Skip to content
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

MultiLine Autocompletion not working even though model is providing multi line responses #4413

Open
3 tasks done
bdavj opened this issue Feb 28, 2025 · 2 comments · May be fixed by #4509
Open
3 tasks done

MultiLine Autocompletion not working even though model is providing multi line responses #4413

bdavj opened this issue Feb 28, 2025 · 2 comments · May be fixed by #4509
Assignees
Labels
area:autocomplete Relates to the auto complete feature ide:jetbrains Relates specifically to JetBrains extension kind:bug Indicates an unexpected problem or unintended behavior "needs-triage"

Comments

@bdavj
Copy link

bdavj commented Feb 28, 2025

Before submitting your bug report

Relevant environment info

Relevant environment info
- OS: MacOS
- Continue version: 1.0.1
- IDE version:IntelliJ IDEA 2024.3.1.1
- Model: Claude 3.5 Haiku
- config:
  
models:
  - name: AWS - Embed
    provider: openai (Via bedrock connector proxy)
    model: ac-claude-3-5-haiku-us
    apiKey: aaa
    apiBase: https://aaa:8080/v1
    roles:
      - autocomplete

Multi Line complete set to always

Description

Prompting an autocompletion results in a single line presented in IJ, even though the prompts.log shows multiple lines:

Image

To reproduce

No response

Log output

@dosubot dosubot bot added area:autocomplete Relates to the auto complete feature ide:jetbrains Relates specifically to JetBrains extension kind:bug Indicates an unexpected problem or unintended behavior labels Feb 28, 2025
@bdavj
Copy link
Author

bdavj commented Mar 5, 2025

This problem appears to be threefold:

  • Model timeout can't be modified, due to relying on Posthog configuration. Resolution is to add this to user configuration in GUI.
  • Debounce delay can't be modified following removal from json file. Resolution is to add this to user configuration.
  • Debounce logic doesn't work for multiple requests, ends up firing many requests at once, without actually debouncing. Resolution is refined debounce logic.

Pull request incoming shortly.

@bdavj bdavj linked a pull request Mar 6, 2025 that will close this issue
@tomasz-stefaniak
Copy link
Collaborator

Thanks @bdavj, we'll get it reviewed soon!

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
area:autocomplete Relates to the auto complete feature ide:jetbrains Relates specifically to JetBrains extension kind:bug Indicates an unexpected problem or unintended behavior "needs-triage"
Projects
None yet
Development

Successfully merging a pull request may close this issue.

2 participants