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

claude 3.7 support #6293

Merged
merged 1 commit into from
Feb 26, 2025
Merged

claude 3.7 support #6293

merged 1 commit into from
Feb 26, 2025

Conversation

hyiip
Copy link
Contributor

@hyiip hyiip commented Feb 24, 2025

πŸ’» ε˜ζ›΄η±»εž‹ | Change Type

  • feat
  • fix
  • refactor
  • perf
  • style
  • test
  • docs
  • ci
  • chore
  • build

πŸ”€ ε˜ζ›΄θ―΄ζ˜Ž | Description of Change

Add support to claude 3.7 sonnet 20250219 version.

πŸ“ θ‘₯充俑息 | Additional Information

Summary by CodeRabbit

  • New Features
    • Expanded the list of available models by adding two advanced options in the Anthropic series, giving users access to the latest enhancements.

Copy link

vercel bot commented Feb 24, 2025

@hyiip is attempting to deploy a commit to the NextChat Team on Vercel.

A member of the Team first needs to authorize it.

Copy link
Contributor

coderabbitai bot commented Feb 24, 2025

Walkthrough

The pull request updates the constant configuration by adding two new entries to the Anthropic models array. Specifically, the models "claude-3-7-sonnet-20250219" and "claude-3-7-sonnet-latest" have been appended to the anthropicModels array in app/constant.ts. The existing entries remain unchanged, and no further modifications to the code or interface declarations have been introduced.

Changes

File Change Summary
app/constant.ts Added two new models ("claude-3-7-sonnet-20250219" and "claude-3-7-sonnet-latest") to the anthropicModels array.

Poem

In my burrow of code, I happily bound,
Two fresh models hopping softly around.
They join the team with a gentle new beat,
Making the Anthropic list ever so complete.
With a twitch of my nose, I celebrate this feat!

✨ Finishing Touches
  • πŸ“ Generate Docstrings (Beta)

Thank you for using CodeRabbit. We offer it for free to the OSS community and would appreciate your support in helping us grow. If you find it useful, would you consider giving us a shout-out on your favorite social media?

❀️ Share
πŸͺ§ Tips

Chat

There are 3 ways to chat with CodeRabbit:

  • Review comments: Directly reply to a review comment made by CodeRabbit. Example:
    • I pushed a fix in commit <commit_id>, please review it.
    • Generate unit testing code for this file.
    • Open a follow-up GitHub issue for this discussion.
  • Files and specific lines of code (under the "Files changed" tab): Tag @coderabbitai in a new review comment at the desired location with your query. Examples:
    • @coderabbitai generate unit testing code for this file.
    • @coderabbitai modularize this function.
  • PR comments: Tag @coderabbitai in a new PR comment to ask questions about the PR branch. For the best results, please provide a very specific query, as very limited context is provided in this mode. Examples:
    • @coderabbitai gather interesting stats about this repository and render them as a table. Additionally, render a pie chart showing the language distribution in the codebase.
    • @coderabbitai read src/utils.ts and generate unit testing code.
    • @coderabbitai read the files in the src/scheduler package and generate a class diagram using mermaid and a README in the markdown format.
    • @coderabbitai help me debug CodeRabbit configuration file.

Note: Be mindful of the bot's finite context window. It's strongly recommended to break down tasks such as reading entire modules into smaller chunks. For a focused discussion, use review comments to chat about specific files and their changes, instead of using the PR comments.

CodeRabbit Commands (Invoked using PR comments)

  • @coderabbitai pause to pause the reviews on a PR.
  • @coderabbitai resume to resume the paused reviews.
  • @coderabbitai review to trigger an incremental review. This is useful when automatic reviews are disabled for the repository.
  • @coderabbitai full review to do a full review from scratch and review all the files again.
  • @coderabbitai summary to regenerate the summary of the PR.
  • @coderabbitai generate docstrings to generate docstrings for this PR. (Beta)
  • @coderabbitai resolve resolve all the CodeRabbit review comments.
  • @coderabbitai configuration to show the current CodeRabbit configuration for the repository.
  • @coderabbitai help to get help.

