
-		delay := retryAt.Sub(c.now())
-		if delay < 0 {
-			delay = 0
-		}
-		return delay, true
-	}
-
-	return 0, false
+	c.http = hc
 }
 
 // doRequest performs an HTTP request with retry on 429 rate limit responses.
-// It respects the Retry-After header when present, supporting both integer
-// seconds and HTTP-date formats (capped at maxRetryAfter).
-func (c *Client) doRequest(ctx context.Context, method, reqURL string, accept string) ([]byte, error) {
-	var backoff []time.Duration
-	if c.retryBackoff != nil {
-		backoff = append([]time.Duration(nil), c.retryBackoff...)
-	} else {
+// It respects the Retry-After header when present.
+func (c *Client) doRequest(ctx context.Context, method, url string, accept string) ([]byte, error) {
+	const maxAttempts = 3
+	backoff := c.RetryBackoff
+	if backoff == nil {
 		backoff = []time.Duration{1 * time.Second, 2 * time.Second}
 	}
 
+	const maxErrorBodyBytes = 64 * 1024
+
 	var lastErr error
-	for attempt := 0; attempt < maxRetryAttempts; attempt++ {
+	for attempt := 0; attempt < maxAttempts; attempt++ {
 		if attempt > 0 {
 			var delay time.Duration
 			if attempt-1 < len(backoff) {
@@ -237,7 +114,6 @@ func (c *Client) doRequest(ctx context.Context, method, reqURL string, accept st
 				timer := time.NewTimer(delay)
 				select {
 				case <-timer.C:
-					timer.Stop()
 				case <-ctx.Done():
 					timer.Stop()
 					return nil, ctx.Err()
@@ -245,7 +121,7 @@ func (c *Client) doRequest(ctx context.Context, method, reqURL string, accept st
 			}
 		}
 
-		req, err := http.NewRequestWithContext(ctx, method, reqURL, nil)
+		req, err := http.NewRequestWithContext(ctx, method, url, nil)
 		if err != nil {
 			return nil, fmt.Errorf("create request: %w", err)
 		}
@@ -256,13 +132,13 @@ func (c *Client) doRequest(ctx context.Context, method, reqURL string, accept st
 			req.Header.Set("Accept", "application/vnd.github+json")
 		}
 
-		resp, err := c.httpClient.Do(req)
+		resp, err := c.http.Do(req)
 		if err != nil {
 			return nil, fmt.Errorf("do request: %w", err)
 		}
 
 		if resp.StatusCode >= 200 && resp.StatusCode < 300 {
-			body, err := io.ReadAll(io.LimitReader(resp.Body, maxResponseBodyBytes))
+			body, err := io.ReadAll(resp.Body)
 			resp.Body.Close()
 			if err != nil {
 				return nil, fmt.Errorf("read response body: %w", err)
@@ -276,16 +152,12 @@ func (c *Client) doRequest(ctx context.Context, method, reqURL string, accept st
 		lastErr = &APIError{StatusCode: resp.StatusCode, Body: string(errBody)}
 
 		// Retry on 429 rate limit
-		if resp.StatusCode == http.StatusTooManyRequests && attempt < maxRetryAttempts-1 {
-			// Check for Retry-After header and override backoff if present.
-			// Supports both integer seconds (common) and HTTP-date format (RFC 7231).
+		if resp.StatusCode == http.StatusTooManyRequests && attempt < maxAttempts-1 {
+			// Check for Retry-After header and override backoff if present
 			if ra := resp.Header.Get("Retry-After"); ra != "" {
-				if delay, ok := c.parseRetryAfter(ra); ok {
-					if delay > maxRetryAfter {
-						delay = maxRetryAfter
-					}
+				if seconds, err := strconv.Atoi(ra); err == nil && seconds > 0 {
 					if attempt < len(backoff) {
-						backoff[attempt] = delay
+						backoff[attempt] = time.Duration(seconds) * time.Second
 					}
 				}
 			}

github/client_test.go

@@ -2,512 +2,223 @@ package github
 
 import (
 	"context"
-	"errors"
 	"net/http"
 	"net/http/httptest"
-	"net/url"
-	"strings"
 	"testing"
 	"time"
 )
 
 func TestNewClient_DefaultBaseURL(t *testing.T) {
-	c := NewClient("tok", "")
-	if c.baseURL != defaultBaseURL {
-		t.Errorf("baseURL = %q, want %q", c.baseURL, defaultBaseURL)
+	c := NewClient("test-token", "")
+	if c.baseURL != "https://api.github.com" {
+		t.Errorf("expected default base URL, got %q", c.baseURL)
 	}
 }
 
 func TestNewClient_CustomBaseURL(t *testing.T) {
-	c := NewClient("tok", "https://github.concur.com/api/v3/")
+	c := NewClient("test-token", "https://github.concur.com/api/v3")
 	if c.baseURL != "https://github.concur.com/api/v3" {
-		t.Errorf("baseURL = %q, want trailing slash stripped", c.baseURL)
+		t.Errorf("expected custom base URL, got %q", c.baseURL)
 	}
 }
 
-func TestDoRequest_Success(t *testing.T) {
+func TestNewClient_TrimsTrailingSlash(t *testing.T) {
+	c := NewClient("test-token", "https://github.concur.com/api/v3/")
+	if c.baseURL != "https://github.concur.com/api/v3" {
+		t.Errorf("expected trailing slash trimmed, got %q", c.baseURL)
+	}
+}
+
+func TestDoRequest_SetsAuthHeader(t *testing.T) {
+	var gotAuth string
 	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
-		if got := r.Header.Get("Authorization"); got != "Bearer test-token" {
-			t.Errorf("Authorization = %q, want Bearer test-token", got)
+		gotAuth = r.Header.Get("Authorization")
+		w.WriteHeader(200)
+		w.Write([]byte("{}"))
+	}))
+	defer srv.Close()
+
+	c := NewClient("my-token", srv.URL)
+	c.SetHTTPClient(srv.Client())
+	_, _ = c.doGet(context.Background(), srv.URL+"/test")
+
+	if gotAuth != "Bearer my-token" {
+		t.Errorf("expected Bearer auth, got %q", gotAuth)
+	}
+}
+
+func TestDoRequest_SetsDefaultAcceptHeader(t *testing.T) {
+	var gotAccept string
+	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		gotAccept = r.Header.Get("Accept")
+		w.WriteHeader(200)
+		w.Write([]byte("{}"))
+	}))
+	defer srv.Close()
+
+	c := NewClient("token", srv.URL)
+	c.SetHTTPClient(srv.Client())
+	_, _ = c.doGet(context.Background(), srv.URL+"/test")
+
+	if gotAccept != "application/vnd.github+json" {
+		t.Errorf("expected default Accept header, got %q", gotAccept)
+	}
+}
+
+func TestDoRequest_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
 		}
-		w.WriteHeader(http.StatusOK)
+		w.WriteHeader(200)
 		w.Write([]byte(`{"ok":true}`))
 	}))
 	defer srv.Close()
 
-	c := NewClient("test-token", srv.URL)
+	c := NewClient("token", srv.URL)
+	c.SetHTTPClient(srv.Client())
+	c.RetryBackoff = []time.Duration{10 * time.Millisecond, 10 * time.Millisecond}
+
 	body, err := c.doGet(context.Background(), srv.URL+"/test")
 	if err != nil {
 		t.Fatalf("unexpected error: %v", err)
 	}
 	if string(body) != `{"ok":true}` {
-		t.Errorf("body = %q, want %q", body, `{"ok":true}`)
-	}
-}
-
-func TestDoRequest_429_RetryAfter_IntegerSeconds(t *testing.T) {
-	attempts := 0
-	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
-		attempts++
-		if attempts == 1 {
-			w.Header().Set("Retry-After", "0")
-			w.WriteHeader(http.StatusTooManyRequests)
-			w.Write([]byte("rate limited"))
-			return
-		}
-		w.WriteHeader(http.StatusOK)
-		w.Write([]byte("success"))
-	}))
-	defer srv.Close()
-
-	c := NewClient("tok", srv.URL)
-	c.SetRetryBackoff([]time.Duration{0, 0})
-
-	body, err := c.doGet(context.Background(), srv.URL+"/test")
-	if err != nil {
-		t.Fatalf("unexpected error: %v", err)
-	}
-	if string(body) != "success" {
-		t.Errorf("body = %q, want %q", body, "success")
+		t.Errorf("unexpected body: %s", body)
 	}
 	if attempts != 2 {
-		t.Errorf("attempts = %d, want 2", attempts)
+		t.Errorf("expected 2 attempts, got %d", attempts)
 	}
 }
 
-func TestDoRequest_429_RetryAfter_HTTPDate(t *testing.T) {
-	// Fix "now" to a known time for deterministic testing.
-	fixedNow := time.Date(2025, 12, 1, 15, 59, 59, 0, time.UTC)
-	retryAt := "Mon, 01 Dec 2025 16:00:00 GMT" // 1 second in the future
-
+func TestDoRequest_429ExhaustsRetries(t *testing.T) {
 	attempts := 0
 	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
 		attempts++
-		if attempts == 1 {
-			w.Header().Set("Retry-After", retryAt)
-			w.WriteHeader(http.StatusTooManyRequests)
-			w.Write([]byte("rate limited"))
-			return
-		}
-		w.WriteHeader(http.StatusOK)
-		w.Write([]byte("success"))
+		w.WriteHeader(429)
+		w.Write([]byte(`{"message":"rate limit"}`))
 	}))
 	defer srv.Close()
 
-	c := NewClient("tok", srv.URL)
-	c.now = func() time.Time { return fixedNow }
-	// Initial backoff is 0; the HTTP-date parser will compute 1s and override.
-	c.SetRetryBackoff([]time.Duration{0, 0})
+	c := NewClient("token", srv.URL)
+	c.SetHTTPClient(srv.Client())
+	c.RetryBackoff = []time.Duration{1 * time.Millisecond, 1 * time.Millisecond}
 
