You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
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
The commented out section about 'Working with large PRs' should either be properly uncommented if needed or removed entirely to maintain documentation clarity
[//]: #(## Working with large PRs)[//]: #()[//]: #(The default mode of CodiumAI is to have a single call per tool, using GPT-4, which has a token limit of 8000 tokens.)[//]: #(This mode provides a very good speed-quality-cost tradeoff, and can handle most PRs successfully.)[//]: #(When the PR is above the token limit, it employs a [PR Compression strategy](../core-abilities/index.md).)[//]: #()[//]: #(However, for very large PRs, or in case you want to emphasize quality over speed and cost, there are two possible solutions:)[//]: #(1) [Use a model](https://qodo-merge-docs.qodo.ai/usage-guide/changing_a_model/) with larger context, like GPT-32K, or claude-100K. This solution will be applicable for all the tools.)[//]: #(2) For the `/improve` tool, there is an ['extended' mode](https://qodo-merge-docs.qodo.ai/tools/improve/)(`/improve --extended`),)[//]: #(which divides the PR into chunks, and processes each chunk separately. With this mode, regardless of the model, no compression will be done (but for large PRs, multiple model calls may occur))
Instead of commenting out the "Working with large PRs" section with HTML comments, consider using a more maintainable approach like a feature flag or configuration option to control the visibility of this section. If the content is truly deprecated, it should be removed entirely.
-[//]: # (## Working with large PRs)+<!-- TODO: Either remove this section entirely if deprecated, or uncomment if still relevant -->+<!-- ## Working with large PRs-[//]: # ()+The default mode of CodiumAI is to have a single call per tool, using GPT-4, which has a token limit of 8000 tokens. -->-[//]: # (The default mode of CodiumAI is to have a single call per tool, using GPT-4, which has a token limit of 8000 tokens.)-
Apply this suggestion
Suggestion importance[1-10]: 4
__
Why: The suggestion addresses a maintainability issue by recommending a cleaner way to handle commented-out documentation sections. While valid, the impact is relatively minor as it's primarily a documentation formatting concern.
Low
General
Improve documentation consistency and clarity
The code shows inconsistency in model references - it first states Claude-3.7-sonnet is default but then shows GPT-4o example first. Reorder the examples to match the stated default model and maintain consistency.
-To restrict Qodo Merge to using only `GPT-4o`, add this setting:+To restrict Qodo Merge to using only `claude-3-7-sonnet` (default), add this setting:
-To restrict Qodo Merge to using only `deepseek-r1` us-hosted, add this setting:
+To restrict Qodo Merge to using only `GPT-4o`, add this setting:
[To ensure code accuracy, apply this suggestion manually]
Suggestion importance[1-10]: 6
__
Why: The suggestion improves documentation clarity by reordering examples to match the stated default model (Claude-3.7-sonnet) and maintaining consistent presentation. This enhances readability and reduces potential confusion for users.
Low
Update
Author self-review: I have reviewed the PR code suggestions, and addressed the relevant ones.
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.
User description
…hout documentation
PR Type
Documentation
Description
Updated references to AI models across documentation.
Replaced outdated model names with current ones (e.g., Claude 3.7 Sonnet, o3-mini).
Clarified model selection and configuration in usage guides.
Improved consistency and accuracy in model-related descriptions.
Changes walkthrough 📝
9 files
Updated model references in introductory content.Updated model references for Chrome extension features.Updated model references in FAQ section.Updated model references in fine-tuning benchmark.Updated model references in local installation guide.Updated model references in PR Agent Pro overview.Simplified model references in tools documentation.Fixed typo and commented out outdated model-related content.Updated model references and configuration examples.