[GH-ISSUE #23188] feat: support additional Anthropic tool_result content types #19914

Closed
opened 2026-04-20 02:28:16 -05:00 by GiteaMirror · 0 comments
Owner

Originally created by @Classic298 on GitHub (Mar 28, 2026).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/23188

Check Existing Issues

  • I have searched for all existing open AND closed issues and discussions for similar requests. I have found none that is comparable to my request.

Verify Feature Scope

  • I have read through and understood the scope definition for feature requests in the Issues section. I believe my feature request meets the definition and belongs in the Issues section instead of the Discussions.

Problem Description

The Anthropic-to-OpenAI payload conversion in utils/anthropic.py only handles text content within tool_result blocks. When a tool call returns an image (or other content types like search_result, document), the content is silently dropped — the request goes through but the model never sees the tool output.

This affects anyone using the Anthropic-compatible endpoint with tools that return multimodal results.

Desired Solution you'd like

support for images and string content in Anthropic tool_result

Alternatives Considered

No response

Additional Context

No response

Originally created by @Classic298 on GitHub (Mar 28, 2026). Original GitHub issue: https://github.com/open-webui/open-webui/issues/23188 ### Check Existing Issues - [x] I have searched for all existing **open AND closed** issues and discussions for similar requests. I have found none that is comparable to my request. ### Verify Feature Scope - [x] I have read through and understood the scope definition for feature requests in the Issues section. I believe my feature request meets the definition and belongs in the Issues section instead of the Discussions. ### Problem Description The Anthropic-to-OpenAI payload conversion in utils/anthropic.py only handles text content within tool_result blocks. When a tool call returns an image (or other content types like search_result, document), the content is silently dropped — the request goes through but the model never sees the tool output. This affects anyone using the Anthropic-compatible endpoint with tools that return multimodal results. ### Desired Solution you'd like support for images and string content in Anthropic tool_result ### Alternatives Considered _No response_ ### Additional Context _No response_
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/open-webui#19914