Please support for an interface similar to OpenAI's multi-turn dialogue

Self Checks

[X] I have searched for existing issues search for existing issues, including closed ones.
[X] I confirm that I am using English to submit this report (我已阅读并同意 Language Policy).
[X] [FOR CHINESE USERS] 请务必使用英文提交 Issue，否则会被关闭。谢谢！:）
[X] 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.

When calling OpenAI's Chat-Message API, you can pass session information using the "messages" parameter, allowing me to manually construct a historical context to include, such as:

curl https://api.openai.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -d '{
     "model": "gpt-4o-mini",
     "messages": [{"role": "user", "content": "Here is the content"}, {"role": "assistant", "content": "OK"}, {"role": "user", "content": "what are we talking about?"}],
     "temperature": 0.7
   }'

However, in the external API interface or Workflow provided by Dify, it is not possible to complete tasks based on context provided externally; you can only initiate a conversation and maintain the context of that conversation through Dify itself.

Therefore, I request that Dify support an interface that allows users to construct their own historical context for conversation generation.

2. Additional context or comments

No response

3. Can you help us with this feature?

[X] I am interested in contributing to this feature.

langgenius / dify