feat(persona): add role-based review personas

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 08:54:38 -07:00
22 changed files with 389 additions and 1338 deletions
@@ -26,40 +26,18 @@ inputs:
    required: false
    default: ''
  llm-base-url:
-    description: 'OpenAI-compatible LLM API base URL (not required for aicore provider)'
-    required: false
-    default: ''
+    description: 'OpenAI-compatible LLM API base URL'
+    required: true
  llm-api-key:
-    description: 'LLM API key (not required for aicore provider)'
-    required: false
-    default: ''
+    description: 'LLM API key'
+    required: true
  llm-model:
    description: 'LLM model name'
    required: true
  llm-provider:
-    description: 'LLM API provider: openai, anthropic, or aicore (default openai)'
+    description: 'LLM API provider: openai or anthropic (default openai)'
    required: false
-    default: 'openai'
-  aicore-client-id:
-    description: 'SAP AI Core client ID (required for aicore provider)'
-    required: false
-    default: ''
-  aicore-client-secret:
-    description: 'SAP AI Core client secret (required for aicore provider)'
-    required: false
-    default: ''
-  aicore-auth-url:
-    description: 'SAP AI Core authentication URL (required for aicore provider)'
-    required: false
-    default: ''
-  aicore-api-url:
-    description: 'SAP AI Core API URL (required for aicore provider)'
-    required: false
-    default: ''
-  aicore-resource-group:
-    description: 'SAP AI Core resource group (default: default)'
-    required: false
-    default: 'default'
+    default: 'openai' 
  conventions-file:
    description: 'Path to conventions file in the repo (e.g. CLAUDE.md)'
    required: false
@@ -101,7 +79,7 @@ inputs:
    required: false
    default: ''
  persona-file:
-    description: 'Path to custom persona JSON file'
+    description: 'Path to persona JSON file with custom review focus'
    required: false
    default: ''

@@ -187,11 +165,6 @@ runs:
        SYSTEM_PROMPT_FILE: ${{ inputs.system-prompt-file }}
        PERSONA: ${{ inputs.persona }}
        PERSONA_FILE: ${{ inputs.persona-file }}
-        AICORE_CLIENT_ID: ${{ inputs.aicore-client-id }}
-        AICORE_CLIENT_SECRET: ${{ inputs.aicore-client-secret }}
-        AICORE_AUTH_URL: ${{ inputs.aicore-auth-url }}
-        AICORE_API_URL: ${{ inputs.aicore-api-url }}
-        AICORE_RESOURCE_GROUP: ${{ inputs.aicore-resource-group }}
      run: |
        ARGS=""
        if [ "${{ inputs.dry-run }}" = "true" ]; then
@@ -18,10 +18,8 @@ jobs:
      - run: go vet ./...
      - run: go build -o review-bot ./cmd/review-bot

-  # Self-review using native SAP AI Core provider
-  # Models must match SAP AI Core deployments
-  # Available models: gpt-5, anthropic--claude-4.6-sonnet, anthropic--claude-4.6-opus
-  # Removed gpt-4.1, gpt-5-mini, gpt-4.1-mini - not deployed on AI Core
+  # Self-review: builds from source since we're pre-release
+  # Models configured to match SAP AI Core deployments
  review:
    runs-on: ubuntu-24.04
    if: github.event_name == 'pull_request'
@@ -31,12 +29,18 @@ jobs:
        include:
          - name: sonnet
            token_secret: SONNET_REVIEW_TOKEN
+            provider: anthropic
+            llm_path: /anthropic/v1
            model: anthropic--claude-4.6-sonnet
          - name: gpt
            token_secret: GPT_REVIEW_TOKEN
+            provider: openai
+            llm_path: /openai/v1
            model: gpt-5
          - name: security
            token_secret: SECURITY_REVIEW_TOKEN
+            provider: openai
+            llm_path: /openai/v1
            model: gpt-5
            system_prompt_file: SECURITY_REVIEW.md
    steps:
@@ -52,13 +56,10 @@ jobs:
          PR_NUMBER: ${{ github.event.pull_request.number }}
          REVIEWER_TOKEN: ${{ secrets[matrix.token_secret] }}
          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 }}
-          AICORE_CLIENT_ID: ${{ secrets.AICORE_CLIENT_ID }}
-          AICORE_CLIENT_SECRET: ${{ secrets.AICORE_CLIENT_SECRET }}
-          AICORE_AUTH_URL: ${{ secrets.AICORE_AUTH_URL }}
-          AICORE_API_URL: ${{ secrets.AICORE_API_URL }}
-          AICORE_RESOURCE_GROUP: ${{ secrets.AICORE_RESOURCE_GROUP }}
+          LLM_PROVIDER: ${{ matrix.provider }}
          CONVENTIONS_FILE: "CONVENTIONS.md"
          PATTERNS_REPO: "rodin/go-patterns"
          PATTERNS_FILES: "README.md,patterns/"
@@ -4,7 +4,7 @@ AI-powered code review bot for Gitea pull requests. Fetches diff + context, send

 ## 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
 - **Smart budget**: Automatically trims context to fit model token limits
 - **Idempotent reviews**: Posts new review, then cleans up stale ones (one review per bot)
@@ -168,41 +168,16 @@ Prints the review to CI logs without posting to the PR. Useful for testing promp
    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

 | Input | Required | Default | Description |
 |-------|----------|---------|-------------|
 | `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. |
-| `llm-base-url` | No* | `""` | LLM API base URL (required unless using aicore provider) |
-| `llm-api-key` | No* | `""` | LLM API key (required unless using aicore provider) |
+| `llm-base-url` | Yes | — | LLM API base URL |
+| `llm-api-key` | Yes | — | LLM API key |
 | `llm-model` | Yes | — | Model name |
-| `llm-provider` | No | `openai` | API provider: `openai`, `anthropic`, or `aicore` |
-| `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 |
+| `llm-provider` | No | `openai` | API provider: `openai` or `anthropic` |
 | `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-files` | No | `README.md` | Files/directories to fetch from pattern repos |
@@ -215,9 +190,6 @@ AI Core handles OAuth token management and deployment discovery automatically. M
 | `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 |