-	body, err := c.doGet(context.Background(), srv.URL+"/test")
-	if err != nil {
-		t.Fatalf("unexpected error: %v", err)
-	}
-	if string(body) != "success" {
-		t.Errorf("body = %q, want %q", body, "success")
-	}
-	if attempts != 2 {
-		t.Errorf("attempts = %d, want 2", attempts)
-	}
-}
-
-func TestDoRequest_429_RetryAfter_HTTPDate_InPast(t *testing.T) {
-	// If the HTTP-date is in the past, delay should be 0 (retry immediately).
-	fixedNow := time.Date(2025, 12, 1, 17, 0, 0, 0, time.UTC)
-	retryAt := "Mon, 01 Dec 2025 16:00:00 GMT" // 1 hour in the past
-
-	attempts := 0
-	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
-		attempts++
-		if attempts == 1 {
-			w.Header().Set("Retry-After", retryAt)
-			w.WriteHeader(http.StatusTooManyRequests)
-			w.Write([]byte("rate limited"))
-			return
-		}
-		w.WriteHeader(http.StatusOK)
-		w.Write([]byte("success"))
-	}))
-	defer srv.Close()
-
-	c := NewClient("tok", srv.URL)
-	c.now = func() time.Time { return fixedNow }
-	c.SetRetryBackoff([]time.Duration{0, 0})
-
-	body, err := c.doGet(context.Background(), srv.URL+"/test")
-	if err != nil {
-		t.Fatalf("unexpected error: %v", err)
-	}
-	if string(body) != "success" {
-		t.Errorf("body = %q, want %q", body, "success")
-	}
-}
-
-func TestDoRequest_429_NoRetryAfter_UsesDefaultBackoff(t *testing.T) {
-	attempts := 0
-	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
-		attempts++
-		if attempts == 1 {
-			w.WriteHeader(http.StatusTooManyRequests)
-			w.Write([]byte("rate limited"))
-			return
-		}
-		w.WriteHeader(http.StatusOK)
-		w.Write([]byte("success"))
-	}))
-	defer srv.Close()
-
-	c := NewClient("tok", srv.URL)
-	c.SetRetryBackoff([]time.Duration{0, 0})
-
-	body, err := c.doGet(context.Background(), srv.URL+"/test")
-	if err != nil {
-		t.Fatalf("unexpected error: %v", err)
-	}
-	if string(body) != "success" {
-		t.Errorf("body = %q, want %q", body, "success")
-	}
-	if attempts != 2 {
-		t.Errorf("attempts = %d, want 2", attempts)
-	}
-}
-
-func TestDoRequest_429_InvalidRetryAfter_UsesDefaultBackoff(t *testing.T) {
-	attempts := 0
-	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
-		attempts++
-		if attempts == 1 {
-			w.Header().Set("Retry-After", "not-a-number-or-date")
-			w.WriteHeader(http.StatusTooManyRequests)
-			w.Write([]byte("rate limited"))
-			return
-		}
-		w.WriteHeader(http.StatusOK)
-		w.Write([]byte("success"))
-	}))
-	defer srv.Close()
-
-	c := NewClient("tok", srv.URL)
-	c.SetRetryBackoff([]time.Duration{0, 0})
-
-	body, err := c.doGet(context.Background(), srv.URL+"/test")
-	if err != nil {
-		t.Fatalf("unexpected error: %v", err)
-	}
-	if string(body) != "success" {
-		t.Errorf("body = %q, want %q", body, "success")
-	}
-}
-
-func TestDoRequest_404_NoRetry(t *testing.T) {
-	attempts := 0
-	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
-		attempts++
-		w.WriteHeader(http.StatusNotFound)
-		w.Write([]byte("not found"))
-	}))
-	defer srv.Close()
-
-	c := NewClient("tok", srv.URL)
 	_, err := c.doGet(context.Background(), srv.URL+"/test")
 	if err == nil {
-		t.Fatal("expected error, got nil")
+		t.Fatal("expected error after exhausting retries")
 	}
+	apiErr, ok := err.(*APIError)
+	if !ok {
+		t.Fatalf("expected *APIError, got %T", err)
+	}
+	if apiErr.StatusCode != 429 {
+		t.Errorf("expected 429, got %d", apiErr.StatusCode)
+	}
+	if attempts != 3 {
+		t.Errorf("expected 3 attempts, got %d", attempts)
+	}
+}
+
+func TestDoRequest_404NoRetry(t *testing.T) {
+	attempts := 0
+	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		attempts++
+		w.WriteHeader(404)
+		w.Write([]byte(`{"message":"not found"}`))
+	}))
+	defer srv.Close()
+
+	c := NewClient("token", srv.URL)
+	c.SetHTTPClient(srv.Client())
+
+	_, err := c.doGet(context.Background(), srv.URL+"/test")
+	if err == nil {
+		t.Fatal("expected error for 404")
+	}
+	if attempts != 1 {
+		t.Errorf("expected 1 attempt (no retry on 404), got %d", attempts)
+	}
+}
+
+func TestDoRequest_401NoRetry(t *testing.T) {
+	attempts := 0
+	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		attempts++
+		w.WriteHeader(401)
+		w.Write([]byte(`{"message":"bad credentials"}`))
+	}))
+	defer srv.Close()
+
+	c := NewClient("token", srv.URL)
+	c.SetHTTPClient(srv.Client())
+
+	_, err := c.doGet(context.Background(), srv.URL+"/test")
+	if err == nil {
+		t.Fatal("expected error for 401")
+	}
+	if attempts != 1 {
+		t.Errorf("expected 1 attempt (no retry on 401), got %d", attempts)
+	}
+}
+
+func TestIsNotFound(t *testing.T) {
+	err := &APIError{StatusCode: 404, Body: "not found"}
 	if !IsNotFound(err) {
-		t.Errorf("expected IsNotFound, got %v", err)
+		t.Error("expected IsNotFound to return true for 404")
 	}
-	if attempts != 1 {
-		t.Errorf("attempts = %d, want 1 (no retry on 404)", attempts)
+	err2 := &APIError{StatusCode: 500, Body: "server error"}
+	if IsNotFound(err2) {
+		t.Error("expected IsNotFound to return false for 500")
 	}
 }
 
-func TestDoRequest_401_NoRetry(t *testing.T) {
+func TestIsUnauthorized(t *testing.T) {
+	err := &APIError{StatusCode: 401, Body: "bad credentials"}
+	if !IsUnauthorized(err) {
+		t.Error("expected IsUnauthorized to return true for 401")
+	}
+}
+
+func TestDoRequest_429RetryAfterHeader(t *testing.T) {
 	attempts := 0
 	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
 		attempts++
-		w.WriteHeader(http.StatusUnauthorized)
-		w.Write([]byte("unauthorized"))
+		if attempts == 1 {
+			w.Header().Set("Retry-After", "1")
+			w.WriteHeader(429)
+			w.Write([]byte(`{"message":"rate limit"}`))
+			return
+		}
+		w.WriteHeader(200)
+		w.Write([]byte(`{"ok":true}`))
 	}))
 	defer srv.Close()
 
-	c := NewClient("tok", srv.URL)
-	_, err := c.doGet(context.Background(), srv.URL+"/test")
-	if err == nil {
-		t.Fatal("expected error, got nil")
-	}
-	if !IsUnauthorized(err) {
-		t.Errorf("expected IsUnauthorized, got %v", err)
-	}
-	if attempts != 1 {
-		t.Errorf("attempts = %d, want 1 (no retry on 401)", attempts)
-	}
-}
+	c := NewClient("token", srv.URL)
+	c.SetHTTPClient(srv.Client())
+	// Use short backoff; Retry-After should override
+	c.RetryBackoff = []time.Duration{1 * time.Millisecond, 1 * time.Millisecond}
 
-func TestDoRequest_ContextCanceled(t *testing.T) {
-	// This test exercises the timer-cancel path in the retry select:
-	//   select { case <-timer.C; case <-ctx.Done() }
-	// The server returns 429 with a long Retry-After, and we cancel the
-	// context shortly after the first response so that cancellation races
-	// against the timer rather than preventing the initial HTTP round-trip.
-	requestReceived := make(chan struct{}, 1)
-	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
-		select {
-		case requestReceived <- struct{}{}:
-		default:
-		}
-		w.Header().Set("Retry-After", "10")
-		w.WriteHeader(http.StatusTooManyRequests)
-	}))
-	defer srv.Close()
+	start := time.Now()
+	body, err := c.doGet(context.Background(), srv.URL+"/test")
+	elapsed := time.Since(start)
 
-	c := NewClient("tok", srv.URL)
-	c.SetRetryBackoff([]time.Duration{10 * time.Second, 10 * time.Second})
-
-	ctx, cancel := context.WithCancel(context.Background())
-	defer cancel()
-
-	// Cancel the context after the first request completes, while the
-	// client is blocked in the retry timer select.
-	go func() {
-		<-requestReceived
-		// Small delay to ensure we're inside the timer select.
-		time.Sleep(50 * time.Millisecond)
-		cancel()
-	}()
-
-	_, err := c.doGet(ctx, srv.URL+"/test")
-	if err == nil {
-		t.Fatal("expected error, got nil")
-	}
-	if !errors.Is(err, context.Canceled) {
-		t.Errorf("err = %v, want context.Canceled", err)
-	}
-}
-
-func TestParseRetryAfter_IntegerSeconds(t *testing.T) {
-	c := NewClient("tok", "")
-	delay, ok := c.parseRetryAfter("42")
-	if !ok {
-		t.Fatal("expected ok=true")
-	}
-	if delay != 42*time.Second {
-		t.Errorf("delay = %v, want 42s", delay)
-	}
-}
-
-func TestParseRetryAfter_ZeroSeconds(t *testing.T) {
-	c := NewClient("tok", "")
-	delay, ok := c.parseRetryAfter("0")
-	if !ok {
-		t.Fatal("expected ok=true for zero seconds (RFC 7231 allows immediate retry)")
-	}
-	if delay != 0 {
-		t.Errorf("delay = %v, want 0", delay)
-	}
-}
-
-func TestParseRetryAfter_NegativeSeconds(t *testing.T) {
-	c := NewClient("tok", "")
-	_, ok := c.parseRetryAfter("-5")
-	if ok {
-		t.Error("expected ok=false for negative seconds")
-	}
-}
-
-func TestParseRetryAfter_HTTPDate_Future(t *testing.T) {
-	fixedNow := time.Date(2025, 12, 1, 15, 59, 50, 0, time.UTC)
-	c := NewClient("tok", "")
-	c.now = func() time.Time { return fixedNow }
-
-	delay, ok := c.parseRetryAfter("Mon, 01 Dec 2025 16:00:00 GMT")
-	if !ok {
-		t.Fatal("expected ok=true")
-	}
-	// Should be 10 seconds in the future.
-	if delay != 10*time.Second {
-		t.Errorf("delay = %v, want 10s", delay)
-	}
-}
-
-func TestParseRetryAfter_HTTPDate_Past(t *testing.T) {
-	fixedNow := time.Date(2025, 12, 1, 17, 0, 0, 0, time.UTC)
-	c := NewClient("tok", "")
-	c.now = func() time.Time { return fixedNow }
-
-	delay, ok := c.parseRetryAfter("Mon, 01 Dec 2025 16:00:00 GMT")
-	if !ok {
-		t.Fatal("expected ok=true")
-	}
-	if delay != 0 {
-		t.Errorf("delay = %v, want 0 (past date)", delay)
-	}
-}
-
-func TestParseRetryAfter_RFC850_Format(t *testing.T) {
-	fixedNow := time.Date(2025, 12, 1, 15, 59, 50, 0, time.UTC)
-	c := NewClient("tok", "")
-	c.now = func() time.Time { return fixedNow }
-
-	// RFC 850 format
-	delay, ok := c.parseRetryAfter("Monday, 01-Dec-25 16:00:00 GMT")
-	if !ok {
-		t.Fatal("expected ok=true for RFC 850 format")
-	}
-	if delay != 10*time.Second {
-		t.Errorf("delay = %v, want 10s", delay)
-	}
-}
-
-func TestParseRetryAfter_Invalid(t *testing.T) {
-	c := NewClient("tok", "")
-	_, ok := c.parseRetryAfter("not-valid")
-	if ok {
-		t.Error("expected ok=false for invalid value")
-	}
-}
-
-func TestParseRetryAfter_EmptyString(t *testing.T) {
-	c := NewClient("tok", "")
-	_, ok := c.parseRetryAfter("")
-	if ok {
-		t.Error("expected ok=false for empty string")
-	}
-}
-
-func TestParseRetryAfter_MaxCap(t *testing.T) {
-	// Verify that parseRetryAfter returns the raw value (capping is done by caller).
-	c := NewClient("tok", "")
-	delay, ok := c.parseRetryAfter("3600")
-	if !ok {
-		t.Fatal("expected ok=true")
-	}
-	if delay != 3600*time.Second {
-		t.Errorf("delay = %v, want 3600s (caller is responsible for capping)", delay)
-	}
-}
-
-func TestAPIError_Error_Truncation(t *testing.T) {
-	longBody := make([]byte, 300)
-	for i := range longBody {
-		longBody[i] = 'x'
-	}
-	apiErr := &APIError{StatusCode: 500, Body: string(longBody)}
-	msg := apiErr.Error()
-	if len(msg) > 250 {
-		// "HTTP 500: " (10) + 200 + "...(truncated)" (14) = 224
-		t.Errorf("error message too long: %d chars", len(msg))
-	}
-}
-
-func TestAPIError_Error_NewlineSanitized(t *testing.T) {
-	apiErr := &APIError{StatusCode: 400, Body: "line1\nline2\rline3"}
-	msg := apiErr.Error()
-	for _, c := range msg {
-		if c == '\n' || c == '\r' {
-			t.Errorf("error message contains unsanitized newline: %q", msg)
-			break
-		}
-	}
-}
-
-func TestNewClient_HasCheckRedirect(t *testing.T) {
-	c := NewClient("secret-token", "https://api.github.com")
-	if c.httpClient.CheckRedirect == nil {
-		t.Fatal("expected CheckRedirect to be set")
-	}
-}
-
-func TestDefaultCheckRedirect_RejectsHTTPSToHTTP(t *testing.T) {
-	prev := &http.Request{URL: &url.URL{Scheme: "https", Host: "api.github.com", Path: "/foo"}}
-	req := &http.Request{
-		URL:    &url.URL{Scheme: "http", Host: "api.github.com", Path: "/foo"},
-		Header: http.Header{"Authorization": []string{"Bearer token"}},
-	}
-	err := defaultCheckRedirect(req, []*http.Request{prev})
-	if err == nil {
-		t.Fatal("expected error on HTTPS->HTTP redirect")
-	}
-	if !strings.Contains(err.Error(), "HTTPS to HTTP downgrade") {
-		t.Errorf("unexpected error message: %v", err)
-	}
-}
-
-func TestDefaultCheckRedirect_RejectsCrossHost(t *testing.T) {
-	prev := &http.Request{URL: &url.URL{Scheme: "https", Host: "api.github.com", Path: "/foo"}}
-	req := &http.Request{
-		URL:    &url.URL{Scheme: "https", Host: "objects.githubusercontent.com", Path: "/bar"},
-		Header: http.Header{"Authorization": []string{"Bearer token"}},
-	}
-	err := defaultCheckRedirect(req, []*http.Request{prev})
-	if err == nil {
-		t.Fatal("expected error on cross-host redirect")
-	}
-	if !strings.Contains(err.Error(), "cross-host") {
-		t.Errorf("unexpected error message: %v", err)
-	}
-}
-
-func TestDefaultCheckRedirect_AllowsSameHost(t *testing.T) {
-	prev := &http.Request{URL: &url.URL{Scheme: "https", Host: "api.github.com", Path: "/foo"}}
-	req := &http.Request{
-		URL:    &url.URL{Scheme: "https", Host: "api.github.com", Path: "/bar"},
-		Header: http.Header{"Authorization": []string{"Bearer token"}},
-	}
-	err := defaultCheckRedirect(req, []*http.Request{prev})
 	if err != nil {
 		t.Fatalf("unexpected error: %v", err)
 	}
-	// Auth should be preserved on same-host redirect
-	if auth := req.Header.Get("Authorization"); auth != "Bearer token" {
-		t.Errorf("expected Authorization to be preserved, got %q", auth)
-	}
-}
-
-func TestDefaultCheckRedirect_AllowsSameHostHTTPToHTTP(t *testing.T) {
-	prev := &http.Request{URL: &url.URL{Scheme: "http", Host: "localhost:8080", Path: "/foo"}}
-	req := &http.Request{
-		URL:    &url.URL{Scheme: "http", Host: "localhost:8080", Path: "/bar"},
-		Header: http.Header{},
-	}
-	err := defaultCheckRedirect(req, []*http.Request{prev})
-	if err != nil {
-		t.Fatalf("unexpected error: %v", err)
-	}
-}
-
-func TestDefaultCheckRedirect_RejectsTooManyRedirects(t *testing.T) {
-	via := make([]*http.Request, 10)
-	for i := range via {
-		via[i] = &http.Request{URL: &url.URL{Scheme: "https", Host: "api.github.com", Path: "/"}}
-	}
-	req := &http.Request{URL: &url.URL{Scheme: "https", Host: "api.github.com", Path: "/final"}}
-	err := defaultCheckRedirect(req, via)
-	if err == nil {
-		t.Fatal("expected error after 10 redirects")
-	}
-	if !strings.Contains(err.Error(), "10 redirects") {
-		t.Errorf("unexpected error message: %v", err)
-	}
-}
-
-func TestDefaultCheckRedirect_EmptyViaAllowed(t *testing.T) {
-	req := &http.Request{URL: &url.URL{Scheme: "https", Host: "api.github.com", Path: "/foo"}}
-	err := defaultCheckRedirect(req, nil)
-	if err != nil {
-		t.Fatalf("unexpected error with empty via: %v", err)
-	}
-}
-
-func TestSetHTTPClient_NilRestoresDefault(t *testing.T) {
-	c := NewClient("token", "https://api.github.com")
-	c.SetHTTPClient(nil)
-	if c.httpClient == nil {
-		t.Fatal("expected non-nil httpClient after SetHTTPClient(nil)")
-	}
-	if c.httpClient.Timeout != 30*time.Second {
-		t.Errorf("expected 30s timeout, got %v", c.httpClient.Timeout)
-	}
-	if c.httpClient.CheckRedirect == nil {
-		t.Fatal("expected CheckRedirect policy after SetHTTPClient(nil)")
+	if string(body) != `{"ok":true}` {
+		t.Errorf("unexpected body: %s", body)
+	}
+	if attempts != 2 {
+		t.Errorf("expected 2 attempts, got %d", attempts)
+	}
+	// Retry-After: 1 means at least 1 second delay
+	if elapsed < 900*time.Millisecond {
+		t.Errorf("expected ~1s delay from Retry-After, got %v", elapsed)
 	}
 }

