✨(ai) add message reply generation tool

[MathisRouget]

Purpose

This feature allows user to generate new messages and answers by AI thanks to a prompt and previous mails context.

Proposal

Add backend feature and frontend AI Toolbar

[Copilot]

Pull Request Overview

This PR introduces AI-powered message generation capabilities to the email application, allowing users to generate new messages and replies using AI assistance based on prompts and context from previous emails.

• Adds backend API endpoints for generating new messages and reply messages using AI
• Implements frontend feature flags to control AI message generation functionality
• Integrates AI prompts configuration for multiple languages

Reviewed Changes

Copilot reviewed 20 out of 20 changed files in this pull request and generated 1 comment.

Show a summary per file

File	Description
src/frontend/src/hooks/use-feature.ts	Adds feature flag for AI message generation
src/frontend/src/features/providers/config.tsx	Adds default config for message generation feature
src/frontend/src/features/api/gen/threads/threads.ts	Adds API client functions for new and reply message generation
src/frontend/src/features/api/gen/models/*.ts	Adds TypeScript types for API requests and responses
src/backend/messages/settings.py	Adds backend configuration for message generation feature
src/backend/core/tests/api/test_config.py	Updates config tests with new feature flag
src/backend/core/api/viewsets/thread.py	Implements API endpoints for message generation
src/backend/core/api/viewsets/config.py	Exposes message generation feature flag in config API
src/backend/core/ai/utils.py	Adds utility functions for AI prompt management
src/backend/core/ai/message_generator.py	Implements core AI message generation logic
src/backend/core/ai/ai_prompts.json	Adds AI prompts for message generation in multiple languages

---

_{Tip: Customize your code reviews with copilot-instructions.md. Create the file or learn how to get started.}

[Copilot]

The code references 'reply_message_generation_query' but the JSON file defines 'thread_response_generation_query'. This will cause a KeyError at runtime when trying to generate reply messages.

Suggested change

	prompt_query = prompt_template["reply_message_generation_query"]
	prompt_query = prompt_template["thread_response_generation_query"]