fix: record reasoning effort consistently in usage logs - #6641
Merged
Conversation
Contributor
WalkthroughReasoning effort is now extracted and normalized across supported relay request formats. Parameter overrides keep relay metadata synchronized. Usage-log details use a shared helper to render reasoning-effort badges. ChangesReasoning effort propagation
Estimated code review effort: 3 (Moderate) | ~25 minutes Possibly related PRs
Suggested reviewers: Poem
🚥 Pre-merge checks | ✅ 4 | ❌ 1❌ Failed checks (1 warning)
✅ Passed checks (4 passed)
✨ Finishing Touches 💡 1🛠️ Fix failing CI checks 💡
🧪 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: 2
🤖 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/common/override.go`:
- Around line 226-253: Update extractReasoningEffortFromJSON to skip
whitespace-only string values and continue checking later paths, allowing OpenAI
reasoning_effort to fall back to reasoning.effort. Preserve exists=true when
aliases are present but all string values are empty, and add the mixed
blank-top-level/fallback case to
TestApplyParamOverrideWithRelayInfoSynchronizesReasoningEffort.
In `@relay/common/relay_info_test.go`:
- Around line 160-178: Update
TestInitChannelMetaRestoresRequestReasoningEffortForRetry to explicitly
initialize pass-through settings: set the global PassThroughRequestEnabled value
to false and restore its original value with t.Cleanup, and attach
ContextKeyChannelSetting to the request context with PassThroughBodyEnabled set
to false before calling InitChannelMeta.
🪄 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 Plus
Run ID: 8c8a9db9-b857-4336-9abe-f58d0dfd3b6a
📒 Files selected for processing (10)
relay/channel/deepseek/adaptor.gorelay/channel/openai/adaptor.gorelay/channel/xai/adaptor.gorelay/claude_handler.gorelay/common/override.gorelay/common/override_test.gorelay/common/relay_info.gorelay/common/relay_info_test.goweb/src/features/usage-logs/components/dialogs/details-dialog.tsxweb/src/features/usage-logs/lib/format.ts
Comment on lines
+226
to
+253
| func extractReasoningEffortFromJSON(format types.RelayFormat, data []byte) (string, bool) { | ||
| var paths []string | ||
| switch format { | ||
| case types.RelayFormatOpenAI: | ||
| paths = []string{"reasoning_effort", "reasoning.effort"} | ||
| case types.RelayFormatOpenAIResponses: | ||
| paths = []string{"reasoning.effort"} | ||
| case types.RelayFormatClaude: | ||
| paths = []string{"output_config.effort"} | ||
| case types.RelayFormatGemini: | ||
| paths = []string{ | ||
| "generationConfig.thinkingConfig.thinkingLevel", | ||
| "generation_config.thinking_config.thinking_level", | ||
| } | ||
| default: | ||
| return "", false | ||
| } | ||
| for _, path := range paths { | ||
| value := gjson.GetBytes(data, path) | ||
| if !value.Exists() { | ||
| continue | ||
| } | ||
| if value.Type != gjson.String { | ||
| return "", true | ||
| } | ||
| return strings.TrimSpace(value.String()), true | ||
| } | ||
| return "", false |
Contributor
There was a problem hiding this comment.
🎯 Functional Correctness | 🟡 Minor | ⚡ Quick win
Fall back to reasoning.effort after a blank reasoning_effort.
Line 251 returns a blank top-level alias before it checks later aliases. reasoningEffortFromRequest treats a whitespace-only OpenAI reasoning_effort as absent and falls back to reasoning.effort.
An unrelated parameter override can therefore reset RelayInfo.ReasoningEffort from "high" to "" for {"reasoning_effort":" ","reasoning":{"effort":"high"}}. Continue after empty string values, while retaining exists=true when every string alias is empty. Add this case to TestApplyParamOverrideWithRelayInfoSynchronizesReasoningEffort.
