Compare commits

..

1 Commits

Author SHA1 Message Date
Rodin a36c3da05b feat(persona): add role-based review personas
PR Ready Gate / clear-labels (pull_request) Successful in 2s
CI / test (pull_request) Successful in 9m33s
CI / review (/anthropic/v1, anthropic--claude-4.6-sonnet, sonnet, anthropic, SONNET_REVIEW_TOKEN) (pull_request) Successful in 10m0s
CI / review (/openai/v1, gpt-5, security, openai, SECURITY_REVIEW.md, SECURITY_REVIEW_TOKEN) (pull_request) Successful in 10m47s
CI / review (/openai/v1, gpt-5, gpt, openai, GPT_REVIEW_TOKEN) (pull_request) Successful in 11m34s
Add persona system for specialized review roles. Each persona defines:
- A specific review focus (security, architecture, documentation)
- Custom system prompt additions
- Personality/tone adjustments

Built-in personas: security, architect, docs
Custom personas: load from JSON via persona-file flag

Includes workspace validation to prevent path traversal attacks.

Closes #51
2026-05-10 09:12:41 -07:00
23 changed files with 119 additions and 2752 deletions
+6 -33
View File
@@ -26,40 +26,18 @@ inputs:
required: false required: false
default: '' default: ''
llm-base-url: llm-base-url:
description: 'OpenAI-compatible LLM API base URL (not required for aicore provider)' description: 'OpenAI-compatible LLM API base URL'
required: false required: true
default: ''
llm-api-key: llm-api-key:
description: 'LLM API key (not required for aicore provider)' description: 'LLM API key'
required: false required: true
default: ''
llm-model: llm-model:
description: 'LLM model name' description: 'LLM model name'
required: true required: true
llm-provider: llm-provider:
description: 'LLM API provider: openai, anthropic, or aicore (default openai)' description: 'LLM API provider: openai or anthropic (default openai)'
required: false required: false
default: 'openai' 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: conventions-file:
description: 'Path to conventions file in the repo (e.g. CLAUDE.md)' description: 'Path to conventions file in the repo (e.g. CLAUDE.md)'
required: false required: false
@@ -101,7 +79,7 @@ inputs:
required: false required: false
default: '' default: ''
persona-file: persona-file:
description: 'Path to custom persona JSON file' description: 'Path to persona JSON file with custom review focus'
required: false required: false
default: '' default: ''
@@ -187,11 +165,6 @@ runs:
SYSTEM_PROMPT_FILE: ${{ inputs.system-prompt-file }} SYSTEM_PROMPT_FILE: ${{ inputs.system-prompt-file }}
PERSONA: ${{ inputs.persona }} PERSONA: ${{ inputs.persona }}
PERSONA_FILE: ${{ inputs.persona-file }} 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: ${{ inputs.aicore-resource-group }}
run: | run: |
ARGS="" ARGS=""
if [ "${{ inputs.dry-run }}" = "true" ]; then if [ "${{ inputs.dry-run }}" = "true" ]; then
+11 -10
View File
@@ -18,10 +18,8 @@ jobs:
- run: go vet ./... - run: go vet ./...
- run: go build -o review-bot ./cmd/review-bot - run: go build -o review-bot ./cmd/review-bot
# Self-review using native SAP AI Core provider # Self-review: builds from source since we're pre-release
# Models must match SAP AI Core deployments # Models configured to 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: review:
runs-on: ubuntu-24.04 runs-on: ubuntu-24.04
if: github.event_name == 'pull_request' if: github.event_name == 'pull_request'
@@ -31,12 +29,18 @@ jobs:
include: include:
- name: sonnet - name: sonnet
token_secret: SONNET_REVIEW_TOKEN token_secret: SONNET_REVIEW_TOKEN
provider: anthropic
llm_path: /anthropic/v1
model: anthropic--claude-4.6-sonnet model: anthropic--claude-4.6-sonnet
- name: gpt - name: gpt
token_secret: GPT_REVIEW_TOKEN token_secret: GPT_REVIEW_TOKEN
provider: openai
llm_path: /openai/v1
model: gpt-5 model: gpt-5
- name: security - name: security
token_secret: SECURITY_REVIEW_TOKEN token_secret: SECURITY_REVIEW_TOKEN
provider: openai
llm_path: /openai/v1
model: gpt-5 model: gpt-5
system_prompt_file: SECURITY_REVIEW.md system_prompt_file: SECURITY_REVIEW.md
steps: steps:
@@ -52,13 +56,10 @@ jobs:
PR_NUMBER: ${{ github.event.pull_request.number }} PR_NUMBER: ${{ github.event.pull_request.number }}
REVIEWER_TOKEN: ${{ secrets[matrix.token_secret] }} REVIEWER_TOKEN: ${{ secrets[matrix.token_secret] }}
REVIEWER_NAME: ${{ matrix.name }} REVIEWER_NAME: ${{ matrix.name }}
LLM_PROVIDER: aicore LLM_BASE_URL: ${{ secrets.LLM_BASE_URL }}${{ matrix.llm_path }}
LLM_API_KEY: ${{ secrets.LLM_API_KEY }}
LLM_MODEL: ${{ matrix.model }} LLM_MODEL: ${{ matrix.model }}
AICORE_CLIENT_ID: ${{ secrets.AICORE_CLIENT_ID }} LLM_PROVIDER: ${{ matrix.provider }}
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" CONVENTIONS_FILE: "CONVENTIONS.md"
PATTERNS_REPO: "rodin/go-patterns" PATTERNS_REPO: "rodin/go-patterns"
PATTERNS_FILES: "README.md,patterns/" PATTERNS_FILES: "README.md,patterns/"
+1 -19
View File
@@ -2,26 +2,8 @@
## Language & Dependencies ## Language & Dependencies
- Go standard library only — no external dependencies.
- Target the latest stable Go release. - Target the latest stable Go release.
- **STRICT ALLOWLIST:** Only packages listed below may be imported. No exceptions.
### Approved Third-Party Packages
| Package | Use Case | Scope |
|---------|----------|-------|
| `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.**
Transitive dependencies of approved packages are automatically allowed.
To request a new dependency:
1. Open a PR that ONLY updates this table
2. Requires explicit approval from Aaron
3. After merge, a separate PR may use the package
*Enforcement: `scripts/check-deps.sh` parses this table — update only here.*
## Error Handling ## Error Handling
+1 -7
View File
@@ -1,4 +1,4 @@
.PHONY: build test test-integration lint clean coverage check-deps precommit .PHONY: build test test-integration lint clean coverage
build: build:
go build -o review-bot ./cmd/review-bot/ go build -o review-bot ./cmd/review-bot/
@@ -12,15 +12,9 @@ test-integration:
lint: lint:
go vet ./... go vet ./...
check-deps:
@./scripts/check-deps.sh
clean: clean:
rm -f review-bot rm -f review-bot
coverage: coverage:
go test -coverprofile=coverage.out ./... go test -coverprofile=coverage.out ./...
go tool cover -func=coverage.out go tool cover -func=coverage.out
# Precommit runs all checks required before pushing
precommit: check-deps lint test
+10 -44
View File
@@ -4,12 +4,12 @@ AI-powered code review bot for Gitea pull requests. Fetches diff + context, send
## Features ## Features
- **Multi-provider**: OpenAI-compatible, Anthropic Messages API, and SAP AI Core - **Multi-provider**: OpenAI-compatible and Anthropic Messages API
- **Context-aware**: Fetches full file content, conventions, language patterns, CI status - **Context-aware**: Fetches full file content, conventions, language patterns, CI status
- **Smart budget**: Automatically trims context to fit model token limits - **Smart budget**: Automatically trims context to fit model token limits
- **Idempotent reviews**: Posts new review, then cleans up stale ones (one review per bot) - **Idempotent reviews**: Posts new review, then cleans up stale ones (one review per bot)
- **Custom prompts**: Load additional instructions from a file (e.g. security-focused review) - **Custom prompts**: Load additional instructions from a file (e.g. security-focused review)
- **Minimal dependencies**: Go stdlib + `gopkg.in/yaml.v3` only - **Zero dependencies**: Go stdlib only
## Quick Start: Composite Action ## Quick Start: Composite Action
@@ -168,56 +168,28 @@ Prints the review to CI logs without posting to the PR. Useful for testing promp
llm-provider: anthropic llm-provider: anthropic
``` ```
### Using SAP AI Core
For SAP environments with AI Core deployments, use the `aicore` provider for native authentication:
```yaml
- uses: https://gitea.weiker.me/rodin/review-bot/.gitea/actions/review@v0.1.0
with:
reviewer-token: ${{ secrets.REVIEW_TOKEN }}
reviewer-name: aicore-review
llm-model: anthropic--claude-4.6-sonnet # or gpt-5
llm-provider: aicore
aicore-client-id: ${{ secrets.AICORE_CLIENT_ID }}
aicore-client-secret: ${{ secrets.AICORE_CLIENT_SECRET }}
aicore-auth-url: ${{ secrets.AICORE_AUTH_URL }}
aicore-api-url: ${{ secrets.AICORE_API_URL }}
aicore-resource-group: default
```
AI Core handles OAuth token management and deployment discovery automatically. Model names must match the deployment name in AI Core (e.g. `anthropic--claude-4.6-sonnet`, `gpt-5`).
## Action Inputs ## Action Inputs
| Input | Required | Default | Description | | Input | Required | Default | Description |
|-------|----------|---------|-------------| |-------|----------|---------|-------------|
| `reviewer-token` | Yes | — | Gitea token for posting reviews (needs `write:issue`, `write:repository`) | | `reviewer-token` | Yes | — | Gitea token for posting reviews (needs `write:issue`, `write:repository`) |
| `reviewer-name` | No | `""` | Logical identity for this reviewer. Used as sentinel for idempotent cleanup. Set this when running multiple review bots on the same PR. | | `reviewer-name` | No | `""` | Logical identity for this reviewer. Used as sentinel for idempotent cleanup. Set this when running multiple review bots on the same PR. |
| `llm-base-url` | No* | `""` | LLM API base URL (required unless using aicore provider) | | `llm-base-url` | Yes | — | LLM API base URL |
| `llm-api-key` | No* | `""` | LLM API key (required unless using aicore provider) | | `llm-api-key` | Yes | — | LLM API key |
| `llm-model` | Yes | — | Model name | | `llm-model` | Yes | — | Model name |
| `llm-provider` | No | `openai` | API provider: `openai`, `anthropic`, or `aicore` | | `llm-provider` | No | `openai` | API provider: `openai` or `anthropic` |
| `aicore-client-id` | No** | `""` | SAP AI Core client ID |
| `aicore-client-secret` | No** | `""` | SAP AI Core client secret |
| `aicore-auth-url` | No** | `""` | SAP AI Core authentication URL |
| `aicore-api-url` | No** | `""` | SAP AI Core API URL |
| `aicore-resource-group` | No | `default` | SAP AI Core resource group |
| `conventions-file` | No | `""` | Path to coding conventions file in the repo | | `conventions-file` | No | `""` | Path to coding conventions file in the repo |
| `patterns-repo` | No | `""` | Comma-separated repos with language patterns (e.g. `rodin/go-patterns`) | | `patterns-repo` | No | `""` | Comma-separated repos with language patterns (e.g. `rodin/go-patterns`) |
| `patterns-files` | No | `README.md` | Files/directories to fetch from pattern repos | | `patterns-files` | No | `README.md` | Files/directories to fetch from pattern repos |
| `system-prompt-file` | No | `""` | Local file with additional system prompt instructions | | `system-prompt-file` | No | `""` | Local file with additional system prompt instructions |
| `persona` | No | `""` | Built-in persona name (security, architect, docs) | | `persona` | No | `""` | Built-in persona name (security, architect, docs) |
| `persona-file` | No | `""` | Path to persona file (YAML or JSON) with custom review focus | | `persona-file` | No | `""` | Path to persona JSON file with custom review focus |
| `temperature` | No | `0` | LLM temperature (0 = server default) | | `temperature` | No | `0` | LLM temperature (0 = server default) |
| `timeout` | No | `300` | LLM request timeout in seconds | | `timeout` | No | `300` | LLM request timeout in seconds |
| `dry-run` | No | `false` | Print review to stdout instead of posting | | `dry-run` | No | `false` | Print review to stdout instead of posting |
| `update-existing` | No | `true` | Delete previous review from same bot before posting. Accepts: true/1/yes or false/0/no | | `update-existing` | No | `true` | Delete previous review from same bot before posting. Accepts: true/1/yes or false/0/no |
| `version` | No | `latest` | review-bot version to install | | `version` | No | `latest` | review-bot version to install |
*Required for `openai` and `anthropic` providers, not for `aicore`.
**Required only for `aicore` provider.
## Runner Requirements ## Runner Requirements
The composite action requires these tools on the runner: The composite action requires these tools on the runner:
@@ -437,9 +409,9 @@ ignore:
- Documentation formatting - Documentation formatting
severity: severity:
major: "Bugs that cause incorrect positions, fills, or money calculations" major: Bugs that cause incorrect positions, fills, or money calculations
minor: "Edge cases that could cause issues under unusual conditions" minor: Edge cases that could cause issues under unusual conditions
nit: "Clarity improvements for domain logic" nit: Clarity improvements for domain logic
``` ```
Use it in CI: Use it in CI:
@@ -452,13 +424,7 @@ Use it in CI:
... ...
``` ```
YAML is the recommended format for personas because it supports: JSON format is also supported for backwards compatibility.
- Multi-line strings with `|` blocks (cleaner identity definitions)
- Comments for documentation
- More readable arrays and nested structures
JSON is also supported for backwards compatibility—just use `.json` extension.
