Open WebUI Release Notes

Added

• 🔐 Custom OIDC logout endpoint. Administrators can now configure a custom OpenID Connect logout URL via OPENID_END_SESSION_ENDPOINT, enabling logout functionality for OIDC providers that require custom endpoints like AWS Cognito. Commit
• 🗄️ MariaDB Vector community support. Added MariaDB Vector as a new vector database backend, enabling deployments with VECTOR_DB=mariadb-vector; supports cosine and euclidean distance strategies with configurable HNSW indexing. #21931
• 📝 Task message truncation. Chat messages sent to task models for title and tag generation can now be truncated using a filter in the prompt template, reducing token usage and processing time for long conversations. #21499
• 🔄 General improvements. Various improvements were implemented across the application to enhance performance, stability, and security.
• 🌐 Translations for Portuguese (Brazil), Spanish, and Malay were enhanced and expanded.

Fixed

• 🔗 Pipeline filter HTTP errors. Fixed a bug where HTTP errors in pipeline inlet/outlet filters would silently corrupt the user's chat payload; errors are now properly raised before parsing the response. #22445
• 📚 Knowledge file embedding updates. Fixed a bug where updating knowledge files left old embeddings in the database, causing search results to include duplicate and stale data. #20558
• 📁 Files list stability. Fixed the files list ordering to use created_at with id as secondary sort, ensuring consistent ordering and preventing page crashes when managing many files. #21879
• 📨 Teams webhook crash. Fixed a TypeError crash in the Teams webhook handler when user data is missing from the event payload. #22444
• 🛠️ Process shutdown handling. Fixed bare except clauses in the main process that prevented clean shutdown; replaced with proper exception handling. #22423
• 🐳 Docker deployment startup. Docker deployments now start correctly; the missing OpenTelemetry system metrics dependency was added. #22447, #22401
• 🛠️ Tool access for non-admin users. Fixed a NameError that prevented non-admin users from viewing tools; the missing has_access function is now properly imported. #22393
• 🔐 OAuth error handling. Fixed a bug where bare except clauses silently caught SystemExit and KeyboardInterrupt, preventing clean process shutdown during OAuth authentication. #22420
• 🛠️ Exception error messages. Fixed three locations where incorrect exception raising caused confusing TypeError messages instead of proper error descriptions, making debugging much easier. #22446
• 📄 YAML file processing. Fixed an error when uploading YAML files with Docling enabled; YAML and YML files are now properly recognized as text files and processed correctly. #22399, #22263
• 📅 Time range month names. Fixed month names in time range labels appearing in the wrong language when OS regional settings differ from browser language; month names now consistently display in English. #22454
• 🔐 OAuth error URL encoding. Fixed OAuth error messages with special characters causing malformed redirect URLs; error messages are now properly URL-encoded. #22415
• 🛠️ Internal tool method filtering. Tools no longer expose internal methods starting with underscore to the LLM, reducing clutter and improving accuracy. #22408
• 🔊 Azure TTS locale extraction. Fixed Azure text-to-speech using incomplete locale codes in SSML; now correctly uses full locale like "en-US" instead of just "en". #22443
• 🎤 Azure speech transcription errors. Improved Azure AI Speech error handling to display user-friendly messages instead of generic connection errors; empty transcripts, no language identified, and other Azure-specific errors now show clear descriptions. #20485
• 📊 Analytics group filtering. Fixed token usage analytics not being filtered by user group; the query now properly respects group filters like other analytics metrics. #22167
• 🔍 Web search favicon fallback. Fixed web search sources showing broken image icons when favicons couldn't be loaded from external sources; now falls back to the default Open WebUI favicon. #21897
• 🔄 Custom model fallback. Fixed custom model fallback not working when the base model is unavailable; the base model ID is now correctly retrieved from model info instead of empty params. #22456
• 🖼️ Pending message image display. Fixed images in queued messages appearing blank; image thumbnails are now properly displayed in the pending message queue. #22256
• 🛠️ File metadata sanitization. Fixed file uploads failing with JSON serialization errors when metadata contained non-serializable objects like callable functions; metadata is now sanitized before database insertion. #20561

