makecindy / makecindy/cindy

功能建议:自动化任务创建时无法配置 provider,导致自定义 API key(DeepSeek)执行时报模型 400 错误

Open
#1,395 1 comment 0 reactions 0 assignees View on GitHub
feature
Dominant language
TypeScript
Stars
2.7k
Forks
395
Avg merge
21h 48m
Merged PRs (30d)
776

Description

**提交人**: 豆豆爸
**客户端版本**: 0.1.26

---

## 使用场景
在设置中配置了自己的 DeepSeek API key,并通过 Cindy 界面的「自动化」入口创建一个自动化任务。任务到点执行时,请求被发往 Anthropic 的接口地址,却传了 DeepSeek 的模型名,返回 400:

```
API Error: 400 400: {'error': 'anthropic_messages: Invalid model name passed in model=deepseek-v4-flash. Call `/v1/models` to view available models for your key.'}
```

## 诉求
创建自动化任务时**没有可配置 provider 的地方**,任务执行时消息被发往默认的 Anthropic 接口;而自定义 API key(DeepSeek)对应的模型名 `deepseek-v4-flash` 在 Anthropic 端不存在,于是报 400「invalid model name」。希望自动化任务也能像普通对话一样配置或自动匹配 provider 与模型。

## 建议方案
1. 自动化任务创建/配置界面支持选择 provider 与模型;
2. 或在选择模型后由系统自动匹配其所属 provider(设置中已配好对应 API key),避免请求被发到错误的接口地址。
---
**版本区域**: CN
**OS**: win32 x64 (10.0.26200)
**界面语言**: zh-CN

Contributor guide

Open the contributing guide

Research direction

Start from the automation entry used to create and execute tasks, then compare it with the ordinary conversation flow and the settings where the DeepSeek API key is configured. Trace how the selected model and provider reach the request layer. Done means an automation task can select or correctly infer its provider and model, avoiding the Anthropic endpoint for DeepSeek models.

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.