-*Required for `openai` and `anthropic` providers, not for `aicore`.
-**Required only for `aicore` provider.
-
 ## Runner Requirements

 The composite action requires these tools on the runner:
@@ -408,32 +380,38 @@ Each persona posts independently with its own sentinel, so reviews don't interfe

 ### Custom Personas

-Create a JSON file with your domain-specific review focus:
+Create a YAML file with your domain-specific review focus:

-```json
-// .review/personas/trading.json
-{
-  "name": "trading",
-  "display_name": "Trading Domain Expert",
-  "identity": "You are a trading systems expert reviewing code for correctness.\n\nYour expertise:\n- Order lifecycle and state machines\n- Fill handling and partial fills\n- Position tracking and P&L calculations\n- Event sourcing invariants",
-  "focus": [
-    "Order state machine correctness",
-    "Fill handling edge cases (partial, overfill)",
-    "Position and P&L calculation accuracy",
-    "Event replay determinism",
-    "Decimal precision for money"
-  ],
-  "ignore": [
-    "Code style",
-    "General performance",
-    "Documentation formatting"
-  ],
-  "severity": {
-    "major": "Bugs that cause incorrect positions, fills, or money calculations",
-    "minor": "Edge cases that could cause issues under unusual conditions",
-    "nit": "Clarity improvements for domain logic"
-  }
-}
+```yaml
+# .review/personas/trading.yaml
+name: trading
+display_name: Trading Domain Expert
+
+identity: |
+  You are a trading systems expert reviewing code for correctness.
+  
+  Your expertise:
+  - Order lifecycle and state machines
+  - Fill handling and partial fills
+  - Position tracking and P&L calculations
+  - Event sourcing invariants
+
+focus:
+  - Order state machine correctness
+  - Fill handling edge cases (partial, overfill)
+  - Position and P&L calculation accuracy
+  - Event replay determinism
+  - Decimal precision for money
+
+ignore:
+  - Code style
+  - General performance
+  - Documentation formatting
+
+severity:
+  major: Bugs that cause incorrect positions, fills, or money calculations
+  minor: Edge cases that could cause issues under unusual conditions
+  nit: Clarity improvements for domain logic
 ```

 Use it in CI:
@@ -442,17 +420,18 @@ Use it in CI:
 - uses: rodin/review-bot/.gitea/actions/review@v1
  with:
    reviewer-name: trading
-    persona-file: .review/personas/trading.json
+    persona-file: .review/personas/trading.yaml
    ...
 ```

+JSON format is also supported for backwards compatibility.

 ### Persona vs system-prompt-file

 | Feature | `persona` / `persona-file` | `system-prompt-file` |
 |---------|---------------------------|----------------------|
 | Replaces base prompt | Yes | No (appends) |
-| Structured format | Yes (JSON) | No (freeform) |
+| Structured format | Yes (YAML/JSON) | No (freeform) |
 | Focus/ignore lists | Yes | Manual |
 | Severity calibration | Yes | Manual |
 | Header display name | Yes | No |
@@ -69,17 +69,10 @@ func main() {
 	dryRun := flag.Bool("dry-run", false, "Print review to stdout instead of posting")
 	llmTemp := flag.Float64("llm-temperature", envOrDefaultFloat("LLM_TEMPERATURE", 0), "LLM temperature (0 = server default)")
 	llmTimeout := flag.Int("llm-timeout", envOrDefaultInt("LLM_TIMEOUT", 300), "LLM request timeout in seconds (default 300)")
-	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)")
 	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()

 	if *versionFlag {
@@ -93,20 +86,10 @@ func main() {
 	slog.Info("review-bot starting", "version", version)

 	// Validate required fields
-	// For aicore provider, llm-base-url and llm-api-key are not required
-	isAICore := llm.Provider(*llmProvider) == llm.ProviderAICore
-	if *giteaURL == "" || *repo == "" || *prNum == "" || *reviewerToken == "" || *llmModel == "" {
+	if *giteaURL == "" || *repo == "" || *prNum == "" || *reviewerToken == "" ||
+		*llmBaseURL == "" || *llmAPIKey == "" || *llmModel == "" {
 		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")
-		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")
+		fmt.Fprintf(os.Stderr, "Required: --gitea-url, --repo, --pr, --reviewer-token, --llm-base-url, --llm-api-key, --llm-model\n")
 		os.Exit(1)
 	}

