feat(summary): allow thinking depth on summary function models - #1152
Open
3316891527 wants to merge 2 commits into
Open
feat(summary): allow thinking depth on summary function models#11523316891527 wants to merge 2 commits into
3316891527 wants to merge 2 commits into
Conversation
Fixes AAswordman#1148. Summary requests used sendMessage without enableThinking, so subscription models that require reasoning failed. Store thinking on FunctionConfigMapping, pass it through sendMessage, and add a small toggle/menu under the summary card in functional config.
3316891527
marked this pull request as ready for review
September 8, 2026 16:39
Make getThinkingRequestForFunction internal so it can return FunctionThinkingRequest. Pass Gemini testConnection sendMessage args by name after thinkingOptionId was added.
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
变更说明 / Description
订阅套餐强制开启思考时,总结请求一直以
enableThinking=false发出去,会被后端拒绝。这次让总结功能可以独立配思考开关和档位,不和聊天全局开关抢同一份状态。背景与动机 / Context and motivation
Fixes #1148. 聊天走全局
enableThinkingMode+ 模型配置上的thinkingOptionId;总结ConversationService.generateSummaryFromPromptTurns调sendMessage时不传enableThinking,默认 false。协议已有ThinkingQualityMapping/ThinkingConfigurationApplier,不把聊天滑条搬进设置。改动范围 / Changes
FunctionConfigMapping增加enableThinking/thinkingOptionId;换模型时保留这两个字段AIService.sendMessage增加可选thinkingOptionId,Provider 请求体优先用这一次传入的档位sendMessage;LEVELS且为空时回退到绑定模型配置的档或第一档TOGGLE_ONLY只显示开关,UNSUPPORTED隐藏,reasoningRequired锁开兼容性与风险 / Compatibility and risks
旧功能映射 JSON 缺字段时默认关闭思考,行为与改前一致。只有用户在总结项下打开思考后,请求才会带档位。
关联 Issue / Related issue
Fixes #1148
验证方式 / Verification
检查清单 / Checklist
dev