@howaboua/pi-codex-conversion
Codex-oriented tool and prompt adapter for pi coding agent
Package details
Install @howaboua/pi-codex-conversion from npm and Pi will load the resources declared by the package manifest.
$ pi install npm:@howaboua/pi-codex-conversion- Package
@howaboua/pi-codex-conversion- Version
1.5.5- Published
- May 17, 2026
- Downloads
- 6,484/mo · 3,449/wk
- Author
- howaboua
- License
- MIT
- Types
- extension
- Size
- 6.9 MB
- Dependencies
- 4 dependencies · 4 peers
Pi manifest JSON
{
"extensions": [
"./src/index.ts"
]
}Security note
Pi packages can execute code and influence agent behavior. Review the source before installing third-party packages.
README
pi-codex-conversion
Codex-style tools for Pi.
[!NOTE] Use the npm package for normal installs. Avoid
pi install git:...unless you know you want the development checkout; see Development checkout.
GPT/Codex models are strongest when the tool surface looks like the Codex CLI they were trained around: shell commands, resumable terminal sessions, and patch-based edits. This extension brings that workflow to Pi while keeping Pi's runtime, sessions, project context, skills, and UI.
The point is to give the model tools it already knows how to use well: shell-first inspection, resumable command sessions, and large one-shot patch edits instead of piecemeal read/edit/write steps.
You can also opt into using the adapter on every provider/model. YMMV: Codex-tuned models are still the best fit, but the shell/patch workflow can help elsewhere too. The extension also has a small /codex settings UI for toggling adapter behavior, web search, image generation, fast mode, and verbosity. See Settings.
Install
pi install npm:@howaboua/pi-codex-conversion

Active tools in adapter mode
When the adapter is active, the LLM sees these tools:
exec_command— shell execution with Codex-stylecmdparameters and resumable sessionswrite_stdin— continue or poll a running exec sessionapply_patch— patch toolweb_search— native OpenAI Codex Responses web search, enabled only on theopenai-codexproviderimage_generation— native OpenAI Codex Responses image generation, enabled only on image-capableopenai-codexmodelsview_image— image-only wrapper around Pi's native image reading, enabled only for image-capable models
Notably:
- there is no dedicated
read,edit, orwritetool in adapter mode - local text-file inspection should happen through
exec_command - file creation and edits should default to
apply_patch - Pi may still expose additional runtime tools such as
parallel; the prompt is written to tolerate that instead of assuming a fixed four-tool universe
Settings
Use /codex to change adapter settings.
/codex all— use the Codex tool and prompt adapter on every model/codex status— toggle the footer/statusline entry/codex fast— toggle priority service tier for the OpenAI Codex provider/codex search— toggle native Codex web search/codex image— toggle native Codex image generation/codex low,/codex medium,/codex high— set Responses API verbosity
Settings are saved globally in ~/.pi/agent/pi-codex-conversion.json.
When all is on, non-Codex providers get the shell, patch, skill, and prompt-adapter behavior, but keep their normal Pi provider path. Native web search, native image generation, and priority service tier stay limited to the OpenAI Codex provider. Verbosity is applied to Responses API providers.
The footer shows the active state, for example:
Codex adapter V: low • web search • image gen
What changes in Pi
- Adapter mode activates automatically for OpenAI
gpt*andcodex*models, then restores the previous tool set when you switch away. - Pi's composed prompt is preserved; the extension only adds a small Codex-style tool-use nudge.
- Shell activity is rendered with Codex-like labels such as
Ran,Explored,Read, and background-terminal status. apply_patchrenders as Codex-styleAdded/Edited/Deletedblocks, including inline partial-failure state.- Native web search appears as a compact expandable summary after a turn, with queries and sources in the expanded view.
- Generated images are saved under
.pi/openai-codex-images/at the workspace/repo root, with the latest image mirrored tolatest.png.
Command rendering examples
rg -n foo src->Explored / Search foo in srcrg --files src | head -n 50->Explored / List srccat README.md->Explored / Read README.mdnpm test->Ran npm testwrite_stdin({ session_id, chars: "" })->Waited for background terminalwrite_stdin({ session_id, chars: "y\n" })->Interacted with background terminal
Raw command output is still available by expanding the tool result.
Details worth knowing
exec_commandandwrite_stdinuse a PTY-backed session manager for interactive commands and long-running processes.apply_patchaccepts absolute paths as-is and resolves relative paths against the current working directory.- Shell
apply_patchis also available insideexec_command, but the dedicatedapply_patchtool is preferred unless you are chaining edits with other shell steps. - Native
web_searchandimage_generationare forwarded to OpenAI Codex Responses tools rather than executed as local function tools.
Development checkout
The Git checkout is mostly for development and mirrors the maintainer workflow. If you run it directly, you may need to build the bundled apply_patch binary for your platform.
Run the current checkout without installing globally:
pi --no-extensions --no-skills -e /path/to/pi-codex-conversion
License
MIT