OMO中是否可以加入deepseekv4 为西西弗斯

各位佬友，我现在手上有GLM5.1，kimik2.6，gpt5.5 请问哪一个更适合当西西弗斯，或者指挥者？我想看deepseekv4的世界知识好像不错，不知道如何发挥他的长处，有没有佬友尝试过了，可以交流一下吗？

我现在刚上手omo 3天，发现omo整体流程很重，模型不太愿意开并发，有严格的先后顺序，且习惯将任务切分的很细，导致有的时候浪费很多时间。还有请问是否可以通过提示词指定模型，还是只能指定agent角色？为什么有的时候sisyphus-junior会被自动指派为gpt5.4mini 或者 5.0nano 但是我的配置文件里没有写，是不是可以手动指定通过提示词指定？

附上我的配置文件

{
  "$schema": "https://raw.githubusercontent.com/code-yeongyu/oh-my-openagent/dev/assets/oh-my-opencode.schema.json",
  "claude_code": {
    "commands": false,
    "skills": false,
    "plugins": false,
    "agents": false,
    "hooks": false,
    "mcp": false
  },
  "agents": {
    "sisyphus": {
      "model": "kimi-for-coding/k2p6",
      "fallback_models": [
        {
          "model": "openai/gpt-5.5",
          "variant": "medium"
        },
        {
          "model": "zai-coding-plan/glm-5.1"
        }
      ]
    },
    "hephaestus": {
      "model": "openai/gpt-5.5",
      "variant": "medium"
    },
    "oracle": {
      "model": "openai/gpt-5.5",
      "variant": "high"
    },
    "librarian": {
      "model": "zai-coding-plan/glm-4.7"
    },
    "explore": {
      "model": "openai/gpt-5.3-codex-spark"
    },
    "multimodal-looker": {
      "model": "openai/gpt-5.5",
      "variant": "medium",
      "fallback_models": [
        {
          "model": "zai-coding-plan/glm-4.6v"
        },
        {
          "model": "openai/gpt-5-nano"
        }
      ]
    },
    "prometheus": {
      "model": "openai/gpt-5.5",
      "variant": "high"
    },
    "metis": {
      "model": "openai/gpt-5.5",
      "variant": "high",
      "fallback_models": [
        {
          "model": "kimi-for-coding/k2p6"
        }
      ]
    },
    "momus": {
      "model": "openai/gpt-5.5",
      "variant": "xhigh"
    },
    "atlas": {
      "model": "openai/gpt-5.5",
      "variant": "medium"
    },
    "sisyphus-junior": {
      "model": "openai/gpt-5.5",
      "variant": "medium"
    }
  },
  "categories": {
    "visual-engineering": {
      "model": "zai-coding-plan/glm-5.1",
      "fallback_models": [
        {
          "model": "kimi-for-coding/k2p6"
        }
      ]
    },
    "ultrabrain": {
      "model": "openai/gpt-5.5",
      "variant": "xhigh"
    },
    "deep": {
      "model": "openai/gpt-5.5",
      "variant": "medium"
    },
    "quick": {
      "model": "openai/gpt-5.4-mini-fast"
    },
    "unspecified-low": {
      "model": "openai/gpt-5.4-fast",
      "variant": "medium"
    },
    "unspecified-high": {
      "model": "openai/gpt-5.5",
      "variant": "medium"
    },
    "writing": {
      "model": "opencode/gpt-5-nano"
    }
  }
}

7 个帖子 - 5 位参与者

阅读完整话题