pi-requesty-discover

This extension helps you discover currently available models in requesty.ai for your Pi Coding Agent.

This is a fork of pi-requesty with additional features:

• Use the apiKey from the model registry allowing you to use pi’s full value resolution capabilities
• Health-check available models and write a log about them
• Brief information about what was found, including added/removed models, health summary
• Confirm before writing models.json, with a dry-run mode that only previews
• A footer status line showing your monthly Requesty spend against your monthly limit
• Optional Settings file in json5 format

When and why use it

Use this extension if

• you are on Requesty.ai
• you are limited to certain models by a company policy (for instance, for data residency/protection reasons)
• you don’t want to handcraft your own curated list of models constantly
• you want to health-check models and preview the diff before writing
• you want to keep in touch with your usage without having to constantly visit the Requesty dashboard

Installation

# NPM
pi install npm:pi-requesty-discover
# GitHub
pi install git:github.com/enolive/pi-requesty-discover

Install locally

Check out the code from the official code repository https://github.com/enolive/pi-requesty-discover, and then:

pi install ./pi-requesty-discover

To run once without installing:

pi -e ./pi-requesty-discover

Configuration

The extension reads the requesty-export provider from ~/.pi/agent/models.json. You can override the provider id via the settings.

Example:

{
  "providers": {
    "requesty-export": {
      "name": "Requesty",
      "baseUrl": "https://router.requesty.ai/v1",
      "api": "openai-completions",
      "apiKey": "$REQUESTY_API_KEY",
      "models": []
    }
  }
}

❗ IMPORTANT
Health checks are designed to use only a few tokens, but they still make real Requesty API calls and will consume credits.

On startup, the extension fetches <baseUrl>/models using the configured apiKey as the bearer token and registers discovered and healthy models with Pi.

Discovery settings

The discovery workflow reads optional settings from requesty-discovery-settings.json5 in the Pi config directory (PI_CODING_AGENT_DIR). The file uses JSON5, so it supports comments. It is optional. When missing, it will be created including defaults.

Example:

{
  "$schema": "https://raw.githubusercontent.com/enolive/pi-requesty-discover/main/docs/requesty-discovery-settings.schema.json",

  // override the default provider id
  providerId: "requesty-export",
  // configure the health check mode
  healthCheckMode: "full", // or "basic", "off"
  // models excluded from discovery; useful for models that keep failing health checks
  bannedModels: [
    // hangs on tool calls
    'requesty/unstable-model',
  ],
}

Banned models are excluded before health checks run (so they cost no credits) and are removed from models.json on the next discovery write.

Environment variables

Name	Required	Type	Default	Meaning
PI_CODING_AGENT_DIR	no	string	~/.pi/agent	pi configuration directory

Command

Inside Pi:

/requesty-discover

The command:

• discovers Requesty models (and optional health checks)
• shows a summary notification (added/removed IDs, health summary)
• asks for confirmation before writing ~/.pi/agent/models.json
• refreshes Pi’s model registry so the new models are immediately available in /model
• reports whether the file was updated

If there are no model ID changes, confirmation still offers a metadata refresh write, which might have changed as well.

/requesty-discover --dry-run

Same discovery and health checks, but never prompts to write and leaves models.json unchanged.

pi -p "/requesty-discover"
pi -p "/requesty-discover --dry-run"

You can also run the command from the CLI in a non-interactive mode.

Usage status

The extension shows your current Requesty monthly spend as a persistent line in Pi’s footer, e.g.:

<API Key Name>: $63.55/$150.00 (42%)

When your API key has no monthly limit (monthly_limit is 0), the limit is treated as unlimited:

<API Key Name>: $63.55 (unlimited)

When you select a model from a provider other than REQUESTY_PROVIDER_ID, the status is cleared — there is no Requesty usage to show for it.

📌 NOTE
The footer update is best-effort and never blocks a turn. If it fails (network error, stale context after /reload), it fails silently without spamming notifications.