@@ -174,17 +157,8 @@ func main() {
 	switch llm.Provider(*llmProvider) {
 	case llm.ProviderOpenAI, llm.ProviderAnthropic:
 		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:
-		slog.Error("invalid LLM provider", "provider", *llmProvider, "valid", "openai, anthropic, aicore")
+		slog.Error("invalid LLM provider", "provider", *llmProvider, "valid", "openai, anthropic")
 		os.Exit(1)
 	}
 	if *llmTimeout > 0 {
@@ -648,28 +622,21 @@ func validateWorkspacePath(path, pathName string) (string, error) {
 	if err != nil {
 		return "", fmt.Errorf("failed to resolve workspace path: %w", err)
 	}
-
 	// Join and clean the path
 	fullPath := filepath.Join(absWorkspace, path)
 	fullPath = filepath.Clean(fullPath)
-
-	// Check path is within workspace using filepath.Rel (more robust than HasPrefix)
-	rel, err := filepath.Rel(absWorkspace, fullPath)
-	if err != nil || strings.HasPrefix(rel, "..") {
+	// Check path is within workspace
+	if !strings.HasPrefix(fullPath, absWorkspace+string(filepath.Separator)) && fullPath != absWorkspace {
 		return "", fmt.Errorf("%s resolves outside workspace: path=%s workspace=%s", pathName, fullPath, absWorkspace)
 	}
-
 	// Resolve symlinks and re-validate to prevent symlink traversal
 	resolvedPath, err := filepath.EvalSymlinks(fullPath)
 	if err != nil {
 		return "", fmt.Errorf("failed to resolve %s: %w", pathName, err)
 	}
-
-	relResolved, err := filepath.Rel(absWorkspace, resolvedPath)
-	if err != nil || strings.HasPrefix(relResolved, "..") {
+	if !strings.HasPrefix(resolvedPath, absWorkspace+string(filepath.Separator)) && resolvedPath != absWorkspace {
 		return "", fmt.Errorf("%s symlink resolves outside workspace: resolved=%s workspace=%s", pathName, resolvedPath, absWorkspace)
 	}
-
 	return resolvedPath, nil
 }

@@ -6,8 +6,8 @@ import (
 	"log/slog"
 	"os"
 	"os/exec"
-	"path/filepath"
 	"strings"
+	"path/filepath"
 	"testing"

 	"gitea.weiker.me/rodin/review-bot/gitea"
@@ -103,13 +103,11 @@ func TestValidateWorkspacePath(t *testing.T) {
 			errMatch:  "resolves outside workspace",
 		},
 		{
-			name:      "absolute path normalized to workspace-relative",
+			name:      "absolute path gets normalized to relative",
 			workspace: tmpDir,
 			path:      "/etc/passwd",
 			wantErr:   true,
-			// Go 1.21+ filepath.Join normalizes absolute paths: Join("/tmp/x", "/etc/passwd")
-			// becomes "/tmp/x/etc/passwd", which is within workspace but doesn't exist.
-			errMatch: "failed to resolve",
+			errMatch:  "failed to resolve", // filepath.Join strips leading / making it <workspace>/etc/passwd which doesn't exist
 		},
 		{
 			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 {
 	r := gitea.Review{
 		ID:    id,
@@ -165,6 +164,7 @@ func makeReview(id int64, login, state string, stale bool, body string) gitea.Re
 	return r
 }

+
 func TestBuildSupersededBody(t *testing.T) {
 	original := "# Review\n\nLooks good.\n\n<!-- review-bot:sonnet -->"
 	sentinel := "<!-- review-bot:sonnet -->"
@@ -734,8 +734,8 @@ func TestExtractSentinelName_EdgeCases(t *testing.T) {
 		{"<!-- review-bot:sonnet --> rest", "sonnet"},
 		{"<!-- review-bot:gpt-review --> rest", "gpt-review"},
 		{"no sentinel here", "unknown"},
-		{"<!-- review-bot:", "unknown"},                   // prefix but no suffix
-		{"prefix <!-- review-bot:abc --> end", "abc"},     // embedded in text
+		{"<!-- review-bot:", "unknown"},       // prefix but no suffix
+		{"prefix <!-- review-bot:abc --> end", "abc"}, // embedded in text
 	}

 	for _, tc := range tests {
@@ -1,9 +1,5 @@
 # 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

 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?
 - **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)
 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

