Feature/tool configurations

.agent/skills/git-worktrees/SKILL.md

@@ -0,0 +1,14 @@
+# Git Worktrees Skill
+
+# IDENTIFIER: automaker-worktree-skill
+
+## Description
+
+This skill enables the agent to manage isolated development environments using Git Worktrees, which is the preferred way to work in the Automaker repository.
+
+## Instructions
+
+- Always use `git worktree list` before creating new ones to avoid path conflicts.
+- Prefer naming worktrees with the prefix `../automaker-worktree-`.
+- Ensure you are in the root of the repository before running worktree commands.
+- Use the `git-worktree` workflow for step-by-step execution.

.agent/workflows/git-worktree.md

@@ -0,0 +1,32 @@
+---
+description: How to manage git worktrees in Automaker (IDENTIFIER: automaker-worktree-workflow)
+---
+
+# Git Worktree Workflow
+
+This workflow describes how to safely use git worktrees for feature development in Automaker.
+
+1. **Check existing worktrees**:
+
+   ```bash
+   git worktree list
+   ```
+
+2. **Create a new worktree for a feature**:
+
+   ```bash
+   git worktree add ../automaker-worktree-<name> -b feature/<name>
+   ```
+
+3. **Navigate to the worktree**:
+   - `cd ../automaker-worktree-<name>`
+
+4. **Remove worktree after completion**:
+
+   ```bash
+   git worktree remove ../automaker-worktree-<name>
+   git branch -d feature/<name>
+   ```
+
+5. **Verify current setup**:
+   git status

.github/workflows/pr_agent.yml

@@ -0,0 +1,24 @@
+name: Qodo PR Agent
+
+on:
+  pull_request:
+    types: [opened, reopened, ready_for_review]
+  issue_comment:
+    types: [created, edited]
+
+permissions:
+  pull-requests: write
+  issues: write
+  contents: read
+
+jobs:
+  pr_agent:
+    runs-on: ubuntu-latest
+    name: Run PR Agent
+    if: ${{ github.event.sender.type != 'Bot' }}
+    steps:
+      - id: pr-agent
+        uses: Codium-ai/pr-agent@main
+        env:
+          OPENAI_KEY: ${{ secrets.OPENAI_KEY }}
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

.pr_agent.toml

@@ -0,0 +1,12 @@
+# Qodo configuration for Automaker
+# IDENTIFIER: automaker-qodo-config
+
+[pr_test]
+testing_framework = "vitest"
+
+[pr_reviewer]
+require_score_review = true
+enable_review_labels_security = true
+enable_review_labels_effort = true
+num_code_suggestions = 4
+inline_code_comments = true

.qodo.toml

@@ -0,0 +1,5 @@
+# Qodo configuration for Automaker
+# IDENTIFIER: automaker-qodo-config
+
+[pr_test]
+testing_framework = "vitest"

apps/server/package.json

@@ -34,6 +34,7 @@
     "@automaker/utils": "1.0.0",
     "@modelcontextprotocol/sdk": "1.25.2",
     "@openai/codex-sdk": "^0.77.0",
+    "axios": "^1.13.2",
     "cookie-parser": "1.4.7",
     "cors": "2.8.5",
     "dotenv": "17.2.3",

apps/server/src/config/sprites.ts

@@ -0,0 +1,13 @@
+export const spritesConfig = {
+  SPRITES_TOKEN: process.env.SPRITES_TOKEN,
+  SPRITES_API_BASE: process.env.SPRITES_API_BASE || 'https://api.sprites.dev/v1',
+  GITHUB_TOKEN: process.env.GITHUB_TOKEN,
+  LINEAR_API_KEY: process.env.LINEAR_API_KEY,
+  CLAUDE_OAUTH_TOKEN: process.env.CLAUDE_OAUTH_TOKEN,
+  DEFAULT_REPO_URL: process.env.DEFAULT_REPO_URL,
+  DEFAULT_BRANCH: process.env.DEFAULT_BRANCH || 'main',
+  GIT_USER_NAME: process.env.GIT_USER_NAME || 'Automaker Agent',
+  GIT_USER_EMAIL: process.env.GIT_USER_EMAIL || 'agent@automaker.dev',
+  OTEL_RECEIVER_PORT: parseInt(process.env.OTEL_RECEIVER_PORT || '4317'),
+  OTEL_RECEIVER_HOST: process.env.OTEL_RECEIVER_HOST || '0.0.0.0',
+};

apps/server/src/lib/sdk-options.ts

@@ -215,6 +215,19 @@ export function getModelForUseCase(
     default: CLAUDE_MODEL_MAP['opus'],
   };
 
