feat(autocomplete): Add Qwen multi-file FIM template for repository-level autocompletion#10612
Open
hiepau1231 wants to merge 1 commit intocontinuedev:mainfrom
Open
feat(autocomplete): Add Qwen multi-file FIM template for repository-level autocompletion#10612hiepau1231 wants to merge 1 commit intocontinuedev:mainfrom
hiepau1231 wants to merge 1 commit intocontinuedev:mainfrom
Conversation
|
All contributors have signed the CLA ✍️ ✅ |
Contributor
There was a problem hiding this comment.
1 issue found across 1 file
Prompt for AI agents (all issues)
Check if these issues are valid — if so, understand the root cause of each and fix them. If appropriate, use sub-agents to investigate and fix each issue separately.
<file name="core/autocomplete/templating/AutocompleteTemplate.ts">
<violation number="1" location="core/autocomplete/templating/AutocompleteTemplate.ts:102">
P1: `relativePaths[i]` returns an object `{ uri, uniquePath }`, not a string. Direct interpolation will emit `[object Object]` in the prompt instead of the file path. Extract the `uniquePath` property like other multi-file templates do (e.g., `relativePaths[i].uniquePath` or via a helper function).</violation>
</file>
Since this is your first cubic review, here's how it works:
- cubic automatically reviews your code and comments on bugs and improvements
- Teach cubic by replying to its comments. cubic learns from your replies and gets better over time
- Add one-off context when rerunning by tagging
@cubic-dev-aiwith guidance or docs links (includingllms.txt) - Ask questions if you need clarification on any suggestion
Reply with feedback, questions, or to request a fix. Tag @cubic-dev-ai to re-run a review.
15a027e to
7122b0f
Compare
Author
|
I have read the CLA Document and I hereby sign the CLA |
…evel autocompletion - Add qwenMultifileFimTemplate supporting repository-level context - Uses <|repo_name|>, <|file_sep|> tokens for multi-file context - Falls back to basic FIM when no snippets provided - Resolves issue continuedev#3589
7122b0f to
a8ac197
Compare
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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.
Summary
qwenMultifileFimTemplatesupporting repository-level autocompletion for Qwen models<|repo_name|>,<|file_sep|>tokens for multi-file contextChanges
qwenMultifileFimTemplateincore/autocomplete/templating/AutocompleteTemplate.tsgetTemplateForModelto use the new template for Qwen Coder modelsDescription
This PR implements the Qwen multi-file FIM template as requested in issue #3589. The template supports:
<|file_sep|>token to separate multiple file contents<|fim_prefix|>,<|fim_suffix|>,<|fim_middle|>tokensThe implementation follows the pattern established by
codestralMultifileFimTemplateand is based on the code snippet provided in the issue.Testing
Continue Tasks:▶️ 2 queued · ▶️ 7 not started · ✅ 6 no changes — View all
Summary by cubic
Added a Qwen multi-file FIM template for repository-level autocompletion and set it as the default for Qwen Coder models. Falls back to basic FIM when no snippets are provided.
Written for commit a8ac197. Summary will update on new commits.
I have read the CLA Document and I hereby sign the CLA