fix: Interactive.Base href rendering and container self-stretch

- Always use Slot in Interactive.Base instead of rendering a separate <a>
  wrapper when href is provided. Interactive.Container now renders an <a>
  when href is present (same pattern as div vs button via type prop). This
  keeps all styling (backgrounds, rounding, overflow) on a single element,
  fixing square corners on hover for link buttons.

- Remove self-stretch from .interactive-container to prevent buttons from
  stretching vertically in row flex layouts.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

.cursor/mcp.json

@@ -0,0 +1,16 @@
+{
+  "mcpServers": {
+    "Playwright": {
+      "command": "npx",
+      "args": [
+        "@playwright/mcp"
+      ]
+    },
+    "Linear": {
+      "url": "https://mcp.linear.app/mcp"
+    },
+    "Figma": {
+      "url": "https://mcp.figma.com/mcp"
+    }
+  }
+}

.github/CODEOWNERS

@@ -6,5 +6,5 @@
 /web/STANDARDS.md @raunakab @Weves
 
 # Agent context files
-/CLAUDE.md.template @Weves
-/AGENTS.md.template @Weves
+/CLAUDE.md @Weves
+/AGENTS.md @Weves

.github/workflows/deployment.yml

@@ -82,7 +82,7 @@ jobs:
           if [[ "$TAG" =~ ^v[0-9]+\.[0-9]+\.[0-9]+$ ]]; then
             IS_STABLE=true
           fi
-          if [[ "$TAG" =~ ^v[0-9]+\.[0-9]+\.[0-9]+-beta\.[0-9]+$ ]]; then
+          if [[ "$TAG" =~ ^v[0-9]+\.[0-9]+\.[0-9]+-beta(\.[0-9]+)?$ ]]; then
             IS_BETA=true
           fi
 
@@ -91,8 +91,8 @@ jobs:
             BUILD_WEB_CLOUD=true
           else
             BUILD_WEB=true
-            # Skip desktop builds on beta tags and nightly runs
-            if [[ "$IS_BETA" != "true" ]] && [[ "$IS_NIGHTLY" != "true" ]]; then
+            # Only build desktop for semver tags (excluding beta)
+            if [[ "$IS_VERSION_TAG" == "true" ]] && [[ "$IS_BETA" != "true" ]]; then
               BUILD_DESKTOP=true
             fi
           fi
@@ -174,23 +174,10 @@ jobs:
         with:
           persist-credentials: false
 
-      - name: Configure AWS credentials
-        uses: aws-actions/configure-aws-credentials@61815dcd50bd041e203e49132bacad1fd04d2708
-        with:
-          role-to-assume: ${{ secrets.AWS_OIDC_ROLE_ARN }}
-          aws-region: us-east-2
-
-      - name: Get AWS Secrets
-        uses: aws-actions/aws-secretsmanager-get-secrets@a9a7eb4e2f2871d30dc5b892576fde60a2ecc802
-        with:
-          secret-ids: |
-            MONITOR_DEPLOYMENTS_WEBHOOK, deploy/monitor-deployments-webhook
-          parse-json-secrets: true
-
       - name: Send Slack notification
         uses: ./.github/actions/slack-notify
         with:
-          webhook-url: ${{ env.MONITOR_DEPLOYMENTS_WEBHOOK }}
+          webhook-url: ${{ secrets.MONITOR_DEPLOYMENTS_WEBHOOK }}
           failed-jobs: "• check-version-tag"
           title: "🚨 Version Tag Check Failed"
           ref-name: ${{ github.ref_name }}
@@ -262,7 +249,7 @@ jobs:
             xdg-utils
 
       - name: setup node
-        uses: actions/setup-node@395ad3262231945c25e8478fd5baf05154b1d79f # ratchet:actions/setup-node@v6.1.0
+        uses: actions/setup-node@6044e13b5dc448c55e2357c09f80417699197238 # ratchet:actions/setup-node@v6.2.0
         with:
           node-version: 24
           package-manager-cache: false
@@ -422,7 +409,7 @@ jobs:
         uses: docker/setup-buildx-action@8d2750c68a42422c14e847fe6c8ac0403b4cbd6f # ratchet:docker/setup-buildx-action@v3
 
       - name: Login to Docker Hub
-        uses: docker/login-action@5e57cd118135c172c3672efd75eb46360885c0ef # ratchet:docker/login-action@v3
+        uses: docker/login-action@c94ce9fb468520275223c153574b00df6fe4bcc9 # ratchet:docker/login-action@v3
         with:
           username: ${{ env.DOCKER_USERNAME }}
           password: ${{ env.DOCKER_TOKEN }}
@@ -495,7 +482,7 @@ jobs:
         uses: docker/setup-buildx-action@8d2750c68a42422c14e847fe6c8ac0403b4cbd6f # ratchet:docker/setup-buildx-action@v3
 
       - name: Login to Docker Hub
-        uses: docker/login-action@5e57cd118135c172c3672efd75eb46360885c0ef # ratchet:docker/login-action@v3
+        uses: docker/login-action@c94ce9fb468520275223c153574b00df6fe4bcc9 # ratchet:docker/login-action@v3
         with:
           username: ${{ env.DOCKER_USERNAME }}
           password: ${{ env.DOCKER_TOKEN }}
@@ -555,7 +542,7 @@ jobs:
         uses: docker/setup-buildx-action@8d2750c68a42422c14e847fe6c8ac0403b4cbd6f # ratchet:docker/setup-buildx-action@v3
 
       - name: Login to Docker Hub
-        uses: docker/login-action@5e57cd118135c172c3672efd75eb46360885c0ef # ratchet:docker/login-action@v3
+        uses: docker/login-action@c94ce9fb468520275223c153574b00df6fe4bcc9 # ratchet:docker/login-action@v3
         with:
           username: ${{ env.DOCKER_USERNAME }}
           password: ${{ env.DOCKER_TOKEN }}
@@ -633,7 +620,7 @@ jobs:
         uses: docker/setup-buildx-action@8d2750c68a42422c14e847fe6c8ac0403b4cbd6f # ratchet:docker/setup-buildx-action@v3
 
       - name: Login to Docker Hub
-        uses: docker/login-action@5e57cd118135c172c3672efd75eb46360885c0ef # ratchet:docker/login-action@v3
+        uses: docker/login-action@c94ce9fb468520275223c153574b00df6fe4bcc9 # ratchet:docker/login-action@v3
         with:
           username: ${{ env.DOCKER_USERNAME }}
           password: ${{ env.DOCKER_TOKEN }}
@@ -653,6 +640,7 @@ jobs:
             NEXT_PUBLIC_POSTHOG_HOST=${{ secrets.POSTHOG_HOST }}
             NEXT_PUBLIC_SENTRY_DSN=${{ secrets.SENTRY_DSN }}
             NEXT_PUBLIC_STRIPE_PUBLISHABLE_KEY=${{ secrets.STRIPE_PUBLISHABLE_KEY }}
+            NEXT_PUBLIC_RECAPTCHA_SITE_KEY=${{ vars.NEXT_PUBLIC_RECAPTCHA_SITE_KEY }}
             NEXT_PUBLIC_GTM_ENABLED=true
             NEXT_PUBLIC_FORGOT_PASSWORD_ENABLED=true
             NEXT_PUBLIC_INCLUDE_ERROR_POPUP_SUPPORT_LINK=true
@@ -714,7 +702,7 @@ jobs:
         uses: docker/setup-buildx-action@8d2750c68a42422c14e847fe6c8ac0403b4cbd6f # ratchet:docker/setup-buildx-action@v3
 
       - name: Login to Docker Hub
-        uses: docker/login-action@5e57cd118135c172c3672efd75eb46360885c0ef # ratchet:docker/login-action@v3
+        uses: docker/login-action@c94ce9fb468520275223c153574b00df6fe4bcc9 # ratchet:docker/login-action@v3
         with:
           username: ${{ env.DOCKER_USERNAME }}
           password: ${{ env.DOCKER_TOKEN }}
@@ -734,6 +722,7 @@ jobs:
             NEXT_PUBLIC_POSTHOG_HOST=${{ secrets.POSTHOG_HOST }}
             NEXT_PUBLIC_SENTRY_DSN=${{ secrets.SENTRY_DSN }}
             NEXT_PUBLIC_STRIPE_PUBLISHABLE_KEY=${{ secrets.STRIPE_PUBLISHABLE_KEY }}
+            NEXT_PUBLIC_RECAPTCHA_SITE_KEY=${{ vars.NEXT_PUBLIC_RECAPTCHA_SITE_KEY }}
             NEXT_PUBLIC_GTM_ENABLED=true
             NEXT_PUBLIC_FORGOT_PASSWORD_ENABLED=true
             NEXT_PUBLIC_INCLUDE_ERROR_POPUP_SUPPORT_LINK=true
@@ -782,7 +771,7 @@ jobs:
         uses: docker/setup-buildx-action@8d2750c68a42422c14e847fe6c8ac0403b4cbd6f # ratchet:docker/setup-buildx-action@v3
 
       - name: Login to Docker Hub
-        uses: docker/login-action@5e57cd118135c172c3672efd75eb46360885c0ef # ratchet:docker/login-action@v3
+        uses: docker/login-action@c94ce9fb468520275223c153574b00df6fe4bcc9 # ratchet:docker/login-action@v3
         with:
           username: ${{ env.DOCKER_USERNAME }}
           password: ${{ env.DOCKER_TOKEN }}
@@ -857,7 +846,7 @@ jobs:
         uses: docker/setup-buildx-action@8d2750c68a42422c14e847fe6c8ac0403b4cbd6f # ratchet:docker/setup-buildx-action@v3
 
       - name: Login to Docker Hub
-        uses: docker/login-action@5e57cd118135c172c3672efd75eb46360885c0ef # ratchet:docker/login-action@v3
+        uses: docker/login-action@c94ce9fb468520275223c153574b00df6fe4bcc9 # ratchet:docker/login-action@v3
         with:
           username: ${{ env.DOCKER_USERNAME }}
           password: ${{ env.DOCKER_TOKEN }}
@@ -929,7 +918,7 @@ jobs:
         uses: docker/setup-buildx-action@8d2750c68a42422c14e847fe6c8ac0403b4cbd6f # ratchet:docker/setup-buildx-action@v3
 
       - name: Login to Docker Hub
-        uses: docker/login-action@5e57cd118135c172c3672efd75eb46360885c0ef # ratchet:docker/login-action@v3
+        uses: docker/login-action@c94ce9fb468520275223c153574b00df6fe4bcc9 # ratchet:docker/login-action@v3
         with:
           username: ${{ env.DOCKER_USERNAME }}
           password: ${{ env.DOCKER_TOKEN }}
@@ -988,7 +977,7 @@ jobs:
         uses: docker/setup-buildx-action@8d2750c68a42422c14e847fe6c8ac0403b4cbd6f # ratchet:docker/setup-buildx-action@v3
 
       - name: Login to Docker Hub
-        uses: docker/login-action@5e57cd118135c172c3672efd75eb46360885c0ef # ratchet:docker/login-action@v3
+        uses: docker/login-action@c94ce9fb468520275223c153574b00df6fe4bcc9 # ratchet:docker/login-action@v3
         with:
           username: ${{ env.DOCKER_USERNAME }}
           password: ${{ env.DOCKER_TOKEN }}
@@ -1066,7 +1055,7 @@ jobs:
         uses: docker/setup-buildx-action@8d2750c68a42422c14e847fe6c8ac0403b4cbd6f # ratchet:docker/setup-buildx-action@v3
 
       - name: Login to Docker Hub
-        uses: docker/login-action@5e57cd118135c172c3672efd75eb46360885c0ef # ratchet:docker/login-action@v3
+        uses: docker/login-action@c94ce9fb468520275223c153574b00df6fe4bcc9 # ratchet:docker/login-action@v3
         with:
           username: ${{ env.DOCKER_USERNAME }}
           password: ${{ env.DOCKER_TOKEN }}
@@ -1139,7 +1128,7 @@ jobs:
         uses: docker/setup-buildx-action@8d2750c68a42422c14e847fe6c8ac0403b4cbd6f # ratchet:docker/setup-buildx-action@v3
 
       - name: Login to Docker Hub
-        uses: docker/login-action@5e57cd118135c172c3672efd75eb46360885c0ef # ratchet:docker/login-action@v3
+        uses: docker/login-action@c94ce9fb468520275223c153574b00df6fe4bcc9 # ratchet:docker/login-action@v3
         with:
           username: ${{ env.DOCKER_USERNAME }}
           password: ${{ env.DOCKER_TOKEN }}
@@ -1200,7 +1189,7 @@ jobs:
         uses: docker/setup-buildx-action@8d2750c68a42422c14e847fe6c8ac0403b4cbd6f # ratchet:docker/setup-buildx-action@v3
 
       - name: Login to Docker Hub
-        uses: docker/login-action@5e57cd118135c172c3672efd75eb46360885c0ef # ratchet:docker/login-action@v3
+        uses: docker/login-action@c94ce9fb468520275223c153574b00df6fe4bcc9 # ratchet:docker/login-action@v3
         with:
           username: ${{ env.DOCKER_USERNAME }}
           password: ${{ env.DOCKER_TOKEN }}
@@ -1280,7 +1269,7 @@ jobs:
           buildkitd-flags: ${{ vars.DOCKER_DEBUG == 'true' && '--debug' || '' }}
 
       - name: Login to Docker Hub
-        uses: docker/login-action@5e57cd118135c172c3672efd75eb46360885c0ef # ratchet:docker/login-action@v3
+        uses: docker/login-action@c94ce9fb468520275223c153574b00df6fe4bcc9 # ratchet:docker/login-action@v3
         with:
           username: ${{ env.DOCKER_USERNAME }}
           password: ${{ env.DOCKER_TOKEN }}
@@ -1359,7 +1348,7 @@ jobs:
           buildkitd-flags: ${{ vars.DOCKER_DEBUG == 'true' && '--debug' || '' }}
 
       - name: Login to Docker Hub
-        uses: docker/login-action@5e57cd118135c172c3672efd75eb46360885c0ef # ratchet:docker/login-action@v3
+        uses: docker/login-action@c94ce9fb468520275223c153574b00df6fe4bcc9 # ratchet:docker/login-action@v3
         with:
           username: ${{ env.DOCKER_USERNAME }}
           password: ${{ env.DOCKER_TOKEN }}
@@ -1422,7 +1411,7 @@ jobs:
         uses: docker/setup-buildx-action@8d2750c68a42422c14e847fe6c8ac0403b4cbd6f # ratchet:docker/setup-buildx-action@v3
 
       - name: Login to Docker Hub
-        uses: docker/login-action@5e57cd118135c172c3672efd75eb46360885c0ef # ratchet:docker/login-action@v3
+        uses: docker/login-action@c94ce9fb468520275223c153574b00df6fe4bcc9 # ratchet:docker/login-action@v3
         with:
           username: ${{ env.DOCKER_USERNAME }}
           password: ${{ env.DOCKER_TOKEN }}
@@ -1709,19 +1698,6 @@ jobs:
         with:
           persist-credentials: false
 
-      - name: Configure AWS credentials
-        uses: aws-actions/configure-aws-credentials@61815dcd50bd041e203e49132bacad1fd04d2708
-        with:
-          role-to-assume: ${{ secrets.AWS_OIDC_ROLE_ARN }}
-          aws-region: us-east-2
-
-      - name: Get AWS Secrets
-        uses: aws-actions/aws-secretsmanager-get-secrets@a9a7eb4e2f2871d30dc5b892576fde60a2ecc802
-        with:
-          secret-ids: |
-            MONITOR_DEPLOYMENTS_WEBHOOK, deploy/monitor-deployments-webhook
-          parse-json-secrets: true
-
       - name: Determine failed jobs
         id: failed-jobs
         shell: bash
@@ -1787,7 +1763,7 @@ jobs:
       - name: Send Slack notification
         uses: ./.github/actions/slack-notify
         with:
-          webhook-url: ${{ env.MONITOR_DEPLOYMENTS_WEBHOOK }}
+          webhook-url: ${{ secrets.MONITOR_DEPLOYMENTS_WEBHOOK }}
           failed-jobs: ${{ steps.failed-jobs.outputs.jobs }}
           title: "🚨 Deployment Workflow Failed"
           ref-name: ${{ github.ref_name }}

.github/workflows/docker-tag-beta.yml

@@ -24,7 +24,7 @@ jobs:
         uses: docker/setup-buildx-action@8d2750c68a42422c14e847fe6c8ac0403b4cbd6f # ratchet:docker/setup-buildx-action@v3
 
       - name: Login to Docker Hub
-        uses: docker/login-action@5e57cd118135c172c3672efd75eb46360885c0ef # ratchet:docker/login-action@v3
+        uses: docker/login-action@c94ce9fb468520275223c153574b00df6fe4bcc9 # ratchet:docker/login-action@v3
         with:
           username: ${{ secrets.DOCKER_USERNAME }}
           password: ${{ secrets.DOCKER_TOKEN }}

.github/workflows/docker-tag-latest.yml

@@ -24,7 +24,7 @@ jobs:
         uses: docker/setup-buildx-action@8d2750c68a42422c14e847fe6c8ac0403b4cbd6f # ratchet:docker/setup-buildx-action@v3
 
       - name: Login to Docker Hub
-        uses: docker/login-action@5e57cd118135c172c3672efd75eb46360885c0ef # ratchet:docker/login-action@v3
+        uses: docker/login-action@c94ce9fb468520275223c153574b00df6fe4bcc9 # ratchet:docker/login-action@v3
         with:
           username: ${{ secrets.DOCKER_USERNAME }}
           password: ${{ secrets.DOCKER_TOKEN }}

.github/workflows/nightly-scan-licenses.yml

@@ -33,7 +33,7 @@ jobs:
           persist-credentials: false
 
       - name: Set up Python
-        uses: actions/setup-python@83679a892e2d95755f2dac6acb0bfd1e9ac5d548 # ratchet:actions/setup-python@v6
+        uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # ratchet:actions/setup-python@v6
         with:
           python-version: '3.11'
           cache: 'pip'
@@ -97,7 +97,7 @@ jobs:
       uses: docker/setup-buildx-action@8d2750c68a42422c14e847fe6c8ac0403b4cbd6f # ratchet:docker/setup-buildx-action@v3
 
     - name: Login to Docker Hub
-      uses: docker/login-action@5e57cd118135c172c3672efd75eb46360885c0ef # ratchet:docker/login-action@v3
+      uses: docker/login-action@c94ce9fb468520275223c153574b00df6fe4bcc9 # ratchet:docker/login-action@v3
       with:
         username: ${{ secrets.DOCKER_USERNAME }}
         password: ${{ secrets.DOCKER_TOKEN }}

.github/workflows/pr-database-tests.yml

@@ -40,13 +40,16 @@ jobs:
 
       - name: Generate OpenAPI schema and Python client
         shell: bash
+        # TODO(Nik): https://linear.app/onyx-app/issue/ENG-1/update-test-infra-to-use-test-license
+        env:
+          LICENSE_ENFORCEMENT_ENABLED: "false"
         run: |
           ods openapi all
 
       # needed for pulling external images otherwise, we hit the "Unauthenticated users" limit
       # https://docs.docker.com/docker-hub/usage/
       - name: Login to Docker Hub
-        uses: docker/login-action@5e57cd118135c172c3672efd75eb46360885c0ef # ratchet:docker/login-action@v3
+        uses: docker/login-action@c94ce9fb468520275223c153574b00df6fe4bcc9 # ratchet:docker/login-action@v3
         with:
           username: ${{ secrets.DOCKER_USERNAME }}
           password: ${{ secrets.DOCKER_TOKEN }}

.github/workflows/pr-desktop-build.yml

@@ -45,12 +45,12 @@ jobs:
 
     steps:
       - name: Checkout code
-        uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd
         with:
           persist-credentials: false
 
       - name: Setup node
-        uses: actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020
+        uses: actions/setup-node@6044e13b5dc448c55e2357c09f80417699197238
         with:
           node-version: 24
           cache: "npm" # zizmor: ignore[cache-poisoning]
@@ -63,7 +63,7 @@ jobs:
           targets: ${{ matrix.target }}
 
       - name: Cache Cargo registry and build
-        uses: actions/cache@0057852bfaa89a56745cba8c7296529d2fc39830 # zizmor: ignore[cache-poisoning]
+        uses: actions/cache@cdf6c1fa76f9f475f3d7449005a359c84ca0f306 # zizmor: ignore[cache-poisoning]
         with:
           path: |
             ~/.cargo/bin/
@@ -105,7 +105,7 @@ jobs:
 
       - name: Upload build artifacts
         if: always()
-        uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02
+        uses: actions/upload-artifact@b7c566a772e6b6bfb58ed0dc250532a479d7789f
         with:
           name: desktop-build-${{ matrix.platform }}-${{ github.run_id }}
           path: |

.github/workflows/pr-external-dependency-unit-tests.yml

@@ -110,7 +110,7 @@ jobs:
       # otherwise, we hit the "Unauthenticated users" limit
       # https://docs.docker.com/docker-hub/usage/
       - name: Login to Docker Hub
-        uses: docker/login-action@5e57cd118135c172c3672efd75eb46360885c0ef # ratchet:docker/login-action@v3
+        uses: docker/login-action@c94ce9fb468520275223c153574b00df6fe4bcc9 # ratchet:docker/login-action@v3
         with:
           username: ${{ secrets.DOCKER_USERNAME }}
           password: ${{ secrets.DOCKER_TOKEN }}
@@ -118,6 +118,7 @@ jobs:
       - name: Create .env file for Docker Compose
         run: |
           cat <<EOF > deployment/docker_compose/.env
+          COMPOSE_PROFILES=s3-filestore
           CODE_INTERPRETER_BETA_ENABLED=true
           DISABLE_TELEMETRY=true
           EOF

.github/workflows/pr-integration-tests.yml

@@ -46,6 +46,7 @@ jobs:
     timeout-minutes: 45
     outputs:
       test-dirs: ${{ steps.set-matrix.outputs.test-dirs }}
+      editions: ${{ steps.set-editions.outputs.editions }}
     steps:
       - name: Checkout code
         uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # ratchet:actions/checkout@v6
@@ -56,7 +57,7 @@ jobs:
         id: set-matrix
         run: |
           # Find all leaf-level directories in both test directories
-          tests_dirs=$(find backend/tests/integration/tests -mindepth 1 -maxdepth 1 -type d ! -name "__pycache__" ! -name "mcp" -exec basename {} \; | sort)
+          tests_dirs=$(find backend/tests/integration/tests -mindepth 1 -maxdepth 1 -type d ! -name "__pycache__" ! -name "mcp" ! -name "no_vectordb" -exec basename {} \; | sort)
           connector_dirs=$(find backend/tests/integration/connector_job_tests -mindepth 1 -maxdepth 1 -type d ! -name "__pycache__" -exec basename {} \; | sort)
 
           # Create JSON array with directory info
@@ -72,6 +73,16 @@ jobs:
           all_dirs="[${all_dirs%,}]"
           echo "test-dirs=$all_dirs" >> $GITHUB_OUTPUT
 
+      - name: Determine editions to test
+        id: set-editions
+        run: |
+          # On PRs, only run EE tests. On merge_group and tags, run both EE and MIT.
+          if [ "${{ github.event_name }}" = "pull_request" ]; then
+            echo 'editions=["ee"]' >> $GITHUB_OUTPUT
+          else
+            echo 'editions=["ee","mit"]' >> $GITHUB_OUTPUT
+          fi
+
   build-backend-image:
     runs-on:
       [
@@ -109,7 +120,7 @@ jobs:
       # otherwise, we hit the "Unauthenticated users" limit
       # https://docs.docker.com/docker-hub/usage/
       - name: Login to Docker Hub
-        uses: docker/login-action@5e57cd118135c172c3672efd75eb46360885c0ef # ratchet:docker/login-action@v3
+        uses: docker/login-action@c94ce9fb468520275223c153574b00df6fe4bcc9 # ratchet:docker/login-action@v3
         with:
           username: ${{ secrets.DOCKER_USERNAME }}
           password: ${{ secrets.DOCKER_TOKEN }}
@@ -169,7 +180,7 @@ jobs:
       # otherwise, we hit the "Unauthenticated users" limit
       # https://docs.docker.com/docker-hub/usage/
       - name: Login to Docker Hub
-        uses: docker/login-action@5e57cd118135c172c3672efd75eb46360885c0ef # ratchet:docker/login-action@v3
+        uses: docker/login-action@c94ce9fb468520275223c153574b00df6fe4bcc9 # ratchet:docker/login-action@v3
         with:
           username: ${{ secrets.DOCKER_USERNAME }}
           password: ${{ secrets.DOCKER_TOKEN }}
@@ -214,7 +225,7 @@ jobs:
       # otherwise, we hit the "Unauthenticated users" limit
       # https://docs.docker.com/docker-hub/usage/
       - name: Login to Docker Hub
-        uses: docker/login-action@5e57cd118135c172c3672efd75eb46360885c0ef # ratchet:docker/login-action@v3
+        uses: docker/login-action@c94ce9fb468520275223c153574b00df6fe4bcc9 # ratchet:docker/login-action@v3
         with:
           username: ${{ secrets.DOCKER_USERNAME }}
           password: ${{ secrets.DOCKER_TOKEN }}
@@ -267,7 +278,7 @@ jobs:
     runs-on:
       - runs-on
       - runner=4cpu-linux-arm64
-      - ${{ format('run-id={0}-integration-tests-job-{1}', github.run_id, strategy['job-index']) }}
+      - ${{ format('run-id={0}-integration-tests-{1}-job-{2}', github.run_id, matrix.edition, strategy['job-index']) }}
       - extras=ecr-cache
     timeout-minutes: 45
 
@@ -275,6 +286,7 @@ jobs:
       fail-fast: false
       matrix:
         test-dir: ${{ fromJson(needs.discover-test-dirs.outputs.test-dirs) }}
+        edition: ${{ fromJson(needs.discover-test-dirs.outputs.editions) }}
 
     steps:
       - uses: runs-on/action@cd2b598b0515d39d78c38a02d529db87d2196d1e # ratchet:runs-on/action@v2
@@ -287,7 +299,7 @@ jobs:
       # otherwise, we hit the "Unauthenticated users" limit
       # https://docs.docker.com/docker-hub/usage/
       - name: Login to Docker Hub
-        uses: docker/login-action@5e57cd118135c172c3672efd75eb46360885c0ef # ratchet:docker/login-action@v3
+        uses: docker/login-action@c94ce9fb468520275223c153574b00df6fe4bcc9 # ratchet:docker/login-action@v3
         with:
           username: ${{ secrets.DOCKER_USERNAME }}
           password: ${{ secrets.DOCKER_TOKEN }}
@@ -298,9 +310,11 @@ jobs:
         env:
           ECR_CACHE: ${{ env.RUNS_ON_ECR_CACHE }}
           RUN_ID: ${{ github.run_id }}
+          EDITION: ${{ matrix.edition }}
         run: |
+          # Base config shared by both editions
           cat <<EOF > deployment/docker_compose/.env
-          ENABLE_PAID_ENTERPRISE_EDITION_FEATURES=true
+          COMPOSE_PROFILES=s3-filestore
           AUTH_TYPE=basic
           POSTGRES_POOL_PRE_PING=true
           POSTGRES_USE_NULL_POOL=true
@@ -309,11 +323,20 @@ jobs:
           ONYX_BACKEND_IMAGE=${ECR_CACHE}:integration-test-backend-test-${RUN_ID}
           ONYX_MODEL_SERVER_IMAGE=${ECR_CACHE}:integration-test-model-server-test-${RUN_ID}
           INTEGRATION_TESTS_MODE=true
-          CHECK_TTL_MANAGEMENT_TASK_FREQUENCY_IN_HOURS=0.001
-          AUTO_LLM_UPDATE_INTERVAL_SECONDS=10
           MCP_SERVER_ENABLED=true
+          AUTO_LLM_UPDATE_INTERVAL_SECONDS=10
+          EOF
+
+          # EE-only config
+          if [ "$EDITION" = "ee" ]; then
+            cat <<EOF >> deployment/docker_compose/.env
+          ENABLE_PAID_ENTERPRISE_EDITION_FEATURES=true
+          # TODO(Nik): https://linear.app/onyx-app/issue/ENG-1/update-test-infra-to-use-test-license
+          LICENSE_ENFORCEMENT_ENABLED=false
+          CHECK_TTL_MANAGEMENT_TASK_FREQUENCY_IN_HOURS=0.001
           USE_LIGHTWEIGHT_BACKGROUND_WORKER=false
           EOF
+          fi
 
       - name: Start Docker containers
         run: |
@@ -376,14 +399,14 @@ jobs:
           docker compose -f docker-compose.mock-it-services.yml \
             -p mock-it-services-stack up -d
 
-      - name: Run Integration Tests for ${{ matrix.test-dir.name }}
+      - name: Run Integration Tests (${{ matrix.edition }}) for ${{ matrix.test-dir.name }}
         uses: nick-fields/retry@ce71cc2ab81d554ebbe88c79ab5975992d79ba08 # ratchet:nick-fields/retry@v3
         with:
           timeout_minutes: 20
           max_attempts: 3
           retry_wait_seconds: 10
           command: |
-            echo "Running integration tests for ${{ matrix.test-dir.path }}..."
+            echo "Running ${{ matrix.edition }} integration tests for ${{ matrix.test-dir.path }}..."
             docker run --rm --network onyx_default \
               --name test-runner \
               -e POSTGRES_HOST=relational_db \
@@ -441,10 +464,143 @@ jobs:
         if: always()
         uses: actions/upload-artifact@b7c566a772e6b6bfb58ed0dc250532a479d7789f
         with:
-          name: docker-all-logs-${{ matrix.test-dir.name }}
+          name: docker-all-logs-${{ matrix.edition }}-${{ matrix.test-dir.name }}
           path: ${{ github.workspace }}/docker-compose.log
       # ------------------------------------------------------------
 
