fix(ui): Fix admin UI layout, sticky headers, LLM filtering, and project view issues (#8496)

Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>

.claude/skills

@@ -0,0 +1 @@
+../.cursor/skills

.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"
+    }
+  }
+}

.cursor/skills/playwright/SKILL.md

@@ -0,0 +1,248 @@
+---
+name: playwright-e2e-tests
+description: Write and maintain Playwright end-to-end tests for the Onyx application. Use when creating new E2E tests, debugging test failures, adding test coverage, or when the user mentions Playwright, E2E tests, or browser testing.
+---
+
+# Playwright E2E Tests
+
+## Project Layout
+
+- **Tests**: `web/tests/e2e/` — organized by feature (`auth/`, `admin/`, `chat/`, `assistants/`, `connectors/`, `mcp/`)
+- **Config**: `web/playwright.config.ts`
+- **Utilities**: `web/tests/e2e/utils/`
+- **Constants**: `web/tests/e2e/constants.ts`
+- **Global setup**: `web/tests/e2e/global-setup.ts`
+- **Output**: `web/output/playwright/`
+
+## Imports
+
+Always use absolute imports with the `@tests/e2e/` prefix — never relative paths (`../`, `../../`). The alias is defined in `web/tsconfig.json` and resolves to `web/tests/`.
+
+```typescript
+import { loginAs } from "@tests/e2e/utils/auth";
+import { OnyxApiClient } from "@tests/e2e/utils/onyxApiClient";
+import { TEST_ADMIN_CREDENTIALS } from "@tests/e2e/constants";
+```
+
+All new files should be `.ts`, not `.js`.
+
+## Running Tests
+
+```bash
+# Run a specific test file
+npx playwright test web/tests/e2e/chat/default_assistant.spec.ts
+
+# Run a specific project
+npx playwright test --project admin
+npx playwright test --project exclusive
+```
+
+## Test Projects
+
+| Project | Description | Parallelism |
+|---------|-------------|-------------|
+| `admin` | Standard tests (excludes `@exclusive`) | Parallel |
+| `exclusive` | Serial, slower tests (tagged `@exclusive`) | 1 worker |
+
+All tests use `admin_auth.json` storage state by default (pre-authenticated admin session).
+
+## Authentication
+
+Global setup (`global-setup.ts`) runs automatically before all tests and handles:
+
+- Server readiness check (polls health endpoint, 60s timeout)
+- Provisioning test users: admin, admin2, and a **pool of worker users** (`worker0@example.com` through `worker7@example.com`) (idempotent)
+- API login + saving storage states: `admin_auth.json`, `admin2_auth.json`, and `worker{N}_auth.json` for each worker user
+- Setting display name to `"worker"` for each worker user
+- Promoting admin2 to admin role
+- Ensuring a public LLM provider exists
+
+Both test projects set `storageState: "admin_auth.json"`, so **every test starts pre-authenticated as admin with no login code needed**.
+
+When a test needs a different user, use API-based login — never drive the login UI:
+
+```typescript
+import { loginAs } from "@tests/e2e/utils/auth";
+
+await page.context().clearCookies();
+await loginAs(page, "admin2");
+
+// Log in as the worker-specific user (preferred for test isolation):
+import { loginAsWorkerUser } from "@tests/e2e/utils/auth";
+await page.context().clearCookies();
+await loginAsWorkerUser(page, testInfo.workerIndex);
+```
+
+## Test Structure
+
+Tests start pre-authenticated as admin — navigate and test directly:
+
+```typescript
+import { test, expect } from "@playwright/test";
+
+test.describe("Feature Name", () => {
+  test("should describe expected behavior clearly", async ({ page }) => {
+    await page.goto("/app");
+    await page.waitForLoadState("networkidle");
+    // Already authenticated as admin — go straight to testing
+  });
+});
+```
+
+**User isolation** — tests that modify visible app state (creating assistants, sending chat messages, pinning items) should run as a **worker-specific user** and clean up resources in `afterAll`. Global setup provisions a pool of worker users (`worker0@example.com` through `worker7@example.com`). `loginAsWorkerUser` maps `testInfo.workerIndex` to a pool slot via modulo, so retry workers (which get incrementing indices beyond the pool size) safely reuse existing users. This ensures parallel workers never share user state, keeps usernames deterministic for screenshots, and avoids cross-contamination:
+
+```typescript
+import { test } from "@playwright/test";
+import { loginAsWorkerUser } from "@tests/e2e/utils/auth";
+
+test.beforeEach(async ({ page }, testInfo) => {
+  await page.context().clearCookies();
+  await loginAsWorkerUser(page, testInfo.workerIndex);
+});
+```
+
+If the test requires admin privileges *and* modifies visible state, use `"admin2"` instead — it's a pre-provisioned admin account that keeps the primary `"admin"` clean for other parallel tests. Switch to `"admin"` only for privileged setup (creating providers, configuring tools), then back to the worker user for the actual test. See `chat/default_assistant.spec.ts` for a full example.
+
+`loginAsRandomUser` exists for the rare case where the test requires a brand-new user (e.g. onboarding flows). Avoid it elsewhere — it produces non-deterministic usernames that complicate screenshots.
+
+**API resource setup** — only when tests need to create backend resources (image gen configs, web search providers, MCP servers). Use `beforeAll`/`afterAll` with `OnyxApiClient` to create and clean up. See `chat/default_assistant.spec.ts` or `mcp/mcp_oauth_flow.spec.ts` for examples. This is uncommon (~4 of 37 test files).
+
+## Key Utilities
+
+### `OnyxApiClient` (`@tests/e2e/utils/onyxApiClient`)
+
+Backend API client for test setup/teardown. Key methods:
+
+- **Connectors**: `createFileConnector()`, `deleteCCPair()`, `pauseConnector()`
+- **LLM Providers**: `ensurePublicProvider()`, `createRestrictedProvider()`, `setProviderAsDefault()`
+- **Assistants**: `createAssistant()`, `deleteAssistant()`, `findAssistantByName()`
+- **User Groups**: `createUserGroup()`, `deleteUserGroup()`, `setUserRole()`
+- **Tools**: `createWebSearchProvider()`, `createImageGenerationConfig()`
+- **Chat**: `createChatSession()`, `deleteChatSession()`
+
+### `chatActions` (`@tests/e2e/utils/chatActions`)
+
+- `sendMessage(page, message)` — sends a message and waits for AI response
+- `startNewChat(page)` — clicks new-chat button and waits for intro
+- `verifyDefaultAssistantIsChosen(page)` — checks Onyx logo is visible
+- `verifyAssistantIsChosen(page, name)` — checks assistant name display
+- `switchModel(page, modelName)` — switches LLM model via popover
+
+### `visualRegression` (`@tests/e2e/utils/visualRegression`)
+
+- `expectScreenshot(page, { name, mask?, hide?, fullPage? })`
+- `expectElementScreenshot(locator, { name, mask?, hide? })`
+- Controlled by `VISUAL_REGRESSION=true` env var
+
+### `theme` (`@tests/e2e/utils/theme`)
+
+- `THEMES` — `["light", "dark"] as const` array for iterating over both themes
+- `setThemeBeforeNavigation(page, theme)` — sets `next-themes` theme via `localStorage` before navigation
+
+When tests need light/dark screenshots, loop over `THEMES` at the `test.describe` level and call `setThemeBeforeNavigation` in `beforeEach` **before** any `page.goto()`. Include the theme in screenshot names. See `admin/admin_pages.spec.ts` or `chat/chat_message_rendering.spec.ts` for examples:
+
+```typescript
+import { THEMES, setThemeBeforeNavigation } from "@tests/e2e/utils/theme";
+
+for (const theme of THEMES) {
+  test.describe(`Feature (${theme} mode)`, () => {
+    test.beforeEach(async ({ page }) => {
+      await setThemeBeforeNavigation(page, theme);
+    });
+
+    test("renders correctly", async ({ page }) => {
+      await page.goto("/app");
+      await expectScreenshot(page, { name: `feature-${theme}` });
+    });
+  });
+}
+```
+
+### `tools` (`@tests/e2e/utils/tools`)
+
+- `TOOL_IDS` — centralized `data-testid` selectors for tool options
+- `openActionManagement(page)` — opens the tool management popover
+
+## Locator Strategy
+
+Use locators in this priority order:
+
+1. **`data-testid` / `aria-label`** — preferred for Onyx components
+   ```typescript
+   page.getByTestId("AppSidebar/new-session")
+   page.getByLabel("admin-page-title")
+   ```
+
+2. **Role-based** — for standard HTML elements
+   ```typescript
+   page.getByRole("button", { name: "Create" })
+   page.getByRole("dialog")
+   ```
+
+3. **Text/Label** — for visible text content
+   ```typescript
+   page.getByText("Custom Assistant")
+   page.getByLabel("Email")
+   ```
+
+4. **CSS selectors** — last resort, only when above won't work
+   ```typescript
+   page.locator('input[name="name"]')
+   page.locator("#onyx-chat-input-textarea")
+   ```
+
+**Never use** `page.locator` with complex CSS/XPath when a built-in locator works.
+
+## Assertions
+
+Use web-first assertions — they auto-retry until the condition is met:
+
+```typescript
+// Visibility
+await expect(page.getByTestId("onyx-logo")).toBeVisible({ timeout: 5000 });
+
+// Text content
+await expect(page.getByTestId("assistant-name-display")).toHaveText("My Assistant");
+
+// Count
+await expect(page.locator('[data-testid="onyx-ai-message"]')).toHaveCount(2, { timeout: 30000 });
+
+// URL
+await expect(page).toHaveURL(/chatId=/);
+
+// Element state
+await expect(toggle).toBeChecked();
+await expect(button).toBeEnabled();
+```
+
+**Never use** `assert` statements or hardcoded `page.waitForTimeout()`.
+
+## Waiting Strategy
+
+```typescript
+// Wait for load state after navigation
+await page.goto("/app");
+await page.waitForLoadState("networkidle");
+
+// Wait for specific element
+await page.getByTestId("chat-intro").waitFor({ state: "visible", timeout: 10000 });
+
+// Wait for URL change
+await page.waitForFunction(() => window.location.href.includes("chatId="), null, { timeout: 10000 });
+
+// Wait for network response
+await page.waitForResponse(resp => resp.url().includes("/api/chat") && resp.status() === 200);
+```
+
+## Best Practices
+
+1. **Descriptive test names** — clearly state expected behavior: `"should display greeting message when opening new chat"`
+2. **API-first setup** — use `OnyxApiClient` for backend state; reserve UI interactions for the behavior under test
+3. **User isolation** — tests that modify visible app state (sidebar, chat history) should run as the worker-specific user via `loginAsWorkerUser(page, testInfo.workerIndex)` (not admin) and clean up resources in `afterAll`. Each parallel worker gets its own user, preventing cross-contamination. Reserve `loginAsRandomUser` for flows that require a brand-new user (e.g. onboarding)
+4. **DRY helpers** — extract reusable logic into `utils/` with JSDoc comments
+5. **No hardcoded waits** — use `waitFor`, `waitForLoadState`, or web-first assertions
+6. **Parallel-safe** — no shared mutable state between tests. Prefer static, human-readable names (e.g. `"E2E-CMD Chat 1"`) and clean up resources by ID in `afterAll`. This keeps screenshots deterministic and avoids needing to mask/hide dynamic text. Only fall back to timestamps (`\`test-${Date.now()}\``) when resources cannot be reliably cleaned up or when name collisions across parallel workers would cause functional failures
+7. **Error context** — catch and re-throw with useful debug info (page text, URL, etc.)
+8. **Tag slow tests** — mark serial/slow tests with `@exclusive` in the test title
+9. **Visual regression** — use `expectScreenshot()` for UI consistency checks
+10. **Minimal comments** — only comment to clarify non-obvious intent; never restate what the next line of code does

.git-blame-ignore-revs

@@ -0,0 +1,8 @@
+# Exclude these commits from git blame (e.g. mass reformatting).
+# These are ignored by GitHub automatically.
+# To enable this locally, run:
+#
+#    git config blame.ignoreRevsFile .git-blame-ignore-revs
+
+3134e5f840c12c8f32613ce520101a047c89dcc2  # refactor(whitespace): rm temporary react fragments (#7161)
+ed3f72bc75f3e3a9ae9e4d8cd38278f9c97e78b4  # refactor(whitespace): rm react fragment #7190

.github/CODEOWNERS

@@ -1,3 +1,10 @@
 * @onyx-dot-app/onyx-core-team
 # Helm charts Owners
 /helm/ @justin-tahara
+
+# Web standards updates
+/web/STANDARDS.md @raunakab @Weves
+
+# Agent context files
+/CLAUDE.md @Weves
+/AGENTS.md @Weves

.github/actionlint.yml

@@ -17,6 +17,7 @@ self-hosted-runner:
     - runner=16cpu-linux-x64
     - ubuntu-slim # Currently in public preview
     - volume=40gb
+    - volume=50gb
 
 # Configuration variables in array of strings defined in your repository or
 # organization. `null` means disabling configuration variables check.

.github/actions/custom-build-and-push/action.yml

@@ -1,135 +0,0 @@
-name: 'Build and Push Docker Image with Retry'
-description: 'Attempts to build and push a Docker image, with a retry on failure'
-inputs:
-  context:
-    description: 'Build context'
-    required: true
-  file:
-    description: 'Dockerfile location'
-    required: true
-  platforms:
-    description: 'Target platforms'
-    required: true
-  pull:
-    description: 'Always attempt to pull a newer version of the image'
-    required: false
-    default: 'true'
-  push:
-    description: 'Push the image to registry'
-    required: false
-    default: 'true'
-  load:
-    description: 'Load the image into Docker daemon'
-    required: false
-    default: 'true'
-  tags:
-    description: 'Image tags'
-    required: true
-  no-cache:
-    description: 'Read from cache'
-    required: false
-    default: 'false'
-  cache-from:
-    description: 'Cache sources'
-    required: false
-  cache-to:
-    description: 'Cache destinations'
-    required: false
-  outputs:
-    description: 'Output destinations'
-    required: false
-  provenance:
-    description: 'Generate provenance attestation'
-    required: false
-    default: 'false'
-  build-args:
-    description: 'Build arguments'
-    required: false
-  retry-wait-time:
-    description: 'Time to wait before attempt 2 in seconds'
-    required: false
-    default: '60'
-  retry-wait-time-2:
-    description: 'Time to wait before attempt 3 in seconds'
-    required: false
-    default: '120'
-
-runs:
-  using: "composite"
-  steps:
-    - name: Build and push Docker image (Attempt 1 of 3)
-      id: buildx1
-      uses: docker/build-push-action@263435318d21b8e681c14492fe198d362a7d2c83 # ratchet:docker/build-push-action@v6
-      continue-on-error: true
-      with:
-        context: ${{ inputs.context }}
-        file: ${{ inputs.file }}
-        platforms: ${{ inputs.platforms }}
-        pull: ${{ inputs.pull }}
-        push: ${{ inputs.push }}
-        load: ${{ inputs.load }}
-        tags: ${{ inputs.tags }}
-        no-cache: ${{ inputs.no-cache }}
-        cache-from: ${{ inputs.cache-from }}
-        cache-to: ${{ inputs.cache-to }}
-        outputs: ${{ inputs.outputs }}
-        provenance: ${{ inputs.provenance }}
-        build-args: ${{ inputs.build-args }}
-
-    - name: Wait before attempt 2
-      if: steps.buildx1.outcome != 'success'
-      run: |
-        echo "First attempt failed. Waiting ${{ inputs.retry-wait-time }} seconds before retry..."
-        sleep ${{ inputs.retry-wait-time }}
-      shell: bash
-
-    - name: Build and push Docker image (Attempt 2 of 3)
-      id: buildx2
-      if: steps.buildx1.outcome != 'success'
-      uses: docker/build-push-action@263435318d21b8e681c14492fe198d362a7d2c83 # ratchet:docker/build-push-action@v6
-      with:
-        context: ${{ inputs.context }}
-        file: ${{ inputs.file }}
-        platforms: ${{ inputs.platforms }}
-        pull: ${{ inputs.pull }}
-        push: ${{ inputs.push }}
-        load: ${{ inputs.load }}
-        tags: ${{ inputs.tags }}
-        no-cache: ${{ inputs.no-cache }}
-        cache-from: ${{ inputs.cache-from }}
-        cache-to: ${{ inputs.cache-to }}
-        outputs: ${{ inputs.outputs }}
-        provenance: ${{ inputs.provenance }}
-        build-args: ${{ inputs.build-args }}
-
-    - name: Wait before attempt 3
-      if: steps.buildx1.outcome != 'success' && steps.buildx2.outcome != 'success'
-      run: |
-        echo "Second attempt failed. Waiting ${{ inputs.retry-wait-time-2 }} seconds before retry..."
-        sleep ${{ inputs.retry-wait-time-2 }}
-      shell: bash
-
-    - name: Build and push Docker image (Attempt 3 of 3)
-      id: buildx3
-      if: steps.buildx1.outcome != 'success' && steps.buildx2.outcome != 'success'
-      uses: docker/build-push-action@263435318d21b8e681c14492fe198d362a7d2c83 # ratchet:docker/build-push-action@v6
-      with:
-        context: ${{ inputs.context }}
-        file: ${{ inputs.file }}
-        platforms: ${{ inputs.platforms }}
-        pull: ${{ inputs.pull }}
-        push: ${{ inputs.push }}
-        load: ${{ inputs.load }}
-        tags: ${{ inputs.tags }}
-        no-cache: ${{ inputs.no-cache }}
-        cache-from: ${{ inputs.cache-from }}
-        cache-to: ${{ inputs.cache-to }}
-        outputs: ${{ inputs.outputs }}
-        provenance: ${{ inputs.provenance }}
-        build-args: ${{ inputs.build-args }}
-
-    - name: Report failure
-      if: steps.buildx1.outcome != 'success' && steps.buildx2.outcome != 'success' && steps.buildx3.outcome != 'success'
-      run: |
-        echo "All attempts failed. Possible transient infrastucture issues? Try again later or inspect logs for details."
-      shell: bash

