Session state (logged_in/anonymous/login_required), current model label, configured project, open chat tabs. Cheap; call first.

Health check: CDP reachable, session state, file input present, available model names, whether the configured project exists. Use when something fails.

List conversations inside the configured ChatGPT project (title + url). Optional substring filter on title.

Open a new conversation inside the configured project and select the configured model. Returns a temporary handle chat (tab:); after the first send you get the permanent chat_url.

Open an existing conversation by URL (https://chatgpt.com/c/...) so you can continue it. Returns turn counts and a preview of the last reply.

Send a message (optionally with files under the work dir, max 10) to a chat. Returns immediately with status=generating unless wait_sec>0 (max 900). reply_format: largest_markdown | text | blocks | all.

Wait for the newest reply in a chat to finish (poll). timeout_sec<=900; if it returns status=generating call wait again. Returns the reply in reply_format.

Read an assistant reply without waiting. index=-1 is the newest. reply_format: text | blocks | largest_markdown | all.

Write a reply to a file under the work dir without passing the whole text through the model. reply_format largest_markdown extracts the biggest ```markdown block (falls back to full text). Returns word/section stats.

Stop the reply currently being generated in a chat.

Close the browser tab of a chat (the conversation stays in ChatGPT).

Offline: word count per ### BÖLÜM n section of a saved notes file.