About chat-messages API response

[htguan]

Self Checks

• I have searched for existing issues search for existing issues, including closed ones.
• I confirm that I am using English to submit this report (我已阅读并同意 Language Policy).
• [FOR CHINESE USERS] 请务必使用英文提交 Issue，否则会被关闭。谢谢！:）
• Please do not modify this template :) and fill in all the required fields.

1. Is this request related to a challenge you're experiencing? Tell me about your story.

According to the Doc, it says

You can create multiple access credentials for an application to deliver to different users or developers. This means that API users can use the AI capabilities provided by the application developer, but the underlying Prompt engineering, knowledge, and tool capabilities are encapsulated.

However, when using the streaming chat-messages API, the interface returns a detailed workflow in the response, including node types, prompts, recalls from knowledge base, etc. That's really terrifying. For exsample, one of the SSE messages is:

{
    "event": "node_finished",
    "conversation_id": "a8de744c-85ab-42c6-a0da-79f1d9fd2ef5",
    "message_id": "52bdef31-8d96-4f6d-8fe5-780420e18b53",
    "created_at": 1737695852,
    "task_id": "6f5ea361-70e6-49e9-9036-67bf7f9c447c",
    "workflow_run_id": "f19bd72a-15ab-4963-ba04-c8d5c0326cbe",
    "data": {
        "id": "f73457c0-7fdd-42b6-9492-d32bcf7e2253",
        "node_id": "1737543704476",
        "node_type": "knowledge-retrieval",
        "title": "知识检索",
        "index": 3,
        "predecessor_node_id": "1737612790330",
        "inputs": {
            "query": "Who is the boss?"
        },
        "process_data": null,
        "outputs": {
            "result": [
                {
                    "metadata": {
                        "_source": "knowledge",
                        "dataset_id": "4aeb36a6-d1cd-48a2-9460-6c5430af80de",
                        "dataset_name": "Company_Information",
                        "document_id": "183a516b-fb87-4bde-91e5-0bafd4afecfd",
                        "document_name": "Company_Info.docx",
                        "document_data_source_type": "upload_file",
                        "segment_id": "79babce4-c472-4fa0-811b-a87ae60aae86",
                        "retriever_from": "workflow",
                        "score": 0.4397774040699005,
                        "segment_hit_count": 0,
                        "segment_word_count": 229,
                        "segment_position": 1,
                        "segment_index_node_hash": "1b6be219d84494e241372136164e0f9d53622f306188a6c0f7f7cc9beda41fca",
                        "position": 1
                    },
                    "title": "Company_Info.docx",
                    "content": "Company Name: XXX Corporation\nRepresentative: XXX\n (more text omitted)"
                }
            ]
        },
        "status": "succeeded",
        "error": null,
        "elapsed_time": 0.201911,
        "execution_metadata": null,
        "created_at": 1737695852,
        "finished_at": 1737695852,
        "files": [],
        "parallel_id": null,
        "parallel_start_node_id": null,
        "parent_parallel_id": null,
        "parent_parallel_start_node_id": null,
        "iteration_id": null
    }
}

This completely fails to achieve the goal of "encapsulate the the underlying Prompt engineering, knowledge, and tool capabilities". And it seems that I haven't found a parameter switch to disable these outputs.

I wonder if there is something wrong with my operation. I look forward to the reply. Thanks.

2. Additional context or comments

No response