Fix OpenAI WS tool continuation recovery#2241
Open
Hundun-Online wants to merge 3 commits intoWei-Shaw:mainfrom
Open
Fix OpenAI WS tool continuation recovery#2241Hundun-Online wants to merge 3 commits intoWei-Shaw:mainfrom
Hundun-Online wants to merge 3 commits intoWei-Shaw:mainfrom
Conversation
- Keep gin v1.9.1 (v1.11+ breaks Get() API compatibility) - Fix quic-go at v0.57.1 (req/v3 v3.57.0 depends on ConnectionTracingID) - Upgrade other Go dependencies (go mod tidy) - Sync frontend package-lock.json
## 版本亮点 修复 OpenAI 兼容接口中未知模型被默认模型静默兜底的问题，请求会保留原始模型并透传上游错误。 ## Bug 修复 - OpenAI 模型转发：移除未知 GPT 模型自动回退到分组默认模型的逻辑，避免无效模型被错误转发为默认模型 - 计费记录：保持渠道未映射请求按实际上游计费模型记录，避免计费模型被原始请求模型覆盖 ## 优化改进 - 模型支持：补充 gpt-5.4-nano 本地兜底计费价格 - 测试覆盖：增加未知模型不兜底、OAuth 透传和模型归一化相关用例
Contributor
|
Thank you for your contribution! Before we can merge this PR, we need you to sign our Contributor License Agreement (CLA). To sign, please reply with the following comment:
You only need to sign once — it will be valid for all your future contributions to this project. I have read the CLA Document and I hereby sign the CLA You can retrigger this bot by commenting recheck in this Pull Request. Posted by the CLA Assistant Lite bot. |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary\n- preserve previous_response_id for function_call_output turns when WS ingress preflight ping recovery reconnects\n- allow a one-time connection drift after a broken strict-affinity connection while keeping tool continuation context intact\n- apply temp-unschedulable rules to OpenAI response.failed SSE events using a synthetic 502 so stream-level capacity/overload failures can influence scheduling\n\n## Tests\n- go test ./internal/service -run 'Test.*OpenAIWS|Test.*FunctionCall|Test.*ToolContinuation|Test.*Streaming|Test.*TempUnsched|Test.*ErrorPolicy'\n- go test ./internal/handler -run 'TestHandleFailoverError|TestOpenAI|Test.*Failover'