Merge pull request #29960 from open-webui/dev

0.11.4

.dockerignore

@@ -18,3 +18,6 @@ uploads
 **/*.db
 _test
 backend/data/*
+
+.venv
+.git

.env.example

@@ -16,6 +16,15 @@ CORS_ALLOW_ORIGIN='*'
 # Set to false to keep memory tools enabled without adding memory context to the system context.
 ENABLE_MEMORY_SYSTEM_CONTEXT=true
 
+# Set to true to add compact row/column stats to parsed CSV retrieval context.
+ENABLE_RAG_CSV_SUMMARY=false
+
+# Set to true to preserve backing file records, storage blobs, and per-file vectors when files are removed from knowledge bases.
+ENABLE_KNOWLEDGE_FILE_RETENTION=false
+
+# Comma-separated chunk metadata keys to expose to the model alongside retrieved content.
+RAG_SOURCE_METADATA_KEYS=''
+
 # Set to false to disable workspace Tools and Functions.
 ENABLE_PLUGINS=true
 

.github/ISSUE_TEMPLATE/bug_report.yaml

@@ -1,41 +1,35 @@
 name: Bug Report
-description: Create a detailed bug report to help us improve Open WebUI.
+description: Tell us what broke in Open WebUI.
 title: 'issue: '
 labels: ['bug', 'triage']
-assignees: []
 body:
   - type: markdown
     attributes:
       value: |
         # Bug Report
 
-        ## Important Notes
+        Use this for real, reproducible bugs. A clear issue is the most useful contribution: include the affected workflow, the expected result, the actual result, and the details needed for someone else to reproduce it.
 
-        - **Before submitting a bug report**: Please check the [Issues](https://github.com/open-webui/open-webui/issues) and [Discussions](https://github.com/open-webui/open-webui/discussions) sections to see if a similar issue has already been reported. If unsure, start a discussion first, as this helps us efficiently focus on improving the project. Duplicates may be closed without notice. **Please search for existing issues AND discussions. No matter open or closed.**
+        Before submitting, search open and closed [Issues](https://github.com/open-webui/open-webui/issues) and [Discussions](https://github.com/open-webui/open-webui/discussions). The issue may already be reported or fixed on `dev`.
 
-        - Check for opened, **but also for (recently) CLOSED issues** as the issue you are trying to report **might already have been fixed on the dev branch!**
+        **Test on the latest release AND on `dev`, right before you submit this report, not last week.** A huge share of reports are for bugs already fixed on `dev`, sometimes weeks earlier, because the reporter only tested an old version and never rechecked. Reports that don't reproduce on latest and on current `dev` at submission time will be closed without further discussion, no exceptions.
 
-        - **Respectful collaboration**: Open WebUI is a volunteer-driven project with a single maintainer and contributors who also have full-time jobs. Please be constructive and respectful in your communication.
+        Please do not open a code pull request for this report unless a maintainer asks for one, or the change is only i18n/localization. If you want to share code as reference, include it here as a local diff or patch. Actionable reproduction details are the most useful next step.
 
-        - **Contributing**: If you encounter an issue, consider submitting a pull request or forking the project. We prioritize preventing contributor burnout to maintain Open WebUI's quality.
+        Security vulnerabilities must not be reported publicly. Use the [GitHub security page](https://github.com/open-webui/open-webui/security) instead.
-
-        - **Bug Reproducibility**: If a bug cannot be reproduced using a `:main` or `:dev` Docker setup or with `pip install` on Python 3.11, community assistance may be required. In such cases, we will move it to the "[Issues](https://github.com/open-webui/open-webui/discussions/categories/issues)" Discussions section. Your help is appreciated!
-
-        - **Scope**: If you want to report a SECURITY VULNERABILITY, then do so through our [GitHub security page](https://github.com/open-webui/open-webui/security).
 
   - type: checkboxes
     id: issue-check
     attributes:
-      label: Check Existing Issues
+      label: Before Submitting
-      description: Confirm that you’ve checked for existing reports before submitting a new one.
       options:
-        - label: I have searched for any existing and/or related issues.
+        - label: I searched open and closed issues and discussions for an existing report.
           required: true
-        - label: I have searched for any existing and/or related discussions.
+        - label: I reproduced this bug on the latest release AND on the current `dev` branch, right before submitting this report. I did not just check an old version or rely on a check from days ago.
           required: true
-        - label: I have also searched in the CLOSED issues AND CLOSED discussions and found no related items (your issue might already be addressed on the development branch!).
+        - label: I understand that maintainers want a well-written issue before any code pull request.
           required: true
-        - label: I am using the latest version of Open WebUI.
+        - label: This is not a security vulnerability.
           required: true
 
   - type: dropdown
@@ -44,9 +38,9 @@ body:
       label: Installation Method
       description: How did you install Open WebUI?
       options:
-        - Git Clone
-        - Pip Install
         - Docker
+        - Pip Install
+        - Git Clone
         - Other
     validations:
       required: true
@@ -55,67 +49,51 @@ body:
     id: open-webui-version
     attributes:
       label: Open WebUI Version
-      description: Specify the version (e.g., v0.6.26)
+      description: Specify the version, commit, or image tag.
+      placeholder: v0.11.0, dev commit SHA, or Docker tag
     validations:
       required: true
 
-  - type: input
-    id: ollama-version
-    attributes:
-      label: Ollama Version (if applicable)
-      description: Specify the version (e.g., v0.2.0, or v0.1.32-rc1)
-    validations:
-      required: false
-
   - type: input
     id: operating-system
     attributes:
       label: Operating System
-      description: Specify the OS (e.g., Windows 10, macOS Sonoma, Ubuntu 22.04, Debian 12)
+      description: Specify the OS and version.
+      placeholder: Windows 11, macOS Tahoe, Ubuntu 26.04, Debian 13
     validations:
       required: true
 
   - type: input
     id: browser
     attributes:
-      label: Browser (if applicable)
+      label: Browser
-      description: Specify the browser/version (e.g., Chrome 100.0, Firefox 98.0)
+      description: If the bug appears in the browser, include browser and version.
+      placeholder: Chrome 151.0, Firefox 153.0.3
     validations:
       required: false
 
-  - type: checkboxes
+  - type: input
-    id: confirmation
+    id: ollama-version
     attributes:
-      label: Confirmation
+      label: Ollama Version
-      description: Ensure the following prerequisites have been met.
+      description: Include this if Ollama is involved.
-      options:
+      placeholder: v0.32.5
-        - label: I have read and followed all instructions in `README.md`.
+    validations:
-          required: true
+      required: false
-        - label: I am using the latest version of **both** Open WebUI and Ollama.
+
-          required: true
+  - type: textarea
-        - label: I have included the browser console logs.
+    id: summary
-          required: true
+    attributes:
-        - label: I have included the Docker container logs.
+      label: Summary
-          required: true
+      description: What is wrong, in a few sentences?
-        - label: I have **provided every relevant configuration, setting, and environment variable used in my setup.**
+    validations:
-          required: true
+      required: true
-        - label: I have clearly **listed every relevant configuration, custom setting, environment variable, and command-line option that influences my setup** (such as Docker Compose overrides, .env values, browser settings, authentication configurations, etc).
+
-          required: true
-        - label: |
-            I have documented **step-by-step reproduction instructions that are precise, sequential, and leave nothing to interpretation**. My steps:
-            - Start with the initial platform/version/OS and dependencies used,
-            - Specify exact install/launch/configure commands,
-            - List URLs visited, user input (incl. example values/emails/passwords if needed),
-            - Describe all options and toggles enabled or changed,
-            - Include any files or environmental changes,
-            - Identify the expected and actual result at each stage,
-            - Ensure any reasonably skilled user can follow and hit the same issue.
-          required: true
   - type: textarea
     id: expected-behavior
     attributes:
       label: Expected Behavior
-      description: Describe what should have happened.
+      description: What should have happened?
     validations:
       required: true
 
@@ -123,7 +101,7 @@ body:
     id: actual-behavior
     attributes:
       label: Actual Behavior
-      description: Describe what actually happened.
+      description: What actually happened?
     validations:
       required: true
 
@@ -131,32 +109,21 @@ body:
     id: reproduction-steps
     attributes:
       label: Steps to Reproduce
-      description: |
+      description: Include the exact commands, settings, URLs, model/provider setup, and user actions needed to hit the bug.
-        Please provide a **very detailed, step-by-step guide** to reproduce the issue. Your instructions should be so clear and precise that anyone can follow them without guesswork. Include every relevant detail—settings, configuration options, exact commands used, values entered, and any prerequisites or environment variables.  
-        **If full reproduction steps and all relevant settings are not provided, your issue may not be addressed.**
-        **If your steps to reproduction are incomplete, lacking detail or not reproducible, your issue can not be addressed.**
-
       placeholder: |
-        Example (include every detail):
+        1. Start Open WebUI with ...
-        1. Start with a clean Ubuntu 22.04 install.
+        2. Configure ...
-        2. Install Docker v24.0.5 and start the service.
+        3. Open ...
-        3. Clone the Open WebUI repo (git clone ...).
+        4. Click ...
-        4. Use the Docker Compose file without modifications.
+        5. See ...
-        5. Open browser Chrome 115.0 in incognito mode.
-        6. Go to http://localhost:8080 and log in with user "test@example.com".
-        7. Set the language to "English" and theme to "Dark".
-        8. Attempt to connect to Ollama at "http://localhost:11434".
-        9. Observe that the error message "Connection refused" appears at the top right.
-
-        Please list each step carefully and include all relevant configuration, settings, and options.
     validations:
       required: true
+
   - type: textarea
     id: logs-screenshots
     attributes:
-      label: Logs & Screenshots
+      label: Logs, Screenshots, and Config
-      description: Include relevant logs, errors, or screenshots to help diagnose the issue.
+      description: Include relevant browser console logs, server/container logs, screenshots, and configuration. If something does not apply, say so.
-      placeholder: 'Attach logs from the browser console, Docker logs, or error messages.'
     validations:
       required: true
 
@@ -164,13 +131,6 @@ body:
     id: additional-info
     attributes:
       label: Additional Information
-      description: Provide any extra details that may assist in understanding the issue.
+      description: Anything else that might help us understand the report.
     validations:
       required: false
-
-  - type: markdown
-    attributes:
-      value: |
-        ## Note
-        **If the bug report is incomplete, does not follow instructions or is lacking details it may not be addressed.** Ensure that you've followed all the **README.md** and **troubleshooting.md** guidelines, and provide all necessary information for us to reproduce the issue.  
-        Thank you for contributing to Open WebUI!

.github/ISSUE_TEMPLATE/feature_request.yaml

@@ -1,76 +1,73 @@
 name: Feature Request
-description: Suggest a new feature or improvement
+description: Describe what you would like Open WebUI to support.
 title: 'feat: '
 labels: ['triage']
 body:
   - type: markdown
     attributes:
       value: |
-        ## Before Submitting
+        # Feature Request
 
-        Please check **open AND closed** [Issues](https://github.com/open-webui/open-webui/issues) and [Discussions](https://github.com/open-webui/open-webui/discussions) for similar requests. If you find one, add your input there instead.
+        Describe the requested behavior, the problem it solves, and any examples, mockups, screenshots, or workflows that clarify the request. A clear issue or discussion is the most useful contribution.
 
-        ### Scope Guidelines
+        Search open and closed [Issues](https://github.com/open-webui/open-webui/issues) and [Discussions](https://github.com/open-webui/open-webui/discussions) before submitting. If the request needs broad product, UX, architecture, compatibility, or maintenance discussion, please start in [Discussions](https://github.com/open-webui/open-webui/discussions) so the community can weigh in.
 
-        Feature requests that require significant implementation effort should be posted in the **Ideas** section of [Discussions](https://github.com/open-webui/open-webui/discussions) instead. We will move oversized feature requests to Discussions to keep the Issues tab focused on actionable items.
+        Please do not open a code pull request for this request unless a maintainer asks for one, or the change is only i18n/localization. If you want to share code as reference, include it here as a local diff or patch. Clear product context is the most useful next step.
 
-        If your request might impact the broader community, please open a Discussion first so others can weigh in on the design.
+        Security vulnerabilities must not be reported publicly. Use the [GitHub security page](https://github.com/open-webui/open-webui/security) instead.
-
-        ### Be Respectful
-
-        Open WebUI is a volunteer-driven project maintained by a small team. We value constructive, positive communication. Please be mindful of maintainers' time and energy.
-
-        ### Contributing
-
-        If you encounter an issue, we encourage you to submit a pull request or fork the project. We actively work to prevent contributor burnout and maintain project quality.
-
-        ### Reproducibility
-
-        If a bug cannot be reproduced with a `:main` or `:dev` Docker setup, or a `pip install` with Python 3.11, it may be moved to the "Issues" section in Discussions for community assistance.
 
   - type: checkboxes
-    id: existing-issue
+    id: existing-request
     attributes:
-      label: Check Existing Issues
+      label: Before Submitting
-      description: Confirm you have searched for similar requests.
       options:
-        - label: I have searched all existing **open AND closed** issues and discussions and found none comparable to my request.
+        - label: I searched open and closed issues and discussions for an existing request.
           required: true
-
+        - label: I checked whether this already exists on the `dev` branch or latest source.
-  - type: checkboxes
+          required: true
-    id: feature-scope
+        - label: I understand that maintainers want a well-written issue or discussion before any code pull request.
-    attributes:
+          required: true
-      label: Verify Feature Scope
+        - label: This request is not a security vulnerability.
-      description: Confirm this request belongs in Issues rather than Discussions.
-      options:
-        - label: I believe this feature request is appropriately scoped for the Issues section as described above.
           required: true
 
   - type: textarea
     id: problem-description
     attributes:
-      label: Problem Description
+      label: Problem
-      description: Is this related to a problem? Describe the pain point clearly.
+      description: What is missing, frustrating, confusing, or unnecessarily hard today?
-      placeholder: "e.g., I'm frustrated when..."
+      placeholder: "I'm trying to..., but..."
     validations:
       required: true
 
   - type: textarea
-    id: solution-description
+    id: desired-behavior
     attributes:
-      label: Proposed Solution
+      label: Desired Behavior
-      description: Describe what you would like to happen.
+      description: What would you like to happen instead?
+      placeholder: "I would like Open WebUI to..."
     validations:
       required: true
 
+  - type: textarea
+    id: why-it-matters
+    attributes:
+      label: Why This Matters
+      description: Who benefits, and what workflow does this unlock or improve?
+    validations:
+      required: true
+
+  - type: textarea
+    id: examples
+    attributes:
+      label: Examples or References
+      description: Add mockups, screenshots, links, prompts, workflows, or examples from other tools.
+    validations:
+      required: false
+
   - type: textarea
     id: alternatives-considered
     attributes:
-      label: Alternatives Considered
+      label: Alternatives or Workarounds
-      description: Describe any alternative solutions or workarounds you have considered.
+      description: What have you tried instead, if anything?
-
+    validations:
-  - type: textarea
+      required: false
-    id: additional-context
-    attributes:
-      label: Additional Context
-      description: Add any other context, mockups, or screenshots about the feature request.

.github/pull_request_template.md

@@ -1,104 +1,95 @@
 <!--
-⚠️ CRITICAL CHECKS FOR CONTRIBUTORS (READ, DON'T DELETE) ⚠️
+Important checks for contributors:
-1. Target the `dev` branch. PRs targeting `main` will be automatically closed.
+1. DO NOT OPEN A CODE PULL REQUEST unless a maintainer explicitly asked you to, or the change is strictly limited to i18n/localization.
-2. Do NOT delete the CLA section at the bottom. It is required for the bot to accept your PR.
+2. Target the `dev` branch. PRs targeting `main` will be closed.
+3. Do not delete the Contributor License Agreement section at the bottom. The CLA bot requires it.
 -->
 
-# Pull Request Checklist
+# Pull Request
 
-### Note to first-time contributors: Please open a discussion post in [Discussions](https://github.com/open-webui/open-webui/discussions) to discuss your idea/fix with the community before creating a pull request, and describe your changes before submitting a pull request.
+**Do not open a code pull request unless a maintainer has explicitly requested it or the change is limited to i18n/localization.**
 
-This is to ensure large feature PRs are discussed with the community first, before starting work on it. If the community does not want this feature or it is not relevant for Open WebUI as a project, it can be identified in the discussion before working on the feature and submitting the PR.
+The most useful way to help is to give us a clear understanding of the problem: report reproducible bugs in [Issues](https://github.com/open-webui/open-webui/issues) and share proposals in [Discussions](https://github.com/open-webui/open-webui/discussions). We use that context to evaluate solutions and refine the implementation internally, accounting for the broader codebase and ongoing work. External implementations usually require substantial reworking to fit the project's standards, and coordinating those revisions usually takes more effort than developing the solution internally. Please follow this process before investing time in a pull request. PRs opened outside these guidelines are generally closed without review.
 
-<!--
+## Maintainer Request
-### ⚠️ Important: Your PR is a contribution, not a guarantee of merge.
 
-The most impactful way to contribute to Open WebUI is through well-written bug reports, detailed feature discussions, and thoughtful ideas. These directly shape the project. If you do open a pull request, please know that Open WebUI is held to the highest standard of code quality, consistency, and architectural coherence, and every line merged becomes something the core team must own, maintain, and support indefinitely. Submitted code may be refactored, rewritten, or used as inspiration for a different implementation. This is not a reflection of your work's quality. It is how we ensure that a small team can deeply understand and evolve every part of the codebase.
+Link the maintainer's request for this PR, or state that the change is limited to i18n/localization.
--->
 
-**Before submitting, make sure you've checked the following:**
+## Checklist
 
-- [ ] **Linked Issue/Discussion:** This PR references an existing [Issue](https://github.com/open-webui/open-webui/issues) or [Discussion](https://github.com/open-webui/open-webui/discussions) — `Closes #___` / `Relates to #___`. If one does not exist, create one first. PRs without a linked issue or discussion may be closed without review.
+- [ ] I have read and I understand the [contribution policy](https://docs.openwebui.com/contributing/#submit-code).
-- [ ] **Target branch:** The pull request targets the `dev` branch. **PRs targeting `main` will be immediately closed.**
+- [ ] This PR targets the `dev` branch.
-- [ ] **Description:** A concise description of the changes is provided below.
+- [ ] This PR links to a well-described, confirmed Issue or active Discussion: `Closes #___` / `Relates to #___`.
-- [ ] **Changelog:** A changelog entry following [Keep a Changelog](https://keepachangelog.com/) format is included at the bottom.
+- [ ] A maintainer explicitly asked me to open this PR, or this PR only updates i18n/localization.
-- [ ] **Documentation:** Relevant documentation has been added or updated in the [Open WebUI Docs Repository](https://github.com/open-webui/docs).
+- [ ] The change is one logical unit with no unrelated commits.
-- [ ] **Dependencies:** Any new or updated dependencies are explained, tested, and documented.
+- [ ] I matched nearby code patterns and avoided unnecessary new settings, abstractions, or dependencies.
-- [ ] **Testing:** Manual tests have been performed to verify the fix/feature works correctly and does not introduce regressions. Screenshots or recordings are included where applicable.
+- [ ] I manually tested the changed workflow and any nearby behavior that could be affected.
-- [ ] **No Unchecked AI Code:** This PR is either human-written or has undergone thorough human review AND manual testing. Unreviewed AI-generated PRs may be closed immediately.
+- [ ] I have not added or rewritten automated tests, fixtures, snapshots, or testing infrastructure unless a maintainer explicitly requested them.
-- [ ] **Self-Review:** A self-review of the code has been performed, ensuring adherence to project coding standards.
+- [ ] I updated relevant docs, including the [Open WebUI Docs Repository](https://github.com/open-webui/docs), if needed.
-- [ ] **Architecture:** Smart defaults are preferred over new settings. Local state is used for ephemeral UI logic. Major architectural or UX changes have been discussed first.
+- [ ] I added screenshots for UI changes, and a recording when motion or interaction matters.
-- [ ] **Git Hygiene:** The PR is atomic (one logical change), rebased on `dev`, and contains no unrelated commits.
+- [ ] I reviewed any AI-generated code before submitting it.
-- [ ] **Title Prefix:** The PR title uses one of the following prefixes:
+- [ ] The PR title uses one of the prefixes listed below.
-  - **BREAKING CHANGE**: Changes affecting backward compatibility
-  - **build**: Build system or dependency changes
-  - **ci**: CI/CD workflow changes
-  - **chore**: Refactoring, cleanup, or non-functional changes
-  - **docs**: Documentation additions or updates
-  - **feat**: New features or enhancements
-  - **fix**: Bug fixes or corrections
-  - **i18n**: Internationalization or localization changes
-  - **perf**: Performance improvements
-  - **refactor**: Code restructuring
-  - **style**: Formatting changes (whitespace, semicolons, etc.)
-  - **test**: Test additions or corrections
-  - **WIP**: Work in progress
 
-# Changelog Entry
+## Title Prefix
 
-### Description
+Use one of the following prefixes:
 
-- [Describe the changes, including motivation and impact]
+- **BREAKING CHANGE**: Changes affecting backward compatibility
+- **build**: Build system or dependency changes
+- **ci**: CI/CD workflow changes
+- **chore**: Refactoring, cleanup, or non-functional changes
+- **docs**: Documentation additions or updates
+- **feat**: New features or enhancements
+- **fix**: Bug fixes or corrections
+- **i18n**: Internationalization or localization changes
+- **perf**: Performance improvements
+- **refactor**: Code restructuring
+
+## Summary
+
+Describe the change, the problem it solves, and the impact on users.
+
+## Verification
+
+Describe how you reproduced the problem and manually checked the behavior before and after the change. Include exact steps, setup details, and relevant logs, screenshots, or recordings. Report results from relevant existing checks and anything you could not verify.
+
+Do not add or rewrite automated tests unless a maintainer explicitly requests them. Tests that repeat an implementation's assumptions can pass while preserving the same mistake; maintainers determine the regression coverage needed. Do not remove, disable, or weaken existing tests to make the change pass.
+
+## Changelog Entry
 
 ### Added
 
-- [New features, functionalities, or additions]
+-
 
 ### Changed
 
-- [Changes, updates, refactorings, or optimizations]
+-
-
-### Deprecated
-
-- [Deprecated functionality or features]
-
-### Removed
-
-- [Removed features, files, or functionalities]
 
 ### Fixed
 
-- [Bug fixes or corrections]
+-
+
+### Removed
+
+-
 
 ### Security
 
-- [Security-related changes or vulnerability fixes]
+-
 
 ### Breaking Changes
 
-- **BREAKING CHANGE**: [Changes affecting compatibility or functionality]
+-
 
----
+## Additional Context
 
-### Additional Information
+Add anything maintainers should know before review.
 
-- [Any additional context, notes, or references to related issues/commits]
+## Contributor License Agreement
-
-### Screenshots or Videos
-
-- [Attach relevant screenshots or videos demonstrating the changes]
-
-### Contributor License Agreement
 
 <!--
-🚨 DO NOT DELETE THE TEXT BELOW 🚨
+DO NOT DELETE THIS SECTION.
-Keep the "Contributor License Agreement" confirmation text intact.
+Your PR will not be reviewed or merged until you check the box below confirming that you have read and agree to the CLA.
-Deleting it will trigger the CLA-Bot to INVALIDATE your PR.
-
-Your PR will NOT be reviewed or merged until you check the box below confirming that you have read and agree to the terms of the CLA.
 -->
 
 - [ ] 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.
-
-> [!NOTE]
-> Deleting the CLA section will lead to immediate closure of your PR and it will not be merged in.

.github/workflows/docker.yaml

@@ -311,7 +311,6 @@ jobs:
     runs-on: ubuntu-latest
     if: ${{ !cancelled() && (github.ref == 'refs/heads/main' || startsWith(github.ref, 'refs/tags/v')) }}
     needs: [merge]
-    continue-on-error: true
     strategy:
       fail-fast: false
       matrix:
@@ -403,5 +402,16 @@ jobs:
             [ -z "$TAG" ] && continue
             DEST="${DOCKERHUB_IMAGE}:${TAG}"
             echo "  -> ${DEST}"
-            docker buildx imagetools create -t "${DEST}" "${SOURCE}"
+            for ATTEMPT in 1 2 3; do
+              if docker buildx imagetools create -t "${DEST}" "${SOURCE}" && \
+                docker buildx imagetools inspect "${DEST}"; then
+                break
+              fi
+              if [ "${ATTEMPT}" = "3" ]; then
+                echo "Failed to copy ${DEST} after ${ATTEMPT} attempts"
+                exit 1
+              fi
+              echo "Copy attempt ${ATTEMPT} for ${DEST} failed, retrying in 15s..."
+              sleep 15
+            done
           done <<< "${{ steps.tags.outputs.tags }}"

.github/workflows/issue-label.yaml

@@ -2,7 +2,7 @@ name: Issue Labeler
 
 on:
   issues:
-    types: [opened]
+    types: [opened, edited]
 
 permissions:
   issues: write
@@ -22,22 +22,118 @@ jobs:
               return;
             }
 
+            const isEdit = context.payload.action === 'edited';
+            const titleWasEdited = Boolean(context.payload.changes?.title);
+
+            if (isEdit && !titleWasEdited) {
+              return;
+            }
+
             const title = issue.title ?? '';
             const body = issue.body ?? '';
 
             // Freeform bug reports: "issue: ...", "bug: ...", "fix: ...", "[Bug] ...", "issue/UX: ..."
-            const bugLikeTitle = /^\s*\[?(bug|issue|fix)\]?\s*[:/\-]/i.test(title);
+            const bugLikeTitle = /^\s*(\[\s*(bug|issue|fix)\b[^\]]*\]|(bug|issue|fix)\s*[:/\-])/i.test(title);
 
             // API/CLI-created issues that reproduce the bug report form structure.
             // Only headings distinctive to the bug form (both are required fields there) —
             // generic headings like "Expected Behavior" also appear in freeform feature requests.
             const bugFormBody = /###\s*(Installation Method|Open WebUI Version)/i.test(body);
 
-            if (bugLikeTitle || bugFormBody) {
+            if (!bugLikeTitle && !bugFormBody) {
-              await github.rest.issues.addLabels({
+              return;
+            }
+
+            if (isEdit) {
+              const events = await github.paginate(github.rest.issues.listEvents, {
                 owner: context.repo.owner,
                 repo: context.repo.repo,
                 issue_number: issue.number,
-                labels: ['bug']
+                per_page: 100
               });
+
+              const bugLabelWasRemoved = events.some(
+                (event) => event.event === 'unlabeled' && event.label?.name === 'bug'
+              );
+
+              if (bugLabelWasRemoved) {
+                return;
+              }
             }
+
+            await github.rest.issues.addLabels({
+              owner: context.repo.owner,
+              repo: context.repo.repo,
+              issue_number: issue.number,
+              labels: ['bug']
+            });
+
+  label-feature-requests:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Add "enhancement" label to unlabeled feature requests
+        uses: actions/github-script@v7
+        with:
+          script: |
+            const issue = context.payload.issue;
+
+            if (issue.labels.some((label) => label.name === 'enhancement')) {
+              return;
+            }
+
+            // A human (or the bug form) already classified this as a bug;
+            // do not stack a second, contradictory classification on it.
+            if (issue.labels.some((label) => label.name === 'bug')) {
+              return;
+            }
+
+            const isEdit = context.payload.action === 'edited';
+            const titleWasEdited = Boolean(context.payload.changes?.title);
+
+            if (isEdit && !titleWasEdited) {
+              return;
+            }
+
+            const title = issue.title ?? '';
+            const body = issue.body ?? '';
+
+            // Feature requests: "feat: ...", "feature: ...", "feature request: ...",
+            // "enhancement: ...", "enh: ...", "[Feature Request] ..." — the feature
+            // request form titles every submission "feat: ", so form submissions are
+            // covered by the same pattern.
+            const featureLikeTitle =
+              /^\s*(\[\s*(feat|feature|enhancement|enh)\b[^\]]*\]|(feat|feature( request)?|enhancement|enh)\s*[:/\-])/i.test(
+                title
+              );
+
+            // API/CLI-created issues that reproduce the feature request form structure.
+            // Only headings distinctive to that form.
+            const featureFormBody = /###\s*(Proposed Solution|Alternatives Considered)/i.test(body);
+
+            if (!featureLikeTitle && !featureFormBody) {
+              return;
+            }
+
+            if (isEdit) {
+              const events = await github.paginate(github.rest.issues.listEvents, {
+                owner: context.repo.owner,
+                repo: context.repo.repo,
+                issue_number: issue.number,
+                per_page: 100
+              });
+
+              const enhancementLabelWasRemoved = events.some(
+                (event) => event.event === 'unlabeled' && event.label?.name === 'enhancement'
+              );
+
+              if (enhancementLabelWasRemoved) {
+                return;
+              }
+            }
+
+            await github.rest.issues.addLabels({
+              owner: context.repo.owner,
+              repo: context.repo.repo,
+              issue_number: issue.number,
+              labels: ['enhancement']
+            });

.github/workflows/regression.yaml

@@ -0,0 +1,45 @@
+# ─────────────────────────────────────────────────────────────────────────────
+# Tests — run the open-webui/tests unit suite against a release candidate
+# Release pull requests go from dev into main and are titled with the version
+# ─────────────────────────────────────────────────────────────────────────────
+name: Tests
+
+on:
+  pull_request:
+    branches: [main, dev]
+    types: [opened, synchronize, reopened, edited]
+
+# An edit must not cancel a running suite: the replacement run would skip it and still report green.
+concurrency:
+  group: regression-${{ github.ref }}
+  cancel-in-progress: ${{ github.event.action != 'edited' }}
+
+jobs:
+  # Into main only the release branch counts; into dev any version title does, so the
+  # suite can be exercised outside a release. Expressions have no regex, hence the literal prefixes.
+  regression:
+    name: Suite
+    if: >-
+      (github.event.pull_request.base.ref == 'dev' ||
+      github.event.pull_request.head.ref == 'dev') &&
+      (github.event.action != 'edited' || github.event.changes.title != null) &&
+      (startsWith(github.event.pull_request.title, '0.') ||
+      startsWith(github.event.pull_request.title, '1.'))
+    permissions:
+      contents: read
+    uses: open-webui/tests/.github/workflows/regression.yml@main
+    with:
+      open-webui-ref: ${{ github.event.pull_request.head.sha }}
+
+  # Single check to require in branch protection.
+  result:
+    name: Result
+    needs: [regression]
+    if: always()
+    runs-on: ubuntu-latest
+    timeout-minutes: 5
+    permissions: {}
+    steps:
+      - name: Fail unless the suite passed or was not required
+        if: needs.regression.result != 'success' && needs.regression.result != 'skipped'
+        run: exit 1

