Skip to content

claude 3.7 support #6293

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.

Sign up for GitHub

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

Merged
Leizhenpeng merged 1 commit into from
Feb 26, 2025
Merged

claude 3.7 support #6293

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 2 additions & 0 deletions app/constant.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -535,6 +535,8 @@ const anthropicModels = [
"claude-3-5-sonnet-20240620",
"claude-3-5-sonnet-20241022",
"claude-3-5-sonnet-latest",
"claude-3-7-sonnet-20250219",
"claude-3-7-sonnet-latest",
Comment on lines +538 to +539
Copy link
Contributor

@coderabbitai coderabbitai bot Feb 24, 2025

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.

];

const baiduModels = [
Expand Down
Loading