**Title:** Support multiple model profiles in settings.json for quick switching via `/model`

[LoveSilverWolf-999]

Problem

Currently, settings.json only accepts a single set of model-related configuration:

{
  "model": "deepseek-v4-pro",
  "thinkingEnabled": true,
  "reasoningEffort": "max",
  "temperature": 0
}

When I need to switch between different models (e.g., deepseek-v4-pro with max reasoning for complex tasks, deepseek-v4-flash without thinking for quick edits), I have to manually adjust each field via /model every time — model name, thinking mode, reasoning effort, and temperature. This is repetitive and error-prone.

Proposed Solution

Support a profiles field in settings.json to predefine multiple named configurations:

{
  "profiles": {
    "pro-max": {
      "model": "deepseek-v4-pro",
      "thinkingEnabled": true,
      "reasoningEffort": "max",
      "temperature": 0
    },
    "flash-quick": {
      "model": "deepseek-v4-flash",
      "thinkingEnabled": false,
      "temperature": 0.7
    },
    "coding-plan": {
      "model": "ark-code-latest",
      "baseUrl": "https://ark.cn-beijing.volces.com/api/coding/v3",
      "thinkingEnabled": true
    }
  },
  "defaultProfile": "pro-max"
}

The /model command would then list these profiles for one-click switching.

Use Cases

1. Heavy reasoning tasks (architecture design, debugging) → switch to pro-max
2. Quick edits / boilerplate → switch to flash-quick for speed and cost savings
3. Third-party models (e.g., Coding Plan) → switch to coding-plan without re-entering BASE_URL and API_KEY each time

Expected Behavior

• profiles entries accept: model, baseUrl, apiKey, thinkingEnabled, reasoningEffort, temperature
• defaultProfile (optional) specifies which profile to use at session start
• /model lists all profiles and allows selecting one to apply immediately
• If profiles is not configured, /model behaves exactly as it does today

---

Thanks for the great tool!