Claude-Code是最近非常火的命令行代码生成工具，最近在疯狂的体验的时候，然后发现自己的钱包被疯狂的掏空。你可能不敢相信，我两年时间居然消耗了170美刀在官方API调用上，这让我觉得100美刀的会员也是非常的便宜了。
最近月之暗面推出了他们的一个开源模型K2，号称在编程上很强，并且API费用亲民：
| 模型 | 计费单位 | 输入价格 （缓存命中） | 输入价格 （缓存未命中） | 输出价格 | 模型上下文长度 |
|---|---|---|---|---|---|
| kimi-k2-0711-preview | 1M tokens | 1.00元 | 4元 | 16元 | 131,072 tokens |
| claude-opus-4-0 | 1M tokens | 15美元 | 75美元 | 200,000 tokens | |
| claude-sonnet-4-0 | 1M tokens | 3美元 | 15美元 | 200,000 tokens |
更为离谱的是，他可以无缝衔接cluade-code，只需要运行一行代码
bash -c "$(curl -fsSL https://raw.githubusercontent.com/LLM-Red-Team/kimi-cc/refs/heads/main/install.sh)"
这个代码实际上做了下面几个事情
第一步，分析当前node版本，如果≤18，则用nvm安装新版本的nodejs
第二步，用nodejs安装npm install -g @anthropic-ai/claude-code
第三步，修改~/.claude.json，写入如下内容，跳过 Onboarding 引导流程
{ hasCompletedOnboarding: true }
第四步，在/.bashrc或/.zshrc中配置claude-code环境变量。这需要你去 https://platform.moonshot.cn/console注册账号，并创建一个API KEY
# Claude Code environment variables
export ANTHROPIC_BASE_URL=https://api.moonshot.cn/anthropic/
export ANTHROPIC_API_KEY=sk-你申请的TOKEN
你没看错，Moonshoot直接后台兼容了anthropic的接口，你根本不需要修改任何其他参数。
第五步，运行claude体验。(后续我就把kimi版本的claude称之为klaude）
我让他做了一个事情，就是开发一个网页，方便课题组调用BLAST。
然后klaude就哼哧哼哧的干了起来，全程我就是负责统一，只有中间在python环境上出错了，我干预了下，主要是告诉klaude我们有micromamba
当前环境有micromamba, 解决
Using cached https://pypi.tuna.tsinghua.edu.cn/packages/2c/d4/590ae7df5044465cc9fa2db152ae12468694d62d952b1528ecff328ef7fc/numpy-1.24.3.tar.gz (10.9 MB)
Installing build dependencies ... done
Getting requirements to build wheel ... error
error: subprocess-exited-with-error
× Getting requirements to build wheel did not run successfully.
│ exit code: 1
╰─> [32 lines of output]
Traceback (most recent call last):
File "/home/xuzhougeng/micromamba/lib/python3.13/site-packages/pip/_vendor/pyproject_hooks/_in_process/_in_process.py", line 389, in <module>
main()
~~~~^^
File "/home/xuzhougeng/micromamba/lib/python3.13/site-packages/pip/_vendor/pyproject_hooks/_in_process/_in_process.py", line 373, in main
json_out["return_val"] = hook(**hook_input["kwargs"])
~~~~^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/xuzhougeng/micromamba/lib/python3.13/site-packages/pip/_vendor/pyproject_hooks/_in_process/_in_process.py", line 137, in get_requires_for_build_wheel
backend = _build_backend()
File "/home/xuzhougeng/micromamba/lib/python3.13/site-packages/pip/_vendor/pyproject_hooks/_in_process/_in_process.py", line 70, in _build_backend
obj = import_module(mod_path)
File "/home/xuzhougeng/micromamba/lib/python3.13/importlib/__init__.py", line 88, in import_module
return _bootstrap._gcd_import(name[level:], package, level)
~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "<frozen importlib._bootstrap>", line 1387, in _gcd_import
File "<frozen importlib._bootstrap>", line 1360, in _find_and_load
File "<frozen importlib._bootstrap>", line 1310, in _find_and_load_unlocked
File "<frozen importlib._bootstrap>", line 488, in _call_with_frames_removed
File "<frozen importlib._bootstrap>", line 1387, in _gcd_import
File "<frozen importlib._bootstrap>", line 1360, in _find_and_load
File "<frozen importlib._bootstrap>", line 1331, in _find_and_load_unlocked
File "<frozen importlib._bootstrap>", line 935, in _load_unlocked
File "<frozen importlib._bootstrap_external>", line 1026, in exec_module
File "<frozen importlib._bootstrap>", line 488, in _call_with_frames_removed
File "/data/tmp/pip-build-env-z4k9gymq/overlay/lib/python3.13/site-packages/setuptools/__init__.py", line 16, in <module>
import setuptools.version
File "/data/tmp/pip-build-env-z4k9gymq/overlay/lib/python3.13/site-packages/setuptools/version.py", line 1, in <module>
import pkg_resources
File "/data/tmp/pip-build-env-z4k9gymq/overlay/lib/python3.13/site-packages/pkg_resources/__init__.py", line 2172, in <module>
register_finder(pkgutil.ImpImporter, find_on_path)
^^^^^^^^^^^^^^^^^^^
AttributeError: module 'pkgutil' has no attribute 'ImpImporter'. Did you mean: 'zipimporter'?
[end of output]
note: This error originates from a subprocess, and is likely not a problem with pip.
error: subprocess-exited-with-error
× Getting requirements to build wheel did not run successfully.
│ exit code: 1
╰─> See above for output.
note: This error originates from a subprocess, and is likely not a problem with pip.
他也很快找到了问题所在
● 这个错误是由于Python 3.13与旧版本的numpy不兼容导致的。让我用micromamba创建一个新的环境来解决这个问题。
● Bash(micromamba create -n blast_tool python=3.10 -y)
⎿ Transaction
Prefix: /home/xuzhougeng/micromamba/envs/blast_tool
… +91 lines (ctrl+r to expand)
● 现在激活新环境并安装依赖：
● Bash(micromamba activate blast_tool && pip install -r requirements.txt -i https://pypi.tuna.tsinghua.edu.cn/simple)
⎿ Error: critical libmamba Shell not initialized
'micromamba' is running as a subprocess and can't modify the parent shell.
Thus you must initialize your shell before using activate and deactivate.
To initialize the current bash shell, run:
$ eval "$(micromamba shell hook --shell bash)"
and then activate or deactivate with:
$ micromamba activate
… +8 lines (ctrl+r to see all)
● 让我使用micromamba run来安装依赖：
之后项目就能运行了，开发 网页如下，有用，但是不支持上传新的基因组
所以继续开启了 klaude 指挥它干活
当前的BLAST工具应该能够自己上传基因组构建索引，并且能够存储下来方便后续使用
最后有两点感受
- 编程效果确实还可以，会调用工具解决问题
- 推理速度不太够，要等好久才能搞定一步