.github/actions/prepare-build/action.yml

@@ -1,42 +0,0 @@
-name: "Prepare Build (OpenAPI generation)"
-description: "Sets up Python with uv, installs deps, generates OpenAPI schema and Python client, uploads artifact"
-inputs:
-  docker-username:
-    required: true
-  docker-password:
-    required: true
-runs:
-  using: "composite"
-  steps:
-    - name: Setup Python and Install Dependencies
-      uses: ./.github/actions/setup-python-and-install-dependencies
-
-    - name: Generate OpenAPI schema
-      shell: bash
-      working-directory: backend
-      env:
-        PYTHONPATH: "."
-      run: |
-        python scripts/onyx_openapi_schema.py --filename generated/openapi.json
-
-    # 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: ${{ inputs['docker-username'] }}
-        password: ${{ inputs['docker-password'] }}
-
-    - name: Generate OpenAPI Python client
-      shell: bash
-      run: |
-        docker run --rm \
-          -v "${{ github.workspace }}/backend/generated:/local" \
-          openapitools/openapi-generator-cli generate \
-          -i /local/openapi.json \
-          -g python \
-          -o /local/onyx_openapi_client \
-          --package-name onyx_openapi_client \
-          --skip-validate-spec \
-          --openapi-normalizer "SIMPLIFY_ONEOF_ANYOF=true,SET_OAS3_NULLABLE=true"

.github/actions/setup-playwright/action.yml

@@ -7,9 +7,9 @@ runs:
       uses: runs-on/cache@50350ad4242587b6c8c2baa2e740b1bc11285ff4 # ratchet:runs-on/cache@v4
       with:
         path: ~/.cache/ms-playwright
-        key: ${{ runner.os }}-playwright-${{ hashFiles('backend/requirements/default.txt') }}
+        key: ${{ runner.os }}-${{ runner.arch }}-playwright-${{ hashFiles('backend/requirements/default.txt') }}
         restore-keys: |
-          ${{ runner.os }}-playwright-
+          ${{ runner.os }}-${{ runner.arch }}-playwright-
 
     - name: Install playwright
       shell: bash

.github/actions/setup-python-and-install-dependencies/action.yml

@@ -1,22 +1,45 @@
 name: "Setup Python and Install Dependencies"
 description: "Sets up Python with uv and installs deps"
+inputs:
+  requirements:
+    description: "Newline-separated list of requirement files to install (relative to repo root)"
+    required: true
 runs:
   using: "composite"
   steps:
-    - name: Setup uv
-      uses: astral-sh/setup-uv@caf0cab7a618c569241d31dcd442f54681755d39 # ratchet:astral-sh/setup-uv@v3
-      # TODO: Enable caching once there is a uv.lock file checked in.
-      # with:
-      #   enable-cache: true
+    - name: Compute requirements hash
+      id: req-hash
+      shell: bash
+      env:
+        REQUIREMENTS: ${{ inputs.requirements }}
+      run: |
+        # Hash the contents of the specified requirement files
+        hash=""
+        while IFS= read -r req; do
+          if [ -n "$req" ] && [ -f "$req" ]; then
+            hash="$hash$(sha256sum "$req")"
+          fi
+        done <<< "$REQUIREMENTS"
+        echo "hash=$(echo "$hash" | sha256sum | cut -d' ' -f1)" >> "$GITHUB_OUTPUT"
 
+    # NOTE: This comes before Setup uv since clean-ups run in reverse chronological order
+    # such that Setup uv's prune-cache is able to prune the cache before we upload.
     - name: Cache uv cache directory
       uses: runs-on/cache@50350ad4242587b6c8c2baa2e740b1bc11285ff4 # ratchet:runs-on/cache@v4
       with:
         path: ~/.cache/uv
-        key: ${{ runner.os }}-uv-${{ hashFiles('backend/requirements/*.txt', 'backend/pyproject.toml') }}
+        key: ${{ runner.os }}-uv-${{ steps.req-hash.outputs.hash }}
         restore-keys: |
           ${{ runner.os }}-uv-
 
+    - name: Setup uv
+      uses: astral-sh/setup-uv@ed21f2f24f8dd64503750218de024bcf64c7250a # ratchet:astral-sh/setup-uv@v7
+      with:
+        version: "0.9.9"
+      # TODO: Enable caching once there is a uv.lock file checked in.
+      # with:
+      #   enable-cache: true
+
     - name: Setup Python
       uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # ratchet:actions/setup-python@v5
       with:
@@ -24,15 +47,30 @@ runs:
 
     - name: Create virtual environment
       shell: bash
-      run: |
-        uv venv ${{ runner.temp }}/venv
-        echo "VENV_PATH=${{ runner.temp }}/venv" >> $GITHUB_ENV
-        echo "${{ runner.temp }}/venv/bin" >> $GITHUB_PATH
+      env:
+        VENV_DIR: ${{ runner.temp }}/venv
+      run: | # zizmor: ignore[github-env]
+        uv venv "$VENV_DIR"
+        # Validate path before adding to GITHUB_PATH to prevent code injection
+        if [ -d "$VENV_DIR/bin" ]; then
+          realpath "$VENV_DIR/bin" >> "$GITHUB_PATH"
+        else
+          echo "Error: $VENV_DIR/bin does not exist"
+          exit 1
+        fi
 
     - name: Install Python dependencies with uv
       shell: bash
+      env:
+        REQUIREMENTS: ${{ inputs.requirements }}
       run: |
-        uv pip install \
-          -r backend/requirements/default.txt \
-          -r backend/requirements/dev.txt \
-          -r backend/requirements/model_server.txt
+        # Build the uv pip install command with each requirement file as array elements
+        cmd=("uv" "pip" "install")
+        while IFS= read -r req; do
+          # Skip empty lines
+          if [ -n "$req" ]; then
+            cmd+=("-r" "$req")
+          fi
+        done <<< "$REQUIREMENTS"
+        echo "Running: ${cmd[*]}"
+        "${cmd[@]}"

.github/actions/slack-notify/action.yml

@@ -21,26 +21,27 @@ runs:
       shell: bash
       env:
         SLACK_WEBHOOK_URL: ${{ inputs.webhook-url }}
+        FAILED_JOBS: ${{ inputs.failed-jobs }}
+        TITLE: ${{ inputs.title }}
+        REF_NAME: ${{ inputs.ref-name }}
+        REPO: ${{ github.repository }}
+        WORKFLOW: ${{ github.workflow }}
+        RUN_NUMBER: ${{ github.run_number }}
+        RUN_ID: ${{ github.run_id }}
+        SERVER_URL: ${{ github.server_url }}
+        GITHUB_REF_NAME: ${{ github.ref_name }}
       run: |
         if [ -z "$SLACK_WEBHOOK_URL" ]; then
           echo "webhook-url input or SLACK_WEBHOOK_URL env var is not set, skipping notification"
           exit 0
         fi
 
-        # Get inputs with defaults
-        FAILED_JOBS="${{ inputs.failed-jobs }}"
-        TITLE="${{ inputs.title }}"
-        REF_NAME="${{ inputs.ref-name }}"
-        REPO="${{ github.repository }}"
-        WORKFLOW="${{ github.workflow }}"
-        RUN_NUMBER="${{ github.run_number }}"
-        RUN_ID="${{ github.run_id }}"
-        SERVER_URL="${{ github.server_url }}"
+        # Build workflow URL
         WORKFLOW_URL="${SERVER_URL}/${REPO}/actions/runs/${RUN_ID}"
 
         # Use ref_name from input or fall back to github.ref_name
         if [ -z "$REF_NAME" ]; then
-          REF_NAME="${{ github.ref_name }}"
+          REF_NAME="$GITHUB_REF_NAME"
         fi
 
         # Escape JSON special characters

.github/dependabot.yml

@@ -4,6 +4,8 @@ updates:
     directory: "/"
     schedule:
       interval: "weekly"
+    cooldown:
+      default-days: 7
     open-pull-requests-limit: 3
     assignees:
       - "jmelahman"
@@ -13,6 +15,8 @@ updates:
     directory: "/backend"
     schedule:
       interval: "weekly"
+    cooldown:
+      default-days: 7
     open-pull-requests-limit: 3
     assignees:
       - "jmelahman"

.github/pull_request_template.md

@@ -1,11 +1,12 @@
 ## Description
 
-[Provide a brief description of the changes in this PR]
+<!--- Provide a brief description of the changes in this PR --->
 
 ## How Has This Been Tested?
 
-[Describe the tests you ran to verify your changes]
+<!--- Describe the tests you ran to verify your changes --->
 
 ## Additional Options
 
+- [ ] [Required] I have considered whether this PR needs to be cherry-picked to the latest beta branch.
 - [ ] [Optional] Override Linear Check

.github/workflows/check-lazy-imports.yml

@@ -1,27 +0,0 @@
-name: Check Lazy Imports
-concurrency:
-  group: Check-Lazy-Imports-${{ github.workflow }}-${{ github.head_ref || github.event.workflow_run.head_branch || github.run_id }}
-  cancel-in-progress: true
-
-on:
-  merge_group:
-  pull_request:
-    branches:
-      - main
-      - 'release/**'
-
-jobs:
-  check-lazy-imports:
-    runs-on: ubuntu-latest
-
-    steps:
-    - name: Checkout code
-      uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # ratchet:actions/checkout@v4
-
-    - name: Set up Python
-      uses: actions/setup-python@e797f83bcb11b83ae66e0230d6156d7c80228e7c # ratchet:actions/setup-python@v6
-      with:
-        python-version: '3.11'
-
-    - name: Check lazy imports
-      run: python3 backend/scripts/check_lazy_imports.py

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

@@ -10,17 +10,21 @@ on:
         description: "The version (ie v1.0.0-beta.0) to tag as beta"
         required: true
 
+permissions:
+  contents: read
+
 jobs:
   tag:
     # See https://runs-on.com/runners/linux/
     # use a lower powered instance since this just does i/o to docker hub
     runs-on: [runs-on, runner=2cpu-linux-x64, "run-id=${{ github.run_id }}-tag"]
+    timeout-minutes: 45
     steps:
       - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@e468171a9de216ec08956ac3ada2f0791b6bd435 # ratchet:docker/setup-buildx-action@v3
+        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 }}
@@ -29,13 +33,19 @@ jobs:
         run: echo "DOCKER_CLI_EXPERIMENTAL=enabled" >> $GITHUB_ENV
 
       - name: Pull, Tag and Push Web Server Image
+        env:
+          VERSION: ${{ github.event.inputs.version }}
         run: |
-          docker buildx imagetools create -t onyxdotapp/onyx-web-server:beta onyxdotapp/onyx-web-server:${{ github.event.inputs.version }}
+          docker buildx imagetools create -t onyxdotapp/onyx-web-server:beta onyxdotapp/onyx-web-server:${VERSION}
 
       - name: Pull, Tag and Push API Server Image
+        env:
+          VERSION: ${{ github.event.inputs.version }}
         run: |
-          docker buildx imagetools create -t onyxdotapp/onyx-backend:beta onyxdotapp/onyx-backend:${{ github.event.inputs.version }}
+          docker buildx imagetools create -t onyxdotapp/onyx-backend:beta onyxdotapp/onyx-backend:${VERSION}
 
       - name: Pull, Tag and Push Model Server Image
+        env:
+          VERSION: ${{ github.event.inputs.version }}
         run: |
-          docker buildx imagetools create -t onyxdotapp/onyx-model-server:beta onyxdotapp/onyx-model-server:${{ github.event.inputs.version }}
+          docker buildx imagetools create -t onyxdotapp/onyx-model-server:beta onyxdotapp/onyx-model-server:${VERSION}

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

@@ -10,17 +10,21 @@ on:
         description: "The version (ie v0.0.1) to tag as latest"
         required: true
 
+permissions:
+  contents: read
+
 jobs:
   tag:
     # See https://runs-on.com/runners/linux/
     # use a lower powered instance since this just does i/o to docker hub
     runs-on: [runs-on, runner=2cpu-linux-x64, "run-id=${{ github.run_id }}-tag"]
+    timeout-minutes: 45
     steps:
       - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@e468171a9de216ec08956ac3ada2f0791b6bd435 # ratchet:docker/setup-buildx-action@v3
+        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 }}
@@ -29,13 +33,19 @@ jobs:
         run: echo "DOCKER_CLI_EXPERIMENTAL=enabled" >> $GITHUB_ENV
 
       - name: Pull, Tag and Push Web Server Image
+        env:
+          VERSION: ${{ github.event.inputs.version }}
         run: |
-          docker buildx imagetools create -t onyxdotapp/onyx-web-server:latest onyxdotapp/onyx-web-server:${{ github.event.inputs.version }}
+          docker buildx imagetools create -t onyxdotapp/onyx-web-server:latest onyxdotapp/onyx-web-server:${VERSION}
 
       - name: Pull, Tag and Push API Server Image
+        env:
+          VERSION: ${{ github.event.inputs.version }}
         run: |
-          docker buildx imagetools create -t onyxdotapp/onyx-backend:latest onyxdotapp/onyx-backend:${{ github.event.inputs.version }}
+          docker buildx imagetools create -t onyxdotapp/onyx-backend:latest onyxdotapp/onyx-backend:${VERSION}
 
       - name: Pull, Tag and Push Model Server Image
+        env:
+          VERSION: ${{ github.event.inputs.version }}
         run: |
-          docker buildx imagetools create -t onyxdotapp/onyx-model-server:latest onyxdotapp/onyx-model-server:${{ github.event.inputs.version }}
+          docker buildx imagetools create -t onyxdotapp/onyx-model-server:latest onyxdotapp/onyx-model-server:${VERSION}

.github/workflows/helm-chart-releases.yml

@@ -12,11 +12,13 @@ jobs:
     permissions:
       contents: write
     runs-on: ubuntu-latest
+    timeout-minutes: 45
     steps:
       - name: Checkout
-        uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # ratchet:actions/checkout@v4
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # ratchet:actions/checkout@v6
         with:
           fetch-depth: 0
+          persist-credentials: false
 
       - name: Install Helm CLI
         uses: azure/setup-helm@1a275c3b69536ee54be43f2070a358922e12c8d4 # ratchet:azure/setup-helm@v4
@@ -27,9 +29,11 @@ jobs:
         run: |
           helm repo add ingress-nginx https://kubernetes.github.io/ingress-nginx
           helm repo add onyx-vespa https://onyx-dot-app.github.io/vespa-helm-charts
+          helm repo add opensearch https://opensearch-project.github.io/helm-charts
           helm repo add cloudnative-pg https://cloudnative-pg.github.io/charts
           helm repo add ot-container-kit https://ot-container-kit.github.io/helm-charts
           helm repo add minio https://charts.min.io/
+          helm repo add code-interpreter https://onyx-dot-app.github.io/code-interpreter/
           helm repo update
 
       - name: Build chart dependencies

.github/workflows/merge-group.yml

@@ -0,0 +1,31 @@
+name: Merge Group-Specific
+
+on:
+  merge_group:
+
+permissions:
+  contents: read
+
+jobs:
+  # This job immediately succeeds to satisfy branch protection rules on merge_group events.
+  # There is a similarly named "required" job in pr-integration-tests.yml which runs the actual
+  # integration tests. That job runs on both pull_request and merge_group events, and this job
+  # exists solely to provide a fast-passing check with the same name for branch protection.
+  # The actual tests remain enforced on presubmit (pull_request events).
+  required:
+    runs-on: ubuntu-latest
+    timeout-minutes: 45
+    steps:
+      - name: Success
+        run: echo "Success"
+  # This job immediately succeeds to satisfy branch protection rules on merge_group events.
+  # There is a similarly named "playwright-required" job in pr-playwright-tests.yml which runs
+  # the actual playwright tests. That job runs on both pull_request and merge_group events, and
+  # this job exists solely to provide a fast-passing check with the same name for branch protection.
+  # The actual tests remain enforced on presubmit (pull_request events).
+  playwright-required:
+    runs-on: ubuntu-latest
+    timeout-minutes: 45
+    steps:
+      - name: Success
+        run: echo "Success"

.github/workflows/nightly-close-stale-issues.yml

@@ -11,8 +11,9 @@ permissions:
 jobs:
   stale:
     runs-on: ubuntu-latest
+    timeout-minutes: 45
     steps:
-      - uses: actions/stale@5bef64f19d7facfb25b37b414482c7164d639639 # ratchet:actions/stale@v9
+      - uses: actions/stale@997185467fa4f803885201cee163a9f38240193d # ratchet:actions/stale@v10
         with:
           stale-issue-message: 'This issue is stale because it has been open 75 days with no activity. Remove stale label or comment or this will be closed in 15 days.'
           stale-pr-message: 'This PR is stale because it has been open 75 days with no activity. Remove stale label or comment or this will be closed in 15 days.'

