Copilot CLI
Use GitHub Copilot CLI for multi-model cloud analysis powered by GitHub's AI infrastructure. Copilot CLI supports Claude, GPT, and Gemini model families through a single tool.
Requirements
copilotCLI installed.GitHub authentication completed (
copilot auth loginor active GitHub session).
Setup
Install CLI:
brew install copilot-cliAuthenticate:
copilot auth loginVerify locally:
copilot -p "hello"Configure in AI Backend settings tab.
Configuration
Preferred Backend
copilot-cli
Copilot CLI Command
copilot or full path
Model examples:
The extension does not maintain a Copilot model allowlist: it forwards the configured command. Available models therefore depend on the installed Copilot CLI version and the authenticated account; use copilot --help to confirm identifiers before saving one.
Notes
Large Prompt Fallback
For prompts above 32_000 characters, the extension writes the combined prompt to a burp_uv_prompt_*.txt temp file (POSIX 0600 where supported) and passes its path to Copilot with an instruction to read the file. The temp file is deleted in a finally block once the response is consumed. This avoids OS-level argv/stdin length limits on long contexts.
Non-Interactive Mode
The extension invokes Copilot CLI with -p (non-interactive) flag, which executes the prompt and exits after completion.
Windows
npm-installed CLI shims are resolved automatically on Windows. The extension detects .cmd siblings and uses them instead of shell script shims that Java cannot execute directly.
Troubleshooting
Related Pages
Last updated