CHANGELOG.md

@@ -5,6 +5,641 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [0.11.4] - 2026-09-21
+
+### Added
+
+- 📉 **Far smaller slim image.** A slim build now comes down at around 175 MB, near enough 89% smaller than the last release, the local models, the packages around them and the tools that installed them all gone from it; what that changes about the way an instance behaves is set out under Changed below and in the documentation. [Commit](https://github.com/open-webui/open-webui/commit/cb942bb94c8dc7941336088fb3392e2398ff56c1), [Commit](https://github.com/open-webui/open-webui/commit/d27aa72ab4a7b5632b4ad49e8467081ad3d7ebb4)
+- 📦 **Smaller standard image.** The image no longer carries a second copy of Python, two sets of fonts nothing ever loaded, packages nothing imports, or the tool that installed them, taking about 170 MB off a standard build. [#29731](https://github.com/open-webui/open-webui/pull/29731), [#29723](https://github.com/open-webui/open-webui/pull/29723), [#29725](https://github.com/open-webui/open-webui/pull/29725), [#29726](https://github.com/open-webui/open-webui/pull/29726), [#29728](https://github.com/open-webui/open-webui/pull/29728), [Commit](https://github.com/open-webui/open-webui/commit/91f8775b28b52c9ae7f2ab990cf2490bda8055d6), [Commit](https://github.com/open-webui/open-webui/commit/98fcb844e1b19f7dd6289af26273cdec5447dc52), [Commit](https://github.com/open-webui/open-webui/commit/508de20779168003e538bb936b49a31d4a8fb8bb), [Commit](https://github.com/open-webui/open-webui/commit/a1c02098aa2687c72482a59117efe643b785df51)
+- 🧑‍💻 **Skills from a terminal.** Skills a connected terminal server offers now sit beside workspace skills everywhere skills are picked — the "$" and "/" menus, the integrations menu and the skills panel, each marked Terminal — and are used the same way: picking one puts its instructions, its folder and the files it ships with in front of the model, and a model that was only told a skill exists can open it itself. They follow whichever terminal is selected and clear when that changes. [Commit](https://github.com/open-webui/open-webui/commit/e69236bccb1e12d14045b09b76ebac0490014851)
+- 📔 **Terminal instructions file.** A model working with a terminal is now handed the AGENTS.md sitting in that terminal's home directory, read afresh at the start of every turn, so the instructions you keep beside your work reach the model without being pasted in. [Commit](https://github.com/open-webui/open-webui/commit/946be432375057dc18dbcc7c3513feb322a83a4b), [Commit](https://github.com/open-webui/open-webui/commit/f6922a4c4293449805938c80fbe54174994a1fc6)
+- 📇 **Automatic skill discovery.** Every skill you can reach is now listed to the model by name and description, and the full text of one is loaded only when it decides to use it; before, a skill you had not selected in the message box was invisible to it, and this applies to models with built-in tools on. [Commit](https://github.com/open-webui/open-webui/commit/e69236bccb1e12d14045b09b76ebac0490014851)
+- 🌄 **Model background images.** A workspace model can now carry a background image, uploaded in its editor and drawn behind the chat whenever that model is selected, sitting below a folder's own background and above your personal one, and it travels with the model through export and import. [Commit](https://github.com/open-webui/open-webui/commit/66addbd6b47bfb25cf9aa37ec70d24db5b28b6b6)
+- 📓 **Skill creation from a chat.** Typing "/skills:create" in a chat that already has content, with a terminal selected, turns the workflow you just went through into a reusable skill written to ".agents/skills" under that terminal's root working directory rather than whatever folder the shell happens to sit in, and authored to Open WebUI's skill standards. [Commit](https://github.com/open-webui/open-webui/commit/113c56fc8c1986359556107a20e206159ca32f59), [Commit](https://github.com/open-webui/open-webui/commit/924a4a10fbd0be508a69faf66bf08ac9761bc24d), [Commit](https://github.com/open-webui/open-webui/commit/58078ab3045cc7aee409d9215f68adf0e02c9165), [Commit](https://github.com/open-webui/open-webui/commit/d25f6c7135e0aee93dc2c840ce320d97617a6e47), [Commit](https://github.com/open-webui/open-webui/commit/a096961a31499be23890b98a040ecf2917405568)
+- 🖥️ **Terminal tabs per command.** The terminal pane now carries a tab for each command a model is running alongside your own shell, so you can watch them as they go, move between them and take the shell yourself, each tab opening with the command that produced it. Opening the pane puts you in a tab, starting your shell where nothing else is running, and closing the last tab folds the pane away again. [Commit](https://github.com/open-webui/open-webui/commit/54a7a7a7ce22725074c29c7e827446f5dce1421c), [Commit](https://github.com/open-webui/open-webui/commit/f3eade42aead0a3b96ada3a300d6c294c89f74a8), [Commit](https://github.com/open-webui/open-webui/commit/de1203f9b5d3d8b2a84bf5c89d1c61542469367a), [Commit](https://github.com/open-webui/open-webui/commit/675b9839f17df94f866c871cbdb9881323a18a8a)
+- 📂 **Folder uploads to terminals.** The file browser beside a terminal takes a folder now, dropped onto it or picked from the Upload Folder entry in its menus, and rebuilds what is inside it as it goes, subfolders and all, where before a drop uploaded only the files sitting loose at the top. [Commit](https://github.com/open-webui/open-webui/commit/f80ef8bd001d7ef650fb278d6fbd05bea4afad0f), [Commit](https://github.com/open-webui/open-webui/commit/4cc0d48b4d83503199bcc5f2322881722971a499), [Commit](https://github.com/open-webui/open-webui/commit/674760bfc1122e0a19fe299e05a86d1cbb528e6f)
+- ⚖️ **Side-by-side file comparison.** Picking two files in the file browser lights up a Compare button that lays them side by side or one above the other, numbering the lines, marking what was added and removed down to the part of the line that changed, counting both, and letting you swap which is which or leave whitespace out of it, a choice it remembers; a terminal too old to offer the comparison says so rather than failing quietly. [Commit](https://github.com/open-webui/open-webui/commit/8556033c6b64fa53e44152ebab1f889a578529af), [Commit](https://github.com/open-webui/open-webui/commit/3808eace6c2beb1904f0f04fdd443ec544f94acb)
+- 🌐 **Suggested prompts in your language.** A fresh install now offers its suggested starter prompts in the language the interface is set to, rather than the same four in English for everyone, and the model defaults panel carries a way back to those defaults once its own suggestions have been edited. [Commit](https://github.com/open-webui/open-webui/commit/30881dbcc966206cc15fb0b2276b41d88f7c0f09), [Commit](https://github.com/open-webui/open-webui/commit/9fba2843b16a111b035949f5865e29ec6cf5ac9c)
+- 📏 **Exa result length cap.** Web search through Exa can be held to a number of characters per result, set beside its key in the admin web search settings or as "EXA_MAX_CONTENT_LENGTH". [Commit](https://github.com/open-webui/open-webui/commit/12b14124b9376eccf2ba7cf3dba92bc145493703)
+- 🇪🇺 **European web search option.** Staan can now be picked as the web search provider, giving deployments that need search inside the EU an option they do not have to host themselves, configured from the admin web search settings or through "STAAN_API_KEY", "STAAN_MARKET" and "STAAN_MAX_SNIPPETS". [#30138](https://github.com/open-webui/open-webui/pull/30138), [#26006](https://github.com/open-webui/open-webui/discussions/26006), [#30303](https://github.com/open-webui/open-webui/pull/30303), [#30301](https://github.com/open-webui/open-webui/issues/30301)
+- 🗣️ **Per-language names and descriptions.** A model, tool, skill, function, banner or arena entry can now hold its name, description, starter prompts and valve labels once per language, written in a searchable table in its own editor or brought in as a JSON file, which is refused where a translation drops one of the placeholders the original fills in. The interface shows the wording for the language it is set to, and falls back to the plain text where that language has none. [Commit](https://github.com/open-webui/open-webui/commit/7b6562e3358956ec71eed05352538a646d047734), [Commit](https://github.com/open-webui/open-webui/commit/858ab727d2d80bb3c9ef40f01a32de7a12ca75c9), [Commit](https://github.com/open-webui/open-webui/commit/3facfa61d413945d7144d26b827fcce1f3aef7c5), [Commit](https://github.com/open-webui/open-webui/commit/85b11a4f3504434bd9cd0748629b8a84817fb4f2)
+- ✏️ **Interface text you can reword.** An administrator can now replace the interface's own wording language by language from a panel in the admin settings, with a replacement refused where it drops one of the placeholders the original fills in. [Commit](https://github.com/open-webui/open-webui/commit/67ac1a4e937271a02bfb02a330aa99dc8192cbf4)
+- 🔓 **Turning off the sign-in form.** The box asking for an email address and a password can now be taken off the sign-in page from the authentication settings, where until now it could only be set before the server started, leaving single sign-on or a directory to sign people in. [Commit](https://github.com/open-webui/open-webui/commit/c4a349651e34bf5d0920bb5e26707ae9961ac39f)
+- 🏷️ **Custom file metadata.** Metadata attached to an uploaded file now travels with the pieces that file is split into and arrives with the retrieved sources, the oversized and internal fields left out, and an operator can name in "RAG_SOURCE_METADATA_KEYS" which of those fields the model itself gets to see alongside the text. [#29499](https://github.com/open-webui/open-webui/pull/29499), [#29486](https://github.com/open-webui/open-webui/issues/29486), [Commit](https://github.com/open-webui/open-webui/commit/894655f66b9563890e63c76090ddecc90a311eb2), [#29502](https://github.com/open-webui/open-webui/pull/29502), [#29696](https://github.com/open-webui/open-webui/pull/29696)
+- 🗑️ **Quick delete shortcut.** Holding Shift over a note in the list or grid, or over a row on the automations page, turns its trailing controls into a delete button, removing the entry in one click rather than the three the menu and its confirmation ask for. [#29635](https://github.com/open-webui/open-webui/pull/29635), [#29633](https://github.com/open-webui/open-webui/issues/29633), [#29640](https://github.com/open-webui/open-webui/pull/29640), [#29637](https://github.com/open-webui/open-webui/issues/29637)
+- 🔀 **Diffs are drawn as diffs.** A diff or patch block in a reply is now laid out as one, with the file and hunk headings, the old and new line numbers, and the added and removed lines picked out down to the part of the line that changed, and a button to switch to the plain text and back. [Commit](https://github.com/open-webui/open-webui/commit/254e29b9af634145dde0450451a36f0dfbd8f421)
+- ✒️ **A formatting switch for notes.** A note you can edit carries a Formatting switch in its menu: turned off, Markdown you type or paste stays as the characters you wrote, a paste keeps its plain text, and a web address is left as text, while formatting already in the note is untouched. [Commit](https://github.com/open-webui/open-webui/commit/d8f27e745bd31c89efa25cbe0f41bb0f70576fc5)
+- 🎛️ **Admin model list filters.** The models page in the admin settings can now be narrowed to the base models a connection offers or to the ones built in the workspace, alongside the filters for enabled, disabled, visible and hidden. [Commit](https://github.com/open-webui/open-webui/commit/9e634c0c56e0a060717f1e24a11b082daf664036)
+- 🔍 **Settings search by name.** The search box in settings now matches each setting's own name and description rather than a keyword list kept per page, in whichever language you are using and regardless of accents, it leaves out anything your permissions do not let you change, and opening a result no longer clears what you typed. [Commit](https://github.com/open-webui/open-webui/commit/7cbaabe02fc3c7c040008e82cf85f590bd0c346a), [Commit](https://github.com/open-webui/open-webui/commit/9d98ffcddf792be8d567ea39370d39fcac649acd), [Commit](https://github.com/open-webui/open-webui/commit/c82634b9d01adadbf9780ff84a0a8168fdc4fdea)
+- 🆘 **A model for every chat.** Opening a conversation whose model has since been retired no longer leaves it stranded with nothing selected; it falls back to your default model, then the configured default, then the first one available, and a chat that still has a live model keeps it. [#29757](https://github.com/open-webui/open-webui/pull/29757)
+- ⚡ **Non-blocking search.** Searching the text of chats and knowledge, and the grep a model runs over a knowledge base, now run beside the rest of the server rather than in front of it, so a long search no longer keeps other requests waiting. [#29621](https://github.com/open-webui/open-webui/pull/29621), [Commit](https://github.com/open-webui/open-webui/commit/d9c8de9c39fca7c4756e0f9bd599b09ebe435208)
+- ✴️ **Lighter shared note editing.** Notes written by several people at once no longer echo every keystroke back to the server once per watcher; the traffic between editors falls by half with two of them and keeps falling as more join, so shared notes stay smooth as the room grows. [#28185](https://github.com/open-webui/open-webui/pull/28185)
+- 🔢 **Sorted knowledge listings.** The "ls", "tree" and "find" commands a model runs over a knowledge base now sort by name and take "-t", "-S" and "-r" for newest first, largest first and reversed. [#29840](https://github.com/open-webui/open-webui/pull/29840)
+- 🪪 **Authentication type header.** A request to an OpenAI or Ollama connection now carries "X-OpenWebUI-Auth-Type", saying whether the person behind it signed in through the browser or called with an API key; its name is set with "FORWARD_USER_INFO_HEADER_AUTH_TYPE" and "{{AUTH_TYPE}}" works in custom headers. [Commit](https://github.com/open-webui/open-webui/commit/ee46e2664ab23bacc536fed21c06ab19067d695b)
+- 💡 **Follow-up ghost text.** Once a reply has finished, the first of the follow-up questions it suggests now sits greyed inside the empty message box as well as under the reply: Tab writes it out, and typing anything of your own clears it away. [Commit](https://github.com/open-webui/open-webui/commit/7aaa4a692e949724913834efc47c57572042703b)
+- 🪵 **Model refusal logging.** A request turned away with "Model not found" now writes a warning naming the account, the model and why it was refused, while the message the caller sees stays as vague as before. [Commit](https://github.com/open-webui/open-webui/commit/f5fcf4c89fb27ed39825875d573446fa84aa2a5b)
+- 🤲 **Cheaper chat requests behind Redis.** Where several servers share their websocket traffic through Redis, a chat request no longer pulls the whole shared model list from Redis to ask about a couple of models; each worker keeps its own copy and refetches only when the list actually changed, so the cost stops growing with the number of models configured. [#28176](https://github.com/open-webui/open-webui/pull/28176), [#28167](https://github.com/open-webui/open-webui/issues/28167)
+- 💽 **Long conversations stream cheaper.** Writing or reading a single message no longer loads, checks and rewrites the entire conversation to change a few hundred bytes, so streaming into a long chat stops getting more expensive as it grows, and the whole round trip a message event costs falls to a fraction on conversations of thousands of messages. [#28184](https://github.com/open-webui/open-webui/pull/28184), [#28169](https://github.com/open-webui/open-webui/issues/28169)
+- 🧱 **In-place streaming appends.** Streamed replies can be assembled with CPython's in-place string append, turned on with "ENABLE_CHAT_RESPONSE_STREAM_INPLACE_APPEND" and left off by default while it is rolled out gradually. [Commit](https://github.com/open-webui/open-webui/commit/113c56fc8c1986359556107a20e206159ca32f59), [Commit](https://github.com/open-webui/open-webui/commit/924a4a10fbd0be508a69faf66bf08ac9761bc24d), [#30066](https://github.com/open-webui/open-webui/pull/30066)
+- 📘 **Direct connection guidance.** The connections and integrations pages in the personal settings now say plainly that a direct connection leans on your browser session to keep requests running, which suits testing and temporary use rather than everyday work. [Commit](https://github.com/open-webui/open-webui/commit/5d66dd6ad291db17894953714c01fd4303093e7e), [Commit](https://github.com/open-webui/open-webui/commit/15e2259a2ae1b7dec1f93a52078304dd3a79a14c)
+- 🔄 **General improvements.** Various improvements were implemented across the application to enhance performance, stability, and security.
+- 🌐 **Translation updates.** Translations for Japanese, Traditional Chinese, Korean, Finnish, Russian, Ukrainian, German, Spanish, Portuguese (Brazil), Arabic, Arabic (Bahrain), Azerbaijani, Bulgarian, Bengali, Tibetan, Bosnian, Catalan, Cebuano, Czech, Danish, Basque, Croatian, Dutch, Italian, Turkish, Simplified Chinese, Bosnian, Catalan, Danish, Estonian, Finnish, Galician, Croatian, Kabyle, Norwegian Bokmål, Portuguese (Portugal), Romanian and Turkmen were enhanced and expanded.
+
+### Fixed
+
+- 🛡️ **Security Advisory**: This release includes security and access-control fixes. We recommend updating production deployments at your earliest convenience. Not all security fixes in this version may be enumerated in the fixed section. Some may be withheld for a short time to give administrators time to upgrade. [Advisories](https://github.com/open-webui/open-webui/security)
+- 🔑 **Tokens stay out of logs.** A failure part way through signing in with an identity provider no longer writes the credentials it was handed into the application log, recording the provider and the error it reported instead. [#29709](https://github.com/open-webui/open-webui/pull/29709)
+- 🔐 **Sign-in role mapping.** Roles sent by an identity provider were in some setups not applied, leaving an account at the default role, and a sign-in whose roles cannot be read is now refused rather than let through. [Commit](https://github.com/open-webui/open-webui/commit/10d1cfe6375f207acaa531e857edb575ded2cfc3)
+- 🚫 **Blocked sign-in groups saved.** Comma-separated group names typed into the blocked groups field now take effect once saved, where the save stored the text as written and the sign-in check then read it as nothing; a group name carrying a comma of its own survives a save too. [Commit](https://github.com/open-webui/open-webui/commit/3fc1146c13d7b4b7a67c7fd058014436f80e0dfd)
+- 🚪 **Signing out ends the session.** Signing out or having every token revoked left any live connection that account already had in place, and those are now cut at the same moment; a token already revoked can no longer be replayed to cut someone else's newer session. [Commit](https://github.com/open-webui/open-webui/commit/3a6d0fd203050401481bdb8621b827089d393817)
+- 🛡 **Diagrams and SVG stay on this origin.** Mermaid diagrams and SVG previews, attached or uploaded, no longer follow references pointing at another origin, a picture, style or configuration line among them, and a diagram that reaches outside is refused with an error; a file whose drawing leans on an external sprite now shows that part blank. [#30271](https://github.com/open-webui/open-webui/pull/30271)
+- 📲 **Terminal sessions follow access changes.** A terminal connection now re-checks your access to it every ten seconds for as long as it stays open, so removing someone's permission or deactivating their account ends their live terminal on the next check, on every worker and not only the one they signed in through. [Commit](https://github.com/open-webui/open-webui/commit/a1189a2d757407530a0c1c85a41b46cd6a4f7da5), [Commit](https://github.com/open-webui/open-webui/commit/e8bd0661d3774248c318286849041b94bb861909)
+- 🔒 **Connection model listing access.** The endpoints that list the models on a single Ollama or OpenAI connection could be reached by a signed-in account of any role, and now check the caller's role. [#29619](https://github.com/open-webui/open-webui/pull/29619)
+- 🔏 **Knowledge file access.** A file's access through a knowledge base now follows its actual attachment alone, rather than also a collection name left behind on the file record. [#29937](https://github.com/open-webui/open-webui/pull/29937)
+- 🌳 **Knowledge directories stay inside their base.** A directory id supplied to the knowledge file routes is now refused where it belongs to a different knowledge base, where a caller-supplied id could reach into a directory tree outside the one being addressed. [Commit](https://github.com/open-webui/open-webui/commit/a9541c18ca2a056f4ccfe56b9c733cba74b86b49), [#29887](https://github.com/open-webui/open-webui/pull/29887)
+- 🍪 **Cookie forwarding scope.** A connection authenticating as the signed-in person is handed this instance's browser cookies only where its new Forward cookies switch is on, which an instance relying on it has to turn on after upgrading. [Commit](https://github.com/open-webui/open-webui/commit/b71744b17823f7a3a9a64cb363e79a7164ed5b23), [Commit](https://github.com/open-webui/open-webui/commit/3cda47cdb449aac970426f0929c9e5f8bb8bd807), [Commit](https://github.com/open-webui/open-webui/commit/f9f815c86220f809fad5ee1300c44f55dea74c79)
+- 🗝️ **Revocation list fallback.** Where the revocation list is kept in Redis and Redis cannot be reached, a token is now accepted rather than the request failing, so signing out may not take effect until Redis is back. [Commit](https://github.com/open-webui/open-webui/commit/c1615bec2f5f143084b5fcc04f42ebfa0dade9df), [Commit](https://github.com/open-webui/open-webui/commit/6a85abb3f5e002f3069007213e16e4ef60776890)
+- 🗒 **Home page chat drafts.** A message typed into a chat started from the home page now comes back after a reload, text, uploads and all, where the draft was stored under a key the page never read again. [#29762](https://github.com/open-webui/open-webui/pull/29762), [#29760](https://github.com/open-webui/open-webui/issues/29760)
+- 🏞️ **S3-hosted chat images.** A chat image whose host echoes a Content-Encoding nothing asked for, an S3 or MinIO object uploaded with that metadata among them, no longer breaks the reply it sits in; it is sent as its link the way an unreachable image already was. [#29623](https://github.com/open-webui/open-webui/pull/29623)
+- 🪆 **Branch descent guard.** Stepping between reply branches walked a chat's children without tracking where it had already been, so a history that pointed back at itself spun forever and locked the tab, and a child id with no message behind it threw; every one of the eleven places that walk now shares a single guarded helper. [#30070](https://github.com/open-webui/open-webui/pull/30070)
+- 🗒️ **Note save on exit.** A note's title and its attachments save a moment after they change, and leaving the note inside that moment dropped the save, so the notes list kept showing the old title until the page was reloaded; the pending save now finishes before the next page opens. [#29745](https://github.com/open-webui/open-webui/pull/29745), [#29744](https://github.com/open-webui/open-webui/issues/29744)
+- 📷 **Attachments sent without text.** Sending an image or a file with nothing typed to a model that has skills attached replaced the empty message with the list of skill names, so the model answered with its own catalogue instead of looking at what you sent. [#30045](https://github.com/open-webui/open-webui/pull/30045), [#30040](https://github.com/open-webui/open-webui/issues/30040)
+- 🖍️ **SVG attachments read as text.** An SVG attached to a chat went up as a picture and came back rejected by every model that tried to decode it, and is now read as its source text instead, which needs a model that accepts file uploads. [#30102](https://github.com/open-webui/open-webui/pull/30102), [#30100](https://github.com/open-webui/open-webui/issues/30100)
+- 🩹 **Notes survive a small edit.** Asked to add a section or change a few lines, a model would send the whole note back and lose the rest of it with nothing to undo, because the editing tool never said when to edit a range instead; it now spells out the range rules the handler already enforced. [#30048](https://github.com/open-webui/open-webui/pull/30048)
+- 📋 **Note paste placement.** A plain paste replaced more of the note than was selected, and a paste into a code block broke out of the block instead of going inside it; both now land exactly where they were dropped. [Commit](https://github.com/open-webui/open-webui/commit/d8f27e745bd31c89efa25cbe0f41bb0f70576fc5)
+- 🧿 **Insert into note on read-only notes.** The Insert into note action no longer appears on a note you may only read, which offered it where it could not land. [#30223](https://github.com/open-webui/open-webui/pull/30223), [#30174](https://github.com/open-webui/open-webui/issues/30174)
+- 🤝 **Note sharing survives a save.** Saving a note you had been given access to took that sharing away, so the note went private and everyone else lost it. [#30175](https://github.com/open-webui/open-webui/pull/30175)
+- 🌍 **Collaborative link handling.** In a note two people are writing at once, a plain web address arriving from the other editor was turned into a link on your screen but not on theirs; it is now left as written. [Commit](https://github.com/open-webui/open-webui/commit/d8f27e745bd31c89efa25cbe0f41bb0f70576fc5)
+- 📑 **Tika 4 document formatting.** Where document extraction runs against a Tika server on version 4, the text now comes back as Markdown rather than a flat run of characters, so headings, lists and tables survive into what the model reads. [Commit](https://github.com/open-webui/open-webui/commit/ba34bee2d17e1c00238c85a8aab1a11a60db164e)
+- ⏳ **Session expiry accuracy.** A session with an identity provider now expires with the token it actually calls with, rather than whichever of its two tokens ran out first, which renewed it early and dropped it whenever that failed. [Commit](https://github.com/open-webui/open-webui/commit/aaaf26fb8ede28854dd660b11b85ba6bafe64007)
+- 🧩 **Tool steps in finished replies.** A reply that called tools showed each step as it ran, then lost them the moment the reply completed, because the provider's closing message replaced everything on screen rather than joining it; the closing message is now merged into what is already there, and a tool call is no longer mistaken for its own result. [Commit](https://github.com/open-webui/open-webui/commit/e1bfefdf9f8f2012cecfc7d81079bd6fff147932), [Commit](https://github.com/open-webui/open-webui/commit/31b272d3c93b87636c920f2aa68d6caaa07ae79a)
+- 🧭 **Streamed replies follow along.** A reply arriving over the response events now keeps the view at the bottom as it is written, as replies on the older path already did, unless you have scrolled up yourself. [Commit](https://github.com/open-webui/open-webui/commit/dfde08aa7391d924359b27f5768411d7a533a6ec), [Commit](https://github.com/open-webui/open-webui/commit/88e78b7819b28ffe91f3dff24d8c5d992004197e)
+- 🚿 **Tool results arrive when the tools are done.** The results of a model's tool calls now reach the reply as soon as the round that produced them finishes, instead of being held back with the rest of the streaming until the throttle let them through, and a channel reply or a continuation no longer carries the picture data a tool handed the model. [Commit](https://github.com/open-webui/open-webui/commit/478d1785fd27f400c614a5700f5b38ec9de412f9)
+- 🧗 **Tagged blocks while streaming.** A reply using reasoning, solution or code interpreter tags briefly showed the raw tag text in the message as it arrived, because the chunk carrying it reached the browser before the cleaned output did; the cleaned output is now sent the moment a tag is taken out, and the code an interpreter block writes fills that block rather than the message body. [Commit](https://github.com/open-webui/open-webui/commit/58b36765a7c20f5943a3180bd289de48876d0878)
+- 📗 **Excel in the code interpreter.** Reading or writing a spreadsheet in code the browser runs failed outright because the library that handles them never reached the browser, and it is now shipped alongside the rest. [#30140](https://github.com/open-webui/open-webui/pull/30140), [#30130](https://github.com/open-webui/open-webui/issues/30130)
+- 📀 **Bundled charts and formatting.** Drawing a chart with seaborn in code the browser runs fetched the library over the internet at that moment rather than taking it from what ships, and the code editor's Format button failed outright for anyone who is not an administrator; both now work from what comes with the application, offline included. [#30148](https://github.com/open-webui/open-webui/pull/30148), [#30145](https://github.com/open-webui/open-webui/issues/30145)
+- 🙋 **Typed answer submission.** In the card a model puts up to ask you a question, choosing one of its options on the last question sends your answers straight away, but typing your own into the Other box left Submit answers greyed out with no way to send it, and it now turns on as soon as that box has text. [#29494](https://github.com/open-webui/open-webui/pull/29494), [#29311](https://github.com/open-webui/open-webui/issues/29311)
+- 🥇 **A truthful Recommended badge.** The card a model puts up to ask you a question marks its first option Recommended, but nothing told the model that, so the badge fell on whichever option happened to be listed first; models are now asked to put the option they recommend there. [#30196](https://github.com/open-webui/open-webui/pull/30196), [#30195](https://github.com/open-webui/open-webui/issues/30195)
+- 🎚️ **Partial settings permissions.** An account barred from changing the interface settings can now save its system prompt, notifications, audio, keyboard shortcuts and pinned models, which were refused along with them. [Commit](https://github.com/open-webui/open-webui/commit/98a920168e2eea435ac15e1ad3d679946631e41d)
+- 🎧 **Speech file types kept.** Saving the audio settings emptied the list of file types accepted for speech recognition, so transcription then turned away the recordings it had taken before. [#30208](https://github.com/open-webui/open-webui/pull/30208)
+- 🚻 **Group picker without permission.** The picker for sharing a chat, a note or a knowledge base with a group was offered to accounts not allowed to share with groups, and is now hidden from them. [#30189](https://github.com/open-webui/open-webui/pull/30189)
+- 🗜️ **Per-field settings saves.** Only the settings actually changed are now stored, rather than the whole object, so another tab's older copy no longer overwrites them and a default an administrator changes still reaches everyone, and pinning a model, reordering the list or picking a default from outside the settings window now saves the same way. [Commit](https://github.com/open-webui/open-webui/commit/98a920168e2eea435ac15e1ad3d679946631e41d), [#30183](https://github.com/open-webui/open-webui/pull/30183)
+- ⚠️ **Failed settings feedback.** Settings that could not be saved were shown as saved anyway until the page was reloaded, because the interface stored them locally without waiting on the server; a failure now raises an error and leaves the panel as it was. [Commit](https://github.com/open-webui/open-webui/commit/98a920168e2eea435ac15e1ad3d679946631e41d)
+- 🔠 **Menu text scaling.** The entries in the menus that drop down across the interface now scale with the rest of it, rather than staying at a fixed size while the menu around them grew. [#29493](https://github.com/open-webui/open-webui/pull/29493), [#29488](https://github.com/open-webui/open-webui/issues/29488)
+- 🪞 **Account menu highlighting.** An account menu entry carrying a pin button beside it now lights up across the whole row in the shared colour, and a long label no longer pushes the pin out of the menu. [Commit](https://github.com/open-webui/open-webui/commit/e723dcda58f638a5da2398743d22d3e5854042bf)
+- 🔲 **Shift-click file selection.** Shift-clicking a file in the terminal's file browser now adds that range to what is already selected, and clicking through a selected file removes its range. [Commit](https://github.com/open-webui/open-webui/commit/f80ef8bd001d7ef650fb278d6fbd05bea4afad0f), [Commit](https://github.com/open-webui/open-webui/commit/4cc0d48b4d83503199bcc5f2322881722971a499), [Commit](https://github.com/open-webui/open-webui/commit/674760bfc1122e0a19fe299e05a86d1cbb528e6f)
+- 🛟 **Attachment name collisions.** Attaching a file to a message on an instance that puts attachments in a terminal's working directory replaced whatever file of that name was sitting there; the upload now takes the next free name, "report (1).pdf" beside "report.pdf", and the attachment shows the name it was saved under, though two uploads arriving at the same moment from different browsers can still land on the same name. [Commit](https://github.com/open-webui/open-webui/commit/d70053e44993f271d534fb87d2b40724b028fca2)
+- 📛 **Failed upload feedback.** A file that could not be written to the terminal now says so, rather than passing in silence while the browser refreshed as though it had arrived. [Commit](https://github.com/open-webui/open-webui/commit/f80ef8bd001d7ef650fb278d6fbd05bea4afad0f), [Commit](https://github.com/open-webui/open-webui/commit/4cc0d48b4d83503199bcc5f2322881722971a499), [Commit](https://github.com/open-webui/open-webui/commit/674760bfc1122e0a19fe299e05a86d1cbb528e6f)
+- ☑️ **Unchecked checkbox defaults.** A prompt variable written as a checkbox with a default of false opened the form already ticked, as did False, "false", 0 and "0", because any non-empty default counted as ticked; it is now ticked only where the value really is true. [#30037](https://github.com/open-webui/open-webui/pull/30037), [#30036](https://github.com/open-webui/open-webui/issues/30036)
+- 🎯 **Prefilled question timing.** Opening a chat from a link holding a question sent it before the box had it, so a question naming a variable went off with the variable unfilled; the send now waits for the text to be in place and filled in. [Commit](https://github.com/open-webui/open-webui/commit/3808eace6c2beb1904f0f04fdd443ec544f94acb), [Commit](https://github.com/open-webui/open-webui/commit/a23b579233276e40159eb615917b9aeb7d5ed5c9)
+- 📜 **Task list height.** The list of steps a model works through ran as long as it needed and pushed the rest of the reply down the page; it now stops at a quarter of the window's height and scrolls within itself. [Commit](https://github.com/open-webui/open-webui/commit/307b9b9133f0c7ad899f4b76226059da6f3177eb)
+- ⎋ **Escape key targeting.** The shortcut for closing a dialog always shut the settings window, whichever dialog was actually in front, so a dialog opened from within settings took both away at once; each dialog now answers the shortcut for itself, as it already did for the escape key. [#29830](https://github.com/open-webui/open-webui/pull/29830), [#29817](https://github.com/open-webui/open-webui/issues/29817)
+- 🎹 **Message pair shortcut.** The shortcut that adds an empty question and answer to a chat also sent whatever was typed in the message box, so the pair arrived alongside a message you had not meant to send yet. [#30167](https://github.com/open-webui/open-webui/pull/30167)
+- 🥁 **Collapsing the task list.** Folding away the list of tasks under a reply also sent whatever you had typed in the message box. [#30202](https://github.com/open-webui/open-webui/pull/30202)
+- 🕰️ **Temporary chat links.** A link carrying the temporary chat marker opened an ordinary chat, because the marker was written into the address but never read back when the page loaded, and such a link now opens the temporary chat it promises. [Commit](https://github.com/open-webui/open-webui/commit/67adde31936d1d2e656140f9edd898b1fbb18a1c)
+- ⌨️ **Recording a new shortcut.** Pressing a key combination to record it as a shortcut also ran whatever that combination was already bound to, so setting one up did the thing you were trying to rebind. [#30160](https://github.com/open-webui/open-webui/pull/30160)
+- 🔃 **Stale tab reload.** A tab still running the previous build met an error page after the server was updated instead of loading the new one, because every image built from Docker carried the same version stamp; the stamp now follows the build, and a stale tab reloads as it was meant to. [#29832](https://github.com/open-webui/open-webui/pull/29832), [#29831](https://github.com/open-webui/open-webui/issues/29831)
+- 📌 **Channel code headers.** The bar naming a piece of code in a channel thread or its pinned messages now sits flush at the top of the panel, clipped to the block, rather than floating over the code as it scrolls. [#29836](https://github.com/open-webui/open-webui/pull/29836), [#29835](https://github.com/open-webui/open-webui/issues/29835)
+- 📨 **Duplicated proxy headers.** A reply proxied from a terminal server or an OpenAI or Ollama connection no longer carries that server's own "Server" and "Date" headers, which had a reverse proxy in front logging a duplicate line for every one. [#29841](https://github.com/open-webui/open-webui/pull/29841), [#29824](https://github.com/open-webui/open-webui/issues/29824), [#29843](https://github.com/open-webui/open-webui/pull/29843)
+- 🎣 **Testing an image connection.** The Verify button beside an image generation connection saved the whole image configuration first and then tested whichever engine was active rather than the connection beside it, and it now tests exactly that connection and changes nothing. [Commit](https://github.com/open-webui/open-webui/commit/64bbdf7a73724986fac8bcf6e880fe32ef9ac495)
+- 🪝 **Responses API tool strictness.** A workspace tool, MCP server or OpenAPI server reaching a model on the Responses API was turned into a strict schema where it had never asked to be, so the model filled every optional field with empty strings, zeros and empty arrays, and search and filter tools were handed values where leaving them out was meant. [#30046](https://github.com/open-webui/open-webui/pull/30046), [#27750](https://github.com/open-webui/open-webui/issues/27750)
+- 🪃 **Responses API tool calling.** A forced tool choice sent to a connection on the Responses API went out in the wrong shape and was refused by providers that check it, and a tool call in a reply that was not streamed came back as empty text, so nothing reading the API ever saw it. [#30095](https://github.com/open-webui/open-webui/pull/30095), [#30085](https://github.com/open-webui/open-webui/issues/30085)
+- ⛓️ **Missing tools in links.** Opening a chat from a link whose "tools" or "tool-ids" parameter names a tool that no longer exists, or that the account cannot see, kept that id in the selection and sent it with the message; ids matching no tool the account has are now dropped and the rest of the link works as before. [#29803](https://github.com/open-webui/open-webui/pull/29803)
+- 🚫 **Model editor error messages.** A workspace model that cannot be loaded for editing now says so, instead of sending you back with "You do not have permission to edit this model" whatever the real reason. [#29694](https://github.com/open-webui/open-webui/pull/29694), [#29629](https://github.com/open-webui/open-webui/issues/29629)
+- 👥 **Directory updates that were dropped.** A change your identity provider sent as an add or a remove, or without naming the attribute it was changing, was accepted and then quietly discarded, so a rename or a deactivation never reached the account; those now take effect. [Commit](https://github.com/open-webui/open-webui/commit/ad9da981680c0fd9151c803a366a01545ea907c1)
+- 🗃️ **Directory request validation.** A provisioning request carrying the wrong kind of value, or an attribute Open WebUI does not support, now comes back as an error instead of passing in silence, and a sync that changes nothing no longer marks the account as touched. [Commit](https://github.com/open-webui/open-webui/commit/ad9da981680c0fd9151c803a366a01545ea907c1)
+- 🔘 **Model editor save button.** Saving a workspace model whose model list could not be refreshed afterwards now reports the error and frees the Save button, rather than leaving it disabled and spinning though the model had been saved. [Commit](https://github.com/open-webui/open-webui/commit/dc98e3023fc6e0113dbad76545cdb15e014db6ad), [Commit](https://github.com/open-webui/open-webui/commit/cc5479d16d5caf28ec19a16ffa1ee4f3dbc0f63f)
+- 🫱 **Rating a reply again.** Switching a reply's rating from one thumb to the other kept the score and the reason given the first time, and rating a reply whose feedback had since been deleted failed outright; both now record the rating you just gave. [#30075](https://github.com/open-webui/open-webui/pull/30075), [#30077](https://github.com/open-webui/open-webui/pull/30077)
+- 📶 **Sorting feedback by user.** The User column in the admin feedback history did nothing when clicked, and now sorts by who left the feedback. [#30191](https://github.com/open-webui/open-webui/pull/30191)
+- 🪂 **Closing the Edit User dialog.** Changes typed into the admin Edit User dialog and then abandoned showed on the row in the user list until the page was reloaded, and closing the dialog now drops them. [#30193](https://github.com/open-webui/open-webui/pull/30193)
+- 🪙 **Model defaults save.** Saving the model defaults in the admin settings put the selected, pinned and ordered models back as they stood when the page was opened, undoing anything changed in between. [#30206](https://github.com/open-webui/open-webui/pull/30206)
+- 👤 **A custom gender shown back.** An account whose gender is a wording of its own came back to an empty dropdown in the account form, and the form now shows Custom with that wording beside it. [#30215](https://github.com/open-webui/open-webui/pull/30215)
+- 🗓️ **Clearing a calendar event.** Emptying the repeat, the description or the location of a calendar event did not take and the old wording came back, and those fields can be cleared again. [#30204](https://github.com/open-webui/open-webui/pull/30204)
+- 📕 **Required prompt dropdowns.** A prompt's form could be sent with a required dropdown left unchosen, and now asks you to pick something first. [#30078](https://github.com/open-webui/open-webui/pull/30078)
+- 🎫 **Account form required fields.** The account form now refuses to save with a required field left empty, the way the admin user dialog does, and a date of birth is no longer demanded of accounts that never set one. [#30296](https://github.com/open-webui/open-webui/pull/30296), [#30295](https://github.com/open-webui/open-webui/issues/30295)
+- 🐑 **Model clones keep their base.** Cloning a model from the admin Models settings now carries the model it was built on, where the clone came out detached from it, and an arena model no longer offers Clone at all. [#30080](https://github.com/open-webui/open-webui/pull/30080), [#30079](https://github.com/open-webui/open-webui/issues/30079)
+- 🧤 **Model sharing survives a save.** Saving a model you cannot fully share no longer strips the access entries you cannot re-create, where an editor resending every stored entry had each one re-checked against what its author may grant, and a save from someone with narrow rights quietly took the model private for everyone else. [Commit](https://github.com/open-webui/open-webui/commit/754c4b5762ed0d79954ff28c4e06631004dc31b3), [#30093](https://github.com/open-webui/open-webui/pull/30093), [#30087](https://github.com/open-webui/open-webui/issues/30087)
+- 📠 **Prompt version saves.** Saving a new version of a prompt without Set as Production leaves the live prompt exactly as it was, where the draft quietly took its place, and the editor now shows the production text the moment a version is set. [#30231](https://github.com/open-webui/open-webui/pull/30231), [#30230](https://github.com/open-webui/open-webui/issues/30230), [#30233](https://github.com/open-webui/open-webui/pull/30233), [#30232](https://github.com/open-webui/open-webui/issues/30232)
+- 💬 **Model description round trips.** A workspace model whose description is switched from the default back to custom saves again, where the switch read the field as empty and the description was dropped on save. [#30249](https://github.com/open-webui/open-webui/pull/30249), [#30247](https://github.com/open-webui/open-webui/issues/30247)
+- 🎚 **Compaction threshold saves.** The context compaction threshold set in general settings now reaches the model parameters, where the value never left the page. [#30270](https://github.com/open-webui/open-webui/pull/30270), [#30269](https://github.com/open-webui/open-webui/issues/30269)
+- 📢 **Speech engine defaults.** Switching the text to speech engine now applies that engine's own default voice and model, where the change kept the previous engine's settings in place. [#30289](https://github.com/open-webui/open-webui/pull/30289), [#30288](https://github.com/open-webui/open-webui/issues/30288)
+- 🗞 **MinerU key in local mode.** The document settings save again in local mode with the MinerU key left empty, where the form demanded a key it did not need. [#30299](https://github.com/open-webui/open-webui/pull/30299), [#30298](https://github.com/open-webui/open-webui/issues/30298)
+- 🫂 **Group dialog reset.** The new-group dialog opens empty after a group is created, where the next one came up holding the group just made. [#30280](https://github.com/open-webui/open-webui/pull/30280), [#30279](https://github.com/open-webui/open-webui/issues/30279)
+- 🧵 **Thread reply notifications.** Clicking the notification for a reply written inside a thread dropped you at the bottom of the channel with the thread still shut and the reply nowhere in sight; it now opens the thread the reply belongs to. [#29856](https://github.com/open-webui/open-webui/pull/29856), [#29855](https://github.com/open-webui/open-webui/issues/29855)
+- 🔽 **Dropdown arrow spacing.** The arrow in the dropdowns drawn no wider than their contents, among them the provider on a new connection, no longer overlaps the last characters of the longest choice. [#29866](https://github.com/open-webui/open-webui/pull/29866), [#29865](https://github.com/open-webui/open-webui/issues/29865)
+- 🧊 **Lowercase header handling.** Headers from an upstream that writes them in lower case, as anything served by uvicorn does, are now matched without regard to case, so "Content-Encoding" is stripped and clients stop failing to decompress a body the server had already decoded. [#29843](https://github.com/open-webui/open-webui/pull/29843)
+- 🛑 **Complete chat stop.** Where a chat had more than one task in flight, stopping it, deleting it, or closing a note being worked on could stop the first and leave the rest running to the end, both because a task that had already finished ended the round early and because the list being worked through was rewritten underneath it as each one was cleared away; every task is now stopped in turn, so a reply that was calling tools stops calling them rather than running on to its own limit, though instances sharing their state through Redis were not affected. [Commit](https://github.com/open-webui/open-webui/commit/e35b907f737e625b900b3a03d61890f67ab0c4b0), [#29844](https://github.com/open-webui/open-webui/pull/29844), [#29816](https://github.com/open-webui/open-webui/issues/29816)
+- 🖊️ **Channel code blocks.** Where a model answers in a channel with structured output, the code inside it was drawn as plain highlighted text rather than in the editor every other message uses, so it could not be edited in place and a diff in it could not be opened for editing; it now renders the same way as everywhere else. [#29861](https://github.com/open-webui/open-webui/pull/29861)
+- 📐 **Code block edits on collapse.** An unsaved edit inside a code block stays on screen when the block is folded away and opened again, where collapsing it showed the saved text though the edit was still pending. [#30284](https://github.com/open-webui/open-webui/pull/30284), [#30283](https://github.com/open-webui/open-webui/issues/30283)
+- 🚨 **Code run errors with output.** A code run that ends with an error now shows the error alongside what it printed, where a run that printed anything at all showed its error nowhere. [#30286](https://github.com/open-webui/open-webui/pull/30286), [#30285](https://github.com/open-webui/open-webui/issues/30285)
+- 🔕 **Reactions on read-only channels.** The reaction picker no longer appears on a channel open to you as a viewer alone, matching the reply and menu options already hidden there. [#30241](https://github.com/open-webui/open-webui/pull/30241), [#30240](https://github.com/open-webui/open-webui/issues/30240)
+- 🎯 **Knowledge search accuracy on PostgreSQL.** A fresh install using PostgreSQL built its search index before a single piece of text existed to organise it around, so the index was never fit for the content that arrived afterwards and every search quietly returned the wrong passages; the index now waits until there is enough text to build on, and until then searches read everything exactly. An install already carrying such an index can restore it by rebuilding that one index. [#30143](https://github.com/open-webui/open-webui/pull/30143), [#30134](https://github.com/open-webui/open-webui/issues/30134)
+- 🗂 **Knowledge file filter on first click.** The File content filter in a knowledge base now narrows the listing the first time it is clicked, where the first click only armed the checkbox and everything stayed listed until it was clicked again. [#30211](https://github.com/open-webui/open-webui/pull/30211), [#30210](https://github.com/open-webui/open-webui/issues/30210)
+- 🔭 **Knowledge base search recall.** Where many knowledge bases are stored together, a search of one holding a small share of what is stored found only a small share of its matches, and the shortfall grew as the store did; the search now keeps looking until it has enough from the knowledge base you asked for, and "PGVECTOR_ITERATIVE_SCAN" switches that off or makes it strict. [#30142](https://github.com/open-webui/open-webui/pull/30142), [#30135](https://github.com/open-webui/open-webui/issues/30135)
+- 🪣 **Searches that found nothing.** A knowledge search that came back empty never handed its database connection back, so enough of them left knowledge search failing outright until the server was restarted; connections are returned now on PostgreSQL and on openGauss alike. [#30142](https://github.com/open-webui/open-webui/pull/30142), [#30133](https://github.com/open-webui/open-webui/issues/30133), [#30144](https://github.com/open-webui/open-webui/pull/30144)
+- 🧽 **Knowledge folder deletion.** Deleting a folder without moving what was in it up a level dropped the files from the listing but left their text in the search index and the files themselves in storage, so a model went on retrieving and citing pages from a folder that was no longer there; the text is now removed with the folder, and a file no other knowledge base holds is deleted with it unless file retention is switched on. [Commit](https://github.com/open-webui/open-webui/commit/17dbc6f001aeea25ae1df528cb79bb272eca4a77)
+- 🦀 **Regex searches over chat and knowledge files.** A pattern search now runs in time proportional to the text whatever the pattern, where a nasty expression could stall the search for good, and the patterns it accepts follow RE2's rules, with no lookarounds or backreferences and character classes matching ASCII only. [Commit](https://github.com/open-webui/open-webui/commit/97e013a66169c4fcd7f26ab9e41a4ff260ffd4da)
+- ⏰ **Automation schedule parsing.** An automation whose rule puts the time in "DTSTART" is now read at that hour, rather than listed at midnight and opened at nine, which moved when it ran as soon as it was saved again. [Commit](https://github.com/open-webui/open-webui/commit/540467b90a430e47e536c20710878b342de659fb)
+- ⏲️ **Recurrence counts and start dates.** A rule repeating a set number of times, ten or a hundred, is read as the limited repeat it is, where any count beginning with a one was treated as one-shot, and a rule carrying its start date on the same line as its repeat text now follows the start you picked, on schedules and calendar events alike. [#29262](https://github.com/open-webui/open-webui/pull/29262)
+- ⌛ **Stalled schedules and stuck tasks.** A schedule whose rule takes too long to work out no longer holds up the round that evaluates it and is skipped with a warning, and background tasks shared through Redis now expire once their worker falls silent, after "REDIS_TASK_TTL" seconds. [Commit](https://github.com/open-webui/open-webui/commit/5fb869db221d9599a576e8e2eea9c3314947d25e)
+- 📣 **Model mention chips.** A mention whose ID carried anything beyond letters, digits and a little punctuation, such as the brackets in some workspace model IDs, stayed on screen as the raw "<@…>" text both in the box you type in and in the message once sent; any ID without a space in it is now drawn as a chip. [#29864](https://github.com/open-webui/open-webui/pull/29864)
+- 😀 **Multi-codepoint emoji.** An emoji whose shortcode is several codepoints, the flags among them, is inserted whole, where only its first part reached the message. [#30213](https://github.com/open-webui/open-webui/pull/30213), [#30212](https://github.com/open-webui/open-webui/issues/30212)
+- 🔔 **Custom webhook names.** A webhook target named with a space or a slash is now tidied the way an automatic name always was, so it can still be edited, deleted, made the default or tested afterwards. [#29947](https://github.com/open-webui/open-webui/pull/29947)
+- 🪛 **Paginated MCP tool lists.** A server that hands its tools back a page at a time had only the first page read, so the rest were never offered to a model; the whole list is now collected before the tools are built. [Commit](https://github.com/open-webui/open-webui/commit/ffae4116a8d58a820f1770c41c69dafe4d51c881)
+- 💭 **Anthropic thinking blocks.** Open WebUI's own thinking blocks are no longer forwarded to an OpenAI-compatible backend, which since 0.11.0 made a strict server such as NVIDIA Dynamo refuse an Anthropic client's second turn; signed blocks still pass through. [#29849](https://github.com/open-webui/open-webui/pull/29849), [#29799](https://github.com/open-webui/open-webui/issues/29799)
+- 🗨️ **Channel model terminals.** A model with a terminal chosen in the workspace had that choice honoured in a chat but dropped where it answered in a channel or ran as a channel automation, so it worked without one; it now carries the same terminal everywhere, alongside the tools, filters and features it already carried. [Commit](https://github.com/open-webui/open-webui/commit/c78ad89934095c4e42e3f059d400a24fe5681de2)
+- 🧺 **Deleted channel messages leave no quotes.** Deleting a channel message now clears the quote of it sitting on every reply and drops it from the reply box, where a reply kept showing the deleted message and could still be sent addressed to it. [#30314](https://github.com/open-webui/open-webui/pull/30314), [#30313](https://github.com/open-webui/open-webui/issues/30313)
+- 🔌 **Terminal tools need a terminal.** A model was offered the tools that read your terminal and type into it whether or not the chat had a terminal switched on and connected in your browser, so it could reach for one that was not there; those tools are now handed over only for the terminal the chat has open. [Commit](https://github.com/open-webui/open-webui/commit/ca1eefe2937081b010ffef3985997d17d3332fa3), [Commit](https://github.com/open-webui/open-webui/commit/1ddba7e2c6f625fbc2c131eb24d3b9775ad898ad)
+- 🔤 **Custom header encoding.** The custom headers a connection sends are encoded once the values are filled in, so a person's name or group carrying anything beyond plain ASCII, a line break included, no longer breaks the request or reaches the other end as something else. [Commit](https://github.com/open-webui/open-webui/commit/7a4a4b93dca34f8ce0c481b180d3eea23797e984)
+- 🆎 **Chromium spellcheck corrections.** Picking a suggestion from the browser's own spelling menu in the message box did nothing, or put the misspelling straight back, because a highlight meant for the notes editor was being drawn over the selection and rebuilding the text underneath it, taking the browser's spelling marks with it; that highlight is now kept out of the message box and only drawn where the editor is not in use. [#29952](https://github.com/open-webui/open-webui/pull/29952), [#29944](https://github.com/open-webui/open-webui/issues/29944)
+- 🈁 **IME composition while renaming.** Confirming a chat rename with Enter or Escape part way through typing with an input method editor now finishes the composition without saving or cancelling the rename, where the key press acted at once. [Commit](https://github.com/open-webui/open-webui/commit/85146206f60a22385ed27dae30d4f00e7e2675eb)
+- 🐳 **Dotless host addresses.** With local web fetching turned on, an address pointing at a container name on the same network, "http://apprise:8000" and the like, is now accepted rather than refused as invalid. [#29945](https://github.com/open-webui/open-webui/pull/29945), [#28161](https://github.com/open-webui/open-webui/issues/28161)
+- 🪧 **False skill mentions.** Something written as "<$fh>" in a message, as Perl and other languages do, was taken for a mention of a skill and quietly removed before the model saw it, and drawn on screen as a chip; only mentions naming a skill that exists and is turned on are treated as mentions now. [Commit](https://github.com/open-webui/open-webui/commit/0edd731c7422870aa109fd0b758c6d68c06655da)
+- 🎒 **Skill settings survive saving.** Saving a skill from its editor cleared the tags and translations it carried and switched it back on where it had been disabled, and all of that now survives the save. [#30185](https://github.com/open-webui/open-webui/pull/30185)
+- 🫥 **Webhook avatar forwarding.** Turning "ENABLE_PROFILE_IMAGE_URL_FORWARDING" off stops browsers being sent on to outside picture addresses, and a channel webhook's picture was sent on regardless; it now serves the built-in picture like the rest, in the webhooks dialog as well as the message list, where the dialog had been sending every viewer's browser straight to the outside address. [#29889](https://github.com/open-webui/open-webui/pull/29889), [#29892](https://github.com/open-webui/open-webui/pull/29892)
+- 🪟 **Statistics window origin.** The window that shares chat statistics with the community accepted requests from any page that opened it and answered to anywhere; it now reads and replies only where the community site is at the other end. [#29918](https://github.com/open-webui/open-webui/pull/29918)
+- 🖼️ **Tool image rendering.** Where a tool answered with an image tucked inside an object or a list rather than on its own, the image was written into the conversation as its raw text, a single screenshot costing hundreds of thousands of tokens and crowding out everything else; such an image is now taken out wherever it sits and attached to the reply, so the model is handed the picture and you see it. An older fault that let every second image through untouched goes with it, and in a saved chat such an image is now kept as a file and referred to rather than written into the conversation itself, so the chat stays small. [#29665](https://github.com/open-webui/open-webui/pull/29665), [#29208](https://github.com/open-webui/open-webui/issues/29208), [Commit](https://github.com/open-webui/open-webui/commit/d372bec70427fe2d568e052ce5e1529e2ad41da9)
+- ⏱️ **Stopped reply state.** Pressing stop saved the reply as finished while the parts inside it were still marked as running, so a block went on reading "Thinking..." or "Executing..." and came back that way after every reload; those parts are now closed off as the reply is stopped, and an open tab settles at once rather than only after a reload, while a tool call still waiting for your approval keeps its prompt. [#29495](https://github.com/open-webui/open-webui/pull/29495), [#29281](https://github.com/open-webui/open-webui/issues/29281)
+- 🩺 **Knowledge sync errors.** A knowledge base sync that fails now names the file it happened on and what the browser said, rather than reporting nothing beyond "Error accessing directory". [#29507](https://github.com/open-webui/open-webui/pull/29507)
+- 🚧 **Terminal proxy restrictions.** Requests passed through to a terminal server are now refused where they aim at that server's administrative endpoints, are not followed on to somewhere else, and are turned away where the path carries characters a parser would rewrite. [Commit](https://github.com/open-webui/open-webui/commit/51bb8cb142f72503e861eeee25ae4dc73c26c36b)
+- ⛔ **Malformed tool calls.** Where a model asked for a tool with arguments that were not an object at all, a bare list or string, the reply stopped there; the model is now told what was wrong with the call and can try again. [Commit](https://github.com/open-webui/open-webui/commit/fed94c9f5af8a59660425d52df09e15fbedb25bc)
+- 📡 **Broken stream reporting.** Where something failed part way through streaming an answer out of "/api/chat/completions", the stream simply stopped, leaving a client waiting on an answer that would never finish; it now closes with an error and a proper end of stream. [Commit](https://github.com/open-webui/open-webui/commit/c0fb36c9b833a85a3a7364e195cf54f3d6c7a787)
+- 🧷 **Chat unblocked after an error.** A reply that failed, on a content filter or an exhausted quota, left the chat turning away everything you typed after it and stopped the message queue. Only the failed reply now ends, so the chat carries on and the other replies in a multi-model answer keep writing. [Commit](https://github.com/open-webui/open-webui/commit/dbb17a5725f9d7f844a6eee63ffca0bd077c7d94)
+- 🫙 **Empty failed replies in history.** An assistant turn that ended in an error with nothing written is no longer handed back to the model as part of the conversation when you send your next message. [Commit](https://github.com/open-webui/open-webui/commit/dbb17a5725f9d7f844a6eee63ffca0bd077c7d94)
+- 📭 **Empty page uploads.** Adding a web address to a knowledge base that came back without any text failed with a bare "Error uploading file" and, where the upload itself was refused, left the row sitting in the list; the reason now reaches you as it was given, and the row is taken away. [Commit](https://github.com/open-webui/open-webui/commit/6786ae1797eadaad7464a147213790e2d272822b)
+- 🎞️ **Tool embed scope.** The frames a tool call can ask to have shown, which run scripts of their own, were drawn wherever a message was rendered, a channel among them; they are now drawn only in the replies of the chat you are in, and never in a channel. [#29985](https://github.com/open-webui/open-webui/pull/29985)
+- 🚰 **Rejected picture addresses.** A model entry carrying a picture address the server refuses no longer leaves that address in memory, where anyone signed in could pile them up. [#29971](https://github.com/open-webui/open-webui/pull/29971)
+- 🖌 **Editing a stored image.** Asking a model to edit an image this instance already holds now works whatever host its address names, where a container name, a default port or a self-composed host made the edit fail with a generic loading error. [#29691](https://github.com/open-webui/open-webui/pull/29691), [#29220](https://github.com/open-webui/open-webui/issues/29220)
+- 🧪 **Memory replies carry less.** The memory tool no longer hands the model each memory's stored metadata, and a memory now records the model's id rather than the whole model entry. [Commit](https://github.com/open-webui/open-webui/commit/e9a0164690a8b1e190bdc8f4613e9d918b26d327)
+- 🔇 **Memory fully off.** With memory switched off, stored memories are no longer folded into a reply's context and the memory tools are no longer offered to the model, where both went on reaching it behind the switch. [#30228](https://github.com/open-webui/open-webui/pull/30228), [#30227](https://github.com/open-webui/open-webui/issues/30227)
+- 🧠 **Memory review behind the switch.** The background review that drafts new memories from a conversation no longer runs when memories are switched off or the account is barred from them, where it went on spending a task-model call every interval turn and failing at the write. [#30309](https://github.com/open-webui/open-webui/pull/30309)
+- 🏗️ **Terminal server save button.** Saving a terminal server now waits for the save to finish before the dialog closes and cannot be set off twice by a second click. [Commit](https://github.com/open-webui/open-webui/commit/1cdd7aa459d6e96905324b452600ff56369d8a4e)
+- 🗺️ **Terminal file panel paths.** The file panel beside a terminal now opens the file a model just wrote even when it is named with a relative path, where the panel could not match the name, jumped to the root and dragged the session's working directory with it. [#30282](https://github.com/open-webui/open-webui/pull/30282), [#30051](https://github.com/open-webui/open-webui/issues/30051)
+- 🍴 **Forked chat folder.** Forking a chat put the copy in the original's folder even where you cannot write to that folder; it is now created outside any folder unless you can. [#30069](https://github.com/open-webui/open-webui/pull/30069)
+- 🪢 **Dropping a folder in place.** Dragging a folder onto the folder it already sits in failed with "Folder already exists", and is now taken for the no-op it is. [#30169](https://github.com/open-webui/open-webui/pull/30169)
+- 🗝️ **Read-only folders read-only everywhere.** A folder shared with you as a viewer no longer shows its edit controls on the empty-chat page, where they appeared and a save went through or failed depending on rights the page never checked. [Commit](https://github.com/open-webui/open-webui/commit/ee3ece1e2b8c9a38c94faf354ca020d66aba801d)
+- 🚿 **Deleting a folder, keeping chats.** Removing a folder while keeping the chats inside it was refused for an account not allowed to delete chats, even though nothing was being deleted, and it now goes through. [#30163](https://github.com/open-webui/open-webui/pull/30163)
+- 🏷️ **Tag cleanup after deletion.** An administrator deleting someone else's chat tidied unused tags out of their own account rather than the owner's, leaving the owner with tags nothing points at. [#30171](https://github.com/open-webui/open-webui/pull/30171)
+- 🌱 **Forking past an unfinished reply.** A chat that held an interrupted reply anywhere in it refused every fork from then on and never recovered; forking now waits only on a reply actually being generated, and a turn paused for tool approval still forks with its prompt showing. [#30131](https://github.com/open-webui/open-webui/pull/30131), [#30128](https://github.com/open-webui/open-webui/issues/30128)
+- 💾 **Deleted tool memory.** Deleting a tool or a function left the whole of its code in memory for as long as the server ran; it is now let go of along with the rest. [#29983](https://github.com/open-webui/open-webui/pull/29983)
+- 🐌 **Sign-in rate limiting.** Counting sign-in attempts through Redis no longer stops the whole worker until Redis answers, so a slow Redis stops freezing every other request with it. [#29977](https://github.com/open-webui/open-webui/pull/29977)
+- ♻️ **Session pool cleanup.** The task that clears out abandoned websocket sessions now carries on through an error from Redis instead of ending for good, and stops properly at shutdown. [#29976](https://github.com/open-webui/open-webui/pull/29976), [#29979](https://github.com/open-webui/open-webui/pull/29979)
+- 🛰️ **Direct connections across workers.** A reply streamed over a direct connection no longer goes quiet part way through where several servers share their websocket traffic through Redis; the events it lives on now travel between workers the way the rest already did. [Commit](https://github.com/open-webui/open-webui/commit/0180efecf362d487e0c30f040f5948c325fbe337)
+- 🫧 **Empty document ids.** A save arriving for a document with no id at all was filed against that empty id and never cleared, so anyone signed in could pile them up; nothing is filed for it now. [#29980](https://github.com/open-webui/open-webui/pull/29980)
+- 🔬 **Page fetch CPU spin.** Fetching a page through the browser-driven loader never returned where that page opened a WebSocket, holding a worker thread at full CPU for the life of the process and costing another core on every further fetch, which left the whole instance slow. [#30050](https://github.com/open-webui/open-webui/pull/30050), [#30024](https://github.com/open-webui/open-webui/issues/30024)
+- 🔁 **Duplicate search tracebacks.** A vector database outage wrote a full traceback twice for every collection and query pair, turning one outage into hundreds of identical stack traces per message on every replica; a single record now names every collection that failed. [#29981](https://github.com/open-webui/open-webui/pull/29981)
+- 🧯 **Page fetch logging.** Fetching a page through the browser-driven loader filled the log with tracebacks where the page closed while it was still pulling pieces of itself, as sites behind Cloudflare and similar do; those requests are now let go of before the page closes. [#29325](https://github.com/open-webui/open-webui/pull/29325), [#28869](https://github.com/open-webui/open-webui/issues/28869)
+- 📤 **Tool export scope.** Exporting all tools at once returned every tool the account could see, the source of a tool shared for reading included; it now returns only the tools it may edit, matching the single-tool export and the way models already export. [#29310](https://github.com/open-webui/open-webui/pull/29310)
+- 🗳️ **Partial workspace exports.** Exporting the prompts or the models from the workspace wrote out only the page you happened to be looking at, so most of them were quietly left out of the file; both now export everything you are allowed to. [#30187](https://github.com/open-webui/open-webui/pull/30187)
+- 🧳 **Imported chats keep more.** A chat brought back from an export arrived unpinned and unarchived and without the variables it was saved with, and all three now survive the round trip. [#30155](https://github.com/open-webui/open-webui/pull/30155), [#30151](https://github.com/open-webui/open-webui/pull/30151)
+- 🗂️ **Unarchiving from search.** The menu on a search result offered to archive a chat that was already archived and said it had been archived when it had been brought back, and it now names and reports whichever of the two it did. [#30177](https://github.com/open-webui/open-webui/pull/30177)
+- 🙈 **Folder filters with no match.** A chat search narrowed by a folder name that matches no folder now finds nothing, where the folder filter was quietly dropped and every chat came back. [#30273](https://github.com/open-webui/open-webui/pull/30273), [#29959](https://github.com/open-webui/open-webui/discussions/29959)
+- 🧹 **Sidebar after bulk actions.** Archiving, deleting or unarchiving every chat at once, or importing a batch of them, left the folders and the pinned chats in the sidebar showing what was no longer there until the page was reloaded, and a bulk action that failed no longer reports success. [Commit](https://github.com/open-webui/open-webui/commit/8b3ee2827241ccc952a3073b2a6bbfad5df01827)
+- 🔐 **Model pictures follow model access.** The picture belonging to a model is now shown only to people who can see that model, where anyone signed in could fetch it and tell an existing model from an unknown one by which picture came back. [#29700](https://github.com/open-webui/open-webui/pull/29700)
+- 🚪 **Webhook pictures follow channel access.** The picture belonging to a channel webhook is now shown only to people with access to that channel, where anyone signed in could fetch it or be sent on to wherever it pointed, and it is refused outright where channels are turned off. [#29703](https://github.com/open-webui/open-webui/pull/29703)
+- 📎 **Safer Word document previews.** Previewing a Word document no longer renders an HTML sub-document embedded inside it, and a link in one opens only where it points at a web address, a mail address or a telephone number. [#29699](https://github.com/open-webui/open-webui/pull/29699)
+- 🚦 **Citation link schemes.** A source attached to a reply now opens only where it points at a web address, falling back to the panel that shows the source rather than following anything else. [#29701](https://github.com/open-webui/open-webui/pull/29701)
+- 🈚 **Citation chips inside formatted text.** A citation inside bold, italic or linked text now renders its chip, where the formatting took it and the citation vanished from the sentence. [#30278](https://github.com/open-webui/open-webui/pull/30278), [#30277](https://github.com/open-webui/open-webui/issues/30277)
+- 🐍 **Saving a tool or function.** Saving a tool or function in the admin pages no longer fails with a missing module error from the built-in code formatter, which was not installing everything it needed. [#29503](https://github.com/open-webui/open-webui/pull/29503)
+- 🛠️ **Tool request duplication.** A tool that writes through an address carrying part of its input no longer has that part repeated in the body of the request as well, which servers checking their input strictly turned away, so those calls now go through. [#29717](https://github.com/open-webui/open-webui/pull/29717), [#29716](https://github.com/open-webui/open-webui/issues/29716)
+- 🍎 **Answers survive on Apple Silicon.** Asking a question that searches a knowledge base with a locally run reranking model no longer takes the whole server down on a Mac, losing the answer and the connection with it. [#29735](https://github.com/open-webui/open-webui/pull/29735), [#29722](https://github.com/open-webui/open-webui/issues/29722)
+- 📚 **Web results stop being cited.** Pages a web search only listed are no longer offered to the model as things to cite, which had it attaching a result id to text from a different result and the citations panel resolving that to a title that looked right. [#29631](https://github.com/open-webui/open-webui/pull/29631), [#29627](https://github.com/open-webui/open-webui/issues/29627)
+- 🔎 **SearchApi errors, news and links.** Web search through searchapi.io now reports a bad key instead of coming back empty, reads the news results it returns alongside its ordinary ones, and hands the web loader the resolved destination link, so citations stop pointing at a redirect page. [#30308](https://github.com/open-webui/open-webui/pull/30308), [#30305](https://github.com/open-webui/open-webui/issues/30305)
+- 🔼 **Honest version checks.** An instance that cannot reach the release listing now says the check failed, instead of reporting whatever it is running as the newest version and recording nothing about it. [#29626](https://github.com/open-webui/open-webui/pull/29626), [#29580](https://github.com/open-webui/open-webui/issues/29580)
+- 🏟️ **Arena models report their errors.** A message to an arena model whose provider answers with an error now shows that error in the chat, where it used to fail on something unrelated and leave the real reason unsaid, and titles and tags no longer break the same way. [#29662](https://github.com/open-webui/open-webui/pull/29662), [#29658](https://github.com/open-webui/open-webui/issues/29658)
+- 🏳️ **Nameless tool calls fail once.** A model endpoint that sends a tool call with no name at all now has that call fail on the spot, rather than the missing name being kept, stored with the message and sent back on the next turn for the endpoint to reject. [#29690](https://github.com/open-webui/open-webui/pull/29690), [#29686](https://github.com/open-webui/open-webui/issues/29686)
+- 🧹 **Direct connections stop leaking listeners.** A server talking to a direct connection no longer leaves a listener behind for every request that ends any way but a clean finish, which grew without limit while a connection kept failing. [#29509](https://github.com/open-webui/open-webui/pull/29509)
+- 🚀 **Cheaper model refreshes.** The model registry shared through Redis is now written only when the models themselves change, rather than on every refresh because of the countdown Ollama attaches to a model it holds in memory. [Commit](https://github.com/open-webui/open-webui/commit/649c012ecf308a994ea180127f7f8f94d0aec311)
+- ✍️ **Continued reply text.** Asking for the rest of a cut-off reply in a temporary chat replaced what was on screen with only the new text, because the message being continued was read back from the saved chat it did not have. It is now taken from the request before the model is called, the continuation joins the same message instead of arriving as a second one, on a connection whose provider is set to llama.cpp the model is told to carry on from the text it is handed rather than repeat it back, opening the result in the message editor no longer shows a line break where the two halves meet, and, where haptic feedback is switched on, a continuation buzzes as it streams like any other reply. [Commit](https://github.com/open-webui/open-webui/commit/77d2000eb79e1cb6ae2004d40e8cca8c9e754cd0), [Commit](https://github.com/open-webui/open-webui/commit/6c7aa3543d21442241f6c53add5ff623ec816c44), [Commit](https://github.com/open-webui/open-webui/commit/57fc344873edc0db9e9f7ff3e9fb167cd80e3ef2), [Commit](https://github.com/open-webui/open-webui/commit/7eefeef4f17118f81c87acb464ad562803a6f26c), [Commit](https://github.com/open-webui/open-webui/commit/d418840aa9c4b77f613308cdaa4f2c6a062a8715), [Commit](https://github.com/open-webui/open-webui/commit/3795d5b29253d4b8d7a0adbab457c7317c40f3c6), [Commit](https://github.com/open-webui/open-webui/commit/57acc2b68f2f9e40b53aa7e609fdd52a4b0d15c4)
+- 🔗 **Cancelled edits keep attachments.** Cancelling the edit of a message no longer strips the files attached to it, where dropping the edit took the attachments down with it. [#30281](https://github.com/open-webui/open-webui/pull/30281), [#30192](https://github.com/open-webui/open-webui/issues/30192)
+- 🏎️ **Faster media page reads.** The browser-driven loader pulled every image, video and font a page referenced down through the server before any text was extracted, so a page carrying a few dozen audio players took ten seconds or timed out. Those requests are now dropped before they are made, and the same page comes back in under three seconds, having pulled 4 MB where it used to pull 55. [#29742](https://github.com/open-webui/open-webui/pull/29742), [#29741](https://github.com/open-webui/open-webui/issues/29741)
+- 📝 **Starting a note from search.** Starting a note from the search box now works when you are already on the notes page, keeps the whole of what you typed including characters such as ampersands and hashes, and no longer makes a further note each time the browser back button is pressed. [#29645](https://github.com/open-webui/open-webui/pull/29645), [#29642](https://github.com/open-webui/open-webui/issues/29642)
+- 📱 **Apple device replies.** An assistant reply no longer comes up blank in a home screen app, an in-app browser or a desktop-class window on Apple devices, where the check that avoided the drawing fault only recognised Safari itself. [#29734](https://github.com/open-webui/open-webui/pull/29734), [#29688](https://github.com/open-webui/open-webui/issues/29688), [#26712](https://github.com/open-webui/open-webui/issues/26712)
+- 📊 **Single source relevance.** A reply drawing on a single source now shows how relevant that source is, where the figure appeared only once a second source joined it and so looked as though it came and went. [#29647](https://github.com/open-webui/open-webui/pull/29647), [#29646](https://github.com/open-webui/open-webui/issues/29646)
+- 🔧 **Arduino sketches upload to knowledge.** A sketch file now reaches the plain text reader like the C++ and header files beside it, rather than being handed to a document extraction server that could make nothing of it and failing the upload. [#29673](https://github.com/open-webui/open-webui/pull/29673), [#29670](https://github.com/open-webui/open-webui/issues/29670)
+- 📰 **Docling conversion failures.** A file that Docling refuses or fails to convert now fails the upload with the reason Docling gave, rather than breaking with a raw error or quietly filing a placeholder that was then indexed and handed to the model in place of the file. [#30107](https://github.com/open-webui/open-webui/pull/30107), [#29808](https://github.com/open-webui/open-webui/issues/29808)
+- 📄 **Uploaded text kept as written.** A file whose text contains escape sequences such as the one standing for a non-breaking space is now stored and read by the model exactly as it was written, rather than having some of them rewritten depending on where in the file they sat. [#29736](https://github.com/open-webui/open-webui/pull/29736), [#29732](https://github.com/open-webui/open-webui/issues/29732)
+- 🔦 **Readable slash command labels.** The entries in the slash command menu no longer show as white text on a white background in the light theme. [#29512](https://github.com/open-webui/open-webui/pull/29512), [#29510](https://github.com/open-webui/open-webui/issues/29510)
+- ⌨️ **Literal arrow sequences.** A sequence such as three hyphens after a less-than sign is now shown as the characters it is made of rather than drawn as an arrow, which had text look changed when it never was. [#29595](https://github.com/open-webui/open-webui/pull/29595), [#29594](https://github.com/open-webui/open-webui/issues/29594)
+- 🖌️ **Editing an image you uploaded.** An image already held by Open WebUI can now be used with image editing, where fetching its own link back over the network could fail on a private network or without a sign-in. [Commit](https://github.com/open-webui/open-webui/commit/50413f34824ea49d5b94d3a97f3fe4bb2e881e38)
+- 🖼 **Playground image edits.** Editing an image in the Images playground now works, where every attempt came back rejected since the request carried its fields under a heading the endpoint never read. [Commit](https://github.com/open-webui/open-webui/commit/c07fa08b995e8d1a1fc2d94a88d8cea691bdc5ee)
+- 🎨 **A tidier attach webpage dialog.** The row holding the Add button no longer carries a grey band of its own between the address box and the button, matching every other dialog. [#29664](https://github.com/open-webui/open-webui/pull/29664), [#29663](https://github.com/open-webui/open-webui/issues/29663)
+- 🖱️ **A plain note date.** The date under a note title no longer shows a pointing hand or announces itself as something to press, having never done anything when clicked. [#29708](https://github.com/open-webui/open-webui/pull/29708)
+- 🌇 **Folder backgrounds on creation.** The background image picked in the Create Folder dialog now arrives on the folder when it is created from the sidebar, where the image was discarded unless the dialog was opened from an existing folder. [#30218](https://github.com/open-webui/open-webui/pull/30218), [#30217](https://github.com/open-webui/open-webui/issues/30217)
+- 🖇 **Delete Chat shortcut everywhere.** The keyboard shortcut that deletes the open chat now works wherever the chat was opened from, where it did nothing unless the chat's row happened to be on screen in the sidebar at that moment. [#30165](https://github.com/open-webui/open-webui/pull/30165), [#30164](https://github.com/open-webui/open-webui/issues/30164)
+- 🚮 **Retired chat variables.** A model whose system prompt no longer declares a variable a previous prompt did stops asking for it, where every new chat kept opening the dialog and refusing to send until a value was entered. [#30173](https://github.com/open-webui/open-webui/pull/30173), [#30172](https://github.com/open-webui/open-webui/issues/30172)
+- 👁️ **Compact hover previews in Safari.** Holding over a chat in the sidebar shows the small preview every other browser shows, rather than one laid out at the width and spacing of a full conversation. [#29734](https://github.com/open-webui/open-webui/pull/29734)
+- 🔖 **Visible title generation faults.** When a new chat's automatic title cannot be generated, the reason now reaches the log at the default level, rather than only under debug logging where a broken feature looked the same as a switched-off one. [#30106](https://github.com/open-webui/open-webui/pull/30106), [#29533](https://github.com/open-webui/open-webui/issues/29533)
+
+### Changed
+
+- 🪶 **Slim starts with nothing configured.** The slim image leaves out the local models and the libraries around them, and still starts and holds a conversation on its defaults; the features that leaned on those models each need an external service of their own. [Commit](https://github.com/open-webui/open-webui/commit/cb942bb94c8dc7941336088fb3392e2398ff56c1)
+- 🗄️ **Slim database support.** The slim image runs on SQLite, its default, or on PostgreSQL; pointed at MySQL, MariaDB or another engine, or started with AWS RDS IAM logins switched on, it stops with an error instead of starting, and those deployments need the standard image. [Commit](https://github.com/open-webui/open-webui/commit/d27aa72ab4a7b5632b4ad49e8467081ad3d7ebb4)
+- 📁 **Slim file storage.** The slim image keeps files on local storage, its default; configured for an S3, Google Cloud or Azure bucket, it stops with an error instead of starting, and those deployments need the standard image. [Commit](https://github.com/open-webui/open-webui/commit/d27aa72ab4a7b5632b4ad49e8467081ad3d7ebb4)
+- 🧮 **Slim searches only through pgvector.** Knowledge search on the slim image needs PostgreSQL with pgvector, and configured for another vector store the instance still starts, and the failure arrives the first time something is searched rather than at startup. [Commit](https://github.com/open-webui/open-webui/commit/cb942bb94c8dc7941336088fb3392e2398ff56c1), [Commit](https://github.com/open-webui/open-webui/commit/d27aa72ab4a7b5632b4ad49e8467081ad3d7ebb4)
+- 🧠 **Slim embedding requirements.** The slim image carries no embedding or reranking model, so knowledge needs OpenAI, Ollama or Azure OpenAI embeddings and an external reranker, falling back to plain cosine scoring where none is set. [Commit](https://github.com/open-webui/open-webui/commit/cb942bb94c8dc7941336088fb3392e2398ff56c1)
+- ✂️ **Slim document splitting.** Splitting a document along a downloaded tokenizer is unavailable on the slim image, which leaves splitting by character or by token count. [Commit](https://github.com/open-webui/open-webui/commit/cb942bb94c8dc7941336088fb3392e2398ff56c1)
+- 📃 **Slim document readers.** The slim image reads text, Markdown, CSV, HTML and XML files as they are; uploading a PDF, a Word file or a presentation fails unless one of the external document extractors is configured. [Commit](https://github.com/open-webui/open-webui/commit/cb942bb94c8dc7941336088fb3392e2398ff56c1)
+- 🎙️ **Slim speech requirements.** The slim image carries neither local Whisper nor local voices, so speech to text and text to speech need an external engine before they will work. [Commit](https://github.com/open-webui/open-webui/commit/cb942bb94c8dc7941336088fb3392e2398ff56c1)
+- 🕸️ **Slim web page fetching.** The slim image carries no headless browser, so a web page is fetched over plain HTTP or through an external loader, and a page that draws itself with JavaScript comes back with less of its content than on the standard image. [Commit](https://github.com/open-webui/open-webui/commit/cb942bb94c8dc7941336088fb3392e2398ff56c1), [Commit](https://github.com/open-webui/open-webui/commit/d27aa72ab4a7b5632b4ad49e8467081ad3d7ebb4)
+- 🔎 **Slim leaves out DDGS.** DDGS, the metasearch provider that needs no key of its own, is not carried in the slim image, so web search there needs a provider with a key. [Commit](https://github.com/open-webui/open-webui/commit/0fa4dea5ff64ea663f162d07c9a1175c39e4aad0)
+- 📥 **Slim code interpreter packages.** The slim image leaves out the code interpreter's packages, so the browser fetches numpy, pandas, matplotlib, scikit-learn and the rest from "cdn.jsdelivr.net" and the interpreter stops working where that is blocked. [Commit](https://github.com/open-webui/open-webui/commit/98fcb844e1b19f7dd6289af26273cdec5447dc52)
+- 🧰 **Slim git requirements.** The slim image no longer carries git, so a tool or function whose requirements point at a "git+https://" address fails to install and needs the standard image or a published package. [Commit](https://github.com/open-webui/open-webui/commit/30eed1251301f74e0dfeaad09c41e81320f790fc)
+- 🧺 **LangChain community removal.** The readers for text, HTML, Word, CSV, PDF and Azure Document Intelligence are now written here rather than taken from "langchain-community", which is no longer installed; a tool or function importing it has to name it in its own requirements from now on. [Commit](https://github.com/open-webui/open-webui/commit/05484aa055a868a49842e1ddff169c19c98b755b)
+- 🧾 **Undeclared package imports.** Packages that sat in the image only by accident, among them nltk, pymongo, the Google Drive client and the Gemini SDK, are no longer installed, so a tool or function importing one must name it in its own requirements. [#29725](https://github.com/open-webui/open-webui/pull/29725), [#29726](https://github.com/open-webui/open-webui/pull/29726), [Commit](https://github.com/open-webui/open-webui/commit/a1c02098aa2687c72482a59117efe643b785df51)
+- 🆔 **Model ID whitespace.** A workspace model whose ID contains a space or a tab is now refused in the editor, through the API and on import; one already stored goes on answering but cannot be saved again until it is recreated. [Commit](https://github.com/open-webui/open-webui/commit/8a19e2f867063256bb2836649e2fe80af41ef748)
+- 🖇️ **Link scheme rendering.** A link in a reply, a citation or a web search result is now rendered only where it points at a web address, a mail address, a telephone number or somewhere inside this instance; anything else, an "ftp://" address or an application link such as "obsidian://" or "vscode://" among them, is shown as the text it is. Two old oddities go with it: a source written as "HTTP://" now becomes a link, and a filename merely containing the letters http no longer becomes one that leads nowhere. [#29890](https://github.com/open-webui/open-webui/pull/29890)
+- 🧲 **Integrations tab is opt-in.** The Integrations tab in personal settings, where tool and terminal connections of your own are managed, is now hidden until an administrator turns on Direct Integrations under Integrations or sets "ENABLE_DIRECT_INTEGRATIONS", and hiding it leaves existing connections working. [Commit](https://github.com/open-webui/open-webui/commit/6d8e63e3666e1b1aa5540ffda0816be5f40c5271), [Commit](https://github.com/open-webui/open-webui/commit/c82634b9d01adadbf9780ff84a0a8168fdc4fdea)
+- 📡 **Image connection check endpoint.** The endpoint that checks an image generation connection has moved and now takes the connection to test in the request itself, so anything calling the old address needs updating. [Commit](https://github.com/open-webui/open-webui/commit/64bbdf7a73724986fac8bcf6e880fe32ef9ac495)
+
+## [0.11.3] - 2026-08-31
+
+### Added
+
+- ♿ **Accessibility mode reaches the menus.** Accessibility mode now marks the menu entry you are pointing at and the model already chosen with a stronger background, across the dropdown menus, their submenus, and the model picker together with its filter and compare controls, so those cues carry the contrast the accessibility guidelines ask for in both themes. [Commit](https://github.com/open-webui/open-webui/commit/a6f9751401589ee73208295b6f6a7f6eae9c1b44), [Commit](https://github.com/open-webui/open-webui/commit/471b5cbbb16c3996c32e68808dde6f8898f64ecd)
+- 🔄 **General improvements.** Various improvements were implemented across the application to enhance performance, stability, and security.
+- 🌐 **Translation updates.** Translations for Indonesian were enhanced and expanded.
+
+### Fixed
+
+- 💥 **Chat branches stay connected after reloads.** A reply saved under an earlier message now stays listed under that message, so branch arrows, exports, reloads, and later edits keep the whole conversation in view, and chats already saved with that link missing are repaired when opened. [#29299](https://github.com/open-webui/open-webui/issues/29299)
+- 🧱 **Upgrades fail clearly instead of starting half updated.** A failed database upgrade now stops at the migration error that caused it, instead of starting anyway and reporting a missing table or column such as 'chat.timer_at' later, which is the upgrade failure seen after moving from 0.11.0, 0.11.1, or 0.11.2. [#29280](https://github.com/open-webui/open-webui/issues/29280)
+- 🔤 **Custom interface fonts reach more of the app.** The font chosen in interface settings now applies to dropdowns and other interface text that previously fell back to the standard font. [Commit](https://github.com/open-webui/open-webui/commit/1457000ba66547b24bd98012aa35ac16fd4bc696)
+- 🔌 **Disconnect OAuth only where there is OAuth.** The disconnect control on a tool server reached over MCP now appears only where that server signs in through OAuth and an account is connected, rather than on servers that use no sign-in at all. [#29296](https://github.com/open-webui/open-webui/issues/29296)
+
+## [0.11.2] - 2026-08-31
+
+### Added
+
+- 🖼️ **Richer previews for terminal files.** Word documents and slide decks produced in the terminal are now previewed as the finished document rather than an approximation, and every document preview gains a page strip down the side with numbered thumbnails you can click to jump straight to a page, and the notice warning that a preview might differ from the download is gone now that it does not. [Commit](https://github.com/open-webui/open-webui/commit/061fb434328ea8365cc4961519e8adbe5ac7b0c1), [Commit](https://github.com/open-webui/open-webui/commit/9d95a0148b3180ba48186bc6928713f969a69047), [Commit](https://github.com/open-webui/open-webui/commit/ae549d3e4af672a63a809e8fe2a6c91e0bfc1067), [Commit](https://github.com/open-webui/open-webui/commit/78d8c9166f1b6626b9aa559a812183ce216eef4f), [Commit](https://github.com/open-webui/open-webui/commit/492ccf3ac0d9aec1f3f2bc6825a3e6d3b32aa0d1)
+- ⚡ **Less overhead on every message.** Deployments without pipelines configured, which is the default, no longer pay setup work for them on each chat message and background task. [#29146](https://github.com/open-webui/open-webui/pull/29146)
+- 🏎️ **Lighter model list refreshes.** On deployments running several workers, a refresh that finds the model list unchanged no longer has every worker rewrite the whole list to the shared cache, cutting the work and the traffic each refresh costs. [#29264](https://github.com/open-webui/open-webui/pull/29264)
+- 🧵 **Smoother busy websocket servers.** Large Redis-backed websocket deployments now spend far less time sweeping old sessions, reading their own session data back from Redis, and checking every outgoing websocket message for file attachments Open WebUI does not send, so channel posts, collaboration updates, heartbeats, and live chat updates put less load on busy servers. [#28835](https://github.com/open-webui/open-webui/pull/28835), [#28180](https://github.com/open-webui/open-webui/pull/28180)
+- 🧰 **A new request filter step.** Filter authors can now use `request` to adjust the payload right before each model call, including follow-up calls after tool use, while existing `inlet`, `stream`, and `outlet` filters keep working as before. [Commit](https://github.com/open-webui/open-webui/commit/2daa610cba514dfe2eae008b1fc440d4ddb0e470), [Commit](https://github.com/open-webui/open-webui/commit/2a4ef46ac86ada3447eb6d6c50fd4c1241eebd4d)
+- 🤏 **More room in file previews on touch screens.** File previews on phones and tablets no longer show zoom buttons that sit over an already small preview, leaving pinch to zoom to do the job. [#29176](https://github.com/open-webui/open-webui/pull/29176), [#29152](https://github.com/open-webui/open-webui/issues/29152)
+- 👆 **Resizing panels by touch.** The divider beside the main sidebar or a side panel can now be dragged on a touchscreen or with a stylus, and a drag made with the mouse keeps following the pointer when it leaves the window. [Commit](https://github.com/open-webui/open-webui/commit/cfa2d25317b426c80dca43829afbf113eeccc365), [Commit](https://github.com/open-webui/open-webui/commit/f0ffa7508e75946434794941378675e0c7151eae), [Commit](https://github.com/open-webui/open-webui/commit/e250be48ee16d71202651e4109a175910a6519bb)
+- 🔤 **Choice of interface font.** Interface settings now offer a font family field where you can name a font installed on your computer and watch it apply across the interface as you type, with an empty field returning to the standard font. [Commit](https://github.com/open-webui/open-webui/commit/b9765fe97943831e17a68490cd01c70a6ccf1c43)
+- ♿ **Wider accessibility mode coverage.** Accessibility mode now lifts the contrast of more of the interface, including muted text, table text, icons, the colours elements change to on hover, and the highlight behind sidebar and menu items you point at, so low-contrast areas meet the level the accessibility guidelines ask for in both light and dark themes, and the close button on the folder dialog now announces itself to screen readers, as do document and slide previews, which can now be reached with the keyboard. [Commit](https://github.com/open-webui/open-webui/commit/e6031ea6daec897eddbcf0c8b03c2d6fad2b506e), [Commit](https://github.com/open-webui/open-webui/commit/797b4c51d1e31f614c8e6eba14ee347c61ad0c7a), [#29160](https://github.com/open-webui/open-webui/pull/29160), [Commit](https://github.com/open-webui/open-webui/commit/e4694f82ebd2e916c099e5e921c0ca8445ba88a7), [Commit](https://github.com/open-webui/open-webui/commit/120409ef016c1e866247e2aa1eba7606f797a20c)
+- 🌐 **Translation updates.** Polish, Simplified Chinese, German, Irish, Catalan, and Portuguese (Brazil) translations were expanded, corrected, and brought up to date with newer interface text. [#29029](https://github.com/open-webui/open-webui/pull/29029), [#29043](https://github.com/open-webui/open-webui/pull/29043), [#29108](https://github.com/open-webui/open-webui/pull/29108), [#29151](https://github.com/open-webui/open-webui/pull/29151), [#29184](https://github.com/open-webui/open-webui/pull/29184), [#29179](https://github.com/open-webui/open-webui/pull/29179), [#29247](https://github.com/open-webui/open-webui/pull/29247), [#29217](https://github.com/open-webui/open-webui/pull/29217)
+
+### Fixed
+
+- 🛡️ **Security Advisory**: This release includes security and access-control fixes. We recommend updating production deployments at your earliest convenience. Not all security fixes in this version may be enumerated in the fixed section. Some may be withheld for a short time to give administrators time to upgrade. [Advisories](https://github.com/open-webui/open-webui/security)
+- 💥 **Replies stop breaking mid-chat.** A conversation no longer fails in the browser and stops showing the assistant reply until you reload, and chats already saved in that state display and can be edited again. [#29250](https://github.com/open-webui/open-webui/pull/29250), [#29244](https://github.com/open-webui/open-webui/issues/29244)
+- ⌨️ **Preview shortcuts stay in the preview.** Arrow keys now page a document or slide preview only while that preview has focus, instead of paging it from anywhere on the page and taking the arrow keys away from whatever you were typing in. [Commit](https://github.com/open-webui/open-webui/commit/b356b80f8c86d110951301b83607de245b4ef6cc), [Commit](https://github.com/open-webui/open-webui/commit/e4694f82ebd2e916c099e5e921c0ca8445ba88a7)
+- 🧊 **Streaming no longer stalls on reasoning models.** A reply from a reasoning model now streams through to the end instead of showing its first few words and then freezing until generation finishes. [#29053](https://github.com/open-webui/open-webui/pull/29053), [#29035](https://github.com/open-webui/open-webui/issues/29035)
+- 💭 **Thinking stays in Thoughts.** After a model uses a tool, its reasoning for the next step now appears in the collapsed Thoughts section instead of being written into the reply as ordinary text. [#29052](https://github.com/open-webui/open-webui/pull/29052), [#29040](https://github.com/open-webui/open-webui/issues/29040)
+- 🧠 **Large tool calls stream faster through Anthropic-compatible clients.** When a streamed tool call sends a large block of arguments, Open WebUI now waits until that block can actually be complete before checking it, instead of doing the same expensive check again on every tiny piece. [#28858](https://github.com/open-webui/open-webui/pull/28858)
+- 🛑 **Stop works across instances.** Stopping a response now takes effect on deployments that spread people across several instances backed by a Redis cluster, instead of the reply continuing to the end regardless. [#29165](https://github.com/open-webui/open-webui/pull/29165), [#19840](https://github.com/open-webui/open-webui/issues/19840)
+- 🎯 **Fewer needless chat reloads.** A conversation holding an older unfinished reply no longer reloads itself each time some other response in it finishes, reloading only for the reply the update actually concerns. [Commit](https://github.com/open-webui/open-webui/commit/22379ded1aebf0537e1ee3f00a20809d47646bf6)
+- 📖 **Banners with underlined text.** A banner containing underlined text now displays instead of failing to render. [#29118](https://github.com/open-webui/open-webui/pull/29118), [#29115](https://github.com/open-webui/open-webui/issues/29115)
+- 🧰 **Pinned models start with their own tools.** Starting a chat from a pinned model in the sidebar now applies that model's tools and skills instead of carrying over the ones from the model you used last. [#29058](https://github.com/open-webui/open-webui/pull/29058), [#29050](https://github.com/open-webui/open-webui/issues/29050)
+- ❓ **Rejected ask_user calls no longer kill the reply.** If a model asks the user a question in a way Open WebUI refuses, the model now receives that error and can continue or retry, instead of leaving the chat stopped with no answer. [#29252](https://github.com/open-webui/open-webui/pull/29252), [#29077](https://github.com/open-webui/open-webui/issues/29077)
+- 🚫 **Disabled models no longer vanish.** Turning a model off in the admin Models list now keeps it in view so you can turn it back on, instead of it disappearing with no way to recover it. [#29037](https://github.com/open-webui/open-webui/pull/29037), [#29036](https://github.com/open-webui/open-webui/issues/29036)
+- ✂️ **Message text kept intact.** Text containing angle brackets and a dollar sign is no longer mistaken for a skill mention and silently removed before your message reaches the model. [#29051](https://github.com/open-webui/open-webui/pull/29051), [#29041](https://github.com/open-webui/open-webui/issues/29041)
+- 📆 **Moved calendar events stay visible.** Changing an event's date no longer makes it disappear from the calendar, and events already stuck in that state show up again. [#29085](https://github.com/open-webui/open-webui/pull/29085), [#29067](https://github.com/open-webui/open-webui/issues/29067)
+- 🔁 **Repeats follow the event.** A repeating event now works out its occurrences from its own date and time, where a repeat rule carrying a start date of its own could place them on the wrong weekday or at the wrong hour. [Commit](https://github.com/open-webui/open-webui/commit/a93c5080380447e3ab9113cacb73b61c57cbc308)
+- 🔟 **Repeating automations keep their count.** An automation set to run a fixed number of times is no longer shown as running once and quietly rewritten to a single run the next time you open and save it. [#29261](https://github.com/open-webui/open-webui/pull/29261), [#29263](https://github.com/open-webui/open-webui/pull/29263)
+- 🗓️ **Schedules survive a save.** An automation carrying a start date now shows its real schedule in the list and keeps its weekly or monthly setting when saved, instead of showing raw rule text and falling back to daily. [#29263](https://github.com/open-webui/open-webui/pull/29263)
+- 🧩 **Custom automation schedules stay custom.** Reopening an automation with a custom repeat rule no longer loses the custom rule from the editor. [#29260](https://github.com/open-webui/open-webui/pull/29260)
+- 🔢 **Accurate admin user counts.** The counts on the admin Users tabs now follow your search and reset when you switch tabs, instead of showing stale or unfiltered numbers. [#29080](https://github.com/open-webui/open-webui/pull/29080), [#29079](https://github.com/open-webui/open-webui/issues/29079)
+- 🧷 **Sidebar folders stop acting stale.** A folder that has been removed from the sidebar is now removed from the internal sidebar registry too, so later sidebar actions do not target a folder that is no longer on screen. [#29121](https://github.com/open-webui/open-webui/pull/29121)
+- 📱 **Readable model list on small screens.** The model identifier and timestamp in the workspace model list no longer overlap the model name on narrow displays. [#29084](https://github.com/open-webui/open-webui/pull/29084), [#29083](https://github.com/open-webui/open-webui/issues/29083)
+- 🧱 **Long setting values stop crushing labels.** Settings rows now let long controls shrink inside the available space instead of squeezing the label beside them. [#29229](https://github.com/open-webui/open-webui/pull/29229)
+- 🧭 **Model defaults panels stay usable.** The model capabilities and prompt suggestion sections in admin settings now scroll inside their panels instead of growing past the available space. [#29235](https://github.com/open-webui/open-webui/pull/29235)
+- 📲 **Dropdowns stay on screen.** A dropdown near the edge of a narrow screen now shifts inward to stay fully visible instead of opening past the edge with its option labels cut off. [#29226](https://github.com/open-webui/open-webui/pull/29226), [#29225](https://github.com/open-webui/open-webui/issues/29225)
+- 🌗 **Dropdown lists follow the theme.** The list a dropdown opens now takes its light or dark colouring from the rest of the interface instead of the system default. [Commit](https://github.com/open-webui/open-webui/commit/58a3fadbf336029733d6e5fdde05fd5a24e656fa)
+- 🎛️ **Valves dialog stays in bounds.** A valve whose selected options form a long line no longer stretches its input past the edge of the dialog and over the page behind it. [#29203](https://github.com/open-webui/open-webui/pull/29203), [#29202](https://github.com/open-webui/open-webui/issues/29202)
+- 🧹 **Shared chats search resets.** Reopening the shared chats dialog now starts with an empty search box and the full list, rather than a leftover search term above unfiltered results. [#29082](https://github.com/open-webui/open-webui/pull/29082), [#29081](https://github.com/open-webui/open-webui/issues/29081)
+- 🔎 **Case-insensitive search beyond English.** Searching and filtering by tag now ignore letter case for accented and non-Latin text on installations backed by SQLite, where only unaccented English letters were matched whatever their case. [Commit](https://github.com/open-webui/open-webui/commit/26f37426b7ef6c0c3b1363f413ac9a83ccaaeb71)
+- 🏷️ **Labels with colons and example URLs translate correctly.** Interface text such as `Warning:`, `http://localhost:8000`, and `https://mineru.net/api/v4` now appears correctly instead of being misread by the translation system. [#29161](https://github.com/open-webui/open-webui/pull/29161), [#29154](https://github.com/open-webui/open-webui/issues/29154)
+- 🔑 **Precise account matching on SQLite.** Signing in through an identity provider now matches your account on its exact identifier, so accounts whose identifier is an unusually long or zero-padded number are no longer at risk of being confused with another. [Commit](https://github.com/open-webui/open-webui/commit/17cc566707cd2ee78b460e39c7fad23b9c258c70)
+- 🗃️ **Knowledge list loads reliably.** The Knowledge page in the workspace now fills in its list on opening instead of occasionally staying empty. [Commit](https://github.com/open-webui/open-webui/commit/e6031ea6daec897eddbcf0c8b03c2d6fad2b506e)
+- 🎟️ **Tool servers without a key.** A tool server connection saved without a key is no longer sent an empty authorization header, which some servers refused outright. [Commit](https://github.com/open-webui/open-webui/commit/26f37426b7ef6c0c3b1363f413ac9a83ccaaeb71)
+- 🐍 **Code interpreter starts on Windows.** The built-in code interpreter now serves its script and WebAssembly files with the browser-safe file types Windows hosts sometimes overwrite, so Pyodide can load instead of failing before code runs. [#29139](https://github.com/open-webui/open-webui/pull/29139), [#29133](https://github.com/open-webui/open-webui/issues/29133)
+
+### Changed
+
+- ⏱️ **Daily limit on repeats.** A calendar event can no longer be set to repeat more often than once a day, and saving one that repeats more often is now refused with a message explaining the limit. [Commit](https://github.com/open-webui/open-webui/commit/a93c5080380447e3ab9113cacb73b61c57cbc308)
+- 🏷️ **High Contrast Mode is now Accessibility Mode.** The interface setting previously called 'High Contrast Mode' is now called 'Accessibility Mode', with the same switch in the same place. [Commit](https://github.com/open-webui/open-webui/commit/e6031ea6daec897eddbcf0c8b03c2d6fad2b506e)
+
+## [0.11.1] - 2026-08-25
+
+### Added
+
+- 🚦 **Human in the loop tool approval.** Where an administrator has turned it on, you can switch a conversation from letting tools run freely to being asked first, so a model that wants to use a tool stops and waits for you to allow or deny it, one call at a time in a saved conversation, by button or by keyboard shortcut, with your choice remembered for this conversation and for future ones, switching back to running freely releasing anything already waiting, and automations, channel replies, and temporary chats unaffected. [Commit](https://github.com/open-webui/open-webui/commit/7d99b2716a0472b2100b3a71825d8eb3fcbbe877), [Commit](https://github.com/open-webui/open-webui/commit/ec36972c2b5a8d48713f1a240b0ed305e535b4cc), [Commit](https://github.com/open-webui/open-webui/commit/653562d660398c32a9a193450bbbee300d7195c3), [Commit](https://github.com/open-webui/open-webui/commit/fa94a5ab2431edba064150651a14dd4992ef29e8), [Commit](https://github.com/open-webui/open-webui/commit/55c202e841e76cd69679206cd0ecb4a65b039ea4), [Commit](https://github.com/open-webui/open-webui/commit/30f82788bc75e6965da3766e3bf43840dd971eed), [Commit](https://github.com/open-webui/open-webui/commit/bbfdbd59f29e246db1d8b5c2401bc7b11aa32c99), [Commit](https://github.com/open-webui/open-webui/commit/7fc5fa1ff3f6cd6f0efcbf847064ca8d21620ba6), [Commit](https://github.com/open-webui/open-webui/commit/3eb65f47151af4fb4ccfaf33d6e77154546e7259), [Commit](https://github.com/open-webui/open-webui/commit/62fc436999ad32e82d1405ac14d1f03e0f0341ec)
+- 🙋‍♂️ **Models that can ask you a question.** A new built-in tool lets a model pause and put up to three multiple-choice questions to you before continuing, with room to type your own answer instead, and the question survives a reload in a saved conversation, so you can come back and answer it later rather than losing the conversation. [Commit](https://github.com/open-webui/open-webui/commit/4465f52a3eb521854cf190f91b0ea7cf3fa21830), [Commit](https://github.com/open-webui/open-webui/commit/133549a87ee371577453d897c2db2d8071223f27), [Commit](https://github.com/open-webui/open-webui/commit/b018feb7419e68314378b3cdd8b7b1b389400a98), [Commit](https://github.com/open-webui/open-webui/commit/083e35144152d6a301bed01aa6d898db3871ddcf), [Commit](https://github.com/open-webui/open-webui/commit/256cce505be8ddd4930e8cb2536faea718d3f789), [Commit](https://github.com/open-webui/open-webui/commit/14e4d72d9a21a10196e8e6efb04180cd9104b8e6), [Commit](https://github.com/open-webui/open-webui/commit/57bd08304e45f707768a898de9f50894929008dd), [Commit](https://github.com/open-webui/open-webui/commit/d9014b3483d4c6e8d99e50395afcdc538bcf05cd)
+- 🖇 **Agents can now display terminal files directly.** A model can now show a file it made in a terminal directly in its reply, with a preview and a download button, instead of describing a path that led nowhere when clicked, and a new interface setting chooses whether these open in the reply or in the files pane. [Commit](https://github.com/open-webui/open-webui/commit/78f48a21eef330c0b78c33f2b5fc2169b084997c), [Commit](https://github.com/open-webui/open-webui/commit/e623c02acc70c4ee5d7f2eb2f32d9b7f39287663), [Commit](https://github.com/open-webui/open-webui/commit/f64c0c87e8d1bfdbe060ea5e5a3dee24c0323657), [#27650](https://github.com/open-webui/open-webui/issues/27650)
+- 📶 **Streaming rebuilt from the ground up.** A reply now streams as small pieces of new text instead of resending the whole message so far with every update, so the data sent over a reply grows with its length rather than with its length squared, which on a server with many people chatting at once means far less processor time spent encoding, passing, and decoding those updates, far less load and memory on the shared cache that carries them between instances, and far less work in your browser, which no longer takes in the whole reply again and redraws the parts of it that have not changed on every update, cutting the data sent and the server work spent appending to a message by up to 1000x on a very long reply, and a reply still in progress is now kept aside on the server, so reopening the conversation after a refresh picks it up where it is rather than showing a blank message, on deployments backed by Redis. [Commit](https://github.com/open-webui/open-webui/commit/a1579a01ff43cacb357269707d36267ad35e01d6), [Commit](https://github.com/open-webui/open-webui/commit/c755ef60c6bd47ea25306bd898d9a6d1bd8e871d), [Commit](https://github.com/open-webui/open-webui/commit/d02b6a21fc02fb073782e25356968cfee3c45c36), [Commit](https://github.com/open-webui/open-webui/commit/3e186abdd91edee9e97e43c9b345714643a84cf5)
+- 🪵 **Much faster throughout.** Hundreds of places across the application no longer assemble detailed log text that is switched off and thrown away unread, so sending messages, uploading and indexing files, running searches, signing in, and loading admin pages all get that time back, with the largest gains on busy servers, in long conversations, and on chats that draw from a large knowledge base. [#27834](https://github.com/open-webui/open-webui/pull/27834), [#27837](https://github.com/open-webui/open-webui/pull/27837)
+- 🚀 **Faster model list lookups.** Title generation, tag suggestions, autocomplete, and other background steps of a chat turn now fetch the model list in one go, which keeps other people's responses flowing on busy Redis-backed instances with many models. [#27821](https://github.com/open-webui/open-webui/pull/27821)
+- 🛰️ **Cheaper log export.** Deployments that export their logs to a telemetry collector, with "ENABLE_OTEL" and "ENABLE_OTEL_LOGS" both set, now prepare each exported line once instead of twice, which matters more than it used to now that log text is only assembled when something will actually read it. [#27840](https://github.com/open-webui/open-webui/pull/27840)
+- 📇 **Faster permission checks on large instances.** Working out which groups you belong to is now a direct lookup rather than a scan of every membership on the server, so chats and the admin user list stay quick as an organization grows. [#27822](https://github.com/open-webui/open-webui/pull/27822)
+- ⚙️ **Much faster JSON handling.** Saving and opening chats, reading settings, returning results from built-in tools, streaming replies, signing in and signing up, working out your permissions, and reading stored chunk details during knowledge base searches on Valkey and Oracle vector storage are all handled much faster across the application when the "ENABLE_ORJSON" option is turned on. [Commit](https://github.com/open-webui/open-webui/commit/bb0f898b431d5aa45efa7805956657ed9c3dd78d), [#28396](https://github.com/open-webui/open-webui/pull/28396), [#27841](https://github.com/open-webui/open-webui/pull/27841), [#27807](https://github.com/open-webui/open-webui/pull/27807), [#27805](https://github.com/open-webui/open-webui/pull/27805), [#27813](https://github.com/open-webui/open-webui/pull/27813)
+- 📤 **Much faster outbound requests.** Conversations and embedding batches sent to Ollama and Anthropic models are packaged for delivery much faster, which is most noticeable in long chats when the "ENABLE_ORJSON" option is turned on. [#27811](https://github.com/open-webui/open-webui/pull/27811), [#27810](https://github.com/open-webui/open-webui/pull/27810)
+- 🐍 **Much faster code interpreter output.** Printed output and generated images from code run in chat appear much faster when the "ENABLE_ORJSON" option is turned on. [#27812](https://github.com/open-webui/open-webui/pull/27812)
+- 🪶 **Lighter page loads.** Several small requests the interface makes on every page load, along with a few administrative ones, no longer set up database access they never used, which took several times longer than the rest of the request put together. [#28178](https://github.com/open-webui/open-webui/pull/28178)
+- ♻️ **One less read per message.** Sending a message no longer loads the whole conversation from the database twice over, which mattered most in long chats where that record is largest. [#28809](https://github.com/open-webui/open-webui/pull/28809)
+- 🏁 **Faster skills on large instances.** Opening the skills list, or sending a message that uses one, no longer checks every skill on the instance one at a time, so both are far quicker where many skills exist and most of them are not yours. [#28798](https://github.com/open-webui/open-webui/pull/28798)
+- 🩻 **Faster tools on large instances.** Listing or exporting tools no longer checks every tool on the instance one at a time, so the integrations menu and the tools workspace open faster where many exist. [Commit](https://github.com/open-webui/open-webui/commit/4807866a1cf47340f1b5ea76fded95f8114305f9)
+- 🧊 **Faster file access checks.** Checking whether you may reach a file no longer walks every workspace model you can see looking for it, so opening a folder of files, downloading one, or retrieving from one is much quicker on instances with many models. [#28802](https://github.com/open-webui/open-webui/pull/28802)
+- 🧱 **Faster folder listings.** Listing your folders now works out your group memberships once for the whole listing rather than again for every item in every folder. [#28810](https://github.com/open-webui/open-webui/pull/28810)
+- 🧼 **Less work per update in a long chat.** Each update saved while a reply streams no longer re-examines the entire conversation, only the part being added, so the cost of an update stops growing with the length of the chat. [#28820](https://github.com/open-webui/open-webui/pull/28820)
+- 🗃 **Cheaper attaching of sources and files to a reply.** Adding a source, file, or embedded item to a reply now reads just that one field rather than rebuilding the whole conversation to find it, which on a two hundred message chat is around 3.1 ms per item down to 0.65 ms, and no longer grows with the length of the conversation. [Commit](https://github.com/open-webui/open-webui/commit/536b9edec00547d5b84ef2e6ea0f929c054c1333), [Commit](https://github.com/open-webui/open-webui/commit/9dff5e93277aa1a2236d702e7e2f55dbb35ea7fa)
+- 🚏 **Faster workspace model lookups.** Working out which workspace models you may edit no longer loads every model on the instance and discards most of them, which also speeds up exporting models and the file access checks that relied on it. [#28795](https://github.com/open-webui/open-webui/pull/28795)
+- 📮 **Faster handing off a streaming reply.** Passing a reply in progress between instances now writes it once rather than converting it back and forth and scanning it for characters that only matter elsewhere, which on a large non-English conversation took most of the time spent on each write. [#28833](https://github.com/open-webui/open-webui/pull/28833)
+- 🥵 **Constant load on an idle instance.** An instance sitting idle no longer works through every chat you have once a second looking for timers that are due, which on a large history kept about a quarter of a processor core busy doing nothing and could exhaust memory until the application was killed. [#27663](https://github.com/open-webui/open-webui/pull/27663), [#27622](https://github.com/open-webui/open-webui/issues/27622), [#27745](https://github.com/open-webui/open-webui/issues/27745)
+- 📍 **Sidebar folders fetched once.** Refreshing the sidebar now asks for your folders once rather than three times, on page load and on every action that refreshes it. [#28662](https://github.com/open-webui/open-webui/pull/28662), [#28661](https://github.com/open-webui/open-webui/issues/28661)
+- 💤 **Far fewer writes just from being signed in.** Recording that someone is online now writes at most once a minute for each person rather than on every single request, where an open tab alone caused two write transactions a minute before anyone touched anything. [#28177](https://github.com/open-webui/open-webui/pull/28177), [#28165](https://github.com/open-webui/open-webui/issues/28165)
+- 🛰 **Less overhead on every request.** The layers each request passes through before it is handled are now one instead of five, which also removes a quarter of that cost from every piece of a streamed reply on instances that set security headers. [Commit](https://github.com/open-webui/open-webui/commit/b96d2b12dae5e953e520bec03f74e9b85b955dc7), [#28171](https://github.com/open-webui/open-webui/issues/28171)
+- 🎏 **Turning off compression of live updates.** A new "UVICORN_WS_PER_MESSAGE_DEFLATE" setting stops the server compressing every live update it sends, which costs processor time on each one for almost no saving now that a reply streams as small pieces; compression stays on unless it is turned off. [#28613](https://github.com/open-webui/open-webui/pull/28613)
+- 🌡 **Faster chat list and unread counts.** Opening the sidebar, and the unread markers on folders, no longer read through your whole chat history to produce a short list, which on an instance with 15000 chats took 2 to 4 seconds. [#27663](https://github.com/open-webui/open-webui/pull/27663), [#27622](https://github.com/open-webui/open-webui/issues/27622), [#27745](https://github.com/open-webui/open-webui/issues/27745)
+- 🥁 **Long replies no longer slow as they grow.** A long reply is no longer re-examined from the beginning for reasoning and code blocks on every piece that arrives, so the work stops growing with the length of the reply, which on a long reply is around 190x less time spent on it. [#28861](https://github.com/open-webui/open-webui/pull/28861)
+- 💽 **Faster saving of long chats.** A chat is now written to the database in one go rather than one message at a time, so saving a long conversation is much quicker and puts far less strain on the database, and saving one where nothing has changed writes nothing at all. [#28806](https://github.com/open-webui/open-webui/pull/28806)
+- 📦 **Faster loading of shared folders.** Folders shared with you now load in a couple of queries rather than one for each folder and each owner, so the list appears sooner for anyone with many of them. [#28804](https://github.com/open-webui/open-webui/pull/28804)
+- ⚡ **Uninterrupted chat during knowledge search.** Responses now keep streaming for everyone on the server while knowledge base searches run, instead of pausing until each search finishes. [#27824](https://github.com/open-webui/open-webui/pull/27824)
+- 🔍 **Smarter chat search.** Searching your chats now finds conversations containing all of your words in any order rather than only the exact phrase you typed, with exact matches still listed first, and the preview snippet points at whichever word it found. [Commit](https://github.com/open-webui/open-webui/commit/0800c21c64c64810f24c2ec88cca5e36daebb10e)
+- ⌨️ **Model switching from the message box.** Typing "/model" now tells you which model you are on, switching to another by name with "/model" followed by its id, or opening the model picker straight from the slash menu without reaching for the mouse. [Commit](https://github.com/open-webui/open-webui/commit/29eeda9f9abeaedf77176908cb036ace7f175e76), [Commit](https://github.com/open-webui/open-webui/commit/9c7ce154e79a3baea3a8223ab1e5b1371ce80dbb)
+- 📎 **Sending while attachments upload.** Sending a message before its files have finished uploading now queues it and sends it automatically once they are ready, instead of refusing with an error, and each queued message shows the progress of its attachments. [Commit](https://github.com/open-webui/open-webui/commit/6c4d0ace163a89aba6e8cd2aa9fef185167ebe0f), [Commit](https://github.com/open-webui/open-webui/commit/c1c07cbe0f847e4dd04e21f2a6c5f12cdc0fc7ee), [#28381](https://github.com/open-webui/open-webui/pull/28381), [#28380](https://github.com/open-webui/open-webui/issues/28380)
+- 📖 **Opening a document at the right page.** A model showing you a PDF, Word document, or slide deck from a terminal can now open it at a particular page or slide, so a reply that cites something on page 76 can put that page in front of you. [Commit](https://github.com/open-webui/open-webui/commit/fd8cc2ba4a226ccbf51e114c71f156676eabb2d9), [Commit](https://github.com/open-webui/open-webui/commit/cf4ac9c8db67031627f196fae894764367fba5b4), [Commit](https://github.com/open-webui/open-webui/commit/6cb2449ab70ed6aa5124fcd2b1291b48527af4cd)
+- 💼 **Attachments that go straight to a terminal.** A terminal connection can now be set to receive files attached in chat into its own working directory rather than into the conversation, which also means files can be attached while using a model that cannot read them itself. [Commit](https://github.com/open-webui/open-webui/commit/8a42aa53e826d5f25d6443ca95e0173e3cf034cf), [Commit](https://github.com/open-webui/open-webui/commit/d7d935275a77fb185586a5130cd37acf1175ca0a), [Commit](https://github.com/open-webui/open-webui/commit/1b3b9375bb4de0f360782dd2f9d8c7c2903b8baa), [Commit](https://github.com/open-webui/open-webui/commit/d17f06a23501e5c39cf98d9c9642178da25343fb)
+- 🔦 **Searching files in the terminal browser.** The file browser now has a search box that finds files by name and by what is inside them, and opening a result takes you to the matching line. [Commit](https://github.com/open-webui/open-webui/commit/7abe11346a1cc309da2c3fcec2f61faaeb47b96a)
+- 🌲 **Browsing files as a tree.** The terminal file browser now expands folders in place rather than only navigating into them, remembers what you had open, offers a right-click menu, can show hidden files, sorts by size, expands a folder you hover over while dragging something onto it, and moves a whole selection in one go when you drop it. [Commit](https://github.com/open-webui/open-webui/commit/7dfbdd221ac0f7a839dd049e3e82b6a84c316860), [Commit](https://github.com/open-webui/open-webui/commit/516cf1a9a6154336182475b9df2d333b1579516d)
+- 🧰 **Managing models on more servers.** Administrators can now download, load, and unload models on llama.cpp and LM Studio connections from the manage models dialog, remove them on llama.cpp, and start a download straight from the model picker's search box, alongside the Ollama support that was already there. [Commit](https://github.com/open-webui/open-webui/commit/85c3d0ae2fad58ffc2b92b1733a6c8bc7ab471db), [Commit](https://github.com/open-webui/open-webui/commit/8260d527ee97372a207ce9bd9c6dab4909061281), [Commit](https://github.com/open-webui/open-webui/commit/25802c048e6123fa602182949ad2a9f349e1e863), [Commit](https://github.com/open-webui/open-webui/commit/31c1ffd55a018a74c7e53a35fb9f9bbe33774b6f), [#28766](https://github.com/open-webui/open-webui/pull/28766)
+- 📢 **Automations that post to a channel.** An automation can now be pointed at a channel instead of a chat, so its scheduled run appears as a message there for everyone to see, chosen from a new destination picker that also covers folders. [Commit](https://github.com/open-webui/open-webui/commit/2649e3305c49cb37101c112ae10ffd8beacb5885)
+- 🙋 **Mentioning people in a channel.** Typing an at sign in a channel now lists that channel's own members first, before everyone else on the server, so the people you are likely to mean are at the top. [Commit](https://github.com/open-webui/open-webui/commit/ba885d0026ad3cce70c7cc36d1d6f59775264a12), [Commit](https://github.com/open-webui/open-webui/commit/dcff244f9e87e615ee0a3f345f7f801c5ebe370d), [#28883](https://github.com/open-webui/open-webui/issues/28883)
+- 🔗 **Attaching any link.** Pasting a link into a chat or a knowledge base now works out what is behind it, downloading a document or image as a real attachment rather than treating everything as a web page to be read as text. [Commit](https://github.com/open-webui/open-webui/commit/8fbfd14a8b3fe7236883594fd18760076e4de0d5)
+- 🔎 **Searching tools and skills in chat.** The integrations menu now has a search box for tools and for skills, so a long list can be narrowed by name instead of scrolled through. [#26709](https://github.com/open-webui/open-webui/issues/26709), [Commit](https://github.com/open-webui/open-webui/commit/954613944b317a78d5929456ae1388543aa052c8), [#28807](https://github.com/open-webui/open-webui/pull/28807), [#28812](https://github.com/open-webui/open-webui/pull/28812)
+- 🧭 **More from the message box.** The slash menu now offers settings and, in a new chat, a toggle for temporary chat, alongside the commands that were already there. [Commit](https://github.com/open-webui/open-webui/commit/a5ea732c1e3d0d1f70a7e4b6a20c30c336114784)
+- 🚨 **Being told when a file fails to process.** A file that cannot be processed for a knowledge base now raises a notification naming the file and what went wrong, and keeps that reason on the file, instead of quietly being marked as failed. [#27666](https://github.com/open-webui/open-webui/pull/27666), [#6311](https://github.com/open-webui/open-webui/issues/6311), [Commit](https://github.com/open-webui/open-webui/commit/1a376ac17fa0c3f957656a997b6f8ffacb1f6f30)
+- 🔬 **Zoom controls on previewed images.** An image opened in the file browser now has zoom in, zoom out, and a reset button showing the current zoom, and pinching, scrolling, and holding a modifier key while scrolling now zoom and pan as they do elsewhere. [Commit](https://github.com/open-webui/open-webui/commit/2befa8f796266e92fa55861bb8eaa81639ff4053), [Commit](https://github.com/open-webui/open-webui/commit/bfb68feea766e8d5408fb6e278be56cbca0c4afe), [Commit](https://github.com/open-webui/open-webui/commit/ec9bf5a64f9f718e472123350ec83bce1b064884), [Commit](https://github.com/open-webui/open-webui/commit/467be93e6d7e4a31358f9c75ee67bfac1200c0a1)
+- 🗂️ **Recognisable file icons.** The terminal file browser now marks each file with an icon for its type, so code, images, archives, documents, and configuration files can be told apart at a glance instead of sharing one generic page icon. [Commit](https://github.com/open-webui/open-webui/commit/60feca71a6a77b7d1eef1c172a61624d5fe48150), [Commit](https://github.com/open-webui/open-webui/commit/8d25ad00e2fc5f0a328a2098c2e73fb00f2ca934), [Commit](https://github.com/open-webui/open-webui/commit/c1f914a6268580f7722825390ac8a204743a4520)
+- 📽️ **Truer PowerPoint previews.** Slide previews now render tables, charts, connectors, gradients, theme colours, bullets, fonts, and text alignment far closer to the original, and the viewer lets you move between slides with the arrow keys or the scroll wheel while the thumbnail strip follows along. [Commit](https://github.com/open-webui/open-webui/commit/8dd23f74c9a59fdfbdaefb4a403ef79bdd3dfed9), [Commit](https://github.com/open-webui/open-webui/commit/048c06399363baac4046717129f072172ee90805), [Commit](https://github.com/open-webui/open-webui/commit/c93c6d6fc48ee8870eec349cb4c5af88c9435cfb), [Commit](https://github.com/open-webui/open-webui/commit/76583749edb966c0239ce203a84c1ee8d8c7faee), [Commit](https://github.com/open-webui/open-webui/commit/b3a5fd3875dc3c29a11eb5435438e55685cad639), [Commit](https://github.com/open-webui/open-webui/commit/794671a9883d5e067c407067f324ffa25ed38e3f), [Commit](https://github.com/open-webui/open-webui/commit/f96b717566b2084bd5fe70fb622ab66b5a643c0d), [Commit](https://github.com/open-webui/open-webui/commit/b7292890ccea794750651abbcde01cda62551e1b), [Commit](https://github.com/open-webui/open-webui/commit/31d08d592c4ee46a7ce827d6ffdf8e3cf16bf2ac)
+- 📄 **Faithful Word document previews.** Word documents now open as proper pages with headers, footers, footnotes, and embedded images intact, and can be zoomed, rather than being flattened into plain formatted text. [Commit](https://github.com/open-webui/open-webui/commit/ff7467b4c593f1e775311c088c63340d0cc1e4a2), [Commit](https://github.com/open-webui/open-webui/commit/060648f939447e2a9de390d05221ca896c50eeed)
+- 🗝 **Deleting your API key.** An API key can now be revoked outright from your account settings, where the only way to retire one was to replace it with a new one. [#28874](https://github.com/open-webui/open-webui/issues/28874), [Commit](https://github.com/open-webui/open-webui/commit/b30b11d4c975b8ff9a6c6eb9e39fbb310aed1072)
+- 🎛️ **Settings for the task model.** Administrators can now set the generation parameters used for background work such as titles, tags, follow-ups, search queries, and conversation summaries, either from the admin panel or through "TASK_MODEL_PARAMS", instead of those requests always using a fixed token limit that could cut a summary short. [#27604](https://github.com/open-webui/open-webui/issues/27604), [Commit](https://github.com/open-webui/open-webui/commit/f0bfcd40976dfb1e1876f86b39d6a659d894d15e), [Commit](https://github.com/open-webui/open-webui/commit/865c80c1600ecc2e606bef4e90540ce305b4b9de)
+- 🎚️ **Default interface settings for everyone.** Administrators can now set system-wide defaults for the interface options in Settings, either from the admin panel or through "DEFAULT_INTERFACE_SETTINGS", with each person's own choices still taking precedence and anything left untouched shown as inherited and kept in step with later changes to the defaults. [Commit](https://github.com/open-webui/open-webui/commit/37f2548155efdd5cd8114ceb9b57c7864de4bef2), [Commit](https://github.com/open-webui/open-webui/commit/13346c5f1621b014e2fcaabd41375d6f7035dd0a), [Commit](https://github.com/open-webui/open-webui/commit/90a0e61cef119154e89d900d6921123b599a0389), [Commit](https://github.com/open-webui/open-webui/commit/eeaf1a1df01525e4b6d4eb73060b32a9a75ebfc6), [Commit](https://github.com/open-webui/open-webui/commit/d4461bd6f39936460a989e8bd50097de604b4b00), [Commit](https://github.com/open-webui/open-webui/commit/b4d3b27caf1587b783a46268c769132eb9211c80), [Commit](https://github.com/open-webui/open-webui/commit/407c40f72cdadcd9f57538d9ce38070662ce42c7), [Commit](https://github.com/open-webui/open-webui/commit/724d2ebbf1bd2fc90f27a2e5bc571d40afc3db4c), [Commit](https://github.com/open-webui/open-webui/commit/1674e5a9ef835696f0963cdbcf477c8b92ce0b8a)
+- 🔠 **Interface scaling throughout.** The UI Scale setting and your browser's own text size now resize the whole interface consistently, including the sidebar, menus, dialogs, and file browser, rather than leaving parts of it fixed. [Commit](https://github.com/open-webui/open-webui/commit/30d08a42f8b0c32cc64dccd81203cc760651584a), [Commit](https://github.com/open-webui/open-webui/commit/b5f86e6a433b519e30a5a6f1b0a5bf985939c9a8), [Commit](https://github.com/open-webui/open-webui/commit/ec03e8814403422a6ab3dc62f4239fd7af439361), [Commit](https://github.com/open-webui/open-webui/commit/72a909fd2f3ac8d67554f6c85bc1723934454e2d)
+- 🏷️ **Named writing blocks.** When a model wraps a draft such as an email in a writing block, the block is now titled with its subject and shows the recipient beside it, rather than every block reading simply as Writing. [#28280](https://github.com/open-webui/open-webui/pull/28280), [#28198](https://github.com/open-webui/open-webui/issues/28198)
+- 🤝 **Files for delegated tasks.** A task handed to a sub-agent can now carry the attachments it needs, so an image or document from your conversation reaches the sub-agent instead of arriving as a file reference it cannot open and may answer about anyway. [Commit](https://github.com/open-webui/open-webui/commit/5ec16e76e6402980b39c26923b8ee26278f0b243), [#28213](https://github.com/open-webui/open-webui/issues/28213)
+- 📟 **Terminal availability and scope.** Administrators can now decide for each managed terminal whether it appears in chats and in automations at all, and whether everyone shares a single workspace or each chat or automation gets its own, with per chat terminals waiting until the conversation has been saved. [Commit](https://github.com/open-webui/open-webui/commit/009999f3636b1a3451f8fe55232e6ab132a64e66)
+- 🔒 **Read-only files in the terminal browser.** Files and folders you are not allowed to change are now labelled read-only, with uploading, editing, renaming, moving, and deleting turned off for them rather than failing at the moment you try. [Commit](https://github.com/open-webui/open-webui/commit/2dadc5435af77b0638af69200e3af1b9654417b6)
+- 🔐 **Terminals that use your own login.** Managed terminals configured for session authentication now authenticate the terminal connection with your own token, where it previously sent no credentials at all. [Commit](https://github.com/open-webui/open-webui/commit/2dadc5435af77b0638af69200e3af1b9654417b6)
+- 🎟 **Setting up a tool server that uses OAuth.** Adding one is now easier to get right: the connection dialog can authorize the account from the dialog itself, the check button tests the sign-in details rather than reporting a connection failure that was never going to succeed without them, and it is now labelled for what it does rather than suggesting it verifies the whole connection. [Commit](https://github.com/open-webui/open-webui/commit/f822605b3563c57030aa200492f68572cadcc4da), [#28552](https://github.com/open-webui/open-webui/issues/28552)
+- 🪤 **Control over what embedded pages may do.** Two new interface settings decide whether pages shown inside a chat, such as an artifact or an HTML preview, may run scripts and start downloads. [Commit](https://github.com/open-webui/open-webui/commit/3c66d639e31ba8a7477d337b37d8d671ea2430cf), [#28924](https://github.com/open-webui/open-webui/issues/28924), [Commit](https://github.com/open-webui/open-webui/commit/842c1f9d677c0d9940cccdd18e34add13f746a68)
+- 🗄 **Keeping files removed from a knowledge base.** A new "ENABLE_KNOWLEDGE_FILE_RETENTION" setting keeps the stored file and its search data when a file is taken out of a knowledge base, rather than deleting them. [Commit](https://github.com/open-webui/open-webui/commit/363ad352fec9553469852d111bc0506b896504a6)
+- 🧾 **CSV shape in retrieval.** Turning on "ENABLE_RAG_CSV_SUMMARY" adds a short line naming the row count, data row count, column count, and column names of a CSV file to what the model sees, giving it the shape of the table alongside its contents. [Commit](https://github.com/open-webui/open-webui/commit/1b72899f246ba46ab8f7cd6aee2d56ef69217d82)
+- 🔭 **OpenSERP in the search settings.** OpenSERP can now be picked as the web search engine in the admin panel, with a field for its address, rather than only being configurable through the environment. [#27594](https://github.com/open-webui/open-webui/pull/27594), [#27592](https://github.com/open-webui/open-webui/issues/27592)
+- 🪧 **Profile changes from single sign-on.** A name, email address, or picture updated from an identity provider at sign-in now raises an event naming what changed, and the rest of the session uses the updated record rather than a stale copy. [Commit](https://github.com/open-webui/open-webui/commit/927ce0eae67af1b4a856d3e82fba0601c3b40d02)
+- 📯 **Group changes from single sign-on.** Group memberships added or removed when someone signs in through an identity provider, and groups created automatically along the way, now raise the same events as the equivalent change made by an administrator or over directory sync. [#27657](https://github.com/open-webui/open-webui/pull/27657)
+- 🔔 **Sign-in and sign-out events for single sign-on.** Signing in through an identity provider now raises the same login event that signing in with a password does, and signing out says which provider the session came from, so a function can set up or tidy up an account in another system when someone arrives or leaves. [#27619](https://github.com/open-webui/open-webui/pull/27619), [#27613](https://github.com/open-webui/open-webui/issues/27613)
+- 🪛 **Naming background worker threads.** A new "THREAD_POOL_THREAD_NAME_PREFIX" setting labels the threads that background work runs in, so they can be told apart when reading a profile or a thread dump. [Commit](https://github.com/open-webui/open-webui/commit/4ec6ee14418edd04eaba9e34bd5868453f61df40)
+- 📙 **OpenDocument files in a temporary chat.** A text document, spreadsheet, or presentation from an office suite that uses the OpenDocument format now has its text read out in the browser when attached to a temporary chat, where the model was handed the raw archive and answered that it could not read the file. [Commit](https://github.com/open-webui/open-webui/commit/9e7c9360b744c878ae0c38aa1caf3886f27b07ab), [#28906](https://github.com/open-webui/open-webui/discussions/28906)
+- 🌍 **Pointing Tavily somewhere else.** A new "TAVILY_API_BASE_URL" setting sends Tavily searches and page fetches to a different address, for instances that reach the internet only through a gateway of their own or that use a compatible service. [Commit](https://github.com/open-webui/open-webui/commit/98ee2bdfd3e90faec6bfe8e7ebf5803159f379e3), [#28701](https://github.com/open-webui/open-webui/issues/28701)
+- 🪟 **Honest OAuth settings.** When single sign-on settings come from the environment rather than being saved in the application, the admin panel now shows them as read-only with a note naming the setting that controls this, instead of accepting edits that were silently discarded on the next restart. [#28276](https://github.com/open-webui/open-webui/pull/28276)
+- 📏 **Widening the chat controls pane.** The controls pane can now be dragged as wide as you like, where it stopped at a fixed limit regardless of screen size. [Commit](https://github.com/open-webui/open-webui/commit/0fb542b3764cefecf2366607a4685288051d1b46)
+- 📱 **Smoother sidebar on mobile.** The sidebar now follows your finger as you swipe it open or closed, responds to a quick flick, dims the page behind it as it moves, and gives every chat row a menu button you can reach without a hover you cannot perform on a touchscreen. [Commit](https://github.com/open-webui/open-webui/commit/b20bcdbba72707e3b0cf2b9a6a5f3168b464ba3c), [Commit](https://github.com/open-webui/open-webui/commit/178ccb30e1253ea727fe5ccbb5cc3ca3832dc70b), [Commit](https://github.com/open-webui/open-webui/commit/943294df9a03d45e2708b330e876967af3463282), [Commit](https://github.com/open-webui/open-webui/commit/d6679082e5c6b0b54ca00a99a88e66a53a30c7d9), [Commit](https://github.com/open-webui/open-webui/commit/d8ae7ed40551362922925d9d6e47ba65d3658cfd), [Commit](https://github.com/open-webui/open-webui/commit/be4afd75452361ead376d9977cf2ca8cb93e55eb), [Commit](https://github.com/open-webui/open-webui/commit/ab41dcc487d1517f7c8c5d0b02a02cdaadedb03d)
+- 🚪 **Sidebar that stays put.** Opening and closing the sidebar is now a smooth transition that keeps your chat list loaded, instead of rebuilding the list each time. [Commit](https://github.com/open-webui/open-webui/commit/3c010951db2cc349466658d3b52234cc22dad327), [Commit](https://github.com/open-webui/open-webui/commit/8edab5020eaa5d47b12a572eb632a891aa29440a), [Commit](https://github.com/open-webui/open-webui/commit/3e9b075954b7fc9d492a7ec832550b10b0bf80ed), [Commit](https://github.com/open-webui/open-webui/commit/3793b0c886f57630dc31320d3c0257c933c6eca1), [Commit](https://github.com/open-webui/open-webui/commit/0b4b7ae5ff3c0a17b58e8e85a5fddf190e3bda14)
+- 👁️ **Turning off chat previews.** A new setting under Settings and Interface lets you switch off the preview card that appears when you hover a chat in the sidebar, useful for a quieter sidebar, for sharing your screen, or on a slow connection. [#27632](https://github.com/open-webui/open-webui/pull/27632), [#27639](https://github.com/open-webui/open-webui/issues/27639)
+- ☑️ **Checkboxes beside their labels.** In the model editor and the admin model defaults, each capability, feature, and tool checkbox now sits directly in front of its own label instead of at the far edge of its column, where it could look like it belonged to the next one, and the label itself can be clicked to toggle it. [#27788](https://github.com/open-webui/open-webui/pull/27788), [#27771](https://github.com/open-webui/open-webui/issues/27771), [Commit](https://github.com/open-webui/open-webui/commit/1b39ff352a2fa3b57bd7815f44c50daf96937a14), [Commit](https://github.com/open-webui/open-webui/commit/0f821398ca9c9ddd8da521b5f9dcf103030202e8)
+- ✍️ **Typing cursor while responding.** A blinking cursor now marks where the reply is being written, from the moment you send your message until generation finishes, in place of the previous loading placeholder. [Commit](https://github.com/open-webui/open-webui/commit/cbb3aade2b4e901c22aa9a30530634721c80b078)
+- ✒️ **Underlined text.** Underlined text now appears underlined in a reply instead of showing the markup around it, and underlining is kept when you edit in a rich text box rather than being dropped. [Commit](https://github.com/open-webui/open-webui/commit/11db926a7b471e9477595786ef451a916174cc18), [#26904](https://github.com/open-webui/open-webui/issues/26904)
+- 📥 **Adding group members from a file.** Administrators can now add many people to a group at once by uploading a CSV of names and email addresses, with a template to download and a message naming any row whose address does not match an account. [Commit](https://github.com/open-webui/open-webui/commit/f3f7659da754b51c216b17b2d6def4d59071d78f)
+- 📑 **Apache Tika 4 support.** Administrators extracting document text with Tika can now choose which server version they run, from Admin Settings under Documents or through "TIKA_SERVER_VERSION", where only Tika 3 was understood before. [Commit](https://github.com/open-webui/open-webui/commit/170ad0595d9440113721eb06375a2fc99aefaad1), [#28939](https://github.com/open-webui/open-webui/issues/28939)
+- 💓 **Tunable heartbeat for live updates.** A new "WEBSOCKET_HEARTBEAT_INTERVAL" setting controls how often each open tab checks in with the server, where it was fixed at 30 seconds, so a large deployment can cut background traffic that no one asked for. [Commit](https://github.com/open-webui/open-webui/commit/3c1017f6c3ffc7194f074f2cfd2ea5f49943c575), [#28166](https://github.com/open-webui/open-webui/issues/28166)
+- ⌛ **Expiring abandoned reply state.** A new "REDIS_RESPONSE_STREAM_TTL" setting expires the saved state of a reply that never finished, so a server killed mid-answer no longer leaves that data behind for good. [Commit](https://github.com/open-webui/open-webui/commit/176fa462128d5298492db29c67080a4e1afc2642)
+- 🖨️ **File and image detail parts on API requests.** A request sent to the OpenAI-compatible endpoint carrying an image detail level or a file part in its message content now forwards both to providers that use the Responses API, where they were dropped, while documents attached inside Open WebUI are unaffected because those still go through knowledge retrieval. [Commit](https://github.com/open-webui/open-webui/commit/ca4e07a40b4ff11989a25d84b517d3d0049f93ae)
+- 🧺 **Leaner stored document metadata.** Bulky extraction details such as page layouts, tables and detected languages are no longer kept alongside a document in the vector store, and a new "RAG_METADATA_MAX_VALUE_CHARS" setting drops any remaining oversized value, falling back to the configured upload size limit so a document that expands enormously while being read cannot exhaust a server's memory. [Commit](https://github.com/open-webui/open-webui/commit/278e97589e71d119b887d5bca9d6ae32912d1dff), [Commit](https://github.com/open-webui/open-webui/commit/e3a7a64d82ab2dd06c681ce85027367ccc8234d4), [#29025](https://github.com/open-webui/open-webui/pull/29025)
+- 💨 **No filter work on installs without filters.** A completed message on an install with no filter functions and no pipeline filters, which is the default, no longer rebuilds the whole conversation and ships it to the browser as an event nothing acts on. [Commit](https://github.com/open-webui/open-webui/commit/28f2965934f5b6fba0e0c38a15b2af6ee790819f)
+- 📂 **Opening a file in a knowledge base.** A file listed in a knowledge base can now be opened and read straight from that list, where the name was shown but nothing happened when it was clicked. [Commit](https://github.com/open-webui/open-webui/commit/20f35d157bc7d535091ce6a90b517c23d26486c0), [#28086](https://github.com/open-webui/open-webui/issues/28086)
+- 🧵 **Cheaper saving of a reply as it streams.** The resume snapshot taken on every piece of a streamed reply no longer rebuilds the whole answer each time, so the cost of a save stops growing with the length of the reply. [#28821](https://github.com/open-webui/open-webui/pull/28821)
+- 📀 **Less repeated work setting up built-in tools.** Every chat request no longer rebuilds a fresh copy of each built-in tool's definition from scratch, which was paid once per tool on every message. [#28860](https://github.com/open-webui/open-webui/pull/28860)
+- 🕹️ **Control over what a terminal port preview may reach.** A new interface setting decides whether a previewed port runs with access to same-origin browser APIs, so you can lock a preview out of them on installs where previews serve content you do not fully trust. [Commit](https://github.com/open-webui/open-webui/commit/54d7a223707f03172efbb9e754db6e69709956d0)
+- ♿ **Improved UI accessibility.** A closed sidebar is no longer reachable by keyboard or announced by screen readers, the tool call blocks in a response can now be expanded with the keyboard, the buttons that normally appear on hover, such as message actions, file removal, and chat menus, now appear when you reach them with the keyboard as well, whatever you have tabbed to is marked with a clear outline throughout the application, and the rows in the integrations menu now tell a screen reader whether each tool or feature is switched on. [Commit](https://github.com/open-webui/open-webui/commit/48a5696042b414f6511911afa72b3289ad2797b9), [Commit](https://github.com/open-webui/open-webui/commit/bd250a0e2431f8c2c7e2f4a34c5327f21fc77d4b), [Commit](https://github.com/open-webui/open-webui/commit/c8f8fa451a60974dfa4ebaf7cd6163ef30c45fd6), [Commit](https://github.com/open-webui/open-webui/commit/29541cbb52659a8a6ee22d255f14e6d2f168a09b), [Commit](https://github.com/open-webui/open-webui/commit/ac0368b4abe4c880f715b236ee0024826b2e3e7a), [Commit](https://github.com/open-webui/open-webui/commit/c086b80313fe0f5ce60831a0d150f695646c66e4), [#27667](https://github.com/open-webui/open-webui/pull/27667), [#17150](https://github.com/open-webui/open-webui/issues/17150)
+- 🔄 **General improvements.** Various improvements were implemented across the application to enhance performance, stability, and security.
+- 🌐 **Translation updates.** Faroese was added, and translations for Slovenian, Hungarian, Finnish, Korean, Portuguese (Brazil), Catalan, and French were enhanced and expanded.
+
+### Fixed
+
+- 🛡️ **Security Advisory**: This release includes security and access-control fixes. We recommend updating production deployments at your earliest convenience. Not all security fixes in this version may be enumerated in the fixed section. Some may be withheld for a short time to give administrators time to upgrade. [Advisories](https://github.com/open-webui/open-webui/security)
+- 🛂 **Knowledge search reaching past what you may read.** Searching knowledge bases now applies the list of collections you are allowed to open, where that restriction was handed to the vector store and silently discarded, so results could include material from knowledge bases you have no access to. [Commit](https://github.com/open-webui/open-webui/commit/1d6d4e6e6647e1d403438ede7bd9ba20bc4cc8f6)
+- 💣 **Documents that unpack far beyond their size.** A Word, Excel, PowerPoint, OpenDocument or EPUB file that expands to far more than it stores is now rejected before it is read, where one could previously be used to exhaust a server's memory. [Commit](https://github.com/open-webui/open-webui/commit/2a0274a0a039dbe0a1ad4d24003b085aae7b896b)
+- ✂️ **Long replies cut off partway.** A single oversized piece of a streamed reply, such as a long reasoning trace or a turn carrying many tool calls, no longer ends the answer early with a misleading error about byte counts, which affected every default installation. [#28114](https://github.com/open-webui/open-webui/pull/28114), [#25664](https://github.com/open-webui/open-webui/issues/25664)
+- 🚧 **Web address checks that could be skipped.** The fetchable-address test and the operator's web fetch filter list now run on every outgoing request, where a proxied or already-open connection could bypass them and a filter entry written as an address range silently matched nothing at all. [#27823](https://github.com/open-webui/open-webui/pull/27823)
+- 🧑‍💻 **Code execution reachable through a tag in a reply.** On installs using native function calling, the older path that runs code found inside a tag in the model's reply is no longer active alongside the built-in tool, so code execution happens only through an explicit tool call. [#29024](https://github.com/open-webui/open-webui/pull/29024)
+- ⌚ **Recurrence rules that could tie up the server.** How often an automation repeats is now taken from the rule the scheduler actually parsed rather than from the text of the rule, so a crafted rule can no longer disagree with what gets scheduled and walk the server through an unbounded run of occurrences, and a rule carrying a time zone on its start date now schedules instead of erroring. [Commit](https://github.com/open-webui/open-webui/commit/067114c28038b77045a3a1983e2e2719b1a32ad8)
+- 🗝️ **Changing a password now ends other sessions.** Changing your password, or an administrator resetting it for you, now stops every device that was already signed in, where they had stayed signed in on the old password until their session expired on its own, up to four weeks by default; the device making the change is signed out too and asked to sign in again, and this requires Redis, without which nothing can be revoked and a warning is now logged saying so. [#28725](https://github.com/open-webui/open-webui/pull/28725), [#28647](https://github.com/open-webui/open-webui/discussions/28647)
+- 🧬 **Workspace models shadowing a real one.** Someone without administrator rights can no longer create, import, or edit a workspace model so that it takes over the identity of a model served by a connected provider, where doing so would have changed what everyone else got when they picked that model. [Commit](https://github.com/open-webui/open-webui/commit/ea55d38793014a4e3cd5a4046816fe22e69e9739)
+- 🌳 **Folders disappearing when moved into themselves.** Moving a folder inside one of its own subfolders is now refused, where it was accepted and made that folder and everything in it vanish from the sidebar with no way to bring it back, while leaving the server walking the loop endlessly and querying the database as it went, which could exhaust a worker and its memory; any folder already in that state is returned to the top level. [#28748](https://github.com/open-webui/open-webui/pull/28748)
+- 🧨 **Searching a knowledge base with a costly pattern.** A search pattern written so that it expands enormously before it even runs is now refused, where it could tie up the server; ordinary patterns are unaffected. [Commit](https://github.com/open-webui/open-webui/commit/d5b66533e7829654f6fb343abbaaeab988dbfde8), [#28284](https://github.com/open-webui/open-webui/pull/28284)
+- 💧 **Attaching a very large file from a link.** A file fetched from a link is now written to disk as it arrives and stops at the configured size limit, where the whole thing was held in memory first with no limit applied, so a large enough file could exhaust the server; a download that fails partway no longer leaves the partial file behind. [#28945](https://github.com/open-webui/open-webui/pull/28945)
+- ⛓ **Deleting one knowledge base removing a shared connection.** Deleting an external knowledge base now leaves its connection in place while other knowledge bases still use it, and only an administrator removing the last one clears it, where any user deleting theirs took the connection away from everyone. [#28113](https://github.com/open-webui/open-webui/pull/28113)
+- 📡 **Intermittent connection failures.** Requests to model providers and to services on the same network no longer fail intermittently with name lookup errors, often surfacing as a misleading model not found message, because addresses are resolved through the system again by default, with the faster resolver still available through "AIOHTTP_CLIENT_ASYNC_DNS_RESOLVER". [#28242](https://github.com/open-webui/open-webui/pull/28242), [#28013](https://github.com/open-webui/open-webui/issues/28013), [#28215](https://github.com/open-webui/open-webui/issues/28215)
+- 🗯️ **Losing the conversation with memory on.** With the memory tool enabled, the model can see the earlier messages in your conversation again, instead of answering the second message as though the first had never been sent. [#28400](https://github.com/open-webui/open-webui/issues/28400)
+- 👻 **Vanishing responses.** Replies from Responses-API providers that report an empty output at the end of a stream no longer disappear the moment generation finishes, leaving an empty message in their place. [#27800](https://github.com/open-webui/open-webui/pull/27800), [#27789](https://github.com/open-webui/open-webui/discussions/27789)
+- 📥 **Queued messages disappearing.** Messages waiting to be sent are put back in the queue if sending them fails, rather than vanishing without being sent. [Commit](https://github.com/open-webui/open-webui/commit/f79b443c226098564386d0a31708e71ec0146158)
+- 🧵 **Replies cut short mid-stream.** A reply no longer breaks off part way through when a provider sends the pieces of its response in an unexpected order, which had left the answer truncated and skipped the filters that run once a message finishes. [#28312](https://github.com/open-webui/open-webui/pull/28312)
+- 🧷 **Replies not carried into the next turn.** With providers that skip parts of the streaming sequence, the finished reply is now taken from the completed message, so it stays available as context for your next question and the citations that arrived with it are no longer dropped. [#28310](https://github.com/open-webui/open-webui/pull/28310)
+- 🌊 **Replies arriving in oversized pieces.** Very large streamed pieces no longer break the response on default settings, where the reader that splits them safely only ran when a chunk size limit was configured. [Commit](https://github.com/open-webui/open-webui/commit/a33fa05adc6def8f3d098539a4786dc9c7bf61d2)
+- 🩹 **Signing in after a long-delayed upgrade.** Accounts on instances that were upgraded from a version older than 0.6.41 to 0.9.6 or newer can sign in again, where an upgrade step had written their single sign-on identity in a form the application could not read afterwards, and a repair step corrects the affected accounts on startup. [#28107](https://github.com/open-webui/open-webui/pull/28107), [#28101](https://github.com/open-webui/open-webui/issues/28101), [Commit](https://github.com/open-webui/open-webui/commit/bd8378f643dd8a56366ad9d1843b7d40f67cf1f9)
+- 🔑 **Signing in with some identity providers.** Logging in through a provider that adds its own vendor-specific information to the header of the sign-in token now completes, rather than failing at the final step with a message claiming the email or password was wrong. [#28065](https://github.com/open-webui/open-webui/pull/28065), [#28062](https://github.com/open-webui/open-webui/issues/28062)
+- 🔌 **Role changes taking effect at once.** Changing someone's role now ends their live sessions no matter how the change was made, whether by a directory sync, an identity provider, a trusted header, or deleting the account, so permissions from their old role cannot linger, and their browser reconnects on its own. [Commit](https://github.com/open-webui/open-webui/commit/ce3c175e260709f359d7e6cbb3132f0572098b95)
+- 🛑 **Memory permission being respected.** Taking away someone's memory permission now also stops their stored memories being added to the context of their conversations, which one path had continued doing regardless. [#27668](https://github.com/open-webui/open-webui/pull/27668)
+- 🔍 **Listing a single connection's models.** Asking for the models or version of one particular connection is now restricted to administrators, and a request naming a specific backend is checked against the models that backend actually serves even where the access control bypass is turned on. [Commit](https://github.com/open-webui/open-webui/commit/16f118d77ad9d68c64116f94551ffb14bf8b2abd)
+- ⚖️ **Sharing defaults matching what was configured.** On instances upgraded from older versions, public sharing of tools and notes no longer shows as switched on in the admin panel, and saving any unrelated permission no longer grants everyone a capability that was never enabled. [#27716](https://github.com/open-webui/open-webui/pull/27716), [#27715](https://github.com/open-webui/open-webui/issues/27715)
+- 🗂️ **Folder permissions when starting a chat.** Starting a conversation filed into a folder now checks that you are allowed to write to that folder, a check the message sending path had been skipping, and every place a chat can be filed now treats ownership, shared access, and unknown folders the same way. [#28366](https://github.com/open-webui/open-webui/pull/28366)
+- 🪧 **Clearer attachment failures.** A link that cannot be read now says so and names the link, and a YouTube video whose transcript is refused explains why and points at the proxy setting that exists for it, instead of both being reported as a knowledge base error. [#28362](https://github.com/open-webui/open-webui/pull/28362), [#28361](https://github.com/open-webui/open-webui/issues/28361)
+- 🔎 **Chat search finding recent messages.** Searching your chats now looks inside the messages of current conversations on default installations, where it had only been reading an older storage format and missing their content entirely. [Commit](https://github.com/open-webui/open-webui/commit/0800c21c64c64810f24c2ec88cca5e36daebb10e)
+- 🧭 **Your place in a compacted chat.** Opening a conversation whose history has been compacted now takes you to its most recent message instead of leaving you parked on the summary, and updates to an existing message no longer move your place in the conversation. [Commit](https://github.com/open-webui/open-webui/commit/5caa91a49304148696641d1cd39e43184ba8d748)
+- 🖥️ **Chats with a personal terminal.** Sending a message with a terminal you added yourself under Settings selected no longer fails with a terminal unavailable error, which had blocked those chats since 0.11.0. [#27621](https://github.com/open-webui/open-webui/issues/27621), [Commit](https://github.com/open-webui/open-webui/commit/5b333d75c6adea4d8bde96439974d6e9c83d8198), [Commit](https://github.com/open-webui/open-webui/commit/3becec6ccfc7dc457270d4e9f0d8c957e8160ddc)
+- 📆 **Default date for new events.** Creating a calendar event now starts on today's date rather than tomorrow's when you open the form in the evening, or yesterday's when you open it early in the morning. [#27779](https://github.com/open-webui/open-webui/pull/27779), [#27778](https://github.com/open-webui/open-webui/issues/27778)
+- 🗓️ **Recurring event times.** Repeating calendar events now show at the time you set them for instead of being worked out in the server's time zone and shifted by the gap between the two. [#27774](https://github.com/open-webui/open-webui/issues/27774), [Commit](https://github.com/open-webui/open-webui/commit/d721b0d19621d01e35505105a778ce5681b2ffba)
+- 🧩 **Chats during model list refreshes.** On direct connections, background work such as title and tag generation no longer fails or runs against a mix of old and new model entries while the model list is being refreshed. [#27821](https://github.com/open-webui/open-webui/pull/27821)
+- 🎛️ **Chat Controls staying put.** Hovering a chat in the sidebar whose preview contains an artifact no longer forces the Chat Controls pane open and fills it with that artifact, over the chat you currently have open. [#27773](https://github.com/open-webui/open-webui/pull/27773), [#27772](https://github.com/open-webui/open-webui/issues/27772)
+- 📨 **Reliable streaming with unusual characters.** Responses containing any of three rare invisible line break characters no longer arrive split or broken when the "ENABLE_ORJSON" option is turned on. [#27819](https://github.com/open-webui/open-webui/pull/27819)
+- 🧮 **JSON options honoured again.** Options passed to the shared JSON helper are no longer silently ignored when the "ENABLE_ORJSON" option is turned on, falling back to the standard encoder that supports them. [Commit](https://github.com/open-webui/open-webui/commit/78ed5a0235c4de67828ba4b0d6147035067cec2c)
+- 🚫 **Duplicate models in lists.** Adding a model that is already on a connection's allowed list is now rejected instead of quietly adding it a second time, the arena picker no longer offers models you have already chosen, and existing duplicates are cleaned up the next time the list is saved. [#28251](https://github.com/open-webui/open-webui/pull/28251), [#28249](https://github.com/open-webui/open-webui/issues/28249)
+- 📁 **Dragging chats into shared folders.** A shared folder you can write to now highlights and accepts a dropped chat, while one you only have read access to no longer offers itself as a drop target for an action that could only fail. [Commit](https://github.com/open-webui/open-webui/commit/e4dd6c4bf14c7ea54c1effa6c40ad9e95185c413), [#28261](https://github.com/open-webui/open-webui/issues/28261)
+- ⏰ **Listing automations through chat.** Asking a model to list your automations without naming a folder now returns every automation you have, instead of only the ones that sit outside a folder. [Commit](https://github.com/open-webui/open-webui/commit/f8ac75d188b7e07906aa1d5e648e3fc25a78ef2b)
+- 🧠 **Faster follow-ups with memory enabled.** The memories handed to the model now appear in a stable order from one message to the next, so servers that reuse their work between turns no longer reprocess the whole conversation each time you reply. [#28292](https://github.com/open-webui/open-webui/issues/28292), [Commit](https://github.com/open-webui/open-webui/commit/ff74bfa6a117c6f03097034c74c2f9bdfb824203), [Commit](https://github.com/open-webui/open-webui/commit/d22bb6703f244e6769ac9b0f2e41d784ad6cf535)
+- 🎯 **Custom model parameters combining.** Setting a custom parameter on a model no longer silently discards every custom parameter defined in the global defaults, and a value sent directly in an API request is no longer overwritten by the model's saved settings. [Commit](https://github.com/open-webui/open-webui/commit/11739a2de8eddf7ef26378356aff8a1bcab4a349), [#28241](https://github.com/open-webui/open-webui/issues/28241)
+- 👥 **Sharing with people already added.** The access picker no longer offers people and groups that already have access, and the Users heading no longer appears above an empty list. [Commit](https://github.com/open-webui/open-webui/commit/385d08bea5899bcb160391db466662b0a0a6f801), [#28253](https://github.com/open-webui/open-webui/issues/28253)
+- 🔧 **Full tool parameter descriptions.** A tool whose parameter description runs over several lines now passes the whole description to the model instead of only its first line. [Commit](https://github.com/open-webui/open-webui/commit/b606e13da3753027ead0e92e35e1399b60c96c8e)
+- 📝 **Notes saved in an unexpected shape.** A note whose content was stored as structured data rather than text no longer breaks the notes page for everything else, and opens with that content shown as a formatted code block. [Commit](https://github.com/open-webui/open-webui/commit/8d1c205d8e7335ef7c292afb125a7270976f327b), [#28222](https://github.com/open-webui/open-webui/issues/28222)
+- 💬 **Direct messages after an account is deleted.** A direct message conversation no longer counts a deleted account among its members, and opening a direct message with someone finds the existing conversation instead of starting a second one alongside it. [Commit](https://github.com/open-webui/open-webui/commit/a41faa3c226b20e7db7508c49c7d1d015ac9e973), [#28257](https://github.com/open-webui/open-webui/issues/28257)
+- 🫥 **Deactivating a model.** Turning a model off no longer removes the wrong entry from the model list, or fails the list outright and leaves the model picker empty for everyone until the model is turned back on. [Commit](https://github.com/open-webui/open-webui/commit/5cecb7dbfad3994228ee53d19232650400462332), [#28202](https://github.com/open-webui/open-webui/issues/28202)
+- 💭 **Readable errors on chat actions.** When moving, renaming, or otherwise changing a chat fails, the message explaining why now appears in place of an unhelpful object placeholder. [#28260](https://github.com/open-webui/open-webui/pull/28260), [#28259](https://github.com/open-webui/open-webui/issues/28259)
+- 🪪 **Authorship in shared chats.** A chat shared with you now shows the name and picture of whoever wrote it, in the message list and in the overview panel, rather than crediting the messages to you. [#28274](https://github.com/open-webui/open-webui/pull/28274), [#28273](https://github.com/open-webui/open-webui/issues/28273)
+- 🖇️ **Adding terminals over plain connections.** Saving a terminal connection now works when the interface is served without HTTPS, where the dialog would sit there doing nothing because the browser withholds the tool used to generate its identifier. [Commit](https://github.com/open-webui/open-webui/commit/2a45fa04cb1d07b258e0b880ab0c02577f0dc035), [#28148](https://github.com/open-webui/open-webui/issues/28148)
+- 🗃️ **openGauss vector storage.** Deployments using openGauss for vector storage no longer fail the moment they touch it. [#27838](https://github.com/open-webui/open-webui/pull/27838)
+- 🎚️ **ColBERT reranker startup.** Loading a ColBERT reranker now names the model in the log rather than printing a logging error and a traceback in its place. [#27838](https://github.com/open-webui/open-webui/pull/27838)
+- 🖼️ **Images that no longer exist.** A message whose image file has been deleted now shows a small unavailable placeholder that cannot be opened, rather than a broken image that spilled the whole reply text into the picture frame and still opened full screen. [#27730](https://github.com/open-webui/open-webui/pull/27730), [#27728](https://github.com/open-webui/open-webui/issues/27728), [Commit](https://github.com/open-webui/open-webui/commit/f8c5fda283e6206d92e81ae3b83ffe5d7a144b03)
+- 🛂 **Connecting external accounts.** Authorizing a tool's external account now completes only for the person who started it, rather than for whoever happens to return with the authorization, and signing out clears the session it relies on. [Commit](https://github.com/open-webui/open-webui/commit/c2107e5bb3689a69c170ca526925f4ed84bd00f5)
+- 🪟 **Starting up on Windows.** The Windows start script now creates the secret key it needs on a fresh installation, instead of printing a run of file not found messages and then refusing to start, and it copes with an installation path that contains spaces. [#28061](https://github.com/open-webui/open-webui/pull/28061), [#28060](https://github.com/open-webui/open-webui/issues/28060)
+- 🕸️ **Overlapping branches in the overview.** Branch nodes in a chat's overview keep a clear gap between them when the interface is scaled up, rather than sitting on top of one another. [#27995](https://github.com/open-webui/open-webui/pull/27995), [#27994](https://github.com/open-webui/open-webui/issues/27994)
+- 🗑️ **Delete offered only when allowed.** The chat deletion controls in the sidebar, the chat menu, search, archived chats, and data controls no longer appear for people whose permissions do not allow deleting, where using them produced an access denied error. [#27714](https://github.com/open-webui/open-webui/pull/27714), [#27713](https://github.com/open-webui/open-webui/issues/27713)
+- 🍴 **Fork offered only when allowed.** The fork action and the fork command no longer appear for people whose chat import permission is turned off, where using them produced an access denied error. [#27711](https://github.com/open-webui/open-webui/pull/27711), [#27692](https://github.com/open-webui/open-webui/issues/27692)
+- ↕️ **Expand button in the message box.** The button that enlarges the message box no longer sits on top of a tagged model's dismiss button or the first attached file, and stays reachable in long prompts. [#27676](https://github.com/open-webui/open-webui/pull/27676), [#26736](https://github.com/open-webui/open-webui/issues/26736)
+- 🔆 **Regenerate in high contrast mode.** With high contrast mode on, the regenerate button now stays visible on earlier replies instead of appearing only when you hover over them. [#27644](https://github.com/open-webui/open-webui/pull/27644), [#27638](https://github.com/open-webui/open-webui/issues/27638)
+- ✂️ **Clipped icons and avatars.** The terminal icon beside the message box and the profile picture in account settings are no longer shaved flat along their left edge. [#27691](https://github.com/open-webui/open-webui/pull/27691), [#27690](https://github.com/open-webui/open-webui/issues/27690)
+- 🪄 **Merged responses after a reload.** Merging the answers from several models now works on a conversation you have reopened, instead of the merging model reporting that the other responses were empty. [#27673](https://github.com/open-webui/open-webui/pull/27673), [#26962](https://github.com/open-webui/open-webui/issues/26962)
+- 🔢 **Token counts for background chats.** Conversations started by automations, timers, sub-agents, and channels now report their token usage like any other chat, rather than arriving without it even when the model is set up to provide it. [#27661](https://github.com/open-webui/open-webui/pull/27661), [#27653](https://github.com/open-webui/open-webui/issues/27653)
+- 📐 **Settings on tall screens.** The settings window now grows with the height of your display instead of stopping short and making you scroll inside it while space sits unused above and below. [#27615](https://github.com/open-webui/open-webui/pull/27615), [#27614](https://github.com/open-webui/open-webui/issues/27614)
+- 🖱️ **Sections opening by accident.** Folders, collapsible sections, and tool call blocks now open and close only when you click them, rather than also reacting when you release the mouse over them after dragging or selecting text. [Commit](https://github.com/open-webui/open-webui/commit/bd250a0e2431f8c2c7e2f4a34c5327f21fc77d4b)
+- 🔁 **Rebuilding knowledge base vectors.** Rebuilding the vectors for a knowledge base now also rebuilds them for each file it contains, so attaching a single file afterwards finds its content instead of quietly returning nothing and letting the model answer from thin air. [#28106](https://github.com/open-webui/open-webui/issues/28106), [Commit](https://github.com/open-webui/open-webui/commit/2a6e671f548970c8223692024e630b9936e9fa7c), [Commit](https://github.com/open-webui/open-webui/commit/89922cc9d585e10b026693681b44afdc4b874588)
+- 📌 **Attaching a chat shared with you.** Attaching a conversation that was shared with you, directly or through a shared folder, now brings its content along instead of quietly attaching nothing. [Commit](https://github.com/open-webui/open-webui/commit/5cd9a395344e882b4384bec0899f503ad540aecc)
+- 🧲 **The page staying still when typing.** Returning focus to the message box no longer scrolls the conversation, so switching chats, running a command, or picking something from a menu leaves your place on screen alone. [Commit](https://github.com/open-webui/open-webui/commit/9122c24ea2d506aad50384ca8aba1616d1bed626)
+- 📷 **Round profile pictures on narrow screens.** Profile pictures in the admin user list and other lists no longer squash into ovals of differing widths when the window is narrow. [#28000](https://github.com/open-webui/open-webui/pull/28000), [#27999](https://github.com/open-webui/open-webui/issues/27999)
+- 🎙️ **Voice mode in the notes editor.** The voice mode button is no longer offered in the chat embedded in a note, where it does not apply. [Commit](https://github.com/open-webui/open-webui/commit/9122c24ea2d506aad50384ca8aba1616d1bed626), [Commit](https://github.com/open-webui/open-webui/commit/e963d36e393aead56b941e99d4167fb0dc9d2d7a)
+- ⏳ **Analytics stuck loading.** Choosing a custom date range in analytics without picking dates yet no longer leaves the tab spinning forever, including after leaving and coming back to it. [#28125](https://github.com/open-webui/open-webui/issues/28125), [Commit](https://github.com/open-webui/open-webui/commit/629cdcb5303958c5b99ee437030ab80cc418bc2e)
+- 🧑‍🤝‍🧑 **Owner avatars on shared chats.** The picture beside a chat someone shared with you now loads, and falls back to the default image if it cannot, rather than leaving a blank gap when the interface and the server are on different addresses. [#28272](https://github.com/open-webui/open-webui/pull/28272), [#28271](https://github.com/open-webui/open-webui/issues/28271)
+- 🎨 **Image generation and web search staying switched off.** Turning either off now takes effect at once on every path: sessions opened beforehand can no longer produce images or run searches, an image request no longer reaches the provider on a model using the older tool-calling method, the entry disappears from the integrations menu right away, and an active marker beside the message box no longer lingers after its feature is withdrawn. [#27759](https://github.com/open-webui/open-webui/pull/27759), [#27758](https://github.com/open-webui/open-webui/issues/27758), [#26842](https://github.com/open-webui/open-webui/issues/26842), [#27669](https://github.com/open-webui/open-webui/pull/27669)
+- 📰 **Attached pages reaching the model.** The text pulled from an attached web page or YouTube video now actually reaches the model, rather than arriving empty so the reply had nothing to work from, and opening the source to check no longer fails. [#28378](https://github.com/open-webui/open-webui/issues/28378), [Commit](https://github.com/open-webui/open-webui/commit/9c21d4ed3ba9ba8e53def7e1a1366b74834cb42d)
+- 🌐 **Tavily page fetching.** Reading a web page with Tavily selected as the loader works again, having failed on every attempt since 0.10.0. [#27636](https://github.com/open-webui/open-webui/pull/27636), [#27602](https://github.com/open-webui/open-webui/issues/27602)
+- 🗒️ **Reply box in threads.** The reply box in a channel thread now stays at the bottom of the panel while you scroll back through the replies, instead of scrolling out of sight with them. [#27768](https://github.com/open-webui/open-webui/pull/27768), [#27767](https://github.com/open-webui/open-webui/issues/27767)
+- 🎹 **Model picker shortcut.** The keyboard shortcut for opening the model picker works again, and a link to a chat naming a model you do not have still opens the picker with that name filled in. [Commit](https://github.com/open-webui/open-webui/commit/e1acd7e7ca5085e03babbea16b4770e51c38886e)
+- ⌨️ **Reaching the download options by keyboard.** In the model picker, arrowing past the last result now moves through the options to fetch that model from each server that can supply it, so they can be chosen with the keyboard instead of only by clicking. [Commit](https://github.com/open-webui/open-webui/commit/4e03d89414a7be1203579f45225ca64f1221205f), [Commit](https://github.com/open-webui/open-webui/commit/25802c048e6123fa602182949ad2a9f349e1e863)
+- 📂 **Opening a folder in the sidebar.** Selecting a folder now refreshes just that folder's chats rather than rebuilding the whole folder tree, and a folder that is empty or still loading says so instead of showing nothing. [Commit](https://github.com/open-webui/open-webui/commit/2e939874904e1ae54d02b8bc6d745931a8e1f673), [Commit](https://github.com/open-webui/open-webui/commit/86b7bf1f7e11109816b0d16ada708c637b50c520)
+- ⏲️ **Changing an automation through chat.** Asking a model to change one thing about an automation no longer moves it out of its folder or drops its model when the model fills those fields in blank instead of omitting them. [Commit](https://github.com/open-webui/open-webui/commit/90bb94abf9a8c6fbb87c72952295ae39d2ad98e5)
+- 🔂 **Automations that run a set number of times.** An automation asked to run a limited number of times is now rejected unless it says when to start counting from, rather than being accepted and then running indefinitely. [#27781](https://github.com/open-webui/open-webui/pull/27781), [#27780](https://github.com/open-webui/open-webui/issues/27780)
+- 📅 **Editing a calendar event through chat.** Asking a model to change one thing about an event, such as its title, no longer fails or wipes the details you did not mention. [#27777](https://github.com/open-webui/open-webui/pull/27777), [#27776](https://github.com/open-webui/open-webui/issues/27776)
+- 🧹 **Session cleanup on multi-instance setups.** The instance doing the periodic session cleanup now keeps its claim on that job alive between passes, so an idle deployment stops logging a renewal warning every two minutes and the claim no longer lapses for half of every cycle. [Commit](https://github.com/open-webui/open-webui/commit/939bcdb79e3dcad2278f1e7f4f517a3f2f36f3ec), [#27762](https://github.com/open-webui/open-webui/issues/27762)
+- 🏠 **Starting folder in the file browser.** Reopening the file browser now keeps the folder you were in, instead of the breadcrumb losing its starting point and jumping you elsewhere. [Commit](https://github.com/open-webui/open-webui/commit/52c5e3b20d3cd8c3a15db50e2cc75bbd6e82068e)
+- 🩺 **Repairing default model settings.** Instances whose stored default and pinned model settings had been written in the wrong shape are corrected on startup, so those defaults take effect again. [Commit](https://github.com/open-webui/open-webui/commit/5c05608e3ac0aefce8c1eed18c3e205c61f6b6fe)
+- 🧽 **Cleaner conversation history for the model.** Internal bookkeeping attached to your messages, such as attachment records and token counts, is no longer sent to the model along with the conversation. [Commit](https://github.com/open-webui/open-webui/commit/a32a17965ca36f730ebf5ff53a2a8e17082b61a6)
+- 🙈 **Needless request from the model picker.** Opening the model picker as a non-administrator no longer fires a request to an administrator-only settings endpoint that was always refused. [Commit](https://github.com/open-webui/open-webui/commit/b4738d1a2e6af1ce20adb322fc6d2aa2c9407901)
+- ⏹️ **Stopping a reply that is waiting.** The stop button now ends a reply that is sitting waiting for you, such as one paused on a tool approval, rather than leaving the conversation stuck part way through. [Commit](https://github.com/open-webui/open-webui/commit/f7767d6be774720e16265c6d016bf6a24a1a8759)
+- 🏷️ **Folder names with unusual characters.** Naming a folder is no longer refused because another folder's name happens to be similar, and a name ending in a backslash no longer fails outright on PostgreSQL, because names are now compared exactly rather than treated as a search pattern. [#28695](https://github.com/open-webui/open-webui/pull/28695), [#28694](https://github.com/open-webui/open-webui/issues/28694)
+- 🤔 **Reasoning carried back to Ollama.** A model's earlier thinking is now passed back to Ollama in its own native field rather than pasted into the message as tagged text, so reasoning models keep their train of thought across turns. [Commit](https://github.com/open-webui/open-webui/commit/3258330729942b533dc5fe141e876cee7e5eb40d)
+- 📎 **Default pinned models taking effect.** Changing the default pinned models now reaches people who have never chosen their own, where simply having opened the interface once was enough to freeze the list they first saw, and reordering a pin no longer moves the wrong one or reopens the sidebar section afterwards. [#28069](https://github.com/open-webui/open-webui/pull/28069), [#28067](https://github.com/open-webui/open-webui/discussions/28067)
+- ✏️ **Editing other people's channel messages.** Asking a model to work on a message in a channel now only applies to your own messages, where write access to the channel had been enough to reach anyone's. [#28631](https://github.com/open-webui/open-webui/pull/28631)
+- 🍪 **Signed-in tool servers.** A tool server that relies on your session now receives the credentials belonging to its own connection, rather than whichever were most recently prepared. [#28630](https://github.com/open-webui/open-webui/pull/28630)
+- 🏗️ **Editing a folder from its page.** Renaming a folder, changing its icon, creating a subfolder, or deleting it from the folder's own page now updates the sidebar straight away, instead of leaving the old name and icon there, and the new subfolder missing, until a reload. [Commit](https://github.com/open-webui/open-webui/commit/a40f6f2860b49b4c7f11e369f11bd46e9451eabf), [Commit](https://github.com/open-webui/open-webui/commit/736e38338ede1fca5af0829e35585a72f8517d32), [#28692](https://github.com/open-webui/open-webui/pull/28692), [#28690](https://github.com/open-webui/open-webui/issues/28690)
+- 📣 **Long channel names in the sidebar.** A channel with a long name no longer squeezes its own menu button out of the row. [Commit](https://github.com/open-webui/open-webui/commit/b5da50f3df51786972010c75c7736d5f95362e58), [#28671](https://github.com/open-webui/open-webui/pull/28671), [#28670](https://github.com/open-webui/open-webui/issues/28670)
+- 📬 **Mark as unread in chat search.** Marking a chat unread from the search dialog now works and updates the sidebar, where the menu entry looked normal but did nothing at all. [#28136](https://github.com/open-webui/open-webui/pull/28136), [#28135](https://github.com/open-webui/open-webui/issues/28135)
+- ⬆️ **Scroll to top on the first click.** In a long chat where older messages had not been loaded yet, one click of scroll to top now reaches the first message instead of stopping short and needing a second. [#28659](https://github.com/open-webui/open-webui/pull/28659), [#28658](https://github.com/open-webui/open-webui/issues/28658)
+- 🔘 **Double bullets in the release notes.** Each entry in the what's new dialog shows a single bullet again, rather than two sitting at different heights. [#28676](https://github.com/open-webui/open-webui/pull/28676), [#28675](https://github.com/open-webui/open-webui/issues/28675)
+- 📚 **Knowledge search and shared files in chat.** A model searching your knowledge bases or reading a file shared with you through a group now works, where it had failed since 0.11.0 and quietly answered as though the knowledge were empty, affecting instances that forward user details to their embedding service and, for shared files, every instance regardless of settings. [#27642](https://github.com/open-webui/open-webui/pull/27642), [#27641](https://github.com/open-webui/open-webui/issues/27641)
+- 🔖 **Skill identifiers that cannot be reached.** Creating a skill whose identifier contains a character that is not allowed in a web address is now refused outright, rather than accepted and then permanently impossible to open, edit, turn off, delete, or recreate. [#27660](https://github.com/open-webui/open-webui/pull/27660), [#27655](https://github.com/open-webui/open-webui/issues/27655)
+- 🔤 **Model names on connections with a prefix.** A connection that adds a prefix to its model names now strips it before sending a request through the responses endpoint, where the prefixed name was passed on and rejected as unknown. [#28575](https://github.com/open-webui/open-webui/pull/28575), [#28574](https://github.com/open-webui/open-webui/issues/28574)
+- 🔓 **Turning on open sharing.** The open sharing permission can now be switched on in the default user permissions, where saving appeared to work but the setting was discarded and came back off. [#27609](https://github.com/open-webui/open-webui/pull/27609), [#27607](https://github.com/open-webui/open-webui/issues/27607)
+- 🖌️ **White boxes behind model icons.** Model icons with a transparent background no longer sit on a white square in the admin models list, matching how they already appeared everywhere else. [#27612](https://github.com/open-webui/open-webui/pull/27612), [#27611](https://github.com/open-webui/open-webui/issues/27611)
+- 🪞 **Matching the right account at sign-in.** Looking up an account by its identity provider details now matches the exact value, where the stored details were searched as loose text and a value contained within another's could be matched instead. [#28624](https://github.com/open-webui/open-webui/pull/28624)
+- 🔄 **Syncing a model catalogue more than once.** Syncing models now updates the ones that already exist, where any repeat of a previous sync silently did nothing at all while still reporting success. [#28036](https://github.com/open-webui/open-webui/pull/28036), [#28033](https://github.com/open-webui/open-webui/issues/28033)
+- 🕰️ **Saving a calendar event without a date.** Creating or editing an event with the date cleared now asks for one, where it was sent anyway, refused by the server, and reported as an unreadable error. [Commit](https://github.com/open-webui/open-webui/commit/f100edb70874808c93fab84eae1810595f9e9dc3), [#28133](https://github.com/open-webui/open-webui/issues/28133)
+- 🔗 **Deleting a message in a looping chat.** Deleting a message no longer hangs when the conversation contains a cycle in its reply structure. [#28035](https://github.com/open-webui/open-webui/pull/28035)
+- 🫀 **Scheduled work stopping without warning.** The routine that runs automations and calendar alerts can no longer be discarded while the application is running, which had silently stopped them firing with nothing reported, and it now stops cleanly on shutdown. [#28053](https://github.com/open-webui/open-webui/pull/28053), [#28052](https://github.com/open-webui/open-webui/issues/28052)
+- 🔋 **Session and usage records left uncleared.** The routines that clear out stale sessions and finished model usage can no longer be discarded while the application is running, so those records stop accumulating unnoticed, and both now stop cleanly on shutdown. [#28053](https://github.com/open-webui/open-webui/pull/28053), [#28052](https://github.com/open-webui/open-webui/issues/28052)
+- ⚗️ **Reasoning carried between turns.** A model's earlier thinking is now recognised from providers that report it in their own nested field, and reasoning that cannot be sent back without a signature is left out rather than being passed on and rejected. [Commit](https://github.com/open-webui/open-webui/commit/b6dc70c93b0d36e2659438e7a55aa8b21fee27f8)
+- 🛎️ **Losing all your settings.** Your interface settings are no longer wiped by a session that failed to load them, which could happen with no action on your part and cleared everything from your theme to your model parameters; saving now changes only the settings you actually changed, and a session that cannot load them tells you instead of carrying on as though you had none. [#27766](https://github.com/open-webui/open-webui/issues/27766), [Commit](https://github.com/open-webui/open-webui/commit/ad8c79f68657bd3bcf5db6be650e498bb904b36b)
+- 🖲️ **Losing the collapsed sidebar.** With the sidebar collapsed, opening a chat no longer pushes the narrow sidebar strip off the edge of the screen, which left no way to reopen the sidebar short of shrinking the window to phone size. [#28501](https://github.com/open-webui/open-webui/pull/28501), [#28500](https://github.com/open-webui/open-webui/issues/28500)
+- 🧯 **Timers that fail without saying so.** A timer whose reply cannot be generated, such as one set against a model that has since been removed, is now recorded as failed with the reason, instead of being marked as completed while the reply never arrives. [#27785](https://github.com/open-webui/open-webui/pull/27785), [#27783](https://github.com/open-webui/open-webui/issues/27783)
+- 🎲 **Timers stop for retired owners.** A timer whose owner has been deleted or demoted to pending is recorded as an error instead of running, so a retired account no longer answers through a timer it set while active. [#30220](https://github.com/open-webui/open-webui/pull/30220)
+- 🖊️ **Message buttons in channels.** The buttons that appear when you hover a channel message now sit above the message rather than over its content, so they can be clicked on a message that starts with a code block or a table, and so the code and table controls stay clickable too. [#27737](https://github.com/open-webui/open-webui/pull/27737), [#27736](https://github.com/open-webui/open-webui/issues/27736)
+- 🔡 **Searching for non-English tags and text.** Searching workspace models by tag, or prompts and automations by their contents, now finds entries containing characters outside the English alphabet, where roughly half were missed depending on which settings were in force when each one was saved. [#28399](https://github.com/open-webui/open-webui/pull/28399)
+- 🔭 **Searching the calendar without an end date.** Asking a model to search your calendar without naming an end date now works on PostgreSQL, where the open-ended range was too large for the database to accept and the search failed outright. [Commit](https://github.com/open-webui/open-webui/commit/9550731cc17759f6862595b8cd849ae48695b5c1), [#27717](https://github.com/open-webui/open-webui/issues/27717)
+- 🫧 **Attachments replaced by a loading dot.** Pinning a channel message, or otherwise updating one, no longer replaces its attachment with a loading indicator that never resolves until you reload or leave the channel. [Commit](https://github.com/open-webui/open-webui/commit/76d01602950a9e40823b53278557708d5bcd1036), [#27734](https://github.com/open-webui/open-webui/pull/27734), [#27731](https://github.com/open-webui/open-webui/issues/27731)
+- 🛠️ **Rebuilding empty server lists on every request.** An instance with no tool servers or no terminal servers configured no longer rebuilds that empty list on every request that needs it. [Commit](https://github.com/open-webui/open-webui/commit/f1a64ccfc2eb2a58086c55fe413a455bb488c35a), [#28568](https://github.com/open-webui/open-webui/issues/28568)
+- 🪫 **Errors logged for a cache that was simply empty.** A shared cache that has not been filled yet no longer logs an error suggesting its stored value is broken. [Commit](https://github.com/open-webui/open-webui/commit/f1a64ccfc2eb2a58086c55fe413a455bb488c35a), [#28568](https://github.com/open-webui/open-webui/issues/28568)
+- ⚓ **Starting up as a non-root user.** Deployments that run the container as a non-root user, such as Kubernetes setups using runAsNonRoot, start again, where a bundled speech model file that only root could read had stopped them since 0.11.0, and a bundled text corpus is now stored somewhere a non-root user can reach. [#27651](https://github.com/open-webui/open-webui/issues/27651), [Commit](https://github.com/open-webui/open-webui/commit/0480ca9653f0d566eaedadf0af0d785a9938480b), [#28866](https://github.com/open-webui/open-webui/pull/28866)
+- 📋 **Finding notes shared read only.** A note shared publicly for reading now appears in the read only view of your notes, where it was readable by anyone with the link but listed nowhere at all. [#27637](https://github.com/open-webui/open-webui/pull/27637), [#27487](https://github.com/open-webui/open-webui/issues/27487)
+- 🫂 **Signing in from another application.** Signing in through an application that exchanges a token from your identity provider now applies your role and group memberships the same way signing in through the browser does, and an account whose provider sends no role keeps the one it has rather than being reset to the default. [Commit](https://github.com/open-webui/open-webui/commit/d799e81edbdc971c6deb096b6474cd95b93504bf), [Commit](https://github.com/open-webui/open-webui/commit/e9684458125c3202ebc3378aef32f0b6015171d8)
+- 🗄️ **Empty models section in the sidebar.** The models section no longer appears with nothing in it when every pinned model has since been removed, renamed, or hidden. [#27634](https://github.com/open-webui/open-webui/pull/27634), [#27633](https://github.com/open-webui/open-webui/issues/27633)
+- 🚧 **The files pane reopening by itself.** With a terminal selected, closing the files pane now keeps it closed, where saving any setting reopened it, including something as incidental as picking an emoji for a folder. [#28693](https://github.com/open-webui/open-webui/pull/28693), [#28691](https://github.com/open-webui/open-webui/issues/28691), [Commit](https://github.com/open-webui/open-webui/commit/c1c81f8127466a4cd59a16d8658155b1b8faa2d0)
+- 🚰 **Watching file processing tying up the database.** Waiting for a file or a knowledge base to finish processing no longer holds a database connection open for as long as the page is watching, which on busy instances could use up every available connection and leave the rest of the application unable to reach the database. [#28183](https://github.com/open-webui/open-webui/pull/28183)
+- 🗜️ **Embedding settings for other providers.** Saving your embedding settings now writes only the provider you have selected, where it also overwrote the address and key stored for the other two, losing them if their fields were not filled in. [Commit](https://github.com/open-webui/open-webui/commit/87d9b7e84e71b097eadf1df4f9852359104f17ed)
+- ↔️ **Connectors in the side-by-side overview.** With the conversation overview laid out left to right, the lines between messages now join at the sides rather than the top and bottom, so they no longer cut across the boxes. [Commit](https://github.com/open-webui/open-webui/commit/6e468c5b9539d3b6057bab63d81e8d2974acff7b)
+- 💫 **Thinking indicator with the fade turned off.** Turning off the fade effect for streaming text no longer hides the thinking indicator and its spinner, which had made a reasoning model look as though it had already finished from the first moment it started. [#28559](https://github.com/open-webui/open-webui/issues/28559), [Commit](https://github.com/open-webui/open-webui/commit/b1dc945bd6cf97a7067e603fc1b797301e626fb6)
+- 🈳 **Conversations compacted too early on llama.cpp.** A conversation served by llama.cpp is no longer shortened at roughly half the size you configured, where its cached input was counted twice, so a chat showing 39,000 tokens was treated as 77,000 against a 70,000 limit. [#28590](https://github.com/open-webui/open-webui/issues/28590), [Commit](https://github.com/open-webui/open-webui/commit/0b27fa5e873c9f3cff7b14e4eeab8321bdd8970c)
+- ◻️ **Settings tabs spilling past the corner.** Scrolling the list of tabs in settings no longer paints a tab or part of an icon across the dialog's rounded bottom corner, where it appeared to sit outside the dialog. [#27617](https://github.com/open-webui/open-webui/pull/27617), [#27616](https://github.com/open-webui/open-webui/issues/27616)
+- 🎰 **Settings for a switched-off function.** A function that has been turned off no longer offers its per-user settings, and saving them is refused, where doing so loaded the function's code and stored settings that had no effect. [Commit](https://github.com/open-webui/open-webui/commit/a3a81fee03ba7ec0ceb4d1f456e80a8f4fc2320f)
+- 🗃 **Shared folders reordering themselves.** The list of folders shared with you now keeps a consistent order, where on PostgreSQL renaming a folder could shuffle the ones beside it. [#28804](https://github.com/open-webui/open-webui/pull/28804)
+- 📜 **System prompt repeated after a tool call.** On models served by a pipe or manifold, the system prompt is no longer added again each time a tool runs, where it built up one extra copy per round and was sent to the provider that way. [#28739](https://github.com/open-webui/open-webui/pull/28739), [#28736](https://github.com/open-webui/open-webui/issues/28736)
+- 🔕 **Calendar reminders stopping for everyone.** A single event whose reminder time was stored as something other than a number no longer stops reminders being sent, for that event or for anyone else's, and falls back to the usual reminder window instead. [#28790](https://github.com/open-webui/open-webui/pull/28790)
+- 🗨 **Attached conversations reaching the model.** A conversation attached to your message is now listed among its attachments, where it was left out entirely and the model was never told it was there. [#28788](https://github.com/open-webui/open-webui/pull/28788)
+- ↔ **Dragging a side panel closed.** Dragging the chat controls, the note chat, or a channel thread panel closed by its edge no longer floods the browser console with errors and leaves stray handlers behind, and the divider can now be moved with the arrow keys once focused. [#28759](https://github.com/open-webui/open-webui/issues/28759), [Commit](https://github.com/open-webui/open-webui/commit/33dff414e829d10dc6691b1cac7457077fa6799c)
+- 🎫 **Saving a message with unusual characters on PostgreSQL.** A message carrying characters PostgreSQL will not store outside its text no longer fails to save, where those characters were cleaned from the conversation but passed through raw to the separate message record. [#28820](https://github.com/open-webui/open-webui/pull/28820)
+- 🔲 **Removing an item in the model editor.** Unticking a tool, skill, action, or filter no longer leaves the next one in the list looking unticked while it is still selected, needing two clicks to remove and passing the same confusion down the list each time. [#28837](https://github.com/open-webui/open-webui/pull/28837), [#28832](https://github.com/open-webui/open-webui/issues/28832)
+- 📉 **Usage figures drifting upward on clustered setups.** The routine that clears out finished model usage no longer stops for good across the whole cluster after a brief interruption, which had left the usage figures counting models nobody was using and grew the work every disconnection had to do. [#28834](https://github.com/open-webui/open-webui/pull/28834)
+- 🔇 **Voice mode staying silent with reasoning models.** Voice mode now speaks when the emoji option is on and the model behind it reports its answer as thinking rather than text, where the whole reply went unspoken and nothing reached the speech service at all. [#28724](https://github.com/open-webui/open-webui/pull/28724)
+- 🏷 **Tags on a chat shared with you.** Opening a chat shared with you, or one in a shared folder, no longer fails to load its tags, and an administrator opening someone else's chat now sees the tags that chat actually carries. [Commit](https://github.com/open-webui/open-webui/commit/7d4747dfd73d7629227b10ae63c6854cc7543bee), [#28767](https://github.com/open-webui/open-webui/issues/28767)
+- 🔻 **Message box controls in a narrow panel.** Narrowing the note chat panel, or squeezing the chat with a wide controls pane, no longer hides the attach and integrations buttons behind the model name or pushes the send button outside the box; the model name is shortened to make room instead. [#28912](https://github.com/open-webui/open-webui/pull/28912), [#28911](https://github.com/open-webui/open-webui/issues/28911)
+- ⌛ **Replies that are all thinking and no answer.** A reply from a provider using the responses format that ends while the model is still in its reasoning, with no answer text after it, now finishes normally instead of failing the whole turn and leaving an unreadable error in place of the reply. [#28872](https://github.com/open-webui/open-webui/pull/28872), [#28871](https://github.com/open-webui/open-webui/issues/28871)
+- 📃 **Word and PowerPoint previews overflowing.** Previewing one of these files now keeps the document inside its frame, with the zoom and slide controls staying put rather than scrolling away, and a presentation opens on its current slide instead of below the visible area. [#28878](https://github.com/open-webui/open-webui/pull/28878), [#28877](https://github.com/open-webui/open-webui/issues/28877)
+- 🎞 **Workspace models in the admin models list.** Workspace models appear in the admin models list again, so they can be ordered, set as the default, and pinned for everyone; choosing one opens its own editor, where it opened the base model editor and could strip the model's base model, turning it into something else. [Commit](https://github.com/open-webui/open-webui/commit/ccbb3303f2ec5db0b16573bbb665a12f6764da66), [#27702](https://github.com/open-webui/open-webui/issues/27702)
+- ⌨ **Errors after sending a long message.** With prompt autocompletion on, sending or clearing a message of several paragraphs within a second of typing no longer throws an error in the browser console. [#28824](https://github.com/open-webui/open-webui/pull/28824), [#28823](https://github.com/open-webui/open-webui/issues/28823)
+- ❌ **Tool calls that failed looking successful.** A tool call that returned an error is now marked as failed with a red cross rather than a green tick, so a reply built on a failed call is easier to spot. [Commit](https://github.com/open-webui/open-webui/commit/f3f76095d18e07a3a944f22a4b25993bbffe90a3), [#28016](https://github.com/open-webui/open-webui/issues/28016)
+- 🗜 **Download links in a cited source doing nothing.** A link in a citation shown as formatted content now downloads the file when clicked, where it silently did nothing at all. [Commit](https://github.com/open-webui/open-webui/commit/3c66d639e31ba8a7477d337b37d8d671ea2430cf), [#28924](https://github.com/open-webui/open-webui/issues/28924)
+- 🗳 **Web searches failing without saying why.** A web search that fails now explains itself instead of returning nothing at all, which most often happens when a search engine has been selected without its key being configured. [#28942](https://github.com/open-webui/open-webui/pull/28942)
+- ✅ **Checklists in notes.** A checklist in a note now previews and downloads as a proper checklist, where each item carried a stray second pair of brackets and its text began two lines below the box. [#27671](https://github.com/open-webui/open-webui/pull/27671), [#26067](https://github.com/open-webui/open-webui/issues/26067)
+- 🧿 **Shortening a conversation with the wrong model.** Choosing to shorten long conversations with the model you are chatting with now does that, where it used the configured task model instead on any instance that has one. [Commit](https://github.com/open-webui/open-webui/commit/5093a9938937153e287db27a671f5ba1fb5d7592), [#27603](https://github.com/open-webui/open-webui/issues/27603)
+- 🖥 **Stopping a reply after the shared cache restarts.** Stopping a reply now keeps working across a cluster after the shared cache restarts or its connection drops, where the part that carries a stop between instances gave up for good and silently, and only restarting the application brought it back. [Commit](https://github.com/open-webui/open-webui/commit/bf3a58dbcd18ddc2c7f130d8f9529477fe7cb042), [#28909](https://github.com/open-webui/open-webui/issues/28909)
+- 📼 **Attached links to media and archives.** Attaching a link that leads to something other than a web page, such as a video or an archive, now reads it as the file it is rather than trying to treat it as text. [Commit](https://github.com/open-webui/open-webui/commit/886248de36e3a60c3687d1bee6af110e14110eca)
+- 🗒 **Editing a workflow from settings.** Opening the code editor for a ComfyUI workflow from the images settings now brings it to the front, where it opened behind the settings dialog and could not be reached at all. [#27648](https://github.com/open-webui/open-webui/pull/27648), [#27647](https://github.com/open-webui/open-webui/issues/27647)
+- 🖼 **Downloading a generated image.** Downloading an image from its preview now saves the image, where it could silently save a small file containing an authentication error instead, and a download that does fail now says so. [Commit](https://github.com/open-webui/open-webui/commit/2578174637e48cafa4bcb09adbb1b7f4b545a8d5), [#27723](https://github.com/open-webui/open-webui/pull/27723), [#27722](https://github.com/open-webui/open-webui/issues/27722)
+- 🗂 **Directory sync listing local accounts.** A directory service syncing accounts over SCIM now sees only the accounts that came from a directory, where it also listed and could modify accounts created with a password in Open WebUI itself. [Commit](https://github.com/open-webui/open-webui/commit/fb4f476316a2f83e4d2914d535c19b3440cbc490)
+- ↕ **Sorting a list of people.** Sorting the admin user list, or a channel's member list, now works when no search term has been entered, where the chosen order was ignored unless something was being searched for. [Commit](https://github.com/open-webui/open-webui/commit/fb4f476316a2f83e4d2914d535c19b3440cbc490)
+- 🧶 **Text dropped from a reply by a filter.** A filter that rewrites a reply as it streams, or a provider that sends something other than plain text in a chunk, no longer causes that part of the reply to vanish without explanation. [#28840](https://github.com/open-webui/open-webui/pull/28840)
+- 🏗 **Timers firing twice after a fork.** Branching a conversation that has a timer set no longer leaves the copy able to fire that timer as well. [#27663](https://github.com/open-webui/open-webui/pull/27663), [#27622](https://github.com/open-webui/open-webui/issues/27622), [#27745](https://github.com/open-webui/open-webui/issues/27745)
+- 🗣 **Sentences skipped in voice mode.** Voice mode now speaks every sentence of a reply, where any sentence that completed in the same piece of the reply as another was silently never read out, which happened routinely with providers that send whole paragraphs at a time. [Commit](https://github.com/open-webui/open-webui/commit/495296346edfcd96a506a22fed4bb5b8faf3cd4d), [#28730](https://github.com/open-webui/open-webui/issues/28730), [#19861](https://github.com/open-webui/open-webui/issues/19861)
+- 🖊 **Dragging a side panel wider than the window.** A side panel can no longer be dragged so wide that the chat beside it is squeezed away, and dragging one below its minimum width now closes it rather than sticking. [Commit](https://github.com/open-webui/open-webui/commit/ef455fcef9d6cb1136275c26e49bc3c5d6661795), [#28965](https://github.com/open-webui/open-webui/issues/28965)
+- 🎙 **The wrong model selected when reopening a chat.** Reopening a conversation where a reply was regenerated with a different model now selects the model behind the reply you are looking at, where it picked the one used for the first attempt, which might be a model no longer available. [#27674](https://github.com/open-webui/open-webui/pull/27674), [#25052](https://github.com/open-webui/open-webui/issues/25052), [Commit](https://github.com/open-webui/open-webui/commit/8a170897bad569d93e069226a996942583ebde80)
+- 🛜 **Coding tools that speak Anthropic's format.** A tool such as Cline pointed at Open WebUI using Anthropic's own message format can reach models again, where every request failed before it was even sent, and once that was corrected the request was rejected by Anthropic for being signed the wrong way. [#27675](https://github.com/open-webui/open-webui/pull/27675), [#27595](https://github.com/open-webui/open-webui/issues/27595), [#27695](https://github.com/open-webui/open-webui/issues/27695)
+- 👯 **Code in pinned messages.** Opening the pinned messages of a channel now shows the code in those messages, where each block appeared empty and its contents were drawn into the channel behind the dialog instead, doubling them there. [#27740](https://github.com/open-webui/open-webui/pull/27740), [#27739](https://github.com/open-webui/open-webui/issues/27739)
+- 🧻 **Logs flooded by an unreachable server.** A terminal or tool server that cannot be reached now records one line per attempt rather than a full stack trace, where a few minutes of downtime could fill the log with hundreds of megabytes and drown out everything else. [#27755](https://github.com/open-webui/open-webui/pull/27755), [#27751](https://github.com/open-webui/open-webui/issues/27751), [#27757](https://github.com/open-webui/open-webui/pull/27757), [#27756](https://github.com/open-webui/open-webui/issues/27756)
+- 🖱 **Clicking inside a chat preview.** Clicking an image or a source in the preview that appears when you hover a chat in the sidebar no longer flashes a viewer open and shut, since the preview is meant only to be read. [#27770](https://github.com/open-webui/open-webui/pull/27770), [#27769](https://github.com/open-webui/open-webui/issues/27769)
+- 🛢 **Using pgvector with database access by role.** An instance on Amazon RDS that signs in to its database with a temporary credential rather than a stored password now starts when pgvector is the vector store, where the two could not be used together and the container exited on startup. [#27754](https://github.com/open-webui/open-webui/pull/27754), [#27752](https://github.com/open-webui/open-webui/issues/27752)
+- 📗 **Opening knowledge attached to a model or folder.** Clicking a knowledge item attached to a model or a folder opens it again, so it can be read and its retrieval mode changed between focused retrieval and the whole document, where since 0.11.0 neither was possible outside a chat. [#27686](https://github.com/open-webui/open-webui/pull/27686), [#27684](https://github.com/open-webui/open-webui/issues/27684), [#27801](https://github.com/open-webui/open-webui/issues/27801), [#28825](https://github.com/open-webui/open-webui/issues/28825)
+- 🎚 **Retrieval mode shown from another item.** The retrieval mode shown when opening a knowledge item is now that item's own, where it could show the setting of whichever item was opened before it. [#27686](https://github.com/open-webui/open-webui/pull/27686), [#27684](https://github.com/open-webui/open-webui/issues/27684), [#27801](https://github.com/open-webui/open-webui/issues/27801), [#28825](https://github.com/open-webui/open-webui/issues/28825)
+- 🔩 **A new chat shown as nearly full.** The indicator of how full a conversation is now counts tokens the same way the shortening does, where the two read different figures from providers that report both and a fresh chat could appear close to its limit. [#27620](https://github.com/open-webui/open-webui/pull/27620), [#27608](https://github.com/open-webui/open-webui/issues/27608), [Commit](https://github.com/open-webui/open-webui/commit/978d2572140e4fe31ebbc33274f699c71b8cdc29)
+- 🫱 **Abandoned changes to a group's sharing setting.** Closing the edit dialog for a user group without saving now discards a change to who can share to that group, where the change stayed on screen and was written to the database the next time anything else about the group was saved. [#28076](https://github.com/open-webui/open-webui/pull/28076), [#28075](https://github.com/open-webui/open-webui/issues/28075)
+- 📛 **Editing the wrong group.** The dialog for editing a user group now stays with the group it was opened for, where a reordering of the list beneath it could leave it saving to a different group. [#28076](https://github.com/open-webui/open-webui/pull/28076), [#28075](https://github.com/open-webui/open-webui/issues/28075)
+- 🪢 **Signing people out from the identity provider.** A sign-out sent by an identity provider to end someone's session now works, where the check that the message was genuine could fail against providers whose signing keys need the same authentication as everything else, leaving the person signed in. [Commit](https://github.com/open-webui/open-webui/commit/aeda6ff13a25d3b3ba1b303609f35382db22142c)
+- 🪣 **Files left behind when a knowledge base is emptied.** Emptying a knowledge base now removes the files it held, along with their stored copies and their search data, where all three were left behind with nothing in the interface to clear them. [Commit](https://github.com/open-webui/open-webui/commit/363ad352fec9553469852d111bc0506b896504a6), [#27988](https://github.com/open-webui/open-webui/issues/27988)
+- ♻ **Blank errors when a tool server's saved sign-in cannot be read.** A tool server whose stored sign-in details cannot be decrypted, which happens when "WEBUI_SECRET_KEY" changes since the key protecting them follows it, now names the server and says to reconnect it, where every startup logged two errors with no message at all. [Commit](https://github.com/open-webui/open-webui/commit/91917b23952af8ca4457f8bb3db70c75ab838fbf), [#28666](https://github.com/open-webui/open-webui/pull/28666), [#28665](https://github.com/open-webui/open-webui/issues/28665)
+- 🖍 **Clearing the supported media types.** Emptying the supported media types in the documents settings now stays empty, where the previous value came back on the next visit, so images kept being sent to the extraction engine instead of straight to a model that can read them. [#28750](https://github.com/open-webui/open-webui/pull/28750), [#28747](https://github.com/open-webui/open-webui/issues/28747), [Commit](https://github.com/open-webui/open-webui/commit/ecad20b77f9bd700bd818a2f447176f5994320c3)
+- 🫳 **Dropping a chat where it already was.** Dragging a chat in the sidebar and releasing it where it started no longer reloads the whole sidebar, which took around a dozen requests for a move that changed nothing. [#28664](https://github.com/open-webui/open-webui/pull/28664), [#28663](https://github.com/open-webui/open-webui/issues/28663)
+- 🖲 **Filtering while on a later page.** Changing a filter in the workspace, such as showing only what you created, now returns to the first page, where the list could come back empty with the page controls gone and no way back. [#28734](https://github.com/open-webui/open-webui/issues/28734), [Commit](https://github.com/open-webui/open-webui/commit/a914868e3c83b08be1399dbae1e4da25a0c00c87)
+- 🪺 **Workspace counts left behind.** The number beside each workspace tab now follows its list, where creating, copying, importing, or deleting something left the old number in place until you moved to another tab or reloaded, and the tools count ignored its search entirely. [#28983](https://github.com/open-webui/open-webui/pull/28983), [#28981](https://github.com/open-webui/open-webui/issues/28981)
+- 📞 **Links that start a voice call.** Opening a link that starts a call now starts one, where it opened the controls pane and stopped there, leaving the only way to begin a call from outside the application broken. [#28721](https://github.com/open-webui/open-webui/pull/28721), [#28677](https://github.com/open-webui/open-webui/issues/28677), [Commit](https://github.com/open-webui/open-webui/commit/8c1f3d382470edb81fa1efdf6cf4fb6bb188c460)
+- 🆔 **Signing in where the provider uses a numeric account id.** Signing in through GitHub, or any other provider that identifies people by a number, works again on PostgreSQL, where every attempt failed outright since 0.10.2, and on SQLite the existing account was not matched; accounts stored the old way are corrected on the next sign-in. [Commit](https://github.com/open-webui/open-webui/commit/a6834f089bc2980fced99a617670e785c988cc9f), [#28954](https://github.com/open-webui/open-webui/pull/28954), [#27760](https://github.com/open-webui/open-webui/issues/27760)
+- ☎ **Chats opening halfway up.** A conversation whose recent messages are short now opens at the latest message rather than somewhere in the middle, and older messages loaded while scrolling up no longer shift what you were reading. [#28657](https://github.com/open-webui/open-webui/pull/28657), [#28656](https://github.com/open-webui/open-webui/issues/28656)
+- 🛤 **The terminal picker vanishing mid-reply.** The terminal picker now stays in place while a reply is being written, greyed out until it finishes, where it disappeared from the message box entirely and took the name of the selected terminal with it. [Commit](https://github.com/open-webui/open-webui/commit/7a533d0d5b85981f8c5668636f931f8b4a97d604)
+- 🎧 **Who a channel says its members are.** The member list of a channel now includes its owner and everyone in a group that was granted access, where the owner never appeared and granting both a person and a group they were not in listed nobody at all while the count beside it said two. [#28289](https://github.com/open-webui/open-webui/pull/28289), [#28288](https://github.com/open-webui/open-webui/issues/28288), [Commit](https://github.com/open-webui/open-webui/commit/e3e82b14714661ba5bd24e2c47e42cef5594b132)
+- ⛳ **Embedding servers behind a password.** An embedding server protected by a username and password rather than a key now works, where an empty key still sent an authorisation header, which such a server rejected and which made document uploads fail. [#28684](https://github.com/open-webui/open-webui/pull/28684), [#28683](https://github.com/open-webui/open-webui/issues/28683), [Commit](https://github.com/open-webui/open-webui/commit/97466deea105d6fdde60bf4d9401703fd32e03e9)
+- ✒ **Note edits lost without warning.** Typing in a note now reaches the database, where a save already waiting could be cancelled without a replacement, leaving the editor showing text that was never stored and nothing to say so; this affected notes written by a model or through the API, and any instance without Redis after a restart. [#28669](https://github.com/open-webui/open-webui/pull/28669), [#28667](https://github.com/open-webui/open-webui/issues/28667)
+- 🗄 **Browsing outside the home directory in a terminal.** A terminal server set to allow browsing the whole filesystem can be browsed above the home directory again, where the file panel pinned itself there and opening a file elsewhere quietly did nothing. [#29006](https://github.com/open-webui/open-webui/pull/29006), [#29000](https://github.com/open-webui/open-webui/issues/29000)
+- 🏞 **Clearing a model's picture.** A model's picture can be reset to the default logo again, where since 0.11.0 a custom one could only ever be replaced. [#29007](https://github.com/open-webui/open-webui/pull/29007), [#27685](https://github.com/open-webui/open-webui/issues/27685), [Commit](https://github.com/open-webui/open-webui/commit/06e7aac219b3027a9d578624c473b041ad26a692)
+- 👤 **Fallback profile pictures.** A profile picture that fails to load, such as one belonging to a deleted account, now falls back to the default avatar instead of showing clipped placeholder text beside the message. [#28270](https://github.com/open-webui/open-webui/pull/28270), [#28269](https://github.com/open-webui/open-webui/issues/28269)
+- ⏱️ **Unanswered prompts in tools.** On deployments that set "WEBSOCKET_EVENT_CALLER_TIMEOUT", a question a tool asks you that goes unanswered now reports a timeout rather than an empty reply, and waiting too long no longer risks disconnecting a tab that is still open. [#28311](https://github.com/open-webui/open-webui/pull/28311)
+- 👪 **Group member counts updating.** Adding or removing someone from a group in the admin panel now updates that group's member count straight away, where it stayed at the old number until the page was reloaded. [Commit](https://github.com/open-webui/open-webui/commit/18bf0ade7b35fb25ff7920ad3713624d93f04401)
+- 🕳️ **Blank messages left in a conversation.** Streamed events that never fill in an item no longer leave an empty assistant message saved in the conversation and sent back to the model on every later turn. [Commit](https://github.com/open-webui/open-webui/commit/2a0274a0a039dbe0a1ad4d24003b085aae7b896b)
+- 📓 **Notes opening blank.** A note whose shared editing session has not been started yet now opens with its stored content even when several people open it at once, where previously anyone but a lone first viewer got an empty document. [Commit](https://github.com/open-webui/open-webui/commit/5078d987f83943671f1d23ebe66bcc8d2af902c3)
+- 🤫 **Replies stopping silently after a tool ran.** When a provider rejects the follow-up request made after a tool finishes, the reason is now shown in the chat instead of the reply simply ending with nothing said. [Commit](https://github.com/open-webui/open-webui/commit/a610d77137fabf60a2e0daa961a8ef8f7320293a), [#28633](https://github.com/open-webui/open-webui/issues/28633)
+- 🎟️ **Connections whose tags were saved as plain text.** A connection with tags stored as plain text no longer breaks its editor panel or silently blanks the tags on every model coming from it. [Commit](https://github.com/open-webui/open-webui/commit/8be4c5fa6a849a9ff4a74f6a2870a115a836e68a), [#28749](https://github.com/open-webui/open-webui/issues/28749)
+- 🔌 **Stream filters on direct API calls.** A filter reading a streamed event as an object now works on requests made straight to the chat completions endpoint, matching every other path, where it used to raise and end the reply partway. [Commit](https://github.com/open-webui/open-webui/commit/684111715f742f56a3c7efac9eb7a1e68e54a3ec)
+- 🔇 **Filter failures that said nothing.** When a filter's outlet or stream hook raises, the failure is now reported with the filter's name and a traceback at the default log level, where it was swallowed and left plugin authors with nothing to go on. [Commit](https://github.com/open-webui/open-webui/commit/35fbde0a3fb303b7076b03465b1a2b0ba832df53)
+- 🪜 **Falling back when a base model is gone.** Chatting with a workspace model whose base model has been removed now falls back to the default model for everyone, where the fallback previously applied only for administrators and anyone else was refused whenever that base model had no workspace entry of its own, such as one supplied by a pipe. [Commit](https://github.com/open-webui/open-webui/commit/20fe43d9da621957c48fc92104bc8f1cc0d691b7)
+- 🧠 **Conversations breaking after a model switch.** Switching to a different model once a reasoning model has answered no longer leaves the conversation unusable, where the earlier model's stored reasoning was replayed to a provider that then rejected every later request. [Commit](https://github.com/open-webui/open-webui/commit/c4b3e6840f34a5d267bc12c0ec1a82156a324d45), [#28240](https://github.com/open-webui/open-webui/issues/28240)
+- 👻 **Messages disappearing from a conversation.** Two things saving the same conversation at once no longer discard each other's changes, where a message could vanish from the screen while still counting toward the model's context and a file attached during a reply was lost on the next save. [Commit](https://github.com/open-webui/open-webui/commit/1c13fedb16e74c5888c52ccd928a5eb5bbb1068d), [#28742](https://github.com/open-webui/open-webui/issues/28742)
+- 🧬 **Workspace models pointing at themselves.** A workspace model whose base model was set to its own identifier is now saved without that reference, where the entry was thrown away while models were being combined so none of its settings ever took effect. [Commit](https://github.com/open-webui/open-webui/commit/eadce55e343df69520e6bc86dbbdfdcdfdcafb30), [#28952](https://github.com/open-webui/open-webui/issues/28952), [#28923](https://github.com/open-webui/open-webui/issues/28923)
+- 📭 **A short model list sticking on every worker.** When one worker briefly reports fewer models than it should, that shorter list is no longer left in place for the whole deployment, where chatting with one of the missing models failed on every server until something restarted. [Commit](https://github.com/open-webui/open-webui/commit/6330350a406d8c1fd603f725e59a88324c8e2256), [#28777](https://github.com/open-webui/open-webui/issues/28777)
+- 📋 **Copying from the terminal file browser.** Copying a file path or a file's contents now works again, where it silently did nothing on deployments the browser does not treat as a secure origin. [Commit](https://github.com/open-webui/open-webui/commit/aa3d56961049618b28717d87acff1d9360cad47a), [Commit](https://github.com/open-webui/open-webui/commit/2f97c9fce36b3794d14c925086eca78ff92adf4a), [#29015](https://github.com/open-webui/open-webui/issues/29015)
+- 🗺️ **Browsing the web through Microsoft Web IQ.** Fetching a page with the web loader set to Microsoft Web IQ now works, where every attempt failed before a single request was made and had done so ever since that loader was added. [Commit](https://github.com/open-webui/open-webui/commit/6dcc2d52692c3fa1993ff1b3ae84c07d35fd9f6b), [Commit](https://github.com/open-webui/open-webui/commit/140d2cf4b59e71d2e9f4986d4d8649fccb47c83d), [#28688](https://github.com/open-webui/open-webui/issues/28688)
+- 🔛 **Enable or disable all automations only reaching the ones on screen.** Turning every automation on or off now covers every automation matching your current search and filter, where it only ever touched the ones loaded on the page you were looking at and left the rest running as they were. [Commit](https://github.com/open-webui/open-webui/commit/f4a0d3c9734d1662a3f78891f21934f2b82aed1e)
+
+### 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.
+- 🏋️ **What "THREAD_POOL_SIZE" now sizes.** The setting now governs both of the pools that background work runs in, where it previously governed only one and the other, carrying most of the blocking work including knowledge searches, sign-ins and file storage, was fixed at a small ceiling no setting could raise, so an instance that set it high will now use more threads than before, up to twice the configured value across the two pools, and one that relied on the old ceiling to hold thread use down should review it. [Commit](https://github.com/open-webui/open-webui/commit/4ec6ee14418edd04eaba9e34bd5868453f61df40), [#28168](https://github.com/open-webui/open-webui/issues/28168)
+- 💾 **Saving replies as they stream.** The "ENABLE_REALTIME_CHAT_SAVE" setting no longer has any effect, because a reply in progress is now held outside the database and written once when it finishes. [Commit](https://github.com/open-webui/open-webui/commit/a1579a01ff43cacb357269707d36267ad35e01d6)
+- 🎭 **Playwright web loader egress.** When a page is fetched with the Playwright loader, the page's own requests for its images, scripts, and stylesheets are now made by the Open WebUI backend instead of by the browser, so administrators using a remote browser through "PLAYWRIGHT_WS_URL" should expect that traffic to leave from the backend's address rather than the browser host, those using a private certificate authority should expect it to be trusted through "AIOHTTP_CLIENT_SSL_CERT_FILE" rather than the browser's own store, and those who set a proxy on the loader should know it no longer applies to these requests, which follow the environment's proxy settings instead. [#28634](https://github.com/open-webui/open-webui/pull/28634)
+- 🐌 **Slower Playwright page loads without async.** A page fetched with the Playwright loader on the synchronous path now fetches its images, scripts, and stylesheets one at a time rather than together, which in the change's own measurements took a page with thirty assets from 2.0 to 3.0 seconds, and one with eight slow assets from 1.1 to 4.5 seconds; the asynchronous path is unaffected. [#28634](https://github.com/open-webui/open-webui/pull/28634)
+- 🐳 **Test-only packages removed from the image.** The container no longer ships pytest, pytest-docker, the Docker SDK, or netcat, none of which anything in Open WebUI used, so the image is smaller; anyone whose own tools or functions relied on those being present will need to install them themselves. [#28726](https://github.com/open-webui/open-webui/pull/28726)
+- 🛡 **Forms in embedded pages now work by default.** A page shown inside a chat, such as an artifact or an HTML preview, may now submit forms unless you turn that off, where it was blocked unless you turned it on. [Commit](https://github.com/open-webui/open-webui/commit/3c66d639e31ba8a7477d337b37d8d671ea2430cf)
+- 🅰 **Connection prefixes now show in model names.** A connection's prefix appears in the name shown in the model picker, not only in its identifier, where whether it did depended on the shape of the provider's reply and so worked on some connections and not others; models on prefixed connections will now read differently than before. [#28950](https://github.com/open-webui/open-webui/pull/28950), [#28929](https://github.com/open-webui/open-webui/issues/28929)
+- 📊 **Default usage statistics range.** Usage statistics now cover the past two years by default for everyone, instead of starting from the date the account was created. [Commit](https://github.com/open-webui/open-webui/commit/8dbbc206c5a0706789722c42827479e5db10bb2b)
+
 ## [0.11.0] - 2026-07-27
 