Proposed fix
func extractReasoningEffortFromJSON(format types.RelayFormat, data []byte) (string, bool) {
var paths []string
+ foundEmptyString := false
switch format {
@@
if value.Type != gjson.String {
return "", true
}
- return strings.TrimSpace(value.String()), true
+ effort := strings.TrimSpace(value.String())
+ if effort == "" {
+ foundEmptyString = true
+ continue
+ }
+ return effort, true
}
- return "", false
+ return "", foundEmptyString
}📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
Suggested change
| func extractReasoningEffortFromJSON(format types.RelayFormat, data []byte) (string, bool) { | |
| var paths []string | |
| switch format { | |
| case types.RelayFormatOpenAI: | |
| paths = []string{"reasoning_effort", "reasoning.effort"} | |
| case types.RelayFormatOpenAIResponses: | |
| paths = []string{"reasoning.effort"} | |
| case types.RelayFormatClaude: | |
| paths = []string{"output_config.effort"} | |
| case types.RelayFormatGemini: | |
| paths = []string{ | |
| "generationConfig.thinkingConfig.thinkingLevel", | |
| "generation_config.thinking_config.thinking_level", | |
| } | |
| default: | |
| return "", false | |
| } | |
| for _, path := range paths { | |
| value := gjson.GetBytes(data, path) | |
| if !value.Exists() { | |
| continue | |
| } | |
| if value.Type != gjson.String { | |
| return "", true | |
| } | |
| return strings.TrimSpace(value.String()), true | |
| } | |
| return "", false | |
| func extractReasoningEffortFromJSON(format types.RelayFormat, data []byte) (string, bool) { | |
| var paths []string | |
| foundEmptyString := false | |
| switch format { | |
| case types.RelayFormatOpenAI: | |
| paths = []string{"reasoning_effort", "reasoning.effort"} | |
| case types.RelayFormatOpenAIResponses: | |
| paths = []string{"reasoning.effort"} | |
| case types.RelayFormatClaude: | |
| paths = []string{"output_config.effort"} | |
| case types.RelayFormatGemini: | |
| paths = []string{ | |
| "generationConfig.thinkingConfig.thinkingLevel", | |
| "generation_config.thinking_config.thinking_level", | |
| } | |
| default: | |
| return "", false | |
| } | |
| for _, path := range paths { | |
| value := gjson.GetBytes(data, path) | |
| if !value.Exists() { | |
| continue | |
| } | |
| if value.Type != gjson.String { | |
| return "", true | |
| } | |
| effort := strings.TrimSpace(value.String()) | |
| if effort == "" { | |
| foundEmptyString = true | |
| continue | |
| } | |
| return effort, true | |
| } | |
| return "", foundEmptyString | |
| } |
🤖 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/common/override.go` around lines 226 - 253, Update
extractReasoningEffortFromJSON to skip whitespace-only string values and
continue checking later paths, allowing OpenAI reasoning_effort to fall back to
reasoning.effort. Preserve exists=true when aliases are present but all string
values are empty, and add the mixed blank-top-level/fallback case to
TestApplyParamOverrideWithRelayInfoSynchronizesReasoningEffort.
Comment on lines
+160
to
+178
| func TestInitChannelMetaRestoresRequestReasoningEffortForRetry(t *testing.T) { | ||
| gin.SetMode(gin.TestMode) | ||
| ctx, _ := gin.CreateTestContext(httptest.NewRecorder()) | ||
| ctx.Request = httptest.NewRequest("POST", "/v1/responses", nil) | ||
| request := &dto.OpenAIResponsesRequest{ | ||
| Model: "gpt-5.6-sol", | ||
| Reasoning: &dto.Reasoning{Effort: "max"}, | ||
| } | ||
| info, err := GenRelayInfo(ctx, types.RelayFormatOpenAIResponses, request, nil) | ||
| require.NoError(t, err) | ||
|
|
||
| info.SetReasoningEffort("high") | ||
| info.InitChannelMeta(ctx) | ||
| assert.Equal(t, "max", info.ReasoningEffort) | ||
|
|
||
| info.SetReasoningEffort("low") | ||
| info.InitChannelMeta(ctx) | ||
| assert.Equal(t, "max", info.ReasoningEffort) | ||
| } |
Contributor
There was a problem hiding this comment.
📐 Maintainability & Code Quality | 🟡 Minor | ⚡ Quick win
Initialize pass-through settings in this retry fixture.
Line 172 calls InitChannelMeta, which reads the global PassThroughRequestEnabled setting. The fixture leaves that setting implicit. A prior test can make Line 173 receive "" instead of "max".
Set global pass-through to false through the test fixture and restore it in t.Cleanup. Set ContextKeyChannelSetting with PassThroughBodyEnabled: false explicitly.
As per coding guidelines, “Initialize database, request context, user group, settings, and cache state explicitly in test fixtures.”
🤖 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/common/relay_info_test.go` around lines 160 - 178, Update
TestInitChannelMetaRestoresRequestReasoningEffortForRetry to explicitly
initialize pass-through settings: set the global PassThroughRequestEnabled value
to false and restore its original value with t.Cleanup, and attach
ContextKeyChannelSetting to the request context with PassThroughBodyEnabled set
to false before calling InitChannelMeta.