github/conformance_test.go

@@ -0,0 +1,13 @@
+package github_test
+
+import (
+	"gitea.weiker.me/rodin/review-bot/github"
+	"gitea.weiker.me/rodin/review-bot/vcs"
+)
+
+// Compile-time interface conformance assertions.
+// These verify github.Client satisfies vcs.PRReader and vcs.FileReader.
+var (
+	_ vcs.PRReader   = (*github.Client)(nil)
+	_ vcs.FileReader = (*github.Client)(nil)
+)

github/files.go

@@ -0,0 +1,68 @@
+package github
+
+import (
+	"context"
+	"encoding/base64"
+	"encoding/json"
+	"fmt"
+	"net/url"
+	"strings"
+
+	"gitea.weiker.me/rodin/review-bot/vcs"
+)
+
+// GetFileContent fetches a file from the default branch of a repo.
+// Delegates to GetFileContentAtRef with an empty ref.
+func (c *Client) GetFileContent(ctx context.Context, owner, repo, path, ref string) (string, error) {
+	return c.GetFileContentAtRef(ctx, owner, repo, path, ref)
+}
+
+// ListContents lists files and directories at a given path in a repo.
+// Returns the directory listing from the GitHub contents API.
+func (c *Client) ListContents(ctx context.Context, owner, repo, path string) ([]vcs.ContentEntry, error) {
+	reqURL := fmt.Sprintf("%s/repos/%s/%s/contents/%s",
+		c.baseURL, url.PathEscape(owner), url.PathEscape(repo), escapePath(path))
+	body, err := c.doGet(ctx, reqURL)
+	if err != nil {
+		return nil, fmt.Errorf("list contents %s: %w", path, err)
+	}
+	var entries []struct {
+		Name string `json:"name"`
+		Path string `json:"path"`
+		Type string `json:"type"`
+	}
+	if err := json.Unmarshal(body, &entries); err != nil {
+		return nil, fmt.Errorf("parse contents JSON: %w", 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
+}
+
+// escapePath escapes each segment of a relative file path for use in URLs.
+// Slashes are preserved as path separators; other special characters are escaped.
+func escapePath(p string) string {
+	parts := strings.Split(p, "/")
+	for i, part := range parts {
+		parts[i] = url.PathEscape(part)
+	}
+	return strings.Join(parts, "/")
+}
+
+// decodeBase64Content decodes base64-encoded content from the GitHub contents API.
+// GitHub returns base64 content with newlines for formatting, which we strip before decoding.
+func decodeBase64Content(encoded string) (string, error) {
+	// GitHub inserts newlines in base64 content
+	cleaned := strings.ReplaceAll(encoded, "\n", "")
+	decoded, err := base64.StdEncoding.DecodeString(cleaned)
+	if err != nil {
+		return "", err
+	}
+	return string(decoded), nil
+}

github/files_test.go

@@ -0,0 +1,277 @@
+package github
+
+import (
+	"context"
+	"encoding/json"
+	"net/http"
+	"net/http/httptest"
+	"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)
+	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)
+	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)
+	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)
+	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)
+	c.SetHTTPClient(srv.Client())
+	c.RetryBackoff = []time.Duration{1 * time.Millisecond}
+
+	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)
+	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)
+	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)
+	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)
+	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)
+	c.SetHTTPClient(srv.Client())
+	c.RetryBackoff = []time.Duration{1 * time.Millisecond}
+
+	entries, err := c.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 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)
+	c.SetHTTPClient(srv.Client())
+
+	_, err := c.ListContents(context.Background(), "owner", "repo", "src")
+	if err == nil {
+		t.Fatal("expected error for malformed JSON")
+	}
+}
+
+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")
+	}
+}

