CherryHQ/cherry-studio

[Discussion] PDF recognition issue with GPT-5.5 via reseller API in Cherry Studio

Open

#14902 opened on May 7, 2026

View on GitHub
 (0 comments) (2 reactions) (0 assignees)TypeScript (45,688 stars) (4,338 forks)batch import
Modelsdiscussionhelp wanted

Description

[!NOTE] This issue was translated by Claude.

Issue Checklist

  • I understand that issues are meant for feedback and problem-solving, not for venting, and I will provide as much detail as possible to help resolve the issue.
  • I have checked the pinned issues and searched through the existing open issues, closed issues, and discussions and did not find a similar suggestion.
  • I confirm that I am here to ask questions and discuss issues, not to report bugs or request features.

Platform

Windows

Version

v1.9.4

Your Question

PDF recognition issue when using reseller's GPT-5.5 API in Cherry Studio

Context

Environment: Using reseller Codex with GPT-5.5 API, provider type selected as OpenAI

Problem: When attaching a PDF document and asking the model to read and summarize it, the model cannot recognize the uploaded document—it only recognizes the filename. The response is approximately: "You haven't uploaded a document, I'll search for the keyword... (the filename of my uploaded document)"

Potentially useful information: I then conducted comparison tests:

  • When I continue using the same reseller's GPT-5.5 with attached images and ask it to read and recognize them, it works normally;

  • When I use KIMI's official KIMI K2.5 with attached PDF documents and ask it to read and summarize, it recognizes them normally

Additional Information

Priority

Low (Review when available)

Issue Checklist

  • I understand that issues are meant for feedback and problem-solving, not for venting, and I will provide as much detail as possible to help resolve the issue.
  • I have checked the pinned issues and searched through the existing open issues, closed issues, and discussions and did not find a similar suggestion.
  • I confirm that I am here to ask questions and discuss issues, not to report bugs or request features.

Platform

Windows

Version

v1.9.4

Your Question

在Cherry studio 中接入中转商的 GPT-5.5，在对话中其无法识别 PDF 的问题

Context

环境：接入中转商的 Codex 用 GPT-5.5 API，提供商类型选择的是 OpenAI

问题：当附加PDF文档，同时对话要求其阅读总结文档时，其会无法识别到我上传的文档，仅识别到我所上传文档的文件名。其大致回复您没有上传文档，我为您搜索关键词...（我上传文档的文件名）

可能有用的信息：随后我做了对比测试

  • 当我在对话中继续使用该中转商的 GPT-5.5 附加图片，同时对话要求其阅读识别图片时，其正常识别；

  • 当我在对话中使用 KIMI 官方的 KIMI K2.5 附加PDF文档，同时附加对话要求其阅读总结文档时，其正常识别

Additional Information

Priority

Low (Review when available)

Contributor guide

Tech stack
typescriptnodejs
Domain
backendapi
Issue type
research
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
3
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
1-3 hours
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
fresh
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
clear
Prerequisites
TypeScriptNode.jsHTTP API understanding
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
35
Research direction
Investigate Cherry Studio's file upload and API request construction for the OpenAI provider. Compare the request payload for PDF versus image files. Check if the reseller API endpoint requires a different content type or URL. Look at the source code in src/.../provider/openai.ts or similar. Also verify if the model name 'GPT 5.5' is correctly mapped to the reseller's model ID. Review any existing issues or discussions about reseller compatibility.