 ### Added

CODE_OF_CONDUCT.md

@@ -20,7 +20,7 @@ Examples of behavior that contribute to a positive and professional community in
 
 - **Respecting others.** Be considerate, listen actively, and engage with empathy toward others' viewpoints and experiences.
 - **Constructive feedback.** Provide actionable, thoughtful, and respectful feedback that helps improve the project and encourages collaboration. Avoid unproductive negativity or hypercriticism.
-- **Recognizing volunteer contributions.** Appreciate that contributors dedicate their free time and resources selflessly. Approach them with gratitude and patience.
+- **Recognizing volunteer contributions.** Appreciate that **contributors dedicate their free time and resources selflessly**. Approach them with gratitude and patience.
 - **Focusing on shared goals.** Collaborate in ways that prioritize the health, success, and sustainability of the community over individual agendas.
 
 Examples of unacceptable behavior include:
@@ -32,11 +32,23 @@ Examples of unacceptable behavior include:
 - **Entitlement, demand, or aggression toward contributors.** Volunteers are under no obligation to provide immediate or personalized support. Rude or dismissive behavior will not be tolerated.
 - **Unproductive or destructive behavior.** This includes venting frustration as hostility ("tantrums"), hypercriticism, attention-seeking negativity, or anything that distracts from the project's goals.
 - **Spamming and promotional exploitation.** Sharing irrelevant product promotions or self-promotion in the community is not allowed unless it directly contributes value to the discussion.
+- Posting low-effort, hard to read, essay-length AI generated comments or other forms of low-quality, hard to parse content that puts the burden of understanding on the reader.
+
+### How We Develop the Project
+
+Development is led by the maintainers, and code pull requests are reserved for work we explicitly request or exceptional contributions we choose to consider at our discretion. We use actionable reports and concrete use cases to understand problems, then evaluate, revise, and implement the appropriate approach internally. We assess each change against the project's architecture, existing behavior, quality standards, and future direction before settling on an implementation. Resolving a reported problem requires that broader context, and a working external patch usually requires substantial rewriting to meet the project's standards. Reviewing the patch, explaining the required changes, and coordinating successive revisions usually takes more effort than developing the solution internally. Fragmented commit histories, branches that have not been rebased, unresolved conflicts, and lengthy or unverified AI-generated comments add cleanup and discussion that delay the underlying work. Maintainers remain responsible for testing, documenting, supporting, and maintaining every accepted change, so we choose the approach based on the whole product and its ongoing maintenance. Clear reports, reproduction details, and relevant context give us what we need to make those decisions and develop the solution. A polished implementation, clean commit history, or completed checklist does not establish an exception to this process, and opening an issue or discussion is not an invitation to submit a PR. Wait for an explicit maintainer request before investing in a PR; unsolicited submissions are generally closed without review, and requested PRs remain subject to maintainer judgment.
 
 ### Feedback and Community Engagement
 
-- **Constructive feedback is encouraged, but hostile or entitled behavior will result in immediate action.** If you disagree with elements of the project, we encourage you to offer meaningful improvements or fork the project if necessary. Healthy discussions and technical disagreements are welcome only when handled with professionalism.
+Participation should help maintainers understand a concrete problem while respecting the project's priorities and available capacity. Please follow the [issue templates](.github/ISSUE_TEMPLATE) and [pull request policy](.github/pull_request_template.md) before submitting anything.
-- **Respect contributors' time and efforts.** No one is entitled to personalized or on-demand assistance. This is a community built on collaboration and shared effort; demanding or demeaning behavior undermines that trust and will not be allowed.
+
+- **Make reports actionable.** Search existing issues and discussions, check the latest version and whether the problem is already addressed on `dev`, and use the appropriate template. Bug reports should describe a reproducible problem, the affected workflow, expected and actual behavior, and relevant evidence. Feature requests should explain the user-facing need; broader product, UX, architecture, or maintenance questions belong in Discussions. Report security concerns privately through the [security reporting process](https://github.com/open-webui/open-webui/security).
+- **Share the problem before investing in code.** Start with an actionable issue or discussion and leave implementation planning to the maintainers. An issue or discussion alone is not an invitation to submit a PR. Please wait for an explicit request before opening one; any exception is at the maintainers' discretion. Implementation notes, local diffs, or patches may be shared as reference in the relevant issue or discussion.
+- **Respect maintainers' discretion.** Submitting an issue, proposal, or pull request does not create an obligation to respond, review, implement, or merge it. Maintainers set the project's direction and defer or close submissions based on scope, quality, maintenance cost, or available capacity. Unsolicited pull requests are generally closed without review.
+- **Keep discussion focused and concise.** Provide new information when it helps evaluate the problem. Repeated bumps, duplicate submissions, unsolicited direct messages seeking attention, or pressure for timelines place an unnecessary burden on contributors.
+- **Respect decisions and boundaries.** Technical disagreement is welcome when expressed professionally. Reopening a declined request or continuing to press for a different outcome without new, relevant information is not constructive. You are free to explore a different direction in your own fork.
+
+Participants are expected to respect maintainers' decisions and the contribution process. Harassment, hostility, or repeated disregard for these boundaries will result in enforcement under this Code of Conduct.
 
 ### Zero Tolerance: No Warnings, Immediate Action
 

Dockerfile

@@ -26,6 +26,9 @@ ARG GID=0
 ######## WebUI frontend ########
 FROM --platform=$BUILDPLATFORM node:22-alpine3.20 AS build
 ARG BUILD_HASH
+ARG USE_SLIM
+ARG UID
+ARG GID
 
 # Set Node.js options (heap limit Allocation failed - JavaScript heap out of memory)
 # ENV NODE_OPTIONS="--max-old-space-size=4096"
@@ -40,7 +43,14 @@ RUN npm ci --force
 
 COPY . .
 ENV APP_BUILD_HASH=${BUILD_HASH}
-RUN npm run build
+RUN npm run build && \
+    if [ "$USE_SLIM" = "true" ]; then find build -type f -name '*.map' -delete; fi
+
+# Prepare backend ownership before the final copy so static assets occupy one layer.
+# Group 0 write access lets arbitrary OpenShift UIDs update these assets at startup.
+RUN chown -R $UID:$GID /app/backend && \
+    chgrp -R 0 /app/backend/open_webui/static && \
+    chmod -R g=u /app/backend/open_webui/static
 
 ######## WebUI backend ########
 FROM python:3.11-slim-bookworm AS base
@@ -123,24 +133,33 @@ RUN echo -n 00000000-0000-0000-0000-000000000000 > $HOME/.cache/chroma/telemetry
 # Make sure the user has access to the app and root directory
 RUN chown -R $UID:$GID /app $HOME
 
-# Install common system dependencies
+# Slim cannot bundle a local model server or GPU runtime.
+RUN if [ "$USE_SLIM" = "true" ] && { [ "$USE_CUDA" = "true" ] || [ "$USE_OLLAMA" = "true" ]; }; then \
+    echo "USE_SLIM cannot be combined with USE_CUDA or USE_OLLAMA" >&2; exit 1; fi
+
+# Keep the slim runtime free of local document/audio processing tools.
+# Git-based tool requirements require the standard image.
 RUN apt-get update && \
     apt-get install -y --no-install-recommends \
-    git build-essential pandoc gcc netcat-openbsd curl jq ca-certificates \
+    curl jq ca-certificates \
-    libmariadb-dev \
+    && if [ "$USE_SLIM" != "true" ]; then \
-    python3-dev \
+    apt-get install -y --no-install-recommends \
-    ffmpeg libsm6 libxext6 zstd \
+    git build-essential pandoc gcc libmariadb-dev ffmpeg libsm6 libxext6; \
-    && rm -rf /var/lib/apt/lists/*
+    fi && if [ "$USE_OLLAMA" = "true" ]; then \
+    apt-get install -y --no-install-recommends zstd; \
+    fi && rm -rf /var/lib/apt/lists/*
 
 # install python dependencies
-COPY --chown=$UID:$GID ./backend/requirements.txt ./requirements.txt
+COPY --chown=$UID:$GID ./backend/requirements*.txt ./
 
 # Set UV_LINK_MODE to copy to prevent 0-byte file corruption in QEMU arm64 cross-builds
 ENV UV_LINK_MODE=copy
 
-RUN set -e; \
+RUN --mount=from=ghcr.io/astral-sh/uv:0.12.10,source=/uv,target=/bin/uv \
-    pip3 install --no-cache-dir uv; \
+    set -e; \
-    if [ "$USE_CUDA" = "true" ]; then \
+    if [ "$USE_SLIM" = "true" ]; then \
+    uv pip install --system -r requirements-slim.txt --no-cache-dir; \
+    elif [ "$USE_CUDA" = "true" ]; then \
     # If you use CUDA the whisper and embedding model will be downloaded on first use
     # fix: pin torch<=2.9.1 - torch 2.10.0 aarch64 wheels cause SIGILL on ARM devices (RPi 4 Cortex-A72) #21349
     pip3 install 'torch<=2.9.1' torchvision torchaudio --index-url https://download.pytorch.org/whl/$USE_CUDA_DOCKER_VER --no-cache-dir; \
@@ -149,7 +168,6 @@ RUN set -e; \
     python -c "import os; from sentence_transformers import SentenceTransformer; SentenceTransformer(os.environ.get('AUXILIARY_EMBEDDING_MODEL', 'TaylorAI/bge-micro-v2'), device='cpu')"; \
     python -c "import os; from faster_whisper import WhisperModel; WhisperModel(os.environ['WHISPER_MODEL'], device='cpu', compute_type='int8', download_root=os.environ['WHISPER_MODEL_DIR'])"; \
     python -c "import os; import tiktoken; tiktoken.get_encoding(os.environ['TIKTOKEN_ENCODING_NAME'])"; \
-    python -c "import nltk; nltk.download('punkt_tab')"; \
     else \
     pip3 install 'torch<=2.9.1' torchvision torchaudio --index-url https://download.pytorch.org/whl/cpu --no-cache-dir; \
     uv pip install --system -r requirements.txt --no-cache-dir; \
@@ -158,12 +176,17 @@ RUN set -e; \
     python -c "import os; from sentence_transformers import SentenceTransformer; SentenceTransformer(os.environ.get('AUXILIARY_EMBEDDING_MODEL', 'TaylorAI/bge-micro-v2'), device='cpu')"; \
     python -c "import os; from faster_whisper import WhisperModel; WhisperModel(os.environ['WHISPER_MODEL'], device='cpu', compute_type='int8', download_root=os.environ['WHISPER_MODEL_DIR'])"; \
     python -c "import os; import tiktoken; tiktoken.get_encoding(os.environ['TIKTOKEN_ENCODING_NAME'])"; \
-    python -c "import nltk; nltk.download('punkt_tab')"; \
     fi; \
     fi; \
     mkdir -p /app/backend/data; chown -R $UID:$GID /app/backend/data/; \
+    if [ -d /app/backend/data/cache ]; then chmod -R a+rX /app/backend/data/cache; fi; \
     rm -rf /var/lib/apt/lists/*;
 
+# Optional: PPTX parsing through unstructured may need spaCy's English model.
+# Keep this out of the default image to avoid the extra image bloat; deployments
+# with read-only site-packages can uncomment it and bake the model in.
+# RUN python -m spacy download en_core_web_sm
+
 # Install Ollama if requested
 RUN if [ "$USE_OLLAMA" = "true" ]; then \
     date +%s > /tmp/ollama_build_hash && \
@@ -181,19 +204,8 @@ COPY --chown=$UID:$GID --from=build /app/build /app/build
 COPY --chown=$UID:$GID --from=build /app/CHANGELOG.md /app/CHANGELOG.md
 COPY --chown=$UID:$GID --from=build /app/package.json /app/package.json
 
-# copy backend files
+# copy backend files with the ownership and static permissions prepared above
-COPY --chown=$UID:$GID ./backend .
+COPY --from=build /app/backend .
-
-# The backend rewrites its bundled static assets (favicons, splash, manifest,
-# loader.js, ...) under open_webui/static at startup. Make that directory
-# writable by an arbitrary UID -- which under OpenShift's restricted SCC is
-# always a member of GID 0 -- so those writes don't fail with EACCES and crash
-# the boot log with "[Errno 13] Permission denied". `chmod -R g=u` mirrors the
-# owner bits onto the group (the Red Hat arbitrary-UID idiom). This is applied
-# unconditionally because it targets a directory the app writes on every start;
-# the broader, opt-in USE_PERMISSION_HARDENING below covers the rest of /app.
-RUN chgrp -R 0 /app/backend/open_webui/static && \
-    chmod -R g=u /app/backend/open_webui/static
 
 EXPOSE 8080
 

README.md

@@ -10,9 +10,7 @@
 [![Discord](https://img.shields.io/badge/Discord-Open_WebUI-blue?logo=discord&logoColor=white)](https://discord.gg/5rJgQTnV4s)
 [![](https://img.shields.io/static/v1?label=Sponsor&message=%E2%9D%A4&logo=GitHub&color=%23fe8e86)](https://github.com/sponsors/open-webui)
 
-![Open WebUI Banner](./banner.png)
+Open WebUI is **a home for AI**, a self-hosted AI platform that's **[extensible](https://docs.openwebui.com/features/extensibility/plugin/)**, **[feature-rich](https://docs.openwebui.com/features/)**, user-friendly, and built to run **[entirely offline](https://openwebui.com/sovereign-ai)**. With support for **Ollama** and **OpenAI-compatible APIs**, it gives you a powerful, provider-agnostic interface for both local and cloud-based models.
-
-**Open WebUI is an [extensible](https://docs.openwebui.com/features/extensibility/plugin), feature-rich, and user-friendly self-hosted AI platform designed to operate entirely offline.** It supports various LLM runners like **Ollama** and **OpenAI-compatible APIs**, with **built-in inference engine** for RAG, making it a **powerful AI deployment solution**.
 
 Passionate about open-source AI? [Join our team →](https://careers.openwebui.com/)
 
@@ -20,8 +18,6 @@ Passionate about open-source AI? [Join our team →](https://careers.openwebui.c
 
 > [!TIP]  
 > **Looking for an [Enterprise Plan](https://docs.openwebui.com/enterprise)?** – **[Speak with Our Sales Team Today!](https://docs.openwebui.com/enterprise)**
->
-> Get **enhanced capabilities**, including **custom theming and branding**, **Service Level Agreement (SLA) support**, **Long-Term Support (LTS) versions**, and **more!**
 
 For more information, be sure to check out our [Open WebUI Documentation](https://docs.openwebui.com/).
 
@@ -37,6 +33,8 @@ For more information, be sure to check out our [Open WebUI Documentation](https:
 
 - 🤖 **Models & Agents**: Wrap any base model with custom instructions, tools, and knowledge to build specialized agents. Supports dynamic variables, per-user/group access control, and community preset imports via [Open WebUI Community](https://openwebui.com/).
 
+- ⚡ **Agentic Execution with [Open Terminal](https://github.com/open-webui/open-terminal)**: Give your agents a terminal and filesystem to carry out multi-step tasks. Let them analyze data, run scripts, fix errors, and produce files directly in chat. Scale to teams with **[Terminals (Enterprise)](https://github.com/open-webui/terminals)** for per-user isolated environments, resource limits, and automatic lifecycle management.
+
 - 📝 **Notes**: A dedicated workspace for content outside conversations. Draft with a rich editor, use AI to rewrite selected text, and attach notes to any chat for full-context injection.
 