github/pr.go

@@ -0,0 +1,233 @@
+package github
+
+import (
+	"context"
+	"encoding/json"
+	"fmt"
+	"net/http"
+	"net/url"
+
+	"gitea.weiker.me/rodin/review-bot/vcs"
+)
+
+// pullRequestResponse is the GitHub API response for a pull request.
+type pullRequestResponse struct {
+	Number int    `json:"number"`
+	Title  string `json:"title"`
+	Body   string `json:"body"`
+	Head   struct {
+		SHA string `json:"sha"`
+		Ref string `json:"ref"`
+	} `json:"head"`
+	Base struct {
+		Ref string `json:"ref"`
+	} `json:"base"`
+}
+
+// changedFileResponse is the GitHub API response for a changed file in a PR.
+type changedFileResponse struct {
+	Filename string `json:"filename"`
+	Status   string `json:"status"`
+	Patch    string `json:"patch"`
+}
+
+// commitStatusResponse is the GitHub combined status API response.
+type commitStatusResponse struct {
+	State    string `json:"state"`
+	Statuses []struct {
+		Context     string `json:"context"`
+		State       string `json:"state"`
+		Description string `json:"description"`
+		TargetURL   string `json:"target_url"`
+	} `json:"statuses"`
+}
+
+// checkRunsResponse is the GitHub check runs API response.
+type checkRunsResponse struct {
+	TotalCount int `json:"total_count"`
+	CheckRuns  []struct {
+		Name       string  `json:"name"`
+		Conclusion *string `json:"conclusion"`
+		Status     string  `json:"status"`
+		HTMLURL    string  `json:"html_url"`
+	} `json:"check_runs"`
+}
+
+// GetPullRequest fetches PR metadata.
+func (c *Client) GetPullRequest(ctx context.Context, owner, repo string, number int) (*vcs.PullRequest, error) {
+	reqURL := fmt.Sprintf("%s/repos/%s/%s/pulls/%d", c.baseURL, url.PathEscape(owner), url.PathEscape(repo), number)
+	body, err := c.doGet(ctx, reqURL)
+	if err != nil {
+		return nil, fmt.Errorf("fetch PR: %w", err)
+	}
+	var resp pullRequestResponse
+	if err := json.Unmarshal(body, &resp); err != nil {
+		return nil, fmt.Errorf("parse PR JSON: %w", err)
+	}
+	return &vcs.PullRequest{
+		Number: resp.Number,
+		Title:  resp.Title,
+		Body:   resp.Body,
+		Head:   vcs.HeadRef{SHA: resp.Head.SHA, Ref: resp.Head.Ref},
+		Base:   vcs.BaseRef{Ref: resp.Base.Ref},
+	}, nil
+}
+
+// GetPullRequestDiff fetches the unified diff for a PR.
+// Uses Accept: application/vnd.github.diff to get raw diff text.
+func (c *Client) GetPullRequestDiff(ctx context.Context, owner, repo string, number int) (string, error) {
+	reqURL := fmt.Sprintf("%s/repos/%s/%s/pulls/%d", c.baseURL, url.PathEscape(owner), url.PathEscape(repo), number)
+	body, err := c.doRequest(ctx, http.MethodGet, reqURL, "application/vnd.github.diff")
+	if err != nil {
+		return "", fmt.Errorf("fetch diff: %w", err)
+	}
+	return string(body), nil
+}
+
+// GetPullRequestFiles fetches the list of files changed in a PR.
+// Paginates through all pages (100 per page) to collect all files.
+func (c *Client) GetPullRequestFiles(ctx context.Context, owner, repo string, number int) ([]vcs.ChangedFile, error) {
+	var allFiles []vcs.ChangedFile
+	page := 1
+
+	for {
+		reqURL := fmt.Sprintf("%s/repos/%s/%s/pulls/%d/files?per_page=100&page=%d",
+			c.baseURL, url.PathEscape(owner), url.PathEscape(repo), number, page)
+		body, err := c.doGet(ctx, reqURL)
+		if err != nil {
+			return nil, fmt.Errorf("fetch PR files page %d: %w", page, err)
+		}
+		var files []changedFileResponse
+		if err := json.Unmarshal(body, &files); err != nil {
+			return nil, fmt.Errorf("parse PR files JSON: %w", err)
+		}
+		if len(files) == 0 {
+			break
+		}
+		for _, f := range files {
+			allFiles = append(allFiles, vcs.ChangedFile{
+				Filename: f.Filename,
+				Status:   f.Status,
+				Patch:    f.Patch,
+			})
+		}
+		if len(files) < 100 {
+			break
+		}
+		page++
+	}
+
+	return allFiles, nil
+}
+
+// GetFileContentAtRef fetches a file at a specific ref from a repo.
+// If ref is empty, the query parameter is omitted (uses default branch).
+func (c *Client) GetFileContentAtRef(ctx context.Context, owner, repo, path, ref string) (string, error) {
+	reqURL := fmt.Sprintf("%s/repos/%s/%s/contents/%s",
+		c.baseURL, url.PathEscape(owner), url.PathEscape(repo), escapePath(path))
+	if ref != "" {
+		reqURL += "?ref=" + url.QueryEscape(ref)
+	}
+	body, err := c.doGet(ctx, reqURL)
+	if err != nil {
+		return "", fmt.Errorf("fetch file %s: %w", path, err)
+	}
+	var resp struct {
+		Content  string `json:"content"`
+		Encoding string `json:"encoding"`
+	}
+	if err := json.Unmarshal(body, &resp); err != nil {
+		return "", fmt.Errorf("parse file content JSON: %w", err)
+	}
+	if resp.Encoding != "base64" {
+		return "", fmt.Errorf("unexpected encoding %q for file %s", resp.Encoding, path)
+	}
+	decoded, err := decodeBase64Content(resp.Content)
+	if err != nil {
+		return "", fmt.Errorf("decode base64 content for %s: %w", path, err)
+	}
+	return decoded, nil
+}
+
+// GetCommitStatuses fetches both commit statuses and check runs for a SHA,
+// merging them into a unified []vcs.CommitStatus slice.
+func (c *Client) GetCommitStatuses(ctx context.Context, owner, repo, sha string) ([]vcs.CommitStatus, error) {
+	var result []vcs.CommitStatus
+
+	// Fetch commit statuses
+	statusURL := fmt.Sprintf("%s/repos/%s/%s/commits/%s/status",
+		c.baseURL, url.PathEscape(owner), url.PathEscape(repo), url.PathEscape(sha))
+	statusBody, err := c.doGet(ctx, statusURL)
+	if err != nil {
+		return nil, fmt.Errorf("fetch commit statuses: %w", err)
+	}
+	var statusResp commitStatusResponse
+	if err := json.Unmarshal(statusBody, &statusResp); err != nil {
+		return nil, fmt.Errorf("parse commit statuses JSON: %w", err)
+	}
+	for _, s := range statusResp.Statuses {
+		result = append(result, vcs.CommitStatus{
+			Context:     s.Context,
+			Status:      s.State,
+			Description: s.Description,
+			TargetURL:   s.TargetURL,
+		})
+	}
+
+	// Fetch check runs (paginated)
+	checkPage := 1
+	for {
+		checkURL := fmt.Sprintf("%s/repos/%s/%s/commits/%s/check-runs?per_page=100&page=%d",
+			c.baseURL, url.PathEscape(owner), url.PathEscape(repo), url.PathEscape(sha), checkPage)
+		checkBody, err := c.doGet(ctx, checkURL)
+		if err != nil {
+			return nil, fmt.Errorf("fetch check runs page %d: %w", checkPage, err)
+		}
+		var checkResp checkRunsResponse
+		if err := json.Unmarshal(checkBody, &checkResp); err != nil {
+			return nil, fmt.Errorf("parse check runs JSON: %w", err)
+		}
+		for _, cr := range checkResp.CheckRuns {
+			result = append(result, vcs.CommitStatus{
+				Context:     cr.Name,
+				Status:      mapCheckRunStatus(cr.Conclusion, cr.Status),
+				Description: derefString(cr.Conclusion),
+				TargetURL:   cr.HTMLURL,
+			})
+		}
+		if len(checkResp.CheckRuns) < 100 {
+			break
+		}
+		checkPage++
+	}
+
+	return result, nil
+}
+
+// mapCheckRunStatus maps a check run conclusion+status to a vcs.CommitStatus status string.
+func mapCheckRunStatus(conclusion *string, status string) string {
+	if conclusion == nil {
+		// Still running or queued
+		return "pending"
+	}
+	switch *conclusion {
+	case "success":
+		return "success"
+	case "failure", "action_required", "timed_out":
+		return "failure"
+	case "cancelled", "skipped", "neutral":
+		return "success" // non-blocking
+	case "in_progress", "queued":
+		return "pending"
+	default:
+		return "pending"
+	}
+}
+
+// derefString safely dereferences a string pointer, returning empty string if nil.
+func derefString(s *string) string {
+	if s == nil {
+		return ""
+	}
+	return *s
+}