-```json
+```yaml
 # .review/personas/security.yaml
 name: security
 display_name: Security Specialist
@@ -81,7 +77,7 @@ output_format: |
 ### 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)
 ```

@@ -322,13 +318,36 @@ Design says header shows "persona display name" but sentinel uses "reviewer-name

 When persona is used, `display_name` takes precedence for the header title, but `reviewer-name` (CLI flag) is still used for the sentinel.

-## Design Revision: YAML with gopkg.in/yaml.v3
+## Design Revision: JSON Instead of YAML

-**Decision:** Add `gopkg.in/yaml.v3` as a dependency.
+**Reason:** Project convention is "Go standard library only — no external dependencies."

-YAML is preferred over JSON for persona files because:
- Multi-line strings are cleaner (no escaping quotes in identity/focus text)
- Comments are supported for documentation
- More human-readable for complex persona definitions
+YAML requires `gopkg.in/yaml.v3` or similar. To maintain zero dependencies, persona files will use JSON instead.

-The implementation supports both YAML (`.yaml`, `.yml`) and JSON (`.json`) for backwards compatibility, with YAML as the default for built-in personas.
+### Updated Persona File Format
+
+```json
+{
+  "name": "security",
+  "display_name": "Security Specialist",
+  "model_preference": "opus",
+  "identity": "You are a security specialist reviewing code for vulnerabilities.\nYour expertise: OWASP Top 10, injection attacks, auth/authz, secrets management.",
+  "focus": [
+    "Injection attacks (SQL, command, path traversal, template)",
+    "Authentication and authorization gaps",
+    "Secrets exposure (hardcoded credentials, tokens in logs)"
+  ],
+  "ignore": [
+    "Code style and naming conventions",
+    "Performance (unless security-related)",
+    "Documentation"
+  ],
+  "severity": {
+    "major": "Privilege escalation, information disclosure, DoS",
+    "minor": "Missing rate limiting, verbose errors",
+    "nit": "Theoretical risk with low exploitability"
+  }
+}
+```
+
+This maintains all the same fields but uses JSON encoding, which Go handles natively via `encoding/json`.
@@ -1,3 +1,5 @@
 module gitea.weiker.me/rodin/review-bot

 go 1.26.2
+
+require gopkg.in/yaml.v3 v3.0.1 // indirect
@@ -0,0 +1,3 @@
+gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
+gopkg.in/yaml.v3 v3.0.1 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA=
+gopkg.in/yaml.v3 v3.0.1/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
@@ -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--")
-}
@@ -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)
-	}
-}
@@ -1,6 +1,6 @@
 // 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

 import (
@@ -22,8 +22,6 @@ const (
 	ProviderOpenAI Provider = "openai"
 	// ProviderAnthropic uses the Anthropic Messages API endpoint.
 	ProviderAnthropic Provider = "anthropic"
-	// ProviderAICore uses SAP AI Core with OAuth authentication.
-	ProviderAICore Provider = "aicore"
 )

 // Client calls an LLM chat completion API.
@@ -37,7 +35,6 @@ type Client struct {
 	temperature float64
 	provider    Provider
 	http        *http.Client
-	aicore      *AICoreClient // Only set when provider is aicore
 }

 // 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).
-// When using AI Core, this also sets the timeout on the AI Core client.
 func (c *Client) WithTimeout(d time.Duration) *Client {
 	c.http.Timeout = d
-	if c.aicore != nil {
-		c.aicore.WithTimeout(d)
-	}
 	return c
 }

@@ -67,21 +60,12 @@ func (c *Client) WithTemperature(t float64) *Client {
 	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 {
 	c.provider = p
 	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.
 type Message struct {
 	Role    string `json:"role"`
@@ -98,8 +82,6 @@ func (c *Client) Complete(ctx context.Context, messages []Message) (string, erro
 		switch c.provider {
 		case ProviderAnthropic:
 			result, err = c.completeAnthropic(ctx, messages)
-		case ProviderAICore:
-			result, err = c.completeAICore(ctx, messages)
 		default:
 			result, err = c.completeOpenAI(ctx, messages)
 		}
@@ -124,18 +106,6 @@ func (c *Client) Complete(ctx context.Context, messages []Message) (string, erro
 	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.
 func isRetryableError(err error) bool {
 	if err == nil {
@@ -206,12 +176,11 @@ func (c *Client) completeOpenAI(ctx context.Context, messages []Message) (string
 // --- Anthropic Messages API implementation ---

 type anthropicRequest struct {
-	AnthropicVersion string         `json:"anthropic_version,omitempty"`
-	Model       string         `json:"model,omitempty"`
-	MaxTokens   int            `json:"max_tokens"`
-	System      string         `json:"system,omitempty"`
-	Messages    []anthropicMsg `json:"messages"`
-	Temperature float64        `json:"temperature,omitempty"`
+	Model       string            `json:"model"`
+	MaxTokens   int               `json:"max_tokens"`
+	System      string            `json:"system,omitempty"`
+	Messages    []anthropicMsg    `json:"messages"`
+	Temperature float64           `json:"temperature,omitempty"`
 }

 type anthropicMsg struct {
@@ -7,7 +7,39 @@ import (

 // FormatMarkdown formats a ReviewResult into the markdown body for a Gitea review.
 func FormatMarkdown(result *ReviewResult, reviewerName string) string {
-	return FormatMarkdownWithDisplay(result, reviewerName, reviewerName)
+	var sb strings.Builder
+
+	if reviewerName != "" {
+		title := strings.ToUpper(reviewerName[:1]) + reviewerName[1:]
+		sb.WriteString(fmt.Sprintf("# %s Review\n\n", title))
+	}
+
+	sb.WriteString("## Summary\n\n")
