[codex] fix MiniMax OpenAI response formatting - #5896
Open
zhukangfeng wants to merge 4 commits into
Open
Conversation
Contributor
|
No actionable comments were generated in the recent review. 🎉 ℹ️ Recent review info⚙️ Run configurationConfiguration used: Organization UI Review profile: CHILL Plan: Pro Plus Run ID: 📒 Files selected for processing (1)
🚧 Files skipped from review as they are similar to previous changes (1)
WalkthroughMiniMax chat-completions routing now targets ChangesMiniMax routing and sanitization documentation
Estimated code review effort: 2 (Simple) | ~10 minutes Poem
🚥 Pre-merge checks | ✅ 4 | ❌ 1❌ Failed checks (1 warning)
✅ Passed checks (4 passed)
✨ Finishing Touches🧪 Generate unit tests (beta)
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 |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
Actionable comments posted: 1
🧹 Nitpick comments (1)
relay/channel/minimax/adaptor_test.go (1)
189-236: 📐 Maintainability & Code Quality | 🔵 Trivial | 💤 Low valueStreaming test doesn't cover top-level
base_resp/input_sensitivestripping for the final SSE chunk.The non-stream test checks
input_sensitive,output_sensitive,service_tier, andbase_respare stripped, but the streaming test only checksmessage/name/audio_content. MiniMax streaming responses commonly attachbase_respon the final chunk too; consider adding that assertion for full parity with issue#5834's requirement covering both paths.🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@relay/channel/minimax/adaptor_test.go` around lines 189 - 236, The streaming coverage in TestDoResponseForOpenAIStreamStripsMiniMaxFieldsAndMessage is missing the final SSE chunk stripping checks that are already validated in the non-stream path. Update this test to assert the final chunk also removes MiniMax-specific top-level fields like base_resp and input_sensitive, alongside the existing message/name/audio_content checks, so DoResponse stays consistent across stream and non-stream responses.
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@docs/superpowers/plans/2026-07-04-minimax-openai-response-sanitize.md`:
- Around line 13-87: The document outline skips levels by going from the
top-level title straight to the task sections, triggering the markdown heading
hierarchy warning. Update the task headings under the main plan so they are all
one level lower than the title (or add an intermediate parent heading) and keep
the rest of the section structure consistent. Apply this to the Task 1/Task
2/Task 3/Task 4 headings so the markdown outline is valid and easy to scan.
---
Nitpick comments:
In `@relay/channel/minimax/adaptor_test.go`:
- Around line 189-236: The streaming coverage in
TestDoResponseForOpenAIStreamStripsMiniMaxFieldsAndMessage is missing the final
SSE chunk stripping checks that are already validated in the non-stream path.
Update this test to assert the final chunk also removes MiniMax-specific
top-level fields like base_resp and input_sensitive, alongside the existing
message/name/audio_content checks, so DoResponse stays consistent across stream
and non-stream responses.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Organization UI
Review profile: CHILL
Plan: Pro
Run ID: 80316fa9-5040-45ae-a85f-afdc72a3c360
📒 Files selected for processing (6)
docs/superpowers/plans/2026-07-04-minimax-openai-response-sanitize.mddocs/superpowers/reports/minimax-openai-response-sanitize-review.htmldocs/superpowers/specs/2026-07-04-minimax-openai-response-sanitize-design.mdrelay/channel/minimax/adaptor.gorelay/channel/minimax/adaptor_test.gorelay/channel/openai/relay-openai.go
Comment on lines
+13
to
+87
| ### Task 1: Non-Streaming Regression Test | ||
|
|
||
| **Files:** | ||
| - Modify: `relay/channel/minimax/adaptor_test.go` | ||
|
|
||
| - [ ] **Step 1: Write the failing test** | ||
|
|
||
| Add a test that sends a MiniMax-style non-streaming response with extra top-level and message fields through `Adaptor.DoResponse`. Assert the recorded response keeps OpenAI fields and omits MiniMax-only fields. | ||
|
|
||