Other keywords and placeholders

  • Add @coderabbitai ignore anywhere in the PR description to prevent this PR from being reviewed.
  • Add @coderabbitai summary to generate the high-level summary at a specific location in the PR description.
  • Add @coderabbitai anywhere in the PR title to generate the title automatically.

CodeRabbit Configuration File (.coderabbit.yaml)

  • You can programmatically configure CodeRabbit by adding a .coderabbit.yaml file to the root of your repository.
  • Please see the configuration documentation for more information.
  • If your editor has YAML language server enabled, you can add the path at the top of this file to enable auto-completion and validation: # yaml-language-server: $schema=https://coderabbit.ai/integrations/schema.v2.json

Documentation and Community

  • Visit our Documentation for detailed information on how to use CodeRabbit.
  • Join our Discord Community to get help, request features, and share feedback.
  • Follow us on X/Twitter for updates and announcements.

Copy link
Contributor

@coderabbitai coderabbitai bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Actionable comments posted: 1

πŸ”­ Outside diff range comments (1)
app/constant.ts (1)

410-433: πŸ› οΈ Refactor suggestion

Add knowledge cutoff dates for the new Claude models.

The knowledge cutoff dates for the new Claude 3.7 models are missing in the KnowledgeCutOffDate record. This information is important for the system template and model behavior.

Add the following entries:

 export const KnowledgeCutOffDate: Record<string, string> = {
   default: "2021-09",
+  "claude-3-7-sonnet-20250219": "2024-12",
+  "claude-3-7-sonnet-latest": "2024-12",
   "gpt-4-turbo": "2023-12",
πŸ“œ Review details

Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro

πŸ“₯ Commits

Reviewing files that changed from the base of the PR and between f5f3ce9 and f3154b2.

πŸ“’ Files selected for processing (1)
  • app/constant.ts (1 hunks)

Comment on lines +538 to +539
"claude-3-7-sonnet-20250219",
"claude-3-7-sonnet-latest",
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

πŸ’‘ Verification agent

🧩 Analysis chain

Verify the model version date.

The model additions follow the correct naming convention and are properly placed in the array. However, the version date "20250219" appears to be in the future (February 19, 2025).


🌐 Web query:

What is the latest version of Claude 3.7?

πŸ’‘ Result:

The latest version is Claude 3.7 Sonnet, released by Anthropic on February 24, 2025[1][4][6]. This model introduces several groundbreaking features:

Key capabilities

  • Hybrid reasoning: Combines rapid responses with extended "chain of thought" reasoning in a single model[1][4]. Users can toggle an "extended thinking mode" for complex tasks[2][4].
  • Visible thought process: Displays raw reasoning steps during problem-solving (with safety filters for sensitive content)[2][6].
  • Enhanced computer interaction:
    • Sustained agentic capabilities for tasks like software testing and process automation[2][3]
    • Improved performance on OSWorld benchmarks for AI agents[2]
    • Demonstrated ability to play complex games like PokΓ©mon Red through thousands of interactions[2]

Developer features

  • Available via API on Vertex AI with enterprise-grade reliability[1]
  • New coding tool Claude Code (limited preview) for terminal-based development tasks[1][4]
  • Cost optimization through batch predictions (50% savings) and prompt caching[1]

This release maintains Anthropic's ASL-2 safety classification while introducing new safeguards for visible reasoning traces and computer use capabilities[2][6].

Citations:


Action Required: Update model version and add missing cutoff dates.

  • The new Claude 3.7 Sonnet models are correctly named and placed.
  • However, the version tag "claude-3-7-sonnet-20250219" does not match the official release date. According to the latest release information, the official date is February 24, 2025. Please update the version string accordingly (e.g., "claude-3-7-sonnet-20250224").
  • Additionally, ensure that the KnowledgeCutOffDate record (lines 410-433) includes entries for these newly added models.

@Leizhenpeng Leizhenpeng merged commit 2167076 into ChatGPTNextWeb:main Feb 26, 2025
1 check failed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants