README
@xl0/pi-lovely-codex
GPT "Fast mode" control and Codex-style apply_patch tool.
Install
pi install npm:@xl0/pi-lovely-codex
Or use without installing:
pi -e npm:@xl0/pi-lovely-codex
/lovely-codex
GPT fast mode ποΈ
Sends service_tier: "priority" to request priority serving:
defaultβ don't sendservice_tierfastβ priority on bothopenaiandopenai-codexfast-codexβ priority onopenai-codexonly
GPT models on those two providers only. Fast mode shows ποΈ in the status line.
On the Codex subscription,
priorityis silently ignored unless your account has Fast mode credits. On the OpenAI API it needs priority processing enabled for your org.
apply_patch
GPT models are trained on Codex's apply_patch; with Pi's edit tool, muscle
memory shows β silly mistakes creep in. This extension gives them the tool they
were trained on.
By default, apply_patch is a plain JSON tool { input: string }. For models
that support OpenAI grammar tools, it can instead be a freeform custom tool
constrained by Codex's Lark grammar.
Patches are applied by shelling out to
codex --codex-run-as-apply-patch. The Codex CLI must be installed and on PATH.
Settings:
add apply_patchβon,off, orgpt-only(default: only for model ids starting withgpt-or containing/gpt-).enable freeformβ use the grammar-constrained custom tool when supported (off by default).disable write/disable editβ drop the now-redundant built-in tools whileapply_patchis active (off by default); restored after, but never beyond what the session started with.disable readβon,off, orgpt-only(default: only for GPT model ids, independent ofapply_patch). Forces bounded shell reads (sed -n/head) instead of whole-file reads, conserving context the way Codex's toolset does. Whilereadis gone, aview_imagetool takes over image reading (which the shell can't provide); turn it off withadd view_image.
Config files
- User:
~/.pi/agent/xl0-pi-lovely-codex.json - Workspace:
<cwd>/.pi/xl0-pi-lovely-codex.json
Workspace overrides User. All keys optional.
Related projects
| Pi Lovely Web | web_search, web_fetch, web_image tools |
| Pi Lovely Dev Tools | interactive debugging helpers /tool, /show-sysprompt, /show-context, /llm-stats |
| Pi Lovely IDE | IDE integration |
| Pi Lovely Config | scoped config helpers for Pi extensions |
| Pi Lovely Comment | open the last assistant message in your editor and sync edits back into the prompt |
| Pi Lovely Rename | automatic and manual session naming |
Like this work? Hire me
Contributors
See what people are saying
Similar repos
Languages
TypeScript
100.0%
README
@xl0/pi-lovely-codex
GPT "Fast mode" control and Codex-style apply_patch tool.
Install
pi install npm:@xl0/pi-lovely-codex
Or use without installing:
pi -e npm:@xl0/pi-lovely-codex
/lovely-codex
GPT fast mode ποΈ
Sends service_tier: "priority" to request priority serving:
defaultβ don't sendservice_tierfastβ priority on bothopenaiandopenai-codexfast-codexβ priority onopenai-codexonly
GPT models on those two providers only. Fast mode shows ποΈ in the status line.
On the Codex subscription,
priorityis silently ignored unless your account has Fast mode credits. On the OpenAI API it needs priority processing enabled for your org.
apply_patch
GPT models are trained on Codex's apply_patch; with Pi's edit tool, muscle
memory shows β silly mistakes creep in. This extension gives them the tool they
were trained on.
By default, apply_patch is a plain JSON tool { input: string }. For models
that support OpenAI grammar tools, it can instead be a freeform custom tool
constrained by Codex's Lark grammar.
Patches are applied by shelling out to
codex --codex-run-as-apply-patch. The Codex CLI must be installed and on PATH.
Settings:
add apply_patchβon,off, orgpt-only(default: only for model ids starting withgpt-or containing/gpt-).enable freeformβ use the grammar-constrained custom tool when supported (off by default).disable write/disable editβ drop the now-redundant built-in tools whileapply_patchis active (off by default); restored after, but never beyond what the session started with.disable readβon,off, orgpt-only(default: only for GPT model ids, independent ofapply_patch). Forces bounded shell reads (sed -n/head) instead of whole-file reads, conserving context the way Codex's toolset does. Whilereadis gone, aview_imagetool takes over image reading (which the shell can't provide); turn it off withadd view_image.
Config files
- User:
~/.pi/agent/xl0-pi-lovely-codex.json - Workspace:
<cwd>/.pi/xl0-pi-lovely-codex.json
Workspace overrides User. All keys optional.
Related projects
| Pi Lovely Web | web_search, web_fetch, web_image tools |
| Pi Lovely Dev Tools | interactive debugging helpers /tool, /show-sysprompt, /show-context, /llm-stats |
| Pi Lovely IDE | IDE integration |
| Pi Lovely Config | scoped config helpers for Pi extensions |
| Pi Lovely Comment | open the last assistant message in your editor and sync edits back into the prompt |
| Pi Lovely Rename | automatic and manual session naming |
Like this work? Hire me
See what people are saying
Similar repos
Contributors
Languages
TypeScript
100.0%