### Persona vs system-prompt-file ### Persona vs system-prompt-file
+28 -97
View File
@@ -69,15 +69,9 @@ func main() {
dryRun := flag.Bool("dry-run", false, "Print review to stdout instead of posting") dryRun := flag.Bool("dry-run", false, "Print review to stdout instead of posting")
llmTemp := flag.Float64("llm-temperature", envOrDefaultFloat("LLM_TEMPERATURE", 0), "LLM temperature (0 = server default)") llmTemp := flag.Float64("llm-temperature", envOrDefaultFloat("LLM_TEMPERATURE", 0), "LLM temperature (0 = server default)")
llmTimeout := flag.Int("llm-timeout", envOrDefaultInt("LLM_TIMEOUT", 300), "LLM request timeout in seconds (default 300)") llmTimeout := flag.Int("llm-timeout", envOrDefaultInt("LLM_TIMEOUT", 300), "LLM request timeout in seconds (default 300)")
llmProvider := flag.String("llm-provider", envOrDefault("LLM_PROVIDER", "openai"), "LLM API provider: openai, anthropic, or aicore") llmProvider := flag.String("llm-provider", envOrDefault("LLM_PROVIDER", "openai"), "LLM API provider: openai or anthropic")
personaName := flag.String("persona", envOrDefault("PERSONA", ""), "Built-in persona name (security, architect, docs)") personaName := flag.String("persona", envOrDefault("PERSONA", ""), "Built-in persona name (security, architect, docs)")
personaFile := flag.String("persona-file", envOrDefault("PERSONA_FILE", ""), "Path to persona JSON file") personaFile := flag.String("persona-file", envOrDefault("PERSONA_FILE", ""), "Path to persona JSON file")
// AI Core specific flags (only used when provider=aicore)
aicoreClientID := flag.String("aicore-client-id", envOrDefault("AICORE_CLIENT_ID", ""), "SAP AI Core client ID (for provider=aicore)")
aicoreClientSecret := flag.String("aicore-client-secret", envOrDefault("AICORE_CLIENT_SECRET", ""), "SAP AI Core client secret (for provider=aicore)")
aicoreAuthURL := flag.String("aicore-auth-url", envOrDefault("AICORE_AUTH_URL", ""), "SAP AI Core auth URL (for provider=aicore)")
aicoreAPIURL := flag.String("aicore-api-url", envOrDefault("AICORE_API_URL", ""), "SAP AI Core API URL (for provider=aicore)")
aicoreResourceGroup := flag.String("aicore-resource-group", envOrDefault("AICORE_RESOURCE_GROUP", "default"), "SAP AI Core resource group (for provider=aicore)")
flag.Parse() flag.Parse()
@@ -92,20 +86,10 @@ func main() {
slog.Info("review-bot starting", "version", version) slog.Info("review-bot starting", "version", version)
// Validate required fields // Validate required fields
// For aicore provider, llm-base-url and llm-api-key are not required if *giteaURL == "" || *repo == "" || *prNum == "" || *reviewerToken == "" ||
isAICore := llm.Provider(*llmProvider) == llm.ProviderAICore *llmBaseURL == "" || *llmAPIKey == "" || *llmModel == "" {
if *giteaURL == "" || *repo == "" || *prNum == "" || *reviewerToken == "" || *llmModel == "" {
fmt.Fprintf(os.Stderr, "Error: missing required flags or environment variables\n\n") fmt.Fprintf(os.Stderr, "Error: missing required flags or environment variables\n\n")
fmt.Fprintf(os.Stderr, "Required: --gitea-url, --repo, --pr, --reviewer-token, --llm-model\n") fmt.Fprintf(os.Stderr, "Required: --gitea-url, --repo, --pr, --reviewer-token, --llm-base-url, --llm-api-key, --llm-model\n")
os.Exit(1)
}
if !isAICore && (*llmBaseURL == "" || *llmAPIKey == "") {
fmt.Fprintf(os.Stderr, "Error: --llm-base-url and --llm-api-key are required for provider=%s\n", *llmProvider)
os.Exit(1)
}
if isAICore && (*aicoreClientID == "" || *aicoreClientSecret == "" || *aicoreAuthURL == "" || *aicoreAPIURL == "") {
fmt.Fprintf(os.Stderr, "Error: AI Core credentials required for provider=aicore\n\n")
fmt.Fprintf(os.Stderr, "Required: --aicore-client-id, --aicore-client-secret, --aicore-auth-url, --aicore-api-url\n")
os.Exit(1) os.Exit(1)
} }
@@ -115,7 +99,29 @@ func main() {
os.Exit(1) os.Exit(1)
} }
// NOTE: Persona loading deferred until after Gitea client init to support repo personas // Load persona if specified
var persona *review.Persona
if *personaName != "" {
var err error
persona, err = review.LoadBuiltinPersona(*personaName)
if err != nil {
slog.Error("failed to load persona", "persona", *personaName, "error", err)
os.Exit(1)
}
slog.Info("loaded built-in persona", "persona", persona.Name, "display", persona.DisplayName)
} else if *personaFile != "" {
resolvedPath, err := validateWorkspacePath(*personaFile, "persona-file")
if err != nil {
slog.Error("invalid persona-file path", "error", err)
os.Exit(1)
}
persona, err = review.LoadPersona(resolvedPath)
if err != nil {
slog.Error("failed to load persona file", "file", *personaFile, "error", err)
os.Exit(1)
}
slog.Info("loaded persona from file", "file", *personaFile, "persona", persona.Name)
}
// Validate reviewer-name: only safe characters allowed in sentinel // Validate reviewer-name: only safe characters allowed in sentinel
if err := validateReviewerName(*reviewerName); err != nil { if err := validateReviewerName(*reviewerName); err != nil {
@@ -151,17 +157,8 @@ func main() {
switch llm.Provider(*llmProvider) { switch llm.Provider(*llmProvider) {
case llm.ProviderOpenAI, llm.ProviderAnthropic: case llm.ProviderOpenAI, llm.ProviderAnthropic:
llmClient.WithProvider(llm.Provider(*llmProvider)) llmClient.WithProvider(llm.Provider(*llmProvider))
case llm.ProviderAICore:
llmClient.WithAICore(llm.AICoreConfig{
ClientID: *aicoreClientID,
ClientSecret: *aicoreClientSecret,
AuthURL: *aicoreAuthURL,
APIURL: *aicoreAPIURL,
ResourceGroup: *aicoreResourceGroup,
})
slog.Info("using SAP AI Core provider", "resource_group", *aicoreResourceGroup)
default: default:
slog.Error("invalid LLM provider", "provider", *llmProvider, "valid", "openai, anthropic, aicore") slog.Error("invalid LLM provider", "provider", *llmProvider, "valid", "openai, anthropic")
os.Exit(1) os.Exit(1)
} }
if *llmTimeout > 0 { if *llmTimeout > 0 {
@@ -173,43 +170,6 @@ func main() {
ctx, cancel := context.WithTimeout(context.Background(), overallTimeout) ctx, cancel := context.WithTimeout(context.Background(), overallTimeout)
defer cancel() defer cancel()
// Load persona if specified (after Gitea client init to support repo personas)
var persona *review.Persona
if *personaName != "" {
// Try loading from repo first, then fall back to built-in
repoPersonas, err := review.LoadRepoPersonas(ctx, newGiteaClientAdapter(giteaClient), owner, repoName)
if err != nil {
slog.Warn("could not load repo personas", "repo", owner+"/"+repoName, "error", err)
// Continue with built-in personas only.
// NOTE: repoPersonas is nil here, but map indexing on a nil map is safe in Go
// (returns the zero value), so the fallback to built-in below works correctly.
}
if p, ok := repoPersonas[*personaName]; ok {
persona = p
slog.Info("loaded repo persona", "persona", persona.Name, "display", persona.DisplayName, "repo", owner+"/"+repoName)
} else {
// Fall back to built-in
persona, err = review.LoadBuiltinPersona(*personaName)
if err != nil {
slog.Error("failed to load persona", "persona", *personaName, "error", err)
os.Exit(1)
}
slog.Info("loaded built-in persona", "persona", persona.Name, "display", persona.DisplayName)
}
} else if *personaFile != "" {
resolvedPath, err := validateWorkspacePath(*personaFile, "persona-file")
if err != nil {
slog.Error("invalid persona-file path", "error", err)
os.Exit(1)
}
persona, err = review.LoadPersona(resolvedPath)
if err != nil {
slog.Error("failed to load persona file", "file", *personaFile, "error", err)
os.Exit(1)
}
slog.Info("loaded persona from file", "file", *personaFile, "persona", persona.Name)
}
slog.Info("reviewing pull request", "pr", prNumber, "repo", fmt.Sprintf("%s/%s", owner, repoName)) slog.Info("reviewing pull request", "pr", prNumber, "repo", fmt.Sprintf("%s/%s", owner, repoName))
// Step 1: Fetch PR metadata // Step 1: Fetch PR metadata
@@ -797,32 +757,3 @@ func shouldSkipStaleReview(evaluatedSHA, currentSHA string) bool {
} }
return evaluatedSHA != currentSHA return evaluatedSHA != currentSHA
} }
// giteaClientAdapter adapts gitea.Client to review.GiteaClient interface.
type giteaClientAdapter struct {
client *gitea.Client
}
func newGiteaClientAdapter(c *gitea.Client) *giteaClientAdapter {
return &giteaClientAdapter{client: c}
}
func (a *giteaClientAdapter) ListContents(ctx context.Context, owner, repo, path string) ([]review.ContentEntry, error) {
entries, err := a.client.ListContents(ctx, owner, repo, path)
if err != nil {
return nil, err
}
result := make([]review.ContentEntry, len(entries))
for i, e := range entries {
result[i] = review.ContentEntry{
Name: e.Name,
Path: e.Path,
Type: e.Type,
}
}
return result, nil
}
func (a *giteaClientAdapter) GetFileContent(ctx context.Context, owner, repo, filepath string) (string, error) {
return a.client.GetFileContent(ctx, owner, repo, filepath)
}
+6 -6
View File
@@ -103,13 +103,11 @@ func TestValidateWorkspacePath(t *testing.T) {
errMatch: "resolves outside workspace", errMatch: "resolves outside workspace",
}, },
{ {
name: "absolute path normalized to workspace-relative", name: "absolute path gets normalized to relative",
workspace: tmpDir, workspace: tmpDir,
path: "/etc/passwd", path: "/etc/passwd",
wantErr: true, wantErr: true,
// Go 1.21+ filepath.Join normalizes absolute paths: Join("/tmp/x", "/etc/passwd") errMatch: "failed to resolve", // filepath.Join strips leading / making it <workspace>/etc/passwd which doesn't exist
// becomes "/tmp/x/etc/passwd", which is within workspace but doesn't exist.
errMatch: "failed to resolve",
}, },
{ {
name: "nonexistent file", name: "nonexistent file",
@@ -154,6 +152,7 @@ func TestValidateWorkspacePath(t *testing.T) {
} }
} }
func makeReview(id int64, login, state string, stale bool, body string) gitea.Review { func makeReview(id int64, login, state string, stale bool, body string) gitea.Review {
r := gitea.Review{ r := gitea.Review{
ID: id, ID: id,
@@ -165,6 +164,7 @@ func makeReview(id int64, login, state string, stale bool, body string) gitea.Re
return r return r
} }
func TestBuildSupersededBody(t *testing.T) { func TestBuildSupersededBody(t *testing.T) {
original := "# Review\n\nLooks good.\n\n<!-- review-bot:sonnet -->" original := "# Review\n\nLooks good.\n\n<!-- review-bot:sonnet -->"
sentinel := "<!-- review-bot:sonnet -->" sentinel := "<!-- review-bot:sonnet -->"
@@ -734,8 +734,8 @@ func TestExtractSentinelName_EdgeCases(t *testing.T) {
{"<!-- review-bot:sonnet --> rest", "sonnet"}, {"<!-- review-bot:sonnet --> rest", "sonnet"},
{"<!-- review-bot:gpt-review --> rest", "gpt-review"}, {"<!-- review-bot:gpt-review --> rest", "gpt-review"},
{"no sentinel here", "unknown"}, {"no sentinel here", "unknown"},
{"<!-- review-bot:", "unknown"}, // prefix but no suffix {"<!-- review-bot:", "unknown"}, // prefix but no suffix
{"prefix <!-- review-bot:abc --> end", "abc"}, // embedded in text {"prefix <!-- review-bot:abc --> end", "abc"}, // embedded in text
} }
for _, tc := range tests { for _, tc := range tests {
+4 -8
View File
@@ -1,9 +1,5 @@
# Design: Role-based Review Personas (Issue #51) # Design: Role-based Review Personas (Issue #51)
> **Note:** This design was revised during implementation to use JSON instead of YAML
> to maintain the repository's zero-external-dependencies convention. All persona
> files use JSON format. See "Design Revision" section at the end for details.
## Problem ## Problem
Current review-bot performs generic code review. Every reviewer (regardless of `reviewer-name`) uses the same base prompt and evaluates the same concerns. This leads to: Current review-bot performs generic code review. Every reviewer (regardless of `reviewer-name`) uses the same base prompt and evaluates the same concerns. This leads to:
@@ -31,14 +27,14 @@ A persona is a named review role with:
- **Scope boundaries** — What do I explicitly NOT comment on? - **Scope boundaries** — What do I explicitly NOT comment on?
- **Severity calibration** — What counts as MAJOR/MINOR/NIT for MY domain? - **Severity calibration** — What counts as MAJOR/MINOR/NIT for MY domain?
Personas are defined in JSON files that can live: Personas are defined in YAML files that can live:
1. In the pattern repos (shared across projects) 1. In the pattern repos (shared across projects)
2. In the target repo (project-specific personas) 2. In the target repo (project-specific personas)
3. Inline via a new `--persona-file` flag (JSON format) 3. Inline via a new `--persona-file` flag
### 2. Persona File Format ### 2. Persona File Format
```json ```yaml
# .review/personas/security.yaml # .review/personas/security.yaml
name: security name: security
display_name: Security Specialist display_name: Security Specialist
@@ -81,7 +77,7 @@ output_format: |
### 3. New CLI Flags ### 3. New CLI Flags
``` ```
--persona-file PATH Path to persona JSON file (local or in repo) --persona-file PATH Path to persona YAML file (local or in repo)
--persona NAME Built-in persona name (security, architect, domain) --persona NAME Built-in persona name (security, architect, domain)
``` ```
-108
View File
@@ -1,108 +0,0 @@
# Design: YAML Support for Persona Files (#57)
## Problem
JSON is awkward for persona files that contain multi-line text (identity, severity descriptions). YAML supports cleaner multi-line strings and comments, improving readability and maintainability.