+  no-vectordb-tests:
+    needs: [build-backend-image, build-integration-image]
+    runs-on:
+      [
+        runs-on,
+        runner=4cpu-linux-arm64,
+        "run-id=${{ github.run_id }}-no-vectordb-tests",
+        "extras=ecr-cache",
+      ]
+    timeout-minutes: 45
+
+    steps:
+      - uses: runs-on/action@cd2b598b0515d39d78c38a02d529db87d2196d1e # ratchet:runs-on/action@v2
+      - name: Checkout code
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # ratchet:actions/checkout@v6
+        with:
+          persist-credentials: false
+
+      - name: Login to Docker Hub
+        uses: docker/login-action@c94ce9fb468520275223c153574b00df6fe4bcc9 # ratchet:docker/login-action@v3
+        with:
+          username: ${{ secrets.DOCKER_USERNAME }}
+          password: ${{ secrets.DOCKER_TOKEN }}
+
+      - name: Create .env file for no-vectordb Docker Compose
+        env:
+          ECR_CACHE: ${{ env.RUNS_ON_ECR_CACHE }}
+          RUN_ID: ${{ github.run_id }}
+        run: |
+          cat <<EOF > deployment/docker_compose/.env
+          COMPOSE_PROFILES=s3-filestore
+          ENABLE_PAID_ENTERPRISE_EDITION_FEATURES=true
+          LICENSE_ENFORCEMENT_ENABLED=false
+          AUTH_TYPE=basic
+          POSTGRES_POOL_PRE_PING=true
+          POSTGRES_USE_NULL_POOL=true
+          REQUIRE_EMAIL_VERIFICATION=false
+          DISABLE_TELEMETRY=true
+          DISABLE_VECTOR_DB=true
+          ONYX_BACKEND_IMAGE=${ECR_CACHE}:integration-test-backend-test-${RUN_ID}
+          INTEGRATION_TESTS_MODE=true
+          USE_LIGHTWEIGHT_BACKGROUND_WORKER=true
+          EOF
+
+      # Start only the services needed for no-vectordb mode (no Vespa, no model servers)
+      - name: Start Docker containers (no-vectordb)
+        run: |
+          cd deployment/docker_compose
+          docker compose -f docker-compose.yml -f docker-compose.no-vectordb.yml -f docker-compose.dev.yml up \
+            relational_db \
+            cache \
+            minio \
+            api_server \
+            background \
+            -d
+        id: start_docker_no_vectordb
+
+      - name: Wait for services to be ready
+        run: |
+          echo "Starting wait-for-service script (no-vectordb)..."
+          start_time=$(date +%s)
+          timeout=300
+          while true; do
+            current_time=$(date +%s)
+            elapsed_time=$((current_time - start_time))
+            if [ $elapsed_time -ge $timeout ]; then
+              echo "Timeout reached. Service did not become ready in $timeout seconds."
+              exit 1
+            fi
+            response=$(curl -s -o /dev/null -w "%{http_code}" http://localhost:8080/health || echo "curl_error")
+            if [ "$response" = "200" ]; then
+              echo "API server is ready!"
+              break
+            elif [ "$response" = "curl_error" ]; then
+              echo "Curl encountered an error; retrying..."
+            else
+              echo "Service not ready yet (HTTP $response). Retrying in 5 seconds..."
+            fi
+            sleep 5
+          done
+
+      - name: Run No-VectorDB Integration Tests
+        uses: nick-fields/retry@ce71cc2ab81d554ebbe88c79ab5975992d79ba08 # ratchet:nick-fields/retry@v3
+        with:
+          timeout_minutes: 20
+          max_attempts: 3
+          retry_wait_seconds: 10
+          command: |
+            echo "Running no-vectordb integration tests..."
+            docker run --rm --network onyx_default \
+              --name test-runner \
+              -e POSTGRES_HOST=relational_db \
+              -e POSTGRES_USER=postgres \
+              -e POSTGRES_PASSWORD=password \
+              -e POSTGRES_DB=postgres \
+              -e DB_READONLY_USER=db_readonly_user \
+              -e DB_READONLY_PASSWORD=password \
+              -e POSTGRES_POOL_PRE_PING=true \
+              -e POSTGRES_USE_NULL_POOL=true \
+              -e REDIS_HOST=cache \
+              -e API_SERVER_HOST=api_server \
+              -e OPENAI_API_KEY=${OPENAI_API_KEY} \
+              -e TEST_WEB_HOSTNAME=test-runner \
+              ${{ env.RUNS_ON_ECR_CACHE }}:integration-test-${{ github.run_id }} \
+              /app/tests/integration/tests/no_vectordb
+
+      - name: Dump API server logs (no-vectordb)
+        if: always()
+        run: |
+          cd deployment/docker_compose
+          docker compose -f docker-compose.yml -f docker-compose.no-vectordb.yml -f docker-compose.dev.yml \
+            logs --no-color api_server > $GITHUB_WORKSPACE/api_server_no_vectordb.log || true
+
+      - name: Dump all-container logs (no-vectordb)
+        if: always()
+        run: |
+          cd deployment/docker_compose
+          docker compose -f docker-compose.yml -f docker-compose.no-vectordb.yml -f docker-compose.dev.yml \
+            logs --no-color > $GITHUB_WORKSPACE/docker-compose-no-vectordb.log || true
+
+      - name: Upload logs (no-vectordb)
+        if: always()
+        uses: actions/upload-artifact@b7c566a772e6b6bfb58ed0dc250532a479d7789f
+        with:
+          name: docker-all-logs-no-vectordb
+          path: ${{ github.workspace }}/docker-compose-no-vectordb.log
+
+      - name: Stop Docker containers (no-vectordb)
+        if: always()
+        run: |
+          cd deployment/docker_compose
+          docker compose -f docker-compose.yml -f docker-compose.no-vectordb.yml -f docker-compose.dev.yml down -v
+
   multitenant-tests:
     needs:
       [build-backend-image, build-model-server-image, build-integration-image]
@@ -465,7 +621,7 @@ jobs:
           persist-credentials: false
 
       - name: Login to Docker Hub
-        uses: docker/login-action@5e57cd118135c172c3672efd75eb46360885c0ef # ratchet:docker/login-action@v3
+        uses: docker/login-action@c94ce9fb468520275223c153574b00df6fe4bcc9 # ratchet:docker/login-action@v3
         with:
           username: ${{ secrets.DOCKER_USERNAME }}
           password: ${{ secrets.DOCKER_TOKEN }}
@@ -477,6 +633,7 @@ jobs:
         run: |
           cd deployment/docker_compose
           ENABLE_PAID_ENTERPRISE_EDITION_FEATURES=true \
+          LICENSE_ENFORCEMENT_ENABLED=false \
           MULTI_TENANT=true \
           AUTH_TYPE=cloud \
           REQUIRE_EMAIL_VERIFICATION=false \
@@ -583,7 +740,7 @@ jobs:
     # NOTE: Github-hosted runners have about 20s faster queue times and are preferred here.
     runs-on: ubuntu-slim
     timeout-minutes: 45
-    needs: [integration-tests, multitenant-tests]
+    needs: [integration-tests, no-vectordb-tests, multitenant-tests]
     if: ${{ always() }}
     steps:
       - name: Check job status

.github/workflows/pr-jest-tests.yml

@@ -28,7 +28,7 @@ jobs:
           persist-credentials: false
 
       - name: Setup node
-        uses: actions/setup-node@395ad3262231945c25e8478fd5baf05154b1d79f # ratchet:actions/setup-node@v4
+        uses: actions/setup-node@6044e13b5dc448c55e2357c09f80417699197238 # ratchet:actions/setup-node@v4
         with:
           node-version: 22
           cache: "npm"

.github/workflows/pr-mit-integration-tests.yml

@@ -1,442 +0,0 @@
-name: Run MIT Integration Tests v2
-concurrency:
-  group: Run-MIT-Integration-Tests-${{ github.workflow }}-${{ github.head_ref || github.event.workflow_run.head_branch || github.run_id }}
-  cancel-in-progress: true
-
-on:
-  merge_group:
-    types: [checks_requested]
-  push:
-    tags:
-      - "v*.*.*"
-
-permissions:
-  contents: read
-
-env:
-  # Test Environment Variables
-  OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
-  SLACK_BOT_TOKEN: ${{ secrets.SLACK_BOT_TOKEN }}
-  EXA_API_KEY: ${{ secrets.EXA_API_KEY }}
-  CONFLUENCE_TEST_SPACE_URL: ${{ vars.CONFLUENCE_TEST_SPACE_URL }}
-  CONFLUENCE_USER_NAME: ${{ vars.CONFLUENCE_USER_NAME }}
-  CONFLUENCE_ACCESS_TOKEN: ${{ secrets.CONFLUENCE_ACCESS_TOKEN }}
-  CONFLUENCE_ACCESS_TOKEN_SCOPED: ${{ secrets.CONFLUENCE_ACCESS_TOKEN_SCOPED }}
-  JIRA_BASE_URL: ${{ secrets.JIRA_BASE_URL }}
-  JIRA_USER_EMAIL: ${{ secrets.JIRA_USER_EMAIL }}
-  JIRA_API_TOKEN: ${{ secrets.JIRA_API_TOKEN }}
-  JIRA_API_TOKEN_SCOPED: ${{ secrets.JIRA_API_TOKEN_SCOPED }}
-  PERM_SYNC_SHAREPOINT_CLIENT_ID: ${{ secrets.PERM_SYNC_SHAREPOINT_CLIENT_ID }}
-  PERM_SYNC_SHAREPOINT_PRIVATE_KEY: ${{ secrets.PERM_SYNC_SHAREPOINT_PRIVATE_KEY }}
-  PERM_SYNC_SHAREPOINT_CERTIFICATE_PASSWORD: ${{ secrets.PERM_SYNC_SHAREPOINT_CERTIFICATE_PASSWORD }}
-  PERM_SYNC_SHAREPOINT_DIRECTORY_ID: ${{ secrets.PERM_SYNC_SHAREPOINT_DIRECTORY_ID }}
-
-jobs:
-  discover-test-dirs:
-    # NOTE: Github-hosted runners have about 20s faster queue times and are preferred here.
-    runs-on: ubuntu-slim
-    timeout-minutes: 45
-    outputs:
-      test-dirs: ${{ steps.set-matrix.outputs.test-dirs }}
-    steps:
-      - name: Checkout code
-        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # ratchet:actions/checkout@v6
-        with:
-          persist-credentials: false
-
-      - name: Discover test directories
-        id: set-matrix
-        run: |
-          # Find all leaf-level directories in both test directories
-          tests_dirs=$(find backend/tests/integration/tests -mindepth 1 -maxdepth 1 -type d ! -name "__pycache__" ! -name "mcp" -exec basename {} \; | sort)
-          connector_dirs=$(find backend/tests/integration/connector_job_tests -mindepth 1 -maxdepth 1 -type d ! -name "__pycache__" -exec basename {} \; | sort)
-
-          # Create JSON array with directory info
-          all_dirs=""
-          for dir in $tests_dirs; do
-            all_dirs="$all_dirs{\"path\":\"tests/$dir\",\"name\":\"tests-$dir\"},"
-          done
-          for dir in $connector_dirs; do
-            all_dirs="$all_dirs{\"path\":\"connector_job_tests/$dir\",\"name\":\"connector-$dir\"},"
-          done
-
-          # Remove trailing comma and wrap in array
-          all_dirs="[${all_dirs%,}]"
-          echo "test-dirs=$all_dirs" >> $GITHUB_OUTPUT
-
-  build-backend-image:
-    runs-on:
-      [
-        runs-on,
-        runner=1cpu-linux-arm64,
-        "run-id=${{ github.run_id }}-build-backend-image",
-        "extras=ecr-cache",
-      ]
-    timeout-minutes: 45
-    steps:
-      - uses: runs-on/action@cd2b598b0515d39d78c38a02d529db87d2196d1e # ratchet:runs-on/action@v2
-      - name: Checkout code
-        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # ratchet:actions/checkout@v6
-        with:
-          persist-credentials: false
-
-      - name: Format branch name for cache
-        id: format-branch
-        env:
-          PR_NUMBER: ${{ github.event.pull_request.number }}
-          REF_NAME: ${{ github.ref_name }}
-        run: |
-          if [ -n "${PR_NUMBER}" ]; then
-            CACHE_SUFFIX="${PR_NUMBER}"
-          else
-            # shellcheck disable=SC2001
-            CACHE_SUFFIX=$(echo "${REF_NAME}" | sed 's/[^A-Za-z0-9._-]/-/g')
-          fi
-          echo "cache-suffix=${CACHE_SUFFIX}" >> $GITHUB_OUTPUT
-
-      - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@8d2750c68a42422c14e847fe6c8ac0403b4cbd6f # ratchet:docker/setup-buildx-action@v3
-
-      # needed for pulling Vespa, Redis, Postgres, and Minio images
-      # otherwise, we hit the "Unauthenticated users" limit
-      # https://docs.docker.com/docker-hub/usage/
-      - name: Login to Docker Hub
-        uses: docker/login-action@5e57cd118135c172c3672efd75eb46360885c0ef # ratchet:docker/login-action@v3
-        with:
-          username: ${{ secrets.DOCKER_USERNAME }}
-          password: ${{ secrets.DOCKER_TOKEN }}
-
-      - name: Build and push Backend Docker image
-        uses: docker/build-push-action@263435318d21b8e681c14492fe198d362a7d2c83 # ratchet:docker/build-push-action@v6
-        with:
-          context: ./backend
-          file: ./backend/Dockerfile
-          push: true
-          tags: ${{ env.RUNS_ON_ECR_CACHE }}:integration-test-backend-test-${{ github.run_id }}
-          cache-from: |
-            type=registry,ref=${{ env.RUNS_ON_ECR_CACHE }}:backend-cache-${{ github.event.pull_request.head.sha || github.sha }}
-            type=registry,ref=${{ env.RUNS_ON_ECR_CACHE }}:backend-cache-${{ steps.format-branch.outputs.cache-suffix }}
-            type=registry,ref=${{ env.RUNS_ON_ECR_CACHE }}:backend-cache
-            type=registry,ref=onyxdotapp/onyx-backend:latest
-          cache-to: |
-            type=registry,ref=${{ env.RUNS_ON_ECR_CACHE }}:backend-cache-${{ github.event.pull_request.head.sha || github.sha }},mode=max
-            type=registry,ref=${{ env.RUNS_ON_ECR_CACHE }}:backend-cache-${{ steps.format-branch.outputs.cache-suffix }},mode=max
-            type=registry,ref=${{ env.RUNS_ON_ECR_CACHE }}:backend-cache,mode=max
-          no-cache: ${{ vars.DOCKER_NO_CACHE == 'true' }}
-
-  build-model-server-image:
-    runs-on:
-      [
-        runs-on,
-        runner=1cpu-linux-arm64,
-        "run-id=${{ github.run_id }}-build-model-server-image",
-        "extras=ecr-cache",
-      ]
-    timeout-minutes: 45
-    steps:
-      - uses: runs-on/action@cd2b598b0515d39d78c38a02d529db87d2196d1e # ratchet:runs-on/action@v2
-      - name: Checkout code
-        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # ratchet:actions/checkout@v6
-        with:
-          persist-credentials: false
-
-      - name: Format branch name for cache
-        id: format-branch
-        env:
-          PR_NUMBER: ${{ github.event.pull_request.number }}
-          REF_NAME: ${{ github.ref_name }}
-        run: |
-          if [ -n "${PR_NUMBER}" ]; then
-            CACHE_SUFFIX="${PR_NUMBER}"
-          else
-            # shellcheck disable=SC2001
-            CACHE_SUFFIX=$(echo "${REF_NAME}" | sed 's/[^A-Za-z0-9._-]/-/g')
-          fi
-          echo "cache-suffix=${CACHE_SUFFIX}" >> $GITHUB_OUTPUT
-
-      - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@8d2750c68a42422c14e847fe6c8ac0403b4cbd6f # ratchet:docker/setup-buildx-action@v3
-
-      # needed for pulling Vespa, Redis, Postgres, and Minio images
-      # otherwise, we hit the "Unauthenticated users" limit
-      # https://docs.docker.com/docker-hub/usage/
-      - name: Login to Docker Hub
-        uses: docker/login-action@5e57cd118135c172c3672efd75eb46360885c0ef # ratchet:docker/login-action@v3
-        with:
-          username: ${{ secrets.DOCKER_USERNAME }}
-          password: ${{ secrets.DOCKER_TOKEN }}
-
-      - name: Build and push Model Server Docker image
-        uses: docker/build-push-action@263435318d21b8e681c14492fe198d362a7d2c83 # ratchet:docker/build-push-action@v6
-        with:
-          context: ./backend
-          file: ./backend/Dockerfile.model_server
-          push: true
-          tags: ${{ env.RUNS_ON_ECR_CACHE }}:integration-test-model-server-test-${{ github.run_id }}
-          cache-from: |
-            type=registry,ref=${{ env.RUNS_ON_ECR_CACHE }}:model-server-cache-${{ github.event.pull_request.head.sha || github.sha }}
-            type=registry,ref=${{ env.RUNS_ON_ECR_CACHE }}:model-server-cache-${{ steps.format-branch.outputs.cache-suffix }}
-            type=registry,ref=${{ env.RUNS_ON_ECR_CACHE }}:model-server-cache
-            type=registry,ref=onyxdotapp/onyx-model-server:latest
-          cache-to: |
-            type=registry,ref=${{ env.RUNS_ON_ECR_CACHE }}:model-server-cache-${{ github.event.pull_request.head.sha || github.sha }},mode=max
-            type=registry,ref=${{ env.RUNS_ON_ECR_CACHE }}:model-server-cache-${{ steps.format-branch.outputs.cache-suffix }},mode=max
-            type=registry,ref=${{ env.RUNS_ON_ECR_CACHE }}:model-server-cache,mode=max
-
-  build-integration-image:
-    runs-on:
-      [
-        runs-on,
-        runner=2cpu-linux-arm64,
-        "run-id=${{ github.run_id }}-build-integration-image",
-        "extras=ecr-cache",
-      ]
-    timeout-minutes: 45
-    steps:
-      - uses: runs-on/action@cd2b598b0515d39d78c38a02d529db87d2196d1e # ratchet:runs-on/action@v2
-      - name: Checkout code
-        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # ratchet:actions/checkout@v6
-        with:
-          persist-credentials: false
-
-      - name: Format branch name for cache
-        id: format-branch
-        env:
-          PR_NUMBER: ${{ github.event.pull_request.number }}
-          REF_NAME: ${{ github.ref_name }}
-        run: |
-          if [ -n "${PR_NUMBER}" ]; then
-            CACHE_SUFFIX="${PR_NUMBER}"
-          else
-            # shellcheck disable=SC2001
-            CACHE_SUFFIX=$(echo "${REF_NAME}" | sed 's/[^A-Za-z0-9._-]/-/g')
-          fi
-          echo "cache-suffix=${CACHE_SUFFIX}" >> $GITHUB_OUTPUT
-
-      - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@8d2750c68a42422c14e847fe6c8ac0403b4cbd6f # ratchet:docker/setup-buildx-action@v3
-
-      # needed for pulling openapitools/openapi-generator-cli
-      # otherwise, we hit the "Unauthenticated users" limit
-      # https://docs.docker.com/docker-hub/usage/
-      - name: Login to Docker Hub
-        uses: docker/login-action@5e57cd118135c172c3672efd75eb46360885c0ef # ratchet:docker/login-action@v3
-        with:
-          username: ${{ secrets.DOCKER_USERNAME }}
-          password: ${{ secrets.DOCKER_TOKEN }}
-
-      - name: Build and push integration test image with Docker Bake
-        env:
-          INTEGRATION_REPOSITORY: ${{ env.RUNS_ON_ECR_CACHE }}
-          TAG: integration-test-${{ github.run_id }}
-          CACHE_SUFFIX: ${{ steps.format-branch.outputs.cache-suffix }}
-          HEAD_SHA: ${{ github.event.pull_request.head.sha || github.sha }}
-        run: |
-          docker buildx bake --push \
-            --set backend.cache-from=type=registry,ref=${RUNS_ON_ECR_CACHE}:backend-cache-${HEAD_SHA} \
-            --set backend.cache-from=type=registry,ref=${RUNS_ON_ECR_CACHE}:backend-cache-${CACHE_SUFFIX} \
-            --set backend.cache-from=type=registry,ref=${RUNS_ON_ECR_CACHE}:backend-cache \
-            --set backend.cache-from=type=registry,ref=onyxdotapp/onyx-backend:latest \
-            --set backend.cache-to=type=registry,ref=${RUNS_ON_ECR_CACHE}:backend-cache-${HEAD_SHA},mode=max \
-            --set backend.cache-to=type=registry,ref=${RUNS_ON_ECR_CACHE}:backend-cache-${CACHE_SUFFIX},mode=max \
-            --set backend.cache-to=type=registry,ref=${RUNS_ON_ECR_CACHE}:backend-cache,mode=max \
-            --set integration.cache-from=type=registry,ref=${RUNS_ON_ECR_CACHE}:integration-cache-${HEAD_SHA} \
-            --set integration.cache-from=type=registry,ref=${RUNS_ON_ECR_CACHE}:integration-cache-${CACHE_SUFFIX} \
-            --set integration.cache-from=type=registry,ref=${RUNS_ON_ECR_CACHE}:integration-cache \
-            --set integration.cache-to=type=registry,ref=${RUNS_ON_ECR_CACHE}:integration-cache-${HEAD_SHA},mode=max \
-            --set integration.cache-to=type=registry,ref=${RUNS_ON_ECR_CACHE}:integration-cache-${CACHE_SUFFIX},mode=max \
-            --set integration.cache-to=type=registry,ref=${RUNS_ON_ECR_CACHE}:integration-cache,mode=max \
-            integration
-
-  integration-tests-mit:
-    needs:
-      [
-        discover-test-dirs,
-        build-backend-image,
-        build-model-server-image,
-        build-integration-image,
-      ]
-    runs-on:
-      - runs-on
-      - runner=4cpu-linux-arm64
-      - ${{ format('run-id={0}-integration-tests-mit-job-{1}', github.run_id, strategy['job-index']) }}
-      - extras=ecr-cache
-    timeout-minutes: 45
-
-    strategy:
-      fail-fast: false
-      matrix:
-        test-dir: ${{ fromJson(needs.discover-test-dirs.outputs.test-dirs) }}
-
-    steps:
-      - uses: runs-on/action@cd2b598b0515d39d78c38a02d529db87d2196d1e # ratchet:runs-on/action@v2
-      - name: Checkout code
-        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # ratchet:actions/checkout@v6
-        with:
-          persist-credentials: false
-
-      # needed for pulling Vespa, Redis, Postgres, and Minio images
-      # otherwise, we hit the "Unauthenticated users" limit
-      # https://docs.docker.com/docker-hub/usage/
-      - name: Login to Docker Hub
-        uses: docker/login-action@5e57cd118135c172c3672efd75eb46360885c0ef # ratchet:docker/login-action@v3
-        with:
-          username: ${{ secrets.DOCKER_USERNAME }}
-          password: ${{ secrets.DOCKER_TOKEN }}
-
-      # NOTE: Use pre-ping/null pool to reduce flakiness due to dropped connections
-      # NOTE: don't need web server for integration tests
-      - name: Create .env file for Docker Compose
-        env:
-          ECR_CACHE: ${{ env.RUNS_ON_ECR_CACHE }}
-          RUN_ID: ${{ github.run_id }}
-        run: |
-          cat <<EOF > deployment/docker_compose/.env
-          AUTH_TYPE=basic
-          POSTGRES_POOL_PRE_PING=true
-          POSTGRES_USE_NULL_POOL=true
-          REQUIRE_EMAIL_VERIFICATION=false
-          DISABLE_TELEMETRY=true
-          ONYX_BACKEND_IMAGE=${ECR_CACHE}:integration-test-backend-test-${RUN_ID}
-          ONYX_MODEL_SERVER_IMAGE=${ECR_CACHE}:integration-test-model-server-test-${RUN_ID}
-          INTEGRATION_TESTS_MODE=true
-          MCP_SERVER_ENABLED=true
-          AUTO_LLM_UPDATE_INTERVAL_SECONDS=10
-          EOF
-
-      - name: Start Docker containers
-        run: |
-          cd deployment/docker_compose
-          docker compose -f docker-compose.yml -f docker-compose.dev.yml up \
-            relational_db \
-            index \
-            cache \
-            minio \
-            api_server \
-            inference_model_server \
-            indexing_model_server \
-            background \
-            -d
-        id: start_docker
-
-      - name: Wait for services to be ready
-        run: |
-          echo "Starting wait-for-service script..."
-
-          wait_for_service() {
-            local url=$1
-            local label=$2
-            local timeout=${3:-300}  # default 5 minutes
-            local start_time
-            start_time=$(date +%s)
-
-            while true; do
-              local current_time
-              current_time=$(date +%s)
-              local elapsed_time=$((current_time - start_time))
-
-              if [ $elapsed_time -ge $timeout ]; then
-                echo "Timeout reached. ${label} did not become ready in $timeout seconds."
-                exit 1
-              fi
-
-              local response
-              response=$(curl -s -o /dev/null -w "%{http_code}" "$url" || echo "curl_error")
-
-              if [ "$response" = "200" ]; then
-                echo "${label} is ready!"
-                break
-              elif [ "$response" = "curl_error" ]; then
-                echo "Curl encountered an error while checking ${label}. Retrying in 5 seconds..."
-              else
-                echo "${label} not ready yet (HTTP status $response). Retrying in 5 seconds..."
-              fi
-
-              sleep 5
-            done
-          }
-
-          wait_for_service "http://localhost:8080/health" "API server"
-          echo "Finished waiting for services."
-
-      - name: Start Mock Services
-        run: |
-          cd backend/tests/integration/mock_services
-          docker compose -f docker-compose.mock-it-services.yml \
-            -p mock-it-services-stack up -d
-
-      # NOTE: Use pre-ping/null to reduce flakiness due to dropped connections
-      - name: Run Integration Tests for ${{ matrix.test-dir.name }}
-        uses: nick-fields/retry@ce71cc2ab81d554ebbe88c79ab5975992d79ba08 # ratchet:nick-fields/retry@v3
-        with:
-          timeout_minutes: 20
-          max_attempts: 3
-          retry_wait_seconds: 10
-          command: |
-            echo "Running integration tests for ${{ matrix.test-dir.path }}..."
-            docker run --rm --network onyx_default \
-              --name test-runner \
-              -e POSTGRES_HOST=relational_db \
-              -e POSTGRES_USER=postgres \
-              -e POSTGRES_PASSWORD=password \
-              -e POSTGRES_DB=postgres \
-              -e DB_READONLY_USER=db_readonly_user \
-              -e DB_READONLY_PASSWORD=password \
-              -e POSTGRES_POOL_PRE_PING=true \
-              -e POSTGRES_USE_NULL_POOL=true \
-              -e VESPA_HOST=index \
-              -e REDIS_HOST=cache \
-              -e API_SERVER_HOST=api_server \
-              -e OPENAI_API_KEY=${OPENAI_API_KEY} \
-              -e EXA_API_KEY=${EXA_API_KEY} \
-              -e SLACK_BOT_TOKEN=${SLACK_BOT_TOKEN} \
-              -e CONFLUENCE_TEST_SPACE_URL=${CONFLUENCE_TEST_SPACE_URL} \
-              -e CONFLUENCE_USER_NAME=${CONFLUENCE_USER_NAME} \
-              -e CONFLUENCE_ACCESS_TOKEN=${CONFLUENCE_ACCESS_TOKEN} \
-              -e CONFLUENCE_ACCESS_TOKEN_SCOPED=${CONFLUENCE_ACCESS_TOKEN_SCOPED} \
-              -e JIRA_BASE_URL=${JIRA_BASE_URL} \
-              -e JIRA_USER_EMAIL=${JIRA_USER_EMAIL} \
-              -e JIRA_API_TOKEN=${JIRA_API_TOKEN} \
-              -e JIRA_API_TOKEN_SCOPED=${JIRA_API_TOKEN_SCOPED} \
-              -e PERM_SYNC_SHAREPOINT_CLIENT_ID=${PERM_SYNC_SHAREPOINT_CLIENT_ID} \
-              -e PERM_SYNC_SHAREPOINT_PRIVATE_KEY="${PERM_SYNC_SHAREPOINT_PRIVATE_KEY}" \
-              -e PERM_SYNC_SHAREPOINT_CERTIFICATE_PASSWORD=${PERM_SYNC_SHAREPOINT_CERTIFICATE_PASSWORD} \
-              -e PERM_SYNC_SHAREPOINT_DIRECTORY_ID=${PERM_SYNC_SHAREPOINT_DIRECTORY_ID} \
-              -e TEST_WEB_HOSTNAME=test-runner \
-              -e MOCK_CONNECTOR_SERVER_HOST=mock_connector_server \
-              -e MOCK_CONNECTOR_SERVER_PORT=8001 \
-              ${{ env.RUNS_ON_ECR_CACHE }}:integration-test-${{ github.run_id }} \
-              /app/tests/integration/${{ matrix.test-dir.path }}
-
-      # ------------------------------------------------------------
-      # Always gather logs BEFORE "down":
-      - name: Dump API server logs
-        if: always()
-        run: |
-          cd deployment/docker_compose
-          docker compose logs --no-color api_server > $GITHUB_WORKSPACE/api_server.log || true
-
-      - name: Dump all-container logs (optional)
-        if: always()
-        run: |
-          cd deployment/docker_compose
-          docker compose logs --no-color > $GITHUB_WORKSPACE/docker-compose.log || true
-
-      - name: Upload logs
-        if: always()
-        uses: actions/upload-artifact@b7c566a772e6b6bfb58ed0dc250532a479d7789f
-        with:
-          name: docker-all-logs-${{ matrix.test-dir.name }}
-          path: ${{ github.workspace }}/docker-compose.log
-      # ------------------------------------------------------------
-
-  required:
-    # NOTE: Github-hosted runners have about 20s faster queue times and are preferred here.
-    runs-on: ubuntu-slim
-    timeout-minutes: 45
-    needs: [integration-tests-mit]
-    if: ${{ always() }}
-    steps:
-      - name: Check job status
-        if: ${{ contains(needs.*.result, 'failure') || contains(needs.*.result, 'cancelled') || contains(needs.*.result, 'skipped') }}
-        run: exit 1

.github/workflows/pr-playwright-tests.yml

@@ -52,6 +52,9 @@ env:
   MCP_SERVER_PUBLIC_HOST: host.docker.internal
   MCP_SERVER_PUBLIC_URL: http://host.docker.internal:8004/mcp
 
+  # Visual regression S3 bucket (shared across all jobs)
+  PLAYWRIGHT_S3_BUCKET: onyx-playwright-artifacts
+
 jobs:
   build-web-image:
     runs-on:
@@ -90,7 +93,7 @@ jobs:
       # needed for pulling external images otherwise, we hit the "Unauthenticated users" limit
       # https://docs.docker.com/docker-hub/usage/
       - name: Login to Docker Hub
-        uses: docker/login-action@5e57cd118135c172c3672efd75eb46360885c0ef # ratchet:docker/login-action@v3
+        uses: docker/login-action@c94ce9fb468520275223c153574b00df6fe4bcc9 # ratchet:docker/login-action@v3
         with:
           username: ${{ secrets.DOCKER_USERNAME }}
           password: ${{ secrets.DOCKER_TOKEN }}
@@ -151,7 +154,7 @@ jobs:
       # needed for pulling external images otherwise, we hit the "Unauthenticated users" limit
       # https://docs.docker.com/docker-hub/usage/
       - name: Login to Docker Hub
-        uses: docker/login-action@5e57cd118135c172c3672efd75eb46360885c0ef # ratchet:docker/login-action@v3
+        uses: docker/login-action@c94ce9fb468520275223c153574b00df6fe4bcc9 # ratchet:docker/login-action@v3
         with:
           username: ${{ secrets.DOCKER_USERNAME }}
           password: ${{ secrets.DOCKER_TOKEN }}
@@ -212,7 +215,7 @@ jobs:
       # needed for pulling external images otherwise, we hit the "Unauthenticated users" limit
       # https://docs.docker.com/docker-hub/usage/
       - name: Login to Docker Hub
-        uses: docker/login-action@5e57cd118135c172c3672efd75eb46360885c0ef # ratchet:docker/login-action@v3
+        uses: docker/login-action@c94ce9fb468520275223c153574b00df6fe4bcc9 # ratchet:docker/login-action@v3
         with:
           username: ${{ secrets.DOCKER_USERNAME }}
           password: ${{ secrets.DOCKER_TOKEN }}
@@ -239,6 +242,9 @@ jobs:
   playwright-tests:
     needs: [build-web-image, build-backend-image, build-model-server-image]
     name: Playwright Tests (${{ matrix.project }})
+    permissions:
+      id-token: write # Required for OIDC-based AWS credential exchange (S3 access)
+      contents: read
     runs-on:
       - runs-on
       - runner=8cpu-linux-arm64
@@ -249,7 +255,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        project: [admin, no-auth, exclusive]
+        project: [admin, exclusive]
     steps:
       - uses: runs-on/action@cd2b598b0515d39d78c38a02d529db87d2196d1e # ratchet:runs-on/action@v2
 
