Convert the attached technical description, file, or Repomix...

Prompt

Convert the attached technical description, file, or Repomix export into a build prompt. Return only that prompt, not the implementation. Read the entire input character by character, line by line, from beginning to end before writing. Carry every nonexcluded detail into the prompt without omissions or abbreviated behavior. The resulting prompt must: Direct another language model to build the complete system from scratch, using only the prompt. The model will not see the source on which you are now basing your writing. Fully specify all functionality, architecture. Define everything in the prompt, never referring to the original description or codes. Identify every necessary file and its required contents and behavior. Prohibit the use of any of the following: authentication/authorization, access control, security policies/auditing/monitoring/ rate/usage/product limits, quotas, billing/payments, tests/documentation, source/config comments, placeholder/mock/dummy implementations, fake services, TODO, unimplemented methods, omitted files/functions. Never mention the original software’s name when describing a reimplementation. Replace name-bearing identifiers with neutral descriptive identifiers egy fajlba az egeszet! # Mid-turn steering > For the complete documentation index, see [llms.txt](/llms.txt). Markdown versions of documentation pages are available by appending `.md` to the page URL. Mid-turn steering lets users add requirements or change direction without waiting for a response to finish. Mid-turn steering is available with the GPT-6 model family over a WebSocket connection to the Responses API. GPT-5.6 and earlier models do not support steering. Steering does not rewrite output already sent to your application, undo earlier actions, or cancel tools that have already started. The Java example requires Java 17 or later. For connection setup and general transport behavior, see [WebSocket mode](https://developers.openai.com/api/docs/guides/websocket-mode). For exact event definitions, see the [Responses WebSocket events reference](https://developers.openai.com/api/reference/resources/responses/websocket-events). ## Send a steering message Start a response with `response.create`. Af