Skip to content

AI assistant

The built-in AI assistant is a chat panel that can read the current request and response as context — useful for explaining an API, drafting a payload, debugging a failed response, or generating a test script.

  • OpenAI (GPT-4o, GPT-4.1, o-series).
  • Anthropic (Claude Sonnet 4.x, Haiku 4.x).
  • OpenRouter — any model OpenRouter relays.

For each provider, paste your own API key (stored as a SecretRef, never plaintext in the renderer). You can also point any of them at a custom base URL for self-hosted gateways or local model servers.

When you invoke a chat that references the current request, Restura builds a context snapshot:

  • The request URL (path only — host is redacted).
  • The request method and selected protocol.
  • Headers (sensitive ones — Authorization, Cookie, X-Api-Key — redacted).
  • The request body (JSON pretty-printed, large blobs truncated).
  • The response status, headers, and body (with the same redaction rules).
  • The active environment name (variables not exposed).

The snapshot is what goes to the provider. Secrets and absolute URLs are stripped before the prompt is sent.

  • Desktop — fully wired. The renderer streams chunks from the Electron main process over IPC; the main process talks to the provider directly. primary path
  • Web — in progress; not all providers proxied through the Worker yet. Check the in-app indicator.
  • Explain the current request or response in plain language.
  • Generate a body, a header value, a test script, or a curl command for the current request.
  • Debug — paste in the response and ask why it’s 4xx.
  • Compose workflow extractions: “extract the user ID from the response and use it in the next request.”
  • Keep prompts short and reference the current request explicitly — the snapshot is dense; you don’t need to repeat what’s already there.
  • For long debugging sessions, save the chat to history — chat history lives alongside request history.