WIP: feat: Add ClaudeMessages relay support for volcengine doubao#287
Open
gkzhb wants to merge 1 commit intoLaisky:mainfrom
Open
WIP: feat: Add ClaudeMessages relay support for volcengine doubao#287gkzhb wants to merge 1 commit intoLaisky:mainfrom
gkzhb wants to merge 1 commit intoLaisky:mainfrom
Conversation
📝 WalkthroughWalkthroughTwo files modified: one extends the Doubao adaptor to route Claude Messages requests to appropriate endpoints based on model name, the other refines thinking content handling in Claude SSE stream conversion using preference and fallback logic. Changes
Estimated code review effort🎯 2 (Simple) | ⏱️ ~10 minutes Poem
🚥 Pre-merge checks | ✅ 2 | ❌ 1❌ Failed checks (1 warning)
✅ Passed checks (2 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing touches
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. Comment |
gkzhb
changed the title
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 0
🧹 Nitpick comments (1)
relay/adaptor/doubao/main.go (1)
22-27: Consider refactoring to eliminate code duplication.The ClaudeMessages case duplicates the exact logic from the ChatCompletions case (lines 16-19). If the routing logic needs to change in the future, both cases must be updated, increasing maintenance burden.
🔎 Proposed refactor to reduce duplication
func GetRequestURL(meta *meta.Meta) (string, error) { switch meta.Mode { - case relaymode.ChatCompletions: - if strings.HasPrefix(meta.ActualModelName, "bot") { - return fmt.Sprintf("%s/api/v3/bots/chat/completions", meta.BaseURL), nil - } - return fmt.Sprintf("%s/api/v3/chat/completions", meta.BaseURL), nil + case relaymode.ChatCompletions, relaymode.ClaudeMessages: + // 豆包支持 Claude Messages API 格式，转换为 ChatCompletions 处理 + if strings.HasPrefix(meta.ActualModelName, "bot") { + return fmt.Sprintf("%s/api/v3/bots/chat/completions", meta.BaseURL), nil + } + return fmt.Sprintf("%s/api/v3/chat/completions", meta.BaseURL), nil case relaymode.Embeddings: return fmt.Sprintf("%s/api/v3/embeddings", meta.BaseURL), nil - case relaymode.ClaudeMessages: - // 豆包支持 Claude Messages API 格式，转换为 ChatCompletions 处理 - if strings.HasPrefix(meta.ActualModelName, "bot") { - return fmt.Sprintf("%s/api/v3/bots/chat/completions", meta.BaseURL), nil - } - return fmt.Sprintf("%s/api/v3/chat/completions", meta.BaseURL), nil default: } return "", errors.Errorf("unsupported relay mode %d for doubao", meta.Mode)
📜 Review details
Configuration used: defaults
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (2)
relay/adaptor/doubao/main.gorelay/adaptor/openai_compatible/claude_convert.go
🧰 Additional context used
🧠 Learnings (7)
📓 Common learnings
Learnt from: CR
Repo: Laisky/one-api PR: 0
File: .github/instructions/memory.instructions.md:0-0
Timestamp: 2025-10-27T15:08:58.269Z
Learning: Applies to relay/adaptor/openai_compatible/claude_messages.go : Use ctxkey.ClaudeMessagesConversion and ctxkey.OriginalClaudeRequest to keep streaming, quota reconciliation, and logging aligned during Claude Messages conversions
Learnt from: CR
Repo: Laisky/one-api PR: 0
File: .github/instructions/memory.instructions.md:0-0
Timestamp: 2025-10-27T15:08:58.269Z
Learning: Applies to relay/adaptor/openai_compatible/claude_messages.go : Implement ConvertClaudeRequest to map Claude Messages to OpenAI ChatCompletion and HandleClaudeMessagesResponse to reverse-map responses
📚 Learning: 2025-10-27T15:08:58.269Z
Learnt from: CR
Repo: Laisky/one-api PR: 0
File: .github/instructions/memory.instructions.md:0-0
Timestamp: 2025-10-27T15:08:58.269Z
Learning: Applies to relay/adaptor/openai_compatible/claude_messages.go : Implement ConvertClaudeRequest to map Claude Messages to OpenAI ChatCompletion and HandleClaudeMessagesResponse to reverse-map responses