Added

• ▶️ Open Terminal notebook cell execution. Users can now run Jupyter Notebook code cells directly in the Open Terminal file navigator, execute entire notebooks with a single click, edit and modify cells before running, and control the kernel - bringing full interactive notebook execution to the browser. Commit
• 🗃️ Open Terminal SQLite browser. Users can now browse SQLite database files directly in the Open Terminal file navigator, viewing tables and running queries without downloading them first. Commit
• 📉 Open Terminal Mermaid diagram rendering. Markdown files with Mermaid code blocks are now rendered as diagrams directly in the Open Terminal file navigator, making it easier to visualize flowcharts and other diagrams. Commit
• 📓 Open Terminal Jupyter Notebook previews. Users can now preview Jupyter Notebook files directly in the Open Terminal file navigator, making it easier to view notebook content without downloading them first. Commit
• 🔃 Open Terminal auto-refresh. The Open Terminal file navigator now automatically refreshes when the model writes or modifies files, keeping the view in sync without manual refresh. Commit
• 📎 Open Terminal file copy button. Users can now copy file contents directly to clipboard in the Open Terminal file navigator with a single click, making it easier to quickly grab file content without downloading. Commit
• 💻 Code syntax highlighting and XLSX improvements in Open Terminal. Code files now display with syntax highlighting in the Open Terminal file navigator, and XLSX spreadsheets now show column headers and row numbers for easier navigation. Commit
• 🌳 Open Terminal JSON tree view. JSON, JSONC, JSONL, and JSON5 files now display as interactive collapsible tree views in the Open Terminal file navigator, and SVG files render as preview images with syntax highlighting support. Commit
• 🛜 Open Terminal port viewing. Users can now view listening ports in the Open Terminal file navigator and open proxy connections to them directly from the UI. Commit
• 🎬 Open Terminal video previews. Users can now preview video and audio files directly in the Open Terminal file navigator, making it easier to view media without downloading them first. Commit
• ✏️ Open Terminal HTML editing. Users can now edit HTML source files in Open Terminal with CodeMirror editor, and the save button is properly hidden in preview mode. Commit
• 📄 Open Terminal DOCX preview. Word documents generated or modified by the AI can now be viewed directly in the file navigator with formatted text, tables, and images rendered inline — no need to download and open in a separate application. Commit
• 📊 Open Terminal XLSX preview. Excel spreadsheets in the file navigator now render as interactive tables with column headers and row numbers, making it easy to verify data the AI has generated or processed. Commit
• 📽️ Open Terminal PPTX preview. PowerPoint presentations created by the AI can now be viewed slide-by-slide directly in the file navigator, enabling quick review and iteration without leaving the browser. Commit
• 📁 Pyodide file system support. Users can now upload files for Python code execution in the code interpreter. Uploaded files are available in the /mnt/uploads/ directory, and code can write output files there for download. The file system persists across code executions within the same session. The code interpreter now also informs models that pip install is not available in the Pyodide environment, guiding them to use alternative approaches with available modules. #3583, Commit, Commit
• 🧰 Tool files access. Tools can now access the files from the current chat context via the files property in their metadata, enabling more powerful tool integrations. Commit
• ⚡ Chat performance. Chat messages now load and display significantly faster thanks to optimized markdown rendering, eliminating delays when viewing messages with mathematical expressions. #22196, #20878
• 📜 Message list performance. Improved message list rendering performance by optimizing array operations, reducing complexity from O(n²) to O(n). #22280
• 🧵 Streaming markdown performance. Improved chat responsiveness during streaming by skipping unnecessary markdown re-parsing when the content hasn't changed, eliminating wasted processing during model pauses. #22183
• 🏃 Chat streaming performance. Chat streaming is now faster for users not using the voice call feature by skipping unnecessary text parsing that was running on every token. #22195
• 🔖 Source list performance. Source lists in chat now render faster thanks to optimized computation that avoids unnecessary recalculations, including moving sourceIds computation to a reactive variable. #22279, Commit, Commit
• 💨 Chat message tree operations. Chat message tree operations are now significantly faster, improving overall chat responsiveness. #22194
• 🚀 Initial page load speed. Page load is now significantly faster thanks to deferred loading of the syntax highlighting library, reducing the initial JavaScript bundle by several megabytes. #22304
• 🗓️ Action priority query optimization. Improved performance of action priority resolution by fixing an N+1 query pattern, reducing database round-trips when loading model actions. #22301
• 🔑 API key middleware optimization. The API key restriction middleware was converted to a pure ASGI middleware for improved streaming performance, removing per-chunk call overhead. #22188
• 🏎️ Model list loading performance. Model lists now load significantly faster thanks to optimized custom model matching that uses dictionary lookups instead of nested loops. #22299, Commit, Commit
• ⏱️ Event call timeout configuration. Administrators can now configure the WebSocket event call timeout via the WEBSOCKET_EVENT_CALLER_TIMEOUT environment variable, giving users more time to respond to event_call forms instead of timing out after 60 seconds. #22222, #22220
• 🔁 File refresh button visibility. The refresh button in the chat file navigator now appears when viewing files as well as directories, allowing users to refresh the file view at any time. Commit
• 📂 Nested folders support. Users can now create subfolders within parent folders, improving organization of chats. A new "Create Subfolder" option is available in the folder context menu. #22073, Commit
• 🔔 Banner loading on navigation. Admin-configured banners now load when navigating to the homepage, not just on page refresh, ensuring users see new banners immediately. #22340, #22180
• 📡 System metrics via OpenTelemetry. Administrators can now monitor Python runtime and system metrics including CPU, memory, garbage collection, and thread counts through the existing OpenTelemetry pipeline. #22265
• 🔄 General improvements. Various improvements were implemented across the application to enhance performance, stability, and security.
• 🌐 Translations for French, Finnish, Turkish, German, Simplified Chinese, and Traditional Chinese were enhanced and expanded.
• 🔍 Web search tool guidance. The web search tool description was updated to encourage direct usage without first checking knowledge bases, making it clearer for users who want to search the web immediately. #22264

Fixed

• 🗄️ Migration memory usage. Database migration on large deployments now processes messages in batches instead of loading everything into memory, preventing out-of-memory errors during upgrades. #21542, #21539
• 🔒 SQLCipher connection stability. Fixed a crash that occurred when using database encryption with SQLCipher by changing the default connection pool behavior, ensuring stable operation during multi-threaded operations like user signup. #22273, #22258
• 🛑 Stop sequence error. Fixed a bug where setting stop sequences on a model caused the chat to fail with a split error, preventing any responses from being returned. The fix handles both string and array formats for stop tokens. #22251, Commit
• 🔐 Microsoft OAuth refresh token fix. Fixed a bug where Microsoft OAuth refresh token requests failed with error AADSTS90009 by adding support for the required scope parameter. Users can now stay logged in reliably with Microsoft OAuth. #22359
• 🛠️ Parameterless tool calls. Fixed parameterless tool calls failing during streaming by correcting the default arguments initialization, eliminating unnecessary model retries. #22189
• 🔧 Tool call streaming fixes. Fixed two bugs where streaming tool calls failed silently for models like GPT-5: function names were incorrectly duplicated when sent in multiple delta chunks, and arguments containing multiple JSON objects were not properly split. Tools now execute correctly instead of failing without explanation. #22177, Commit, Commit
• 🔗 Tool server URL trailing slash. Fixed tool server connection failures when URLs have trailing slashes by stripping them before path concatenation. Previously, URLs like "http://host:8080/v1/" + "/openapi.json" produced double-slash URLs that some servers rejected. #22116, #21917
• 🛡️ Citation parser error handling. Fixed crashes when tools return error strings instead of expected data structures by adding type guards to the citation parser. The system now returns an empty source list instead of crashing with AttributeError. #22118
• 🧠 Artifacts memory leak. Fixed a memory leak where Svelte store subscriptions in the Artifacts component were not properly cleaned up when the component unmounted, causing memory to accumulate over time. #22303
• ♾️ Artifacts reactive loop fix. Fixed an infinite reactive loop in chat when artifacts are present by moving the animation frame logic outside the reactive block, preventing continuous re-rendering and CPU usage. #22238, Commit
• 🔀 Artifact navigation. Artifact navigation via arrow buttons now works correctly; the selected artifact is no longer reset when content updates. #22239
• 🧩 Artifact thinking block fix. Fixed a bug where HTML preview rendered code blocks inside thinking blocks for certain models like Mistral and Z.ai, causing stray code with ">" symbols to appear before the actual artifact. The fix strips thinking blocks before extracting code for artifact rendering. #22267, Commit
• 💬 Floating Quick Actions availability. Fixed an issue where the "Ask" and "Explain" Floating Quick Actions were missing when selecting text in chats that used a model that is no longer available. #22149, #22139
• 💡 Follow-up suggestions. Fixed follow-up suggestions not appearing by correcting contradictory format instructions in the prompt template, ensuring the LLM returns the correct JSON object format. #22212
• 🔊 TTS thinking content. Fixed TTS playback reading think tags instead of skipping them by handling edge cases where code blocks inside thinking content prevented proper tag removal. #22237, #22197
• 🎨 Button spinner alignment. Button spinners across multiple modals now align correctly and stay on the same line as the button text, fixing layout issues when loading states are displayed. #22227
• 📶 Terminal keepalive. Terminal connections now stay active without being closed by idle timeouts from proxies or load balancers, and spurious disconnection messages no longer appear. Commit
• 📥 Chat archive handler. The archive button in the chat navbar now actually archives the chat and refreshes the chat list, instead of doing nothing. #22229
• 🐍 BeautifulSoup4 dependency. Added the missing BeautifulSoup4 package to backend requirements, fixing failures when using features that depend on HTML parsing. #22231
• 👥 Group users default sort. Group members in the admin panel now sort by last active time by default instead of creation date, making it easier to find active users. #22211
• 🔓 Tool access permissions. Users can now change tool and skill access permissions from private to public without errors. #22325, #22324
• 🖥️ Open Terminal permission fix. Open Terminal is now visible without requiring "Allow Speech to Text" permission, fixing an issue where users without microphone access couldn't access the terminal feature. #22374, Commit
• 📌 Stale pinned models cleanup. Pinned models that are deleted or hidden are now automatically unpinned, keeping your pinned models list up to date. Commit
• 📏 OpenTelemetry metric descriptions. Fixed conflicting metric instrument descriptions that caused warnings in the OpenTelemetry collector, resulting in cleaner telemetry logs for administrators. #22293
• 🔢 Non-streaming token tracking. Token usage from non-streaming chat responses is now correctly saved to the database, fixing missing token counts in the Admin Panel analytics. Previously, non-streaming responses saved NULL usage data, causing messages to be excluded from token aggregation queries. #22166
• ⌨️ Inline code typing. Fixed a bug where typing inline code with backticks incorrectly deleted the character immediately before the opening backtick, so text formatted as inline code now correctly produces the full word instead of missing the last character. #20417, Commit
• 📝 Variable input newlines. Fixed a bug where variables containing newlines were not displayed correctly in chat messages, and input values from Windows systems are now properly normalized to use standard line endings. #21447, Commit
• 📷 Android photo capture. Fixed an issue where the first photo taken in chat appeared completely black on some Android devices by using an alternative canvas export method. #22317
• 🪟 Open Terminal Windows path fix. Fixed a bug where navigating back to parent directories on Windows added an incorrect leading slash, causing directory loads to fail. Paths are now properly normalized for Windows drive letters. #22352, Commit
• 🖼️ Chat overview profile image sizing. Fixed a bug where profile images in the chat overview could shrink incorrectly in tight spaces. The images now maintain their proper size with the flex-shrink-0 property. #22261
• 📨 Queued messages display. Fixed an issue where queued messages could be cut off or hidden. The queued messages area now scrolls properly when content exceeds the visible area, showing up to 25% of the viewport height. #22176
• 🖌️ Image generation in temporary chats. Generated images now display correctly in temporary chat mode when using builtin image generation tools. Previously, images were not shown because the code was overwriting the image list with a null database response. #22330, #22309
• 🤖 Ollama model unload fix. Fixed a bug where unloading a model from Ollama via the Open WebUI proxy failed with a "Field required" error for the prompt field. The proxy now correctly allows omitting the prompt when using keep_alive: 0 to unload models. #22260, Commit
• 🏷️ Banner type dropdown fix. Fixed a bug where selecting a banner type required two clicks to register, as the first selection was being swallowed due to DOM structure changes. The dropdown now works correctly on the first click. #22378
• 📈 Analytics URL encoding fix. Fixed a bug where the Analytics page failed to load data for models with slashes in their ID, such as "anthropic/claude-opus-4.6". The frontend now properly URL-encodes forward slashes, allowing model analytics to load correctly. #22380, #22382
• 📋 Analytics chat list duplicate fix. Fixed a bug where the Analytics page chat list threw an "each_key_duplicate" Svelte error when chat IDs were duplicated during pagination. The fix adds deterministic ordering to prevent duplicate entries. #22383
• 📂 Folder knowledge base native tool call fix. Fixed a bug where folders with attached knowledge bases were querying the knowledge base twice when using native tool call mode. The fix now correctly separates knowledge files from regular attachments, letting the builtin query_knowledge_files tool handle knowledge searches instead of duplicating RAG queries. #22236, Commit, Commit

[0.8.8] - 2026-03-02

Added

• 📁 Open Terminal file moving. Users can now move files and folders between directories in the Open Terminal file browser by dragging and dropping them. Commit, Commit, Commit, Commit
• 📄 Open Terminal HTML file preview. Users can now preview HTML files directly in the Open Terminal file browser, with a rendered iframe view and source toggle, enabling iterative AI editing of HTML files. Commit, Commit
• 🌐 Open Terminal WebSocket proxy. Added a new WebSocket proxy endpoint for interactive terminal sessions, enabling real-time bidirectional terminal communication with the terminal server. Commit
• ⚙️ Open Terminal feature toggle. Administrators can now enable or disable the Interactive Terminal feature for Open Terminal via configuration on the terminal server, controlling access to terminal routes. Commit
• 🔄 General improvements. Various improvements were implemented across the application to enhance performance, stability, and security.
• 🌐 Translations for Simplified Chinese, Traditional Chinese, Irish, and Catalan were enhanced and expanded.

Fixed

• 🔧 Middleware variable shadowing. Fixed a variable shadowing issue in the middleware that could cause incorrect tool output processing during chat. #22145
• ⚡ ChatControls reactivity fix. Fixed a Svelte reactivity issue where the active tab state in the ChatControls panel was not properly saved when switching between chats. #22127
• 🔧 ChatControls TypeScript fix. Fixed a TypeScript syntax error in ChatControls.svelte where the module script block was missing lang="ts", causing esbuild to fail during vite dev. #22131
• 🔌 Open Terminal tools for direct connections. Fixed an issue where Open Terminal tools were not available to the model when the terminal was configured via direct connection settings, ensuring users can now interact with terminal files and operations through the AI. #22137
• 📜 Chat history pagination. Fixed an issue where older messages in long chats were not loaded when scrolling to the top. Commit, Commit
• 🔧 Terminal tool null parameter handling. Fixed a bug where null parameters in terminal tool calls were sent as the string "None" instead of being omitted, causing 422 validation errors from the open-terminal server. #22124, #22144

Changed

[0.8.7] - 2026-03-01

Fixed

• 🔒 Connection access control privacy. Tool server and terminal connections without explicit access grants are now private (admin-only) by default, fixing a bug where connections configured with no access grants were visible to all users instead of being restricted. Commit
• 🧠 ChatControls memory leak. The ChatControls panel no longer leaks event listeners, ResizeObserver instances, and media query handlers when navigating between chats, fixing memory accumulation that could degrade performance during extended use. #22112
• 💾 Temporary chat params preservation. Model parameters are now correctly saved when creating a temporary chat, ensuring custom settings like temperature and top_p persist across the session. Commit
• ⚡ Faster artifact content updates. Artifact content extraction during streaming is now debounced via requestAnimationFrame, reducing redundant DOM reads and improving CPU efficiency when tokens arrive faster than the browser can paint. Commit

[0.8.6] - 2026-03-01

Added

• 🖥️ Open Terminal integration. Users can now connect to Open Terminal instances to browse, read, and upload files directly in chat, with the terminal acting as an always-on tool. File navigation includes folder browsing, image and PDF previews, drag-and-drop uploads, directory creation, and file deletion. The current working directory is automatically injected into tool descriptions for context-aware commands. Commit, Commit, Commit
• 📄 Terminal file creation. Users can now create new empty files directly in the Open Terminal file browser, in addition to the existing folder creation functionality. Commit
• ✏️ Terminal file editing. Users can now edit text files directly in the Open Terminal file browser, with the ability to save changes back to the terminal. Commit
• 🛠️ Terminal file preview toolbar. The Open Terminal file browser now displays contextual toolbar buttons based on file type, including preview/source toggle for Markdown and CSV files, reset view for images, and improved editing controls for text files. Commit
• 🔄 Terminal file write refresh. The file browser now automatically refreshes when files are written or modified via the write_file or replace_file_content tools, eliminating the need to manually refresh. Commit
• 🛡️ Docker image SBOM attestation. Docker images now include a Software Bill of Materials (SBOM) for vulnerability scanning and supply chain security compliance. #21779, Commit
• 📡 Reporting-Endpoints security header. Administrators can now configure a Reporting-Endpoints header via the REPORTING_ENDPOINTS environment variable to receive CSP violation reports directly, aiding in security policy debugging and hardening. #21830
• 🎯 Action button priority sorting. Action buttons under assistant messages now appear in a consistent order based on the priority field from function Valves, allowing developers to control button placement. #21790
• 🏷️ Public/Private model filtering. The Admin Settings Model listing now displays Public/Private badges and includes filter options to easily view public or private models. #21732, #21797
• 👁️ Show/Hide all models bulk action. Administrators can now show or hide all models at once from the Admin Settings Models page Actions menu, making it faster to manage model visibility. Bulk actions now display a single toast notification on success for better user feedback. #21838, #21958
• 🔐 Individual user sharing control. Administrators can now disable individual user sharing via the USER_PERMISSIONS_ACCESS_GRANTS_ALLOW_USERS environment variable, allowing only group-based sharing when set to false. #21793, Commit, Commit
• 🔄 OAuth profile sync on login. Administrators can now enable automatic synchronization of user profile name and email from OAuth providers on login via the OAUTH_UPDATE_NAME_ON_LOGIN and OAUTH_UPDATE_EMAIL_ON_LOGIN environment variables. #21787, Commit
• 👥 Default group share permission. Administrators can now configure the default sharing permission for new groups via the DEFAULT_GROUP_SHARE_PERMISSION environment variable, controlling whether anyone, no one, or only members can share to new groups. Commit
• 💨 Streaming performance. Chat responses now render more efficiently during streaming, reducing CPU usage and improving responsiveness. Commit
• 🧮 Streaming message comparison. Chat message updates during streaming are now faster thanks to an optimization that skips expensive comparisons when content changes. #21884
• 🚀 Streaming scroll optimization. Chat auto-scroll during streaming is now more efficient by batching scroll operations via requestAnimationFrame, reducing unnecessary layout reflows when tokens arrive faster than the browser can paint. #21946
• 📋 Message cloning performance. Chat message cloning during streaming is now more efficient thanks to the use of structuredClone() instead of JSON.parse(JSON.stringify(...)). #21948
• 🎯 Faster code block rendering. Chat message updates during streaming are now faster. #22101
• 📊 Faster status history display. Chat message updates during streaming are now faster. #22103
• 🛠️ Faster tool result handling. Tool execution results are now handled more efficiently, improving streaming performance. #22104
• 💾 Faster model and file operations. Model selection, file preparation, and history saving are now faster. #22102
• 🛠️ Tool server advanced options toggle. Advanced OpenAPI configuration options in the tool server modal are now hidden by default behind a toggle, simplifying the interface for basic setups. The admin settings tab was also renamed from "Tools" to "Integrations" for clearer organization. Commit, Commit
• 🔧 Faster tool loading. Tool access control now skips an unnecessary database query when no tools are attached to the request, slightly improving performance. #21873
• ➗ Faster math rendering. Mathematical notation now renders more efficiently, improving responsiveness when displaying equations in chat. #21880
• 🏎️ Faster message list updates. The chat message list now rebuilds at most once per animation frame during streaming, reducing CPU overhead. #21885
• 📋 Faster message rendering. Chat message rendering is now more efficient during streaming. #22086
• 🗄️ Faster real-time chat updates. Chat responses now process faster with improved handling for concurrent users. #22087
• 📝 Faster status persistence. Only final status updates are now saved to the database during streaming, reducing unnecessary writes. #22085
• 🔄 Faster event matching. Event handling in the socket handler is now more efficient. Commit
• 🔀 General improvements. Various improvements were implemented across the application to enhance performance, stability, and security.
• 🌐 Translation updates. Translations for German, Portuguese (Brazil), Simplified Chinese, Traditional Chinese, Catalan, and Spanish were enhanced and expanded.

Fixed

• 🗄️ Database migration execution. Database migrations now run correctly on startup, fixing a circular import issue that caused schema updates to fail silently. #21848, Commit
• 🔔 Notification HTML escaping. Notification messages now properly escape HTML content, matching the behavior in chat messages and ensuring consistent rendering across the interface. #21860, Commit
• 🛠️ Tool call JSON error handling. Chat no longer crashes when models generate malformed JSON in tool call arguments; instead, a descriptive error message is returned to the model for retry. #21984, Commit
• 🧠 Reasoning model KV cache preservation. Reasoning model thinking tags are no longer stored as HTML in the database, preserving KV cache efficiency for backends like llama.cpp and ensuring faster subsequent conversation turns. #21815, Commit
• ⚡ Duplicate model execution prevention. Models are no longer called twice when no tools are configured, eliminating unnecessary API requests and reducing latency. #21802, Commit
• 🔐 OAuth session database error. OAuth login no longer fails with a database error when creating sessions, fixing the "'NoneType' object has no attribute 'id'" and "can't adapt type 'dict'" errors that occurred during OAuth group creation. #21788
• 👤 User sharing permission enforcement. The user sharing option now correctly respects the USER_PERMISSIONS_ACCESS_GRANTS_ALLOW_USERS setting, fixing an issue where sharing to individual users was incorrectly allowed even when disabled. #21856, Commit, Commit
• 🔑 Password manager autofill. Password manager autofill (like iCloud Passwords, 1Password, Bitwarden) now correctly captures filled-in passwords, fixing login failures where the password appeared filled but was sent as empty. #21869, Commit
• 📝 RAG template duplication. RAG templates are no longer duplicated in chat messages when models make multiple tool calls, preventing hallucinations and incorrect tool usage. #21780, Commit
• 📋 Audit log stdout. Audit logs now correctly appear on stdout when the ENABLE_AUDIT_STDOUT environment variable is set to true, aligning runtime behavior with the intended configuration. #21777
• 🎯 Function valve priority resolution. Function priorities defined in code are now correctly applied when no custom value has been saved in the database, ensuring consistent action button and filter ordering. #21841
• 📄 Web content knowledge base append. Processing web URLs with overwrite=false now correctly appends content to existing knowledge bases instead of silently doing nothing, fixing a regression where no content was being added. #21786, Commit
• 🔍 Web search domain filter config. The WEB_SEARCH_DOMAIN_FILTER_LIST environment variable is now correctly read and applied, fixing an issue where domain filtering for web searches always used an empty default value. #21964, #20186
• 🧹 Tooltip memory leak. Tooltip instances are now properly destroyed when elements change, fixing a memory leak that could cause performance issues over time. #21969
• ⌨️ MessageInput memory leak. Event listeners in the message input component are now properly cleaned up, preventing a memory leak that could cause page crashes during extended use. #21968
• 📝 Notes memory leak. Event listeners in the Notes component are now properly cleaned up, fixing a memory leak that could cause page crashes during extended use. #21963
• 🏗️ Model create memory leak. Event listeners in the model creation page are now properly cleaned up, fixing a memory leak that could cause page crashes during extended use. #21966
• 💬 MentionList memory leak. Event listeners in the MentionList component are now properly cleaned up, fixing a memory leak that could cause page crashes during extended use. #21965
• 📐 Sidebar memory leak. Event listeners in the Sidebar component are now properly cleaned up, fixing a memory leak that could cause page crashes during extended use. #22082
• 🎨 Sidebar user menu positioning. The sidebar user menu no longer drifts rightward when the sidebar is resized, keeping the menu properly aligned with its trigger. #21853
• 💻 Code block UI. Code block headers are now sticky and properly positioned, with language labels now showing tooltips for truncated text. Commit
• 📊 Multi-model responses horizontal scroll. The model list in multi-model responses tabs now has horizontal scroll support, making all models accessible on desktop screens. #21800, Commit
• 🎭 TailwindCSS gray color theme. Custom gray color palette is now correctly applied to the CSS root theme layer, fixing an issue where --color-gray-x variables were missing. #21900, #21899
• 📎 Broken documentation links. Fixed broken links in the backend config and admin settings that pointed to outdated documentation locations. #21904
• 🔓 OAuth session token decryption. OAuth sessions are now properly detached from the database context before token decryption, preventing potential database session conflicts when reading encrypted tokens. #21794
• 🕐 Chat timestamp i18n fix. Chat timestamps in the sidebar now display correctly, fixing an issue where the time ago format (e.g., "5m", "2h", "3d") was not being localized properly due to incorrect variable casing in the translation function. Commit
• 🍞 Model toast notification fix. Hiding or showing a single model now displays only one toast notification instead of two, removing the redundant generic "model updated" message when a specific action toast is shown. #22079
• 📡 Offline mode embedding model fix. Open WebUI no longer attempts to download embedding models when in offline mode, fixing error logs that occurred when trying to fetch models that weren't cached locally. #22106, #21405

[0.8.5] - 2026-02-23

Added

• ⌨️ Voice dictation shortcut. Users can now toggle voice dictation using Cmd+Shift+L (or Ctrl+Shift+L on Windows/Linux), making it faster to start and stop dictation without clicking the microphone button.

Fixed

• 🚫 Model access KeyError fix. The /api/models endpoint no longer crashes with a 500 error when models have incomplete info metadata missing the user_id field (e.g. models using global default metadata).
• 🔄 Frontend initialization resilience. The app layout now gracefully handles individual API failures during initialization (getModels, getBanners, getTools, getUserSettings, setToolServers) instead of blocking the entire page load when any single call fails.
• 🛡️ Backend config null safety. Language detection during app initialization no longer crashes when the backend config fetch fails, preventing a secondary cause of infinite loading.

[0.8.4] - 2026-02-23

Added

• 🛜 Provider URL suggestions. The connection form now displays a dropdown with suggested URLs for popular AI providers, making it easier to configure connections. Commit
• ☁️ Anthropic model fetching. The system now properly fetches available models from the Anthropic API, ensuring all Anthropic models are accessible. Commit
• 💡 No models prompt. When no models are available, a helpful prompt now guides users to manage their provider connections. Commit
• ⚙️ Connection enable/disable toggles. Individual provider connections can now be enabled or disabled from both admin and user settings. Commit
• ⏸️ Prompt enable/disable toggle. Users can now enable or disable prompts directly from the prompts list using a toggle switch, without needing to delete and recreate them. Inactive prompts display an "Inactive" badge and are still visible in the list. Commit
• 🗑️ Memory deletion. Agents can now delete specific memories that are no longer relevant, duplicated, or incorrect, giving better control over stored memory content. Commit
• 📋 Memory listing. Agents can now list all stored memories, enabling them to identify which memories to manage or delete based on the complete memory inventory. Commit
• 📦 Auto pip install toggle. Administrators can now disable automatic pip package installation from function frontmatter requirements using the ENABLE_PIP_INSTALL_FRONTMATTER_REQUIREMENTS environment variable, providing more control over function dependency management. Commit
• 🔗 Anthropic Messages API proxy. A new API endpoint now supports the Anthropic Messages API format, allowing tools like Claude Code to authenticate through Open WebUI and access configured models. Tool calls are now properly supported in streaming responses with correct multi-block indexing, and error status from tools is propagated correctly. The endpoint converts requests to OpenAI format internally, routes them through the existing chat pipeline, and returns responses in Anthropic format. #21390, Commit, Commit
• 👥 Multi-device OAuth sessions. Users can now stay logged in on multiple devices simultaneously with OAuth, as re-logging in no longer terminates existing sessions. The oldest sessions are automatically pruned when the session limit is exceeded. #21647, Commit
• 🔐 OAuth group default share setting. Administrators can now configure the default sharing setting for OAuth-created groups using the OAUTH_GROUP_DEFAULT_SHARE environment variable, allowing control over whether new groups default to private or shared with members. #21679, Commit
• 🔧 Knowledge base import behavior. The web content import endpoint now supports a configurable overwrite flag, allowing users to add multiple URLs to the same knowledge base instead of replacing existing content. #21613, #21336, Commit
• 🧩 Skill JSON import support. Skills can now be imported from both JSON and Markdown files. #21511
• 🔍 You.com web search provider. A new web search provider option for You.com is now available, giving users another search engine choice for web-enabled models. The You.com provider enriches search results by including both descriptions and snippets for better context. #21599
• 🚀 Message list performance. Loading conversation history when sending messages is now significantly faster, improving response latency before the model starts generating. This also speeds up chat search and RAG context building. #21588
• 🎯 Concurrent embedding request control. Administrators can now control the maximum number of concurrent embedding API requests using the RAG_EMBEDDING_CONCURRENT_REQUESTS environment variable, helping manage API rate limits while maintaining embedding performance. #21662, Commit
• ⚡ Message upsert optimization. Loading chat data during message saving is now significantly faster by eliminating a redundant database call that occurred on every message upsert, which happens many times during streaming responses. #21592
• ⚡ Message send optimization. Loading chat data during message sending is now significantly faster by eliminating unnecessary full conversation history loads. The system now uses targeted queries that fetch only the needed data instead of loading entire chat objects with all message history. #21596
• 🚀 Tag filtering optimization. Chat search with tag filtering now uses more efficient database queries, making filtered searches significantly faster. Commit
• ⚡ Shared chat loading optimization. The shared chats endpoint now loads only the needed columns instead of the full conversation history, making shared chat listings significantly faster. #21614
• 🗂️ Archived and pinned chat loading. Loading archived and pinned chat lists is now significantly faster by loading only the needed columns instead of full conversation data. #21591
• 💨 Chat title query optimization. Retrieving chat titles now queries only the title column instead of the entire conversation history, making title lookups significantly faster and reducing database load. #21590
• 🗄️ Batch access grants for multiple resources. Loading channels, knowledge bases, models, notes, prompts, skills, and tools now uses batch database queries for access grants instead of individual queries per item, significantly reducing database load. For 30 items, this reduces approximately 31 queries to just 3. #21616
• 📋 Notes list payload optimization. Notes list and search endpoints now return only a 200-character preview instead of the full note content, reducing response payload from ~167 MB to ~10 KB for 60 notes and eliminating N+1 queries for access grants. The Notes tab now loads in seconds instead of tens of seconds. #21549
• ⚡ Tools list performance. Loading the tools list is now significantly faster by deferring content and specs fields from database queries, and using cached tool modules instead of reloading them for each request. Commit
• 📝 Group description display. The admin groups list now shows each group's description, making it easier for administrators to identify groups at a glance.
• 🏷️ Sort by dropdown. Administrators can now sort groups using a dropdown menu with options for Name or Members, replacing the previous clickable column headers.
• 📶 Admin groups list sorting. The Group and Users columns in the admin groups list are now clickable for sorting, allowing administrators to sort groups alphabetically by name or numerically by member count. #21692
• 🔽 Rich UI auto-scroll. The view now automatically scrolls to action-generated Rich UI content once it renders, ensuring users can see the results without manually scrolling. #21698, #21482
• 📊 Admin analytics toggle. Administrators can now enable or disable the analytics feature using the ENABLE_ADMIN_ANALYTICS environment variable, giving more control over available admin features. #21651, Commit
• 📊 Analytics sorting enhancement. The Analytics dashboard now supports sorting by Tokens column for both Model Usage and User Usage tables, and the Share/Percentage columns are now clickable for sorting. Administrators can more easily identify the most token-consuming models and users. Commit
• 📑 Fetch URL citation sources. When models fetch URLs during tool calling, the fetched URLs now appear as clickable citation sources in the UI with content previews, matching the existing behavior of web search and knowledge file tools. #21669
• 🔗 Admin settings tab navigation. The admin settings sidebar now supports native browser tab opening, allowing users to middle-click or right-click to open settings pages in new tabs. The navigation was converted from button-based to anchor-based elements. #21721
• 🏷️ Model visibility badges. The Admin Settings Models page now displays Public or Private badges directly on each model, making it easy to identify model access levels at a glance without opening the edit screen. #21732, Commit
• 🛠️ Global model defaults. Administrators can now configure default metadata and parameters that automatically apply to all models, reducing manual configuration for newly discovered models. Default capabilities (like vision, web search, code interpreter) and parameters (like temperature, max_tokens) can be set globally in Admin Settings, with per-model overrides still available. #20658, Commit
• 💬 Plaintext tool output display. Tool outputs that are plain strings now display naturally in a monospace block instead of quoted/escaped format, making multi-line string outputs easier to read. #21553, Commit
• 🔐 Event call input masking. Functions can now request masked password input in confirmation dialogs, allowing sensitive data entry to be hidden from view. This extends the existing masking feature from user valves to event calls. #21540, Commit
• 🗂️ JSON logging support. Administrators can now enable JSON-formatted logging by setting the LOG_FORMAT environment variable to "json", making logs suitable for log aggregators like Loki, Fluentd, CloudWatch, and Datadog. #21747
• ♿ UI accessibility improvements. Screen reader users can now navigate the interface more easily with improved keyboard navigation in dialogs and proper ARIA labels on all interactive elements. Added aria-labels to close, back, and action buttons across various components, and improved semantic HTML and screen reader support across auth, sidebar, chat, and notification components, addressing WCAG compliance. Added aria-labels to search inputs, select fields, and modals in admin and user settings, and improved accessibility for text inputs, rating components, citations, and web search results. Added aria-labels to workspace components including Knowledge, Models, Prompts, Skills, and Tools pages for improved screen reader support. #21706, #21705, #21710, #21709, #21717, #21715, #21708, #21719
• 🔄 General improvements. Various improvements were implemented across the application to enhance performance, stability, and security.
• 🌐 Translations for Finnish, French, Portuguese (Brazil), Simplified Chinese, and Traditional Chinese were enhanced and expanded.

Fixed

• 💥 Admin functions page crash fix. The admin Functions tab no longer crashes when clicked, fixing a null reference error that occurred while the functions list was loading. #21661, Commit
• 💀 Cyclic chat history deadlock fix. Chat histories with circular parent-child message references no longer cause the backend to freeze when syncing usage stats. The system now detects and safely aborts when encountering cyclic message references. #21681
• 🔀 Model fallback routing fix. Custom model fallback now works correctly across all model types, preventing "Model not found" errors when the fallback model uses a different backend (pipe, Ollama, or OpenAI). #21736
• 🐛 Default model selection fix. Admin-configured default models are now properly respected when starting new chats instead of being overwritten by the first available model. #21736
• 👁️ Scroll jumping fix. Deleting a message pair after stopping generation no longer causes the chat to visually jump around, making message deletion smoother. #21743, Commit
• 💬 New chat message handling fix. Fixed a bug where clicking "New Chat" after sending a message would silently drop subsequent messages. The system now properly clears pending message queues when starting a new conversation. #21731
• 🔍 RAG template mutation fix. Fixed a bug where RAG template text was recursively injected into user messages during multiple sequential tool calls, causing message content to grow exponentially and potentially confuse the model. The system now preserves the original user message before tool-calling loops and correctly accumulates citation sources. #21663, #21668, Commit
• 🔒 Iframe sandbox security. Embedded tools can no longer submit forms or access same-origin content by default, improving security for users. #21529
• 🔐 Signup race condition fix. Fixed a security vulnerability where multiple admin accounts could be created on fresh deployments when running multiple uvicorn workers. The signup handler now properly handles concurrent requests during first-user registration, preventing unauthorized admin privilege escalation. #21631
• 🔐 LDAP optional fields fix. LDAP configuration now properly accepts empty Application DN and password values, allowing LDAP authentication to work without these optional fields. Previously, empty values caused authentication failures. Commit
• 🛠️ API tools fix. The /api/v1/chat/completions endpoint now properly respects caller-provided tools instead of overriding them with server-side tools, fixing issues where external agents like Claude Code or Cursor would receive unexpected tool advertisements. #21557, #21555
• ⏱️ Embeddings and proxy timeout fix. The embeddings and OpenAI proxy endpoints now properly honor the AIOHTTP_CLIENT_TIMEOUT environment variable, instead of using default timeouts that could cause requests to hang. #21558
• 📄 Text file type detection fix. TypeScript and other text files that were mis-detected as video files based on their extension are now correctly identified and processed as text files, fixing upload rejections for .ts files. #21454, Commit
• 🗄️ File access control respect. The files list and search endpoints now properly respect the BYPASS_ADMIN_ACCESS_CONTROL setting, ensuring admins only see their own files when the setting is disabled, consistent with other endpoints. #21595, #21589
• 🗄️ PostgreSQL workspace cloning. Cloning workspace models now works correctly on PostgreSQL databases by generating proper unique IDs for access grants instead of using potentially duplicate or invalid IDs. Commit
• 🔓 MCP SSL verification fix. MCP tool connections now properly respect the AIOHTTP_CLIENT_SESSION_TOOL_SERVER_SSL environment variable to disable SSL verification, instead of always verifying SSL certificates. Commit, #21481
• 🔒 Model default feature permissions. Model default features like code interpreter, web search, and image generation now respect global configuration and user permission settings, preventing disabled features from appearing in the chat input. #21690
• 🔍 Model selector typing fix. The model selector list no longer disappears or becomes grayed out when typing quickly in the search field, thanks to improved virtual scroll handling. #21659
• ⛔ Disabled model cloning prevention. Disabled models can no longer be cloned as workspace models, preventing invalid empty configurations from being created. The Clone option is now hidden for inactive models. #21724
• 🔧 SCIM parameter handling. The SCIM Users and Groups endpoints now accept out-of-range startIndex and count values by clamping them to valid ranges instead of returning errors, in compliance with RFC 7644. #21577
• 🔍 Hybrid search result fix. Hybrid search now returns correct results after fixing a bug where query result unpacking order was mismatched, causing search results to appear empty. #21562
• 🛠️ Imported items display. Imported functions and tools now appear immediately in the list after import, without requiring a page reload. #21593
• 🔄 WebSocket race condition fix. Collaborative note saves no longer crash with errors when users disconnect before pending saves complete, preventing AttributeError exceptions and excessive logging. #21601, Commit
• ✋ Drag-and-drop overlay fix. The "Add Files" overlay no longer remains stuck on screen when dragging files back out of the chat window in Mozilla Firefox. #21664
• 👁️ Group search visibility fix. Groups now appear correctly in access control search results, even when the search doesn't match any users. #21691
• 🖱️ User menu drag and click fixes. Fixed draggable ghost images when dragging menu items and eliminated phantom link clicks that occurred when dragging outside dropdown menus. #21699
• 🧭 Admin and workspace nav drag fix. Fixed ghost drag images when dragging top navigation tabs in the Admin and Workspace panels by adding proper drag constraints and text selection prevention. #21701
• 🎮 Playground nav drag fix. Fixed ghost drag images when dragging top navigation tabs in the Playground panel by adding proper drag constraints and text selection prevention. #21704
• ✋ Dropdown menu drag fix. Dropdown menu items can no longer be accidentally dragged as ghost images when highlighting text, making menu interactions smoother. #21713
• 🗂️ Folder menu drag fix. Folder dropdown menu items can no longer be accidentally highlighted or dragged as ghost images, making folder options behave like standard menus. #21753
• 📝 Console log spam fix. Requesting deleted or missing files no longer floods the backend console with Python traceback logs, thanks to proper exception handling for expected 404 errors. #21687
• 🐛 Firefox avatar overflow fix. Fixed a visual bug in Firefox where broken model or user avatar images would display overflowing alt text that overlapped adjacent labels on the Analytics and Leaderboard pages. Failed avatar images now properly show fallback icons instead. #21730
• 🎨 Dark mode select background fix. Fixed an issue where select inputs and dropdown menus had inconsistent lighter background colors in dark mode by removing conflicting dark theme overrides, ensuring a cohesive transparent look. #21728
• 💾 Prompt import fix. Importing prompts that were previously exported no longer fails with a "[object Object]" error toast, making prompt backup and restore work correctly. #21594
• 🔧 Ollama reasoning effort fix. Reasoning effort now works correctly with Ollama models that require string values ("low", "medium", "high") instead of boolean, fixing "invalid option provided" errors when using models like GPT-OSS. #20921, #20928, Commit
• 🔍 Hybrid search deduplication fix. Hybrid search now correctly deduplicates results using content hashes, preventing duplicate chunks from appearing when using enriched text for BM25 search. Commit
• 📋 SQLAlchemy warning fix. Fixed a SQLAlchemy warning that appeared in logs when deleting shared chats, improving log clarity. Commit

Changed

• 🎯 Prompt suggestions relocated. Prompt suggestions have been moved from Admin Panel - Settings - Interface to Admin Panel - Settings - Models, where they can now be configured per-model or globally via the new model defaults.
• 📢 Banners relocated. Banners configuration has been moved from Admin Panel - Settings - Interface to Admin Panel - Settings - General.

[0.8.3] - 2026-02-17

Added

• ✏️ Model edit shortcut. Users can now edit models directly from the model selector dropdown menu, making it faster to modify model settings without navigating to separate admin or workspace pages. Commit
• 🎨 Image edit API background support. The image edit API now supports the background parameter for OpenAI's gpt-image-1 model, enabling background transparency control ("transparent", "opaque", "auto") when the feature is exposed in the UI. #21459
• ⚡ Faster model filtering. Model access control filtering no longer makes a redundant database query to re-fetch model info that is already available in memory, reducing latency when loading model lists for non-admin users. Commit
• 🔧 Tool call display improvements. Tool call results now display arguments in a cleaner key-value format instead of raw JSON, with a responsive layout that shows only the tool name on narrow screens and the full label on wider screens, preventing text wrapping to multiple lines. Commit
• 🔄 General improvements. Various improvements were implemented across the application to enhance performance, stability, and security.
• 🌐 Translations for Portuguese (Brazil), Simplified Chinese, and Traditional Chinese were enhanced and expanded.

Fixed

• 📧 USER_EMAIL variable fix. The {{USER_EMAIL}} template variable now correctly returns the user's email address instead of "Unknown" in prompts. #21479, #21465
• 🖼️ Image and file attachment handling fixes. Uploaded images are now correctly sent to vision-enabled models, and file attachments now work even when no user text is entered alongside a system prompt. This fixes two issues where the backend was not properly processing file attachments: images weren't converted to the expected format for API requests, and file context was dropped when the user sent only a file without accompanying text. Commit, #21477, #21457
• 🛡️ Missing function error handling. Models that reference deleted functions no longer cause the entire /api/models endpoint to crash; instead, the missing functions are skipped and logged, allowing the rest of the models to load successfully. #21476, #21464
• 🚀 Startup model pre-fetch error handling. If model pre-fetching fails during app startup, the application now logs a warning and continues instead of crashing entirely. Commit
• ⚙️ Function module loading error handling. Function modules that fail to load during startup or model processing are now caught and logged, preventing crashes when models reference functions with loading errors. Commit
• 🗄️ PostgreSQL group query fix. The '/api/v1/groups/' endpoint no longer fails with a GROUP BY error when using PostgreSQL; member counts are now calculated using correlated subqueries for better database compatibility. #21458, #21467

[0.8.2] - 2026-02-16

Added

• 🧠 Skill content handling. User-selected skills now have their full content injected into the chat, while model-attached skills only display name and description in the available skills list. This allows users to override skill behavior while model-attached skills remain flexible. Commit
• ⚙️ Chat toggles now control built-in tools. Users can now disable web search, image generation, and code execution on a per-conversation basis, even when those tools are enabled as builtin tools on the model. #20641, #21318, Commit, Commit
• 🖼️ Image preview in file modal. Images uploaded to chats can now be previewed directly in the file management modal, making it easier to identify and manage image files. #21413, Commit
• 🏷️ Batch tag operations. Tag creation, deletion, and orphan cleanup for chats now use batch database queries instead of per-tag loops, significantly reducing database round trips when updating, archiving, or deleting chats with multiple tags. Commit
• 💨 Faster group list loading. Group lists and search results now load with a single database query that joins member counts, replacing the previous pattern of fetching groups first and then counting members in a separate batch query. Commit
• 🔐 Skills sharing permissions. Administrators can now control skills sharing and public sharing permissions per-group, matching the existing capabilities for tools, knowledge, and prompts. Commit
• ⚡ Long content truncation in preview modals. Citation and file content modals now truncate markdown-rendered content at 10,000 characters with a "Show all" expansion button, preventing UI jank when previewing very large documents.
• 🌐 Translation updates. Translations for Spanish and German were enhanced and expanded.