## Constraints
- Backwards compatibility: existing JSON personas must continue to work
- Security: protect against DoS via deeply nested YAML (AIKIDO-2024-10486)
- Consistency: use `.yaml` extension (not `.yml`)
- Library: use `gopkg.in/yaml.v3` (approved in CONVENTIONS.md) with explicit depth limiting
## Proposed Approach
1. **Update `parsePersona`** to detect format from file extension
2. **Add YAML parsing** with explicit depth limit (defense in depth)
3. **Keep JSON as fallback** for files without `.yaml`/`.yml` extension
4. **Convert built-in personas** to YAML format
5. **Update embed directive** to include both formats
### File Extension Detection
```go
func parsePersona(data []byte, source string) (*Persona, error) {
isYAML := strings.HasSuffix(source, ".yaml") || strings.HasSuffix(source, ".yml")
if isYAML {
return parseYAML(data, source)
}
return parseJSON(data, source)
}
```
### YAML Parsing with Depth Protection
```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)
}
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
}
```
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
No new state. Same `Persona` struct, just different parsing.
## Error Cases
| Error | Handling |
|-------|----------|
| Invalid YAML syntax | Return parse error with source file |
| Deeply nested YAML | Library rejects (v1.16.0+ fix) |
| Unknown extension | Fall back to JSON parsing |
| Missing required fields | Validation rejects after parse |
## Edge Cases
- File with `.json` extension but YAML content → JSON parse fails, user sees error
- File with no extension → defaults to JSON
- Embedded persona reference like `builtin:security` → detect by embed path (`personas/X.yaml`)
## Testing Strategy
1. Unit tests for YAML parsing (valid, invalid, deeply nested)
2. Unit tests for extension detection
3. Integration test for built-in personas (now YAML)
4. Backwards compat test: verify JSON still works for external files
## Completion Checklist
1. [ ] `go-yaml` dependency added at v1.16.0+
2. [ ] Extension detection uses case-insensitive comparison
3. [ ] YAML parse errors include source file name
4. [ ] JSON parsing still works for `.json` files
5. [ ] Built-in personas converted to YAML with readable multi-line strings
6. [ ] Embed directive updated to include `*.yaml`
7. [ ] Test for deeply nested YAML rejection
8. [ ] All existing tests pass
## Open Questions
- Should we support both `.yaml` AND `.yml`? Issue says `.yaml` only for consistency, but some users expect `.yml`. **Decision:** Support both for reading, recommend `.yaml` in docs.
- Should we add a "format" field to detect mismatched extension/content? **Decision:** No, keep it simple. Extension determines format.
+1 -1
View File
@@ -2,4 +2,4 @@ module gitea.weiker.me/rodin/review-bot
go 1.26.2 go 1.26.2
require gopkg.in/yaml.v3 v3.0.1 require gopkg.in/yaml.v3 v3.0.1 // indirect
-1
View File
@@ -1,4 +1,3 @@
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/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 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA=
gopkg.in/yaml.v3 v3.0.1/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM= gopkg.in/yaml.v3 v3.0.1/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
-391
View File
@@ -1,391 +0,0 @@
package llm
import (
"bytes"
"context"
"encoding/json"
"fmt"
"io"
"net/http"
"net/url"
"strings"
"sync"
"time"
)
// AICoreOpenAIAPIVersion is the API version used for OpenAI models through AI Core.
// Update this when SAP AI Core releases a new stable version.
const AICoreOpenAIAPIVersion = "2024-12-01-preview"
// maxErrorBodyLen limits the length of response bodies included in error messages
// to prevent leaking potentially sensitive upstream details in logs.
const maxErrorBodyLen = 200
// AICoreConfig holds SAP AI Core authentication and connection settings.
type AICoreConfig struct {
ClientID string
ClientSecret string
AuthURL string
APIURL string
ResourceGroup string
}
// AICoreClient wraps AI Core authentication and deployment discovery.
// Thread-safe for concurrent use after construction.
//
// Design: The deployment cache is populated once and never invalidated. This is
// acceptable for short-lived CI runner processes, but longer-lived deployments
// may want to add a TTL or re-fetch on errors.
type AICoreClient struct {
config AICoreConfig
http *http.Client
mu sync.RWMutex
token string
tokenExpiry time.Time
deployments map[string]string // model name -> deployment URL
}
// NewAICoreClient creates a new AI Core client with the given configuration.
// The client uses a default 5-minute timeout; use WithTimeout to customize.
func NewAICoreClient(cfg AICoreConfig) *AICoreClient {
return &AICoreClient{
config: cfg,
http: &http.Client{Timeout: 5 * time.Minute},
deployments: make(map[string]string),
}
}
// WithTimeout sets the HTTP request timeout for AI Core calls.
// This should be called during construction, before concurrent use.
func (c *AICoreClient) WithTimeout(d time.Duration) *AICoreClient {
c.http.Timeout = d
return c
}
// truncateBody truncates a response body for inclusion in error messages.
// This prevents leaking potentially sensitive upstream response details in logs.
func truncateBody(body []byte) string {
if len(body) <= maxErrorBodyLen {
return string(body)
}
return string(body[:maxErrorBodyLen]) + "..."
}
// getToken returns a valid OAuth token, refreshing if necessary.
func (c *AICoreClient) getToken(ctx context.Context) (string, error) {
c.mu.RLock()
if c.token != "" && time.Now().Add(5*time.Minute).Before(c.tokenExpiry) {
token := c.token
c.mu.RUnlock()
return token, nil
}
c.mu.RUnlock()
c.mu.Lock()
defer c.mu.Unlock()
// Double-check after acquiring write lock
if c.token != "" && time.Now().Add(5*time.Minute).Before(c.tokenExpiry) {
return c.token, nil
}
token, expiry, err := c.fetchToken(ctx)
if err != nil {
return "", err
}
c.token = token
c.tokenExpiry = expiry
return token, nil
}
func (c *AICoreClient) fetchToken(ctx context.Context) (string, time.Time, error) {
tokenURL := strings.TrimRight(c.config.AuthURL, "/") + "/oauth/token"
data := url.Values{}
data.Set("grant_type", "client_credentials")
data.Set("client_id", c.config.ClientID)
data.Set("client_secret", c.config.ClientSecret)
req, err := http.NewRequestWithContext(ctx, http.MethodPost, tokenURL, strings.NewReader(data.Encode()))
if err != nil {
return "", time.Time{}, fmt.Errorf("create token request: %w", err)
}
req.Header.Set("Content-Type", "application/x-www-form-urlencoded")
resp, err := c.http.Do(req)
if err != nil {
return "", time.Time{}, fmt.Errorf("token request: %w", err)
}
defer resp.Body.Close()
body, err := io.ReadAll(resp.Body)
if err != nil {
return "", time.Time{}, fmt.Errorf("read token response: %w", err)
}
if resp.StatusCode < 200 || resp.StatusCode >= 300 {
return "", time.Time{}, fmt.Errorf("token request failed (status %d): %s", resp.StatusCode, truncateBody(body))
}
var tokenResp struct {
AccessToken string `json:"access_token"`
ExpiresIn int `json:"expires_in"`
}
if err := json.Unmarshal(body, &tokenResp); err != nil {
return "", time.Time{}, fmt.Errorf("parse token response: %w", err)
}
if tokenResp.AccessToken == "" {
return "", time.Time{}, fmt.Errorf("empty access token in response")
}
expiry := time.Now().Add(time.Duration(tokenResp.ExpiresIn) * time.Second)
return tokenResp.AccessToken, expiry, nil
}
// getDeploymentURL returns the deployment URL for a model, fetching deployments if needed.
// getDeploymentURL returns the deployment URL for a model, fetching deployments if needed.
// Also returns a valid token for use by the caller, avoiding redundant getToken calls.
//
// Note: The token is fetched before acquiring the write lock to avoid holding the lock
// during network I/O. In rare cases where multiple goroutines race and one waits a long
// time for the write lock, the token could theoretically expire. The 5-minute refresh
// buffer in getToken makes this extremely unlikely in practice.
func (c *AICoreClient) getDeploymentURL(ctx context.Context, model string) (deployURL, token string, err error) {
c.mu.RLock()
if u, ok := c.deployments[model]; ok {
c.mu.RUnlock()
// Still need a token for the caller
token, err = c.getToken(ctx)
if err != nil {
return "", "", fmt.Errorf("get token: %w", err)
}
return u, token, nil
}
c.mu.RUnlock()
// Fetch token first (before acquiring write lock to avoid holding lock during I/O)
token, err = c.getToken(ctx)
if err != nil {
return "", "", fmt.Errorf("get token for deployments: %w", err)
}
c.mu.Lock()
defer c.mu.Unlock()
// Double-check after acquiring write lock
if u, ok := c.deployments[model]; ok {
return u, token, nil
}
if err := c.fetchDeployments(ctx, token); err != nil {
return "", "", err
}
if u, ok := c.deployments[model]; ok {
return u, token, nil
}
return "", "", fmt.Errorf("no deployment found for model %q", model)
}
func (c *AICoreClient) fetchDeployments(ctx context.Context, token string) error {
deployURL := strings.TrimRight(c.config.APIURL, "/") + "/v2/lm/deployments"
req, err := http.NewRequestWithContext(ctx, http.MethodGet, deployURL, nil)
if err != nil {
return fmt.Errorf("create deployments request: %w", err)
}
req.Header.Set("Authorization", "Bearer "+token)
req.Header.Set("AI-Resource-Group", c.config.ResourceGroup)
resp, err := c.http.Do(req)
if err != nil {
return fmt.Errorf("deployments request: %w", err)
}
defer resp.Body.Close()
body, err := io.ReadAll(resp.Body)
if err != nil {
return fmt.Errorf("read deployments response: %w", err)
}
if resp.StatusCode < 200 || resp.StatusCode >= 300 {
return fmt.Errorf("deployments request failed (status %d): %s", resp.StatusCode, truncateBody(body))
}
var deployResp struct {
Resources []struct {
DeploymentURL string `json:"deploymentUrl"`
Status string `json:"status"`
Details struct {
Resources struct {
BackendDetails struct {
Model struct {
Name string `json:"name"`
} `json:"model"`
} `json:"backend_details"`
} `json:"resources"`
} `json:"details"`
} `json:"resources"`
}
if err := json.Unmarshal(body, &deployResp); err != nil {
return fmt.Errorf("parse deployments response: %w", err)
}
for _, r := range deployResp.Resources {
if r.Status != "RUNNING" {
continue
}
modelName := r.Details.Resources.BackendDetails.Model.Name
if modelName == "" {
continue
}
c.deployments[modelName] = r.DeploymentURL
}
return nil
}
// CompleteAnthropic sends a request to an Anthropic model via AI Core.
func (c *AICoreClient) CompleteAnthropic(ctx context.Context, model string, messages []Message, maxTokens int, temperature float64) (string, error) {
deployURL, token, err := c.getDeploymentURL(ctx, model)
if err != nil {
return "", err
}
// Extract system message
var system string
var userMessages []anthropicMsg
for _, m := range messages {
if m.Role == "system" {
system = m.Content
} else {
userMessages = append(userMessages, anthropicMsg{
Role: m.Role,
Content: m.Content,
})
}
}
reqBody := anthropicRequest{
AnthropicVersion: "bedrock-2023-05-31", // SAP AI Core uses Bedrock format
// Model omitted - AI Core deployment already specifies model
MaxTokens: maxTokens,
System: system,
Messages: userMessages,
}
if temperature > 0 {
reqBody.Temperature = temperature
}
data, err := json.Marshal(reqBody)
if err != nil {
return "", fmt.Errorf("marshal request: %w", err)
}
// AI Core uses /invoke for Anthropic models
invokeURL := strings.TrimRight(deployURL, "/") + "/invoke"
req, err := http.NewRequestWithContext(ctx, http.MethodPost, invokeURL, bytes.NewReader(data))
if err != nil {
return "", fmt.Errorf("create request: %w", err)
}
req.Header.Set("Authorization", "Bearer "+token)
req.Header.Set("AI-Resource-Group", c.config.ResourceGroup)
req.Header.Set("Content-Type", "application/json")
resp, err := c.http.Do(req)
if err != nil {
return "", fmt.Errorf("AI Core request: %w", err)
}
defer resp.Body.Close()
body, err := io.ReadAll(resp.Body)
if err != nil {
return "", fmt.Errorf("read response: %w", err)
}
if resp.StatusCode < 200 || resp.StatusCode >= 300 {
return "", fmt.Errorf("AI Core API error (status %d): %s", resp.StatusCode, truncateBody(body))
}
var anthropicResp anthropicResponse
if err := json.Unmarshal(body, &anthropicResp); err != nil {
return "", fmt.Errorf("parse response: %w", err)
}
if len(anthropicResp.Content) == 0 {
return "", fmt.Errorf("no content in response")
}
var sb strings.Builder
for _, block := range anthropicResp.Content {
if block.Type == "text" {
sb.WriteString(block.Text)
}
}
result := sb.String()
if result == "" {
return "", fmt.Errorf("no text content in response")
}
return result, nil
}
// CompleteOpenAI sends a request to an OpenAI model via AI Core.
func (c *AICoreClient) CompleteOpenAI(ctx context.Context, model string, messages []Message, temperature float64) (string, error) {
deployURL, token, err := c.getDeploymentURL(ctx, model)
if err != nil {
return "", err
}
reqBody := ChatRequest{
Model: model,
Temperature: temperature,
Messages: messages,
}
data, err := json.Marshal(reqBody)
if err != nil {
return "", fmt.Errorf("marshal request: %w", err)
}
// AI Core uses /chat/completions?api-version=<version> for OpenAI models
chatURL := strings.TrimRight(deployURL, "/") + "/chat/completions?api-version=" + AICoreOpenAIAPIVersion
req, err := http.NewRequestWithContext(ctx, http.MethodPost, chatURL, bytes.NewReader(data))
if err != nil {
return "", fmt.Errorf("create request: %w", err)
}
req.Header.Set("Authorization", "Bearer "+token)
req.Header.Set("AI-Resource-Group", c.config.ResourceGroup)
req.Header.Set("Content-Type", "application/json")
resp, err := c.http.Do(req)
if err != nil {
return "", fmt.Errorf("AI Core request: %w", err)
}
defer resp.Body.Close()
body, err := io.ReadAll(resp.Body)
if err != nil {
return "", fmt.Errorf("read response: %w", err)
}
if resp.StatusCode < 200 || resp.StatusCode >= 300 {
return "", fmt.Errorf("AI Core API error (status %d): %s", resp.StatusCode, truncateBody(body))
}
var openaiResp ChatResponse
if err := json.Unmarshal(body, &openaiResp); err != nil {
return "", fmt.Errorf("parse response: %w", err)
}
if len(openaiResp.Choices) == 0 {
return "", fmt.Errorf("no choices in response")
}
return openaiResp.Choices[0].Message.Content, nil
}
// IsAnthropicModel returns true if the model name indicates an Anthropic model.
