8000 Add claude 4 models and set sonnet 4 to default anthropic model by rahulkarajgikar · Pull Request #119 · truffle-ai/saiki · GitHub
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content

Add claude 4 models and set sonnet 4 to default anthropic model #119

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

Jump to bottom
Merged
merged 1 commit into from
May 23, 2025
Merged

Add claude 4 models and set sonnet 4 to default anthropic model #119

merged 1 commit into from
May 23, 2025

Conversation

rahulkarajgikar
Copy link
Collaborator
@rahulkarajgikar rahulkarajgikar commented May 23, 2025 •
edited by coderabbitai bot
Loading

tested with:

saiki -m claude-4-opus-20250514 "hello"
saiki -m claude-4-sonnet-20250514 "hello"

both worked

logs:

[  9:17PM ]  [ karaj@MacBook-Pro:~/Projects/saiki/configuration(main✗) ]
 $ saiki -m claude-4-opus-20250514 "hello"
21:17:59 INFO: Initializing Saiki with config: /Users/karaj/Projects/sa
8000
iki/configuration/saiki.yml
21:17:59 INFO: New agent configuration loaded and validated.
21:17:59 INFO: Attempting to connect to new server 'filesystem'...
21:17:59 INFO: =======================================
21:17:59 INFO: MCP SERVER: npx -y @modelcontextprotocol/server-filesystem .
21:17:59 INFO: Environment:
21:17:59 INFO: =======================================

21:17:59 INFO: Connecting to MCP server: "filesystem" (npx -y @modelcontextprotocol/server-filesystem .)
21:17:59 INFO: Establishing connection...
21:17:59 INFO: Attempting to connect to new server 'puppeteer'...
21:17:59 INFO: =======================================
21:17:59 INFO: MCP SERVER: npx -y @truffle-ai/puppeteer-server
21:17:59 INFO: Environment:
21:17:59 INFO: =======================================

21:17:59 INFO: Connecting to MCP server: "puppeteer" (npx -y @truffle-ai/puppeteer-server)
21:17:59 INFO: Establishing connection...
21:17:59 INFO: Attempting to connect to new server 'hf'...
21:17:59 INFO: =======================================
21:17:59 INFO: MCP SERVER: npx -y @llmindset/mcp-hfspace
21:17:59 INFO: Environment:
21:17:59 INFO: =======================================

21:17:59 INFO: Connecting to MCP server: "hf" (npx -y @llmindset/mcp-hfspace)
21:17:59 INFO: Establishing connection...
Secure MCP Filesystem Server running on stdio
Allowed directories: [ '/Users/karaj/Projects/saiki/configuration' ]
21:18:00 INFO: ✅ Stdio SERVER "filesystem" (npx -y @modelcontextprotocol/server-filesystem .) SPAWNED
21:18:00 INFO: Connection established!


21:18:00 INFO: Registered client: filesystem
21:18:00 INFO: Successfully connected and cached new server 'filesystem'
21:18:00 INFO: ✅ Stdio SERVER "puppeteer" (npx -y @truffle-ai/puppeteer-server) SPAWNED
21:18:00 INFO: Connection established!


21:18:00 INFO: Registered client: puppeteer
21:18:00 INFO: Successfully connected and cached new server 'puppeteer'
21:18:01 INFO: ✅ Stdio SERVER "hf" (npx -y @llmindset/mcp-hfspace) SPAWNED
21:18:01 INFO: Connection established!