Applied to files:
relay/adaptor/doubao/main.gorelay/adaptor/openai_compatible/claude_convert.go
📚 Learning: 2025-10-27T15:08:58.269Z
Learnt from: CR
Repo: Laisky/one-api PR: 0
File: .github/instructions/memory.instructions.md:0-0
Timestamp: 2025-10-27T15:08:58.269Z
Learning: Applies to relay/adaptor/openai_compatible/claude_messages.go : Use ctxkey.ClaudeMessagesConversion and ctxkey.OriginalClaudeRequest to keep streaming, quota reconciliation, and logging aligned during Claude Messages conversions
Applied to files:
relay/adaptor/doubao/main.gorelay/adaptor/openai_compatible/claude_convert.go
📚 Learning: 2025-10-27T15:08:58.269Z
Learnt from: CR
Repo: Laisky/one-api PR: 0
File: .github/instructions/memory.instructions.md:0-0
Timestamp: 2025-10-27T15:08:58.269Z
Learning: Applies to relay/adaptor/openai_compatible/claude_messages.go : Consider gating structured-output promotion per provider/model to avoid empty or missing structured outputs for specific upstreams (e.g., Azure gpt-5-nano, OpenAI gpt-5-mini streaming Claude, DeepSeek Response structured)
Applied to files:
relay/adaptor/doubao/main.gorelay/adaptor/openai_compatible/claude_convert.go
📚 Learning: 2025-10-27T15:08:58.269Z
Learnt from: CR
Repo: Laisky/one-api PR: 0
File: .github/instructions/memory.instructions.md:0-0
Timestamp: 2025-10-27T15:08:58.269Z
Learning: Applies to relay/adaptor/openai_compatible/claude_messages.go : Structured-output promotion to response_format=json_schema only when all conditions pass: one tool with additionalProperties=false; no existing tool_use/tool_result; tool_choice matches name case-insensitively; description or text references JSON/structured/schema semantics. When promoted, drop tools/tool_choice, set strict=true, and treat as structured output
Applied to files:
relay/adaptor/doubao/main.go
📚 Learning: 2025-10-27T15:08:58.269Z
Learnt from: CR
Repo: Laisky/one-api PR: 0
File: .github/instructions/memory.instructions.md:0-0
Timestamp: 2025-10-27T15:08:58.269Z
Learning: Applies to relay/adaptor/openai_compatible/*_test.go : Maintain regression tests for structured-output promotion: TestConvertClaudeRequest_StructuredToolPromoted and TestConvertClaudeRequest_ToolNotPromoted
Applied to files:
relay/adaptor/doubao/main.gorelay/adaptor/openai_compatible/claude_convert.go
📚 Learning: 2025-10-27T15:08:58.269Z
Learnt from: CR
Repo: Laisky/one-api PR: 0
File: .github/instructions/memory.instructions.md:0-0
Timestamp: 2025-10-27T15:08:58.269Z
Learning: Applies to relay/controller/response.go : ConvertResponseAPIToChatCompletionRequest for non-OpenAI channels, execute as ChatCompletions, then rewrap via ctxkey.ResponseRewriteHandler; ensure text-only collapses to a single string message and multimodal stays structured; tool definitions, reasoning config, and JSON schema must round-trip
Applied to files:
relay/adaptor/doubao/main.go
🧬 Code graph analysis (2)
relay/adaptor/doubao/main.go (1)
common/ctxkey/key.go (1)
BaseURL(144-144)
relay/adaptor/openai_compatible/claude_convert.go (2)
relay/adaptor/anthropic/model.go (1)
Delta(116-124)relay/model/general.go (1)
Thinking(179-182)
🔇 Additional comments (1)
relay/adaptor/openai_compatible/claude_convert.go (1)
264-302: LGTM! Thinking content fallback logic correctly addresses the PR objective.The change implements a proper preference-and-fallback pattern:
- Prefers
Delta.Thinkingwhen available and non-empty- Falls back to
Delta.ReasoningContentwhenThinkingis absent- Only emits thinking blocks when content is non-empty
This correctly addresses the issue mentioned in the PR title where thinking_delta was not being returned. The resolved
thinkingContentvariable is safely dereferenced on line 289 because the guard on line 272 ensures it's non-nil and non-empty.