github/pr_test.go

@@ -0,0 +1,637 @@
+package github
+
+import (
+	"context"
+	"encoding/json"
+	"fmt"
+	"net/http"
+	"net/http/httptest"
+	"strings"
+	"testing"
+	"time"
+)
+
+func TestGetPullRequest_HappyPath(t *testing.T) {
+	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		if r.URL.Path != "/repos/owner/repo/pulls/42" {
+			t.Errorf("unexpected path: %s", r.URL.Path)
+		}
+		json.NewEncoder(w).Encode(map[string]interface{}{
+			"number": 42,
+			"title":  "Test PR",
+			"body":   "Description",
+			"head":   map[string]string{"sha": "abc123", "ref": "feature-branch"},
+			"base":   map[string]string{"ref": "main"},
+		})
+	}))
+	defer srv.Close()
+
+	c := NewClient("token", srv.URL)
+	c.SetHTTPClient(srv.Client())
+
+	pr, err := c.GetPullRequest(context.Background(), "owner", "repo", 42)
+	if err != nil {
+		t.Fatalf("unexpected error: %v", err)
+	}
+	if pr.Number != 42 {
+		t.Errorf("expected number 42, got %d", pr.Number)
+	}
+	if pr.Title != "Test PR" {
+		t.Errorf("expected title 'Test PR', got %q", pr.Title)
+	}
+	if pr.Body != "Description" {
+		t.Errorf("expected body 'Description', got %q", pr.Body)
+	}
+	if pr.Head.SHA != "abc123" {
+		t.Errorf("expected head SHA 'abc123', got %q", pr.Head.SHA)
+	}
+	if pr.Head.Ref != "feature-branch" {
+		t.Errorf("expected head ref 'feature-branch', got %q", pr.Head.Ref)
+	}
+	if pr.Base.Ref != "main" {
+		t.Errorf("expected base ref 'main', got %q", pr.Base.Ref)
+	}
+}
+
+func TestGetPullRequest_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)
+	c.SetHTTPClient(srv.Client())
+
+	_, err := c.GetPullRequest(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 TestGetPullRequest_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)
+	c.SetHTTPClient(srv.Client())
+
+	_, err := c.GetPullRequest(context.Background(), "owner", "repo", 1)
+	if err == nil {
+		t.Fatal("expected error for 401")
+	}
+	if !IsUnauthorized(err) {
+		t.Errorf("expected IsUnauthorized=true, got error: %v", err)
+	}
+}
+
+func TestGetPullRequest_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]interface{}{
+			"number": 1,
+			"title":  "PR",
+			"body":   "",
+			"head":   map[string]string{"sha": "abc", "ref": "br"},
+			"base":   map[string]string{"ref": "main"},
+		})
+	}))
+	defer srv.Close()
+
+	c := NewClient("token", srv.URL)
+	c.SetHTTPClient(srv.Client())
+	c.RetryBackoff = []time.Duration{1 * time.Millisecond}
+
+	pr, err := c.GetPullRequest(context.Background(), "owner", "repo", 1)
+	if err != nil {
+		t.Fatalf("unexpected error: %v", err)
+	}
+	if pr.Number != 1 {
+		t.Errorf("expected number 1, got %d", pr.Number)
+	}
+	if attempts != 2 {
+		t.Errorf("expected 2 attempts, got %d", attempts)
+	}
+}
+
+func TestGetPullRequest_MalformedJSON(t *testing.T) {
+	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		w.WriteHeader(200)
+		w.Write([]byte(`{invalid json`))
+	}))
+	defer srv.Close()
+
+	c := NewClient("token", srv.URL)
+	c.SetHTTPClient(srv.Client())
+
+	_, err := c.GetPullRequest(context.Background(), "owner", "repo", 1)
+	if err == nil {
+		t.Fatal("expected error for malformed JSON")
+	}
+	if !strings.Contains(err.Error(), "parse PR JSON") {
+		t.Errorf("expected parse error, got: %v", err)
+	}
+}
+
+func TestGetPullRequestDiff_HappyPath(t *testing.T) {
+	expectedDiff := "diff --git a/file.go b/file.go\n--- a/file.go\n+++ b/file.go\n@@ -1,3 +1,4 @@\n+// new line\n"
+	var gotAccept string
+	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		gotAccept = r.Header.Get("Accept")
+		w.WriteHeader(200)
+		w.Write([]byte(expectedDiff))
+	}))
+	defer srv.Close()
+
+	c := NewClient("token", srv.URL)
+	c.SetHTTPClient(srv.Client())
+
+	diff, err := c.GetPullRequestDiff(context.Background(), "owner", "repo", 42)
+	if err != nil {
+		t.Fatalf("unexpected error: %v", err)
+	}
+	if diff != expectedDiff {
+		t.Errorf("unexpected diff: %q", diff)
+	}
+	if gotAccept != "application/vnd.github.diff" {
+		t.Errorf("expected diff Accept header, got %q", gotAccept)
+	}
+}
+
+func TestGetPullRequestDiff_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)
+	c.SetHTTPClient(srv.Client())
+
+	_, err := c.GetPullRequestDiff(context.Background(), "owner", "repo", 999)
+	if err == nil {
+		t.Fatal("expected error for 404")
+	}
+}
+
+func TestGetPullRequestDiff_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)
+	c.SetHTTPClient(srv.Client())
+
+	_, err := c.GetPullRequestDiff(context.Background(), "owner", "repo", 1)
+	if err == nil {
+		t.Fatal("expected error for 401")
+	}
+}
+
+func TestGetPullRequestFiles_HappyPath(t *testing.T) {
+	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		json.NewEncoder(w).Encode([]map[string]interface{}{
+			{"filename": "main.go", "status": "modified", "patch": "@@ -1,3 +1,4 @@\n+line"},
+			{"filename": "test.go", "status": "added", "patch": "@@ -0,0 +1,5 @@\n+new file"},
+		})
+	}))
+	defer srv.Close()
+
+	c := NewClient("token", srv.URL)
+	c.SetHTTPClient(srv.Client())
+
+	files, err := c.GetPullRequestFiles(context.Background(), "owner", "repo", 1)
+	if err != nil {
+		t.Fatalf("unexpected error: %v", err)
+	}
+	if len(files) != 2 {
+		t.Fatalf("expected 2 files, got %d", len(files))
+	}
+	if files[0].Filename != "main.go" {
+		t.Errorf("expected filename 'main.go', got %q", files[0].Filename)
+	}
+	if files[0].Status != "modified" {
+		t.Errorf("expected status 'modified', got %q", files[0].Status)
+	}
+	if files[0].Patch != "@@ -1,3 +1,4 @@\n+line" {
+		t.Errorf("unexpected patch: %q", files[0].Patch)
+	}
+}
+
+func TestGetPullRequestFiles_Pagination(t *testing.T) {
+	// Simulate > 100 files requiring pagination
+	page1Files := make([]map[string]string, 100)
+	for i := 0; i < 100; i++ {
+		page1Files[i] = map[string]string{
+			"filename": fmt.Sprintf("file%d.go", i),
+			"status":   "modified",
+			"patch":    fmt.Sprintf("patch%d", i),
+		}
+	}
+	page2Files := []map[string]string{
+		{"filename": "file100.go", "status": "added", "patch": "patch100"},
+	}
+
+	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		page := r.URL.Query().Get("page")
+		if page == "" || page == "1" {
+			json.NewEncoder(w).Encode(page1Files)
+		} else {
+			json.NewEncoder(w).Encode(page2Files)
+		}
+	}))
+	defer srv.Close()
+
+	c := NewClient("token", srv.URL)
+	c.SetHTTPClient(srv.Client())
+
+	files, err := c.GetPullRequestFiles(context.Background(), "owner", "repo", 1)
+	if err != nil {
+		t.Fatalf("unexpected error: %v", err)
+	}
+	if len(files) != 101 {
+		t.Errorf("expected 101 files (paginated), got %d", len(files))
+	}
+	if files[100].Filename != "file100.go" {
+		t.Errorf("expected last file 'file100.go', got %q", files[100].Filename)
+	}
+	if files[100].Patch != "patch100" {
+		t.Errorf("expected last patch 'patch100', got %q", files[100].Patch)
+	}
+}
+
+func TestGetPullRequestFiles_BinaryFile_NoPatch(t *testing.T) {
+	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		// Binary files have no patch field in GitHub response
+		json.NewEncoder(w).Encode([]map[string]interface{}{
+			{"filename": "image.png", "status": "added"},
+		})
+	}))
+	defer srv.Close()
+
+	c := NewClient("token", srv.URL)
+	c.SetHTTPClient(srv.Client())
+
+	files, err := c.GetPullRequestFiles(context.Background(), "owner", "repo", 1)
+	if err != nil {
+		t.Fatalf("unexpected error: %v", err)
+	}
+	if len(files) != 1 {
+		t.Fatalf("expected 1 file, got %d", len(files))
+	}
+	if files[0].Patch != "" {
+		t.Errorf("expected empty patch for binary file, got %q", files[0].Patch)
+	}
+}
+
+func TestGetPullRequestFiles_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)
+	c.SetHTTPClient(srv.Client())
+
+	_, err := c.GetPullRequestFiles(context.Background(), "owner", "repo", 999)
+	if err == nil {
+		t.Fatal("expected error for 404")
+	}
+}
+
+func TestGetPullRequestFiles_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)
+	c.SetHTTPClient(srv.Client())
+
+	_, err := c.GetPullRequestFiles(context.Background(), "owner", "repo", 1)
+	if err == nil {
+		t.Fatal("expected error for malformed JSON")
+	}
+}
+
+func TestGetFileContentAtRef_HappyPath(t *testing.T) {
+	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		if r.URL.Path != "/repos/owner/repo/contents/path/to/file.go" {
+			t.Errorf("unexpected path: %s", r.URL.Path)
+		}
+		if r.URL.Query().Get("ref") != "abc123" {
+			t.Errorf("unexpected ref: %s", r.URL.Query().Get("ref"))
+		}
+		json.NewEncoder(w).Encode(map[string]string{
+			"content":  "cGFja2FnZSBtYWlu", // "package main" in base64
+			"encoding": "base64",
+		})
+	}))
+	defer srv.Close()
+
+	c := NewClient("token", srv.URL)
+	c.SetHTTPClient(srv.Client())
+
+	content, err := c.GetFileContentAtRef(context.Background(), "owner", "repo", "path/to/file.go", "abc123")
+	if err != nil {
+		t.Fatalf("unexpected error: %v", err)
+	}
+	if content != "package main" {
+		t.Errorf("expected 'package main', got %q", content)
+	}
+}
+
+func TestGetFileContentAtRef_EmptyRef(t *testing.T) {
+	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		if r.URL.Query().Get("ref") != "" {
+			t.Errorf("expected no ref param, got %q", r.URL.Query().Get("ref"))
+		}
+		json.NewEncoder(w).Encode(map[string]string{
+			"content":  "aGVsbG8=", // "hello" in base64
+			"encoding": "base64",
+		})
+	}))
+	defer srv.Close()
+
+	c := NewClient("token", srv.URL)
+	c.SetHTTPClient(srv.Client())
+
+	content, err := c.GetFileContentAtRef(context.Background(), "owner", "repo", "file.txt", "")
+	if err != nil {
+		t.Fatalf("unexpected error: %v", err)
+	}
+	if content != "hello" {
+		t.Errorf("expected 'hello', got %q", content)
+	}
+}
+
+func TestGetFileContentAtRef_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)
+	c.SetHTTPClient(srv.Client())
+
+	_, err := c.GetFileContentAtRef(context.Background(), "owner", "repo", "missing.go", "main")
+	if err == nil {
+		t.Fatal("expected error for 404")
+	}
+}
+
+func TestGetFileContentAtRef_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)
+	c.SetHTTPClient(srv.Client())
+
+	_, err := c.GetFileContentAtRef(context.Background(), "owner", "repo", "file.go", "main")
+	if err == nil {
+		t.Fatal("expected error for 401")
+	}
+}
+
+func TestGetFileContentAtRef_MalformedJSON(t *testing.T) {
+	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		w.WriteHeader(200)
+		w.Write([]byte(`not valid json`))
+	}))
+	defer srv.Close()
+
+	c := NewClient("token", srv.URL)
+	c.SetHTTPClient(srv.Client())
+
+	_, err := c.GetFileContentAtRef(context.Background(), "owner", "repo", "file.go", "main")
+	if err == nil {
+		t.Fatal("expected error for malformed JSON")
+	}
+}
+
+func TestGetFileContentAtRef_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=", // "ok" in base64
+			"encoding": "base64",
+		})
+	}))
+	defer srv.Close()
+
+	c := NewClient("token", srv.URL)
+	c.SetHTTPClient(srv.Client())
+	c.RetryBackoff = []time.Duration{1 * time.Millisecond}
+
+	content, err := c.GetFileContentAtRef(context.Background(), "owner", "repo", "file.go", "main")
+	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 TestGetCommitStatuses_HappyPath(t *testing.T) {
+	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		switch {
+		case strings.Contains(r.URL.Path, "/status"):
+			json.NewEncoder(w).Encode(map[string]interface{}{
+				"state": "success",
+				"statuses": []map[string]string{
+					{
+						"context":     "ci/build",
+						"state":       "success",
+						"description": "Build passed",
+						"target_url":  "https://ci.example.com/1",
+					},
+				},
+			})
+		case strings.Contains(r.URL.Path, "/check-runs"):
+			conclusion := "success"
+			json.NewEncoder(w).Encode(map[string]interface{}{
+				"total_count": 1,
+				"check_runs": []map[string]interface{}{
+					{
+						"name":       "lint",
+						"conclusion": &conclusion,
+						"status":     "completed",
+						"html_url":   "https://github.com/check/1",
+					},
+				},
+			})
+		default:
+			t.Errorf("unexpected path: %s", r.URL.Path)
+			w.WriteHeader(404)
+		}
+	}))
+	defer srv.Close()
+
+	c := NewClient("token", srv.URL)
+	c.SetHTTPClient(srv.Client())
+
+	statuses, err := c.GetCommitStatuses(context.Background(), "owner", "repo", "abc123")
+	if err != nil {
+		t.Fatalf("unexpected error: %v", err)
+	}
+	if len(statuses) != 2 {
+		t.Fatalf("expected 2 statuses, got %d", len(statuses))
+	}
+	// First should be from commit statuses
+	if statuses[0].Context != "ci/build" {
+		t.Errorf("expected context 'ci/build', got %q", statuses[0].Context)
+	}
+	if statuses[0].Status != "success" {
+		t.Errorf("expected status 'success', got %q", statuses[0].Status)
+	}
+	// Second should be from check runs
+	if statuses[1].Context != "lint" {
+		t.Errorf("expected context 'lint', got %q", statuses[1].Context)
+	}
+	if statuses[1].Status != "success" {
+		t.Errorf("expected status 'success', got %q", statuses[1].Status)
+	}
+}
+
+func TestGetCommitStatuses_CheckRunConclusions(t *testing.T) {
+	tests := []struct {
+		conclusion *string
+		status     string
+		want       string
+	}{
+		{strPtr("success"), "completed", "success"},
+		{strPtr("failure"), "completed", "failure"},
+		{strPtr("action_required"), "completed", "failure"},
+		{strPtr("timed_out"), "completed", "failure"},
+		{strPtr("cancelled"), "completed", "success"},
+		{strPtr("skipped"), "completed", "success"},
+		{strPtr("neutral"), "completed", "success"},
+		{nil, "in_progress", "pending"},
+		{nil, "queued", "pending"},
+	}
+
+	for _, tt := range tests {
+		name := "nil"
+		if tt.conclusion != nil {
+			name = *tt.conclusion
+		}
+		t.Run(name, func(t *testing.T) {
+			srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+				if strings.Contains(r.URL.Path, "/status") {
+					json.NewEncoder(w).Encode(map[string]interface{}{
+						"state":    "success",
+						"statuses": []interface{}{},
+					})
+					return
+				}
+				json.NewEncoder(w).Encode(map[string]interface{}{
+					"total_count": 1,
+					"check_runs": []map[string]interface{}{
+						{
+							"name":       "check",
+							"conclusion": tt.conclusion,
+							"status":     tt.status,
+							"html_url":   "https://github.com/check/1",
+						},
+					},
+				})
+			}))
+			defer srv.Close()
+
+			c := NewClient("token", srv.URL)
+			c.SetHTTPClient(srv.Client())
+
+			statuses, err := c.GetCommitStatuses(context.Background(), "owner", "repo", "sha1")
+			if err != nil {
+				t.Fatalf("unexpected error: %v", err)
+			}
+			if len(statuses) != 1 {
+				t.Fatalf("expected 1 status, got %d", len(statuses))
+			}
+			if statuses[0].Status != tt.want {
+				t.Errorf("expected status %q, got %q", tt.want, statuses[0].Status)
+			}
+		})
+	}
+}
+
+func TestGetCommitStatuses_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)
+	c.SetHTTPClient(srv.Client())
+
+	_, err := c.GetCommitStatuses(context.Background(), "owner", "repo", "badsha")
+	if err == nil {
+		t.Fatal("expected error for 404")
+	}
+}
+
+func TestGetCommitStatuses_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)
+	c.SetHTTPClient(srv.Client())
+
+	_, err := c.GetCommitStatuses(context.Background(), "owner", "repo", "sha")
+	if err == nil {
+		t.Fatal("expected error for 401")
+	}
+}
+
+func TestGetCommitStatuses_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)
+	c.SetHTTPClient(srv.Client())
+
+	_, err := c.GetCommitStatuses(context.Background(), "owner", "repo", "sha")
+	if err == nil {
+		t.Fatal("expected error for malformed JSON")
+	}
+}
+
+func strPtr(s string) *string {
+	return &s
+}

go.mod

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

go.sum

@@ -1,2 +1,4 @@
-github.com/goccy/go-yaml v1.19.2 h1:PmFC1S6h8ljIz6gMRBopkjP1TVT7xuwrButHID66PoM=
-github.com/goccy/go-yaml v1.19.2/go.mod h1:XBurs7gK8ATbW4ZPGKgcbrY1Br56PdM69F7LkFRi1kA=
+gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405 h1:yhCVgyC4o1eVCa2tZl7eS0r+SDo693bJlVdllGtEeKM=
+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=

review/persona.go

@@ -5,15 +5,12 @@ import (
 	"embed"
 	"encoding/json"
 	"fmt"
-	"io"
 	"os"
 	"sort"
 	"strings"
 	"unicode/utf8"
 
-	"github.com/goccy/go-yaml"
-	"github.com/goccy/go-yaml/ast"
-	"github.com/goccy/go-yaml/parser"
+	"gopkg.in/yaml.v3"
 )
 