@@ -259,7 +265,7 @@ jobs:
           persist-credentials: false
 
       - name: Setup node
-        uses: actions/setup-node@395ad3262231945c25e8478fd5baf05154b1d79f # ratchet:actions/setup-node@v4
+        uses: actions/setup-node@6044e13b5dc448c55e2357c09f80417699197238 # ratchet:actions/setup-node@v4
         with:
           node-version: 22
           cache: "npm"
@@ -289,7 +295,10 @@ jobs:
           RUN_ID: ${{ github.run_id }}
         run: |
           cat <<EOF > deployment/docker_compose/.env
+          COMPOSE_PROFILES=s3-filestore
           ENABLE_PAID_ENTERPRISE_EDITION_FEATURES=true
+          # TODO(Nik): https://linear.app/onyx-app/issue/ENG-1/update-test-infra-to-use-test-license
+          LICENSE_ENFORCEMENT_ENABLED=false
           AUTH_TYPE=basic
           GEN_AI_API_KEY=${OPENAI_API_KEY_VALUE}
           EXA_API_KEY=${EXA_API_KEY_VALUE}
@@ -299,15 +308,12 @@ jobs:
           ONYX_MODEL_SERVER_IMAGE=${ECR_CACHE}:playwright-test-model-server-${RUN_ID}
           ONYX_WEB_SERVER_IMAGE=${ECR_CACHE}:playwright-test-web-${RUN_ID}
           EOF
-          if [ "${{ matrix.project }}" = "no-auth" ]; then
-            echo "PLAYWRIGHT_FORCE_EMPTY_LLM_PROVIDERS=true" >> deployment/docker_compose/.env
-          fi
 
       # needed for pulling Vespa, Redis, Postgres, and Minio images
       # otherwise, we hit the "Unauthenticated users" limit
       # https://docs.docker.com/docker-hub/usage/
       - name: Login to Docker Hub
-        uses: docker/login-action@5e57cd118135c172c3672efd75eb46360885c0ef # ratchet:docker/login-action@v3
+        uses: docker/login-action@c94ce9fb468520275223c153574b00df6fe4bcc9 # ratchet:docker/login-action@v3
         with:
           username: ${{ secrets.DOCKER_USERNAME }}
           password: ${{ secrets.DOCKER_TOKEN }}
@@ -428,11 +434,6 @@ jobs:
         env:
           PROJECT: ${{ matrix.project }}
         run: |
-          # Create test-results directory to ensure it exists for artifact upload
-          mkdir -p test-results
-          if [ "${PROJECT}" = "no-auth" ]; then
-            export PLAYWRIGHT_FORCE_EMPTY_LLM_PROVIDERS=true
-          fi
           npx playwright test --project ${PROJECT}
 
       - uses: actions/upload-artifact@b7c566a772e6b6bfb58ed0dc250532a479d7789f
@@ -440,9 +441,134 @@ jobs:
         with:
           # Includes test results and trace.zip files
           name: playwright-test-results-${{ matrix.project }}-${{ github.run_id }}
-          path: ./web/test-results/
+          path: ./web/output/playwright/
           retention-days: 30
 
+      - name: Upload screenshots
+        uses: actions/upload-artifact@b7c566a772e6b6bfb58ed0dc250532a479d7789f
+        if: always()
+        with:
+          name: playwright-screenshots-${{ matrix.project }}-${{ github.run_id }}
+          path: ./web/output/screenshots/
+          retention-days: 30
+
+      # --- Visual Regression Diff ---
+      - name: Configure AWS credentials
+        if: always()
+        uses: aws-actions/configure-aws-credentials@61815dcd50bd041e203e49132bacad1fd04d2708
+        with:
+          role-to-assume: ${{ secrets.AWS_OIDC_ROLE_ARN }}
+          aws-region: us-east-2
+
+      - name: Install the latest version of uv
+        if: always()
+        uses: astral-sh/setup-uv@61cb8a9741eeb8a550a1b8544337180c0fc8476b # ratchet:astral-sh/setup-uv@v7
+        with:
+          enable-cache: false
+          version: "0.9.9"
+
+      - name: Determine baseline revision
+        if: always()
+        id: baseline-rev
+        env:
+          EVENT_NAME: ${{ github.event_name }}
+          BASE_REF: ${{ github.event.pull_request.base.ref }}
+          MERGE_GROUP_BASE_REF: ${{ github.event.merge_group.base_ref }}
+          GH_REF: ${{ github.ref }}
+          REF_NAME: ${{ github.ref_name }}
+        run: |
+          if [ "${EVENT_NAME}" = "pull_request" ]; then
+            # PRs compare against the base branch (e.g. main, release/2.5)
+            echo "rev=${BASE_REF}" >> "$GITHUB_OUTPUT"
+          elif [ "${EVENT_NAME}" = "merge_group" ]; then
+            # Merge queue compares against the target branch (e.g. refs/heads/main -> main)
+            echo "rev=${MERGE_GROUP_BASE_REF#refs/heads/}" >> "$GITHUB_OUTPUT"
+          elif [[ "${GH_REF}" == refs/tags/* ]]; then
+            # Tag builds compare against the tag name
+            echo "rev=${REF_NAME}" >> "$GITHUB_OUTPUT"
+          else
+            # Push builds (main, release/*) compare against the branch name
+            echo "rev=${REF_NAME}" >> "$GITHUB_OUTPUT"
+          fi
+
+      - name: Generate screenshot diff report
+        if: always()
+        env:
+          PROJECT: ${{ matrix.project }}
+          PLAYWRIGHT_S3_BUCKET: ${{ env.PLAYWRIGHT_S3_BUCKET }}
+          BASELINE_REV: ${{ steps.baseline-rev.outputs.rev }}
+        run: |
+          uv run --no-sync --with onyx-devtools ods screenshot-diff compare \
+            --project "${PROJECT}" \
+            --rev "${BASELINE_REV}"
+
+      - name: Upload visual diff report to S3
+        if: always()
+        env:
+          PROJECT: ${{ matrix.project }}
+          PR_NUMBER: ${{ github.event.pull_request.number }}
+          RUN_ID: ${{ github.run_id }}
+        run: |
+          SUMMARY_FILE="web/output/screenshot-diff/${PROJECT}/summary.json"
+          if [ ! -f "${SUMMARY_FILE}" ]; then
+            echo "No summary file found — skipping S3 upload."
+            exit 0
+          fi
+
+          HAS_DIFF=$(jq -r '.has_differences' "${SUMMARY_FILE}")
+          if [ "${HAS_DIFF}" != "true" ]; then
+            echo "No visual differences for ${PROJECT} — skipping S3 upload."
+            exit 0
+          fi
+
+          aws s3 sync "web/output/screenshot-diff/${PROJECT}/" \
+            "s3://${PLAYWRIGHT_S3_BUCKET}/reports/pr-${PR_NUMBER}/${RUN_ID}/${PROJECT}/"
+
+      - name: Upload visual diff summary
+        uses: actions/upload-artifact@b7c566a772e6b6bfb58ed0dc250532a479d7789f
+        if: always()
+        with:
+          name: screenshot-diff-summary-${{ matrix.project }}
+          path: ./web/output/screenshot-diff/${{ matrix.project }}/summary.json
+          if-no-files-found: ignore
+          retention-days: 5
+
+      - name: Upload visual diff report artifact
+        uses: actions/upload-artifact@b7c566a772e6b6bfb58ed0dc250532a479d7789f
+        if: always()
+        with:
+          name: screenshot-diff-report-${{ matrix.project }}-${{ github.run_id }}
+          path: ./web/output/screenshot-diff/${{ matrix.project }}/
+          if-no-files-found: ignore
+          retention-days: 30
+
+      - name: Update S3 baselines
+        if: >-
+          success() && (
+            github.ref == 'refs/heads/main' ||
+            startsWith(github.ref, 'refs/heads/release/') ||
+            startsWith(github.ref, 'refs/tags/v') ||
+            (
+              github.event_name == 'merge_group' && (
+                github.event.merge_group.base_ref == 'refs/heads/main' ||
+                startsWith(github.event.merge_group.base_ref, 'refs/heads/release/')
+              )
+            )
+          )
+        env:
+          PROJECT: ${{ matrix.project }}
+          PLAYWRIGHT_S3_BUCKET: ${{ env.PLAYWRIGHT_S3_BUCKET }}
+          BASELINE_REV: ${{ steps.baseline-rev.outputs.rev }}
+        run: |
+          if [ -d "web/output/screenshots/" ] && [ "$(ls -A web/output/screenshots/)" ]; then
+            uv run --no-sync --with onyx-devtools ods screenshot-diff upload-baselines \
+              --project "${PROJECT}" \
+              --rev "${BASELINE_REV}" \
+              --delete
+          else
+            echo "No screenshots to upload for ${PROJECT} — skipping baseline update."
+          fi
+
       # save before stopping the containers so the logs can be captured
       - name: Save Docker logs
         if: success() || failure()
@@ -460,6 +586,95 @@ jobs:
           name: docker-logs-${{ matrix.project }}-${{ github.run_id }}
           path: ${{ github.workspace }}/docker-compose.log
 
+  # Post a single combined visual regression comment after all matrix jobs finish
+  visual-regression-comment:
+    needs: [playwright-tests]
+    if: always() && github.event_name == 'pull_request'
+    runs-on: ubuntu-slim
+    timeout-minutes: 5
+    permissions:
+      pull-requests: write
+    steps:
+      - name: Download visual diff summaries
+        uses: actions/download-artifact@95815c38cf2ff2164869cbab79da8d1f422bc89e # ratchet:actions/download-artifact@v4
+        with:
+          pattern: screenshot-diff-summary-*
+          path: summaries/
+
+      - name: Post combined PR comment
+        env:
+          GH_TOKEN: ${{ github.token }}
+          PR_NUMBER: ${{ github.event.pull_request.number }}
+          RUN_ID: ${{ github.run_id }}
+          REPO: ${{ github.repository }}
+          S3_BUCKET: ${{ env.PLAYWRIGHT_S3_BUCKET }}
+        run: |
+          MARKER="<!-- visual-regression-report -->"
+
+          # Build the markdown table from all summary files
+          TABLE_HEADER="| Project | Changed | Added | Removed | Unchanged | Report |"
+          TABLE_DIVIDER="|---------|---------|-------|---------|-----------|--------|"
+          TABLE_ROWS=""
+          HAS_ANY_SUMMARY=false
+
+          for SUMMARY_DIR in summaries/screenshot-diff-summary-*/; do
+            SUMMARY_FILE="${SUMMARY_DIR}summary.json"
+            if [ ! -f "${SUMMARY_FILE}" ]; then
+              continue
+            fi
+
+            HAS_ANY_SUMMARY=true
+            PROJECT=$(jq -r '.project' "${SUMMARY_FILE}")
+            CHANGED=$(jq -r '.changed' "${SUMMARY_FILE}")
+            ADDED=$(jq -r '.added' "${SUMMARY_FILE}")
+            REMOVED=$(jq -r '.removed' "${SUMMARY_FILE}")
+            UNCHANGED=$(jq -r '.unchanged' "${SUMMARY_FILE}")
+            TOTAL=$(jq -r '.total' "${SUMMARY_FILE}")
+            HAS_DIFF=$(jq -r '.has_differences' "${SUMMARY_FILE}")
+
+            if [ "${TOTAL}" = "0" ]; then
+              REPORT_LINK="_No screenshots_"
+            elif [ "${HAS_DIFF}" = "true" ]; then
+              REPORT_URL="https://${S3_BUCKET}.s3.us-east-2.amazonaws.com/reports/pr-${PR_NUMBER}/${RUN_ID}/${PROJECT}/index.html"
+              REPORT_LINK="[View Report](${REPORT_URL})"
+            else
+              REPORT_LINK="✅ No changes"
+            fi
+
+            TABLE_ROWS="${TABLE_ROWS}| \`${PROJECT}\` | ${CHANGED} | ${ADDED} | ${REMOVED} | ${UNCHANGED} | ${REPORT_LINK} |\n"
+          done
+
+          if [ "${HAS_ANY_SUMMARY}" = "false" ]; then
+            echo "No visual diff summaries found — skipping PR comment."
+            exit 0
+          fi
+
+          BODY=$(printf '%s\n' \
+            "${MARKER}" \
+            "### 🖼️ Visual Regression Report" \
+            "" \
+            "${TABLE_HEADER}" \
+            "${TABLE_DIVIDER}" \
+            "$(printf '%b' "${TABLE_ROWS}")")
+
+          # Upsert: find existing comment with the marker, or create a new one
+          EXISTING_COMMENT_ID=$(gh api \
+            "repos/${REPO}/issues/${PR_NUMBER}/comments" \
+            --jq ".[] | select(.body | startswith(\"${MARKER}\")) | .id" \
+            2>/dev/null | head -1)
+
+          if [ -n "${EXISTING_COMMENT_ID}" ]; then
+            gh api \
+              --method PATCH \
+              "repos/${REPO}/issues/comments/${EXISTING_COMMENT_ID}" \
+              -f body="${BODY}"
+          else
+            gh api \
+              --method POST \
+              "repos/${REPO}/issues/${PR_NUMBER}/comments" \
+              -f body="${BODY}"
+          fi
+
   playwright-required:
     # NOTE: Github-hosted runners have about 20s faster queue times and are preferred here.
     runs-on: ubuntu-slim
@@ -470,48 +685,3 @@ jobs:
       - name: Check job status
         if: ${{ contains(needs.*.result, 'failure') || contains(needs.*.result, 'cancelled') || contains(needs.*.result, 'skipped') }}
         run: exit 1
-
-# NOTE: Chromatic UI diff testing is currently disabled.
-# We are using Playwright for local and CI testing without visual regression checks.
-# Chromatic may be reintroduced in the future for UI diff testing if needed.
-
-# chromatic-tests:
-#   name: Chromatic Tests
-
-#   needs: playwright-tests
-#   runs-on:
-#     [
-#       runs-on,
-#       runner=32cpu-linux-x64,
-#       disk=large,
-#       "run-id=${{ github.run_id }}",
-#     ]
-#   steps:
-#     - name: Checkout code
-#       uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # ratchet:actions/checkout@v6
-#       with:
-#         fetch-depth: 0
-
-#     - name: Setup node
-#       uses: actions/setup-node@395ad3262231945c25e8478fd5baf05154b1d79f # ratchet:actions/setup-node@v4
-#       with:
-#         node-version: 22
-
-#     - name: Install node dependencies
-#       working-directory: ./web
-#       run: npm ci
-
-#     - name: Download Playwright test results
-#       uses: actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093 # ratchet:actions/download-artifact@v4
-#       with:
-#         name: test-results
-#         path: ./web/test-results
-
-#     - name: Run Chromatic
-#       uses: chromaui/action@latest
-#       with:
-#         playwright: true
-#         projectToken: ${{ secrets.CHROMATIC_PROJECT_TOKEN }}
-#         workingDir: ./web
-#       env:
-#         CHROMATIC_ARCHIVE_LOCATION: ./test-results

.github/workflows/pr-python-checks.yml

@@ -42,6 +42,9 @@ jobs:
 
       - name: Generate OpenAPI schema and Python client
         shell: bash
+        # TODO(Nik): https://linear.app/onyx-app/issue/ENG-1/update-test-infra-to-use-test-license
+        env:
+          LICENSE_ENFORCEMENT_ENABLED: "false"
         run: |
           ods openapi all
 

.github/workflows/pr-python-model-tests.yml

@@ -64,7 +64,7 @@ jobs:
           echo "cache-suffix=${CACHE_SUFFIX}" >> $GITHUB_OUTPUT
 
       - name: Login to Docker Hub
-        uses: docker/login-action@5e57cd118135c172c3672efd75eb46360885c0ef
+        uses: docker/login-action@c94ce9fb468520275223c153574b00df6fe4bcc9
         with:
           username: ${{ secrets.DOCKER_USERNAME }}
           password: ${{ secrets.DOCKER_TOKEN }}

.github/workflows/pr-python-tests.yml

@@ -27,6 +27,8 @@ jobs:
       PYTHONPATH: ./backend
       REDIS_CLOUD_PYTEST_PASSWORD: ${{ secrets.REDIS_CLOUD_PYTEST_PASSWORD }}
       DISABLE_TELEMETRY: "true"
+      # TODO(Nik): https://linear.app/onyx-app/issue/ENG-1/update-test-infra-to-use-test-license
+      LICENSE_ENFORCEMENT_ENABLED: "false"
 
     steps:
     - uses: runs-on/action@cd2b598b0515d39d78c38a02d529db87d2196d1e # ratchet:runs-on/action@v2

.github/workflows/pr-quality-checks.yml

@@ -24,13 +24,13 @@ jobs:
         with:
           fetch-depth: 0
           persist-credentials: false
-      - uses: actions/setup-python@83679a892e2d95755f2dac6acb0bfd1e9ac5d548 # ratchet:actions/setup-python@v6
+      - uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # ratchet:actions/setup-python@v6
         with:
           python-version: "3.11"
       - name: Setup Terraform
         uses: hashicorp/setup-terraform@b9cd54a3c349d3f38e8881555d616ced269862dd # ratchet:hashicorp/setup-terraform@v3
       - name: Setup node
-        uses: actions/setup-node@395ad3262231945c25e8478fd5baf05154b1d79f # ratchet:actions/setup-node@v6
+        uses: actions/setup-node@6044e13b5dc448c55e2357c09f80417699197238 # ratchet:actions/setup-node@v6
         with: # zizmor: ignore[cache-poisoning]
           node-version: 22
           cache: "npm"

.github/workflows/preview.yml

@@ -0,0 +1,73 @@
+name: Preview Deployment
+env:
+  VERCEL_ORG_ID: ${{ secrets.VERCEL_ORG_ID }}
+  VERCEL_PROJECT_ID: ${{ secrets.VERCEL_PROJECT_ID }}
+  VERCEL_CLI: vercel@50.14.1
+on:
+  push:
+    branches-ignore:
+      - main
+    paths:
+      - "web/**"
+permissions:
+  contents: read
+  pull-requests: write
+jobs:
+  Deploy-Preview:
+    runs-on: ubuntu-latest
+    timeout-minutes: 30
+    steps:
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd
+        with:
+          persist-credentials: false
+
+      - name: Setup node
+        uses: actions/setup-node@6044e13b5dc448c55e2357c09f80417699197238 # ratchet:actions/setup-node@v4
+        with:
+          node-version: 22
+          cache: "npm"
+          cache-dependency-path: ./web/package-lock.json
+
+      - name: Pull Vercel Environment Information
+        run: npx --yes ${{ env.VERCEL_CLI }} pull --yes --environment=preview --token=${{ secrets.VERCEL_TOKEN }}
+
+      - name: Build Project Artifacts
+        run: npx --yes ${{ env.VERCEL_CLI }} build --token=${{ secrets.VERCEL_TOKEN }}
+
+      - name: Deploy Project Artifacts to Vercel
+        id: deploy
+        run: |
+          DEPLOYMENT_URL=$(npx --yes ${{ env.VERCEL_CLI }} deploy --prebuilt --token=${{ secrets.VERCEL_TOKEN }})
+          echo "url=$DEPLOYMENT_URL" >> "$GITHUB_OUTPUT"
+
+      - name: Update PR comment with deployment URL
+        if: always() && steps.deploy.outputs.url
+        env:
+          GH_TOKEN: ${{ github.token }}
+          DEPLOYMENT_URL: ${{ steps.deploy.outputs.url }}
+        run: |
+          # Find the PR for this branch
+          PR_NUMBER=$(gh pr list --head "$GITHUB_REF_NAME" --json number --jq '.[0].number')
+          if [ -z "$PR_NUMBER" ]; then
+            echo "No open PR found for branch $GITHUB_REF_NAME, skipping comment."
+            exit 0
+          fi
+
+          COMMENT_MARKER="<!-- preview-deployment -->"
+          COMMENT_BODY="$COMMENT_MARKER
+          **Preview Deployment**
+
+          | Status | Preview | Commit | Updated |
+          | --- | --- | --- | --- |
+          | ✅ |  $DEPLOYMENT_URL | \`${GITHUB_SHA::7}\` | $(date -u '+%Y-%m-%d %H:%M:%S UTC') |"
+
+          # Find existing comment by marker
+          EXISTING_COMMENT_ID=$(gh api "repos/$GITHUB_REPOSITORY/issues/$PR_NUMBER/comments" \
+            --jq ".[] | select(.body | startswith(\"$COMMENT_MARKER\")) | .id" | head -1)
+
+          if [ -n "$EXISTING_COMMENT_ID" ]; then
+            gh api "repos/$GITHUB_REPOSITORY/issues/comments/$EXISTING_COMMENT_ID" \
+              --method PATCH --field body="$COMMENT_BODY"
+          else
+            gh pr comment "$PR_NUMBER" --body "$COMMENT_BODY"
+          fi

.github/workflows/sandbox-deployment.yml

@@ -0,0 +1,290 @@
+name: Build and Push Sandbox Image on Tag
+
+on:
+  push:
+    tags:
+      - "experimental-cc4a.*"
+
+# Restrictive defaults; jobs declare what they need.
+permissions: {}
+
+jobs:
+  check-sandbox-changes:
+    runs-on: ubuntu-slim
+    timeout-minutes: 10
+    permissions:
+      contents: read
+    outputs:
+      sandbox-changed: ${{ steps.check.outputs.sandbox-changed }}
+      new-version: ${{ steps.version.outputs.new-version }}
+    steps:
+      - name: Checkout
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # ratchet:actions/checkout@v6
+        with:
+          persist-credentials: false
+          fetch-depth: 0
+
+      - name: Check for sandbox-relevant file changes
+        id: check
+        run: |
+          # Get the previous tag to diff against
+          CURRENT_TAG="${GITHUB_REF_NAME}"
+          PREVIOUS_TAG=$(git tag --sort=-creatordate | grep '^experimental-cc4a\.' | grep -v "^${CURRENT_TAG}$" | head -n 1)
+
+          if [ -z "$PREVIOUS_TAG" ]; then
+            echo "No previous experimental-cc4a tag found, building unconditionally"
+            echo "sandbox-changed=true" >> "$GITHUB_OUTPUT"
+            exit 0
+          fi
+
+          echo "Comparing ${PREVIOUS_TAG}..${CURRENT_TAG}"
+
+          # Check if any sandbox-relevant files changed
+          SANDBOX_PATHS=(
+            "backend/onyx/server/features/build/sandbox/"
+          )
+
+          CHANGED=false
+          for path in "${SANDBOX_PATHS[@]}"; do
+            if git diff --name-only "${PREVIOUS_TAG}..${CURRENT_TAG}" -- "$path" | grep -q .; then
+              echo "Changes detected in: $path"
+              CHANGED=true
+              break
+            fi
+          done
+
+          echo "sandbox-changed=$CHANGED" >> "$GITHUB_OUTPUT"
+
+      - name: Determine new sandbox version
+        id: version
+        if: steps.check.outputs.sandbox-changed == 'true'
+        run: |
+          # Query Docker Hub for the latest versioned tag
+          LATEST_TAG=$(curl -s "https://hub.docker.com/v2/repositories/onyxdotapp/sandbox/tags?page_size=100" \
+            | jq -r '.results[].name' \
+            | grep -E '^v[0-9]+\.[0-9]+\.[0-9]+$' \
+            | sort -V \
+            | tail -n 1)
+
+          if [ -z "$LATEST_TAG" ]; then
+            echo "No existing version tags found on Docker Hub, starting at 0.1.1"
+            NEW_VERSION="0.1.1"
+          else
+            CURRENT_VERSION="${LATEST_TAG#v}"
+            echo "Latest version on Docker Hub: $CURRENT_VERSION"
+
+            # Increment patch version
+            MAJOR=$(echo "$CURRENT_VERSION" | cut -d. -f1)
+            MINOR=$(echo "$CURRENT_VERSION" | cut -d. -f2)
+            PATCH=$(echo "$CURRENT_VERSION" | cut -d. -f3)
+            NEW_PATCH=$((PATCH + 1))
+            NEW_VERSION="${MAJOR}.${MINOR}.${NEW_PATCH}"
+          fi
+
+          echo "New version: $NEW_VERSION"
+          echo "new-version=$NEW_VERSION" >> "$GITHUB_OUTPUT"
+
+  build-sandbox-amd64:
+    needs: check-sandbox-changes
+    if: needs.check-sandbox-changes.outputs.sandbox-changed == 'true'
+    runs-on:
+      - runs-on
+      - runner=4cpu-linux-x64
+      - run-id=${{ github.run_id }}-sandbox-amd64
+      - extras=ecr-cache
+    timeout-minutes: 90
+    environment: release
+    permissions:
+      contents: read
+      id-token: write
+    outputs:
+      digest: ${{ steps.build.outputs.digest }}
+    env:
+      REGISTRY_IMAGE: onyxdotapp/sandbox
+    steps:
+      - uses: runs-on/action@cd2b598b0515d39d78c38a02d529db87d2196d1e # ratchet:runs-on/action@v2
+
+      - name: Checkout
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # ratchet:actions/checkout@v6
+        with:
+          persist-credentials: false
+
+      - name: Configure AWS credentials
+        uses: aws-actions/configure-aws-credentials@61815dcd50bd041e203e49132bacad1fd04d2708
+        with:
+          role-to-assume: ${{ secrets.AWS_OIDC_ROLE_ARN }}
+          aws-region: us-east-2
+
+      - name: Get AWS Secrets
+        uses: aws-actions/aws-secretsmanager-get-secrets@a9a7eb4e2f2871d30dc5b892576fde60a2ecc802
+        with:
+          secret-ids: |
+            DOCKER_USERNAME, deploy/docker-username
+            DOCKER_TOKEN, deploy/docker-token
+          parse-json-secrets: true
+
+      - name: Docker meta
+        id: meta
+        uses: docker/metadata-action@c299e40c65443455700f0fdfc63efafe5b349051 # ratchet:docker/metadata-action@v5
+        with:
+          images: ${{ env.REGISTRY_IMAGE }}
+          flavor: |
+            latest=false
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@8d2750c68a42422c14e847fe6c8ac0403b4cbd6f # ratchet:docker/setup-buildx-action@v3
+
+      - name: Login to Docker Hub
+        uses: docker/login-action@c94ce9fb468520275223c153574b00df6fe4bcc9 # ratchet:docker/login-action@v3
+        with:
+          username: ${{ env.DOCKER_USERNAME }}
+          password: ${{ env.DOCKER_TOKEN }}
+
+      - name: Build and push AMD64
+        id: build
+        uses: docker/build-push-action@263435318d21b8e681c14492fe198d362a7d2c83 # ratchet:docker/build-push-action@v6
+        with:
+          context: ./backend/onyx/server/features/build/sandbox/kubernetes/docker
+          file: ./backend/onyx/server/features/build/sandbox/kubernetes/docker/Dockerfile
+          platforms: linux/amd64
+          labels: ${{ steps.meta.outputs.labels }}
+          cache-from: |
+            type=registry,ref=${{ env.REGISTRY_IMAGE }}:latest
+          cache-to: |
+            type=inline
+          outputs: type=image,name=${{ env.REGISTRY_IMAGE }},push-by-digest=true,name-canonical=true,push=true
+
+  build-sandbox-arm64:
+    needs: check-sandbox-changes
+    if: needs.check-sandbox-changes.outputs.sandbox-changed == 'true'
+    runs-on:
+      - runs-on
+      - runner=4cpu-linux-arm64
+      - run-id=${{ github.run_id }}-sandbox-arm64
+      - extras=ecr-cache
+    timeout-minutes: 90
+    environment: release
+    permissions:
+      contents: read
+      id-token: write
+    outputs:
+      digest: ${{ steps.build.outputs.digest }}
+    env:
+      REGISTRY_IMAGE: onyxdotapp/sandbox
+    steps:
+      - uses: runs-on/action@cd2b598b0515d39d78c38a02d529db87d2196d1e # ratchet:runs-on/action@v2
+
+      - name: Checkout
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # ratchet:actions/checkout@v6
+        with:
+          persist-credentials: false
+
+      - name: Configure AWS credentials
+        uses: aws-actions/configure-aws-credentials@61815dcd50bd041e203e49132bacad1fd04d2708
+        with:
+          role-to-assume: ${{ secrets.AWS_OIDC_ROLE_ARN }}
+          aws-region: us-east-2
+
+      - name: Get AWS Secrets
+        uses: aws-actions/aws-secretsmanager-get-secrets@a9a7eb4e2f2871d30dc5b892576fde60a2ecc802
+        with:
+          secret-ids: |
+            DOCKER_USERNAME, deploy/docker-username
+            DOCKER_TOKEN, deploy/docker-token
+          parse-json-secrets: true
+
+      - name: Docker meta
+        id: meta
+        uses: docker/metadata-action@c299e40c65443455700f0fdfc63efafe5b349051 # ratchet:docker/metadata-action@v5
+        with:
+          images: ${{ env.REGISTRY_IMAGE }}
+          flavor: |
+            latest=false
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@8d2750c68a42422c14e847fe6c8ac0403b4cbd6f # ratchet:docker/setup-buildx-action@v3
+
+      - name: Login to Docker Hub
+        uses: docker/login-action@c94ce9fb468520275223c153574b00df6fe4bcc9 # ratchet:docker/login-action@v3
+        with:
+          username: ${{ env.DOCKER_USERNAME }}
+          password: ${{ env.DOCKER_TOKEN }}
+
+      - name: Build and push ARM64
+        id: build
+        uses: docker/build-push-action@263435318d21b8e681c14492fe198d362a7d2c83 # ratchet:docker/build-push-action@v6
+        with:
+          context: ./backend/onyx/server/features/build/sandbox/kubernetes/docker
+          file: ./backend/onyx/server/features/build/sandbox/kubernetes/docker/Dockerfile
+          platforms: linux/arm64
+          labels: ${{ steps.meta.outputs.labels }}
+          cache-from: |
+            type=registry,ref=${{ env.REGISTRY_IMAGE }}:latest
+          cache-to: |
+            type=inline
+          outputs: type=image,name=${{ env.REGISTRY_IMAGE }},push-by-digest=true,name-canonical=true,push=true
+
+  merge-sandbox:
+    needs:
+      - check-sandbox-changes
+      - build-sandbox-amd64
+      - build-sandbox-arm64
+    runs-on:
+      - runs-on
+      - runner=2cpu-linux-x64
+      - run-id=${{ github.run_id }}-merge-sandbox
+      - extras=ecr-cache
+    timeout-minutes: 30
+    environment: release
+    permissions:
+      id-token: write
+    env:
+      REGISTRY_IMAGE: onyxdotapp/sandbox
+    steps:
+      - uses: runs-on/action@cd2b598b0515d39d78c38a02d529db87d2196d1e # ratchet:runs-on/action@v2
+
+      - name: Configure AWS credentials
+        uses: aws-actions/configure-aws-credentials@61815dcd50bd041e203e49132bacad1fd04d2708
+        with:
+          role-to-assume: ${{ secrets.AWS_OIDC_ROLE_ARN }}
+          aws-region: us-east-2
+
+      - name: Get AWS Secrets
+        uses: aws-actions/aws-secretsmanager-get-secrets@a9a7eb4e2f2871d30dc5b892576fde60a2ecc802
+        with:
+          secret-ids: |
+            DOCKER_USERNAME, deploy/docker-username
+            DOCKER_TOKEN, deploy/docker-token
+          parse-json-secrets: true
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@8d2750c68a42422c14e847fe6c8ac0403b4cbd6f # ratchet:docker/setup-buildx-action@v3
+
+      - name: Login to Docker Hub
+        uses: docker/login-action@c94ce9fb468520275223c153574b00df6fe4bcc9 # ratchet:docker/login-action@v3
+        with:
+          username: ${{ env.DOCKER_USERNAME }}
+          password: ${{ env.DOCKER_TOKEN }}
+
+      - name: Docker meta
+        id: meta
+        uses: docker/metadata-action@c299e40c65443455700f0fdfc63efafe5b349051 # ratchet:docker/metadata-action@v5
+        with:
+          images: ${{ env.REGISTRY_IMAGE }}
+          flavor: |
+            latest=false
+          tags: |
+            type=raw,value=v${{ needs.check-sandbox-changes.outputs.new-version }}
+            type=raw,value=latest
+
+      - name: Create and push manifest
+        env:
+          IMAGE_REPO: ${{ env.REGISTRY_IMAGE }}
+          AMD64_DIGEST: ${{ needs.build-sandbox-amd64.outputs.digest }}
+          ARM64_DIGEST: ${{ needs.build-sandbox-arm64.outputs.digest }}
+          META_TAGS: ${{ steps.meta.outputs.tags }}
+        run: |
+          IMAGES="${IMAGE_REPO}@${AMD64_DIGEST} ${IMAGE_REPO}@${ARM64_DIGEST}"
+          docker buildx imagetools create \
+            $(printf '%s\n' "${META_TAGS}" | xargs -I {} echo -t {}) \
+            $IMAGES

.gitignore

@@ -6,6 +6,7 @@
 !/.vscode/tasks.template.jsonc
 .zed
 .cursor
+!/.cursor/mcp.json
 
 # macos
 .DS_store
@@ -40,10 +41,6 @@ settings.json
 /backend/tests/regression/answer_quality/search_test_config.yaml
 *.egg-info
 
-# Claude
-AGENTS.md
-CLAUDE.md
-
 # Local .terraform directories
 **/.terraform/*
 

.vscode/launch.json

@@ -246,7 +246,7 @@
         "--loglevel=INFO",
         "--hostname=light@%n",
         "-Q",
-        "vespa_metadata_sync,connector_deletion,doc_permissions_upsert,index_attempt_cleanup"
+        "vespa_metadata_sync,connector_deletion,doc_permissions_upsert,index_attempt_cleanup,opensearch_migration"
       ],
       "presentation": {
         "group": "2"
@@ -275,7 +275,7 @@
         "--loglevel=INFO",
         "--hostname=background@%n",
         "-Q",
-        "vespa_metadata_sync,connector_deletion,doc_permissions_upsert,checkpoint_cleanup,index_attempt_cleanup,docprocessing,connector_doc_fetching,user_files_indexing,connector_pruning,connector_doc_permissions_sync,connector_external_group_sync,csv_generation,kg_processing,monitoring,user_file_processing,user_file_project_sync,user_file_delete"
+        "vespa_metadata_sync,connector_deletion,doc_permissions_upsert,checkpoint_cleanup,index_attempt_cleanup,docprocessing,connector_doc_fetching,connector_pruning,connector_doc_permissions_sync,connector_external_group_sync,csv_generation,kg_processing,monitoring,user_file_processing,user_file_project_sync,user_file_delete,opensearch_migration"
       ],
       "presentation": {
         "group": "2"
@@ -419,7 +419,7 @@
         "--loglevel=INFO",
         "--hostname=docfetching@%n",
         "-Q",
-        "connector_doc_fetching,user_files_indexing"
+        "connector_doc_fetching"
       ],
       "presentation": {
         "group": "2"

AGENTS.md

@@ -1,26 +1,25 @@
-# CLAUDE.md
+# PROJECT KNOWLEDGE BASE
 
-This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
+This file provides guidance to AI agents when working with code in this repository.
 
