Repository navigation
feat(minimax-code): effort xhigh, permission full, 모델 한도·thinking 정의 - #154
Merged
Merged
Conversation
…(AC-G2) - mcode exec 에 --effort xhigh 를 고정하고 권한을 smart → full 로 바꾼다. smart 는 사람 없이 대부분의 셸 명령을 거부해 무인 실행 turn 을 실패시킨다. - 관리형 설정의 모델 정의를 mcode 내장 M3 계열 정의에 맞춘다: effortOptions (없으면 mcode 가 --effort 를 거부), thinking_config forced_on, variants, 그리고 MiniMax-M3.1-Flash 의 limit 512k/128k (없으면 max_tokens 16384). - 캡처 서버로 확인한 실제 요청: max_tokens 128000, thinking adaptive, output_config.effort xhigh. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01R1VrPpZUiPjHiu3NHL7jrA
dlddu
added
the
deploy/preview
Claude
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
요약
minimax-code 실행 파라미터를 코딩 성능 쪽으로 조정합니다 (AC-G2).
--permission smart(무인 실행에서 셸 명령 대부분 거부)--permission fullbudget_tokens: 8192고정 thinking)--effort xhigh→output_config.effort: xhigh,thinking: adaptivemax_tokens: 16384(custom 모델 fallback)max_tokens: 128000변경
data-plane/cmd/agent/minimax_code.go--effort xhigh, 권한fulleffortOptions(없으면 mcode가--effort를 거부하고 실행 자체가 실패),thinking_config: forced_on,variantslimit {context: 512000, output: 128000}은MiniMax-M3.1-Flash에만. 한도를 모르는 모델은 mcode fallback을 유지TestMiniMaxManagedModelDefinition추가 (mutation 확인: limit 제거·xhigh 제거 시 실패)data-plane/README.md검증
--effort xhigh→does not support reasoning effort selection로 실행 실패/v1/messages에max_tokens: 128000,thinking: {type: adaptive},output_config: {effort: xhigh}go test ./...(data-plane) 통과, comment policy / fidelity allowlist / scenario mapping 게이트 통과Generated by Claude Code