 - 📢 **Channels**: Real-time shared spaces where your team and AI models collaborate in one timeline. Tag models to draft or critique, with threads, reactions, pins, and access control.

backend/dev.sh

@@ -1,3 +1,3 @@
 export CORS_ALLOW_ORIGIN="http://localhost:5173;http://localhost:8080"
 PORT="${PORT:-8080}"
-uvicorn open_webui.main:app --port $PORT --host 0.0.0.0 --forwarded-allow-ips "${FORWARDED_ALLOW_IPS:-*}" --reload
+uvicorn open_webui.main:app --port $PORT --host 0.0.0.0 --forwarded-allow-ips "${FORWARDED_ALLOW_IPS:-*}" --ws-per-message-deflate "${UVICORN_WS_PER_MESSAGE_DEFLATE:-true}" --reload

backend/open_webui/__init__.py

@@ -18,6 +18,9 @@ def version_callback(value: bool) -> None:
     if value:
         from open_webui.env import VERSION
 
+        # LICENSE covers this Open WebUI CLI identifier.
+        # Do not alter, remove, obscure, or replace it except as LICENSE permits:
+        # https://docs.openwebui.com/license.
         typer.echo(f'Open WebUI version: {VERSION}')
         raise typer.Exit()
 
@@ -71,7 +74,7 @@ def serve(
             os.environ['LD_LIBRARY_PATH'] = ':'.join(LD_LIBRARY_PATH)
 
     import open_webui.main  # noqa: F401
-    from open_webui.env import UVICORN_WORKERS  # Import the workers setting
+    from open_webui.env import UVICORN_WORKERS, UVICORN_WS_PER_MESSAGE_DEFLATE
 
     # On Windows, uvicorn's default loop factory hardcodes ProactorEventLoop,
     # which is incompatible with psycopg v3 async.  Setting loop='none' lets
@@ -84,6 +87,7 @@ def serve(
         port=port,
         forwarded_allow_ips='*',
         workers=UVICORN_WORKERS,
+        ws_per_message_deflate=UVICORN_WS_PER_MESSAGE_DEFLATE,
         loop=loop,
     )
 
@@ -94,12 +98,15 @@ def dev(
     port: int = 8080,
     reload: bool = True,
 ):
+    from open_webui.env import UVICORN_WS_PER_MESSAGE_DEFLATE
+
     uvicorn.run(
         'open_webui.main:app',
         host=host,
         port=port,
         reload=reload,
         forwarded_allow_ips='*',
+        ws_per_message_deflate=UVICORN_WS_PER_MESSAGE_DEFLATE,
     )
 
 

backend/open_webui/config.py

@@ -1,7 +1,6 @@
 from __future__ import annotations
 
 import base64
-import json
 import logging
 import os
 import shutil
@@ -18,8 +17,10 @@ from authlib.integrations.starlette_client import OAuth
 from pydantic import BaseModel
 
 from open_webui.env import (
+    USE_SLIM,
     DATA_DIR,
     DATABASE_URL,
+    ENABLE_ADMIN_CHAT_ACCESS,
     ENABLE_DB_MIGRATIONS,
     ENV,
     FRONTEND_BUILD_DIR,
@@ -35,11 +36,12 @@ from open_webui.env import (
     log,
 )
 from open_webui.models.config import Config
+from open_webui.utils.json_codec import JSONCodec
 
 
 async def seed_registered_defaults():
     await Config.rename_prefix('rag.web', 'web')
-    await Config.repair_flattened_dict_configs()
+    await Config.repair_config_rows()
     await Config.seed_defaults(DEFAULT_CONFIG)
 
 
@@ -73,6 +75,7 @@ def run_migrations():
         command.upgrade(alembic_cfg, 'head')
     except Exception as e:
         log.exception(f'Error running migrations: {e}')
+        raise
 
 
 if ENABLE_DB_MIGRATIONS:
@@ -84,7 +87,7 @@ async def import_legacy_config_json():
     if not os.path.exists(f'{DATA_DIR}/config.json'):
         return
     with open(f'{DATA_DIR}/config.json', 'r') as _f:
-        await Config.upsert(json.load(_f))
+        await Config.upsert(JSONCodec.loads(_f.read()))
     os.rename(f'{DATA_DIR}/config.json', f'{DATA_DIR}/old_config.json')
 
 
@@ -114,6 +117,9 @@ for file_path in (FRONTEND_BUILD_DIR / 'static').glob('**/*'):
         except Exception as e:
             logging.error(f'An error occurred: {e}')
 
+# LICENSE covers copied Open WebUI logo/favicon assets.
+# Do not alter, remove, obscure, or replace them except as LICENSE permits:
+# https://docs.openwebui.com/license.
 frontend_favicon = FRONTEND_BUILD_DIR / 'static' / 'favicon.png'
 
 if frontend_favicon.exists():
@@ -181,6 +187,9 @@ CACHE_DIR.mkdir(parents=True, exist_ok=True)
 # CUSTOM_NAME (Legacy)
 ####################################
 
+# LICENSE covers this legacy Open WebUI branding path.
+# Do not alter, remove, obscure, or replace it except as LICENSE permits:
+# https://docs.openwebui.com/license.
 CUSTOM_NAME = os.getenv('CUSTOM_NAME', '')
 
 if CUSTOM_NAME:
@@ -219,6 +228,7 @@ if CUSTOM_NAME:
 ####################################
 
 ENABLE_DIRECT_CONNECTIONS = os.getenv('ENABLE_DIRECT_CONNECTIONS', 'False').lower() == 'true'
+ENABLE_DIRECT_INTEGRATIONS = os.getenv('ENABLE_DIRECT_INTEGRATIONS', 'False').lower() == 'true'
 
 ####################################
 # OLLAMA_BASE_URL
@@ -270,9 +280,9 @@ def _resolve_ollama_base_url(url: str) -> str:
 
     if not default.result() and fallback.result():
         url = url.replace(':11434', ':12434')
-        log.info(f'Ollama port 11434 unreachable on {host}, falling back to 12434')
+        log.info('Ollama port 11434 unreachable on %s, falling back to 12434', host)
     elif not default.result():
-        log.info(f'Ollama ports 11434 and 12434 both unreachable on {host}')
+        log.info('Ollama ports 11434 and 12434 both unreachable on %s', host)
 
     return url
 
@@ -293,12 +303,12 @@ OLLAMA_API_CONFIGS = {}
 _ollama_api_configs = os.getenv('OLLAMA_API_CONFIGS', '')
 if _ollama_api_configs:
     try:
-        parsed = json.loads(_ollama_api_configs)
+        parsed = JSONCodec.loads(_ollama_api_configs)
         if isinstance(parsed, dict):
             OLLAMA_API_CONFIGS = parsed
         else:
             log.warning('OLLAMA_API_CONFIGS must be a JSON object, ignoring')
-    except (json.JSONDecodeError, TypeError):
+    except (JSONCodec.JSONDecodeError, TypeError):
         log.warning('OLLAMA_API_CONFIGS is not valid JSON, ignoring')
 
 ####################################
@@ -340,12 +350,12 @@ OPENAI_API_CONFIGS = {}
 _openai_api_configs = os.getenv('OPENAI_API_CONFIGS', '')
 if _openai_api_configs:
     try:
-        parsed = json.loads(_openai_api_configs)
+        parsed = JSONCodec.loads(_openai_api_configs)
         if isinstance(parsed, dict):
             OPENAI_API_CONFIGS = parsed
         else:
             log.warning('OPENAI_API_CONFIGS must be a JSON object, ignoring')
-    except (json.JSONDecodeError, TypeError):
+    except (JSONCodec.JSONDecodeError, TypeError):
         log.warning('OPENAI_API_CONFIGS is not valid JSON, ignoring')
 
 # Get the actual OpenAI API key based on the base URL
@@ -369,7 +379,7 @@ ENABLE_BASE_MODELS_CACHE = os.getenv('ENABLE_BASE_MODELS_CACHE', 'False').lower(
 ####################################
 
 try:
-    tool_server_connections = json.loads(os.getenv('TOOL_SERVER_CONNECTIONS', '[]'))
+    tool_server_connections = JSONCodec.loads(os.getenv('TOOL_SERVER_CONNECTIONS', '[]'))
 except Exception as e:
     log.exception(f'Error loading TOOL_SERVER_CONNECTIONS: {e}')
     tool_server_connections = []
@@ -383,12 +393,12 @@ OAUTH_CLIENT_TIMEOUT = os.getenv('OAUTH_CLIENT_TIMEOUT', '')
 # TERMINAL_SERVER
 ####################################
 
-terminal_server_connections = json.loads(os.getenv('TERMINAL_SERVER_CONNECTIONS', '[]'))
+terminal_server_connections = JSONCodec.loads(os.getenv('TERMINAL_SERVER_CONNECTIONS', '[]'))
 
 TERMINAL_SERVER_CONNECTIONS = terminal_server_connections
 
 try:
-    TERMINAL_PROXY_HEADERS = json.loads(os.getenv('TERMINAL_PROXY_HEADERS', '{}'))
+    TERMINAL_PROXY_HEADERS = JSONCodec.loads(os.getenv('TERMINAL_PROXY_HEADERS', '{}'))
 except Exception:
     TERMINAL_PROXY_HEADERS = {}
 
@@ -490,12 +500,12 @@ CODE_INTERPRETER_PYODIDE_PROMPT = """
 # Vector Database
 ####################################
 
-VECTOR_DB = os.getenv('VECTOR_DB', 'chroma')
+VECTOR_DB = os.getenv('VECTOR_DB', 'pgvector' if USE_SLIM else 'chroma')
 
 # Chroma
 CHROMA_DATA_PATH = f'{DATA_DIR}/vector_db'
 
-if VECTOR_DB == 'chroma':
+if VECTOR_DB == 'chroma' and not USE_SLIM:
     import chromadb
 
     CHROMA_TENANT = os.getenv('CHROMA_TENANT', chromadb.DEFAULT_TENANT)
@@ -636,7 +646,7 @@ SSL_ASSERT_FINGERPRINT = os.getenv('SSL_ASSERT_FINGERPRINT', None)
 ELASTICSEARCH_INDEX_PREFIX = os.getenv('ELASTICSEARCH_INDEX_PREFIX', 'open_webui_collections')
 # Pgvector
 PGVECTOR_DB_URL = os.getenv('PGVECTOR_DB_URL', DATABASE_URL)
-if VECTOR_DB == 'pgvector' and not PGVECTOR_DB_URL.startswith('postgres'):
+if not USE_SLIM and VECTOR_DB == 'pgvector' and not PGVECTOR_DB_URL.startswith('postgres'):
     raise ValueError(
         'Pgvector requires setting PGVECTOR_DB_URL or using Postgres with vector extension as the primary database.'
     )
@@ -731,6 +741,10 @@ else:
     except Exception:
         PGVECTOR_IVFFLAT_LISTS = 100
 
+PGVECTOR_ITERATIVE_SCAN = os.getenv('PGVECTOR_ITERATIVE_SCAN', 'relaxed_order').strip().lower()
+if PGVECTOR_ITERATIVE_SCAN not in ('off', 'relaxed_order', 'strict_order'):
+    PGVECTOR_ITERATIVE_SCAN = 'relaxed_order'
+
 # openGauss
 OPENGAUSS_DB_URL = os.getenv('OPENGAUSS_DB_URL', DATABASE_URL)
 
@@ -797,7 +811,7 @@ ORACLE_DB_POOL_MAX = int(os.getenv('ORACLE_DB_POOL_MAX', 10))
 ORACLE_DB_POOL_INCREMENT = int(os.getenv('ORACLE_DB_POOL_INCREMENT', 1))
 
 
-if VECTOR_DB == 'oracle23ai':
+if not USE_SLIM and VECTOR_DB == 'oracle23ai':
     if not ORACLE_DB_USER or not ORACLE_DB_PASSWORD or not ORACLE_DB_DSN:
         raise ValueError('Oracle23ai requires setting ORACLE_DB_USER, ORACLE_DB_PASSWORD, and ORACLE_DB_DSN.')
     if ORACLE_DB_USE_WALLET and (not ORACLE_WALLET_DIR or not ORACLE_WALLET_PASSWORD):
@@ -805,7 +819,7 @@ if VECTOR_DB == 'oracle23ai':
             'Oracle23ai requires setting ORACLE_WALLET_DIR and ORACLE_WALLET_PASSWORD when using wallet authentication.'
         )
 
-log.info(f'VECTOR_DB: {VECTOR_DB}')
+log.info('VECTOR_DB: %s', VECTOR_DB)
 
 # S3 Vector
 S3_VECTOR_BUCKET_NAME = os.getenv('S3_VECTOR_BUCKET_NAME', None)
@@ -894,8 +908,8 @@ MINERU_API_KEY = os.getenv('MINERU_API_KEY', '')
 
 mineru_params = os.getenv('MINERU_PARAMS', '')
 try:
-    mineru_params = json.loads(mineru_params)
+    mineru_params = JSONCodec.loads(mineru_params)
-except json.JSONDecodeError:
+except JSONCodec.JSONDecodeError:
     mineru_params = {}
 
 MINERU_PARAMS = mineru_params
@@ -908,8 +922,8 @@ EXTERNAL_DOCUMENT_LOADER_API_KEY = os.getenv('EXTERNAL_DOCUMENT_LOADER_API_KEY',
 
 external_document_loader_headers = os.getenv('EXTERNAL_DOCUMENT_LOADER_HEADERS', '')
 try:
-    external_document_loader_headers = json.loads(external_document_loader_headers)
+    external_document_loader_headers = JSONCodec.loads(external_document_loader_headers)
-except json.JSONDecodeError:
+except JSONCodec.JSONDecodeError:
     external_document_loader_headers = {}
 if not isinstance(external_document_loader_headers, dict):
     external_document_loader_headers = {}
@@ -918,14 +932,16 @@ EXTERNAL_DOCUMENT_LOADER_HEADERS = external_document_loader_headers
 
 TIKA_SERVER_URL = os.getenv('TIKA_SERVER_URL', 'http://tika:9998')
 
+TIKA_SERVER_VERSION = os.getenv('TIKA_SERVER_VERSION', '3')
+
 DOCLING_SERVER_URL = os.getenv('DOCLING_SERVER_URL', 'http://docling:5001')
 
 DOCLING_API_KEY = os.getenv('DOCLING_API_KEY', '')
 
 docling_params = os.getenv('DOCLING_PARAMS', '')
 try:
-    docling_params = json.loads(docling_params)
+    docling_params = JSONCodec.loads(docling_params)
-except json.JSONDecodeError:
+except JSONCodec.JSONDecodeError:
     docling_params = {}
 
 DOCLING_PARAMS = docling_params
@@ -966,6 +982,8 @@ RAG_FILE_MAX_COUNT = int(os.getenv('RAG_FILE_MAX_COUNT')) if os.getenv('RAG_FILE
 
 RAG_FILE_MAX_SIZE = int(os.getenv('RAG_FILE_MAX_SIZE')) if os.getenv('RAG_FILE_MAX_SIZE') else None
 
+ENABLE_KNOWLEDGE_FILE_RETENTION = os.getenv('ENABLE_KNOWLEDGE_FILE_RETENTION', 'False').lower() == 'true'
+
 RAG_FILE_CONTENT_SEARCH_MAX_CHARS = int(os.getenv('RAG_FILE_CONTENT_SEARCH_MAX_CHARS', str(64 * 1024 * 1024)))
 
 FILE_IMAGE_COMPRESSION_WIDTH = (
@@ -988,7 +1006,7 @@ PDF_EXTRACT_IMAGES = os.getenv('PDF_EXTRACT_IMAGES', 'False').lower() == 'true'
 PDF_LOADER_MODE = os.getenv('PDF_LOADER_MODE', 'page')
 
 RAG_EMBEDDING_MODEL = os.getenv('RAG_EMBEDDING_MODEL', 'sentence-transformers/all-MiniLM-L6-v2')
-log.info(f'Embedding model set: {RAG_EMBEDDING_MODEL}')
+log.info('Embedding model set: %s', RAG_EMBEDDING_MODEL)
 
 RAG_TOKENIZER_MODEL = os.getenv('RAG_TOKENIZER_MODEL', '')
 
@@ -1016,7 +1034,7 @@ RAG_RERANKING_ENGINE = os.getenv('RAG_RERANKING_ENGINE', '')
 
 RAG_RERANKING_MODEL = os.getenv('RAG_RERANKING_MODEL', '')
 if RAG_RERANKING_MODEL != '':
-    log.info(f'Reranking model set: {RAG_RERANKING_MODEL}')
+    log.info('Reranking model set: %s', RAG_RERANKING_MODEL)
 
 
 RAG_RERANKING_MODEL_AUTO_UPDATE = (
@@ -1100,12 +1118,26 @@ ENABLE_LOCAL_WEB_FETCH = (
 ENABLE_RAG_LOCAL_WEB_FETCH = ENABLE_LOCAL_WEB_FETCH
 
 
+# Operators extend this through WEB_FETCH_FILTER_LIST.
 DEFAULT_WEB_FETCH_FILTER_LIST = [
     '!169.254.169.254',
     '!fd00:ec2::254',
     '!metadata.google.internal',
     '!metadata.azure.com',
     '!100.100.100.200',
+    '!168.63.129.16',  # Azure platform channel, reachable from every Azure VM
+    '!192.88.99.0/24',  # 6to4 relay anycast, deprecated by RFC 7526
+    '!224.0.0.0/4',  # IPv4 multicast
+    '!::ffff:0:0:0/96',  # IPv4-translated (SIIT, RFC 2765), never routed
+    '!64:ff9b:1::/48',  # NAT64 local-use prefix, RFC 8215, not a public destination
+    '!100:0:0:1::/64',  # dummy prefix, RFC 9780
+    '!2001:1::1',  # PCP anycast, RFC 7723, answered by the local network's own edge device
+    '!2001:1::2',  # TURN anycast, RFC 8155, likewise
+    '!2001:20::/28',  # ORCHIDv2, RFC 7343, never routed
+    '!2001:30::/28',  # DRIP, RFC 9374, never routed
+    '!5f00::/16',  # SRv6 SIDs, RFC 9602, internal to one segment routing domain
+    '!fec0::/10',  # IPv6 site-local, deprecated by RFC 3879
+    '!ff00::/8',  # IPv6 multicast
 ]
 
 web_fetch_filter_list = os.getenv('WEB_FETCH_FILTER_LIST', '')
@@ -1148,7 +1180,7 @@ WEB_SEARCH_RESULT_COUNT = int(os.getenv('WEB_SEARCH_RESULT_COUNT', '3'))
 
 
 try:
-    web_search_domain_filter_list = json.loads(os.getenv('WEB_SEARCH_DOMAIN_FILTER_LIST', '[]'))
+    web_search_domain_filter_list = JSONCodec.loads(os.getenv('WEB_SEARCH_DOMAIN_FILTER_LIST', '[]'))
 except Exception as e:
     web_search_domain_filter_list = [
         # "wikipedia.com",
@@ -1244,6 +1276,9 @@ AZURE_AI_SEARCH_ENDPOINT = os.getenv('AZURE_AI_SEARCH_ENDPOINT', '')
 AZURE_AI_SEARCH_INDEX_NAME = os.getenv('AZURE_AI_SEARCH_INDEX_NAME', '')
 
 EXA_API_KEY = os.getenv('EXA_API_KEY', '')
+EXA_MAX_CONTENT_LENGTH = int(os.environ['EXA_MAX_CONTENT_LENGTH']) if os.getenv('EXA_MAX_CONTENT_LENGTH') else None
+if EXA_MAX_CONTENT_LENGTH is not None and EXA_MAX_CONTENT_LENGTH <= 0:
+    raise ValueError('EXA_MAX_CONTENT_LENGTH must be a positive integer or unset')
 
 PERPLEXITY_API_KEY = os.getenv('PERPLEXITY_API_KEY', '')
 
@@ -1267,6 +1302,12 @@ TAVILY_API_KEY = os.getenv('TAVILY_API_KEY', '')
 
 TAVILY_EXTRACT_DEPTH = os.getenv('TAVILY_EXTRACT_DEPTH', 'basic')
 
+STAAN_API_KEY = os.getenv('STAAN_API_KEY', '')
+
+STAAN_MARKET = os.getenv('STAAN_MARKET', 'en-us')
+
+STAAN_MAX_SNIPPETS = int(os.getenv('STAAN_MAX_SNIPPETS', '0'))
+
 PLAYWRIGHT_WS_URL = os.getenv('PLAYWRIGHT_WS_URL', '')
 
 PLAYWRIGHT_TIMEOUT = int(os.getenv('PLAYWRIGHT_TIMEOUT', '10000'))
@@ -1297,8 +1338,8 @@ LINKUP_API_KEY = os.getenv('LINKUP_API_KEY', '')
 
 linkup_search_params = os.getenv('LINKUP_SEARCH_PARAMS', '')
 try:
-    linkup_search_params = json.loads(linkup_search_params)
+    linkup_search_params = JSONCodec.loads(linkup_search_params)
-except json.JSONDecodeError:
+except JSONCodec.JSONDecodeError:
     linkup_search_params = {}
 
 LINKUP_SEARCH_PARAMS = linkup_search_params
@@ -1330,8 +1371,8 @@ AUTOMATIC1111_API_AUTH = os.getenv('AUTOMATIC1111_API_AUTH', '')
 
 automatic1111_params = os.getenv('AUTOMATIC1111_PARAMS', '')
 try:
-    automatic1111_params = json.loads(automatic1111_params)
+    automatic1111_params = JSONCodec.loads(automatic1111_params)
-except json.JSONDecodeError:
+except JSONCodec.JSONDecodeError:
     automatic1111_params = {}
 
 AUTOMATIC1111_PARAMS = automatic1111_params
@@ -1455,8 +1496,8 @@ COMFYUI_WORKFLOW = os.getenv('COMFYUI_WORKFLOW', COMFYUI_DEFAULT_WORKFLOW)
 
 comfyui_workflow_nodes = os.getenv('COMFYUI_WORKFLOW_NODES', '')
 try:
-    comfyui_workflow_nodes = json.loads(comfyui_workflow_nodes)
+    comfyui_workflow_nodes = JSONCodec.loads(comfyui_workflow_nodes)
-except json.JSONDecodeError:
+except JSONCodec.JSONDecodeError:
     comfyui_workflow_nodes = []
 
 COMFYUI_WORKFLOW_NODES = comfyui_workflow_nodes
@@ -1468,8 +1509,8 @@ IMAGES_OPENAI_API_KEY = os.getenv('IMAGES_OPENAI_API_KEY', OPENAI_API_KEY)
 
 images_openai_params = os.getenv('IMAGES_OPENAI_PARAMS', '')
 try:
-    images_openai_params = json.loads(images_openai_params)
+    images_openai_params = JSONCodec.loads(images_openai_params)
-except json.JSONDecodeError:
+except JSONCodec.JSONDecodeError:
     images_openai_params = {}
 
 
@@ -1507,8 +1548,8 @@ IMAGES_EDIT_COMFYUI_WORKFLOW = os.getenv('IMAGES_EDIT_COMFYUI_WORKFLOW', '')
 
 images_edit_comfyui_workflow_nodes = os.getenv('IMAGES_EDIT_COMFYUI_WORKFLOW_NODES', '')
 try:
-    images_edit_comfyui_workflow_nodes = json.loads(images_edit_comfyui_workflow_nodes)
+    images_edit_comfyui_workflow_nodes = JSONCodec.loads(images_edit_comfyui_workflow_nodes)
-except json.JSONDecodeError:
+except JSONCodec.JSONDecodeError:
     images_edit_comfyui_workflow_nodes = []
 
 IMAGES_EDIT_COMFYUI_WORKFLOW_NODES = images_edit_comfyui_workflow_nodes
@@ -1582,8 +1623,8 @@ AUDIO_TTS_OPENAI_API_KEY = os.getenv('AUDIO_TTS_OPENAI_API_KEY', OPENAI_API_KEY)
 
 audio_tts_openai_params = os.getenv('AUDIO_TTS_OPENAI_PARAMS', '')
 try:
-    audio_tts_openai_params = json.loads(audio_tts_openai_params)
+    audio_tts_openai_params = JSONCodec.loads(audio_tts_openai_params)
-except json.JSONDecodeError:
+except JSONCodec.JSONDecodeError:
     audio_tts_openai_params = {}
 
 AUDIO_TTS_OPENAI_PARAMS = audio_tts_openai_params
@@ -1634,46 +1675,17 @@ DEFAULT_MODELS = os.getenv('DEFAULT_MODELS', None)
 
 DEFAULT_PINNED_MODELS = os.getenv('DEFAULT_PINNED_MODELS', None)
 
+# None uses the frontend's localized defaults; an empty list disables suggestions.
 try:
-    default_prompt_suggestions = json.loads(os.getenv('DEFAULT_PROMPT_SUGGESTIONS', '[]'))
+    DEFAULT_PROMPT_SUGGESTIONS = JSONCodec.loads(os.getenv('DEFAULT_PROMPT_SUGGESTIONS', 'null'))
 except Exception as e:
     log.exception(f'Error loading DEFAULT_PROMPT_SUGGESTIONS: {e}')
-    default_prompt_suggestions = []
+    DEFAULT_PROMPT_SUGGESTIONS = None
-if default_prompt_suggestions == []:
-    default_prompt_suggestions = [
-        {
-            'title': ['Help me study', 'vocabulary for a college entrance exam'],
-            'content': "Help me study vocabulary: write a sentence for me to fill in the blank, and I'll try to pick the correct option.",
-        },
-        {
-            'title': ['Give me ideas', "for what to do with my kids' art"],
-            'content': "What are 5 creative things I could do with my kids' art? I don't want to throw them away, but it's also so much clutter.",
-        },
-        {
-            'title': ['Tell me a fun fact', 'about the Roman Empire'],
-            'content': 'Tell me a random fun fact about the Roman Empire',
-        },
-        {
-            'title': ['Show me a code snippet', "of a website's sticky header"],
-            'content': "Show me a code snippet of a website's sticky header in CSS and JavaScript.",
-        },
-        {
-            'title': [
-                'Explain options trading',
-                "if I'm familiar with buying and selling stocks",
-            ],
-            'content': "Explain options trading in simple terms if I'm familiar with buying and selling stocks.",
-        },
-        {
-            'title': ['Overcome procrastination', 'give me tips'],
-            'content': 'Could you start by asking me about instances when I procrastinate the most and then give me some suggestions to overcome it?',
-        },
-    ]
 
-DEFAULT_PROMPT_SUGGESTIONS = default_prompt_suggestions
+DEFAULT_PROMPT_SUGGESTIONS_I18N = {}
 
 try:
-    model_order_list = json.loads(os.getenv('MODEL_ORDER_LIST', '[]'))
+    model_order_list = JSONCodec.loads(os.getenv('MODEL_ORDER_LIST', '[]'))
 except Exception as e:
     log.exception(f'Error loading MODEL_ORDER_LIST: {e}')
     model_order_list = []
@@ -1681,7 +1693,7 @@ except Exception as e:
 MODEL_ORDER_LIST = model_order_list
 
 try:
-    default_model_metadata = json.loads(os.getenv('DEFAULT_MODEL_METADATA', '{}'))
+    default_model_metadata = JSONCodec.loads(os.getenv('DEFAULT_MODEL_METADATA', '{}'))
 except Exception as e:
     log.exception(f'Error loading DEFAULT_MODEL_METADATA: {e}')
     default_model_metadata = {}
@@ -1689,13 +1701,22 @@ except Exception as e:
 DEFAULT_MODEL_METADATA = default_model_metadata
 
 try:
-    default_model_params = json.loads(os.getenv('DEFAULT_MODEL_PARAMS', '{}'))
+    default_model_params = JSONCodec.loads(os.getenv('DEFAULT_MODEL_PARAMS', '{}'))
 except Exception as e:
     log.exception(f'Error loading DEFAULT_MODEL_PARAMS: {e}')
     default_model_params = {}
 
 DEFAULT_MODEL_PARAMS = default_model_params
 
+
+try:
+    default_interface_settings = JSONCodec.loads(os.getenv('DEFAULT_INTERFACE_SETTINGS', '{}'))
+except Exception as e:
+    log.exception(f'Error loading DEFAULT_INTERFACE_SETTINGS: {e}')
+    default_interface_settings = {}
+
+DEFAULT_INTERFACE_SETTINGS = default_interface_settings if isinstance(default_interface_settings, dict) else {}
+
 DEFAULT_USER_ROLE = os.getenv('DEFAULT_USER_ROLE', 'pending')
 
 DEFAULT_GROUP_ID = os.getenv('DEFAULT_GROUP_ID', '')
@@ -2032,7 +2053,7 @@ ENABLE_USER_STATUS = os.getenv('ENABLE_USER_STATUS', 'True').lower() == 'true'
 
 ENABLE_EVALUATION_ARENA_MODELS = os.getenv('ENABLE_EVALUATION_ARENA_MODELS', 'True').lower() == 'true'
 try:
-    evaluation_arena_models = json.loads(os.getenv('EVALUATION_ARENA_MODELS', '[]'))
+    evaluation_arena_models = JSONCodec.loads(os.getenv('EVALUATION_ARENA_MODELS', '[]'))
     if not isinstance(evaluation_arena_models, list) or not all(
         isinstance(model, dict) for model in evaluation_arena_models
     ):
@@ -2047,6 +2068,9 @@ DEFAULT_ARENA_MODEL = {
     'id': 'arena-model',
     'name': 'Arena Model',
     'meta': {
+        # LICENSE covers this Open WebUI fallback logo.
+        # Do not alter, remove, obscure, or replace it except as LICENSE permits:
+        # https://docs.openwebui.com/license.
         'profile_image_url': '/favicon.png',
         'description': 'Submit your questions to anonymous AI chatbots and vote on the best response.',
         'model_ids': None,
@@ -2067,8 +2091,6 @@ BYPASS_ADMIN_ACCESS_CONTROL = (
     == 'true'
 )
 
-ENABLE_ADMIN_CHAT_ACCESS = os.getenv('ENABLE_ADMIN_CHAT_ACCESS', 'True').lower() == 'true'
-
 ENABLE_ADMIN_ANALYTICS = os.getenv('ENABLE_ADMIN_ANALYTICS', 'True').lower() == 'true'
 
 ENABLE_COMMUNITY_SHARING = os.getenv('ENABLE_COMMUNITY_SHARING', 'True').lower() == 'true'
@@ -2079,6 +2101,7 @@ ENABLE_USER_WEBHOOKS = os.getenv('ENABLE_USER_WEBHOOKS', 'False').lower() == 'tr
 
 # FastAPI / AnyIO settings
 THREAD_POOL_SIZE = os.getenv('THREAD_POOL_SIZE', None)
+THREAD_POOL_THREAD_NAME_PREFIX = os.getenv('THREAD_POOL_THREAD_NAME_PREFIX', '')
 
 if THREAD_POOL_SIZE is not None and isinstance(THREAD_POOL_SIZE, str):
     try:
@@ -2125,6 +2148,7 @@ else:
 
 
 class BannerModel(BaseModel):
+    i18n: dict[str, dict[str, str]] | None = None
     id: str
     type: str
     title: str | None = None
@@ -2134,7 +2158,7 @@ class BannerModel(BaseModel):
 
 
 try:
-    banners = json.loads(os.getenv('WEBUI_BANNERS', '[]'))
+    banners = JSONCodec.loads(os.getenv('WEBUI_BANNERS', '[]'))
     banners = [BannerModel(**banner) for banner in banners]
 except Exception as e:
     log.exception(f'Error loading WEBUI_BANNERS: {e}')
@@ -2157,10 +2181,20 @@ TASK_MODEL = os.getenv('TASK_MODEL', '')
 
 TASK_MODEL_EXTERNAL = os.getenv('TASK_MODEL_EXTERNAL', '')
 
+try:
+    task_model_params = JSONCodec.loads(os.getenv('TASK_MODEL_PARAMS', '{}'))
+except Exception as e:
+    log.exception(f'Error loading TASK_MODEL_PARAMS: {e}')
+    task_model_params = {}
+
+TASK_MODEL_PARAMS = task_model_params
+
 CONTEXT_COMPACTION_MODEL = os.getenv('CONTEXT_COMPACTION_MODEL', '')
 
 ENABLE_CONTEXT_COMPACTION = os.getenv('ENABLE_CONTEXT_COMPACTION', 'False').lower() == 'true'
 
+ENABLE_TOOL_PERMISSIONS = os.getenv('ENABLE_TOOL_PERMISSIONS', 'False').lower() == 'true'
+
 CONTEXT_COMPACTION_TOKEN_THRESHOLD = int(os.getenv('CONTEXT_COMPACTION_TOKEN_THRESHOLD', '80000'))
 
 _CONTEXT_COMPACTION_TOKEN_CAP = os.getenv('CONTEXT_COMPACTION_TOKEN_CAP')
@@ -2470,12 +2504,12 @@ GOOGLE_OAUTH_AUTHORIZE_PARAMS = {}
 _google_oauth_authorize_params = os.getenv('GOOGLE_OAUTH_AUTHORIZE_PARAMS', '')
 if _google_oauth_authorize_params:
     try:
-        _parsed = json.loads(_google_oauth_authorize_params)
+        _parsed = JSONCodec.loads(_google_oauth_authorize_params)
         if isinstance(_parsed, dict):
             GOOGLE_OAUTH_AUTHORIZE_PARAMS = _parsed
         else:
             log.warning('GOOGLE_OAUTH_AUTHORIZE_PARAMS must be a JSON object, ignoring')
-    except (json.JSONDecodeError, TypeError):
+    except (JSONCodec.JSONDecodeError, TypeError):
         log.warning('GOOGLE_OAUTH_AUTHORIZE_PARAMS is not valid JSON, ignoring')
 
 MICROSOFT_CLIENT_ID = os.getenv('MICROSOFT_CLIENT_ID', '')
@@ -2590,12 +2624,12 @@ OAUTH_AUTHORIZE_PARAMS = {}
 _oauth_authorize_params = os.getenv('OAUTH_AUTHORIZE_PARAMS', '')
 if _oauth_authorize_params:
     try:
-        _parsed = json.loads(_oauth_authorize_params)
+        _parsed = JSONCodec.loads(_oauth_authorize_params)
         if isinstance(_parsed, dict):
             OAUTH_AUTHORIZE_PARAMS = _parsed
         else:
             log.warning('OAUTH_AUTHORIZE_PARAMS must be a JSON object, ignoring')
-    except (json.JSONDecodeError, TypeError):
+    except (JSONCodec.JSONDecodeError, TypeError):
         log.warning('OAUTH_AUTHORIZE_PARAMS is not valid JSON, ignoring')
 
 
@@ -2787,6 +2821,7 @@ LDAP_ATTRIBUTE_FOR_GROUPS = os.getenv('LDAP_ATTRIBUTE_FOR_GROUPS', 'memberOf')
 
 DEFAULT_CONFIG = {
     'direct.enable': ENABLE_DIRECT_CONNECTIONS,
+    'direct.integrations.enable': ENABLE_DIRECT_INTEGRATIONS,
     'ollama.enable': ENABLE_OLLAMA_API,
     'ollama.base_urls': OLLAMA_BASE_URLS,
     'ollama.api_configs': OLLAMA_API_CONFIGS,
@@ -2848,6 +2883,7 @@ DEFAULT_CONFIG = {
     'rag.external_document_loader_api_key': EXTERNAL_DOCUMENT_LOADER_API_KEY,
     'rag.external_document_loader_headers': EXTERNAL_DOCUMENT_LOADER_HEADERS,
     'rag.tika_server_url': TIKA_SERVER_URL,
+    'rag.tika_server_version': TIKA_SERVER_VERSION,
     'rag.docling_server_url': DOCLING_SERVER_URL,
     'rag.docling_api_key': DOCLING_API_KEY,
     'rag.docling_params': DOCLING_PARAMS,
@@ -2950,6 +2986,7 @@ DEFAULT_CONFIG = {
     'web.search.azure_ai_search_endpoint': AZURE_AI_SEARCH_ENDPOINT,
     'web.search.azure_ai_search_index_name': AZURE_AI_SEARCH_INDEX_NAME,
     'web.search.exa_api_key': EXA_API_KEY,
+    'web.search.exa_max_content_length': EXA_MAX_CONTENT_LENGTH,
     'web.search.perplexity_api_key': PERPLEXITY_API_KEY,
     'web.search.perplexity_model': PERPLEXITY_MODEL,
     'web.search.perplexity_search_context_usage': PERPLEXITY_SEARCH_CONTEXT_USAGE,
@@ -2961,6 +2998,9 @@ DEFAULT_CONFIG = {
     'web.search.sougou_api_sk': SOUGOU_API_SK,
     'web.search.tavily_api_key': TAVILY_API_KEY,
     'web.search.tavily_extract_depth': TAVILY_EXTRACT_DEPTH,
+    'web.search.staan_api_key': STAAN_API_KEY,
+    'web.search.staan_market': STAAN_MARKET,
+    'web.search.staan_max_snippets': STAAN_MAX_SNIPPETS,
     'web.loader.playwright_ws_url': PLAYWRIGHT_WS_URL,
     'web.loader.playwright_timeout': PLAYWRIGHT_TIMEOUT,
     'web.loader.firecrawl_api_key': FIRECRAWL_API_KEY,
@@ -3046,7 +3086,10 @@ DEFAULT_CONFIG = {
     'ui.default_locale': DEFAULT_LOCALE,
     'ui.default_models': DEFAULT_MODELS,
     'ui.default_pinned_models': DEFAULT_PINNED_MODELS,
+    'ui.default_interface_settings': DEFAULT_INTERFACE_SETTINGS,
+    'ui.i18n': {},
     'ui.prompt_suggestions': DEFAULT_PROMPT_SUGGESTIONS,
+    'ui.prompt_suggestions_i18n': DEFAULT_PROMPT_SUGGESTIONS_I18N,
     'ui.model_order_list': MODEL_ORDER_LIST,
     'models.default_metadata': DEFAULT_MODEL_METADATA,
     'models.default_params': DEFAULT_MODEL_PARAMS,
@@ -3085,12 +3128,14 @@ DEFAULT_CONFIG = {
     'auth.admin.email': ADMIN_EMAIL,
     'task.model.default': TASK_MODEL,
     'task.model.external': TASK_MODEL_EXTERNAL,
+    'task.model.params': TASK_MODEL_PARAMS,
     'chat.context_compaction.model': CONTEXT_COMPACTION_MODEL,
     'chat.context_compaction.enable': ENABLE_CONTEXT_COMPACTION,
     'chat.context_compaction.token_threshold': CONTEXT_COMPACTION_TOKEN_THRESHOLD,
     'chat.context_compaction.token_cap': CONTEXT_COMPACTION_TOKEN_CAP,
     'chat.context_compaction.retention_percentage': CONTEXT_COMPACTION_RETENTION_PERCENTAGE,
     'chat.context_compaction.prompt_template': CONTEXT_COMPACTION_PROMPT_TEMPLATE,
+    'chat.tool_permissions.enable': ENABLE_TOOL_PERMISSIONS,
     'task.title.prompt_template': TITLE_GENERATION_PROMPT_TEMPLATE,
     'task.tags.prompt_template': TAGS_GENERATION_PROMPT_TEMPLATE,
     'task.image.prompt_template': IMAGE_PROMPT_GENERATION_PROMPT_TEMPLATE,

backend/open_webui/constants.py

@@ -3,7 +3,6 @@ from __future__ import annotations
 import errno
 from enum import Enum
 
-
 _ERRNO_MESSAGES = {
     errno.ENAMETOOLONG: 'File name is too long.',
     errno.ENOSPC: 'The server is out of storage space.',
@@ -99,7 +98,7 @@ class ERROR_MESSAGES(str, Enum):
 
     INVALID_URL = 'The URL you provided is invalid. Please double-check and try again.'
 
-    WEB_SEARCH_ERROR = lambda err='': err if err else 'Something went wrong while searching the web.'
+    WEB_SEARCH_ERROR = 'Something went wrong while searching the web.'
 
     OLLAMA_API_DISABLED = 'The Ollama API is disabled. Please enable it to use this feature.'
 
@@ -118,9 +117,16 @@ class ERROR_MESSAGES(str, Enum):
     AUTOMATION_TOO_FREQUENT = lambda interval='': f'Schedule too frequent. Minimum interval is {interval} seconds.'
     AUTOMATION_INVALID_RRULE = lambda err='': f'Invalid RRULE: {err}'
     AUTOMATION_NO_FUTURE_RUNS = 'RRULE has no future occurrences'
+    AUTOMATION_COUNT_REQUIRES_DTSTART = (
+        'RRULE with COUNT requires an explicit DTSTART line to anchor the occurrence window'
+    )
+    CALENDAR_RRULE_TOO_FREQUENT = 'Recurring events cannot repeat more often than daily'
 
     FEATURE_DISABLED = lambda name='': f'{name} is disabled'
     INPUT_TOO_LONG = lambda size='': f'Input prompt exceeds maximum length of {size}'
+    # LICENSE covers this Open WebUI error identifier.
+    # Do not alter, remove, obscure, or replace it except as LICENSE permits:
+    # https://docs.openwebui.com/license.
     SERVER_CONNECTION_ERROR = 'Open WebUI: Server Connection Error'
     REQUIRED_FIELD_EMPTY = lambda name='': f'Required field {name} is empty'
     OAUTH_NOT_CONFIGURED = lambda name='': f"Provider '{name}' is not configured"

backend/open_webui/env.py

@@ -7,7 +7,9 @@ import pkgutil
 import re
 import shutil
 import sys
+import threading
 import traceback
+from contextlib import nullcontext
 from pathlib import Path
 from typing import Any, Optional
 from uuid import uuid4
@@ -40,12 +42,13 @@ except ImportError:
     print('dotenv not installed, skipping...')
 
 DOCKER = os.getenv('DOCKER', 'False').lower() == 'true'
+USE_SLIM = os.getenv('USE_SLIM_DOCKER', 'False').lower() == 'true'
 
 USE_CUDA = os.getenv('USE_CUDA_DOCKER', 'false')
 DEVICE_TYPE = 'cpu'
 _cuda_error: Optional[str] = None
 
-if USE_CUDA.lower() == 'true':
+if not USE_SLIM and USE_CUDA.lower() == 'true':
     try:
         import torch  # noqa: E402
 
@@ -57,7 +60,7 @@ if USE_CUDA.lower() == 'true':
         os.environ['USE_CUDA_DOCKER'] = 'false'
         USE_CUDA = 'false'
 
-if sys.platform == 'darwin' and DEVICE_TYPE == 'cpu':
+if not USE_SLIM and sys.platform == 'darwin' and DEVICE_TYPE == 'cpu':
     try:
         import torch  # noqa: E402
 
@@ -66,6 +69,9 @@ if sys.platform == 'darwin' and DEVICE_TYPE == 'cpu':
     except Exception:
         pass
 
+# Torch MPS inference is not thread-safe and a concurrent call kills the whole process.
+MPS_INFERENCE_LOCK = threading.Lock() if DEVICE_TYPE == 'mps' else nullcontext()
+
 ####################################
 # LOGGING
 ####################################
@@ -227,7 +233,7 @@ if FROM_INIT_PY:
 
     # Check if the data directory exists in the package directory
     if DATA_DIR.exists() and DATA_DIR != NEW_DATA_DIR:
-        log.info(f'Moving {DATA_DIR} to {NEW_DATA_DIR}')
+        log.info('Moving %s to %s', DATA_DIR, NEW_DATA_DIR)
         for item in DATA_DIR.iterdir():
             dest = NEW_DATA_DIR / item.name
             if item.is_dir():
@@ -245,8 +251,6 @@ if FROM_INIT_PY:
 
 STATIC_DIR = Path(os.getenv('STATIC_DIR', OPEN_WEBUI_DIR / 'static'))
 
-FONTS_DIR = Path(os.getenv('FONTS_DIR', OPEN_WEBUI_DIR / 'static' / 'fonts'))
-
 FRONTEND_BUILD_DIR = Path(os.getenv('FRONTEND_BUILD_DIR', BASE_DIR / 'build')).resolve()
 
 if FROM_INIT_PY:
@@ -353,20 +357,23 @@ DATABASE_SQLITE_PRAGMA_MMAP_SIZE = os.getenv('DATABASE_SQLITE_PRAGMA_MMAP_SIZE',
 # truncated.  67108864 ≈ 64 MB.  Set to -1 for no limit (SQLite default).
 DATABASE_SQLITE_PRAGMA_JOURNAL_SIZE_LIMIT = os.getenv('DATABASE_SQLITE_PRAGMA_JOURNAL_SIZE_LIMIT', '67108864')
 
-DATABASE_USER_ACTIVE_STATUS_UPDATE_INTERVAL = os.getenv('DATABASE_USER_ACTIVE_STATUS_UPDATE_INTERVAL', None)
+# Seconds between presence writes per user per worker; keep under the 180s active-user window. 0 disables.
-if DATABASE_USER_ACTIVE_STATUS_UPDATE_INTERVAL is not None:
+try:
-    try:
+    DATABASE_USER_ACTIVE_STATUS_UPDATE_INTERVAL = float(os.getenv('DATABASE_USER_ACTIVE_STATUS_UPDATE_INTERVAL', '60'))
-        DATABASE_USER_ACTIVE_STATUS_UPDATE_INTERVAL = float(DATABASE_USER_ACTIVE_STATUS_UPDATE_INTERVAL)
+except ValueError:
-    except Exception:
+    DATABASE_USER_ACTIVE_STATUS_UPDATE_INTERVAL = 60.0
-        DATABASE_USER_ACTIVE_STATUS_UPDATE_INTERVAL = 0.0
 
 DATABASE_ENABLE_SESSION_SHARING = os.getenv('DATABASE_ENABLE_SESSION_SHARING', 'False').lower() == 'true'
 ENABLE_PUBLIC_ACTIVE_USERS_COUNT = os.getenv('ENABLE_PUBLIC_ACTIVE_USERS_COUNT', 'True').lower() == 'true'
 RESET_CONFIG_ON_START = os.getenv('RESET_CONFIG_ON_START', 'False').lower() == 'true'
 ENABLE_REALTIME_CHAT_SAVE = os.getenv('ENABLE_REALTIME_CHAT_SAVE', 'False').lower() == 'true'
 ENABLE_QUERIES_CACHE = os.getenv('ENABLE_QUERIES_CACHE', 'False').lower() == 'true'
+ENABLE_ADMIN_CHAT_ACCESS = os.getenv('ENABLE_ADMIN_CHAT_ACCESS', 'True').lower() == 'true'
 RAG_SYSTEM_CONTEXT = os.getenv('RAG_SYSTEM_CONTEXT', 'False').lower() == 'true'
 
+# Empty by default: chunk metadata also holds internal bookkeeping (file hashes, collection names, scores).
+RAG_SOURCE_METADATA_KEYS = [key.strip() for key in os.getenv('RAG_SOURCE_METADATA_KEYS', '').split(',') if key.strip()]
+
 ####################################
 # REDIS
 ####################################
@@ -376,6 +383,19 @@ REDIS_CLUSTER = os.getenv('REDIS_CLUSTER', 'False').lower() == 'true'
 
 REDIS_KEY_PREFIX = os.getenv('REDIS_KEY_PREFIX', 'open-webui')
 
+try:
+    REDIS_RESPONSE_STREAM_TTL = int(os.getenv('REDIS_RESPONSE_STREAM_TTL', '3600'))
+except ValueError:
+    REDIS_RESPONSE_STREAM_TTL = 3600
+
+# Seconds a task survives without a heartbeat. 0 disables expiry.
+try:
+    REDIS_TASK_TTL = int(os.getenv('REDIS_TASK_TTL', '300'))
+    if REDIS_TASK_TTL != 0 and REDIS_TASK_TTL < 60:
+        REDIS_TASK_TTL = 300
+except ValueError:
+    REDIS_TASK_TTL = 300
+
 REDIS_SENTINEL_HOSTS = os.getenv('REDIS_SENTINEL_HOSTS', '')
 REDIS_SENTINEL_PORT = os.getenv('REDIS_SENTINEL_PORT', '26379')
 
@@ -443,6 +463,9 @@ try:
 except (ValueError, TypeError):
     UVICORN_WORKERS = 1
 
+# tiny delta-stream frames make per-frame websocket compression CPU-bound, allow opting out (true/false)
+UVICORN_WS_PER_MESSAGE_DEFLATE = os.getenv('UVICORN_WS_PER_MESSAGE_DEFLATE', 'True').lower() == 'true'
+
 ####################################
 # WEBSOCKET SUPPORT
 ####################################
@@ -499,6 +522,15 @@ try:
 except ValueError:
     WEBSOCKET_SERVER_PING_INTERVAL = 25
 
+WEBSOCKET_HEARTBEAT_INTERVAL = os.getenv('WEBSOCKET_HEARTBEAT_INTERVAL', '')
+if WEBSOCKET_HEARTBEAT_INTERVAL == '':
+    WEBSOCKET_HEARTBEAT_INTERVAL = None
+else:
+    try:
+        WEBSOCKET_HEARTBEAT_INTERVAL = min(max(int(WEBSOCKET_HEARTBEAT_INTERVAL), 5), 90)
+    except ValueError:
+        WEBSOCKET_HEARTBEAT_INTERVAL = 30
+
 WEBSOCKET_EVENT_CALLER_TIMEOUT = os.getenv('WEBSOCKET_EVENT_CALLER_TIMEOUT', '')
 
 if WEBSOCKET_EVENT_CALLER_TIMEOUT == '':
@@ -571,6 +603,8 @@ def _parse_ssl_env(value: str) -> 'bool | _ssl.SSLContext':
 
 REQUESTS_VERIFY = os.getenv('REQUESTS_VERIFY', 'True').lower() == 'true'
 
+TAVILY_API_BASE_URL = os.getenv('TAVILY_API_BASE_URL', 'https://api.tavily.com').rstrip('/')
+
 _aiohttp_timeout_raw = os.getenv('AIOHTTP_CLIENT_TIMEOUT', '')
 try:
     AIOHTTP_CLIENT_TIMEOUT = int(_aiohttp_timeout_raw) if _aiohttp_timeout_raw else None
@@ -602,6 +636,18 @@ SEARXNG_CLIENT_KEY_FILE = os.getenv('SEARXNG_CLIENT_KEY_FILE', '').strip()
 # When False (default), outbound HTTP requests do not follow 3xx redirects.
 AIOHTTP_CLIENT_ALLOW_REDIRECTS = os.getenv('AIOHTTP_CLIENT_ALLOW_REDIRECTS', 'False').lower() == 'true'
 
+# Opt-in c-ares DNS resolution (aiodns). Off by default: c-ares breaks name
+# resolution in some environments (#28013, #28215). Must run before any
+# TCPConnector is constructed.
+AIOHTTP_CLIENT_ASYNC_DNS_RESOLVER = os.getenv('AIOHTTP_CLIENT_ASYNC_DNS_RESOLVER', 'False').lower() == 'true'
+
+if not AIOHTTP_CLIENT_ASYNC_DNS_RESOLVER:
+    import aiohttp
+
+    aiohttp.DefaultResolver = aiohttp.resolver.ThreadedResolver  # for plugin code
+    aiohttp.resolver.DefaultResolver = aiohttp.resolver.ThreadedResolver
+    aiohttp.connector.DefaultResolver = aiohttp.resolver.ThreadedResolver
+
 # Optional User-Agent override for outbound web-loader fetches.  When set,
 # SafeWebBaseLoader sends this value instead of the default python-requests UA
 # which is aggressively blocked by Cloudflare, Wikipedia, and similar services.
@@ -791,6 +837,16 @@ BYPASS_RETRIEVAL_ACCESS_CONTROL = os.getenv('BYPASS_RETRIEVAL_ACCESS_CONTROL', '
 # for non-admin users.  When False (default), unknown collection names are
 # denied — closing the legacy unscoped namespace.
 ENABLE_RETRIEVAL_UNSCOPED_COLLECTIONS = os.getenv('ENABLE_RETRIEVAL_UNSCOPED_COLLECTIONS', 'False').lower() == 'true'
+
+# Falls back to the upload size limit, because a document cannot legitimately carry more metadata
+# than the file itself is allowed to be. Left unbounded, a small archive that expands enormously
+# during extraction can exhaust memory. RAG_FILE_MAX_SIZE is in MB.
+RAG_METADATA_MAX_VALUE_CHARS = (
+    int(os.getenv('RAG_METADATA_MAX_VALUE_CHARS'))
+    if os.getenv('RAG_METADATA_MAX_VALUE_CHARS')
+    else ((int(os.getenv('RAG_FILE_MAX_SIZE', '0')) or 0) * 1024 * 1024 or None)
+)
+
 MINERU_MAX_MARKDOWN_BYTES = (
     int(os.getenv('MINERU_MAX_MARKDOWN_BYTES')) if os.getenv('MINERU_MAX_MARKDOWN_BYTES') else None
 )
@@ -798,7 +854,7 @@ MINERU_MAX_MARKDOWN_BYTES = (
 # When enabled, skips pydub-based preprocessing (format conversion, compression,
 # and chunked splitting) before sending files to processing engines. Useful when
 # the upstream provider handles these steps or when ffmpeg is unavailable.
-BYPASS_PYDUB_PREPROCESSING = os.getenv('BYPASS_PYDUB_PREPROCESSING', 'False').lower() == 'true'
+BYPASS_PYDUB_PREPROCESSING = USE_SLIM or os.getenv('BYPASS_PYDUB_PREPROCESSING', 'False').lower() == 'true'
 
 # When disabled (default), the OpenAI catch-all proxy endpoint (/{path:path})
 # is blocked. Enable only if you need direct passthrough to upstream OpenAI-
@@ -888,10 +944,18 @@ if LICENSE_PUBLIC_KEY:
 # WEBUI Identity
 ####################################
 
+# LICENSE covers this Open WebUI branding surface, including name, logo,
+# visual, textual, symbolic identifiers, metadata, and surrounding UI.
+# Do not alter, remove, obscure, or replace it except as LICENSE permits:
+# https://docs.openwebui.com/license.
 WEBUI_NAME = os.getenv('WEBUI_NAME', 'Open WebUI')
 if WEBUI_NAME != 'Open WebUI':
     WEBUI_NAME += ' (Open WebUI)'
 
+# LICENSE covers this Open WebUI branding surface, including this favicon
+# and any visual, textual, or symbolic identifiers it preserves.
+# Do not alter, remove, obscure, or replace it except as LICENSE permits:
+# https://docs.openwebui.com/license.
 WEBUI_FAVICON_URL = 'https://openwebui.com/favicon.png'
 WEBUI_BUILD_HASH = os.getenv('WEBUI_BUILD_HASH', 'dev-build')
 TRUSTED_SIGNATURE_KEY = os.getenv('TRUSTED_SIGNATURE_KEY', '')
@@ -930,6 +994,7 @@ FORWARD_USER_INFO_HEADER_USER_NAME = os.getenv('FORWARD_USER_INFO_HEADER_USER_NA
 FORWARD_USER_INFO_HEADER_USER_ID = os.getenv('FORWARD_USER_INFO_HEADER_USER_ID', 'X-OpenWebUI-User-Id')
 FORWARD_USER_INFO_HEADER_USER_EMAIL = os.getenv('FORWARD_USER_INFO_HEADER_USER_EMAIL', 'X-OpenWebUI-User-Email')
 FORWARD_USER_INFO_HEADER_USER_ROLE = os.getenv('FORWARD_USER_INFO_HEADER_USER_ROLE', 'X-OpenWebUI-User-Role')
+FORWARD_USER_INFO_HEADER_AUTH_TYPE = os.getenv('FORWARD_USER_INFO_HEADER_AUTH_TYPE', 'X-OpenWebUI-Auth-Type')
 FORWARD_SESSION_INFO_HEADER_MESSAGE_ID = os.getenv('FORWARD_SESSION_INFO_HEADER_MESSAGE_ID', 'X-OpenWebUI-Message-Id')
 FORWARD_SESSION_INFO_HEADER_CHAT_ID = os.getenv('FORWARD_SESSION_INFO_HEADER_CHAT_ID', 'X-OpenWebUI-Chat-Id')
 
@@ -948,6 +1013,10 @@ except ValueError:
 # Progressive Web App
 ####################################
 
+# LICENSE covers this install-time Open WebUI branding surface, including
+# names, logos, manifests, metadata, and surrounding UI.
+# Do not alter, remove, obscure, or replace it except as LICENSE permits:
+# https://docs.openwebui.com/license.
 EXTERNAL_PWA_MANIFEST_URL = os.getenv('EXTERNAL_PWA_MANIFEST_URL', None)
 
 ####################################
@@ -984,6 +1053,13 @@ ENABLE_CHAT_RESPONSE_BASE64_IMAGE_URL_CONVERSION = (
 )
 ENABLE_API_OUTLET_FILTERS = os.getenv('ENABLE_API_OUTLET_FILTERS', 'True').lower() == 'true'
 
+# Opt in to CPython's in-place string append optimization for streamed responses.
+# Off by default for a staged rollout. Only a host already out of memory can lose
+# text here; the default path (a full copy per chunk) raises there too.
+ENABLE_CHAT_RESPONSE_STREAM_INPLACE_APPEND = (
+    os.getenv('ENABLE_CHAT_RESPONSE_STREAM_INPLACE_APPEND', 'False').lower() == 'true'
+)
+
 # When enabled, uses a hardcoded extension-to-MIME dictionary as a last-resort
 # fallback when both mimetypes.guess_type() and file.meta.content_type fail to
 # determine the content type. This can help on minimal container images (e.g.

backend/open_webui/events.py

@@ -411,6 +411,11 @@ class EventDefinitions(BaseModel):
         description='Retrieval content was processed.',
         message='Retrieval Content processed',
     )
+    RETRIEVAL_CONTENT_PROCESS_FAILED: EventDefinition = EventDefinition(
+        name='retrieval.content.process_failed',
+        description='Retrieval content processing failed.',
+        message='Retrieval Content process failed',
+    )
     RETRIEVAL_COLLECTION_DELETED: EventDefinition = EventDefinition(
         name='retrieval.collection.deleted',
         description='A retrieval collection was deleted.',
@@ -666,6 +671,7 @@ NOTIFICATION_EVENTS = (
     EVENTS.CHAT_FAILED.name,
     EVENTS.CHANNEL_MESSAGE.name,
     EVENTS.CALENDAR_ALERT.name,
+    EVENTS.RETRIEVAL_CONTENT_PROCESS_FAILED.name,
 )
 
 
@@ -1026,6 +1032,9 @@ def build_event(
 
 
 async def dispatch_webhook_event(app: Any, event: Event) -> None:
+    # LICENSE covers this Open WebUI webhook identifier.
+    # Do not alter, remove, obscure, or replace it except as LICENSE permits:
+    # https://docs.openwebui.com/license.
     name = getattr(getattr(app, 'state', None), 'WEBUI_NAME', 'Open WebUI')
     subject = event.subject or {}
     subject_id = subject.get('id')
@@ -1077,6 +1086,20 @@ class NotificationEventSink:
             schedule_notification_dispatch(app, event)
 
 
+class SocketSessionEventSink:
+    async def handle_event(self, app: Any, event: Event, request: Any | None = None) -> None:
+        if event.event not in {EVENTS.USER_DELETED.name, EVENTS.USER_ROLE_UPDATED.name}:
+            return
+
+        subject = event.subject or {}
+        if subject.get('type') != 'user' or not subject.get('id'):
+            return
+
+        from open_webui.socket.main import disconnect_user_sessions
+
+        await disconnect_user_sessions(str(subject['id']))
+
+
 async def dispatch_event_functions(
     app: Any, event: Event, request: Any | None = None, extra_function_ids: list[str] | None = None
 ) -> None:
@@ -1145,7 +1168,7 @@ class EventFunctionSink:
         schedule_event_function_dispatch(app, event, request)
 
 
-EVENT_SINKS = [EventFunctionSink(), WebhookEventSink(), NotificationEventSink()]
+EVENT_SINKS = [SocketSessionEventSink(), EventFunctionSink(), WebhookEventSink(), NotificationEventSink()]
 
 
 async def publish_event(

backend/open_webui/functions.py

@@ -1,6 +1,5 @@
 import asyncio
 import inspect
-import json
 import logging
 import sys
 from typing import AsyncGenerator, Generator, Iterator
@@ -29,6 +28,7 @@ from open_webui.socket.main import (
     get_event_emitter,
 )
 from open_webui.utils.access_control import check_model_access
+from open_webui.utils.json_codec import JSONCodec
 from open_webui.utils.misc import (
     add_or_update_system_message,
     get_last_user_message,
@@ -100,7 +100,7 @@ async def get_function_models(request):
                     log.exception(e)
                     sub_pipes = []
 
-                log.debug(f"get_function_models: function '{pipe.id}' is a manifold of {sub_pipes}")
+                log.debug("get_function_models: function '%s' is a manifold of %s", pipe.id, sub_pipes)
 
                 for p in sub_pipes:
                     sub_pipe_id = f'{pipe.id}.{p["id"]}'
@@ -126,7 +126,10 @@ async def get_function_models(request):
                 pipe_flag = {'type': 'pipe'}
 
                 log.debug(
-                    f"get_function_models: function '{pipe.id}' is a single pipe {{ 'id': {pipe.id}, 'name': {pipe.name} }}"
+                    "get_function_models: function '%s' is a single pipe { 'id': %s, 'name': %s }",
+                    pipe.id,
+                    pipe.id,
+                    pipe.name,
                 )
 
                 pipe_models.append(
@@ -170,7 +173,7 @@ async def generate_function_chat_completion(request, form_data, user, models: di
             line = line.model_dump_json()
             line = f'data: {line}'
         if isinstance(line, dict):
-            line = f'data: {json.dumps(line)}'
+            line = f'data: {JSONCodec.dumps(line)}'
 
         try:
             line = line.decode('utf-8')
@@ -181,7 +184,7 @@ async def generate_function_chat_completion(request, form_data, user, models: di
             return f'{line}\n\n'
         else:
             line = openai_chat_chunk_message_template(form_data['model'], line)
-            return f'data: {json.dumps(line)}\n\n'
+            return f'data: {JSONCodec.dumps(line)}\n\n'
 
     def get_pipe_id(form_data: dict) -> str:
         pipe_id = form_data['model']
@@ -209,6 +212,9 @@ async def generate_function_chat_completion(request, form_data, user, models: di
 
         return params
 
+    # Set server-side by utils/chat.py, never by client input. Mirrors the routers.
+    bypass_system_prompt = getattr(request.state, 'bypass_system_prompt', False)
+
     # Copy so the base-model substitution below doesn't leak into the caller's
     # payload, which the tool-call continuation re-submits. Mirrors the routers.
     form_data = {**form_data}
@@ -288,7 +294,8 @@ async def generate_function_chat_completion(request, form_data, user, models: di
         if params:
             system = params.pop('system', None)
             form_data = apply_model_params_to_body_openai(params, form_data)
-            form_data = await apply_system_prompt_to_body(system, form_data, metadata, user)
+            if not bypass_system_prompt:
+                form_data = await apply_system_prompt_to_body(system, form_data, metadata, user)
 
     pipe_id = get_pipe_id(form_data)
     function_module = await get_function_module_by_id(request, pipe_id)
@@ -308,17 +315,17 @@ async def generate_function_chat_completion(request, form_data, user, models: di
                         yield data
                     return
                 if isinstance(res, dict):
-                    yield f'data: {json.dumps(res)}\n\n'
+                    yield f'data: {JSONCodec.dumps(res)}\n\n'
                     return
 
             except Exception as e:
                 log.error(f'Error: {e}')
-                yield f'data: {json.dumps({"error": {"detail": str(e)}})}\n\n'
+                yield f'data: {JSONCodec.dumps({"error": {"detail": str(e)}})}\n\n'
                 return
 
             if isinstance(res, str):
                 message = openai_chat_chunk_message_template(form_data['model'], res)
-                yield f'data: {json.dumps(message)}\n\n'
+                yield f'data: {JSONCodec.dumps(message)}\n\n'
 
             if isinstance(res, Iterator):
                 for line in res:
@@ -330,7 +337,7 @@ async def generate_function_chat_completion(request, form_data, user, models: di
 
             finish_message = openai_chat_chunk_message_template(form_data['model'], '')
             finish_message['choices'][0]['finish_reason'] = 'stop'
-            yield f'data: {json.dumps(finish_message)}\n\n'
+            yield f'data: {JSONCodec.dumps(finish_message)}\n\n'
             yield 'data: [DONE]'
 
         return StreamingResponse(stream_content(), media_type='text/event-stream')

backend/open_webui/internal/db.py

@@ -1,8 +1,8 @@
 from __future__ import annotations
 
-import json
 import logging
 import os
+import re
 import sys
 from contextlib import asynccontextmanager, contextmanager
 from datetime import datetime, timedelta, timezone
@@ -27,7 +27,9 @@ from open_webui.env import (
     DATABASE_URL,
     ENABLE_DB_MIGRATIONS,
     OPEN_WEBUI_DIR,
+    USE_SLIM,
 )
+from open_webui.utils.json_codec import JSONCodec
 from sqlalchemy import Dialect, MetaData, create_engine, event, types
 from sqlalchemy.engine.url import make_url
 from sqlalchemy.ext.asyncio import AsyncSession, async_sessionmaker, create_async_engine
@@ -124,23 +126,34 @@ class JSONField(types.TypeDecorator):  # TEXT-backed JSON storage
     """Store arbitrary Python objects as JSON-encoded TEXT.
 
     Used instead of native JSON columns for portability across SQLite and
-    PostgreSQL.  Values are serialized with ``json.dumps`` on write and
+    PostgreSQL.  Values are serialized with ``JSONCodec.dumps`` on write and
-    deserialized with ``json.loads`` on read.
+    deserialized with ``JSONCodec.loads`` on read.
     """
 
     impl = types.UnicodeText
     cache_ok = True
 
     def process_bind_param(self, value: _T | None, dialect: Dialect) -> Any:
-        return json.dumps(value) if value is not None else None
+        return JSONCodec.dumps(value) if value is not None else None
 
     def process_result_value(self, value: _T | None, dialect: Dialect) -> Any:
-        return json.loads(value) if value is not None else None
+        return JSONCodec.loads(value) if value is not None else None
 
     def copy(self, **kwargs: Any) -> Self:
         return JSONField(length=self.impl.length)
 
 
+if USE_SLIM:
+    if make_url(DATABASE_URL).get_backend_name() not in ('sqlite', 'postgresql', 'postgres'):
+        raise ValueError(
+            'Slim requires SQLite or PostgreSQL for DATABASE_URL. Use the standard image for other databases.'
+        )
+    if DATABASE_ENABLE_IAM_TOKEN_AUTH:
+        raise ValueError(
+            'AWS RDS IAM authentication requires the standard image. Slim supports PostgreSQL database credentials.'
+        )
+
+
 # Normalize SSL params from the URL once; the sync engine needs them
 # reattached in canonical libpq form for psycopg2.
 _url_without_ssl, _ssl_dict = extract_ssl_params_from_url(DATABASE_URL)
@@ -202,6 +215,20 @@ def enable_iam_token_auth(connectable) -> None:
         return
 
     engine = getattr(connectable, 'sync_engine', connectable)
+    url = engine.url
+    auth = _rds_iam_token_auth
+    # The token is bound to one host/port/user pair; leave other databases on their own credentials.
+    if (url.host, url.port or 5432, url.username) != (auth.host, auth.port, auth.username):
+        log.warning(
+            'AWS RDS IAM token auth not applied to %s: the token is issued for %s@%s:%s, '
+            'so this connection uses the password from its own URL',
+            url.render_as_string(hide_password=True),
+            auth.username,
+            auth.host,
+            auth.port,
+        )
+        return
+
     if not event.contains(engine, 'do_connect', _set_iam_token_password):
         event.listen(engine, 'do_connect', _set_iam_token_password)
 
@@ -232,6 +259,27 @@ def _make_async_url(url: str) -> str:
     return url
 
 
+def _json_codec_kwargs(kwargs: dict) -> dict:
+    """Default an engine to JSONCodec for native ``JSON`` columns.
+
+    Unlike ``JSONField``, those serialize through the engine, which otherwise uses
+    stdlib ``json``. With ``ENABLE_ORJSON`` off JSONCodec is stdlib ``json`` anyway.
+    """
+    kwargs.setdefault('json_serializer', JSONCodec.dumps)
+    kwargs.setdefault('json_deserializer', JSONCodec.loads)
+    return kwargs
+
+
+def _create_engine(*args, **kwargs):
+    """``create_engine`` with the app JSON codec wired in."""
+    return create_engine(*args, **_json_codec_kwargs(kwargs))
+
+
+def _create_async_engine(*args, **kwargs):
+    """``create_async_engine`` with the app JSON codec wired in."""
+    return create_async_engine(*args, **_json_codec_kwargs(kwargs))
+
+
 # ============================================================
 # SYNC ENGINE (used only for: startup migrations, config loading,
 #              Alembic, peewee migration, health checks)
@@ -260,7 +308,7 @@ if SQLALCHEMY_DATABASE_URL.startswith('sqlite+sqlcipher://'):
     # in the native sqlcipher3 C library. Use NullPool by default for safety,
     # or QueuePool if DATABASE_POOL_SIZE is explicitly configured.
     if isinstance(DATABASE_POOL_SIZE, int) and DATABASE_POOL_SIZE > 0:
-        engine = create_engine(
+        engine = _create_engine(
             'sqlite://',
             creator=create_sqlcipher_connection,
             pool_size=DATABASE_POOL_SIZE,
@@ -272,7 +320,7 @@ if SQLALCHEMY_DATABASE_URL.startswith('sqlite+sqlcipher://'):
             echo=False,
         )
     else:
-        engine = create_engine(
+        engine = _create_engine(
             'sqlite://',
             creator=create_sqlcipher_connection,
             poolclass=NullPool,
@@ -282,10 +330,49 @@ if SQLALCHEMY_DATABASE_URL.startswith('sqlite+sqlcipher://'):
     log.info('Connected to encrypted SQLite database using SQLCipher')
 
 elif 'sqlite' in SQLALCHEMY_DATABASE_URL:
-    engine = create_engine(SQLALCHEMY_DATABASE_URL, connect_args={'check_same_thread': False})
+    engine = _create_engine(SQLALCHEMY_DATABASE_URL, connect_args={'check_same_thread': False})
 
     def _apply_sqlite_pragmas(dbapi_connection):
         """Apply all configured SQLite PRAGMAs to a raw DBAPI connection."""
+        # SQLite LIKE folds ASCII only; SQLAlchemy SQLite ILIKE compiles to lower(x) LIKE lower(?).
+        compiled_patterns = {}
+
+        def like(pattern, value, escape=None):
+            if pattern is None or value is None:
+                return None
+
+            pattern = str(pattern).lower()
+            escape = str(escape).lower() if escape is not None else None
+            key = (pattern, escape)
+            compiled = compiled_patterns.get(key)
+            if compiled is False:
+                return False
+            if compiled is None:
+                regex = []
+                escaped = False
+                for char in pattern:
+                    if escape and not escaped and char == escape:
+                        escaped = True
+                        continue
+                    regex.append(
+                        '.*' if not escaped and char == '%' else '.' if not escaped and char == '_' else re.escape(char)
+                    )
+                    escaped = False
+                if escaped:
+                    compiled = False
+                    if len(compiled_patterns) >= 512:
+                        compiled_patterns.clear()
+                    compiled_patterns[key] = compiled
+                    return False
+                compiled = re.compile(''.join(regex), re.DOTALL)
+                if len(compiled_patterns) >= 512:
+                    compiled_patterns.clear()
+                compiled_patterns[key] = compiled
+
+            return compiled.fullmatch(str(value).lower()) is not None
+
+        dbapi_connection.create_function('like', 2, like, deterministic=True)
+        dbapi_connection.create_function('like', 3, like, deterministic=True)
         cursor = dbapi_connection.cursor()
         if DATABASE_ENABLE_SQLITE_WAL:
             cursor.execute('PRAGMA journal_mode=WAL')
@@ -314,7 +401,7 @@ elif 'sqlite' in SQLALCHEMY_DATABASE_URL:
 else:
     if isinstance(DATABASE_POOL_SIZE, int):
         if DATABASE_POOL_SIZE > 0:
-            engine = create_engine(
+            engine = _create_engine(
                 SQLALCHEMY_DATABASE_URL,
                 pool_size=DATABASE_POOL_SIZE,
                 max_overflow=DATABASE_POOL_MAX_OVERFLOW,
@@ -324,9 +411,9 @@ else:
                 poolclass=QueuePool,
             )
         else:
-            engine = create_engine(SQLALCHEMY_DATABASE_URL, pool_pre_ping=True, poolclass=NullPool)
+            engine = _create_engine(SQLALCHEMY_DATABASE_URL, pool_pre_ping=True, poolclass=NullPool)
     else:
-        engine = create_engine(SQLALCHEMY_DATABASE_URL, pool_pre_ping=True)
+        engine = _create_engine(SQLALCHEMY_DATABASE_URL, pool_pre_ping=True)
 
 enable_iam_token_auth(engine)
 
@@ -373,7 +460,7 @@ if 'sqlite' in ASYNC_SQLALCHEMY_DATABASE_URL:
     # No pool_pre_ping: a local SQLite file cannot drop connections, and the
     # ping costs a worker-thread hop plus a SELECT 1 on every checkout.
     _sqlite_pool_size = DATABASE_POOL_SIZE if isinstance(DATABASE_POOL_SIZE, int) and DATABASE_POOL_SIZE > 0 else 512
-    async_engine = create_async_engine(
+    async_engine = _create_async_engine(
         ASYNC_SQLALCHEMY_DATABASE_URL,
         connect_args={'check_same_thread': False},
         pool_size=_sqlite_pool_size,
@@ -387,7 +474,7 @@ if 'sqlite' in ASYNC_SQLALCHEMY_DATABASE_URL:
 else:
     if isinstance(DATABASE_POOL_SIZE, int):
         if DATABASE_POOL_SIZE > 0:
-            async_engine = create_async_engine(
+            async_engine = _create_async_engine(
                 ASYNC_SQLALCHEMY_DATABASE_URL,
                 pool_size=DATABASE_POOL_SIZE,
                 max_overflow=DATABASE_POOL_MAX_OVERFLOW,
@@ -396,13 +483,13 @@ else:
                 pool_pre_ping=True,
             )
         else:
-            async_engine = create_async_engine(
+            async_engine = _create_async_engine(
                 ASYNC_SQLALCHEMY_DATABASE_URL,
                 pool_pre_ping=True,
                 poolclass=NullPool,
             )
     else:
-        async_engine = create_async_engine(
+        async_engine = _create_async_engine(
             ASYNC_SQLALCHEMY_DATABASE_URL,
             pool_pre_ping=True,
         )

backend/open_webui/main.py

@@ -1,17 +1,19 @@
 from __future__ import annotations
 
 import asyncio
-import json
+import copy
 import logging
 import mimetypes
 import os
 import sys
 import time
+from concurrent.futures import ThreadPoolExecutor
 from contextlib import asynccontextmanager
 from uuid import uuid4
 
 import aiohttp
 import anyio.to_thread
+from cryptography.fernet import InvalidToken
 from fastapi import (
     Depends,
     FastAPI,
@@ -64,6 +66,7 @@ from open_webui.config import (
     ONEDRIVE_SHAREPOINT_URL,
     STATIC_DIR,
     THREAD_POOL_SIZE,
+    THREAD_POOL_THREAD_NAME_PREFIX,
     WEBUI_AUTH,
     WEBUI_NAME,
     async_reset_config,
@@ -71,7 +74,9 @@ from open_webui.config import (
     seed_registered_defaults,
 )
 from open_webui.constants import ERROR_MESSAGES, TASKS
+from open_webui.utils.recurrence import RecurrenceEvaluationTimeout
 from open_webui.env import (
+    USE_SLIM,
     AIOHTTP_CLIENT_SESSION_SSL,
     AUDIT_EXCLUDED_PATHS,
     AUDIT_INCLUDED_PATHS,
@@ -83,19 +88,19 @@ from open_webui.env import (
     ENABLE_COMPRESSION_MIDDLEWARE,
     ENABLE_CUSTOM_MODEL_FALLBACK,
     ENABLE_EASTER_EGGS,
-    ENABLE_PLUGINS,
-    EXTERNAL_PWA_MANIFEST_URL,
     # OAuth Back-Channel Logout
     ENABLE_OAUTH_BACKCHANNEL_LOGOUT,
     ENABLE_OTEL,
+    ENABLE_PLUGINS,
     ENABLE_PUBLIC_ACTIVE_USERS_COUNT,
+    ENABLE_PYODIDE_FILE_PERSISTENCE,
     # SCIM
     ENABLE_SCIM,
     ENABLE_SIGNUP_PASSWORD_CONFIRMATION,
     ENABLE_STAR_SESSIONS_MIDDLEWARE,
-    ENABLE_PYODIDE_FILE_PERSISTENCE,
     ENABLE_VERSION_UPDATE_CHECK,
     ENABLE_WEBSOCKET_SUPPORT,
+    EXTERNAL_PWA_MANIFEST_URL,
     GLOBAL_LOG_LEVEL,
     INSTANCE_ID,
     LICENSE_KEY,
@@ -103,11 +108,14 @@ from open_webui.env import (
     MAX_BODY_LOG_SIZE,
     # Redis
     REDIS_KEY_PREFIX,
+    REDIS_TASK_TTL,
     REDIS_URL,
     RESET_CONFIG_ON_START,
     SAFE_MODE,
     SCIM_TOKEN,
     VERSION,
+    WEBSOCKET_HEARTBEAT_INTERVAL,
+    WEBSOCKET_MANAGER,
     # Admin Account Runtime Creation
     WEBUI_ADMIN_EMAIL,
     WEBUI_ADMIN_NAME,
@@ -121,12 +129,14 @@ from open_webui.env import (
 from open_webui.events import (
     EVENTS,
     delete_event_webhook,
-    get_event_catalog as get_event_catalog_items,
     get_event_webhooks,
     migrate_legacy_webhook_config,
     publish_event,
     upsert_event_webhook,
 )
+from open_webui.events import (
+    get_event_catalog as get_event_catalog_items,
+)
 from open_webui.internal.db import engine, get_async_session
 from open_webui.models.access_grants import AccessGrants
 from open_webui.models.channels import Channels
@@ -134,7 +144,7 @@ from open_webui.models.chats import ChatForm, Chats
 from open_webui.models.config import Config
 from open_webui.models.functions import Functions
 from open_webui.models.messages import Messages
-from open_webui.models.models import Models
+from open_webui.models.models import Models, normalize_model_tags
 from open_webui.models.users import Users
 from open_webui.routers import (
     analytics,
@@ -154,8 +164,8 @@ from open_webui.routers import (
     knowledge,
     memories,
     models,
-    notifications,
     notes,
+    notifications,
     ollama,
     openai,
     pipelines,
@@ -182,6 +192,7 @@ from open_webui.socket.main import (
     get_user_id_from_session_pool,
     periodic_session_pool_cleanup,
     periodic_usage_pool_cleanup,
+    redis_event_listener,
 )
 from open_webui.socket.main import (
     app as socket_app,
@@ -193,18 +204,15 @@ from open_webui.tasks import (
     list_task_ids_by_item_id,
     list_tasks,
     redis_task_command_listener,
+    redis_task_heartbeat,
     stop_item_tasks,
     stop_task,
 )  # Import from tasks.py
 from open_webui.utils import logger
 from open_webui.utils.access_control import has_permission
+from open_webui.utils.access_control.folders import has_folder_write_access
 from open_webui.utils.actions import chat_action as chat_action_handler
-from open_webui.utils.asgi_middleware import (
+from open_webui.utils.asgi_middleware import AppHTTPMiddleware
-    AuthTokenMiddleware,
-    CommitSessionMiddleware,
-    RedirectMiddleware,
-    WebsocketUpgradeGuardMiddleware,
-)
 from open_webui.utils.audit import AuditLevel, AuditLoggingMiddleware
 from open_webui.utils.auth import (
     create_admin_user,
@@ -229,14 +237,17 @@ from open_webui.utils.chat_variables import (
     normalize_chat_variables,
 )
 from open_webui.utils.embeddings import generate_embeddings
+from open_webui.utils.json_codec import JSONCodec
 from open_webui.utils.json_response import apply_orjson_http_json
 from open_webui.utils.logger import start_logger
 from open_webui.utils.middleware import (
     background_tasks_handler,
     build_chat_response_context,
+    drain_approved_tool_calls,
     process_chat_payload,
     process_chat_response,
 )
+from open_webui.utils.misc import get_response_error_detail, merge_model_params
 from open_webui.utils.model_ids import strip_provider_model_prefix
 from open_webui.utils.models import (
     check_model_access,
@@ -258,8 +269,12 @@ from open_webui.utils.oauth import (
 )
 from open_webui.utils.plugin import install_tool_and_function_dependencies
 from open_webui.utils.redis import get_redis_client
-from open_webui.utils.security_headers import SecurityHeadersMiddleware
+from open_webui.utils.session_pool import cleanup_response, get_client_timeout, get_session, stream_wrapper
-from open_webui.utils.session_pool import cleanup_response, get_session, stream_wrapper
+from open_webui.utils.tool_approval import (
+    ResolveToolCallForm,
+    build_tool_approval_resume_payload,
+    resolve_tool_call_output,
+)
 from open_webui.utils.tools import set_terminal_servers, set_tool_servers
 
 if SAFE_MODE:
@@ -320,6 +335,9 @@ https://github.com/open-webui/open-webui
         print(banner)
     except UnicodeEncodeError:
         # Stdout can't encode the box-drawing banner (Windows cp1252, redirected/headless stdout); fall back to ASCII.
+        # LICENSE covers this Open WebUI CLI identifier.
+        # Do not alter, remove, obscure, or replace it except as LICENSE permits:
+        # https://docs.openwebui.com/license.
         print(f'Open WebUI v{VERSION} - building the best AI user interface.\nhttps://github.com/open-webui/open-webui')
 
 
@@ -329,6 +347,16 @@ async def lifespan(app: FastAPI):
     # This allows sync functions to schedule work on the main loop without blocking health checks
     app.state.main_loop = asyncio.get_running_loop()
 
+    if THREAD_POOL_SIZE and THREAD_POOL_SIZE > 0:
+        # asyncio offloads bypass AnyIO's limiter, so configure both before the first offload.
+        anyio.to_thread.current_default_thread_limiter().total_tokens = THREAD_POOL_SIZE
+        app.state.main_loop.set_default_executor(
+            ThreadPoolExecutor(
+                max_workers=THREAD_POOL_SIZE,
+                thread_name_prefix=THREAD_POOL_THREAD_NAME_PREFIX,
+            )
+        )
+
     app.state.instance_id = INSTANCE_ID
     start_logger()
 
@@ -363,17 +391,18 @@ async def lifespan(app: FastAPI):
 
     if app.state.redis is not None:
         app.state.redis_task_command_listener = asyncio.create_task(redis_task_command_listener(app))
+        if REDIS_TASK_TTL > 0:
+            app.state.redis_task_heartbeat = asyncio.create_task(redis_task_heartbeat(app))
 
-    if THREAD_POOL_SIZE and THREAD_POOL_SIZE > 0:
+    if WEBSOCKET_MANAGER == 'redis':
-        limiter = anyio.to_thread.current_default_thread_limiter()
+        app.state.redis_event_listener = asyncio.create_task(redis_event_listener())
-        limiter.total_tokens = THREAD_POOL_SIZE
 
-    asyncio.create_task(periodic_usage_pool_cleanup())
+    app.state.periodic_usage_pool_cleanup = asyncio.create_task(periodic_usage_pool_cleanup())
-    asyncio.create_task(periodic_session_pool_cleanup())
+    app.state.periodic_session_pool_cleanup = asyncio.create_task(periodic_session_pool_cleanup())
 
     from open_webui.utils.automations import scheduler_worker_loop
 
-    asyncio.create_task(scheduler_worker_loop(app))
+    app.state.scheduler_worker_loop = asyncio.create_task(scheduler_worker_loop(app))
 
     if await Config.get('models.base_models_cache'):
         try:
@@ -420,13 +449,13 @@ async def lifespan(app: FastAPI):
         log.info('Initializing tool servers...')
         try:
             await set_tool_servers(mock_request)
-            log.info(f'Initialized {len(app.state.TOOL_SERVERS)} tool server(s)')
+            log.info('Initialized %s tool server(s)', len(app.state.TOOL_SERVERS))
         except Exception as e:
             log.warning(f'Failed to initialize tool servers at startup: {e}')
 
         try:
             await set_terminal_servers(mock_request)
-            log.info(f'Initialized {len(app.state.TERMINAL_SERVERS)} terminal server(s)')
+            log.info('Initialized %s terminal server(s)', len(app.state.TERMINAL_SERVERS))
         except Exception as e:
             log.warning(f'Failed to initialize terminal servers at startup: {e}')
 
@@ -454,6 +483,16 @@ async def lifespan(app: FastAPI):
     if hasattr(app.state, 'redis_task_command_listener'):
         app.state.redis_task_command_listener.cancel()
 
+    if hasattr(app.state, 'redis_task_heartbeat'):
+        app.state.redis_task_heartbeat.cancel()
+
+    if hasattr(app.state, 'redis_event_listener'):
+        app.state.redis_event_listener.cancel()
+
+    app.state.periodic_usage_pool_cleanup.cancel()
+    app.state.periodic_session_pool_cleanup.cancel()
+    app.state.scheduler_worker_loop.cancel()
+
     await publish_event(app, EVENTS.SYSTEM_SHUTDOWN_COMPLETED, source='system')
 
 
@@ -461,6 +500,9 @@ async def lifespan(app: FastAPI):
 # response_model routes keep FastAPI's Pydantic fast path either way.
 apply_orjson_http_json()
 
+# LICENSE covers this Open WebUI API metadata identifier.
+# Do not alter, remove, obscure, or replace it except as LICENSE permits:
+# https://docs.openwebui.com/license.
 app = FastAPI(
     title='Open WebUI',
     docs_url='/docs' if ENV == 'dev' else None,
@@ -469,6 +511,12 @@ app = FastAPI(
     lifespan=lifespan,
 )
 
+
+@app.exception_handler(RecurrenceEvaluationTimeout)
+async def recurrence_timeout_handler(request: Request, exc: RecurrenceEvaluationTimeout):
+    return JSONResponse(status_code=400, content={'detail': str(exc)})
+
+
 # Used by readiness checks to gate traffic until startup work is done.
 app.state.startup_complete = False
 
@@ -483,6 +531,10 @@ app.state.oauth_client_manager = oauth_client_manager
 app.state.instance_id = None
 app.state.redis = None
 
+# LICENSE covers this Open WebUI branding surface, including name, logo,
+# visual, textual, symbolic identifiers, metadata, and surrounding UI.
+# Do not alter, remove, obscure, or replace it except as LICENSE permits:
+# https://docs.openwebui.com/license.
 app.state.WEBUI_NAME = WEBUI_NAME
 app.state.LICENSE_METADATA = None
 app.state.USER_COUNT = None
@@ -592,8 +644,18 @@ async def initialize_runtime_config(app: FastAPI):
                         f'mcp:{server_id}',
                         OAuthClientInformationFull(**oauth_client_info),
                     )
+                except InvalidToken:
+                    log.error(
+                        'Error adding OAuth client for MCP tool server %s: InvalidToken. '
+                        'Stored OAuth client data is invalid; reconnect this tool server.',
+                        server_id,
+                    )
                 except Exception as e:
-                    log.error(f'Error adding OAuth client for MCP tool server {server_id}: {e}')
+                    log.error(
+                        'Error adding OAuth client for MCP tool server %s: %s',
+                        server_id,
+                        f'{type(e).__name__}: {e}' if str(e) else type(e).__name__,
+                    )
 
     arena_models = await Config.get('evaluation.arena.models', []) or []
     if any('access_control' in m.get('meta', {}) for m in arena_models):
@@ -763,11 +825,7 @@ if ENABLE_COMPRESSION_MIDDLEWARE:
 # `terminate_force_close` tracebacks under aiosqlite and as random
 # CancelledError storms across the request path. See
 # `open_webui.utils.asgi_middleware` for the rationale.
-app.add_middleware(RedirectMiddleware)
+app.add_middleware(AppHTTPMiddleware)
-app.add_middleware(SecurityHeadersMiddleware)
-app.add_middleware(CommitSessionMiddleware)
-app.add_middleware(AuthTokenMiddleware, fastapi_app=app)
-app.add_middleware(WebsocketUpgradeGuardMiddleware)
 
 
 app.add_middleware(
@@ -855,19 +913,17 @@ async def get_models(request: Request, refresh: bool = False, user=Depends(get_v
     models = await get_filtered_models(models, user)
 
     for model in models:
+        info = model.get('info') if isinstance(model.get('info'), dict) else {}
+        meta = info.get('meta') if isinstance(info.get('meta'), dict) else {}
+
         # Remove profile image URL to reduce payload size
-        if model.get('info', {}).get('meta', {}).get('profile_image_url'):
+        meta.pop('profile_image_url', None)
-            model['info']['meta'].pop('profile_image_url', None)
 
-        try:
+        if 'tags' in meta:
-            model_tags = [tag.get('name') for tag in model.get('info', {}).get('meta', {}).get('tags', [])]
+            meta['tags'] = normalize_model_tags(meta['tags'])
-            tags = [tag.get('name') for tag in model.get('tags', [])]
 
-            tags = list(set(model_tags + tags))
+        tags = normalize_model_tags(meta.get('tags')) + normalize_model_tags(model.get('tags'))
-            model['tags'] = [{'name': tag} for tag in tags]
+        model['tags'] = list({tag['name']: tag for tag in tags}.values())
-        except Exception as e:
-            log.debug(f'Error processing model tags: {e}')
-            model['tags'] = []
 
     model_order_list = await Config.get('ui.model_order_list')
     if model_order_list:
@@ -882,7 +938,7 @@ async def get_models(request: Request, refresh: bool = False, user=Depends(get_v
 
     if log.isEnabledFor(logging.DEBUG):
         log.debug(
-            f'/api/models returned filtered models accessible to the user: {json.dumps([model.get("id") for model in models])}'
+            f'/api/models returned filtered models accessible to the user: {JSONCodec.dumps([model.get("id") for model in models])}'
         )
     return {'data': models}
 
@@ -935,7 +991,7 @@ async def unload_model(request: Request, form_data: ModelUnloadForm, user=Depend
             prefix_id = api_config.get('prefix_id', None)
             actual_model = strip_provider_model_prefix(model_id, prefix_id)
 