// SAP AI Core uses "anthropic--" prefix for Anthropic models (e.g., "anthropic--claude-3-5-sonnet").
func IsAnthropicModel(model string) bool {
return strings.HasPrefix(model, "anthropic--")
}
-535
View File
@@ -1,535 +0,0 @@
package llm
import (
"context"
"encoding/json"
"fmt"
"net/http"
"net/http/httptest"
"strings"
"sync/atomic"
"testing"
"time"
)
func TestAICoreClient_TokenFetch(t *testing.T) {
tokenCalls := int32(0)
server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
if r.URL.Path == "/oauth/token" {
atomic.AddInt32(&tokenCalls, 1)
if r.Method != http.MethodPost {
t.Errorf("expected POST for token, got %s", r.Method)
}
if r.Header.Get("Content-Type") != "application/x-www-form-urlencoded" {
t.Errorf("expected form content type")
}
w.Header().Set("Content-Type", "application/json")
json.NewEncoder(w).Encode(map[string]interface{}{
"access_token": "test-token-123",
"expires_in": 3600,
})
return
}
t.Errorf("unexpected path: %s", r.URL.Path)
}))
defer server.Close()
client := NewAICoreClient(AICoreConfig{
ClientID: "test-id",
ClientSecret: "test-secret",
AuthURL: server.URL,
APIURL: server.URL,
ResourceGroup: "default",
})
token, err := client.getToken(context.Background())
if err != nil {
t.Fatalf("unexpected error: %v", err)
}
if token != "test-token-123" {
t.Errorf("expected token 'test-token-123', got %q", token)
}
// Second call should use cached token
token2, err := client.getToken(context.Background())
if err != nil {
t.Fatalf("unexpected error: %v", err)
}
if token2 != "test-token-123" {
t.Errorf("expected cached token")
}
if atomic.LoadInt32(&tokenCalls) != 1 {
t.Errorf("expected 1 token call (cached), got %d", tokenCalls)
}
}
func TestAICoreClient_DeploymentFetch(t *testing.T) {
server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
if r.URL.Path == "/oauth/token" {
w.Header().Set("Content-Type", "application/json")
json.NewEncoder(w).Encode(map[string]interface{}{
"access_token": "test-token",
"expires_in": 3600,
})
return
}
if r.URL.Path == "/v2/lm/deployments" {
if r.Header.Get("Authorization") != "Bearer test-token" {
t.Errorf("expected Bearer auth")
}
if r.Header.Get("AI-Resource-Group") != "default" {
t.Errorf("expected resource group header")
}
w.Header().Set("Content-Type", "application/json")
json.NewEncoder(w).Encode(map[string]interface{}{
"resources": []map[string]interface{}{
{
"id": "deploy-123",
"deploymentUrl": "https://example.com/v2/inference/deployments/deploy-123",
"status": "RUNNING",
"details": map[string]interface{}{
"resources": map[string]interface{}{
"backend_details": map[string]interface{}{
"model": map[string]interface{}{
"name": "anthropic--claude-4.6-sonnet",
},
},
},
},
},
{
"id": "deploy-456",
"deploymentUrl": "https://example.com/v2/inference/deployments/deploy-456",
"status": "STOPPED",
"details": map[string]interface{}{
"resources": map[string]interface{}{
"backend_details": map[string]interface{}{
"model": map[string]interface{}{
"name": "gpt-5",
},
},
},
},
},
{
"id": "deploy-789",
"deploymentUrl": "https://example.com/v2/inference/deployments/deploy-789",
"status": "RUNNING",
"details": map[string]interface{}{
"resources": map[string]interface{}{
"backend_details": map[string]interface{}{
"model": map[string]interface{}{
"name": "gpt-5",
},
},
},
},
},
},
})
return
}
t.Errorf("unexpected path: %s", r.URL.Path)
}))
defer server.Close()
client := NewAICoreClient(AICoreConfig{
ClientID: "test-id",
ClientSecret: "test-secret",
AuthURL: server.URL,
APIURL: server.URL,
ResourceGroup: "default",
})
// Should find running deployment
url, _, err := client.getDeploymentURL(context.Background(), "anthropic--claude-4.6-sonnet")
if err != nil {
t.Fatalf("unexpected error: %v", err)
}
if url != "https://example.com/v2/inference/deployments/deploy-123" {
t.Errorf("unexpected URL: %s", url)
}
// Should find running gpt-5, not stopped one
url, _, err = client.getDeploymentURL(context.Background(), "gpt-5")
if err != nil {
t.Fatalf("unexpected error: %v", err)
}
if url != "https://example.com/v2/inference/deployments/deploy-789" {
t.Errorf("unexpected URL: %s", url)
}
// Should error on unknown model
_, _, err = client.getDeploymentURL(context.Background(), "unknown-model")
if err == nil {
t.Error("expected error for unknown model")
}
}
func TestAICoreClient_CompleteAnthropic(t *testing.T) {
// baseURL is set after server creation; captured by closure in handlers
var baseURL string
mux := http.NewServeMux()
mux.HandleFunc("/oauth/token", func(w http.ResponseWriter, r *http.Request) {
w.Header().Set("Content-Type", "application/json")
json.NewEncoder(w).Encode(map[string]interface{}{
"access_token": "test-token",
"expires_in": 3600,
})
})
mux.HandleFunc("/v2/lm/deployments", func(w http.ResponseWriter, r *http.Request) {
w.Header().Set("Content-Type", "application/json")
json.NewEncoder(w).Encode(map[string]interface{}{
"resources": []map[string]interface{}{
{
"id": "deploy-anthropic",
"deploymentUrl": baseURL + "/deployments/anthropic",
"status": "RUNNING",
"details": map[string]interface{}{
"resources": map[string]interface{}{
"backend_details": map[string]interface{}{
"model": map[string]interface{}{
"name": "anthropic--claude-4.6-sonnet",
},
},
},
},
},
},
})
})
mux.HandleFunc("/deployments/anthropic/invoke", func(w http.ResponseWriter, r *http.Request) {
if r.Header.Get("Authorization") != "Bearer test-token" {
t.Errorf("expected Bearer auth on invoke")
}
var req anthropicRequest
if err := json.NewDecoder(r.Body).Decode(&req); err != nil {
t.Fatalf("decode request: %v", err)
}
if req.AnthropicVersion != "bedrock-2023-05-31" {
t.Errorf("expected bedrock anthropic_version in request")
}
if req.System != "You are helpful" {
t.Errorf("expected system prompt: %q", req.System)
}
w.Header().Set("Content-Type", "application/json")
json.NewEncoder(w).Encode(map[string]interface{}{
"content": []map[string]interface{}{
{"type": "text", "text": "Hello from AI Core!"},
},
})
})
server := httptest.NewServer(mux)
baseURL = server.URL
defer server.Close()
client := NewAICoreClient(AICoreConfig{
ClientID: "test-id",
ClientSecret: "test-secret",
AuthURL: server.URL,
APIURL: server.URL,
ResourceGroup: "default",
})
result, err := client.CompleteAnthropic(context.Background(), "anthropic--claude-4.6-sonnet", []Message{
{Role: "system", Content: "You are helpful"},
{Role: "user", Content: "Hello"},
}, 8192, 0)
if err != nil {
t.Fatalf("unexpected error: %v", err)
}
if result != "Hello from AI Core!" {
t.Errorf("expected 'Hello from AI Core!', got %q", result)
}
}
func TestAICoreClient_CompleteOpenAI(t *testing.T) {
var baseURL string
mux := http.NewServeMux()
mux.HandleFunc("/oauth/token", func(w http.ResponseWriter, r *http.Request) {
w.Header().Set("Content-Type", "application/json")
json.NewEncoder(w).Encode(map[string]interface{}{
"access_token": "test-token",
"expires_in": 3600,
})
})
mux.HandleFunc("/v2/lm/deployments", func(w http.ResponseWriter, r *http.Request) {
w.Header().Set("Content-Type", "application/json")
json.NewEncoder(w).Encode(map[string]interface{}{
"resources": []map[string]interface{}{
{
"id": "deploy-openai",
"deploymentUrl": baseURL + "/deployments/openai",
"status": "RUNNING",
"details": map[string]interface{}{
"resources": map[string]interface{}{
"backend_details": map[string]interface{}{
"model": map[string]interface{}{
"name": "gpt-5",
},
},
},
},
},
},
})
})
mux.HandleFunc("/deployments/openai/chat/completions", func(w http.ResponseWriter, r *http.Request) {
if r.URL.Query().Get("api-version") != AICoreOpenAIAPIVersion {
t.Errorf("expected api-version %s, got %s", AICoreOpenAIAPIVersion, r.URL.Query().Get("api-version"))
}
var req ChatRequest
if err := json.NewDecoder(r.Body).Decode(&req); err != nil {
t.Fatalf("decode request: %v", err)
}
if req.Model != "gpt-5" {
t.Errorf("expected model gpt-5, got %s", req.Model)
}
w.Header().Set("Content-Type", "application/json")
json.NewEncoder(w).Encode(ChatResponse{
Choices: []struct {
Message struct {
Content string `json:"content"`
} `json:"message"`
}{
{Message: struct {
Content string `json:"content"`
}{Content: "Hello from GPT-5!"}},
},
})
})
server := httptest.NewServer(mux)
baseURL = server.URL
defer server.Close()
client := NewAICoreClient(AICoreConfig{
ClientID: "test-id",
ClientSecret: "test-secret",
AuthURL: server.URL,
APIURL: server.URL,
ResourceGroup: "default",
})
result, err := client.CompleteOpenAI(context.Background(), "gpt-5", []Message{
{Role: "user", Content: "Hello"},
}, 0)
if err != nil {
t.Fatalf("unexpected error: %v", err)
}
if result != "Hello from GPT-5!" {
t.Errorf("expected 'Hello from GPT-5!', got %q", result)
}
}
func TestIsAnthropicModel(t *testing.T) {
tests := []struct {
model string
expected bool
}{
// SAP AI Core uses "anthropic--" prefix for Anthropic models
{"anthropic--claude-4.6-sonnet", true},
{"anthropic--claude-4.6-opus", true},
{"anthropic--claude-3-5-sonnet", true},
// Non-prefixed model names are not detected as Anthropic
// (SAP AI Core always uses the prefix for Anthropic models)
{"claude-sonnet-4", false},
{"gpt-5", false},
{"gpt-4.1", false},
{"llama-3", false},
{"my-claude-model", false}, // Avoid false positives on "claude" substring
}
for _, tt := range tests {
got := IsAnthropicModel(tt.model)
if got != tt.expected {
t.Errorf("IsAnthropicModel(%q) = %v, want %v", tt.model, got, tt.expected)
}
}
}
func TestAICoreClient_TokenExpiry(t *testing.T) {
tokenCalls := int32(0)
server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
if r.URL.Path == "/oauth/token" {
call := atomic.AddInt32(&tokenCalls, 1)
w.Header().Set("Content-Type", "application/json")
json.NewEncoder(w).Encode(map[string]interface{}{
"access_token": fmt.Sprintf("token-%d", call),
"expires_in": 1, // 1 second expiry
})
return
}
}))
defer server.Close()
client := NewAICoreClient(AICoreConfig{
ClientID: "test-id",
ClientSecret: "test-secret",
AuthURL: server.URL,
APIURL: server.URL,
ResourceGroup: "default",
})
// First call
token1, err := client.getToken(context.Background())
if err != nil {
t.Fatalf("first getToken: %v", err)
}
// Force token expiry by manipulating expiry time
client.mu.Lock()
client.tokenExpiry = time.Now().Add(-time.Hour)
client.mu.Unlock()
// Should fetch new token
token2, err := client.getToken(context.Background())
if err != nil {
t.Fatalf("second getToken: %v", err)
}
if token1 == token2 {
t.Error("expected different tokens after expiry")
}
if atomic.LoadInt32(&tokenCalls) != 2 {
t.Errorf("expected 2 token calls, got %d", tokenCalls)
}
}
func TestAICoreClient_WithTimeout(t *testing.T) {
client := NewAICoreClient(AICoreConfig{
ClientID: "test-id",
ClientSecret: "test-secret",
AuthURL: "https://auth.example.com",
APIURL: "https://api.example.com",
ResourceGroup: "default",
})
// Default timeout is 5 minutes
if client.http.Timeout != 5*time.Minute {
t.Errorf("expected default timeout 5m, got %v", client.http.Timeout)
}
// WithTimeout should update the timeout
client.WithTimeout(10 * time.Minute)
if client.http.Timeout != 10*time.Minute {
t.Errorf("expected timeout 10m, got %v", client.http.Timeout)
}
}
func TestClient_WithAICore(t *testing.T) {
client := NewClient("http://example.com", "key", "model")
if client.provider != ProviderOpenAI {
t.Errorf("expected default provider openai, got %s", client.provider)
}
client.WithAICore(AICoreConfig{
ClientID: "id",
ClientSecret: "secret",
AuthURL: "https://auth.example.com",
APIURL: "https://api.example.com",
ResourceGroup: "default",
})
if client.provider != ProviderAICore {
t.Errorf("expected provider aicore, got %s", client.provider)
}
if client.aicore == nil {
t.Error("expected aicore client to be set")
}
}
func TestClient_WithTimeout_PropagatestoAICore(t *testing.T) {
client := NewClient("http://example.com", "key", "model").
