Unofficial API in JS/TS

Manages authenticated sessions to OpenAI's ChatGPT web interface by automating browser interactions through Puppeteer, handling login flows, session persistence, and token refresh cycles. Implements headless Chrome automation to bypass API rate limits and access ChatGPT without official API keys, storing session cookies and maintaining stateful connections across multiple conversation turns.

Tracks multi-turn conversations by maintaining parentMessageId and conversationId references, enabling the library to reconstruct conversation threads and send follow-up messages in the correct context. Implements client-side conversation history tracking that maps message IDs to their parent messages, allowing the browser automation layer to inject the correct context when submitting new messages to ChatGPT.

Maps ChatGPT web interface interactions to underlying API endpoints by analyzing network traffic and DOM structure, allowing the library to send requests directly to ChatGPT's backend services. Implements endpoint discovery and request/response serialization that mirrors ChatGPT's internal API contracts, including payload formatting, authentication headers, and response parsing without official API documentation.

Implements exponential backoff and retry mechanisms to handle transient failures in browser automation, including network timeouts, ChatGPT service unavailability, and DOM parsing errors. Detects specific error conditions (e.g., CAPTCHA challenges, session expiration, rate limiting) and applies targeted recovery strategies such as session refresh or request retry with exponential delays.

Provides TypeScript interfaces and types that model ChatGPT's request and response structures, enabling type-safe interactions with the reverse-engineered API. Defines types for conversation objects, message payloads, and API responses, allowing developers to catch type errors at compile time rather than runtime.

Implements streaming response parsing to deliver ChatGPT responses incrementally as they arrive, rather than waiting for the complete response. Uses event-based callbacks or async iterators to emit partial messages as the browser receives them from ChatGPT, enabling real-time UI updates and reduced perceived latency in chat applications.