+	sb.WriteString(result.Summary)
+	sb.WriteString("\n\n")
+
+	if len(result.Findings) > 0 {
+		sb.WriteString("## Findings\n\n")
+		sb.WriteString("| # | Severity | File | Line | Finding |\n")
+		sb.WriteString("|---|----------|------|------|--------|\n")
+
+		for i, f := range result.Findings {
+			sb.WriteString(fmt.Sprintf("| %d | [%s] | `%s` | %d | %s |\n",
+				i+1, f.Severity, f.File, f.Line, f.Finding))
+		}
+		sb.WriteString("\n")
+	}
+
+	sb.WriteString("## Recommendation\n\n")
+	sb.WriteString(fmt.Sprintf("**%s** — %s\n", result.Verdict, result.Recommendation))
+
+	if reviewerName != "" {
+		sb.WriteString(fmt.Sprintf("\n---\n*Review by %s*\n", reviewerName))
+		// Hidden sentinel for identifying this bot's reviews during cleanup
+		sb.WriteString(fmt.Sprintf("\n<!-- review-bot:%s -->\n", reviewerName))
+	}
+
+	return sb.String()
 }

 // GiteaEvent converts the verdict to the Gitea API event string.
@@ -23,8 +55,6 @@ func GiteaEvent(verdict string) string {
 }

 // FormatMarkdownWithDisplay formats a ReviewResult with separate display name and sentinel name.
-// Note: displayName is not HTML-escaped as Gitea sanitizes rendered Markdown.
-// Persona display names are controlled by repo owners (trusted input).
 // displayName is used for the header title, sentinelName is used for the cleanup sentinel.
 // If displayName is empty, sentinelName is used for both.
 func FormatMarkdownWithDisplay(result *ReviewResult, displayName, sentinelName string) string {
@@ -37,7 +67,7 @@ func FormatMarkdownWithDisplay(result *ReviewResult, displayName, sentinelName s
 	}

 	if headerName != "" {
-		title := CapitalizeFirst(headerName)
+		title := strings.ToUpper(headerName[:1]) + headerName[1:]
 		sb.WriteString(fmt.Sprintf("# %s Review\n\n", title))
 	}

@@ -5,34 +5,37 @@ import (
 	"encoding/json"
 	"fmt"
 	"os"
+	"path/filepath"
 	"strings"
-	"unicode/utf8"
+
+	"gopkg.in/yaml.v3"
 )

-//go:embed personas/*.json
+//go:embed personas/*.yaml
 var embeddedPersonas embed.FS

 // Persona defines a specialized review role with focused expertise.
 type Persona struct {
-	Name         string   `json:"name"`
-	DisplayName  string   `json:"display_name"`
-	ModelPref    string   `json:"model_preference,omitempty"`
-	Identity     string   `json:"identity"`
-	Focus        []string `json:"focus"`
-	Ignore       []string `json:"ignore"`
-	Severity     Severity `json:"severity"`
-	OutputFormat string   `json:"output_format,omitempty"`
+	Name         string   `json:"name" yaml:"name"`
+	DisplayName  string   `json:"display_name" yaml:"display_name"`
+	ModelPref    string   `json:"model_preference,omitempty" yaml:"model_preference,omitempty"`
+	Identity     string   `json:"identity" yaml:"identity"`
+	Focus        []string `json:"focus" yaml:"focus"`
+	Ignore       []string `json:"ignore" yaml:"ignore"`
+	Severity     Severity `json:"severity" yaml:"severity"`
+	OutputFormat string   `json:"output_format,omitempty" yaml:"output_format,omitempty"`
 }

 // Severity defines what constitutes each severity level for this persona.
 // These are prompt guidance for the LLM, not output format changes.
 type Severity struct {
-	Major string `json:"major"`
-	Minor string `json:"minor"`
-	Nit   string `json:"nit"`
+	Major string `json:"major" yaml:"major"`
+	Minor string `json:"minor" yaml:"minor"`
+	Nit   string `json:"nit" yaml:"nit"`
 }

-// LoadPersona loads a persona from a JSON file path.
+// LoadPersona loads a persona from a file path.
+// Supports both YAML (.yaml, .yml) and JSON (.json) formats.
 func LoadPersona(path string) (*Persona, error) {
 	data, err := os.ReadFile(path)
 	if err != nil {
@@ -44,8 +47,8 @@ func LoadPersona(path string) (*Persona, error) {
 // LoadBuiltinPersona loads a built-in persona by name.
 // Returns an error if the persona doesn't exist.
 func LoadBuiltinPersona(name string) (*Persona, error) {
-	filename := name + ".json"
-	data, err := embeddedPersonas.ReadFile("personas/" + filename) // embed.FS paths use forward slashes per io/fs spec
+	filename := name + ".yaml"
+	data, err := embeddedPersonas.ReadFile(filepath.Join("personas", filename))
 	if err != nil {
 		available := ListBuiltinPersonas()
 		return nil, fmt.Errorf("unknown built-in persona %q (available: %s)", name, strings.Join(available, ", "))
@@ -54,11 +57,10 @@ func LoadBuiltinPersona(name string) (*Persona, error) {
 }

 // ListBuiltinPersonas returns the names of all built-in personas.
-// Returns an empty slice if the embedded directory cannot be read.
 func ListBuiltinPersonas() []string {
 	entries, err := embeddedPersonas.ReadDir("personas")
 	if err != nil {
-		return []string{}
+		return nil
 	}
 	var names []string
 	for _, e := range entries {
@@ -66,8 +68,10 @@ func ListBuiltinPersonas() []string {
 			continue
 		}
 		name := e.Name()
-		if strings.HasSuffix(name, ".json") {
-			names = append(names, strings.TrimSuffix(name, ".json"))
+		if strings.HasSuffix(name, ".yaml") {
+			names = append(names, strings.TrimSuffix(name, ".yaml"))
+		} else if strings.HasSuffix(name, ".yml") {
+			names = append(names, strings.TrimSuffix(name, ".yml"))
 		}
 	}
 	return names
@@ -75,9 +79,20 @@ func ListBuiltinPersonas() []string {

 func parsePersona(data []byte, source string) (*Persona, error) {
 	var p Persona
-	if err := json.Unmarshal(data, &p); err != nil {
-		return nil, fmt.Errorf("parse persona %s: %w", source, err)
+	
+	// Determine format by extension or try YAML first (it's a superset of JSON)
+	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 {
+		// YAML (also handles .yaml, .yml, and builtin: prefix)
