feat(cli): implement Claude CLI detection and model selection for features

- Added a new service to detect the installation status of Claude Code CLI, providing users with installation recommendations and commands.
- Integrated CLI detection into the SettingsView to inform users about the CLI status and its benefits for ultrathink tasks.
- Enhanced feature creation and editing dialogs to allow users to select from multiple models (Haiku, Sonnet, Opus) and specify thinking levels (None, Low, Medium, High, Ultrathink).
- Updated the feature executor to utilize the selected model and thinking configuration during task execution, improving flexibility and performance.

This update enhances user experience by providing clearer options for model selection and ensuring optimal performance with the Claude CLI.

🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Sonnet 4 <noreply@anthropic.com>

.automaker/feature_list.json

@@ -71,5 +71,22 @@
     "startedAt": "2025-12-09T22:31:41.946Z",
     "imagePaths": [],
     "skipTests": true
+  },
+  {
+    "id": "feature-1765321570899-oefrfast6",
+    "category": "Core",
+    "description": "I would like to have abbility to set correct model for new feautres. so inteas of only using claude opus we could use other models like sonnet or haiku for easier / light one tasks as well to add abbility how much thinking lvl we wanna use on each task as well",
+    "steps": [
+      "User add new feature",
+      "User Describe it",
+      "Select the automated testing or manual one",
+      "If the task is light / easy to implement he use lighter model from anthropi sdk such as sonnet / haiku",
+      "agent execute task with correct model "
+    ],
+    "status": "verified",
+    "startedAt": "2025-12-09T23:07:37.223Z",
+    "imagePaths": [],
+    "skipTests": false,
+    "summary": "Added model selection (Haiku/Sonnet/Opus) and thinking level (None/Low/Medium/High) controls to feature creation and edit dialogs. Modified: app-store.ts (added AgentModel and ThinkingLevel types), board-view.tsx (UI controls), feature-executor.js (dynamic model/thinking config), feature-loader.js (field persistence). Agent now executes with user-selected model and extended thinking settings."
   }
 ]