💄 style: support for parsing imageOutput (#7140)

Co-authored-by: Arvin Xu <arvinx@foxmail.com>

docs/self-hosting/advanced/model-list.mdx

@@ -17,7 +17,7 @@ LobeChat supports customizing the model list during deployment. This configurati
 You can use `+` to add a model, `-` to hide a model, and use `model name->deploymentName=display name<extension configuration>` to customize the display name of a model, separated by English commas. The basic syntax is as follows:
 
 ```text
-id->deploymentName=displayName<maxToken:vision:reasoning:search:fc:file>,model2,model3
+id->deploymentName=displayName<maxToken:vision:reasoning:search:fc:file:imageOutput>,model2,model3
 ```
 
 For example: `+qwen-7b-chat,+glm-6b,-gpt-3.5-turbo,gpt-4-0125-preview=gpt-4-turbo`
@@ -29,7 +29,7 @@ In the above example, it adds `qwen-7b-chat` and `glm-6b` to the model list, rem
 Considering the diversity of model capabilities, we started to add extension configuration in version `0.147.8`, with the following rules:
 
 ```shell
-id->deploymentName=displayName<maxToken:vision:reasoning:search:fc:file>
+id->deploymentName=displayName<maxToken:vision:reasoning:search:fc:file:imageOutput>
 ```
 
 The first value in angle brackets is designated as the `maxToken` for this model. The second value and beyond are the model's extension capabilities, separated by colons `:`, and the order is not important.
@@ -41,7 +41,8 @@ Examples are as follows:
 - `gemini-1.5-flash-latest=Gemini 1.5 Flash<16000:vision>`: Google Vision model, maximum context of 16k, supports image recognition;
 - `o3-mini=OpenAI o3-mini<200000:reasoning:fc>`: OpenAI o3-mini model, maximum context of 200k, supports reasoning and Function Call;
 - `qwen-max-latest=Qwen Max<32768:search:fc>`: Qwen 2.5 Max model, maximum context of 32k, supports web search and Function Call;
-- `gpt-4-all=ChatGPT Plus<128000:fc:vision:file>`, hacked version of ChatGPT Plus web, context of 128k, supports image recognition, Function Call, file upload.
+- `gpt-4-all=ChatGPT Plus<128000:fc:vision:file>`, hacked version of ChatGPT Plus web, context of 128k, supports image recognition, Function Call, file upload;
+- `gemini-2.0-flash-exp-image-generation=Gemini 2.0 Flash (Image Generation) Experimental<32768:imageOutput:vision>`, Gemini 2.0 Flash Experimental model for image generation, maximum context of 32k, supports image generation and recognition.
 
 Currently supported extension capabilities are:
 
@@ -49,6 +50,7 @@ Currently supported extension capabilities are:
 | ----------- | -------------------------------------------------------- |
 | `fc`        | Function Calling                                         |
 | `vision`    | Image Recognition                                        |
+| `imageOutput`    | Image Generation                                        |
 | `reasoning` | Support Reasoning                                        |
 | `search`    | Support Web Search                                        |
 | `file`      | File Upload (a bit hacky, not recommended for daily use) |

docs/self-hosting/advanced/model-list.zh-CN.mdx

@@ -16,7 +16,7 @@ LobeChat 支持在部署时自定义模型列表，详情请参考 [模型提供
 你可以使用 `+` 增加一个模型，使用 `-` 来隐藏一个模型，使用 `模型名->部署名=展示名<扩展配置>` 来自定义模型的展示名，用英文逗号隔开。通过 `<>` 来添加扩展配置。基本语法如下：
 
 ```text
-id->deploymentName=displayName<maxToken:vision:reasoning:search:fc:file>,model2,model3
+id->deploymentName=displayName<maxToken:vision:reasoning:search:fc:file:imageOutput>,model2,model3
 ```
 
 例如： `+qwen-7b-chat,+glm-6b,-gpt-3.5-turbo,gpt-4-0125-preview=gpt-4-turbo`
@@ -28,7 +28,7 @@ id->deploymentName=displayName<maxToken:vision:reasoning:search:fc:file>,model2,
 考虑到模型的能力多样性，我们在 `0.147.8` 版本开始增加扩展性配置，它的规则如下：
 
 ```shell
-id->deploymentName=displayName<maxToken:vision:reasoning:search:fc:file>
+id->deploymentName=displayName<maxToken:vision:reasoning:search:fc:file:imageOutput>
 ```
 
 尖括号第一个值约定为这个模型的 `maxToken` 。第二个及以后作为模型的扩展能力，能力与能力之间用冒号 `:` 作为分隔符，顺序不重要。
@@ -40,7 +40,8 @@ id->deploymentName=displayName<maxToken:vision:reasoning:search:fc:file>
 - `gemini-1.5-flash-latest=Gemini 1.5 Flash<16000:vision>`：Google 视觉模型，最大上下文 16k，支持图像识别；
 - `o3-mini=OpenAI o3-mini<200000:reasoning:fc>`：OpenAI o3-mini 模型，最大上下文 200k，支持推理及 Function Call；
 - `qwen-max-latest=Qwen Max<32768:search:fc>`：通义千问 2.5 Max 模型，最大上下文 32k，支持联网搜索及 Function Call；
-- `gpt-4-all=ChatGPT Plus<128000:fc:vision:file>`，hack 的 ChatGPT Plus 网页版，上下 128k ，支持图像识别、Function Call、文件上传
+- `gpt-4-all=ChatGPT Plus<128000:fc:vision:file>`，hack 的 ChatGPT Plus 网页版，上下 128k ，支持图像识别、Function Call、文件上传；
+- `gemini-2.0-flash-exp-image-generation=Gemini 2.0 Flash (Image Generation) Experimental<32768:imageOutput:vision>`，Gemini 2.0 Flash 实验模型，最大上下文 32k，支持图像生成和识别
 
 目前支持的扩展能力有：
 
@@ -48,6 +49,7 @@ id->deploymentName=displayName<maxToken:vision:reasoning:search:fc:file>
 | ----------- | ---------------------- |
 | `fc`        | 函数调用（function calling） |
 | `vision`    | 视觉识别                   |
+| `imageOutput`      | 图像生成  |
 | `reasoning` | 支持推理                   |
 | `search`    | 支持联网搜索                   |
 | `file`      | 文件上传（比较 hack，不建议日常使用）  |

src/utils/parseModels.test.ts

@@ -86,6 +86,20 @@ describe('parseModelString', () => {
       });
     });
 
+    it('token and image output', () => {
+      const result = parseModelString('gemini-2.0-flash-exp-image-generation=Gemini 2.0 Flash (Image Generation) Experimental<32768:imageOutput>');
+
+      expect(result.add[0]).toEqual({
+        displayName: 'Gemini 2.0 Flash (Image Generation) Experimental',
+        abilities: {
+          imageOutput: true,
+        },
+        id: 'gemini-2.0-flash-exp-image-generation',
+        contextWindowTokens: 32_768,
+        type: 'chat',
+      });
+    });
+
     it('multi models', () => {
       const result = parseModelString(
         'gemini-1.5-flash-latest=Gemini 1.5 Flash<16000:vision>,gpt-4-all=ChatGPT Plus<128000:fc:vision:file>',

src/utils/parseModels.ts

@@ -84,6 +84,10 @@ export const parseModelString = (modelString: string = '', withDeploymentName =
             model.abilities!.search = true;
             break;
           }
+          case 'imageOutput': {
+            model.abilities!.imageOutput = true;
+            break;
+          }
           default: {
             console.warn(`Unknown capability: ${capability}`);
           }