 ## KEY NOTES
 
 - If you run into any missing python dependency errors, try running your command with `source .venv/bin/activate` \
-to assume the python venv.
+  to assume the python venv.
 - To make tests work, check the `.env` file at the root of the project to find an OpenAI key.
 - If using `playwright` to explore the frontend, you can usually log in with username `a@example.com` and password
-`a`. The app can be accessed at `http://localhost:3000`.
+  `a`. The app can be accessed at `http://localhost:3000`.
 - You should assume that all Onyx services are running. To verify, you can check the `backend/log` directory to
-make sure we see logs coming out from the relevant service.
+  make sure we see logs coming out from the relevant service.
 - To connect to the Postgres database, use: `docker exec -it onyx-relational_db-1 psql -U postgres -c "<SQL>"`
 - When making calls to the backend, always go through the frontend. E.g. make a call to `http://localhost:3000/api/persona` not `http://localhost:8080/api/persona`
 - Put ALL db operations under the `backend/onyx/db` / `backend/ee/onyx/db` directories. Don't run queries
-outside of those directories.
+  outside of those directories.
 
 ## Project Overview
 
 **Onyx** (formerly Danswer) is an open-source Gen-AI and Enterprise Search platform that connects to company documents, apps, and people. It features a modular architecture with both Community Edition (MIT licensed) and Enterprise Edition offerings.
 
-
 ### Background Workers (Celery)
 
 Onyx uses Celery for asynchronous task processing with multiple specialized workers:
@@ -92,6 +91,7 @@ Onyx uses Celery for asynchronous task processing with multiple specialized work
 Onyx supports two deployment modes for background workers, controlled by the `USE_LIGHTWEIGHT_BACKGROUND_WORKER` environment variable:
 
 **Lightweight Mode** (default, `USE_LIGHTWEIGHT_BACKGROUND_WORKER=true`):
+
 - Runs a single consolidated `background` worker that handles all background tasks:
   - Light worker tasks (Vespa operations, permissions sync, deletion)
   - Document processing (indexing pipeline)
@@ -105,12 +105,14 @@ Onyx supports two deployment modes for background workers, controlled by the `US
 - Default concurrency: 20 threads (increased to handle combined workload)
 
 **Standard Mode** (`USE_LIGHTWEIGHT_BACKGROUND_WORKER=false`):
+
 - Runs separate specialized workers as documented above (light, docprocessing, docfetching, heavy, kg_processing, monitoring, user_file_processing)
 - Better isolation and scalability
 - Can scale individual workers independently based on workload
 - Suitable for production deployments with higher load
 
 The deployment mode affects:
+
 - **Backend**: Worker processes spawned by supervisord or dev scripts
 - **Helm**: Which Kubernetes deployments are created
 - **Dev Environment**: Which workers `dev_run_background_jobs.py` spawns
@@ -119,18 +121,18 @@ The deployment mode affects:
 
 - **Thread-based Workers**: All workers use thread pools (not processes) for stability
 - **Tenant Awareness**: Multi-tenant support with per-tenant task isolation. There is a
-middleware layer that automatically finds the appropriate tenant ID when sending tasks
-via Celery Beat.
+  middleware layer that automatically finds the appropriate tenant ID when sending tasks
+  via Celery Beat.
 - **Task Prioritization**: High, Medium, Low priority queues
 - **Monitoring**: Built-in heartbeat and liveness checking
 - **Failure Handling**: Automatic retry and failure recovery mechanisms
 - **Redis Coordination**: Inter-process communication via Redis
 - **PostgreSQL State**: Task state and metadata stored in PostgreSQL
 
-
 #### Important Notes
 
-**Defining Tasks**: 
+**Defining Tasks**:
+
 - Always use `@shared_task` rather than `@celery_app`
 - Put tasks under `background/celery/tasks/` or `ee/background/celery/tasks`
 
@@ -142,7 +144,12 @@ function.
 If you make any updates to a celery worker and you want to test these changes, you will need
 to ask me to restart the celery worker. There is no auto-restart on code-change mechanism.
 
+**Task Time Limits**:
+Since all tasks are executed in thread pools, the time limit features of Celery are silently 
+disabled and won't work. Timeout logic must be implemented within the task itself.
+
 ### Code Quality
+
 ```bash
 # Install and run pre-commit hooks
 pre-commit install
@@ -154,6 +161,7 @@ NOTE: Always make sure everything is strictly typed (both in Python and Typescri
 ## Architecture Overview
 
 ### Technology Stack
+
 - **Backend**: Python 3.11, FastAPI, SQLAlchemy, Alembic, Celery
 - **Frontend**: Next.js 15+, React 18, TypeScript, Tailwind CSS
 - **Database**: PostgreSQL with Redis caching
@@ -435,6 +443,7 @@ function ContactForm() {
 **Reason:** Our custom color system uses CSS variables that automatically handle dark mode and maintain design consistency across the app. Standard Tailwind colors bypass this system.
 
 **Available color categories:**
+
 - **Text:** `text-01` through `text-05`, `text-inverted-XX`
 - **Backgrounds:** `background-neutral-XX`, `background-tint-XX` (and inverted variants)
 - **Borders:** `border-01` through `border-05`, `border-inverted-XX`
@@ -467,6 +476,7 @@ function ContactForm() {
 ## Database & Migrations
 
 ### Running Migrations
+
 ```bash
 # Standard migrations
 alembic upgrade head
@@ -476,6 +486,7 @@ alembic -n schema_private upgrade head
 ```
 
 ### Creating Migrations
+
 ```bash
 # Create migration
 alembic revision -m "description"
@@ -488,13 +499,14 @@ Write the migration manually and place it in the file that alembic creates when
 
 ## Testing Strategy
 
-First, you must activate the virtual environment with `source .venv/bin/activate`. 
+First, you must activate the virtual environment with `source .venv/bin/activate`.
 
 There are 4 main types of tests within Onyx:
 
 ### Unit Tests
+
 These should not assume any Onyx/external services are available to be called.
-Interactions with the outside world should be mocked using `unittest.mock`. Generally, only 
+Interactions with the outside world should be mocked using `unittest.mock`. Generally, only
 write these for complex, isolated modules e.g. `citation_processing.py`.
 
 To run them:
@@ -504,13 +516,14 @@ pytest -xv backend/tests/unit
 ```
 
 ### External Dependency Unit Tests
-These tests assume that all external dependencies of Onyx are available and callable (e.g. Postgres, Redis, 
+
+These tests assume that all external dependencies of Onyx are available and callable (e.g. Postgres, Redis,
 MinIO/S3, Vespa are running + OpenAI can be called + any request to the internet is fine + etc.).
 
 However, the actual Onyx containers are not running and with these tests we call the function to test directly.
-We can also mock components/calls at will. 
+We can also mock components/calls at will.
 
-The goal with these tests are to minimize mocking while giving some flexibility to mock things that are flakey, 
+The goal with these tests are to minimize mocking while giving some flexibility to mock things that are flakey,
 need strictly controlled behavior, or need to have their internal behavior validated (e.g. verify a function is called
 with certain args, something that would be impossible with proper integration tests).
 
@@ -523,15 +536,16 @@ python -m dotenv -f .vscode/.env run -- pytest backend/tests/external_dependency
 ```
 
 ### Integration Tests
-Standard integration tests. Every test in `backend/tests/integration` runs against a real Onyx deployment. We cannot 
-mock anything in these tests. Prefer writing integration tests (or External Dependency Unit Tests if mocking/internal 
+
+Standard integration tests. Every test in `backend/tests/integration` runs against a real Onyx deployment. We cannot
+mock anything in these tests. Prefer writing integration tests (or External Dependency Unit Tests if mocking/internal
 verification is necessary) over any other type of test.
 
 Tests are parallelized at a directory level.
 
-When writing integration tests, make sure to check the root `conftest.py` for useful fixtures + the `backend/tests/integration/common_utils` directory for utilities. Prefer (if one exists), calling the appropriate Manager 
+When writing integration tests, make sure to check the root `conftest.py` for useful fixtures + the `backend/tests/integration/common_utils` directory for utilities. Prefer (if one exists), calling the appropriate Manager
 class in the utils over directly calling the APIs with a library like `requests`. Prefer using fixtures rather than
-calling the utilities directly (e.g. do NOT create admin users with 
+calling the utilities directly (e.g. do NOT create admin users with
 `admin_user = UserManager.create(name="admin_user")`, instead use the `admin_user` fixture).
 
 A great example of this type of test is `backend/tests/integration/dev_apis/test_simple_chat_api.py`.
@@ -543,8 +557,9 @@ python -m dotenv -f .vscode/.env run -- pytest backend/tests/integration
 ```
 
 ### Playwright (E2E) Tests
-These tests are an even more complete version of the Integration Tests mentioned above. Has all services of Onyx 
-running, *including* the Web Server.
+
+These tests are an even more complete version of the Integration Tests mentioned above. Has all services of Onyx
+running, _including_ the Web Server.
 
 Use these tests for anything that requires significant frontend <-> backend coordination.
 
@@ -556,13 +571,11 @@ To run them:
 npx playwright test <TEST_NAME>
 ```
 
-
 ## Logs
 
 When (1) writing integration tests or (2) doing live tests (e.g. curl / playwright) you can get access
 to logs via the `backend/log/<service_name>_debug.log` file. All Onyx services (api_server, web_server, celery_X)
-will be tailing their logs to this file. 
-
+will be tailing their logs to this file.
 
 ## Security Considerations
 
@@ -581,6 +594,7 @@ will be tailing their logs to this file.
 - Custom prompts and agent actions
 
 ## Creating a Plan
+
 When creating a plan in the `plans` directory, make sure to include at least these elements:
 
 **Issues to Address**
@@ -593,10 +607,10 @@ Things you come across in your research that are important to the implementation
 How you are going to make the changes happen. High level approach.
 
 **Tests**
-What unit (use rarely), external dependency unit, integration, and playwright tests you plan to write to 
+What unit (use rarely), external dependency unit, integration, and playwright tests you plan to write to
 verify the correct behavior. Don't overtest. Usually, a given change only needs one type of test.
 
-Do NOT include these: *Timeline*, *Rollback plan*
+Do NOT include these: _Timeline_, _Rollback plan_
 
 This is a minimal list - feel free to include more. Do NOT write code as part of your plan.
 Keep it high level. You can reference certain files or functions though.

AGENTS.md.template

@@ -1,599 +0,0 @@
-# AGENTS.md
-
-This file provides guidance to AI agents when working with code in this repository.
-
-## KEY NOTES
-
-- If you run into any missing python dependency errors, try running your command with `source .venv/bin/activate` \
-to assume the python venv.
-- To make tests work, check the `.env` file at the root of the project to find an OpenAI key.
-- If using `playwright` to explore the frontend, you can usually log in with username `a@example.com` and password
-`a`. The app can be accessed at `http://localhost:3000`.
-- You should assume that all Onyx services are running. To verify, you can check the `backend/log` directory to
-make sure we see logs coming out from the relevant service.
-- To connect to the Postgres database, use: `docker exec -it onyx-relational_db-1 psql -U postgres -c "<SQL>"`
-- When making calls to the backend, always go through the frontend. E.g. make a call to `http://localhost:3000/api/persona` not `http://localhost:8080/api/persona`
-- Put ALL db operations under the `backend/onyx/db` / `backend/ee/onyx/db` directories. Don't run queries
-outside of those directories.
-
-## Project Overview
-
-**Onyx** (formerly Danswer) is an open-source Gen-AI and Enterprise Search platform that connects to company documents, apps, and people. It features a modular architecture with both Community Edition (MIT licensed) and Enterprise Edition offerings.
-
-
-### Background Workers (Celery)
-
-Onyx uses Celery for asynchronous task processing with multiple specialized workers:
-
-#### Worker Types
-
-1. **Primary Worker** (`celery_app.py`)
-   - Coordinates core background tasks and system-wide operations
-   - Handles connector management, document sync, pruning, and periodic checks
-   - Runs with 4 threads concurrency
-   - Tasks: connector deletion, vespa sync, pruning, LLM model updates, user file sync
-
-2. **Docfetching Worker** (`docfetching`)
-   - Fetches documents from external data sources (connectors)
-   - Spawns docprocessing tasks for each document batch
-   - Implements watchdog monitoring for stuck connectors
-   - Configurable concurrency (default from env)
-
-3. **Docprocessing Worker** (`docprocessing`)
-   - Processes fetched documents through the indexing pipeline:
-     - Upserts documents to PostgreSQL
-     - Chunks documents and adds contextual information
-     - Embeds chunks via model server
-     - Writes chunks to Vespa vector database
-     - Updates document metadata
-   - Configurable concurrency (default from env)
-
-4. **Light Worker** (`light`)
-   - Handles lightweight, fast operations
-   - Tasks: vespa operations, document permissions sync, external group sync
-   - Higher concurrency for quick tasks
-
-5. **Heavy Worker** (`heavy`)
-   - Handles resource-intensive operations
-   - Primary task: document pruning operations
-   - Runs with 4 threads concurrency
-
-6. **KG Processing Worker** (`kg_processing`)
-   - Handles Knowledge Graph processing and clustering
-   - Builds relationships between documents
-   - Runs clustering algorithms
-   - Configurable concurrency
-
-7. **Monitoring Worker** (`monitoring`)
-   - System health monitoring and metrics collection
-   - Monitors Celery queues, process memory, and system status
-   - Single thread (monitoring doesn't need parallelism)
-   - Cloud-specific monitoring tasks
-
-8. **User File Processing Worker** (`user_file_processing`)
-   - Processes user-uploaded files
-   - Handles user file indexing and project synchronization
-   - Configurable concurrency
-
-9. **Beat Worker** (`beat`)
-   - Celery's scheduler for periodic tasks
-   - Uses DynamicTenantScheduler for multi-tenant support
-   - Schedules tasks like:
-     - Indexing checks (every 15 seconds)
-     - Connector deletion checks (every 20 seconds)
-     - Vespa sync checks (every 20 seconds)
-     - Pruning checks (every 20 seconds)
-     - KG processing (every 60 seconds)
-     - Monitoring tasks (every 5 minutes)
-     - Cleanup tasks (hourly)
-
-#### Worker Deployment Modes
-
-Onyx supports two deployment modes for background workers, controlled by the `USE_LIGHTWEIGHT_BACKGROUND_WORKER` environment variable:
-
-**Lightweight Mode** (default, `USE_LIGHTWEIGHT_BACKGROUND_WORKER=true`):
-- Runs a single consolidated `background` worker that handles all background tasks:
-  - Pruning operations (from `heavy` worker)
-  - Knowledge graph processing (from `kg_processing` worker)
-  - Monitoring tasks (from `monitoring` worker)
-  - User file processing (from `user_file_processing` worker)
-- Lower resource footprint (single worker process)
-- Suitable for smaller deployments or development environments
-- Default concurrency: 6 threads
-
-**Standard Mode** (`USE_LIGHTWEIGHT_BACKGROUND_WORKER=false`):
-- Runs separate specialized workers as documented above (heavy, kg_processing, monitoring, user_file_processing)
-- Better isolation and scalability
-- Can scale individual workers independently based on workload
-- Suitable for production deployments with higher load
-
-The deployment mode affects:
-- **Backend**: Worker processes spawned by supervisord or dev scripts
-- **Helm**: Which Kubernetes deployments are created
-- **Dev Environment**: Which workers `dev_run_background_jobs.py` spawns
-
-#### Key Features
-
-- **Thread-based Workers**: All workers use thread pools (not processes) for stability
-- **Tenant Awareness**: Multi-tenant support with per-tenant task isolation. There is a 
-middleware layer that automatically finds the appropriate tenant ID when sending tasks 
-via Celery Beat.
-- **Task Prioritization**: High, Medium, Low priority queues
-- **Monitoring**: Built-in heartbeat and liveness checking
-- **Failure Handling**: Automatic retry and failure recovery mechanisms
-- **Redis Coordination**: Inter-process communication via Redis
-- **PostgreSQL State**: Task state and metadata stored in PostgreSQL
-
-
-#### Important Notes
-
-**Defining Tasks**: 
-- Always use `@shared_task` rather than `@celery_app`
-- Put tasks under `background/celery/tasks/` or `ee/background/celery/tasks`
-
-**Defining APIs**:
-When creating new FastAPI APIs, do NOT use the `response_model` field. Instead, just type the
-function.
-
-**Testing Updates**:
-If you make any updates to a celery worker and you want to test these changes, you will need
-to ask me to restart the celery worker. There is no auto-restart on code-change mechanism.
-
-### Code Quality
-```bash
-# Install and run pre-commit hooks
-pre-commit install
-pre-commit run --all-files
-```
-
-NOTE: Always make sure everything is strictly typed (both in Python and Typescript).
-
-## Architecture Overview
-
-### Technology Stack
-- **Backend**: Python 3.11, FastAPI, SQLAlchemy, Alembic, Celery
-- **Frontend**: Next.js 15+, React 18, TypeScript, Tailwind CSS
-- **Database**: PostgreSQL with Redis caching
-- **Search**: Vespa vector database
-- **Auth**: OAuth2, SAML, multi-provider support
-- **AI/ML**: LangChain, LiteLLM, multiple embedding models
-
-### Directory Structure
-
-```
-backend/
-├── onyx/
-│   ├── auth/                    # Authentication & authorization
-│   ├── chat/                    # Chat functionality & LLM interactions
-│   ├── connectors/              # Data source connectors
-│   ├── db/                      # Database models & operations
-│   ├── document_index/          # Vespa integration
-│   ├── federated_connectors/    # External search connectors
-│   ├── llm/                     # LLM provider integrations
-│   └── server/                  # API endpoints & routers
-├── ee/                          # Enterprise Edition features
-├── alembic/                     # Database migrations
-└── tests/                       # Test suites
-
-web/
-├── src/app/                     # Next.js app router pages
-├── src/components/              # Reusable React components
-└── src/lib/                     # Utilities & business logic
-```
-
-## Frontend Standards
-
-### 1. Import Standards
-
-**Always use absolute imports with the `@` prefix.**
-
-**Reason:** Moving files around becomes easier since you don't also have to update those import statements. This makes modifications to the codebase much nicer.
-
-```typescript
-// ✅ Good
-import { Button } from "@/components/ui/button";
-import { useAuth } from "@/hooks/useAuth";
-import { Text } from "@/refresh-components/texts/Text";
-
-// ❌ Bad
-import { Button } from "../../../components/ui/button";
-import { useAuth } from "./hooks/useAuth";
-```
-
-### 2. React Component Functions
-
-**Prefer regular functions over arrow functions for React components.**
-
-**Reason:** Functions just become easier to read.
-
-```typescript
-// ✅ Good
-function UserProfile({ userId }: UserProfileProps) {
-  return <div>User Profile</div>
-}
-
-// ❌ Bad
-const UserProfile = ({ userId }: UserProfileProps) => {
-  return <div>User Profile</div>
-}
-```
-
-### 3. Props Interface Extraction
-
-**Extract prop types into their own interface definitions.**
-
-**Reason:** Functions just become easier to read.
-
-```typescript
-// ✅ Good
-interface UserCardProps {
-  user: User
-  showActions?: boolean
-  onEdit?: (userId: string) => void
-}
-
-function UserCard({ user, showActions = false, onEdit }: UserCardProps) {
-  return <div>User Card</div>
-}
-
-// ❌ Bad
-function UserCard({
-  user,
-  showActions = false,
-  onEdit
-}: {
-  user: User
-  showActions?: boolean
-  onEdit?: (userId: string) => void
-}) {
-  return <div>User Card</div>
-}
-```
-
-### 4. Spacing Guidelines
-
-**Prefer padding over margins for spacing.**
-
-**Reason:** We want to consolidate usage to paddings instead of margins.
-
-```typescript
-// ✅ Good
-<div className="p-4 space-y-2">
-  <div className="p-2">Content</div>
-</div>
-
-// ❌ Bad
-<div className="m-4 space-y-2">
-  <div className="m-2">Content</div>
-</div>
-```
-
-### 5. Tailwind Dark Mode
-
-**Strictly forbid using the `dark:` modifier in Tailwind classes, except for logo icon handling.**
-
-**Reason:** The `colors.css` file already, VERY CAREFULLY, defines what the exact opposite colour of each light-mode colour is. Overriding this behaviour is VERY bad and will lead to horrible UI breakages.
-
-**Exception:** The `createLogoIcon` helper in `web/src/components/icons/icons.tsx` uses `dark:` modifiers (`dark:invert`, `dark:hidden`, `dark:block`) to handle third-party logo icons that cannot automatically adapt through `colors.css`. This is the ONLY acceptable use of dark mode modifiers.
-
-```typescript
-// ✅ Good - Standard components use `web/tailwind-themes/tailwind.config.js` / `web/src/app/css/colors.css`
-<div className="bg-background-neutral-03 text-text-02">
-  Content
-</div>
-
-// ✅ Good - Logo icons with dark mode handling via createLogoIcon
-export const GithubIcon = createLogoIcon(githubLightIcon, {
-  monochromatic: true,  // Will apply dark:invert internally
-});
-
-export const GitbookIcon = createLogoIcon(gitbookLightIcon, {
-  darkSrc: gitbookDarkIcon,  // Will use dark:hidden/dark:block internally
-});
-
-// ❌ Bad - Manual dark mode overrides
-<div className="bg-white dark:bg-black text-black dark:text-white">
-  Content
-</div>
-```
-
-### 6. Class Name Utilities
-
-**Use the `cn` utility instead of raw string formatting for classNames.**
-
-**Reason:** `cn`s are easier to read. They also allow for more complex types (i.e., string-arrays) to get formatted properly (it flattens each element in that string array down). As a result, it can allow things such as conditionals (i.e., `myCondition && "some-tailwind-class"`, which evaluates to `false` when `myCondition` is `false`) to get filtered out.
-
-```typescript
-import { cn } from '@/lib/utils'
-
-// ✅ Good
-<div className={cn(
-  'base-class',
-  isActive && 'active-class',
-  className
-)}>
-  Content
-</div>
-
-// ❌ Bad
-<div className={`base-class ${isActive ? 'active-class' : ''} ${className}`}>
-  Content
-</div>
-```
-
-### 7. Custom Hooks Organization
-
-**Follow a "hook-per-file" layout. Each hook should live in its own file within `web/src/hooks`.**
-
-**Reason:** This is just a layout preference. Keeps code clean.
-
-```typescript
-// web/src/hooks/useUserData.ts
-export function useUserData(userId: string) {
-  // hook implementation
-}
-
-// web/src/hooks/useLocalStorage.ts
-export function useLocalStorage<T>(key: string, initialValue: T) {
-  // hook implementation
-}
-```
-
-### 8. Icon Usage
-
-**ONLY use icons from the `web/src/icons` directory. Do NOT use icons from `react-icons`, `lucide`, or other external libraries.**
-
-**Reason:** We have a very carefully curated selection of icons that match our Onyx guidelines. We do NOT want to muddy those up with different aesthetic stylings.
-
-```typescript
-// ✅ Good
-import SvgX from "@/icons/x";
-import SvgMoreHorizontal from "@/icons/more-horizontal";
-
-// ❌ Bad
-import { User } from "lucide-react";
-import { FiSearch } from "react-icons/fi";
-```
-
-**Missing Icons**: If an icon is needed but doesn't exist in the `web/src/icons` directory, import it from Figma using the Figma MCP tool and add it to the icons directory.
-If you need help with this step, reach out to `raunak@onyx.app`.
-
-### 9. Text Rendering
-
-**Prefer using the `refresh-components/texts/Text` component for all text rendering. Avoid "naked" text nodes.**
-
-**Reason:** The `Text` component is fully compliant with the stylings provided in Figma. It provides easy utilities to specify the text-colour and font-size in the form of flags. Super duper easy.
-
-```typescript
-// ✅ Good
-import { Text } from '@/refresh-components/texts/Text'
-
-function UserCard({ name }: { name: string }) {
-  return (
-    <Text
-      {/* The `text03` flag makes the text it renders to be coloured the 3rd-scale grey */}
-      text03
-      {/* The `mainAction` flag makes the text it renders to be "main-action" font + line-height + weightage, as described in the Figma */}
-      mainAction
-    >
-      {name}
-    </Text>
-  )
-}
-
-// ❌ Bad
-function UserCard({ name }: { name: string }) {
-  return (
-    <div>
-      <h2>{name}</h2>
-      <p>User details</p>
-    </div>
-  )
-}
-```
-
-### 10. Component Usage
-
-**Heavily avoid raw HTML input components. Always use components from the `web/src/refresh-components` or `web/lib/opal/src` directory.**
-
-**Reason:** We've put in a lot of effort to unify the components that are rendered in the Onyx app. Using raw components breaks the entire UI of the application, and leaves it in a muddier state than before.
-
-```typescript
-// ✅ Good
-import Button from '@/refresh-components/buttons/Button'
-import InputTypeIn from '@/refresh-components/inputs/InputTypeIn'
-import SvgPlusCircle from '@/icons/plus-circle'
-
-function ContactForm() {
-  return (
-    <form>
-      <InputTypeIn placeholder="Search..." />
-      <Button type="submit" leftIcon={SvgPlusCircle}>Submit</Button>
-    </form>
-  )
-}
-
-// ❌ Bad
-function ContactForm() {
-  return (
-    <form>
-      <input placeholder="Name" />
-      <textarea placeholder="Message" />
-      <button type="submit">Submit</button>
-    </form>
-  )
-}
-```
-
-### 11. Colors
-
-**Always use custom overrides for colors and borders rather than built in Tailwind CSS colors. These overrides live in `web/tailwind-themes/tailwind.config.js`.**
-
-**Reason:** Our custom color system uses CSS variables that automatically handle dark mode and maintain design consistency across the app. Standard Tailwind colors bypass this system.
-
-**Available color categories:**
-- **Text:** `text-01` through `text-05`, `text-inverted-XX`
-- **Backgrounds:** `background-neutral-XX`, `background-tint-XX` (and inverted variants)
-- **Borders:** `border-01` through `border-05`, `border-inverted-XX`
-- **Actions:** `action-link-XX`, `action-danger-XX`
-- **Status:** `status-info-XX`, `status-success-XX`, `status-warning-XX`, `status-error-XX`
-- **Theme:** `theme-primary-XX`, `theme-red-XX`, `theme-blue-XX`, etc.
-
-```typescript
-// ✅ Good - Use custom Onyx color classes
-<div className="bg-background-neutral-01 border border-border-02" />
-<div className="bg-background-tint-02 border border-border-01" />
-<div className="bg-status-success-01" />
-<div className="bg-action-link-01" />
-<div className="bg-theme-primary-05" />
-
-// ❌ Bad - Do NOT use standard Tailwind colors
-<div className="bg-gray-100 border border-gray-300 text-gray-600" />
-<div className="bg-white border border-slate-200" />
-<div className="bg-green-100 text-green-700" />
-<div className="bg-blue-100 text-blue-600" />
-<div className="bg-indigo-500" />
-```
-
-### 12. Data Fetching
-
-**Prefer using `useSWR` for data fetching. Data should generally be fetched on the client side. Components that need data should display a loader / placeholder while waiting for that data. Prefer loading data within the component that needs it rather than at the top level and passing it down.**
-
-**Reason:** Client side fetching allows us to load the skeleton of the page without waiting for data to load, leading to a snappier UX. Loading data where needed reduces dependencies between a component and its parent component(s).
-
-## Database & Migrations
-
-### Running Migrations
-```bash
-# Standard migrations
-alembic upgrade head
-
-# Multi-tenant (Enterprise)
-alembic -n schema_private upgrade head
-```
-
-### Creating Migrations
-```bash
-# Create migration
-alembic revision -m "description"
-
-# Multi-tenant migration
-alembic -n schema_private revision -m "description"
-```
-
-Write the migration manually and place it in the file that alembic creates when running the above command.
-
-## Testing Strategy
-
-There are 4 main types of tests within Onyx:
-
-### Unit Tests
-These should not assume any Onyx/external services are available to be called.
-Interactions with the outside world should be mocked using `unittest.mock`. Generally, only 
-write these for complex, isolated modules e.g. `citation_processing.py`.
-
-To run them:
-
-```bash
-python -m dotenv -f .vscode/.env run -- pytest -xv backend/tests/unit
-```
-
-### External Dependency Unit Tests
-These tests assume that all external dependencies of Onyx are available and callable (e.g. Postgres, Redis, 
-MinIO/S3, Vespa are running + OpenAI can be called + any request to the internet is fine + etc.).
-
-However, the actual Onyx containers are not running and with these tests we call the function to test directly.
-We can also mock components/calls at will. 
-
-The goal with these tests are to minimize mocking while giving some flexibility to mock things that are flakey, 
-need strictly controlled behavior, or need to have their internal behavior validated (e.g. verify a function is called
-with certain args, something that would be impossible with proper integration tests).
-
-A great example of this type of test is `backend/tests/external_dependency_unit/connectors/confluence/test_confluence_group_sync.py`.
-
-To run them:
-
-```bash
-python -m dotenv -f .vscode/.env run -- pytest backend/tests/external_dependency_unit
-```
-
-### Integration Tests
-Standard integration tests. Every test in `backend/tests/integration` runs against a real Onyx deployment. We cannot 
-mock anything in these tests. Prefer writing integration tests (or External Dependency Unit Tests if mocking/internal 
-verification is necessary) over any other type of test.
-
-Tests are parallelized at a directory level.
-
-When writing integration tests, make sure to check the root `conftest.py` for useful fixtures + the `backend/tests/integration/common_utils` directory for utilities. Prefer (if one exists), calling the appropriate Manager 
-class in the utils over directly calling the APIs with a library like `requests`. Prefer using fixtures rather than
-calling the utilities directly (e.g. do NOT create admin users with 
-`admin_user = UserManager.create(name="admin_user")`, instead use the `admin_user` fixture).
-
-A great example of this type of test is `backend/tests/integration/dev_apis/test_simple_chat_api.py`.
-
-To run them:
-
-```bash
-python -m dotenv -f .vscode/.env run -- pytest backend/tests/integration
-```
-
-### Playwright (E2E) Tests
-These tests are an even more complete version of the Integration Tests mentioned above. Has all services of Onyx 
-running, *including* the Web Server.
-
-Use these tests for anything that requires significant frontend <-> backend coordination.
-
-Tests are located at `web/tests/e2e`. Tests are written in TypeScript.
-
-To run them:
-
-```bash
-npx playwright test <TEST_NAME>
-```
-
-
-## Logs
-
-When (1) writing integration tests or (2) doing live tests (e.g. curl / playwright) you can get access
-to logs via the `backend/log/<service_name>_debug.log` file. All Onyx services (api_server, web_server, celery_X)
-will be tailing their logs to this file. 
-
-
-## Security Considerations
-
-- Never commit API keys or secrets to repository
-- Use encrypted credential storage for connector credentials
-- Follow RBAC patterns for new features
-- Implement proper input validation with Pydantic models
-- Use parameterized queries to prevent SQL injection
-
-## AI/LLM Integration
-
-- Multiple LLM providers supported via LiteLLM
-- Configurable models per feature (chat, search, embeddings)
-- Streaming support for real-time responses
-- Token management and rate limiting
-- Custom prompts and agent actions
-
-## Creating a Plan
-When creating a plan in the `plans` directory, make sure to include at least these elements:
-
-**Issues to Address**
-What the change is meant to do.
-
-**Important Notes**
-Things you come across in your research that are important to the implementation.
-
-**Implementation strategy**
-How you are going to make the changes happen. High level approach.
-
-**Tests**
-What unit (use rarely), external dependency unit, integration, and playwright tests you plan to write to 
-verify the correct behavior. Don't overtest. Usually, a given change only needs one type of test.
-
-Do NOT include these: *Timeline*, *Rollback plan*
-
-This is a minimal list - feel free to include more. Do NOT write code as part of your plan.
-Keep it high level. You can reference certain files or functions though.
-
-Before writing your plan, make sure to do research. Explore the relevant sections in the codebase.

