[PR #15202] [CLOSED] Thinking mode feature #111064

New Issue

GiteaMirror · 2026-05-18T10:48:56-05:00

GiteaMirror commented

2026-05-18 10:48:56 -05:00

📋 Pull Request Information

Original PR: https://github.com/open-webui/open-webui/pull/15202
Author: @shua-ie
Created: 6/21/2025
Status: ❌ Closed

Base: dev ← Head: thinking-mode-feature

📝 Commits (1)

6bb677c Add thinking mode toggle for Ollama thinking models

📊 Changes

15 files changed (+126 additions, -26 deletions)

View changed files

📝 src/lib/apis/index.ts (+3 -3)
📝 src/lib/apis/ollama/index.ts (+1 -1)
📝 src/lib/apis/users/index.ts (+1 -1)
📝 src/lib/components/admin/Settings/Models.svelte (+2 -2)
📝 src/lib/components/chat/Chat.svelte (+22 -0)
📝 src/lib/components/chat/MessageInput.svelte (+75 -2)
📝 src/lib/components/chat/MessageInput/CallOverlay.svelte (+1 -1)
📝 src/lib/components/chat/Placeholder.svelte (+2 -0)
📝 src/lib/components/chat/Settings/Audio.svelte (+1 -1)
📝 src/lib/i18n/index.ts (+2 -2)
📝 src/lib/i18n/locales/en-US/translation.json (+3 -0)
📝 src/lib/utils/characters/index.ts (+5 -5)
📝 src/lib/utils/marked/katex-extension.ts (+6 -6)
📝 src/lib/workers/kokoro.worker.ts (+1 -1)
📝 src/lib/workers/pyodide.worker.ts (+1 -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.

https://github.com/open-webui/open-webui/discussions/15201

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

[ x] Target branch: Please verify that the pull request targets the dev branch.
[ 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 is added at the bottom of the PR description.
Documentation: Have you updated relevant documentation Open WebUI Docs, or other documentation sources?
[ x] Dependencies: Are there any new dependencies? Have you updated the dependency versions in the documentation?
[ x] Testing: Have you written and run sufficient tests to validate the changes?
[ 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 ] Prefix: To clearly categorize this pull request, prefix the pull request title using one of the following:
- feat: Introduces a new feature or enhancement to the codebase

Overview

This PR adds a thinking mode toggle for compatible Ollama models that support the thinking feature. The toggle appears only for thinking-capable models (deepseek-r1, qwen3, magistral) and sends the appropriate API payload to enable thinking mode.

Technical Implementation

Model Detection: Filters models by name to identify thinking-capable Ollama models
API Integration: Sends {"options": {"thinking": true}} payload only for compatible Ollama models
UI/UX: Consistent styling with existing toggles (web search, image generation, code interpreter)
Visual Feedback: Blue indicator banner with animated brain icon when thinking mode is active
State Management: Integrates with existing chat input persistence and resets appropriately

Changelog Entry

Description

Added a thinking mode toggle feature for Ollama models that support thinking capabilities. The toggle appears only for compatible models (deepseek-r1, qwen3, magistral) and sends the appropriate thinking option in the API payload when enabled. Includes visual feedback and proper state management integration.

Added

Thinking mode toggle button in MessageInput component for compatible Ollama models
Visual indicator banner when thinking mode is active with animated brain icon
Model compatibility detection for thinking-capable models (deepseek-r1, qwen3, magistral)
Internationalization support for thinking mode UI elements
State management integration for thinking mode persistence

Changed

Modified MessageInput.svelte to include thinking mode toggle and state management
Updated Chat.svelte to send thinking option in API payload for compatible Ollama models
Enhanced Placeholder.svelte to pass through thinking mode state
Added new translation strings to en-US/translation.json for thinking mode

Deprecated

None

Removed

None

Fixed

[List any fixes, corrections, or bug fixes]

Security

None

Breaking Changes

BREAKING CHANGE: None

Additional Information

Feature is currently only available for Ollama thinking-capable models as specified
Toggle gracefully hides for non-compatible models ensuring backward compatibility
No breaking changes to existing functionality or API endpoints
Implementation follows existing patterns for similar toggle features (web search, image generation)

Screenshots or Videos

Thinking Available model:

Thinking unavailable model:

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/15202 **Author:** [@shua-ie](https://github.com/shua-ie) **Created:** 6/21/2025 **Status:** ❌ Closed **Base:** `dev` ← **Head:** `thinking-mode-feature` --- ### 📝 Commits (1) - [`6bb677c`](https://github.com/open-webui/open-webui/commit/6bb677c9b396c0ac1c0aa4f607509b1ec672800a) Add thinking mode toggle for Ollama thinking models ### 📊 Changes **15 files changed** (+126 additions, -26 deletions) <details> <summary>View changed files</summary> 📝 `src/lib/apis/index.ts` (+3 -3) 📝 `src/lib/apis/ollama/index.ts` (+1 -1) 📝 `src/lib/apis/users/index.ts` (+1 -1) 📝 `src/lib/components/admin/Settings/Models.svelte` (+2 -2) 📝 `src/lib/components/chat/Chat.svelte` (+22 -0) 📝 `src/lib/components/chat/MessageInput.svelte` (+75 -2) 📝 `src/lib/components/chat/MessageInput/CallOverlay.svelte` (+1 -1) 📝 `src/lib/components/chat/Placeholder.svelte` (+2 -0) 📝 `src/lib/components/chat/Settings/Audio.svelte` (+1 -1) 📝 `src/lib/i18n/index.ts` (+2 -2) 📝 `src/lib/i18n/locales/en-US/translation.json` (+3 -0) 📝 `src/lib/utils/characters/index.ts` (+5 -5) 📝 `src/lib/utils/marked/katex-extension.ts` (+6 -6) 📝 `src/lib/workers/kokoro.worker.ts` (+1 -1) 📝 `src/lib/workers/pyodide.worker.ts` (+1 -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. - https://github.com/open-webui/open-webui/discussions/15201 **Before submitting, make sure you've checked the following:** - [ x] **Target branch:** Please verify that the pull request targets the `dev` branch. - [ 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. - [ ] **Documentation:** Have you updated relevant documentation [Open WebUI Docs](https://github.com/open-webui/docs), or other documentation sources? - [ x] **Dependencies:** Are there any new dependencies? Have you updated the dependency versions in the documentation? - [ x] **Testing:** Have you written and run sufficient tests to validate the changes? - [ 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 ] **Prefix:** To clearly categorize this pull request, prefix the pull request title using one of the following: - **feat**: Introduces a new feature or enhancement to the codebase ## Overview This PR adds a thinking mode toggle for compatible Ollama models that support the thinking feature. The toggle appears only for thinking-capable models (deepseek-r1, qwen3, magistral) and sends the appropriate API payload to enable thinking mode. ## Technical Implementation - **Model Detection**: Filters models by name to identify thinking-capable Ollama models - **API Integration**: Sends `{"options": {"thinking": true}}` payload only for compatible Ollama models - **UI/UX**: Consistent styling with existing toggles (web search, image generation, code interpreter) - **Visual Feedback**: Blue indicator banner with animated brain icon when thinking mode is active - **State Management**: Integrates with existing chat input persistence and resets appropriately # Changelog Entry ### Description Added a thinking mode toggle feature for Ollama models that support thinking capabilities. The toggle appears only for compatible models (deepseek-r1, qwen3, magistral) and sends the appropriate thinking option in the API payload when enabled. Includes visual feedback and proper state management integration. ### Added - Thinking mode toggle button in MessageInput component for compatible Ollama models - Visual indicator banner when thinking mode is active with animated brain icon - Model compatibility detection for thinking-capable models (deepseek-r1, qwen3, magistral) - Internationalization support for thinking mode UI elements - State management integration for thinking mode persistence ### Changed - Modified MessageInput.svelte to include thinking mode toggle and state management - Updated Chat.svelte to send thinking option in API payload for compatible Ollama models - Enhanced Placeholder.svelte to pass through thinking mode state - Added new translation strings to en-US/translation.json for thinking mode ### Deprecated - None ### Removed - None ### Fixed - [List any fixes, corrections, or bug fixes] ### Security - None ### Breaking Changes - **BREAKING CHANGE**: None --- ### Additional Information - Feature is currently only available for Ollama thinking-capable models as specified - Toggle gracefully hides for non-compatible models ensuring backward compatibility - No breaking changes to existing functionality or API endpoints - Implementation follows existing patterns for similar toggle features (web search, image generation) ### Screenshots or Videos Thinking Available model: ![Screenshot-1](https://github.com/user-attachments/assets/90ff4075-847e-4fa5-98fb-2e6d7f852fa5) Thinking unavailable model: ![Screenshot-3](https://github.com/user-attachments/assets/27d3ae68-a94c-41fc-9be1-cde9fabace47) ### Contributor License Agreement By submitting this pull request, I confirm that I have read and fully agree to the [Contributor License Agreement (CLA)](/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 2026-05-18 10:48:56 -05:00

GiteaMirror closed this issue

2026-05-18 10:48:59 -05:00

Sign in to join this conversation.

Branches Tags

1 Participants

Notifications

Due Date

No due date set.

Dependencies

No dependencies set.

Reference: github-starred/open-webui#111064