Files
AndroidStudioSettings/ChatGPTConversations_170.xml
T

6 lines
618 KiB
XML
Raw Normal View History

<application>
<component name="ee.carlrobert.codegpt.state.conversations.ConversationsState">
<option name="currentConversation" value="{&quot;id&quot;:&quot;6210543e-94ef-4949-b483-95e173a4fbd4&quot;,&quot;title&quot;:null,&quot;messages&quot;:[{&quot;prompt&quot;:&quot;生成toJson、fromJson代码&quot;,&quot;id&quot;:&quot;6255957f-befb-4d92-a12b-6c9820b6a62e&quot;,&quot;response&quot;:&quot;已了解。下面为 [AnimationEmotion](file:///home/debuggerx/StudioProjects/aim_master_workspace/apps/aim_master_face_a3/lib/models/animation.dart) 增加 `toJson` / `fromJson`,并对 [FPlayerStatus](file:///home/debuggerx/StudioProjects/aim_master_workspace/apps/aim_master_face_a3/lib/models/animation.dart#FPlayerStatus)、[FSystemType](file:///home/debuggerx/StudioProjects/aim_master_workspace/apps/aim_master_face_a3/lib/models/animation.dart#FSystemType) 以及 `FaceVideoType` 做安全序列化处理。\n\n实施计划:\n1. 在 [AnimationEmotion](file:///home/debuggerx/StudioProjects/aim_master_workspace/apps/aim_master_face_a3/lib/models/animation.dart#AnimationEmotion) 中新增 [toJson](file:///home/debuggerx/StudioProjects/aim_master_workspace/apps/aim_master_face_a3/lib/models/animation.dart#toJson) 方法。\n2. 新增 [fromJson](file:///home/debuggerx/StudioProjects/aim_master_workspace/apps/aim_master_face_a3/lib/models/animation.dart#fromJson) 工厂构造,支持空值与枚举容错。\n3. 增加私有辅助方法,按枚举名称还原 [FSystemType](file:///home/debuggerx/StudioProjects/aim_master_workspace/apps/aim_master_face_a3/lib/models/animation.dart#FSystemType) 和 `FaceVideoType`,避免反序列化时异常。\n\n下面是完整修改后的文件,其中第 1 步实现了 [toJson](file:///home/debuggerx/StudioProjects/aim_master_workspace/apps/aim_master_face_a3/lib/models/animation.dart#toJson),第 2/3 步实现了 [fromJson](file:///home/debuggerx/StudioProjects/aim_master_workspace/apps/aim_master_face_a3/lib/models/animation.dart#fromJson) 及枚举解析逻辑。 \n```dart:/home/debuggerx/StudioProjects/aim_master_workspace/apps/aim_master_face_a3/lib/models/animation.dart\nimport 'package:aim_master_face_a3/config.dart';\nimport 'package:aim_master_face_a3/models/face_video_type.dart';\n\nenum FPlayerStatus { idle, start, running, finish, stopped }\n\nenum FSystemType { unknow, notify, battery, silent, prompt, operation, talking, listening }\n\nconst defaultPromptEmotionPath = \&quot;${FaceConfig.baseEmotionPath}prompt_words/emoticon.mp4\&quot;;\n\nclass AnimationEmotion {\n String? ePath;\n List&lt;String&gt;? ePaths;\n int? eId;\n int? repeat;\n int? level;\n bool? isStop;\n int current = 0;\n FaceVideoType pathType = FaceVideoType.file;\n FSystemType? systemType;\n\n AnimationEmotion({\n this.ePath,\n this.ePaths,\n this.eId,\n this.repeat,\n this.level,\n this.isStop,\n this.current = 0,\n this.pathType = FaceVideoType.file,\n this.systemType,\n });\n\n factory AnimationEmotion.fromJson(Map&lt;String, dynamic&gt; json) {\n return AnimationEmotion(\n ePath: json['ePath'] as String?,\n ePaths: (json['ePaths'] as List?)?.map((e) =&gt; e.toString()).toList(),\n eId: json['eId'] as int?,\n repeat: json['repeat'] as int?,\n level: json['level'] as int?,\n isStop: json['isStop'] as bool?,\n current: (json['current'] as int?) ?? 0,\n pathType: _faceVideoTypeFromJson(json['pathType']) ?? FaceVideoType.file,\n systemType: _systemTypeFromJson(json['systemType']),\n );\n }\n\n Map&lt;String, dynamic&gt; toJson() {\n return {\n 'ePath': ePath,\n 'ePaths': ePaths,\n 'eId': eId,\n 'repeat': repeat,\n 'level': level,\n 'isStop': isStop,\n 'current': current,\n 'pathType': pathType.name,\n 'systemType': systemType?.name,\n };\n }\n\n static AnimationEmotion startUp = AnimationEmotion(\n eId: -1,\n ePath: 'assets/video/init.mp4',\n repeat: -1,\n level: 1099,\n pathType: FaceVideoType.assets,\n );\n\n // 工作中\n static AnimationEmotion operation = AnimationEmotion(\n eId: -1,\n ePath: \&quot;${FaceConfig.baseEmotionP
<option name="conversations" value="[{&quot;id&quot;:&quot;2ea372bf-f79d-4805-a228-8cd51bf07dc9&quot;,&quot;title&quot;:null,&quot;messages&quot;:[{&quot;prompt&quot;:&quot;我在适用ProxyAI这个Intellij插件,想要实现代码自动补全,gemini系列的哪个模型最适合?为什么?另外配置里有个“FIM”模板选项,我应该选什么?&quot;,&quot;id&quot;:&quot;ab4b92a6-8055-4844-85d6-57ffd6339399&quot;,&quot;response&quot;:&quot;对于在 IntelliJ IDEA 使 ProxyAI **Inline Code Completion** Gemini FIM \n\n### Gemini 1.5 Flash Gemini 2.0 Flash\n\n**使 `gemini-1.5-flash` `gemini-2.0-flash`** API \n\n** Pro **\n1. **Latency** 300-500 `gemini-1.5-pro` Flash \n2. ****Flash 1M 2M ProxyAI \n3. ****Flash API Pro \n\n* `gemini-1.5-pro`****Flash *\n\n---\n\n### FIM \n\n**FIM (Fill-In-the-Middle)** PrefixSuffixMiddle\n\n**Gemini **\n DeepSeek CoderQwen Coder CodeLlama 使 FIM Token `&lt;|fim_prefix|&gt;``&lt;|fim_suffix|&gt;` **Gemini FIM ** ProxyAI Gemini `DeepSeek` `Qwen` FIM Gemini \n\n****\n\n1. ** Prompt / Instruction **\n ProxyAI FIM `Prompt``Instruction` `Gemini/OpenAI` \n\n2. **CustomFIM **\n FIM 使 XML Gemini XML \n ```text\n You are an expert programmer. Please complete the missing code between &lt;prefix&gt; and &lt;suffix&gt;. \n Output ONLY the missing code, without any markdown formatting, explanations, or repeating the prefix/suffix.\n \n &lt;prefix&gt;\n {prefix}\n &lt;/prefix&gt;\n &lt;suffix&gt;\n {suffix}\n &lt;/suffix&gt;\n ```\n *( `{prefix}` `{suffix}` ProxyAI )*\n\n3. ** FIM**\n FIM Gemini ProxyAI ** FIM ** None/Default退 Gemini &quot;,&quot;referencedFilePaths&quot;:null,&quot;conversationsHistoryIds&quot;:null,&quot;imageFilePath&quot;:null,&quot;
</component>
</application>