Adds an AI disclosure instruction to the <EXTERNAL_SERVICES> section of the system prompt. When the agent posts messages, comments, issues, or any human-readable content to external services, it should include a brief note indicating the content was generated by an AI agent on behalf of the user. https://github.com/OpenHands/software-agent-sdk/pull/2476 What do y'all think of this? Right now it is a bit hard to differentiate AI and human, especially we are sharing the github account 😅