+  // Fallback to OpenAI if Anthropic key is missing but OpenAI key is present
+  if (!process.env.ANTHROPIC_API_KEY && process.env.OPENAI_API_KEY) {
+    // Override defaults with OpenAI equivalents
+    defaultModels.spec = 'codex-gpt-4o';
+    defaultModels.features = 'codex-gpt-4o';
+    defaultModels.suggestions = 'codex-gpt-4o';
+    defaultModels.chat = 'codex-gpt-4o';
+    defaultModels.auto = 'codex-gpt-4o';
+    defaultModels.default = 'codex-gpt-4o';
+
+    logger.info(`Using OpenAI (codex-gpt-4o) for ${useCase} due to missing Anthropic key`);
+  }
+
   return resolveModelString(defaultModels[useCase] || DEFAULT_MODELS.claude);
 }
 

apps/server/src/routes/features/routes/generate-title.ts

@@ -60,12 +60,23 @@ export function createGenerateTitleHandler(
       const prompts = await getPromptCustomization(settingsService, '[GenerateTitle]');
       const systemPrompt = prompts.titleGeneration.systemPrompt;
 
+      let model = CLAUDE_MODEL_MAP.haiku;
+
+      // Fallback to OpenAI if Anthropic key is missing but OpenAI key is present
+      if (!process.env.ANTHROPIC_API_KEY && process.env.OPENAI_API_KEY) {
+        // Use gpt-4o which is comparable/better than haiku
+        model = 'codex-gpt-4o';
+        logger.info(
+          'Using OpenAI (codex-gpt-4o) for title generation due to missing Anthropic key'
+        );
+      }
+
       const userPrompt = `Generate a concise title for this feature:\n\n${trimmedDescription}`;
 
       // Use simpleQuery - provider abstraction handles all the streaming/extraction
       const result = await simpleQuery({
         prompt: `${systemPrompt}\n\n${userPrompt}`,
-        model: CLAUDE_MODEL_MAP.haiku,
+        model,
         cwd: process.cwd(),
         maxTurns: 1,
         allowedTools: [],

apps/server/src/services/codex-model-cache-service.ts

@@ -149,6 +149,37 @@ export class CodexModelCacheService {
     try {
       // Check if app-server is available
       const isAvailable = await this.appServerService.isAvailable();
+
+      // FALLBACK: If CLI is not available but we have an OpenAI API Key (e.g. in CI or limited env),
+      // provide default models so the UI doesn't block.
+      if (!isAvailable && process.env.OPENAI_API_KEY) {
+        logger.info('[doRefresh] CLI unavailable but OPENAI_API_KEY found. Using fallback models.');
+        const fallbackModels: CodexModel[] = [
+          {
+            id: 'codex-gpt-4o',
+            label: 'GPT-4o (Fallback)',
+            description: 'Fallback model using direct OpenAI API',
+            hasThinking: false,
+            supportsVision: true,
+            tier: 'premium',
+            isDefault: true,
+          },
+          {
+            id: 'codex-gpt-4o-mini',
+            label: 'GPT-4o Mini (Fallback)',
+            description: 'Fast fallback model using direct OpenAI API',
+            hasThinking: false,
+            supportsVision: true,
+            tier: 'basic',
+            isDefault: false,
+          },
+        ];
+
+        // Save to cache so subsequent requests are fast
+        await this.saveToCache(fallbackModels);
+        return fallbackModels;
+      }
+
       if (!isAvailable) {
         return [];
       }