WithAICore(AICoreConfig{
ClientID: "id",
ClientSecret: "secret",
AuthURL: "https://auth.example.com",
APIURL: "https://api.example.com",
ResourceGroup: "default",
})
// Default should be 5 minutes (inherited from parent client)
if client.aicore.http.Timeout != 5*time.Minute {
t.Errorf("expected aicore default timeout 5m, got %v", client.aicore.http.Timeout)
}
// WithTimeout should propagate to AI Core client
client.WithTimeout(15 * time.Minute)
if client.http.Timeout != 15*time.Minute {
t.Errorf("expected parent timeout 15m, got %v", client.http.Timeout)
}
if client.aicore.http.Timeout != 15*time.Minute {
t.Errorf("expected aicore timeout 15m, got %v", client.aicore.http.Timeout)
}
}
func TestClient_CompleteAICore(t *testing.T) {
var baseURL string
mux := http.NewServeMux()
mux.HandleFunc("/oauth/token", func(w http.ResponseWriter, r *http.Request) {
w.Header().Set("Content-Type", "application/json")
json.NewEncoder(w).Encode(map[string]interface{}{
"access_token": "test-token",
"expires_in": 3600,
})
})
mux.HandleFunc("/v2/lm/deployments", func(w http.ResponseWriter, r *http.Request) {
w.Header().Set("Content-Type", "application/json")
json.NewEncoder(w).Encode(map[string]interface{}{
"resources": []map[string]interface{}{
{
"id": "deploy-test",
"deploymentUrl": baseURL + "/deployments/test",
"status": "RUNNING",
"details": map[string]interface{}{
"resources": map[string]interface{}{
"backend_details": map[string]interface{}{
"model": map[string]interface{}{
"name": "gpt-5",
},
},
},
},
},
},
})
})
mux.HandleFunc("/deployments/test/chat/completions", func(w http.ResponseWriter, r *http.Request) {
w.Header().Set("Content-Type", "application/json")
json.NewEncoder(w).Encode(ChatResponse{
Choices: []struct {
Message struct {
Content string `json:"content"`
} `json:"message"`
}{
{Message: struct {
Content string `json:"content"`
}{Content: "AI Core via Client works!"}},
},
})
})
server := httptest.NewServer(mux)
baseURL = server.URL
defer server.Close()
client := NewClient("", "", "gpt-5").WithAICore(AICoreConfig{
ClientID: "test-id",
ClientSecret: "test-secret",
AuthURL: server.URL,
APIURL: server.URL,
ResourceGroup: "default",
})
result, err := client.Complete(context.Background(), []Message{
{Role: "user", Content: "Hello"},
})
if err != nil {
t.Fatalf("unexpected error: %v", err)
}
if !strings.Contains(result, "AI Core via Client works!") {
t.Errorf("unexpected result: %s", result)
}
}
+7 -38
View File
@@ -1,6 +1,6 @@
// Package llm provides clients for LLM chat completion APIs. // Package llm provides clients for LLM chat completion APIs.
// //
// Supports OpenAI-compatible (default), Anthropic Messages API, and SAP AI Core providers. // Supports OpenAI-compatible (default) and Anthropic Messages API providers.
package llm package llm
import ( import (
@@ -22,8 +22,6 @@ const (
ProviderOpenAI Provider = "openai" ProviderOpenAI Provider = "openai"
// ProviderAnthropic uses the Anthropic Messages API endpoint. // ProviderAnthropic uses the Anthropic Messages API endpoint.
ProviderAnthropic Provider = "anthropic" ProviderAnthropic Provider = "anthropic"
// ProviderAICore uses SAP AI Core with OAuth authentication.
ProviderAICore Provider = "aicore"
) )
// Client calls an LLM chat completion API. // Client calls an LLM chat completion API.
@@ -37,7 +35,6 @@ type Client struct {
temperature float64 temperature float64
provider Provider provider Provider
http *http.Client http *http.Client
aicore *AICoreClient // Only set when provider is aicore
} }
// NewClient creates a new LLM client. Default provider is OpenAI-compatible. // NewClient creates a new LLM client. Default provider is OpenAI-compatible.
@@ -52,12 +49,8 @@ func NewClient(baseURL, apiKey, model string) *Client {
} }
// WithTimeout sets the HTTP request timeout for LLM calls (default 5 minutes). // WithTimeout sets the HTTP request timeout for LLM calls (default 5 minutes).
// When using AI Core, this also sets the timeout on the AI Core client.
func (c *Client) WithTimeout(d time.Duration) *Client { func (c *Client) WithTimeout(d time.Duration) *Client {
c.http.Timeout = d c.http.Timeout = d
if c.aicore != nil {
c.aicore.WithTimeout(d)
}
return c return c
} }
@@ -67,21 +60,12 @@ func (c *Client) WithTemperature(t float64) *Client {
return c return c
} }
// WithProvider sets the API provider format (openai, anthropic, or aicore). // WithProvider sets the API provider format (openai or anthropic).
func (c *Client) WithProvider(p Provider) *Client { func (c *Client) WithProvider(p Provider) *Client {
c.provider = p c.provider = p
return c return c
} }
// WithAICore configures the client to use SAP AI Core for authentication.
// This sets the provider to aicore automatically.
// The AI Core client inherits the current HTTP timeout from this client.
func (c *Client) WithAICore(cfg AICoreConfig) *Client {
c.provider = ProviderAICore
c.aicore = NewAICoreClient(cfg).WithTimeout(c.http.Timeout)
return c
}
// Message represents a chat message. // Message represents a chat message.
type Message struct { type Message struct {
Role string `json:"role"` Role string `json:"role"`
@@ -98,8 +82,6 @@ func (c *Client) Complete(ctx context.Context, messages []Message) (string, erro
switch c.provider { switch c.provider {
case ProviderAnthropic: case ProviderAnthropic:
result, err = c.completeAnthropic(ctx, messages) result, err = c.completeAnthropic(ctx, messages)
case ProviderAICore:
result, err = c.completeAICore(ctx, messages)
default: default:
result, err = c.completeOpenAI(ctx, messages) result, err = c.completeOpenAI(ctx, messages)
} }
@@ -124,18 +106,6 @@ func (c *Client) Complete(ctx context.Context, messages []Message) (string, erro
return "", err return "", err
} }
// completeAICore routes to AI Core using the appropriate endpoint based on model type.
func (c *Client) completeAICore(ctx context.Context, messages []Message) (string, error) {
if c.aicore == nil {
return "", fmt.Errorf("AI Core client not configured")
}
if IsAnthropicModel(c.model) {
return c.aicore.CompleteAnthropic(ctx, c.model, messages, 8192, c.temperature)
}
return c.aicore.CompleteOpenAI(ctx, c.model, messages, c.temperature)
}
// isRetryableError returns true for transient errors worth retrying. // isRetryableError returns true for transient errors worth retrying.
func isRetryableError(err error) bool { func isRetryableError(err error) bool {
if err == nil { if err == nil {
@@ -206,12 +176,11 @@ func (c *Client) completeOpenAI(ctx context.Context, messages []Message) (string
// --- Anthropic Messages API implementation --- // --- Anthropic Messages API implementation ---
type anthropicRequest struct { type anthropicRequest struct {
AnthropicVersion string `json:"anthropic_version,omitempty"` Model string `json:"model"`
Model string `json:"model,omitempty"` MaxTokens int `json:"max_tokens"`
MaxTokens int `json:"max_tokens"` System string `json:"system,omitempty"`
System string `json:"system,omitempty"` Messages []anthropicMsg `json:"messages"`
Messages []anthropicMsg `json:"messages"` Temperature float64 `json:"temperature,omitempty"`
Temperature float64 `json:"temperature,omitempty"`
} }
type anthropicMsg struct { type anthropicMsg struct {
+1 -1
View File
@@ -37,7 +37,7 @@ func FormatMarkdownWithDisplay(result *ReviewResult, displayName, sentinelName s
} }
if headerName != "" { if headerName != "" {
title := CapitalizeFirst(headerName) title := strings.ToUpper(headerName[:1]) + headerName[1:]
sb.WriteString(fmt.Sprintf("# %s Review\n\n", title)) sb.WriteString(fmt.Sprintf("# %s Review\n\n", title))
} }
+25 -170
View File
@@ -1,14 +1,12 @@
package review package review
import ( import (
"bytes"
"embed" "embed"
"encoding/json" "encoding/json"
"fmt" "fmt"
"os" "os"
"sort" "path/filepath"
"strings" "strings"
"unicode/utf8"
"gopkg.in/yaml.v3" "gopkg.in/yaml.v3"
) )
@@ -16,18 +14,6 @@ import (
//go:embed personas/*.yaml //go:embed personas/*.yaml
var embeddedPersonas embed.FS var embeddedPersonas embed.FS
// MaxPersonaFileSize is the maximum size for persona files (64 KB).
// This prevents denial-of-service via excessively large files.
const MaxPersonaFileSize = 64 * 1024
// MaxYAMLDepth is the maximum nesting depth allowed in YAML persona files.
// This prevents stack exhaustion from deeply nested structures.
const MaxYAMLDepth = 20
// MaxYAMLNodes is the maximum number of YAML nodes allowed in persona files.
// This prevents DoS via wide-but-shallow structures that bypass depth limits.
const MaxYAMLNodes = 1000
// Persona defines a specialized review role with focused expertise. // Persona defines a specialized review role with focused expertise.
type Persona struct { type Persona struct {
Name string `json:"name" yaml:"name"` Name string `json:"name" yaml:"name"`
@@ -48,189 +34,71 @@ type Severity struct {
Nit string `json:"nit" yaml:"nit"` Nit string `json:"nit" yaml:"nit"`
} }
// LoadPersona loads a persona from a JSON or YAML file path. // LoadPersona loads a persona from a file path.
// Format is detected by file extension: .yaml/.yml for YAML, .json or other for JSON. // Supports both YAML (.yaml, .yml) and JSON (.json) formats.
// Files larger than MaxPersonaFileSize are rejected.
//
// Symlinks are supported: os.Stat follows symlinks, so a symlink pointing to
// a regular file will pass the IsRegular() check. Symlinks to non-regular files
// (directories, FIFOs, devices) are still rejected.
func LoadPersona(path string) (*Persona, error) { func LoadPersona(path string) (*Persona, error) {
// os.Stat follows symlinks, so symlinks to regular files are supported.
// The IsRegular() check operates on the target, not the symlink itself.
info, err := os.Stat(path)
if err != nil {
return nil, fmt.Errorf("read persona file %s: %w", path, err)
}
if !info.Mode().IsRegular() {
return nil, fmt.Errorf("persona file %s is not a regular file", path)
}
if info.Size() > MaxPersonaFileSize {
return nil, fmt.Errorf("persona file %s exceeds maximum size (%d bytes)", path, MaxPersonaFileSize)
}
data, err := os.ReadFile(path) data, err := os.ReadFile(path)
if err != nil { if err != nil {
return nil, fmt.Errorf("read persona file %s: %w", path, err) return nil, fmt.Errorf("read persona file %s: %w", path, err)
} }
// Re-check size after read to defend against TOCTOU races where file
// grows between stat and read (e.g., appending process, replaced file).
if len(data) > MaxPersonaFileSize {
return nil, fmt.Errorf("persona file %s exceeds maximum size (%d bytes)", path, MaxPersonaFileSize)
}
return parsePersona(data, path) return parsePersona(data, path)
} }
// LoadBuiltinPersona loads a built-in persona by name. // LoadBuiltinPersona loads a built-in persona by name.
// Returns an error if the persona doesn't exist. // Returns an error if the persona doesn't exist.
// Built-in personas are stored in YAML format only (see embed directive).
func LoadBuiltinPersona(name string) (*Persona, error) { func LoadBuiltinPersona(name string) (*Persona, error) {
yamlFile := name + ".yaml" filename := name + ".yaml"
data, err := embeddedPersonas.ReadFile("personas/" + yamlFile) data, err := embeddedPersonas.ReadFile("personas/" + filename) // embed.FS paths use forward slashes per io/fs spec
if err != nil { if err != nil {
available := ListBuiltinPersonas() available := ListBuiltinPersonas()
return nil, fmt.Errorf("unknown built-in persona %q (available: %s)", name, strings.Join(available, ", ")) return nil, fmt.Errorf("unknown built-in persona %q (available: %s)", name, strings.Join(available, ", "))
} }
return parsePersona(data, "builtin:"+yamlFile) return parsePersona(data, "builtin:"+name)
} }
// ListBuiltinPersonas returns the names of all built-in personas in sorted order. // ListBuiltinPersonas returns the names of all built-in personas.
// Returns an empty slice if the embedded directory cannot be read.
func ListBuiltinPersonas() []string { func ListBuiltinPersonas() []string {
entries, err := embeddedPersonas.ReadDir("personas") entries, err := embeddedPersonas.ReadDir("personas")
if err != nil { if err != nil {
return []string{} return nil
} }
seen := make(map[string]bool) var names []string
for _, e := range entries { for _, e := range entries {
if e.IsDir() { if e.IsDir() {
continue continue
} }
name := e.Name() name := e.Name()
// Strip extension to get persona name if strings.HasSuffix(name, ".yaml") {
var personaName string names = append(names, strings.TrimSuffix(name, ".yaml"))
switch { } else if strings.HasSuffix(name, ".yml") {
case strings.HasSuffix(name, ".yaml"): names = append(names, strings.TrimSuffix(name, ".yml"))
personaName = strings.TrimSuffix(name, ".yaml")
case strings.HasSuffix(name, ".yml"):
personaName = strings.TrimSuffix(name, ".yml")
case strings.HasSuffix(name, ".json"):
personaName = strings.TrimSuffix(name, ".json")
default:
continue
}
if !seen[personaName] {
seen[personaName] = true
} }
} }
names := make([]string, 0, len(seen))
for name := range seen {
names = append(names, name)
}
sort.Strings(names)
return names return names
} }
// parsePersona parses persona data from JSON or YAML format.