CLAUDE.md

@@ -0,0 +1 @@
+AGENTS.md

LICENSE

@@ -2,7 +2,10 @@ Copyright (c) 2023-present DanswerAI, Inc.
 
 Portions of this software are licensed as follows:
 
-- All content that resides under "ee" directories of this repository, if that directory exists, is licensed under the license defined in "backend/ee/LICENSE". Specifically all content under "backend/ee" and "web/src/app/ee" is licensed under the license defined in "backend/ee/LICENSE".
+- All content that resides under "ee" directories of this repository is licensed under the Onyx Enterprise License. Each ee directory contains an identical copy of this license at its root:
+  - backend/ee/LICENSE
+  - web/src/app/ee/LICENSE
+  - web/src/ee/LICENSE
 - All third party components incorporated into the Onyx Software are licensed under the original license provided by the owner of the applicable component.
 - Content outside of the above mentioned directories or restrictions above is available under the "MIT Expat" license as defined below.
 

backend/Dockerfile

@@ -134,6 +134,7 @@ COPY --chown=onyx:onyx ./alembic_tenants /app/alembic_tenants
 COPY --chown=onyx:onyx ./alembic.ini /app/alembic.ini
 COPY supervisord.conf /usr/etc/supervisord.conf
 COPY --chown=onyx:onyx ./static /app/static
+COPY --chown=onyx:onyx ./keys /app/keys
 
 # Escape hatch scripts
 COPY --chown=onyx:onyx ./scripts/debugging /app/scripts/debugging
@@ -149,6 +150,11 @@ RUN if [ "$ENABLE_CRAFT" = "true" ]; then \
         ENABLE_CRAFT=true /app/scripts/setup_craft_templates.sh; \
     fi
 
+# Set Craft template paths to the in-image locations
+# These match the paths where setup_craft_templates.sh creates the templates
+ENV OUTPUTS_TEMPLATE_PATH=/app/onyx/server/features/build/sandbox/kubernetes/docker/templates/outputs
+ENV VENV_TEMPLATE_PATH=/app/onyx/server/features/build/sandbox/kubernetes/docker/templates/venv
+
 # Put logo in assets
 COPY --chown=onyx:onyx ./assets /app/assets
 

backend/Dockerfile.model_server

@@ -48,6 +48,7 @@ WORKDIR /app
 # Utils used by model server
 COPY ./onyx/utils/logger.py /app/onyx/utils/logger.py
 COPY ./onyx/utils/middleware.py /app/onyx/utils/middleware.py
+COPY ./onyx/utils/tenant.py /app/onyx/utils/tenant.py
 
 # Place to fetch version information
 COPY ./onyx/__init__.py /app/onyx/__init__.py

backend/alembic/env.py

@@ -57,7 +57,7 @@ if USE_IAM_AUTH:
 
 
 def include_object(
-    object: SchemaItem,
+    object: SchemaItem,  # noqa: ARG001
     name: str | None,
     type_: Literal[
         "schema",
@@ -67,8 +67,8 @@ def include_object(
         "unique_constraint",
         "foreign_key_constraint",
     ],
-    reflected: bool,
-    compare_to: SchemaItem | None,
+    reflected: bool,  # noqa: ARG001
+    compare_to: SchemaItem | None,  # noqa: ARG001
 ) -> bool:
     if type_ == "table" and name in EXCLUDE_TABLES:
         return False
@@ -244,7 +244,7 @@ def do_run_migrations(
 
 
 def provide_iam_token_for_alembic(
-    dialect: Any, conn_rec: Any, cargs: Any, cparams: Any
+    dialect: Any, conn_rec: Any, cargs: Any, cparams: Any  # noqa: ARG001
 ) -> None:
     if USE_IAM_AUTH:
         # Database connection settings
@@ -474,7 +474,7 @@ def run_migrations_online() -> None:
 
     if connectable is not None:
         # pytest-alembic is providing an engine - use it directly
-        logger.info("run_migrations_online starting (pytest-alembic mode).")
+        logger.debug("run_migrations_online starting (pytest-alembic mode).")
 
         # For pytest-alembic, we use the default schema (public)
         schema_name = context.config.attributes.get(

backend/alembic/run_multitenant_migrations.py

@@ -0,0 +1,343 @@
+#!/usr/bin/env python3
+"""Parallel Alembic Migration Runner
+
+Upgrades tenant schemas to head in batched, parallel alembic subprocesses.
+Each subprocess handles a batch of schemas (via ``-x schemas=a,b,c``),
+reducing per-process overhead compared to one-schema-per-process.
+
+Usage examples::
+
+    # defaults: 6 workers, 50 schemas/batch
+    python alembic/run_multitenant_migrations.py
+
+    # custom settings
+    python alembic/run_multitenant_migrations.py -j 8 -b 100
+"""
+from __future__ import annotations
+
+import argparse
+import subprocess
+import sys
+import threading
+import time
+from concurrent.futures import ThreadPoolExecutor, as_completed
+from typing import List, NamedTuple
+
+from alembic.config import Config
+from alembic.script import ScriptDirectory
+from sqlalchemy import text
+
+from onyx.db.engine.sql_engine import is_valid_schema_name
+from onyx.db.engine.sql_engine import SqlEngine
+from onyx.db.engine.tenant_utils import get_all_tenant_ids
+from shared_configs.configs import TENANT_ID_PREFIX
+
+
+# ---------------------------------------------------------------------------
+# Data types
+# ---------------------------------------------------------------------------
+
+
+class Args(NamedTuple):
+    jobs: int
+    batch_size: int
+
+
+class BatchResult(NamedTuple):
+    schemas: list[str]
+    success: bool
+    output: str
+    elapsed_sec: float
+
+
+# ---------------------------------------------------------------------------
+# Core functions
+# ---------------------------------------------------------------------------
+
+
+def run_alembic_for_batch(schemas: list[str]) -> BatchResult:
+    """Run ``alembic upgrade head`` for a batch of schemas in one subprocess.
+
+    If the batch fails, it is automatically retried with ``-x continue=true``
+    so that the remaining schemas in the batch still get migrated.  The retry
+    output (which contains alembic's per-schema error messages) is returned
+    for diagnosis.
+    """
+    csv = ",".join(schemas)
+    base_cmd = ["alembic", "-x", f"schemas={csv}"]
+
+    start = time.monotonic()
+    result = subprocess.run(
+        [*base_cmd, "upgrade", "head"],
+        stdout=subprocess.PIPE,
+        stderr=subprocess.STDOUT,
+        text=True,
+    )
+
+    if result.returncode == 0:
+        elapsed = time.monotonic() - start
+        return BatchResult(schemas, True, result.stdout or "", elapsed)
+
+    # At least one schema failed.  Print the initial error output, then
+    # re-run with continue=true so the remaining schemas still get migrated.
+    if result.stdout:
+        print(f"Initial error output:\n{result.stdout}", file=sys.stderr, flush=True)
+    print(
+        f"Batch failed (exit {result.returncode}), retrying with 'continue=true'...",
+        file=sys.stderr,
+        flush=True,
+    )
+
+    retry = subprocess.run(
+        [*base_cmd, "-x", "continue=true", "upgrade", "head"],
+        stdout=subprocess.PIPE,
+        stderr=subprocess.STDOUT,
+        text=True,
+    )
+    elapsed = time.monotonic() - start
+    return BatchResult(schemas, False, retry.stdout or "", elapsed)
+
+
+def get_head_revision() -> str | None:
+    """Get the head revision from the alembic script directory."""
+    alembic_cfg = Config("alembic.ini")
+    script = ScriptDirectory.from_config(alembic_cfg)
+    return script.get_current_head()
+
+
+def get_schemas_needing_migration(
+    tenant_schemas: List[str], head_rev: str
+) -> List[str]:
+    """Return only schemas whose current alembic version is not at head."""
+    if not tenant_schemas:
+        return []
+
+    engine = SqlEngine.get_engine()
+
+    with engine.connect() as conn:
+        # Find which schemas actually have an alembic_version table
+        rows = conn.execute(
+            text(
+                "SELECT table_schema FROM information_schema.tables "
+                "WHERE table_name = 'alembic_version' "
+                "AND table_schema = ANY(:schemas)"
+            ),
+            {"schemas": tenant_schemas},
+        )
+        schemas_with_table = set(row[0] for row in rows)
+
+        # Schemas without the table definitely need migration
+        needs_migration = [s for s in tenant_schemas if s not in schemas_with_table]
+
+        if not schemas_with_table:
+            return needs_migration
+
+        # Validate schema names before interpolating into SQL
+        for schema in schemas_with_table:
+            if not is_valid_schema_name(schema):
+                raise ValueError(f"Invalid schema name: {schema}")
+
+        # Single query to get every schema's current revision at once.
+        # Use integer tags instead of interpolating schema names into
+        # string literals to avoid quoting issues.
+        schema_list = list(schemas_with_table)
+        union_parts = [
+            f'SELECT {i} AS idx, version_num FROM "{schema}".alembic_version'
+            for i, schema in enumerate(schema_list)
+        ]
+        rows = conn.execute(text(" UNION ALL ".join(union_parts)))
+        version_by_schema = {schema_list[row[0]]: row[1] for row in rows}
+
+        needs_migration.extend(
+            s for s in schemas_with_table if version_by_schema.get(s) != head_rev
+        )
+
+    return needs_migration
+
+
+def run_migrations_parallel(
+    schemas: list[str],
+    max_workers: int,
+    batch_size: int,
+) -> bool:
+    """Chunk *schemas* into batches and run them in parallel.
+
+    A background monitor thread prints a status line every 60 s listing
+    which batches are still in-flight, making it easy to spot hung tenants.
+    """
+    batches = [schemas[i : i + batch_size] for i in range(0, len(schemas), batch_size)]
+    total_batches = len(batches)
+    print(
+        f"{len(schemas)} schemas in {total_batches} batch(es) "
+        f"with {max_workers} workers (batch size: {batch_size})...",
+        flush=True,
+    )
+    all_success = True
+
+    # Thread-safe tracking of in-flight batches for the monitor thread.
+    in_flight: dict[int, list[str]] = {}
+    prev_in_flight: set[int] = set()
+    lock = threading.Lock()
+    stop_event = threading.Event()
+
+    def _monitor() -> None:
+        """Print a status line every 60 s listing batches still in-flight.
+
+        Only prints batches that were also present in the previous tick,
+        making it easy to spot batches that are stuck.
+        """
+        nonlocal prev_in_flight
+        while not stop_event.wait(60):
+            with lock:
+                if not in_flight:
+                    prev_in_flight = set()
+                    continue
+                current = set(in_flight)
+                stuck = current & prev_in_flight
+                prev_in_flight = current
+
+                if not stuck:
+                    continue
+
+                schemas = [s for idx in sorted(stuck) for s in in_flight[idx]]
+                print(
+                    f"⏳ batch(es) still running since last check "
+                    f"({', '.join(str(i + 1) for i in sorted(stuck))}): "
+                    + ", ".join(schemas),
+                    flush=True,
+                )
+
+    monitor_thread = threading.Thread(target=_monitor, daemon=True)
+    monitor_thread.start()
+
+    try:
+        with ThreadPoolExecutor(max_workers=max_workers) as executor:
+
+            def _run(batch_idx: int, batch: list[str]) -> BatchResult:
+                with lock:
+                    in_flight[batch_idx] = batch
+                print(
+                    f"Batch {batch_idx + 1}/{total_batches} started "
+                    f"({len(batch)} schemas): {', '.join(batch)}",
+                    flush=True,
+                )
+                result = run_alembic_for_batch(batch)
+                with lock:
+                    in_flight.pop(batch_idx, None)
+                return result
+
+            future_to_idx = {
+                executor.submit(_run, i, b): i for i, b in enumerate(batches)
+            }
+
+            for future in as_completed(future_to_idx):
+                batch_idx = future_to_idx[future]
+                try:
+                    result = future.result()
+                    status = "✓" if result.success else "✗"
+
+                    print(
+                        f"Batch {batch_idx + 1}/{total_batches} "
+                        f"{status} {len(result.schemas)} schemas "
+                        f"in {result.elapsed_sec:.1f}s",
+                        flush=True,
+                    )
+
+                    if not result.success:
+                        # Print last 20 lines of retry output for diagnosis
+                        tail = result.output.strip().splitlines()[-20:]
+                        for line in tail:
+                            print(f"    {line}", flush=True)
+                        all_success = False
+
+                except Exception as e:
+                    print(
+                        f"Batch {batch_idx + 1}/{total_batches} " f"✗ exception: {e}",
+                        flush=True,
+                    )
+                    all_success = False
+    finally:
+        stop_event.set()
+        monitor_thread.join(timeout=2)
+
+    return all_success
+
+
+# ---------------------------------------------------------------------------
+# CLI
+# ---------------------------------------------------------------------------
+
+
+def parse_args() -> Args:
+    parser = argparse.ArgumentParser(
+        description="Run alembic migrations for all tenant schemas in parallel"
+    )
+    parser.add_argument(
+        "-j",
+        "--jobs",
+        type=int,
+        default=6,
+        metavar="N",
+        help="Number of parallel alembic processes (default: 6)",
+    )
+    parser.add_argument(
+        "-b",
+        "--batch-size",
+        type=int,
+        default=50,
+        metavar="N",
+        help="Schemas per alembic process (default: 50)",
+    )
+    args = parser.parse_args()
+    if args.jobs < 1:
+        parser.error("--jobs must be >= 1")
+    if args.batch_size < 1:
+        parser.error("--batch-size must be >= 1")
+    return Args(jobs=args.jobs, batch_size=args.batch_size)
+
+
+def main() -> int:
+    args = parse_args()
+
+    head_rev = get_head_revision()
+    if head_rev is None:
+        print("Could not determine head revision.", file=sys.stderr)
+        return 1
+
+    with SqlEngine.scoped_engine(pool_size=5, max_overflow=2):
+        tenant_ids = get_all_tenant_ids()
+        tenant_schemas = [tid for tid in tenant_ids if tid.startswith(TENANT_ID_PREFIX)]
+
+        if not tenant_schemas:
+            print(
+                "No tenant schemas found. Is MULTI_TENANT=true set?",
+                file=sys.stderr,
+            )
+            return 1
+
+        schemas_to_migrate = get_schemas_needing_migration(tenant_schemas, head_rev)
+
+    if not schemas_to_migrate:
+        print(
+            f"All {len(tenant_schemas)} tenants are already at head "
+            f"revision ({head_rev})."
+        )
+        return 0
+
+    print(
+        f"{len(schemas_to_migrate)}/{len(tenant_schemas)} tenants need "
+        f"migration (head: {head_rev})."
+    )
+
+    success = run_migrations_parallel(
+        schemas_to_migrate,
+        max_workers=args.jobs,
+        batch_size=args.batch_size,
+    )
+
+    print(f"\n{'All migrations successful' if success else 'Some migrations failed'}")
+    return 0 if success else 1
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())

backend/alembic/versions/001984c88745_llmprovider_deprecated_fields_are_.py

@@ -1,58 +0,0 @@
-"""LLMProvider deprecated fields are nullable
-
-Revision ID: 001984c88745
-Revises: 01f8e6d95a33
-Create Date: 2026-02-01 22:24:34.171100
-
-"""
-
-from alembic import op
-import sqlalchemy as sa
-
-
-# revision identifiers, used by Alembic.
-revision = "001984c88745"
-down_revision = "01f8e6d95a33"
-branch_labels = None
-depends_on = None
-
-
-def upgrade() -> None:
-    # Make default_model_name nullable (was NOT NULL)
-    op.alter_column(
-        "llm_provider",
-        "default_model_name",
-        existing_type=sa.String(),
-        nullable=True,
-    )
-
-    # Remove server_default from is_default_vision_provider (was server_default=false())
-    op.alter_column(
-        "llm_provider",
-        "is_default_vision_provider",
-        existing_type=sa.Boolean(),
-        server_default=None,
-    )
-
-    # is_default_provider and default_vision_model are already nullable with no server_default
-
-
-def downgrade() -> None:
-    # Restore default_model_name to NOT NULL (set empty string for any NULLs first)
-    op.execute(
-        "UPDATE llm_provider SET default_model_name = '' WHERE default_model_name IS NULL"
-    )
-    op.alter_column(
-        "llm_provider",
-        "default_model_name",
-        existing_type=sa.String(),
-        nullable=False,
-    )
-
-    # Restore server_default for is_default_vision_provider
-    op.alter_column(
-        "llm_provider",
-        "is_default_vision_provider",
-        existing_type=sa.Boolean(),
-        server_default=sa.false(),
-    )

backend/alembic/versions/01f8e6d95a33_populate_flow_mapping_data.py

@@ -1,7 +1,7 @@
 """Populate flow mapping data
 
 Revision ID: 01f8e6d95a33
-Revises: f220515df7b4
+Revises: d5c86e2c6dc6
 Create Date: 2026-01-31 17:37:10.485558
 
 """
@@ -11,7 +11,7 @@ from alembic import op
 
 # revision identifiers, used by Alembic.
 revision = "01f8e6d95a33"
-down_revision = "f220515df7b4"
+down_revision = "d5c86e2c6dc6"
 branch_labels = None
 depends_on = None
 
@@ -23,7 +23,7 @@ def upgrade() -> None:
         """
         INSERT INTO llm_model_flow (llm_model_flow_type, is_default, model_configuration_id)
         SELECT
-            'chat' AS llm_model_flow_type,
+            'CHAT' AS llm_model_flow_type,
             COALESCE(
                 (lp.is_default_provider IS TRUE AND lp.default_model_name = mc.name),
                 FALSE
@@ -44,7 +44,7 @@ def upgrade() -> None:
         """
         INSERT INTO llm_model_flow (llm_model_flow_type, is_default, model_configuration_id)
         SELECT
-            'vision' AS llm_model_flow_type,
+            'VISION' AS llm_model_flow_type,
             COALESCE(
                 (lp.is_default_vision_provider IS TRUE AND lp.default_vision_model = mc.name),
                 FALSE
@@ -68,7 +68,7 @@ def downgrade() -> None:
             default_vision_model = mc.name
         FROM llm_model_flow mf
         JOIN model_configuration mc ON mc.id = mf.model_configuration_id
-        WHERE mf.llm_model_flow_type = 'vision'
+        WHERE mf.llm_model_flow_type = 'VISION'
           AND mf.is_default = TRUE
           AND mc.llm_provider_id = lp.id;
         """
@@ -83,7 +83,7 @@ def downgrade() -> None:
             default_model_name = mc.name
         FROM llm_model_flow mf
         JOIN model_configuration mc ON mc.id = mf.model_configuration_id
-        WHERE mf.llm_model_flow_type = 'chat'
+        WHERE mf.llm_model_flow_type = 'CHAT'
           AND mf.is_default = TRUE
           AND mc.llm_provider_id = lp.id;
         """
@@ -100,7 +100,7 @@ def downgrade() -> None:
             FROM model_configuration mc
             JOIN llm_model_flow mf ON mf.model_configuration_id = mc.id
             WHERE mc.llm_provider_id = lp.id
-              AND mf.llm_model_flow_type = 'chat'
+              AND mf.llm_model_flow_type = 'CHAT'
             ORDER BY mc.is_visible DESC, mc.id ASC
             LIMIT 1
         )

backend/alembic/versions/114a638452db_add_default_app_mode_to_user.py

@@ -0,0 +1,33 @@
+"""add default_app_mode to user
+
+Revision ID: 114a638452db
+Revises: feead2911109
+Create Date: 2026-02-09 18:57:08.274640
+
+"""
+
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision = "114a638452db"
+down_revision = "feead2911109"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    op.add_column(
+        "user",
+        sa.Column(
+            "default_app_mode",
+            sa.String(),
+            nullable=False,
+            server_default="CHAT",
+        ),
+    )
+
+
+def downgrade() -> None:
+    op.drop_column("user", "default_app_mode")

backend/alembic/versions/12635f6655b7_drive_canonical_ids.py

@@ -11,7 +11,6 @@ import sqlalchemy as sa
 from urllib.parse import urlparse, urlunparse
 from httpx import HTTPStatusError
 import httpx
-from onyx.document_index.factory import get_default_document_index
 from onyx.db.search_settings import SearchSettings
 from onyx.document_index.vespa.shared_utils.utils import get_vespa_http_client
 from onyx.document_index.vespa.shared_utils.utils import (
@@ -519,15 +518,11 @@ def delete_document_from_db(current_doc_id: str, index_name: str) -> None:
 def upgrade() -> None:
     if SKIP_CANON_DRIVE_IDS:
         return
-    current_search_settings, future_search_settings = active_search_settings()
-    document_index = get_default_document_index(
-        current_search_settings,
-        future_search_settings,
-    )
+    current_search_settings, _ = active_search_settings()
 
     # Get the index name
-    if hasattr(document_index, "index_name"):
-        index_name = document_index.index_name
+    if hasattr(current_search_settings, "index_name"):
+        index_name = current_search_settings.index_name
     else:
         # Default index name if we can't get it from the document_index
         index_name = "danswer_index"

backend/alembic/versions/175ea04c7087_add_user_preferences.py

@@ -0,0 +1,27 @@
+"""add_user_preferences
+
+Revision ID: 175ea04c7087
+Revises: d56ffa94ca32
+Create Date: 2026-02-04 18:16:24.830873
+
+"""
+
+from alembic import op
+import sqlalchemy as sa
+
+# revision identifiers, used by Alembic.
+revision = "175ea04c7087"
+down_revision = "d56ffa94ca32"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    op.add_column(
+        "user",
+        sa.Column("user_preferences", sa.Text(), nullable=True),
+    )
+
+
+def downgrade() -> None:
+    op.drop_column("user", "user_preferences")

backend/alembic/versions/19c0ccb01687_migrate_to_contextual_rag_model.py

@@ -0,0 +1,71 @@
+"""Migrate to contextual rag model
+
+Revision ID: 19c0ccb01687
+Revises: 9c54986124c6
+Create Date: 2026-02-12 11:21:41.798037
+
+"""
+
+import sqlalchemy as sa
+from alembic import op
+
+
+# revision identifiers, used by Alembic.
+revision = "19c0ccb01687"
+down_revision = "9c54986124c6"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    # Widen the column to fit 'CONTEXTUAL_RAG' (15 chars); was varchar(10)
+    # when the table was created with only CHAT/VISION values.
+    op.alter_column(
+        "llm_model_flow",
+        "llm_model_flow_type",
+        type_=sa.String(length=20),
+        existing_type=sa.String(length=10),
+        existing_nullable=False,
+    )
+
+    # For every search_settings row that has contextual rag configured,
+    # create an llm_model_flow entry. is_default is TRUE if the row
+    # belongs to the PRESENT search settings, FALSE otherwise.
+    op.execute(
+        """
+        INSERT INTO llm_model_flow (llm_model_flow_type, model_configuration_id, is_default)
+        SELECT DISTINCT
+            'CONTEXTUAL_RAG',
+            mc.id,
+            (ss.status = 'PRESENT')
+        FROM search_settings ss
+        JOIN llm_provider lp
+            ON lp.name = ss.contextual_rag_llm_provider
+        JOIN model_configuration mc
+            ON mc.llm_provider_id = lp.id
+            AND mc.name = ss.contextual_rag_llm_name
+        WHERE ss.enable_contextual_rag = TRUE
+            AND ss.contextual_rag_llm_name IS NOT NULL
+            AND ss.contextual_rag_llm_provider IS NOT NULL
+        ON CONFLICT (llm_model_flow_type, model_configuration_id)
+            DO UPDATE SET is_default = EXCLUDED.is_default
+            WHERE EXCLUDED.is_default = TRUE
+        """
+    )
+
+
+def downgrade() -> None:
+    op.execute(
+        """
+        DELETE FROM llm_model_flow
+        WHERE llm_model_flow_type = 'CONTEXTUAL_RAG'
+        """
+    )
+
+    op.alter_column(
+        "llm_model_flow",
+        "llm_model_flow_type",
+        type_=sa.String(length=10),
+        existing_type=sa.String(length=20),
+        existing_nullable=False,
+    )

backend/alembic/versions/90b409d06e50_add_chat_compression_fields.py

@@ -0,0 +1,36 @@
+"""add_chat_compression_fields
+
+Revision ID: 90b409d06e50
+Revises: f220515df7b4
+Create Date: 2026-01-26 09:13:09.635427
+
+"""
+
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision = "90b409d06e50"
+down_revision = "f220515df7b4"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    # Add last_summarized_message_id to chat_message
+    # This field marks a message as a summary and indicates the last message it covers.
+    # Summaries are branch-aware via their parent_message_id pointing to the branch.
+    op.add_column(
+        "chat_message",
+        sa.Column(
+            "last_summarized_message_id",
+            sa.Integer(),
+            sa.ForeignKey("chat_message.id", ondelete="SET NULL"),
+            nullable=True,
+        ),
+    )
+
+
+def downgrade() -> None:
+    op.drop_column("chat_message", "last_summarized_message_id")

backend/alembic/versions/90e3b9af7da4_tag_fix.py

@@ -16,7 +16,6 @@ from typing import Generator
 from alembic import op
 import sqlalchemy as sa
 
-from onyx.document_index.factory import get_default_document_index
 from onyx.document_index.vespa_constants import DOCUMENT_ID_ENDPOINT
 from onyx.db.search_settings import SearchSettings
 from onyx.configs.app_configs import AUTH_TYPE
@@ -126,14 +125,11 @@ def remove_old_tags() -> None:
     the document got reindexed, the old tag would not be removed.
     This function removes those old tags by comparing it against the tags in vespa.
     """
-    current_search_settings, future_search_settings = active_search_settings()
-    document_index = get_default_document_index(
-        current_search_settings, future_search_settings
-    )
+    current_search_settings, _ = active_search_settings()
 
     # Get the index name
-    if hasattr(document_index, "index_name"):
-        index_name = document_index.index_name
+    if hasattr(current_search_settings, "index_name"):
+        index_name = current_search_settings.index_name
     else:
         # Default index name if we can't get it from the document_index
         index_name = "danswer_index"

backend/alembic/versions/93c15d6a6fbb_add_chunk_error_and_vespa_count_columns_.py

