refactor: Convert config comments to English and improve model display

- Remove all Chinese comments from mindmap_ai_config.toml
- Always display both prompt and mindmap model configuration at start
- Show model name when generating each language version
- Improve visibility of which models are being used during generation

Author: lufftw

tools/mindmap_ai_config.toml

@@ -20,10 +20,10 @@
 #   - Optimizing existing prompts (when selecting [o] Optimize option)
 #   - First-time prompt generation (when selecting [o] Generate prompt with AI option)
 #
-# Recommended: Models good at understanding and optimizing text (e.g., GPT-4 series)
-prompt_model = "gpt-4o"
+# Recommended: Models good at understanding and optimizing text (e.g., gpt-5.2, gpt-5.1)
+prompt_model = "gpt-5.2"
 prompt_temperature = 0.7
-prompt_max_completion_tokens = 8000
+prompt_max_completion_tokens = 10000
 
 # -----------------------------------------------------------------------------
 # Mind Map Generation Model
@@ -32,7 +32,7 @@ prompt_max_completion_tokens = 8000
 #   - Generating final mind map content based on prompts
 #   - This is the main generation task and consumes more tokens
 #
-# Recommended: Models good at creative generation and long text output (e.g., GPT-5.1-codex, GPT-5.2)
+# Recommended: Models good at creative generation and long text output (e.g., gpt-5.1-codex, gpt-5.2, gpt-5.1)
 mindmap_model = "gpt-5.1-codex"
 mindmap_temperature = 0.7
 # GPT-5.1-codex uses max_completion_tokens (older models use max_tokens)