+		if err := yaml.Unmarshal(data, &p); err != nil {
+			return nil, fmt.Errorf("parse persona %s: %w", source, err)
+		}
 	}
+	
 	if err := validatePersona(&p, source); err != nil {
 		return nil, err
 	}
@@ -97,16 +112,3 @@ func validatePersona(p *Persona, source string) error {
 	}
 	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:]
-}
@@ -50,7 +50,7 @@ func BuildPersonaSystemPrompt(p *Persona) string {
 		sb.WriteString("\n")
 	}

-	// Output format instructions (shared schema from prompt.go)
+	// Output format instructions (same as base, but with persona context)
 	sb.WriteString("## Review Instructions\n\n")
 	sb.WriteString("CONTEXT:\n")
 	sb.WriteString("- You will receive the full content of modified files for reference, followed by the diff showing what changed.\n")
@@ -61,10 +61,24 @@ func BuildPersonaSystemPrompt(p *Persona) string {
 	sb.WriteString("2. Consider the CI status — if CI has failed, that is an automatic REQUEST_CHANGES regardless of code quality.\n")
 	sb.WriteString("3. Output your review as structured JSON (and ONLY JSON, no markdown fences or other text).\n\n")
 	sb.WriteString("Output format:\n")
-	sb.WriteString(outputSchemaJSON)
-	sb.WriteString("\n\n")
-	sb.WriteString(verdictRules)
-	sb.WriteString("\n- Only report findings within your focus areas. Ignore everything else.\n")
+	sb.WriteString("{\n")
+	sb.WriteString("  \"verdict\": \"APPROVE\" or \"REQUEST_CHANGES\",\n")
+	sb.WriteString("  \"summary\": \"Brief overall assessment (1-3 sentences)\",\n")
+	sb.WriteString("  \"findings\": [\n")
+	sb.WriteString("    {\n")
+	sb.WriteString("      \"severity\": \"MAJOR\" or \"MINOR\" or \"NIT\",\n")
+	sb.WriteString("      \"file\": \"path/to/file\",\n")
+	sb.WriteString("      \"line\": <line number from the diff>,\n")
+	sb.WriteString("      \"finding\": \"Description of the issue\"\n")
+	sb.WriteString("    }\n")
+	sb.WriteString("  ],\n")
+	sb.WriteString("  \"recommendation\": \"Full recommendation text explaining your verdict\"\n")
+	sb.WriteString("}\n\n")
+	sb.WriteString("Rules:\n")
+	sb.WriteString("- If there are any MAJOR findings → verdict must be REQUEST_CHANGES\n")
+	sb.WriteString("- If there are no MAJOR findings → verdict should be APPROVE\n")
+	sb.WriteString("- If CI has failed → verdict must be REQUEST_CHANGES with a finding noting the CI failure\n")
+	sb.WriteString("- Only report findings within your focus areas. Ignore everything else.\n")
 	sb.WriteString("- Line numbers should reference the new file line numbers from the diff headers.\n")
 	sb.WriteString("- If the diff has no changes relevant to your focus areas, APPROVE with no findings.\n")

@@ -87,22 +87,26 @@ func TestListBuiltinPersonas(t *testing.T) {
 	}
 }

-func TestLoadPersonaFromJSONFile(t *testing.T) {
+func TestLoadPersonaFromYAMLFile(t *testing.T) {
 	dir := t.TempDir()
-	path := filepath.Join(dir, "test.json")
+	path := filepath.Join(dir, "test.yaml")

-	content := `{
-		"name": "test",
-		"display_name": "Test Persona",
-		"identity": "You are a test persona.\nMulti-line identity works.",
-		"focus": ["testing", "validation"],
-		"ignore": ["nothing"],
-		"severity": {
-			"major": "Big problems",
-			"minor": "Small problems",
-			"nit": "Tiny problems"
-		}
-	}`
+	content := `
+name: test
+display_name: Test Persona
+identity: |
+  You are a test persona.
+  Multi-line identity works.
+focus:
+  - testing
+  - validation
+ignore:
+  - nothing
+severity:
+  major: Big problems
+  minor: Small problems
+  nit: Tiny problems
+`

 	if err := os.WriteFile(path, []byte(content), 0644); err != nil {
 		t.Fatalf("failed to write test file: %v", err)
@@ -127,25 +131,59 @@ func TestLoadPersonaFromJSONFile(t *testing.T) {
 	}
 }

+func TestLoadPersonaFromJSONFile(t *testing.T) {
+	dir := t.TempDir()
+	path := filepath.Join(dir, "test.json")
+
+	content := `{
+		"name": "test",
+		"display_name": "Test Persona",
+		"identity": "You are a test persona.",
+		"focus": ["testing"],
+		"ignore": ["nothing"],
+		"severity": {
+			"major": "Big problems",
+			"minor": "Small problems",
+			"nit": "Tiny problems"
+		}
+	}`
+
+	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 Persona" {
+		t.Errorf("DisplayName = %q, want %q", p.DisplayName, "Test Persona")
+	}
+}
+
 func TestLoadPersonaValidation(t *testing.T) {
 	tests := []struct {
 		name    string
-		json    string
+		yaml    string
 		wantErr string
 	}{
 		{
 			name:    "missing name",
-			json:    `{"identity": "test"}`,
+			yaml:    "identity: test",
 			wantErr: "name is required",
 		},
 		{
 			name:    "missing identity",
-			json:    `{"name": "test"}`,
+			yaml:    "name: test",
 			wantErr: "identity is required",
 		},
 		{
 			name: "display_name defaults to name",
-			json: `{"name": "test", "identity": "test identity"}`,
+			yaml: "name: test\nidentity: test identity",
 			// No error expected - should succeed
 		},
 	}
@@ -153,8 +191,8 @@ func TestLoadPersonaValidation(t *testing.T) {
 	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.json), 0644); err != nil {
+			path := filepath.Join(dir, "test.yaml")
+			if err := os.WriteFile(path, []byte(tt.yaml), 0644); err != nil {
 				t.Fatalf("failed to write test file: %v", err)
 			}

@@ -184,56 +222,21 @@ func TestLoadPersonaValidation(t *testing.T) {
 }

 func TestLoadPersonaFileNotFound(t *testing.T) {
-	_, err := LoadPersona("/nonexistent/path/persona.json")
+	_, err := LoadPersona("/nonexistent/path/persona.yaml")
 	if err == nil {
 		t.Error("expected error for nonexistent file")
 	}
 }

-func TestLoadPersonaInvalidJSON(t *testing.T) {