Fixed

• 🔐 OAuth session error handling. Corrupted OAuth sessions are now gracefully handled and automatically cleaned up instead of causing errors. Commit
• 🐛 Task model selector validation. The task model selector in admin settings now correctly accepts models based on the new access grants system instead of rejecting all models with an incorrect error. Commit
• 🔗 Tool call message preservation. Models no longer hallucinate tool outputs in multi-turn conversations because tool call history is now properly preserved instead of being merged into assistant messages. #21098, #20600, Commit
• 🔧 Tool server startup initialization. External tool servers configured via the "TOOL_SERVER_CONNECTIONS" environment variable now initialize automatically on startup, eliminating the need to manually visit the Admin Panel and save for tools to become available. This enables proper GitOps and containerized deployments. #18140, #20914, Commit
• ♻️ Resource handle cleanup. File handles are now properly closed during audio transcription and pipeline uploads, preventing resource leaks that could cause system instability over time. #21411
• ⌨️ Strikethrough shortcut conflict fix. Pressing Ctrl+Shift+S to toggle the sidebar no longer causes text to become struck through in the chat input, by disabling the TipTap Strike extension's default keyboard shortcut when rich text mode is off. Commit
• 🔧 Tool call finish_reason fix. API responses now correctly set finish_reason to "tool_calls" instead of "stop" when tool calls are present, fixing an issue where external API clients (such as OpenCode) would halt prematurely after tool execution when routing Ollama models through the Open WebUI API. #20896

[0.8.1] - 2026-02-14

Caution

⚠️ Database Migrations: This release includes database schema changes; we strongly recommend backing up your database and all associated data before upgrading in production environments. If you are running a multi-worker, multi-server, or load-balanced deployment, all instances must be updated simultaneously, rolling updates are not supported and will cause application failures due to schema incompatibility.

Added

• 🚀 Channel user active status. Checking user active status in channels is now faster thanks to optimized database queries. Commit
• 🔗 Responses API endpoint with model routing. The OpenAI API proxy now supports a /responses endpoint that routes requests to the correct backend based on the model field in the request, instead of always using the first configured endpoint. This enables support for backends like vLLM that provide /skills and /v1/responses endpoints. Commit, Commit
• ⚡ Model and prompt list optimization. Improved performance when loading models and prompts by pre-fetching user group IDs once instead of making multiple database queries. Commit
• 🗄️ Batch access control queries. Improved performance when loading models, prompts, and knowledge bases by replacing multiple individual access checks with single batch queries, significantly reducing database load for large deployments. Commit
• 💨 Faster user list loading. User lists now load significantly faster by deferring profile image loading; images are fetched separately in parallel by the browser, improving caching and reducing database load. Commit
• 🔍 Web search result count. The built-in search_web tool now respects the admin-configured "Search Result Count" setting instead of always returning 5 results when using Native Function Calling mode. #21373, #21371
• 🔐 SCIM externalId support. SCIM-enabled deployments can now store and manage externalId for user provisioning, enabling better integration with identity providers like Microsoft Entra ID and Okta. #21099, #21280, Commit
• 🌐 Translation updates. Portuguese (Brazil) translations were updated.

Fixed

• 🛡️ Public sharing security fix. Fixed a security issue where users with write access could see the Public sharing option regardless of their actual public sharing permission, and direct API calls could bypass frontend sharing restrictions. #21358, #21356
• 🔒 Direct model access control fix. Model access control changes now persist correctly for direct Ollama and OpenAI models that don't have database entries, and error messages display properly instead of showing "[object Object]". Commit, #21377
• 💭 Reasoning trace rendering performance. Reasoning traces from models now render properly without being split into many fragments, preventing browser slowdowns during streaming responses. #21348, Commit
• 🖥️ ARM device compatibility fix. Fixed an issue where upgrading to 0.8.0 would fail to start on ARM devices (like Raspberry Pi 4) due to torch 2.10.0 causing SIGILL errors; now pinned to torch<=2.9.1. #21385, #21349
• 🗄️ Skills PostgreSQL compatibility fix. Fixed a PostgreSQL compatibility issue where creating or listing skills would fail with a TypeError, while SQLite worked correctly. #21372, Commit, #21365
• 🗄️ PostgreSQL analytics query fix. Fixed an issue where retrieving chat IDs by model ID would fail on PostgreSQL due to incompatible DISTINCT ordering, while SQLite worked correctly. #21347, Commit
• 🗃️ SQLite cascade delete fix. Deleting chats now properly removes all associated messages in SQLite, matching PostgreSQL behavior and preventing orphaned data. #21362
• ☁️ Ollama Cloud model naming fix. Fixed an issue where using Ollama Cloud models would fail with "Model not found" errors because ":latest" was incorrectly appended to model names. #21386
• 🛠️ Knowledge selector tooltip z-index. Fixed an issue where tooltips in the "Select Knowledge" dropdown were hidden behind the menu, making it difficult to read knowledge item names and descriptions. #21375
• 🎯 Model selector scroll position. The model selector dropdown now correctly scrolls to and centers the currently selected model when opened, and resets scroll position when reopened. Commit
• 🐛 Sync modal unexpected appearance. Fixed an issue where the Sync Modal would appear unexpectedly after enabling the "Community Sharing" feature if the user had previously visited the app with the sync parameter. #21376
• 🎨 Knowledge collection layout fix. Fixed a layout issue in the Knowledge integration menu where long collection names caused indentation artifacts and now properly truncate with ellipsis. #21374
• 📝 Metadata processing crash fix. Fixed a latent bug where processing document metadata containing certain keys (content, pages, tables, paragraphs, sections, figures) would cause a RuntimeError due to dictionary mutation during iteration. #21105
• 🔑 Password validation regex fix. Fixed the password validation regex by adding the raw string prefix, ensuring escape sequences like d and w are interpreted correctly. #21400, #21399

Changed

• ⚠️ Database Migrations: This release includes database schema changes; we strongly recommend backing up your database and all associated data before upgrading in production environments. If you are running a multi-worker, multi-server, or load-balanced deployment, all instances must be updated simultaneously, rolling updates are not supported and will cause application failures due to schema incompatibility.