-            payload = json.dumps({'model': actual_model, 'keep_alive': 0, 'prompt': ''})
+            payload = JSONCodec.dumps({'model': actual_model, 'keep_alive': 0, 'prompt': ''})
 
             try:
                 timeout = aiohttp.ClientTimeout(total=30)
@@ -1066,53 +1122,67 @@ async def chat_completion(
     metadata = {}
     try:
         model_info = None
+        fallback_model = None
+        missing_base_model = False
         if not model_item.get('direct', False):
             if model_id not in request.app.state.MODELS:
                 raise Exception('Model not found')
 
             model = request.app.state.MODELS[model_id]
             model_info = await Models.get_model_by_id(model_id)
+            missing_base_model = bool(
+                model_info and model_info.base_model_id and model_info.base_model_id not in request.app.state.MODELS
+            )
+
+            if missing_base_model and ENABLE_CUSTOM_MODEL_FALLBACK:
+                fallback_model_id = next(
+                    (
+                        model_id.strip()
+                        for model_id in ((await Config.get('ui.default_models')) or '').split(',')
+                        if model_id.strip()
+                    ),
+                    None,
+                )
+                if fallback_model_id:
+                    fallback_model = request.app.state.MODELS.get(fallback_model_id)
 
             # Check if user has access to the model
             if not BYPASS_MODEL_ACCESS_CONTROL and (user.role != 'admin' or not BYPASS_ADMIN_ACCESS_CONTROL):
                 try:
-                    await check_model_access(user, model, model_info=model_info)
+                    access_model_info = (
+                        model_info.model_copy(update={'base_model_id': None})
+                        if fallback_model is not None
+                        else model_info
+                    )
+                    await check_model_access(user, model, model_info=access_model_info)
+                    if fallback_model is not None:
+                        await check_model_access(user, fallback_model)
                 except Exception as e:
                     raise e
         else:
             model = model_item
             await _set_direct_model(request, model, user)
 
+        # Read before the fallback below can rebind model to a different one.
+        model_capabilities = ((model.get('info') or {}).get('meta') or {}).get('capabilities') or {}
+
         # Model params: global defaults as base, per-model overrides win
-        default_model_params = await Config.get('models.default_params', {}) or {}
+        default_model_params = copy.deepcopy(await Config.get('models.default_params', {}) or {})
-        model_info_params = {
+        model_info_params = merge_model_params(
-            **default_model_params,
+            default_model_params,
-            **(model_info.params.model_dump() if model_info and model_info.params else {}),
+            model_info.params.model_dump() if model_info and model_info.params else {},
-        }
+        )
         request_params = {key: value for key, value in (form_data.get('params') or {}).items() if value is not None}
         if model_info_params or request_params:
-            form_data['params'] = {
+            form_data['params'] = merge_model_params(model_info_params, request_params)
-                **model_info_params,
-                **request_params,
-            }
 
         # Check base model existence for custom models
-        if model_info and model_info.base_model_id:
+        if missing_base_model:
-            base_model_id = model_info.base_model_id
+            if fallback_model is None:
-            if base_model_id not in request.app.state.MODELS:
+                raise Exception('Model not found')
-                if ENABLE_CUSTOM_MODEL_FALLBACK:
+            # Update model and form_data so routing uses the fallback model's type
-                    default_models = ((await Config.get('ui.default_models')) or '').split(',')
+            model = fallback_model
-
+            form_data['model'] = fallback_model['id']
-                    fallback_model_id = default_models[0].strip() if default_models[0] else None
-
-                    if fallback_model_id and fallback_model_id in request.app.state.MODELS:
-                        # Update model and form_data so routing uses the fallback model's type
-                        model = request.app.state.MODELS[fallback_model_id]
-                        form_data['model'] = fallback_model_id
-                    else:
-                        raise Exception('Model not found')
-                else:
-                    raise Exception('Model not found')
 
         # Chat Params
         stream_delta_chunk_size = form_data.get('params', {}).get('stream_delta_chunk_size')
@@ -1123,6 +1193,10 @@ async def chat_completion(
         if model_info_params.get('stream_response') is not None:
             form_data['stream'] = model_info_params.get('stream_response')
 
+        # Providers only report token counts when asked, so ask on every caller's behalf.
+        if form_data.get('stream') and model_capabilities.get('usage'):
+            form_data['stream_options'] = {**(form_data.get('stream_options') or {}), 'include_usage': True}
+
         if model_info_params.get('stream_delta_chunk_size'):
             stream_delta_chunk_size = model_info_params.get('stream_delta_chunk_size')
 
@@ -1155,7 +1229,7 @@ async def chat_completion(
             message_ids = [{'model_id': model_id, 'message_id': form_data.pop('id', None)}]
 
         user_message = form_data.pop('user_message', None) or form_data.pop('parent_message', None)
-        chat_id = form_data.get('chat_id') or ''
+        chat_id = form_data.pop('chat_id', None) or ''
         chat_variables = form_data.pop('chat_variables', None)
         if chat_variables is None:
             existing_chat = await Chats.get_chat_by_id(chat_id) if is_saved_chat_id(chat_id) else None
@@ -1177,15 +1251,28 @@ async def chat_completion(
         ):
             tool_servers = None
 
+        automation_id = form_data.pop('automation_id', None)
+        tool_approval_mode = (
+            'full'
+            if automation_id or chat_id.startswith('channel:')
+            else (
+                form_data.get('params', {}).get('tool_approval_mode')
+                if await Config.get('chat.tool_permissions.enable', False)
+                else 'full'
+            )
+            or 'full'
+        )
+
         metadata = {
             'user_id': user.id,
             'user_agent': request.headers.get('user-agent', '') or '',
             'internal': getattr(request.state, 'internal', False) is True,
-            'chat_id': form_data.pop('chat_id', None) or '',
+            'chat_id': chat_id,
             'user_message': user_message,
             'user_message_id': user_message.get('id') if user_message else None,
             'assistant_message_id': form_data.pop('assistant_message_id', None),
             'session_id': form_data.pop('session_id', None),
+            'automation_id': automation_id,
             'folder_id': form_data.pop('folder_id', None),
             'filter_ids': form_data.pop('filter_ids', []),
             'tool_ids': form_data.get('tool_ids', None),
@@ -1205,6 +1292,7 @@ async def chat_completion(
                     or model_info_params.get('function_calling')
                     or 'native'
                 ),
+                'tool_approval_mode': tool_approval_mode,
             },
         }
 
@@ -1218,8 +1306,8 @@ async def chat_completion(
         if metadata.get('chat_id') and user:
             chat_id = metadata['chat_id']
 
-            # Gate channel: branch — caller needs write access on the channel
+            # Gate channel: branch — caller needs write access on the channel, and the
-            # and the supplied message_id must belong to that channel.
+            # supplied message_id must belong to that channel and be the caller's own.
             if chat_id.startswith('channel:'):
                 channel_id = chat_id.removeprefix('channel:')
                 channel = await Channels.get_channel_by_id(channel_id)
@@ -1251,7 +1339,11 @@ async def chat_completion(
                     if not target_message_id:
                         continue
                     target_message = await Messages.get_message_by_id(target_message_id)
-                    if target_message and target_message.channel_id != channel.id:
+                    if target_message and (
+                        target_message.channel_id != channel.id
+                        # Write access is not authorship — block cross-member edits.
+                        or (user.role != 'admin' and target_message.user_id != user.id)
+                    ):
                         raise HTTPException(
                             status_code=status.HTTP_403_FORBIDDEN,
                             detail=ERROR_MESSAGES.DEFAULT(),
@@ -1259,6 +1351,14 @@ async def chat_completion(
 
             if is_saved_chat_id(chat_id):
                 if is_new_chat:
+                    # The chat created below is persisted with this folder_id.
+                    folder_id = metadata['folder_id']
+                    if folder_id is not None and not await has_folder_write_access(user.id, folder_id):
+                        raise HTTPException(
+                            status_code=status.HTTP_404_NOT_FOUND,
+                            detail=ERROR_MESSAGES.NOT_FOUND,
+                        )
+
                     # Build the full history upfront with ALL assistant placeholders
                     user_message = metadata.get('user_message') or {}
                     user_message_id = user_message.get('id') if user_message else None
@@ -1365,7 +1465,7 @@ async def chat_completion(
                                 user.id,
                             )
                         except Exception as e:
-                            log.debug(f'Error inserting chat files: {e}')
+                            log.debug('Error inserting chat files: %s', e)
                             pass
 
                     if initial_title_generation is not None and all_assistant_ids:
@@ -1386,8 +1486,8 @@ async def chat_completion(
                         async def run_initial_title_generation():
                             try:
                                 await background_tasks_handler(title_ctx)
-                            except Exception as e:
+                            except Exception:
-                                log.debug(f'Error generating initial chat title: {e}')
+                                log.exception('Error generating initial chat title')
 
                         asyncio.create_task(run_initial_title_generation())
                 else:
@@ -1407,15 +1507,13 @@ async def chat_completion(
                     # The old frontend saveChatHandler did this on every message;
                     # now the backend owns persistence.
                     chat_files = metadata.get('files')
-                    if chat_files is not None or selected_chat_models:
+                    chat_fields = {}
-                        existing_chat = await Chats.get_chat_by_id(chat_id)
+                    if chat_files is not None:
-                        if existing_chat:
+                        chat_fields['files'] = chat_files
-                            updated = {**existing_chat.chat}
+                    if selected_chat_models:
-                            if chat_files is not None:
+                        chat_fields['models'] = selected_chat_models
-                                updated['files'] = chat_files
+                    if chat_fields:
-                            if selected_chat_models:
+                        await Chats.update_chat_by_id(chat_id, chat_fields, touch=False)
-                                updated['models'] = selected_chat_models
-                            await Chats.update_chat_by_id(chat_id, updated, touch=False)
 
                     await Chats.update_chat_variables_by_id(chat_id, chat_variables)
 
@@ -1475,7 +1573,7 @@ async def chat_completion(
                                 user.id,
                             )
                         except Exception as e:
-                            log.debug(f'Error inserting chat files: {e}')
+                            log.debug('Error inserting chat files: %s', e)
                             pass
 
                     # Save ALL assistant placeholders
@@ -1500,6 +1598,8 @@ async def chat_completion(
                     for entry in message_ids:
                         target_model_id = entry['model_id']
                         assistant_message_id = entry['message_id']
+                        if assistant_message_id and assistant_message_id == metadata.get('assistant_message_id'):
+                            continue
                         if assistant_message_id:
                             assistant_message = {
                                 'id': assistant_message_id,
@@ -1546,26 +1646,28 @@ async def chat_completion(
 
     async def process_chat(request, form_data, user, metadata, model, tasks=None):
         try:
+            ctx = None
+            if metadata.get('assistant_message_id'):
+                ctx = await build_chat_response_context(request, form_data, user, model, metadata, tasks, [])
             form_data, metadata, events = await process_chat_payload(request, form_data, user, metadata, model)
 
+            if await drain_approved_tool_calls(request, form_data, user, model, metadata):
+                return {'status': True, 'chat_id': metadata.get('chat_id'), 'paused': True}
+
             response = await chat_completion_handler(request, form_data, user)
 
             # When the upstream provider returns an error (e.g. HTTP 400
             # content-filter, quota exceeded), generate_chat_completion
             # returns a JSONResponse instead of raising.  Detect this and
-            # raise so the except-block below emits chat:message:error +
+            # raise so the except-block below emits a terminal
-            # chat:tasks:cancel, unblocking the frontend.
+            # chat:message:error, unblocking the frontend.
             if isinstance(response, JSONResponse) and response.status_code >= 400:
-                try:
+                raise Exception(get_response_error_detail(response))
-                    error_body = json.loads(response.body.decode('utf-8', 'replace'))
-                    detail = error_body.get('error', error_body) if isinstance(error_body, dict) else error_body
-                    if isinstance(detail, dict):
-                        detail = detail.get('message', detail.get('detail', str(detail)))
-                except Exception:
-                    detail = f'Provider returned HTTP {response.status_code}'
-                raise Exception(detail)
 
-            ctx = await build_chat_response_context(request, form_data, user, model, metadata, tasks, events)
+            if ctx is None:
+                ctx = await build_chat_response_context(request, form_data, user, model, metadata, tasks, events)
+            else:
+                ctx.update(form_data=form_data, metadata=metadata, events=events)
 
             return await process_chat_response(response, ctx)
         except asyncio.CancelledError:
@@ -1594,6 +1696,7 @@ async def chat_completion(
                             {
                                 'parentId': metadata.get('user_message_id', None),
                                 'error': {'content': error_detail},
+                                'done': True,
                             },
                         )
 
@@ -1602,12 +1705,9 @@ async def chat_completion(
                         await event_emitter(
                             {
                                 'type': 'chat:message:error',
-                                'data': {'error': {'content': error_detail}},
+                                'data': {'error': {'content': error_detail}, 'done': True},
                             }
                         )
-                        await event_emitter(
-                            {'type': 'chat:tasks:cancel'},
-                        )
 
                 except Exception:
                     pass
@@ -1641,9 +1741,9 @@ async def chat_completion(
                         try:
                             await client.disconnect()
                         except BaseException as e:
-                            log.debug(f'Error disconnecting MCP client: {e}')
+                            log.debug('Error disconnecting MCP client: %s', e)
             except BaseException as e:
-                log.debug(f'Error cleaning up MCP clients: {e}')
+                log.debug('Error cleaning up MCP clients: %s', e)
 
             # Deregister this task, then emit chat:active=false if no others remain
             try:
@@ -1789,6 +1889,27 @@ async def chat_completion(
 generate_chat_completions = chat_completion
 generate_chat_completion = chat_completion
 
+
+@app.post('/api/v1/chats/{id}/messages/{message_id}/resolve')
+async def resolve_chat_message_tool_call(
+    request: Request,
+    id: str,
+    message_id: str,
+    form_data: ResolveToolCallForm,
+    user=Depends(get_verified_user),
+    db: AsyncSession = Depends(get_async_session),
+):
+    resolution = await resolve_tool_call_output(id, message_id, form_data, user, db=db)
+    payload = await build_tool_approval_resume_payload(id, message_id, chat=resolution['chat'])
+    result = await chat_completion(request, payload, user)
+    return {
+        'status': True,
+        'chat_id': id,
+        'message_id': message_id,
+        **(result if isinstance(result, dict) else {}),
+    }
+
+
 # Expose as app.state so internal callers (e.g. automations) can
 # use the full pipeline without importing from main.py (avoids circular deps).
 app.state.CHAT_COMPLETION_HANDLER = chat_completion
@@ -1820,7 +1941,7 @@ async def count_message_tokens(
 
 
 async def passthrough_anthropic_messages(request: Request, form_data: dict, user) -> Response | dict:
-    requested_model, payload, url, key, headers, cookies = await openai.get_anthropic_token_count_target(
+    requested_model, payload, url, key, headers, cookies = await openai.get_anthropic_request_target(
         request, form_data, user
     )
     request_url = f'{url.rstrip("/")}/messages'
@@ -1832,11 +1953,11 @@ async def passthrough_anthropic_messages(request: Request, form_data: dict, user
         response = await session.request(
             method='POST',
             url=request_url,
-            data=json.dumps(payload),
+            data=JSONCodec.dumps(payload),
             headers=headers,
             cookies=cookies,
             ssl=AIOHTTP_CLIENT_SESSION_SSL,
-            timeout=aiohttp.ClientTimeout(total=openai.AIOHTTP_CLIENT_TIMEOUT),
+            timeout=get_client_timeout(stream=bool(payload.get('stream'))),
         )
 
         if 'text/event-stream' in response.headers.get('Content-Type', ''):
@@ -1925,13 +2046,6 @@ async def generate_messages(
 
     # Convert Anthropic payload to OpenAI format
     openai_payload = convert_anthropic_to_openai_payload(form_data, passthrough_params)
-    model_meta = model_info.meta.model_dump() if model_info and model_info.meta else {}
-    if (model_meta.get('capabilities') or {}).get('usage') is True:
-        if openai_payload.get('stream'):
-            stream_options = openai_payload.get('stream_options')
-            if not isinstance(stream_options, dict):
-                stream_options = {}
-            openai_payload['stream_options'] = {**stream_options, 'include_usage': True}
 
     # Route through the existing chat_completion handler
     response = await chat_completion(request, openai_payload, user)
@@ -2039,13 +2153,14 @@ async def list_tasks_by_chat_id_endpoint(request: Request, chat_id: str, user=De
 
     task_ids = await list_task_ids_by_item_id(request.app.state.redis, chat_id)
 
-    log.debug(f'Task IDs for chat {chat_id}: {task_ids}')
+    log.debug('Task IDs for chat %s: %s', chat_id, task_ids)
     return {'task_ids': task_ids}
 
 
 @app.post('/api/tasks/chat/{chat_id:path}/stop')
 async def stop_tasks_by_chat_id_endpoint(request: Request, chat_id: str, user=Depends(get_verified_user)):
     socket_id = get_temporary_chat_session_id(chat_id)
+    chat = None
     if socket_id:
         owner_id = get_user_id_from_session_pool(socket_id)
         if owner_id != user.id and user.role != 'admin':
@@ -2055,6 +2170,47 @@ async def stop_tasks_by_chat_id_endpoint(request: Request, chat_id: str, user=De
         if chat is None or (chat.user_id != user.id and user.role != 'admin'):
             raise HTTPException(status_code=status.HTTP_404_NOT_FOUND, detail=ERROR_MESSAGES.NOT_FOUND)
     result = await stop_item_tasks(request.app.state.redis, chat_id)
+
+    if not socket_id and str(result.get('message', '')).startswith('No tasks found'):
+        messages_map = await Chats.get_messages_map_by_chat_id(chat_id) or {}
+        for message_id, message in messages_map.items():
+            if message.get('role') != 'assistant' or message.get('done') is not False:
+                continue
+
+            output = message.get('output')
+            if isinstance(output, list):
+                for item in output:
+                    if item.get('type') == 'function_call' and item.get('status') in {
+                        'pending',
+                        'queued',
+                        'requires_approval',
+                    }:
+                        item['status'] = 'rejected'
+                        item.pop('approved', None)
+
+            await Chats.upsert_message_to_chat_by_id_and_message_id(
+                chat_id,
+                message_id,
+                {'done': True, **({'output': output} if isinstance(output, list) else {})},
+                touch=False,
+            )
+            result = {
+                'status': True,
+                'message': 'Finalized pending approval message.',
+            }
+
+            event_emitter = await get_event_emitter(
+                {
+                    'user_id': chat.user_id,
+                    'chat_id': chat_id,
+                    'message_id': message_id,
+                },
+                update_db=False,
+            )
+            if event_emitter:
+                await event_emitter({'type': 'chat:completion', 'data': {'done': True, 'output': output}})
+                await event_emitter({'type': 'chat:tasks:cancel'})
+
     return result
 
 
@@ -2106,6 +2262,7 @@ async def get_app_config(request: Request):
         'auth.enable_api_keys',
         'ui.enable_password_change_form',
         'direct.enable',
+        'direct.integrations.enable',
         'folders.enable',
         'folders.max_file_count',
         'channels.enable',
@@ -2113,6 +2270,7 @@ async def get_app_config(request: Request):
         'automations.enable',
         'notes.enable',
         'chat.context_compaction.enable',
+        'chat.tool_permissions.enable',
         'web.search.enable',
         'web.search.confirmation.enable',
         'web.search.confirmation.content',
@@ -2129,7 +2287,10 @@ async def get_app_config(request: Request):
         'memories.enable',
         'ui.default_models',
         'ui.default_pinned_models',
+        'ui.default_interface_settings',
+        'ui.i18n',
         'ui.prompt_suggestions',
+        'ui.prompt_suggestions_i18n',
         'code_execution.engine',
         'code_interpreter.engine',
         'audio.tts.engine',
@@ -2152,6 +2313,7 @@ async def get_app_config(request: Request):
         'name': app.state.WEBUI_NAME,
         'version': VERSION,
         'default_locale': str(DEFAULT_LOCALE),
+        'i18n': config.get('ui.i18n') or {},
         'oauth': {
             # Hide providers (and thus the login buttons / auto-redirect) when OAuth
             # is disabled, without clearing the admin's provider configuration.
@@ -2163,6 +2325,7 @@ async def get_app_config(request: Request):
             'auto_redirect': config.get('oauth.auto_redirect'),
         },
         'features': {
+            'slim': USE_SLIM,
             # --- Public: required by login/signup page pre-auth ---
             'auth': WEBUI_AUTH,
             'auth_trusted_header': bool(WEBUI_AUTH_TRUSTED_EMAIL_HEADER),
@@ -2171,6 +2334,11 @@ async def get_app_config(request: Request):
             'enable_signup': config.get('ui.enable_signup'),
             'enable_login_form': config.get('ui.enable_login_form'),
             'enable_websocket': ENABLE_WEBSOCKET_SUPPORT,
+            **(
+                {'websocket_heartbeat_interval': WEBSOCKET_HEARTBEAT_INTERVAL}
+                if WEBSOCKET_HEARTBEAT_INTERVAL is not None
+                else {}
+            ),
             # --- Authenticated: only consumed by logged-in frontend ---
             **(
                 {
@@ -2181,6 +2349,7 @@ async def get_app_config(request: Request):
                     'enable_public_active_users_count': ENABLE_PUBLIC_ACTIVE_USERS_COUNT,
                     'enable_easter_eggs': ENABLE_EASTER_EGGS,
                     'enable_direct_connections': config.get('direct.enable'),
+                    'enable_direct_integrations': config.get('direct.integrations.enable', False),
                     'enable_plugins': ENABLE_PLUGINS,
                     'enable_folders': config.get('folders.enable'),
                     'folder_max_file_count': config.get('folders.max_file_count'),
@@ -2189,6 +2358,7 @@ async def get_app_config(request: Request):
                     'enable_automations': config.get('automations.enable'),
                     'enable_notes': config.get('notes.enable'),
                     'enable_context_compaction': config.get('chat.context_compaction.enable'),
+                    'enable_tool_permissions': config.get('chat.tool_permissions.enable'),
                     'enable_web_search': config.get('web.search.enable'),
                     'enable_web_search_confirmation': config.get('web.search.confirmation.enable'),
                     'web_search_confirmation_content': config.get('web.search.confirmation.content'),
@@ -2224,6 +2394,7 @@ async def get_app_config(request: Request):
                 'default_models': config.get('ui.default_models'),
                 'default_pinned_models': config.get('ui.default_pinned_models'),
                 'default_prompt_suggestions': config.get('ui.prompt_suggestions'),
+                'default_prompt_suggestions_i18n': config.get('ui.prompt_suggestions_i18n'),
                 **({'user_count': user_count} if user_count is not None else {}),
                 'code': {
                     'engine': config.get('code_execution.engine'),
@@ -2259,6 +2430,7 @@ async def get_app_config(request: Request):
                     'sharepoint_tenant_id': ONEDRIVE_SHAREPOINT_TENANT_ID,
                 },
                 'ui': {
+                    'default_interface_settings': config.get('ui.default_interface_settings'),
                     'pending_user_overlay_title': config.get('ui.pending_user_overlay_title'),
                     'pending_user_overlay_content': config.get('ui.pending_user_overlay_content'),
                     'response_watermark': config.get('ui.watermark'),
@@ -2437,8 +2609,8 @@ async def get_app_latest_release_version(user=Depends(get_verified_user)):
 
                 return {'current': VERSION, 'latest': latest_version[1:]}
     except Exception as e:
-        log.debug(e)
+        log.warning(f'Version update check failed: {e}')
-        return {'current': VERSION, 'latest': VERSION}
+        return {'current': VERSION, 'latest': None}
 
 
 @app.get('/api/changelog')
@@ -2559,8 +2731,19 @@ async def register_client(request, client_id: str) -> bool:
                 oauth_server_key,
                 oauth_scope=oauth_scope,
             )
+    except InvalidToken:
+        log.error(
+            'OAuth client re-registration failed for %s: InvalidToken. '
+            'Stored OAuth client data is invalid; reconnect this tool server.',
+            client_id,
+        )
+        return False
     except Exception as e:
-        log.error(f'OAuth client re-registration failed for {client_id}: {e}')
+        log.error(
+            'OAuth client re-registration failed for %s: %s',
+            client_id,
+            f'{type(e).__name__}: {e}' if str(e) else type(e).__name__,
+        )
         return False
 
     try:
@@ -2582,7 +2765,7 @@ async def register_client(request, client_id: str) -> bool:
         **apply_connection_oauth_options(connection, oauth_client_info.model_dump(mode='json'))
     )
     oauth_client_manager.add_client(client_id, oauth_client_info)
-    log.info(f'Re-registered OAuth client {client_id} for tool server')
+    log.info('Re-registered OAuth client %s for tool server', client_id)
     return True
 
 
@@ -2626,7 +2809,7 @@ async def oauth_client_authorize(
                 detail='OAuth client registration is still invalid after re-registration',
             )
 
-    return await oauth_client_manager.handle_authorize(request, client_id=client_id)
+    return await oauth_client_manager.handle_authorize(request, client_id=client_id, user_id=user.id)
 
 
 @app.get('/oauth/clients/{client_id}/callback')
@@ -2634,12 +2817,10 @@ async def oauth_client_callback(
     client_id: str,
     request: Request,
     response: Response,
-    user=Depends(get_verified_user),
 ):
     return await oauth_client_manager.handle_callback(
         request,
         client_id=client_id,
-        user_id=user.id if user else None,
         response=response,
     )
 
@@ -2688,6 +2869,10 @@ async def oauth_backchannel_logout(
 async def get_manifest_json():
     external_pwa_manifest_url = getattr(app.state, 'EXTERNAL_PWA_MANIFEST_URL', None)
     if external_pwa_manifest_url:
+        # LICENSE covers this install-time Open WebUI branding surface, including
+        # names, logos, manifests, metadata, and surrounding UI.
+        # Do not alter, remove, obscure, or replace it except as LICENSE permits:
+        # https://docs.openwebui.com/license.
         session = await get_session()
         async with session.get(
             external_pwa_manifest_url,
@@ -2696,6 +2881,10 @@ async def get_manifest_json():
             r.raise_for_status()
             return await r.json()
     else:
+        # LICENSE covers this generated Open WebUI install branding surface,
+        # including names, logos, manifests, metadata, and surrounding UI.
+        # Do not alter, remove, obscure, or replace it except as LICENSE permits:
+        # https://docs.openwebui.com/license.
         return {
             'name': app.state.WEBUI_NAME,
             'short_name': app.state.WEBUI_NAME,
@@ -2704,6 +2893,9 @@ async def get_manifest_json():
             'display': 'standalone',
             'background_color': '#343541',
             'icons': [
+                # LICENSE covers this Open WebUI install icon.
+                # Do not alter, remove, obscure, or replace it except as LICENSE permits:
+                # https://docs.openwebui.com/license.
                 {
                     'src': '/static/logo.png',
                     'type': 'image/png',
@@ -2728,6 +2920,9 @@ async def get_manifest_json():
 @app.get('/opensearch.xml')
 async def get_opensearch_xml():
     webui_url = await Config.get('webui.url')
+    # LICENSE covers this Open WebUI search identifier.
+    # Do not alter, remove, obscure, or replace it except as LICENSE permits:
+    # https://docs.openwebui.com/license.
     xml_content = rf"""
     <OpenSearchDescription xmlns="http://a9.com/-/spec/opensearch/1.1/" xmlns:moz="http://www.mozilla.org/2006/browser/search/">
     <ShortName>{app.state.WEBUI_NAME}</ShortName>
@@ -2745,7 +2940,7 @@ def _sync_db_ping() -> None:
     """Verify the database is reachable with a simple SELECT 1.
 
     Uses a raw connection from the engine pool instead of the thread-local
-    ScopedSession.  This is necessary because CommitSessionMiddleware
+    ScopedSession.  This is necessary because AppHTTPMiddleware
     deliberately skips healthcheck paths (/health, /ready, /health/db),
     so any ScopedSession opened on a healthcheck worker thread is never
     rolled back or removed.  If the session ever enters an invalid state
@@ -2819,6 +3014,11 @@ async def check_db_health():
 
 
 # --- static assets & files ---
+# Windows registry entries can override these with text/plain, which breaks module and wasm loading
+mimetypes.add_type('text/javascript', '.js')
+mimetypes.add_type('text/javascript', '.mjs')
+mimetypes.add_type('application/wasm', '.wasm')
+
 # Serve build-time static assets (CSS, JS, images, favicon, etc.)
 app.mount('/static', StaticFiles(directory=STATIC_DIR), name='static')
 
@@ -2864,7 +3064,6 @@ def swagger_ui_html(*args, **kwargs):
 applications.get_swagger_ui_html = swagger_ui_html
 
 if os.path.exists(FRONTEND_BUILD_DIR):
-    mimetypes.add_type('text/javascript', '.js')
     pyodide_dir = FRONTEND_BUILD_DIR / 'pyodide'
     if os.path.exists(pyodide_dir):
         app.mount('/pyodide', CORSStaticFiles(directory=pyodide_dir), name='pyodide')

backend/open_webui/migrations/versions/1ce6ade7d93b_add_group_member_user_id_index.py

@@ -0,0 +1,28 @@
+"""Add group_member user_id index
+
+Revision ID: 1ce6ade7d93b
+Revises: f0bd01a18a3d
+Create Date: 2026-07-31 03:00:00.000000
+
+"""
+
+import sqlalchemy as sa
+from alembic import op
+
+revision = '1ce6ade7d93b'
+down_revision = 'f0bd01a18a3d'
+branch_labels = None
+depends_on = None
+
+
+def upgrade():
+    conn = op.get_bind()
+    inspector = sa.inspect(conn)
+    existing_indexes = {idx['name'] for idx in inspector.get_indexes('group_member')}
+
+    if 'ix_group_member_user_id_group_id' not in existing_indexes:
+        op.create_index('ix_group_member_user_id_group_id', 'group_member', ['user_id', 'group_id'])
+
+
+def downgrade():
+    op.drop_index('ix_group_member_user_id_group_id', table_name='group_member')

backend/open_webui/migrations/versions/6d09d1bf1f23_repair_double_encoded_user_oauth.py

@@ -0,0 +1,64 @@
+"""repair double encoded user oauth
+
+Revision ID: 6d09d1bf1f23
+Revises: 1ce6ade7d93b
+Create Date: 2026-08-10 23:20:20.374826
+
+"""
+
+import json
+from typing import Sequence, Union
+
+from alembic import op
+import sqlalchemy as sa
+import open_webui.internal.db
+
+
+# revision identifiers, used by Alembic.
+revision: str = '6d09d1bf1f23'
+down_revision: Union[str, None] = '1ce6ade7d93b'
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+_user = sa.table(
+    'user',
+    sa.column('id', sa.Text),
+    sa.column('oauth', sa.JSON),
+)
+
+
+def _decode_json_object(value: str) -> dict | None:
+    try:
+        decoded = json.loads(value)
+    except Exception:
+        return None
+    return decoded if isinstance(decoded, dict) else None
+
+
+def upgrade() -> None:
+    conn = op.get_bind()
+    inspector = sa.inspect(conn)
+
+    if 'user' not in inspector.get_table_names():
+        return
+
+    user_columns = {c['name'] for c in inspector.get_columns('user')}
+    if 'oauth' not in user_columns:
+        return
+
+    rows = conn.execute(sa.select(_user.c.id, _user.c.oauth).where(_user.c.oauth.is_not(None))).fetchall()
+
+    for uid, oauth in rows:
+        if not isinstance(oauth, str):
+            continue
+
+        decoded = _decode_json_object(oauth)
+        if decoded is None:
+            continue
+
+        conn.execute(sa.update(_user).where(_user.c.id == uid).values(oauth=decoded))
+
+
+def downgrade() -> None:
+    pass

backend/open_webui/migrations/versions/b10670c03dd5_update_user_table.py

@@ -185,9 +185,7 @@ def upgrade() -> None:
         for uid, oauth_sub in rows:
             if oauth_sub:
                 provider, sub = oauth_sub.split('@', 1) if '@' in oauth_sub else ('oidc', oauth_sub)
-                conn.execute(
+                conn.execute(sa.update(_user).where(_user.c.id == uid).values(oauth={provider: {'sub': sub}}))
-                    sa.update(_user).where(_user.c.id == uid).values(oauth=json.dumps({provider: {'sub': sub}}))
-                )
 
     # ── Migrate api_key column → api_key table (only if old column still exists)
     if 'api_key' in user_columns:
@@ -226,7 +224,7 @@ def downgrade() -> None:
 
     for uid, oauth in rows:
         try:
-            data = json.loads(oauth)
+            data = oauth if isinstance(oauth, dict) else json.loads(oauth)
             provider = list(data.keys())[0]
             sub = data[provider].get('sub')
             oauth_sub = f'{provider}@{sub}'

backend/open_webui/migrations/versions/d4c1a8e37b62_add_chat_timer_at_and_chat_indexes.py

@@ -0,0 +1,70 @@
+"""add chat timer_at and chat list, unread and timer indexes
+
+Revision ID: d4c1a8e37b62
+Revises: 6d09d1bf1f23
+Create Date: 2026-08-23 18:05:12.441907
+
+"""
+
+from collections.abc import Sequence
+
+import sqlalchemy as sa
+from alembic import op
+
+# revision identifiers, used by Alembic.
+revision: str = 'd4c1a8e37b62'
+down_revision: str | None = '6d09d1bf1f23'
+branch_labels: str | Sequence[str] | None = None
+depends_on: str | Sequence[str] | None = None
+
+
+def upgrade() -> None:
+    op.add_column('chat', sa.Column('timer_at', sa.BigInteger(), nullable=True))
+    op.create_index(
+        'timer_at_idx',
+        'chat',
+        ['timer_at'],
+        sqlite_where=sa.text('timer_at IS NOT NULL'),
+        postgresql_where=sa.text('timer_at IS NOT NULL'),
+    )
+
+    # Timers created before this migration carry their due time in meta only, and would never fire.
+    chat = sa.table(
+        'chat', sa.column('id', sa.String), sa.column('meta', sa.JSON), sa.column('timer_at', sa.BigInteger)
+    )
+    conn = op.get_bind()
+    pending = conn.execute(
+        sa.select(chat.c.id, chat.c.meta)
+        .where(chat.c.meta['type'].as_string() == 'timer')
+        .where(chat.c.meta['status'].as_string() == 'pending')
+    ).all()
+    for chat_id, meta in pending:
+        try:  # imported chats can carry any meta, and a non-numeric due time must not abort the migration
+            due_at = int(meta.get('timer_at'))
+        except (TypeError, ValueError):
+            continue
+        conn.execute(chat.update().where(chat.c.id == chat_id).values(timer_at=due_at))
+
+    op.create_index('user_id_updated_at_id_idx', 'chat', ['user_id', sa.text('updated_at DESC'), 'id'])
+    op.create_index(
+        'user_id_timer_at_idx',
+        'chat',
+        ['user_id', 'timer_at'],
+        sqlite_where=sa.text('timer_at IS NOT NULL'),
+        postgresql_where=sa.text('timer_at IS NOT NULL'),
+    )
+    op.create_index(
+        'user_id_folder_unread_idx',
+        'chat',
+        ['user_id', 'folder_id', 'archived', 'updated_at', 'last_read_at', 'id'],
+    )
+    op.create_index('chat_message_chat_role_done_idx', 'chat_message', ['chat_id', 'role', 'done'])
+
+
+def downgrade() -> None:
+    op.drop_index('chat_message_chat_role_done_idx', table_name='chat_message')
+    op.drop_index('user_id_folder_unread_idx', table_name='chat')
+    op.drop_index('user_id_timer_at_idx', table_name='chat')
+    op.drop_index('user_id_updated_at_id_idx', table_name='chat')
+    op.drop_index('timer_at_idx', table_name='chat')
+    op.drop_column('chat', 'timer_at')

backend/open_webui/models/access_grants.py

@@ -839,7 +839,8 @@ class AccessGrantsTable:
     ):
         """
         Filter for items where user has read BUT NOT write access.
-        Public items are NOT considered read_only.
+        A public (user:*) read grant counts as read access, so publicly shared
+        read-only items are listed rather than being reachable only by direct link.
 
         Note: This method builds SQLAlchemy expressions and does NOT perform I/O itself,
         so it remains synchronous. The caller is responsible for executing the query
@@ -850,7 +851,6 @@ class AccessGrantsTable:
 
         from sqlalchemy import exists as sa_exists
 
-        # Has read grant (not public)
         read_grant_exists = (
             select(AccessGrant.id)
             .where(
@@ -858,6 +858,10 @@ class AccessGrantsTable:
                 AccessGrant.resource_id == DocumentModel.id,
                 AccessGrant.permission == 'read',
                 or_(
+                    and_(
+                        AccessGrant.principal_type == 'user',
+                        AccessGrant.principal_id == '*',
+                    ),
                     *(
                         [
                             and_(
@@ -884,7 +888,6 @@ class AccessGrantsTable:
             .exists()
         )
 
-        # Does NOT have write grant
         write_grant_exists = (
             select(AccessGrant.id)
             .where(
@@ -892,6 +895,10 @@ class AccessGrantsTable:
                 AccessGrant.resource_id == DocumentModel.id,
                 AccessGrant.permission == 'write',
                 or_(
+                    and_(
+                        AccessGrant.principal_type == 'user',
+                        AccessGrant.principal_id == '*',
+                    ),
                     *(
                         [
                             and_(
@@ -918,21 +925,7 @@ class AccessGrantsTable:
             .exists()
         )
 
-        # Is NOT public
+        conditions = [read_grant_exists, ~write_grant_exists]
-        public_grant_exists = (
-            select(AccessGrant.id)
-            .where(
-                AccessGrant.resource_type == resource_type,
-                AccessGrant.resource_id == DocumentModel.id,
-                AccessGrant.permission == 'read',
-                AccessGrant.principal_type == 'user',
-                AccessGrant.principal_id == '*',
-            )
-            .correlate(DocumentModel)
-            .exists()
-        )
-
-        conditions = [read_grant_exists, ~write_grant_exists, ~public_grant_exists]
 
         # Not owner
         if user_id:

backend/open_webui/models/auths.py

@@ -9,7 +9,7 @@ from typing import Optional
 import bcrypt
 from open_webui.internal.db import Base, JSONField, get_async_db_context
 from open_webui.models.users import User, UserModel, UserProfileImageResponse, Users
-from open_webui.utils.validate import validate_profile_image_url
+from open_webui.utils.validate import validate_image_url
 from pydantic import BaseModel, field_validator
 from sqlalchemy import Boolean, Column, String, Text, delete, select, update
 from sqlalchemy.exc import IntegrityError
@@ -87,7 +87,7 @@ class SignupForm(BaseModel):
     @classmethod
     def check_profile_image_url(cls, v: str | None) -> str | None:
         if v is not None:
-            return validate_profile_image_url(v)
+            return validate_image_url(v)
         return v
 
 

backend/open_webui/models/automations.py

@@ -1,9 +1,10 @@
 import logging
 import time
-from typing import Optional
+from typing import Literal, Optional
 from uuid import uuid4
 
 from open_webui.internal.db import Base, get_async_db_context
+from open_webui.utils.misc import json_text_variants
 from pydantic import BaseModel, ConfigDict
 from sqlalchemy import JSON, BigInteger, Boolean, Column, Index, String, Text, cast, delete, func, or_, select, update
 from sqlalchemy.ext.asyncio import AsyncSession
@@ -64,11 +65,17 @@ class AutomationTerminalConfig(BaseModel):
     cwd: Optional[str] = None
 
 
+class AutomationTarget(BaseModel):
+    type: Literal['chat', 'channel'] = 'chat'
+    channel_id: Optional[str] = None
+
+
 class AutomationData(BaseModel):
     prompt: str
     model_id: str
     rrule: str
     terminal: Optional[AutomationTerminalConfig] = None
+    target: Optional[AutomationTarget] = None
 
 
 class AutomationModel(BaseModel):
@@ -179,16 +186,16 @@ class AutomationTable:
         async with get_async_db_context(db) as db:
             stmt = select(Automation).filter_by(user_id=user_id)
 
-            if folder_id is not None:
+            if folder_id:
-                stmt = stmt.filter(Automation.folder_id == (folder_id or None))
+                stmt = stmt.filter(Automation.folder_id == folder_id)
 
             if query:
-                search = f'%{query}%'
+                # Search the name column and the prompt inside the JSON data.
-                # Search in name and prompt inside JSON data
+                data_text = cast(Automation.data, String)
                 stmt = stmt.filter(
                     or_(
-                        Automation.name.ilike(search),
+                        Automation.name.ilike(f'%{query}%'),
-                        cast(Automation.data, String).ilike(search),
+                        *(data_text.ilike(f'%{variant}%') for variant in json_text_variants(query)),
                     )
                 )
 
@@ -305,6 +312,7 @@ class AutomationTable:
             rows = result.scalars().all()
 
             from open_webui.utils.automations import next_run_ns
+            from open_webui.utils.recurrence import RecurrenceEvaluationTimeout
 
             # Batch-fetch user timezones so rescheduling respects each
             # user's local timezone instead of falling back to server time.
@@ -316,13 +324,20 @@ class AutomationTable:
                 tz_result = await db.execute(select(User.id, User.timezone).where(User.id.in_(user_ids)))
                 timezone_by_user_id = {uid: tz for uid, tz in tz_result.all()}
 
+            claimed = []
             for row in rows:
+                try:
+                    next_run_at = await next_run_ns(row.data.get('rrule', ''), tz=timezone_by_user_id.get(row.user_id))
+                except RecurrenceEvaluationTimeout:
+                    log.warning('Skipping automation %s: recurrence evaluation timed out', row.id)
+                    continue
                 row.last_run_at = now_ns
-                row.next_run_at = next_run_ns(row.data.get('rrule', ''), tz=timezone_by_user_id.get(row.user_id))
+                row.next_run_at = next_run_at
+                claimed.append(row)
 
             await db.commit()
 
-            return [AutomationModel.model_validate(r) for r in rows]
+            return [AutomationModel.model_validate(r) for r in claimed]
 
 
 ####################

backend/open_webui/models/calendar.py

@@ -4,6 +4,7 @@ from typing import Optional
 from uuid import uuid4
 
 from open_webui.internal.db import Base, get_async_db_context
+from open_webui.constants import ERROR_MESSAGES
 from open_webui.models.access_grants import AccessGrantModel, AccessGrants
 from open_webui.models.groups import Groups
 from open_webui.models.users import User, UserModel, UserResponse
@@ -26,6 +27,7 @@ from sqlalchemy import (
 from sqlalchemy.ext.asyncio import AsyncSession
 
 log = logging.getLogger(__name__)
+MIN_CALENDAR_RRULE_INTERVAL_SECONDS = 24 * 60 * 60
 
 
 ####################
@@ -177,6 +179,20 @@ class CalendarUpdateForm(BaseModel):
     access_grants: Optional[list[dict]] = None
 
 
+async def validate_calendar_rrule(value: Optional[str]) -> None:
+    if value:
+        from open_webui.utils.recurrence import rrule_interval_seconds
+
+        try:
+            interval = await rrule_interval_seconds(value)
+        except ValueError:
+            raise
+        except Exception as e:
+            raise ValueError(ERROR_MESSAGES.AUTOMATION_INVALID_RRULE(e)) from e
+        if interval is not None and interval < MIN_CALENDAR_RRULE_INTERVAL_SECONDS:
+            raise ValueError(ERROR_MESSAGES.CALENDAR_RRULE_TOO_FREQUENT)
+
+
 class CalendarEventForm(BaseModel):
     calendar_id: str
     title: str
@@ -431,6 +447,7 @@ class CalendarEventTable:
     async def insert_new_event(
         self, user_id: str, form_data: CalendarEventForm, db: Optional[AsyncSession] = None
     ) -> Optional[CalendarEventModel]:
+        await validate_calendar_rrule(form_data.rrule)
         async with get_async_db_context(db) as db:
             now = int(time.time_ns())
             event = CalendarEvent(
@@ -533,7 +550,8 @@ class CalendarEventTable:
                             & (CalendarEvent.start_at < end)
                             & or_(
                                 CalendarEvent.end_at.is_(None) & (CalendarEvent.start_at >= start),
-                                CalendarEvent.end_at.isnot(None) & (CalendarEvent.end_at > start),
+                                CalendarEvent.end_at.isnot(None)
+                                & ((CalendarEvent.end_at > start) | (CalendarEvent.start_at >= start)),
                             )
                         ),
                         # Recurring: fetch all (expansion in Python)
@@ -660,6 +678,7 @@ class CalendarEventTable:
     async def update_event_by_id(
         self, id: str, form_data: CalendarEventUpdateForm, db: Optional[AsyncSession] = None
     ) -> Optional[CalendarEventModel]:
+        await validate_calendar_rrule(form_data.rrule)
         async with get_async_db_context(db) as db:
             result = await db.execute(select(CalendarEvent).filter(CalendarEvent.id == id))
             event = result.scalars().first()
@@ -734,10 +753,10 @@ class CalendarEventTable:
         events = []
         for event, tz in rows:
             model = CalendarEventModel.model_validate(event)
-            # Determine per-event alert window
+            # meta is user-writable and this poll is shared by every user.
-            alert_minutes = None
+            alert_minutes = (model.meta or {}).get('alert_minutes')
-            if model.meta and 'alert_minutes' in model.meta:
+            if not isinstance(alert_minutes, (int, float)):
-                alert_minutes = model.meta['alert_minutes']
+                alert_minutes = None
 
             if alert_minutes is not None:
                 if alert_minutes < 0:

backend/open_webui/models/channels.py

@@ -1,4 +1,3 @@
-import json
 import secrets
 import time
 import uuid
@@ -10,7 +9,8 @@ from open_webui.models.access_grants import (
     AccessGrants,
 )
 from open_webui.models.groups import Groups
-from open_webui.utils.validate import validate_profile_image_url
+from open_webui.models.users import User
+from open_webui.utils.validate import validate_image_url
 from pydantic import BaseModel, ConfigDict, Field, field_validator
 from sqlalchemy import (
     JSON,
@@ -253,7 +253,7 @@ class ChannelWebhookForm(BaseModel):
     def check_profile_image_url(cls, v: Optional[str]) -> Optional[str]:
         if v is None:
             return v
-        return validate_profile_image_url(v)
+        return validate_image_url(v)
 
 
 class ChannelTable:
@@ -438,17 +438,17 @@ class ChannelTable:
 
             match_count = func.sum(
                 case(
-                    (ChannelMember.user_id.in_(unique_user_ids), 1),
+                    (User.id.in_(unique_user_ids), 1),
                     else_=0,
                 )
             )
 
             subquery = (
                 select(ChannelMember.channel_id)
+                .join(User, User.id == ChannelMember.user_id)
                 .group_by(ChannelMember.channel_id)
-                # 1. Channel must have exactly len(user_ids) members
+                # Match the exact set of accounts that still exist.
-                .having(func.count(ChannelMember.user_id) == len(unique_user_ids))
+                .having(func.count(User.id) == len(unique_user_ids))
-                # 2. All those members must be in unique_user_ids
                 .having(match_count == len(unique_user_ids))
                 .subquery()
             )

backend/open_webui/models/chat_messages.py

@@ -1,4 +1,3 @@
-import json
 import time
 import uuid
 from collections import Counter
@@ -169,6 +168,7 @@ class ChatMessage(Base):
         Index('chat_message_chat_parent_idx', 'chat_id', 'parent_id'),
         Index('chat_message_model_created_idx', 'model_id', 'created_at'),
         Index('chat_message_user_created_idx', 'user_id', 'created_at'),
+        Index('chat_message_chat_role_done_idx', 'chat_id', 'role', 'done'),  # unfinished-assistant probe
     )
 
 
@@ -207,6 +207,66 @@ class ChatMessageModel(BaseModel):
 
 
 class ChatMessageTable:
+    @staticmethod
+    def _apply_message_data(message: ChatMessage, data: dict, now: int) -> None:
+        """Overwrite only the fields the payload carries."""
+        if 'role' in data:
+            message.role = data['role']
+        if 'parent_id' in data or 'parentId' in data:
+            message.parent_id = data.get('parent_id') or data.get('parentId')
+        if 'content' in data:
+            message.content = data.get('content')
+        if 'output' in data:
+            message.output = data.get('output')
+        if 'model_id' in data or 'model' in data:
+            message.model_id = data.get('model_id') or data.get('model')
+        if 'files' in data:
+            message.files = data.get('files')
+        if 'sources' in data:
+            message.sources = data.get('sources')
+        if 'embeds' in data:
+            message.embeds = data.get('embeds')
+        if 'meta' in data:
+            message.meta = data.get('meta')
+        if 'done' in data:
+            message.done = data['done']
+        if 'status_history' in data or 'statusHistory' in data:
+            message.status_history = data.get('status_history') or data.get('statusHistory')
+        if 'error' in data:
+            message.error = data.get('error')
+        if 'context_summary' in data or 'contextSummary' in data:
+            message.context_summary = data.get('context_summary') or data.get('contextSummary')
+
+        usage = get_usage(data)
+        if usage:
+            existing_usage = normalize_usage(message.usage)
+            message.usage = existing_usage if usage == existing_usage else merge_usage(existing_usage, usage)
+        message.updated_at = now
+
+    @staticmethod
+    def _build_message(composite_id: str, chat_id: str, user_id: str, data: dict, now: int) -> ChatMessage:
+        return ChatMessage(
+            id=composite_id,
+            chat_id=chat_id,
+            user_id=user_id,
+            role=data.get('role', 'user'),
+            parent_id=data.get('parent_id') or data.get('parentId'),
+            content=data.get('content'),
+            output=data.get('output'),
+            model_id=data.get('model_id') or data.get('model'),
+            files=data.get('files'),
+            sources=data.get('sources'),
+            embeds=data.get('embeds'),
+            meta=data.get('meta'),
+            done=data.get('done', True),
+            status_history=data.get('status_history') or data.get('statusHistory'),
+            error=data.get('error'),
+            usage=get_usage(data),
+            context_summary=data.get('context_summary') or data.get('contextSummary'),
+            created_at=data.get('timestamp', now),
+            updated_at=now,
+        )
+
     async def upsert_message(
         self,
         message_id: str,
@@ -218,76 +278,46 @@ class ChatMessageTable:
         """Insert or update a chat message."""
         async with get_async_db_context(db) as db:
             now = int(time.time())
-            timestamp = data.get('timestamp', now)
-
             # Use composite ID: {chat_id}-{message_id}
             composite_id = f'{chat_id}-{message_id}'
 
-            existing = await db.get(ChatMessage, composite_id)
+            message = await db.get(ChatMessage, composite_id)
-            if existing:
+            if message:
-                # Update existing
+                self._apply_message_data(message, data, now)
-                if 'role' in data:
-                    existing.role = data['role']
-                if 'parent_id' in data or 'parentId' in data:
-                    existing.parent_id = data.get('parent_id') or data.get('parentId')
-                if 'content' in data:
-                    existing.content = data.get('content')
-                if 'output' in data:
-                    existing.output = data.get('output')
-                if 'model_id' in data or 'model' in data:
-                    existing.model_id = data.get('model_id') or data.get('model')
-                if 'files' in data:
-                    existing.files = data.get('files')
-                if 'sources' in data:
-                    existing.sources = data.get('sources')
-                if 'embeds' in data:
-                    existing.embeds = data.get('embeds')
-                if 'meta' in data:
-                    existing.meta = data.get('meta')
-                if 'done' in data:
-                    existing.done = data.get('done', True)
-                if 'status_history' in data or 'statusHistory' in data:
-                    existing.status_history = data.get('status_history') or data.get('statusHistory')
-                if 'error' in data:
-                    existing.error = data.get('error')
-                if 'context_summary' in data or 'contextSummary' in data:
-                    existing.context_summary = data.get('context_summary') or data.get('contextSummary')
-                # Extract and normalize usage
-                usage = get_usage(data)
-                if usage:
-                    existing_usage = normalize_usage(existing.usage or {}) if existing.usage else {}
-                    existing.usage = existing_usage if usage == existing_usage else merge_usage(existing_usage, usage)
-                existing.updated_at = now
-                await db.commit()
-                return ChatMessageModel.model_validate(existing)
             else:
-                # Insert new
+                message = self._build_message(composite_id, chat_id, user_id, data, now)
-                # Extract and normalize usage
-                usage = get_usage(data)
-                message = ChatMessage(
-                    id=composite_id,
-                    chat_id=chat_id,
-                    user_id=user_id,
-                    role=data.get('role', 'user'),
-                    parent_id=data.get('parent_id') or data.get('parentId'),
-                    content=data.get('content'),
-                    output=data.get('output'),
-                    model_id=data.get('model_id') or data.get('model'),
-                    files=data.get('files'),
-                    sources=data.get('sources'),
-                    embeds=data.get('embeds'),
-                    meta=data.get('meta'),
-                    done=data.get('done', True),
-                    status_history=data.get('status_history') or data.get('statusHistory'),
-                    error=data.get('error'),
-                    usage=usage,
-                    context_summary=data.get('context_summary') or data.get('contextSummary'),
-                    created_at=timestamp,
-                    updated_at=now,
-                )
                 db.add(message)
-                await db.commit()
+
-                return ChatMessageModel.model_validate(message)
+            await db.commit()
+            return ChatMessageModel.model_validate(message)
+
+    async def upsert_messages(
+        self,
+        chat_id: str,
+        user_id: str,
+        messages: dict[str, dict],
+        db: AsyncSession | None = None,
+    ) -> None:
+        """Insert or update the given messages of one chat."""
+        if not messages:
+            return
+
+        async with get_async_db_context(db) as db:
+            now = int(time.time())
+            result = await db.execute(
+                select(ChatMessage).filter(ChatMessage.id.in_([f'{chat_id}-{message_id}' for message_id in messages]))
+            )
+            existing_by_id = {row.id: row for row in result.scalars().all()}
+
+            for message_id, data in messages.items():
+                composite_id = f'{chat_id}-{message_id}'
+                message = existing_by_id.get(composite_id)
+                if message:
+                    self._apply_message_data(message, data, now)
+                else:
+                    db.add(self._build_message(composite_id, chat_id, user_id, data, now))
+
+            await db.commit()
 
     async def get_message_by_id(self, id: str, db: Optional[AsyncSession] = None) -> Optional[ChatMessageModel]:
         async with get_async_db_context(db) as db:

backend/open_webui/models/chats.py

@@ -2,13 +2,16 @@
 
 from __future__ import annotations
 
-import json
 import logging
+import re
 import time
 import uuid
+from typing import Any, Literal
 
 # local imports
+from open_webui.env import ENABLE_ADMIN_CHAT_ACCESS
 from open_webui.internal.db import Base, JSONField, get_async_db_context
+from open_webui.models.access_grants import AccessGrants
 from open_webui.models.automations import AutomationRun
 from open_webui.models.chat_messages import ChatMessage, ChatMessages
 from open_webui.models.folders import Folders
@@ -41,6 +44,62 @@ from sqlalchemy.sql.expression import bindparam
 
 log = logging.getLogger(__name__)
 ACTIVE_CHAT_GAP_SECONDS = 30 * 60
+CHAT_SEARCH_FILTER_PREFIXES = ('tag:', 'folder:', 'pinned:', 'archived:', 'shared:')
+
+
+def chat_search_content_query(text: str) -> str:
+    words = sanitize_text_for_db(text).lower().strip().split()
+    return ' '.join(word for word in words if not word.startswith(CHAT_SEARCH_FILTER_PREFIXES)).strip()
+
+
+def chat_search_terms(text: str) -> list[str]:
+    return list(dict.fromkeys(re.findall(r'[a-z0-9]+', text.lower())))
+
+
+def chat_search_message_content_match_sql(dialect_name: str, key: str) -> str:
+    if dialect_name == 'sqlite':
+        return f"""
+        (
+            EXISTS (
+                SELECT 1
+                FROM json_each(Chat.chat, '$.history.messages') AS history_message
+                WHERE LOWER(history_message.value->>'content') LIKE '%' || :{key} || '%'
+            )
+            OR EXISTS (
+                SELECT 1
+                FROM json_each(Chat.chat, '$.messages') AS legacy_message
+                WHERE LOWER(legacy_message.value->>'content') LIKE '%' || :{key} || '%'
+            )
+        )
+        """
+
+    if dialect_name == 'postgresql':
+        return f"""
+        (
+            EXISTS (
+                SELECT 1
+                FROM chat_message AS message
+                WHERE message.chat_id = Chat.id
+                AND message.user_id = Chat.user_id
+                AND json_typeof(message.content) = 'string'
+                AND LOWER(message.content #>> '{{}}') LIKE '%' || :{key} || '%'
+            )
+            OR EXISTS (
+                SELECT 1
+                FROM json_each(Chat.chat#>'{{history,messages}}') AS history_message
+                WHERE json_typeof(history_message.value->'content') = 'string'
+                AND LOWER(history_message.value->>'content') LIKE '%' || :{key} || '%'
+            )
+            OR EXISTS (
+                SELECT 1
+                FROM json_array_elements(Chat.chat->'messages') AS legacy_message
+                WHERE json_typeof(legacy_message->'content') = 'string'
+                AND LOWER(legacy_message->>'content') LIKE '%' || :{key} || '%'
+            )
+        )
+        """
+
+    raise NotImplementedError(f'Unsupported dialect: {dialect_name}')
 
 
 def chat_list_order(sort_by: str = 'updated_at', sort_dir: str = 'desc', user_id: str | None = None):
@@ -91,6 +150,7 @@ class Chat(Base):  # database table mapping for chat entity
     current_message_id = Column(Text, nullable=True)
 
     last_read_at = Column(BigInteger, nullable=True)
+    timer_at = Column(BigInteger, nullable=True)  # ns due time, set only while a timer chat waits to be claimed
 
     __table_args__ = (
         # Performance indexes for common queries
@@ -99,6 +159,23 @@ class Chat(Base):  # database table mapping for chat entity
         Index('user_id_archived_idx', 'user_id', 'archived'),
         Index('updated_at_user_id_idx', 'updated_at', 'user_id'),
         Index('folder_id_user_id_idx', 'folder_id', 'user_id'),
+        Index('user_id_updated_at_id_idx', 'user_id', updated_at.desc(), 'id'),
+        Index(
+            'timer_at_idx',
+            'timer_at',
+            sqlite_where=text('timer_at IS NOT NULL'),
+            postgresql_where=text('timer_at IS NOT NULL'),
+        ),
+        # timer_at key column turns the IS NOT NULL into a seek, so this beats the plain user_id indexes
+        Index(
+            'user_id_timer_at_idx',
+            'user_id',
+            'timer_at',
+            sqlite_where=text('timer_at IS NOT NULL'),
+            postgresql_where=text('timer_at IS NOT NULL'),
+        ),
+        # covering index: lets SQLite serve count_unread_by_folder_ids without reading chat rows
+        Index('user_id_folder_unread_idx', 'user_id', 'folder_id', 'archived', 'updated_at', 'last_read_at', 'id'),
     )
 
 
@@ -129,6 +206,7 @@ class ChatModel(BaseModel):
     current_message_id: str | None = None
 
     last_read_at: int | None = None
+    timer_at: int | None = None
 
     @field_validator('variables', mode='before')
     @classmethod
@@ -180,6 +258,7 @@ class ChatForm(BaseModel):
 class ChatImportForm(ChatForm):
     meta: dict | None = {}
     pinned: bool | None = False
+    archived: bool | None = False
     current_message_id: str | None = None
     created_at: int | None = None
     updated_at: int | None = None
@@ -189,11 +268,6 @@ class ChatsImportForm(BaseModel):
     chats: list[ChatImportForm]
 
 
-class ChatTitleMessagesForm(BaseModel):
-    title: str
-    messages: list[dict]
-
-
 class ChatTitleForm(BaseModel):
     title: str
 
@@ -231,6 +305,7 @@ class ChatTitleIdResponse(BaseModel):
     last_read_at: int | None = None
     snippet: str | None = None
     active: bool = False
+    archived: bool = False
 
 
 class SharedChatResponse(BaseModel):
@@ -284,7 +359,7 @@ class MessageStats(BaseModel):
     token_count: int | None = None
     timestamp: int | None = None
     rating: int | None = None  # Derived from message.annotation.rating
-    tags: list[str | None] = None  # Derived from message.annotation.tags
+    tags: list[str] | None = None  # Derived from message.annotation.tags
 
 
 class ChatHistoryStats(BaseModel):
@@ -361,6 +436,37 @@ class ChatTable:
 
         return changed
 
+    @staticmethod
+    def _last_descendant_id(messages: dict, message_id: str) -> str:
+        seen_ids = set()
+        while message_id in messages and message_id not in seen_ids:
+            seen_ids.add(message_id)
+            message = messages[message_id]
+            child_ids = message.get('childrenIds') if isinstance(message, dict) else []
+            child_ids = child_ids if isinstance(child_ids, list) else []
+            next_id = next((child_id for child_id in reversed(child_ids) if child_id in messages), None)
+            if not next_id:
+                break
+            message_id = next_id
+        return message_id
+
+    @staticmethod
+    def _add_child_id_to_parent(messages: dict, parent_id: str | None, child_id: str) -> bool:
+        parent = messages.get(parent_id) if parent_id else None
+        if not isinstance(parent, dict):
+            return False
+
+        child_ids = parent.get('childrenIds')
+        if not isinstance(child_ids, list):
+            child_ids = []
+            parent['childrenIds'] = child_ids
+
+        if child_id in child_ids:
+            return False
+
+        child_ids.append(child_id)
+        return True
+
     def _repair_chat_current_id(self, chat: dict) -> bool:
         history = chat.get('history')
         if not isinstance(history, dict):
@@ -370,6 +476,12 @@ class ChatTable:
         if not isinstance(messages, dict):
             return False
 
+        changed = False
+        for message_id, message in messages.items():
+            if not isinstance(message, dict):
+                continue
+            changed = self._add_child_id_to_parent(messages, message.get('parentId'), message_id) or changed
+
         current_id = history.get('currentId')
         current_message = messages.get(current_id)
         output = []
@@ -393,7 +505,13 @@ class ChatTable:
             and current_message.get('role')
             and not current_is_bad_leaf
         ):
-            return False
+            if current_message.get('contextSummary') or current_message.get('context_summary'):
+                last_descendant_id = self._last_descendant_id(messages, current_id)
+                if last_descendant_id != current_id:
+                    history['currentId'] = last_descendant_id
+                    return True
+
+            return changed
 
         latest_leaf_id = None
         latest_timestamp = -1
@@ -408,7 +526,7 @@ class ChatTable:
                 latest_timestamp = timestamp
 
         if not latest_leaf_id or latest_leaf_id == current_id:
-            return False
+            return changed
 
         history['currentId'] = latest_leaf_id
         return True
@@ -421,6 +539,7 @@ class ChatTable:
         db: AsyncSession | None = None,
         *,
         internal_meta: dict | None = None,
+        timer_at: int | None = None,
     ) -> ChatModel | None:
         async with get_async_db_context(db) as session:
             chat = ChatModel(
@@ -433,6 +552,7 @@ class ChatTable:
                     'chat': self._clean_null_bytes(form_data.chat),
                     'folder_id': form_data.folder_id,
                     'meta': internal_meta or {},
+                    'timer_at': timer_at,
                     'variables': form_data.variables or {},
                     'current_message_id': self.get_current_message_id(form_data.chat),
                     'created_at': int(time.time()),
@@ -523,6 +643,7 @@ class ChatTable:
                 'meta': form_data.meta,
                 'variables': form_data.variables or {},
                 'pinned': form_data.pinned,
+                'archived': form_data.archived,
                 'folder_id': form_data.folder_id,
                 'current_message_id': form_data.current_message_id or self.get_current_message_id(form_data.chat),
                 'created_at': (form_data.created_at if form_data.created_at else int(time.time())),
@@ -596,17 +717,29 @@ class ChatTable:
         *,
         touch: bool = True,
     ) -> ChatModel | None:
-        """Persist updated chat content, sanitizing null bytes."""
+        """Patch top-level chat keys; history is merged so stale writers don't drop messages."""
-        try:  # load the chat record for in-place mutation
+        try:
             async with get_async_db_context(db) as session:
-                chat_item = await session.get(Chat, id)
+                chat_item = await session.get(
+                    Chat,
+                    id,
+                    populate_existing=True,
+                    with_for_update=session.bind.dialect.name == 'postgresql',
+                )
                 if chat_item is None:
                     return None
 
-                chat_item.chat = self._clean_null_bytes(chat)
+                stored = chat_item.chat or {}
-                chat_item.title = self._clean_null_bytes(chat['title']) if 'title' in chat else 'New Chat'
+                updated = {**stored, **chat}
+                if 'history' in chat:
+                    # The caller built its history from an earlier read; merge so messages saved since then survive.
+                    updated['history'] = self.merge_history(stored.get('history'), chat['history'])
+
+                updated = self._clean_null_bytes(updated)
+                chat_item.chat = updated
+                chat_item.title = updated.get('title', 'New Chat')
                 if any(key in chat for key in ('history', 'messages', 'currentId', 'branchPointMessageId')):
-                    chat_item.current_message_id = self.get_current_message_id(chat)
+                    chat_item.current_message_id = self.get_current_message_id(updated)
 
                 if touch:
                     chat_item.updated_at = int(time.time())
@@ -713,7 +846,12 @@ class ChatTable:
     async def update_chat_title_by_id(self, id: str, title: str) -> ChatModel | None:
         try:
             async with get_async_db_context() as session:
-                chat_item = await session.get(Chat, id)
+                chat_item = await session.get(
+                    Chat,
+                    id,
+                    populate_existing=True,
+                    with_for_update=session.bind.dialect.name == 'postgresql',
+                )
                 if chat_item is None:
                     return None
                 clean_title = self._clean_null_bytes(title)
@@ -774,11 +912,12 @@ class ChatTable:
     def merge_history(existing_history: dict | None, incoming_history: dict | None) -> dict:
         existing = (existing_history or {}).get('messages') or {}
         incoming = (incoming_history or {}).get('messages') or {}
-        merged = {**existing, **incoming}
+        merged = {
-        merged = {message_id: message for message_id, message in merged.items() if isinstance(message, dict)}
+            message_id: {**message, 'childrenIds': []}
+            for message_id, message in {**existing, **incoming}.items()
+            if isinstance(message, dict)
+        }
 
-        for message in merged.values():
-            message['childrenIds'] = []
         for message_id, message in merged.items():
             parent_id = message.get('parentId')
             if parent_id in merged:
@@ -826,8 +965,10 @@ class ChatTable:
             if current_id is None
             else messages.get(current_id, {}).get('childrenIds', [])
         )
-        while child_ids:
+        visited_ids = set()
+        while child_ids and child_ids[-1] not in visited_ids:
             current_id = child_ids[-1]
+            visited_ids.add(current_id)
             child_ids = messages.get(current_id, {}).get('childrenIds', [])
         history['currentId'] = current_id if current_id in messages else None
         return deleted_ids
@@ -874,26 +1015,24 @@ class ChatTable:
                 'role': role,
                 'timestamp': message.get('timestamp') or int(time.time()),
             }
+            history['currentId'] = message_id
 
-        history['currentId'] = message_id
+        ChatTable._add_child_id_to_parent(messages, messages[message_id].get('parentId'), message_id)
         return messages[message_id]
 
     async def backfill_messages_by_chat_id(self, chat_id: str, user_id: str, messages: dict[str, dict]) -> None:
         """Write messages to the ``chat_message`` table so future lookups
         use the fast path.  Errors are logged but never raised.
         """
-        for message_id, message in messages.items():
+        writable = {
-            if not isinstance(message, dict) or not message.get('role'):
+            message_id: message
-                continue
+            for message_id, message in messages.items()
-            try:
+            if isinstance(message, dict) and message.get('role')
-                await ChatMessages.upsert_message(
+        }
-                    message_id=message_id,
+        try:
-                    chat_id=chat_id,
+            await ChatMessages.upsert_messages(chat_id, user_id, writable)
-                    user_id=user_id,
+        except Exception as e:
-                    data=message,
+            log.warning('Backfill failed for chat %s: %s', chat_id, e)
-                )
-            except Exception as e:
-                log.warning('Backfill failed for message %s in chat %s: %s', message_id, chat_id, e)
 
     async def reconcile_messages_by_chat_id(self, chat_id: str, user_id: str, messages: dict[str, dict]) -> None:
         """Sync ``chat_message`` rows with the committed JSON blob.
@@ -960,11 +1099,44 @@ class ChatTable:
         return history_messages
 
     async def get_message_by_id_and_message_id(self, id: str, message_id: str) -> dict | None:
-        chat = await self.get_chat_by_id(id)
+        messages_map = await ChatMessages.get_messages_map_by_chat_id(id)
+        if messages_map and message_id in messages_map:
+            return messages_map[message_id]
+
+        # Messages the frontend saved straight into the chat blob have no chat_message row yet.
+        async with get_async_db_context() as session:
+            result = await session.execute(select(Chat.chat[('history', 'messages')]).filter_by(id=id))
+            row = result.one_or_none()
+
+        if row is None:
+            return None
+
+        messages = row[0] or {}
+        return self._clean_null_bytes(messages.get(message_id, {}))
+
+    async def get_message_metadata(
+        self,
+        chat_id: str,
+        message_id: str,
+        metadata_key: Literal['files', 'sources', 'embeds'],
+    ) -> Any | None:
+        """Read one message metadata field without rebuilding the whole history."""
+        async with get_async_db_context() as db:
+            # Read the column directly; some stored rows cannot be validated as full ChatMessageModel objects.
+            result = await db.execute(
+                select(getattr(ChatMessage, metadata_key)).where(ChatMessage.id == f'{chat_id}-{message_id}')
+            )
+            metadata_row = result.first()
+
+        if metadata_row is not None:
+            return metadata_row[0]
+
+        chat = await self.get_chat_by_id(chat_id)
         if chat is None:
             return None
 
-        return chat.chat.get('history', {}).get('messages', {}).get(message_id, {})
+        message = chat.chat.get('history', {}).get('messages', {}).get(message_id, {})
+        return message.get(metadata_key)
 
     async def upsert_message_to_chat_by_id_and_message_id(
         self, id: str, message_id: str, message: dict, *, touch: bool = True
@@ -974,27 +1146,29 @@ class ChatTable:
             if output_text:
                 message['content'] = output_text
 
-        # Sanitize message content for null characters before upserting
+        message = self._clean_null_bytes(message)
-        if isinstance(message.get('content'), str):
+        message_id = self._clean_null_bytes(message_id)
-            message['content'] = sanitize_text_for_db(message['content'])
 
         try:
             async with get_async_db_context() as session:
-                chat_item = await session.get(Chat, id)
+                chat_item = await session.get(
+                    Chat,
+                    id,
+                    populate_existing=True,
+                    with_for_update=session.bind.dialect.name == 'postgresql',
+                )
                 if chat_item is None:
                     return None
 
-                self._sanitize_chat_row(chat_item)
                 chat = chat_item.chat or {}
                 self._repair_chat_current_id(chat)
 
                 history = chat.get('history', {})
                 saved_message = self.upsert_message_to_history(history, message_id, message)
                 chat['history'] = history
-                clean_chat = self._clean_null_bytes(chat)
+                chat_item.chat = chat  # chat is a fresh dict when the column was empty
-                chat_item.chat = clean_chat
+                chat_item.title = self._clean_null_bytes(chat.get('title', 'New Chat'))
-                chat_item.title = self._clean_null_bytes(clean_chat['title']) if 'title' in clean_chat else 'New Chat'
+                chat_item.current_message_id = self.get_current_message_id(chat)
-                chat_item.current_message_id = self.get_current_message_id(clean_chat)
                 flag_modified(chat_item, 'chat')
 
                 if touch:
@@ -1022,33 +1196,33 @@ class ChatTable:
     async def delete_message_from_chat_by_id_and_message_id(self, id: str, message_id: str) -> ChatModel | None:
         try:
             async with get_async_db_context() as session:
-                chat_item = await session.get(Chat, id)
+                chat_item = await session.get(
+                    Chat,
+                    id,
+                    populate_existing=True,
+                    with_for_update=session.bind.dialect.name == 'postgresql',
+                )
                 if chat_item is None:
                     return None
 
-                self._sanitize_chat_row(chat_item)
                 chat = chat_item.chat or {}
                 self._repair_chat_current_id(chat)
 
                 history = chat.get('history', {})
                 deleted_ids = self.delete_message_from_history(history, message_id)
                 if not deleted_ids:
-                    clean_chat = self._clean_null_bytes(chat)
+                    chat_item.chat = chat
-                    chat_item.chat = clean_chat
+                    chat_item.title = self._clean_null_bytes(chat.get('title', 'New Chat'))
-                    chat_item.title = (
+                    chat_item.current_message_id = self.get_current_message_id(chat)
-                        self._clean_null_bytes(clean_chat['title']) if 'title' in clean_chat else 'New Chat'
-                    )
-                    chat_item.current_message_id = self.get_current_message_id(clean_chat)
                     flag_modified(chat_item, 'chat')
                     await session.commit()
                     return ChatModel.model_validate(chat_item)
 
                 messages = history.get('messages') or {}
                 chat['history'] = history
-                clean_chat = self._clean_null_bytes(chat)
+                chat_item.chat = chat
-                chat_item.chat = clean_chat
+                chat_item.title = self._clean_null_bytes(chat.get('title', 'New Chat'))
-                chat_item.title = self._clean_null_bytes(clean_chat['title']) if 'title' in clean_chat else 'New Chat'
+                chat_item.current_message_id = self.get_current_message_id(chat)
-                chat_item.current_message_id = self.get_current_message_id(clean_chat)
                 flag_modified(chat_item, 'chat')
                 chat_item.updated_at = int(time.time())
                 await session.commit()
@@ -1066,12 +1240,17 @@ class ChatTable:
         self, id: str, message_id: str, status: dict
     ) -> ChatModel | None:
         try:
+            status = self._clean_null_bytes(status)
             async with get_async_db_context() as session:
-                chat_item = await session.get(Chat, id)
+                chat_item = await session.get(
+                    Chat,
+                    id,
+                    populate_existing=True,
+                    with_for_update=session.bind.dialect.name == 'postgresql',
+                )
                 if chat_item is None:
                     return None
 
-                self._sanitize_chat_row(chat_item)
                 chat = chat_item.chat or {}
                 self._repair_chat_current_id(chat)
                 history = chat.get('history', {})
@@ -1082,10 +1261,9 @@ class ChatTable:
                     history['messages'][message_id]['statusHistory'] = status_history
 
                 chat['history'] = history
-                clean_chat = self._clean_null_bytes(chat)
+                chat_item.chat = chat
-                chat_item.chat = clean_chat
+                chat_item.title = self._clean_null_bytes(chat.get('title', 'New Chat'))
-                chat_item.title = self._clean_null_bytes(clean_chat['title']) if 'title' in clean_chat else 'New Chat'
+                chat_item.current_message_id = self.get_current_message_id(chat)
-                chat_item.current_message_id = self.get_current_message_id(clean_chat)
                 flag_modified(chat_item, 'chat')
                 await session.commit()
 
@@ -1093,13 +1271,20 @@ class ChatTable:
         except Exception:
             return None
 
-    async def add_message_files_by_id_and_message_id(self, id: str, message_id: str, files: list[dict]) -> list[dict]:
+    async def add_message_files_by_id_and_message_id(
+        self, id: str, message_id: str, files: list[dict]
+    ) -> list[dict] | None:
         async with get_async_db_context() as session:
-            chat = await self.get_chat_by_id(id, db=session)
+            chat_item = await session.get(
-            if chat is None:
+                Chat,
+                id,
+                populate_existing=True,
+                with_for_update=session.bind.dialect.name == 'postgresql',
+            )
+            if chat_item is None:
                 return None
 
-            chat = chat.chat
+            chat = chat_item.chat or {}
             history = chat.get('history', {})
 
             message_files = []
@@ -1109,8 +1294,14 @@ class ChatTable:
                 message_files = message_files + files
                 history['messages'][message_id]['files'] = message_files
 
+            # Written here rather than through update_chat_by_id: with session sharing off that opens a second
+            # connection, which then blocks on the lock this one holds.
             chat['history'] = history
-            await self.update_chat_by_id(id, chat, db=session)
+            chat_item.chat = self._clean_null_bytes(chat)
+            # History was mutated in place, so the new blob compares equal to the loaded one.
+            flag_modified(chat_item, 'chat')
+            chat_item.updated_at = int(time.time())
+            await session.commit()
             return message_files
 
     async def insert_shared_chat_by_chat_id(self, chat_id: str, db: AsyncSession | None = None) -> ChatModel | None:
@@ -1508,6 +1699,7 @@ class ChatTable:
 
                 repaired_history = self._repair_chat_current_id(chat_item.chat or {})
                 if repaired_history:
+                    chat_item.current_message_id = self.get_current_message_id(chat_item.chat)
                     flag_modified(chat_item, 'chat')
                 if self._sanitize_chat_row(chat_item) or repaired_history:
                     await session.commit()
@@ -1549,6 +1741,7 @@ class ChatTable:
 
                 repaired_history = self._repair_chat_current_id(chat.chat or {})
                 if repaired_history:
+                    chat.current_message_id = self.get_current_message_id(chat.chat)
                     flag_modified(chat, 'chat')
                 if self._sanitize_chat_row(chat) or repaired_history:
                     await session.commit()
@@ -1557,6 +1750,41 @@ class ChatTable:
         except Exception:
             return None
 
+    async def get_chat_by_id_for_user(
+        self,
+        id: str,
+        user,
+        db: AsyncSession | None = None,
+    ) -> ChatModel | None:
+        chat = await self.get_chat_by_id_and_user_id(id, user.id, db=db)
+        if chat:
+            return chat
+
+        chat = await self.get_chat_by_id(id, db=db)
+        if not chat:
+            return None
+
+        if user.role == 'admin' and (ENABLE_ADMIN_CHAT_ACCESS or is_internal_chat(chat.meta)):
+            return chat
+
+        if await AccessGrants.has_access(
+            user_id=user.id,
+            resource_type='shared_chat',
+            resource_id=id,
+            permission='read',
+            db=db,
+        ):
+            return chat
+
+        if chat.folder_id:
+            from open_webui.utils.access_control.folders import has_folder_access
+
+            folder = await Folders.get_folder_by_id(chat.folder_id, db=db)
+            if folder and await has_folder_access(user.id, folder, 'read', db):
+                return chat
+
+        return None
+
     async def is_chat_owner(self, id: str, user_id: str, db: AsyncSession | None = None) -> bool:
         """
         Lightweight ownership check — uses EXISTS subquery instead of loading
@@ -1732,7 +1960,7 @@ class ChatTable:
             return [ChatModel.model_validate(chat) for chat in result.scalars().all()]
 
     # search user conversations
-    async def get_chats_by_user_id_and_search_text(
+    async def get_chats_by_user_id_and_search_text(  # noqa: C901
         self,
         user_id: str,
         search_text: str,
@@ -1751,7 +1979,7 @@ class ChatTable:
                 user_id, include_archived, filter={}, skip=skip, limit=limit, db=db
             )
 
-        search_text_words = search_text.split(' ')
+        search_text_words = search_text.split()
 
         # search_text might contain 'tag:tag_name' format so we need to extract the tag_name
         tag_ids = [
@@ -1759,10 +1987,8 @@ class ChatTable:
         ]
 
         # Extract folder names
-        folders = await Folders.search_folders_by_names(
+        folder_names = [word.replace('folder:', '') for word in search_text_words if word.startswith('folder:')]
-            user_id,
+        folders = await Folders.search_folders_by_names(user_id, folder_names)
-            [word.replace('folder:', '') for word in search_text_words if word.startswith('folder:')],
-        )
         folder_ids = [folder.id for folder in folders]
 
         is_pinned = None
@@ -1783,19 +2009,10 @@ class ChatTable:
         elif 'shared:false' in search_text_words:
             is_shared = False
 
-        search_text_words = [
+        search_text_words = [word for word in search_text_words if not word.startswith(CHAT_SEARCH_FILTER_PREFIXES)]
-            word
-            for word in search_text_words
-            if (
-                not word.startswith('tag:')
-                and not word.startswith('folder:')
-                and not word.startswith('pinned:')
-                and not word.startswith('archived:')
-                and not word.startswith('shared:')
-            )
-        ]
 
-        search_text = ' '.join(search_text_words)
+        phrase_query = ' '.join(search_text_words).strip()
+        search_terms = chat_search_terms(phrase_query)
 
         async with get_async_db_context(db) as session:
             stmt = select(Chat).filter(Chat.user_id == user_id)
@@ -1815,30 +2032,46 @@ class ChatTable:
                 else:
                     stmt = stmt.filter(Chat.share_id.is_(None))
 
-            if folder_ids:
+            if folder_names:
                 stmt = stmt.filter(Chat.folder_id.in_(folder_ids))
 
-            stmt = stmt.order_by(Chat.updated_at.desc(), Chat.id)
-
             # Check if the database dialect is either 'sqlite' or 'postgresql'
             bind = await session.connection()
             dialect_name = bind.dialect.name
-            if dialect_name == 'sqlite':
+
-                # SQLite case: using JSON1 extension for JSON searching
+            search_params = {}
-                sqlite_content_sql = (
+            exact_match_clause = None
-                    'EXISTS ('
+            if phrase_query:
-                    '    SELECT 1 '
+                exact_match_clause = or_(
-                    "    FROM json_each(Chat.chat, '$.messages') AS message "
+                    Chat.title.ilike(bindparam('phrase_title_key')),
-                    "    WHERE LOWER(message.value->>'content') LIKE '%' || :content_key || '%'"
+                    text(chat_search_message_content_match_sql(dialect_name, 'phrase_content_key')),
-                    ')'
                 )
-                sqlite_content_clause = text(sqlite_content_sql)
+                search_params.update(
-                stmt = stmt.filter(
+                    {
-                    or_(Chat.title.ilike(bindparam('title_key')), sqlite_content_clause).params(
+                        'phrase_title_key': f'%{phrase_query}%',
-                        title_key=f'%{search_text}%', content_key=search_text
+                        'phrase_content_key': phrase_query,
-                    )
+                    }
                 )
 
+                term_clauses = []
+                for term_idx, term in enumerate(search_terms):
+                    title_key = f'term_title_key_{term_idx}'
+                    content_key = f'term_content_key_{term_idx}'
+                    term_clauses.append(
+                        or_(
+                            Chat.title.ilike(bindparam(title_key)),
+                            text(chat_search_message_content_match_sql(dialect_name, content_key)),
+                        )
+                    )
+                    search_params[title_key] = f'%{term}%'
+                    search_params[content_key] = term
+
+                if term_clauses:
+                    stmt = stmt.filter(or_(exact_match_clause, and_(*term_clauses)))
+                else:
+                    stmt = stmt.filter(exact_match_clause)
+
+            if dialect_name == 'sqlite':
                 # Check if there are any tags to filter
                 if 'none' in tag_ids:
                     stmt = stmt.filter(
@@ -1872,38 +2105,6 @@ class ChatTable:
                 # Safety filter: title must not contain actual null bytes
                 stmt = stmt.filter(text("Chat.title::text NOT LIKE '%\\x00%'"))
 
-                postgres_content_sql = """
-                EXISTS (
-                    SELECT 1
-                    FROM chat_message AS message
-                    WHERE message.chat_id = Chat.id
-                    AND message.user_id = Chat.user_id
-                    AND json_typeof(message.content) = 'string'
-                    AND LOWER(message.content #>> '{}') LIKE '%' || :content_key || '%'
-                )
-                OR EXISTS (
-                    SELECT 1
-                    FROM json_each(Chat.chat#>'{history,messages}') AS history_message
-                    WHERE json_typeof(history_message.value->'content') = 'string'
-                    AND LOWER(history_message.value->>'content') LIKE '%' || :content_key || '%'
-                )
-                OR EXISTS (
-                    SELECT 1
-                    FROM json_array_elements(Chat.chat->'messages') AS legacy_message
-                    WHERE json_typeof(legacy_message->'content') = 'string'
-                    AND LOWER(legacy_message->>'content') LIKE '%' || :content_key || '%'
-                )
-                """
-
-                postgres_content_clause = text(postgres_content_sql)
-
-                stmt = stmt.filter(
-                    or_(
-                        Chat.title.ilike(bindparam('title_key')),
-                        postgres_content_clause,
-                    )
-                ).params(title_key=f'%{search_text}%', content_key=search_text.lower())
-
                 if 'none' in tag_ids:
                     stmt = stmt.filter(
                         text("""
@@ -1931,12 +2132,20 @@ class ChatTable:
             else:
                 raise NotImplementedError(f'Unsupported dialect: {dialect_name}')
 
+            if exact_match_clause is not None:
+                stmt = stmt.order_by(case((exact_match_clause, 0), else_=1), Chat.updated_at.desc(), Chat.id)
+            else:
+                stmt = stmt.order_by(Chat.updated_at.desc(), Chat.id)
+
+            if search_params:
+                stmt = stmt.params(**search_params)
+
             # Perform pagination at the SQL level
             stmt = stmt.offset(skip).limit(limit)
             result = await session.execute(stmt)
             all_chats = result.scalars().all()
 
-            log.info(f'The number of chats: {len(all_chats)}')
+            log.info('The number of chats: %s', len(all_chats))
 
             # Validate and return chats
             return [ChatModel.model_validate(chat) for chat in all_chats]
@@ -2101,7 +2310,7 @@ class ChatTable:
 
             bind = await session.connection()
             dialect_name = bind.dialect.name
-            log.info(f'DB dialect name: {dialect_name}')
+            log.info('DB dialect name: %s', dialect_name)
             if dialect_name == 'sqlite':
                 stmt = stmt.filter(
                     text(f"EXISTS (SELECT 1 FROM json_each(Chat.meta, '$.tags') WHERE json_each.value = :tag_id)")
@@ -2228,7 +2437,7 @@ class ChatTable:
             result = await session.execute(stmt.where(Chat.meta['internal'].as_boolean().is_not(True)))
             count = result.scalar()
 
-            log.info(f"Count of chats for folder '{folder_id}': {count}")
+            log.info("Count of chats for folder '%s': %s", folder_id, count)
             return count
 
     async def count_chats_by_folder_ids_and_user_id(
@@ -2242,7 +2451,7 @@ class ChatTable:
             result = await session.execute(stmt.where(Chat.meta['internal'].as_boolean().is_not(True)))
             count = result.scalar()
 
-            log.info(f"Count of chats for folders '{folder_ids}': {count}")
+            log.info("Count of chats for folders '%s': %s", folder_ids, count)
             return count
 
     async def delete_tag_by_id_and_user_id_and_tag_name(
@@ -2326,18 +2535,15 @@ class ChatTable:
         except Exception:
             return False
 
-    async def move_chats_by_user_id_and_folder_id(
+    async def move_chats_by_folder_id(
         self,
-        user_id: str,
         folder_id: str,
         new_folder_id: str | None,
         db: AsyncSession | None = None,
     ) -> bool:
         try:
             async with get_async_db_context(db) as session:
-                await session.execute(
+                await session.execute(update(Chat).filter_by(folder_id=folder_id).values(folder_id=new_folder_id))
-                    update(Chat).filter_by(user_id=user_id, folder_id=folder_id).values(folder_id=new_folder_id)
-                )
                 await session.commit()
 
                 return True
@@ -2369,7 +2575,7 @@ class ChatTable:
         file_ids: list[str],
         user_id: str,
         db: AsyncSession | None = None,
-    ) -> list[ChatFileModel | None]:
+    ) -> list[ChatFileModel] | None:
         if not file_ids:
             return None
 

backend/open_webui/models/config.py

@@ -32,6 +32,8 @@ DICT_CONFIG_KEY_ALIASES = {
     'audio.tts.openai.params': ('AUDIO_TTS_OPENAI_PARAMS',),
     'models.default_metadata': ('DEFAULT_MODEL_METADATA',),
     'models.default_params': ('DEFAULT_MODEL_PARAMS',),
+    'task.model.params': ('TASK_MODEL_PARAMS',),
+    'ui.default_interface_settings': ('DEFAULT_INTERFACE_SETTINGS',),
     'user.permissions': ('USER_PERMISSIONS',),
 }
 DICT_CONFIG_KEYS = tuple(DICT_CONFIG_KEY_ALIASES)
@@ -298,14 +300,16 @@ class Config(Base):
             )
 
     @staticmethod
-    async def repair_flattened_dict_configs() -> None:
+    async def repair_config_rows() -> None:
-        """Reassemble dict config values flattened by the per-key migration."""
+        """Repair known legacy config row shapes."""
         if not Config.PERSISTENT_ENABLED:
             return
 
         async with get_async_db() as db:
             repaired_keys: list[str] = []
             orphan_keys: list[str] = []
+            default_model_keys: list[str] = []
+            now = int(time.time())
 
             for config_key, aliases in DICT_CONFIG_KEY_ALIASES.items():
                 prefixes = (config_key, *aliases)
@@ -353,14 +357,26 @@ class Config(Base):
 
                 if existing:
                     existing.value = repaired
-                    existing.updated_at = int(time.time())
+                    existing.updated_at = now
                 else:
-                    db.add(Config(key=config_key, value=repaired, updated_at=int(time.time())))
+                    db.add(Config(key=config_key, value=repaired, updated_at=now))
                 repaired_keys.append(config_key)
 
             if orphan_keys:
                 await db.execute(delete(Config).where(Config.key.in_(orphan_keys)))
 
-            if repaired_keys or orphan_keys:
+            for key in ('ui.default_models', 'ui.default_pinned_models'):
+                row = await db.get(Config, key)
+                if not row or not isinstance(row.value, list):
+                    continue
+
+                row.value = ','.join(model_id for model_id in (str(item).strip() for item in row.value) if model_id)
+                row.updated_at = now
+                default_model_keys.append(key)
+
+            if repaired_keys or orphan_keys or default_model_keys:
                 await db.commit()
-                log.info('Repaired flattened dict config rows for %s', ', '.join(repaired_keys))
+                if repaired_keys or orphan_keys:
+                    log.info('Repaired flattened dict config rows for %s', ', '.join(repaired_keys))
+                if default_model_keys:
+                    log.info('Repaired default model config rows for %s', ', '.join(default_model_keys))

backend/open_webui/models/folders.py

@@ -157,6 +157,11 @@ class FolderTable:
         except Exception:
             return None
 
+    async def get_folders_by_ids(self, ids: list[str], db: AsyncSession | None = None) -> list[FolderModel]:
+        async with get_async_db_context(db) as db:
+            result = await db.execute(select(Folder).filter(Folder.id.in_(ids)).order_by(Folder.updated_at.desc()))
+            return [FolderModel.model_validate(folder) for folder in result.scalars().all()]
+
     async def get_shared_folder_ids_for_user(
         self, user_id: str, user_group_ids: set[str], db: Optional[AsyncSession] = None
     ) -> dict[str, str]:
@@ -197,10 +202,14 @@ class FolderTable:
         try:
             async with get_async_db_context(db) as db:
                 folders = []
+                seen_ids = {id}
 
                 async def get_children(folder):
                     children = await self.get_folders_by_parent_id_and_user_id(folder.id, user_id, db=db)
                     for child in children:
+                        if child.id in seen_ids:
+                            continue
+                        seen_ids.add(child.id)
                         await get_children(child)
                         folders.append(child)
 
@@ -230,7 +239,9 @@ class FolderTable:
             async with get_async_db_context(db) as db:
                 # Check if folder exists
                 result = await db.execute(
-                    select(Folder).filter_by(parent_id=parent_id, user_id=user_id).filter(Folder.name.ilike(name))
+                    select(Folder)
+                    .filter_by(parent_id=parent_id, user_id=user_id)
+                    .filter(func.lower(Folder.name) == func.lower(name))
                 )
                 folder = result.scalars().first()
 
@@ -246,7 +257,9 @@ class FolderTable:
         self, parent_id: Optional[str], user_id: str, db: Optional[AsyncSession] = None
     ) -> list[FolderModel]:
         async with get_async_db_context(db) as db:
-            result = await db.execute(select(Folder).filter_by(parent_id=parent_id, user_id=user_id))
+            result = await db.execute(
+                select(Folder).filter_by(parent_id=parent_id, user_id=user_id).order_by(Folder.updated_at.desc())
+            )
             return [FolderModel.model_validate(folder) for folder in result.scalars().all()]
 
     async def get_folder_ids_by_id_and_user_id_in_subtree(
@@ -258,15 +271,17 @@ class FolderTable:
             if not folder:
                 return []
 
-            folder_ids = [folder.id]
+            folder_ids = {folder.id}
             folders = [FolderModel.model_validate(folder)]
             while folders:
                 current_folder = folders.pop()
                 children = await self.get_folders_by_parent_id_and_user_id(current_folder.id, user_id, db=db)
-                folder_ids.extend(child.id for child in children)
+                for child in children:
-                folders.extend(children)
+                    if child.id not in folder_ids:
+                        folder_ids.add(child.id)
+                        folders.append(child)
 
-            return folder_ids
+            return list(folder_ids)
 
     async def update_folder_parent_id_by_id_and_user_id(
         self,
@@ -376,11 +391,15 @@ class FolderTable:
                     return folder_ids
 
                 folder_ids.append(folder.id)
+                seen_ids = {folder.id}
 
                 # Delete all children folders
                 async def delete_children(folder):
                     folder_children = await self.get_folders_by_parent_id_and_user_id(folder.id, user_id, db=db)
                     for folder_child in folder_children:
+                        if folder_child.id in seen_ids:
+                            continue
+                        seen_ids.add(folder_child.id)
                         await delete_children(folder_child)
                         folder_ids.append(folder_child.id)
 

backend/open_webui/models/groups.py

@@ -1,4 +1,3 @@
-import json
 import logging
 import time
 import uuid
@@ -13,6 +12,7 @@ from sqlalchemy import (
     BigInteger,
     Column,
     ForeignKey,
+    Index,
     String,
     Text,
     and_,
@@ -72,6 +72,8 @@ class GroupModel(BaseModel):
 
 class GroupMember(Base):
     __tablename__ = 'group_member'
+    # The table's (group_id, user_id) unique constraint cannot serve user_id lookups.
+    __table_args__ = (Index('ix_group_member_user_id_group_id', 'user_id', 'group_id'),)
 
     id = Column(Text, unique=True, primary_key=True)
     group_id = Column(

backend/open_webui/models/knowledge.py

@@ -1,4 +1,3 @@
-import json
 import logging
 import time
 import uuid
@@ -468,14 +467,22 @@ class KnowledgeTable:
             print('search_knowledge_files error:', e)
             return KnowledgeFileListResponse(items=[], total=0)
 
-    async def check_access_by_user_id(self, id, user_id, permission='write', db: Optional[AsyncSession] = None) -> bool:
+    async def check_access_by_user_id(
+        self,
+        id,
+        user_id,
+        permission='write',
+        db: Optional[AsyncSession] = None,
+        user_group_ids: set[str] | None = None,
+    ) -> bool:
         knowledge = await self.get_knowledge_by_id(id, db=db)
         if not knowledge:
             return False
         if knowledge.user_id == user_id:
             return True
-        user_groups = await Groups.get_groups_by_member_id(user_id, db=db)
+        if user_group_ids is None:
-        user_group_ids = {group.id for group in user_groups}
+            user_groups = await Groups.get_groups_by_member_id(user_id, db=db)
+            user_group_ids = {group.id for group in user_groups}
         return await AccessGrants.has_access(
             user_id=user_id,
             resource_type='knowledge',
@@ -485,24 +492,6 @@ class KnowledgeTable:
             db=db,
         )
 
-    async def get_knowledge_bases_by_user_id(
-        self, user_id: str, permission: str = 'write', db: Optional[AsyncSession] = None
-    ) -> list[KnowledgeUserModel]:
-        knowledge_bases = await self.get_knowledge_bases(db=db)
-        user_groups = await Groups.get_groups_by_member_id(user_id, db=db)
-        user_group_ids = {group.id for group in user_groups}
-
-        # One grants query for all non-owned knowledge bases instead of one each
-        accessible_ids = await AccessGrants.get_accessible_resource_ids(
-            user_id=user_id,
-            resource_type='knowledge',
-            resource_ids=[kb.id for kb in knowledge_bases if kb.user_id != user_id],
-            permission=permission,
-            user_group_ids=user_group_ids,
-            db=db,
-        )
-        return [kb for kb in knowledge_bases if kb.user_id == user_id or kb.id in accessible_ids]
-
     async def get_knowledge_by_id(self, id: str, db: Optional[AsyncSession] = None) -> Optional[KnowledgeModel]:
         try:
             async with get_async_db_context(db) as db:
@@ -512,29 +501,6 @@ class KnowledgeTable:
         except Exception:
             return None
 
-    async def get_knowledge_by_id_and_user_id(
-        self, id: str, user_id: str, db: Optional[AsyncSession] = None
-    ) -> Optional[KnowledgeModel]:
-        knowledge = await self.get_knowledge_by_id(id, db=db)
-        if not knowledge:
-            return None
-
-        if knowledge.user_id == user_id:
-            return knowledge
-
-        user_groups = await Groups.get_groups_by_member_id(user_id, db=db)
-        user_group_ids = {group.id for group in user_groups}
-        if await AccessGrants.has_access(
-            user_id=user_id,
-            resource_type='knowledge',
-            resource_id=knowledge.id,
-            permission='write',
-            user_group_ids=user_group_ids,
-            db=db,
-        ):
-            return knowledge
-        return None
-
     async def get_knowledges_by_file_id(self, file_id: str, db: Optional[AsyncSession] = None) -> list[KnowledgeModel]:
         try:
             async with get_async_db_context(db) as db:
@@ -659,6 +625,7 @@ class KnowledgeTable:
                         db=db,
                     ),
                     breadcrumbs=await self.get_directory_breadcrumbs(
+                        knowledge_id,
                         filter.get('directory_id') if filter else None,
                         db=db,
                     ),
@@ -809,25 +776,6 @@ class KnowledgeTable:
             log.exception(e)
             return None
 
-    async def update_knowledge_data_by_id(
-        self, id: str, data: dict, db: Optional[AsyncSession] = None
-    ) -> Optional[KnowledgeModel]:
-        try:
-            async with get_async_db_context(db) as db:
-                await db.execute(
-                    update(Knowledge)
-                    .filter_by(id=id)
-                    .values(
-                        data=data,
-                        updated_at=int(time.time()),
-                    )
-                )
-                await db.commit()
-                return await self.get_knowledge_by_id(id=id, db=db)
-        except Exception as e:
-            log.exception(e)
-            return None
-
     async def update_knowledge_meta_by_id(
         self, id: str, meta: dict, db: Optional[AsyncSession] = None
     ) -> Optional[KnowledgeModel]:
@@ -961,6 +909,7 @@ class KnowledgeTable:
 
     async def get_directory_breadcrumbs(
         self,
+        knowledge_id: str,
         directory_id: Optional[str],
         db: Optional[AsyncSession] = None,
     ) -> list[KnowledgeDirectoryModel]:
@@ -975,7 +924,10 @@ class KnowledgeTable:
 
             while current_id and current_id not in seen:
                 seen.add(current_id)
-                result = await db.execute(select(KnowledgeDirectory).filter_by(id=current_id))
+                # Scoped by knowledge base so a caller-supplied id cannot walk another one's tree.
+                result = await db.execute(
+                    select(KnowledgeDirectory).filter_by(id=current_id, knowledge_id=knowledge_id)
+                )
                 directory = result.scalars().first()
                 if not directory:
                     break
@@ -1122,6 +1074,26 @@ class KnowledgeTable:
         for child_id in child_ids:
             await self._delete_files_in_subtree(child_id, db=db)
 
+    async def get_files_by_id_and_directory_id(
+        self,
+        knowledge_id: str,
+        directory_id: str,
+        db: Optional[AsyncSession] = None,
+    ) -> list[FileModel]:
+        """Get all files in a directory and its subdirectories."""
+        async with get_async_db_context(db) as db:
+            directory_ids = [directory_id]
+            for parent_id in directory_ids:
+                result = await db.execute(select(KnowledgeDirectory.id).filter_by(parent_id=parent_id))
+                directory_ids.extend(result.scalars().all())
+            result = await db.execute(
+                select(File)
+                .join(KnowledgeFile, File.id == KnowledgeFile.file_id)
+                .filter(KnowledgeFile.knowledge_id == knowledge_id)
+                .filter(KnowledgeFile.directory_id.in_(directory_ids))
+            )
+            return [FileModel.model_validate(file) for file in result.scalars().all()]
+
     async def move_file_to_directory(
         self,
         knowledge_id: str,

backend/open_webui/models/messages.py

@@ -1,4 +1,3 @@
-import json
 import time
 import uuid
 from typing import Optional

backend/open_webui/models/models.py

@@ -1,26 +1,33 @@
 from __future__ import annotations
 
-import json
 import logging
 import time
 from copy import deepcopy
-from typing import Any, Optional
+from typing import Any
 
 from open_webui.internal.db import Base, JSONField, get_async_db_context
 from open_webui.models.access_grants import AccessGrantModel, AccessGrants
 from open_webui.models.groups import Groups
 from open_webui.models.users import User, UserModel, UserResponse, Users
-from open_webui.utils.validate import validate_profile_image_url
+from open_webui.utils.misc import json_text_variants
-from pydantic import BaseModel, ConfigDict, Field, field_validator, model_validator
+from open_webui.utils.validate import validate_image_url
+from pydantic import BaseModel, ConfigDict, Field, ValidationInfo, field_validator, model_validator
 from sqlalchemy import BigInteger, Boolean, Column, String, Text, cast, delete, func, or_, select, update
-from sqlalchemy.dialects.postgresql import JSONB
 from sqlalchemy.ext.asyncio import AsyncSession
 
 log = logging.getLogger(__name__)
 
-# Track invalid profile_image_url values we've already warned about so we
+
-# don't flood the logs on every DB read (the validator fires per-row).
+def normalize_model_tags(tags: Any) -> list[dict[str, str]]:
-_warned_profile_urls: set[str] = set()
+    if not isinstance(tags, list):
+        return []
+
+    normalized = []
+    for tag in tags:
+        name = tag.get('name') if isinstance(tag, dict) else tag
+        if isinstance(name, str) and name.strip():
+            normalized.append({'name': name.strip()})
+    return normalized
 
 
 def strip_extracted_content_from_model_knowledge(knowledge: Any) -> Any:
@@ -68,26 +75,24 @@ class ModelMeta(BaseModel):
     """Metadata for a workspace model entry (profile, description, tags, capabilities)."""
 
     profile_image_url: str | None = None
+    background_image_url: str | None = None
     description: str | None = Field(default=None, description='User-facing description of the model.')
+    i18n: dict[str, Any] | None = None
     capabilities: dict | None = None
     knowledge: list[Any] | None = None
 
     model_config = ConfigDict(extra='allow')
 
-    @field_validator('profile_image_url', mode='before')
+    @field_validator('profile_image_url', 'background_image_url', mode='before')
     @classmethod
-    def check_profile_image_url(cls, v: str | None) -> str | None:
+    def check_image_url(cls, v: str | None, info: ValidationInfo) -> str | None:
         if v is None:
             return v
         try:
-            return validate_profile_image_url(v)
+            return validate_image_url(v, file_only=info.field_name == 'background_image_url')
         except ValueError:
-            if v not in _warned_profile_urls:
+            if info.field_name == 'background_image_url':
-                _warned_profile_urls.add(v)
+                raise
-                log.warning(
-                    'Clearing invalid profile_image_url stored in DB (likely a legacy SVG data-URI): %.80s…',
-                    v,
-                )
             return None
 
     @field_validator('knowledge', mode='before')
@@ -99,15 +104,7 @@ class ModelMeta(BaseModel):
     @classmethod
     def normalize_tags(cls, data):
         if isinstance(data, dict) and 'tags' in data:
-            raw_tags = data['tags']
+            data['tags'] = normalize_model_tags(data['tags'])
-            if isinstance(raw_tags, list):
-                normalized = []
-                for tag in raw_tags:
-                    if isinstance(tag, str):
-                        normalized.append({'name': tag})
-                    elif isinstance(tag, dict) and 'name' in tag:
-                        normalized.append(tag)
-                data['tags'] = normalized
         return data
 
 
@@ -172,12 +169,12 @@ class ModelAccessListResponse(BaseModel):
 class ModelForm(BaseModel):
     model_config = ConfigDict(extra='ignore')
 
-    id: str
+    id: str = Field(pattern=r'^\S+$')
     base_model_id: str | None = None
     name: str
     meta: ModelMeta
     params: ModelParams
-    access_grants: list[dict | None] = None
+    access_grants: list[dict] | None = None
     is_active: bool = True
 
 
@@ -188,7 +185,7 @@ class ModelsTable:
     async def _to_model_model(
         self,
         model: Model,
-        access_grants: list[AccessGrantModel | None] = None,
+        access_grants: list[AccessGrantModel] | None = None,
         db: AsyncSession | None = None,
     ) -> ModelModel:
         if isinstance(model.meta, dict):
@@ -244,9 +241,24 @@ class ModelsTable:
                     log.error('Skipping model %r during get_all_models due to error: %s', model.id, exc)
             return models
 
-    async def get_models(self, db: AsyncSession | None = None) -> list[ModelUserResponse]:
+    async def get_models(
+        self, writable_by_user_id: str | None = None, db: AsyncSession | None = None, ids: list[str] | None = None
+    ) -> list[ModelUserResponse]:
         async with get_async_db_context(db) as db:
-            result = await db.execute(select(Model).filter(Model.base_model_id != None))
+            stmt = select(Model).filter(Model.base_model_id != None)
+
+            if ids is not None:
+                stmt = stmt.filter(Model.id.in_(ids))
+
+            if writable_by_user_id:
+                user_group_ids = {
+                    group.id for group in await Groups.get_groups_by_member_id(writable_by_user_id, db=db)
+                }
+                stmt = self._has_permission(
+                    db, stmt, {'user_id': writable_by_user_id, 'group_ids': user_group_ids}, permission='write'
+                )
+
+            result = await db.execute(stmt)
             all_models = result.scalars().all()
 
             user_ids = list(set(model.user_id for model in all_models))
@@ -275,6 +287,27 @@ class ModelsTable:
                 )
             return models
 
+    async def get_model_owner_ids_by_file_id(
+        self, file_id: str, db: AsyncSession | None = None, include_background: bool = False
+    ) -> dict[str, str]:
+        """Return model IDs mapped to owner IDs for models referencing the file."""
+        async with get_async_db_context(db) as db:
+            # File ids are server-generated uuids, so the text match can only over-match.
+            result = await db.execute(
+                select(Model.id, Model.user_id, Model.meta).filter(
+                    Model.base_model_id.is_not(None), cast(Model.meta, String).like(f'%{file_id}%')
+                )
+            )
+            return {
+                model_id: user_id
+                for model_id, user_id, meta in result.all()
+                if any(
+                    isinstance(item, dict) and item.get('type') == 'file' and item.get('id') == file_id
+                    for item in meta.get('knowledge') or []
+                )
+                or (include_background and meta.get('background_image_url') == f'/api/v1/files/{file_id}/content')
+            }
+
     @staticmethod
     def _meta_has_tag(meta: dict | None, tag: str) -> bool:
         if not meta:
@@ -301,28 +334,6 @@ class ModelsTable:
                 for model in all_models
             ]
 
-    async def get_models_by_user_id(
-        self,
-        user_id: str,
-        permission: str = 'write',
-        db: AsyncSession | None = None,
-        user_group_ids: set[str] | None = None,
-    ) -> list[ModelUserResponse]:
-        models = await self.get_models(db=db)
-        if user_group_ids is None:
-            user_group_ids = {group.id for group in await Groups.get_groups_by_member_id(user_id, db=db)}
-
-        # One grants query for all non-owned models instead of one per model
-        accessible_ids = await AccessGrants.get_accessible_resource_ids(
-            user_id=user_id,
-            resource_type='model',
-            resource_ids=[model.id for model in models if model.user_id != user_id],
-            permission=permission,
-            user_group_ids=user_group_ids,
-            db=db,
-        )
-        return [model for model in models if model.user_id == user_id or model.id in accessible_ids]
-
     def _has_permission(self, db, query, filter: dict, permission: str = 'read'):
         return AccessGrants.has_permission_filter(
             db=db,
@@ -374,20 +385,14 @@ class ModelsTable:
 
                 tag = filter.get('tag')
                 if tag:
-                    # SQLite stores JSON text via json.dumps(ensure_ascii=True),
+                    if db.bind.dialect.name == 'sqlite' and not tag.isascii():
-                    # so non-ASCII chars are \uXXXX-escaped. PostgreSQL native JSONB
+                        # SQLite's LOWER() is ASCII-only, so match non-ASCII tags exact-case.
-                    # stores literal Unicode. Use the right pattern for each.
+                        meta_text = cast(Model.meta, String)
-                    if db.bind.dialect.name == 'sqlite':
+                        variants = json_text_variants(tag)
-                        if tag.isascii():
-                            meta_text = func.lower(cast(Model.meta, String))
-                            pattern = f'%{json.dumps(tag.lower())}%'
-                        else:
-                            meta_text = cast(Model.meta, String)
-                            pattern = f'%{json.dumps(tag)}%'
                     else:
                         meta_text = func.lower(cast(Model.meta, String))
-                        pattern = f'%{json.dumps(tag.lower(), ensure_ascii=False)}%'
+                        variants = json_text_variants(tag.lower())
-                    stmt = stmt.filter(meta_text.like(pattern))
+                    stmt = stmt.filter(or_(*(meta_text.like(f'%"{variant}"%') for variant in variants)))
 
                 order_by = filter.get('order_by')
                 direction = filter.get('direction')
@@ -443,11 +448,13 @@ class ModelsTable:
 
             return ModelListResponse(items=models, total=total)
 
-    async def get_model_meta_by_id(self, id: str, db: AsyncSession | None = None) -> tuple[dict, int | None]:
+    async def get_model_meta_by_id(
-        """Return (meta, updated_at) for a model, skipping access grant resolution."""
+        self, id: str, db: AsyncSession | None = None
+    ) -> tuple[dict, str, int | None] | None:
+        """Return (meta, user_id, updated_at) for a model, skipping access grant resolution."""
         try:
             async with get_async_db_context(db) as db:
-                result = await db.execute(select(Model.meta, Model.updated_at).filter_by(id=id))
+                result = await db.execute(select(Model.meta, Model.user_id, Model.updated_at).filter_by(id=id))
                 return result.first()
         except Exception:
             return None
@@ -605,25 +612,16 @@ class ModelsTable:
 
                 # Update or insert models
                 for model in models:
+                    model_data = {
+                        **model.model_dump(exclude={'access_grants'}),
+                        'user_id': user_id,
+                        'updated_at': int(time.time()),
+                    }
+
                     if model.id in existing_ids:
-                        await db.execute(
+                        await db.execute(update(Model).filter_by(id=model.id).values(**model_data))
-                            update(Model)
-                            .filter_by(id=model.id)
-                            .values(
-                                **model.model_dump(exclude={'access_grants'}),
-                                user_id=user_id,
-                                updated_at=int(time.time()),
-                            )
-                        )
                     else:
-                        new_model = Model(
+                        db.add(Model(**model_data))
-                            **{
-                                **model.model_dump(exclude={'access_grants'}),
-                                'user_id': user_id,
-                                'updated_at': int(time.time()),
-                            }
-                        )
-                        db.add(new_model)
                     await AccessGrants.set_access_grants('model', model.id, model.access_grants, db=db)
 
                 # Remove models that are no longer present

backend/open_webui/models/notes.py

@@ -1,4 +1,3 @@
-import json
 import time
 import uuid
 from functools import lru_cache
@@ -8,7 +7,8 @@ from open_webui.internal.db import Base, get_async_db_context
 from open_webui.models.access_grants import AccessGrantModel, AccessGrants
 from open_webui.models.groups import Groups
 from open_webui.models.users import User, UserModel, UserResponse, Users
-from pydantic import BaseModel, ConfigDict, Field
+from open_webui.utils.json_codec import JSONCodec
+from pydantic import BaseModel, ConfigDict, Field, field_validator
 from sqlalchemy import JSON, BigInteger, Boolean, Column, ForeignKey, Text, delete, func, or_, select, update
 from sqlalchemy.ext.asyncio import AsyncSession
 
@@ -31,6 +31,32 @@ class Note(Base):
     updated_at = Column(BigInteger)
 
 
+def sanitize_note_data(data: Optional[dict]) -> Optional[dict]:
+    """Sanitize malformed note.data so content.md is always markdown text."""
+    if data is None:
+        return None
+    if not isinstance(data, dict):
+        return {'content': {'md': str(data)}}
+
+    content = data.get('content')
+    if not isinstance(content, dict) or 'md' not in content or isinstance(content.get('md'), str):
+        return data
+
+    md = content.get('md') if content.get('md') is not None else ''
+    if isinstance(md, (dict, list)):
+        md = f'```json\n{JSONCodec.dumps(md, indent=2, ensure_ascii=False)}\n```'
+    else:
+        md = str(md)
+
+    return {
+        **data,
+        'content': {
+            **content,
+            'md': md,
+        },
+    }
+
+
 class NoteModel(BaseModel):
     model_config = ConfigDict(from_attributes=True)
 
@@ -47,6 +73,11 @@ class NoteModel(BaseModel):
     created_at: int  # timestamp in epoch
     updated_at: int  # timestamp in epoch
 
+    @field_validator('data', mode='before')
+    @classmethod
+    def sanitize_data(cls, data):
+        return sanitize_note_data(data)
+
 
 class PinnedNote(Base):
     __tablename__ = 'pinned_note'
@@ -68,6 +99,11 @@ class NoteForm(BaseModel):
     meta: Optional[dict] = None
     access_grants: Optional[list[dict]] = None
 
+    @field_validator('data', mode='before')
+    @classmethod
+    def sanitize_data(cls, data):
+        return sanitize_note_data(data)
+
 
 class NoteUpdateForm(BaseModel):
     title: Optional[str] = None
@@ -75,6 +111,11 @@ class NoteUpdateForm(BaseModel):
     meta: Optional[dict] = None
     access_grants: Optional[list[dict]] = None
 
+    @field_validator('data', mode='before')
+    @classmethod
+    def sanitize_data(cls, data):
+        return sanitize_note_data(data)
+
 
 class NoteUserResponse(NoteModel):
     user: Optional[UserResponse] = None
@@ -305,6 +346,7 @@ class NoteTable:
                 return None
 
             form_data = form_data.model_dump(exclude_unset=True)
+            note.data = sanitize_note_data(note.data) or {}
 
             if 'title' in form_data:
                 note.title = form_data['title']

backend/open_webui/models/oauth_sessions.py

@@ -1,6 +1,5 @@
 import base64
 import hashlib
-import json
 import logging
 import time
 import uuid
@@ -9,6 +8,7 @@ from typing import List, Optional
 from cryptography.fernet import Fernet
 from open_webui.env import OAUTH_SESSION_TOKEN_ENCRYPTION_KEY
 from open_webui.internal.db import Base, get_async_db_context
+from open_webui.utils.json_codec import JSONCodec
 from pydantic import BaseModel, ConfigDict
 from sqlalchemy import BigInteger, Column, Index, String, Text, delete, select, update
 from sqlalchemy.ext.asyncio import AsyncSession
@@ -85,7 +85,7 @@ class OAuthSessionTable:
     def _encrypt_token(self, token) -> str:
         """Encrypt OAuth tokens for storage"""
         try:
-            token_json = json.dumps(token)
+            token_json = JSONCodec.dumps(token)
             encrypted = self.fernet.encrypt(token_json.encode()).decode()
             return encrypted
         except Exception as e:
@@ -96,7 +96,7 @@ class OAuthSessionTable:
         """Decrypt OAuth tokens from storage"""
         try:
             decrypted = self.fernet.decrypt(token.encode()).decode()
-            return json.loads(decrypted)
+            return JSONCodec.loads(decrypted)
         except Exception as e:
             log.error(f'Error decrypting tokens: {type(e).__name__}: {e}')
             raise

backend/open_webui/models/prompt_history.py

@@ -1,7 +1,6 @@
 """Prompt history model for version tracking."""
 
 import difflib
-import json
 import time
 import uuid
 from typing import Optional

backend/open_webui/models/prompts.py

@@ -2,7 +2,6 @@
 
 from __future__ import annotations
 
-import json
 import logging
 import time
 import uuid
@@ -15,6 +14,7 @@ from open_webui.models.access_grants import AccessGrantModel, AccessGrants
 from open_webui.models.groups import Groups
 from open_webui.models.prompt_history import PromptHistories
 from open_webui.models.users import User, UserModel, UserResponse, Users
+from open_webui.utils.misc import json_text_variants
 from pydantic import BaseModel, ConfigDict, Field
 from sqlalchemy import JSON, BigInteger, Boolean, Column, String, Text, cast, delete, func, or_, select, text, update
 from sqlalchemy.ext.asyncio import AsyncSession
@@ -47,7 +47,7 @@ class PromptModel(BaseModel):
     content: str
     data: dict | None = None
     meta: dict | None = None
-    tags: list[str | None] = None
+    tags: list[str] | None = None
     is_active: bool | None = True
     version_id: str | None = None
     created_at: int | None = None
@@ -86,8 +86,8 @@ class PromptForm(BaseModel):
     content: str
     data: dict | None = None
     meta: dict | None = None
-    tags: list[str | None] = None
+    tags: list[str] | None = None
-    access_grants: list[dict | None] = None
+    access_grants: list[dict] | None = None
     version_id: str | None = None  # Active version
     commit_message: str | None = None  # For history tracking
     is_production: bool | None = True  # Whether to set new version as production
@@ -100,7 +100,7 @@ class PromptsTable:
     async def _to_prompt_model(
         self,
         prompt: Prompt,
-        access_grants: list[AccessGrantModel | None] = None,
+        access_grants: list[AccessGrantModel] | None = None,
         db: AsyncSession | None = None,
     ) -> PromptModel:
         prompt_model = PromptModel.model_validate(prompt)
@@ -334,17 +334,19 @@ class PromptsTable:
                     tag_lower = tag.lower()
 
                     if dialect_name == 'sqlite':
+                        tag_lower = tag.replace('\\', '\\\\').replace('%', '\\%').replace('_', '\\_')
                         tag_clause = text(
-                            'EXISTS (SELECT 1 FROM json_each(prompt.tags) t WHERE LOWER(t.value) = :tag_val)'
+                            "EXISTS (SELECT 1 FROM json_each(prompt.tags) t WHERE t.value LIKE :tag_val ESCAPE '\\')"
                         )
                     elif dialect_name == 'postgresql':
                         tag_clause = text(
                             'EXISTS (SELECT 1 FROM json_array_elements_text(prompt.tags) t WHERE LOWER(t) = :tag_val)'
                         )
                     else:
-                        # Fallback: LIKE on serialised JSON text (ASCII-safe only)
+                        # Fallback for dialects with no JSON array function: LIKE on the text.
-                        tag_clause = func.lower(cast(Prompt.tags, String)).like(
+                        tags_text = func.lower(cast(Prompt.tags, String))
-                            f'%{json.dumps(tag_lower, ensure_ascii=False)}%'
+                        tag_clause = or_(
+                            *(tags_text.like(f'%"{variant}"%') for variant in json_text_variants(tag_lower))
                         )
                         tag_lower = None
 
@@ -504,14 +506,16 @@ class PromptsTable:
                 )
 
                 # Update prompt fields
-                prompt.name = form_data.name
                 prompt.command = form_data.command
-                prompt.content = form_data.content
-                prompt.data = form_data.data or prompt.data
-                prompt.meta = form_data.meta or prompt.meta
 
-                if form_data.tags is not None:
+                if form_data.is_production:
-                    prompt.tags = form_data.tags
+                    prompt.name = form_data.name
+                    prompt.content = form_data.content
+                    prompt.data = form_data.data or prompt.data
+                    prompt.meta = form_data.meta or prompt.meta
+
+                    if form_data.tags is not None:
+                        prompt.tags = form_data.tags
 
                 if form_data.access_grants is not None:
                     await AccessGrants.set_access_grants('prompt', prompt.id, form_data.access_grants, db=session)
@@ -529,7 +533,7 @@ class PromptsTable:
                         'command': prompt.command,
                         'data': form_data.data or {},
                         'meta': form_data.meta or {},
-                        'tags': prompt.tags or [],
+                        'tags': form_data.tags if form_data.tags is not None else (prompt.tags or []),
                         'access_grants': [grant.model_dump() for grant in current_access_grants],
                     }
 
@@ -556,7 +560,7 @@ class PromptsTable:
         prompt_id: str,
         name: str,
         command: str,
-        tags: list[str | None] = None,
+        tags: list[str] | None = None,
         db: AsyncSession | None = None,
     ) -> PromptModel | None:
         """Update only name, command, and tags (no history created)."""

backend/open_webui/models/skills.py

@@ -33,6 +33,7 @@ class Skill(Base):
 
 
 class SkillMeta(BaseModel):
+    i18n: dict[str, dict[str, str]] | None = None
     tags: Optional[list[str]] = []
 
 
@@ -163,9 +164,30 @@ class SkillsTable:
         except Exception:
             return None
 
-    async def get_skills(self, db: Optional[AsyncSession] = None) -> list[SkillUserModel]:
+    async def get_skills(
+        self,
+        user_id: str | None = None,
+        ids: list[str] | None = None,
+        db: AsyncSession | None = None,
+    ) -> list[SkillUserModel]:
         async with get_async_db_context(db) as db:
-            result = await db.execute(select(Skill).order_by(Skill.updated_at.desc()))
+            stmt = select(Skill).order_by(Skill.updated_at.desc())
+
+            if ids is not None:
+                stmt = stmt.filter(Skill.id.in_(ids))
+
+            if user_id is not None:
+                user_group_ids = {group.id for group in await Groups.get_groups_by_member_id(user_id, db=db)}
+                stmt = AccessGrants.has_permission_filter(
+                    db=db,
+                    query=stmt,
+                    DocumentModel=Skill,
+                    filter={'user_id': user_id, 'group_ids': user_group_ids},
+                    resource_type='skill',
+                    permission='read',
+                )
+
+            result = await db.execute(stmt)
             all_skills = result.scalars().all()
 
             user_ids = list(set(skill.user_id for skill in all_skills))
@@ -194,28 +216,6 @@ class SkillsTable:
                 )
             return skills
 
-    async def get_skills_by_user_id(
-        self, user_id: str, permission: str = 'write', db: Optional[AsyncSession] = None
-    ) -> list[SkillUserModel]:
-        skills = await self.get_skills(db=db)
-        user_groups = await Groups.get_groups_by_member_id(user_id, db=db)
-        user_group_ids = {group.id for group in user_groups}
-
-        result = []
-        for skill in skills:
-            if skill.user_id == user_id:
-                result.append(skill)
-            elif await AccessGrants.has_access(
-                user_id=user_id,
-                resource_type='skill',
-                resource_id=skill.id,
-                permission=permission,
-                user_group_ids=user_group_ids,
-                db=db,
-            ):
-                result.append(skill)
-        return result
-
     async def search_skills(
         self,
         user_id: str,

backend/open_webui/models/tags.py

@@ -97,7 +97,7 @@ class TagTable:
             async with get_async_db_context(db) as db:
                 id = name.replace(' ', '_').lower()
                 result = await db.execute(delete(Tag).filter_by(id=id, user_id=user_id))
-                log.debug(f'res: {result.rowcount}')
+                log.debug('res: %s', result.rowcount)
                 await db.commit()
                 return True
         except Exception as e:

backend/open_webui/models/tools.py

@@ -34,6 +34,7 @@ class Tool(Base):  # database table definition
 
 
 class ToolMeta(BaseModel):
+    i18n: dict[str, dict[str, str]] | None = None
     description: str | None = None
     manifest: dict | None = {}
     has_user_valves: bool = False
@@ -89,7 +90,7 @@ class ToolForm(BaseModel):
     name: str
     content: str
     meta: ToolMeta
-    access_grants: list[dict | None] = None
+    access_grants: list[dict] | None = None
 
 
 class ToolValves(BaseModel):
@@ -103,7 +104,7 @@ class ToolsTable:
     async def _to_tool_model(
         self,
         tool: Tool,
-        access_grants: list[AccessGrantModel | None] = None,
+        access_grants: list[AccessGrantModel] | None = None,
         db: AsyncSession | None = None,
     ) -> ToolModel:
         tool_model = ToolModel.model_validate(tool)
@@ -169,20 +170,37 @@ class ToolsTable:
                 for tool in tools
             }
 
-    async def get_tools(self, defer_content: bool = False, db: AsyncSession | None = None) -> list[ToolUserModel]:
+    async def get_tools(
+        self,
+        defer_content: bool = False,
+        db: AsyncSession | None = None,
+        user_id: str | None = None,
+        user_group_ids: set[str] | None = None,
+        permission: str = 'read',
+    ) -> list[ToolUserModel]:
         async with get_async_db_context(db) as db:
-            if defer_content:
+            # Skip Tool.content (plugin source, potentially large) via a
-                # Skip Tool.content (plugin source, potentially large) via a
+            # column select; Row attributes satisfy from_attributes.
-                # column select; Row attributes satisfy from_attributes.
+            stmt = (
-                result = await db.execute(
+                select(Tool.id, Tool.user_id, Tool.name, Tool.specs, Tool.meta, Tool.updated_at, Tool.created_at)
-                    select(
+                if defer_content
-                        Tool.id, Tool.user_id, Tool.name, Tool.specs, Tool.meta, Tool.updated_at, Tool.created_at
+                else select(Tool)
-                    ).order_by(Tool.updated_at.desc())
+            ).order_by(Tool.updated_at.desc())
+
+            if user_id is not None:
+                if user_group_ids is None:
+                    user_group_ids = {group.id for group in await Groups.get_groups_by_member_id(user_id, db=db)}
+                stmt = AccessGrants.has_permission_filter(
+                    db=db,
+                    query=stmt,
+                    DocumentModel=Tool,
+                    filter={'user_id': user_id, 'group_ids': user_group_ids},
+                    resource_type='tool',
+                    permission=permission,
                 )
-                all_tools = result.all()
+
-            else:
+            result = await db.execute(stmt)
-                result = await db.execute(select(Tool).order_by(Tool.updated_at.desc()))
+            all_tools = result.all() if defer_content else result.scalars().all()
-                all_tools = result.scalars().all()
 
             user_ids = list(set(tool.user_id for tool in all_tools))
             tool_ids = [tool.id for tool in all_tools]
@@ -217,20 +235,15 @@ class ToolsTable:
         defer_content: bool = False,
         db: AsyncSession | None = None,
     ) -> list[ToolUserModel]:
-        tools = await self.get_tools(defer_content=defer_content, db=db)
         user_groups = await Groups.get_groups_by_member_id(user_id, db=db)
         user_group_ids = {group.id for group in user_groups}
-
+        return await self.get_tools(
-        # One grants query for all non-owned tools instead of one per tool
+            defer_content=defer_content,
-        accessible_ids = await AccessGrants.get_accessible_resource_ids(
-            user_id=user_id,
-            resource_type='tool',
-            resource_ids=[tool.id for tool in tools if tool.user_id != user_id],
-            permission=permission,
-            user_group_ids=user_group_ids,
             db=db,
+            user_id=user_id,
+            user_group_ids=user_group_ids,
+            permission=permission,
         )
-        return [tool for tool in tools if tool.user_id == user_id or tool.id in accessible_ids]
 
     async def get_tool_valves_by_id(self, id: str, db: AsyncSession | None = None) -> dict | None:
         try:

backend/open_webui/models/users.py

@@ -4,12 +4,18 @@ from __future__ import annotations
 
 import datetime
 import time
-from typing import Optional
+from typing import Literal, Optional
 from open_webui.env import DATABASE_USER_ACTIVE_STATUS_UPDATE_INTERVAL
 from open_webui.internal.db import Base, JSONField, get_async_db_context
 from open_webui.utils.misc import throttle
-from open_webui.utils.validate import validate_profile_image_url
+from open_webui.utils.validate import validate_image_url
-from pydantic import BaseModel, ConfigDict, Field, field_validator, model_validator
+from pydantic import (
+    BaseModel,
+    ConfigDict,
+    Field,
+    field_validator,
+    model_validator,
+)
 from sqlalchemy import (
     JSON,
     BigInteger,
@@ -27,7 +33,6 @@ from sqlalchemy import (
     select,
     update,
 )
-from sqlalchemy.dialects.postgresql import JSONB
 from sqlalchemy.ext.asyncio import AsyncSession
 
 ####################
@@ -37,6 +42,97 @@ from sqlalchemy.ext.asyncio import AsyncSession
 ####################
 
 
+class InterfaceTitleSettings(BaseModel):
+    model_config = ConfigDict(extra='forbid')
+
+    auto: bool | None = None
+
+
+class InterfaceImageCompressionSize(BaseModel):
+    model_config = ConfigDict(extra='forbid')
+
+    width: int | float | Literal[''] | None = None
+    height: int | float | Literal[''] | None = None
+
+
+class InterfaceFloatingActionButton(BaseModel):
+    model_config = ConfigDict(extra='forbid')
+
+    id: str
+    label: str
+    input: bool
+    prompt: str
+
+
+class InterfaceSettings(BaseModel):
+    """Fields owned by the Interface settings panel; not the entire user UI dict."""
+
+    model_config = ConfigDict(extra='forbid')
+
+    autoTags: bool | None = None
+    autoFollowUps: bool | None = None
+    highContrastMode: bool | None = None
+    detectArtifacts: bool | None = None
+    responseAutoCopy: bool | None = None
+    showUsername: bool | None = None
+    showUpdateToast: bool | None = None
+    showChangelog: bool | None = None
+    showEmojiInCall: bool | None = None
+    voiceInterruption: bool | None = None
+    displayMultiModelResponsesInTabs: bool | None = None
+    chatFadeStreamingText: bool | None = None
+    richTextInput: bool | None = None
+    showFormattingToolbar: bool | None = None
+    insertPromptAsRichText: bool | None = None
+    promptAutocomplete: bool | None = None
+    insertSuggestionPrompt: bool | None = None
+    keepFollowUpPrompts: bool | None = None
+    insertFollowUpPrompt: bool | None = None
+    regenerateMenu: bool | None = None
+    enableMessageQueue: bool | None = None
+    largeTextAsFile: bool | None = None
+    copyFormatted: bool | None = None
+    collapseCodeBlocks: bool | None = None
+    renderMarkdownInUserMessages: bool | None = None
+    renderMarkdownInAssistantMessages: bool | None = None
+    expandDetails: bool | None = None
+    chatHoverPreview: bool | None = None
+    renderMarkdownInPreviews: bool | None = None
+    chatBubble: bool | None = None
+    widescreenMode: bool | None = None
+    splitLargeChunks: bool | None = None
+    scrollOnBranchChange: bool | None = None
+    scrollOnResponseGeneration: bool | None = None
+    showFilesOnTerminalSelect: bool | None = None
+    temporaryChatByDefault: bool | None = None
+    userLocation: bool | None = None
+    showChatTitleInTab: bool | None = None
+    iframeSandboxAllowScripts: bool | None = None
+    iframeSandboxAllowSameOrigin: bool | None = None
+    iframeSandboxAllowForms: bool | None = None
+    iframeSandboxAllowDownloads: bool | None = None
+    terminalPreviewAllowSameOrigin: bool | None = None
+    stylizedPdfExport: bool | None = None
+    hapticFeedback: bool | None = None
+    ctrlEnterToSend: bool | None = None
+    showFloatingActionButtons: bool | None = None
+    imageCompression: bool | None = None
+    imageCompressionInChannels: bool | None = None
+
+    landingPageMode: Literal['', 'chat'] | None = None
+    chatDirection: Literal['LTR', 'RTL', 'auto'] | None = None
+    terminalFileDisplay: Literal['sidebar', 'inline'] | None = None
+    defaultUploadContext: Literal['full', 'focused'] | None = None
+    webSearch: Literal['always'] | None = None
+    models: list[str] | None = None
+    backgroundImageUrl: str | None = None
+    fontFamily: str | None = None
+    textScale: float | None = None
+    title: InterfaceTitleSettings | None = None
+    imageCompressionSize: InterfaceImageCompressionSize | None = None
+    floatingActionButtons: list[InterfaceFloatingActionButton] | None = None
+
+
 class UserSettings(BaseModel):
     ui: dict | None = {}
     model_config = ConfigDict(extra='allow')
@@ -181,7 +277,7 @@ class UpdateProfileForm(BaseModel):
     @field_validator('profile_image_url')
     @classmethod
     def check_profile_image_url(cls, v: str) -> str:
-        return validate_profile_image_url(v)
+        return validate_image_url(v)
 
 
 class UserGroupIdsModel(UserModel):
@@ -271,7 +367,7 @@ class UserUpdateForm(BaseModel):
     def check_profile_image_url(cls, v: str | None) -> str | None:
         if v is None:
             return v
-        return validate_profile_image_url(v)
+        return validate_image_url(v)
 
 
 class UsersTable:
@@ -287,7 +383,7 @@ class UsersTable:
         db: AsyncSession | None = None,
     ) -> UserModel | None:
         try:
-            profile_image_url = validate_profile_image_url(profile_image_url)
+            profile_image_url = validate_image_url(profile_image_url)
         except ValueError:
             profile_image_url = '/user.png'
 
@@ -360,16 +456,17 @@ class UsersTable:
         sub: str,
         db: AsyncSession | None = None,
     ) -> UserModel | None:
-        """Look up a user by OAuth provider + subject claim (dialect-aware JSON filter)."""
+        """Look up a user by OAuth provider + subject claim."""
+        sub = str(sub)
         async with get_async_db_context(db) as session:
-            dialect = session.bind.dialect.name
+            # Subscript, never contains(): on a JSON column contains() degrades to a substring LIKE.
-            query = select(User)
+            sub_expr = User.oauth[provider]['sub'].as_string()
-            if dialect == 'sqlite':
+            query = select(User).where(sub_expr == sub)
-                oauth_match = User.oauth.contains({provider: {'sub': sub}})
+            # SQLite preserves JSON numeric type here; Postgres ->> already compares numeric JSON as text.
-                query = query.where(oauth_match)
+            if session.get_bind().dialect.name == 'sqlite' and sub.isdecimal():
-            elif dialect == 'postgresql':
+                sub_int = int(sub)
-                oauth_match = User.oauth[provider].cast(JSONB)['sub'].astext == sub
+                if str(sub_int) == sub and sub_int <= 2**63 - 1:
-                query = query.where(oauth_match)
+                    query = select(User).where(or_(sub_expr == sub, sub_expr == sub_int))
             row = (await session.execute(query)).scalars().first()
             return UserModel.model_validate(row) if row else None
 
@@ -379,27 +476,76 @@ class UsersTable:
         external_id: str,
         db: AsyncSession | None = None,
     ) -> UserModel | None:
-        """Look up a user by SCIM provider + external ID (dialect-aware JSON filter)."""
+        """Look up a user by SCIM provider + external ID."""
         async with get_async_db_context(db) as session:
-            dialect = session.bind.dialect.name
+            # Subscript, never contains(): on a JSON column contains() degrades to a substring LIKE.
-            query = select(User)
+            query = select(User).where(User.scim[provider]['external_id'].as_string() == external_id)
-            if dialect == 'sqlite':
-                scim_match = User.scim.contains({provider: {'external_id': external_id}})
-                query = query.where(scim_match)
-            elif dialect == 'postgresql':
-                scim_match = User.scim[provider].cast(JSONB)['external_id'].astext == external_id
-                query = query.where(scim_match)
             row = (await session.execute(query)).scalars().first()
             return UserModel.model_validate(row) if row else None
 
-    async def get_users(
+    async def get_scim_users(
         self,
         filter: dict | None = None,
+        sort: dict | None = None,
         skip: int | None = None,
         limit: int | None = None,
         db: AsyncSession | None = None,
     ) -> dict:
-        """Paginated user listing with optional filters for role, group, and channel."""
+        async with get_async_db_context(db) as session:
+            stmt = select(User).where(or_(User.oauth.cast(String) != 'null', User.scim.cast(String) != 'null'))
+
+            if filter:
+                user_id = filter.get('id')
+                if user_id:
+                    stmt = stmt.where(User.id == user_id)
+
+                email = filter.get('email')
+                if email:
+                    stmt = stmt.where(func.lower(User.email) == email.lower())
+
+            order_by = sort.get('order_by') if sort else None
+            direction = sort.get('direction') if sort else None
+
+            if order_by == 'created_at':
+                stmt = stmt.order_by(User.created_at.asc() if direction == 'asc' else User.created_at.desc())
+
+            count_result = await session.execute(select(func.count()).select_from(stmt.subquery()))
+            total = count_result.scalar()
+
+            if skip is not None:
+                stmt = stmt.offset(skip)
+            if limit is not None:
+                stmt = stmt.limit(limit)
+
+            result = await session.execute(stmt)
+            users = result.scalars().all()
+            return {
+                'users': [UserModel.model_validate(user) for user in users],
+                'total': total,
+            }
+
+    async def get_scim_user_by_id(
+        self,
+        id: str,
+        db: AsyncSession | None = None,
+    ) -> UserModel | None:
+        async with get_async_db_context(db) as session:
+            stmt = select(User).where(
+                User.id == id,
+                or_(User.oauth.cast(String) != 'null', User.scim.cast(String) != 'null'),
+            )
+            user = (await session.execute(stmt)).scalars().first()
+            return UserModel.model_validate(user) if user else None
+
+    async def get_users(
+        self,
+        filter: dict | None = None,
+        sort: dict | None = None,
+        skip: int | None = None,
+        limit: int | None = None,
+        db: AsyncSession | None = None,
+    ) -> dict:
+        """Paginated user listing with optional filters and sort."""
         async with get_async_db_context(db) as session:
             # Deferred imports to avoid circular dependencies
             from open_webui.models.channels import ChannelMember
@@ -460,64 +606,63 @@ class UsersTable:
                     if exclude_roles:
                         stmt = stmt.filter(~User.role.in_(exclude_roles))
 
-                order_by = filter.get('order_by')
+            order_by = sort.get('order_by') if sort else None
-                direction = filter.get('direction')
+            direction = sort.get('direction') if sort else None
 
-                if order_by and order_by.startswith('group_id:'):
+            if order_by and order_by.startswith('group_id:'):
-                    group_id = order_by.split(':', 1)[1]
+                group_id = order_by.split(':', 1)[1]
 
-                    # Subquery that checks if the user belongs to the group
+                # Subquery that checks if the user belongs to the group
-                    membership_exists = exists(
+                membership_exists = exists(
-                        select(GroupMember.id).where(
+                    select(GroupMember.id).where(
-                            GroupMember.user_id == User.id,
+                        GroupMember.user_id == User.id,
-                            GroupMember.group_id == group_id,
+                        GroupMember.group_id == group_id,
-                        )
                     )
+                )
 
-                    # CASE: user in group → 1, user not in group → 0
+                # CASE: user in group → 1, user not in group → 0
-                    group_sort = case((membership_exists, 1), else_=0)
+                group_sort = case((membership_exists, 1), else_=0)
 
-                    if direction == 'asc':
+                if direction == 'asc':
-                        stmt = stmt.order_by(group_sort.asc(), User.name.asc())
+                    stmt = stmt.order_by(group_sort.asc(), User.name.asc())
-                    else:
+                else:
-                        stmt = stmt.order_by(group_sort.desc(), User.name.asc())
+                    stmt = stmt.order_by(group_sort.desc(), User.name.asc())
 
-                elif order_by == 'name':
+            elif order_by == 'name':
-                    if direction == 'asc':
+                if direction == 'asc':
-                        stmt = stmt.order_by(User.name.asc())
+                    stmt = stmt.order_by(User.name.asc())
-                    else:
+                else:
-                        stmt = stmt.order_by(User.name.desc())
+                    stmt = stmt.order_by(User.name.desc())
 
-                elif order_by == 'email':
+            elif order_by == 'email':
-                    if direction == 'asc':
+                if direction == 'asc':
-                        stmt = stmt.order_by(User.email.asc())
+                    stmt = stmt.order_by(User.email.asc())
-                    else:
+                else:
-                        stmt = stmt.order_by(User.email.desc())
+                    stmt = stmt.order_by(User.email.desc())
 
-                elif order_by == 'created_at':
+            elif order_by == 'created_at':
-                    if direction == 'asc':
+                if direction == 'asc':
-                        stmt = stmt.order_by(User.created_at.asc())
+                    stmt = stmt.order_by(User.created_at.asc())
-                    else:
+                else:
-                        stmt = stmt.order_by(User.created_at.desc())
+                    stmt = stmt.order_by(User.created_at.desc())
 
-                elif order_by == 'last_active_at':
+            elif order_by == 'last_active_at':
-                    if direction == 'asc':
+                if direction == 'asc':
-                        stmt = stmt.order_by(User.last_active_at.asc())
+                    stmt = stmt.order_by(User.last_active_at.asc())
-                    else:
+                else:
-                        stmt = stmt.order_by(User.last_active_at.desc())
+                    stmt = stmt.order_by(User.last_active_at.desc())
 
-                elif order_by == 'updated_at':
+            elif order_by == 'updated_at':
-                    if direction == 'asc':
+                if direction == 'asc':
-                        stmt = stmt.order_by(User.updated_at.asc())
+                    stmt = stmt.order_by(User.updated_at.asc())
-                    else:
+                else:
-                        stmt = stmt.order_by(User.updated_at.desc())
+                    stmt = stmt.order_by(User.updated_at.desc())
-                elif order_by == 'role':
+            elif order_by == 'role':
-                    if direction == 'asc':
+                if direction == 'asc':
-                        stmt = stmt.order_by(User.role.asc())
+                    stmt = stmt.order_by(User.role.asc())
-                    else:
+                else:
-                        stmt = stmt.order_by(User.role.desc())
+                    stmt = stmt.order_by(User.role.desc())
-
+            elif not filter:
-            else:
                 stmt = stmt.order_by(User.created_at.desc())
 
             # Count BEFORE pagination
@@ -609,7 +754,7 @@ class UsersTable:
         db: AsyncSession | None = None,
     ) -> UserModel | None:
         try:
-            profile_image_url = validate_profile_image_url(profile_image_url)
+            profile_image_url = validate_image_url(profile_image_url)
         except ValueError:
             profile_image_url = '/user.png'
 
@@ -636,7 +781,10 @@ class UsersTable:
             if not user:
                 return None
             oauth = dict(user.oauth or {})
-            oauth[provider] = {'sub': sub}
+            provider_oauth = oauth.get(provider)
+            provider_oauth = dict(provider_oauth) if isinstance(provider_oauth, dict) else {}
+            provider_oauth['sub'] = str(sub)
+            oauth[provider] = provider_oauth
             user.oauth = oauth
             await session.commit()
             return UserModel.model_validate(user)
@@ -645,7 +793,7 @@ class UsersTable:
         self,
         id: str,
         provider: str,
-        external_id: str,
+        external_id: str | None,
         db: AsyncSession | None = None,
     ) -> UserModel | None:
         """Update or insert a SCIM provider/external_id pair into the user's scim JSON field."""
@@ -655,7 +803,9 @@ class UsersTable:
                 return None
             scim = dict(user.scim or {})
             scim[provider] = {'external_id': external_id}
-            user.scim = scim
+            if scim != user.scim:
+                user.scim = scim
+                user.updated_at = int(time.time())
             await session.commit()
             return UserModel.model_validate(user)
 
@@ -678,7 +828,18 @@ class UsersTable:
             if not user:
                 return None
             user_settings = dict(user.settings or {})
+            updated = dict(updated)
+            ui_settings = updated.pop('ui', None)
             user_settings.update(updated)
+            if ui_settings is not None:
+                # UI updates are field-level patches: omission keeps a value; null resets it.
+                current_ui_settings = dict(user_settings.get('ui') or {})
+                for key, value in ui_settings.items():
+                    if value is None:
+                        current_ui_settings.pop(key, None)
+                    else:
+                        current_ui_settings[key] = value
+                user_settings['ui'] = current_ui_settings
             user.settings = user_settings
             await session.commit()
             return UserModel.model_validate(user)

backend/open_webui/retrieval/loaders/datalab_marker.py

@@ -7,6 +7,7 @@ from typing import List, Optional
 import requests
 from fastapi import HTTPException, status
 from langchain_core.documents import Document
+from open_webui.utils.json_codec import JSONCodec
 
 log = logging.getLogger(__name__)
 
@@ -64,25 +65,6 @@ class DatalabMarkerLoader:
         }
         return mime_map.get(ext, 'application/octet-stream')
 
-    def check_marker_request_status(self, request_id: str) -> dict:
-        url = f'{self.api_base_url}/{request_id}'
-        headers = {'X-Api-Key': self.api_key}
-        try:
-            response = requests.get(url, headers=headers)
-            response.raise_for_status()
-            result = response.json()
-            log.info(f'Marker API status check for request {request_id}: {result}')
-            return result
-        except requests.HTTPError as e:
-            log.error(f'Error checking Marker request status: {e}')
-            raise HTTPException(
-                status.HTTP_502_BAD_GATEWAY,
-                detail=f'Failed to check Marker request: {e}',
-            )
-        except ValueError as e:
-            log.error(f'Invalid JSON checking Marker request: {e}')
-            raise HTTPException(status.HTTP_502_BAD_GATEWAY, detail=f'Invalid JSON: {e}')
-
     def load(self) -> List[Document]:
         filename = os.path.basename(self.file_path)
         mime_type = self._get_mime_type(filename)
@@ -103,7 +85,10 @@ class DatalabMarkerLoader:
             form_data['additional_config'] = self.additional_config
 
         log.info(
-            f"Datalab Marker POST request parameters: {{'filename': '{filename}', 'mime_type': '{mime_type}', **{form_data}}}"
+            "Datalab Marker POST request parameters: {'filename': '%s', 'mime_type': '%s', **%s}",
+            filename,
+            mime_type,
+            form_data,
         )
 
         try:
@@ -167,7 +152,7 @@ class DatalabMarkerLoader:
                             'total_cost',
                         )
                     }
-                    log.info(f'Marker processing completed successfully: {json.dumps(summary, indent=2)}')
+                    log.info('Marker processing completed successfully: %s', json.dumps(summary, indent=2))
                     break
 
                 if status_val == 'failed' or success_val is False:
@@ -234,7 +219,7 @@ class DatalabMarkerLoader:
         try:
             with open(output_path, 'w', encoding='utf-8') as f:
                 f.write(full_text)
-            log.info(f'Saved Marker output to: {output_path}')
+            log.info('Saved Marker output to: %s', output_path)
         except Exception as e:
             log.warning(f'Failed to write marker output to disk: {e}')
 
@@ -249,11 +234,11 @@ class DatalabMarkerLoader:
         images = final_result.get('images', {})
         if images:
             metadata['image_count'] = len(images)
-            metadata['images'] = json.dumps(list(images.keys()))
+            metadata['images'] = JSONCodec.dumps(list(images.keys()))
 
         for k, v in metadata.items():
             if isinstance(v, (dict, list)):
-                metadata[k] = json.dumps(v)
+                metadata[k] = JSONCodec.dumps(v)
             elif v is None:
                 metadata[k] = ''
 

backend/open_webui/retrieval/loaders/external_web.py

@@ -30,6 +30,9 @@ class ExternalWebLoader(BaseLoader):
                 response = requests.post(
                     self.external_url,
                     headers={
+                        # LICENSE covers this Open WebUI user-agent identifier.
+                        # Do not alter, remove, obscure, or replace it except as LICENSE permits:
+                        # https://docs.openwebui.com/license.
                         'User-Agent': 'Open WebUI (https://github.com/open-webui/open-webui) External Web Loader',
                         'Authorization': f'Bearer {self.external_api_key}',
                     },

backend/open_webui/retrieval/loaders/local.py

@@ -0,0 +1,121 @@
+from importlib import import_module
+from pathlib import Path
+
+from bs4 import BeautifulSoup
+from langchain_core.documents import Document
+
+
+class TextLoader:
+    def __init__(self, file_path, encoding=None):
+        self.file_path = str(file_path)
+        self.encoding = encoding
+
+    def load(self) -> list[Document]:
+        try:
+            text = Path(self.file_path).read_text(encoding=self.encoding)
+        except Exception as e:
+            raise RuntimeError(f'Error loading {self.file_path}') from e
+        return [
+            Document(
+                page_content=text,
+                metadata={'source': self.file_path},
+            )
+        ]
+
+
+class HTMLLoader(TextLoader):
+    def load(self) -> list[Document]:
+        with open(self.file_path, encoding=self.encoding) as file:
+            soup = BeautifulSoup(file, 'lxml')
+        return [
+            Document(
+                page_content=soup.get_text(),
+                metadata={'source': self.file_path, 'title': str(soup.title.string) if soup.title else ''},
+            )
+        ]
+
+
+class DocxLoader(TextLoader):
+    def load(self) -> list[Document]:
+        import docx2txt
+
+        return [
+            Document(
+                page_content=docx2txt.process(Path(self.file_path).expanduser()),
+                metadata={'source': self.file_path},
+            )
+        ]
+
+
+class UnstructuredLoader:
+    def __init__(self, file_path, file_format, mode='single', **kwargs):
+        # Match the optional-package check; format dependencies are loaded when parsing.
+        import_module('unstructured')
+        self.file_path = file_path
+        self.file_format = file_format
+        self.mode = mode
+        self.kwargs = kwargs
+
+    def load(self) -> list[Document]:
+        file_format = self.file_format
+        if file_format in ('doc', 'ppt', 'pptx'):
+            from unstructured.file_utils.filetype import detect_filetype
+
+            legacy_format = 'doc' if file_format == 'doc' else 'ppt'
+            try:
+                import_module('magic')
+            except ImportError:
+                is_legacy = Path(self.file_path).suffix == f'.{legacy_format}'
+            else:
+                is_legacy = detect_filetype(self.file_path).name.lower() == legacy_format
+            file_format = legacy_format if is_legacy else legacy_format + 'x'
+        elif file_format == 'msg':
+            from unstructured.file_utils.filetype import detect_filetype
+
+            detected = detect_filetype(self.file_path).name
+            if detected not in ('EML', 'MSG'):
+                raise ValueError(f'Unsupported email file type: {detected}')
+            file_format = 'email' if detected == 'EML' else 'msg'
+
+        module = import_module(f'unstructured.partition.{file_format}')
+        elements = getattr(module, f'partition_{file_format}')(filename=self.file_path, **self.kwargs)
+        metadata = {'source': str(self.file_path)}
+        if self.mode == 'elements':
+            return [
+                Document(
+                    page_content=str(element),
+                    metadata={
+                        **metadata,
+                        **element.metadata.to_dict(),
+                        'category': element.category,
+                        'element_id': element.id,
+                    },
+                )
+                for element in elements
+            ]
+        return [Document(page_content='\n\n'.join(map(str, elements)), metadata=metadata)]
+
+
+class DocumentIntelligenceLoader:
+    def __init__(self, file_path, api_endpoint, api_key=None, azure_credential=None, api_model='prebuilt-layout'):
+        if (api_key is None) == (azure_credential is None):
+            raise ValueError('Provide exactly one of api_key or azure_credential.')
+        self.file_path = file_path
+        self.api_endpoint = api_endpoint
+        self.api_key = api_key
+        self.azure_credential = azure_credential
+        self.api_model = api_model
+
+    def load(self) -> list[Document]:
+        from azure.ai.documentintelligence import DocumentIntelligenceClient
+        from azure.core.credentials import AzureKeyCredential
+
+        credential = self.azure_credential if self.azure_credential is not None else AzureKeyCredential(self.api_key)
+        with DocumentIntelligenceClient(self.api_endpoint, credential) as client, open(self.file_path, 'rb') as file:
+            result = client.begin_analyze_document(
+                self.api_model,
+                body=file,
+                content_type='application/octet-stream',
+                output_content_format='markdown',
+            ).result()
+        return [Document(page_content=result.content, metadata=result.as_dict())]

backend/open_webui/retrieval/loaders/main.py

@@ -1,33 +1,37 @@
 import asyncio
-import json
+import csv
 import logging
+import os
 import sys
+import zipfile
 
 import ftfy
 import requests
+from fastapi import HTTPException
 from azure.identity import DefaultAzureCredential
-from langchain_community.document_loaders import (
-    AzureAIDocumentIntelligenceLoader,
-    BSHTMLLoader,
-    CSVLoader,
-    Docx2txtLoader,
-    PyPDFLoader,
-    TextLoader,
-    YoutubeLoader,
-)
 from langchain_core.documents import Document
 from open_webui.env import (
     AIOHTTP_CLIENT_SESSION_SSL,
     GLOBAL_LOG_LEVEL,
+    USE_SLIM,
     MINERU_MAX_MARKDOWN_BYTES,
     REQUESTS_VERIFY,
 )
 from open_webui.retrieval.loaders.datalab_marker import DatalabMarkerLoader
 from open_webui.retrieval.loaders.external_document import ExternalDocumentLoader
+from open_webui.retrieval.loaders.local import (
+    DocumentIntelligenceLoader,
+    DocxLoader,
+    HTMLLoader,
+    TextLoader,
+    UnstructuredLoader,
+)
 from open_webui.retrieval.loaders.mineru import MinerULoader
 from open_webui.retrieval.loaders.mistral import MistralLoader
 from open_webui.retrieval.loaders.paddleocr_vl import PADDLEOCR_VL_SUPPORTED_EXTENSIONS, PaddleOCRVLLoader
+from open_webui.retrieval.loaders.pdf import PDFLoader
 from open_webui.utils.headers import get_user_groups_for_custom_headers
+from open_webui.utils.json_codec import JSONCodec
 
 logging.basicConfig(stream=sys.stdout, level=GLOBAL_LOG_LEVEL)
 log = logging.getLogger(__name__)
@@ -48,6 +52,7 @@ known_source_ext = [
     'h',
     'c',
     'cs',
+    'ino',
     'sql',
     'log',
     'ini',
@@ -86,8 +91,18 @@ known_source_ext = [
     'yaml',
     'yml',
     'toml',
+    'svg',
 ]
 
+known_archive_ext = {'docx', 'epub', 'odt', 'pptx', 'xlsx'}
+known_archive_content_types = {
+    'application/epub+zip',
+    'application/vnd.oasis.opendocument.text',
+    'application/vnd.openxmlformats-officedocument.presentationml.presentation',
+    'application/vnd.openxmlformats-officedocument.spreadsheetml.sheet',
+    'application/vnd.openxmlformats-officedocument.wordprocessingml.document',
+}
+
 
 class ExcelLoader:
     """Fallback Excel loader using pandas when unstructured is not installed."""
@@ -111,6 +126,66 @@ class ExcelLoader:
         ]
 
 
+def get_csv_summary(filename: str, file_path: str, encoding: str) -> str | None:
+    try:
+        with open(file_path, newline='', encoding=encoding) as f:
+            sample = f.read(4096)
+            f.seek(0)
+            try:
+                dialect = csv.Sniffer().sniff(sample)
+            except csv.Error:
+                dialect = csv.excel
+
+            total_rows = 0
+            max_columns = 0
+            headers = []
+            for row in csv.reader(f, dialect):
+                total_rows += 1
+                max_columns = max(max_columns, len(row))
+                if total_rows == 1:
+                    headers = [header.lstrip('\ufeff') for header in row]
+    except Exception:
+        return None
+
+    if total_rows == 0:
+        return None
+
+    return (
+        f'Table: {total_rows} rows incl. header; '
+        f'{max(total_rows - 1, 0)} data rows; '
+        f'{max_columns} columns: {", ".join(headers)}.'
+    )
+
+
+class CSVLoaderWithSummary:
+    def __init__(self, file_path: str, filename: str, encoding: str):
+        self.file_path = file_path
+        self.filename = filename
+        self.encoding = encoding
+
+    def load(self) -> list[Document]:
+        docs = []
+        try:
+            with open(self.file_path, newline='', encoding=self.encoding) as file:
+                for index, row in enumerate(csv.DictReader(file)):
+                    fields = []
+                    for key, value in row.items():
+                        if isinstance(value, str):
+                            value = value.strip()
+                        elif isinstance(value, list):
+                            value = ','.join(v.strip() for v in value)
+                        fields.append(f'{key.strip() if key is not None else key}: {value}')
+                    content = '\n'.join(fields)
+                    docs.append(Document(page_content=content, metadata={'source': self.file_path, 'row': index}))
+        except Exception as e:
+            raise RuntimeError(f'Error loading {self.file_path}') from e
+        if os.getenv('ENABLE_RAG_CSV_SUMMARY', 'False').lower() == 'true':
+            summary = get_csv_summary(self.filename, self.file_path, self.encoding)
+            if summary:
+                docs.insert(0, Document(page_content=summary, metadata={'source': self.file_path, 'row': -1}))
+        return docs
+
+
 class PptxLoader:
     """Fallback PowerPoint loader using python-pptx when unstructured is not installed."""
 
@@ -138,10 +213,11 @@ class PptxLoader:
 
 
 class TikaLoader:
-    def __init__(self, url, file_path, mime_type=None, extract_images=None):
+    def __init__(self, url, file_path, mime_type=None, extract_images=None, server_version='3'):
         self.url = url
         self.file_path = file_path
         self.mime_type = mime_type
+        self.server_version = str(server_version or '3')
 
         self.extract_images = extract_images
 
@@ -157,16 +233,15 @@ class TikaLoader:
         if self.extract_images == True:
             headers['X-Tika-PDFextractInlineImages'] = 'true'
 
-        endpoint = self.url
+        endpoint_path = 'tika/json/md' if self.server_version == '4' else 'tika/text'
-        if not endpoint.endswith('/'):
+        content_key = 'tk:content' if self.server_version == '4' else 'X-TIKA:content'
-            endpoint += '/'
+        endpoint = f'{self.url.rstrip("/")}/{endpoint_path}'
-        endpoint += 'tika/text'
 
         r = requests.put(endpoint, data=data, headers=headers, verify=REQUESTS_VERIFY)
 
         if r.ok:
             raw_metadata = r.json()
-            text = raw_metadata.get('X-TIKA:content', '<No text content found>').strip()
+            text = raw_metadata.get(content_key, '<No text content found>').strip()
 
             if 'Content-Type' in raw_metadata:
                 headers['Content-Type'] = raw_metadata['Content-Type']
@@ -216,8 +291,17 @@ class DoclingLoader:
             )
         if r.ok:
             result = r.json()
+            # Docling reports failed and skipped conversions inside HTTP 200 responses.
+            conversion_status = result.get('status')
+            if conversion_status in ['failure', 'skipped']:
+                error_details = (
+                    '; '.join(filter(None, (error.get('error_message') for error in result.get('errors', []))))
+                    or 'no error message provided'
+                )
+                raise Exception(f'Error calling Docling: conversion status {conversion_status} - {error_details}')
+
             document_data = result.get('document', {})
-            md_content = document_data.get('md_content', '')
+            md_content = document_data.get('md_content') or ''
             text = md_content or '<No text content found>'
 
             metadata = {'Content-Type': self.mime_type} if self.mime_type else {}
@@ -256,7 +340,11 @@ class Loader:
     def load(self, filename: str, file_content_type: str, file_path: str) -> list[Document]:
         loader = self._get_loader(filename, file_content_type, file_path)
         docs = loader.load()
-        return [Document(page_content=ftfy.fix_text(doc.page_content), metadata=doc.metadata) for doc in docs]
+        # ftfy's auto mode unescapes entities on every line before the first literal '<', rewriting the document.
+        return [
+            Document(page_content=ftfy.fix_text(doc.page_content, unescape_html=False), metadata=doc.metadata)
+            for doc in docs
+        ]
 
     async def aload(self, filename: str, file_content_type: str, file_path: str) -> list[Document]:
         """
@@ -429,6 +517,27 @@ class Loader:
     def _get_loader(self, filename: str, file_content_type: str, file_path: str):
         file_ext = filename.split('.')[-1].lower()
 
+        if file_ext in known_archive_ext or file_content_type in known_archive_content_types:
+            max_file_size = self.kwargs.get('FILE_MAX_SIZE')
+            try:
+                max_file_size_bytes = int(max_file_size) * 1024 * 1024 if max_file_size else 100 * 1024 * 1024
+            except (TypeError, ValueError):
+                max_file_size_bytes = 100 * 1024 * 1024
+
+            if max_file_size_bytes > 0:
+                try:
+                    with zipfile.ZipFile(file_path) as archive:
+                        uncompressed_size = sum(entry.file_size for entry in archive.infolist())
+                except (zipfile.BadZipFile, OSError):
+                    pass
+                else:
+                    max_bytes = min(
+                        max(10 * 1024 * 1024, os.path.getsize(file_path) * 100),
+                        max_file_size_bytes,
+                    )
+                    if uncompressed_size > max_bytes:
+                        raise ValueError('Document archive is too large after decompression')
+
         if (
             self.engine == 'external'
             and self.kwargs.get('EXTERNAL_DOCUMENT_LOADER_URL')
@@ -455,6 +564,7 @@ class Loader:
                 loader = TikaLoader(
                     url=self.kwargs.get('TIKA_SERVER_URL'),
                     file_path=file_path,
+                    server_version=self.kwargs.get('TIKA_SERVER_VERSION'),
                     extract_images=self.kwargs.get('PDF_EXTRACT_IMAGES'),
                 )
         elif (
@@ -508,8 +618,8 @@ class Loader:
                 params = self.kwargs.get('DOCLING_PARAMS', {})
                 if not isinstance(params, dict):
                     try:
-                        params = json.loads(params)
+                        params = JSONCodec.loads(params)
-                    except json.JSONDecodeError:
+                    except JSONCodec.JSONDecodeError:
                         log.error('Invalid DOCLING_PARAMS format, expected JSON object')
                         params = {}
 
@@ -534,14 +644,14 @@ class Loader:
             )
         ):
             if self.kwargs.get('DOCUMENT_INTELLIGENCE_KEY') != '':
-                loader = AzureAIDocumentIntelligenceLoader(
+                loader = DocumentIntelligenceLoader(
                     file_path=file_path,
                     api_endpoint=self.kwargs.get('DOCUMENT_INTELLIGENCE_ENDPOINT'),
                     api_key=self.kwargs.get('DOCUMENT_INTELLIGENCE_KEY'),
                     api_model=self.kwargs.get('DOCUMENT_INTELLIGENCE_MODEL'),
                 )
             else:
-                loader = AzureAIDocumentIntelligenceLoader(
+                loader = DocumentIntelligenceLoader(
                     file_path=file_path,
                     api_endpoint=self.kwargs.get('DOCUMENT_INTELLIGENCE_ENDPOINT'),
                     azure_credential=DefaultAzureCredential(),
@@ -587,19 +697,34 @@ class Loader:
                 file_path=file_path,
             )
         else:
+            if USE_SLIM:
+                if file_ext == 'csv':
+                    return CSVLoaderWithSummary(file_path, filename, self._detect_text_encoding(file_path))
+                if file_ext in ['htm', 'html']:
+                    return HTMLLoader(file_path, encoding=self._detect_text_encoding(file_path))
+                if file_ext in ['txt', 'md', 'markdown', 'rst', 'xml'] or self._is_text_file(
+                    file_ext, file_content_type
+                ):
+                    return TextLoader(file_path, encoding=self._detect_text_encoding(file_path))
+                raise HTTPException(
+                    503,
+                    'This file type requires an external document extractor in slim. Configure one that supports it.',
+                )
             if file_ext == 'pdf':
-                loader = PyPDFLoader(
+                loader = PDFLoader(
                     file_path,
                     extract_images=self.kwargs.get('PDF_EXTRACT_IMAGES'),
                     mode=self.kwargs.get('PDF_LOADER_MODE', 'page'),
                 )
             elif file_ext == 'csv':
-                loader = CSVLoader(file_path, encoding=self._detect_text_encoding(file_path))
+                loader = CSVLoaderWithSummary(
+                    file_path,
+                    filename,
+                    self._detect_text_encoding(file_path),
+                )
             elif file_ext == 'rst':
                 try:
-                    from langchain_community.document_loaders import UnstructuredRSTLoader
+                    loader = UnstructuredLoader(file_path, 'rst', mode='elements')
-
-                    loader = UnstructuredRSTLoader(file_path, mode='elements')
                 except ImportError:
                     log.warning(
                         "The 'unstructured' package is not installed. "
@@ -609,9 +734,7 @@ class Loader:
                     loader = TextLoader(file_path, encoding=self._detect_text_encoding(file_path))
             elif file_ext == 'xml':
                 try:
-                    from langchain_community.document_loaders import UnstructuredXMLLoader
+                    loader = UnstructuredLoader(file_path, 'xml')
-
-                    loader = UnstructuredXMLLoader(file_path)
                 except ImportError:
                     log.warning(
                         "The 'unstructured' package is not installed. "
@@ -620,14 +743,12 @@ class Loader:
                     )
                     loader = TextLoader(file_path, encoding=self._detect_text_encoding(file_path))
             elif file_ext in ['htm', 'html']:
-                loader = BSHTMLLoader(file_path, open_encoding='unicode_escape')
+                loader = HTMLLoader(file_path, encoding='unicode_escape')
             elif file_ext == 'md':
                 loader = TextLoader(file_path, encoding=self._detect_text_encoding(file_path))
             elif file_content_type == 'application/epub+zip':
                 try:
-                    from langchain_community.document_loaders import UnstructuredEPubLoader
+                    loader = UnstructuredLoader(file_path, 'epub')
-
-                    loader = UnstructuredEPubLoader(file_path)
                 except ImportError:
                     raise ValueError(
                         "Processing .epub files requires the 'unstructured' package. "
@@ -637,12 +758,10 @@ class Loader:
                 file_content_type == 'application/vnd.openxmlformats-officedocument.wordprocessingml.document'
                 or file_ext == 'docx'
             ):
-                loader = Docx2txtLoader(file_path)
+                loader = DocxLoader(file_path)
             elif file_ext == 'doc' or file_content_type == 'application/msword':
                 try:
-                    from langchain_community.document_loaders import UnstructuredWordDocumentLoader
+                    loader = UnstructuredLoader(file_path, 'doc')
-
-                    loader = UnstructuredWordDocumentLoader(file_path)
                 except ImportError:
                     raise ValueError(
                         "Processing .doc files requires the 'unstructured' package. "
@@ -653,9 +772,7 @@ class Loader:
                 'application/vnd.openxmlformats-officedocument.spreadsheetml.sheet',
             ] or file_ext in ['xls', 'xlsx']:
                 try:
-                    from langchain_community.document_loaders import UnstructuredExcelLoader
+                    loader = UnstructuredLoader(file_path, 'xlsx')
-
-                    loader = UnstructuredExcelLoader(file_path)
                 except ImportError:
                     log.warning(
                         "The 'unstructured' package is not installed. "
@@ -668,9 +785,7 @@ class Loader:
                 'application/vnd.openxmlformats-officedocument.presentationml.presentation',
             ] or file_ext in ['ppt', 'pptx']:
                 try:
-                    from langchain_community.document_loaders import UnstructuredPowerPointLoader
+                    loader = UnstructuredLoader(file_path, 'ppt' if file_ext == 'ppt' else 'pptx')
-
-                    loader = UnstructuredPowerPointLoader(file_path)
                 except ImportError:
                     log.warning(
                         "The 'unstructured' package is not installed. "
@@ -680,12 +795,8 @@ class Loader:
                     loader = PptxLoader(file_path)
             elif file_ext == 'msg':
                 try:
-                    from langchain_community.document_loaders import (
-                        UnstructuredEmailLoader,
-                    )
-
                     # unstructured parses .msg via python-oxmsg; avoids extract_msg's beautifulsoup4<4.14 conflict
-                    loader = UnstructuredEmailLoader(file_path, process_attachments=False)
+                    loader = UnstructuredLoader(file_path, 'msg', process_attachments=False)
                 except ImportError:
                     raise ValueError(
                         "Processing .msg files requires the 'unstructured' package. "
@@ -693,9 +804,7 @@ class Loader:
                     )
             elif file_ext == 'odt':
                 try:
-                    from langchain_community.document_loaders import UnstructuredODTLoader
+                    loader = UnstructuredLoader(file_path, 'odt')
-
-                    loader = UnstructuredODTLoader(file_path)
                 except ImportError:
                     raise ValueError(
                         "Processing .odt files requires the 'unstructured' package. "

backend/open_webui/retrieval/loaders/microsoft_web_iq.py

@@ -10,7 +10,6 @@ from langchain_core.documents import Document
 
 log = logging.getLogger(__name__)
 
-DEFAULT_MICROSOFT_WEB_IQ_API_BASE_URL = 'https://api.microsoft.ai/v3'
 MICROSOFT_BROWSE_RETRY_STATUS_CODES = {202, 429, 500, 502, 503, 504}
 MICROSOFT_BROWSE_MAX_RETRIES = 2
 
@@ -27,7 +26,7 @@ class MicrosoftWebIQLoader(BaseLoader):
         continue_on_failure: bool = True,
     ) -> None:
         self.urls = urls if isinstance(urls, list) else [urls]
-        self.api_base_url = (api_base_url or DEFAULT_MICROSOFT_WEB_IQ_API_BASE_URL).rstrip('/')
+        self.api_base_url = api_base_url.rstrip('/')
         self.api_key = api_key
         self.language = language
         self.verify_ssl = verify_ssl

backend/open_webui/retrieval/loaders/mineru.py

@@ -74,7 +74,7 @@ class MinerULoader:
         Load document using Local API (synchronous).
         Posts file to /file_parse endpoint and gets immediate response.
         """
-        log.info(f'Using MinerU Local API at {self.api_url}')
+        log.info('Using MinerU Local API at %s', self.api_url)
 
         filename = os.path.basename(self.file_path)
 
@@ -97,8 +97,8 @@ class MinerULoader:
             with open(self.file_path, 'rb') as f:
                 files = {'files': (filename, f, 'application/octet-stream')}
 
-                log.info(f'Sending file to MinerU Local API: {filename}')
+                log.info('Sending file to MinerU Local API: %s', filename)
-                log.debug(f'Local API parameters: {form_data}')
+                log.debug('Local API parameters: %s', form_data)
 
                 response = requests.post(
                     f'{self.api_url}/file_parse',
@@ -163,7 +163,7 @@ class MinerULoader:
                 detail='MinerU returned empty markdown content',
             )
 
-        log.info(f'Successfully parsed document with MinerU Local API: {filename}')
+        log.info('Successfully parsed document with MinerU Local API: %s', filename)
 
         # Create metadata
         metadata = {
@@ -180,7 +180,7 @@ class MinerULoader:
         Load document using Cloud API (asynchronous).
         Uses batch upload endpoint to avoid need for public file URLs.
         """
-        log.info(f'Using MinerU Cloud API at {self.api_url}')
+        log.info('Using MinerU Cloud API at %s', self.api_url)
 
         filename = os.path.basename(self.file_path)
 
@@ -196,7 +196,7 @@ class MinerULoader:
         # Step 4: Download and extract markdown from ZIP
         markdown_content = self._download_and_extract_zip(result['full_zip_url'], filename)
 
-        log.info(f'Successfully parsed document with MinerU Cloud API: {filename}')
+        log.info('Successfully parsed document with MinerU Cloud API: %s', filename)
 
         # Create metadata
         metadata = {
@@ -232,8 +232,8 @@ class MinerULoader:
         if self.page_ranges:
             request_body['files'][0]['page_ranges'] = self.page_ranges
 
-        log.info(f'Requesting upload URL for: {filename}')
+        log.info('Requesting upload URL for: %s', filename)
-        log.debug(f'Cloud API request body: {request_body}')
+        log.debug('Cloud API request body: %s', request_body)
 
         try:
             response = requests.post(
@@ -284,7 +284,7 @@ class MinerULoader:
             )
 
         upload_url = file_urls[0]
-        log.info(f'Received upload URL for batch: {batch_id}')
+        log.info('Received upload URL for batch: %s', batch_id)
 
         return batch_id, upload_url
 
@@ -334,7 +334,7 @@ class MinerULoader:
         max_iterations = 300  # 10 minutes max (2 seconds per iteration)
         poll_interval = 2  # seconds
 
-        log.info(f'Polling batch status: {batch_id}')
+        log.info('Polling batch status: %s', batch_id)
 
         for iteration in range(max_iterations):
             try:
@@ -393,7 +393,7 @@ class MinerULoader:
             state = file_result.get('state')
 
             if state == 'done':
-                log.info(f'Processing complete for {filename}')
+                log.info('Processing complete for %s', filename)
                 return file_result
             elif state == 'failed':
                 error_msg = file_result.get('err_msg', 'Unknown error')
@@ -404,7 +404,7 @@ class MinerULoader:
             elif state in ['waiting-file', 'pending', 'running', 'converting']:
                 # Still processing
                 if iteration % 10 == 0:  # Log every 20 seconds
-                    log.info(f'Processing status: {state} (iteration {iteration + 1}/{max_iterations})')
+                    log.info('Processing status: %s (iteration %s/%s)', state, iteration + 1, max_iterations)
                 time.sleep(poll_interval)
             else:
                 log.warning(f'Unknown state: {state}')
@@ -421,7 +421,7 @@ class MinerULoader:
         Download ZIP file from CDN and extract markdown content.
         Returns the markdown content as a string.
         """
-        log.info(f'Downloading results from: {zip_url}')
+        log.info('Downloading results from: %s', zip_url)
 
         try:
             response = requests.get(zip_url, timeout=60)
@@ -452,7 +452,7 @@ class MinerULoader:
                 read_errors = []
 
                 for member in md_members:
-                    log.info(f'Found markdown file in ZIP: {member.filename}')
+                    log.info('Found markdown file in ZIP: %s', member.filename)
                     try:
                         with zip_ref.open(member, 'r') as f:
                             if self.max_markdown_bytes is None:
@@ -515,5 +515,5 @@ class MinerULoader:
                 detail='Extracted markdown content is empty',
             )
 
-        log.info(f'Successfully extracted markdown content ({len(markdown_content)} characters)')
+        log.info('Successfully extracted markdown content (%s characters)', len(markdown_content))
         return markdown_content

backend/open_webui/retrieval/loaders/mistral.py

@@ -1,16 +1,13 @@
-import asyncio
 import base64
 import logging
 import os
 import sys
 import time
-from contextlib import asynccontextmanager
 from typing import Any, Dict, List, Optional
 
-import aiohttp
 import requests
 from langchain_core.documents import Document
-from open_webui.env import AIOHTTP_CLIENT_SESSION_SSL, ENABLE_FORWARD_USER_INFO_HEADERS, GLOBAL_LOG_LEVEL
+from open_webui.env import ENABLE_FORWARD_USER_INFO_HEADERS, GLOBAL_LOG_LEVEL
 from open_webui.utils.headers import include_user_info_headers
 
 logging.basicConfig(stream=sys.stdout, level=GLOBAL_LOG_LEVEL)
@@ -19,15 +16,12 @@ log = logging.getLogger(__name__)
 
 class MistralLoader:
     """
-    Enhanced Mistral OCR loader with both sync and async support.
+    Enhanced Mistral OCR loader.
     Loads documents by processing them through the Mistral OCR API.
 
     Performance Optimizations:
     - Differentiated timeouts for different operations
     - Intelligent retry logic with exponential backoff
-    - Memory-efficient file streaming for large files
-    - Connection pooling and keepalive optimization
-    - Semaphore-based concurrency control for batch processing
     - Enhanced error handling with retryable error classification
     """
 
@@ -63,7 +57,6 @@ class MistralLoader:
         self.base_url = base_url.rstrip('/') if base_url else 'https://api.mistral.ai/v1'
         self.api_key = api_key
         self.file_path = file_path
-        self.timeout = timeout
         self.max_retries = max_retries
         self.debug = enable_debug_logging
         self.use_base64 = use_base64
@@ -118,32 +111,6 @@ class MistralLoader:
             log.error(f'JSON decode error: {json_err} - Response: {response.text}')
             raise  # Re-raise after logging
 
-    async def _handle_response_async(self, response: aiohttp.ClientResponse) -> Dict[str, Any]:
-        """Async version of response handling with better error info."""
-        try:
-            response.raise_for_status()
-
-            # Check content type
-            content_type = response.headers.get('content-type', '')
-            if 'application/json' not in content_type:
-                if response.status == 204:
-                    return {}
-                text = await response.text()
-                raise ValueError(f'Unexpected content type: {content_type}, body: {text[:200]}...')
-
-            return await response.json()
-
-        except aiohttp.ClientResponseError as e:
-            error_text = await response.text() if response else 'No response'
-            log.error(f'HTTP {e.status}: {e.message} - Response: {error_text[:500]}')
-            raise
-        except aiohttp.ClientError as e:
-            log.error(f'Client error: {e}')
-            raise
-        except Exception as e:
-            log.error(f'Unexpected error processing response: {e}')
-            raise
-
     def _is_retryable_error(self, error: Exception) -> bool:
         """
         ENHANCEMENT: Intelligent error classification for retry logic.
@@ -173,10 +140,6 @@ class MistralLoader:
                 status_code = error.response.status_code
                 return status_code >= 500 or status_code == 429
             return False
-        if isinstance(error, (aiohttp.ClientConnectionError, aiohttp.ServerTimeoutError)):
-            return True  # Async network/timeout errors are retryable
-        if isinstance(error, aiohttp.ClientResponseError):
-            return error.status >= 500 or error.status == 429
         return False  # All other errors are non-retryable
 
     def _retry_request_sync(self, request_func, *args, **kwargs):
@@ -203,32 +166,11 @@ class MistralLoader:
                 )
                 time.sleep(wait_time)
 
-    async def _retry_request_async(self, request_func, *args, **kwargs):
-        """
-        ENHANCEMENT: Async retry logic with intelligent error classification.
-
-        Async version of retry logic that doesn't block the event loop during
-        wait periods. Uses the same exponential backoff strategy as sync version.
-        """
-        for attempt in range(self.max_retries):
-            try:
-                return await request_func(*args, **kwargs)
-            except Exception as e:
-                if attempt == self.max_retries - 1 or not self._is_retryable_error(e):
-                    raise
-
-                # PERFORMANCE OPTIMIZATION: Non-blocking exponential backoff
-                wait_time = min((2**attempt) + 0.5, 30)  # Cap at 30 seconds
-                log.warning(
-                    f'Retryable error (attempt {attempt + 1}/{self.max_retries}): {e}. Retrying in {wait_time}s...'
-                )
-                await asyncio.sleep(wait_time)  # Non-blocking wait
-
     def _upload_file(self) -> str:
         """
         PERFORMANCE OPTIMIZATION: Enhanced file upload with streaming consideration.
 
-        Uploads the file to Mistral for OCR processing (sync version).
+        Uploads the file to Mistral for OCR processing.
         Uses context manager for file handling to ensure proper resource cleanup.
         Although streaming is not enabled for this endpoint, the file is opened
         in a context manager to minimize memory usage duration.
@@ -261,56 +203,15 @@ class MistralLoader:
             file_id = response_data.get('id')
             if not file_id:
                 raise ValueError('File ID not found in upload response.')
-            log.info(f'File uploaded successfully. File ID: {file_id}')
+            log.info('File uploaded successfully. File ID: %s', file_id)
             return file_id
         except Exception as e:
             log.error(f'Failed to upload file: {e}')
             raise
 
-    async def _upload_file_async(self, session: aiohttp.ClientSession) -> str:
-        """Async file upload with streaming for better memory efficiency."""
-        url = f'{self.base_url}/files'
-
-        async def upload_request():
-            # Open inside the request so the handle stays valid for the whole
-            # streamed POST and is closed right after.
-            with open(self.file_path, 'rb') as f:
-                writer = aiohttp.MultipartWriter('form-data')
-
-                # Add purpose field
-                purpose_part = writer.append('ocr')
-                purpose_part.set_content_disposition('form-data', name='purpose')
-
-                # Stream the file. aiohttp builds a payload from the file object;
-                # the previous aiohttp.streams.FilePayload was removed upstream
-                # (payloads live in aiohttp.payload and there is no FilePayload),
-                # so this path raised AttributeError on every async OCR upload.
-                file_part = writer.append(f, {'Content-Type': 'application/pdf'})
-                file_part.set_content_disposition('form-data', name='file', filename=self.file_name)
-
-                self._debug_log(f'Uploading file: {self.file_name} ({self.file_size:,} bytes)')
-
-                async with session.post(
-                    url,
-                    data=writer,
-                    headers=self.headers,
-                    timeout=aiohttp.ClientTimeout(total=self.upload_timeout),
-                    ssl=AIOHTTP_CLIENT_SESSION_SSL,
-                ) as response:
-                    return await self._handle_response_async(response)
-
-        response_data = await self._retry_request_async(upload_request)
-
-        file_id = response_data.get('id')
-        if not file_id:
-            raise ValueError('File ID not found in upload response.')
-
-        log.info(f'File uploaded successfully. File ID: {file_id}')
-        return file_id
-
     def _get_signed_url(self, file_id: str) -> str:
-        """Retrieves a temporary signed URL for the uploaded file (sync version)."""
+        """Retrieves a temporary signed URL for the uploaded file."""
-        log.info(f'Getting signed URL for file ID: {file_id}')
+        log.info('Getting signed URL for file ID: %s', file_id)
         url = f'{self.base_url}/files/{file_id}/url'
         params = {'expiry': 1}
         signed_url_headers = {**self.headers, 'Accept': 'application/json'}
@@ -330,35 +231,8 @@ class MistralLoader:
             log.error(f'Failed to get signed URL: {e}')
             raise
 
-    async def _get_signed_url_async(self, session: aiohttp.ClientSession, file_id: str) -> str:
-        """Async signed URL retrieval."""
-        url = f'{self.base_url}/files/{file_id}/url'
-        params = {'expiry': 1}
-
-        headers = {**self.headers, 'Accept': 'application/json'}
-
-        async def url_request():
-            self._debug_log(f'Getting signed URL for file ID: {file_id}')
-            async with session.get(
-                url,
-                headers=headers,
-                params=params,
-                timeout=aiohttp.ClientTimeout(total=self.url_timeout),
-                ssl=AIOHTTP_CLIENT_SESSION_SSL,
-            ) as response:
-                return await self._handle_response_async(response)
-
-        response_data = await self._retry_request_async(url_request)
-
-        signed_url = response_data.get('url')
-        if not signed_url:
-            raise ValueError('Signed URL not found in response.')
-
-        self._debug_log('Signed URL received successfully')
-        return signed_url
-
     def _process_ocr(self, signed_url: str) -> Dict[str, Any]:
-        """Sends the signed URL to the OCR endpoint for processing (sync version)."""
+        """Sends the signed URL to the OCR endpoint for processing."""
         log.info('Processing OCR via Mistral API')
         url = f'{self.base_url}/ocr'
         ocr_headers = {
@@ -388,113 +262,24 @@ class MistralLoader:
             log.error(f'Failed during OCR processing: {e}')
             raise
 
-    async def _process_ocr_async(self, session: aiohttp.ClientSession, signed_url: str) -> Dict[str, Any]:
-        """Async OCR processing with timing metrics."""
-        url = f'{self.base_url}/ocr'
-
-        headers = {
-            **self.headers,
-            'Content-Type': 'application/json',
-            'Accept': 'application/json',
-        }
-
-        payload = {
-            'model': 'mistral-ocr-latest',
-            'document': {
-                'type': 'document_url',
-                'document_url': signed_url,
-            },
-            'include_image_base64': False,
-        }
-
-        async def ocr_request():
-            log.info('Starting OCR processing via Mistral API')
-            start_time = time.time()
-
-            async with session.post(
-                url,
-                json=payload,
-                headers=headers,
-                timeout=aiohttp.ClientTimeout(total=self.ocr_timeout),
-                ssl=AIOHTTP_CLIENT_SESSION_SSL,
-            ) as response:
-                ocr_response = await self._handle_response_async(response)
-
-            processing_time = time.time() - start_time
-            log.info(f'OCR processing completed in {processing_time:.2f}s')
-
-            return ocr_response
-
-        return await self._retry_request_async(ocr_request)
-
     def _get_file_data_url(self) -> str:
         with open(self.file_path, 'rb') as f:
             encoded_file = base64.b64encode(f.read()).decode('utf-8')
         return f'data:application/pdf;base64,{encoded_file}'
 
     def _delete_file(self, file_id: str) -> None:
-        """Deletes the file from Mistral storage (sync version)."""
+        """Deletes the file from Mistral storage."""
-        log.info(f'Deleting uploaded file ID: {file_id}')
+        log.info('Deleting uploaded file ID: %s', file_id)
         url = f'{self.base_url}/files/{file_id}'
 
         try:
             response = requests.delete(url, headers=self.headers, timeout=self.cleanup_timeout)
             delete_response = self._handle_response(response)
-            log.info(f'File deleted successfully: {delete_response}')
+            log.info('File deleted successfully: %s', delete_response)
         except Exception as e:
             # Log error but don't necessarily halt execution if deletion fails
             log.error(f'Failed to delete file ID {file_id}: {e}')
 
-    async def _delete_file_async(self, session: aiohttp.ClientSession, file_id: str) -> None:
-        """Async file deletion with error tolerance."""
-        try:
-
-            async def delete_request():
-                self._debug_log(f'Deleting file ID: {file_id}')
-                async with session.delete(
-                    url=f'{self.base_url}/files/{file_id}',
-                    headers=self.headers,
-                    timeout=aiohttp.ClientTimeout(total=self.cleanup_timeout),
-                    ssl=AIOHTTP_CLIENT_SESSION_SSL,
-                ) as response:
-                    return await self._handle_response_async(response)
-
-            await self._retry_request_async(delete_request)
-            self._debug_log(f'File {file_id} deleted successfully')
-
-        except Exception as e:
-            # Don't fail the entire process if cleanup fails
-            log.warning(f'Failed to delete file ID {file_id}: {e}')
-
-    @asynccontextmanager
-    async def _get_session(self):
-        """Context manager for HTTP session with optimized settings."""
-        connector = aiohttp.TCPConnector(
-            limit=20,  # Increased total connection limit for better throughput
-            limit_per_host=10,  # Increased per-host limit for API endpoints
-            ttl_dns_cache=600,  # Longer DNS cache TTL (10 minutes)
-            use_dns_cache=True,
-            keepalive_timeout=60,  # Increased keepalive for connection reuse
-            enable_cleanup_closed=True,
-            force_close=False,  # Allow connection reuse
-            resolver=aiohttp.AsyncResolver(),  # Use async DNS resolver
-        )
-
-        timeout = aiohttp.ClientTimeout(
-            total=self.timeout,
-            connect=30,  # Connection timeout
-            sock_read=60,  # Socket read timeout
-        )
-
-        async with aiohttp.ClientSession(
-            connector=connector,
-            timeout=timeout,
-            headers={'User-Agent': 'OpenWebUI-MistralLoader/2.0'},
-            raise_for_status=False,  # We handle status codes manually
-            trust_env=True,
-        ) as session:
-            yield session
-
     def _process_results(self, ocr_response: Dict[str, Any]) -> List[Document]:
         """Process OCR results into Document objects with enhanced metadata and memory efficiency."""
         pages_data = ocr_response.get('pages')
@@ -519,7 +304,7 @@ class MistralLoader:
             if page_content is None or page_index is None:
                 skipped_pages += 1
                 self._debug_log(
-                    f"Skipping page due to missing 'markdown' or 'index'. Data keys: {list(page_data.keys())}"
+                    "Skipping page due to missing 'markdown' or 'index'. Data keys: %s", list(page_data.keys())
                 )
                 continue
 
@@ -531,7 +316,7 @@ class MistralLoader:
 
             if not cleaned_content:
                 skipped_pages += 1
-                self._debug_log(f'Skipping empty page {page_index}')
+                self._debug_log('Skipping empty page %s', page_index)
                 continue
 
             # Create document with optimized metadata
@@ -551,7 +336,7 @@ class MistralLoader:
             )
 
         if skipped_pages > 0:
-            log.info(f'Processed {len(documents)} pages, skipped {skipped_pages} empty/invalid pages')
+            log.info('Processed %s pages, skipped %s empty/invalid pages', len(documents), skipped_pages)
 
         if not documents:
             # Case where pages existed but none had valid markdown/index
@@ -572,7 +357,6 @@ class MistralLoader:
     def load(self) -> List[Document]:
         """
         Executes the full OCR workflow: upload, get URL, process OCR, delete file.
-        Synchronous version for backward compatibility.
 
         Returns:
             A list of Document objects, one for each page processed.
@@ -584,7 +368,7 @@ class MistralLoader:
             if self.use_base64:
                 documents = self._process_results(self._process_ocr(self._get_file_data_url()))
                 total_time = time.time() - start_time
-                log.info(f'Sync OCR workflow completed in {total_time:.2f}s, produced {len(documents)} documents')
+                log.info('Sync OCR workflow completed in %.2fs, produced %s documents', total_time, len(documents))
                 return documents
 
             # 1. Upload file
@@ -600,7 +384,7 @@ class MistralLoader:
             documents = self._process_results(ocr_response)
 
             total_time = time.time() - start_time
-            log.info(f'Sync OCR workflow completed in {total_time:.2f}s, produced {len(documents)} documents')
+            log.info('Sync OCR workflow completed in %.2fs, produced %s documents', total_time, len(documents))
 
             return documents
 
@@ -625,125 +409,3 @@ class MistralLoader:
                 except Exception as del_e:
                     # Log deletion error, but don't overwrite original error if one occurred
                     log.error(f'Cleanup error: Could not delete file ID {file_id}. Reason: {del_e}')
-
-    async def load_async(self) -> List[Document]:
-        """
-        Asynchronous OCR workflow execution with optimized performance.
-
-        Returns:
-            A list of Document objects, one for each page processed.
-        """
-        file_id = None
-        start_time = time.time()
-
-        try:
-            async with self._get_session() as session:
-                if self.use_base64:
-                    ocr_response = await self._process_ocr_async(session, self._get_file_data_url())
-                    documents = self._process_results(ocr_response)
-                    total_time = time.time() - start_time
-                    log.info(f'Async OCR workflow completed in {total_time:.2f}s, produced {len(documents)} documents')
-                    return documents
-
-                # 1. Upload file with streaming
-                file_id = await self._upload_file_async(session)
-
-                # 2. Get signed URL
-                signed_url = await self._get_signed_url_async(session, file_id)
-
-                # 3. Process OCR
-                ocr_response = await self._process_ocr_async(session, signed_url)
-
-                # 4. Process results
-                documents = self._process_results(ocr_response)
-
-                total_time = time.time() - start_time
-                log.info(f'Async OCR workflow completed in {total_time:.2f}s, produced {len(documents)} documents')
-
-                return documents
-
-        except Exception as e:
-            total_time = time.time() - start_time
-            log.error(f'Async OCR workflow failed after {total_time:.2f}s: {e}')
-            return [
-                Document(
-                    page_content=f'Error during OCR processing: {e}',
-                    metadata={
-                        'error': 'processing_failed',
-                        'file_name': self.file_name,
-                    },
-                )
-            ]
-        finally:
-            # 5. Cleanup - always attempt file deletion
-            if file_id:
-                try:
-                    async with self._get_session() as session:
-                        await self._delete_file_async(session, file_id)
-                except Exception as cleanup_error:
-                    log.error(f'Cleanup failed for file ID {file_id}: {cleanup_error}')
-
-    @staticmethod
-    async def load_multiple_async(
-        loaders: List['MistralLoader'],
-        max_concurrent: int = 5,  # Limit concurrent requests
-    ) -> List[List[Document]]:
-        """
-        Process multiple files concurrently with controlled concurrency.
-
-        Args:
-            loaders: List of MistralLoader instances
-            max_concurrent: Maximum number of concurrent requests
-
-        Returns:
-            List of document lists, one for each loader
-        """
-        if not loaders:
-            return []
-
-        log.info(f'Starting concurrent processing of {len(loaders)} files with max {max_concurrent} concurrent')
-        start_time = time.time()
-
-        # Use semaphore to control concurrency
-        semaphore = asyncio.Semaphore(max_concurrent)
-
-        async def process_with_semaphore(loader: 'MistralLoader') -> List[Document]:
-            async with semaphore:
-                return await loader.load_async()
-
-        # Process all files with controlled concurrency
-        tasks = [process_with_semaphore(loader) for loader in loaders]
-        results = await asyncio.gather(*tasks, return_exceptions=True)
-
-        # Handle any exceptions in results
-        processed_results = []
-        for i, result in enumerate(results):
-            if isinstance(result, Exception):
-                log.error(f'File {i} failed: {result}')
-                processed_results.append(
-                    [
-                        Document(
-                            page_content=f'Error processing file: {result}',
-                            metadata={
-                                'error': 'batch_processing_failed',
-                                'file_index': i,
-                            },
-                        )
-                    ]
-                )
-            else:
-                processed_results.append(result)
-
-        # MONITORING: Log comprehensive batch processing statistics
-        total_time = time.time() - start_time
-        total_docs = sum(len(docs) for docs in processed_results)
-        success_count = sum(1 for result in results if not isinstance(result, Exception))
-        failure_count = len(results) - success_count
-
-        log.info(
-            f'Batch processing completed in {total_time:.2f}s: '
-            f'{success_count} files succeeded, {failure_count} files failed, '
-            f'produced {total_docs} total documents'
-        )
-
-        return processed_results

backend/open_webui/retrieval/loaders/paddleocr_vl.py

@@ -35,7 +35,7 @@ class PaddleOCRVLLoader:
         self.file_name = os.path.basename(file_path)
 
     def load(self) -> List[Document]:
-        log.info(f'Processing with PaddleOCR-vl: {self.file_path}')
+        log.info('Processing with PaddleOCR-vl: %s', self.file_path)
 
         try:
             with open(self.file_path, 'rb') as file:
@@ -96,7 +96,7 @@ class PaddleOCRVLLoader:
                 )
 
             if skipped_pages > 0:
-                log.info(f'PaddleOCR-vl: Processed {len(documents)} pages, skipped {skipped_pages} empty pages.')
+                log.info('PaddleOCR-vl: Processed %s pages, skipped %s empty pages.', len(documents), skipped_pages)
 
             if not documents:
                 log.warning('No valid text content found by PaddleOCR-vl.')

backend/open_webui/retrieval/loaders/pdf.py

@@ -0,0 +1,101 @@
+import datetime as dt
+import io
+import logging
+from pathlib import Path
+
+from langchain_core.document_loaders import BaseLoader
+from langchain_core.documents import Document
+
+log = logging.getLogger(__name__)
+
+
+class PDFLoader(BaseLoader):
+    def __init__(self, file_path, *, extract_images=False, mode='page'):
+        if mode not in ('single', 'page'):
+            raise ValueError("PDF mode must be 'single' or 'page'")
+        self.file_path = str(Path(file_path).expanduser())
+        self.extract_images = extract_images
+        self.mode = mode
+        self.ocr = None
+
+    def lazy_load(self):
+        from pypdf import PdfReader
+
+        with open(self.file_path, 'rb') as file:
+            reader = PdfReader(file)
+            metadata = {'producer': 'PyPDF', 'creator': 'PyPDF', 'creationdate': ''}
+            for key, value in (reader.metadata or {}).items():
+                key = key.removeprefix('/').lower()
+                value = value if type(value) in (str, int) else str(value)
+                if key in ('creationdate', 'moddate') and isinstance(value, str):
+                    try:
+                        value = dt.datetime.strptime(value.replace("'", ''), 'D:%Y%m%d%H%M%S%z').isoformat()
+                    except ValueError:
+                        pass
+                metadata[key] = (
+                    value.strip()
+                    if isinstance(value, str) and key not in ('creationdate', 'moddate', 'page_count', 'file_path')
+                    else value
+                )
+            metadata.update(source=self.file_path, total_pages=len(reader.pages))
+            labels = reader.page_labels if self.mode == 'page' else None
+            texts = []
+            for index, page in enumerate(reader.pages):
+                text = page.extract_text()
+                if self.extract_images:
+                    image_text = self._extract_images(page)
+                    if image_text:
+                        text = self._merge_image_text(text, image_text)
+                text = text.strip()
+                if self.mode == 'page':
+                    yield Document(page_content=text, metadata={**metadata, 'page': index, 'page_label': labels[index]})
+                else:
+                    texts.append(text)
+            if self.mode == 'single':
+                yield Document(page_content='\n\f'.join(texts), metadata=metadata)
+
+    @staticmethod
+    def _merge_image_text(text, image_text):
+        # Insert before the final paragraphs/footer where possible, matching existing chunks.
+        position, separator = len(text), '\n\n'
+        for _ in range(2):
+            for delimiter in ('\n\n\n', '\n\n'):
+                found = text.rfind(delimiter, 0, position)
+                if found >= 0:
+                    position, separator = found, delimiter
+                    break
+            else:
+                break
+        return text[:position] + separator + image_text + text[position:]
+
+    def _extract_images(self, page):
+        import numpy as np
+        from PIL import Image, UnidentifiedImageError
+
+        if '/Resources' not in page or '/XObject' not in page['/Resources']:
+            return ''
+        texts = []
+        xobjects = page['/Resources']['/XObject']
+        for name in xobjects:
+            try:
+                stream = xobjects[name]
+                if stream.get('/Subtype') != '/Image':
+                    continue
+                try:
+                    # Encoded images, including CMYK JPEGs, can go straight to Pillow.
+                    image = Image.open(io.BytesIO(stream.get_data()))
+                except UnidentifiedImageError:
+                    image = stream.decode_as_image()
+                pixels = np.array(image.convert('RGB'))
+            except Exception as e:
+                log.warning('Skipping unreadable PDF image %s: %s', name, e)
+                continue
+
+            if self.ocr is None:
+                from rapidocr import RapidOCR
+
+                self.ocr = RapidOCR()
+            result = self.ocr(pixels)
+            if result and result.txts:
+                texts.append('\n'.join(result.txts).strip())
+        return '\n\n' + '\n'.join(filter(None, texts)) + '\n\n' if any(texts) else ''

backend/open_webui/retrieval/loaders/tavily.py

@@ -4,6 +4,7 @@ from typing import Iterator, List, Literal, Union
 import requests
 from langchain_core.document_loaders import BaseLoader
 from langchain_core.documents import Document
+from open_webui.env import TAVILY_API_BASE_URL
 
 log = logging.getLogger(__name__)
 
@@ -48,7 +49,7 @@ class TavilyLoader(BaseLoader):
         self.urls = urls if isinstance(urls, list) else [urls]
         self.extract_depth = extract_depth
         self.continue_on_failure = continue_on_failure
-        self.api_url = 'https://api.tavily.com/extract'
+        self.api_url = f'{TAVILY_API_BASE_URL}/extract'
 
     def lazy_load(self) -> Iterator[Document]:
         """Extract and yield documents from the URLs using Tavily Extract API."""

backend/open_webui/retrieval/loaders/youtube.py

@@ -18,6 +18,32 @@ ALLOWED_NETLOCS = {
 }
 
 
+class YoutubeTranscriptError(Exception):
+    """A YouTube transcript could not be retrieved."""
+
+
+def _transcript_error_message(error: Exception, video_id: str) -> str:
+    name = type(error).__name__
+
+    if name in {'RequestBlocked', 'IpBlocked'}:
+        return (
+            f'YouTube blocked the transcript request for {video_id} from this server. '
+            'This usually means the server address is rate limited or belongs to a cloud '
+            'provider. A proxy for these requests can be configured under Admin Settings, '
+            'Web Search, Youtube Proxy URL.'
+        )
+    if name == 'TranscriptsDisabled':
+        return f'Transcripts are disabled for the YouTube video {video_id}.'
+    if name == 'AgeRestricted':
+        return f'The YouTube video {video_id} is age restricted, so its transcript cannot be retrieved.'
+    if name in {'VideoUnavailable', 'VideoUnplayable', 'InvalidVideoId'}:
+        return f'The YouTube video {video_id} is unavailable.'
+    if name == 'PoTokenRequired':
+        return f'YouTube requires additional verification to return the transcript for {video_id}.'
+
+    return f'Could not retrieve a transcript for the YouTube video {video_id}.'
+
+
 def _parse_video_id(url: str) -> Optional[str]:
     """Parse a YouTube URL and return the video ID if valid, otherwise None."""
     parsed_url = urlparse(url)
@@ -90,7 +116,7 @@ class YoutubeLoader:
 
         if self.proxy_url:
             youtube_proxies = GenericProxyConfig(http_url=self.proxy_url, https_url=self.proxy_url)
-            log.debug(f'Using proxy URL: {self.proxy_url[:14]}...')
+            log.debug('Using proxy URL: %s...', self.proxy_url[:14])
         else:
             youtube_proxies = None
 
@@ -98,31 +124,31 @@ class YoutubeLoader:
         try:
             transcript_list = transcript_api.list(self.video_id)
         except Exception as e:
-            log.warning(f'Loading YouTube transcript failed: {e}')
+            log.warning('Loading YouTube transcript failed: %s', e)
-            return []
+            raise YoutubeTranscriptError(_transcript_error_message(e, self.video_id)) from e
 
         # Try each language in order of priority
         for lang in self.language:
             try:
                 transcript = transcript_list.find_transcript([lang])
                 if transcript.is_generated:
-                    log.debug(f"Found generated transcript for language '{lang}'")
+                    log.debug("Found generated transcript for language '%s'", lang)
                     try:
                         transcript = transcript_list.find_manually_created_transcript([lang])
-                        log.debug(f"Found manual transcript for language '{lang}'")
+                        log.debug("Found manual transcript for language '%s'", lang)
                     except NoTranscriptFound:
-                        log.debug(f"No manual transcript found for language '{lang}', using generated")
+                        log.debug("No manual transcript found for language '%s', using generated", lang)
                         pass
 
-                log.debug(f"Found transcript for language '{lang}'")
+                log.debug("Found transcript for language '%s'", lang)
                 try:
                     transcript_pieces: List[Dict[str, Any]] = transcript.fetch()
                 except ParseError:
-                    log.debug(f"Empty or invalid transcript for language '{lang}'")
+                    log.debug("Empty or invalid transcript for language '%s'", lang)
                     continue
 
                 if not transcript_pieces:
-                    log.debug(f"Empty transcript for language '{lang}'")
+                    log.debug("Empty transcript for language '%s'", lang)
                     continue
 
                 transcript_text = ' '.join(
@@ -135,18 +161,20 @@ class YoutubeLoader:
                 )
                 return [Document(page_content=transcript_text, metadata=self._metadata)]
             except NoTranscriptFound:
-                log.debug(f"No transcript found for language '{lang}'")
+                log.debug("No transcript found for language '%s'", lang)
                 continue
             except Exception as e:
-                log.info(f"Error finding transcript for language '{lang}'")
+                log.info("Error finding transcript for language '%s'", lang)
-                raise e
+                raise YoutubeTranscriptError(_transcript_error_message(e, self.video_id)) from e
 
         # If we get here, all languages failed
         languages_tried = ', '.join(self.language)
         log.warning(
             f'No transcript found for any of the specified languages: {languages_tried}. Verify if the video has transcripts, add more languages if needed.'
         )
-        raise NoTranscriptFound(self.video_id, self.language, list(transcript_list))
+        raise YoutubeTranscriptError(
+            f'No transcript found for the YouTube video {self.video_id} in these languages: {languages_tried}.'
+        )
 
     async def aload(self) -> Generator[Document, None, None]:
         """Asynchronously load YouTube transcripts into `Document` objects."""

backend/open_webui/retrieval/models/colbert.py

@@ -12,7 +12,7 @@ log = logging.getLogger(__name__)
 
 class ColBERT(BaseReranker):
     def __init__(self, name, **kwargs) -> None:
-        log.info('ColBERT: Loading model', name)
+        log.info('ColBERT: Loading model %s', name)
         self.device = 'cuda' if torch.cuda.is_available() else 'cpu'
 
         DOCKER = kwargs.get('env') == 'docker'

backend/open_webui/retrieval/models/external.py

@@ -35,8 +35,8 @@ class ExternalReranker(BaseReranker):
         }
 
         try:
-            log.info(f'ExternalReranker:predict:model {self.model}')
+            log.info('ExternalReranker:predict:model %s', self.model)
-            log.info(f'ExternalReranker:predict:query {query}')
+            log.info('ExternalReranker:predict:query %s', query)
 
             headers = {
                 'Content-Type': 'application/json',

backend/open_webui/retrieval/utils.py

@@ -6,18 +6,17 @@ import logging
 import os
 import re
 import time
-from concurrent.futures import ThreadPoolExecutor
 from typing import Awaitable, Optional, Union
 from urllib.parse import quote
 
 import aiohttp
+import numpy as np
 import requests
-from huggingface_hub import snapshot_download
+from fastapi import HTTPException
 from langchain_classic.retrievers import (
     ContextualCompressionRetriever,
     EnsembleRetriever,
 )
-from langchain_community.retrievers import BM25Retriever
 from langchain_core.documents import Document
 from open_webui.config import (
     RAG_EMBEDDING_CONTENT_PREFIX,
@@ -25,6 +24,7 @@ from open_webui.config import (
     RAG_EMBEDDING_QUERY_PREFIX,
     VECTOR_DB,
 )
+from open_webui.constants import ERROR_MESSAGES
 from open_webui.env import (
     AIOHTTP_CLIENT_ALLOW_REDIRECTS,
     AIOHTTP_CLIENT_SESSION_SSL,
@@ -32,7 +32,10 @@ from open_webui.env import (
     BYPASS_RETRIEVAL_ACCESS_CONTROL,
     ENABLE_FORWARD_USER_INFO_HEADERS,
     ENABLE_RETRIEVAL_UNSCOPED_COLLECTIONS,
+    MPS_INFERENCE_LOCK,
     OFFLINE_MODE,
+    RAG_SOURCE_METADATA_KEYS,
+    USE_SLIM,
 )
 from open_webui.models.access_grants import AccessGrants
 from open_webui.models.chats import Chats
@@ -45,12 +48,12 @@ from open_webui.models.users import UserModel
 from open_webui.retrieval.loaders.youtube import YoutubeLoader
 from open_webui.retrieval.vector.async_client import ASYNC_VECTOR_DB_CLIENT
 from open_webui.retrieval.external import retrieve_external_knowledge
-from open_webui.retrieval.vector.factory import VECTOR_DB_CLIENT
+from open_webui.retrieval.vector.factory import get_vector_db_client
 from open_webui.retrieval.vector.main import GetResult, SearchResult
 from open_webui.retrieval.web.utils import get_web_loader
 from open_webui.utils.access_control.files import get_owner_accessible_folder_files, has_access_to_file
 from open_webui.utils.access_control.folders import has_folder_access
-from open_webui.utils.headers import include_user_info_headers
+from open_webui.utils.headers import get_json_bearer_headers, include_user_info_headers
 from open_webui.utils.misc import get_content_from_message, get_message_list
 
 log = logging.getLogger(__name__)
@@ -62,12 +65,22 @@ from langchain_core.callbacks import CallbackManagerForRetrieverRun
 from langchain_core.retrievers import BaseRetriever
 
 
+class BM25Retriever(BaseRetriever):
+    docs: list[Document]
+    vectorizer: Any
+    k: int
+
+    def _get_relevant_documents(self, query: str, *, run_manager: CallbackManagerForRetrieverRun) -> list[Document]:
+        return self.vectorizer.get_top_n(query.split(), self.docs, n=self.k)
+
+
 def is_youtube_url(url: str) -> bool:
     youtube_regex = r'^(https?://)?(www\.)?(youtube\.com|youtu\.be)/.+$'
     return re.match(youtube_regex, url) is not None
 
 
 LOADER_CONFIG_KEYS = {
+    'file_max_size': 'rag.file.max_size',
     'youtube_language': 'rag.youtube_loader_language',
     'youtube_proxy_url': 'rag.youtube_loader_proxy_url',
     'web_loader_ssl_verification': 'web.loader.ssl_verification',
@@ -103,6 +116,7 @@ LOADER_CONFIG_KEYS = {
     'EXTERNAL_DOCUMENT_LOADER_API_KEY': 'rag.external_document_loader_api_key',
     'EXTERNAL_DOCUMENT_LOADER_HEADERS': 'rag.external_document_loader_headers',
     'TIKA_SERVER_URL': 'rag.tika_server_url',
+    'TIKA_SERVER_VERSION': 'rag.tika_server_version',
     'DOCLING_SERVER_URL': 'rag.docling_server_url',
     'DOCLING_API_KEY': 'rag.docling_api_key',
     'DOCLING_PARAMS': 'rag.docling_params',
@@ -151,6 +165,7 @@ def build_loader_from_config(request, config: dict):
     from open_webui.retrieval.loaders.main import Loader
 
     loader_config = {key: config.get(key) for key in LOADER_CONFIG_KEYS if key.isupper()}
+    loader_config['FILE_MAX_SIZE'] = config.get('file_max_size')
     return Loader(
         engine=loader_config['CONTENT_EXTRACTION_ENGINE'],
         **{key: value for key, value in loader_config.items() if key != 'CONTENT_EXTRACTION_ENGINE'},
@@ -183,11 +198,20 @@ def _extract_text_from_binary_response(
 
     suffix = '.' + filename.split('.')[-1].lower() if '.' in filename else ''
 
-    with tempfile.NamedTemporaryFile(suffix=suffix, delete=False) as tmp:
+    max_size = loader_config.get('file_max_size')
-        tmp.write(response.content)
+    max_bytes = int(max_size) * 1024 * 1024 if max_size else 0
-        tmp_path = tmp.name
 
+    tmp_fd, tmp_path = tempfile.mkstemp(suffix=suffix)
     try:
+        downloaded = 0
+        # Stream to disk; response.content buffers the whole body in memory first.
+        with os.fdopen(tmp_fd, 'wb') as tmp:
+            for chunk in response.iter_content(64 * 1024):
+                downloaded += len(chunk)
+                if max_bytes and downloaded > max_bytes:
+                    raise ValueError(ERROR_MESSAGES.FILE_TOO_LARGE(size=f'{max_size} MB'))
+                tmp.write(chunk)
+
         loader = build_loader_from_config(request, loader_config)
         docs = loader.load(filename, content_type, tmp_path)
         for doc in docs:
@@ -198,14 +222,24 @@ def _extract_text_from_binary_response(
         os.remove(tmp_path)
 
 
+TEXT_APPLICATION_CONTENT_TYPES = {
+    'application/javascript',
+    'application/json',
+    'application/xml',
+    'application/x-javascript',
+}
+
+
 def _is_text_content_type(content_type: str) -> bool:
     """Return True if the content type should be handled by the web loader."""
     ct = content_type.split(';')[0].strip().lower()
+    if not ct:
+        return True
     if ct.startswith('text/'):
         return True
-    if any(t in ct for t in ['xml', 'json', 'javascript']):
+    if ct in TEXT_APPLICATION_CONTENT_TYPES:
         return True
-    return not ct  # empty / missing → assume HTML
+    return ct.endswith(('+xml', '+json'))
 
 
 async def get_content_from_url(request, url: str) -> str:
@@ -218,7 +252,7 @@ async def get_content_from_url(request, url: str) -> str:
 
 
 def _get_content_from_url_sync(request, url: str, loader_config):
-    from open_webui.retrieval.web.utils import validate_url, _SSRFSafeAdapter
+    from open_webui.retrieval.web.utils import validate_url, get_ssrf_safe_requests_session
 
     # Validate URL before making any request (blocks private IPs, non-HTTP, filter list)
     validate_url(url)
@@ -242,9 +276,7 @@ def _get_content_from_url_sync(request, url: str, loader_config):
     # cloud-metadata 169.254.169.254) via a public host that redirects internally.
     try:
         # Probe through the connect-time SSRF guard; bare requests.get re-resolves (DNS-rebinding gap).
-        session = requests.Session()
+        session = get_ssrf_safe_requests_session()
-        session.mount('http://', _SSRFSafeAdapter())
-        session.mount('https://', _SSRFSafeAdapter())
         response = session.get(url, stream=True, timeout=30, allow_redirects=AIOHTTP_CLIENT_ALLOW_REDIRECTS)
         response.raise_for_status()
         content_type = response.headers.get('Content-Type', '')
@@ -310,30 +342,26 @@ class VectorSearchRetriever(BaseRetriever):
 
 
 def query_doc(collection_name: str, query_embedding: list[float], k: int, user: UserModel = None):
-    try:
+    log.debug('query_doc:doc %s', collection_name)
-        log.debug(f'query_doc:doc {collection_name}')
+    result = get_vector_db_client().search(
-        result = VECTOR_DB_CLIENT.search(
+        collection_name=collection_name,
-            collection_name=collection_name,
+        vectors=[query_embedding],
-            vectors=[query_embedding],
+        limit=k,
-            limit=k,
+    )
-        )
 
-        if result:
+    if result:
-            log.info(f'query_doc:result {result.ids} {result.metadatas}')
+        log.info('query_doc:result %s %s', result.ids, result.metadatas)
 
-        return result
+    return result
-    except Exception as e:
-        log.exception(f'Error querying doc {collection_name} with limit {k}: {e}')
-        raise e
 
 
 def get_doc(collection_name: str, user: UserModel = None):
     try:
-        log.debug(f'get_doc:doc {collection_name}')
+        log.debug('get_doc:doc %s', collection_name)
-        result = VECTOR_DB_CLIENT.get(collection_name=collection_name)
+        result = get_vector_db_client().get(collection_name=collection_name)
 
         if result:
-            log.info(f'query_doc:result {result.ids} {result.metadatas}')
+            log.info('query_doc:result %s %s', result.ids, result.metadatas)
 
         return result
     except Exception as e:
@@ -458,7 +486,7 @@ async def query_doc_with_native_hybrid_search(
             'metadatas': [metadatas],
         }
     except Exception as e:
-        log.debug(f'Native hybrid search failed for {collection_name}, falling back to legacy hybrid search: {e}')
+        log.debug('Native hybrid search failed for %s, falling back to legacy hybrid search: %s', collection_name, e)
         return None
 
 
@@ -475,122 +503,116 @@ async def query_doc_with_hybrid_search(
     enable_enriched_texts: bool = False,
     native_hybrid_search: bool = True,
 ) -> dict:
-    try:
+    if native_hybrid_search and not enable_enriched_texts:
-        if native_hybrid_search and not enable_enriched_texts:
+        native_result = await query_doc_with_native_hybrid_search(
-            native_result = await query_doc_with_native_hybrid_search(
-                collection_name=collection_name,
-                query=query,
-                embedding_function=embedding_function,
-                k=k,
-                reranking_function=reranking_function,
-                k_reranker=k_reranker,
-                r=r,
-                hybrid_bm25_weight=hybrid_bm25_weight,
-            )
-            if native_result is not None:
-                return native_result
-
-        if collection_result is None:
-            collection_result = await ASYNC_VECTOR_DB_CLIENT.get(collection_name=collection_name)
-
-        # First check if collection_result has the required attributes
-        if (
-            not collection_result
-            or not hasattr(collection_result, 'documents')
-            or not hasattr(collection_result, 'metadatas')
-        ):
-            log.warning(f'query_doc_with_hybrid_search:no_docs {collection_name}')
-            return {'documents': [], 'metadatas': [], 'distances': []}
-
-        # Now safely check the documents content after confirming attributes exist
-        if (
-            not collection_result.documents
-            or len(collection_result.documents) == 0
-            or not collection_result.documents[0]
-        ):
-            log.warning(f'query_doc_with_hybrid_search:no_docs {collection_name}')
-            return {'documents': [], 'metadatas': [], 'distances': []}
-
-        log.debug(f'query_doc_with_hybrid_search:doc {collection_name}')
-
-        original_texts = collection_result.documents[0]
-        bm25_metadatas = [
-            {**meta, CHUNK_HASH_KEY: _content_hash(original_texts[idx])}
-            for idx, meta in enumerate(collection_result.metadatas[0])
-        ]
-
-        bm25_texts = get_enriched_texts(collection_result) if enable_enriched_texts else original_texts
-
-        bm25_retriever = BM25Retriever.from_texts(
-            texts=bm25_texts,
-            metadatas=bm25_metadatas,
-        )
-        bm25_retriever.k = k
-
-        vector_search_retriever = VectorSearchRetriever(
             collection_name=collection_name,
+            query=query,
             embedding_function=embedding_function,
-            top_k=k,
+            k=k,
-        )
-
-        # Use CHUNK_HASH_KEY for dedup so enriched BM25 texts don't defeat RRF
-        if hybrid_bm25_weight <= 0:
-            ensemble_retriever = EnsembleRetriever(
-                retrievers=[vector_search_retriever],
-                weights=[1.0],
-                id_key=CHUNK_HASH_KEY,
-            )
-        elif hybrid_bm25_weight >= 1:
-            ensemble_retriever = EnsembleRetriever(
-                retrievers=[bm25_retriever],
-                weights=[1.0],
-                id_key=CHUNK_HASH_KEY,
-            )
-        else:
-            ensemble_retriever = EnsembleRetriever(
-                retrievers=[bm25_retriever, vector_search_retriever],
-                weights=[hybrid_bm25_weight, 1.0 - hybrid_bm25_weight],
-                id_key=CHUNK_HASH_KEY,
-            )
-
-        compressor = RerankCompressor(
-            embedding_function=embedding_function,
-            top_n=k_reranker,
             reranking_function=reranking_function,
-            r_score=r,
+            k_reranker=k_reranker,
+            r=r,
+            hybrid_bm25_weight=hybrid_bm25_weight,
+        )
+        if native_result is not None:
+            return native_result
+
+    if collection_result is None:
+        collection_result = await ASYNC_VECTOR_DB_CLIENT.get(collection_name=collection_name)
+
+    # First check if collection_result has the required attributes
+    if (
+        not collection_result
+        or not hasattr(collection_result, 'documents')
+        or not hasattr(collection_result, 'metadatas')
+    ):
+        log.warning(f'query_doc_with_hybrid_search:no_docs {collection_name}')
+        return {'documents': [], 'metadatas': [], 'distances': []}
+
+    # Now safely check the documents content after confirming attributes exist
+    if not collection_result.documents or len(collection_result.documents) == 0 or not collection_result.documents[0]:
+        log.warning(f'query_doc_with_hybrid_search:no_docs {collection_name}')
+        return {'documents': [], 'metadatas': [], 'distances': []}
+
+    log.debug('query_doc_with_hybrid_search:doc %s', collection_name)
+
+    original_texts = collection_result.documents[0]
+    bm25_metadatas = [
+        {**meta, CHUNK_HASH_KEY: _content_hash(original_texts[idx])}
+        for idx, meta in enumerate(collection_result.metadatas[0])
+    ]
+
+    bm25_texts = get_enriched_texts(collection_result) if enable_enriched_texts else original_texts
+
+    from rank_bm25 import BM25Okapi
+
+    bm25_retriever = BM25Retriever(
+        docs=[Document(page_content=text, metadata=meta) for text, meta in zip(bm25_texts, bm25_metadatas)],
+        vectorizer=BM25Okapi([text.split() for text in bm25_texts]),
+        k=k,
+    )
+
+    vector_search_retriever = VectorSearchRetriever(
+        collection_name=collection_name,
+        embedding_function=embedding_function,
+        top_k=k,
+    )
+
+    # Use CHUNK_HASH_KEY for dedup so enriched BM25 texts don't defeat RRF
+    if hybrid_bm25_weight <= 0:
+        ensemble_retriever = EnsembleRetriever(
+            retrievers=[vector_search_retriever],
+            weights=[1.0],
+            id_key=CHUNK_HASH_KEY,
+        )
+    elif hybrid_bm25_weight >= 1:
+        ensemble_retriever = EnsembleRetriever(
+            retrievers=[bm25_retriever],
+            weights=[1.0],
+            id_key=CHUNK_HASH_KEY,
+        )
+    else:
+        ensemble_retriever = EnsembleRetriever(
+            retrievers=[bm25_retriever, vector_search_retriever],
+            weights=[hybrid_bm25_weight, 1.0 - hybrid_bm25_weight],
+            id_key=CHUNK_HASH_KEY,
         )
 
-        compression_retriever = ContextualCompressionRetriever(
+    compressor = RerankCompressor(
-            base_compressor=compressor, base_retriever=ensemble_retriever
+        embedding_function=embedding_function,
-        )
+        top_n=k_reranker,
+        reranking_function=reranking_function,
+        r_score=r,
+    )
 
-        result = await compression_retriever.ainvoke(query)
+    compression_retriever = ContextualCompressionRetriever(
+        base_compressor=compressor, base_retriever=ensemble_retriever
+    )
 
-        distances = [d.metadata.get('score') for d in result]
+    result = await compression_retriever.ainvoke(query)
-        documents = [d.page_content for d in result]
-        metadatas = [d.metadata for d in result]
 
-        # retrieve only min(k, k_reranker) items, sort and cut by distance if k < k_reranker
+    distances = [d.metadata.get('score') for d in result]
-        if k < k_reranker:
+    documents = [d.page_content for d in result]
-            sorted_items = sorted(zip(distances, documents, metadatas), key=lambda x: x[0], reverse=True)
+    metadatas = [d.metadata for d in result]
-            sorted_items = sorted_items[:k]
 
-            if sorted_items:
+    # retrieve only min(k, k_reranker) items, sort and cut by distance if k < k_reranker
-                distances, documents, metadatas = map(list, zip(*sorted_items))
+    if k < k_reranker:
-            else:
+        sorted_items = sorted(zip(distances, documents, metadatas), key=lambda x: x[0], reverse=True)
-                distances, documents, metadatas = [], [], []
+        sorted_items = sorted_items[:k]
 
-        result = {
+        if sorted_items:
-            'distances': [distances],
+            distances, documents, metadatas = map(list, zip(*sorted_items))
-            'documents': [documents],
+        else:
-            'metadatas': [metadatas],
+            distances, documents, metadatas = [], [], []
-        }
 
-        log.info('query_doc_with_hybrid_search:result ' + f'{result["metadatas"]} {result["distances"]}')
+    result = {
-        return result
+        'distances': [distances],
-    except Exception as e:
+        'documents': [documents],
-        log.exception(f'Error querying doc {collection_name} with hybrid search: {e}')
+        'metadatas': [metadatas],
-        raise e
+    }
+
+    log.info('query_doc_with_hybrid_search:result %s %s', result['metadatas'], result['distances'])
+    return result
 
 
 def merge_get_results(get_results: list[dict]) -> dict:
@@ -634,7 +656,7 @@ def merge_and_sort_query_results(query_results: list[dict], k: int) -> dict:
             if isinstance(document, str):
                 doc_hash = (metadata or {}).get(CHUNK_HASH_KEY) or _content_hash(document)
 
-                if doc_hash not in combined.keys():
+                if doc_hash not in combined:
                     combined[doc_hash] = (distance, document, metadata)
                     continue  # if doc is new, no further comparison is needed
 
@@ -708,10 +730,11 @@ async def query_collection(
                 enable_enriched_texts=config.get('rag.enable_hybrid_search_enriched_texts'),
             )
         except Exception as e:
-            log.debug(f'Hybrid search failed, falling back to vector search: {e}')
+            log.debug('Hybrid search failed, falling back to vector search: %s', e)
 
     results = []
-    error = False
+    last_error = None
+    failed_collection_names = set()
 
     def process_query_collection(collection_name, query_embedding):
         try:
@@ -722,11 +745,10 @@ async def query_collection(
                     query_embedding=query_embedding,
                 )
                 if result is not None:
-                    return result.model_dump(), None
+                    return result.model_dump(), None, collection_name
-            return None, None
+            return None, None, collection_name
         except Exception as e:
-            log.exception(f'Error when querying the collection: {e}')
+            return None, e, collection_name
-            return None, e
 
     # Sanitize: filter out None/empty queries to prevent embedding crashes
     # (e.g. when get_last_user_message returns None)
@@ -737,24 +759,30 @@ async def query_collection(
 
     # Generate all query embeddings (in one call)
     query_embeddings = await embedding_function(queries, prefix=RAG_EMBEDDING_QUERY_PREFIX)
-    log.debug(f'query_collection: processing {len(queries)} queries across {len(collection_names)} collections')
+    log.debug('query_collection: processing %s queries across %s collections', len(queries), len(collection_names))
 
-    with ThreadPoolExecutor() as executor:
+    task_results = await asyncio.gather(
-        future_results = []
+        *[
-        for query_embedding in query_embeddings:
+            asyncio.to_thread(process_query_collection, collection_name, query_embedding)
-            for collection_name in collection_names:
+            for query_embedding in query_embeddings
-                result = executor.submit(process_query_collection, collection_name, query_embedding)
+            for collection_name in collection_names
-                future_results.append(result)
+        ]
-        task_results = [future.result() for future in future_results]
+    )
 
-    for result, err in task_results:
+    for result, err, collection_name in task_results:
         if err is not None:
-            error = True
+            last_error = err
+            failed_collection_names.add(collection_name)
         elif result is not None:
             results.append(result)
 
-    if error and not results:
+    if failed_collection_names:
-        log.warning('All collection queries failed. No results returned.')
+        log.error(
+            'query_collection: %s collection(s) had failing queries: %s',
+            len(failed_collection_names),
+            ', '.join(sorted(failed_collection_names)),
+            exc_info=last_error,
+        )
 
     return merge_and_sort_query_results(results, k=k)
 
@@ -771,7 +799,8 @@ async def query_collection_with_hybrid_search(
     enable_enriched_texts: bool = False,
 ) -> dict:
     results = []
-    error = False
+    last_error = None
+    failed_collection_names = set()
 
     if not enable_enriched_texts:
 
@@ -813,7 +842,7 @@ async def query_collection_with_hybrid_search(
 
     collection_results = dict(await asyncio.gather(*(_fetch_collection(name) for name in collection_names)))
 
-    log.info(f'Starting hybrid search for {len(queries)} queries in {len(collection_names)} collections...')
+    log.info('Starting hybrid search for %s queries in %s collections...', len(queries), len(collection_names))
 
     async def process_query(collection_name, query):
         try:
@@ -830,10 +859,9 @@ async def query_collection_with_hybrid_search(
                 enable_enriched_texts=enable_enriched_texts,
                 native_hybrid_search=False,
             )
-            return result, None
+            return result, None, collection_name
         except Exception as e:
-            log.exception(f'Error when querying the collection with hybrid_search: {e}')
+            return None, e, collection_name
-            return None, e
 
     # Prepare tasks for all collections and queries
     # Avoid running any tasks for collections that failed to fetch data (have assigned None)
@@ -847,13 +875,22 @@ async def query_collection_with_hybrid_search(
     # Run all queries in parallel using asyncio.gather
     task_results = await asyncio.gather(*[process_query(collection_name, query) for collection_name, query in tasks])
 
-    for result, err in task_results:
+    for result, err, collection_name in task_results:
         if err is not None:
-            error = True
+            last_error = err
+            failed_collection_names.add(collection_name)
         elif result is not None:
             results.append(result)
 
-    if error and not results:
+    if failed_collection_names:
+        log.error(
+            'query_collection_with_hybrid_search: %s collection(s) had failing queries: %s',
+            len(failed_collection_names),
+            ', '.join(sorted(failed_collection_names)),
+            exc_info=last_error,
+        )
+
+    if failed_collection_names and not results:
         raise Exception('Hybrid search failed for all collections. Using Non-hybrid search as fallback.')
 
     return merge_and_sort_query_results(results, k=k)
@@ -867,15 +904,12 @@ def generate_openai_batch_embeddings(
     prefix: str = None,
     user: UserModel = None,
 ) -> list[list[float]]:
-    log.debug(f'generate_openai_batch_embeddings:model {model} batch size: {len(texts)}')
+    log.debug('generate_openai_batch_embeddings:model %s batch size: %s', model, len(texts))
     json_data = {'input': texts, 'model': model}
     if isinstance(RAG_EMBEDDING_PREFIX_FIELD_NAME, str) and isinstance(prefix, str):
         json_data[RAG_EMBEDDING_PREFIX_FIELD_NAME] = prefix
 
-    headers = {
+    headers = get_json_bearer_headers(key)
-        'Content-Type': 'application/json',
-        'Authorization': f'Bearer {key}',
-    }
     if ENABLE_FORWARD_USER_INFO_HEADERS and user:
         headers = include_user_info_headers(headers, user)
 
@@ -900,15 +934,12 @@ async def agenerate_openai_batch_embeddings(
     prefix: str = None,
     user: UserModel = None,
 ) -> list[list[float]]:
-    log.debug(f'agenerate_openai_batch_embeddings:model {model} batch size: {len(texts)}')
+    log.debug('agenerate_openai_batch_embeddings:model %s batch size: %s', model, len(texts))
     form_data = {'input': texts, 'model': model}
     if isinstance(RAG_EMBEDDING_PREFIX_FIELD_NAME, str) and isinstance(prefix, str):
         form_data[RAG_EMBEDDING_PREFIX_FIELD_NAME] = prefix
 
-    headers = {
+    headers = get_json_bearer_headers(key)
-        'Content-Type': 'application/json',
-        'Authorization': f'Bearer {key}',
-    }
     if ENABLE_FORWARD_USER_INFO_HEADERS and user:
         headers = include_user_info_headers(headers, user)
 
@@ -938,7 +969,7 @@ def generate_azure_openai_batch_embeddings(
     prefix: str = None,
     user: UserModel = None,
 ) -> list[list[float]]:
-    log.debug(f'generate_azure_openai_batch_embeddings:deployment {model} batch size: {len(texts)}')
+    log.debug('generate_azure_openai_batch_embeddings:deployment %s batch size: %s', model, len(texts))
     json_data = {'input': texts}
     if isinstance(RAG_EMBEDDING_PREFIX_FIELD_NAME, str) and isinstance(prefix, str):
         json_data[RAG_EMBEDDING_PREFIX_FIELD_NAME] = prefix
@@ -980,7 +1011,7 @@ async def agenerate_azure_openai_batch_embeddings(
     prefix: str = None,
     user: UserModel = None,
 ) -> list[list[float]]:
-    log.debug(f'agenerate_azure_openai_batch_embeddings:deployment {model} batch size: {len(texts)}')
+    log.debug('agenerate_azure_openai_batch_embeddings:deployment %s batch size: %s', model, len(texts))
     form_data = {'input': texts}
     if isinstance(RAG_EMBEDDING_PREFIX_FIELD_NAME, str) and isinstance(prefix, str):
         form_data[RAG_EMBEDDING_PREFIX_FIELD_NAME] = prefix
@@ -1019,15 +1050,12 @@ def generate_ollama_batch_embeddings(
     prefix: str = None,
     user: UserModel = None,
 ) -> list[list[float]]:
-    log.debug(f'generate_ollama_batch_embeddings:model {model} batch size: {len(texts)}')
+    log.debug('generate_ollama_batch_embeddings:model %s batch size: %s', model, len(texts))
     json_data = {'input': texts, 'model': model, 'truncate': True}
     if isinstance(RAG_EMBEDDING_PREFIX_FIELD_NAME, str) and isinstance(prefix, str):
         json_data[RAG_EMBEDDING_PREFIX_FIELD_NAME] = prefix
 
-    headers = {
+    headers = get_json_bearer_headers(key)
-        'Content-Type': 'application/json',
-        'Authorization': f'Bearer {key}',
-    }
     if ENABLE_FORWARD_USER_INFO_HEADERS and user:
         headers = include_user_info_headers(headers, user)
 
@@ -1055,15 +1083,12 @@ async def agenerate_ollama_batch_embeddings(
     prefix: str = None,
     user: UserModel = None,
 ) -> list[list[float]]:
-    log.debug(f'agenerate_ollama_batch_embeddings:model {model} batch size: {len(texts)}')
+    log.debug('agenerate_ollama_batch_embeddings:model %s batch size: %s', model, len(texts))
     form_data = {'input': texts, 'model': model, 'truncate': True}
     if isinstance(RAG_EMBEDDING_PREFIX_FIELD_NAME, str) and isinstance(prefix, str):
         form_data[RAG_EMBEDDING_PREFIX_FIELD_NAME] = prefix
 
-    headers = {
+    headers = get_json_bearer_headers(key)
-        'Content-Type': 'application/json',
-        'Authorization': f'Bearer {key}',
-    }
     if ENABLE_FORWARD_USER_INFO_HEADERS and user:
         headers = include_user_info_headers(headers, user)
 
@@ -1101,6 +1126,8 @@ def get_embedding_function(
     if embedding_engine == '':
         # Sentence transformers: CPU-bound sync operation
         async def async_embedding_function(query, prefix=None, user=None):
+            if USE_SLIM:
+                raise HTTPException(503, 'Configure an external embedding engine (openai, ollama, azure_openai).')
             # Deferred so a missing local model degrades RAG instead of crashing boot.
             if embedding_function is None:
                 raise ValueError(
@@ -1108,17 +1135,16 @@ def get_embedding_function(
                     'SentenceTransformer model name, or configure an external '
                     'RAG_EMBEDDING_ENGINE (ollama, openai, azure_openai).'
                 )
-            return await asyncio.to_thread(
+
-                (
+            def encode():
-                    lambda query, prefix=None: embedding_function.encode(
+                with MPS_INFERENCE_LOCK:
+                    return embedding_function.encode(
                         query,
                         batch_size=int(embedding_batch_size),
                         **({'prompt': prefix} if prefix else {}),
                     ).tolist()
-                ),
+
-                query,
+            return await asyncio.to_thread(encode)
-                prefix,
-            )
 
         return async_embedding_function
     elif embedding_engine in ['ollama', 'openai', 'azure_openai']:
@@ -1139,7 +1165,7 @@ def get_embedding_function(
                 batches = [query[i : i + embedding_batch_size] for i in range(0, len(query), embedding_batch_size)]
 
                 if enable_async:
-                    log.debug(f'generate_multiple_async: Processing {len(batches)} batches in parallel')
+                    log.debug('generate_multiple_async: Processing %s batches in parallel', len(batches))
                     # Use semaphore to limit concurrent embedding API requests
                     # 0 = unlimited (no semaphore)
                     if concurrent_requests:
@@ -1154,7 +1180,7 @@ def get_embedding_function(
                         tasks = [embedding_function(batch, prefix=prefix, user=user) for batch in batches]
                     batch_results = await asyncio.gather(*tasks)
                 else:
-                    log.debug(f'generate_multiple_async: Processing {len(batches)} batches sequentially')
+                    log.debug('generate_multiple_async: Processing %s batches sequentially', len(batches))
                     batch_results = []
                     for batch in batches:
                         batch_results.append(await embedding_function(batch, prefix=prefix, user=user))
@@ -1167,7 +1193,9 @@ def get_embedding_function(
                     embeddings.extend(batch_embeddings)
 
                 log.debug(
-                    f'generate_multiple_async: Generated {len(embeddings)} embeddings from {len(batches)} parallel batches'
+                    'generate_multiple_async: Generated %s embeddings from %s parallel batches',
+                    len(embeddings),
+                    len(batches),
                 )
                 return embeddings
             else:
@@ -1233,6 +1261,14 @@ async def generate_embeddings(
 
 
 def get_reranking_function(reranking_engine, reranking_model, reranking_function, reranking_batch_size=32):
+    if USE_SLIM and reranking_model and reranking_engine != 'external':
+
+        def unavailable(query, documents, user=None):
+            raise HTTPException(
+                503, 'Configure an external reranker, or clear the reranking model to use cosine scoring.'
+            )
+
+        return unavailable
     if reranking_function is None:
         return None
     if reranking_engine == 'external':
@@ -1240,9 +1276,14 @@ def get_reranking_function(reranking_engine, reranking_model, reranking_function
             [(query, doc.page_content) for doc in documents], user=user
         )
     else:
-        return lambda query, documents, user=None: reranking_function.predict(
+
-            [(query, doc.page_content) for doc in documents], batch_size=int(reranking_batch_size)
+        def predict(query, documents, user=None):
-        )
+            with MPS_INFERENCE_LOCK:
+                return reranking_function.predict(
+                    [(query, doc.page_content) for doc in documents], batch_size=int(reranking_batch_size)
+                )
+
+        return predict
 
 
 # UUIDs, SHA-256 digests, and prefixed variants thereof all fit [A-Za-z0-9_-].
@@ -1321,6 +1362,11 @@ async def filter_accessible_collections(
     return validated
 
 
+def filter_source_metadata(metadata: dict) -> dict:
+    """Keep only the chunk metadata keys the operator allowed the model to see."""
+    return {key: metadata[key] for key in RAG_SOURCE_METADATA_KEYS if metadata.get(key) is not None}
+
+
 async def get_sources_from_items(
     request,
     items,
@@ -1415,8 +1461,21 @@ async def get_sources_from_items(
         elif item.get('type') == 'chat':
             # Chat Attached
             chat = await Chats.get_chat_by_id(item.get('id'))
+            has_read_access = bool(chat and (user.role == 'admin' or chat.user_id == user.id))
 
-            if chat and (user.role == 'admin' or chat.user_id == user.id):
+            if chat and not has_read_access:
+                has_read_access = await AccessGrants.has_access(
+                    user_id=user.id,
+                    resource_type='shared_chat',
+                    resource_id=chat.id,
+                    permission='read',
+                )
+
+            if chat and not has_read_access and chat.folder_id:
+                folder = await Folders.get_folder_by_id(chat.folder_id)
+                has_read_access = folder and await has_folder_access(user.id, folder, 'read', db=None)
+
+            if has_read_access:
                 messages_map = chat.chat.get('history', {}).get('messages', {})
                 message_id = chat.chat.get('history', {}).get('currentId')
 
@@ -1607,14 +1666,14 @@ async def get_sources_from_items(
         if query_result is None and collection_names:
             collection_names = set(collection_names).difference(extracted_collections)
             if not collection_names:
-                log.debug(f'skipping {item} as it has already been extracted')
+                log.debug('skipping %s as it has already been extracted', item)
                 continue
 
             # Filter out collections the user cannot read
             if user and (item.get('type'), item.get('id')) not in folder_items:
                 collection_names = await filter_accessible_collections(collection_names, user)
                 if not collection_names:
-                    log.debug(f'access denied for all collections in item {item}')
+                    log.debug('access denied for all collections in item %s', item)
                     continue
 
             try:
@@ -1660,6 +1719,8 @@ async def get_sources_from_items(
 
 
 def get_model_path(model: str, update_model: bool = False):
+    from huggingface_hub import snapshot_download
+
     # Construct huggingface_hub kwargs with local_files_only to return the snapshot path
     cache_dir = os.getenv('SENTENCE_TRANSFORMERS_HOME')
 
@@ -1673,8 +1734,8 @@ def get_model_path(model: str, update_model: bool = False):
         'local_files_only': local_files_only,
     }
 
-    log.debug(f'model: {model}')
+    log.debug('model: %s', model)
-    log.debug(f'snapshot_kwargs: {snapshot_kwargs}')
+    log.debug('snapshot_kwargs: %s', snapshot_kwargs)
 
     # Inspiration from upstream sentence_transformers
     if os.path.exists(model) or ('\\' in model or model.count('/') > 1) and local_files_only:
@@ -1689,7 +1750,7 @@ def get_model_path(model: str, update_model: bool = False):
     # Attempt to query the huggingface_hub library to determine the local path and/or to update
     try:
         model_repo_path = snapshot_download(**snapshot_kwargs)
-        log.debug(f'model_repo_path: {model_repo_path}')
+        log.debug('model_repo_path: %s', model_repo_path)
         return model_repo_path
     except Exception as e:
         log.exception(f'Cannot determine model snapshot path: {e}')
@@ -1705,6 +1766,17 @@ from langchain_core.callbacks import Callbacks
 from langchain_core.documents import BaseDocumentCompressor, Document
 
 
+def cosine_similarity(query, documents) -> np.ndarray:
+    """Score one query against documents without loading a model runtime."""
+    if len(documents) == 0:
+        return np.array([], dtype=float)
+    query = np.asarray(query, dtype=float).reshape(-1)
+    documents = np.asarray(documents, dtype=float)
+    query = query / max(np.linalg.norm(query), 1e-12)
+    documents = documents / np.maximum(np.linalg.norm(documents, axis=1, keepdims=True), 1e-12)
+    return documents @ query
+
+
 class RerankCompressor(BaseDocumentCompressor):
     embedding_function: Any
     top_n: int
@@ -1740,18 +1812,18 @@ class RerankCompressor(BaseDocumentCompressor):
         query: str,
         callbacks: Callbacks | None = None,
     ) -> Sequence[Document]:
+        if not documents:
+            return []
         reranking = self.reranking_function is not None
 
         scores = None
         if reranking:
             scores = await asyncio.to_thread(self.reranking_function, query, documents)
         else:
-            from sentence_transformers import util as st_util
-
             query_embedding = await self.embedding_function(query, RAG_EMBEDDING_QUERY_PREFIX)
             doc_texts = [doc.page_content for doc in documents]
             document_embedding = await self.embedding_function(doc_texts, RAG_EMBEDDING_CONTENT_PREFIX)
-            scores = st_util.cos_sim(query_embedding, document_embedding)[0]
+            scores = cosine_similarity(query_embedding, document_embedding)
 
         if scores is not None:
             docs_with_scores = list(

backend/open_webui/retrieval/vector/async_client.py

@@ -15,9 +15,8 @@ transparently dispatches each call to a worker thread via
 `asyncio.to_thread`. Async callers can `await ASYNC_VECTOR_DB_CLIENT.x(...)`
 in place of `VECTOR_DB_CLIENT.x(...)` and the loop stays responsive.
 
-The original `VECTOR_DB_CLIENT` is unchanged, so callers already running
+Client initialization and calls run in the worker thread. Synchronous callers
-inside `run_in_threadpool` (e.g. `save_docs_to_vector_db`) are not
+already inside `run_in_threadpool` use `get_vector_db_client()` directly.
-affected.
 
 Thread-safety expectations
 --------------------------
@@ -55,7 +54,7 @@ from __future__ import annotations
 import asyncio
 from typing import Dict, List, Optional, Union
 
-from open_webui.retrieval.vector.factory import VECTOR_DB_CLIENT
+from open_webui.retrieval.vector.factory import get_vector_db_client
 from open_webui.retrieval.vector.main import (
     GetResult,
     SearchResult,
@@ -73,30 +72,30 @@ class AsyncVectorDBClient:
     typically swallowed by surrounding ``try/except``).
     """
 
-    def __init__(self, sync_client: VectorDBBase) -> None:
+    def __init__(self, sync_client: Optional[VectorDBBase] = None) -> None:
         self._sync = sync_client
 
     @property
     def sync(self) -> VectorDBBase:
         """Escape hatch for code that must call the sync client directly
         (e.g. already inside a worker thread)."""
-        return self._sync
+        return self._sync if self._sync is not None else get_vector_db_client()
 
     @property
     def supports_hybrid_search(self) -> bool:
-        return type(self._sync).hybrid_search is not VectorDBBase.hybrid_search
+        return type(self.sync).hybrid_search is not VectorDBBase.hybrid_search
 
     async def has_collection(self, collection_name: str) -> bool:
-        return await asyncio.to_thread(self._sync.has_collection, collection_name)
+        return await asyncio.to_thread(lambda: self.sync.has_collection(collection_name))
 
     async def delete_collection(self, collection_name: str) -> None:
-        return await asyncio.to_thread(self._sync.delete_collection, collection_name)
+        return await asyncio.to_thread(lambda: self.sync.delete_collection(collection_name))
 
     async def insert(self, collection_name: str, items: List[VectorItem]) -> None:
-        return await asyncio.to_thread(self._sync.insert, collection_name, items)
+        return await asyncio.to_thread(lambda: self.sync.insert(collection_name, items))
 
     async def upsert(self, collection_name: str, items: List[VectorItem]) -> None:
-        return await asyncio.to_thread(self._sync.upsert, collection_name, items)
+        return await asyncio.to_thread(lambda: self.sync.upsert(collection_name, items))
 
     async def search(
         self,
@@ -105,7 +104,7 @@ class AsyncVectorDBClient:
         filter: Optional[Dict] = None,
         limit: int = 10,
     ) -> Optional[SearchResult]:
-        return await asyncio.to_thread(self._sync.search, collection_name, vectors, filter, limit)
+        return await asyncio.to_thread(lambda: self.sync.search(collection_name, vectors, filter, limit))
 
     async def hybrid_search(
         self,
@@ -117,13 +116,7 @@ class AsyncVectorDBClient:
         hybrid_bm25_weight: float = 0.5,
     ) -> Optional[SearchResult]:
         return await asyncio.to_thread(
-            self._sync.hybrid_search,
+            lambda: self.sync.hybrid_search(collection_name, query, vectors, filter, limit, hybrid_bm25_weight)
-            collection_name,
-            query,
-            vectors,
-            filter,
-            limit,
-            hybrid_bm25_weight,
         )
 
     async def query(
@@ -132,10 +125,10 @@ class AsyncVectorDBClient:
         filter: Dict,
         limit: Optional[int] = None,
     ) -> Optional[GetResult]:
-        return await asyncio.to_thread(self._sync.query, collection_name, filter, limit)
+        return await asyncio.to_thread(lambda: self.sync.query(collection_name, filter, limit))
 
     async def get(self, collection_name: str) -> Optional[GetResult]:
-        return await asyncio.to_thread(self._sync.get, collection_name)
+        return await asyncio.to_thread(lambda: self.sync.get(collection_name))
 
     async def delete(
         self,
@@ -143,10 +136,10 @@ class AsyncVectorDBClient:
         ids: Optional[List[str]] = None,
         filter: Optional[Dict] = None,
     ) -> None:
-        return await asyncio.to_thread(self._sync.delete, collection_name, ids, filter)
+        return await asyncio.to_thread(lambda: self.sync.delete(collection_name, ids, filter))
 
     async def reset(self) -> None:
-        return await asyncio.to_thread(self._sync.reset)
+        return await asyncio.to_thread(lambda: self.sync.reset())
 
 
-ASYNC_VECTOR_DB_CLIENT = AsyncVectorDBClient(VECTOR_DB_CLIENT)
+ASYNC_VECTOR_DB_CLIENT = AsyncVectorDBClient()

backend/open_webui/retrieval/vector/dbs/chroma.py

@@ -16,6 +16,8 @@ from open_webui.config import (
     CHROMA_HTTP_SSL,
     CHROMA_TENANT,
 )
+from open_webui.env import USE_SLIM
+from fastapi import HTTPException
 from open_webui.retrieval.vector.main import (
     GetResult,
     SearchResult,
@@ -29,6 +31,8 @@ log = logging.getLogger(__name__)
 
 class ChromaClient(VectorDBBase):
     def __init__(self):
+        if USE_SLIM and not CHROMA_HTTP_HOST:
+            raise HTTPException(503, 'Configure CHROMA_HTTP_HOST: embedded Chroma is unavailable in slim.')
         settings_dict = {
             'allow_reset': True,
             'anonymized_telemetry': False,
@@ -58,7 +62,7 @@ class ChromaClient(VectorDBBase):
 
     def has_collection(self, collection_name: str) -> bool:
         try:
-            self.client.get_collection(name=collection_name)
+            self.client.get_collection(name=collection_name, embedding_function=None)
             return True
         except NotFoundError:
             return False
@@ -76,7 +80,7 @@ class ChromaClient(VectorDBBase):
     ) -> Optional[SearchResult]:
         # Search for the nearest neighbor items based on the vectors and return 'limit' number of results.
         try:
-            collection = self.client.get_collection(name=collection_name)
+            collection = self.client.get_collection(name=collection_name, embedding_function=None)
             if collection:
                 result = collection.query(
                     query_embeddings=vectors,
@@ -105,7 +109,7 @@ class ChromaClient(VectorDBBase):
     def query(self, collection_name: str, filter: dict, limit: Optional[int] = None) -> Optional[GetResult]:
         # Query the items from the collection based on the filter.
         try:
-            collection = self.client.get_collection(name=collection_name)
+            collection = self.client.get_collection(name=collection_name, embedding_function=None)
             if collection:
                 result = collection.get(
                     where=filter,
@@ -125,7 +129,7 @@ class ChromaClient(VectorDBBase):
 
     def get(self, collection_name: str) -> Optional[GetResult]:
         # Get all the items in the collection.
-        collection = self.client.get_collection(name=collection_name)
+        collection = self.client.get_collection(name=collection_name, embedding_function=None)
         if collection:
             result = collection.get()
             return GetResult(
@@ -139,7 +143,9 @@ class ChromaClient(VectorDBBase):
 
     def insert(self, collection_name: str, items: list[VectorItem]):
         # Insert the items into the collection, if the collection does not exist, it will be created.
-        collection = self.client.get_or_create_collection(name=collection_name, metadata={'hnsw:space': 'cosine'})
+        collection = self.client.get_or_create_collection(
+            name=collection_name, metadata={'hnsw:space': 'cosine'}, embedding_function=None
+        )
 
         ids = [item['id'] for item in items]
         documents = [item['text'] for item in items]
@@ -157,7 +163,9 @@ class ChromaClient(VectorDBBase):
 
     def upsert(self, collection_name: str, items: list[VectorItem]):
         # Update the items in the collection, if the items are not present, insert them. If the collection does not exist, it will be created.
-        collection = self.client.get_or_create_collection(name=collection_name, metadata={'hnsw:space': 'cosine'})
+        collection = self.client.get_or_create_collection(
+            name=collection_name, metadata={'hnsw:space': 'cosine'}, embedding_function=None
+        )
 
         ids = [item['id'] for item in items]
         documents = [item['text'] for item in items]
@@ -174,7 +182,7 @@ class ChromaClient(VectorDBBase):
     ):
         # Delete the items from the collection based on the ids.
         try:
-            collection = self.client.get_collection(name=collection_name)
+            collection = self.client.get_collection(name=collection_name, embedding_function=None)
             if collection:
                 if ids:
                     collection.delete(ids=ids)
@@ -182,7 +190,7 @@ class ChromaClient(VectorDBBase):
                     collection.delete(where=filter)
         except Exception as e:
             # If collection doesn't exist, that's fine - nothing to delete
-            log.debug(f'Attempted to delete from non-existent collection {collection_name}. Ignoring.')
+            log.debug('Attempted to delete from non-existent collection %s. Ignoring.', collection_name)
             pass
 
     def reset(self):

backend/open_webui/retrieval/vector/dbs/elasticsearch.py

@@ -3,7 +3,7 @@ NOTE: This vector database integration is community-supported and maintained on
 """
 
 import ssl
-from typing import Optional
+from typing import Any, Optional
 
 from elasticsearch import BadRequestError, Elasticsearch
 from elasticsearch.helpers import bulk, scan
@@ -23,7 +23,13 @@ from open_webui.retrieval.vector.main import (
     VectorDBBase,
     VectorItem,
 )
-from open_webui.retrieval.vector.utils import process_metadata
+from open_webui.retrieval.vector.utils import iter_filter_conditions, process_metadata
+
+
+def _metadata_filter(key: str, op: str, value: Any) -> dict:
+    if op == '$in':
+        return {'terms': {f'metadata.{key}': value}}
+    return {'term': {f'metadata.{key}': value}}
 
 
 class ElasticsearchClient(VectorDBBase):
@@ -161,12 +167,16 @@ class ElasticsearchClient(VectorDBBase):
         filter: Optional[dict] = None,
         limit: int = 10,
     ) -> Optional[SearchResult]:
+        filters = [{'term': {'collection': collection_name}}]
+        if filter:
+            filters.extend(_metadata_filter(key, op, value) for key, op, value in iter_filter_conditions(filter))
+
         query = {
             'size': limit,
             '_source': ['text', 'metadata'],
             'query': {
                 'script_score': {
-                    'query': {'bool': {'filter': [{'term': {'collection': collection_name}}]}},
+                    'query': {'bool': {'filter': filters}},
                     'script': {
                         'source': "cosineSimilarity(params.vector, 'vector') + 1.0",
                         'params': {'vector': vectors[0]},  # Assuming single query vector

backend/open_webui/retrieval/vector/dbs/mariadb_vector.py

@@ -5,7 +5,6 @@ NOTE: This vector database integration is community-supported and maintained on
 from __future__ import annotations
 
 import array
-import json
 import logging
 import math
 import re
@@ -30,6 +29,7 @@ from open_webui.retrieval.vector.main import (
     VectorItem,
 )
 from open_webui.retrieval.vector.utils import process_metadata
+from open_webui.utils.json_codec import JSONCodec
 from sqlalchemy import create_engine
 from sqlalchemy.pool import NullPool, QueuePool
 
@@ -72,7 +72,7 @@ def _safe_json(v: Any) -> Dict[str, Any]:
             return {}
     if isinstance(v, str):
         try:
-            j = json.loads(v)
+            j = JSONCodec.loads(v)
             return j if isinstance(j, dict) else {}
         except Exception:
             return {}
@@ -324,7 +324,7 @@ class MariaDBVectorClient(VectorDBBase):
                                 emb,
                                 collection_name,
                                 item.get('text'),
-                                json.dumps(meta),
+                                JSONCodec.dumps(meta),
                             )
                         )
                     cur.executemany(sql, params)
@@ -367,7 +367,7 @@ class MariaDBVectorClient(VectorDBBase):
                                 emb,
                                 collection_name,
                                 item.get('text'),
-                                json.dumps(meta),
+                                JSONCodec.dumps(meta),
                             )
                         )
                     cur.executemany(sql, params)

backend/open_webui/retrieval/vector/dbs/milvus.py

@@ -2,9 +2,9 @@
 NOTE: This vector database integration is community-supported and maintained on a best-effort basis.
 """
 
-import json
 import logging
-from typing import Optional
+import re
+from typing import Any, Optional
 
 from open_webui.config import (
     MILVUS_DB,
@@ -24,7 +24,8 @@ from open_webui.retrieval.vector.main import (
     VectorDBBase,
     VectorItem,
 )
-from open_webui.retrieval.vector.utils import process_metadata
+from open_webui.retrieval.vector.utils import iter_filter_conditions, process_metadata
+from open_webui.utils.json_codec import JSONCodec
 from pymilvus import DataType
 from pymilvus import MilvusClient as Client
 from pymilvus.exceptions import MilvusException
@@ -35,6 +36,36 @@ log = logging.getLogger(__name__)
 # field). Clamp long chunks before insert so one oversized chunk can't fail the
 # whole batch and leave the file with zero embeddings.
 MILVUS_TEXT_MAX_LENGTH = 65535
+_SAFE_METADATA_KEY_RE = re.compile(r'^[A-Za-z_][A-Za-z0-9_]{0,63}$')
+
+
+def _escape_milvus_string(value: str) -> str:
+    if not isinstance(value, str):
+        raise TypeError(f'Expected str, got {type(value).__name__}')
+    return value.replace('\\', '\\\\').replace("'", "\\'")
+
+
+def _milvus_literal(value: Any) -> str:
+    if isinstance(value, str):
+        return f"'{_escape_milvus_string(value)}'"
+    if isinstance(value, bool):
+        return str(value).lower()
+    if isinstance(value, (int, float)):
+        return str(value)
+    raise TypeError(f'Unsupported Milvus filter value type: {type(value).__name__}')
+
+
+def _metadata_exprs(filter: Optional[dict]) -> list[str]:
+    exprs = []
+    for key, op, value in iter_filter_conditions(filter):
+        if not isinstance(key, str) or not _SAFE_METADATA_KEY_RE.fullmatch(key):
+            raise ValueError(f'Invalid Milvus metadata filter key: {key!r}')
+        if op == '$in':
+            items = [f"metadata['{key}'] == {_milvus_literal(item)}" for item in value]
+            exprs.append(f'({" or ".join(items)})' if items else 'false')
+        else:
+            exprs.append(f"metadata['{key}'] == {_milvus_literal(value)}")
+    return exprs
 
 
 class MilvusClient(VectorDBBase):
@@ -125,7 +156,7 @@ class MilvusClient(VectorDBBase):
         index_type = MILVUS_INDEX_TYPE.upper()
         metric_type = MILVUS_METRIC_TYPE.upper()
 
-        log.info(f'Using Milvus index type: {index_type}, metric type: {metric_type}')
+        log.info('Using Milvus index type: %s, metric type: %s', index_type, metric_type)
 
         index_creation_params = {}
         if index_type == 'HNSW':
@@ -133,18 +164,18 @@ class MilvusClient(VectorDBBase):
                 'M': MILVUS_HNSW_M,
                 'efConstruction': MILVUS_HNSW_EFCONSTRUCTION,
             }
-            log.info(f'HNSW params: {index_creation_params}')
+            log.info('HNSW params: %s', index_creation_params)
         elif index_type == 'IVF_FLAT':
             index_creation_params = {'nlist': MILVUS_IVF_FLAT_NLIST}
-            log.info(f'IVF_FLAT params: {index_creation_params}')
+            log.info('IVF_FLAT params: %s', index_creation_params)
         elif index_type == 'DISKANN':
             index_creation_params = {
                 'max_degree': MILVUS_DISKANN_MAX_DEGREE,
                 'search_list_size': MILVUS_DISKANN_SEARCH_LIST_SIZE,
             }
-            log.info(f'DISKANN params: {index_creation_params}')
+            log.info('DISKANN params: %s', index_creation_params)
         elif index_type in ['FLAT', 'AUTOINDEX']:
-            log.info(f'Using {index_type} index with no specific build-time params.')
+            log.info('Using %s index with no specific build-time params.', index_type)
         else:
             log.warning(
                 f"Unsupported MILVUS_INDEX_TYPE: '{index_type}'. "
@@ -167,7 +198,11 @@ class MilvusClient(VectorDBBase):
             index_params=index_params,
         )
         log.info(
-            f"Successfully created collection '{self.collection_prefix}_{collection_name}' with index type '{index_type}' and metric '{metric_type}'."
+            "Successfully created collection '%s_%s' with index type '%s' and metric '%s'.",
+            self.collection_prefix,
+            collection_name,
+            index_type,
+            metric_type,
         )
 
     def has_collection(self, collection_name: str) -> bool:
@@ -189,6 +224,9 @@ class MilvusClient(VectorDBBase):
     ) -> Optional[SearchResult]:
         # Search for the nearest neighbor items based on the vectors and return 'limit' number of results.
         collection_name = collection_name.replace('-', '_')
+        kwargs = {}
+        if filter:
+            kwargs['filter'] = ' and '.join(_metadata_exprs(filter))
         # For some index types like IVF_FLAT, search params like nprobe can be set.
         # Example: search_params = {"nprobe": 10} if using IVF_FLAT
         # For simplicity, not adding configurable search_params here, but could be extended.
@@ -197,6 +235,7 @@ class MilvusClient(VectorDBBase):
             data=vectors,
             limit=limit,
             output_fields=['data', 'metadata'],
+            **kwargs,
             # search_params=search_params # Potentially add later if needed
         )
         return self._result_to_search_result(result)
@@ -220,7 +259,11 @@ class MilvusClient(VectorDBBase):
 
         try:
             log.info(
-                f"Querying collection {self.collection_prefix}_{collection_name} with filter: '{filter_string}', limit: {limit}"
+                "Querying collection %s_%s with filter: '%s', limit: %s",
+                self.collection_prefix,
+                collection_name,
+                filter_string,
+                limit,
             )
 
             iterator = self.client.query_iterator(
@@ -242,7 +285,7 @@ class MilvusClient(VectorDBBase):
                     break
                 all_results.extend(batch)
 
-            log.debug(f'Total results from query: {len(all_results)}')
+            log.debug('Total results from query: %s', len(all_results))
             return self._result_to_get_result([all_results] if all_results else [[]])
 
         except Exception as e:
@@ -265,7 +308,7 @@ class MilvusClient(VectorDBBase):
         # Insert the items into the collection, if the collection does not exist, it will be created.
         collection_name = collection_name.replace('-', '_')
         if not self.client.has_collection(collection_name=f'{self.collection_prefix}_{collection_name}'):
-            log.info(f'Collection {self.collection_prefix}_{collection_name} does not exist. Creating now.')
+            log.info('Collection %s_%s does not exist. Creating now.', self.collection_prefix, collection_name)
             if not items:
                 log.error(
                     f'Cannot create collection {self.collection_prefix}_{collection_name} without items to determine dimension.'
@@ -273,7 +316,7 @@ class MilvusClient(VectorDBBase):
                 raise ValueError('Cannot create Milvus collection without items to determine vector dimension.')
             self._create_collection(collection_name=collection_name, dimension=len(items[0]['vector']))
 
-        log.info(f'Inserting {len(items)} items into collection {self.collection_prefix}_{collection_name}.')
+        log.info('Inserting %s items into collection %s_%s.', len(items), self.collection_prefix, collection_name)
         data = []
         for item in items:
             text = item['text'] or ''
@@ -301,7 +344,9 @@ class MilvusClient(VectorDBBase):
         # Update the items in the collection, if the items are not present, insert them. If the collection does not exist, it will be created.
         collection_name = collection_name.replace('-', '_')
         if not self.client.has_collection(collection_name=f'{self.collection_prefix}_{collection_name}'):
-            log.info(f'Collection {self.collection_prefix}_{collection_name} does not exist for upsert. Creating now.')
+            log.info(
+                'Collection %s_%s does not exist for upsert. Creating now.', self.collection_prefix, collection_name
+            )
             if not items:
                 log.error(
                     f'Cannot create collection {self.collection_prefix}_{collection_name} for upsert without items to determine dimension.'
@@ -311,7 +356,7 @@ class MilvusClient(VectorDBBase):
                 )
             self._create_collection(collection_name=collection_name, dimension=len(items[0]['vector']))
 
-        log.info(f'Upserting {len(items)} items into collection {self.collection_prefix}_{collection_name}.')
+        log.info('Upserting %s items into collection %s_%s.', len(items), self.collection_prefix, collection_name)
         data = []
         for item in items:
             text = item['text'] or ''
@@ -348,15 +393,20 @@ class MilvusClient(VectorDBBase):
             return None
 
         if ids:
-            log.info(f'Deleting items by IDs from {self.collection_prefix}_{collection_name}. IDs: {ids}')
+            log.info('Deleting items by IDs from %s_%s. IDs: %s', self.collection_prefix, collection_name, ids)
             return self.client.delete(
                 collection_name=f'{self.collection_prefix}_{collection_name}',
                 ids=ids,
             )
         elif filter:
-            filter_string = ' && '.join([f'metadata["{key}"] == {json.dumps(value)}' for key, value in filter.items()])
+            filter_string = ' && '.join(
+                [f'metadata["{key}"] == {JSONCodec.dumps(value)}' for key, value in filter.items()]
+            )
             log.info(
-                f'Deleting items by filter from {self.collection_prefix}_{collection_name}. Filter: {filter_string}'
+                'Deleting items by filter from %s_%s. Filter: %s',
+                self.collection_prefix,
+                collection_name,
+                filter_string,
             )
             return self.client.delete(
                 collection_name=f'{self.collection_prefix}_{collection_name}',
@@ -378,7 +428,7 @@ class MilvusClient(VectorDBBase):
                 try:
                     self.client.drop_collection(collection_name=collection_name_full)
                     deleted_collections.append(collection_name_full)
-                    log.info(f'Deleted collection: {collection_name_full}')
+                    log.info('Deleted collection: %s', collection_name_full)
                 except Exception as e:
                     log.error(f'Error deleting collection {collection_name_full}: {e}')
-        log.info(f'Milvus reset complete. Deleted collections: {deleted_collections}')
+        log.info('Milvus reset complete. Deleted collections: %s', deleted_collections)

backend/open_webui/retrieval/vector/dbs/milvus_multitenancy.py

@@ -17,12 +17,14 @@ from open_webui.config import (
     MILVUS_TOKEN,
     MILVUS_URI,
 )
+from open_webui.retrieval.vector.dbs.milvus import _metadata_exprs
 from open_webui.retrieval.vector.main import (
     GetResult,
     SearchResult,
     VectorDBBase,
     VectorItem,
 )
+from open_webui.retrieval.vector.utils import process_metadata
 from pymilvus import DataType
 from pymilvus import MilvusClient as Client
 from pymilvus.exceptions import MilvusException
@@ -146,7 +148,7 @@ class MilvusClient(VectorDBBase):
                 # The index only accelerates resource_id filters; never fail
                 # collection creation over it.
                 log.warning(f'Could not create {RESOURCE_ID_FIELD} index on {mt_collection_name}: {e}')
-        log.info(f'Created shared collection: {mt_collection_name}')
+        log.info('Created shared collection: %s', mt_collection_name)
 
     def _ensure_collection(self, mt_collection_name: str, dimension: int):
         if not self.client.has_collection(mt_collection_name):
@@ -190,7 +192,7 @@ class MilvusClient(VectorDBBase):
                     'id': item['id'],
                     'vector': item['vector'],
                     'text': text,
-                    'metadata': item['metadata'],
+                    'metadata': process_metadata(item['metadata']),
                     RESOURCE_ID_FIELD: resource_id,
                 }
             )
@@ -221,13 +223,14 @@ class MilvusClient(VectorDBBase):
 
         self.client.load_collection(mt_collection)
 
+        expr = [f"{RESOURCE_ID_FIELD} == '{resource_id}'", *_metadata_exprs(filter)]
         results = self.client.search(
             collection_name=mt_collection,
             data=vectors,
             anns_field='vector',
             search_params={'metric_type': MILVUS_METRIC_TYPE, 'params': {}},
             limit=limit,
-            filter=f"{RESOURCE_ID_FIELD} == '{resource_id}'",
+            filter=' and '.join(expr),
             output_fields=['id', 'text', 'metadata'],
         )
 

backend/open_webui/retrieval/vector/dbs/opengauss.py

@@ -2,7 +2,6 @@
 NOTE: This vector database integration is community-supported and maintained on a best-effort basis.
 """
 
-import json
 import logging
 import re
 from typing import Any, Dict, List, Optional
@@ -63,20 +62,18 @@ from open_webui.config import (
     OPENGAUSS_POOL_SIZE,
     OPENGAUSS_POOL_TIMEOUT,
 )
-from open_webui.env import SRC_LOG_LEVELS
 from open_webui.retrieval.vector.main import (
     GetResult,
     SearchResult,
     VectorDBBase,
     VectorItem,
 )
-from open_webui.retrieval.vector.utils import process_metadata
+from open_webui.retrieval.vector.utils import iter_filter_conditions, process_metadata
 
 VECTOR_LENGTH = OPENGAUSS_INITIALIZE_MAX_VECTOR_LENGTH
 Base = declarative_base()
 
 log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS['RAG'])
 
 
 class DocumentChunk(Base):
@@ -89,6 +86,12 @@ class DocumentChunk(Base):
     vmetadata = Column(MutableDict.as_mutable(JSONB), nullable=True)
 
 
+def _metadata_clause(key: str, op: str, value: Any):
+    if op == '$in':
+        return DocumentChunk.vmetadata[key].astext.in_([str(v) for v in value])
+    return DocumentChunk.vmetadata[key].astext == str(value)
+
+
 class OpenGaussClient(VectorDBBase):
     def __init__(self) -> None:
         if not OPENGAUSS_DB_URL:
@@ -182,7 +185,7 @@ class OpenGaussClient(VectorDBBase):
                 new_items.append(new_chunk)
             self.session.bulk_save_objects(new_items)
             self.session.commit()
-            log.info(f"Inserting {len(new_items)} items into collection '{collection_name}'.")
+            log.info("Inserting %s items into collection '%s'.", len(new_items), collection_name)
         except Exception as e:
             self.session.rollback()
             log.exception(f'Failed to insert data: {e}')
@@ -208,7 +211,7 @@ class OpenGaussClient(VectorDBBase):
                     )
                     self.session.add(new_chunk)
             self.session.commit()
-            log.info(f"Inserting/updating {len(items)} items in collection '{collection_name}'.")
+            log.info("Inserting/updating %s items in collection '%s'.", len(items), collection_name)
         except Exception as e:
             self.session.rollback()
             log.exception(f'Failed to insert or update data.: {e}')
@@ -245,10 +248,15 @@ class OpenGaussClient(VectorDBBase):
                 DocumentChunk.vmetadata,
                 (DocumentChunk.vector.cosine_distance(query_vectors.c.q_vector)).label('distance'),
             ]
+            where_clauses = [DocumentChunk.collection_name == collection_name]
+            if filter:
+                where_clauses.extend(
+                    _metadata_clause(key, op, value) for key, op, value in iter_filter_conditions(filter)
+                )
 
             subq = (
                 select(*result_fields)
-                .where(DocumentChunk.collection_name == collection_name)
+                .where(*where_clauses)
                 .order_by(DocumentChunk.vector.cosine_distance(query_vectors.c.q_vector))
             )
             if limit is not None:
@@ -303,6 +311,7 @@ class OpenGaussClient(VectorDBBase):
             results = query.all()
 
             if not results:
+                self.session.rollback()
                 return None
 
             ids = [[result.id for result in results]]
@@ -325,6 +334,7 @@ class OpenGaussClient(VectorDBBase):
             results = query.all()
 
             if not results:
+                self.session.rollback()
                 return None
 
             ids = [[result.id for result in results]]
@@ -353,7 +363,7 @@ class OpenGaussClient(VectorDBBase):
                     query = query.filter(DocumentChunk.vmetadata[key].astext == str(value))
             deleted = query.delete(synchronize_session=False)
             self.session.commit()
-            log.info(f"Deleted {deleted} items from collection '{collection_name}'")
+            log.info("Deleted %s items from collection '%s'", deleted, collection_name)
         except Exception as e:
             self.session.rollback()
             log.exception(f'Failed to delete data: {e}')
@@ -363,7 +373,7 @@ class OpenGaussClient(VectorDBBase):
         try:
             deleted = self.session.query(DocumentChunk).delete()
             self.session.commit()
-            log.info(f'Reset completed. Deleted {deleted} items')
+            log.info('Reset completed. Deleted %s items', deleted)
         except Exception as e:
             self.session.rollback()
             log.exception(f'Reset failed: {e}')
@@ -387,4 +397,4 @@ class OpenGaussClient(VectorDBBase):
 
     def delete_collection(self, collection_name: str) -> None:
         self.delete(collection_name)
-        log.info(f"Collection '{collection_name}' has been deleted")
+        log.info("Collection '%s' has been deleted", collection_name)

backend/open_webui/retrieval/vector/dbs/opensearch.py

@@ -2,7 +2,7 @@
 NOTE: This vector database integration is community-supported and maintained on a best-effort basis.
 """
 
-from typing import Optional
+from typing import Any, Optional
 
 from open_webui.config import (
     OPENSEARCH_CERT_VERIFY,
@@ -17,11 +17,17 @@ from open_webui.retrieval.vector.main import (
     VectorDBBase,
     VectorItem,
 )
-from open_webui.retrieval.vector.utils import process_metadata
+from open_webui.retrieval.vector.utils import iter_filter_conditions, process_metadata
 from opensearchpy import OpenSearch
 from opensearchpy.helpers import bulk
 
 
+def _metadata_filter(key: str, op: str, value: Any) -> dict:
+    if op == '$in':
+        return {'terms': {f'metadata.{key}.keyword': value}}
+    return {'term': {f'metadata.{key}.keyword': value}}
+
+
 class OpenSearchClient(VectorDBBase):
     def __init__(self):
         self.index_prefix = 'open_webui'
@@ -121,6 +127,8 @@ class OpenSearchClient(VectorDBBase):
         filter: Optional[dict] = None,
         limit: int = 10,
     ) -> Optional[SearchResult]:
+        filter_clauses = [_metadata_filter(key, op, value) for key, op, value in iter_filter_conditions(filter)]
+
         try:
             if not self.has_collection(collection_name):
                 return None
@@ -130,7 +138,7 @@ class OpenSearchClient(VectorDBBase):
                 '_source': ['text', 'metadata'],
                 'query': {
                     'script_score': {
-                        'query': {'match_all': {}},
+                        'query': {'bool': {'filter': filter_clauses}} if filter_clauses else {'match_all': {}},
                         'script': {
                             'source': '(cosineSimilarity(params.query_value, doc[params.field]) + 1.0) / 2.0',
                             'params': {

backend/open_webui/retrieval/vector/dbs/oracle23ai.py

@@ -32,6 +32,7 @@ import array
 import json
 import logging
 import os
+import re
 import threading
 import time
 from decimal import Decimal
@@ -56,8 +57,29 @@ from open_webui.retrieval.vector.main import (
     VectorDBBase,
     VectorItem,
 )
+from open_webui.retrieval.vector.utils import iter_filter_conditions, process_metadata
+from open_webui.utils.json_codec import JSONCodec
 
 log = logging.getLogger(__name__)
+_SAFE_METADATA_KEY_RE = re.compile(r'^[A-Za-z_][A-Za-z0-9_]{0,63}$')
+
+
+def _metadata_where(filter: Optional[dict]) -> tuple[str, dict[str, Any]]:
+    clause = ''
+    params: dict[str, Any] = {}
+    for i, (key, op, value) in enumerate(iter_filter_conditions(filter)):
+        if not isinstance(key, str) or not _SAFE_METADATA_KEY_RE.fullmatch(key):
+            raise ValueError(f'Invalid Oracle metadata filter key: {key!r}')
+        json_value = f"JSON_VALUE(dc.vmetadata, '$.{key}' RETURNING VARCHAR2(4096))"
+        if op == '$in':
+            names = [f'value_{i}_{j}' for j, _ in enumerate(value)]
+            clause += f' AND {json_value} IN ({", ".join(f":{name}" for name in names)})' if names else ' AND 1 = 0'
+            params.update({name: str(item) for name, item in zip(names, value)})
+        else:
+            name = f'value_{i}'
+            clause += f' AND {json_value} = :{name}'
+            params[name] = str(value)
+    return clause, params
 
 
 class Oracle23aiClient(VectorDBBase):
@@ -93,10 +115,10 @@ class Oracle23aiClient(VectorDBBase):
                 self._create_dbcs_pool()
 
             dsn = ORACLE_DB_DSN
-            log.info(f'Creating Connection Pool [{ORACLE_DB_USER}:**@{dsn}]')
+            log.info('Creating Connection Pool [%s:**@%s]', ORACLE_DB_USER, dsn)
 
             with self.get_connection() as connection:
-                log.info(f'Connection version: {connection.version}')
+                log.info('Connection version: %s', connection.version)
                 self._initialize_database(connection)
 
             log.info('Oracle Vector Search initialization complete.')
@@ -158,7 +180,7 @@ class Oracle23aiClient(VectorDBBase):
 
                 if attempt < max_retries - 1:
                     wait_time = 2**attempt
-                    log.info(f'Retrying in {wait_time} seconds...')
+                    log.info('Retrying in %s seconds...', wait_time)
                     time.sleep(wait_time)
                 else:
                     raise
@@ -183,7 +205,7 @@ class Oracle23aiClient(VectorDBBase):
 
         thread = threading.Thread(target=_monitor, daemon=True)
         thread.start()
-        log.info(f'Started DB health monitor every {interval_seconds} seconds.')
+        log.info('Started DB health monitor every %s seconds.', interval_seconds)
 
     def _reconnect_pool(self):
         """
@@ -378,7 +400,7 @@ class Oracle23aiClient(VectorDBBase):
         Returns:
             str: JSON representation of metadata
         """
-        return json.dumps(metadata, default=self._decimal_handler) if metadata else '{}'
+        return json.dumps(process_metadata(metadata), default=self._decimal_handler) if metadata else '{}'
 
     def _json_to_metadata(self, json_str: str) -> Dict:
         """
@@ -390,7 +412,7 @@ class Oracle23aiClient(VectorDBBase):
         Returns:
             Dict: Metadata dictionary
         """
-        return json.loads(json_str) if json_str else {}
+        return JSONCodec.loads(json_str) if json_str else {}
 
     def insert(self, collection_name: str, items: List[VectorItem]) -> None:
         """
@@ -411,7 +433,7 @@ class Oracle23aiClient(VectorDBBase):
             ... ]
             >>> client.insert("my_collection", items)
         """
-        log.info(f"Inserting {len(items)} items into collection '{collection_name}'.")
+        log.info("Inserting %s items into collection '%s'.", len(items), collection_name)
 
         with self.get_connection() as connection:
             try:
@@ -436,7 +458,7 @@ class Oracle23aiClient(VectorDBBase):
                         )
 
                 connection.commit()
-                log.info(f"Successfully inserted {len(items)} items into collection '{collection_name}'.")
+                log.info("Successfully inserted %s items into collection '%s'.", len(items), collection_name)
 
             except Exception as e:
                 connection.rollback()
@@ -465,7 +487,7 @@ class Oracle23aiClient(VectorDBBase):
             ... ]
             >>> client.upsert("my_collection", items)
         """
-        log.info(f"Upserting {len(items)} items into collection '{collection_name}'.")
+        log.info("Upserting %s items into collection '%s'.", len(items), collection_name)
 
         with self.get_connection() as connection:
             try:
@@ -504,7 +526,7 @@ class Oracle23aiClient(VectorDBBase):
                         )
 
                 connection.commit()
-                log.info(f"Successfully upserted {len(items)} items into collection '{collection_name}'.")
+                log.info("Successfully upserted %s items into collection '%s'.", len(items), collection_name)
 
             except Exception as e:
                 connection.rollback()
@@ -540,7 +562,7 @@ class Oracle23aiClient(VectorDBBase):
             ...     for i, (id, dist) in enumerate(zip(results.ids[0], results.distances[0])):
             ...         log.info(f"Match {i+1}: id={id}, distance={dist}")
         """
-        log.info(f"Searching items from collection '{collection_name}' with limit {limit}.")
+        log.info("Searching items from collection '%s' with limit %s.", collection_name, limit)
 
         try:
             if not vectors:
@@ -548,6 +570,7 @@ class Oracle23aiClient(VectorDBBase):
                 return None
 
             num_queries = len(vectors)
+            filter_clause, filter_params = _metadata_where(filter)
 
             ids = [[] for _ in range(num_queries)]
             distances = [[] for _ in range(num_queries)]
@@ -560,12 +583,12 @@ class Oracle23aiClient(VectorDBBase):
                         vector_blob = self._vector_to_blob(vector)
 
                         cursor.execute(
-                            """
+                            f"""
-                            SELECT dc.id, dc.text, 
+                            SELECT dc.id, dc.text,
                                 JSON_SERIALIZE(dc.vmetadata RETURNING VARCHAR2(4096)) as vmetadata,
                                 VECTOR_DISTANCE(dc.vector, :query_vector, COSINE) as distance
                             FROM document_chunk dc
-                            WHERE dc.collection_name = :collection_name
+                            WHERE dc.collection_name = :collection_name{filter_clause}
                             ORDER BY VECTOR_DISTANCE(dc.vector, :query_vector, COSINE)
                             FETCH APPROX FIRST :limit ROWS ONLY
                         """,
@@ -573,6 +596,7 @@ class Oracle23aiClient(VectorDBBase):
                                 'query_vector': vector_blob,
                                 'collection_name': collection_name,
                                 'limit': limit,
+                                **filter_params,
                             },
                         )
 
@@ -586,7 +610,7 @@ class Oracle23aiClient(VectorDBBase):
                             metadatas[qid].append(self._json_to_metadata(metadata_str))
                             distances[qid].append(float(row[3]))
 
-            log.info(f'Search completed. Found {sum(len(ids[i]) for i in range(num_queries))} total results.')
+            log.info('Search completed. Found %s total results.', sum(len(ids[i]) for i in range(num_queries)))
 
             return SearchResult(ids=ids, distances=distances, documents=documents, metadatas=metadatas)
 
@@ -615,7 +639,7 @@ class Oracle23aiClient(VectorDBBase):
             >>> if results:
             ...     print(f"Found {len(results.ids[0])} matching documents")
         """
-        log.info(f"Querying items from collection '{collection_name}' with filters.")
+        log.info("Querying items from collection '%s' with filters.", collection_name)
 
         try:
             limit = limit or 100
@@ -655,7 +679,7 @@ class Oracle23aiClient(VectorDBBase):
                 ]
             ]
 
-            log.info(f'Query completed. Found {len(results)} results.')
+            log.info('Query completed. Found %s results.', len(results))
 
             return GetResult(ids=ids, documents=documents, metadatas=metadatas)
 
@@ -746,7 +770,7 @@ class Oracle23aiClient(VectorDBBase):
             >>> # Or delete by metadata filter
             >>> client.delete("my_collection", filter={"source": "deprecated_source"})
         """
-        log.info(f"Deleting items from collection '{collection_name}'.")
+        log.info("Deleting items from collection '%s'.", collection_name)
 
         try:
             query = 'DELETE FROM document_chunk WHERE collection_name = :collection_name'
@@ -771,7 +795,7 @@ class Oracle23aiClient(VectorDBBase):
                     deleted = cursor.rowcount
                 connection.commit()
 
-            log.info(f"Deleted {deleted} items from collection '{collection_name}'.")
+            log.info("Deleted %s items from collection '%s'.", deleted, collection_name)
 
         except Exception as e:
             log.exception(f'Error during delete: {e}')
@@ -799,7 +823,7 @@ class Oracle23aiClient(VectorDBBase):
                     deleted = cursor.rowcount
                 connection.commit()
 
-            log.info(f"Reset complete. Deleted {deleted} items from 'document_chunk' table.")
+            log.info("Reset complete. Deleted %s items from 'document_chunk' table.", deleted)
 
         except Exception as e:
             log.exception(f'Error during reset: {e}')
@@ -874,7 +898,7 @@ class Oracle23aiClient(VectorDBBase):
             >>> client = Oracle23aiClient()
             >>> client.delete_collection("obsolete_collection")
         """
-        log.info(f"Deleting collection '{collection_name}'.")
+        log.info("Deleting collection '%s'.", collection_name)
 
         try:
             with self.get_connection() as connection:
@@ -890,7 +914,7 @@ class Oracle23aiClient(VectorDBBase):
                     deleted = cursor.rowcount
                 connection.commit()
 
-            log.info(f"Collection '{collection_name}' deleted. Removed {deleted} items.")
+            log.info("Collection '%s' deleted. Removed %s items.", collection_name, deleted)
 
         except Exception as e:
             log.exception(f"Error deleting collection '{collection_name}': {e}")

backend/open_webui/retrieval/vector/dbs/pgvector.py

@@ -1,4 +1,3 @@
-import json
 import logging
 from typing import Any, Dict, List, Optional, Tuple
 
@@ -9,6 +8,7 @@ from open_webui.config import (
     PGVECTOR_HNSW_M,
     PGVECTOR_INDEX_METHOD,
     PGVECTOR_INITIALIZE_MAX_VECTOR_LENGTH,
+    PGVECTOR_ITERATIVE_SCAN,
     PGVECTOR_IVFFLAT_LISTS,
     PGVECTOR_PGCRYPTO,
     PGVECTOR_PGCRYPTO_KEY,
@@ -18,6 +18,7 @@ from open_webui.config import (
     PGVECTOR_POOL_TIMEOUT,
     PGVECTOR_USE_HALFVEC,
 )
+from open_webui.internal.db import ScopedSession, enable_iam_token_auth
 from open_webui.retrieval.vector.main import (
     GetResult,
     SearchResult,
@@ -25,6 +26,7 @@ from open_webui.retrieval.vector.main import (
     VectorItem,
 )
 from open_webui.retrieval.vector.utils import merge_hybrid_search_results, process_metadata
+from open_webui.utils.json_codec import JSONCodec
 from open_webui.utils.misc import sanitize_text_for_db
 from pgvector.sqlalchemy import HALFVEC, Vector
 from sqlalchemy import (
@@ -87,8 +89,6 @@ class PgvectorClient(VectorDBBase):
     def __init__(self) -> None:
         # if no pgvector uri, use the existing database connection
         if not PGVECTOR_DB_URL:
-            from open_webui.internal.db import ScopedSession
-
             self.session = ScopedSession
         else:
             if isinstance(PGVECTOR_POOL_SIZE, int):
@@ -107,6 +107,7 @@ class PgvectorClient(VectorDBBase):
             else:
                 engine = create_engine(PGVECTOR_DB_URL, pool_pre_ping=True)
 
+            enable_iam_token_auth(engine)
             SessionLocal = sessionmaker(autocommit=False, autoflush=False, bind=engine, expire_on_commit=False)
             self.session = scoped_session(SessionLocal)
 
@@ -154,6 +155,7 @@ class PgvectorClient(VectorDBBase):
             index_method, index_options = self._vector_index_configuration()
             self._ensure_vector_index(index_method, index_options)
             self._ensure_text_search_index()
+            self.iterative_scan_sql = self._iterative_scan_setting(index_method)
 
             self.session.execute(
                 text(
@@ -223,6 +225,9 @@ class PgvectorClient(VectorDBBase):
             )
 
         if not existing_index_def:
+            if index_method == 'ivfflat' and not self._has_enough_ivfflat_training_rows():
+                return
+
             index_sql = (
                 f'CREATE INDEX IF NOT EXISTS {index_name} '
                 f'ON document_chunk USING {index_method} (vector {VECTOR_OPCLASS})'
@@ -237,6 +242,38 @@ class PgvectorClient(VectorDBBase):
                 f' {index_options}' if index_options else '',
             )
 
+    def _has_enough_ivfflat_training_rows(self) -> bool:
+        # ivfflat samples 50 rows per list to place its centroids, so recall stays poor until the table holds that many
+        min_training_rows = 50 * PGVECTOR_IVFFLAT_LISTS
+        row_count = self.session.execute(
+            text('SELECT count(*) FROM (SELECT 1 FROM document_chunk LIMIT :min_training_rows) AS sample'),
+            {'min_training_rows': min_training_rows},
+        ).scalar()
+
+        if row_count < min_training_rows:
+            log.info(
+                "Deferring vector index 'idx_document_chunk_vector' until document_chunk holds %s rows to cluster on, "
+                'it has %s. Searches run as an exact scan until then.',
+                min_training_rows,
+                row_count,
+            )
+            return False
+        return True
+
+    def _iterative_scan_setting(self, index_method: str) -> Optional[str]:
+        if PGVECTOR_ITERATIVE_SCAN == 'off':
+            return None
+
+        version = self.session.execute(text("SELECT extversion FROM pg_extension WHERE extname = 'vector'")).scalar()
+        version_parts = [int(part) for part in (version or '').split('.') if part.isdigit()]
+        if version_parts[:2] < [0, 8]:
+            log.info('Iterative scan needs pgvector 0.8 or newer, the server has %s.', version or 'none')
+            return None
+
+        # ivfflat only accepts relaxed_order
+        mode = 'relaxed_order' if index_method == 'ivfflat' else PGVECTOR_ITERATIVE_SCAN
+        return f'SET LOCAL {index_method}.iterative_scan = {mode}'
+
     def _ensure_text_search_index(self) -> None:
         if PGVECTOR_PGCRYPTO:
             return
@@ -303,7 +340,7 @@ class PgvectorClient(VectorDBBase):
                     # Use raw SQL for BYTEA/pgcrypto
                     # Ensure metadata is converted to its JSON text representation
                     # Sanitize to strip null bytes / surrogates that PostgreSQL cannot store
-                    json_metadata = sanitize_text_for_db(json.dumps(item['metadata']))
+                    json_metadata = sanitize_text_for_db(JSONCodec.dumps(item['metadata']))
                     item_text = sanitize_text_for_db(item['text'])
                     self.session.execute(
                         text("""
@@ -326,7 +363,7 @@ class PgvectorClient(VectorDBBase):
                         },
                     )
                 self.session.commit()
-                log.info(f"Encrypted & inserted {len(items)} into '{collection_name}'")
+                log.info("Encrypted & inserted %s into '%s'", len(items), collection_name)
 
             else:
                 new_items = []
@@ -342,7 +379,7 @@ class PgvectorClient(VectorDBBase):
                     new_items.append(new_chunk)
                 self.session.bulk_save_objects(new_items)
                 self.session.commit()
-                log.info(f"Inserted {len(new_items)} items into collection '{collection_name}'.")
+                log.info("Inserted %s items into collection '%s'.", len(new_items), collection_name)
         except Exception as e:
             self.session.rollback()
             log.exception(f'Error during insert: {e}')
@@ -354,7 +391,7 @@ class PgvectorClient(VectorDBBase):
                 for item in items:
                     vector = self.adjust_vector_length(item['vector'])
                     # Sanitize to strip null bytes / surrogates that PostgreSQL cannot store
-                    json_metadata = sanitize_text_for_db(json.dumps(item['metadata']))
+                    json_metadata = sanitize_text_for_db(JSONCodec.dumps(item['metadata']))
                     item_text = sanitize_text_for_db(item['text'])
                     self.session.execute(
                         text("""
@@ -381,7 +418,7 @@ class PgvectorClient(VectorDBBase):
                         },
                     )
                 self.session.commit()
-                log.info(f"Encrypted & upserted {len(items)} into '{collection_name}'")
+                log.info("Encrypted & upserted %s into '%s'", len(items), collection_name)
             else:
                 for item in items:
                     vector = self.adjust_vector_length(item['vector'])
@@ -401,7 +438,7 @@ class PgvectorClient(VectorDBBase):
                         )
                         self.session.add(new_chunk)
                 self.session.commit()
-                log.info(f"Upserted {len(items)} items into collection '{collection_name}'.")
+                log.info("Upserted %s items into collection '%s'.", len(items), collection_name)
         except Exception as e:
             self.session.rollback()
             log.exception(f'Error during upsert: {e}')
@@ -503,6 +540,9 @@ class PgvectorClient(VectorDBBase):
                 .order_by(query_vectors.c.qid, subq.c.distance)
             )
 
+            if self.iterative_scan_sql:
+                self.session.execute(text(self.iterative_scan_sql))
+
             result_proxy = self.session.execute(stmt)
             results = result_proxy.all()
 
@@ -512,6 +552,7 @@ class PgvectorClient(VectorDBBase):
             metadatas = [[] for _ in range(num_queries)]
 
             if not results:
+                self.session.rollback()
                 return SearchResult(
                     ids=ids,
                     distances=distances,
@@ -631,6 +672,7 @@ class PgvectorClient(VectorDBBase):
                 results = query.all()
 
             if not results:
+                self.session.rollback()
                 return None
 
             ids = [[result.id for result in results]]
@@ -670,6 +712,7 @@ class PgvectorClient(VectorDBBase):
                 results = query.all()
 
                 if not results:
+                    self.session.rollback()
                     return None
 
                 ids = [[result.id for result in results]]
@@ -712,7 +755,7 @@ class PgvectorClient(VectorDBBase):
                         query = query.filter(DocumentChunk.vmetadata[key].astext == str(value))
                 deleted = query.delete(synchronize_session=False)
             self.session.commit()
-            log.info(f"Deleted {deleted} items from collection '{collection_name}'.")
+            log.info("Deleted %s items from collection '%s'.", deleted, collection_name)
         except Exception as e:
             self.session.rollback()
             log.exception(f'Error during delete: {e}')
@@ -722,7 +765,7 @@ class PgvectorClient(VectorDBBase):
         try:
             deleted = self.session.query(DocumentChunk).delete()
             self.session.commit()
-            log.info(f"Reset complete. Deleted {deleted} items from 'document_chunk' table.")
+            log.info("Reset complete. Deleted %s items from 'document_chunk' table.", deleted)
         except Exception as e:
             self.session.rollback()
             log.exception(f'Error during reset: {e}')
@@ -746,4 +789,4 @@ class PgvectorClient(VectorDBBase):
 
     def delete_collection(self, collection_name: str) -> None:
         self.delete(collection_name)
-        log.info(f"Collection '{collection_name}' deleted.")
+        log.info("Collection '%s' deleted.", collection_name)

backend/open_webui/retrieval/vector/dbs/pinecone.py

@@ -35,7 +35,7 @@ from open_webui.retrieval.vector.main import (
     VectorDBBase,
     VectorItem,
 )
-from open_webui.retrieval.vector.utils import process_metadata
+from open_webui.retrieval.vector.utils import normalize_filter, process_metadata
 
 NO_LIMIT = 10000  # Reasonable limit to avoid overwhelming the system
 BATCH_SIZE = 100  # Recommended batch size for Pinecone operations
@@ -106,16 +106,16 @@ class PineconeClient(VectorDBBase):
         try:
             # Check if index exists
             if self.index_name not in self.client.list_indexes().names():
-                log.info(f"Creating Pinecone index '{self.index_name}'...")
+                log.info("Creating Pinecone index '%s'...", self.index_name)
                 self.client.create_index(
                     name=self.index_name,
                     dimension=self.dimension,
                     metric=self.metric,
                     spec=ServerlessSpec(cloud=self.cloud, region=self.environment),
                 )
-                log.info(f"Successfully created Pinecone index '{self.index_name}'")
+                log.info("Successfully created Pinecone index '%s'", self.index_name)
             else:
-                log.info(f"Using existing Pinecone index '{self.index_name}'")
+                log.info("Using existing Pinecone index '%s'", self.index_name)
 
             # Connect to the index
             self.index = self.client.Index(
@@ -245,7 +245,7 @@ class PineconeClient(VectorDBBase):
         collection_name_with_prefix = self._get_collection_name_with_prefix(collection_name)
         try:
             self.index.delete(filter={'collection_name': collection_name_with_prefix})
-            log.info(f"Collection '{collection_name_with_prefix}' deleted (all vectors removed).")
+            log.info("Collection '%s' deleted (all vectors removed).", collection_name_with_prefix)
         except Exception as e:
             log.warning(f"Failed to delete collection '{collection_name_with_prefix}': {e}")
             raise
@@ -274,9 +274,9 @@ class PineconeClient(VectorDBBase):
                 log.error(f'Error inserting batch: {e}')
                 raise
         elapsed = time.time() - start_time
-        log.debug(f'Insert of {len(points)} vectors took {elapsed:.2f} seconds')
+        log.debug('Insert of %s vectors took %.2f seconds', len(points), elapsed)
         log.info(
-            f"Successfully inserted {len(points)} vectors in parallel batches into '{collection_name_with_prefix}'"
+            "Successfully inserted %s vectors in parallel batches into '%s'", len(points), collection_name_with_prefix
         )
 
     def upsert(self, collection_name: str, items: List[VectorItem]) -> None:
@@ -303,9 +303,9 @@ class PineconeClient(VectorDBBase):
                 log.error(f'Error upserting batch: {e}')
                 raise
         elapsed = time.time() - start_time
-        log.debug(f'Upsert of {len(points)} vectors took {elapsed:.2f} seconds')
+        log.debug('Upsert of %s vectors took %.2f seconds', len(points), elapsed)
         log.info(
-            f"Successfully upserted {len(points)} vectors in parallel batches into '{collection_name_with_prefix}'"
+            "Successfully upserted %s vectors in parallel batches into '%s'", len(points), collection_name_with_prefix
         )
 
     async def insert_async(self, collection_name: str, items: List[VectorItem]) -> None:
@@ -326,7 +326,9 @@ class PineconeClient(VectorDBBase):
             if isinstance(result, Exception):
                 log.error(f'Error in async insert batch: {result}')
                 raise result
-        log.info(f"Successfully async inserted {len(points)} vectors in batches into '{collection_name_with_prefix}'")
+        log.info(
+            "Successfully async inserted %s vectors in batches into '%s'", len(points), collection_name_with_prefix
+        )
 
     async def upsert_async(self, collection_name: str, items: List[VectorItem]) -> None:
         """Async version of upsert using asyncio and run_in_executor for improved performance."""
@@ -346,7 +348,9 @@ class PineconeClient(VectorDBBase):
             if isinstance(result, Exception):
                 log.error(f'Error in async upsert batch: {result}')
                 raise result
-        log.info(f"Successfully async upserted {len(points)} vectors in batches into '{collection_name_with_prefix}'")
+        log.info(
+            "Successfully async upserted %s vectors in batches into '%s'", len(points), collection_name_with_prefix
+        )
 
     def search(
         self,
@@ -368,13 +372,15 @@ class PineconeClient(VectorDBBase):
         try:
             # Search using the first vector (assuming this is the intended behavior)
             query_vector = vectors[0]
+            pinecone_filter = normalize_filter(filter)
+            pinecone_filter['collection_name'] = collection_name_with_prefix
 
             # Perform the search
             query_response = self.index.query(
                 vector=query_vector,
                 top_k=limit,
                 include_metadata=True,
-                filter={'collection_name': collection_name_with_prefix},
+                filter=pinecone_filter,
             )
 
             matches = getattr(query_response, 'matches', []) or []
@@ -474,8 +480,10 @@ class PineconeClient(VectorDBBase):
                     # Note: When deleting by ID, we can't filter by collection_name
                     # This is a limitation of Pinecone - be careful with ID uniqueness
                     self.index.delete(ids=batch_ids)
-                    log.debug(f"Deleted batch of {len(batch_ids)} vectors by ID from '{collection_name_with_prefix}'")
+                    log.debug(
-                log.info(f"Successfully deleted {len(ids)} vectors by ID from '{collection_name_with_prefix}'")
+                        "Deleted batch of %s vectors by ID from '%s'", len(batch_ids), collection_name_with_prefix
+                    )
+                log.info("Successfully deleted %s vectors by ID from '%s'", len(ids), collection_name_with_prefix)
 
             elif filter:
                 # Combine user filter with collection_name
@@ -484,7 +492,7 @@ class PineconeClient(VectorDBBase):
                     pinecone_filter.update(filter)
                 # Delete by metadata filter
                 self.index.delete(filter=pinecone_filter)
-                log.info(f"Successfully deleted vectors by filter from '{collection_name_with_prefix}'")
+                log.info("Successfully deleted vectors by filter from '%s'", collection_name_with_prefix)
 
             else:
                 log.warning('No ids or filter provided for delete operation')

backend/open_webui/retrieval/vector/dbs/qdrant.py

@@ -3,7 +3,7 @@ NOTE: This vector database integration is community-supported and maintained on
 """
 
 import logging
-from typing import Optional
+from typing import Any, Optional
 from urllib.parse import urlparse
 
 from open_webui.config import (
@@ -22,6 +22,7 @@ from open_webui.retrieval.vector.main import (
     VectorDBBase,
     VectorItem,
 )
+from open_webui.retrieval.vector.utils import iter_filter_conditions, process_metadata
 from qdrant_client import QdrantClient as Qclient
 from qdrant_client.http.models import PointStruct
 from qdrant_client.models import models
@@ -31,6 +32,11 @@ NO_LIMIT = 999999999
 log = logging.getLogger(__name__)
 
 
+def _metadata_filter(key: str, op: str, value: Any) -> models.FieldCondition:
+    match = models.MatchAny(any=value) if op == '$in' else models.MatchValue(value=value)
+    return models.FieldCondition(key=f'metadata.{key}', match=match)
+
+
 class QdrantClient(VectorDBBase):
     def __init__(self):
         self.collection_prefix = QDRANT_COLLECTION_PREFIX
@@ -119,7 +125,7 @@ class QdrantClient(VectorDBBase):
                 on_disk=self.QDRANT_ON_DISK,
             ),
         )
-        log.info(f'collection {collection_name_with_prefix} successfully created!')
+        log.info('collection %s successfully created!', collection_name_with_prefix)
 
     def _create_collection_if_not_exists(self, collection_name, dimension):
         if not self.has_collection(collection_name=collection_name):
@@ -130,7 +136,7 @@ class QdrantClient(VectorDBBase):
             PointStruct(
                 id=item['id'],
                 vector=item['vector'],
-                payload={'text': item['text'], 'metadata': item['metadata']},
+                payload={'text': item['text'], 'metadata': process_metadata(item['metadata'])},
             )
             for item in items
         ]
@@ -152,10 +158,13 @@ class QdrantClient(VectorDBBase):
         if limit is None:
             limit = NO_LIMIT  # otherwise qdrant would set limit to 10!
 
+        conditions = [_metadata_filter(key, op, value) for key, op, value in iter_filter_conditions(filter)]
+        query_filter = models.Filter(must=conditions) if conditions else None
         query_response = self.client.query_points(
             collection_name=f'{self.collection_prefix}_{collection_name}',
             query=vectors[0],
             limit=limit,
+            query_filter=query_filter,
         )
         get_result = self._result_to_get_result(query_response.points)
         return SearchResult(

backend/open_webui/retrieval/vector/dbs/qdrant_multitenancy.py

@@ -23,6 +23,7 @@ from open_webui.retrieval.vector.main import (
     VectorDBBase,
     VectorItem,
 )
+from open_webui.retrieval.vector.utils import iter_filter_conditions, process_metadata
 from qdrant_client import QdrantClient as Qclient
 from qdrant_client.http.exceptions import UnexpectedResponse
 from qdrant_client.http.models import PointStruct
@@ -39,8 +40,9 @@ def _tenant_filter(tenant_id: str) -> models.FieldCondition:
     return models.FieldCondition(key=TENANT_ID_FIELD, match=models.MatchValue(value=tenant_id))
 
 
-def _metadata_filter(key: str, value: Any) -> models.FieldCondition:
+def _metadata_filter(key: str, op: str, value: Any) -> models.FieldCondition:
-    return models.FieldCondition(key=f'metadata.{key}', match=models.MatchValue(value=value))
+    match = models.MatchAny(any=value) if op == '$in' else models.MatchValue(value=value)
+    return models.FieldCondition(key=f'metadata.{key}', match=match)
 
 
 class QdrantClient(VectorDBBase):
@@ -148,7 +150,7 @@ class QdrantClient(VectorDBBase):
                 m=0,
             ),
         )
-        log.info(f'Multi-tenant collection {mt_collection_name} created with dimension {dimension}!')
+        log.info('Multi-tenant collection %s created with dimension %s!', mt_collection_name, dimension)
 
         self.client.create_payload_index(
             collection_name=mt_collection_name,
@@ -180,7 +182,7 @@ class QdrantClient(VectorDBBase):
                 vector=item['vector'],
                 payload={
                     'text': item['text'],
-                    'metadata': item['metadata'],
+                    'metadata': process_metadata(item['metadata']),
                     TENANT_ID_FIELD: tenant_id,
                 },
             )
@@ -224,7 +226,7 @@ class QdrantClient(VectorDBBase):
 
         mt_collection, tenant_id = self._get_collection_and_tenant_id(collection_name)
         if not self.client.collection_exists(collection_name=mt_collection):
-            log.debug(f"Collection {mt_collection} doesn't exist, nothing to delete")
+            log.debug("Collection %s doesn't exist, nothing to delete", mt_collection)
             return None
 
         must_conditions = [_tenant_filter(tenant_id)]
@@ -234,7 +236,7 @@ class QdrantClient(VectorDBBase):
             # whose payload omits an id (e.g. memories), leaving orphaned vectors.
             must_conditions.append(models.HasIdCondition(has_id=ids))
         elif filter:
-            must_conditions += [_metadata_filter(k, v) for k, v in filter.items()]
+            must_conditions += [_metadata_filter(k, '$eq', v) for k, v in filter.items()]
 
         return self.client.delete(
             collection_name=mt_collection,
@@ -255,15 +257,17 @@ class QdrantClient(VectorDBBase):
             return None
         mt_collection, tenant_id = self._get_collection_and_tenant_id(collection_name)
         if not self.client.collection_exists(collection_name=mt_collection):
-            log.debug(f"Collection {mt_collection} doesn't exist, search returns None")
+            log.debug("Collection %s doesn't exist, search returns None", mt_collection)
             return None
 
-        tenant_filter = _tenant_filter(tenant_id)
+        conditions = [_tenant_filter(tenant_id)]
+        if filter:
+            conditions.extend(_metadata_filter(key, op, value) for key, op, value in iter_filter_conditions(filter))
         query_response = self.client.query_points(
             collection_name=mt_collection,
             query=vectors[0],
             limit=limit,
-            query_filter=models.Filter(must=[tenant_filter]),
+            query_filter=models.Filter(must=conditions),
         )
         get_result = self._result_to_get_result(query_response.points)
         return SearchResult(
@@ -281,12 +285,12 @@ class QdrantClient(VectorDBBase):
             return None
         mt_collection, tenant_id = self._get_collection_and_tenant_id(collection_name)
         if not self.client.collection_exists(collection_name=mt_collection):
-            log.debug(f"Collection {mt_collection} doesn't exist, query returns None")
+            log.debug("Collection %s doesn't exist, query returns None", mt_collection)
             return None
         if limit is None:
             limit = NO_LIMIT
         tenant_filter = _tenant_filter(tenant_id)
-        field_conditions = [_metadata_filter(k, v) for k, v in filter.items()]
+        field_conditions = [_metadata_filter(k, '$eq', v) for k, v in filter.items()]
         combined_filter = models.Filter(must=[tenant_filter, *field_conditions])
         points = self.client.scroll(
             collection_name=mt_collection,
@@ -303,7 +307,7 @@ class QdrantClient(VectorDBBase):
             return None
         mt_collection, tenant_id = self._get_collection_and_tenant_id(collection_name)
         if not self.client.collection_exists(collection_name=mt_collection):
-            log.debug(f"Collection {mt_collection} doesn't exist, get returns None")
+            log.debug("Collection %s doesn't exist, get returns None", mt_collection)
             return None
         tenant_filter = _tenant_filter(tenant_id)
         points = self.client.scroll(
@@ -350,7 +354,7 @@ class QdrantClient(VectorDBBase):
             return None
         mt_collection, tenant_id = self._get_collection_and_tenant_id(collection_name)
         if not self.client.collection_exists(collection_name=mt_collection):
-            log.debug(f"Collection {mt_collection} doesn't exist, nothing to delete")
+            log.debug("Collection %s doesn't exist, nothing to delete", mt_collection)
             return None
         self.client.delete(
             collection_name=mt_collection,

backend/open_webui/retrieval/vector/dbs/s3vector.py

@@ -13,7 +13,7 @@ from open_webui.retrieval.vector.main import (
     VectorDBBase,
     VectorItem,
 )
-from open_webui.retrieval.vector.utils import process_metadata
+from open_webui.retrieval.vector.utils import metadata_matches_filter, normalize_filter, process_metadata
 
 log = logging.getLogger(__name__)
 
@@ -36,7 +36,7 @@ class S3VectorClient(VectorDBBase):
         if self.bucket_name and self.region:
             try:
                 self.client = boto3.client('s3vectors', region_name=self.region)
-                log.info(f"S3Vector client initialized for bucket '{self.bucket_name}' in region '{self.region}'")
+                log.info("S3Vector client initialized for bucket '%s' in region '%s'", self.bucket_name, self.region)
             except Exception as e:
                 log.error(f'Failed to initialize S3Vector client: {e}')
                 self.client = None
@@ -54,7 +54,7 @@ class S3VectorClient(VectorDBBase):
         Create a new index in the S3 vector bucket for the given collection if it does not exist.
         """
         if self.has_collection(index_name):
-            log.debug(f"Index '{index_name}' already exists, skipping creation")
+            log.debug("Index '%s' already exists, skipping creation", index_name)
             return
 
         try:
@@ -70,7 +70,9 @@ class S3VectorClient(VectorDBBase):
                     ]
                 },
             )
-            log.info(f'Created S3 index: {index_name} (dim={dimension}, type={data_type}, metric={distance_metric})')
+            log.info(
+                'Created S3 index: %s (dim=%s, type=%s, metric=%s)', index_name, dimension, data_type, distance_metric
+            )
         except Exception as e:
             log.error(f"Error creating S3 index '{index_name}': {e}")
             raise
@@ -137,9 +139,9 @@ class S3VectorClient(VectorDBBase):
             return
 
         try:
-            log.info(f"Deleting collection '{collection_name}'")
+            log.info("Deleting collection '%s'", collection_name)
             self.client.delete_index(vectorBucketName=self.bucket_name, indexName=collection_name)
-            log.info(f"Successfully deleted collection '{collection_name}'")
+            log.info("Successfully deleted collection '%s'", collection_name)
         except Exception as e:
             log.error(f"Error deleting collection '{collection_name}': {e}")
             raise
@@ -156,7 +158,7 @@ class S3VectorClient(VectorDBBase):
 
         try:
             if not self.has_collection(collection_name):
-                log.info(f"Index '{collection_name}' does not exist. Creating index.")
+                log.info("Index '%s' does not exist. Creating index.", collection_name)
                 self._create_index(
                     index_name=collection_name,
                     dimension=dimension,
@@ -202,9 +204,11 @@ class S3VectorClient(VectorDBBase):
                     indexName=collection_name,
                     vectors=batch,
                 )
-                log.info(f"Inserted batch {i // batch_size + 1}: {len(batch)} vectors into index '{collection_name}'.")
+                log.info(
+                    "Inserted batch %s: %s vectors into index '%s'.", i // batch_size + 1, len(batch), collection_name
+                )
 
-            log.info(f"Completed insertion of {len(vectors)} vectors into index '{collection_name}'.")
+            log.info("Completed insertion of %s vectors into index '%s'.", len(vectors), collection_name)
         except Exception as e:
             log.error(f'Error inserting vectors: {e}')
             raise
@@ -218,11 +222,11 @@ class S3VectorClient(VectorDBBase):
             return
 
         dimension = len(items[0]['vector'])
-        log.info(f'Upsert dimension: {dimension}')
+        log.info('Upsert dimension: %s', dimension)
 
         try:
             if not self.has_collection(collection_name):
-                log.info(f"Index '{collection_name}' does not exist. Creating index for upsert.")
+                log.info("Index '%s' does not exist. Creating index for upsert.", collection_name)
                 self._create_index(
                     index_name=collection_name,
                     dimension=dimension,
@@ -264,10 +268,14 @@ class S3VectorClient(VectorDBBase):
                 batch = vectors[i : i + batch_size]
                 if i == 0:  # Log sample info for first batch only
                     log.info(
-                        f'Upserting batch 1: {len(batch)} vectors. First vector sample: key={batch[0]["key"]}, data_type={type(batch[0]["data"]["float32"])}, data_len={len(batch[0]["data"]["float32"])}'
+                        'Upserting batch 1: %s vectors. First vector sample: key=%s, data_type=%s, data_len=%s',
+                        len(batch),
+                        batch[0]['key'],
+                        type(batch[0]['data']['float32']),
+                        len(batch[0]['data']['float32']),
                     )
                 else:
-                    log.info(f'Upserting batch {i // batch_size + 1}: {len(batch)} vectors.')
+                    log.info('Upserting batch %s: %s vectors.', i // batch_size + 1, len(batch))
 
                 self.client.put_vectors(
                     vectorBucketName=self.bucket_name,
@@ -275,7 +283,7 @@ class S3VectorClient(VectorDBBase):
                     vectors=batch,
                 )
 
-            log.info(f"Completed upsert of {len(vectors)} vectors into index '{collection_name}'.")
+            log.info("Completed upsert of %s vectors into index '%s'.", len(vectors), collection_name)
         except Exception as e:
             log.error(f'Error upserting vectors: {e}')
             raise
@@ -300,7 +308,8 @@ class S3VectorClient(VectorDBBase):
             return None
 
         try:
-            log.info(f"Searching collection '{collection_name}' with {len(vectors)} query vectors, limit={limit}")
+            log.info("Searching collection '%s' with %s query vectors, limit=%s", collection_name, len(vectors), limit)
+            vector_filter = normalize_filter(filter)
 
             # Initialize result lists
             all_ids = []
@@ -310,20 +319,23 @@ class S3VectorClient(VectorDBBase):
 
             # Process each query vector
             for i, query_vector in enumerate(vectors):
-                log.debug(f'Processing query vector {i + 1}/{len(vectors)}')
+                log.debug('Processing query vector %s/%s', i + 1, len(vectors))
 
                 # Prepare the query vector in S3 Vector format
                 query_vector_dict = {'float32': [float(x) for x in query_vector]}
 
-                # Call S3 Vector query API
+                request_params = {
-                response = self.client.query_vectors(
+                    'vectorBucketName': self.bucket_name,
-                    vectorBucketName=self.bucket_name,
+                    'indexName': collection_name,
-                    indexName=collection_name,
+                    'topK': limit,
-                    topK=limit,
+                    'queryVector': query_vector_dict,
-                    queryVector=query_vector_dict,
+                    'returnMetadata': True,
-                    returnMetadata=True,
+                    'returnDistance': True,
-                    returnDistance=True,
+                }
-                )
+                if vector_filter:
+                    request_params['filter'] = vector_filter
+
+                response = self.client.query_vectors(**request_params)
 
                 # Process results for this query
                 query_ids = []
@@ -338,6 +350,9 @@ class S3VectorClient(VectorDBBase):
                     vector_metadata = vector.get('metadata', {})
                     vector_distance = vector.get('distance', 0.0)
 
+                    if vector_filter and not metadata_matches_filter(vector_metadata, vector_filter):
+                        continue
+
                     # Extract document text from metadata
                     document_text = ''
                     if isinstance(vector_metadata, dict):
@@ -362,7 +377,7 @@ class S3VectorClient(VectorDBBase):
                 all_metadatas.append(query_metadatas)
                 all_distances.append(query_distances)
 
-            log.info(f'Search completed. Found results for {len(all_ids)} queries')
+            log.info('Search completed. Found results for %s queries', len(all_ids))
 
             # Return SearchResult format
             return SearchResult(
@@ -402,7 +417,7 @@ class S3VectorClient(VectorDBBase):
             return self.get(collection_name)
 
         try:
-            log.info(f"Querying collection '{collection_name}' with filter: {filter}")
+            log.info("Querying collection '%s' with filter: %s", collection_name, filter)
 
             # For S3 Vector, we need to use list_vectors and then filter results
             # Since S3 Vector may not support complex server-side filtering,
@@ -437,7 +452,7 @@ class S3VectorClient(VectorDBBase):
                     if limit and len(filtered_ids) >= limit:
                         break
 
-            log.info(f'Filter applied: {len(filtered_ids)} vectors match out of {len(all_ids)} total')
+            log.info('Filter applied: %s vectors match out of %s total', len(filtered_ids), len(all_ids))
 
             # Return GetResult format
             if filtered_ids:
@@ -472,7 +487,7 @@ class S3VectorClient(VectorDBBase):
             return GetResult(ids=[[]], documents=[[]], metadatas=[[]])
 
         try:
-            log.info(f"Retrieving all vectors from collection '{collection_name}'")
+            log.info("Retrieving all vectors from collection '%s'", collection_name)
 
             # Initialize result lists
             all_ids = []
@@ -521,7 +536,7 @@ class S3VectorClient(VectorDBBase):
                             )
 
                         # Log the actual content for debugging
-                        log.debug(f'Document text preview (first 200 chars): {str(document_text)[:200]}')
+                        log.debug('Document text preview (first 200 chars): %s', str(document_text)[:200])
                     else:
                         document_text = vector_id
 
@@ -534,7 +549,7 @@ class S3VectorClient(VectorDBBase):
                 if not next_token:
                     break
 
-            log.info(f"Retrieved {len(all_ids)} vectors from collection '{collection_name}'")
+            log.info("Retrieved %s vectors from collection '%s'", len(all_ids), collection_name)
 
             # Return in GetResult format
             # The Open WebUI GetResult expects lists of lists, so we wrap each list
@@ -576,17 +591,17 @@ class S3VectorClient(VectorDBBase):
         try:
             if ids:
                 # Delete by specific vector IDs/keys
-                log.info(f"Deleting {len(ids)} vectors by IDs from collection '{collection_name}'")
+                log.info("Deleting %s vectors by IDs from collection '%s'", len(ids), collection_name)
                 self.client.delete_vectors(
                     vectorBucketName=self.bucket_name,
                     indexName=collection_name,
                     keys=ids,
                 )
-                log.info(f"Deleted {len(ids)} vectors from index '{collection_name}'")
+                log.info("Deleted %s vectors from index '%s'", len(ids), collection_name)
 
             elif filter:
                 # Handle filter-based deletion
-                log.info(f"Deleting vectors by filter from collection '{collection_name}': {filter}")
+                log.info("Deleting vectors by filter from collection '%s': %s", collection_name, filter)
 
                 # If this is a knowledge collection and we have a file_id filter,
                 # also clean up the corresponding file-specific collection
@@ -595,7 +610,8 @@ class S3VectorClient(VectorDBBase):
                     file_collection_name = f'file-{file_id}'
                     if self.has_collection(file_collection_name):
                         log.info(
-                            f"Found related file-specific collection '{file_collection_name}', deleting it to prevent duplicates"
+                            "Found related file-specific collection '%s', deleting it to prevent duplicates",
+                            file_collection_name,
                         )
                         self.delete_collection(file_collection_name)
 
@@ -604,7 +620,7 @@ class S3VectorClient(VectorDBBase):
                 query_result = self.query(collection_name, filter)
                 if query_result and query_result.ids and query_result.ids[0]:
                     matching_ids = query_result.ids[0]
-                    log.info(f'Found {len(matching_ids)} vectors matching filter, deleting them')
+                    log.info('Found %s vectors matching filter, deleting them', len(matching_ids))
 
                     # Delete the matching vectors by ID
                     self.client.delete_vectors(
@@ -612,7 +628,7 @@ class S3VectorClient(VectorDBBase):
                         indexName=collection_name,
                         keys=matching_ids,
                     )
-                    log.info(f"Deleted {len(matching_ids)} vectors from index '{collection_name}' using filter")
+                    log.info("Deleted %s vectors from index '%s' using filter", len(matching_ids), collection_name)
                 else:
                     log.warning('No vectors found matching the filter criteria')
             else:
@@ -645,11 +661,11 @@ class S3VectorClient(VectorDBBase):
                     try:
                         self.client.delete_index(vectorBucketName=self.bucket_name, indexName=index_name)
                         deleted_count += 1
-                        log.info(f'Deleted index: {index_name}')
+                        log.info('Deleted index: %s', index_name)
                     except Exception as e:
                         log.error(f"Error deleting index '{index_name}': {e}")
 
-            log.info(f'Reset completed: deleted {deleted_count} indexes')
+            log.info('Reset completed: deleted %s indexes', deleted_count)
 
         except Exception as e:
             log.error(f'Error during reset: {e}')

backend/open_webui/retrieval/vector/dbs/valkey.py

@@ -2,7 +2,6 @@
 # Requires Valkey core >= 9.0.1 with the valkey-search module >= 1.2.0 loaded.
 
 import atexit
-import json
 import logging
 import re
 import struct
@@ -24,6 +23,7 @@ from open_webui.retrieval.vector.main import (
     VectorItem,
 )
 from open_webui.retrieval.vector.utils import process_metadata
+from open_webui.utils.json_codec import JSONCodec
 
 log = logging.getLogger(__name__)
 
@@ -279,7 +279,7 @@ class ValkeyClient(VectorDBBase):
                 f'{self._format_version(MIN_VALKEY_VERSION)}. valkey-search 1.2.0 requires Valkey core '
                 '9.0.1 or later. Upgrade your server or use valkey-bundle:9.1.0-rc2+.'
             )
-        log.info(f'Valkey core version: {self._format_version(version) if version else "unknown"}')
+        log.info('Valkey core version: %s', self._format_version(version) if version else 'unknown')
 
     def _check_search_module(self) -> None:
         try:
@@ -331,7 +331,7 @@ class ValkeyClient(VectorDBBase):
                 'TEXT field type and filter-only FT.SEARCH support required by this backend. '
                 'Upgrade to valkey-bundle:9.1.0-rc2+ or load valkey-search 1.2.0+ as a module.'
             )
-        log.info(f'valkey-search version: {self._format_version(search_version) if search_version else "unknown"}')
+        log.info('valkey-search version: %s', self._format_version(search_version) if search_version else 'unknown')
 
     def _index_name(self, collection_name: str) -> str:
         return f'idx:{self.collection_prefix}:{collection_name}'
@@ -385,12 +385,15 @@ class ValkeyClient(VectorDBBase):
         try:
             g['glide_ft'].create(self.client, index_name, schema, options)
             log.info(
-                f'Created Valkey index {index_name} with dimension={dimension}, '
+                'Created Valkey index %s with dimension=%s, type=%s, metric=%s',
-                f'type={self.index_type}, metric={self.distance_metric}'
+                index_name,
+                dimension,
+                self.index_type,
+                self.distance_metric,
             )
         except g['RequestError'] as e:
             if 'already exists' in str(e).lower():
-                log.debug(f'Index {index_name} already exists, skipping creation.')
+                log.debug('Index %s already exists, skipping creation.', index_name)
             else:
                 raise
 
@@ -456,9 +459,9 @@ class ValkeyClient(VectorDBBase):
         index_name = self._index_name(collection_name)
         try:
             self._g['glide_ft'].dropindex(self.client, index_name)
-            log.info(f'Dropped index {index_name}')
+            log.info('Dropped index %s', index_name)
         except self._g['RequestError'] as e:
-            log.debug(f'Could not drop index {index_name}: {e}')
+            log.debug('Could not drop index %s: %s', index_name, e)
 
         self._delete_keys_by_prefix(self._key_prefix(collection_name))
 
@@ -482,7 +485,7 @@ class ValkeyClient(VectorDBBase):
                 'id': item['id'],
                 'vector': _vector_to_bytes(item['vector']),
                 'text': item['text'],
-                'metadata_json': json.dumps(metadata),
+                'metadata_json': JSONCodec.dumps(metadata),
                 # `or ''` prevents indexing literal 'None' as a TAG value, which would
                 # poison $ne / equality queries.
                 'hash': str(metadata.get('hash') or ''),
@@ -492,7 +495,7 @@ class ValkeyClient(VectorDBBase):
             }
             self.batch_client.hset(self._item_key(collection_name, item['id']), mapping)
 
-        log.debug(f'Inserted {len(items)} items into collection {collection_name}')
+        log.debug('Inserted %s items into collection %s', len(items), collection_name)
 
     def upsert(self, collection_name: str, items: list[VectorItem]):
         self.insert(collection_name, items)
@@ -588,8 +591,8 @@ class ValkeyClient(VectorDBBase):
                     ids.append(_decode(fields.get(b'id', b'')))
                     documents.append(_decode(fields.get(b'text', b'')))
                     try:
-                        metadatas.append(json.loads(_decode(fields.get(b'metadata_json', b'{}'))))
+                        metadatas.append(JSONCodec.loads(_decode(fields.get(b'metadata_json', b'{}'))))
-                    except (json.JSONDecodeError, TypeError):
+                    except (ValueError, TypeError):
                         metadatas.append({})
                     if limit is not None and limit > 0 and len(ids) >= limit:
                         return GetResult(ids=[ids], documents=[documents], metadatas=[metadatas])
@@ -656,7 +659,7 @@ class ValkeyClient(VectorDBBase):
                     collections.append(name[len(idx_prefix) :])
                     try:
                         glide_ft.dropindex(self.client, idx)
-                        log.info(f'Dropped index: {name}')
+                        log.info('Dropped index: %s', name)
                     except Exception as e:
                         log.error(f'Error dropping index {name}: {e}')
         except Exception as e:
@@ -664,7 +667,7 @@ class ValkeyClient(VectorDBBase):
 
         for collection in collections:
             self._delete_keys_by_prefix(self._key_prefix(collection))
-        log.info(f'Valkey vector store reset complete (prefix: {self.collection_prefix})')
+        log.info('Valkey vector store reset complete (prefix: %s)', self.collection_prefix)
 
     def _delete_keys_by_prefix(self, prefix: str) -> None:
         cursor = '0'
@@ -734,8 +737,8 @@ class ValkeyClient(VectorDBBase):
             ids.append(_decode(fields.get(b'id', b'')))
             documents.append(_decode(fields.get(b'text', b'')))
             try:
-                metadatas.append(json.loads(_decode(fields.get(b'metadata_json', b'{}'))))
+                metadatas.append(JSONCodec.loads(_decode(fields.get(b'metadata_json', b'{}'))))
-            except (json.JSONDecodeError, TypeError):
+            except (ValueError, TypeError):
                 metadatas.append({})
 
             if include_score:

backend/open_webui/retrieval/vector/dbs/weaviate.py

@@ -23,7 +23,7 @@ from open_webui.retrieval.vector.main import (
     VectorDBBase,
     VectorItem,
 )
-from open_webui.retrieval.vector.utils import process_metadata
+from open_webui.retrieval.vector.utils import iter_filter_conditions, process_metadata
 
 
 def _convert_uuids_to_strings(obj: Any) -> Any:
@@ -54,6 +54,20 @@ def _convert_uuids_to_strings(obj: Any) -> Any:
         return obj
 
 
+def _metadata_filter(filter: Optional[dict]) -> Any:
+    clauses = []
+    for key, op, value in iter_filter_conditions(filter):
+        if op == '$in':
+            clauses.append(
+                weaviate.classes.query.Filter.any_of(
+                    [weaviate.classes.query.Filter.by_property(name=key).equal(item) for item in value]
+                )
+            )
+        else:
+            clauses.append(weaviate.classes.query.Filter.by_property(name=key).equal(value))
+    return weaviate.classes.query.Filter.all_of(clauses) if len(clauses) > 1 else (clauses[0] if clauses else None)
+
+
 class WeaviateClient(VectorDBBase):
     def __init__(self):
         self.url = WEAVIATE_HTTP_HOST
@@ -168,6 +182,7 @@ class WeaviateClient(VectorDBBase):
             return None
 
         collection = self.client.collections.get(sane_collection_name)
+        weaviate_filter = _metadata_filter(filter)
 
         result_ids, result_documents, result_metadatas, result_distances = (
             [],
@@ -181,6 +196,7 @@ class WeaviateClient(VectorDBBase):
                 response = collection.query.near_vector(
                     near_vector=vector_embedding,
                     limit=limit,
+                    filters=weaviate_filter,
                     return_metadata=weaviate.classes.query.MetadataQuery(distance=True),
                 )
 

backend/open_webui/retrieval/vector/factory.py

@@ -1,8 +1,12 @@
+from threading import Lock
+
+from fastapi import HTTPException
 from open_webui.config import (
     ENABLE_MILVUS_MULTITENANCY_MODE,
     ENABLE_QDRANT_MULTITENANCY_MODE,
     VECTOR_DB,
 )
+from open_webui.env import USE_SLIM
 from open_webui.retrieval.vector.main import VectorDBBase
 from open_webui.retrieval.vector.type import VectorType
 
@@ -13,6 +17,11 @@ class Vector:
         """
         get vector db instance by vector type
         """
+        if USE_SLIM and vector_type != VectorType.PGVECTOR:
+            raise HTTPException(
+                503,
+                'Slim requires PostgreSQL/pgvector for vector storage. Set VECTOR_DB=pgvector and PGVECTOR_DB_URL, or use the standard image.',
+            )
         match vector_type:
             case VectorType.MILVUS:
                 if ENABLE_MILVUS_MULTITENANCY_MODE:
@@ -88,4 +97,27 @@ class Vector:
                 raise ValueError(f'Unsupported vector type: {vector_type}')
 
 
-VECTOR_DB_CLIENT = Vector.get_vector(VECTOR_DB)
+VECTOR_DB_CLIENT = None if USE_SLIM else Vector.get_vector(VECTOR_DB)
+_vector_client_lock = Lock()
+
+
+def get_vector_db_client() -> VectorDBBase:
+    """Initialize slim's remote client on first use so chat can start without it."""
+    global VECTOR_DB_CLIENT
+    if VECTOR_DB_CLIENT is not None:
+        return VECTOR_DB_CLIENT
+    with _vector_client_lock:
+        if VECTOR_DB_CLIENT is None:
+            from open_webui import config
+
+            if VECTOR_DB == VectorType.PGVECTOR and not config.PGVECTOR_DB_URL.startswith('postgres'):
+                raise HTTPException(503, 'Configure PGVECTOR_DB_URL for remote vector storage.')
+            try:
+                VECTOR_DB_CLIENT = Vector.get_vector(VECTOR_DB)
+            except HTTPException:
+                raise
+            except Exception as exc:
+                raise HTTPException(
+                    503, f'Unable to connect to configured vector database ({VECTOR_DB}): {exc}'
+                ) from exc
+    return VECTOR_DB_CLIENT

backend/open_webui/retrieval/vector/utils.py

@@ -1,16 +1,38 @@
 import datetime as dt
 from typing import Any
 
+from open_webui.env import RAG_METADATA_MAX_VALUE_CHARS
 from open_webui.retrieval.vector.main import SearchResult
 from open_webui.utils.misc import sanitize_text_for_db
 
-KEYS_TO_EXCLUDE = ['content', 'pages', 'tables', 'paragraphs', 'sections', 'figures']
+KEYS_TO_EXCLUDE = [
+    'content',
+    'pages',
+    'tables',
+    'paragraphs',
+    'sections',
+    'figures',
+    'documents',
+    'keyValuePairs',
+    'styles',
+    'languages',
+]
 
 
 def filter_metadata(metadata: dict[str, any]) -> dict[str, any]:
     # Removes large/redundant fields from metadata dict.
-    metadata = {key: value for key, value in metadata.items() if key not in KEYS_TO_EXCLUDE}
+    result = {}
-    return metadata
+    for key, value in metadata.items():
+        if key in KEYS_TO_EXCLUDE:
+            continue
+        if RAG_METADATA_MAX_VALUE_CHARS is not None and isinstance(value, (list, dict)):
+            try:
+                if len(str(value)) > RAG_METADATA_MAX_VALUE_CHARS:
+                    continue
+            except (MemoryError, RecursionError, ValueError):
+                continue
+        result[key] = value
+    return result
 
 
 def process_metadata(
@@ -25,6 +47,12 @@ def process_metadata(
             continue
         if value is None:
             continue
+        if RAG_METADATA_MAX_VALUE_CHARS is not None and isinstance(value, (list, dict)):
+            try:
+                if len(str(value)) > RAG_METADATA_MAX_VALUE_CHARS:
+                    continue
+            except (MemoryError, RecursionError, ValueError):
+                continue
         # Convert non-serializable fields to strings
         if isinstance(value, (dt.datetime, list, dict)):
             result[key] = sanitize_text_for_db(str(value))
@@ -33,6 +61,33 @@ def process_metadata(
     return result
 
 
+def iter_filter_conditions(filter: dict[str, Any] | None):
+    for key, value in (filter or {}).items():
+        if isinstance(value, dict):
+            if set(value) != {'$in'}:
+                raise ValueError(f"Unsupported metadata filter for '{key}': {value}")
+            yield key, '$in', list(value['$in'])
+        else:
+            yield key, '$eq', value
+
+
+def normalize_filter(filter: dict[str, Any] | None) -> dict[str, Any]:
+    return {key: {'$in': value} if op == '$in' else value for key, op, value in iter_filter_conditions(filter)}
+
+
+def metadata_matches_filter(metadata: dict[str, Any], filter: dict[str, Any] | None) -> bool:
+    if not isinstance(metadata, dict):
+        return False
+    for key, op, value in iter_filter_conditions(filter):
+        actual = metadata.get(key)
+        if op == '$in':
+            if actual not in value:
+                return False
+        elif actual != value:
+            return False
+    return True
+
+
 def merge_hybrid_search_results(
     vector_result: SearchResult | None,
     fts_results: list[dict[str, Any]],

backend/open_webui/retrieval/web/bocha.py

@@ -1,9 +1,9 @@
-import json
 import logging
 from typing import Optional
 
 import requests
 from open_webui.retrieval.web.main import SearchResult, get_filtered_results
+from open_webui.utils.json_codec import JSONCodec
 
 log = logging.getLogger(__name__)
 
@@ -41,7 +41,7 @@ def search_bocha(api_key: str, query: str, count: int, filter_list: Optional[lis
     url = 'https://api.bochaai.com/v1/web-search?utm_source=ollama'
     headers = {'Authorization': f'Bearer {api_key}', 'Content-Type': 'application/json'}
 
-    payload = json.dumps({'query': query, 'summary': True, 'freshness': 'noLimit', 'count': count})
+    payload = JSONCodec.dumps({'query': query, 'summary': True, 'freshness': 'noLimit', 'count': count})
 
     response = requests.post(url, headers=headers, data=payload, timeout=5)
     response.raise_for_status()

backend/open_webui/retrieval/web/brave.py

@@ -16,7 +16,7 @@ async def search_brave(
     api_key: str,
     query: str,
     count: int,
-    filter_list: list[str | None] | None = None,
+    filter_list: list[str] | None = None,
 ) -> list[SearchResult]:
     """Query the Brave Web Search API and return normalised results.
 

backend/open_webui/retrieval/web/duckduckgo.py

@@ -3,8 +3,7 @@ from __future__ import annotations
 import logging
 import urllib.request
 
-from ddgs import DDGS
+from open_webui.env import USE_SLIM
-from ddgs.exceptions import RatelimitException
 from open_webui.retrieval.web.main import SearchResult, get_filtered_results
 
 log = logging.getLogger(__name__)
@@ -13,7 +12,7 @@ log = logging.getLogger(__name__)
 def search_duckduckgo(
     query: str,
     count: int,
-    filter_list: list[str | None] = None,
+    filter_list: list[str] | None = None,
     concurrent_requests: int | None = None,
     backend: str | None = 'auto',
 ) -> list[SearchResult]:
@@ -27,25 +26,22 @@ def search_duckduckgo(
     Returns:
         list[SearchResult]: A list of search results
     """
+    if USE_SLIM:
+        raise ValueError(
+            'DDGS is unavailable in slim. Configure another web search provider in Admin Settings > Web Search.'
+        )
+
+    from ddgs import DDGS
+
     # The ddgs library (primp-based) does not auto-detect proxy env vars.
     # Resolve via stdlib getproxies() — same pattern as the other loaders.
     env_proxies = urllib.request.getproxies()
     proxy = env_proxies.get('https') or env_proxies.get('http')
-    search_results = []
     with DDGS(proxy=proxy) as ddgs:
         if concurrent_requests:
             ddgs.threads = concurrent_requests
 
-        # Use the ddgs.text() method to perform the search
+        search_results = ddgs.text(query, safesearch='moderate', max_results=count, backend=backend or 'auto')
-        try:
-            kwargs = {'safesearch': 'moderate', 'max_results': count}
-            if backend and backend != 'auto':
-                kwargs['backend'] = backend
-            results = ddgs.text(query, **kwargs)
-            search_results = results if results is not None else []
-        except RatelimitException as e:
-            log.error(f'RatelimitException: {e}')
-            search_results = []
     if filter_list:
         search_results = get_filtered_results(search_results, filter_list)
 

backend/open_webui/retrieval/web/exa.py

@@ -1,6 +1,4 @@
 import logging
-from dataclasses import dataclass
-from typing import Optional
 
 import requests
 from open_webui.retrieval.web.main import SearchResult
@@ -10,18 +8,12 @@ log = logging.getLogger(__name__)
 EXA_API_BASE = 'https://api.exa.ai'
 
 
-@dataclass
-class ExaResult:
-    url: str
-    title: str
-    text: str
-
-
 def search_exa(
     api_key: str,
     query: str,
     count: int,
-    filter_list: Optional[list[str]] = None,
+    filter_list: list[str] | None = None,
+    max_content_length: int | None = None,
 ) -> list[SearchResult]:
     """Search using Exa Search API and return the results as a list of SearchResult objects.
 
@@ -29,9 +21,10 @@ def search_exa(
         api_key (str): A Exa Search API key
         query (str): The query to search for
         count (int): Number of results to return
-        filter_list (Optional[list[str]]): List of domains to filter results by
+        filter_list (list[str] | None): List of domains to filter results by
+        max_content_length (int | None): Maximum characters per result; None leaves text unlimited.
     """
-    log.info(f'Searching with Exa for query: {query}')
+    log.info('Searching with Exa for query: %s', query)
 
     headers = {'Authorization': f'Bearer {api_key}', 'Content-Type': 'application/json'}
 
@@ -39,7 +32,7 @@ def search_exa(
         'query': query,
         'numResults': count or 5,
         'includeDomains': filter_list,
-        'contents': {'text': True, 'highlights': True},
+        'contents': {'text': {'maxCharacters': max_content_length} if max_content_length is not None else True},
         'type': 'auto',  # Use the auto search type (keyword or neural)
     }
 
@@ -48,22 +41,13 @@ def search_exa(
         response.raise_for_status()
         data = response.json()
 
-        results = []
+        results = data['results']
-        for result in data['results']:
+        log.info('Found %s results', len(results))
-            results.append(
-                ExaResult(
-                    url=result['url'],
-                    title=result['title'],
-                    text=result['text'],
-                )
-            )
-
-        log.info(f'Found {len(results)} results')
         return [
             SearchResult(
-                link=result.url,
+                link=result['url'],
-                title=result.title,
+                title=result['title'],
-                snippet=result.text,
+                snippet=(result.get('text') or '')[:max_content_length],
             )
             for result in results
         ]

backend/open_webui/retrieval/web/external.py

@@ -21,6 +21,9 @@ def search_external(
 ) -> List[SearchResult]:
     try:
         headers = {
+            # LICENSE covers this Open WebUI user-agent identifier.
+            # Do not alter, remove, obscure, or replace it except as LICENSE permits:
+            # https://docs.openwebui.com/license.
             'User-Agent': 'Open WebUI (https://github.com/open-webui/open-webui) RAG Bot',
             'Authorization': f'Bearer {external_api_key}',
         }
@@ -50,7 +53,7 @@ def search_external(
             )
             for result in results[:count]
         ]
-        log.info(f'External search results: {results}')
+        log.info('External search results: %s', results)
         return results
     except Exception as e:
         log.error(f'Error in External search: {e}')

backend/open_webui/retrieval/web/firecrawl.py

@@ -225,7 +225,7 @@ def search_firecrawl(
                 )
             )
 
-        log.info(f'FireCrawl search results: {search_results}')
+        log.info('FireCrawl search results: %s', search_results)
         return search_results
     except Exception as e:
         log.error(f'Error in FireCrawl search: {e}')

backend/open_webui/retrieval/web/google_pse.py

@@ -13,7 +13,7 @@ async def search_google_pse(
     search_engine_id: str,
     query: str,
     count: int,
-    filter_list: list[str | None] | None = None,
+    filter_list: list[str] | None = None,
     referer: str | None = None,
 ) -> list[SearchResult]:
     """Query Google Programmable Search Engine with automatic pagination.

backend/open_webui/retrieval/web/main.py

@@ -1,11 +1,10 @@
 from __future__ import annotations
 
-import ipaddress
 from urllib.parse import urlparse
 
 import validators
 from open_webui.retrieval.web.utils import resolve_hostname
-from open_webui.utils.misc import get_allow_block_lists, is_host_allowed
+from open_webui.utils.misc import as_network, get_allow_block_lists, is_host_allowed
 from pydantic import BaseModel
 
 
@@ -14,14 +13,8 @@ def get_filtered_results(results, filter_list):
         return results
 
     allow_list, block_list = get_allow_block_lists(filter_list)
-    resolve_ips = False
+    # Only worth a lookup when an entry names an address, since a hostname entry matches by name.
-    for entry in allow_list + block_list:
+    resolve_ips = any(as_network(entry) is not None for entry in allow_list + block_list)
-        try:
-            ipaddress.ip_address(entry)
-        except ValueError:
-            continue
-        resolve_ips = True
-        break
 
     filtered_results = []
 

backend/open_webui/retrieval/web/microsoft_web_iq.py

@@ -9,20 +9,18 @@ from open_webui.utils.headers import include_user_info_headers
 
 log = logging.getLogger(__name__)
 
-DEFAULT_MICROSOFT_WEB_IQ_API_BASE_URL = 'https://api.microsoft.ai/v3'
-
 
 def search_microsoft_web_iq(
     api_base_url: str,
     api_key: str,
     query: str,
     count: int,
-    filter_list: list[str | None] | None = None,
+    filter_list: list[str] | None = None,
     language: str = 'en',
     user=None,
 ) -> list[SearchResult]:
     try:
-        api_base_url = (api_base_url or DEFAULT_MICROSOFT_WEB_IQ_API_BASE_URL).rstrip('/')
+        api_base_url = api_base_url.rstrip('/')
         headers = {
             'host': urlparse(api_base_url).netloc or 'api.microsoft.ai',
             'x-apikey': api_key,

backend/open_webui/retrieval/web/mojeek.py

@@ -8,7 +8,7 @@ from open_webui.retrieval.web.main import SearchResult, get_filtered_results
 log = logging.getLogger(__name__)
 
 
-def search_mojeek(api_key: str, query: str, count: int, filter_list: list[str | None] = None) -> list[SearchResult]:
+def search_mojeek(api_key: str, query: str, count: int, filter_list: list[str] | None = None) -> list[SearchResult]:
     """Search using Mojeek's Search API and return the results as a list of SearchResult objects.
 
     Args:

backend/open_webui/retrieval/web/ollama.py

@@ -23,7 +23,7 @@ def search_ollama_cloud(
         count (int): Number of results to return
         filter_list (Optional[list[str]]): List of domains to filter results by
     """
-    log.info(f'Searching with Ollama for query: {query}')
+    log.info('Searching with Ollama for query: %s', query)
 
     headers = {'Authorization': f'Bearer {api_key}', 'Content-Type': 'application/json'}
     payload = {'query': query, 'max_results': count}
@@ -34,7 +34,7 @@ def search_ollama_cloud(
         data = response.json()
 
         results = data.get('results', [])
-        log.info(f'Found {len(results)} results')
+        log.info('Found %s results', len(results))
 
         if filter_list:
             results = get_filtered_results(results, filter_list)

backend/open_webui/retrieval/web/openserp.py

@@ -12,7 +12,7 @@ async def search_openserp(
     base_url: str,
     query: str,
     count: int,
-    filter_list: list[str | None] | None = None,
+    filter_list: list[str] | None = None,
 ) -> list[SearchResult]:
     """Query an OpenSERP instance and return normalised results.
 

backend/open_webui/retrieval/web/searchapi.py

@@ -26,19 +26,26 @@ def search_searchapi(
     engine = engine or 'google'
 
     payload = {'engine': engine, 'q': query, 'api_key': api_key}
+    if engine.startswith('google'):
+        payload['link'] = 'resolved'
 
     url = f'{url}?{urlencode(payload)}'
-    response = requests.request('GET', url)
+    response = requests.request('GET', url, timeout=30)
+    response.raise_for_status()
 
     json_response = response.json()
-    log.info(f'results from searchapi search: {json_response}')
+    log.debug('results from searchapi search: %s', json_response)
 
-    results = sorted(json_response.get('organic_results', []), key=lambda x: x.get('position', 0))
+    # top_stories entries carry no position, so the merged list keeps API order
+    results = [
+        *json_response.get('organic_results', []),
+        *json_response.get('top_stories', []),
+    ]
     if filter_list:
         results = get_filtered_results(results, filter_list)
     return [
         SearchResult(
-            link=result['link'],
+            link=result.get('link', ''),
             title=result.get('title'),
             snippet=result.get('snippet'),
         )

backend/open_webui/retrieval/web/searxng.py

@@ -12,6 +12,9 @@ log = logging.getLogger(__name__)
 
 # SearXNG request headers — identifies the bot to instance operators.
 _SEARXNG_HEADERS = {
+    # LICENSE covers this Open WebUI user-agent identifier.
+    # Do not alter, remove, obscure, or replace it except as LICENSE permits:
+    # https://docs.openwebui.com/license.
     'User-Agent': 'Open WebUI (https://github.com/open-webui/open-webui) RAG Bot',
     'Accept': 'text/html',
     'Accept-Encoding': 'gzip, deflate',
@@ -37,7 +40,7 @@ async def search_searxng(
     query_url: str,
     query: str,
     count: int,
-    filter_list: list[str | None] | None = None,
+    filter_list: list[str] | None = None,
     **kwargs,
 ) -> list[SearchResult]:
     """Query a SearXNG instance and return results sorted by relevance score.

backend/open_webui/retrieval/web/serpapi.py

@@ -31,7 +31,7 @@ def search_serpapi(
     response = requests.request('GET', url)
 
     json_response = response.json()
-    log.info(f'results from serpapi search: {json_response}')
+    log.info('results from serpapi search: %s', json_response)
 
     results = sorted(json_response.get('organic_results', []), key=lambda x: x.get('position', 0))
     if filter_list:

backend/open_webui/retrieval/web/serper.py

@@ -1,9 +1,9 @@
 from __future__ import annotations
 
-import json
 import logging
 
 from open_webui.retrieval.web.main import SearchResult, get_filtered_results
+from open_webui.utils.json_codec import JSONCodec
 from open_webui.utils.session_pool import get_session
 
 log = logging.getLogger(__name__)
@@ -13,7 +13,7 @@ async def search_serper(
     api_key: str,
     query: str,
     count: int,
-    filter_list: list[str | None] | None = None,
+    filter_list: list[str] | None = None,
 ) -> list[SearchResult]:
     """Query the serper.dev Google Search API and return normalised results.
 
@@ -23,7 +23,7 @@ async def search_serper(
     headers = {'X-API-KEY': api_key, 'Content-Type': 'application/json'}
 
     session = await get_session()
-    async with session.post(url, headers=headers, data=json.dumps({'q': query})) as response:
+    async with session.post(url, headers=headers, data=JSONCodec.dumps({'q': query})) as response:
         response.raise_for_status()
         payload = await response.json()
 

backend/open_webui/retrieval/web/serphouse.py

@@ -9,7 +9,7 @@ async def search_serphouse(
     domain: str,
     query: str,
     count: int,
-    filter_list: list[str | None] | None = None,
+    filter_list: list[str] | None = None,
 ) -> list[SearchResult]:
     """Query SERPHouse and return normalised organic results."""
     session = await get_session()

backend/open_webui/retrieval/web/serply.py

@@ -17,7 +17,7 @@ def search_serply(
     limit: int = 10,
     device_type: str = 'desktop',
     proxy_location: str = 'US',
-    filter_list: list[str | None] = None,
+    filter_list: list[str] | None = None,
 ) -> list[SearchResult]:
     """Search using serper.dev's API and return the results as a list of SearchResult objects.
 
@@ -51,7 +51,7 @@ def search_serply(
     response.raise_for_status()
 
     json_response = response.json()
-    log.info(f'results from serply search: {json_response}')
+    log.info('results from serply search: %s', json_response)
 
     results = sorted(json_response.get('results', []), key=lambda x: x.get('realPosition', 0))
     if filter_list:

backend/open_webui/retrieval/web/serpstack.py

@@ -12,7 +12,7 @@ async def search_serpstack(
     api_key: str,
     query: str,
     count: int,
-    filter_list: list[str | None] | None = None,
+    filter_list: list[str] | None = None,
     https_enabled: bool = True,
 ) -> list[SearchResult]:
     """Query the serpstack.com API and return normalised results.

backend/open_webui/retrieval/web/sougou.py

@@ -1,8 +1,8 @@
-import json
 import logging
 from typing import List, Optional
 
 from open_webui.retrieval.web.main import SearchResult, get_filtered_results
+from open_webui.utils.json_codec import JSONCodec
 
 log = logging.getLogger(__name__)
 
@@ -28,10 +28,11 @@ def search_sougou(
         http_profile.endpoint = 'tms.tencentcloudapi.com'
         client_profile = ClientProfile()
         client_profile.http_profile = http_profile
-        params = json.dumps({'Query': query, 'Cnt': 20})
+        params = JSONCodec.dumps({'Query': query, 'Cnt': 20})
         common_client = CommonClient('tms', '2020-12-29', cred, '', profile=client_profile)
         results = [
-            json.loads(page) for page in common_client.call_json('SearchPro', json.loads(params))['Response']['Pages']
+            JSONCodec.loads(page)
+            for page in common_client.call_json('SearchPro', JSONCodec.loads(params))['Response']['Pages']
         ]
         sorted_results = sorted(results, key=lambda x: x.get('scour', 0.0), reverse=True)
         if filter_list:

backend/open_webui/retrieval/web/staan.py

@@ -0,0 +1,60 @@
+from __future__ import annotations
+
+import requests
+from open_webui.retrieval.web.main import SearchResult, get_filtered_results
+
+
+def search_staan(
+    api_key: str,
+    query: str,
+    count: int,
+    filter_list: list[str] | None = None,
+    market: str | None = None,
+    max_snippets: int | None = None,
+) -> list[SearchResult]:
+    """Search using Staan's Web Search API and return the results as a list of SearchResult objects.
+
+    Args:
+        api_key (str): A Staan API key
+        query (str): The query to search for
+        count (int): The maximum number of results to return
+        filter_list (list[str] | None): The domains to allow or block
+        market (str | None): The market to search in, e.g. 'en-us'
+        max_snippets (int | None): The maximum extra snippets to request per result
+
+    Returns:
+        A list of SearchResult objects.
+    """
+    url = 'https://api.staan.ai/v2/search/web'
+    headers = {
+        'Accept': 'application/json',
+        'Authorization': f'Bearer {api_key}',
+    }
+    params = {'q': query, 'market': market}
+
+    if max_snippets:
+        params['extra_snippets'] = 'true'
+        params['max_snippets'] = max_snippets
+
+    response = requests.get(url, headers=headers, params=params)
+    response.raise_for_status()
+
+    results = response.json().get('web', {}).get('results', [])
+    if filter_list:
+        results = get_filtered_results(results, filter_list)
+
+    return [
+        SearchResult(
+            link=result.get('url', ''),
+            title=result.get('title'),
+            snippet=_build_snippet(result),
+        )
+        for result in results[:count]
+    ]
+
+
+def _build_snippet(result: dict) -> str:
+    """Combine the snippet and the extra snippets list into a single string."""
+    parts = [result.get('snippet')]
+    parts.extend(extra.get('chunk') for extra in result.get('extra_snippets', []))
+    return '\n\n'.join(part for part in parts if part)

backend/open_webui/retrieval/web/tavily.py

@@ -3,6 +3,7 @@ from __future__ import annotations
 import logging
 
 import requests
+from open_webui.env import TAVILY_API_BASE_URL
 from open_webui.retrieval.web.main import SearchResult, get_filtered_results
 
 log = logging.getLogger(__name__)
@@ -12,7 +13,7 @@ def search_tavily(
     api_key: str,
     query: str,
     count: int,
-    filter_list: list[str | None] = None,
+    filter_list: list[str] | None = None,
     # **kwargs,
 ) -> list[SearchResult]:
     """Search using Tavily's Search API and return the results as a list of SearchResult objects.
@@ -25,7 +26,7 @@ def search_tavily(
     Returns:
         A list of SearchResult objects.
     """
-    url = 'https://api.tavily.com/search'
+    url = f'{TAVILY_API_BASE_URL}/search'
     headers = {
         'Content-Type': 'application/json',
         'Authorization': f'Bearer {api_key}',