 //go:embed personas/*.yaml
@@ -121,7 +118,9 @@ func ListBuiltinPersonas() []string {
 		default:
 			continue
 		}
-		seen[personaName] = true
+		if !seen[personaName] {
+			seen[personaName] = true
+		}
 	}
 	names := make([]string, 0, len(seen))
 	for name := range seen {
@@ -143,19 +142,10 @@ func parsePersona(data []byte, source string) (*Persona, error) {
 		err = unmarshalYAMLWithDepthLimit(data, &p, MaxYAMLDepth)
 	} else {
 		// 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.DisallowUnknownFields()
 		err = dec.Decode(&p)
-		if err == nil {
-			// Reject trailing content after the first valid JSON object.
-			// Without this check, input like `{"name":"x"}garbage` would
-			// silently succeed because Decoder stops after one object.
-			var dummy json.RawMessage
-			if err2 := dec.Decode(&dummy); err2 != io.EOF {
-				err = fmt.Errorf("unexpected trailing content after JSON object")
-			}
-		}
 	}
 	if err != nil {
 		return nil, fmt.Errorf("parse persona %s: %w", source, err)
@@ -166,164 +156,70 @@ func parsePersona(data []byte, source string) (*Persona, error) {
 	return &p, nil
 }
 
-// unmarshalYAMLWithDepthLimit unmarshals YAML data with three safety checks:
-//   - Depth limiting: rejects AST trees exceeding maxDepth to prevent stack exhaustion.
-//   - Multi-document rejection: prevents silent data loss from ignored extra documents.
-//   - Strict field checking: rejects unknown YAML keys to catch typos early.
+// unmarshalYAMLWithDepthLimit unmarshals YAML data with explicit depth limiting
+// and strict field checking. This protects against stack exhaustion from deeply
+// nested structures and catches typos in field names.
+// Multi-document YAML files are rejected to prevent silent data loss.
 func unmarshalYAMLWithDepthLimit(data []byte, out any, maxDepth int) error {
-	// First pass: parse into AST to check depth limits, node counts, and
-	// multi-document rejection. This prevents stack exhaustion before we
-	// attempt to decode into structs.
-	file, err := parser.ParseBytes(data, 0)
-	if err != nil {
+	// First pass: decode into a yaml.Node to check depth limits and node counts.
+	// This prevents stack exhaustion before we attempt to decode into structs.
+	var node yaml.Node
+	dec := yaml.NewDecoder(bytes.NewReader(data))
+	if err := dec.Decode(&node); err != nil {
 		return err
 	}
 
-	// Reject empty YAML input (whitespace-only, comment-only, or truly empty files).
-	// The parser returns a single doc with nil body for these cases.
-	if len(file.Docs) == 0 || file.Docs[0].Body == nil {
-		return fmt.Errorf("empty YAML document")
-	}
-
 	// Reject multi-document YAML files - silently ignoring additional documents
 	// could lead to confusing behavior where users think their changes take effect.
-	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")
 	}
 
 	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
 	}
 
 	// Second pass: decode with strict field checking enabled.
-	// Strict() rejects unknown keys, catching typos like "focuss" or "identiy".
-	//
-	// Safety note: goccy/go-yaml's decoder does not expand YAML aliases
-	// recursively — it resolves them via the pre-built AST, which our first
-	// pass already depth-checked. Alias chains that would exceed depth limits
-	// are caught above; the decoder merely reads the resolved scalar values.
-	dec := yaml.NewDecoder(bytes.NewReader(data), yaml.Strict())
-	return dec.Decode(out)
+	// KnownFields(true) rejects unknown keys, catching typos like "focuss" or "identiy".
+	// We must re-decode from the original data because yaml.Node.Decode() doesn't
+	// support the KnownFields option.
+	strictDec := yaml.NewDecoder(bytes.NewReader(data))
+	strictDec.KnownFields(true)
+	return strictDec.Decode(out)
 }
 
-// checkYAMLDepth recursively checks that YAML AST nodes don't exceed the depth
-// limit or the total node count limit. It uses two tracking maps:
-//   - validated: maps each node to the maximum depth at which it was previously
-//     checked. If a node is revisited at a deeper depth (e.g., via an alias),
-//     we re-check it to ensure the combined effective depth doesn't exceed limits.
-//   - visiting: per-path recursion stack for true cycle detection. A node on the
-//     current path is a cycle (alias loop); we return nil to avoid infinite recursion.
-//
-// This design prevents the alias depth bypass where an anchored subtree validated
-// at a shallow depth could be referenced via alias at a greater depth, effectively
-// exceeding MaxYAMLDepth.
-func checkYAMLDepth(node ast.Node, depth, maxDepth, maxNodes int, validated map[ast.Node]int, visiting map[ast.Node]bool, nodeCount *int) error {
-	if node == nil {
-		return nil
-	}
-
+// checkYAMLDepth recursively checks that YAML nodes don't exceed the depth limit
+// or the total node count limit. It also detects alias cycles to prevent infinite
+// recursion from crafted YAML with self-referential aliases.
+func checkYAMLDepth(node *yaml.Node, depth, maxDepth, maxNodes int, seen map[*yaml.Node]struct{}, nodeCount *int) error {
 	if depth > maxDepth {
 		return fmt.Errorf("YAML nesting depth exceeds maximum (%d)", maxDepth)
 	}
 
-	// Cycle detection: if we're currently visiting this node on the current
-	// recursion path, it's a cycle (e.g., alias pointing to an ancestor).
-	// Return nil to break the cycle without error — cycles are a structural
-	// property, not a depth violation.
-	if visiting[node] {
-		return nil
-	}
-
 	// Track total nodes visited as defense-in-depth against wide-but-shallow attacks.
-	// Placed after cycle detection but before the depth-aware short-circuit. This means
-	// nodes revisited at shallower depths (via aliases) are counted each time they are
-	// encountered — intentional conservative overcounting. This bounds the total work
-	// performed during validation rather than tracking unique nodes, which is the safer
-	// security posture for untrusted YAML input.
 	*nodeCount++
 	if *nodeCount > maxNodes {
 		return fmt.Errorf("YAML node count exceeds maximum (%d)", maxNodes)
 	}
 
-	// Depth-aware short-circuit: skip re-validation only when the current visit
-	// depth is the same or shallower than the depth at which this node was
-	// previously validated. A shallower (or equal) current depth means the
-	// prior, deeper validation already covered any subtree depth violations.
-	// If the current depth exceeds the previous validation depth (e.g., an alias
-	// references this node deeper in the tree), we must re-traverse to ensure
-	// the combined effective depth doesn't exceed maxDepth.
-	//
-	// Note: using ast.Node (interface) as map key relies on pointer identity,
-	// which is correct because all goccy/go-yaml AST node types are pointer
-	// receivers (*MappingNode, *SequenceNode, etc.), never value types.
-	if prevDepth, ok := validated[node]; ok && depth <= prevDepth {
-		return nil
+	// Cycle detection: if we've seen this node before, we're in a cycle.
+	if _, ok := seen[node]; ok {
+		return nil // Already validated this subtree, skip to avoid infinite recursion.
 	}
-	validated[node] = depth
+	seen[node] = struct{}{}
 
-	// Mark as visiting (on the current recursion path) for cycle detection.
-	visiting[node] = true
-	defer func() { visiting[node] = false }()
+	// Handle alias nodes: follow the alias to its anchor target.
+	// Increment depth when following aliases since they expand the effective structure.
+	if node.Kind == yaml.AliasNode && node.Alias != nil {
+		return checkYAMLDepth(node.Alias, depth+1, maxDepth, maxNodes, seen, nodeCount)
+	}
 
-	// Walk children based on node type.
-	switch n := node.(type) {
-	case *ast.MappingNode:
-		for _, value := range n.Values {
-			if err := checkYAMLDepth(value, depth+1, maxDepth, maxNodes, validated, visiting, nodeCount); err != nil {
-				return err
-			}
-		}
-	case *ast.MappingValueNode:
-		// Both Key and Value are visited at depth+1 relative to this
-		// MappingValueNode. Since MappingNode visits its MappingValueNode
-		// children at depth+1 as well, keys and values end up at depth+2
-		// from the parent MappingNode. This is intentional: it mirrors the
-		// actual nesting structure (mapping → key-value pair → key/value).
-		if err := checkYAMLDepth(n.Key, depth+1, maxDepth, maxNodes, validated, visiting, nodeCount); err != nil {
+	for _, child := range node.Content {
+		if err := checkYAMLDepth(child, depth+1, maxDepth, maxNodes, seen, 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
 }
@@ -331,11 +227,7 @@ func checkYAMLDepth(node ast.Node, depth, maxDepth, maxNodes int, validated map[
 // ParsePersonaBytes parses persona data from bytes with a source label for errors.
 // This is useful for parsing personas fetched from external sources (e.g., Gitea API)
 // without requiring filesystem access. Format is detected by source extension.
-// Input is bounded by MaxPersonaFileSize to prevent resource exhaustion.
 func ParsePersonaBytes(data []byte, source string) (*Persona, error) {
-	if len(data) > MaxPersonaFileSize {
-		return nil, fmt.Errorf("persona data from %s exceeds maximum size (%d bytes, limit %d)", source, len(data), MaxPersonaFileSize)
-	}
 	return parsePersona(data, source)
 }
 

review/persona_test.go

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

review/repo_persona.go

@@ -4,32 +4,19 @@ import (
 	"context"
 	"log/slog"
 	"strings"
+
+	"gitea.weiker.me/rodin/review-bot/vcs"
 )
 
 // 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) {
+func LoadRepoPersonas(ctx context.Context, client vcs.FileReader, owner, repo string) (map[string]*Persona, error) {
 	result := make(map[string]*Persona)
 
 	entries, err := client.ListContents(ctx, owner, repo, RepoPersonaPath)
@@ -57,7 +44,7 @@ func LoadRepoPersonas(ctx context.Context, client GiteaClient, owner, repo strin
 			continue
 		}
 
-		content, err := client.GetFileContent(ctx, owner, repo, entry.Path)
+		content, err := client.GetFileContent(ctx, owner, repo, entry.Path, "")
 		if err != nil {
 			slog.Warn("could not fetch repo persona file",
 				"file", entry.Path,

review/repo_persona_test.go

@@ -5,23 +5,21 @@ import (
 	"errors"
 	"strings"
 	"testing"
+
+	"gitea.weiker.me/rodin/review-bot/vcs"
 )
 
 func TestParsePersonaBytes(t *testing.T) {
 	tests := []struct {
-		name       string
-		data       string
-		source     string
-		wantName   string
-		wantErr    string
+		name     string
+		data     string
+		source   string
+		wantName string
+		wantErr  string
 	}{
 		{
 			name: "valid yaml",
-			data: `name: test
-identity: test identity
-focus:
-  - testing
-`,
+			data: "name: test\nidentity: test identity\nfocus:\n  - testing\n",
 			source:   "test.yaml",
 			wantName: "test",
 		},
@@ -38,8 +36,8 @@ focus:
 			wantErr: "parse",
 		},
 		{
-			name: "json format by extension",
-			data: `{"name": "jsontest", "identity": "json identity"}`,
+			name:     "json format by extension",
+			data:     `{"name": "jsontest", "identity": "json identity"}`,
 			source:   "test.json",
 			wantName: "jsontest",
 		},
@@ -67,15 +65,15 @@ focus:
 	}
 }
 
-// mockGiteaClient implements GiteaClient for testing.
+// mockGiteaClient implements vcs.FileReader for testing.
 type mockGiteaClient struct {
-	contents map[string][]ContentEntry // path -> entries
-	files    map[string]string         // path -> content
+	contents map[string][]vcs.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) {
+func (m *mockGiteaClient) ListContents(ctx context.Context, owner, repo, path string) ([]vcs.ContentEntry, error) {
 	if m.listErr != nil {
 		return nil, m.listErr
 	}
@@ -86,7 +84,7 @@ func (m *mockGiteaClient) ListContents(ctx context.Context, owner, repo, path st
 	return entries, nil
 }
 