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

@@ -1,142 +0,0 @@
-# Scan for problematic software licenses
-
-# trivy has their own rate limiting issues causing this action to flake
-# we worked around it by hardcoding to different db repos in env
-# can re-enable when they figure it out
-# https://github.com/aquasecurity/trivy/discussions/7538
-# https://github.com/aquasecurity/trivy-action/issues/389
-
-name: 'Nightly - Scan licenses'
-on:
-#   schedule:
-#     - cron: '0 14 * * *'  # Runs every day at 6 AM PST / 7 AM PDT / 2 PM UTC
-  workflow_dispatch:  # Allows manual triggering
-
-permissions:
-  actions: read
-  contents: read
-  security-events: write
-
-jobs:
-  scan-licenses:
-    # See https://runs-on.com/runners/linux/
-    runs-on: [runs-on,runner=2cpu-linux-x64,"run-id=${{ github.run_id }}-scan-licenses"]
-
-    steps:
-      - name: Checkout code
-        uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # ratchet:actions/checkout@v4
-
-      - name: Set up Python
-        uses: actions/setup-python@e797f83bcb11b83ae66e0230d6156d7c80228e7c # ratchet:actions/setup-python@v6
-        with:
-          python-version: '3.11'
-          cache: 'pip'
-          cache-dependency-path: |
-            backend/requirements/default.txt
-            backend/requirements/dev.txt
-            backend/requirements/model_server.txt
-
-      - name: Get explicit and transitive dependencies
-        run: |
-          python -m pip install --upgrade pip
-          pip install --retries 5 --timeout 30 -r backend/requirements/default.txt
-          pip install --retries 5 --timeout 30 -r backend/requirements/dev.txt
-          pip install --retries 5 --timeout 30 -r backend/requirements/model_server.txt
-          pip freeze > requirements-all.txt
-
-      - name: Check python
-        id: license_check_report
-        uses: pilosus/action-pip-license-checker@e909b0226ff49d3235c99c4585bc617f49fff16a # ratchet:pilosus/action-pip-license-checker@v3
-        with:
-          requirements: 'requirements-all.txt'
-          fail: 'Copyleft'
-          exclude: '(?i)^(pylint|aio[-_]*).*'
-
-      - name: Print report
-        if: always()
-        run: echo "${{ steps.license_check_report.outputs.report }}"
-
-      - name: Install npm dependencies
-        working-directory: ./web
-        run: npm ci
-
-        # be careful enabling the sarif and upload as it may spam the security tab
-        # with a huge amount of items. Work out the issues before enabling upload.
-#       - name: Run Trivy vulnerability scanner in repo mode
-#         if: always()
-#         uses: aquasecurity/trivy-action@b6643a29fecd7f34b3597bc6acb0a98b03d33ff8 # ratchet:aquasecurity/trivy-action@0.33.1
-#         with:
-#           scan-type: fs
-#           scan-ref: .
-#           scanners: license
-#           format: table
-#           severity: HIGH,CRITICAL
-# #           format: sarif
-# #           output: trivy-results.sarif
-#
-# #       - name: Upload Trivy scan results to GitHub Security tab
-# #         uses: github/codeql-action/upload-sarif@v3
-# #         with:
-# #           sarif_file: trivy-results.sarif
-
-  scan-trivy:
-    # See https://runs-on.com/runners/linux/
-    runs-on: [runs-on,runner=2cpu-linux-x64,"run-id=${{ github.run_id }}-scan-trivy"]
-
-    steps:
-    - name: Set up Docker Buildx
-      uses: docker/setup-buildx-action@e468171a9de216ec08956ac3ada2f0791b6bd435 # ratchet:docker/setup-buildx-action@v3
-
-    - name: Login to Docker Hub
-      uses: docker/login-action@5e57cd118135c172c3672efd75eb46360885c0ef # ratchet:docker/login-action@v3
-      with:
-        username: ${{ secrets.DOCKER_USERNAME }}
-        password: ${{ secrets.DOCKER_TOKEN }}
-
-    # Backend
-    - name: Pull backend docker image
-      run: docker pull onyxdotapp/onyx-backend:latest
-
-    - name: Run Trivy vulnerability scanner on backend
-      uses: aquasecurity/trivy-action@b6643a29fecd7f34b3597bc6acb0a98b03d33ff8 # ratchet:aquasecurity/trivy-action@0.33.1
-      env:
-        TRIVY_DB_REPOSITORY: 'public.ecr.aws/aquasecurity/trivy-db:2'
-        TRIVY_JAVA_DB_REPOSITORY: 'public.ecr.aws/aquasecurity/trivy-java-db:1'
-      with:
-        image-ref: onyxdotapp/onyx-backend:latest
-        scanners: license
-        severity: HIGH,CRITICAL
-        vuln-type: library
-        exit-code: 0  # Set to 1 if we want a failed scan to fail the workflow
-
-    # Web server
-    - name: Pull web server docker image
-      run: docker pull onyxdotapp/onyx-web-server:latest
-
-    - name: Run Trivy vulnerability scanner on web server
-      uses: aquasecurity/trivy-action@b6643a29fecd7f34b3597bc6acb0a98b03d33ff8 # ratchet:aquasecurity/trivy-action@0.33.1
-      env:
-        TRIVY_DB_REPOSITORY: 'public.ecr.aws/aquasecurity/trivy-db:2'
-        TRIVY_JAVA_DB_REPOSITORY: 'public.ecr.aws/aquasecurity/trivy-java-db:1'
-      with:
-        image-ref: onyxdotapp/onyx-web-server:latest
-        scanners: license
-        severity: HIGH,CRITICAL
-        vuln-type: library
-        exit-code: 0
-
-    # Model server
-    - name: Pull model server docker image
-      run: docker pull onyxdotapp/onyx-model-server:latest
-
-    - name: Run Trivy vulnerability scanner
-      uses: aquasecurity/trivy-action@b6643a29fecd7f34b3597bc6acb0a98b03d33ff8 # ratchet:aquasecurity/trivy-action@0.33.1
-      env:
-        TRIVY_DB_REPOSITORY: 'public.ecr.aws/aquasecurity/trivy-db:2'
-        TRIVY_JAVA_DB_REPOSITORY: 'public.ecr.aws/aquasecurity/trivy-java-db:1'
-      with:
-        image-ref: onyxdotapp/onyx-model-server:latest
-        scanners: license
-        severity: HIGH,CRITICAL
-        vuln-type: library
-        exit-code: 0

.github/workflows/pr-beta-cherrypick-check.yml

@@ -0,0 +1,28 @@
+name: Require beta cherry-pick consideration
+concurrency:
+  group: Require-Beta-Cherrypick-Consideration-${{ github.workflow }}-${{ github.head_ref || github.event.workflow_run.head_branch || github.run_id }}
+  cancel-in-progress: true
+
+on:
+  pull_request:
+    types: [opened, edited, reopened, synchronize]
+
+permissions:
+  contents: read
+
+jobs:
+  beta-cherrypick-check:
+    runs-on: ubuntu-latest
+    timeout-minutes: 45
+    steps:
+      - name: Check PR body for beta cherry-pick consideration
+        env:
+          PR_BODY: ${{ github.event.pull_request.body }}
+        run: |
+          if echo "$PR_BODY" | grep -qiE "\\[x\\][[:space:]]*\\[Required\\][[:space:]]*I have considered whether this PR needs to be cherry[- ]picked to the latest beta branch"; then
+            echo "Cherry-pick consideration box is checked. Check passed."
+            exit 0
+          fi
+
+          echo "::error::Please check the 'I have considered whether this PR needs to be cherry-picked to the latest beta branch' box in the PR description."
+          exit 1

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

@@ -0,0 +1,65 @@
+name: Database Tests
+concurrency:
+  group: Database-Tests-${{ github.workflow }}-${{ github.head_ref || github.event.workflow_run.head_branch || github.run_id }}
+  cancel-in-progress: true
+
+on:
+  merge_group:
+  pull_request:
+    branches:
+      - main
+      - "release/**"
+  push:
+    tags:
+      - "v*.*.*"
+
+permissions:
+  contents: read
+
+jobs:
+  database-tests:
+    runs-on:
+      - runs-on
+      - runner=2cpu-linux-arm64
+      - "run-id=${{ github.run_id }}-database-tests"
+    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: Setup Python and Install Dependencies
+        uses: ./.github/actions/setup-python-and-install-dependencies
+        with:
+          requirements: |
+            backend/requirements/default.txt
+            backend/requirements/dev.txt
+
+      - 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@c94ce9fb468520275223c153574b00df6fe4bcc9 # ratchet:docker/login-action@v3
+        with:
+          username: ${{ secrets.DOCKER_USERNAME }}
+          password: ${{ secrets.DOCKER_TOKEN }}
+
+      - name: Start Docker containers
+        working-directory: ./deployment/docker_compose
+        run: |
+          docker compose -f docker-compose.yml -f docker-compose.dev.yml up -d \
+            relational_db
+
+      - name: Run Database Tests
+        working-directory: ./backend
+        run: pytest -m alembic tests/integration/tests/migrations/

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

@@ -0,0 +1,114 @@
+name: Build Desktop App
+concurrency:
+  group: Build-Desktop-App-${{ github.workflow }}-${{ github.head_ref || github.event.workflow_run.head_branch || github.run_id }}
+  cancel-in-progress: true
+
+on:
+  merge_group:
+  pull_request:
+    branches:
+      - main
+      - "release/**"
+    paths:
+      - "desktop/**"
+      - ".github/workflows/pr-desktop-build.yml"
+  push:
+    tags:
+      - "v*.*.*"
+
+permissions:
+  contents: read
+
+jobs:
+  build-desktop:
+    name: Build Desktop (${{ matrix.platform }})
+    runs-on: ${{ matrix.os }}
+    timeout-minutes: 60
+    strategy:
+      fail-fast: false
+      matrix:
+        include:
+          - platform: linux
+            os: ubuntu-latest
+            target: x86_64-unknown-linux-gnu
+            args: "--bundles deb,rpm"
+          # TODO: Fix and enable the macOS build.
+          #- platform: macos
+          #  os: macos-latest
+          #  target: universal-apple-darwin
+          #  args: "--target universal-apple-darwin"
+          # TODO: Fix and enable the Windows build.
+          #- platform: windows
+          #  os: windows-latest
+          #  target: x86_64-pc-windows-msvc
+          #  args: ""
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd
+        with:
+          persist-credentials: false
+
+      - name: Setup node
+        uses: actions/setup-node@6044e13b5dc448c55e2357c09f80417699197238
+        with:
+          node-version: 24
+          cache: "npm" # zizmor: ignore[cache-poisoning]
+          cache-dependency-path: ./desktop/package-lock.json
+
+      - name: Setup Rust
+        uses: dtolnay/rust-toolchain@4be9e76fd7c4901c61fb841f559994984270fce7
+        with:
+          toolchain: stable
+          targets: ${{ matrix.target }}
+
+      - name: Cache Cargo registry and build
+        uses: actions/cache@cdf6c1fa76f9f475f3d7449005a359c84ca0f306 # zizmor: ignore[cache-poisoning]
+        with:
+          path: |
+            ~/.cargo/bin/
+            ~/.cargo/registry/index/
+            ~/.cargo/registry/cache/
+            ~/.cargo/git/db/
+            desktop/src-tauri/target/
+          key: ${{ runner.os }}-cargo-${{ hashFiles('desktop/src-tauri/Cargo.lock') }}
+          restore-keys: |
+            ${{ runner.os }}-cargo-
+
+      - name: Install Linux dependencies
+        if: matrix.platform == 'linux'
+        run: |
+          sudo apt-get update
+          sudo apt-get install -y \
+            build-essential \
+            libglib2.0-dev \
+            libgirepository1.0-dev \
+            libgtk-3-dev \
+            libjavascriptcoregtk-4.1-dev \
+            libwebkit2gtk-4.1-dev \
+            libayatana-appindicator3-dev \
+            gobject-introspection \
+            pkg-config \
+            curl \
+            xdg-utils
+
+      - name: Install npm dependencies
+        working-directory: ./desktop
+        run: npm ci
+
+      - name: Build desktop app
+        working-directory: ./desktop
+        run: npx tauri build ${{ matrix.args }}
+        env:
+          TAURI_SIGNING_PRIVATE_KEY: ""
+          TAURI_SIGNING_PRIVATE_KEY_PASSWORD: ""
+
+      - name: Upload build artifacts
+        if: always()
+        uses: actions/upload-artifact@b7c566a772e6b6bfb58ed0dc250532a479d7789f
+        with:
+          name: desktop-build-${{ matrix.platform }}-${{ github.run_id }}
+          path: |
+            desktop/src-tauri/target/release/bundle/
+          retention-days: 7
+          if-no-files-found: ignore

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

@@ -7,14 +7,22 @@ on:
   merge_group:
   pull_request:
     branches: [main]
+  push:
+    tags:
+      - "v*.*.*"
+
+permissions:
+  contents: read
 
 env:
-  # AWS
-  S3_AWS_ACCESS_KEY_ID: ${{ secrets.S3_AWS_ACCESS_KEY_ID }}
-  S3_AWS_SECRET_ACCESS_KEY: ${{ secrets.S3_AWS_SECRET_ACCESS_KEY }}
+  # AWS credentials for S3-specific test
+  S3_AWS_ACCESS_KEY_ID_FOR_TEST: ${{ secrets.S3_AWS_ACCESS_KEY_ID }}
+  S3_AWS_SECRET_ACCESS_KEY_FOR_TEST: ${{ secrets.S3_AWS_SECRET_ACCESS_KEY }}
 
   # MinIO
   S3_ENDPOINT_URL: "http://localhost:9004"
+  S3_AWS_ACCESS_KEY_ID: "minioadmin"
+  S3_AWS_SECRET_ACCESS_KEY: "minioadmin"
 
   # Confluence
   CONFLUENCE_TEST_SPACE_URL: ${{ vars.CONFLUENCE_TEST_SPACE_URL }}
@@ -24,19 +32,34 @@ env:
   CONFLUENCE_ACCESS_TOKEN: ${{ secrets.CONFLUENCE_ACCESS_TOKEN }}
   CONFLUENCE_ACCESS_TOKEN_SCOPED: ${{ secrets.CONFLUENCE_ACCESS_TOKEN_SCOPED }}
 
+  # Jira
+  JIRA_ADMIN_API_TOKEN: ${{ secrets.JIRA_ADMIN_API_TOKEN }}
+
   # LLMs
   OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
   ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
+  VERTEX_CREDENTIALS: ${{ secrets.VERTEX_CREDENTIALS }}
+  VERTEX_LOCATION: ${{ vars.VERTEX_LOCATION }}
+
+  # Code Interpreter
+  # TODO: debug why this is failing and enable
+  CODE_INTERPRETER_BASE_URL: http://localhost:8000
+
+  # OpenSearch
+  OPENSEARCH_ADMIN_PASSWORD: "StrongPassword123!"
 
 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@08eba0b27e820071cde6df949e0beb9ba4906955 # ratchet:actions/checkout@v4
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # ratchet:actions/checkout@v6
+        with:
+          persist-credentials: false
 
       - name: Discover test directories
         id: set-matrix
@@ -53,6 +76,7 @@ jobs:
       - runner=2cpu-linux-arm64
       - ${{ format('run-id={0}-external-dependency-unit-tests-job-{1}', github.run_id, strategy['job-index']) }}
       - extras=s3-cache
+    timeout-minutes: 45
     strategy:
       fail-fast: false
       matrix:
@@ -61,15 +85,23 @@ jobs:
     env:
       PYTHONPATH: ./backend
       MODEL_SERVER_HOST: "disabled"
+      DISABLE_TELEMETRY: "true"
 
     steps:
       - uses: runs-on/action@cd2b598b0515d39d78c38a02d529db87d2196d1e # ratchet:runs-on/action@v2
 
       - name: Checkout code
-        uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # ratchet:actions/checkout@v4
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # ratchet:actions/checkout@v6
+        with:
+          persist-credentials: false
 
       - name: Setup Python and Install Dependencies
         uses: ./.github/actions/setup-python-and-install-dependencies
+        with:
+          requirements: |
+            backend/requirements/default.txt
+            backend/requirements/dev.txt
+            backend/requirements/ee.txt
 
       - name: Setup Playwright
         uses: ./.github/actions/setup-playwright
@@ -78,15 +110,33 @@ 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 }}
 
+      - 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
+
       - name: Set up Standard Dependencies
         run: |
           cd deployment/docker_compose
-          docker compose -f docker-compose.yml -f docker-compose.dev.yml up -d minio relational_db cache index
+          docker compose \
+            -f docker-compose.yml \
+            -f docker-compose.dev.yml \
+            -f docker-compose.opensearch.yml \
+            up -d \
+            minio \
+            relational_db \
+            cache \
+            index \
+            opensearch \
+            code-interpreter
 
       - name: Run migrations
         run: |
@@ -97,10 +147,39 @@ jobs:
 
       - name: Run Tests for ${{ matrix.test-dir }}
         shell: script -q -e -c "bash --noprofile --norc -eo pipefail {0}"
+        env:
+          TEST_DIR: ${{ matrix.test-dir }}
         run: |
           py.test \
             --durations=8 \
             -o junit_family=xunit2 \
             -xv \
             --ff \
-            backend/tests/external_dependency_unit/${{ matrix.test-dir }}
+            backend/tests/external_dependency_unit/${TEST_DIR}
+
+      - name: Collect Docker logs on failure
+        if: failure()
+        run: |
+          mkdir -p docker-logs
+          cd deployment/docker_compose
+
+          # Get list of running containers
+          containers=$(docker compose -f docker-compose.yml -f docker-compose.dev.yml -f docker-compose.opensearch.yml ps -q)
+
+          # Collect logs from each container
+          for container in $containers; do
+            container_name=$(docker inspect --format='{{.Name}}' $container | sed 's/^\///')
+            echo "Collecting logs from $container_name..."
+            docker logs $container > ../../docker-logs/${container_name}.log 2>&1
+          done
+
+          cd ../..
+          echo "Docker logs collected in docker-logs directory"
+
+      - name: Upload Docker logs
+        if: failure()
+        uses: actions/upload-artifact@b7c566a772e6b6bfb58ed0dc250532a479d7789f
+        with:
+          name: docker-logs-${{ matrix.test-dir }}
+          path: docker-logs/
+          retention-days: 7

.github/workflows/pr-helm-chart-testing.yml

@@ -6,226 +6,251 @@ concurrency:
 on:
   merge_group:
   pull_request:
-    branches: [ main ]
-  workflow_dispatch:  # Allows manual triggering
+    branches: [main]
+  push:
+    tags:
+      - "v*.*.*"
+  workflow_dispatch: # Allows manual triggering
+
+permissions:
+  contents: read
 
 jobs:
   helm-chart-check:
     # See https://runs-on.com/runners/linux/
-    runs-on: [runs-on,runner=8cpu-linux-x64,hdd=256,"run-id=${{ github.run_id }}-helm-chart-check"]
+    runs-on:
+      [
+        runs-on,
+        runner=8cpu-linux-x64,
+        hdd=256,
+        "run-id=${{ github.run_id }}-helm-chart-check",
+      ]
+    timeout-minutes: 45
 
     # fetch-depth 0 is required for helm/chart-testing-action
     steps:
-    - name: Checkout code
-      uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # ratchet:actions/checkout@v4
-      with:
-        fetch-depth: 0
+      - name: Checkout code
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # ratchet:actions/checkout@v6
+        with:
+          fetch-depth: 0
+          persist-credentials: false
 
-    - name: Set up Helm
-      uses: azure/setup-helm@1a275c3b69536ee54be43f2070a358922e12c8d4 # ratchet:azure/setup-helm@v4.3.1
-      with:
-        version: v3.19.0
+      - name: Set up Helm
+        uses: azure/setup-helm@1a275c3b69536ee54be43f2070a358922e12c8d4 # ratchet:azure/setup-helm@v4.3.1
+        with:
+          version: v3.19.0
 
