Add 5 1 codex max prompting guide #2272
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Lupie
reviewed
Dec 4, 2025
Contributor
Lupie
left a comment
Lupie
left a comment
There was a problem hiding this comment.
can we approve these changes real quick
| "\n", | ||
| "Key improvements\n", | ||
| "\n", | ||
| "* Faster and more token efficient: Matches GPT-5.1-Codex performance on SWE-Bench Verified with \\~30% fewer thinking tokens. We recommend “medium” reasoning effort as a good all-around daily driver model. \n", |
Contributor
There was a problem hiding this comment.
don't love "daily driver model" for anyone whose first lang isn't english but it's not a big dealio
Contributor
There was a problem hiding this comment.
are you cool with this instead @nm ?
Suggested change
| "* Faster and more token efficient: Matches GPT-5.1-Codex performance on SWE-Bench Verified with \\~30% fewer thinking tokens. We recommend “medium” reasoning effort as a good all-around daily driver model. \n", | |
| "* Faster and more token efficient: Matches GPT-5.1-Codex performance on SWE-Bench Verified with \\~30% fewer thinking tokens. We recommend `medium` reasoning effort as a good all-around, regular-use model. \n", |
| "Key improvements\n", | ||
| "\n", | ||
| "* Faster and more token efficient: Matches GPT-5.1-Codex performance on SWE-Bench Verified with \\~30% fewer thinking tokens. We recommend “medium” reasoning effort as a good all-around daily driver model. \n", | ||
| "* Higher intelligence and long-running autonomy: Codex is very capable and will work autonomously for hours to complete your hardest tasks. You can use “high” or “xhigh” reasoning effort for your hardest tasks. \n", |
Contributor
There was a problem hiding this comment.
Suggested change
| "* Higher intelligence and long-running autonomy: Codex is very capable and will work autonomously for hours to complete your hardest tasks. You can use “high” or “xhigh” reasoning effort for your hardest tasks. \n", | |
| "* Higher intelligence and long-running autonomy: Codex is very capable and will work autonomously for hours to complete your hardest tasks. You can use `high` or `xhigh` reasoning effort for your hardest tasks. \n", |
Contributor
There was a problem hiding this comment.
note that we need to change to xhigh in the other doc too–i put extra high
| "\n", | ||
| "* Faster and more token efficient: Matches GPT-5.1-Codex performance on SWE-Bench Verified with \\~30% fewer thinking tokens. We recommend “medium” reasoning effort as a good all-around daily driver model. \n", | ||
| "* Higher intelligence and long-running autonomy: Codex is very capable and will work autonomously for hours to complete your hardest tasks. You can use “high” or “xhigh” reasoning effort for your hardest tasks. \n", | ||
| "* First-class compaction support: Compaction enables multi-hour reasoning without hitting context limits, and longer continuous user conversations without needing to start new chat sessions. \n", |
Contributor
There was a problem hiding this comment.
Suggested change
| "* First-class compaction support: Compaction enables multi-hour reasoning without hitting context limits, and longer continuous user conversations without needing to start new chat sessions. \n", | |
| "* First-class compaction support: Compaction enables multi-hour reasoning without hitting context limits and longer continuous user conversations without needing to start new chat sessions. \n", |
| "\n", | ||
| "# Getting Started\n", | ||
| "\n", | ||
| "If you already have a working Codex implementation, this model should work well with relatively minimal updates, but if you’re starting with a prompt and set of tools that’s optimized for GPT-5-series models, or a third-party model, we recommend making more significant changes. The best reference implementation is our fully open source codex-cli agent, available on [GitHub](https://github.com/openai/codex); we recommend cloning this repo and using codex (or any coding agent) to ask questions about how things are implemented. However, by working with customers we’ve also learned how to customize agent harnesses beyond this particular implementation.\n", |
Contributor
There was a problem hiding this comment.
Suggested change
| "If you already have a working Codex implementation, this model should work well with relatively minimal updates, but if you’re starting with a prompt and set of tools that’s optimized for GPT-5-series models, or a third-party model, we recommend making more significant changes. The best reference implementation is our fully open source codex-cli agent, available on [GitHub](https://github.com/openai/codex); we recommend cloning this repo and using codex (or any coding agent) to ask questions about how things are implemented. However, by working with customers we’ve also learned how to customize agent harnesses beyond this particular implementation.\n", | |
| "If you already have a working Codex implementation, this model should work well with relatively minimal updates, but if you’re starting with a prompt and set of tools optimized for GPT-5-series models, or a third-party model, we recommend making more significant changes. The best reference implementation is our fully open-source codex-cli agent, available on [GitHub](https://github.com/openai/codex). Clone this repo and use Codex (or any coding agent) to ask questions about how things are implemented. From working with customers, we’ve also learned how to customize agent harnesses beyond this particular implementation.\n", |
| "## General\n", | ||
| "\n", | ||
| "- When searching for text or files, prefer using `rg` or `rg --files` respectively because `rg` is much faster than alternatives like `grep`. (If the `rg` command is not found, then use alternatives.)\n", | ||
| "- If a tool exists for an action, prefer to use the tool instead of shell commands (e.g read_file over cat). Strictly avoid raw `cmd`/terminal when a dedicated tool exists. Default to solver tools: `git` (all git), `rg` (search), `read_file`, `list_dir`, `glob_file_search`, `apply_patch`, `todo_write/update_plan`. Use `cmd`/`run_terminal_cmd` only when no listed tool can perform the action.\n", |
Contributor
There was a problem hiding this comment.
Suggested change
| "- If a tool exists for an action, prefer to use the tool instead of shell commands (e.g read_file over cat). Strictly avoid raw `cmd`/terminal when a dedicated tool exists. Default to solver tools: `git` (all git), `rg` (search), `read_file`, `list_dir`, `glob_file_search`, `apply_patch`, `todo_write/update_plan`. Use `cmd`/`run_terminal_cmd` only when no listed tool can perform the action.\n", | |
| "- If a tool exists for an action, prefer to use the tool instead of shell commands (e.g., `read_file` over `cat`). Strictly avoid raw `cmd`/terminal when a dedicated tool exists. Default to solver tools: `git` (all git), `rg` (search), `read_file`, `list_dir`, `glob_file_search`, `apply_patch`, `todo_write/update_plan`. Use `cmd`/`run_terminal_cmd` only when no listed tool can perform the action.\n", |
dkundel-openai
approved these changes
Dec 4, 2025
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Summary
Briefly describe the changes and the goal of this PR. Make sure the PR title summarizes the changes effectively.
Motivation
Why are these changes necessary? How do they improve the cookbook?
For new content
When contributing new content, read through our contribution guidelines, and mark the following action items as completed:
We will rate each of these areas on a scale from 1 to 4, and will only accept contributions that score 3 or higher on all areas. Refer to our contribution guidelines for more details.