Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.capriole.ai/llms.txt

Use this file to discover all available pages before exploring further.

​
What is GitHub Copilot CLI

GitHub Copilot CLI is a terminal-native coding assistant. Its BYOK provider mode can use an OpenAI Chat Completions-compatible endpoint, which lets it send model requests to Capriole AI. This is a direct model-provider setup for Copilot CLI. It is separate from Microsoft 365 Copilot.

​
Prerequisites

Before you begin, make sure you have:

​
Installation

Install GitHub Copilot CLI with npm: 
npm install -g @github/copilot
Verify the install: 
copilot --version
GitHub authentication is not required when COPILOT_PROVIDER_BASE_URL is set for BYOK mode.

​
Configuration

Set Capriole AI as the OpenAI-compatible model provider: 
export CAPRIOLE_AI_API_KEY="YOUR_CAPRIOLE_AI_API_KEY"
export COPILOT_PROVIDER_TYPE="openai"
export COPILOT_PROVIDER_BASE_URL="https://api.caprioletech.com/v1"
export COPILOT_PROVIDER_API_KEY="$CAPRIOLE_AI_API_KEY"
export COPILOT_PROVIDER_WIRE_API="completions"
Choose GPT 5.5 on Chat Completions: 
export COPILOT_PROVIDER_MODEL_ID="gpt-5.5"
export COPILOT_PROVIDER_WIRE_MODEL="openai/gpt-5.5"
Or choose GPT 5.4 Mini on Chat Completions: 
export COPILOT_PROVIDER_MODEL_ID="gpt-5.4"
export COPILOT_PROVIDER_WIRE_MODEL="openai/gpt-5.4-mini"
COPILOT_PROVIDER_MODEL_ID tells Copilot CLI which built-in model behavior to use. COPILOT_PROVIDER_WIRE_MODEL is the Capriole AI model ID sent to POST /v1/chat/completions.

​
Persistent setup

GitHub Copilot CLI stores general CLI settings in its own config, but BYOK provider settings are environment variables. For a simple persistent setup, put one Capriole AI profile in your shell config. Add this GPT 5.5 Responses profile to ~/.zshrc: 
export CAPRIOLE_AI_API_KEY="YOUR_CAPRIOLE_AI_API_KEY"
export COPILOT_PROVIDER_TYPE="openai"
export COPILOT_PROVIDER_BASE_URL="https://api.caprioletech.com/v1"
export COPILOT_PROVIDER_API_KEY="$CAPRIOLE_AI_API_KEY"
export COPILOT_PROVIDER_WIRE_API="responses"
export COPILOT_PROVIDER_MODEL_ID="gpt-5.5"
export COPILOT_PROVIDER_WIRE_MODEL="openai/gpt-5.5"
alias capriole-copilot="copilot --stream on"
Reload your shell: 
source ~/.zshrc
Then run: 
capriole-copilot
For a one-off prompt: 
capriole-copilot -p "Explain this repository structure." --allow-all-tools
To switch profiles, change only COPILOT_PROVIDER_WIRE_API, COPILOT_PROVIDER_MODEL_ID, COPILOT_PROVIDER_WIRE_MODEL, and for Claude Messages use COPILOT_PROVIDER_TYPE, COPILOT_PROVIDER_BASE_URL, and COPILOT_PROVIDER_BEARER_TOKEN.

​
Interface options

​
OpenAI Chat Completions

Use this path when you want the broadest Capriole AI model coverage in GitHub Copilot CLI. 
export COPILOT_PROVIDER_TYPE="openai"
export COPILOT_PROVIDER_BASE_URL="https://api.caprioletech.com/v1"
export COPILOT_PROVIDER_API_KEY="$CAPRIOLE_AI_API_KEY"
export COPILOT_PROVIDER_WIRE_API="completions"
Validated wire models:
  • openai/gpt-5.5 with COPILOT_PROVIDER_MODEL_ID="gpt-5.5"
  • openai/gpt-5.4-mini with COPILOT_PROVIDER_MODEL_ID="gpt-5.4"
  • anthropic/claude-opus-4-8 with COPILOT_PROVIDER_MODEL_ID="gpt-5.4"
  • anthropic/claude-opus-4-7 with COPILOT_PROVIDER_MODEL_ID="gpt-5.4"
  • google/gemini-3.1-pro-preview with COPILOT_PROVIDER_MODEL_ID="gpt-5.4"
  • google/gemini-3.5-flash with COPILOT_PROVIDER_MODEL_ID="gpt-5.4"
Copilot CLI does not have a native Gemini provider. Gemini runs through Capriole AI’s OpenAI-compatible Chat Completions proxy.