-    - name: Set up chart-testing
-      uses: helm/chart-testing-action@6ec842c01de15ebb84c8627d2744a0c2f2755c9f # ratchet:helm/chart-testing-action@v2.8.0
+      - name: Set up chart-testing
+        uses: helm/chart-testing-action@b5eebdd9998021f29756c53432f48dab66394810
+        with:
+          uv_version: "0.9.9"
 
-    # even though we specify chart-dirs in ct.yaml, it isn't used by ct for the list-changed command...
-    - name: Run chart-testing (list-changed)
-      id: list-changed
-      run: |
-        echo "default_branch: ${{ github.event.repository.default_branch }}"
-        changed=$(ct list-changed --remote origin --target-branch ${{ github.event.repository.default_branch }} --chart-dirs deployment/helm/charts)
-        echo "list-changed output: $changed"
-        if [[ -n "$changed" ]]; then
-          echo "changed=true" >> "$GITHUB_OUTPUT"
-        fi
-
-    # uncomment to force run chart-testing
-#     - name: Force run chart-testing (list-changed)
-#       id: list-changed
-#       run: echo "changed=true" >> $GITHUB_OUTPUT
-
-    # lint all charts if any changes were detected
-    - name: Run chart-testing (lint)
-      if: steps.list-changed.outputs.changed == 'true'
-      run: ct lint --config ct.yaml --all
-      # the following would lint only changed charts, but linting isn't expensive
-      # run: ct lint --config ct.yaml --target-branch ${{ github.event.repository.default_branch }}
-
-    - name: Create kind cluster
-      if: steps.list-changed.outputs.changed == 'true'
-      uses: helm/kind-action@92086f6be054225fa813e0a4b13787fc9088faab # ratchet:helm/kind-action@v1.13.0
-
-    - name: Pre-install cluster status check
-      if: steps.list-changed.outputs.changed == 'true'
-      run: |
-        echo "=== Pre-install Cluster Status ==="
-        kubectl get nodes -o wide
-        kubectl get pods --all-namespaces
-        kubectl get storageclass
-
-    - name: Add Helm repositories and update
-      if: steps.list-changed.outputs.changed == 'true'
-      run: |
-        echo "=== Adding Helm repositories ==="
-        helm repo add ingress-nginx https://kubernetes.github.io/ingress-nginx
-        helm repo add vespa https://onyx-dot-app.github.io/vespa-helm-charts
-        helm repo add cloudnative-pg https://cloudnative-pg.github.io/charts
-        helm repo add ot-container-kit https://ot-container-kit.github.io/helm-charts
-        helm repo add minio https://charts.min.io/
-        helm repo update
-
-    - name: Install Redis operator
-      if: steps.list-changed.outputs.changed == 'true'
-      shell: bash
-      run: |
-        echo "=== Installing redis-operator CRDs ==="
-        helm upgrade --install redis-operator ot-container-kit/redis-operator \
-          --namespace redis-operator --create-namespace --wait --timeout 300s
-
-    - name: Pre-pull required images
-      if: steps.list-changed.outputs.changed == 'true'
-      run: |
-        echo "=== Pre-pulling required images to avoid timeout ==="
-        KIND_CLUSTER=$(kubectl config current-context | sed 's/kind-//')
-        echo "Kind cluster: $KIND_CLUSTER"
-
-        IMAGES=(
-          "ghcr.io/cloudnative-pg/cloudnative-pg:1.27.0"
-          "quay.io/opstree/redis:v7.0.15"
-          "docker.io/onyxdotapp/onyx-web-server:latest"
-        )
-
-        for image in "${IMAGES[@]}"; do
-          echo "Pre-pulling $image"
-          if docker pull "$image"; then
-            kind load docker-image "$image" --name "$KIND_CLUSTER" || echo "Failed to load $image into kind"
-          else
-            echo "Failed to pull $image"
+      # even though we specify chart-dirs in ct.yaml, it isn't used by ct for the list-changed command...
+      - name: Run chart-testing (list-changed)
+        id: list-changed
+        env:
+          DEFAULT_BRANCH: ${{ github.event.repository.default_branch }}
+        run: |
+          echo "default_branch: ${DEFAULT_BRANCH}"
+          changed=$(ct list-changed --remote origin --target-branch ${DEFAULT_BRANCH} --chart-dirs deployment/helm/charts)
+          echo "list-changed output: $changed"
+          if [[ -n "$changed" ]]; then
+            echo "changed=true" >> "$GITHUB_OUTPUT"
           fi
-        done
 
-        echo "=== Images loaded into Kind cluster ==="
-        docker exec "$KIND_CLUSTER"-control-plane crictl images | grep -E "(cloudnative-pg|redis|onyx)" || echo "Some images may still be loading..."
+      # uncomment to force run chart-testing
+      #     - name: Force run chart-testing (list-changed)
+      #       id: list-changed
+      #       run: echo "changed=true" >> $GITHUB_OUTPUT
+      # lint all charts if any changes were detected
+      - name: Run chart-testing (lint)
+        if: steps.list-changed.outputs.changed == 'true'
+        run: ct lint --config ct.yaml --all
+        # the following would lint only changed charts, but linting isn't expensive
+        # run: ct lint --config ct.yaml --target-branch ${{ github.event.repository.default_branch }}
 
-    - name: Validate chart dependencies
-      if: steps.list-changed.outputs.changed == 'true'
-      run: |
-        echo "=== Validating chart dependencies ==="
-        cd deployment/helm/charts/onyx
-        helm dependency update
-        helm lint .
+      - name: Create kind cluster
+        if: steps.list-changed.outputs.changed == 'true'
+        uses: helm/kind-action@92086f6be054225fa813e0a4b13787fc9088faab # ratchet:helm/kind-action@v1.13.0
 
-    - name: Run chart-testing (install) with enhanced monitoring
-      timeout-minutes: 25
-      if: steps.list-changed.outputs.changed == 'true'
-      run: |
-        echo "=== Starting chart installation with monitoring ==="
+      - name: Pre-install cluster status check
+        if: steps.list-changed.outputs.changed == 'true'
+        run: |
+          echo "=== Pre-install Cluster Status ==="
+          kubectl get nodes -o wide
+          kubectl get pods --all-namespaces
+          kubectl get storageclass
 
-        # Function to monitor cluster state
-        monitor_cluster() {
-          while true; do
-            echo "=== Cluster Status Check at $(date) ==="
-            # Only show non-running pods to reduce noise
-            NON_RUNNING_PODS=$(kubectl get pods --all-namespaces --field-selector=status.phase!=Running,status.phase!=Succeeded --no-headers 2>/dev/null | wc -l)
-            if [ "$NON_RUNNING_PODS" -gt 0 ]; then
-              echo "Non-running pods:"
-              kubectl get pods --all-namespaces --field-selector=status.phase!=Running,status.phase!=Succeeded
+      - name: Add Helm repositories and update
+        if: steps.list-changed.outputs.changed == 'true'
+        run: |
+          echo "=== Adding Helm repositories ==="
+          helm repo add ingress-nginx https://kubernetes.github.io/ingress-nginx
+          helm repo add vespa https://onyx-dot-app.github.io/vespa-helm-charts
+          helm repo add opensearch https://opensearch-project.github.io/helm-charts
+          helm repo add cloudnative-pg https://cloudnative-pg.github.io/charts
+          helm repo add ot-container-kit https://ot-container-kit.github.io/helm-charts
+          helm repo add minio https://charts.min.io/
+          helm repo add code-interpreter https://onyx-dot-app.github.io/code-interpreter/
+          helm repo update
+
+      - name: Install Redis operator
+        if: steps.list-changed.outputs.changed == 'true'
+        shell: bash
+        run: |
+          echo "=== Installing redis-operator CRDs ==="
+          helm upgrade --install redis-operator ot-container-kit/redis-operator \
+            --namespace redis-operator --create-namespace --wait --timeout 300s
+
+      - name: Pre-pull required images
+        if: steps.list-changed.outputs.changed == 'true'
+        run: |
+          echo "=== Pre-pulling required images to avoid timeout ==="
+          KIND_CLUSTER=$(kubectl config current-context | sed 's/kind-//')
+          echo "Kind cluster: $KIND_CLUSTER"
+
+          IMAGES=(
+            "ghcr.io/cloudnative-pg/cloudnative-pg:1.27.0"
+            "quay.io/opstree/redis:v7.0.15"
+            "docker.io/onyxdotapp/onyx-web-server:latest"
+          )
+
+          for image in "${IMAGES[@]}"; do
+            echo "Pre-pulling $image"
+            if docker pull "$image"; then
+              kind load docker-image "$image" --name "$KIND_CLUSTER" || echo "Failed to load $image into kind"
             else
-              echo "All pods running successfully"
+              echo "Failed to pull $image"
             fi
-            # Only show recent events if there are issues
-            RECENT_EVENTS=$(kubectl get events --sort-by=.lastTimestamp --all-namespaces --field-selector=type!=Normal 2>/dev/null | tail -5)
-            if [ -n "$RECENT_EVENTS" ]; then
-              echo "Recent warnings/errors:"
-              echo "$RECENT_EVENTS"
-            fi
-            sleep 60
           done
-        }
 
-        # Start monitoring in background
-        monitor_cluster &
-        MONITOR_PID=$!
+          echo "=== Images loaded into Kind cluster ==="
+          docker exec "$KIND_CLUSTER"-control-plane crictl images | grep -E "(cloudnative-pg|redis|onyx)" || echo "Some images may still be loading..."
 
-        # Set up cleanup
-        cleanup() {
-          echo "=== Cleaning up monitoring process ==="
-          kill $MONITOR_PID 2>/dev/null || true
+      - name: Validate chart dependencies
+        if: steps.list-changed.outputs.changed == 'true'
+        run: |
+          echo "=== Validating chart dependencies ==="
+          cd deployment/helm/charts/onyx
+          helm dependency update
+          helm lint .
+
+      - name: Run chart-testing (install) with enhanced monitoring
+        timeout-minutes: 25
+        if: steps.list-changed.outputs.changed == 'true'
+        run: |
+          echo "=== Starting chart installation with monitoring ==="
+
+          # Function to monitor cluster state
+          monitor_cluster() {
+            while true; do
+              echo "=== Cluster Status Check at $(date) ==="
+              # Only show non-running pods to reduce noise
+              NON_RUNNING_PODS=$(kubectl get pods --all-namespaces --field-selector=status.phase!=Running,status.phase!=Succeeded --no-headers 2>/dev/null | wc -l)
+              if [ "$NON_RUNNING_PODS" -gt 0 ]; then
+                echo "Non-running pods:"
+                kubectl get pods --all-namespaces --field-selector=status.phase!=Running,status.phase!=Succeeded
+              else
+                echo "All pods running successfully"
+              fi
+              # Only show recent events if there are issues
+              RECENT_EVENTS=$(kubectl get events --sort-by=.lastTimestamp --all-namespaces --field-selector=type!=Normal 2>/dev/null | tail -5)
+              if [ -n "$RECENT_EVENTS" ]; then
+                echo "Recent warnings/errors:"
+                echo "$RECENT_EVENTS"
+              fi
+              sleep 60
+            done
+          }
+
+          # Start monitoring in background
+          monitor_cluster &
+          MONITOR_PID=$!
+
+          # Set up cleanup
+          cleanup() {
+            echo "=== Cleaning up monitoring process ==="
+            kill $MONITOR_PID 2>/dev/null || true
+            echo "=== Final cluster state ==="
+            kubectl get pods --all-namespaces
+            kubectl get events --all-namespaces --sort-by=.lastTimestamp | tail -20
+          }
+
+          # Trap cleanup on exit
+          trap cleanup EXIT
+
+          # Run the actual installation with detailed logging
+          # Note that opensearch.enabled is true whereas others in this install
+          # are false. There is some work that needs to be done to get this
+          # entire step working in CI, enabling opensearch here is a small step
+          # in that direction. If this is causing issues, disabling it in this
+          # step should be ok in the short term.
+          echo "=== Starting ct install ==="
+          set +e
+          ct install --all \
+            --helm-extra-set-args="\
+              --set=nginx.enabled=false \
+              --set=minio.enabled=false \
+              --set=vespa.enabled=false \
+              --set=opensearch.enabled=true \
+              --set=auth.opensearch.enabled=true \
+              --set=slackbot.enabled=false \
+              --set=postgresql.enabled=true \
+              --set=postgresql.cluster.storage.storageClass=standard \
+              --set=redis.enabled=true \
+              --set=redis.storageSpec.volumeClaimTemplate.spec.storageClassName=standard \
+              --set=webserver.replicaCount=1 \
+              --set=api.replicaCount=0 \
+              --set=inferenceCapability.replicaCount=0 \
+              --set=indexCapability.replicaCount=0 \
+              --set=celery_beat.replicaCount=0 \
+              --set=celery_worker_heavy.replicaCount=0 \
+              --set=celery_worker_docfetching.replicaCount=0 \
+              --set=celery_worker_docprocessing.replicaCount=0 \
+              --set=celery_worker_light.replicaCount=0 \
+              --set=celery_worker_monitoring.replicaCount=0 \
+              --set=celery_worker_primary.replicaCount=0 \
+              --set=celery_worker_user_file_processing.replicaCount=0 \
+              --set=celery_worker_user_files_indexing.replicaCount=0" \
+            --helm-extra-args="--timeout 900s --debug" \
+            --debug --config ct.yaml
+          CT_EXIT=$?
+          set -e
+
+          if [[ $CT_EXIT -ne 0 ]]; then
+            echo "ct install failed with exit code $CT_EXIT"
+            exit $CT_EXIT
+          else
+            echo "=== Installation completed successfully ==="
+          fi
+
+          kubectl get pods --all-namespaces
+
+      - name: Post-install verification
+        if: steps.list-changed.outputs.changed == 'true'
+        run: |
+          echo "=== Post-install verification ==="
+          kubectl get pods --all-namespaces
+          kubectl get services --all-namespaces
+          # Only show issues if they exist
+          kubectl describe pods --all-namespaces | grep -A 5 -B 2 "Failed\|Error\|Warning" || echo "No pod issues found"
+
+      - name: Cleanup on failure
+        if: failure() && steps.list-changed.outputs.changed == 'true'
+        run: |
+          echo "=== Cleanup on failure ==="
           echo "=== Final cluster state ==="
           kubectl get pods --all-namespaces
-          kubectl get events --all-namespaces --sort-by=.lastTimestamp | tail -20
-        }
+          kubectl get events --all-namespaces --sort-by=.lastTimestamp | tail -10
 
-        # Trap cleanup on exit
-        trap cleanup EXIT
+          echo "=== Pod descriptions for debugging ==="
+          kubectl describe pods --all-namespaces | grep -A 10 -B 3 "Failed\|Error\|Warning\|Pending" || echo "No problematic pods found"
 
-        # Run the actual installation with detailed logging
-        echo "=== Starting ct install ==="
-        set +e
-        ct install --all \
-          --helm-extra-set-args="\
-            --set=nginx.enabled=false \
-            --set=minio.enabled=false \
-            --set=vespa.enabled=false \
-            --set=slackbot.enabled=false \
-            --set=postgresql.enabled=true \
-            --set=postgresql.nameOverride=cloudnative-pg \
-            --set=postgresql.cluster.storage.storageClass=standard \
-            --set=redis.enabled=true \
-            --set=redis.storageSpec.volumeClaimTemplate.spec.storageClassName=standard \
-            --set=webserver.replicaCount=1 \
-            --set=api.replicaCount=0 \
-            --set=inferenceCapability.replicaCount=0 \
-            --set=indexCapability.replicaCount=0 \
-            --set=celery_beat.replicaCount=0 \
-            --set=celery_worker_heavy.replicaCount=0 \
-            --set=celery_worker_docfetching.replicaCount=0 \
-            --set=celery_worker_docprocessing.replicaCount=0 \
-            --set=celery_worker_light.replicaCount=0 \
-            --set=celery_worker_monitoring.replicaCount=0 \
-            --set=celery_worker_primary.replicaCount=0 \
-            --set=celery_worker_user_file_processing.replicaCount=0 \
-            --set=celery_worker_user_files_indexing.replicaCount=0" \
-          --helm-extra-args="--timeout 900s --debug" \
-          --debug --config ct.yaml
-        CT_EXIT=$?
-        set -e
+          echo "=== Recent logs for debugging ==="
+          kubectl logs --all-namespaces --tail=50 | grep -i "error\|timeout\|failed\|pull" || echo "No error logs found"
 
-        if [[ $CT_EXIT -ne 0 ]]; then
-          echo "ct install failed with exit code $CT_EXIT"
-          exit $CT_EXIT
-        else
-          echo "=== Installation completed successfully ==="
-        fi
-
-        kubectl get pods --all-namespaces
-
-    - name: Post-install verification
-      if: steps.list-changed.outputs.changed == 'true'
-      run: |
-        echo "=== Post-install verification ==="
-        kubectl get pods --all-namespaces
-        kubectl get services --all-namespaces
-        # Only show issues if they exist
-        kubectl describe pods --all-namespaces | grep -A 5 -B 2 "Failed\|Error\|Warning" || echo "No pod issues found"
-
-    - name: Cleanup on failure
-      if: failure() && steps.list-changed.outputs.changed == 'true'
-      run: |
-        echo "=== Cleanup on failure ==="
-        echo "=== Final cluster state ==="
-        kubectl get pods --all-namespaces
-        kubectl get events --all-namespaces --sort-by=.lastTimestamp | tail -10
-
-        echo "=== Pod descriptions for debugging ==="
-        kubectl describe pods --all-namespaces | grep -A 10 -B 3 "Failed\|Error\|Warning\|Pending" || echo "No problematic pods found"
-
-        echo "=== Recent logs for debugging ==="
-        kubectl logs --all-namespaces --tail=50 | grep -i "error\|timeout\|failed\|pull" || echo "No error logs found"
-
-        echo "=== Helm releases ==="
-        helm list --all-namespaces
-      # the following would install only changed charts, but we only have one chart so
-      # don't worry about that for now
-      # run: ct install --target-branch ${{ github.event.repository.default_branch }}
+          echo "=== Helm releases ==="
+          helm list --all-namespaces
+        # the following would install only changed charts, but we only have one chart so
+        # don't worry about that for now
+        # run: ct install --target-branch ${{ github.event.repository.default_branch }}

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

@@ -9,6 +9,12 @@ on:
     branches:
       - main
       - "release/**"
+  push:
+    tags:
+      - "v*.*.*"
+
+permissions:
+  contents: read
 
 env:
   # Test Environment Variables
@@ -27,22 +33,31 @@ env:
   PERM_SYNC_SHAREPOINT_CERTIFICATE_PASSWORD: ${{ secrets.PERM_SYNC_SHAREPOINT_CERTIFICATE_PASSWORD }}
   PERM_SYNC_SHAREPOINT_DIRECTORY_ID: ${{ secrets.PERM_SYNC_SHAREPOINT_DIRECTORY_ID }}
   EXA_API_KEY: ${{ secrets.EXA_API_KEY }}
+  GITHUB_PERMISSION_SYNC_TEST_ACCESS_TOKEN: ${{ secrets.ONYX_GITHUB_PERMISSION_SYNC_TEST_ACCESS_TOKEN }}
+  GITHUB_PERMISSION_SYNC_TEST_ACCESS_TOKEN_CLASSIC: ${{ secrets.ONYX_GITHUB_PERMISSION_SYNC_TEST_ACCESS_TOKEN_CLASSIC }}
+  GITHUB_ADMIN_EMAIL: ${{ secrets.ONYX_GITHUB_ADMIN_EMAIL }}
+  GITHUB_TEST_USER_1_EMAIL: ${{ secrets.ONYX_GITHUB_TEST_USER_1_EMAIL }}
+  GITHUB_TEST_USER_2_EMAIL: ${{ secrets.ONYX_GITHUB_TEST_USER_2_EMAIL }}
 
 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 }}
+      editions: ${{ steps.set-editions.outputs.editions }}
     steps:
       - name: Checkout code
-        uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # ratchet:actions/checkout@v4
+        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=$(find backend/tests/integration/tests -mindepth 1 -maxdepth 1 -type d ! -name "__pycache__" -exec basename {} \; | sort)
+          tests_dirs=$(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
@@ -58,22 +73,54 @@ 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: [runs-on, runner=1cpu-linux-arm64, "run-id=${{ github.run_id }}-build-backend-image", "extras=ecr-cache"]
+    runs-on:
+      [
+        runs-on,
+        runner=1cpu-linux-arm64,
+        "run-id=${{ 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@08eba0b27e820071cde6df949e0beb9ba4906955 # ratchet:actions/checkout@v4
+        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@e468171a9de216ec08956ac3ada2f0791b6bd435 # ratchet:docker/setup-buildx-action@v3
+        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
+        uses: docker/login-action@c94ce9fb468520275223c153574b00df6fe4bcc9 # ratchet:docker/login-action@v3
         with:
           username: ${{ secrets.DOCKER_USERNAME }}
           password: ${{ secrets.DOCKER_TOKEN }}
@@ -85,26 +132,55 @@ jobs:
           file: ./backend/Dockerfile
           push: true
           tags: ${{ env.RUNS_ON_ECR_CACHE }}:integration-test-backend-test-${{ github.run_id }}
-          cache-from: type=registry,ref=${{ env.RUNS_ON_ECR_CACHE }}:integration-test-backend-cache
-          cache-to: type=registry,ref=${{ env.RUNS_ON_ECR_CACHE }}:integration-test-backend-cache,mode=max
+          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=${{ github.run_id }}-build-model-server-image", "extras=ecr-cache"]
+    runs-on:
+      [
+        runs-on,
+        runner=1cpu-linux-arm64,
+        "run-id=${{ 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@08eba0b27e820071cde6df949e0beb9ba4906955 # ratchet:actions/checkout@v4
+        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@e468171a9de216ec08956ac3ada2f0791b6bd435 # ratchet:docker/setup-buildx-action@v3
+        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
+        uses: docker/login-action@c94ce9fb468520275223c153574b00df6fe4bcc9 # ratchet:docker/login-action@v3
         with:
           username: ${{ secrets.DOCKER_USERNAME }}
           password: ${{ secrets.DOCKER_TOKEN }}
@@ -116,34 +192,80 @@ jobs:
           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=${{ env.RUNS_ON_ECR_CACHE }}:integration-test-model-server-cache
-          cache-to: type=registry,ref=${{ env.RUNS_ON_ECR_CACHE }}:integration-test-model-server-cache,mode=max
-
+          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=${{ github.run_id }}-build-integration-image", "extras=ecr-cache"]
+    runs-on:
+      [
+        runs-on,
+        runner=2cpu-linux-arm64,
+        "run-id=${{ 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@08eba0b27e820071cde6df949e0beb9ba4906955 # ratchet:actions/checkout@v4
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # ratchet:actions/checkout@v6
+        with:
+          persist-credentials: false
 
       - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@e468171a9de216ec08956ac3ada2f0791b6bd435 # ratchet:docker/setup-buildx-action@v3
+        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
+        uses: docker/login-action@c94ce9fb468520275223c153574b00df6fe4bcc9 # ratchet:docker/login-action@v3
         with:
           username: ${{ secrets.DOCKER_USERNAME }}
           password: ${{ secrets.DOCKER_TOKEN }}
 
+      - 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: Build and push integration test image with Docker Bake
         env:
-          REPOSITORY: ${{ env.RUNS_ON_ECR_CACHE }}
+          INTEGRATION_REPOSITORY: ${{ env.RUNS_ON_ECR_CACHE }}
           TAG: integration-test-${{ github.run_id }}
-        run: cd backend && docker buildx bake --push integration
+          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:
     needs:
@@ -156,43 +278,69 @@ 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
 
     strategy:
       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
       - name: Checkout code
-        uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # ratchet:actions/checkout@v4
+        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
+        uses: docker/login-action@c94ce9fb468520275223c153574b00df6fe4bcc9 # 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 }}
+          EDITION: ${{ matrix.edition }}
+        run: |
+          # Base config shared by both editions
+          cat <<EOF > deployment/docker_compose/.env
+          COMPOSE_PROFILES=s3-filestore
+          AUTH_TYPE=basic
+          POSTGRES_POOL_PRE_PING=true
+          POSTGRES_USE_NULL_POOL=true
+          REQUIRE_EMAIL_VERIFICATION=false
+          DISABLE_TELEMETRY=true
+          ONYX_BACKEND_IMAGE=${ECR_CACHE}:integration-test-backend-test-${RUN_ID}
+          ONYX_MODEL_SERVER_IMAGE=${ECR_CACHE}:integration-test-model-server-test-${RUN_ID}
+          INTEGRATION_TESTS_MODE=true
+          MCP_SERVER_ENABLED=true
+          AUTO_LLM_UPDATE_INTERVAL_SECONDS=10
+          EOF
+
+          # EE-only config
+          if [ "$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: |
           cd deployment/docker_compose
-          ENABLE_PAID_ENTERPRISE_EDITION_FEATURES=true \
-          AUTH_TYPE=basic \
-          POSTGRES_POOL_PRE_PING=true \
-          POSTGRES_USE_NULL_POOL=true \
-          REQUIRE_EMAIL_VERIFICATION=false \
-          DISABLE_TELEMETRY=true \
-          ONYX_BACKEND_IMAGE=${{ env.RUNS_ON_ECR_CACHE }}:integration-test-backend-test-${{ github.run_id }} \
-          ONYX_MODEL_SERVER_IMAGE=${{ env.RUNS_ON_ECR_CACHE }}:integration-test-model-server-test-${{ github.run_id }} \
-          INTEGRATION_TESTS_MODE=true \
-          CHECK_TTL_MANAGEMENT_TASK_FREQUENCY_IN_HOURS=0.001 \
           docker compose -f docker-compose.yml -f docker-compose.dev.yml up \
             relational_db \
             index \
@@ -205,39 +353,45 @@ jobs:
             -d
         id: start_docker
 
-      - name: Wait for service to be ready
+      - name: Wait for services to be ready
         run: |
           echo "Starting wait-for-service script..."
 
-          docker logs -f onyx-api_server-1 &
+          wait_for_service() {
+            local url=$1
+            local label=$2
+            local timeout=${3:-300}  # default 5 minutes
+            local start_time
+            start_time=$(date +%s)
 
-          start_time=$(date +%s)
-          timeout=300  # 5 minutes in seconds
+            while true; do
+              local current_time
+              current_time=$(date +%s)
+              local elapsed_time=$((current_time - start_time))
 
-          while true; do
-            current_time=$(date +%s)
-            elapsed_time=$((current_time - start_time))
+              if [ $elapsed_time -ge $timeout ]; then
+                echo "Timeout reached. ${label} did not become ready in $timeout seconds."
+                exit 1
+              fi
 
-            if [ $elapsed_time -ge $timeout ]; then
-              echo "Timeout reached. Service did not become ready in 5 minutes."
-              exit 1
-            fi
+              local response
+              response=$(curl -s -o /dev/null -w "%{http_code}" "$url" || echo "curl_error")
 
-            # Use curl with error handling to ignore specific exit code 56
-            response=$(curl -s -o /dev/null -w "%{http_code}" http://localhost:8080/health || echo "curl_error")
+              if [ "$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
 
-            if [ "$response" = "200" ]; then
-              echo "Service is ready!"
-              break
-            elif [ "$response" = "curl_error" ]; then
-              echo "Curl encountered an error, possibly exit code 56. Continuing to retry..."
-            else
-              echo "Service not ready yet (HTTP status $response). Retrying in 5 seconds..."
-            fi
+              sleep 5
+            done
+          }
 
-            sleep 5
-          done
-          echo "Finished waiting for service."
+          wait_for_service "http://localhost:8080/health" "API server"
+          echo "Finished waiting for services."
 
       - name: Start Mock Services
         run: |
@@ -245,14 +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 ${{ matrix.test-dir.path }}..."
             docker run --rm --network onyx_default \
               --name test-runner \
               -e POSTGRES_HOST=relational_db \
@@ -267,6 +421,7 @@ jobs:
               -e REDIS_HOST=cache \
               -e API_SERVER_HOST=api_server \
               -e OPENAI_API_KEY=${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} \
@@ -280,6 +435,11 @@ jobs:
               -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=${PERM_SYNC_SHAREPOINT_DIRECTORY_ID} \
+              -e GITHUB_PERMISSION_SYNC_TEST_ACCESS_TOKEN=${GITHUB_PERMISSION_SYNC_TEST_ACCESS_TOKEN} \
+              -e GITHUB_PERMISSION_SYNC_TEST_ACCESS_TOKEN_CLASSIC=${GITHUB_PERMISSION_SYNC_TEST_ACCESS_TOKEN_CLASSIC} \
+              -e GITHUB_ADMIN_EMAIL=${GITHUB_ADMIN_EMAIL} \
+              -e GITHUB_TEST_USER_1_EMAIL=${GITHUB_TEST_USER_1_EMAIL} \
+              -e GITHUB_TEST_USER_2_EMAIL=${GITHUB_TEST_USER_2_EMAIL} \
               -e TEST_WEB_HOSTNAME=test-runner \
               -e MOCK_CONNECTOR_SERVER_HOST=mock_connector_server \
               -e MOCK_CONNECTOR_SERVER_PORT=8001 \
@@ -302,43 +462,185 @@ jobs:
 
       - name: Upload logs
         if: always()
-        uses: actions/upload-artifact@330a01c490aca151604b8cf639adc76d48f6c5d4 # ratchet:actions/upload-artifact@v4
+        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
       # ------------------------------------------------------------
 
-
-  multitenant-tests:
-    needs:
+  no-vectordb-tests:
+    needs: [build-backend-image, build-integration-image]
+    runs-on:
       [
-        build-backend-image,
-        build-model-server-image,
-        build-integration-image,
+        runs-on,
+        runner=4cpu-linux-arm64,
+        "run-id=${{ github.run_id }}-no-vectordb-tests",
+        "extras=ecr-cache",
       ]
-    runs-on: [runs-on, runner=8cpu-linux-arm64, "run-id=${{ github.run_id }}-multitenant-tests", "extras=ecr-cache"]
+    timeout-minutes: 45
 
     steps:
       - uses: runs-on/action@cd2b598b0515d39d78c38a02d529db87d2196d1e # ratchet:runs-on/action@v2
       - name: Checkout code
-        uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # ratchet:actions/checkout@v4
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # ratchet:actions/checkout@v6
+        with:
+          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 }}
+
+      - 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: ${{ github.workspace }}/docker-compose-no-vectordb.log
+
+      - name: Stop Docker containers (no-vectordb)
+        if: always()
+        run: |
+          cd deployment/docker_compose
+          docker compose -f docker-compose.yml -f docker-compose.no-vectordb.yml -f docker-compose.dev.yml down -v
+
+  multitenant-tests:
+    needs:
+      [build-backend-image, build-model-server-image, build-integration-image]
+    runs-on:
+      [
+        runs-on,
+        runner=8cpu-linux-arm64,
+        "run-id=${{ github.run_id }}-multitenant-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: Start Docker containers for multi-tenant tests
+        env:
+          ECR_CACHE: ${{ env.RUNS_ON_ECR_CACHE }}
+          RUN_ID: ${{ github.run_id }}
         run: |
           cd deployment/docker_compose
           ENABLE_PAID_ENTERPRISE_EDITION_FEATURES=true \
+          LICENSE_ENFORCEMENT_ENABLED=false \
           MULTI_TENANT=true \
           AUTH_TYPE=cloud \
           REQUIRE_EMAIL_VERIFICATION=false \
           DISABLE_TELEMETRY=true \
-          ONYX_BACKEND_IMAGE=${{ env.RUNS_ON_ECR_CACHE }}:integration-test-backend-test-${{ github.run_id }} \
-          ONYX_MODEL_SERVER_IMAGE=${{ env.RUNS_ON_ECR_CACHE }}:integration-test-model-server-test-${{ github.run_id }} \
+          OPENAI_DEFAULT_API_KEY=${OPENAI_API_KEY} \
+          ONYX_BACKEND_IMAGE=${ECR_CACHE}:integration-test-backend-test-${RUN_ID} \
+          ONYX_MODEL_SERVER_IMAGE=${ECR_CACHE}:integration-test-model-server-test-${RUN_ID} \
           DEV_MODE=true \
           docker compose -f docker-compose.multitenant-dev.yml up \
             relational_db \
@@ -379,6 +681,9 @@ jobs:
           echo "Finished waiting for service."
 
       - name: Run Multi-Tenant Integration Tests
+        env:
+          ECR_CACHE: ${{ env.RUNS_ON_ECR_CACHE }}
+          RUN_ID: ${{ github.run_id }}
         run: |
           echo "Running multi-tenant integration tests..."
           docker run --rm --network onyx_default \
@@ -394,6 +699,7 @@ jobs:
             -e REDIS_HOST=cache \
             -e API_SERVER_HOST=api_server \
             -e OPENAI_API_KEY=${OPENAI_API_KEY} \
+            -e EXA_API_KEY=${EXA_API_KEY} \
             -e SLACK_BOT_TOKEN=${SLACK_BOT_TOKEN} \
             -e TEST_WEB_HOSTNAME=test-runner \
             -e AUTH_TYPE=cloud \
@@ -402,7 +708,7 @@ jobs:
             -e REQUIRE_EMAIL_VERIFICATION=false \
             -e DISABLE_TELEMETRY=true \
             -e DEV_MODE=true \
-            ${{ env.RUNS_ON_ECR_CACHE }}:integration-test-${{ github.run_id }} \
+            ${ECR_CACHE}:integration-test-${RUN_ID} \
             /app/tests/integration/multitenant_tests
 
       - name: Dump API server logs (multi-tenant)
@@ -419,7 +725,7 @@ jobs:
 
       - name: Upload logs (multi-tenant)
         if: always()
-        uses: actions/upload-artifact@330a01c490aca151604b8cf639adc76d48f6c5d4 # ratchet:actions/upload-artifact@v4
+        uses: actions/upload-artifact@b7c566a772e6b6bfb58ed0dc250532a479d7789f
         with:
           name: docker-all-logs-multitenant
           path: ${{ github.workspace }}/docker-compose-multitenant.log
@@ -433,16 +739,10 @@ jobs:
   required:
     # NOTE: Github-hosted runners have about 20s faster queue times and are preferred here.
     runs-on: ubuntu-slim
-    needs: [integration-tests, multitenant-tests]
+    timeout-minutes: 45
+    needs: [integration-tests, no-vectordb-tests, multitenant-tests]
     if: ${{ always() }}
     steps:
-      - uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # ratchet:actions/github-script@v8
-        with:
-          script: |
-            const needs = ${{ toJSON(needs) }};
-            const failed = Object.values(needs).some(n => n.result !== 'success');
-            if (failed) {
-              core.setFailed('One or more upstream jobs failed or were cancelled.');
-            } else {
-              core.notice('All required jobs succeeded.');
-            }
+      - name: Check job status
+        if: ${{ contains(needs.*.result, 'failure') || contains(needs.*.result, 'cancelled') || contains(needs.*.result, 'skipped') }}
+        run: exit 1

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

@@ -3,21 +3,35 @@ concurrency:
   group: Run-Jest-Tests-${{ github.workflow }}-${{ github.head_ref || github.event.workflow_run.head_branch || github.run_id }}
   cancel-in-progress: true
 
-on: push
+on:
+  merge_group:
+  pull_request:
+    branches:
+      - main
+      - "release/**"
+  push:
+    tags:
+      - "v*.*.*"
+
+permissions:
+  contents: read
 
 jobs:
   jest-tests:
     name: Jest Tests
     runs-on: ubuntu-latest
+    timeout-minutes: 45
     steps:
       - name: Checkout code
-        uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # ratchet:actions/checkout@v4
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # ratchet:actions/checkout@v6
+        with:
+          persist-credentials: false
 
       - name: Setup node
-        uses: actions/setup-node@2028fbc5c25fe9cf00d9f06a71cc4710d4507903 # ratchet:actions/setup-node@v4
+        uses: actions/setup-node@6044e13b5dc448c55e2357c09f80417699197238 # ratchet:actions/setup-node@v4
         with:
           node-version: 22
-          cache: 'npm'
+          cache: "npm"
           cache-dependency-path: ./web/package-lock.json
 
       - name: Install node dependencies
@@ -30,7 +44,7 @@ jobs:
 
       - name: Upload coverage reports
         if: always()
-        uses: actions/upload-artifact@330a01c490aca151604b8cf639adc76d48f6c5d4 # ratchet:actions/upload-artifact@v4
+        uses: actions/upload-artifact@b7c566a772e6b6bfb58ed0dc250532a479d7789f
         with:
           name: jest-coverage-${{ github.run_id }}
           path: ./web/coverage

.github/workflows/pr-labeler.yml

@@ -1,7 +1,7 @@
 name: PR Labeler
 
 on:
-  pull_request_target:
+  pull_request:
     branches:
       - main
     types:
@@ -12,11 +12,11 @@ on:
 
 permissions:
   contents: read
-  pull-requests: write
 
 jobs:
   validate_pr_title:
     runs-on: ubuntu-latest
+    timeout-minutes: 45
     steps:
       - name: Check PR title for Conventional Commits
         env:

.github/workflows/pr-linear-check.yml

@@ -7,9 +7,13 @@ on:
   pull_request:
     types: [opened, edited, reopened, synchronize]
 
+permissions:
+  contents: read
+
 jobs:
   linear-check:
     runs-on: ubuntu-latest
+    timeout-minutes: 45
     steps:
       - name: Check PR body for Linear link or override
         env:

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

@@ -1,319 +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]
-
-env:
-  # Test Environment Variables
-  OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
-  SLACK_BOT_TOKEN: ${{ secrets.SLACK_BOT_TOKEN }}
-  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
-    outputs:
-      test-dirs: ${{ steps.set-matrix.outputs.test-dirs }}
-    steps:
-      - name: Checkout code
-        uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # ratchet:actions/checkout@v4
-
-      - name: Discover test directories
-        id: set-matrix
-        run: |
-          # Find all leaf-level directories in both test directories
-          tests_dirs=$(find backend/tests/integration/tests -mindepth 1 -maxdepth 1 -type d ! -name "__pycache__" -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"]
-    steps:
-      - uses: runs-on/action@cd2b598b0515d39d78c38a02d529db87d2196d1e # ratchet:runs-on/action@v2
-      - name: Checkout code
-        uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # ratchet:actions/checkout@v4
-
-      - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@e468171a9de216ec08956ac3ada2f0791b6bd435 # 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=${{ env.RUNS_ON_ECR_CACHE }}:integration-test-backend-cache
-          cache-to: type=registry,ref=${{ env.RUNS_ON_ECR_CACHE }}:integration-test-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"]
-    steps:
-      - uses: runs-on/action@cd2b598b0515d39d78c38a02d529db87d2196d1e # ratchet:runs-on/action@v2
-      - name: Checkout code
-        uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # ratchet:actions/checkout@v4
-
-      - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@e468171a9de216ec08956ac3ada2f0791b6bd435 # 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=${{ env.RUNS_ON_ECR_CACHE }}:integration-test-model-server-cache
-          cache-to: type=registry,ref=${{ env.RUNS_ON_ECR_CACHE }}:integration-test-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"]
-    steps:
-      - uses: runs-on/action@cd2b598b0515d39d78c38a02d529db87d2196d1e # ratchet:runs-on/action@v2
-      - name: Checkout code
-        uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # ratchet:actions/checkout@v4
-
-      - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@e468171a9de216ec08956ac3ada2f0791b6bd435 # 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:
-          REPOSITORY: ${{ env.RUNS_ON_ECR_CACHE }}
-          TAG: integration-test-${{ github.run_id }}
-        run: cd backend && docker buildx bake --push 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
-
-    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@08eba0b27e820071cde6df949e0beb9ba4906955 # ratchet:actions/checkout@v4
-
-      # 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: ${{ secrets.DOCKER_TOKEN }}
-
-      # NOTE: Use pre-ping/null pool to reduce flakiness due to dropped connections
-      # NOTE: don't need web server for integration tests
-      - name: Start Docker containers
-        run: |
-          cd deployment/docker_compose
-          AUTH_TYPE=basic \
-          POSTGRES_POOL_PRE_PING=true \
-          POSTGRES_USE_NULL_POOL=true \
-          REQUIRE_EMAIL_VERIFICATION=false \
-          DISABLE_TELEMETRY=true \
-          ONYX_BACKEND_IMAGE=${{ env.RUNS_ON_ECR_CACHE }}:integration-test-backend-test-${{ github.run_id }} \
-          ONYX_MODEL_SERVER_IMAGE=${{ env.RUNS_ON_ECR_CACHE }}:integration-test-model-server-test-${{ github.run_id }} \
-          INTEGRATION_TESTS_MODE=true \
-          docker compose -f docker-compose.yml -f docker-compose.dev.yml up \
-            relational_db \
-            index \
-            cache \
-            minio \
-            api_server \
-            inference_model_server \
-            indexing_model_server \
-            background \
-            -d
-        id: start_docker
-
-      - name: Wait for service to be ready
-        run: |
-          echo "Starting wait-for-service script..."
-
-          docker logs -f onyx-api_server-1 &
-
-          start_time=$(date +%s)
-          timeout=300  # 5 minutes in seconds
-
-          while true; do
-            current_time=$(date +%s)
-            elapsed_time=$((current_time - start_time))
-
-            if [ $elapsed_time -ge $timeout ]; then
-              echo "Timeout reached. Service did not become ready in 5 minutes."
-              exit 1
-            fi
-
-            # Use curl with error handling to ignore specific exit code 56
-            response=$(curl -s -o /dev/null -w "%{http_code}" http://localhost:8080/health || echo "curl_error")
-
-            if [ "$response" = "200" ]; then
-              echo "Service is ready!"
-              break
-            elif [ "$response" = "curl_error" ]; then
-              echo "Curl encountered an error, possibly exit code 56. Continuing to retry..."
-            else
-              echo "Service not ready yet (HTTP status $response). Retrying in 5 seconds..."
-            fi
-
-            sleep 5
-          done
-          echo "Finished waiting for service."
-
-      - 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 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 > $GITHUB_WORKSPACE/docker-compose.log || true
-
-      - name: Upload logs
-        if: always()
-        uses: actions/upload-artifact@330a01c490aca151604b8cf639adc76d48f6c5d4 # ratchet:actions/upload-artifact@v4
-        with:
-          name: docker-all-logs-${{ 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
-    needs: [integration-tests-mit]
-    if: ${{ always() }}
-    steps:
-      - uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # ratchet:actions/github-script@v8
-        with:
-          script: |
-            const needs = ${{ toJSON(needs) }};
-            const failed = Object.values(needs).some(n => n.result !== 'success');
-            if (failed) {
-              core.setFailed('One or more upstream jobs failed or were cancelled.');
-            } else {
-              core.notice('All required jobs succeeded.');
-            }

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

@@ -3,7 +3,18 @@ concurrency:
   group: Run-Playwright-Tests-${{ github.workflow }}-${{ github.head_ref || github.event.workflow_run.head_branch || github.run_id }}
   cancel-in-progress: true
 
-on: push
+on:
+  merge_group:
+  pull_request:
+    branches:
+      - main
+      - "release/**"
+  push:
+    tags:
+      - "v*.*.*"
+
+permissions:
+  contents: read
 
 env:
   # Test Environment Variables
@@ -11,6 +22,9 @@ env:
   SLACK_BOT_TOKEN: ${{ secrets.SLACK_BOT_TOKEN }}
   GEN_AI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
   EXA_API_KEY: ${{ secrets.EXA_API_KEY }}
+  FIRECRAWL_API_KEY: ${{ secrets.FIRECRAWL_API_KEY }}
+  GOOGLE_PSE_API_KEY: ${{ secrets.GOOGLE_PSE_API_KEY }}
+  GOOGLE_PSE_SEARCH_ENGINE_ID: ${{ secrets.GOOGLE_PSE_SEARCH_ENGINE_ID }}
 
   # for federated slack tests
   SLACK_CLIENT_ID: ${{ secrets.SLACK_CLIENT_ID }}
@@ -24,6 +38,13 @@ env:
   MCP_OAUTH_USERNAME: ${{ vars.MCP_OAUTH_USERNAME }}
   MCP_OAUTH_PASSWORD: ${{ secrets.MCP_OAUTH_PASSWORD }}
 
+  # for MCP API Key tests
+  MCP_API_KEY: test-api-key-12345
+  MCP_API_KEY_TEST_PORT: 8005
+  MCP_API_KEY_TEST_URL: http://host.docker.internal:8005/mcp
+  MCP_API_KEY_SERVER_HOST: 0.0.0.0
+  MCP_API_KEY_SERVER_PUBLIC_HOST: host.docker.internal
+
   MOCK_LLM_RESPONSE: true
   MCP_TEST_SERVER_PORT: 8004
   MCP_TEST_SERVER_URL: http://host.docker.internal:8004/mcp
@@ -34,22 +55,48 @@ 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: [runs-on, runner=4cpu-linux-arm64, "run-id=${{ github.run_id }}-build-web-image", "extras=ecr-cache"]
+    runs-on:
+      [
+        runs-on,
+        runner=4cpu-linux-arm64,
+        "run-id=${{ github.run_id }}-build-web-image",
+        "extras=ecr-cache",
+      ]
+    timeout-minutes: 45
     steps:
       - uses: runs-on/action@cd2b598b0515d39d78c38a02d529db87d2196d1e # ratchet:runs-on/action@v2
 
       - name: Checkout code
-        uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # ratchet:actions/checkout@v4
+        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@e468171a9de216ec08956ac3ada2f0791b6bd435 # ratchet:docker/setup-buildx-action@v3
+        uses: docker/setup-buildx-action@8d2750c68a42422c14e847fe6c8ac0403b4cbd6f # ratchet:docker/setup-buildx-action@v3
 
       # 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 }}
@@ -62,25 +109,55 @@ jobs:
           platforms: linux/arm64
           tags: ${{ env.RUNS_ON_ECR_CACHE }}:playwright-test-web-${{ github.run_id }}
           push: true
-          cache-from: type=registry,ref=${{ env.RUNS_ON_ECR_CACHE }}:playwright-test-web-cache
-          cache-to: type=registry,ref=${{ env.RUNS_ON_ECR_CACHE }}:playwright-test-web-cache,mode=max
+          cache-from: |
+            type=registry,ref=${{ env.RUNS_ON_ECR_CACHE }}:web-cache-${{ github.event.pull_request.head.sha || github.sha }}
+            type=registry,ref=${{ env.RUNS_ON_ECR_CACHE }}:web-cache-${{ steps.format-branch.outputs.cache-suffix }}
+            type=registry,ref=${{ env.RUNS_ON_ECR_CACHE }}:web-cache
+            type=registry,ref=onyxdotapp/onyx-web-server:latest
+          cache-to: |
+            type=registry,ref=${{ env.RUNS_ON_ECR_CACHE }}:web-cache-${{ github.event.pull_request.head.sha || github.sha }},mode=max
+            type=registry,ref=${{ env.RUNS_ON_ECR_CACHE }}:web-cache-${{ steps.format-branch.outputs.cache-suffix }},mode=max
+            type=registry,ref=${{ env.RUNS_ON_ECR_CACHE }}:web-cache,mode=max
           no-cache: ${{ vars.DOCKER_NO_CACHE == 'true' }}
 
   build-backend-image:
-    runs-on: [runs-on, runner=1cpu-linux-arm64, "run-id=${{ github.run_id }}-build-backend-image", "extras=ecr-cache"]
+    runs-on:
+      [
+        runs-on,
+        runner=1cpu-linux-arm64,
+        "run-id=${{ 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@08eba0b27e820071cde6df949e0beb9ba4906955 # ratchet:actions/checkout@v4
+        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@e468171a9de216ec08956ac3ada2f0791b6bd435 # ratchet:docker/setup-buildx-action@v3
+        uses: docker/setup-buildx-action@8d2750c68a42422c14e847fe6c8ac0403b4cbd6f # ratchet:docker/setup-buildx-action@v3
 
       # 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 }}
@@ -93,25 +170,55 @@ jobs:
           platforms: linux/arm64
           tags: ${{ env.RUNS_ON_ECR_CACHE }}:playwright-test-backend-${{ github.run_id }}
           push: true
-          cache-from: type=registry,ref=${{ env.RUNS_ON_ECR_CACHE }}:playwright-test-backend-cache
-          cache-to: type=registry,ref=${{ env.RUNS_ON_ECR_CACHE }}:playwright-test-backend-cache,mode=max
+          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=${{ github.run_id }}-build-model-server-image", "extras=ecr-cache"]
+    runs-on:
+      [
+        runs-on,
+        runner=1cpu-linux-arm64,
+        "run-id=${{ 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@08eba0b27e820071cde6df949e0beb9ba4906955 # ratchet:actions/checkout@v4
+        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@e468171a9de216ec08956ac3ada2f0791b6bd435 # ratchet:docker/setup-buildx-action@v3
+        uses: docker/setup-buildx-action@8d2750c68a42422c14e847fe6c8ac0403b4cbd6f # ratchet:docker/setup-buildx-action@v3
 
       # 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 }}
@@ -124,31 +231,47 @@ jobs:
           platforms: linux/arm64
           tags: ${{ env.RUNS_ON_ECR_CACHE }}:playwright-test-model-server-${{ github.run_id }}
           push: true
-          cache-from: type=registry,ref=${{ env.RUNS_ON_ECR_CACHE }}:playwright-test-model-server-cache
-          cache-to: type=registry,ref=${{ env.RUNS_ON_ECR_CACHE }}:playwright-test-model-server-cache,mode=max
+          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
           no-cache: ${{ vars.DOCKER_NO_CACHE == 'true' }}
 
   playwright-tests:
     needs: [build-web-image, build-backend-image, build-model-server-image]
     name: Playwright Tests (${{ matrix.project }})
-    runs-on: [runs-on, runner=8cpu-linux-arm64, "run-id=${{ github.run_id }}-playwright-tests-${{ matrix.project }}", "extras=ecr-cache"]
+    permissions:
+      id-token: write # Required for OIDC-based AWS credential exchange (S3 access)
+      contents: read
+    runs-on:
+      - runs-on
+      - runner=8cpu-linux-arm64
+      - "run-id=${{ github.run_id }}-playwright-tests-${{ matrix.project }}"
+      - "extras=ecr-cache"
+      - volume=50gb
+    timeout-minutes: 45
     strategy:
       fail-fast: false
       matrix:
-        project: [admin, no-auth, exclusive]
+        project: [admin, exclusive]
     steps:
       - uses: runs-on/action@cd2b598b0515d39d78c38a02d529db87d2196d1e # ratchet:runs-on/action@v2
 
       - name: Checkout code
-        uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # ratchet:actions/checkout@v4
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # ratchet:actions/checkout@v6
         with:
-          fetch-depth: 0
+          persist-credentials: false
 
       - name: Setup node
-        uses: actions/setup-node@2028fbc5c25fe9cf00d9f06a71cc4710d4507903 # ratchet:actions/setup-node@v4
+        uses: actions/setup-node@6044e13b5dc448c55e2357c09f80417699197238 # ratchet:actions/setup-node@v4
         with:
           node-version: 22
-          cache: 'npm'
+          cache: "npm"
           cache-dependency-path: ./web/package-lock.json
 
       - name: Install node dependencies
@@ -168,24 +291,33 @@ jobs:
         run: npx playwright install --with-deps
 
       - name: Create .env file for Docker Compose
+        env:
+          OPENAI_API_KEY_VALUE: ${{ env.OPENAI_API_KEY }}
+          EXA_API_KEY_VALUE: ${{ env.EXA_API_KEY }}
+          ECR_CACHE: ${{ env.RUNS_ON_ECR_CACHE }}
+          RUN_ID: ${{ github.run_id }}
         run: |
           cat <<EOF > deployment/docker_compose/.env
+          COMPOSE_PROFILES=s3-filestore
           ENABLE_PAID_ENTERPRISE_EDITION_FEATURES=true
+          # TODO(Nik): https://linear.app/onyx-app/issue/ENG-1/update-test-infra-to-use-test-license
+          LICENSE_ENFORCEMENT_ENABLED=false
           AUTH_TYPE=basic
-          GEN_AI_API_KEY=${{ env.OPENAI_API_KEY }}
-          EXA_API_KEY=${{ env.EXA_API_KEY }}
+          INTEGRATION_TESTS_MODE=true
+          GEN_AI_API_KEY=${OPENAI_API_KEY_VALUE}
+          EXA_API_KEY=${EXA_API_KEY_VALUE}
           REQUIRE_EMAIL_VERIFICATION=false
           DISABLE_TELEMETRY=true
-          ONYX_BACKEND_IMAGE=${{ env.RUNS_ON_ECR_CACHE }}:playwright-test-backend-${{ github.run_id }}
-          ONYX_MODEL_SERVER_IMAGE=${{ env.RUNS_ON_ECR_CACHE }}:playwright-test-model-server-${{ github.run_id }}
-          ONYX_WEB_SERVER_IMAGE=${{ env.RUNS_ON_ECR_CACHE }}:playwright-test-web-${{ github.run_id }}
+          ONYX_BACKEND_IMAGE=${ECR_CACHE}:playwright-test-backend-${RUN_ID}
+          ONYX_MODEL_SERVER_IMAGE=${ECR_CACHE}:playwright-test-model-server-${RUN_ID}
+          ONYX_WEB_SERVER_IMAGE=${ECR_CACHE}:playwright-test-web-${RUN_ID}
           EOF
 
       # 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 }}
@@ -193,7 +325,7 @@ jobs:
       - name: Start Docker containers
         run: |
           cd deployment/docker_compose
-          docker compose -f docker-compose.yml -f docker-compose.dev.yml -f docker-compose.mcp-oauth-test.yml up -d
+          docker compose -f docker-compose.yml -f docker-compose.dev.yml -f docker-compose.mcp-oauth-test.yml -f docker-compose.mcp-api-key-test.yml up -d
         id: start_docker
 
       - name: Wait for service to be ready
@@ -253,78 +385,310 @@ jobs:
             sleep 3
           done
 
