-
Notifications
You must be signed in to change notification settings - Fork 17
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
@generate mode doesn't know the name of the pinned context file #2010
Comments
Title: Update Navie to Recognize and Use Pinned Context File Names in Problem: When using the Analysis: The root cause of this issue seems to be the lack of a direct mapping or recognition mechanism within Navie's To resolve this, the system requires enhancements in how contexts are processed and used. Adjustments to data structures or handling logic that allow inclusion and recognition of metadata, like filenames, are necessary. This kind of structured information will enable Navie to correlate the specific content, intended file references, and context needed for precise code generation. Proposed Changes:
This approach will align the |
In the first image, no code snippets are found. The instructions referencing a file are included as part of the code snippet prompt description, which will not be included in the absence of code snippets: |
When using the
@generate
command, Navie doesn't know the name of the pinned file.You can see how, in this screenshot, I have pinned a context file called "official.py".
Then I've asked a typical code generation question. Navie outputs code snippets referring to `/path/to/your/script.py' rather than the pinned file.
It will also propose (correct) changes to the wrong file name:
See also
--
@generate
mode should observe and use the file names provided in the pinned context.The text was updated successfully, but these errors were encountered: