[PR #18840] [CLOSED] fix: <details> tags for reasoning not identified if tag is present in user message #11785

Closed
opened 2025-11-11 19:57:02 -06:00 by GiteaMirror · 0 comments
Owner

📋 Pull Request Information

Original PR: https://github.com/open-webui/open-webui/pull/18840
Author: @acomarcho
Created: 11/1/2025
Status: Closed

Base: devHead: fix/details-tag-for-reasoning-not-identified


📝 Commits (1)

  • 867d0cf fix:
    tags for reasoning not identified if tag is present in user message

📊 Changes

2 files changed (+15 additions, -3 deletions)

View changed files

📝 backend/open_webui/utils/middleware.py (+4 -2)
📝 src/lib/components/chat/Messages/Markdown/MarkdownTokens.svelte (+11 -1)

📄 Description

Pull Request Checklist

Note to first-time contributors: Please open a discussion post in Discussions and describe your changes before submitting a pull request.

Before submitting, make sure you've checked the following:

  • Target branch: Verify that the pull request targets the dev branch. Not targeting the dev branch may lead to immediate closure of the PR.
  • Description: Provide a concise description of the changes made in this pull request.
  • Changelog: Ensure a changelog entry following the format of Keep a Changelog is added at the bottom of the PR description.
  • Documentation: If necessary, update relevant documentation Open WebUI Docs like environment variables, the tutorials, or other documentation sources.
  • Dependencies: Are there any new dependencies? Have you updated the dependency versions in the documentation?
  • Testing: Perform manual tests to verify the implemented fix/feature works as intended AND does not break any other functionality. Take this as an opportunity to make screenshots of the feature/fix and include it in the PR description.
  • Agentic AI Code:: Confirm this Pull Request is not written by any AI Agent or has at least gone through additional human review and manual testing. If any AI Agent is the co-author of this PR, it may lead to immediate closure of the PR.
  • Code review: Have you performed a self-review of your code, addressing any coding standard issues and ensuring adherence to the project's coding standards?
  • Title Prefix: To clearly categorize this pull request, prefix the pull request title using one of the following:
    • BREAKING CHANGE: Significant changes that may affect compatibility
    • build: Changes that affect the build system or external dependencies
    • ci: Changes to our continuous integration processes or workflows
    • chore: Refactor, cleanup, or other non-functional code changes
    • docs: Documentation update or addition
    • feat: Introduces a new feature or enhancement to the codebase
    • fix: Bug fix or error correction
    • i18n: Internationalization or localization changes
    • perf: Performance improvement
    • refactor: Code restructuring for better maintainability, readability, or scalability
    • style: Changes that do not affect the meaning of the code (white space, formatting, missing semi-colons, etc.)
    • test: Adding missing tests or correcting existing tests
    • WIP: Work in progress, a temporary label for incomplete or ongoing work

Changelog Entry

Description

Fixes this bug presented in https://github.com/open-webui/open-webui/issues/18294 .

See "Additional information" for technical details.

Added

None

Changed

None

Deprecated

None

Removed

None

Fixed

Fixes issue https://github.com/open-webui/open-webui/issues/18294

Security

None

Breaking Changes

None


Additional Information

Before, as the contents were not escaped, the block had some troubles deciding which one is the actual <details> block. The main reason was because the serialization of reasoning blocks in middleware.py is not escaped.

This is different from tool_calls that already do it:

                                if tool_result is not None:
                                    tool_result_embeds = result.get("embeds", "")
                                    tool_calls_display_content = f'{tool_calls_display_content}<details type="tool_calls" done="true" id="{tool_call_id}" name="{tool_name}" arguments="{html.escape(json.dumps(tool_arguments))}" result="{html.escape(json.dumps(tool_result, ensure_ascii=False))}" files="{html.escape(json.dumps(tool_result_files)) if tool_result_files else ""}" embeds="{html.escape(json.dumps(tool_result_embeds))}">\n<summary>Tool Executed</summary>\n</details>\n'
                                else:
                                    tool_calls_display_content = f'{tool_calls_display_content}<details type="tool_calls" done="false" id="{tool_call_id}" name="{tool_name}" arguments="{html.escape(json.dumps(tool_arguments))}">\n<summary>Executing...</summary>\n</details>\n'

or code_interpreter that does it too:

                        if output:
                            output = html.escape(json.dumps(output))

                            if raw:
                                content = f'{content}<code_interpreter type="code" lang="{lang}">\n{block["content"]}\n</code_interpreter>\n```output\n{output}\n```\n'
                            else:
                                content = f'{content}<details type="code_interpreter" done="true" output="{output}">\n<summary>Analyzed</summary>\n```{lang}\n{block["content"]}\n```\n</details>\n'
                        else:
                            if raw:
                                content = f'{content}<code_interpreter type="code" lang="{lang}">\n{block["content"]}\n</code_interpreter>\n'
                            else:
                                content = f'{content}<details type="code_interpreter" done="false">\n<summary>Analyzing...</summary>\n```{lang}\n{block["content"]}\n```\n</details>\n'

By following the same logic to perform HTML escape in the reasoning part, i.e. adding:

escaped_reasoning_display_content = html.escape(reasoning_display_content)

and properly decoding it at the frontend, this problem is solved.

Screenshots or Videos

https://github.com/user-attachments/assets/1990b9a8-d7be-414c-9b0d-5a2babaa30ca

image

Contributor License Agreement

By submitting this pull request, I confirm that I have read and fully agree to the Contributor License Agreement (CLA), and I am providing my contributions under its terms.


🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.