| - [ ] **Step 2: Run test to verify it fails** | ||
|
|
||
| Run: `go test ./relay/channel/minimax -run TestDoResponseForOpenAITextStripsMiniMaxFields -count=1` | ||
|
|
||
| Expected before implementation: FAIL because `input_sensitive`, `base_resp`, `name`, or `audio_content` appears in the response body. | ||
|
|
||
| ### Task 2: Streaming Regression Test | ||
|
|
||
| **Files:** | ||
| - Modify: `relay/channel/minimax/adaptor_test.go` | ||
|
|
||
| - [ ] **Step 1: Write the failing test** | ||
|
|
||
| Add a streaming test that sends SSE chunks containing MiniMax-only `delta.name`, `delta.audio_content`, and a final chunk containing `choices[].message`. Assert the downstream SSE omits those fields and still emits `[DONE]`. | ||
|
|
||
| - [ ] **Step 2: Run test to verify it fails** | ||
|
|
||
| Run: `go test ./relay/channel/minimax -run TestDoResponseForOpenAIStreamStripsMiniMaxFieldsAndMessage -count=1` | ||
|
|
||
| Expected before implementation: FAIL because raw SSE chunks are forwarded with `name`, `audio_content`, or `message`. | ||
|
|
||
| ### Task 3: Minimal Implementation | ||
|
|
||
| **Files:** | ||
| - Modify: `relay/channel/minimax/adaptor.go` | ||
| - Modify: `relay/channel/openai/relay-openai.go` | ||
|
|
||
| - [ ] **Step 1: Force formatting for MiniMax OpenAI text responses** | ||
|
|
||
| In `Adaptor.DoResponse`, before delegating to `openai.Adaptor`, set `info.ChannelSetting.ForceFormat = true` when: | ||
|
|
||
| - `info.RelayFormat` is `types.RelayFormatOpenAI` | ||
| - `info.RelayMode` is `constant.RelayModeChatCompletions` | ||
|
|
||
| - [ ] **Step 2: Run targeted tests** | ||
|
|
||
| In `OpenaiHandler`, when `forceFormat` is true, clear `simpleResponse.Choices[i].Message.Name` before marshalling the response. | ||
|
|
||
| - [ ] **Step 3: Run targeted tests** | ||
|
|
||
| Run: `go test ./relay/channel/minimax -count=1` | ||
|
|
||
| Expected after implementation: PASS. | ||
|
|
||
| ### Task 4: Related Verification | ||
|
|
||
| **Files:** | ||
| - No production edits expected. | ||
|
|
||
| - [ ] **Step 1: Run delegated OpenAI handler tests** | ||
|
|
||
| Run: `go test ./relay/channel/openai -count=1` | ||
|
|
||
| Expected: PASS. | ||
|
|
||
| - [ ] **Step 2: Run touched relay package tests** | ||
|
|
||
| Run: `go test ./relay/channel/minimax ./relay/channel/openai -count=1` | ||
|
|
||
| Expected: PASS. | ||
|
|
||
| - [ ] **Step 3: Inspect diff** | ||
|
|
||
| Run: `git diff -- relay/channel/minimax/adaptor.go relay/channel/minimax/adaptor_test.go docs/superpowers/specs/2026-07-04-minimax-openai-response-sanitize-design.md docs/superpowers/plans/2026-07-04-minimax-openai-response-sanitize.md` | ||
|
|
||
| Expected: Only the planned MiniMax adaptor, tests, and docs changed. |
Contributor
There was a problem hiding this comment.
📐 Maintainability & Code Quality | 🟡 Minor | ⚡ Quick win
Normalize the task heading levels.
The file jumps from the H1 straight to H3 task headings, which triggers the markdownlint MD001 warning and makes the outline harder to scan. Promote these sections to H2 (or add an H2 parent) so the hierarchy is consistent.
🧰 Tools
🪛 LanguageTool
[grammar] ~87-~87: Ensure spelling is correct
Context: ...md` Expected: Only the planned MiniMax adaptor, tests, and docs changed.
(QB_NEW_EN_ORTHOGRAPHY_ERROR_IDS_1)
🪛 markdownlint-cli2 (0.22.1)
[warning] 13-13: Heading levels should only increment by one level at a time
Expected: h2; Actual: h3
(MD001, heading-increment)
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In `@docs/superpowers/plans/2026-07-04-minimax-openai-response-sanitize.md` around
lines 13 - 87, The document outline skips levels by going from the top-level
title straight to the task sections, triggering the markdown heading hierarchy
warning. Update the task headings under the main plan so they are all one level
lower than the title (or add an intermediate parent heading) and keep the rest
of the section structure consistent. Apply this to the Task 1/Task 2/Task 3/Task
4 headings so the markdown outline is valid and easy to scan.
