feat(ai): 🤖 update LLM models and configuration

- Changed default model from `ollama:llama3.2:3b` to `ollama:gemma3:4b`
- Updated model token limits and added new models:
  - Added `gemma3:4b` with vision support
  - Removed `phi4:14b` and added `phi4-reasoning:14b`
  - Updated token limits for existing models
- Added new AI-related roles:
  - `commit-message.md`
  - `email-answer.md`
  - `emoji-commit-message.md`
  - `git-branch.md`
  - `improve-prompt.md`
  - `improve-writing.md`
  - `linkedin-answer.md`
  - Enhanced `to-emoji.md` and added `to-emojies.md`
- Added `ai` alias for `aichat` in fish config
- Updated NixOS configuration to load new models

home/.config/aichat/roles/email-answer.md

@@ -0,0 +1,33 @@
+---
+model: deepseek:deepseek-chat
+
+---
+Please help me craft a professional yet human-sounding email response based on the following:
+
+**Format:**
+```
+Email:
+<received email>
+
+Draft/Notes:
+<my response draft, suggestions, or key points to include>
+```
+
+**Response Requirements:**
+- Format as a complete email response (include greeting, body, and closing)
+- Maintain the tone and structure of the original email
+- Keep it concise but descriptive (2-3 paragraphs max)
+- Sound professional but natural (avoid robotic/formulaic language)
+- Address all key points from the original email
+- Include any necessary details from my draft/key points
+- End with an appropriate closing and signature
+
+**Important:** 
+- Match the level of formality of the original email
+- If the original email was friendly, mirror that tone
+- If it was more formal, maintain that professionalism
+- Mirror formating of received mail when appropriate
+- Builds rapport when appropriate
+- Include proper spacing and formatting for readability
+- ONLY output the formatted email response (no commentary or notes)
+- Do not include any meta-commentary or notes