+func TestLoadPersonaInvalidYAML(t *testing.T) {
 	dir := t.TempDir()
-	path := filepath.Join(dir, "invalid.json")
-	if err := os.WriteFile(path, []byte("not valid json {"), 0644); err != nil {
+	path := filepath.Join(dir, "invalid.yaml")
+	if err := os.WriteFile(path, []byte("not: valid: yaml: here"), 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 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")
+		t.Error("expected error for invalid YAML")
 	}
 }
@@ -1,26 +0,0 @@
-{
-  "name": "architect",
-  "display_name": "Software Architect",
-  "identity": "You are a software architect reviewing code for design quality.\n\nYour expertise:\n- Design patterns and anti-patterns\n- Code organization and module boundaries\n- API design and contracts\n- Testability and dependency injection\n- Consistency with existing architecture\n- Technical debt identification",
-  "focus": [
-    "Design pattern violations or misuse",
-    "Module boundary violations (inappropriate coupling)",
-    "API design issues (unclear contracts, leaky abstractions)",
-    "Testability problems (hidden dependencies, god objects)",
-    "Inconsistency with existing codebase patterns",
-    "Unnecessary complexity or over-engineering",
-    "Missing abstractions or premature abstraction"
-  ],
-  "ignore": [
-    "Security vulnerabilities (security persona handles these)",
-    "Performance micro-optimizations",
-    "Code style and formatting",
-    "Documentation typos",
-    "Test implementation details"
-  ],
-  "severity": {
-    "major": "Architectural violations that will cause maintenance problems or make the codebase harder to evolve",
-    "minor": "Design issues that reduce clarity or testability but don't block progress",
-    "nit": "Minor pattern deviations or style preferences"
-  }
-}
@@ -0,0 +1,34 @@
+name: architect
+display_name: Software Architect
+
+identity: |
+  You are a software architect reviewing code for design quality.
+  
+  Your expertise:
+  - Design patterns and anti-patterns
+  - Code organization and module boundaries
+  - API design and contracts
+  - Testability and dependency injection
+  - Consistency with existing architecture
+  - Technical debt identification
+
+focus:
+  - Design pattern violations or misuse
+  - Module boundary violations (inappropriate coupling)
+  - API design issues (unclear contracts, leaky abstractions)
+  - Testability problems (hidden dependencies, god objects)
+  - Inconsistency with existing codebase patterns
+  - Unnecessary complexity or over-engineering
+  - Missing abstractions or premature abstraction
+
+ignore:
+  - Security vulnerabilities (security persona handles these)
+  - Performance micro-optimizations
+  - Code style and formatting
+  - Documentation typos
+  - Test implementation details
+
+severity:
+  major: "Architectural violations that will cause maintenance problems or make the codebase harder to evolve"
+  minor: "Design issues that reduce clarity or testability but don't block progress"
+  nit: "Minor pattern deviations or style preferences"
@@ -1,26 +0,0 @@
-{
-  "name": "docs",
-  "display_name": "Documentation Reviewer",
-  "identity": "You are a documentation specialist reviewing code for clarity and documentation quality.\n\nYour expertise:\n- API documentation and examples\n- Code comments and their accuracy\n- Error message clarity\n- README and guide quality\n- Naming clarity and self-documenting code",
-  "focus": [
-    "Missing or outdated documentation",
-    "Unclear or misleading comments",
-    "Poor error messages (cryptic, unhelpful, missing context)",
-    "Confusing naming (functions, variables, types)",
-    "Missing examples for complex APIs",
-    "Inconsistent terminology",
-    "Documentation that contradicts the code"
-  ],
-  "ignore": [
-    "Security vulnerabilities",
-    "Performance issues",
-    "Design patterns",
-    "Test coverage",
-    "Code style (unless it affects readability)"
-  ],
-  "severity": {
-    "major": "Documentation that actively misleads or missing docs for critical functionality",
-    "minor": "Unclear documentation or poor error messages that will confuse users",
-    "nit": "Minor clarity improvements or typo fixes"
-  }
-}
@@ -0,0 +1,33 @@
+name: docs
+display_name: Documentation Reviewer
+
+identity: |
+  You are a documentation specialist reviewing code for clarity and documentation quality.
+  
+  Your expertise:
+  - API documentation and examples
+  - Code comments and their accuracy
+  - Error message clarity
+  - README and guide quality
+  - Naming clarity and self-documenting code
+
+focus:
+  - Missing or outdated documentation
+  - Unclear or misleading comments
+  - Poor error messages (cryptic, unhelpful, missing context)
+  - Confusing naming (functions, variables, types)
+  - Missing examples for complex APIs
+  - Inconsistent terminology
+  - Documentation that contradicts the code
+
+ignore:
+  - Security vulnerabilities
+  - Performance issues
+  - Design patterns
+  - Test coverage
+  - Code style (unless it affects readability)
+
+severity:
+  major: "Documentation that actively misleads or missing docs for critical functionality"
+  minor: "Unclear documentation or poor error messages that will confuse users"
+  nit: "Minor clarity improvements or typo fixes"
@@ -1,26 +0,0 @@
-{
-  "name": "security",
-  "display_name": "Security Specialist",
-  "identity": "You are a security specialist reviewing code for vulnerabilities.\n\nYour expertise:\n- OWASP Top 10 vulnerabilities\n- Injection attacks (SQL, command, path traversal, template)\n- Authentication and authorization patterns\n- Secrets management and exposure risks\n- Race conditions with security implications\n- Event sourcing attack vectors (replay attacks, event injection)",
