docs: make English the default docs language and fix link paths

docs/models/deepseek.mdx

@@ -1,11 +1,11 @@
 ---
 title: DeepSeek
-description: DeepSeek 模型配置（文本对话 + 思考模式）
+description: DeepSeek model configuration (Text Chat + Thinking Mode)
 ---
 
-DeepSeek 是当前 Agent 模式默认推荐的厂商之一，主打高性价比的文本对话和任务规划能力。
+DeepSeek is one of the default recommended vendors in Agent mode, focused on cost-effective text chat and task planning.
 
-## 文本对话
+## Text Chat
 
 ```json
 {
@@ -14,26 +14,26 @@ DeepSeek 是当前 Agent 模式默认推荐的厂商之一，主打高性价比
 }
 ```
 
-| 参数 | 说明 |
+| Parameter | Description |
 | --- | --- |
-| `model` | 支持 `deepseek-v4-flash`（默认）、`deepseek-v4-pro` |
-| `deepseek_api_key` | 在 [DeepSeek 平台](https://platform.deepseek.com/api_keys) 创建 |
-| `deepseek_api_base` | 可选，默认为 `https://api.deepseek.com/v1`，可修改为第三方代理地址 |
+| `model` | Supports `deepseek-v4-flash` (Default), `deepseek-v4-pro` |
+| `deepseek_api_key` | Create one on the [DeepSeek Platform](https://platform.deepseek.com/api_keys) |
+| `deepseek_api_base` | Optional, defaults to `https://api.deepseek.com/v1`. Can be changed to a third-party proxy |
 
-### 模型选择
+### Model Selection
 
-| 模型 | 适用场景 |
+| Model | Use Case |
 | --- | --- |
-| `deepseek-v4-flash` | 默认推荐，速度快、成本低 |
-| `deepseek-v4-pro` | 更智能，复杂任务效果更强 |
+| `deepseek-v4-flash` | Default recommended; fast and low cost |
+| `deepseek-v4-pro` | Smarter; better for complex tasks |
 
-## 思考模式
+## Thinking Mode
 
-V4 系列（`deepseek-v4-flash` / `deepseek-v4-pro`）支持显式的「思考模式」：模型在输出最终回答前，先输出一段思维链（`reasoning_content`），从而提升答案质量。
+The V4 series (`deepseek-v4-flash` / `deepseek-v4-pro`) supports an explicit "thinking mode": before producing the final answer, the model emits a chain of thought (`reasoning_content`) to improve answer quality.
 
-### 开关
+### Toggle
 
-通过全局配置 `enable_thinking` 控制，也可在 web控制台 - 配置页面中进行切换：
+Controlled by the global `enable_thinking` config, and can also be toggled from the Web Console's configuration page:
 
 ```json
 {
@@ -41,12 +41,12 @@ V4 系列（`deepseek-v4-flash` / `deepseek-v4-pro`）支持显式的「思考
 }
 ```
 
-- `true`：所有渠道下模型都会先思考再作答。Web 控制台会展示思考过程，IM 渠道（微信 / 企微 / 钉钉 / 飞书）虽不展示但同样获得更好答案。
-- `false`：关闭思考，响应更快，首字延迟更低。
+- `true`: the model thinks before answering across all channels. The Web Console displays the thinking process; IM channels (WeChat / WeCom / DingTalk / Feishu) do not show it but still get better answers.
+- `false`: thinking is disabled, responses are faster, and time-to-first-token is lower.
 
-### 推理强度
+### Reasoning Effort
 
-思考模式下可通过 `reasoning_effort` 控制推理强度：
+Under thinking mode, `reasoning_effort` controls reasoning intensity:
 
 ```json
 {
@@ -55,18 +55,18 @@ V4 系列（`deepseek-v4-flash` / `deepseek-v4-pro`）支持显式的「思考
 }
 ```
 
-| 取值 | 适用场景 |
+| Value | Use Case |
 | --- | --- |
-| `high`（默认） | 日常 Agent 任务，思考与速度的平衡 |
-| `max` | 复杂编码、长链路规划、严格约束的任务，推理更深但耗时与输出 token 更多 |
+| `high` (Default) | Day-to-day Agent tasks; balanced reasoning and speed |
+| `max` | Complex coding, long-horizon planning, strictly constrained tasks; deeper reasoning but more time and output tokens |
 
-`reasoning_effort` 仅在 `enable_thinking` 为 `true` 时生效；模型不支持思考模式时该字段自动忽略。
+`reasoning_effort` only takes effect when `enable_thinking` is `true`; it is ignored automatically when the model does not support thinking mode.
 
-### 行为说明
+### Behavior Notes
 
-- **采样参数**：思考模式下 `temperature`、`top_p`、`presence_penalty`、`frequency_penalty` 会被服务端忽略（不会报错），CowAgent 会自动跳过传入。
-- **多轮工具调用**：当历史中包含工具调用时，DeepSeek 要求所有 assistant 消息必须回传 `reasoning_content`。CowAgent 会自动处理回传逻辑，跨轮次切换思考开关也不会出错。
+- **Sampling parameters**: in thinking mode, `temperature`, `top_p`, `presence_penalty`, and `frequency_penalty` are ignored by the server (without errors). CowAgent automatically skips them.
+- **Multi-turn tool calls**: when the history contains tool calls, DeepSeek requires every assistant message to include `reasoning_content`. CowAgent handles this automatically, so toggling thinking mode across turns will not cause errors.
 
 <Tip>
-  默认使用 `deepseek-v4-flash`；复杂任务可使用 `deepseek-v4-pro`；需要深度推理可开启 `enable_thinking`。
+  `deepseek-v4-flash` is used by default; switch to `deepseek-v4-pro` for complex tasks; enable `enable_thinking` when deep reasoning is needed.
 </Tip>