codex启动多个agent同步跑的话，原来都是gpt5.4mini吗？
- 内容介绍
- 文章标签
- 相关推荐
image537×303 19.5 KB
rt，我以为也会以5.4 来启动的，原来是mini
--【壹】--：
感谢分享。。。。。。。。。。。。。。。。。。
--【贰】--：
多谢佬 thanks, 一下就找到你的回答, 简洁明了, 已经用上啦
--【叁】--： Linus Torvalds:
agents.toml
image420×769 14.7 KB
我codex下面这有这些，没找到有agents的位置
--【肆】--：
默认是3个agents（default、explorer、worker），需要自己来配置这三个agent对应的toml~
config.toml：
这三个的description是官方源码里写的，我直接复制过来了~
[agents.default]
description = "Default agent."
config_file = "./agents/default.toml"
[agents.explorer]
description = """
Use `explorer` for specific codebase questions.
Explorers are fast and authoritative.
They must be used to ask specific, well-scoped questions on the codebase.
Rules:
- In order to avoid redundant work, you should avoid exploring the same problem that explorers have already covered. Typically, you should trust the explorer results without additional verification. You are still allowed to inspect the code yourself to gain the needed context!
- You are encouraged to spawn up multiple explorers in parallel when you have multiple distinct questions to ask about the codebase that can be answered independently. This allows you to get more information faster without waiting for one question to finish before asking the next. While waiting for the explorer results, you can continue working on other local tasks that do not depend on those results. This parallelism is a key advantage of delegation, so use it whenever you have multiple questions to ask.
- Reuse existing explorers for related questions.
"""
config_file = "./agents/explorer.toml"
[agents.worker]
description = """
Use for execution and production work.
Typical tasks:
- Implement part of a feature
- Fix tests or bugs
- Split large refactors into independent chunks
Rules:
- Explicitly assign **ownership** of the task (files / responsibility). When the subtask involves code changes, you should clearly specify which files or modules the worker is responsible for. This helps avoid merge conflicts and ensures accountability. For example, you can say "Worker 1 is responsible for updating the authentication module, while Worker 2 will handle the database layer." By defining clear ownership, you can delegate more effectively and reduce coordination overhead.
- Always tell workers they are **not alone in the codebase**, and they should not revert the edits made by others, and they should adjust their implementation to accommodate the changes made by others. This is important because there may be multiple workers making changes in parallel, and they need to be aware of each other's work to avoid conflicts and ensure a cohesive final product.
"""
config_file = "./agents/worker.toml"
然后这三个可以自定义
#:schema https://developers.openai.com/codex/config-schema.json
model = "gpt-5.4"
review_model = "gpt-5.4"
model_reasoning_effort = "xhigh"
plan_mode_reasoning_effort = "xhigh"
image1099×258 24 KB
--【伍】--：
我只能说无敌了，佬们还是太权威了，原来可以设置啊我超
--【陆】--：
Mark标记一下，明天早上就在电脑上试试
--【柒】--：
spawn subagent为explorer的时候，主agent似乎倾向于使用5.4mini，但是可以用prompt或者AGENTS.md修改吧
--【捌】--： Linus Torvalds:
model = "gpt-5.4" review_model = "gpt-5.4" model_reasoning_effort = "xhigh" plan_mode_reasoning_effort = "xhigh"
搞定！佬真的牛逼，感觉我问gpt也不一定有这么清晰明确，来l站真是来对了
--【玖】--：
需要自己新建一个agents文件夹~
Custom agents - Subagents – Codex | OpenAI Developers
Codex can run subagent workflows by spawning specialized agents in parallel and then collecting their results in one response. This can be particularly helpful for complex tasks that are highly parallel, such as codebase exploration or implementing a...
image537×303 19.5 KB
rt，我以为也会以5.4 来启动的，原来是mini
--【壹】--：
感谢分享。。。。。。。。。。。。。。。。。。
--【贰】--：
多谢佬 thanks, 一下就找到你的回答, 简洁明了, 已经用上啦
--【叁】--： Linus Torvalds:
agents.toml
image420×769 14.7 KB
我codex下面这有这些，没找到有agents的位置
--【肆】--：
默认是3个agents（default、explorer、worker），需要自己来配置这三个agent对应的toml~
config.toml：
这三个的description是官方源码里写的，我直接复制过来了~
[agents.default]
description = "Default agent."
config_file = "./agents/default.toml"
[agents.explorer]
description = """
Use `explorer` for specific codebase questions.
Explorers are fast and authoritative.
They must be used to ask specific, well-scoped questions on the codebase.
Rules:
- In order to avoid redundant work, you should avoid exploring the same problem that explorers have already covered. Typically, you should trust the explorer results without additional verification. You are still allowed to inspect the code yourself to gain the needed context!
- You are encouraged to spawn up multiple explorers in parallel when you have multiple distinct questions to ask about the codebase that can be answered independently. This allows you to get more information faster without waiting for one question to finish before asking the next. While waiting for the explorer results, you can continue working on other local tasks that do not depend on those results. This parallelism is a key advantage of delegation, so use it whenever you have multiple questions to ask.
- Reuse existing explorers for related questions.
"""
config_file = "./agents/explorer.toml"
[agents.worker]
description = """
Use for execution and production work.
Typical tasks:
- Implement part of a feature
- Fix tests or bugs
- Split large refactors into independent chunks
Rules:
- Explicitly assign **ownership** of the task (files / responsibility). When the subtask involves code changes, you should clearly specify which files or modules the worker is responsible for. This helps avoid merge conflicts and ensures accountability. For example, you can say "Worker 1 is responsible for updating the authentication module, while Worker 2 will handle the database layer." By defining clear ownership, you can delegate more effectively and reduce coordination overhead.
- Always tell workers they are **not alone in the codebase**, and they should not revert the edits made by others, and they should adjust their implementation to accommodate the changes made by others. This is important because there may be multiple workers making changes in parallel, and they need to be aware of each other's work to avoid conflicts and ensure a cohesive final product.
"""
config_file = "./agents/worker.toml"
然后这三个可以自定义
#:schema https://developers.openai.com/codex/config-schema.json
model = "gpt-5.4"
review_model = "gpt-5.4"
model_reasoning_effort = "xhigh"
plan_mode_reasoning_effort = "xhigh"
image1099×258 24 KB
--【伍】--：
我只能说无敌了，佬们还是太权威了，原来可以设置啊我超
--【陆】--：
Mark标记一下，明天早上就在电脑上试试
--【柒】--：
spawn subagent为explorer的时候，主agent似乎倾向于使用5.4mini，但是可以用prompt或者AGENTS.md修改吧
--【捌】--： Linus Torvalds:
model = "gpt-5.4" review_model = "gpt-5.4" model_reasoning_effort = "xhigh" plan_mode_reasoning_effort = "xhigh"
搞定！佬真的牛逼，感觉我问gpt也不一定有这么清晰明确，来l站真是来对了
--【玖】--：
需要自己新建一个agents文件夹~
Custom agents - Subagents – Codex | OpenAI Developers
Codex can run subagent workflows by spawning specialized agents in parallel and then collecting their results in one response. This can be particularly helpful for complex tasks that are highly parallel, such as codebase exploration or implementing a...