+      - name: Wait for MCP API Key mock server
+        run: |
+          echo "Waiting for MCP API Key mock server on port ${MCP_API_KEY_TEST_PORT:-8005}..."
+          start_time=$(date +%s)
+          timeout=120
+
+          while true; do
+            current_time=$(date +%s)
+            elapsed_time=$((current_time - start_time))
+
+            if [ $elapsed_time -ge $timeout ]; then
+              echo "Timeout reached. MCP API Key mock server did not become ready in ${timeout}s."
+              exit 1
+            fi
+
+            if curl -sf "http://localhost:${MCP_API_KEY_TEST_PORT:-8005}/healthz" > /dev/null; then
+              echo "MCP API Key mock server is ready!"
+              break
+            fi
+
+            sleep 3
+          done
+
+      - name: Wait for web server to be ready
+        run: |
+          echo "Waiting for web server on port 3000..."
+          start_time=$(date +%s)
+          timeout=120
+
+          while true; do
+            current_time=$(date +%s)
+            elapsed_time=$((current_time - start_time))
+
+            if [ $elapsed_time -ge $timeout ]; then
+              echo "Timeout reached. Web server did not become ready in ${timeout}s."
+              exit 1
+            fi
+
+            if curl -sf "http://localhost:3000/api/health" > /dev/null 2>&1 || \
+               curl -sf "http://localhost:3000/" > /dev/null 2>&1; then
+              echo "Web server is ready!"
+              break
+            fi
+
+            echo "Web server not ready yet. Retrying in 3 seconds..."
+            sleep 3
+          done
+
       - name: Run Playwright tests
         working-directory: ./web
+        env:
+          PROJECT: ${{ matrix.project }}
         run: |
-          # Create test-results directory to ensure it exists for artifact upload
-          mkdir -p test-results
-          npx playwright test --project ${{ matrix.project }}
+          npx playwright test --project ${PROJECT}
 
-      - uses: actions/upload-artifact@330a01c490aca151604b8cf639adc76d48f6c5d4 # ratchet:actions/upload-artifact@v4
+      - uses: actions/upload-artifact@b7c566a772e6b6bfb58ed0dc250532a479d7789f
         if: always()
         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()
+        env:
+          WORKSPACE: ${{ github.workspace }}
         run: |
           cd deployment/docker_compose
           docker compose logs > docker-compose.log
-          mv docker-compose.log ${{ github.workspace }}/docker-compose.log
+          mv docker-compose.log ${WORKSPACE}/docker-compose.log
 
       - name: Upload logs
         if: success() || failure()
-        uses: actions/upload-artifact@330a01c490aca151604b8cf639adc76d48f6c5d4 # ratchet:actions/upload-artifact@v4
+        uses: actions/upload-artifact@b7c566a772e6b6bfb58ed0dc250532a479d7789f
         with:
           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' &&
+      needs.playwright-tests.result != 'cancelled'
+    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/
 
-# 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.
+      - 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 -->"
 
-# chromatic-tests:
-#   name: Chromatic Tests
+          # Build the markdown table from all summary files
+          TABLE_HEADER="| Project | Changed | Added | Removed | Unchanged | Report |"
+          TABLE_DIVIDER="|---------|---------|-------|---------|-----------|--------|"
+          TABLE_ROWS=""
+          HAS_ANY_SUMMARY=false
 
-#   needs: playwright-tests
-#   runs-on:
-#     [
-#       runs-on,
-#       runner=32cpu-linux-x64,
-#       disk=large,
-#       "run-id=${{ github.run_id }}",
-#     ]
-#   steps:
-#     - name: Checkout code
-#       uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # ratchet:actions/checkout@v4
-#       with:
-#         fetch-depth: 0
+          for SUMMARY_DIR in summaries/screenshot-diff-summary-*/; do
+            SUMMARY_FILE="${SUMMARY_DIR}summary.json"
+            if [ ! -f "${SUMMARY_FILE}" ]; then
+              continue
+            fi
 
-#     - name: Setup node
-#       uses: actions/setup-node@2028fbc5c25fe9cf00d9f06a71cc4710d4507903 # ratchet:actions/setup-node@v4
-#       with:
-#         node-version: 22
+            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}")
 
-#     - name: Install node dependencies
-#       working-directory: ./web
-#       run: npm ci
+            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
 
-#     - name: Download Playwright test results
-#       uses: actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093 # ratchet:actions/download-artifact@v4
-#       with:
-#         name: test-results
-#         path: ./web/test-results
+            TABLE_ROWS="${TABLE_ROWS}| \`${PROJECT}\` | ${CHANGED} | ${ADDED} | ${REMOVED} | ${UNCHANGED} | ${REPORT_LINK} |\n"
+          done
 
-#     - name: Run Chromatic
-#       uses: chromaui/action@latest
-#       with:
-#         playwright: true
-#         projectToken: ${{ secrets.CHROMATIC_PROJECT_TOKEN }}
-#         workingDir: ./web
-#       env:
-#         CHROMATIC_ARCHIVE_LOCATION: ./test-results
+          if [ "${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
+    timeout-minutes: 45
+    needs: [playwright-tests]
+    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-python-checks.yml

@@ -9,6 +9,12 @@ on:
     branches:
       - main
       - 'release/**'
+  push:
+    tags:
+      - "v*.*.*"
+
+permissions:
+  contents: read
 
 jobs:
   mypy-check:
@@ -16,34 +22,40 @@ jobs:
     # Note: Mypy seems quite optimized for x64 compared to arm64.
     # Similarly, mypy is single-threaded and incremental, so 2cpu is sufficient.
     runs-on: [runs-on, runner=2cpu-linux-x64, "run-id=${{ github.run_id }}-mypy-check", "extras=s3-cache"]
+    timeout-minutes: 45
 
     steps:
       - uses: runs-on/action@cd2b598b0515d39d78c38a02d529db87d2196d1e # ratchet:runs-on/action@v2
       - name: Checkout code
-        uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # ratchet:actions/checkout@v4
-
-      # 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
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # ratchet:actions/checkout@v6
         with:
-          username: ${{ secrets.DOCKER_USERNAME }}
-          password: ${{ secrets.DOCKER_TOKEN }}
+          persist-credentials: false
 
-      - name: Prepare build
-        uses: ./.github/actions/prepare-build
+      - name: Setup Python and Install Dependencies
+        uses: ./.github/actions/setup-python-and-install-dependencies
         with:
-          docker-username: ${{ secrets.DOCKER_USERNAME }}
-          docker-password: ${{ secrets.DOCKER_TOKEN }}
+          requirements: |
+            backend/requirements/default.txt
+            backend/requirements/dev.txt
+            backend/requirements/model_server.txt
+            backend/requirements/ee.txt
+
+      - 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
 
       - name: Cache mypy cache
         if: ${{ vars.DISABLE_MYPY_CACHE != 'true' }}
         uses: runs-on/cache@50350ad4242587b6c8c2baa2e740b1bc11285ff4 # ratchet:runs-on/cache@v4
         with:
           path: backend/.mypy_cache
-          key: mypy-${{ runner.os }}-${{ hashFiles('**/*.py', '**/*.pyi', 'backend/pyproject.toml') }}
+          key: mypy-${{ runner.os }}-${{ github.base_ref || github.event.merge_group.base_ref || 'main' }}-${{ hashFiles('**/*.py', '**/*.pyi', 'backend/pyproject.toml') }}
           restore-keys: |
+            mypy-${{ runner.os }}-${{ github.base_ref || github.event.merge_group.base_ref || 'main' }}-
             mypy-${{ runner.os }}-
 
       - name: Run MyPy
@@ -53,11 +65,8 @@ jobs:
           TERM: xterm-256color
         run: mypy .
 
-      - name: Check import order with reorder-python-imports
-        working-directory: ./backend
-        run: |
-          find ./onyx -name "*.py" | xargs reorder-python-imports --py311-plus
-
-      - name: Check code formatting with Black
-        working-directory: ./backend
-        run: black --check .
+      - name: Run MyPy (tools/)
+        env:
+          MYPY_FORCE_COLOR: 1
+          TERM: xterm-256color
+        run: mypy tools/

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

@@ -7,10 +7,16 @@ on:
   merge_group:
   pull_request:
     branches: [main]
+  push:
+    tags:
+      - "v*.*.*"
   schedule:
     # This cron expression runs the job daily at 16:00 UTC (9am PT)
     - cron: "0 16 * * *"
 
+permissions:
+  contents: read
+
 env:
   # AWS
   AWS_ACCESS_KEY_ID_DAILY_CONNECTOR_TESTS: ${{ secrets.AWS_ACCESS_KEY_ID_DAILY_CONNECTOR_TESTS }}
@@ -59,7 +65,7 @@ env:
   ZENDESK_TOKEN: ${{ secrets.ZENDESK_TOKEN }}
 
   # Salesforce
-  SF_USERNAME: ${{ secrets.SF_USERNAME }}
+  SF_USERNAME: ${{ vars.SF_USERNAME }}
   SF_PASSWORD: ${{ secrets.SF_PASSWORD }}
   SF_SECURITY_TOKEN: ${{ secrets.SF_SECURITY_TOKEN }}
 
@@ -104,6 +110,9 @@ env:
   # Slack
   SLACK_BOT_TOKEN: ${{ secrets.SLACK_BOT_TOKEN }}
 
+  # Discord
+  DISCORD_CONNECTOR_BOT_TOKEN: ${{ secrets.DISCORD_CONNECTOR_BOT_TOKEN }}
+
   # Teams
   TEAMS_APPLICATION_ID: ${{ secrets.TEAMS_APPLICATION_ID }}
   TEAMS_DIRECTORY_ID: ${{ secrets.TEAMS_DIRECTORY_ID }}
@@ -123,18 +132,26 @@ jobs:
   connectors-check:
     # See https://runs-on.com/runners/linux/
     runs-on: [runs-on, runner=8cpu-linux-x64, "run-id=${{ github.run_id }}-connectors-check", "extras=s3-cache"]
+    timeout-minutes: 45
 
     env:
       PYTHONPATH: ./backend
+      DISABLE_TELEMETRY: "true"
 
     steps:
       - uses: runs-on/action@cd2b598b0515d39d78c38a02d529db87d2196d1e # ratchet:runs-on/action@v2
 
       - name: Checkout code
-        uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # ratchet:actions/checkout@v4
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # ratchet:actions/checkout@v6
+        with:
+          persist-credentials: false
 
       - name: Setup Python and Install Dependencies
         uses: ./.github/actions/setup-python-and-install-dependencies
+        with:
+          requirements: |
+            backend/requirements/default.txt
+            backend/requirements/dev.txt
 
       - name: Setup Playwright
         uses: ./.github/actions/setup-playwright
@@ -147,16 +164,20 @@ jobs:
             hubspot:
               - 'backend/onyx/connectors/hubspot/**'
               - 'backend/tests/daily/connectors/hubspot/**'
+              - 'uv.lock'
             salesforce:
               - 'backend/onyx/connectors/salesforce/**'
               - 'backend/tests/daily/connectors/salesforce/**'
+              - 'uv.lock'
             github:
               - 'backend/onyx/connectors/github/**'
               - 'backend/tests/daily/connectors/github/**'
+              - 'uv.lock'
             file_processing:
               - 'backend/onyx/file_processing/**'
+              - 'uv.lock'
 
-      - name: Run Tests (excluding HubSpot, Salesforce, and GitHub)
+      - name: Run Tests (excluding HubSpot, Salesforce, GitHub, and Coda)
         shell: script -q -e -c "bash --noprofile --norc -eo pipefail {0}"
         run: |
           py.test \
@@ -169,7 +190,8 @@ jobs:
             backend/tests/daily/connectors \
             --ignore backend/tests/daily/connectors/hubspot \
             --ignore backend/tests/daily/connectors/salesforce \
-            --ignore backend/tests/daily/connectors/github
+            --ignore backend/tests/daily/connectors/github \
+            --ignore backend/tests/daily/connectors/coda
 
       - name: Run HubSpot Connector Tests
         if: ${{ github.event_name == 'schedule' || steps.changes.outputs.hubspot == 'true' || steps.changes.outputs.file_processing == 'true' }}
@@ -214,8 +236,10 @@ jobs:
         if: failure() && github.event_name == 'schedule'
         env:
           SLACK_WEBHOOK: ${{ secrets.SLACK_WEBHOOK }}
+          REPO: ${{ github.repository }}
+          RUN_ID: ${{ github.run_id }}
         run: |
           curl -X POST \
             -H 'Content-type: application/json' \
-            --data '{"text":"Scheduled Connector Tests failed! Check the run at: https://github.com/${{ github.repository }}/actions/runs/${{ github.run_id }}"}' \
+            --data "{\"text\":\"Scheduled Connector Tests failed! Check the run at: https://github.com/${REPO}/actions/runs/${RUN_ID}\"}" \
             $SLACK_WEBHOOK

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

@@ -5,11 +5,9 @@ on:
     # This cron expression runs the job daily at 16:00 UTC (9am PT)
     - cron: "0 16 * * *"
   workflow_dispatch:
-    inputs:
-      branch:
-        description: 'Branch to run the workflow on'
-        required: false
-        default: 'main'
+
+permissions:
+  contents: read
 
 env:
   # Bedrock
@@ -28,115 +26,103 @@ env:
 jobs:
   model-check:
     # See https://runs-on.com/runners/linux/
-    runs-on: [runs-on,runner=8cpu-linux-x64,"run-id=${{ github.run_id }}-model-check"]
+    runs-on:
+      - runs-on
+      - runner=4cpu-linux-arm64
+      - "run-id=${{ github.run_id }}-model-check"
+      - "extras=ecr-cache"
+    timeout-minutes: 45
 
     env:
       PYTHONPATH: ./backend
 
     steps:
       - name: Checkout code
-        uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # ratchet:actions/checkout@v4
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # ratchet:actions/checkout@v6
+        with:
+          persist-credentials: false
+
+      - name: Setup Python and Install Dependencies
+        uses: ./.github/actions/setup-python-and-install-dependencies
+        with:
+          requirements: |
+            backend/requirements/default.txt
+            backend/requirements/dev.txt
+
+      - 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: Login to Docker Hub
-        uses: docker/login-action@5e57cd118135c172c3672efd75eb46360885c0ef # ratchet:docker/login-action@v3
+        uses: docker/login-action@c94ce9fb468520275223c153574b00df6fe4bcc9
         with:
           username: ${{ secrets.DOCKER_USERNAME }}
           password: ${{ secrets.DOCKER_TOKEN }}
 
-      # tag every docker image with "test" so that we can spin up the correct set
-      # of images during testing
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@8d2750c68a42422c14e847fe6c8ac0403b4cbd6f
 
-      # We don't need to build the Web Docker image since it's not yet used
-      # in the integration tests. We have a separate action to verify that it builds
-      # successfully.
-      - name: Pull Model Server Docker image
-        run: |
-          docker pull onyxdotapp/onyx-model-server:latest
-          docker tag onyxdotapp/onyx-model-server:latest onyxdotapp/onyx-model-server:test
-
-      - name: Set up Python
-        uses: actions/setup-python@e797f83bcb11b83ae66e0230d6156d7c80228e7c # ratchet:actions/setup-python@v6
+      - name: Build and load
+        uses: docker/bake-action@5be5f02ff8819ecd3092ea6b2e6261c31774f2b4 # ratchet:docker/bake-action@v6
+        env:
+          TAG: model-server-${{ github.run_id }}
         with:
-          python-version: "3.11"
-          cache: "pip"
-          cache-dependency-path: |
-            backend/requirements/default.txt
-            backend/requirements/dev.txt
-
-      - name: Install Dependencies
-        run: |
-          python -m pip install --upgrade pip
-          pip install --retries 5 --timeout 30 -r backend/requirements/default.txt
-          pip install --retries 5 --timeout 30 -r backend/requirements/dev.txt
+          load: true
+          targets: model-server
+          set: |
+            model-server.cache-from=type=registry,ref=${{ env.RUNS_ON_ECR_CACHE }}:model-server-cache-${{ github.event.pull_request.head.sha || github.sha }}
+            model-server.cache-from=type=registry,ref=${{ env.RUNS_ON_ECR_CACHE }}:model-server-cache-${{ steps.format-branch.outputs.cache-suffix }}
+            model-server.cache-from=type=registry,ref=${{ env.RUNS_ON_ECR_CACHE }}:model-server-cache
+            model-server.cache-from=type=registry,ref=onyxdotapp/onyx-model-server:latest
+            model-server.cache-to=type=registry,ref=${{ env.RUNS_ON_ECR_CACHE }}:model-server-cache-${{ github.event.pull_request.head.sha || github.sha }},mode=max
+            model-server.cache-to=type=registry,ref=${{ env.RUNS_ON_ECR_CACHE }}:model-server-cache-${{ steps.format-branch.outputs.cache-suffix }},mode=max
+            model-server.cache-to=type=registry,ref=${{ env.RUNS_ON_ECR_CACHE }}:model-server-cache,mode=max
 
       - name: Start Docker containers
+        id: start_docker
+        env:
+          IMAGE_TAG: model-server-${{ github.run_id }}
         run: |
           cd deployment/docker_compose
-          ENABLE_PAID_ENTERPRISE_EDITION_FEATURES=true \
-          AUTH_TYPE=basic \
-          REQUIRE_EMAIL_VERIFICATION=false \
-          DISABLE_TELEMETRY=true \
-          IMAGE_TAG=test \
-          docker compose -f docker-compose.model-server-test.yml up -d indexing_model_server
-        id: start_docker
-
-      - name: Wait for service to be ready
-        run: |
-          echo "Starting wait-for-service script..."
-
-          start_time=$(date +%s)
-          timeout=300  # 5 minutes in seconds
-
-          while true; do
-            current_time=$(date +%s)
-            elapsed_time=$((current_time - start_time))
-
-            if [ $elapsed_time -ge $timeout ]; then
-              echo "Timeout reached. Service did not become ready in 5 minutes."
-              exit 1
-            fi
-
-            # Use curl with error handling to ignore specific exit code 56
-            response=$(curl -s -o /dev/null -w "%{http_code}" http://localhost:9000/api/health || echo "curl_error")
-
-            if [ "$response" = "200" ]; then
-              echo "Service is ready!"
-              break
-            elif [ "$response" = "curl_error" ]; then
-              echo "Curl encountered an error, possibly exit code 56. Continuing to retry..."
-            else
-              echo "Service not ready yet (HTTP status $response). Retrying in 5 seconds..."
-            fi
-
-            sleep 5
-          done
-          echo "Finished waiting for service."
+          docker compose \
+            -f docker-compose.yml \
+            -f docker-compose.dev.yml \
+            up -d --wait \
+            inference_model_server
 