// Format is detected by the source file extension.
func parsePersona(data []byte, source string) (*Persona, error) { func parsePersona(data []byte, source string) (*Persona, error) {
lowerSource := strings.ToLower(source)
isYAML := strings.HasSuffix(lowerSource, ".yaml") || strings.HasSuffix(lowerSource, ".yml")
var p Persona var p Persona
var err error
if isYAML { // Determine format by extension or try YAML first (it's a superset of JSON)
err = unmarshalYAMLWithDepthLimit(data, &p, MaxYAMLDepth) ext := strings.ToLower(filepath.Ext(source))
if ext == ".json" {
if err := json.Unmarshal(data, &p); err != nil {
return nil, fmt.Errorf("parse persona %s: %w", source, err)
}
} else { } else {
// Use json.Decoder with DisallowUnknownFields for consistency with // YAML (also handles .yaml, .yml, and builtin: prefix)
// YAML's KnownFields(true) - both reject unknown fields to catch typos. if err := yaml.Unmarshal(data, &p); err != nil {
dec := json.NewDecoder(bytes.NewReader(data)) return nil, fmt.Errorf("parse persona %s: %w", source, err)
dec.DisallowUnknownFields() }
err = dec.Decode(&p)
}
if err != nil {
return nil, fmt.Errorf("parse persona %s: %w", source, err)
} }
if err := validatePersona(&p, source); err != nil { if err := validatePersona(&p, source); err != nil {
return nil, err return nil, err
} }
return &p, nil return &p, nil
} }
// 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: 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 multi-document YAML files - silently ignoring additional documents
// could lead to confusing behavior where users think their changes take effect.
var extra yaml.Node
if dec.Decode(&extra) == nil {
return fmt.Errorf("multi-document YAML is not supported; only single-document files are allowed")
}
nodeCount := 0
if err := checkYAMLDepth(&node, 0, maxDepth, MaxYAMLNodes, make(map[*yaml.Node]struct{}), &nodeCount); err != nil {
return err
}
// Second pass: decode with strict field checking enabled.
// 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 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)
}
// Track total nodes visited as defense-in-depth against wide-but-shallow attacks.
*nodeCount++
if *nodeCount > maxNodes {
return fmt.Errorf("YAML node count exceeds maximum (%d)", maxNodes)
}
// Cycle detection: if we've seen this node before, we're in a cycle.
if _, ok := seen[node]; ok {
return nil // Already validated this subtree, skip to avoid infinite recursion.
}
seen[node] = struct{}{}
// 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)
}
for _, child := range node.Content {
if err := checkYAMLDepth(child, depth+1, maxDepth, maxNodes, seen, nodeCount); err != nil {
return err
}
}
return nil
}
// ParsePersonaBytes parses persona data from bytes with a source label for errors.
// This is useful for parsing personas fetched from external sources (e.g., Gitea API)
// without requiring filesystem access. Format is detected by source extension.
func ParsePersonaBytes(data []byte, source string) (*Persona, error) {
return parsePersona(data, source)
}
func validatePersona(p *Persona, source string) error { func validatePersona(p *Persona, source string) error {
if p.Name == "" { if p.Name == "" {
return fmt.Errorf("persona %s: name is required", source) return fmt.Errorf("persona %s: name is required", source)
@@ -244,16 +112,3 @@ func validatePersona(p *Persona, source string) error {
} }
return nil return nil
} }
// CapitalizeFirst capitalizes the first rune of a string in a Unicode-safe way.
// Returns the original string if it's empty.
func CapitalizeFirst(s string) string {
if s == "" {
return s
}
r, size := utf8.DecodeRuneInString(s)
if r == utf8.RuneError {
return s
}
return strings.ToUpper(string(r)) + s[size:]
}
+13 -549
View File
@@ -1,13 +1,10 @@
package review package review
import ( import (
"fmt"
"os" "os"
"path/filepath" "path/filepath"
"strings" "strings"
"testing" "testing"
"gopkg.in/yaml.v3"
) )
func TestLoadBuiltinPersona(t *testing.T) { func TestLoadBuiltinPersona(t *testing.T) {
@@ -94,7 +91,7 @@ func TestLoadPersonaFromYAMLFile(t *testing.T) {
dir := t.TempDir() dir := t.TempDir()
path := filepath.Join(dir, "test.yaml") path := filepath.Join(dir, "test.yaml")
content := `# Test persona content := `
name: test name: test
display_name: Test Persona display_name: Test Persona
identity: | identity: |
@@ -134,39 +131,6 @@ severity:
} }
} }
func TestLoadPersonaFromYMLFile(t *testing.T) {
dir := t.TempDir()
path := filepath.Join(dir, "test.yml")
content := `name: test
display_name: Test YML
identity: Test identity
focus:
- testing
ignore: []
severity:
major: Big
minor: Small
nit: Tiny
`
if err := os.WriteFile(path, []byte(content), 0644); err != nil {
t.Fatalf("failed to write test file: %v", err)
}
p, err := LoadPersona(path)
if err != nil {
t.Fatalf("LoadPersona failed: %v", err)
}
if p.Name != "test" {
t.Errorf("Name = %q, want %q", p.Name, "test")
}
if p.DisplayName != "Test YML" {
t.Errorf("DisplayName = %q, want %q", p.DisplayName, "Test YML")
}
}
func TestLoadPersonaFromJSONFile(t *testing.T) { func TestLoadPersonaFromJSONFile(t *testing.T) {
dir := t.TempDir() dir := t.TempDir()
path := filepath.Join(dir, "test.json") path := filepath.Join(dir, "test.json")
@@ -174,9 +138,8 @@ func TestLoadPersonaFromJSONFile(t *testing.T) {
content := `{ content := `{
"name": "test", "name": "test",
"display_name": "Test Persona", "display_name": "Test Persona",
"identity": "You are a test persona.\nMulti-line identity works.", "identity": "You are a test persona.",
"focus": ["testing", "validation"], "focus": ["testing"],
"ignore": ["nothing"], "ignore": ["nothing"],
"severity": { "severity": {
"major": "Big problems", "major": "Big problems",
@@ -200,49 +163,27 @@ func TestLoadPersonaFromJSONFile(t *testing.T) {
if p.DisplayName != "Test Persona" { if p.DisplayName != "Test Persona" {
t.Errorf("DisplayName = %q, want %q", p.DisplayName, "Test Persona") t.Errorf("DisplayName = %q, want %q", p.DisplayName, "Test Persona")
} }
if len(p.Focus) != 2 {
t.Errorf("Focus len = %d, want 2", len(p.Focus))
}
if !strings.Contains(p.Identity, "Multi-line") {
t.Error("Identity should contain multi-line content")
}
} }
func TestLoadPersonaValidation(t *testing.T) { func TestLoadPersonaValidation(t *testing.T) {
tests := []struct { tests := []struct {
name string name string
content string yaml string
ext string
wantErr string wantErr string
}{ }{
{ {
name: "missing name yaml", name: "missing name",
content: "identity: test\n", yaml: "identity: test",
ext: ".yaml",
wantErr: "name is required", wantErr: "name is required",
}, },
{ {
name: "missing identity yaml", name: "missing identity",
content: "name: test\n", yaml: "name: test",
ext: ".yaml",
wantErr: "identity is required", wantErr: "identity is required",
}, },
{ {
name: "missing name json", name: "display_name defaults to name",
content: `{"identity": "test"}`, yaml: "name: test\nidentity: test identity",
ext: ".json",
wantErr: "name is required",
},
{
name: "missing identity json",
content: `{"name": "test"}`,
ext: ".json",
wantErr: "identity is required",
},
{
name: "display_name defaults to name",
content: "name: test\nidentity: test identity\n",
ext: ".yaml",
// No error expected - should succeed // No error expected - should succeed
}, },
} }
@@ -250,8 +191,8 @@ func TestLoadPersonaValidation(t *testing.T) {
for _, tt := range tests { for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) { t.Run(tt.name, func(t *testing.T) {
dir := t.TempDir() dir := t.TempDir()
path := filepath.Join(dir, "test"+tt.ext) path := filepath.Join(dir, "test.yaml")
if err := os.WriteFile(path, []byte(tt.content), 0644); err != nil { if err := os.WriteFile(path, []byte(tt.yaml), 0644); err != nil {
t.Fatalf("failed to write test file: %v", err) t.Fatalf("failed to write test file: %v", err)
} }
@@ -290,7 +231,7 @@ func TestLoadPersonaFileNotFound(t *testing.T) {
func TestLoadPersonaInvalidYAML(t *testing.T) { func TestLoadPersonaInvalidYAML(t *testing.T) {
dir := t.TempDir() dir := t.TempDir()
path := filepath.Join(dir, "invalid.yaml") path := filepath.Join(dir, "invalid.yaml")
if err := os.WriteFile(path, []byte("not valid yaml:\n - [broken"), 0644); err != nil { if err := os.WriteFile(path, []byte("not: valid: yaml: here"), 0644); err != nil {
t.Fatalf("failed to write test file: %v", err) t.Fatalf("failed to write test file: %v", err)
} }
@@ -299,480 +240,3 @@ func TestLoadPersonaInvalidYAML(t *testing.T) {
t.Error("expected error for invalid YAML") t.Error("expected error for invalid YAML")
} }
} }
func TestLoadPersonaInvalidJSON(t *testing.T) {
dir := t.TempDir()
path := filepath.Join(dir, "invalid.json")
if err := os.WriteFile(path, []byte("not valid json {"), 0644); err != nil {
t.Fatalf("failed to write test file: %v", err)
}
_, err := LoadPersona(path)
if err == nil {
t.Error("expected error for invalid JSON")
}
}
func TestLoadPersonaCaseInsensitiveExtension(t *testing.T) {
tests := []struct {
name string
ext string
}{
{"lowercase yaml", ".yaml"},
{"uppercase YAML", ".YAML"},
{"mixed case Yaml", ".Yaml"},
{"lowercase yml", ".yml"},
{"uppercase YML", ".YML"},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
dir := t.TempDir()
path := filepath.Join(dir, "test"+tt.ext)
content := "name: test\nidentity: test identity\n"
if err := os.WriteFile(path, []byte(content), 0644); err != nil {
t.Fatalf("failed to write test file: %v", err)
}
p, err := LoadPersona(path)
if err != nil {
t.Fatalf("LoadPersona failed for extension %s: %v", tt.ext, err)
}
if p.Name != "test" {
t.Errorf("Name = %q, want %q", p.Name, "test")
}
})
}
}
func TestCapitalizeFirst(t *testing.T) {
tests := []struct {
input string
want string
}{
{"hello", "Hello"},
{"Hello", "Hello"},
{"HELLO", "HELLO"},
{"a", "A"},
{"", ""},
{"日本語", "日本語"}, // Non-ASCII: Japanese doesn't have case
{"über", "Über"}, // German umlaut
{"élève", "Élève"}, // French accent
}
for _, tt := range tests {
t.Run(tt.input, func(t *testing.T) {
got := CapitalizeFirst(tt.input)
if got != tt.want {
t.Errorf("CapitalizeFirst(%q) = %q, want %q", tt.input, got, tt.want)
}
})
}
}
func TestListBuiltinPersonasReturnsEmptySlice(t *testing.T) {
// ListBuiltinPersonas should return an empty slice (not nil) on error.
// We can't easily test the error case, but we can verify the success case
// returns a proper slice.
names := ListBuiltinPersonas()
if names == nil {
t.Error("ListBuiltinPersonas should return empty slice, not nil")
}
}
func TestYAMLMultilineStrings(t *testing.T) {
dir := t.TempDir()
path := filepath.Join(dir, "multiline.yaml")
// Test literal block scalar (|) which preserves newlines
content := `name: multiline
display_name: Multiline Test
identity: |
First line.
Second line.
Third line.
focus:
- item one
ignore: []
severity:
major: Major issue
minor: Minor issue
nit: Nit
`
if err := os.WriteFile(path, []byte(content), 0644); err != nil {
t.Fatalf("failed to write test file: %v", err)
}
p, err := LoadPersona(path)
if err != nil {
t.Fatalf("LoadPersona failed: %v", err)
}
// Literal block scalar preserves newlines
if !strings.Contains(p.Identity, "\n") {
t.Error("Identity should contain newlines from literal block scalar")
}
if !strings.Contains(p.Identity, "Second line") {
t.Error("Identity should contain 'Second line'")
}
}
func TestYAMLComments(t *testing.T) {
dir := t.TempDir()
path := filepath.Join(dir, "comments.yaml")
content := `# This is a comment
name: commented # inline comment
display_name: Commented Persona
# Another comment
identity: Test identity
focus:
- item # comment after item
ignore: []
severity:
major: Major
minor: Minor
nit: Nit
`
if err := os.WriteFile(path, []byte(content), 0644); err != nil {
t.Fatalf("failed to write test file: %v", err)
}
p, err := LoadPersona(path)
if err != nil {
t.Fatalf("LoadPersona failed: %v", err)
}
// Comments should be ignored
if p.Name != "commented" {
t.Errorf("Name = %q, want %q", p.Name, "commented")
}
if p.Focus[0] != "item" {
t.Errorf("Focus[0] = %q, want %q", p.Focus[0], "item")
}
}
func TestYAMLDeeplyNestedRejection(t *testing.T) {
dir := t.TempDir()
path := filepath.Join(dir, "deeply-nested.yaml")
// Build a deeply nested YAML structure that exceeds MaxYAMLDepth (20).