-func (m *mockGiteaClient) GetFileContent(ctx context.Context, owner, repo, filepath string) (string, error) {
+func (m *mockGiteaClient) GetFileContent(ctx context.Context, owner, repo, filepath, ref string) (string, error) {
 	if m.fileErr != nil {
 		if err, ok := m.fileErr[filepath]; ok {
 			return "", err
@@ -118,7 +116,7 @@ func TestLoadRepoPersonas(t *testing.T) {
 
 	t.Run("empty directory returns empty map", func(t *testing.T) {
 		client := &mockGiteaClient{
-			contents: map[string][]ContentEntry{
+			contents: map[string][]vcs.ContentEntry{
 				RepoPersonaPath: {},
 			},
 		}
@@ -133,27 +131,15 @@ func TestLoadRepoPersonas(t *testing.T) {
 
 	t.Run("loads valid personas", func(t *testing.T) {
 		client := &mockGiteaClient{
-			contents: map[string][]ContentEntry{
+			contents: map[string][]vcs.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
-`,
+				".review-bot/personas/trading.yaml": "name: trading\ndisplay_name: Trading Expert\nidentity: You are a trading expert.\nfocus:\n  - order handling\n  - risk management\n",
+				".review-bot/personas/crypto.yaml":  "name: crypto\ndisplay_name: Crypto Expert\nidentity: You are a cryptography expert.\nfocus:\n  - key management\n  - encryption\n",
 			},
 		}
 		personas, err := LoadRepoPersonas(ctx, client, "owner", "repo")
@@ -176,16 +162,14 @@ focus:
 
 	t.Run("skips invalid persona files", func(t *testing.T) {
 		client := &mockGiteaClient{
-			contents: map[string][]ContentEntry{
+			contents: map[string][]vcs.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/valid.yaml":   "name: valid\nidentity: Valid persona\n",
 				".review-bot/personas/invalid.yaml": "not valid yaml: [broken",
 			},
 		}
@@ -193,7 +177,6 @@ identity: Valid persona
 		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))
 		}
@@ -204,7 +187,7 @@ identity: Valid persona
 
 	t.Run("skips non-yaml files", func(t *testing.T) {
 		client := &mockGiteaClient{
-			contents: map[string][]ContentEntry{
+			contents: map[string][]vcs.ContentEntry{
 				RepoPersonaPath: {
 					{Name: "persona.yaml", Path: ".review-bot/personas/persona.yaml", Type: "file"},
 					{Name: "README.md", Path: ".review-bot/personas/README.md", Type: "file"},
@@ -212,10 +195,8 @@ identity: Valid persona
 				},
 			},
 			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.",
+				".review-bot/personas/persona.yaml": "name: test\nidentity: Test persona\n",
+				".review-bot/personas/README.md":    "# Personas\n\nPut your personas here.",
 			},
 		}
 		personas, err := LoadRepoPersonas(ctx, client, "owner", "repo")
@@ -229,16 +210,14 @@ identity: Test persona
 
 	t.Run("skips subdirectories", func(t *testing.T) {
 		client := &mockGiteaClient{
-			contents: map[string][]ContentEntry{
+			contents: map[string][]vcs.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
-`,
+				".review-bot/personas/persona.yaml": "name: test\nidentity: Test persona\n",
 			},
 		}
 		personas, err := LoadRepoPersonas(ctx, client, "owner", "repo")
@@ -265,16 +244,14 @@ identity: Test persona
 
 	t.Run("skips files that fail to fetch", func(t *testing.T) {
 		client := &mockGiteaClient{
-			contents: map[string][]ContentEntry{
+			contents: map[string][]vcs.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
-`,
+				".review-bot/personas/good.yaml": "name: good\nidentity: Good persona\n",
 			},
 			fileErr: map[string]error{
 				".review-bot/personas/bad.yaml": errors.New("HTTP 500: internal server error"),
@@ -290,27 +267,23 @@ identity: Good persona
 	})
 
 	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{
+			contents: map[string][]vcs.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,
+				".review-bot/personas/normal.yaml": "name: normal\nidentity: Normal sized persona\n",
+				".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))
 		}
@@ -370,7 +343,6 @@ func TestGetBuiltinPersonasMap(t *testing.T) {
 		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 {
@@ -378,7 +350,6 @@ func TestGetBuiltinPersonasMap(t *testing.T) {
 		}
 	}
 
-	// Verify personas are valid
 	for name, p := range personas {
 		if p.Name != name {
 			t.Errorf("persona %q has mismatched name %q", name, p.Name)
@@ -422,8 +393,6 @@ func TestIsNotFoundError(t *testing.T) {
 		{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},

vcs/check_test.go

@@ -0,0 +1,27 @@
+//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)

vcs/interfaces.go

@@ -0,0 +1,43 @@
+// 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)
+	GetFileContentAtRef(ctx context.Context, owner, repo, path, ref string) (string, error)
+	GetCommitStatuses(ctx context.Context, owner, repo, sha string) ([]CommitStatus, 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
+	DismissReview(ctx context.Context, owner, repo string, number int, reviewID int64, message string) 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
+}

vcs/types.go

@@ -0,0 +1,98 @@
+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"
+)
+
+// BaseRef identifies the target branch of a pull request.
+type BaseRef struct {
+	Ref string `json:"ref"`
+}
+
+// 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 {
+	Number int     `json:"number"`
+	Title  string  `json:"title"`
+	Body   string  `json:"body"`
+	Head   HeadRef `json:"head"`
+	Base   BaseRef `json:"base"`
+}
+
+// ChangedFile represents a file modified in a PR.
+type ChangedFile struct {
+	Filename string `json:"filename"`
+	Status   string `json:"status"`
+	Patch    string `json:"patch"`
+}
+
+// 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"
+}
+
+// CommitStatus represents a single CI status entry for a commit.
+type CommitStatus struct {
+	Status      string `json:"status"`
+	Context     string `json:"context"`
+	Description string `json:"description"`
+	TargetURL   string `json:"target_url"`
+}
+
+// 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"`
+}

vcs/util.go

@@ -0,0 +1,193 @@
+package vcs
+
+import (
+	"context"
+	"fmt"
+	"strconv"
+	"strings"
+)
+
+const (
+	// maxFilesInPath is the maximum number of files GetAllFilesInPath will fetch.
+	// Prevents unbounded resource consumption on very large directory trees.
+	maxFilesInPath = 10000
+
+	// maxTotalBytesInPath is the maximum total bytes GetAllFilesInPath will accumulate.
+	// Prevents memory exhaustion when fetching large repositories.
+	maxTotalBytesInPath = 100 * 1024 * 1024 // 100 MB
+)
+
+// GetAllFilesInPath recursively fetches all file contents under a path using the
+// provided FileReader. Returns a map of filepath -> content for all files found.
+// If the path points to an empty directory, returns an empty map.
+//
+// This function uses fail-fast error handling: any error from ListContents or
+// GetFileContent aborts the entire traversal and returns the error immediately.
+// This differs from gitea.Client.GetAllFilesInPath, which logs errors and continues.
+// The fail-fast contract ensures callers can trust that a nil error means all files
+// were successfully fetched.
+//
+// Resource limits: the traversal is bounded by maxFilesInPath (file count) and
+// maxTotalBytesInPath (total accumulated bytes). The context is checked before each
+// recursive call and file fetch to respect cancellation.
+func GetAllFilesInPath(ctx context.Context, client FileReader, owner, repo, path string) (map[string]string, error) {
+	results := make(map[string]string)
+	totalBytes := 0
+
+	var walk func(string) error
+	walk = func(dir string) error {
+		if err := ctx.Err(); err != nil {
+			return fmt.Errorf("context canceled during traversal: %w", err)
+		}
+
+		entries, err := client.ListContents(ctx, owner, repo, dir)
+		if err != nil {
+			return fmt.Errorf("list contents %q: %w", dir, err)
+		}
+
+		for _, entry := range entries {
+			if err := ctx.Err(); err != nil {
+				return fmt.Errorf("context canceled during traversal: %w", err)
+			}
+
+			switch entry.Type {
+			case "file":
+				if len(results) >= maxFilesInPath {
+					return fmt.Errorf("exceeded max file count (%d) in path %q", maxFilesInPath, path)
+				}
+
+				content, err := client.GetFileContent(ctx, owner, repo, entry.Path, "")
+				if err != nil {
+					return fmt.Errorf("get file %q: %w", entry.Path, err)
+				}
+
+				totalBytes += len(content)
+				if totalBytes > maxTotalBytesInPath {
+					return fmt.Errorf("exceeded max total bytes (%d) in path %q", maxTotalBytesInPath, path)
+				}
+
+				results[entry.Path] = content
+			case "dir":
+				if err := walk(entry.Path); err != nil {
+					return err
+				}
+			}
+		}
+		return nil
+	}
+
+	if err := walk(path); err != nil {
+		return nil, err
+	}
+	return results, nil
+}
+
+// BuildLineToPositionMap parses a unified diff and returns a map of
+// filename -> (new line number -> diff position). The diff position is a
+// 1-indexed offset from the @@ hunk header line for each file.
+// Only lines that appear in the new file (context lines and additions) are mapped.
+// Deletion-only lines are not included.
+func BuildLineToPositionMap(diff string) map[string]map[int]int {
+	result := make(map[string]map[int]int)
+
+	lines := strings.Split(diff, "\n")
+	var currentFile string
+	var position int
+	var newLine int
+
+	for _, line := range lines {
+		// Detect new file in diff
+		if strings.HasPrefix(line, "+++ b/") {
+			currentFile = strings.TrimPrefix(line, "+++ b/")
+			position = 0
+			newLine = 0
+			if result[currentFile] == nil {
+				result[currentFile] = make(map[int]int)
+			}
+			continue
+		}
+
+		// Skip --- lines (old file header)
+		if strings.HasPrefix(line, "--- ") {
+			continue
+		}
+
+		// Skip diff --git lines
+		if strings.HasPrefix(line, "diff --git") {
+			continue
+		}
+
+		// Skip index lines
+		if strings.HasPrefix(line, "index ") {
+			continue
+		}
+
+		// Parse hunk headers
+		if strings.HasPrefix(line, "@@") {
+			position++
+			// Extract new file start line from @@ -a,b +c,d @@
+			newLine = parseHunkNewStart(line)
+			continue
+		}
+
+		// We need a current file to map lines
+		if currentFile == "" {
+			continue
+		}
+
+		// Skip "\ No newline at end of file" markers — these are git diff
+		// metadata and not part of the file content.
+		if strings.HasPrefix(line, `\`) {
+			continue
+		}
+
+		// Process diff content lines
+		if strings.HasPrefix(line, "+") {
+			position++
+			result[currentFile][newLine] = position
+			newLine++
+		} else if strings.HasPrefix(line, "-") {
+			position++
+			// Deletion lines don't map to new line numbers
+		} else if strings.HasPrefix(line, " ") {
+			// Context line (space-prefixed).
+			// Only map if position > 0, which means we've seen a hunk header.
+			// Lines before the first hunk header (position == 0) are not part
+			// of any diff hunk and should be skipped.
+			if position > 0 {
+				position++
+				result[currentFile][newLine] = position
+				newLine++
+			}
+		}
+	}
+
+	return result
+}
+
+// parseHunkNewStart extracts the new-file starting line number from a hunk header.
+// Format: @@ -old_start[,old_count] +new_start[,new_count] @@
+func parseHunkNewStart(hunkLine string) int {
+	// Find the +N part
+	plusIdx := strings.Index(hunkLine, "+")
+	if plusIdx < 0 {
+		return 1
+	}
+	rest := hunkLine[plusIdx+1:]
+
+	// Find the end of the number (first non-digit after +)
+	endIdx := 0
+	for endIdx < len(rest) && rest[endIdx] >= '0' && rest[endIdx] <= '9' {
+		endIdx++
+	}
+
+	if endIdx == 0 {
+		return 1
+	}
+
+	n, err := strconv.Atoi(rest[:endIdx])
+	if err != nil {
+		return 1
+	}
+	return n
+}