gkzhb
changed the title
Owner
|
Are you still working on it, or do you need my help? |
Author
|
I'm still working on this pr, and any guidance would be welcome. |
Owner
Could you provide a request body that will cause the error? This would be very helpful for fixing the issue and for testing. |
Author
|
Request path is {
"model": "kimi-k2-thinking-251104",
"max_tokens": 32000,
"system": [],
"messages": [
{
"role": "user",
"content": [
{
"type": "text",
"text": "hi",
"cache_control": {
"type": "ephemeral"
}
}
]
}
],
"tools": [
{
"name": "bash",
"description": "Executes a given bash command in a persistent shell session with optional timeout, ensuring proper handling and security measures.\n\nAll commands run in /data00/home/zhanghaibin.zhb/gitrep/one-api by default. Use the `workdir` parameter if you need to run a command in a different directory. AVOID using `cd <directory> && <command>` patterns - use `workdir` instead.\n\nIMPORTANT: This tool is for terminal operations like git, npm, docker, etc. DO NOT use it for file operations (reading, writing, editing, searching, finding files) - use the specialized tools for this instead.\n\nBefore executing the command, please follow these steps:\n\n1. Directory Verification:\n - If the command will create new directories or files, first use `ls` to verify the parent directory exists and is the correct location\n - For example, before running \"mkdir foo/bar\", first use `ls foo` to check that \"foo\" exists and is the intended parent directory\n\n2. Command Execution:\n - Always quote file paths that contain spaces with double quotes (e.g., rm \"path with spaces/file.txt\")\n - Examples of proper quoting:\n - mkdir \"/Users/name/My Documents\" (correct)\n - mkdir /Users/name/My Documents (incorrect - will fail)\n - python \"/path/with spaces/script.py\" (correct)\n - python /path/with spaces/script.py (incorrect - will fail)\n - After ensuring proper quoting, execute the command.\n - Capture the output of the command.\n\nUsage notes:\n - The command argument is required.\n - You can specify an optional timeout in milliseconds (up to 600000ms / 10 minutes). If not specified, commands will time out after 120000ms (2 minutes).\n - It is very helpful if you write a clear, concise description of what this command does in 5-10 words.\n - If the output exceeds 30000 characters, output will be truncated before being returned to you.\n - You can use the `run_in_background` parameter to run the command in the background, which allows you to continue working while the command runs. You can monitor the output using the Bash tool as it becomes available. You do not need to use '&' at the end of the command when using this parameter.\n\n - Avoid using Bash with the `find`, `grep`, `cat`, `head`, `tail`, `sed`, `awk`, or `echo` commands, unless explicitly instructed or when these commands are truly necessary for the task. Instead, always prefer using the dedicated tools for these commands:\n - File search: Use Glob (NOT find or ls)\n - Content search: Use Grep (NOT grep or rg)\n - Read files: Use Read (NOT cat/head/tail)\n - Edit files: Use Edit (NOT sed/awk)\n - Write files: Use Write (NOT echo >/cat <<EOF)\n - Communication: Output text directly (NOT echo/printf)\n - When issuing multiple commands:\n - If the commands are independent and can run in parallel, make multiple Bash tool calls in a single message. For example, if you need to run \"git status\" and \"git diff\", send a single message with two Bash tool calls in parallel.\n - If the commands depend on each other and must run sequentially, use a single Bash call with '&&' to chain them together (e.g., `git add . && git commit -m \"message\" && git push`). For instance, if one operation must complete before another starts (like mkdir before cp, Write before Bash for git operations, or git add before git commit), run these operations sequentially instead.\n - Use ';' only when you need to run commands sequentially but don't care if earlier commands fail\n - DO NOT use newlines to separate commands (newlines are ok in quoted strings)\n - AVOID using `cd <directory> && <command>`. Use the `workdir` parameter to change directories instead.\n <good-example>\n Use workdir=\"/foo/bar\" with command: pytest tests\n </good-example>\n <bad-example>\n cd /foo/bar && pytest tests\n </bad-example>\n\n# Committing changes with git\n\nOnly create commits when requested by the user. If unclear, ask first. When the user asks you to create a new git commit, follow these steps carefully:\n\nGit Safety Protocol:\n- NEVER update the git config\n- NEVER run destructive/irreversible git commands (like push --force, hard reset, etc) unless the user explicitly requests them\n- NEVER skip hooks (--no-verify, --no-gpg-sign, etc) unless the user explicitly requests it\n- NEVER run force push to main/master, warn the user if they request it\n- Avoid git commit --amend. ONLY use --amend when ALL conditions are met:\n (1) User explicitly requested amend, OR commit SUCCEEDED but pre-commit hook auto-modified files that need including\n (2) HEAD commit was created by you in this conversation (verify: git log -1 --format='%an %ae')\n (3) Commit has NOT been pushed to remote (verify: git status shows \"Your branch is ahead\")\n- CRITICAL: If commit FAILED or was REJECTED by hook, NEVER amend - fix the issue and create a NEW commit\n- CRITICAL: If you already pushed to remote, NEVER amend unless user explicitly requests it (requires force push)\n- NEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked, otherwise the user will feel that you are being too proactive.