// Each level adds 2 to the depth count (key + value mapping).
var sb strings.Builder
sb.WriteString("name: test\nidentity: test\nnested:\n")
indent := " "
for i := 0; i < 25; i++ {
sb.WriteString(strings.Repeat(indent, i+1))
sb.WriteString(fmt.Sprintf("level%d:\n", i))
}
sb.WriteString(strings.Repeat(indent, 26))
sb.WriteString("value: too-deep\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.Error("expected error for deeply nested YAML, got nil")
}
if !strings.Contains(err.Error(), "nesting depth exceeds") {
t.Errorf("error = %q, want containing 'nesting depth exceeds'", err.Error())
}
}
func TestYAMLFileSizeLimit(t *testing.T) {
dir := t.TempDir()
path := filepath.Join(dir, "huge.yaml")
// Create a file larger than MaxPersonaFileSize (64 KB)
content := "name: test\nidentity: " + strings.Repeat("x", MaxPersonaFileSize+1) + "\n"
if err := os.WriteFile(path, []byte(content), 0644); err != nil {
t.Fatalf("failed to write test file: %v", err)
}
_, err := LoadPersona(path)
if err == nil {
t.Error("expected error for oversized file, got nil")
}
if !strings.Contains(err.Error(), "exceeds maximum size") {
t.Errorf("error = %q, want containing 'exceeds maximum size'", err.Error())
}
}
func TestYAMLAliasCycleDetection(t *testing.T) {
// Test that our checkYAMLDepth function handles alias cycles gracefully
// 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 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 := &yaml.Node{
Kind: yaml.AliasNode,
Alias: parent,
}
parent.Content = append(parent.Content, aliasToParent)
nodeCount := 0
seen := make(map[*yaml.Node]struct{})
// 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 seen map
if _, ok := seen[parent]; !ok {
t.Error("parent node not tracked in seen map")
}
}
func TestYAMLMultiDocumentRejection(t *testing.T) {
dir := t.TempDir()
path := filepath.Join(dir, "multi.yaml")
// Multi-document YAML (documents separated by ---)
content := `name: first
identity: first document
---
name: second
identity: second document
`
if err := os.WriteFile(path, []byte(content), 0644); err != nil {
t.Fatalf("failed to write test file: %v", err)
}
_, err := LoadPersona(path)
if err == nil {
t.Error("expected error for multi-document YAML, got nil")
}
if !strings.Contains(err.Error(), "multi-document") {
t.Errorf("error = %q, want containing 'multi-document'", err.Error())
}
}
func TestYAMLNodeCountLimit(t *testing.T) {
dir := t.TempDir()
path := filepath.Join(dir, "wide.yaml")
// Build a YAML structure that's shallow but wide - many keys at the same level
// to test the node count limit (should exceed MaxYAMLNodes = 1000)
var sb strings.Builder
sb.WriteString("name: test\nidentity: test\n")
for i := 0; i < 600; i++ {
sb.WriteString(fmt.Sprintf("key%d: value%d\n", i, i))
}
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.Error("expected error for wide YAML exceeding node count, got nil")
}
if !strings.Contains(err.Error(), "node count exceeds") {
t.Errorf("error = %q, want containing 'node count exceeds'", err.Error())
}
}
func TestCheckYAMLDepthCycleDetectionDirect(t *testing.T) {
// Direct test of cycle detection in checkYAMLDepth by creating
// a node structure with an artificial cycle.
// This tests the seen map logic independent of go-yaml's parsing.
node := &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 := &yaml.Node{
Kind: yaml.AliasNode,
Alias: node, // Points back to the parent
}
node.Content = append(node.Content,
&yaml.Node{Kind: yaml.ScalarNode, Value: "cyclic"},
cycleChild,
)
nodeCount := 0
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 seen map should contain multiple entries
if len(seen) < 2 {
t.Errorf("seen map has %d entries, expected at least 2", len(seen))
}
}
func TestListBuiltinPersonasSortedOrder(t *testing.T) {
names := ListBuiltinPersonas()
if len(names) < 2 {
t.Skip("need at least 2 personas to test ordering")
}
// Verify the list is sorted
for i := 1; i < len(names); i++ {
if names[i-1] > names[i] {
t.Errorf("ListBuiltinPersonas not sorted: %q > %q", names[i-1], names[i])
}
}
}
func TestYAMLUnknownFieldsRejected(t *testing.T) {
tests := []struct {
name string
content string
wantErr string
}{
{
name: "unknown top-level field",
content: `name: test
identity: test identity
unknown_field: should fail
`,
wantErr: "unknown_field",
},
{
name: "typo in field name",
content: `name: test
identiy: typo should fail
`,
wantErr: "identiy",
},
{
name: "unknown field in severity",
content: `name: test
identity: test
severity:
major: Major
minro: typo
`,
wantErr: "minro",
},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
dir := t.TempDir()
path := filepath.Join(dir, "unknown.yaml")
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.Errorf("expected error for unknown field %q, got nil", tt.wantErr)
return
}
if !strings.Contains(err.Error(), tt.wantErr) {
t.Errorf("error = %q, want containing %q", err.Error(), tt.wantErr)
}
})
}
}
func TestJSONUnknownFieldsRejected(t *testing.T) {
tests := []struct {
name string
content string
wantErr string
}{
{
name: "unknown top-level field",
content: `{
"name": "test",
"identity": "test identity",
"unknown_field": "should fail"
}`,
wantErr: "unknown_field",
},
{
name: "typo in field name",
content: `{
"name": "test",
"identiy": "typo should fail"
}`,
wantErr: "identiy",
},
{
name: "unknown field in severity",
content: `{
"name": "test",
"identity": "test",
"severity": {
"major": "ok",
"miner": "typo"
}
}`,
wantErr: "miner",
},
}
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 unknown field, got nil")
}
if !strings.Contains(err.Error(), tt.wantErr) {
t.Errorf("error = %q, want to contain %q", err.Error(), tt.wantErr)
}
})
}
}
func TestLoadPersonaSymlink(t *testing.T) {
// Create a regular persona file
dir := t.TempDir()
realFile := filepath.Join(dir, "real.yaml")
content := `name: test
identity: test identity
`
if err := os.WriteFile(realFile, []byte(content), 0644); err != nil {
t.Fatalf("failed to write test file: %v", err)
}
// Create a symlink to it
symlink := filepath.Join(dir, "link.yaml")
if err := os.Symlink(realFile, symlink); err != nil {
t.Fatalf("failed to create symlink: %v", err)
}
// LoadPersona should work via symlink
p, err := LoadPersona(symlink)
if err != nil {
t.Fatalf("LoadPersona via symlink failed: %v", err)
}
if p.Name != "test" {
t.Errorf("Name = %q, want %q", p.Name, "test")
}
}
-3
View File
@@ -1,6 +1,3 @@
# Software Architect Persona
# Focuses on design quality, patterns, and code organization
name: architect name: architect
display_name: Software Architect display_name: Software Architect
-3
View File
@@ -1,6 +1,3 @@
# Documentation Reviewer Persona
# Focuses on clarity, documentation quality, and self-documenting code
name: docs name: docs
display_name: Documentation Reviewer display_name: Documentation Reviewer
-3
View File
@@ -1,6 +1,3 @@
# Security Specialist Persona
# Focuses on vulnerabilities, auth issues, and security best practices
name: security name: security
display_name: Security Specialist display_name: Security Specialist
-150
View File
@@ -1,150 +0,0 @@
package review
import (
"context"
"log/slog"
"strings"
)
// RepoPersonaPath is the directory path where repo-specific personas are stored.
const RepoPersonaPath = ".review-bot/personas"
// GiteaClient defines the subset of gitea.Client methods needed for loading repo personas.
// This interface allows for easier testing and decouples the review package from gitea.
type GiteaClient interface {
ListContents(ctx context.Context, owner, repo, path string) ([]ContentEntry, error)
GetFileContent(ctx context.Context, owner, repo, filepath string) (string, error)
}
// ContentEntry represents a file or directory entry from the contents API.
// This mirrors gitea.ContentEntry to avoid import cycles.
type ContentEntry struct {
Name string `json:"name"`
Path string `json:"path"`
Type string `json:"type"` // "file" or "dir"
}
// LoadRepoPersonas fetches personas from a repository's .review-bot/personas/ directory.
// Returns an empty map (not nil) if the directory doesn't exist or is empty.
// Individual parse failures are logged and skipped; the remaining personas are still returned.
// Auth errors and other non-404 errors are propagated.
// Files exceeding MaxPersonaFileSize are rejected to prevent resource exhaustion.
func LoadRepoPersonas(ctx context.Context, client GiteaClient, owner, repo string) (map[string]*Persona, error) {
result := make(map[string]*Persona)
entries, err := client.ListContents(ctx, owner, repo, RepoPersonaPath)
if err != nil {
// Check if this is a 404 (directory doesn't exist) - expected case
if isNotFoundError(err) {
slog.Debug("no repo personas directory found", "repo", owner+"/"+repo)
return result, nil
}
// Other errors (auth, server) should propagate
return nil, err
}
if len(entries) == 0 {
slog.Debug("repo personas directory is empty", "repo", owner+"/"+repo)
return result, nil
}
for _, entry := range entries {
if entry.Type != "file" {
continue
}
// Only process YAML files
if !isYAMLFile(entry.Name) {
continue
}
content, err := client.GetFileContent(ctx, owner, repo, entry.Path)
if err != nil {
slog.Warn("could not fetch repo persona file",
"file", entry.Path,
"repo", owner+"/"+repo,
"error", err)
continue
}
// Enforce size limit before parsing to prevent resource exhaustion
if len(content) > MaxPersonaFileSize {
slog.Warn("repo persona file exceeds maximum size",
"file", entry.Path,
"repo", owner+"/"+repo,
"size", len(content),
"max", MaxPersonaFileSize)
continue
}
persona, err := ParsePersonaBytes([]byte(content), entry.Path)
if err != nil {
slog.Warn("could not parse repo persona file",
"file", entry.Path,
"repo", owner+"/"+repo,
"error", err)
continue
}
result[persona.Name] = persona
slog.Debug("loaded repo persona",
"name", persona.Name,
"file", entry.Path,
"repo", owner+"/"+repo)
}
return result, nil
}
// MergePersonas combines built-in personas with repo personas.
// Repo personas take precedence on name collision.
// Returns a new map; inputs are not modified.
func MergePersonas(builtin, repo map[string]*Persona) map[string]*Persona {
result := make(map[string]*Persona, len(builtin)+len(repo))
// Copy built-in personas first
for name, p := range builtin {
result[name] = p
}
// Overlay repo personas (override on collision)
for name, p := range repo {
if _, exists := result[name]; exists {
slog.Debug("repo persona overrides built-in", "name", name)
}
result[name] = p
}
return result
}
// GetBuiltinPersonasMap returns all built-in personas as a map keyed by name.
// Returns an empty map (not nil) if loading fails.
func GetBuiltinPersonasMap() map[string]*Persona {
result := make(map[string]*Persona)
for _, name := range ListBuiltinPersonas() {
p, err := LoadBuiltinPersona(name)
if err != nil {
slog.Warn("could not load built-in persona", "name", name, "error", err)
continue
}
result[name] = p
}
return result
}
// isYAMLFile checks if a filename has a YAML extension.
func isYAMLFile(name string) bool {
lower := strings.ToLower(name)
return strings.HasSuffix(lower, ".yaml") || strings.HasSuffix(lower, ".yml")
}
// isNotFoundError checks if an error represents a 404 response.
// This uses a specific "HTTP 404" substring match rather than a generic "not found"
// match to avoid masking authentication failures or transport errors that might
// contain "not found" in their message.
func isNotFoundError(err error) bool {
if err == nil {
return false
}
return strings.Contains(err.Error(), "HTTP 404")
}
-443
View File
@@ -1,443 +0,0 @@
package review
import (
"context"
"errors"
"strings"
"testing"
)
func TestParsePersonaBytes(t *testing.T) {
tests := []struct {
name string
data string
source string
wantName string
wantErr string
}{
{
name: "valid yaml",
data: `name: test
identity: test identity
focus:
- testing
`,
source: "test.yaml",
wantName: "test",
},
{
name: "missing name",
data: "identity: test\n",
source: "test.yaml",
wantErr: "name is required",
},
{
name: "invalid yaml",
data: "not: valid:\n yaml: [broken",
source: "test.yaml",
wantErr: "parse",
},
{
name: "json format by extension",
data: `{"name": "jsontest", "identity": "json identity"}`,
source: "test.json",
wantName: "jsontest",
},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
p, err := ParsePersonaBytes([]byte(tt.data), tt.source)
if tt.wantErr != "" {
if err == nil {
t.Fatalf("expected error containing %q, got nil", tt.wantErr)
}
if !strings.Contains(err.Error(), tt.wantErr) {
t.Errorf("error = %q, want containing %q", err.Error(), tt.wantErr)
}
return
}
if err != nil {
t.Fatalf("unexpected error: %v", err)
}
if p.Name != tt.wantName {
t.Errorf("Name = %q, want %q", p.Name, tt.wantName)
}
})
}
}
// mockGiteaClient implements GiteaClient for testing.
type mockGiteaClient struct {
contents map[string][]ContentEntry // path -> entries
files map[string]string // path -> content
listErr error
fileErr map[string]error // path -> error
}
func (m *mockGiteaClient) ListContents(ctx context.Context, owner, repo, path string) ([]ContentEntry, error) {
if m.listErr != nil {
return nil, m.listErr
}
entries, ok := m.contents[path]
if !ok {
return nil, errors.New("list contents .review-bot/personas: HTTP 404: not found")
}
return entries, nil
}
func (m *mockGiteaClient) GetFileContent(ctx context.Context, owner, repo, filepath string) (string, error) {
if m.fileErr != nil {
if err, ok := m.fileErr[filepath]; ok {
return "", err
}
}
content, ok := m.files[filepath]
if !ok {
return "", errors.New("HTTP 404: file not found")
}
return content, nil
}
func TestLoadRepoPersonas(t *testing.T) {
ctx := context.Background()
t.Run("directory not found returns empty map", func(t *testing.T) {
client := &mockGiteaClient{} // No contents configured -> 404
personas, err := LoadRepoPersonas(ctx, client, "owner", "repo")
if err != nil {
t.Fatalf("unexpected error: %v", err)
}
if personas == nil {
t.Error("expected empty map, got nil")
}
if len(personas) != 0 {
t.Errorf("expected 0 personas, got %d", len(personas))
}
})
t.Run("empty directory returns empty map", func(t *testing.T) {
client := &mockGiteaClient{
contents: map[string][]ContentEntry{
RepoPersonaPath: {},
},
}
personas, err := LoadRepoPersonas(ctx, client, "owner", "repo")
if err != nil {
t.Fatalf("unexpected error: %v", err)
}
if len(personas) != 0 {
t.Errorf("expected 0 personas, got %d", len(personas))
}
})
t.Run("loads valid personas", func(t *testing.T) {
client := &mockGiteaClient{
contents: map[string][]ContentEntry{
RepoPersonaPath: {
{Name: "trading.yaml", Path: ".review-bot/personas/trading.yaml", Type: "file"},
{Name: "crypto.yaml", Path: ".review-bot/personas/crypto.yaml", Type: "file"},
},
},
files: map[string]string{
".review-bot/personas/trading.yaml": `name: trading
display_name: Trading Expert
identity: You are a trading expert.
