Skip to content

feat: support deepseek claude format (convert) - #1522

Merged
Calcium-Ion merged 1 commit into
alphafrom
support-deepseek-claude
Aug 7, 2025
Merged

feat: support deepseek claude format (convert)#1522
Calcium-Ion merged 1 commit into
alphafrom
support-deepseek-claude

Conversation

@Calcium-Ion

@Calcium-Ion Calcium-Ion commented Aug 7, 2025

Copy link
Copy Markdown
Member

Summary by CodeRabbit

  • Bug Fixes

    • Improved JSON output by omitting the server tool use field when not present.
    • Enhanced response handling to better manage finish reasons in streaming scenarios.
    • Expanded stop reason mapping for more accurate status reporting.
  • Refactor

    • Updated request conversion logic to delegate processing to a shared implementation, replacing a previous placeholder.

@coderabbitai

coderabbitai Bot commented Aug 7, 2025

Copy link
Copy Markdown
Contributor

Caution

Review failed

The pull request is closed.

Walkthrough

The changes update JSON serialization for a struct field to use omitempty, implement the ConvertClaudeRequest method in the Deepseek adaptor by delegating to the OpenAI adaptor, and refine control flow in OpenAI-to-Claude streaming response conversion, including expanded handling for stop reasons.

Changes

Cohort / File(s) Change Summary
ClaudeUsage JSON Serialization
dto/claude.go
Updated the ServerToolUse field's JSON tag in ClaudeUsage struct to use omitempty.
Deepseek Adaptor Claude Request Conversion
relay/channel/deepseek/adaptor.go
Implemented ConvertClaudeRequest by delegating to openai.Adaptor{}.ConvertClaudeRequest.
OpenAI-to-Claude Stream Response Logic
service/convert.go
Modified control flow for handling FinishReason and expanded stop reason mapping in conversion logic.

Sequence Diagram(s)

sequenceDiagram
    participant Client
    participant DeepseekAdaptor
    participant OpenAIAdaptor

    Client->>DeepseekAdaptor: ConvertClaudeRequest(ctx, relayInfo, claudeReq)
    DeepseekAdaptor->>OpenAIAdaptor: ConvertClaudeRequest(ctx, relayInfo, claudeReq)
    OpenAIAdaptor-->>DeepseekAdaptor: result, error
    DeepseekAdaptor-->>Client: result, error
Loading

Estimated code review effort

🎯 2 (Simple) | ⏱️ ~8 minutes

Possibly related PRs

Poem

A nibble here, a tweak just right,
Omitting fields that hide from sight.
Adaptor calls now pass the test,
With stop reasons handled at their best.
In code’s bright warren, changes hop—
This rabbit’s work will never stop! 🐇✨

Note

⚡️ Unit Test Generation is now available in beta!

Learn more here, or try it out under "Finishing Touches" below.


📜 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 3c4b1ef and 18c630e.

📒 Files selected for processing (3)
  • dto/claude.go (1 hunks)
  • relay/channel/deepseek/adaptor.go (1 hunks)
  • service/convert.go (2 hunks)
✨ Finishing Touches
  • 📝 Generate Docstrings
🧪 Generate unit tests
  • Create PR with unit tests
  • Post copyable unit tests in a comment
  • Commit unit tests in branch support-deepseek-claude

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.
  • 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.

Support

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

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 generate unit tests to generate unit tests for 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.

@Calcium-Ion
Calcium-Ion merged commit ba7325c into alpha Aug 7, 2025
1 of 2 checks passed
@liaokaime

Copy link
Copy Markdown

@Calcium-Ion 如何使用claude格式请求deepseek模型?在哪里设置,没看到呀

@Calcium-Ion

Copy link
Copy Markdown
Member Author

不用设置啊,直接请求就行了

@liaokaime

Copy link
Copy Markdown

不用设置啊,直接请求就行了

image @Calcium-Ion 我用exe启动new-api,设置了deepseek渠道,确认可用,用cherry studio的Anthropic连one-api,请求claude 4模型,提示不可用

@liaokaime

liaokaime commented Aug 8, 2025

Copy link
Copy Markdown

我明白了,是直接以claude的格式请求deepseek模型,模型名id要填deepseek的,如果要以"claude-sonnet-4-20250514"模型名请求openai的模型,则需要填模型重定向,并且要将"claude-sonnet-4-20250514"填入模型。openai转claude同理

{
 "claude-sonnet-4-20250514": "deepseek-chat"
}

@Calcium-Ion

Copy link
Copy Markdown
Member Author

我明白了,是直接以claude的格式请求deepseek模型,模型名id要填deepseek的,如果要以"claude-sonnet-4-20250514"模型名请求openai的模型,则需要填模型重定向,并且要将"claude-sonnet-4-20250514"填入模型。openai转claude同理

{
 "claude-sonnet-4-20250514": "deepseek-chat"
}

对的,是这样

@Calcium-Ion
Calcium-Ion deleted the support-deepseek-claude branch August 9, 2025 10:27
@liaokaime

Copy link
Copy Markdown

我明白了,是直接以claude的格式请求deepseek模型,模型名id要填deepseek的,如果要以"claude-sonnet-4-20250514"模型名请求openai的模型,则需要填模型重定向,并且要将"claude-sonnet-4-20250514"填入模型。openai转claude同理

{
 "claude-sonnet-4-20250514": "deepseek-chat"
}

对的,是这样

@Calcium-Ion 但似乎Azure Openai尚未支持转换为claude格式,我只能运行2个new-api服务,一个将azure openai转为openai,另一个从openai转为claude,有支持azure的计划吗?

@Calcium-Ion

Copy link
Copy Markdown
Member Author

我明白了,是直接以claude的格式请求deepseek模型,模型名id要填deepseek的,如果要以"claude-sonnet-4-20250514"模型名请求openai的模型,则需要填模型重定向,并且要将"claude-sonnet-4-20250514"填入模型。openai转claude同理

{
 "claude-sonnet-4-20250514": "deepseek-chat"
}

对的,是这样

@Calcium-Ion 但似乎Azure Openai尚未支持转换为claude格式,我只能运行2个new-api服务,一个将azure openai转为openai,另一个从openai转为claude,有支持azure的计划吗?

azure支持转claude,走的是openai的同一套逻辑,并且有问题提issue讨论,不要在这里讨论

@QuantumNous QuantumNous locked and limited conversation to collaborators Aug 10, 2025
Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants