docs(site): document native reasoning parameters (#2705)

* docs(site): document native reasoning parameters

* docs(site): clarify reasoning provider docs

Author: EAGzzyCSL

apps/site/docs/en/model-strategy.mdx

@@ -145,10 +145,21 @@ You can control model-native thinking with the following reasoning settings.
   - `false`: Force-disable model-native thinking (Midscene's default behavior).
   - `true`: Force-enable model-native thinking.
   - `default`: Follow the model's default behavior. Midscene will not send any setting that enables or disables thinking. In this case, explicitly configured `MIDSCENE_MODEL_REASONING_BUDGET` and `MIDSCENE_MODEL_REASONING_EFFORT` will also be ignored.
-- `MIDSCENE_MODEL_REASONING_BUDGET`: Controls the model's thinking budget (supported by some models). See [Common Model Configuration](./model-common-config) for examples.
-- `MIDSCENE_MODEL_REASONING_EFFORT`: Controls the model's thinking effort (supported by some models). See [Common Model Configuration](./model-common-config) for examples.
-
-Note: Different model providers use different parameters to control model-native thinking. If an explicit reasoning setting is not supported by the current model, Midscene ignores that setting instead of guessing provider-specific private parameters.
+  - The following models currently support this setting:
+    - Qwen: corresponds to `enable_thinking` in the Qwen docs.
+    - Doubao: corresponds to `thinking.type` in the Doubao docs.
+    - Zhipu GLM: corresponds to `thinking.type` in the Zhipu docs.
+    - GPT-5: corresponds to `reasoning_effort` in the OpenAI docs. Midscene uses `medium` when enabled and `none` when disabled.
+    - Kimi: corresponds to `thinking.type` in the Kimi docs.
+    - Xiaomi Mimo: corresponds to `thinking.type` in the Xiaomi Mimo docs.
+- `MIDSCENE_MODEL_REASONING_BUDGET`: Controls the model's thinking budget. The following models currently support this setting:
+  - Qwen: corresponds to `thinking_budget` in the Qwen docs.
+- `MIDSCENE_MODEL_REASONING_EFFORT`: Controls the model's thinking effort. The following models currently support this setting:
+  - Doubao: corresponds to `reasoning_effort` in the Doubao docs.
+  - Gemini: corresponds to `thinking_config.thinking_level` in the Gemini docs.
+  - GPT-5: corresponds to `reasoning_effort` in the OpenAI docs.
+
+Note: Different model providers use different parameters to control model-native thinking. For specific values and supported model versions, see the official docs from each model provider. If an explicit reasoning setting is not supported by the current model, Midscene ignores that setting instead of guessing provider-specific private parameters.
 
 ### "MIDSCENE_MODEL_FAMILY is not set to a multimodal model" error
 

apps/site/docs/zh/model-strategy.mdx

@@ -146,11 +146,21 @@ Midscene 会默认关闭模型原生思考，以获得更好的执行速度和
   - `false`：强制关闭模型原生思考（Midscene 默认行为）。
   - `true`：强制开启模型原生思考。
   - `default`：遵循模型的默认行为，Midscene 将不会向模型发送任何开启或关闭思考的配置。此时，显式配置的 `MIDSCENE_MODEL_REASONING_BUDGET` 和 `MIDSCENE_MODEL_REASONING_EFFORT` 也会被忽略。
-- `MIDSCENE_MODEL_REASONING_BUDGET`：控制模型的思考限额（部分模型支持），具体示例请参考[常用模型配置](./model-common-config)。
-- `MIDSCENE_MODEL_REASONING_EFFORT`：控制模型的思考力度（部分模型支持），具体示例请参考[常用模型配置](./model-common-config)。
-
-
-注意：不同模型厂商控制模型原生思考方式的参数各不相同。如果某个显式的 reasoning 配置不被当前模型支持，Midscene 会忽略该配置，而不会猜测服务商的私有参数。
+  - 目前有以下模型支持该参数：
+    - Qwen：对应 Qwen 文档中的 `enable_thinking`。
+    - 豆包：对应豆包文档中的 `thinking.type`。
+    - 智谱 GLM：对应智谱文档中的 `thinking.type`。
+    - GPT-5：对应 OpenAI 文档中的 `reasoning_effort`，开启时默认使用 `medium`，关闭时使用 `none`。
+    - Kimi：对应 Kimi 文档中的 `thinking.type`。
+    - 小米 Mimo：对应小米 Mimo 文档中的 `thinking.type`。
+- `MIDSCENE_MODEL_REASONING_BUDGET`：控制模型的思考限额，目前有以下模型支持该参数：
+  - Qwen：对应 Qwen 文档中的 `thinking_budget`。
+- `MIDSCENE_MODEL_REASONING_EFFORT`：控制模型的思考力度，目前有以下模型支持该参数：
+  - 豆包：对应豆包文档中的 `reasoning_effort`。
+  - Gemini：对应 Gemini 文档中的 `thinking_config.thinking_level`。
+  - GPT-5：对应 OpenAI 文档中的 `reasoning_effort`。
+
+注意：不同模型厂商控制模型原生思考方式的参数各不相同，具体取值和适用模型版本请参考各模型厂商的官方文档。如果某个显式的 reasoning 配置不被当前模型支持，Midscene 会忽略该配置，而不会猜测服务商的私有参数。
 
 ### "MIDSCENE_MODEL_FAMILY is not set to a multimodal model" 错误