\n\n1. You can call multiple tools in a single response. When multiple independent pieces of information are requested and all commands are likely to succeed, run multiple tool calls in parallel for optimal performance. run the following bash commands in parallel, each using the Bash tool:\n - Run a git status command to see all untracked files.\n - Run a git diff command to see both staged and unstaged changes that will be committed.\n - Run a git log command to see recent commit messages, so that you can follow this repository's commit message style.\n2. Analyze all staged changes (both previously staged and newly added) and draft a commit message:\n - Summarize the nature of the changes (eg. new feature, enhancement to an existing feature, bug fix, refactoring, test, docs, etc.). Ensure the message accurately reflects the changes and their purpose (i.e. \"add\" means a wholly new feature, \"update\" means an enhancement to an existing feature, \"fix\" means a bug fix, etc.).\n - Do not commit files that likely contain secrets (.env, credentials.json, etc.). Warn the user if they specifically request to commit those files\n - Draft a concise (1-2 sentences) commit message that focuses on the \"why\" rather than the \"what\"\n - Ensure it accurately reflects the changes and their purpose\n3. You can call multiple tools in a single response. When multiple independent pieces of information are requested and all commands are likely to succeed, run multiple tool calls in parallel for optimal performance. run the following commands:\n - Add relevant untracked files to the staging area.\n - Create the commit with a message\n - Run git status after the commit completes to verify success.\n Note: git status depends on the commit completing, so run it sequentially after the commit.\n4. If the commit fails due to pre-commit hook, fix the issue and create a NEW commit (see amend rules above)\n\nImportant notes:\n- NEVER run additional commands to read or explore code, besides git bash commands\n- NEVER use the TodoWrite or Task tools\n- DO NOT push to the remote repository unless the user explicitly asks you to do so\n- IMPORTANT: Never use git commands with the -i flag (like git rebase -i or git add -i) since they require interactive input which is not supported.\n- If there are no changes to commit (i.e., no untracked files and no modifications), do not create an empty commit\n\n# Creating pull requests\nUse the gh command via the Bash tool for ALL GitHub-related tasks including working with issues, pull requests, checks, and releases. If given a Github URL use the gh command to get the information needed.\n\nIMPORTANT: When the user asks you to create a pull request, follow these steps carefully:\n\n1. You can call multiple tools in a single response. When multiple independent pieces of information are requested and all commands are likely to succeed, run multiple tool calls in parallel for optimal performance. run the following bash commands in parallel using the Bash tool, in order to understand the current state of the branch since it diverged from the main branch:\n - Run a git status command to see all untracked files\n - Run a git diff command to see both staged and unstaged changes that will be committed\n - Check if the current branch tracks a remote branch and is up to date with the remote, so you know if you need to push to the remote\n - Run a git log command and `git diff [base-branch]...HEAD` to understand the full commit history for the current branch (from the time it diverged from the base branch)\n2. Analyze all changes that will be included in the pull request, making sure to look at all relevant commits (NOT just the latest commit, but ALL commits that will be included in the pull request!!!), and draft a pull request summary\n3. You can call multiple tools in a single response. When multiple independent pieces of information are requested and all commands are likely to succeed, run multiple tool calls in parallel for optimal performance. run the following commands in parallel:\n - Create new branch if needed\n - Push to remote with -u flag if needed\n - Create PR using gh pr create with the format below. Use a HEREDOC to pass the body to ensure correct formatting.\n<example>\ngh pr create --title \"the pr title\" --body \"$(cat <<'EOF'\n## Summary\n<1-3 bullet points>\n</example>\n\nImportant:\n- DO NOT use the TodoWrite or Task tools\n- Return the PR URL when you're done, so the user can see it\n\n# Other common operations\n- View comments on a Github PR: gh api repos/foo/bar/pulls/123/comments\n",
"input_schema": {
"$schema": "https://json-schema.org/draft/2020-12/schema",
"type": "object",
"properties": {
"command": {
"description": "The command to execute",
"type": "string"
},
"timeout": {
"description": "Optional timeout in milliseconds",
"type": "number"
},
"workdir": {
"description": "The working directory to run the command in. Defaults to /data00/home/zhanghaibin.zhb/gitrep/one-api. Use this instead of 'cd' commands.",
"type": "string"
},
"description": {
"description": "Clear, concise description of what this command does in 5-10 words. Examples:\nInput: ls\nOutput: Lists files in current directory\n\nInput: git status\nOutput: Shows working tree status\n\nInput: npm install\nOutput: Installs package dependencies\n\nInput: mkdir foo\nOutput: Creates directory 'foo'",
"type": "string"
}
},
"required": [
"command",
"description"
],
"additionalProperties": false
}
}
],
"tool_choice": {
"type": "auto"
},
"stream": true
} |
Author
|
I may need to split this PR into two separate ones:
|
gkzhb
changed the title
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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.
TODOs:
Summary by CodeRabbit
New Features
Bug Fixes
✏️ Tip: You can customize this high-level summary in your review settings.