Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Just like #361 (comment) , I extracted the hard coded fields from the code and stored them in fragment.json. For readability, I used prefix naming to indicate which part of the program prompt each fragment is working on.Now it is possible to customize all parts of the prompt without changing the framework

I verified the correctness of fragment I added in the Chinese prompt template:
As a result, the content of fragmentjson has swelled a lot. I think adding comments is necessary for readability. Considering that json files cannot have comments, I once considered replacing them with configuration files in other formats (such as YAML), but gave up for compatibility with the tasks in the examples.
In addition, I also want to add similar images in the issue I mentioned to illustrate the process of constructing prompts, but it is currently unclear whether PNG images or Mermaid are more suitable?