​
OpenAI Responses

Use this path when you want GitHub Copilot CLI to call Capriole AI’s Responses-compatible endpoint. 
export COPILOT_PROVIDER_TYPE="openai"
export COPILOT_PROVIDER_BASE_URL="https://api.caprioletech.com/v1"
export COPILOT_PROVIDER_API_KEY="$CAPRIOLE_AI_API_KEY"
export COPILOT_PROVIDER_WIRE_API="responses"
Validated wire models:
  • openai/gpt-5.5 with COPILOT_PROVIDER_MODEL_ID="gpt-5.5"
  • openai/gpt-5.4-mini with COPILOT_PROVIDER_MODEL_ID="gpt-5.4"
Responses is an OpenAI wire protocol in Capriole AI. Claude and Gemini model IDs are not supported on POST /v1/responses.

​
Anthropic Messages

Use this path when you want GitHub Copilot CLI to call Capriole AI’s Anthropic Messages-compatible endpoint. 
export COPILOT_PROVIDER_TYPE="anthropic"
export COPILOT_PROVIDER_BASE_URL="https://api.caprioletech.com"
export COPILOT_PROVIDER_BEARER_TOKEN="$CAPRIOLE_AI_API_KEY"
export COPILOT_PROVIDER_MODEL_ID="claude-sonnet-4"
export COPILOT_PROVIDER_WIRE_MODEL="claude-opus-4-8"
Validated wire models:
  • claude-opus-4-8 with COPILOT_PROVIDER_MODEL_ID="claude-sonnet-4"
  • claude-opus-4-7 with COPILOT_PROVIDER_MODEL_ID="claude-sonnet-4"
Use COPILOT_PROVIDER_BEARER_TOKEN for this path. COPILOT_PROVIDER_API_KEY sends provider-style auth and does not satisfy Capriole AI’s public Bearer-token auth gate.

​
Run GitHub Copilot CLI

Start an interactive session: 
copilot --stream on
Run a one-off request: 
copilot -p "Explain this repository structure." --allow-all-tools --stream on
For scripted use, keep streaming enabled. Capriole AI’s validated Copilot CLI paths all use streaming with tool calls.

​
Supported models

These model/provider mappings have been validated with Copilot CLI BYOK, streaming responses, and local shell tool use:
  • Chat Completions: openai/gpt-5.5, openai/gpt-5.4-mini, anthropic/claude-opus-4-8, anthropic/claude-opus-4-7, google/gemini-3.1-pro-preview, and google/gemini-3.5-flash
  • Responses: openai/gpt-5.5 and openai/gpt-5.4-mini
  • Anthropic Messages: claude-opus-4-8 and claude-opus-4-7
Other public model IDs returned by GET /v1/models can be tested through the same OpenAI-compatible provider path, but do not use them for coding-agent workflows until tool use is validated.

​
Troubleshooting

​
Why does Copilot CLI return an authentication error?

Confirm that CAPRIOLE_AI_API_KEY is exported and that COPILOT_PROVIDER_API_KEY points to it in the same shell before starting Copilot CLI.

​
Why do requests fail with endpoint errors?

For OpenAI-compatible Chat Completions or Responses, confirm that COPILOT_PROVIDER_BASE_URL is https://api.caprioletech.com/v1. For Anthropic Messages, confirm that COPILOT_PROVIDER_BASE_URL is https://api.caprioletech.com without /v1.

​
Why does Copilot CLI say the model is missing?

Set both COPILOT_PROVIDER_MODEL_ID and COPILOT_PROVIDER_WIRE_MODEL. The model ID should be the Copilot-side base model, while the wire model should be the Capriole AI model ID.

​
Why should streaming stay enabled?

GitHub’s BYOK requirements state that models must support streaming and tool/function calling. Capriole AI validates GitHub Copilot CLI on the streaming path.

​
Notes

  • Capriole AI exposes GitHub Copilot CLI through POST /v1/chat/completions.
  • Capriole AI also validates GitHub Copilot CLI through POST /v1/responses for OpenAI models and POST /v1/messages for Claude models.
  • GitHub Copilot CLI executes coding tools locally. Capriole AI only handles model requests.
  • GitHub Copilot CLI does not have a wire API for Capriole AI’s native POST /v1/chat route.
  • Official references: GitHub Copilot CLI installation, GitHub Copilot CLI BYOK, and GitHub Copilot SDK BYOK.