feat(tool) show tool usage via channel

[afjcjsbx]

📝 Description

Introduced an (optional) real-time feedback mechanism to notify users when the agent is actively using a tool (e.g., executing a command or searching the web). This vastly improves the UX by showing that the agent is "thinking" and performing actions, rather than just hanging silently while processing.

Key implementations:

• Added a NotificationFormatter interface in the tools package. The core agent loop now checks if a tool implements this interface via type assertion.
• Global Toggle: Added enable_notifications boolean under the tools configuration (defaults to false) so users can silence these intermediate messages if they prefer a cleaner chat.

🗣️ Type of Change

• 🐞 Bug fix (non-breaking change which fixes an issue)
• ✨ New feature (non-breaking change which adds functionality)
• 📖 Documentation update
• ⚡ Code refactoring (no functional changes, no api changes)

🤖 AI Code Generation

• 🤖 Fully AI-generated (100% AI, 0% Human)
• 🛠️ Mostly AI-generated (AI draft, Human verified/modified)
• 👨‍💻 Mostly Human-written (Human lead, AI assisted or none)

🔗 Related Issue

📚 Technical Context (Skip for Docs)

• Reference URL: N/A
• Reasoning:

🧪 Test Environment

• Hardware: PC / Server
• OS: Linux / macOS
• Model/Provider: OpenAI / Anthropic
• Channels: Telegram / CLI

📸 Evidence (Optional)

---

Configuration Example (config.json):
Users can disable this feature globally:

{
  "tools": {
    "enable_notifications": false
  }
}

☑️ Checklist

• My code/docs follow the style of this project.
• I have performed a self-review of my own changes.
• I have updated the documentation accordingly.