Source: Coding guidelines
latioswang
added a commit
to trycortexai/new-api
that referenced
this pull request
Aug 10, 2026
* fix(relay): set Request.GetBody so the HTTP/2 transport can transparently retry after an upstream stream reset (QuantumNous#6249) * fix(relay): set Request.GetBody so the HTTP/2 transport can transparently retry after an upstream stream reset The outbound request body is a type-erased io.Reader over BodyStorage, so net/http cannot derive Request.GetBody (it only does so for *bytes.Reader, *bytes.Buffer and *strings.Reader). With GetBody nil, the HTTP/2 transport cannot transparently retry a request once the body has been written and the upstream resets the stream with a retryable error (REFUSED_STREAM, or a connection-level GOAWAY); the relay request then fails with: http2: Transport: cannot retry err [...] after Request.Body was written; define Request.GetBody to avoid this error This affects every relay path that goes through DoApiRequest (chat, claude, gemini, responses, embedding, image, rerank). BodyStorage (memory and disk) already implements io.Seeker, so replay support only needed wiring: - NewOutboundJSONBody additionally returns a getBody that rewinds the storage and hands out a fresh non-closing reader. The transport only calls GetBody after the previous attempt's body has been abandoned, so the rewind cannot race an in-flight read. - RelayInfo carries it in the new UpstreamRequestGetBody field, set alongside UpstreamRequestBodySize by the handlers that build storage-backed bodies. - applyUpstreamGetBody (symmetric with applyUpstreamContentLength) wires it into DoApiRequest/DoFormRequest/DoTaskApiRequest, only when req.GetBody is still nil. Also remove the hand-rolled GetBody override in DoTaskApiRequest: it returned the same already-consumed reader, so any transport-level replay would have silently sent an empty body, and it clobbered the correct snapshot-based GetBody that net/http derives from the *bytes.Reader bodies the task adaptors pass in. For non-replayable bodies GetBody now stays nil, so a retry fails loudly instead of corrupting the request. Covered by unit tests plus an end-to-end raw-frame HTTP/2 test that resets the first stream with REFUSED_STREAM after the body is written and asserts the transport transparently retries with the complete body. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix(relay): hand out independent readers from GetBody (address review) Per the http.Request.GetBody contract ("returns a new copy of Body"), each call must yield a reader with its own cursor. The previous implementation rewound and reused the shared BodyStorage, so two consecutive GetBody readers would interfere with each other, and a replay could disturb the primary body's offset under extreme transport timing (e.g. attempt N's body write not yet fully abandoned when the transport builds attempt N+1). Instead of snapshotting the payload (an extra copy), add BodyStorage.NewReader, which returns an independent zero-copy reader: - memory mode: a fresh bytes.Reader over the same immutable backing array; - disk mode: a separate file descriptor over the cache file, so the transport closing a replayed body only closes that descriptor. NewOutboundJSONBody's getBody now simply hands out storage.NewReader, and once the handler releases the storage, GetBody fails with ErrStorageClosed instead of replaying stale data. Tests: interleaved reads across two replay readers and the primary body each observe exactly their own byte stream, for both the memory and the disk-backed storage; the existing GetBody and HTTP/2 retry suites still pass (h2 e2e tests flake-free with -count=20). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix(relay): bind replayable metadata on pass-through requests * fix(relay): reset upstream body metadata between channels * test(relay): cover replay across retries and channel attempts * fix(relay): stop following upstream redirects --------- Co-authored-by: Claude Fable 5 <noreply@anthropic.com> * refactor(relay): move replay metadata onto request bodies * Merge commit from fork * feat(channels): refine fetched model categorization (QuantumNous#6632) * feat(channels): refine fetched model categorization * fix: channel category * fix: hy3 category * fix: test Claude/Gemini endpoints with native request format (QuantumNous#6698) * feat(rate-limit): add user critical rate limit middleware for access token and aff transfer routes * fix: 修复兑换码额度精度损失 (QuantumNous#6685) * fix: 修复兑换码额度精度损失(QuantumNous#6680) * fix(redemption): guard update data integrity * CI: enhance release synchronization workflow with optional file syncing * fix(ali): stop injecting top_p into requests that omit it (QuantumNous#6674) * fix(channels): classify Qwen TTS models correctly (QuantumNous#6711) * feat(channels): add auto-disable-only channel test mode (QuantumNous#6728) * perf(web): debounce server and large-list searches (QuantumNous#6727) * fix: record reasoning effort consistently in usage logs (QuantumNous#6641) * feat(relay): expose user and group context to parameter overrides (QuantumNous#6534) * fix(ollama): preserve reasoning and tool-call context (QuantumNous#6605) * fix: backend length validation (QuantumNous#5548) * feat(billing): highlight matched conditional multipliers in logs (QuantumNous#6561) * feat(billing): highlight matched conditional multipliers in usage logs * fix(billing): make request rule tracing stable and type-safe * fix(web): require confirmation before rotating access token (QuantumNous#6749) --------- Co-authored-by: Lucas <hepo.lucas@gmail.com> Co-authored-by: Claude Fable 5 <noreply@anthropic.com> Co-authored-by: CaIon <i@caion.me> Co-authored-by: RedwindA <128586631+RedwindA@users.noreply.github.com> Co-authored-by: Seefs <40468931+seefs001@users.noreply.github.com> Co-authored-by: lihu-001 <lihu9048@gmail.com> Co-authored-by: ENCHIGO <38551565+ENCHIGO@users.noreply.github.com>
0401lucky
pushed a commit
to 0401lucky/new-api
that referenced
this pull request
Aug 16, 2026
DayFliggy
pushed a commit
to DayFliggy/Ren2Hub
that referenced
this pull request
Aug 17, 2026
330079598
pushed a commit
to 330079598/new-api
that referenced
this pull request
Aug 19, 2026
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
(简述：做了什么？为什么这样改能生效？请基于你对代码逻辑的理解来写，避免粘贴未经整理的内容)
🚀 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
(请在此粘贴截图、关键日志或测试报告，以证明变更生效)
Summary by CodeRabbit
Bug Fixes
Usage Logs
Quality