21:18:01 INFO: Registered client: hf
21:18:01 INFO: Successfully connected and cached new server 'hf'
21:18:01 INFO: Agent using model config: {
  "router": "vercel",
  "provider": "anthropic",
  "model": {
    "specificationVersion": "v1",
    "defaultObjectGenerationMode": "tool",
    "supportsImageUrls": true,
    "modelId": "claude-4-opus-20250514",
    "settings": {},
    "config": {
      "provider": "anthropic.messages",
      "baseURL": "https://api.anthropic.com/v1"
    }
  },
  "configuredMaxTokens": 200000,
  "modelMaxTokens": 200000
}
21:18:01 INFO: SaikiAgent initialized.
21:18:01 INFO: Connected servers: 3
21:18:01 INFO: Setting up CLI event subscriptions...
21:18:01 INFO: Loading available tools...
21:18:01 INFO: Loaded 26 tools from 3 MCP servers
21:18:01 INFO: CLI initialized successfully. Ready for input.
21:18:01 INFO: AI thinking...
┌─────────────────── 🤖 AI Response ───────────────────┐
│                                                      │
│   Hello! I'm Saiki, your helpful AI assistant. I     │
│   have access to various tools that can help you     │
│   with tasks like:                                   │
│                                                      │
│   - File operations (reading, writing, editing       │
│   files)                                             │
│   - Web browsing and interaction (navigating         │
│   websites, clicking buttons, filling forms,         │
│   downloading files)                                 │
│   - Image generation using FLUX.1-schnell            │
│   - Searching for Hugging Face Spaces                │
│   - And more!                                        │
│                                                      │
│   How can I help you today?                          │
│                                                      │
└──────────────────────────────────────────────────────┘
[  9:18PM ]  [ karaj@MacBook-Pro:~/Projects/saiki/configuration(main✗) ]

Summary by CodeRabbit

  • New Features
    • Added new Anthropic models: Claude 4 Opus (20250514) and Claude 4 Sonnet (20250514), both supporting up to 200,000 tokens.
    • Set Claude 4 Sonnet (20250514) as the new default model for Anthropic.

@coderabbitai coderabbitai
Copy link
coderabbitai bot commented May 23, 2025 •
edited
Loading

Caution

Review failed

The pull request is closed.

Walkthrough

The update revises the LLM_REGISTRY constant by adding two new Anthropic models, claude-4-opus-20250514 and claude-4-sonnet-20250514, each with a maxTokens of 200000. The new claude-4-sonnet-20250514 model is set as the default, replacing the previous default.

Changes

File(s) Change Summary
src/core/ai/llm/registry.ts Added two new Anthropic models (claude-4-opus-20250514, claude-4-sonnet-20250514), updated default.

Poem

Two new models join the list,
With tokens tall as a mountain mist.
Sonnet now wears the default crown,
While Opus, too, comes hopping down.
Rabbits cheer with every byte—
The future of prompts is looking bright!
🐰✨

Warning

There were issues while running some tools. Please review the errors and either fix the tool's configuration or disable the tool if it's a critical failure.

🔧 ESLint

If the error stems from missing dependencies, add them to the package.json file. For unrecoverable errors (e.g., due to private dependencies), disable the tool in the CodeRabbit configuration.

npm warn config production Use --omit=dev instead.
npm error Exit handler never called!
npm error This is an error with npm itself. Please report this error at:
npm error https://github.com/npm/cli/issues
npm error A complete log of this run can be found in: /.npm/_logs/2025-05-23T04_21_28_480Z-debug-0.log

📜 Recent review details

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

📥 Commits

Reviewing files that changed from the base of the PR and between f71534e and ed05971.

📒 Files selected for processing (1)
  • src/core/ai/llm/registry.ts (1 hunks)
✨ Finishing Touches
  • 📝 Generate Docstrings

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share
🪧 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.
    • Explain this complex logic.
    • 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 explain this code block.
    • @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 explain its main purpose.
    • @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.

Support

Need help? Create a ticket on our support page for assistance with any issues or questions.

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.
  • @coderabbitai generate sequence diagram to generate a sequence diagram of the changes in this PR.
  • @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.

@rahulkarajgikar rahulkarajgikar merged commit 68e0be9 into truffle-ai:main May 23, 2025
1 check was pending
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers
No reviews
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
1 participant
@rahulkarajgikar
0