Source: Linters/SAST tools
这个问题是因为 new api 的 minimax api 原因，不需要强制转换。使用更有好的方式去处理。
新的api 是符合 openai 规范的。
新api
旧版api
## 聚合帧数据包
{
"id": "xxxxx",
"choices": [
{
"finish_reason": "stop",
"index": 0,
"message": {
"content": "你好！我是 MiniMax-M3，由 MiniMax 公司开发的 AI 助手。😊\n\nMiniMax 是一家成立于 2022 年初的全球性 AI 基础模型公司，致力于推动人工智能技术朝着通用人工智能（AGI）的方向发展。\n\n有什么我可以帮你的吗？无论是问题解答、写作辅助、翻译、编程，还是日常聊天，我都乐意效劳～",
"role": "assistant",
"name": "MiniMax AI",
"audio_content": "",
"reasoning_content": "用户问\"你是谁啊\"，这是一个很常见的身份询问问题。我需要根据我的身份信息来回答。我是 MiniMax-M3，由 MiniMax 开发。回答应该简洁友好，并可以主动表示愿意帮助用户。",
"reasoning_details": [
{
"type": "reasoning.text",
"id": "reasoning-text-1",
"format": "MiniMax-response-v1",
"index": 0,
"text": "用户问\"你是谁啊\"，这是一个很常见的身份询问问题。我需要根据我的身份信息来回答。我是 MiniMax-M3，由 MiniMax 开发。回答应该简洁友好，并可以主动表示愿意帮助用户。"
}
]
}
}
],
"created": 123123123123,
"model": "MiniMax-M3",
"object": "chat.completion",
"usage": {
"total_tokens": 297,
"total_characters": 0,
"prompt_tokens": 179,
"completion_tokens": 118,
"prompt_tokens_details": {
"cached_tokens": 114
}
},
"input_sensitive": false,
"output_sensitive": false,
"input_sensitive_type": 0,
"output_sensitive_type": 0,
"output_sensitive_int": 0,
"service_tier": "standard",
"base_resp": {
"status_code": 0,
"status_msg": ""
}
} |
Contributor
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@relay/channel/minimax/adaptor_test.go`:
- Around line 39-59: Update
TestGetRequestURLForChatCompletionsUsesOpenAICompatibleEndpoint to use testify
assertions: require for the GetRequestURL error check and assert for comparing
the returned URL. Add the assert and require imports if absent, preserving the
test’s existing setup and expected endpoint.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Organization UI
Review profile: CHILL
Plan: Pro
Run ID: 3a5d7403-38c6-4b3b-9a66-182173c1674a
📒 Files selected for processing (2)
relay/channel/minimax/adaptor_test.gorelay/channel/minimax/relay-minimax.go
Calcium-Ion
force-pushed
the
main
branch
2 times, most recently
from
August 30, 2026 15:03
51fdfc5 to
2b6f1df
Compare
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.
Important
📝 变更描述 / Description
修复 MiniMax 以 OpenAI Chat Completions 格式转发时的响应字段污染问题。
MiniMax 的 OpenAI 兼容响应会返回一些非 OpenAI Chat Completions 字段，例如非流式响应里的
input_sensitive、output_sensitive、service_tier、base_resp，以及响应消息中的name、audio_content；流式响应最后一个 chunk 还会额外带message块。该 PR 在 MiniMax OpenAI Chat Completions 响应路径启用 OpenAI force format，使响应重新经过 OpenAI DTO 序列化，只保留兼容字段；同时在 force format 的非流式路径清理复用请求 DTO 带来的message.name。这能让 MiniMax 对外返回更接近标准 OpenAI Chat Completions 的非流式 JSON 与 SSE chunk，避免客户端因额外字段或最后一个流式 chunk 的
message块出现兼容性问题。🚀 变更类型 / Type of change
🔗 关联任务 / Related Issue
✅ 提交前检查项 / Checklist
Bug fix，我已提交或关联对应 Issue，且不会将设计取舍、预期不一致或理解偏差直接归类为 bug。📸 运行证明 / Proof of Work
本地验证通过：
另外使用本地 MiniMax mock upstream 启动真实 new-api 服务完成端到端验证：
/v1/chat/completions返回 HTTP 200，保留object、message.content、usage，不再包含input_sensitive、output_sensitive、service_tier、base_resp、audio_content、message.name。/v1/chat/completions返回 HTTP 200 SSE，保留delta.role、delta.content、reasoning_content、finish_reason、data: [DONE]，不再包含最后一个 chunk 的message块、delta.name、audio_content。Summary by CodeRabbit
Bug Fixes
/v1/chat/completionsendpoint.Documentation