vcs/util_test.go

@@ -0,0 +1,331 @@
+package vcs_test
+
+import (
+	"context"
+	"fmt"
+	"strings"
+	"testing"
+
+	"gitea.weiker.me/rodin/review-bot/vcs"
+)
+
+// mockFileReader implements vcs.FileReader for testing.
+type mockFileReader struct {
+	contents map[string][]vcs.ContentEntry // path -> entries
+	files    map[string]string             // path -> content
+}
+
+func (m *mockFileReader) GetFileContent(ctx context.Context, owner, repo, path, ref string) (string, error) {
+	content, ok := m.files[path]
+	if !ok {
+		return "", fmt.Errorf("HTTP 404: file not found: %s", path)
+	}
+	return content, nil
+}
+
+func (m *mockFileReader) ListContents(ctx context.Context, owner, repo, path string) ([]vcs.ContentEntry, error) {
+	entries, ok := m.contents[path]
+	if !ok {
+		return nil, fmt.Errorf("HTTP 404: path not found: %s", path)
+	}
+	return entries, nil
+}
+
+func TestGetAllFilesInPath(t *testing.T) {
+	ctx := context.Background()
+
+	t.Run("empty directory", func(t *testing.T) {
+		client := &mockFileReader{
+			contents: map[string][]vcs.ContentEntry{
+				"src": {},
+			},
+		}
+		result, err := vcs.GetAllFilesInPath(ctx, client, "owner", "repo", "src")
+		if err != nil {
+			t.Fatalf("unexpected error: %v", err)
+		}
+		if len(result) != 0 {
+			t.Errorf("expected empty map, got %d entries", len(result))
+		}
+	})
+
+	t.Run("flat directory", func(t *testing.T) {
+		client := &mockFileReader{
+			contents: map[string][]vcs.ContentEntry{
+				"src": {
+					{Name: "main.go", Path: "src/main.go", Type: "file"},
+					{Name: "util.go", Path: "src/util.go", Type: "file"},
+				},
+			},
+			files: map[string]string{
+				"src/main.go": "package main",
+				"src/util.go": "package main\n// util",
+			},
+		}
+		result, err := vcs.GetAllFilesInPath(ctx, client, "owner", "repo", "src")
+		if err != nil {
+			t.Fatalf("unexpected error: %v", err)
+		}
+		if len(result) != 2 {
+			t.Fatalf("expected 2 files, got %d", len(result))
+		}
+		if result["src/main.go"] != "package main" {
+			t.Errorf("main.go content = %q", result["src/main.go"])
+		}
+		if result["src/util.go"] != "package main\n// util" {
+			t.Errorf("util.go content = %q", result["src/util.go"])
+		}
+	})
+
+	t.Run("nested directories", func(t *testing.T) {
+		client := &mockFileReader{
+			contents: map[string][]vcs.ContentEntry{
+				"src": {
+					{Name: "main.go", Path: "src/main.go", Type: "file"},
+					{Name: "pkg", Path: "src/pkg", Type: "dir"},
+				},
+				"src/pkg": {
+					{Name: "lib.go", Path: "src/pkg/lib.go", Type: "file"},
+					{Name: "sub", Path: "src/pkg/sub", Type: "dir"},
+				},
+				"src/pkg/sub": {
+					{Name: "deep.go", Path: "src/pkg/sub/deep.go", Type: "file"},
+				},
+			},
+			files: map[string]string{
+				"src/main.go":         "package main",
+				"src/pkg/lib.go":      "package pkg",
+				"src/pkg/sub/deep.go": "package sub",
+			},
+		}
+		result, err := vcs.GetAllFilesInPath(ctx, client, "owner", "repo", "src")
+		if err != nil {
+			t.Fatalf("unexpected error: %v", err)
+		}
+		if len(result) != 3 {
+			t.Fatalf("expected 3 files, got %d", len(result))
+		}
+		if result["src/main.go"] != "package main" {
+			t.Errorf("main.go content = %q", result["src/main.go"])
+		}
+		if result["src/pkg/lib.go"] != "package pkg" {
+			t.Errorf("lib.go content = %q", result["src/pkg/lib.go"])
+		}
+		if result["src/pkg/sub/deep.go"] != "package sub" {
+			t.Errorf("deep.go content = %q", result["src/pkg/sub/deep.go"])
+		}
+	})
+
+	t.Run("mixed files and dirs", func(t *testing.T) {
+		client := &mockFileReader{
+			contents: map[string][]vcs.ContentEntry{
+				"root": {
+					{Name: "README.md", Path: "root/README.md", Type: "file"},
+					{Name: "docs", Path: "root/docs", Type: "dir"},
+					{Name: "config.yaml", Path: "root/config.yaml", Type: "file"},
+				},
+				"root/docs": {
+					{Name: "guide.md", Path: "root/docs/guide.md", Type: "file"},
+				},
+			},
+			files: map[string]string{
+				"root/README.md":     "# Hello",
+				"root/config.yaml":   "key: value",
+				"root/docs/guide.md": "## Guide",
+			},
+		}
+		result, err := vcs.GetAllFilesInPath(ctx, client, "owner", "repo", "root")
+		if err != nil {
+			t.Fatalf("unexpected error: %v", err)
+		}
+		if len(result) != 3 {
+			t.Fatalf("expected 3 files, got %d", len(result))
+		}
+		if result["root/README.md"] != "# Hello" {
+			t.Errorf("README content = %q", result["root/README.md"])
+		}
+		if result["root/docs/guide.md"] != "## Guide" {
+			t.Errorf("guide content = %q", result["root/docs/guide.md"])
+		}
+	})
+}
+
+func TestBuildLineToPositionMap(t *testing.T) {
+	t.Run("single hunk", func(t *testing.T) {
+		diff := "diff --git a/file.go b/file.go\nindex abc..def 100644\n--- a/file.go\n+++ b/file.go\n@@ -1,3 +1,4 @@\n package main\n \n+// new comment\n func main() {}\n"
+		result := vcs.BuildLineToPositionMap(diff)
+		fileMap, ok := result["file.go"]
+		if !ok {
+			t.Fatal("expected file.go in result")
+		}
+		// Hunk header @@ is position 1
+		// Line 1: " package main" -> position 2
+		if fileMap[1] != 2 {
+			t.Errorf("line 1 position = %d, want 2", fileMap[1])
+		}
+		// Line 2: " " (context) -> position 3
+		if fileMap[2] != 3 {
+			t.Errorf("line 2 position = %d, want 3", fileMap[2])
+		}
+		// Line 3: "+// new comment" -> position 4
+		if fileMap[3] != 4 {
+			t.Errorf("line 3 position = %d, want 4", fileMap[3])
+		}
+		// Line 4: " func main() {}" -> position 5
+		if fileMap[4] != 5 {
+			t.Errorf("line 4 position = %d, want 5", fileMap[4])
+		}
+	})
+
+	t.Run("multi hunk", func(t *testing.T) {
+		diff := "diff --git a/file.go b/file.go\n--- a/file.go\n+++ b/file.go\n@@ -1,3 +1,3 @@\n package main\n \n-// old\n+// new\n@@ -10,3 +10,4 @@\n func foo() {\n+\t// added\n \treturn\n }\n"
+		result := vcs.BuildLineToPositionMap(diff)
+		fileMap, ok := result["file.go"]
+		if !ok {
+			t.Fatal("expected file.go in result")
+		}
+		// First hunk: @@ is position 1
+		// Line 1: " package main" -> position 2
+		if fileMap[1] != 2 {
+			t.Errorf("line 1 position = %d, want 2", fileMap[1])
+		}
+		// Line 3: "+// new" -> position 5 (after " ", "-// old" at pos 3,4)
+		if fileMap[3] != 5 {
+			t.Errorf("line 3 position = %d, want 5", fileMap[3])
+		}
+		// Second hunk: @@ is position 6
+		// Line 10: " func foo() {" -> position 7
+		if fileMap[10] != 7 {
+			t.Errorf("line 10 position = %d, want 7", fileMap[10])
+		}
+		// Line 11: "+\t// added" -> position 8
+		if fileMap[11] != 8 {
+			t.Errorf("line 11 position = %d, want 8", fileMap[11])
+		}
+	})
+
+	t.Run("deletion lines not in map", func(t *testing.T) {
+		diff := "diff --git a/file.go b/file.go\n--- a/file.go\n+++ b/file.go\n@@ -1,4 +1,3 @@\n package main\n \n-// deleted line\n func main() {}\n"
+		result := vcs.BuildLineToPositionMap(diff)
+		fileMap, ok := result["file.go"]
+		if !ok {
+			t.Fatal("expected file.go in result")
+		}
+		// Line 1: " package main" -> position 2
+		if fileMap[1] != 2 {
+			t.Errorf("line 1 position = %d, want 2", fileMap[1])
+		}
+		// Line 3 in new file: " func main() {}" -> position 5 (after deletion at pos 4)
+		if fileMap[3] != 5 {
+			t.Errorf("line 3 position = %d, want 5", fileMap[3])
+		}
+		// Should only have 3 entries (lines 1, 2, 3 of new file)
+		if len(fileMap) != 3 {
+			t.Errorf("expected 3 mapped lines, got %d: %v", len(fileMap), fileMap)
+		}
+	})
+
+	t.Run("multiple files", func(t *testing.T) {
+		diff := "diff --git a/a.go b/a.go\n--- a/a.go\n+++ b/a.go\n@@ -1,2 +1,3 @@\n package a\n \n+// file a\ndiff --git a/b.go b/b.go\n--- a/b.go\n+++ b/b.go\n@@ -1,2 +1,3 @@\n package b\n \n+// file b\n"
+		result := vcs.BuildLineToPositionMap(diff)
+		if len(result) != 2 {
+			t.Fatalf("expected 2 files, got %d", len(result))
+		}
+		aMap, ok := result["a.go"]
+		if !ok {
+			t.Fatal("expected a.go in result")
+		}
+		bMap, ok := result["b.go"]
+		if !ok {
+			t.Fatal("expected b.go in result")
+		}
+		// a.go line 3: "+// file a" -> position 4
+		if aMap[3] != 4 {
+			t.Errorf("a.go line 3 position = %d, want 4", aMap[3])
+		}
+		// b.go line 3: "+// file b" -> position 4
+		if bMap[3] != 4 {
+			t.Errorf("b.go line 3 position = %d, want 4", bMap[3])
+		}
+	})
+}
+
+func TestGetAllFilesInPath_ErrorPropagation(t *testing.T) {
+	ctx := context.Background()
+
+	t.Run("ListContents error propagates", func(t *testing.T) {
+		client := &mockFileReader{
+			contents: map[string][]vcs.ContentEntry{
+				// "src" not in map, so ListContents will fail
+			},
+		}
+		_, err := vcs.GetAllFilesInPath(ctx, client, "owner", "repo", "src")
+		if err == nil {
+			t.Fatal("expected error, got nil")
+		}
+		if !strings.Contains(err.Error(), "list contents") {
+			t.Errorf("expected error about list contents, got: %v", err)
+		}
+	})
+
+	t.Run("GetFileContent error propagates", func(t *testing.T) {
+		client := &mockFileReader{
+			contents: map[string][]vcs.ContentEntry{
+				"src": {
+					{Name: "main.go", Path: "src/main.go", Type: "file"},
+				},
+			},
+			files: map[string]string{
+				// "src/main.go" not in files map, so GetFileContent will fail
+			},
+		}
+		_, err := vcs.GetAllFilesInPath(ctx, client, "owner", "repo", "src")
+		if err == nil {
+			t.Fatal("expected error, got nil")
+		}
+		if !strings.Contains(err.Error(), "get file") {
+			t.Errorf("expected error about get file, got: %v", err)
+		}
+	})
+
+	t.Run("nested ListContents error propagates", func(t *testing.T) {
+		client := &mockFileReader{
+			contents: map[string][]vcs.ContentEntry{
+				"src": {
+					{Name: "pkg", Path: "src/pkg", Type: "dir"},
+				},
+				// "src/pkg" not in map, so recursive ListContents will fail
+			},
+		}
+		_, err := vcs.GetAllFilesInPath(ctx, client, "owner", "repo", "src")
+		if err == nil {
+			t.Fatal("expected error, got nil")
+		}
+		if !strings.Contains(err.Error(), "list contents") {
+			t.Errorf("expected error about list contents, got: %v", err)
+		}
+	})
+
+	t.Run("canceled context propagates", func(t *testing.T) {
+		ctx, cancel := context.WithCancel(context.Background())
+		cancel() // Cancel immediately
+
+		client := &mockFileReader{
+			contents: map[string][]vcs.ContentEntry{
+				"src": {
+					{Name: "main.go", Path: "src/main.go", Type: "file"},
+				},
+			},
+			files: map[string]string{
+				"src/main.go": "package main",
+			},
+		}
+		_, err := vcs.GetAllFilesInPath(ctx, client, "owner", "repo", "src")
+		if err == nil {
+			t.Fatal("expected error from canceled context, got nil")
+		}
+		if !strings.Contains(err.Error(), "context canceled") {
+			t.Errorf("expected context cancellation error, got: %v", err)
+		}
+	})
+}