makecindy / makecindy/cindy

codex 终端会话内切换推理强度缺少 xhigh / max 档位

Open
#1,869 2 comments 1 reaction 0 assignees View on GitHub
feature
Dominant language
TypeScript
Stars
2.7k
Forks
401
Avg merge
21h 48m
Merged PRs (30d)
776

Description

**提交人**: yugui
**客户端版本**: 0.1.31

---

## 使用场景

在 codex 终端里使用 GPT-5.6 模型时,会话内切换推理强度的入口只提供 minimal / low / medium / high 四档,最高只能选到 high。遇到需要更深推理的任务(架构设计、疑难调试)时,无法在会话中把强度拉到 codex 本身支持的更高档位。

## 诉求

希望在会话内切换推理强度的选项里补齐更高档位 —— xhigh 与 max,让 Cindy 暴露的档位与 codex CLI / 所选模型实际支持的取值保持一致。

## 建议方案

- 会话内推理强度选择器在 high 之后补上 xhigh 和 max。
- 档位列表尽量跟随 codex CLI 与所选模型实际支持的取值动态生成,而不是写死一份固定列表,避免上游新增档位后再次出现缺档。
- 若某个模型确实不支持 xhigh / max,对该模型置灰或隐藏,而不是所有模型都看不到这两档。
---
**OS**: win32 x64 (10.0.19045)
**界面语言**: zh-CN

Contributor guide

Open the contributing guide

Research direction

Start by tracing the Codex terminal session's reasoning-strength selector and the source of supported values for the selected model. Check how the current minimal, low, medium, and high options are produced, then verify that supported models expose xhigh and max while unsupported models hide or disable them. Done means the session selector matches the model's available reasoning levels.

Written by the indexing model from the issue text.

Assessment

Tech stack
typescript
Domain
cli, frontend
Issue type
Feature
Difficulty
4/5
Estimated time
3-5 days
Activity status
Quiet
Clarity
Mostly clear
Newbie friendliness
52/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.