-  "focus": [
-    "Injection attacks (SQL, command, path traversal, template injection)",
-    "Authentication and authorization gaps or bypasses",
-    "Secrets exposure (hardcoded credentials, tokens in logs, config leaks)",
-    "Input validation failures (unsanitized input, unsafe deserialization)",
-    "Race conditions that could be exploited",
-    "Cryptographic weaknesses (weak algorithms, improper key handling)",
-    "Information disclosure through error messages or logs"
-  ],
-  "ignore": [
-    "Code style and naming conventions",
-    "Performance optimizations (unless security-related)",
-    "Documentation quality",
-    "General code quality or readability",
-    "Test coverage"
-  ],
-  "severity": {
-    "major": "Exploitable vulnerabilities: auth bypass, injection, data exfiltration, privilege escalation, RCE",
-    "minor": "Defense-in-depth issues: missing rate limiting, verbose errors, weak input validation",
-    "nit": "Theoretical risks with low exploitability or impact"
-  }
-}
@@ -0,0 +1,34 @@
+name: security
+display_name: Security Specialist
+
+identity: |
+  You are a security specialist reviewing code for vulnerabilities.
+  
+  Your expertise:
+  - OWASP Top 10 vulnerabilities
+  - Injection attacks (SQL, command, path traversal, template)
+  - Authentication and authorization patterns
+  - Secrets management and exposure risks
+  - Race conditions with security implications
+  - Event sourcing attack vectors (replay attacks, event injection)
+
+focus:
+  - Injection attacks (SQL, command, path traversal, template injection)
+  - Authentication and authorization gaps or bypasses
+  - Secrets exposure (hardcoded credentials, tokens in logs, config leaks)
+  - Input validation failures (unsanitized input, unsafe deserialization)
+  - Race conditions that could be exploited
+  - Cryptographic weaknesses (weak algorithms, improper key handling)
+  - Information disclosure through error messages or logs
+
+ignore:
+  - Code style and naming conventions
+  - Performance optimizations (unless security-related)
+  - Documentation quality
+  - General code quality or readability
+  - Test coverage
+
+severity:
+  major: "Exploitable vulnerabilities: auth bypass, injection, data exfiltration, privilege escalation, RCE"
+  minor: "Defense-in-depth issues: missing rate limiting, verbose errors, weak input validation"
+  nit: "Theoretical risks with low exploitability or impact"
@@ -7,28 +7,6 @@ import (
 	"strings"
 )

-// outputSchemaJSON is the shared JSON output format specification used by both
-// the generic reviewer and persona-based reviewers.
-const outputSchemaJSON = `{
-  "verdict": "APPROVE" or "REQUEST_CHANGES",
-  "summary": "Brief overall assessment (1-3 sentences)",
-  "findings": [
-    {
-      "severity": "MAJOR" or "MINOR" or "NIT",
-      "file": "path/to/file",
-      "line": <line number from the diff>,
-      "finding": "Description of the issue"
-    }
-  ],
-  "recommendation": "Full recommendation text explaining your verdict"
-}`
-
-// verdictRules is the shared verdict determination rules.
-const verdictRules = `Rules:
- If there are any MAJOR findings → verdict must be REQUEST_CHANGES
- If there are no MAJOR findings → verdict should be APPROVE
- If CI has failed → verdict must be REQUEST_CHANGES with a finding noting the CI failure`
-
 // BuildSystemBase returns the core system prompt instructions without
 // patterns or conventions. Used by the budget package to separate
 // trimmable from non-trimmable content.
@@ -45,10 +23,24 @@ func BuildSystemBase() string {
 	sb.WriteString("2. Consider the CI status — if CI has failed, that is an automatic REQUEST_CHANGES regardless of code quality.\n")
 	sb.WriteString("3. Output your review as structured JSON (and ONLY JSON, no markdown fences or other text).\n\n")
 	sb.WriteString("Output format:\n")
-	sb.WriteString(outputSchemaJSON)
-	sb.WriteString("\n\n")
-	sb.WriteString(verdictRules)
-	sb.WriteString("\n- Be thorough but fair. Don't nitpick style unless it impacts readability significantly.\n")
+	sb.WriteString("{\n")
+	sb.WriteString("  \"verdict\": \"APPROVE\" or \"REQUEST_CHANGES\",\n")
+	sb.WriteString("  \"summary\": \"Brief overall assessment (1-3 sentences)\",\n")
+	sb.WriteString("  \"findings\": [\n")
+	sb.WriteString("    {\n")
+	sb.WriteString("      \"severity\": \"MAJOR\" or \"MINOR\" or \"NIT\",\n")
+	sb.WriteString("      \"file\": \"path/to/file\",\n")
+	sb.WriteString("      \"line\": <line number from the diff>,\n")
+	sb.WriteString("      \"finding\": \"Description of the issue\"\n")
+	sb.WriteString("    }\n")
+	sb.WriteString("  ],\n")
+	sb.WriteString("  \"recommendation\": \"Full recommendation text explaining your verdict\"\n")
+	sb.WriteString("}\n\n")
+	sb.WriteString("Rules:\n")
+	sb.WriteString("- If there are any MAJOR findings → verdict must be REQUEST_CHANGES\n")
+	sb.WriteString("- If there are no MAJOR findings → verdict should be APPROVE\n")
+	sb.WriteString("- If CI has failed → verdict must be REQUEST_CHANGES with a finding noting the CI failure\n")
+	sb.WriteString("- Be thorough but fair. Don't nitpick style unless it impacts readability significantly.\n")
 	sb.WriteString("- Line numbers should reference the new file line numbers from the diff headers.\n")
 	sb.WriteString("- If the diff is empty or trivial (only formatting/whitespace), APPROVE with no findings.\n")