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/config.yaml

@@ -1,4 +1,4 @@
-# model: ollama:llama3.2:3b
+# model: ollama:gemma3:4b
 model: deepseek:deepseek-chat
 keybindings: vi
 function_calling: true
@@ -12,20 +12,38 @@ clients:
     max_input_tokens: 128000
     supports_function_calling: true
 
-  - name: phi4:14b
-    max_input_tokens: 16000
+  - name: phi4-reasoning:14b
+    max_input_tokens: 32000
     supports_function_calling: true
 
   - name: dolphin3:8b
-    max_input_tokens: 130000
+    max_input_tokens: 128000
     supports_function_calling: true
 
   - name: smallthinker:3b
-    max_input_tokens: 16384
+    max_input_tokens: 32000
     supports_function_calling: true
 
-  - name: qwq:32b
-    max_input_tokens: 33000
+  - name: gemma3:4b
+    max_input_tokens: 128000
+    supports_vision: true
+    supports_function_calling: true
+
+  - name: gemma3:12b
+    max_input_tokens: 128000
+    supports_vision: true
+    supports_function_calling: true
+
+  - name: gemma3:27b
+    max_input_tokens: 128000
+    supports_vision: true
+    supports_function_calling: true
+
+  - name: deepcoder:14b
+    max_input_tokens: 128000
+
+  - name: qwen3:14b
+    max_input_tokens: 40000
     supports_function_calling: true
 
   - name: nomic-embed-text:latest