makecindy / makecindy/cindy

自定义 API Key 模型应支持识别并配置实际上下文长度

Open
#1,145 3 comments 0 reactions 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**: pengtiancheng
**客户端版本**: 0.1.16

---

## 使用场景

在 Cindy 中使用自行配置的 API Key 和模型时,模型上下文长度目前会采用系统默认值,而不是模型实际支持的长度。

例如:配置 Kimi K3 时,模型实际支持 1M 上下文,但 Cindy 中显示或采用的是 200K。目前主要问题是配置与模型真实能力不一致。

## 诉求

希望 Cindy 能使用模型实际支持的上下文长度,避免自定义模型的能力被默认值限制,并让上下文预算的展示与计算更加准确。

## 建议方案

- 优先通过 API 或模型元数据自动识别上下文长度。
- 在自定义 API Key / 模型配置中增加可手动填写或覆盖上下文长度的选项。
- 无法自动识别时再使用默认值,并清楚标明当前数值来自默认配置。
---
**OS**: win32 x64 (10.0.19045)
**界面语言**: zh-CN

Contributor guide

Open the contributing guide

Research direction

Start by locating the custom API key/model configuration and the code that supplies the current default context length. Trace how model metadata or API responses are handled, then verify that a manual override and an automatic value can be distinguished. Done means custom models use their actual or configured context length, fall back clearly to the default when necessary, and display and calculate the corresponding budget accurately.

Written by the indexing model from the issue text.

Assessment

Tech stack
typescript
Domain
ai, api
Issue type
Feature
Difficulty
4/5
Estimated time
3-5 days
Activity status
Quiet
Clarity
Mostly clear
Newbie friendliness
48/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.