@@ -0,0 +1,43 @@
+"""add chunk error and vespa count columns to opensearch tenant migration
+
+Revision ID: 93c15d6a6fbb
+Revises: d3fd499c829c
+Create Date: 2026-02-11 23:07:34.576725
+
+"""
+
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision = "93c15d6a6fbb"
+down_revision = "d3fd499c829c"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    op.add_column(
+        "opensearch_tenant_migration_record",
+        sa.Column(
+            "total_chunks_errored",
+            sa.Integer(),
+            nullable=False,
+            server_default="0",
+        ),
+    )
+    op.add_column(
+        "opensearch_tenant_migration_record",
+        sa.Column(
+            "total_chunks_in_vespa",
+            sa.Integer(),
+            nullable=False,
+            server_default="0",
+        ),
+    )
+
+
+def downgrade() -> None:
+    op.drop_column("opensearch_tenant_migration_record", "total_chunks_in_vespa")
+    op.drop_column("opensearch_tenant_migration_record", "total_chunks_errored")

backend/alembic/versions/9c54986124c6_add_scim_tables.py

@@ -0,0 +1,124 @@
+"""add_scim_tables
+
+Revision ID: 9c54986124c6
+Revises: b51c6844d1df
+Create Date: 2026-02-12 20:29:47.448614
+
+"""
+
+from alembic import op
+import fastapi_users_db_sqlalchemy
+import sqlalchemy as sa
+
+# revision identifiers, used by Alembic.
+revision = "9c54986124c6"
+down_revision = "b51c6844d1df"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    op.create_table(
+        "scim_token",
+        sa.Column("id", sa.Integer(), nullable=False),
+        sa.Column("name", sa.String(), nullable=False),
+        sa.Column("hashed_token", sa.String(length=64), nullable=False),
+        sa.Column("token_display", sa.String(), nullable=False),
+        sa.Column(
+            "created_by_id",
+            fastapi_users_db_sqlalchemy.generics.GUID(),
+            nullable=False,
+        ),
+        sa.Column(
+            "is_active",
+            sa.Boolean(),
+            server_default=sa.text("true"),
+            nullable=False,
+        ),
+        sa.Column(
+            "created_at",
+            sa.DateTime(timezone=True),
+            server_default=sa.text("now()"),
+            nullable=False,
+        ),
+        sa.Column("last_used_at", sa.DateTime(timezone=True), nullable=True),
+        sa.ForeignKeyConstraint(["created_by_id"], ["user.id"], ondelete="CASCADE"),
+        sa.PrimaryKeyConstraint("id"),
+        sa.UniqueConstraint("hashed_token"),
+    )
+    op.create_table(
+        "scim_group_mapping",
+        sa.Column("id", sa.Integer(), nullable=False),
+        sa.Column("external_id", sa.String(), nullable=False),
+        sa.Column("user_group_id", sa.Integer(), nullable=False),
+        sa.Column(
+            "created_at",
+            sa.DateTime(timezone=True),
+            server_default=sa.text("now()"),
+            nullable=False,
+        ),
+        sa.Column(
+            "updated_at",
+            sa.DateTime(timezone=True),
+            server_default=sa.text("now()"),
+            onupdate=sa.text("now()"),
+            nullable=False,
+        ),
+        sa.ForeignKeyConstraint(
+            ["user_group_id"], ["user_group.id"], ondelete="CASCADE"
+        ),
+        sa.PrimaryKeyConstraint("id"),
+        sa.UniqueConstraint("user_group_id"),
+    )
+    op.create_index(
+        op.f("ix_scim_group_mapping_external_id"),
+        "scim_group_mapping",
+        ["external_id"],
+        unique=True,
+    )
+    op.create_table(
+        "scim_user_mapping",
+        sa.Column("id", sa.Integer(), nullable=False),
+        sa.Column("external_id", sa.String(), nullable=False),
+        sa.Column(
+            "user_id",
+            fastapi_users_db_sqlalchemy.generics.GUID(),
+            nullable=False,
+        ),
+        sa.Column(
+            "created_at",
+            sa.DateTime(timezone=True),
+            server_default=sa.text("now()"),
+            nullable=False,
+        ),
+        sa.Column(
+            "updated_at",
+            sa.DateTime(timezone=True),
+            server_default=sa.text("now()"),
+            onupdate=sa.text("now()"),
+            nullable=False,
+        ),
+        sa.ForeignKeyConstraint(["user_id"], ["user.id"], ondelete="CASCADE"),
+        sa.PrimaryKeyConstraint("id"),
+        sa.UniqueConstraint("user_id"),
+    )
+    op.create_index(
+        op.f("ix_scim_user_mapping_external_id"),
+        "scim_user_mapping",
+        ["external_id"],
+        unique=True,
+    )
+
+
+def downgrade() -> None:
+    op.drop_index(
+        op.f("ix_scim_user_mapping_external_id"),
+        table_name="scim_user_mapping",
+    )
+    op.drop_table("scim_user_mapping")
+    op.drop_index(
+        op.f("ix_scim_group_mapping_external_id"),
+        table_name="scim_group_mapping",
+    )
+    op.drop_table("scim_group_mapping")
+    op.drop_table("scim_token")

backend/alembic/versions/b51c6844d1df_seed_memory_tool.py

@@ -0,0 +1,81 @@
+"""seed_memory_tool and add enable_memory_tool to user
+
+Revision ID: b51c6844d1df
+Revises: 93c15d6a6fbb
+Create Date: 2026-02-11 00:00:00.000000
+
+"""
+
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision = "b51c6844d1df"
+down_revision = "93c15d6a6fbb"
+branch_labels = None
+depends_on = None
+
+
+MEMORY_TOOL = {
+    "name": "MemoryTool",
+    "display_name": "Add Memory",
+    "description": "Save memories about the user for future conversations.",
+    "in_code_tool_id": "MemoryTool",
+    "enabled": True,
+}
+
+
+def upgrade() -> None:
+    conn = op.get_bind()
+
+    existing = conn.execute(
+        sa.text(
+            "SELECT in_code_tool_id FROM tool WHERE in_code_tool_id = :in_code_tool_id"
+        ),
+        {"in_code_tool_id": MEMORY_TOOL["in_code_tool_id"]},
+    ).fetchone()
+
+    if existing:
+        conn.execute(
+            sa.text(
+                """
+                UPDATE tool
+                SET name = :name,
+                    display_name = :display_name,
+                    description = :description
+                WHERE in_code_tool_id = :in_code_tool_id
+                """
+            ),
+            MEMORY_TOOL,
+        )
+    else:
+        conn.execute(
+            sa.text(
+                """
+                INSERT INTO tool (name, display_name, description, in_code_tool_id, enabled)
+                VALUES (:name, :display_name, :description, :in_code_tool_id, :enabled)
+                """
+            ),
+            MEMORY_TOOL,
+        )
+
+    op.add_column(
+        "user",
+        sa.Column(
+            "enable_memory_tool",
+            sa.Boolean(),
+            nullable=False,
+            server_default=sa.true(),
+        ),
+    )
+
+
+def downgrade() -> None:
+    op.drop_column("user", "enable_memory_tool")
+
+    conn = op.get_bind()
+    conn.execute(
+        sa.text("DELETE FROM tool WHERE in_code_tool_id = :in_code_tool_id"),
+        {"in_code_tool_id": MEMORY_TOOL["in_code_tool_id"]},
+    )

backend/alembic/versions/d3fd499c829c_add_file_reader_tool.py

@@ -0,0 +1,102 @@
+"""add_file_reader_tool
+
+Revision ID: d3fd499c829c
+Revises: 114a638452db
+Create Date: 2026-02-07 19:28:22.452337
+
+"""
+
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision = "d3fd499c829c"
+down_revision = "114a638452db"
+branch_labels = None
+depends_on = None
+
+FILE_READER_TOOL = {
+    "name": "read_file",
+    "display_name": "File Reader",
+    "description": (
+        "Read sections of user-uploaded files by character offset. "
+        "Useful for inspecting large files that cannot fit entirely in context."
+    ),
+    "in_code_tool_id": "FileReaderTool",
+    "enabled": True,
+}
+
+
+def upgrade() -> None:
+    conn = op.get_bind()
+
+    # Check if tool already exists
+    existing = conn.execute(
+        sa.text("SELECT id FROM tool WHERE in_code_tool_id = :in_code_tool_id"),
+        {"in_code_tool_id": FILE_READER_TOOL["in_code_tool_id"]},
+    ).fetchone()
+
+    if existing:
+        # Update existing tool
+        conn.execute(
+            sa.text(
+                """
+                UPDATE tool
+                SET name = :name,
+                    display_name = :display_name,
+                    description = :description
+                WHERE in_code_tool_id = :in_code_tool_id
+                """
+            ),
+            FILE_READER_TOOL,
+        )
+        tool_id = existing[0]
+    else:
+        # Insert new tool
+        result = conn.execute(
+            sa.text(
+                """
+                INSERT INTO tool (name, display_name, description, in_code_tool_id, enabled)
+                VALUES (:name, :display_name, :description, :in_code_tool_id, :enabled)
+                RETURNING id
+                """
+            ),
+            FILE_READER_TOOL,
+        )
+        tool_id = result.scalar_one()
+
+    # Attach to the default persona (id=0) if not already attached
+    conn.execute(
+        sa.text(
+            """
+            INSERT INTO persona__tool (persona_id, tool_id)
+            VALUES (0, :tool_id)
+            ON CONFLICT DO NOTHING
+            """
+        ),
+        {"tool_id": tool_id},
+    )
+
+
+def downgrade() -> None:
+    conn = op.get_bind()
+    in_code_tool_id = FILE_READER_TOOL["in_code_tool_id"]
+
+    # Remove persona associations first (FK constraint)
+    conn.execute(
+        sa.text(
+            """
+            DELETE FROM persona__tool
+            WHERE tool_id IN (
+                SELECT id FROM tool WHERE in_code_tool_id = :in_code_tool_id
+            )
+            """
+        ),
+        {"in_code_tool_id": in_code_tool_id},
+    )
+
+    conn.execute(
+        sa.text("DELETE FROM tool WHERE in_code_tool_id = :in_code_tool_id"),
+        {"in_code_tool_id": in_code_tool_id},
+    )

backend/alembic/versions/d56ffa94ca32_add_file_content.py

@@ -0,0 +1,35 @@
+"""add_file_content
+
+Revision ID: d56ffa94ca32
+Revises: 01f8e6d95a33
+Create Date: 2026-02-06 15:29:34.192960
+
+"""
+
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision = "d56ffa94ca32"
+down_revision = "01f8e6d95a33"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    op.create_table(
+        "file_content",
+        sa.Column(
+            "file_id",
+            sa.String(),
+            sa.ForeignKey("file_record.file_id", ondelete="CASCADE"),
+            primary_key=True,
+        ),
+        sa.Column("lobj_oid", sa.BigInteger(), nullable=False),
+        sa.Column("file_size", sa.BigInteger(), nullable=False, server_default="0"),
+    )
+
+
+def downgrade() -> None:
+    op.drop_table("file_content")

backend/alembic/versions/d5c86e2c6dc6_add_cascade_delete_to_search_query_user_.py

@@ -0,0 +1,35 @@
+"""add_cascade_delete_to_search_query_user_id
+
+Revision ID: d5c86e2c6dc6
+Revises: 90b409d06e50
+Create Date: 2026-02-04 16:05:04.749804
+
+"""
+
+from alembic import op
+
+
+# revision identifiers, used by Alembic.
+revision = "d5c86e2c6dc6"
+down_revision = "90b409d06e50"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    op.drop_constraint("search_query_user_id_fkey", "search_query", type_="foreignkey")
+    op.create_foreign_key(
+        "search_query_user_id_fkey",
+        "search_query",
+        "user",
+        ["user_id"],
+        ["id"],
+        ondelete="CASCADE",
+    )
+
+
+def downgrade() -> None:
+    op.drop_constraint("search_query_user_id_fkey", "search_query", type_="foreignkey")
+    op.create_foreign_key(
+        "search_query_user_id_fkey", "search_query", "user", ["user_id"], ["id"]
+    )

backend/alembic/versions/feead2911109_add_opensearch_tenant_migration_columns.py

@@ -0,0 +1,69 @@
+"""add_opensearch_tenant_migration_columns
+
+Revision ID: feead2911109
+Revises: d56ffa94ca32
+Create Date: 2026-02-10 17:46:34.029937
+
+"""
+
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision = "feead2911109"
+down_revision = "175ea04c7087"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    op.add_column(
+        "opensearch_tenant_migration_record",
+        sa.Column("vespa_visit_continuation_token", sa.Text(), nullable=True),
+    )
+    op.add_column(
+        "opensearch_tenant_migration_record",
+        sa.Column(
+            "total_chunks_migrated",
+            sa.Integer(),
+            nullable=False,
+            server_default="0",
+        ),
+    )
+    op.add_column(
+        "opensearch_tenant_migration_record",
+        sa.Column(
+            "created_at",
+            sa.DateTime(timezone=True),
+            nullable=False,
+            server_default=sa.func.now(),
+        ),
+    )
+    op.add_column(
+        "opensearch_tenant_migration_record",
+        sa.Column(
+            "migration_completed_at",
+            sa.DateTime(timezone=True),
+            nullable=True,
+        ),
+    )
+    op.add_column(
+        "opensearch_tenant_migration_record",
+        sa.Column(
+            "enable_opensearch_retrieval",
+            sa.Boolean(),
+            nullable=False,
+            server_default="false",
+        ),
+    )
+
+
+def downgrade() -> None:
+    op.drop_column("opensearch_tenant_migration_record", "enable_opensearch_retrieval")
+    op.drop_column("opensearch_tenant_migration_record", "migration_completed_at")
+    op.drop_column("opensearch_tenant_migration_record", "created_at")
+    op.drop_column("opensearch_tenant_migration_record", "total_chunks_migrated")
+    op.drop_column(
+        "opensearch_tenant_migration_record", "vespa_visit_continuation_token"
+    )

backend/alembic_tenants/env.py

@@ -39,7 +39,7 @@ EXCLUDE_TABLES = {"kombu_queue", "kombu_message"}
 
 
 def include_object(
-    object: SchemaItem,
+    object: SchemaItem,  # noqa: ARG001
     name: str | None,
     type_: Literal[
         "schema",
@@ -49,8 +49,8 @@ def include_object(
         "unique_constraint",
         "foreign_key_constraint",
     ],
-    reflected: bool,
-    compare_to: SchemaItem | None,
+    reflected: bool,  # noqa: ARG001
+    compare_to: SchemaItem | None,  # noqa: ARG001
 ) -> bool:
     if type_ == "table" and name in EXCLUDE_TABLES:
         return False

backend/ee/LICENSE

@@ -1,20 +1,20 @@
-The DanswerAI Enterprise license (the “Enterprise License”)
+The Onyx Enterprise License (the "Enterprise License")
 Copyright (c) 2023-present DanswerAI, Inc.
 
 With regard to the Onyx Software:
 
 This software and associated documentation files (the "Software") may only be
 used in production, if you (and any entity that you represent) have agreed to,
-and are in compliance with, the DanswerAI Subscription Terms of Service, available
-at https://onyx.app/terms (the “Enterprise Terms”), or other
+and are in compliance with, the Onyx Subscription Terms of Service, available
+at https://www.onyx.app/legal/self-host (the "Enterprise Terms"), or other
 agreement governing the use of the Software, as agreed by you and DanswerAI,
-and otherwise have a valid Onyx Enterprise license for the
+and otherwise have a valid Onyx Enterprise License for the
 correct number of user seats. Subject to the foregoing sentence, you are free to
 modify this Software and publish patches to the Software. You agree that DanswerAI
 and/or its licensors (as applicable) retain all right, title and interest in and
 to all such modifications and/or patches, and all such modifications and/or
 patches may only be used, copied, modified, displayed, distributed, or otherwise
-exploited with a valid Onyx Enterprise license for the correct
+exploited with a valid Onyx Enterprise License for the correct
 number of user seats. Notwithstanding the foregoing, you may copy and modify
 the Software for development and testing purposes, without requiring a
 subscription. You agree that DanswerAI and/or its licensors (as applicable) retain

backend/ee/onyx/background/celery/apps/background.py

@@ -1,12 +1,15 @@
+from onyx.background.celery.apps import app_base
 from onyx.background.celery.apps.background import celery_app
 
 
 celery_app.autodiscover_tasks(
-    [
-        "ee.onyx.background.celery.tasks.doc_permission_syncing",
-        "ee.onyx.background.celery.tasks.external_group_syncing",
-        "ee.onyx.background.celery.tasks.cleanup",
-        "ee.onyx.background.celery.tasks.tenant_provisioning",
-        "ee.onyx.background.celery.tasks.query_history",
-    ]
+    app_base.filter_task_modules(
+        [
+            "ee.onyx.background.celery.tasks.doc_permission_syncing",
+            "ee.onyx.background.celery.tasks.external_group_syncing",
+            "ee.onyx.background.celery.tasks.cleanup",
+            "ee.onyx.background.celery.tasks.tenant_provisioning",
+            "ee.onyx.background.celery.tasks.query_history",
+        ]
+    )
 )

backend/ee/onyx/background/celery/apps/heavy.py

@@ -1,11 +1,14 @@
+from onyx.background.celery.apps import app_base
 from onyx.background.celery.apps.heavy import celery_app
 
 
 celery_app.autodiscover_tasks(
-    [
-        "ee.onyx.background.celery.tasks.doc_permission_syncing",
-        "ee.onyx.background.celery.tasks.external_group_syncing",
-        "ee.onyx.background.celery.tasks.cleanup",
-        "ee.onyx.background.celery.tasks.query_history",
-    ]
+    app_base.filter_task_modules(
+        [
+            "ee.onyx.background.celery.tasks.doc_permission_syncing",
+            "ee.onyx.background.celery.tasks.external_group_syncing",
+            "ee.onyx.background.celery.tasks.cleanup",
+            "ee.onyx.background.celery.tasks.query_history",
+        ]
+    )
 )

backend/ee/onyx/background/celery/apps/light.py

@@ -1,8 +1,11 @@
+from onyx.background.celery.apps import app_base
 from onyx.background.celery.apps.light import celery_app
 
 celery_app.autodiscover_tasks(
-    [
-        "ee.onyx.background.celery.tasks.doc_permission_syncing",
-        "ee.onyx.background.celery.tasks.external_group_syncing",
-    ]
+    app_base.filter_task_modules(
+        [
+            "ee.onyx.background.celery.tasks.doc_permission_syncing",
+            "ee.onyx.background.celery.tasks.external_group_syncing",
+        ]
+    )
 )

backend/ee/onyx/background/celery/apps/monitoring.py

@@ -1,7 +1,10 @@
+from onyx.background.celery.apps import app_base
 from onyx.background.celery.apps.monitoring import celery_app
 
 celery_app.autodiscover_tasks(
-    [
-        "ee.onyx.background.celery.tasks.tenant_provisioning",
-    ]
+    app_base.filter_task_modules(
+        [
+            "ee.onyx.background.celery.tasks.tenant_provisioning",
+        ]
+    )
 )

backend/ee/onyx/background/celery/apps/primary.py

@@ -1,12 +1,15 @@
+from onyx.background.celery.apps import app_base
 from onyx.background.celery.apps.primary import celery_app
 
 
 celery_app.autodiscover_tasks(
-    [
-        "ee.onyx.background.celery.tasks.doc_permission_syncing",
-        "ee.onyx.background.celery.tasks.external_group_syncing",
-        "ee.onyx.background.celery.tasks.cloud",
-        "ee.onyx.background.celery.tasks.ttl_management",
-        "ee.onyx.background.celery.tasks.usage_reporting",
-    ]
+    app_base.filter_task_modules(
+        [
+            "ee.onyx.background.celery.tasks.doc_permission_syncing",
+            "ee.onyx.background.celery.tasks.external_group_syncing",
+            "ee.onyx.background.celery.tasks.cloud",
+            "ee.onyx.background.celery.tasks.ttl_management",
+            "ee.onyx.background.celery.tasks.usage_reporting",
+        ]
+    )
 )

backend/ee/onyx/background/celery/tasks/doc_permission_syncing/tasks.py

@@ -536,7 +536,9 @@ def connector_permission_sync_generator_task(
             )
             redis_connector.permissions.set_fence(new_payload)
 
-            callback = PermissionSyncCallback(redis_connector, lock, r)
+            callback = PermissionSyncCallback(
+                redis_connector, lock, r, timeout_seconds=JOB_TIMEOUT
+            )
 
             # pass in the capability to fetch all existing docs for the cc_pair
             # this is can be used to determine documents that are "missing" and thus
@@ -576,6 +578,13 @@ def connector_permission_sync_generator_task(
             tasks_generated = 0
             docs_with_errors = 0
             for doc_external_access in document_external_accesses:
+                if callback.should_stop():
+                    raise RuntimeError(
+                        f"Permission sync task timed out or stop signal detected: "
+                        f"cc_pair={cc_pair_id} "
+                        f"tasks_generated={tasks_generated}"
+                    )
+
                 result = redis_connector.permissions.update_db(
                     lock=lock,
                     new_permissions=[doc_external_access],
@@ -932,6 +941,7 @@ class PermissionSyncCallback(IndexingHeartbeatInterface):
         redis_connector: RedisConnector,
         redis_lock: RedisLock,
         redis_client: Redis,
+        timeout_seconds: int | None = None,
     ):
         super().__init__()
         self.redis_connector: RedisConnector = redis_connector
@@ -944,14 +954,29 @@ class PermissionSyncCallback(IndexingHeartbeatInterface):
         self.last_tag: str = "PermissionSyncCallback.__init__"
         self.last_lock_reacquire: datetime = datetime.now(timezone.utc)
         self.last_lock_monotonic = time.monotonic()
+        self.start_monotonic = time.monotonic()
+        self.timeout_seconds = timeout_seconds
 
     def should_stop(self) -> bool:
         if self.redis_connector.stop.fenced:
             return True
 
+        # Check if the task has exceeded its timeout
+        # NOTE: Celery's soft_time_limit does not work with thread pools,
+        # so we must enforce timeouts internally.
+        if self.timeout_seconds is not None:
+            elapsed = time.monotonic() - self.start_monotonic
+            if elapsed > self.timeout_seconds:
+                logger.warning(
+                    f"PermissionSyncCallback - task timeout exceeded: "
+                    f"elapsed={elapsed:.0f}s timeout={self.timeout_seconds}s "
+                    f"cc_pair={self.redis_connector.cc_pair_id}"
+                )
+                return True
+
         return False
 
-    def progress(self, tag: str, amount: int) -> None:
+    def progress(self, tag: str, amount: int) -> None:  # noqa: ARG002
         try:
             self.redis_connector.permissions.set_active()
 
@@ -982,7 +1007,7 @@ class PermissionSyncCallback(IndexingHeartbeatInterface):
 
 
 def monitor_ccpair_permissions_taskset(
-    tenant_id: str, key_bytes: bytes, r: Redis, db_session: Session
+    tenant_id: str, key_bytes: bytes, r: Redis, db_session: Session  # noqa: ARG001
 ) -> None:
     fence_key = key_bytes.decode("utf-8")
     cc_pair_id_str = RedisConnector.get_id_from_fence_key(fence_key)

backend/ee/onyx/background/celery/tasks/external_group_syncing/tasks.py

@@ -259,7 +259,7 @@ def check_for_external_group_sync(self: Task, *, tenant_id: str) -> bool | None:
 def try_creating_external_group_sync_task(
     app: Celery,
     cc_pair_id: int,
-    r: Redis,
+    r: Redis,  # noqa: ARG001
     tenant_id: str,
 ) -> str | None:
     """Returns an int if syncing is needed. The int represents the number of sync tasks generated.
@@ -344,7 +344,7 @@ def try_creating_external_group_sync_task(
     bind=True,
 )
 def connector_external_group_sync_generator_task(
-    self: Task,
+    self: Task,  # noqa: ARG001
     cc_pair_id: int,
     tenant_id: str,
 ) -> None:
@@ -466,6 +466,7 @@ def connector_external_group_sync_generator_task(
 def _perform_external_group_sync(
     cc_pair_id: int,
     tenant_id: str,
+    timeout_seconds: int = JOB_TIMEOUT,
 ) -> None:
     # Create attempt record at the start
     with get_session_with_current_tenant() as db_session:
@@ -518,9 +519,23 @@ def _perform_external_group_sync(
         seen_users: set[str] = set()  # Track unique users across all groups
         total_groups_processed = 0
         total_group_memberships_synced = 0
+        start_time = time.monotonic()
         try:
             external_user_group_generator = ext_group_sync_func(tenant_id, cc_pair)
             for external_user_group in external_user_group_generator:
+                # Check if the task has exceeded its timeout
+                # NOTE: Celery's soft_time_limit does not work with thread pools,
+                # so we must enforce timeouts internally.
+                elapsed = time.monotonic() - start_time
+                if elapsed > timeout_seconds:
+                    raise RuntimeError(
+                        f"External group sync task timed out: "
+                        f"cc_pair={cc_pair_id} "
+                        f"elapsed={elapsed:.0f}s "
+                        f"timeout={timeout_seconds}s "
+                        f"groups_processed={total_groups_processed}"
+                    )
+
                 external_user_group_batch.append(external_user_group)
 
                 # Track progress
@@ -590,8 +605,8 @@ def _perform_external_group_sync(
 
 def validate_external_group_sync_fences(
     tenant_id: str,
-    celery_app: Celery,
-    r: Redis,
+    celery_app: Celery,  # noqa: ARG001
+    r: Redis,  # noqa: ARG001
     r_replica: Redis,
     r_celery: Redis,
     lock_beat: RedisLock,

backend/ee/onyx/background/celery/tasks/query_history/tasks.py

@@ -40,7 +40,7 @@ def export_query_history_task(
     end: datetime,
     start_time: datetime,
     # Need to include the tenant_id since the TenantAwareTask needs this
-    tenant_id: str,
+    tenant_id: str,  # noqa: ARG001
 ) -> None:
     if not self.request.id:
         raise RuntimeError("No task id defined for this task; cannot identify it")

backend/ee/onyx/background/celery/tasks/tenant_provisioning/tasks.py

@@ -43,7 +43,7 @@ _TENANT_PROVISIONING_TIME_LIMIT = 60 * 10  # 10 minutes
     trail=False,
     bind=True,
 )
-def check_available_tenants(self: Task) -> None:
+def check_available_tenants(self: Task) -> None:  # noqa: ARG001
     """
     Check if we have enough pre-provisioned tenants available.
     If not, trigger the pre-provisioning of new tenants.

backend/ee/onyx/background/celery/tasks/usage_reporting/tasks.py

@@ -21,9 +21,9 @@ logger = setup_logger()
     trail=False,
 )
 def generate_usage_report_task(
-    self: Task,
+    self: Task,  # noqa: ARG001
     *,
-    tenant_id: str,
+    tenant_id: str,  # noqa: ARG001
     user_id: str | None = None,
     period_from: str | None = None,
     period_to: str | None = None,

backend/ee/onyx/background/task_name_builders.py

@@ -7,7 +7,7 @@ QUERY_HISTORY_TASK_NAME_PREFIX = OnyxCeleryTask.EXPORT_QUERY_HISTORY_TASK
 
 
 def name_chat_ttl_task(
-    retention_limit_days: float, tenant_id: str | None = None
+    retention_limit_days: float, tenant_id: str | None = None  # noqa: ARG001
 ) -> str:
     return f"chat_ttl_{retention_limit_days}_days"
 

backend/ee/onyx/configs/app_configs.py

@@ -134,7 +134,7 @@ GATED_TENANTS_KEY = "gated_tenants"
 
 # License enforcement - when True, blocks API access for gated/expired licenses
 LICENSE_ENFORCEMENT_ENABLED = (
-    os.environ.get("LICENSE_ENFORCEMENT_ENABLED", "").lower() == "true"
+    os.environ.get("LICENSE_ENFORCEMENT_ENABLED", "true").lower() == "true"
 )
 
 # Cloud data plane URL - self-hosted instances call this to reach cloud proxy endpoints

backend/ee/onyx/db/document_set.py

@@ -54,7 +54,7 @@ def delete_document_set_privacy__no_commit(
 def fetch_document_sets(
     user_id: UUID | None,
     db_session: Session,
-    include_outdated: bool = True,  # Parameter only for versioned implementation, unused
+    include_outdated: bool = True,  # Parameter only for versioned implementation, unused  # noqa: ARG001
 ) -> list[tuple[DocumentSet, list[ConnectorCredentialPair]]]:
     assert user_id is not None
 

backend/ee/onyx/db/hierarchy.py

@@ -5,8 +5,10 @@ It filters hierarchy nodes based on user email and external group membership.
 """
 
 from sqlalchemy import any_
+from sqlalchemy import cast
 from sqlalchemy import or_
 from sqlalchemy import select
+from sqlalchemy import String
 from sqlalchemy.dialects import postgresql
 from sqlalchemy.orm import Session
 from sqlalchemy.sql.elements import ColumnElement
@@ -32,7 +34,7 @@ def _build_hierarchy_access_filter(
     if external_group_ids:
         access_filters.append(
             HierarchyNode.external_user_group_ids.overlap(
-                postgresql.array(external_group_ids)
+                cast(postgresql.array(external_group_ids), postgresql.ARRAY(String))
             )
         )
     return or_(*access_filters)

backend/ee/onyx/db/license.py

@@ -11,6 +11,7 @@ from ee.onyx.server.license.models import LicenseMetadata
 from ee.onyx.server.license.models import LicensePayload
 from ee.onyx.server.license.models import LicenseSource
 from onyx.auth.schemas import UserRole
+from onyx.configs.constants import ANONYMOUS_USER_EMAIL
 from onyx.db.models import License
 from onyx.db.models import User
 from onyx.redis.redis_pool import get_redis_client
@@ -107,7 +108,8 @@ def get_used_seats(tenant_id: str | None = None) -> int:
     Get current seat usage directly from database.
 
     For multi-tenant: counts users in UserTenantMapping for this tenant.
-    For self-hosted: counts all active users (excludes EXT_PERM_USER role).
+    For self-hosted: counts all active users (excludes EXT_PERM_USER role
+    and the anonymous system user).
 
     TODO: Exclude API key dummy users from seat counting. API keys create
     users with emails like `__DANSWER_API_KEY_*` that should not count toward
@@ -127,6 +129,7 @@ def get_used_seats(tenant_id: str | None = None) -> int:
                 .where(
                     User.is_active == True,  # type: ignore  # noqa: E712
                     User.role != UserRole.EXT_PERM_USER,
+                    User.email != ANONYMOUS_USER_EMAIL,  # type: ignore
                 )
             )
             return result.scalar() or 0

backend/ee/onyx/db/user_group.py

@@ -643,7 +643,7 @@ def add_users_to_user_group(
 
 def update_user_group(
     db_session: Session,
-    user: User,
+    user: User,  # noqa: ARG001
     user_group_id: int,
     user_group_update: UserGroupUpdate,
 ) -> UserGroup:

backend/ee/onyx/external_permissions/confluence/doc_sync.py

@@ -25,7 +25,7 @@ CONFLUENCE_DOC_SYNC_LABEL = "confluence_doc_sync"
 
 def confluence_doc_sync(
     cc_pair: ConnectorCredentialPair,
-    fetch_all_existing_docs_fn: FetchAllDocumentsFunction,
+    fetch_all_existing_docs_fn: FetchAllDocumentsFunction,  # noqa: ARG001
     fetch_all_existing_docs_ids_fn: FetchAllDocumentsIdsFunction,
     callback: IndexingHeartbeatInterface | None,
 ) -> Generator[ElementExternalAccess, None, None]:

backend/ee/onyx/external_permissions/confluence/page_access.py

@@ -1,6 +1,8 @@
 from typing import Any
 
 from onyx.access.models import ExternalAccess
+from onyx.access.utils import build_ext_group_name_for_onyx
+from onyx.configs.constants import DocumentSource
 from onyx.connectors.confluence.onyx_confluence import (
     get_user_email_from_username__server,
 )
@@ -72,6 +74,7 @@ def get_page_restrictions(
     page_id: str,
     page_restrictions: dict[str, Any],
     ancestors: list[dict[str, Any]],
+    add_prefix: bool = False,
 ) -> ExternalAccess | None:
     """
     This function gets the restrictions for a page. In Confluence, a child can have
@@ -79,6 +82,9 @@ def get_page_restrictions(
 
     If no restrictions are found anywhere, then return None, indicating that the page
     should inherit the space's restrictions.
+
+    add_prefix: When True, prefix group IDs with source type (for indexing path).
+               When False (default), leave unprefixed (for permission sync path).
     """
     found_user_emails: set[str] = set()
     found_group_names: set[str] = set()
@@ -92,13 +98,22 @@ def get_page_restrictions(
             restrictions=page_restrictions,
         )
     )
+
+    def _maybe_prefix_groups(group_names: set[str]) -> set[str]:
+        if add_prefix:
+            return {
+                build_ext_group_name_for_onyx(g, DocumentSource.CONFLUENCE)
+                for g in group_names
+            }
+        return group_names
+
     # if there are individual page-level restrictions, then this is the accurate
     # restriction for the page. You cannot both have page-level restrictions AND
     # inherit restrictions from the parent.
     if found_any_page_level_restriction:
         return ExternalAccess(
             external_user_emails=found_user_emails,
-            external_user_group_ids=found_group_names,
+            external_user_group_ids=_maybe_prefix_groups(found_group_names),
             is_public=False,
         )
 
@@ -125,7 +140,7 @@ def get_page_restrictions(
             )
             return ExternalAccess(
                 external_user_emails=ancestor_user_emails,
-                external_user_group_ids=ancestor_group_names,
+                external_user_group_ids=_maybe_prefix_groups(ancestor_group_names),
                 is_public=False,
             )
 

backend/ee/onyx/external_permissions/confluence/space_access.py

@@ -3,6 +3,8 @@ from ee.onyx.external_permissions.confluence.constants import ALL_CONF_EMAILS_GR
 from ee.onyx.external_permissions.confluence.constants import REQUEST_PAGINATION_LIMIT
 from ee.onyx.external_permissions.confluence.constants import VIEWSPACE_PERMISSION_TYPE
 from onyx.access.models import ExternalAccess
+from onyx.access.utils import build_ext_group_name_for_onyx
+from onyx.configs.constants import DocumentSource
 from onyx.connectors.confluence.onyx_confluence import (
     get_user_email_from_username__server,
 )
@@ -112,6 +114,7 @@ def get_space_permission(
     confluence_client: OnyxConfluence,
     space_key: str,
     is_cloud: bool,
+    add_prefix: bool = False,
 ) -> ExternalAccess:
     if is_cloud:
         space_permissions = _get_cloud_space_permissions(confluence_client, space_key)
@@ -130,13 +133,32 @@ def get_space_permission(
             f"permissions for space '{space_key}'"
         )
 
+    # Prefix group IDs with source type if requested (for indexing path)
+    if add_prefix and space_permissions.external_user_group_ids:
+        prefixed_groups = {
+            build_ext_group_name_for_onyx(g, DocumentSource.CONFLUENCE)
+            for g in space_permissions.external_user_group_ids
+        }
+        return ExternalAccess(
+            external_user_emails=space_permissions.external_user_emails,
+            external_user_group_ids=prefixed_groups,
+            is_public=space_permissions.is_public,
+        )
+
     return space_permissions
 
 
 def get_all_space_permissions(
     confluence_client: OnyxConfluence,
     is_cloud: bool,
+    add_prefix: bool = False,
 ) -> dict[str, ExternalAccess]:
+    """
+    Get access permissions for all spaces in Confluence.
+
+    add_prefix: When True, prefix group IDs with source type (for indexing path).
+               When False (default), leave unprefixed (for permission sync path).
+    """
     logger.debug("Getting space permissions")
     # Gets all the spaces in the Confluence instance
     all_space_keys = [
@@ -151,7 +173,9 @@ def get_all_space_permissions(
     logger.debug(f"Got {len(all_space_keys)} spaces from confluence")
     space_permissions_by_space_key: dict[str, ExternalAccess] = {}
     for space_key in all_space_keys:
-        space_permissions = get_space_permission(confluence_client, space_key, is_cloud)
+        space_permissions = get_space_permission(
+            confluence_client, space_key, is_cloud, add_prefix
+        )
 
         # Stores the permissions for each space
         space_permissions_by_space_key[space_key] = space_permissions

backend/ee/onyx/external_permissions/github/doc_sync.py

@@ -34,7 +34,7 @@ GITHUB_DOC_SYNC_LABEL = "github_doc_sync"
 def github_doc_sync(
     cc_pair: ConnectorCredentialPair,
     fetch_all_existing_docs_fn: FetchAllDocumentsFunction,
-    fetch_all_existing_docs_ids_fn: FetchAllDocumentsIdsFunction,
+    fetch_all_existing_docs_ids_fn: FetchAllDocumentsIdsFunction,  # noqa: ARG001
     callback: IndexingHeartbeatInterface | None = None,
 ) -> Generator[DocExternalAccess, None, None]:
     """
@@ -50,7 +50,12 @@ def github_doc_sync(
         **cc_pair.connector.connector_specific_config
     )
 
-    github_connector.load_credentials(cc_pair.credential.credential_json)
+    credential_json = (
+        cc_pair.credential.credential_json.get_value(apply_mask=False)
+        if cc_pair.credential.credential_json
+        else {}
+    )
+    github_connector.load_credentials(credential_json)
     logger.info("GitHub connector credentials loaded successfully")
 
     if not github_connector.github_client:
@@ -60,21 +65,7 @@ def github_doc_sync(
     # Get all repositories from GitHub API
     logger.info("Fetching all repositories from GitHub API")
     try:
-        repos = []
-        if github_connector.repositories:
-            if "," in github_connector.repositories:
-                # Multiple repositories specified
-                repos = github_connector.get_github_repos(
-                    github_connector.github_client
-                )
-            else:
-                # Single repository
-                repos = [
-                    github_connector.get_github_repo(github_connector.github_client)
-                ]
-        else:
-            # All repositories
-            repos = github_connector.get_all_repos(github_connector.github_client)
+        repos = github_connector.fetch_configured_repos()
 
         logger.info(f"Found {len(repos)} repositories to check")
     except Exception as e:

backend/ee/onyx/external_permissions/github/group_sync.py

@@ -12,13 +12,18 @@ logger = setup_logger()
 
 
 def github_group_sync(
-    tenant_id: str,
+    tenant_id: str,  # noqa: ARG001
     cc_pair: ConnectorCredentialPair,
 ) -> Generator[ExternalUserGroup, None, None]:
     github_connector: GithubConnector = GithubConnector(
         **cc_pair.connector.connector_specific_config
     )
-    github_connector.load_credentials(cc_pair.credential.credential_json)
+    credential_json = (
+        cc_pair.credential.credential_json.get_value(apply_mask=False)
+        if cc_pair.credential.credential_json
+        else {}
+    )
+    github_connector.load_credentials(credential_json)
     if not github_connector.github_client:
         raise ValueError("github_client is required")
 

backend/ee/onyx/external_permissions/github/utils.py

@@ -91,7 +91,7 @@ class TeamInfo(BaseModel):
 
 
 def _fetch_organization_members(
-    github_client: Github, org_name: str, retry_count: int = 0
+    github_client: Github, org_name: str, retry_count: int = 0  # noqa: ARG001
 ) -> List[UserInfo]:
     """Fetch all organization members including owners and regular members."""
     org_members: List[UserInfo] = []
@@ -124,7 +124,7 @@ def _fetch_organization_members(
 
 
 def _fetch_repository_teams_detailed(
-    repo: Repository, github_client: Github, retry_count: int = 0
+    repo: Repository, github_client: Github, retry_count: int = 0  # noqa: ARG001
 ) -> List[TeamInfo]:
     """Fetch teams with access to the repository and their members."""
     teams_data: List[TeamInfo] = []
@@ -167,7 +167,7 @@ def _fetch_repository_teams_detailed(
 
 
 def fetch_repository_team_slugs(
-    repo: Repository, github_client: Github, retry_count: int = 0
+    repo: Repository, github_client: Github, retry_count: int = 0  # noqa: ARG001
 ) -> List[str]:
     """Fetch team slugs with access to the repository."""
     logger.info(f"Fetching team slugs for repository {repo.full_name}")

backend/ee/onyx/external_permissions/gmail/doc_sync.py

@@ -39,8 +39,8 @@ def _get_slim_doc_generator(
 
 def gmail_doc_sync(
     cc_pair: ConnectorCredentialPair,
-    fetch_all_existing_docs_fn: FetchAllDocumentsFunction,
-    fetch_all_existing_docs_ids_fn: FetchAllDocumentsIdsFunction,
+    fetch_all_existing_docs_fn: FetchAllDocumentsFunction,  # noqa: ARG001
+    fetch_all_existing_docs_ids_fn: FetchAllDocumentsIdsFunction,  # noqa: ARG001
     callback: IndexingHeartbeatInterface | None,
 ) -> Generator[ElementExternalAccess, None, None]:
     """
@@ -50,7 +50,12 @@ def gmail_doc_sync(
     already populated.
     """
     gmail_connector = GmailConnector(**cc_pair.connector.connector_specific_config)
-    gmail_connector.load_credentials(cc_pair.credential.credential_json)
+    credential_json = (
+        cc_pair.credential.credential_json.get_value(apply_mask=False)
+        if cc_pair.credential.credential_json
+        else {}
+    )
+    gmail_connector.load_credentials(credential_json)
 
     slim_doc_generator = _get_slim_doc_generator(
         cc_pair, gmail_connector, callback=callback

backend/ee/onyx/external_permissions/google_drive/doc_sync.py

@@ -13,6 +13,7 @@ from onyx.access.models import DocExternalAccess
 from onyx.access.models import ElementExternalAccess
 from onyx.access.models import ExternalAccess
 from onyx.access.models import NodeExternalAccess
+from onyx.access.utils import build_ext_group_name_for_onyx
 from onyx.configs.constants import DocumentSource
 from onyx.connectors.google_drive.connector import GoogleDriveConnector
 from onyx.connectors.google_drive.models import GoogleDriveFileType
@@ -67,11 +68,17 @@ def get_external_access_for_raw_gdrive_file(
     company_domain: str,
     retriever_drive_service: GoogleDriveService | None,
     admin_drive_service: GoogleDriveService,
+    add_prefix: bool = False,
 ) -> ExternalAccess:
     """
     Get the external access for a raw Google Drive file.
 
     Assumes the file we retrieved has EITHER `permissions` or `permission_ids`
+
+    add_prefix: When this method is called during the initial indexing via the connector,
+                set add_prefix to True so group IDs are prefixed with the source type.
+                When invoked from doc_sync (permission sync), use the default (False)
+                since upsert_document_external_perms handles prefixing.
     """
     doc_id = file.get("id")
     if not doc_id:
@@ -164,6 +171,13 @@ def get_external_access_for_raw_gdrive_file(
         | ({drive_id} if drive_id is not None else set())
     )
 
+    # Prefix group IDs with source type if requested (for indexing path)
+    if add_prefix:
+        group_ids = {
+            build_ext_group_name_for_onyx(group_id, DocumentSource.GOOGLE_DRIVE)
+            for group_id in group_ids
+        }
+
     return ExternalAccess(
         external_user_emails=user_emails,
         external_user_group_ids=group_ids,
@@ -175,6 +189,7 @@ def get_external_access_for_folder(
     folder: GoogleDriveFileType,
     google_domain: str,
     drive_service: GoogleDriveService,
+    add_prefix: bool = False,
 ) -> ExternalAccess:
     """
     Extract ExternalAccess from a folder's permissions.
@@ -186,6 +201,8 @@ def get_external_access_for_folder(
         folder: The folder metadata from Google Drive API (must include permissionIds field)
         google_domain: The company's Google Workspace domain (e.g., "company.com")
         drive_service: Google Drive service for fetching permission details
+        add_prefix: When True, prefix group IDs with source type (for indexing path).
+                   When False (default), leave unprefixed (for permission sync path).
 
     Returns:
         ExternalAccess with extracted permission info
@@ -248,17 +265,25 @@ def get_external_access_for_folder(
             # If allowFileDiscovery is False, it's "link only" access
             is_public = permission.allow_file_discovery is not False
 
+    # Prefix group IDs with source type if requested (for indexing path)
+    group_ids: set[str] = group_emails
+    if add_prefix:
+        group_ids = {
+            build_ext_group_name_for_onyx(group_id, DocumentSource.GOOGLE_DRIVE)
+            for group_id in group_emails
+        }
+
     return ExternalAccess(
         external_user_emails=user_emails,
-        external_user_group_ids=group_emails,
+        external_user_group_ids=group_ids,
         is_public=is_public,
     )
 
 
 def gdrive_doc_sync(
     cc_pair: ConnectorCredentialPair,
-    fetch_all_existing_docs_fn: FetchAllDocumentsFunction,
-    fetch_all_existing_docs_ids_fn: FetchAllDocumentsIdsFunction,
+    fetch_all_existing_docs_fn: FetchAllDocumentsFunction,  # noqa: ARG001
+    fetch_all_existing_docs_ids_fn: FetchAllDocumentsIdsFunction,  # noqa: ARG001
     callback: IndexingHeartbeatInterface | None,
 ) -> Generator[ElementExternalAccess, None, None]:
     """
@@ -270,7 +295,12 @@ def gdrive_doc_sync(
     google_drive_connector = GoogleDriveConnector(
         **cc_pair.connector.connector_specific_config
     )
-    google_drive_connector.load_credentials(cc_pair.credential.credential_json)
+    credential_json = (
+        cc_pair.credential.credential_json.get_value(apply_mask=False)
+        if cc_pair.credential.credential_json
+        else {}
+    )
+    google_drive_connector.load_credentials(credential_json)
 
     slim_doc_generator = _get_slim_doc_generator(cc_pair, google_drive_connector)
 

backend/ee/onyx/external_permissions/google_drive/group_sync.py

@@ -384,14 +384,19 @@ def _build_onyx_groups(
 
 
 def gdrive_group_sync(
-    tenant_id: str,
+    tenant_id: str,  # noqa: ARG001
     cc_pair: ConnectorCredentialPair,
 ) -> Generator[ExternalUserGroup, None, None]:
     # Initialize connector and build credential/service objects
     google_drive_connector = GoogleDriveConnector(
         **cc_pair.connector.connector_specific_config
     )
-    google_drive_connector.load_credentials(cc_pair.credential.credential_json)
+    credential_json = (
+        cc_pair.credential.credential_json.get_value(apply_mask=False)
+        if cc_pair.credential.credential_json
+        else {}
+    )
+    google_drive_connector.load_credentials(credential_json)
     admin_service = get_admin_service(
         google_drive_connector.creds, google_drive_connector.primary_admin_email
     )

backend/ee/onyx/external_permissions/jira/doc_sync.py

@@ -17,14 +17,19 @@ JIRA_DOC_SYNC_TAG = "jira_doc_sync"
 
 def jira_doc_sync(
     cc_pair: ConnectorCredentialPair,
-    fetch_all_existing_docs_fn: FetchAllDocumentsFunction,
+    fetch_all_existing_docs_fn: FetchAllDocumentsFunction,  # noqa: ARG001
     fetch_all_existing_docs_ids_fn: FetchAllDocumentsIdsFunction,
     callback: IndexingHeartbeatInterface | None = None,
 ) -> Generator[ElementExternalAccess, None, None]:
     jira_connector = JiraConnector(
         **cc_pair.connector.connector_specific_config,
     )
-    jira_connector.load_credentials(cc_pair.credential.credential_json)
+    credential_json = (
+        cc_pair.credential.credential_json.get_value(apply_mask=False)
+        if cc_pair.credential.credential_json
+        else {}
+    )
+    jira_connector.load_credentials(credential_json)
 
     yield from generic_doc_sync(
         cc_pair=cc_pair,

backend/ee/onyx/external_permissions/jira/group_sync.py

@@ -102,7 +102,7 @@ def _build_group_member_email_map(
 
 
 def jira_group_sync(
-    tenant_id: str,
+    tenant_id: str,  # noqa: ARG001
     cc_pair: ConnectorCredentialPair,
 ) -> Generator[ExternalUserGroup, None, None]:
     """
@@ -119,8 +119,13 @@ def jira_group_sync(
     if not jira_base_url:
         raise ValueError("No jira_base_url found in connector config")
 
+    credential_json = (
+        cc_pair.credential.credential_json.get_value(apply_mask=False)
+        if cc_pair.credential.credential_json
+        else {}
+    )
     jira_client = build_jira_client(
-        credentials=cc_pair.credential.credential_json,
+        credentials=credential_json,
         jira_base=jira_base_url,
         scoped_token=scoped_token,
     )

backend/ee/onyx/external_permissions/jira/page_access.py

@@ -8,6 +8,8 @@ from ee.onyx.external_permissions.jira.models import Holder
 from ee.onyx.external_permissions.jira.models import Permission
 from ee.onyx.external_permissions.jira.models import User
 from onyx.access.models import ExternalAccess
+from onyx.access.utils import build_ext_group_name_for_onyx
+from onyx.configs.constants import DocumentSource
 from onyx.utils.logger import setup_logger
 
 HolderMap = dict[str, list[Holder]]
@@ -252,7 +254,14 @@ def _build_external_access_from_holder_map(
 def get_project_permissions(
     jira_client: JIRA,
     jira_project: str,
+    add_prefix: bool = False,
 ) -> ExternalAccess | None:
+    """
+    Get project permissions from Jira.
+
+    add_prefix: When True, prefix group IDs with source type (for indexing path).
+               When False (default), leave unprefixed (for permission sync path).
+    """
     project_permissions: PermissionScheme = jira_client.project_permissionscheme(
         project=jira_project
     )
@@ -267,6 +276,20 @@ def get_project_permissions(
 
     holder_map = _build_holder_map(permissions=project_permissions.permissions)
 
-    return _build_external_access_from_holder_map(
+    external_access = _build_external_access_from_holder_map(
         jira_client=jira_client, jira_project=jira_project, holder_map=holder_map
     )
+
+    # Prefix group IDs with source type if requested (for indexing path)
+    if add_prefix and external_access and external_access.external_user_group_ids:
+        prefixed_groups = {
+            build_ext_group_name_for_onyx(g, DocumentSource.JIRA)
+            for g in external_access.external_user_group_ids
+        }
+        return ExternalAccess(
+            external_user_emails=external_access.external_user_emails,
+            external_user_group_ids=prefixed_groups,
+            is_public=external_access.is_public,
+        )
+
+    return external_access

backend/ee/onyx/external_permissions/salesforce/postprocessing.py

@@ -23,7 +23,7 @@ ContentRange = tuple[int, int | None]  # (start_index, end_index) None means to
 
 # NOTE: Used for testing timing
 def _get_dummy_object_access_map(
-    object_ids: set[str], user_email: str, chunks: list[InferenceChunk]
+    object_ids: set[str], user_email: str, chunks: list[InferenceChunk]  # noqa: ARG001
 ) -> dict[str, bool]:
     time.sleep(0.15)
     # return {object_id: True for object_id in object_ids}

backend/ee/onyx/external_permissions/salesforce/utils.py

@@ -30,7 +30,11 @@ def get_any_salesforce_client_for_doc_id(
     if _ANY_SALESFORCE_CLIENT is None:
         cc_pairs = get_cc_pairs_for_document(db_session, doc_id)
         first_cc_pair = cc_pairs[0]
-        credential_json = first_cc_pair.credential.credential_json
+        credential_json = (
+            first_cc_pair.credential.credential_json.get_value(apply_mask=False)
+            if first_cc_pair.credential.credential_json
+            else {}
+        )
         _ANY_SALESFORCE_CLIENT = Salesforce(
             username=credential_json["sf_username"],
             password=credential_json["sf_password"],
@@ -158,7 +162,11 @@ def _get_salesforce_client_for_doc_id(db_session: Session, doc_id: str) -> Sales
         )
         if cc_pair is None:
             raise ValueError(f"CC pair {cc_pair_id} not found")
-        credential_json = cc_pair.credential.credential_json
+        credential_json = (
+            cc_pair.credential.credential_json.get_value(apply_mask=False)
+            if cc_pair.credential.credential_json
+            else {}
+        )
         _CC_PAIR_ID_SALESFORCE_CLIENT_MAP[cc_pair_id] = Salesforce(
             username=credential_json["sf_username"],
             password=credential_json["sf_password"],

backend/ee/onyx/external_permissions/sharepoint/doc_sync.py

@@ -17,14 +17,19 @@ SHAREPOINT_DOC_SYNC_TAG = "sharepoint_doc_sync"
 
 def sharepoint_doc_sync(
     cc_pair: ConnectorCredentialPair,
-    fetch_all_existing_docs_fn: FetchAllDocumentsFunction,
+    fetch_all_existing_docs_fn: FetchAllDocumentsFunction,  # noqa: ARG001
     fetch_all_existing_docs_ids_fn: FetchAllDocumentsIdsFunction,
     callback: IndexingHeartbeatInterface | None = None,
 ) -> Generator[ElementExternalAccess, None, None]:
     sharepoint_connector = SharepointConnector(
         **cc_pair.connector.connector_specific_config,
     )
-    sharepoint_connector.load_credentials(cc_pair.credential.credential_json)
+    credential_json = (
+        cc_pair.credential.credential_json.get_value(apply_mask=False)
+        if cc_pair.credential.credential_json
+        else {}
+    )
+    sharepoint_connector.load_credentials(credential_json)
 
     yield from generic_doc_sync(
         cc_pair=cc_pair,

backend/ee/onyx/external_permissions/sharepoint/group_sync.py

@@ -1,12 +1,9 @@
 from collections.abc import Generator
 
-from office365.sharepoint.client_context import ClientContext  # type: ignore[import-untyped]
-
 from ee.onyx.db.external_perm import ExternalUserGroup
 from ee.onyx.external_permissions.sharepoint.permission_utils import (
     get_sharepoint_external_groups,
 )
-from onyx.connectors.sharepoint.connector import acquire_token_for_rest
 from onyx.connectors.sharepoint.connector import SharepointConnector
 from onyx.db.models import ConnectorCredentialPair
 from onyx.utils.logger import setup_logger
@@ -15,7 +12,7 @@ logger = setup_logger()
 
 
 def sharepoint_group_sync(
-    tenant_id: str,
+    tenant_id: str,  # noqa: ARG001
     cc_pair: ConnectorCredentialPair,
 ) -> Generator[ExternalUserGroup, None, None]:
     """Sync SharePoint groups and their members"""
@@ -25,7 +22,12 @@ def sharepoint_group_sync(
 
     # Create SharePoint connector instance and load credentials
     connector = SharepointConnector(**connector_config)
-    connector.load_credentials(cc_pair.credential.credential_json)
+    credential_json = (
+        cc_pair.credential.credential_json.get_value(apply_mask=False)
+        if cc_pair.credential.credential_json
+        else {}
+    )
+    connector.load_credentials(credential_json)
 
     if not connector.msal_app:
         raise RuntimeError("MSAL app not initialized in connector")
@@ -41,16 +43,11 @@ def sharepoint_group_sync(
 
     logger.info(f"Processing {len(site_descriptors)} sites for group sync")
 
-    msal_app = connector.msal_app
-    sp_tenant_domain = connector.sp_tenant_domain
     # Process each site
     for site_descriptor in site_descriptors:
         logger.debug(f"Processing site: {site_descriptor.url}")
 
-        # Create client context for the site using connector's MSAL app
-        ctx = ClientContext(site_descriptor.url).with_access_token(
-            lambda: acquire_token_for_rest(msal_app, sp_tenant_domain)
-        )
+        ctx = connector._create_rest_client_context(site_descriptor.url)
 
         # Get external groups for this site
         external_groups = get_sharepoint_external_groups(ctx, connector.graph_client)

backend/ee/onyx/external_permissions/slack/doc_sync.py

@@ -103,7 +103,7 @@ def _fetch_channel_permissions(
 
 def _get_slack_document_access(
     slack_connector: SlackConnector,
-    channel_permissions: dict[str, ExternalAccess],
+    channel_permissions: dict[str, ExternalAccess],  # noqa: ARG001
     callback: IndexingHeartbeatInterface | None,
 ) -> Generator[DocExternalAccess, None, None]:
     slim_doc_generator = slack_connector.retrieve_all_slim_docs_perm_sync(
@@ -136,8 +136,8 @@ def _get_slack_document_access(
 
 def slack_doc_sync(
     cc_pair: ConnectorCredentialPair,
-    fetch_all_existing_docs_fn: FetchAllDocumentsFunction,
-    fetch_all_existing_docs_ids_fn: FetchAllDocumentsIdsFunction,
+    fetch_all_existing_docs_fn: FetchAllDocumentsFunction,  # noqa: ARG001
+    fetch_all_existing_docs_ids_fn: FetchAllDocumentsIdsFunction,  # noqa: ARG001
     callback: IndexingHeartbeatInterface | None,
 ) -> Generator[DocExternalAccess, None, None]:
     """
@@ -151,9 +151,14 @@ def slack_doc_sync(
     tenant_id = get_current_tenant_id()
     provider = OnyxDBCredentialsProvider(tenant_id, "slack", cc_pair.credential.id)
     r = get_redis_client(tenant_id=tenant_id)
+    credential_json = (
+        cc_pair.credential.credential_json.get_value(apply_mask=False)
+        if cc_pair.credential.credential_json
+        else {}
+    )
     slack_client = SlackConnector.make_slack_web_client(
         provider.get_provider_key(),
-        cc_pair.credential.credential_json["slack_bot_token"],
+        credential_json["slack_bot_token"],
         SlackConnector.MAX_RETRIES,
         r,
     )

backend/ee/onyx/external_permissions/slack/group_sync.py

@@ -63,9 +63,14 @@ def slack_group_sync(
 
     provider = OnyxDBCredentialsProvider(tenant_id, "slack", cc_pair.credential.id)
     r = get_redis_client(tenant_id=tenant_id)
+    credential_json = (
+        cc_pair.credential.credential_json.get_value(apply_mask=False)
+        if cc_pair.credential.credential_json
+        else {}
+    )
     slack_client = SlackConnector.make_slack_web_client(
         provider.get_provider_key(),
-        cc_pair.credential.credential_json["slack_bot_token"],
+        credential_json["slack_bot_token"],
         SlackConnector.MAX_RETRIES,
         r,
     )

backend/ee/onyx/external_permissions/sync_params.py

@@ -72,10 +72,10 @@ class SyncConfig(BaseModel):
 
 # Mock doc sync function for testing (no-op)
 def mock_doc_sync(
-    cc_pair: "ConnectorCredentialPair",
-    fetch_all_docs_fn: FetchAllDocumentsFunction,
-    fetch_all_docs_ids_fn: FetchAllDocumentsIdsFunction,
-    callback: Optional["IndexingHeartbeatInterface"],
+    cc_pair: "ConnectorCredentialPair",  # noqa: ARG001
+    fetch_all_docs_fn: FetchAllDocumentsFunction,  # noqa: ARG001
+    fetch_all_docs_ids_fn: FetchAllDocumentsIdsFunction,  # noqa: ARG001
+    callback: Optional["IndexingHeartbeatInterface"],  # noqa: ARG001
 ) -> Generator["DocExternalAccess", None, None]:
     """Mock doc sync function for testing - returns empty list since permissions are fetched during indexing"""
     yield from []

backend/ee/onyx/external_permissions/teams/doc_sync.py

@@ -18,14 +18,19 @@ TEAMS_DOC_SYNC_LABEL = "teams_doc_sync"
 
 def teams_doc_sync(
     cc_pair: ConnectorCredentialPair,
-    fetch_all_existing_docs_fn: FetchAllDocumentsFunction,
+    fetch_all_existing_docs_fn: FetchAllDocumentsFunction,  # noqa: ARG001
     fetch_all_existing_docs_ids_fn: FetchAllDocumentsIdsFunction,
     callback: IndexingHeartbeatInterface | None,
 ) -> Generator[ElementExternalAccess, None, None]:
     teams_connector = TeamsConnector(
         **cc_pair.connector.connector_specific_config,
     )
-    teams_connector.load_credentials(cc_pair.credential.credential_json)
+    credential_json = (
+        cc_pair.credential.credential_json.get_value(apply_mask=False)
+        if cc_pair.credential.credential_json
+        else {}
+    )
+    teams_connector.load_credentials(credential_json)
 
     yield from generic_doc_sync(
         cc_pair=cc_pair,

backend/ee/onyx/search/process_search_query.py

@@ -77,7 +77,7 @@ def stream_search_query(
     # Get document index
     search_settings = get_current_search_settings(db_session)
     # This flow is for search so we do not get all indices.
-    document_index = get_default_document_index(search_settings, None)
+    document_index = get_default_document_index(search_settings, None, db_session)
 
     # Determine queries to execute
     original_query = request.search_query

backend/ee/onyx/server/billing/api.py

@@ -32,6 +32,7 @@ from sqlalchemy.orm import Session
 
 from ee.onyx.auth.users import current_admin_user
 from ee.onyx.db.license import get_license
+from ee.onyx.db.license import get_used_seats
 from ee.onyx.server.billing.models import BillingInformationResponse
 from ee.onyx.server.billing.models import CreateCheckoutSessionRequest
 from ee.onyx.server.billing.models import CreateCheckoutSessionResponse
@@ -164,6 +165,16 @@ async def create_checkout_session(
     seats = request.seats if request else None
     email = request.email if request else None
 
+    # Validate that requested seats is not less than current used seats
+    if seats is not None:
+        used_seats = get_used_seats(tenant_id)
+        if seats < used_seats:
+            raise HTTPException(
+                status_code=400,
+                detail=f"Cannot subscribe with fewer seats than current usage. "
+                f"You have {used_seats} active users/integrations but requested {seats} seats.",
+            )
+
     # Build redirect URL for after checkout completion
     redirect_url = f"{WEB_DOMAIN}/admin/billing?checkout=success"
 
@@ -265,6 +276,15 @@ async def update_seats(
     if not MULTI_TENANT and not license_data:
         raise HTTPException(status_code=400, detail="No license found")
 
+    # Validate that new seat count is not less than current used seats
+    used_seats = get_used_seats(tenant_id)
+    if request.new_seat_count < used_seats:
+        raise HTTPException(
+            status_code=400,
+            detail=f"Cannot reduce seats below current usage. "
+            f"You have {used_seats} active users/integrations but requested {request.new_seat_count} seats.",
+        )
+
     try:
         result = await update_seat_service(
             new_seat_count=request.new_seat_count,

backend/ee/onyx/server/billing/service.py

@@ -109,7 +109,9 @@ async def _make_billing_request(
     headers = _get_headers(license_data)
 
     try:
-        async with httpx.AsyncClient(timeout=_REQUEST_TIMEOUT) as client:
+        async with httpx.AsyncClient(
+            timeout=_REQUEST_TIMEOUT, follow_redirects=True
+        ) as client:
             if method == "GET":
                 response = await client.get(url, headers=headers, params=params)
             else:

backend/ee/onyx/server/enterprise_settings/api.py

@@ -139,7 +139,7 @@ def put_logo(
     upload_logo(file=file, is_logotype=is_logotype)
 
 
-def fetch_logo_helper(db_session: Session) -> Response:
+def fetch_logo_helper(db_session: Session) -> Response:  # noqa: ARG001
     try:
         file_store = get_default_file_store()
         onyx_file = file_store.get_file_with_mime_type(get_logo_filename())
@@ -155,7 +155,7 @@ def fetch_logo_helper(db_session: Session) -> Response:
         return Response(content=onyx_file.data, media_type=onyx_file.mime_type)
 
 
-def fetch_logotype_helper(db_session: Session) -> Response:
+def fetch_logotype_helper(db_session: Session) -> Response:  # noqa: ARG001
     try:
         file_store = get_default_file_store()
         onyx_file = file_store.get_file_with_mime_type(get_logotype_filename())

backend/ee/onyx/server/evals/api.py

@@ -17,7 +17,7 @@ router = APIRouter(prefix="/evals")
 @router.post("/eval_run", response_model=EvalRunAck)
 def eval_run(
     request: EvalConfigurationOptions,
-    user: User = Depends(current_cloud_superuser),
+    user: User = Depends(current_cloud_superuser),  # noqa: ARG001
 ) -> EvalRunAck:
     """
     Run an evaluation with the given message and optional dataset.

backend/ee/onyx/server/license/api.py

@@ -42,6 +42,20 @@ logger = setup_logger()
 
 router = APIRouter(prefix="/license")
 
+# PEM-style delimiters used in license file format
+_PEM_BEGIN = "-----BEGIN ONYX LICENSE-----"
+_PEM_END = "-----END ONYX LICENSE-----"
+
+
+def _strip_pem_delimiters(content: str) -> str:
+    """Strip PEM-style delimiters from license content if present."""
+    content = content.strip()
+    if content.startswith(_PEM_BEGIN) and content.endswith(_PEM_END):
+        # Remove first and last lines (the delimiters)
+        lines = content.split("\n")
+        return "\n".join(lines[1:-1]).strip()
+    return content
+
 
 @router.get("")
 async def get_license_status(
@@ -106,6 +120,11 @@ async def claim_license(
     - Updating seats via the billing API
     - Returning from the Stripe customer portal
     - Any operation that regenerates the license on control plane
+    Claim a license from the control plane (self-hosted only).
+
+    Two modes:
+    1. With session_id: After Stripe checkout, exchange session_id for license
+    2. Without session_id: Re-claim using existing license for auth
     """
     if MULTI_TENANT:
         raise HTTPException(
@@ -210,6 +229,10 @@ async def upload_license(
     try:
         content = await license_file.read()
         license_data = content.decode("utf-8").strip()
+        # Strip PEM-style delimiters if present (used in .lic file format)
+        license_data = _strip_pem_delimiters(license_data)
+        # Remove any stray whitespace/newlines from user input
+        license_data = license_data.strip()
     except UnicodeDecodeError:
         raise HTTPException(status_code=400, detail="Invalid license file format")
 

backend/ee/onyx/server/oauth/confluence_cloud.py

@@ -260,7 +260,7 @@ def confluence_oauth_accessible_resources(
     credential_id: int,
     user: User = Depends(current_admin_user),
     db_session: Session = Depends(get_session),
-    tenant_id: str | None = Depends(get_current_tenant_id),
+    tenant_id: str | None = Depends(get_current_tenant_id),  # noqa: ARG001
 ) -> JSONResponse:
     """Atlassian's API is weird and does not supply us with enough info to be in a
     usable state after authorizing.  All API's require a cloud id. We have to list
@@ -270,7 +270,11 @@ def confluence_oauth_accessible_resources(
     if not credential:
         raise HTTPException(400, f"Credential {credential_id} not found.")
 
