codex app 能不能添加其他模型名称?

始皇帝 2026-07-09 13:01 1



目前我是用的别名把其他模型通过 cpa 使用,但是这样就区分不了用的是哪个模型。

可以在画框区域添加其他模型名称吗?

最新回复 (4)
  • Linus Torvalds 07-09 13:03
    1

    可以使用cc-switch,会生成model_catalog_json,就会显示模型名称,比如ds、glm之类的

  • 地狱之歌 07-09 13:09
    2

    用第三方插件可以cc-switch 或者PLUSPLUS

  • 始皇帝 楼主 07-09 13:51
    3

    cc-switch 有点重,会把原 config 搞崩,让 AI 又给恢复了

  • 道爷我成了 07-09 13:58
    4

    可以的,就是有点麻烦,修改配置文件config.toml,加上:model_catalog_json=文件路径

    文件内容参考:


    {

    “models”: [

    {

    “slug”: “mimo-v2.5-pro”,

    “display_name”: “mimo-v2.5-pro”,

    “description”: “MiMo-v2.5-Pro: Trillion-parameter Flagship Agent Foundation”,

    “default_reasoning_level”: “high”,

    “supported_reasoning_levels”: [

    {

    “effort”: “none”,

    “description”: “Disable Thinking”

    },

    {

    “effort”: “high”,

    “description”: “Enabled Thinking”

    }

    ],

    “shell_type”: “shell_command”,

    “visibility”: “list”,

    “supported_in_api”: true,

    “priority”: 0,

    “base_instructions”: “You are MiMo, an AI assistant developed by Xiaomi. Today’s date: {date} {week}. Your knowledge cutoff date is December 2024.”,

    “supports_reasoning_summaries”: true,

    “default_reasoning_summary”: “none”,

    “support_verbosity”: false,

    “truncation_policy”: {

    “mode”: “bytes”,

    “limit”: 10000

    },

    “supports_parallel_tool_calls”: false,

    “supports_image_detail_original”: false,

    “context_window”: 1048576,

    “max_context_window”: 1048576,

    “effective_context_window_percent”: 95,

    “experimental_supported_tools”: ,

    “input_modalities”: [“text”],

    “supports_search_tool”: false

    },

    {

    “slug”: “mimo-v2.5”,

    “display_name”: “mimo-v2.5”,

    “description”: “MiMo-V2.5: Native Omni-modal Perception Model”,

    “default_reasoning_level”: “high”,

    “supported_reasoning_levels”: [

    {

    “effort”: “none”,

    “description”: “Disable Thinking”

    },

    {

    “effort”: “high”,

    “description”: “Enabled Thinking”

    }

    ],

    “shell_type”: “shell_command”,

    “visibility”: “list”,

    “supported_in_api”: true,

    “priority”: 1,

    “base_instructions”: “You are MiMo, an AI assistant developed by Xiaomi. Today’s date: {date} {week}. Your knowledge cutoff date is December 2024.”,

    “supports_reasoning_summaries”: true,

    “default_reasoning_summary”: “none”,

    “support_verbosity”: false,

    “truncation_policy”: {

    “mode”: “bytes”,

    “limit”: 10000

    },

    “supports_parallel_tool_calls”: false,

    “supports_image_detail_original”: true,

    “context_window”: 1048576,

    “max_context_window”: 1048576,

    “effective_context_window_percent”: 95,

    “experimental_supported_tools”: ,

    “input_modalities”: [“text”, “image”],

    “supports_search_tool”: false

    },

    {

    “slug”: “MiniMax-M3”,

    “display_name”: “MiniMax-M3”,

    “description”: “MiniMax”,

    “default_reasoning_level”: “high”,

    “supported_reasoning_levels”: [

    { “effort”: “none”, “description”: “Think-Off” },

    { “effort”: “high”, “description”: “Deep” }

    ],

    “shell_type”: “shell_command”,

    “visibility”: “list”,

    “supported_in_api”: true,

    “priority”: 0,

    “base_instructions”: “You are Codex, a coding agent based on MiniMax-M3. You and the user share the same workspace and collaborate to achieve the user’s goals.”,

    “supports_reasoning_summaries”: true,

    “default_reasoning_summary”: “none”,

    “support_verbosity”: false,

    “truncation_policy”: { “mode”: “bytes”, “limit”: 10000 },

    “supports_parallel_tool_calls”: true,

    “experimental_supported_tools”: ,

    “input_modalities”: [“text”, “image”]

    }

    ]

    }


    我这样改是可以在codex中使用mimo和minimax,就是模型拉跨不好使

* 帖子来源Linux.do
返回