## 📋 Pull Request Information **Original PR:** https://github.com/open-webui/open-webui/pull/18840 **Author:** [@acomarcho](https://github.com/acomarcho) **Created:** 11/1/2025 **Status:** ❌ Closed **Base:** `dev` ← **Head:** `fix/details-tag-for-reasoning-not-identified` --- ### 📝 Commits (1) - [`867d0cf`](https://github.com/open-webui/open-webui/commit/867d0cfd5f05960385d06f486b060bb758e96833) fix: <details> tags for reasoning not identified if tag is present in user message ### 📊 Changes **2 files changed** (+15 additions, -3 deletions) <details> <summary>View changed files</summary> 📝 `backend/open_webui/utils/middleware.py` (+4 -2) 📝 `src/lib/components/chat/Messages/Markdown/MarkdownTokens.svelte` (+11 -1) </details> ### 📄 Description # Pull Request Checklist ### Note to first-time contributors: Please open a discussion post in [Discussions](https://github.com/open-webui/open-webui/discussions) and describe your changes before submitting a pull request. **Before submitting, make sure you've checked the following:** - [x] **Target branch:** Verify that the pull request targets the `dev` branch. Not targeting the `dev` branch may lead to immediate closure of the PR. - [x] **Description:** Provide a concise description of the changes made in this pull request. - [x] **Changelog:** Ensure a changelog entry following the format of [Keep a Changelog](https://keepachangelog.com/) is added at the bottom of the PR description. - [x] **Documentation:** If necessary, update relevant documentation [Open WebUI Docs](https://github.com/open-webui/docs) like environment variables, the tutorials, or other documentation sources. - [x] **Dependencies:** Are there any new dependencies? Have you updated the dependency versions in the documentation? - [x] **Testing:** Perform manual tests to verify the implemented fix/feature works as intended AND does not break any other functionality. Take this as an opportunity to make screenshots of the feature/fix and include it in the PR description. - [x] **Agentic AI Code:**: Confirm this Pull Request is **not written by any AI Agent** or has at least gone through additional human review **and** manual testing. If any AI Agent is the co-author of this PR, it may lead to immediate closure of the PR. - [x] **Code review:** Have you performed a self-review of your code, addressing any coding standard issues and ensuring adherence to the project's coding standards? - [x] **Title Prefix:** To clearly categorize this pull request, prefix the pull request title using one of the following: - **BREAKING CHANGE**: Significant changes that may affect compatibility - **build**: Changes that affect the build system or external dependencies - **ci**: Changes to our continuous integration processes or workflows - **chore**: Refactor, cleanup, or other non-functional code changes - **docs**: Documentation update or addition - **feat**: Introduces a new feature or enhancement to the codebase - **fix**: Bug fix or error correction - **i18n**: Internationalization or localization changes - **perf**: Performance improvement - **refactor**: Code restructuring for better maintainability, readability, or scalability - **style**: Changes that do not affect the meaning of the code (white space, formatting, missing semi-colons, etc.) - **test**: Adding missing tests or correcting existing tests - **WIP**: Work in progress, a temporary label for incomplete or ongoing work # Changelog Entry ### Description Fixes this bug presented in https://github.com/open-webui/open-webui/issues/18294 . See "Additional information" for technical details. ### Added None ### Changed None ### Deprecated None ### Removed None ### Fixed Fixes issue https://github.com/open-webui/open-webui/issues/18294 ### Security None ### Breaking Changes None --- ### Additional Information Before, as the contents were not escaped, the block had some troubles deciding which one is the actual `<details>` block. The main reason was because the serialization of reasoning blocks in `middleware.py` is not escaped. This is different from tool_calls that already do it: ```py if tool_result is not None: tool_result_embeds = result.get("embeds", "") tool_calls_display_content = f'{tool_calls_display_content}<details type="tool_calls" done="true" id="{tool_call_id}" name="{tool_name}" arguments="{html.escape(json.dumps(tool_arguments))}" result="{html.escape(json.dumps(tool_result, ensure_ascii=False))}" files="{html.escape(json.dumps(tool_result_files)) if tool_result_files else ""}" embeds="{html.escape(json.dumps(tool_result_embeds))}">\n<summary>Tool Executed</summary>\n</details>\n' else: tool_calls_display_content = f'{tool_calls_display_content}<details type="tool_calls" done="false" id="{tool_call_id}" name="{tool_name}" arguments="{html.escape(json.dumps(tool_arguments))}">\n<summary>Executing...</summary>\n</details>\n' ``` or `code_interpreter` that does it too: ```py if output: output = html.escape(json.dumps(output)) if raw: content = f'{content}<code_interpreter type="code" lang="{lang}">\n{block["content"]}\n</code_interpreter>\n```output\n{output}\n```\n' else: content = f'{content}<details type="code_interpreter" done="true" output="{output}">\n<summary>Analyzed</summary>\n```{lang}\n{block["content"]}\n```\n</details>\n' else: if raw: content = f'{content}<code_interpreter type="code" lang="{lang}">\n{block["content"]}\n</code_interpreter>\n' else: content = f'{content}<details type="code_interpreter" done="false">\n<summary>Analyzing...</summary>\n```{lang}\n{block["content"]}\n```\n</details>\n' ``` By following the same logic to perform HTML escape in the reasoning part, i.e. adding: ```py escaped_reasoning_display_content = html.escape(reasoning_display_content) ``` and properly decoding it at the frontend, this problem is solved. ### Screenshots or Videos https://github.com/user-attachments/assets/1990b9a8-d7be-414c-9b0d-5a2babaa30ca <img width="1239" height="379" alt="image" src="https://github.com/user-attachments/assets/752521fb-a5d7-4e75-afc9-ae267e00e18a" /> ### Contributor License Agreement By submitting this pull request, I confirm that I have read and fully agree to the [Contributor License Agreement (CLA)](https://github.com/open-webui/open-webui/blob/main/CONTRIBUTOR_LICENSE_AGREEMENT), and I am providing my contributions under its terms. --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>
GiteaMirror added the pull-request label 2025-11-11 19:57:02 -06:00
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/open-webui#11785