@georgedong32/pi-effort

Pi extension for controlling thinking effort with model-adaptive min/max aliases

Packages

Package details

extension

Install @georgedong32/pi-effort from npm and Pi will load the resources declared by the package manifest.

$ pi install npm:@georgedong32/pi-effort
Package
@georgedong32/pi-effort
Version
0.1.0
Published
Jul 1, 2026
Downloads
40/mo · 14/wk
Author
georgedong32
License
Apache-2.0
Types
extension
Size
49.7 KB
Dependencies
0 dependencies · 2 peers
Pi manifest JSON
{
  "extensions": [
    "./index.ts"
  ]
}

Security note

Pi packages can execute code and influence agent behavior. Review the source before installing third-party packages.

README

pi-effort

Extension for pi: small command surface for reasoning effort and OpenAI/Codex fast mode.

Commands

Exactly two slash commands are exposed:

/effort {min|minimal|low|medium|high|xhigh|max}
/fast [on|off]

No /effort show, /effort default, /effort options, /effort fast, or /fast status. Bare /fast toggles the current fast-mode setting.

Effort

/effort accepts the current model's supported reasoning levels plus two adaptive aliases:

Model type min max Explicit levels
Non-reasoning (thinking unavailable)
Reasoning minimal high minimal, low, medium, high
xhigh-capable reasoning minimal xhigh minimal, low, medium, high, xhigh

Examples:

/effort min
/effort medium
/effort max

Interactive picker

Bare /effort (no argument) opens a horizontal slider with the model's supported levels, current selection highlighted. Use ←/→ to move, Enter to confirm, Esc to cancel. The strongest available level sits flush against the right edge — no trailing whitespace.

                              Effort

              ──────────────────▲─────────────────────────────────
              minimal      low      medium      high        xhigh

              ←/→ to adjust · Enter to confirm · Esc to cancel

Tab also advances one step to the right. The picker falls back to a plain select dialog in non-TUI modes (RPC, print).

Fast mode

Fast mode is the latency/service-tier knob. When enabled, pi-effort adds service_tier: "priority" to GPT-5 / OpenAI-Codex provider requests that do not already specify a tier.

/fast      # toggle
/fast on   # force on
/fast off  # force off

Fast mode persists in ~/.pi/agent/settings.json under:

{
  "pi-effort": {
    "fastMode": true
  }
}

Footer status

For compact powerline footers, the extension publishes these status keys:

  • pi-effort-thinkingthink:<level>
  • pi-effort-fastfast only when fast mode is enabled and applies to the current model

Keyboard shortcut

Ctrl+Shift+E cycles through the current model's reasoning levels.

CLI flag

pi --effort max
pi --effort min
pi --effort high

The flag uses the same values as /effort.

Install

pi install npm:@georgedong32/pi-effort

Verify what Pi is loading:

pi list
npm list -g --depth=0 @georgedong32/pi-effort

The durable Pi setting is the package entry in ~/.pi/agent/settings.json:

{
  "packages": [
    "npm:@georgedong32/pi-effort"
  ]
}

Local development

For a one-off local test from this checkout:

npm install
pi -e ./index.ts

For a longer local-path development install:

pi remove npm:@georgedong32/pi-effort
pi install "$(pwd)"

After publishing a new version, switch back to the npm package:

npm publish
pi remove "$(pwd)"
pi install npm:@georgedong32/pi-effort

Verification

npm run check
npm test
npm pack --dry-run

Repo structure

index.ts        Pi extension entrypoint
effort.ts       Parsing, settings, and model capability logic
effort-picker.ts  Custom TUI component for the /effort overlay
package.json    Package metadata and Pi manifest
tsconfig.json   TypeScript configuration

License

Apache-2.0