-    credential_dict = credential.credential_json
+    credential_dict = (
+        credential.credential_json.get_value(apply_mask=False)
+        if credential.credential_json
+        else {}
+    )
     access_token = credential_dict["confluence_access_token"]
 
     try:
@@ -323,7 +327,7 @@ def confluence_oauth_finalize(
     cloud_url: str,
     user: User = Depends(current_admin_user),
     db_session: Session = Depends(get_session),
-    tenant_id: str | None = Depends(get_current_tenant_id),
+    tenant_id: str | None = Depends(get_current_tenant_id),  # noqa: ARG001
 ) -> JSONResponse:
     """Saves the info for the selected cloud site to the credential.
     This is the final step in the confluence oauth flow where after the traditional
@@ -337,7 +341,12 @@ def confluence_oauth_finalize(
             detail=f"Confluence Cloud OAuth failed - credential {credential_id} not found.",
         )
 
-    new_credential_json: dict[str, Any] = dict(credential.credential_json)
+    existing_credential_json = (
+        credential.credential_json.get_value(apply_mask=False)
+        if credential.credential_json
+        else {}
+    )
+    new_credential_json: dict[str, Any] = dict(existing_credential_json)
     new_credential_json["cloud_id"] = cloud_id
     new_credential_json["cloud_name"] = cloud_name
     new_credential_json["wiki_base"] = cloud_url

backend/ee/onyx/server/query_and_chat/models.py

@@ -27,6 +27,8 @@ class SearchFlowClassificationResponse(BaseModel):
     is_search_flow: bool
 
 
+# NOTE: This model is used for the core flow of the Onyx application, any changes to it should be reviewed and approved by an
+# experienced team member. It is very important to 1. avoid bloat and 2. that this remains backwards compatible across versions.
 class SendSearchQueryRequest(BaseModel):
     search_query: str
     filters: BaseFilters | None = None

backend/ee/onyx/server/query_and_chat/search_backend.py

@@ -26,6 +26,7 @@ from onyx.db.models import User
 from onyx.llm.factory import get_default_llm
 from onyx.server.usage_limits import check_llm_cost_limit_for_provider
 from onyx.server.utils import get_json_line
+from onyx.server.utils_vector_db import require_vector_db
 from onyx.utils.logger import setup_logger
 from shared_configs.contextvars import get_current_tenant_id
 
@@ -66,7 +67,13 @@ def search_flow_classification(
     return SearchFlowClassificationResponse(is_search_flow=is_search_flow)
 
 
-@router.post("/send-search-message", response_model=None)
+# NOTE: This endpoint is used for the core flow of the Onyx application, any changes to it should be reviewed and approved by an
+# experienced team member. It is very important to 1. avoid bloat and 2. that this remains backwards compatible across versions.
+@router.post(
+    "/send-search-message",
+    response_model=None,
+    dependencies=[Depends(require_vector_db)],
+)
 def handle_send_search_message(
     request: SendSearchQueryRequest,
     user: User = Depends(current_user),

backend/ee/onyx/server/query_history/api.py

@@ -78,7 +78,7 @@ def fetch_and_process_chat_session_history(
     db_session: Session,
     start: datetime,
     end: datetime,
-    limit: int | None = 500,
+    limit: int | None = 500,  # noqa: ARG001
 ) -> Generator[ChatSessionSnapshot]:
     PAGE_SIZE = 100
 

backend/ee/onyx/server/reporting/usage_export_api.py

@@ -59,7 +59,7 @@ def generate_report(
 def read_usage_report(
     report_name: str,
     _: User = Depends(current_admin_user),
-    db_session: Session = Depends(get_session),
+    db_session: Session = Depends(get_session),  # noqa: ARG001
 ) -> Response:
     try:
         file = get_usage_report_data(report_name)

backend/ee/onyx/server/scim/filtering.py

@@ -0,0 +1,96 @@
+"""SCIM filter expression parser (RFC 7644 §3.4.2.2).
+
+Identity providers (Okta, Azure AD, OneLogin, etc.) use filters to look up
+resources before deciding whether to create or update them. For example, when
+an admin assigns a user to the Onyx app, the IdP first checks whether that
+user already exists::
+
+    GET /scim/v2/Users?filter=userName eq "john@example.com"
+
+If zero results come back the IdP creates the user (``POST``); if a match is
+found it links to the existing record and uses ``PUT``/``PATCH`` going forward.
+The same pattern applies to groups (``displayName eq "Engineering"``).
+
+This module parses the subset of the SCIM filter grammar that identity
+providers actually send in practice:
+
+    attribute SP operator SP value
+
+Supported operators: ``eq``, ``co`` (contains), ``sw`` (starts with).
+Compound filters (``and`` / ``or``) are not supported; if an IdP sends one
+the parser returns ``None`` and the caller falls back to an unfiltered list.
+"""
+
+from __future__ import annotations
+
+import re
+from dataclasses import dataclass
+from enum import Enum
+
+
+class ScimFilterOperator(str, Enum):
+    """Supported SCIM filter operators."""
+
+    EQUAL = "eq"
+    CONTAINS = "co"
+    STARTS_WITH = "sw"
+
+
+@dataclass(frozen=True, slots=True)
+class ScimFilter:
+    """Parsed SCIM filter expression."""
+
+    attribute: str
+    operator: ScimFilterOperator
+    value: str
+
+
+# Matches: attribute operator "value" (with or without quotes around value)
+# Groups: (attribute) (operator) ("quoted value" | unquoted_value)
+_FILTER_RE = re.compile(
+    r"^(\S+)\s+(eq|co|sw)\s+"  # attribute + operator
+    r'(?:"([^"]*)"'  # quoted value
+    r"|'([^']*)')"  # or single-quoted value
+    r"$",
+    re.IGNORECASE,
+)
+
+
+def parse_scim_filter(filter_string: str | None) -> ScimFilter | None:
+    """Parse a simple SCIM filter expression.
+
+    Args:
+        filter_string: Raw filter query parameter value, e.g.
+            ``'userName eq "john@example.com"'``
+
+    Returns:
+        A ``ScimFilter`` if the expression is valid and uses a supported
+        operator, or ``None`` if the input is empty / missing.
+
+    Raises:
+        ValueError: If the filter string is present but malformed or uses
+            an unsupported operator.
+    """
+    if not filter_string or not filter_string.strip():
+        return None
+
+    match = _FILTER_RE.match(filter_string.strip())
+    if not match:
+        raise ValueError(f"Unsupported or malformed SCIM filter: {filter_string}")
+
+    return _build_filter(match, filter_string)
+
+
+def _build_filter(match: re.Match[str], raw: str) -> ScimFilter:
+    """Extract fields from a regex match and construct a ScimFilter."""
+    attribute = match.group(1)
+    op_str = match.group(2).lower()
+    # Value is in group 3 (double-quoted) or group 4 (single-quoted)
+    value = match.group(3) if match.group(3) is not None else match.group(4)
+
+    if value is None:
+        raise ValueError(f"Unsupported or malformed SCIM filter: {raw}")
+
+    operator = ScimFilterOperator(op_str)
+
+    return ScimFilter(attribute=attribute, operator=operator, value=value)

backend/ee/onyx/server/scim/models.py

@@ -0,0 +1,255 @@
+"""Pydantic schemas for SCIM 2.0 provisioning (RFC 7643 / RFC 7644).
+
+SCIM protocol schemas follow the wire format defined in:
+  - Core Schema: https://datatracker.ietf.org/doc/html/rfc7643
+  - Protocol:    https://datatracker.ietf.org/doc/html/rfc7644
+
+Admin API schemas are internal to Onyx and used for SCIM token management.
+"""
+
+from datetime import datetime
+from enum import Enum
+
+from pydantic import BaseModel
+from pydantic import ConfigDict
+from pydantic import Field
+
+
+# ---------------------------------------------------------------------------
+# SCIM Schema URIs (RFC 7643 §8)
+# Every SCIM JSON payload includes a "schemas" array identifying its type.
+# IdPs like Okta/Azure AD use these URIs to determine how to parse responses.
+# ---------------------------------------------------------------------------
+
+SCIM_USER_SCHEMA = "urn:ietf:params:scim:schemas:core:2.0:User"
+SCIM_GROUP_SCHEMA = "urn:ietf:params:scim:schemas:core:2.0:Group"
+SCIM_LIST_RESPONSE_SCHEMA = "urn:ietf:params:scim:api:messages:2.0:ListResponse"
+SCIM_PATCH_OP_SCHEMA = "urn:ietf:params:scim:api:messages:2.0:PatchOp"
+SCIM_ERROR_SCHEMA = "urn:ietf:params:scim:api:messages:2.0:Error"
+SCIM_SERVICE_PROVIDER_CONFIG_SCHEMA = (
+    "urn:ietf:params:scim:schemas:core:2.0:ServiceProviderConfig"
+)
+SCIM_RESOURCE_TYPE_SCHEMA = "urn:ietf:params:scim:schemas:core:2.0:ResourceType"
+
+
+# ---------------------------------------------------------------------------
+# SCIM Protocol Schemas
+# ---------------------------------------------------------------------------
+
+
+class ScimName(BaseModel):
+    """User name components (RFC 7643 §4.1.1)."""
+
+    givenName: str | None = None
+    familyName: str | None = None
+    formatted: str | None = None
+
+
+class ScimEmail(BaseModel):
+    """Email sub-attribute (RFC 7643 §4.1.2)."""
+
+    value: str
+    type: str | None = None
+    primary: bool = False
+
+
+class ScimMeta(BaseModel):
+    """Resource metadata (RFC 7643 §3.1)."""
+
+    resourceType: str | None = None
+    created: datetime | None = None
+    lastModified: datetime | None = None
+    location: str | None = None
+
+
+class ScimUserResource(BaseModel):
+    """SCIM User resource representation (RFC 7643 §4.1).
+
+    This is the JSON shape that IdPs send when creating/updating a user via
+    SCIM, and the shape we return in GET responses. Field names use camelCase
+    to match the SCIM wire format (not Python convention).
+    """
+
+    schemas: list[str] = Field(default_factory=lambda: [SCIM_USER_SCHEMA])
+    id: str | None = None  # Onyx's internal user ID, set on responses
+    externalId: str | None = None  # IdP's identifier for this user
+    userName: str  # Typically the user's email address
+    name: ScimName | None = None
+    emails: list[ScimEmail] = Field(default_factory=list)
+    active: bool = True
+    meta: ScimMeta | None = None
+
+
+class ScimGroupMember(BaseModel):
+    """Group member reference (RFC 7643 §4.2).
+
+    Represents a user within a SCIM group. The IdP sends these when adding
+    or removing users from groups. ``value`` is the Onyx user ID.
+    """
+
+    value: str  # User ID of the group member
+    display: str | None = None
+
+
+class ScimGroupResource(BaseModel):
+    """SCIM Group resource representation (RFC 7643 §4.2)."""
+
+    schemas: list[str] = Field(default_factory=lambda: [SCIM_GROUP_SCHEMA])
+    id: str | None = None
+    externalId: str | None = None
+    displayName: str
+    members: list[ScimGroupMember] = Field(default_factory=list)
+    meta: ScimMeta | None = None
+
+
+class ScimListResponse(BaseModel):
+    """Paginated list response (RFC 7644 §3.4.2)."""
+
+    schemas: list[str] = Field(default_factory=lambda: [SCIM_LIST_RESPONSE_SCHEMA])
+    totalResults: int
+    startIndex: int = 1
+    itemsPerPage: int = 100
+    Resources: list[ScimUserResource | ScimGroupResource] = Field(default_factory=list)
+
+
+class ScimPatchOperationType(str, Enum):
+    """Supported PATCH operations (RFC 7644 §3.5.2)."""
+
+    ADD = "add"
+    REPLACE = "replace"
+    REMOVE = "remove"
+
+
+class ScimPatchOperation(BaseModel):
+    """Single PATCH operation (RFC 7644 §3.5.2)."""
+
+    op: ScimPatchOperationType
+    path: str | None = None
+    value: str | list[dict[str, str]] | dict[str, str | bool] | bool | None = None
+
+
+class ScimPatchRequest(BaseModel):
+    """PATCH request body (RFC 7644 §3.5.2).
+
+    IdPs use PATCH to make incremental changes — e.g. deactivating a user
+    (replace active=false) or adding/removing group members — instead of
+    replacing the entire resource with PUT.
+    """
+
+    schemas: list[str] = Field(default_factory=lambda: [SCIM_PATCH_OP_SCHEMA])
+    Operations: list[ScimPatchOperation]
+
+
+class ScimError(BaseModel):
+    """SCIM error response (RFC 7644 §3.12)."""
+
+    schemas: list[str] = Field(default_factory=lambda: [SCIM_ERROR_SCHEMA])
+    status: str
+    detail: str | None = None
+    scimType: str | None = None
+
+
+# ---------------------------------------------------------------------------
+# Service Provider Configuration (RFC 7643 §5)
+# ---------------------------------------------------------------------------
+
+
+class ScimSupported(BaseModel):
+    """Generic supported/not-supported flag used in ServiceProviderConfig."""
+
+    supported: bool
+
+
+class ScimFilterConfig(BaseModel):
+    """Filter configuration within ServiceProviderConfig (RFC 7643 §5)."""
+
+    supported: bool
+    maxResults: int = 100
+
+
+class ScimServiceProviderConfig(BaseModel):
+    """SCIM ServiceProviderConfig resource (RFC 7643 §5).
+
+    Served at GET /scim/v2/ServiceProviderConfig. IdPs fetch this during
+    initial setup to discover which SCIM features our server supports
+    (e.g. PATCH yes, bulk no, filtering yes).
+    """
+
+    schemas: list[str] = Field(
+        default_factory=lambda: [SCIM_SERVICE_PROVIDER_CONFIG_SCHEMA]
+    )
+    patch: ScimSupported = ScimSupported(supported=True)
+    bulk: ScimSupported = ScimSupported(supported=False)
+    filter: ScimFilterConfig = ScimFilterConfig(supported=True)
+    changePassword: ScimSupported = ScimSupported(supported=False)
+    sort: ScimSupported = ScimSupported(supported=False)
+    etag: ScimSupported = ScimSupported(supported=False)
+    authenticationSchemes: list[dict[str, str]] = Field(
+        default_factory=lambda: [
+            {
+                "type": "oauthbearertoken",
+                "name": "OAuth Bearer Token",
+                "description": "Authentication scheme using a SCIM bearer token",
+            }
+        ]
+    )
+
+
+class ScimSchemaExtension(BaseModel):
+    """Schema extension reference within ResourceType (RFC 7643 §6)."""
+
+    model_config = ConfigDict(populate_by_name=True)
+
+    schema_: str = Field(alias="schema")
+    required: bool
+
+
+class ScimResourceType(BaseModel):
+    """SCIM ResourceType resource (RFC 7643 §6).
+
+    Served at GET /scim/v2/ResourceTypes. Tells the IdP which resource
+    types are available (Users, Groups) and their respective endpoints.
+    """
+
+    model_config = ConfigDict(populate_by_name=True)
+
+    schemas: list[str] = Field(default_factory=lambda: [SCIM_RESOURCE_TYPE_SCHEMA])
+    id: str
+    name: str
+    endpoint: str
+    description: str | None = None
+    schema_: str = Field(alias="schema")
+    schemaExtensions: list[ScimSchemaExtension] = Field(default_factory=list)
+
+
+# ---------------------------------------------------------------------------
+# Admin API Schemas (Onyx-internal, for SCIM token management)
+# These are NOT part of the SCIM protocol. They power the Onyx admin UI
+# where admins create/revoke the bearer tokens that IdPs use to authenticate.
+# ---------------------------------------------------------------------------
+
+
+class ScimTokenCreate(BaseModel):
+    """Request to create a new SCIM bearer token."""
+
+    name: str
+
+
+class ScimTokenResponse(BaseModel):
+    """SCIM token metadata returned in list/get responses."""
+
+    id: int
+    name: str
+    token_display: str
+    is_active: bool
+    created_at: datetime
+    last_used_at: datetime | None = None
+
+
+class ScimTokenCreatedResponse(ScimTokenResponse):
+    """Response returned when a new SCIM token is created.
+
+    Includes the raw token value which is only available at creation time.
+    """
+
+    raw_token: str

backend/ee/onyx/server/scim/patch.py

@@ -0,0 +1,256 @@
+"""SCIM PATCH operation handler (RFC 7644 §3.5.2).
+
+Identity providers use PATCH to make incremental changes to SCIM resources
+instead of replacing the entire resource with PUT. Common operations include:
+
+  - Deactivating a user: ``replace`` ``active`` with ``false``
+  - Adding group members: ``add`` to ``members``
+  - Removing group members: ``remove`` from ``members[value eq "..."]``
+
+This module applies PATCH operations to Pydantic SCIM resource objects and
+returns the modified result. It does NOT touch the database — the caller is
+responsible for persisting changes.
+"""
+
+from __future__ import annotations
+
+import re
+
+from ee.onyx.server.scim.models import ScimGroupResource
+from ee.onyx.server.scim.models import ScimPatchOperation
+from ee.onyx.server.scim.models import ScimPatchOperationType
+from ee.onyx.server.scim.models import ScimUserResource
+
+
+class ScimPatchError(Exception):
+    """Raised when a PATCH operation cannot be applied."""
+
+    def __init__(self, detail: str, status: int = 400) -> None:
+        self.detail = detail
+        self.status = status
+        super().__init__(detail)
+
+
+# Pattern for member removal path: members[value eq "user-id"]
+_MEMBER_FILTER_RE = re.compile(
+    r'^members\[value\s+eq\s+"([^"]+)"\]$',
+    re.IGNORECASE,
+)
+
+
+def apply_user_patch(
+    operations: list[ScimPatchOperation],
+    current: ScimUserResource,
+) -> ScimUserResource:
+    """Apply SCIM PATCH operations to a user resource.
+
+    Returns a new ``ScimUserResource`` with the modifications applied.
+    The original object is not mutated.
+
+    Raises:
+        ScimPatchError: If an operation targets an unsupported path.
+    """
+    data = current.model_dump()
+    name_data = data.get("name") or {}
+
+    for op in operations:
+        if op.op == ScimPatchOperationType.REPLACE:
+            _apply_user_replace(op, data, name_data)
+        elif op.op == ScimPatchOperationType.ADD:
+            _apply_user_replace(op, data, name_data)
+        else:
+            raise ScimPatchError(
+                f"Unsupported operation '{op.op.value}' on User resource"
+            )
+
+    data["name"] = name_data
+    return ScimUserResource.model_validate(data)
+
+
+def _apply_user_replace(
+    op: ScimPatchOperation,
+    data: dict,
+    name_data: dict,
+) -> None:
+    """Apply a replace/add operation to user data."""
+    path = (op.path or "").lower()
+
+    if not path:
+        # No path — value is a dict of top-level attributes to set
+        if isinstance(op.value, dict):
+            for key, val in op.value.items():
+                _set_user_field(key.lower(), val, data, name_data)
+        else:
+            raise ScimPatchError("Replace without path requires a dict value")
+        return
+
+    _set_user_field(path, op.value, data, name_data)
+
+
+def _set_user_field(
+    path: str,
+    value: str | bool | dict | list | None,
+    data: dict,
+    name_data: dict,
+) -> None:
+    """Set a single field on user data by SCIM path."""
+    if path == "active":
+        data["active"] = value
+    elif path == "username":
+        data["userName"] = value
+    elif path == "externalid":
+        data["externalId"] = value
+    elif path == "name.givenname":
+        name_data["givenName"] = value
+    elif path == "name.familyname":
+        name_data["familyName"] = value
+    elif path == "name.formatted":
+        name_data["formatted"] = value
+    elif path == "displayname":
+        # Some IdPs send displayName on users; map to formatted name
+        name_data["formatted"] = value
+    else:
+        raise ScimPatchError(f"Unsupported path '{path}' for User PATCH")
+
+
+def apply_group_patch(
+    operations: list[ScimPatchOperation],
+    current: ScimGroupResource,
+) -> tuple[ScimGroupResource, list[str], list[str]]:
+    """Apply SCIM PATCH operations to a group resource.
+
+    Returns:
+        A tuple of (modified group, added member IDs, removed member IDs).
+        The caller uses the member ID lists to update the database.
+
+    Raises:
+        ScimPatchError: If an operation targets an unsupported path.
+    """
+    data = current.model_dump()
+    current_members: list[dict] = list(data.get("members") or [])
+    added_ids: list[str] = []
+    removed_ids: list[str] = []
+
+    for op in operations:
+        if op.op == ScimPatchOperationType.REPLACE:
+            _apply_group_replace(op, data, current_members, added_ids, removed_ids)
+        elif op.op == ScimPatchOperationType.ADD:
+            _apply_group_add(op, current_members, added_ids)
+        elif op.op == ScimPatchOperationType.REMOVE:
+            _apply_group_remove(op, current_members, removed_ids)
+        else:
+            raise ScimPatchError(
+                f"Unsupported operation '{op.op.value}' on Group resource"
+            )
+
+    data["members"] = current_members
+    group = ScimGroupResource.model_validate(data)
+    return group, added_ids, removed_ids
+
+
+def _apply_group_replace(
+    op: ScimPatchOperation,
+    data: dict,
+    current_members: list[dict],
+    added_ids: list[str],
+    removed_ids: list[str],
+) -> None:
+    """Apply a replace operation to group data."""
+    path = (op.path or "").lower()
+
+    if not path:
+        if isinstance(op.value, dict):
+            for key, val in op.value.items():
+                if key.lower() == "members":
+                    _replace_members(val, current_members, added_ids, removed_ids)
+                else:
+                    _set_group_field(key.lower(), val, data)
+        else:
+            raise ScimPatchError("Replace without path requires a dict value")
+        return
+
+    if path == "members":
+        _replace_members(op.value, current_members, added_ids, removed_ids)
+        return
+
+    _set_group_field(path, op.value, data)
+
+
+def _replace_members(
+    value: str | list | dict | bool | None,
+    current_members: list[dict],
+    added_ids: list[str],
+    removed_ids: list[str],
+) -> None:
+    """Replace the entire group member list."""
+    if not isinstance(value, list):
+        raise ScimPatchError("Replace members requires a list value")
+
+    old_ids = {m["value"] for m in current_members}
+    new_ids = {m.get("value", "") for m in value}
+
+    removed_ids.extend(old_ids - new_ids)
+    added_ids.extend(new_ids - old_ids)
+
+    current_members[:] = value
+
+
+def _set_group_field(
+    path: str,
+    value: str | bool | dict | list | None,
+    data: dict,
+) -> None:
+    """Set a single field on group data by SCIM path."""
+    if path == "displayname":
+        data["displayName"] = value
+    elif path == "externalid":
+        data["externalId"] = value
+    else:
+        raise ScimPatchError(f"Unsupported path '{path}' for Group PATCH")
+
+
+def _apply_group_add(
+    op: ScimPatchOperation,
+    members: list[dict],
+    added_ids: list[str],
+) -> None:
+    """Add members to a group."""
+    path = (op.path or "").lower()
+
+    if path and path != "members":
+        raise ScimPatchError(f"Unsupported add path '{op.path}' for Group")
+
+    if not isinstance(op.value, list):
+        raise ScimPatchError("Add members requires a list value")
+
+    existing_ids = {m["value"] for m in members}
+    for member_data in op.value:
+        member_id = member_data.get("value", "")
+        if member_id and member_id not in existing_ids:
+            members.append(member_data)
+            added_ids.append(member_id)
+            existing_ids.add(member_id)
+
+
+def _apply_group_remove(
+    op: ScimPatchOperation,
+    members: list[dict],
+    removed_ids: list[str],
+) -> None:
+    """Remove members from a group."""
+    if not op.path:
+        raise ScimPatchError("Remove operation requires a path")
+
+    match = _MEMBER_FILTER_RE.match(op.path)
+    if not match:
+        raise ScimPatchError(
+            f"Unsupported remove path '{op.path}'. "
+            'Expected: members[value eq "user-id"]'
+        )
+
+    target_id = match.group(1)
+    original_len = len(members)
+    members[:] = [m for m in members if m.get("value") != target_id]
+
+    if len(members) < original_len:
+        removed_ids.append(target_id)

backend/ee/onyx/server/seeding.py

@@ -123,14 +123,9 @@ def _seed_llms(
             upsert_llm_provider(llm_upsert_request, db_session)
             for llm_upsert_request in llm_upsert_requests
         ]
-
-        if len(seeded_providers[0].model_configurations) > 0:
-            default_model = seeded_providers[0].model_configurations[0].name
-            update_default_provider(
-                provider_id=seeded_providers[0].id,
-                model_name=default_model,
-                db_session=db_session,
-            )
+        update_default_provider(
+            provider_id=seeded_providers[0].id, db_session=db_session
+        )
 
 
 def _seed_personas(db_session: Session, personas: list[PersonaUpsertRequest]) -> None:

backend/ee/onyx/server/settings/api.py

@@ -4,6 +4,7 @@ from redis.exceptions import RedisError
 
 from ee.onyx.configs.app_configs import LICENSE_ENFORCEMENT_ENABLED
 from ee.onyx.db.license import get_cached_license_metadata
+from onyx.configs.app_configs import ENTERPRISE_EDITION_ENABLED
 from onyx.server.settings.models import ApplicationStatus
 from onyx.server.settings.models import Settings
 from onyx.utils.logger import setup_logger
@@ -58,26 +59,46 @@ def apply_license_status_to_settings(settings: Settings) -> Settings:
     For self-hosted, looks up license metadata and overrides application_status
     if the license indicates GATED_ACCESS (fully expired).
 
+    Also sets ee_features_enabled based on license status to control
+    visibility of EE features in the UI.
+
     For multi-tenant (cloud), the settings already have the correct status
     from the control plane, so no override is needed.
 
-    If LICENSE_ENFORCEMENT_ENABLED is false, settings are returned unchanged,
-    allowing the product to function normally without license checks.
+    If LICENSE_ENFORCEMENT_ENABLED is false, ee_features_enabled is set to True
+    (since EE code was loaded via ENABLE_PAID_ENTERPRISE_EDITION_FEATURES).
     """
     if not LICENSE_ENFORCEMENT_ENABLED:
+        # License enforcement disabled - EE code is loaded via
+        # ENABLE_PAID_ENTERPRISE_EDITION_FEATURES, so EE features are on
+        settings.ee_features_enabled = True
         return settings
 
     if MULTI_TENANT:
+        # Cloud mode - EE features always available (gating handled by is_tenant_gated)
+        settings.ee_features_enabled = True
         return settings
 
     tenant_id = get_current_tenant_id()
     try:
         metadata = get_cached_license_metadata(tenant_id)
-        if metadata and metadata.status == _BLOCKING_STATUS:
-            settings.application_status = metadata.status
-        # No license = user hasn't purchased yet, allow access for upgrade flow
-        # GRACE_PERIOD/PAYMENT_REMINDER don't block - they're for notifications
+        if metadata:
+            if metadata.status == _BLOCKING_STATUS:
+                settings.application_status = metadata.status
+                settings.ee_features_enabled = False
+            else:
+                # Has a valid license (GRACE_PERIOD/PAYMENT_REMINDER still allow EE features)
+                settings.ee_features_enabled = True
+        else:
+            # No license found.
+            if ENTERPRISE_EDITION_ENABLED:
+                # Legacy EE flag is set → prior EE usage (e.g. permission
+                # syncing) means indexed data may need protection.
+                settings.application_status = _BLOCKING_STATUS
+            settings.ee_features_enabled = False
     except RedisError as e:
         logger.warning(f"Failed to check license metadata for settings: {e}")
+        # Fail closed - disable EE features if we can't verify license
+        settings.ee_features_enabled = False
 
     return settings

backend/ee/onyx/server/tenants/billing.py

@@ -19,6 +19,7 @@ logger = setup_logger()
 def fetch_stripe_checkout_session(
     tenant_id: str,
     billing_period: Literal["monthly", "annual"] = "monthly",
+    seats: int | None = None,
 ) -> str:
     token = generate_data_plane_token()
     headers = {
@@ -29,10 +30,23 @@ def fetch_stripe_checkout_session(
     payload = {
         "tenant_id": tenant_id,
         "billing_period": billing_period,
+        "seats": seats,
     }
     response = requests.post(url, headers=headers, json=payload)
-    response.raise_for_status()
-    return response.json()["sessionId"]
+    if not response.ok:
+        try:
+            data = response.json()
+            error_msg = (
+                data.get("error")
+                or f"Request failed with status {response.status_code}"
+            )
+        except (ValueError, requests.exceptions.JSONDecodeError):
+            error_msg = f"Request failed with status {response.status_code}: {response.text[:200]}"
+        raise Exception(error_msg)
+    data = response.json()
+    if data.get("error"):
+        raise Exception(data["error"])
+    return data["sessionId"]
 
 
 def fetch_tenant_stripe_information(tenant_id: str) -> dict:
@@ -51,7 +65,6 @@ def fetch_tenant_stripe_information(tenant_id: str) -> dict:
 def fetch_billing_information(
     tenant_id: str,
 ) -> BillingInformation | SubscriptionStatusResponse:
-    logger.info("Fetching billing information")
     token = generate_data_plane_token()
     headers = {
         "Authorization": f"Bearer {token}",