focus:
- order handling
- risk management
`,
".review-bot/personas/crypto.yaml": `name: crypto
display_name: Crypto Expert
identity: You are a cryptography expert.
focus:
- key management
- encryption
`,
},
}
personas, err := LoadRepoPersonas(ctx, client, "owner", "repo")
if err != nil {
t.Fatalf("unexpected error: %v", err)
}
if len(personas) != 2 {
t.Fatalf("expected 2 personas, got %d", len(personas))
}
if personas["trading"] == nil {
t.Error("expected trading persona")
}
if personas["crypto"] == nil {
t.Error("expected crypto persona")
}
if personas["trading"].DisplayName != "Trading Expert" {
t.Errorf("trading display name = %q, want %q", personas["trading"].DisplayName, "Trading Expert")
}
})
t.Run("skips invalid persona files", func(t *testing.T) {
client := &mockGiteaClient{
contents: map[string][]ContentEntry{
RepoPersonaPath: {
{Name: "valid.yaml", Path: ".review-bot/personas/valid.yaml", Type: "file"},
{Name: "invalid.yaml", Path: ".review-bot/personas/invalid.yaml", Type: "file"},
},
},
files: map[string]string{
".review-bot/personas/valid.yaml": `name: valid
identity: Valid persona
`,
".review-bot/personas/invalid.yaml": "not valid yaml: [broken",
},
}
personas, err := LoadRepoPersonas(ctx, client, "owner", "repo")
if err != nil {
t.Fatalf("unexpected error: %v", err)
}
// Should have the valid one, skip the invalid
if len(personas) != 1 {
t.Fatalf("expected 1 persona (skipped invalid), got %d", len(personas))
}
if personas["valid"] == nil {
t.Error("expected valid persona")
}
})
t.Run("skips non-yaml files", func(t *testing.T) {
client := &mockGiteaClient{
contents: map[string][]ContentEntry{
RepoPersonaPath: {
{Name: "persona.yaml", Path: ".review-bot/personas/persona.yaml", Type: "file"},
{Name: "README.md", Path: ".review-bot/personas/README.md", Type: "file"},
{Name: "notes.txt", Path: ".review-bot/personas/notes.txt", Type: "file"},
},
},
files: map[string]string{
".review-bot/personas/persona.yaml": `name: test
identity: Test persona
`,
".review-bot/personas/README.md": "# Personas\n\nPut your personas here.",
},
}
personas, err := LoadRepoPersonas(ctx, client, "owner", "repo")
if err != nil {
t.Fatalf("unexpected error: %v", err)
}
if len(personas) != 1 {
t.Fatalf("expected 1 persona (yaml only), got %d", len(personas))
}
})
t.Run("skips subdirectories", func(t *testing.T) {
client := &mockGiteaClient{
contents: map[string][]ContentEntry{
RepoPersonaPath: {
{Name: "persona.yaml", Path: ".review-bot/personas/persona.yaml", Type: "file"},
{Name: "subdir", Path: ".review-bot/personas/subdir", Type: "dir"},
},
},
files: map[string]string{
".review-bot/personas/persona.yaml": `name: test
identity: Test persona
`,
},
}
personas, err := LoadRepoPersonas(ctx, client, "owner", "repo")
if err != nil {
t.Fatalf("unexpected error: %v", err)
}
if len(personas) != 1 {
t.Fatalf("expected 1 persona (files only), got %d", len(personas))
}
})
t.Run("propagates auth errors", func(t *testing.T) {
client := &mockGiteaClient{
listErr: errors.New("HTTP 401: unauthorized"),
}
_, err := LoadRepoPersonas(ctx, client, "owner", "repo")
if err == nil {
t.Fatal("expected error for auth failure")
}
if !strings.Contains(err.Error(), "401") {
t.Errorf("error = %q, want containing '401'", err.Error())
}
})
t.Run("skips files that fail to fetch", func(t *testing.T) {
client := &mockGiteaClient{
contents: map[string][]ContentEntry{
RepoPersonaPath: {
{Name: "good.yaml", Path: ".review-bot/personas/good.yaml", Type: "file"},
{Name: "bad.yaml", Path: ".review-bot/personas/bad.yaml", Type: "file"},
},
},
files: map[string]string{
".review-bot/personas/good.yaml": `name: good
identity: Good persona
`,
},
fileErr: map[string]error{
".review-bot/personas/bad.yaml": errors.New("HTTP 500: internal server error"),
},
}
personas, err := LoadRepoPersonas(ctx, client, "owner", "repo")
if err != nil {
t.Fatalf("unexpected error: %v", err)
}
if len(personas) != 1 {
t.Fatalf("expected 1 persona (skipped failed fetch), got %d", len(personas))
}
})
t.Run("skips oversized files", func(t *testing.T) {
// Create a content string that exceeds MaxPersonaFileSize (64KB)
oversizedContent := strings.Repeat("a", MaxPersonaFileSize+1)
client := &mockGiteaClient{
contents: map[string][]ContentEntry{
RepoPersonaPath: {
{Name: "normal.yaml", Path: ".review-bot/personas/normal.yaml", Type: "file"},
{Name: "huge.yaml", Path: ".review-bot/personas/huge.yaml", Type: "file"},
},
},
files: map[string]string{
".review-bot/personas/normal.yaml": `name: normal
identity: Normal sized persona
`,
".review-bot/personas/huge.yaml": oversizedContent,
},
}
personas, err := LoadRepoPersonas(ctx, client, "owner", "repo")
if err != nil {
t.Fatalf("unexpected error: %v", err)
}
// Should have the normal one, skip the oversized
if len(personas) != 1 {
t.Fatalf("expected 1 persona (skipped oversized), got %d", len(personas))
}
if personas["normal"] == nil {
t.Error("expected normal persona")
}
})
}
func TestMergePersonas(t *testing.T) {
builtin := map[string]*Persona{
"security": {Name: "security", Identity: "Built-in security"},
"docs": {Name: "docs", Identity: "Built-in docs"},
}
repo := map[string]*Persona{
"security": {Name: "security", Identity: "Repo security override"},
"trading": {Name: "trading", Identity: "Repo trading"},
}
merged := MergePersonas(builtin, repo)
t.Run("repo overrides builtin on collision", func(t *testing.T) {
if merged["security"].Identity != "Repo security override" {
t.Errorf("security identity = %q, want repo override", merged["security"].Identity)
}
})
t.Run("builtin preserved when no collision", func(t *testing.T) {
if merged["docs"].Identity != "Built-in docs" {
t.Errorf("docs identity = %q, want built-in", merged["docs"].Identity)
}
})
t.Run("repo-only persona added", func(t *testing.T) {
if merged["trading"] == nil {
t.Error("expected trading persona from repo")
}
if merged["trading"].Identity != "Repo trading" {
t.Errorf("trading identity = %q, want repo", merged["trading"].Identity)
}
})
t.Run("original maps not modified", func(t *testing.T) {
if builtin["trading"] != nil {
t.Error("builtin map was modified")
}
if len(repo) != 2 {
t.Error("repo map was modified")
}
})
}
func TestGetBuiltinPersonasMap(t *testing.T) {
personas := GetBuiltinPersonasMap()
if len(personas) == 0 {
t.Fatal("expected at least one built-in persona")
}
// Verify expected personas exist
expected := []string{"security", "architect", "docs"}
for _, name := range expected {
if personas[name] == nil {
t.Errorf("expected built-in persona %q", name)
}
}
// Verify personas are valid
for name, p := range personas {
if p.Name != name {
t.Errorf("persona %q has mismatched name %q", name, p.Name)
}
if p.Identity == "" {
t.Errorf("persona %q has empty identity", name)
}
}
}
func TestIsYAMLFile(t *testing.T) {
tests := []struct {
name string
want bool
}{
{"test.yaml", true},
{"test.yml", true},
{"test.YAML", true},
{"test.YML", true},
{"test.json", false},
{"test.md", false},
{"test.txt", false},
{"yaml", false},
{"yaml.md", false},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
if got := isYAMLFile(tt.name); got != tt.want {
t.Errorf("isYAMLFile(%q) = %v, want %v", tt.name, got, tt.want)
}
})
}
}
func TestIsNotFoundError(t *testing.T) {
tests := []struct {
err error
want bool
}{
{nil, false},
{errors.New("HTTP 404: not found"), true},
{errors.New("HTTP 404"), true},
// Intentionally false: generic "not found" could mask auth/transport errors.
// Only explicit HTTP 404 responses should be treated as "directory doesn't exist".
{errors.New("something not found"), false},
{errors.New("HTTP 401: unauthorized"), false},
{errors.New("connection refused"), false},
}
for _, tt := range tests {
name := "nil"
if tt.err != nil {
name = tt.err.Error()
}
t.Run(name, func(t *testing.T) {
if got := isNotFoundError(tt.err); got != tt.want {
t.Errorf("isNotFoundError(%v) = %v, want %v", tt.err, got, tt.want)
}
})
}
}
-127
View File
@@ -1,127 +0,0 @@
#!/usr/bin/env bash
# check-deps.sh - Enforces the strict dependency allowlist from CONVENTIONS.md
# Exit 1 if any unapproved import is found.
#
# Requires: Bash 4+ (for associative arrays), Go toolchain
#
# The allowlist is parsed from CONVENTIONS.md to maintain a single source of truth.
# Enforces Scope column: "test only" packages cannot appear in non-test code.
set -euo pipefail
# Check bash version
if ((BASH_VERSINFO[0] < 4)); then
echo "❌ Bash 4+ required (found ${BASH_VERSION})"
echo " On macOS: brew install bash"
exit 1
fi
CONVENTIONS_FILE="${1:-CONVENTIONS.md}"
if [ ! -f "$CONVENTIONS_FILE" ]; then
echo "❌ CONVENTIONS.md not found"
exit 1
fi
# Parse approved packages from CONVENTIONS.md table using awk (POSIX-compatible)
# Format: | `package` | use case | scope |
declare -A ALLOWED_PROD=()
declare -A ALLOWED_TEST=()
while IFS= read -r line; do
# Use awk to extract package and scope from table row
pkg=$(echo "$line" | awk -F'|' '{gsub(/^[[:space:]]*`|`[[:space:]]*$/, "", $2); print $2}')
scope=$(echo "$line" | awk -F'|' '{gsub(/^[[:space:]]+|[[:space:]]+$/, "", $4); print tolower($4)}')
if [ -n "$pkg" ] && [ "$pkg" != "Package" ] && [[ "$pkg" =~ ^[a-zA-Z] ]]; then
if [[ "$scope" == *"test"* ]]; then
ALLOWED_TEST["$pkg"]=1
else
ALLOWED_PROD["$pkg"]=1
fi
fi
done < <(grep '| `' "$CONVENTIONS_FILE" 2>/dev/null || true)
ALL_ALLOWED=("${!ALLOWED_PROD[@]}" "${!ALLOWED_TEST[@]}")
if [ ${#ALL_ALLOWED[@]} -eq 0 ]; then
echo "⚠️ No approved packages found in $CONVENTIONS_FILE"
echo " (This is fine if you want stdlib-only)"
fi
# Helper: check if import matches any package in an associative array (literal prefix, no glob)
matches_allowlist() {
local import="$1"
shift
local -n allowlist=$1
for allowed in "${!allowlist[@]}"; do
# Exact match
if [ "$import" = "$allowed" ]; then
return 0
fi
# Literal prefix match for subpackages: must match "pkg/" exactly
if [ "${import#"$allowed/"}" != "$import" ]; then
return 0
fi
done
return 1
}
# Get direct module dependencies from go.mod
DIRECT_IMPORTS=$(go list -m -f '{{if and (not .Indirect) (not .Main)}}{{.Path}}{{end}}' all 2>&1) || {
echo "❌ Failed to list dependencies: $DIRECT_IMPORTS"
exit 1
}
DIRECT_IMPORTS=$(echo "$DIRECT_IMPORTS" | grep -v '^$' || true)
if [ -z "$DIRECT_IMPORTS" ]; then
echo "✅ No external dependencies"
exit 0
fi
# Check ALL direct dependencies are in some allowlist
VIOLATIONS=""
while IFS= read -r import; do
[ -z "$import" ] && continue
if ! matches_allowlist "$import" ALLOWED_PROD && ! matches_allowlist "$import" ALLOWED_TEST; then
VIOLATIONS="${VIOLATIONS} - ${import} (not in allowlist)"$'\n'
fi
done <<< "$DIRECT_IMPORTS"
if [ -n "$VIOLATIONS" ]; then
echo "❌ UNAPPROVED DEPENDENCIES DETECTED"
echo ""
echo "The following imports are not in the allowlist:"
printf "%s" "$VIOLATIONS"
echo ""
echo "To add a dependency, update CONVENTIONS.md (requires Aaron's approval)"
exit 1
fi
# Enforce Scope: test-only packages must not appear in non-test code
# Get imports used by non-test code only (go list -deps without -test excludes test deps)
PROD_IMPORTS=$(go list -deps -f '{{if not .Standard}}{{.ImportPath}}{{end}}' ./... 2>/dev/null || true)
TEST_ONLY_IN_PROD=""
for test_pkg in "${!ALLOWED_TEST[@]}"; do
# Use word-boundary matching: exact match or followed by /
if echo "$PROD_IMPORTS" | grep -qE "^${test_pkg}(/|\$|$)"; then
TEST_ONLY_IN_PROD="${TEST_ONLY_IN_PROD} - ${test_pkg} (marked 'test only' but used in production code)"$'\n'
fi
done
if [ -n "$TEST_ONLY_IN_PROD" ]; then
echo "❌ TEST-ONLY DEPENDENCIES IN PRODUCTION CODE"
echo ""
printf "%s" "$TEST_ONLY_IN_PROD"
echo ""
echo "These packages are marked 'test only' in CONVENTIONS.md"
echo "and must only be imported from *_test.go files."
exit 1
fi
echo "✅ All dependencies are approved"
echo " Direct module deps: $(echo "$DIRECT_IMPORTS" | wc -l | tr -d ' ')"
echo " Production allowlist: ${#ALLOWED_PROD[@]}, Test-only allowlist: ${#ALLOWED_TEST[@]}"