feat: add per-turn reasoning effort selection to chat API#26975
Draft
DanielleMaywood wants to merge 1 commit into
Draft
feat: add per-turn reasoning effort selection to chat API#26975DanielleMaywood wants to merge 1 commit into
DanielleMaywood wants to merge 1 commit into
Conversation
Docs preview📖 View docs preview for |
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Builds on the per-model
reasoning_effort{default, max}config to let users pick the reasoning effort per turn, clamped server-side to the model's max.Changes
reasoning_effortonCreateChatRequest,CreateChatMessageRequest, andEditChatMessageRequest(400 on values outside the global scale);Chatexposeslast_reasoning_effort.model_config_idflow. The value is stored per message (chat_messages.reasoning_effort), survives queueing (chat_queued_messages.reasoning_effort), andInsertChatMessagesupdateschats.last_reasoning_effortfrom the last message in the batch carrying one (unchanged when absent). Editing a message preserves its original effort unless the request overrides it.chats.last_reasoning_effort(else the config default), clamps to the config max, and snaps into the provider's supported set. Models without effort config ignore user-supplied values. Subagent chats intentionally start unset and use the model default.Part of the reasoning effort stack (base: #26974; the chat slider UI follows in #26977).
🤖 Generated by Coder Agents on behalf of @DanielleMaywood