       - name: Run Tests
-        shell: script -q -e -c "bash --noprofile --norc -eo pipefail {0}"
         run: |
           py.test -o junit_family=xunit2 -xv --ff backend/tests/daily/llm
           py.test -o junit_family=xunit2 -xv --ff backend/tests/daily/embedding
 
       - name: Alert on Failure
         if: failure() && github.event_name == 'schedule'
-        env:
-          SLACK_WEBHOOK: ${{ secrets.SLACK_WEBHOOK }}
-        run: |
-          curl -X POST \
-            -H 'Content-type: application/json' \
-            --data '{"text":"Scheduled Model Tests failed! Check the run at: https://github.com/${{ github.repository }}/actions/runs/${{ github.run_id }}"}' \
-            $SLACK_WEBHOOK
+        uses: ./.github/actions/slack-notify
+        with:
+          webhook-url: ${{ secrets.SLACK_WEBHOOK }}
+          failed-jobs: model-check
+          title: "🚨 Scheduled Model Tests failed!"
+          ref-name: ${{ github.ref_name }}
 
       - name: Dump all-container logs (optional)
         if: always()
         run: |
           cd deployment/docker_compose
-          docker compose -f docker-compose.model-server-test.yml logs --no-color > $GITHUB_WORKSPACE/docker-compose.log || true
+          docker compose logs --no-color > $GITHUB_WORKSPACE/docker-compose.log || true
 
       - name: Upload logs
         if: always()
-        uses: actions/upload-artifact@330a01c490aca151604b8cf639adc76d48f6c5d4 # ratchet:actions/upload-artifact@v4
+        uses: actions/upload-artifact@b7c566a772e6b6bfb58ed0dc250532a479d7789f
         with:
           name: docker-all-logs
           path: ${{ github.workspace }}/docker-compose.log

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

@@ -9,28 +9,43 @@ on:
     branches:
       - main
       - 'release/**'
+  push:
+    tags:
+      - "v*.*.*"
+
+permissions:
+  contents: read
 
 jobs:
   backend-check:
     # See https://runs-on.com/runners/linux/
     runs-on: [runs-on, runner=2cpu-linux-arm64, "run-id=${{ github.run_id }}-backend-check"]
+    timeout-minutes: 45
 
 
     env:
       PYTHONPATH: ./backend
       REDIS_CLOUD_PYTEST_PASSWORD: ${{ secrets.REDIS_CLOUD_PYTEST_PASSWORD }}
-      SF_USERNAME: ${{ secrets.SF_USERNAME }}
-      SF_PASSWORD: ${{ secrets.SF_PASSWORD }}
-      SF_SECURITY_TOKEN: ${{ secrets.SF_SECURITY_TOKEN }}
+      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
 
     - name: Checkout code
-      uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # ratchet:actions/checkout@v4
+      uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # ratchet:actions/checkout@v6
+      with:
+        persist-credentials: false
 
     - name: Setup Python and Install Dependencies
       uses: ./.github/actions/setup-python-and-install-dependencies
+      with:
+        requirements: |
+          backend/requirements/default.txt
+          backend/requirements/dev.txt
+          backend/requirements/model_server.txt
+          backend/requirements/ee.txt
 
     - name: Run Tests
       shell: script -q -e -c "bash --noprofile --norc -eo pipefail {0}"

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

@@ -6,21 +6,44 @@ concurrency:
 on:
   merge_group:
   pull_request: null
+  push:
+    branches:
+      - main
+    tags:
+      - "v*.*.*"
+
+permissions:
+  contents: read
 
 jobs:
   quality-checks:
-    # See https://runs-on.com/runners/linux/
-    runs-on: [runs-on, runner=1cpu-linux-arm64, "run-id=${{ github.run_id }}-quality-checks"]
+    runs-on: ubuntu-latest
+    timeout-minutes: 45
     steps:
-      - uses: runs-on/action@cd2b598b0515d39d78c38a02d529db87d2196d1e # ratchet:runs-on/action@v2
-      - uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # ratchet:actions/checkout@v4
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # ratchet:actions/checkout@v6
         with:
           fetch-depth: 0
-      - uses: actions/setup-python@e797f83bcb11b83ae66e0230d6156d7c80228e7c # ratchet:actions/setup-python@v6
+          persist-credentials: false
+      - 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
-      - uses: pre-commit/action@2c7b3805fd2a0fd8c1884dcaebf91fc102a13ecd # ratchet:pre-commit/action@v3.0.1
+      - name: Setup node
+        uses: actions/setup-node@6044e13b5dc448c55e2357c09f80417699197238 # ratchet:actions/setup-node@v6
+        with: # zizmor: ignore[cache-poisoning]
+          node-version: 22
+          cache: "npm"
+          cache-dependency-path: ./web/package-lock.json
+      - name: Install node dependencies
+        working-directory: ./web
+        run: npm ci
+      - uses: j178/prek-action@9d6a3097e0c1865ecce00cfb89fe80f2ee91b547 # ratchet:j178/prek-action@v1
         with:
-          extra_args: ${{ github.event_name == 'pull_request' && format('--from-ref {0} --to-ref {1}', github.event.pull_request.base.sha, github.event.pull_request.head.sha) || '' }}
+          prek-version: '0.2.21'
+          extra-args: ${{ github.event_name == 'pull_request' && format('--from-ref {0} --to-ref {1}', github.event.pull_request.base.sha, github.event.pull_request.head.sha) || github.event_name == 'merge_group' && format('--from-ref {0} --to-ref {1}', github.event.merge_group.base_sha, github.event.merge_group.head_sha) || github.ref_name == 'main' && '--all-files' || '' }}
+      - name: Check Actions
+        uses: giner/check-actions@28d366c7cbbe235f9624a88aa31a628167eee28c # ratchet:giner/check-actions@v1.0.1
+        with:
+          check_permissions: false
+          check_versions: false

.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/release-devtools.yml

@@ -0,0 +1,41 @@
+name: Release Devtools
+
+on:
+  push:
+    tags:
+      - "ods/v*.*.*"
+
+jobs:
+  pypi:
+    runs-on: ubuntu-latest
+    environment:
+      name: release-devtools
+    permissions:
+      id-token: write
+    timeout-minutes: 10
+    strategy:
+      matrix:
+        os-arch:
+          - { goos: "linux", goarch: "amd64" }
+          - { goos: "linux", goarch: "arm64" }
+          - { goos: "windows", goarch: "amd64" }
+          - { goos: "windows", goarch: "arm64" }
+          - { goos: "darwin", goarch: "amd64" }
+          - { goos: "darwin", goarch: "arm64" }
+          - { goos: "", goarch: "" }
+    steps:
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # ratchet:actions/checkout@v6
+        with:
+          persist-credentials: false
+          fetch-depth: 0
+      - uses: astral-sh/setup-uv@61cb8a9741eeb8a550a1b8544337180c0fc8476b # ratchet:astral-sh/setup-uv@v7
+        with:
+          enable-cache: false
+          version: "0.9.9"
+      - run: |
+          GOOS="${{ matrix.os-arch.goos }}" \
+          GOARCH="${{ matrix.os-arch.goarch }}" \
+          uv build --wheel
+        working-directory: tools/ods
+      - run: uv publish
+        working-directory: tools/ods

.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

.github/workflows/sync_foss.yml

@@ -9,13 +9,15 @@ on:
 jobs:
   sync-foss:
     runs-on: ubuntu-latest
+    timeout-minutes: 45
     permissions:
       contents: read
     steps:
       - name: Checkout main Onyx repo
-        uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # ratchet:actions/checkout@v4
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # ratchet:actions/checkout@v6
         with:
           fetch-depth: 0
+          persist-credentials: false
 
       - name: Install git-filter-repo
         run: |

.github/workflows/tag-nightly.yml

@@ -3,30 +3,30 @@ name: Nightly Tag Push
 on:
   schedule:
     - cron: "0 10 * * *" # Runs every day at 2 AM PST / 3 AM PDT / 10 AM UTC
+  workflow_dispatch:
 
 permissions:
   contents: write # Allows pushing tags to the repository
 
 jobs:
   create-and-push-tag:
-    runs-on: [runs-on, runner=2cpu-linux-x64, "run-id=${{ github.run_id }}-create-and-push-tag"]
+    runs-on: ubuntu-slim
+    timeout-minutes: 45
 
     steps:
       # actions using GITHUB_TOKEN cannot trigger another workflow, but we do want this to trigger docker pushes
       # see https://github.com/orgs/community/discussions/27028#discussioncomment-3254367 for the workaround we
       # implement here which needs an actual user's deploy key
-
-      # Additional NOTE: even though this is named "rkuo", the actual key is tied to the onyx repo
-      # and not rkuo's personal account. It is fine to leave this key as is!
       - name: Checkout code
-        uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # ratchet:actions/checkout@v4
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # ratchet:actions/checkout@v6
         with:
-          ssh-key: "${{ secrets.RKUO_DEPLOY_KEY }}"
+          ssh-key: "${{ secrets.DEPLOY_KEY }}"
+          persist-credentials: true
 
       - name: Set up Git user
         run: |
-          git config user.name "Richard Kuo [bot]"
-          git config user.email "rkuo[bot]@onyx.app"
+          git config user.name "Onyx Bot [bot]"
+          git config user.email "onyx-bot[bot]@onyx.app"
 
       - name: Check for existing nightly tag
         id: check_tag
@@ -54,3 +54,12 @@ jobs:
         run: |
           TAG_NAME="nightly-latest-$(date +'%Y%m%d')"
           git push origin $TAG_NAME
+
+      - name: Send Slack notification
+        if: failure()
+        uses: ./.github/actions/slack-notify
+        with:
+          webhook-url: ${{ secrets.MONITOR_DEPLOYMENTS_WEBHOOK }}
+          title: "🚨 Nightly Tag Push Failed"
+          ref-name: ${{ github.ref_name }}
+          failed-jobs: "create-and-push-tag"

.github/workflows/zizmor.yml

@@ -0,0 +1,41 @@
+name: Run Zizmor
+
+on:
+  push:
+    branches: ["main"]
+  pull_request:
+    branches: ["**"]
+    paths:
+      - ".github/**"
+
+permissions: {}
+
+jobs:
+  zizmor:
+    name: zizmor
+    runs-on: ubuntu-slim
+    timeout-minutes: 45
+    permissions:
+      security-events: write # needed for SARIF uploads
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # ratchet:actions/checkout@v6.0.2
+        with:
+          persist-credentials: false
+
+      - name: Install the latest version of uv
+        uses: astral-sh/setup-uv@61cb8a9741eeb8a550a1b8544337180c0fc8476b # ratchet:astral-sh/setup-uv@v7
+        with:
+          enable-cache: false
+          version: "0.9.9"
+
+      - name: Run zizmor
+        run: uv run --no-sync --with zizmor zizmor --format=sarif . > results.sarif
+        env:
+          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Upload SARIF file
+        uses: github/codeql-action/upload-sarif@ba454b8ab46733eb6145342877cd148270bb77ab # ratchet:github/codeql-action/upload-sarif@codeql-bundle-v2.23.5
+        with:
+          sarif_file: results.sarif
+          category: zizmor

.gitignore

@@ -1,6 +1,13 @@
 # editors
-.vscode
+.vscode/*
+!/.vscode/env_template.txt
+!/.vscode/env.web_template.txt
+!/.vscode/launch.json
+!/.vscode/tasks.template.jsonc
 .zed
+.cursor
+!/.cursor/mcp.json
+!/.cursor/skills/
 
 # macos
 .DS_store
@@ -20,6 +27,7 @@ backend/tests/regression/search_quality/*.json
 backend/onyx/evals/data/
 backend/onyx/evals/one_off/*.json
 *.log
+*.csv
 
 # secret files
 .env
@@ -28,14 +36,12 @@ settings.json
 
 # others
 /deployment/data/nginx/app.conf
+/deployment/data/nginx/mcp.conf.inc
+/deployment/data/nginx/mcp_upstream.conf.inc
 *.sw?
 /backend/tests/regression/answer_quality/search_test_config.yaml
 *.egg-info
 
-# Claude
-AGENTS.md
-CLAUDE.md
-
 # Local .terraform directories
 **/.terraform/*
 
@@ -46,5 +52,10 @@ CLAUDE.md
 # Local .terraform.lock.hcl file
 .terraform.lock.hcl
 
+node_modules
+
 # MCP configs
 .playwright-mcp
+
+# plans
+plans/

.mcp.json.template

@@ -1,8 +0,0 @@
-{
-  "mcpServers": {
-    "onyx-mcp": {
-      "type": "http",
-      "url": "http://localhost:8000/mcp"
-    }
-  }
-}

.pre-commit-config.yaml

@@ -1,61 +1,149 @@
+default_install_hook_types:
+  - pre-commit
+  - post-checkout
+  - post-merge
+  - post-rewrite
 repos:
-  - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v4.6.0
+  - repo: https://github.com/astral-sh/uv-pre-commit
+    # From: https://github.com/astral-sh/uv-pre-commit/pull/53/commits/d30b4298e4fb63ce8609e29acdbcf4c9018a483c
+    rev: d30b4298e4fb63ce8609e29acdbcf4c9018a483c
     hooks:
-      - id: check-yaml
-        files: ^.github/
+      - id: uv-sync
+        args: ["--locked", "--all-extras"]
+      - id: uv-lock
+      - id: uv-export
+        name: uv-export default.txt
+        args:
+          [
+            "--no-emit-project",
+            "--no-default-groups",
+            "--no-hashes",
+            "--extra",
+            "backend",
+            "-o",
+            "backend/requirements/default.txt",
+          ]
+        files: ^(pyproject\.toml|uv\.lock|backend/requirements/.*\.txt)$
+      - id: uv-export
+        name: uv-export dev.txt
+        args:
+          [
+            "--no-emit-project",
+            "--no-default-groups",
+            "--no-hashes",
+            "--extra",
+            "dev",
+            "-o",
+            "backend/requirements/dev.txt",
+          ]
+        files: ^(pyproject\.toml|uv\.lock|backend/requirements/.*\.txt)$
+      - id: uv-export
+        name: uv-export ee.txt
+        args:
+          [
+            "--no-emit-project",
+            "--no-default-groups",
+            "--no-hashes",
+            "--extra",
+            "ee",
+            "-o",
+            "backend/requirements/ee.txt",
+          ]
+        files: ^(pyproject\.toml|uv\.lock|backend/requirements/.*\.txt)$
+      - id: uv-export
+        name: uv-export model_server.txt
+        args:
+          [
+            "--no-emit-project",
+            "--no-default-groups",
+            "--no-hashes",
+            "--extra",
+            "model_server",
+            "-o",
+            "backend/requirements/model_server.txt",
+          ]
+        files: ^(pyproject\.toml|uv\.lock|backend/requirements/.*\.txt)$
+      - id: uv-run
+        name: Check lazy imports
+        args: ["--active", "--with=onyx-devtools", "ods", "check-lazy-imports"]
+        pass_filenames: true
+        files: ^backend/(?!\.venv/|scripts/).*\.py$
+      # NOTE: This takes ~6s on a single, large module which is prohibitively slow.
+      # - id: uv-run
+      #   name: mypy
+      #   args: ["--all-extras", "mypy"]
+      #   pass_filenames: true
+      #   files: ^backend/.*\.py$
+
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: 3e8a8703264a2f4a69428a0aa4dcb512790b2c8c # frozen: v6.0.0
+    hooks:
+      - id: check-added-large-files
+        name: Check for added large files
+        args: ["--maxkb=1500"]
 
   - repo: https://github.com/rhysd/actionlint
-    rev: v1.7.8
+    rev: a443f344ff32813837fa49f7aa6cbc478d770e62 # frozen: v1.7.9
     hooks:
       - id: actionlint
 
   - repo: https://github.com/psf/black
-    rev: 25.1.0
+    rev: 8a737e727ac5ab2f1d4cf5876720ed276dc8dc4b # frozen: 25.1.0
     hooks:
-    - id: black
-      language_version: python3.11
+      - id: black
+        language_version: python3.11
 
   # this is a fork which keeps compatibility with black
   - repo: https://github.com/wimglenn/reorder-python-imports-black
-    rev: v3.14.0
+    rev: f55cd27f90f0cf0ee775002c2383ce1c7820013d # frozen: v3.14.0
     hooks:
-    - id: reorder-python-imports
-      args: ['--py311-plus', '--application-directories=backend/']
-      # need to ignore alembic files, since reorder-python-imports gets confused
-      # and thinks that alembic is a local package since there is a folder
-      # in the backend directory called `alembic`
-      exclude: ^backend/alembic/
+      - id: reorder-python-imports
+        args: ["--py311-plus", "--application-directories=backend/"]
+        # need to ignore alembic files, since reorder-python-imports gets confused
+        # and thinks that alembic is a local package since there is a folder
+        # in the backend directory called `alembic`
+        exclude: ^backend/alembic/
 
   # These settings will remove unused imports with side effects
   # Note: The repo currently does not and should not have imports with side effects
   - repo: https://github.com/PyCQA/autoflake
-    rev: v2.3.1
+    rev: 0544741e2b4a22b472d9d93e37d4ea9153820bb1 # frozen: v2.3.1
     hooks:
       - id: autoflake
-        args: [ '--remove-all-unused-imports', '--remove-unused-variables', '--in-place' , '--recursive']
+        args:
+          [
+            "--remove-all-unused-imports",
+            "--remove-unused-variables",
+            "--in-place",
+            "--recursive",
+          ]
+
+  - repo: https://github.com/golangci/golangci-lint
+    rev: 9f61b0f53f80672872fced07b6874397c3ed197b # frozen: v2.7.2
+    hooks:
+      - id: golangci-lint
+        entry: bash -c "find tools/ -name go.mod -print0 | xargs -0 -I{} bash -c 'cd \"$(dirname {})\" && golangci-lint run ./...'"
 
   - repo: https://github.com/astral-sh/ruff-pre-commit
     # Ruff version.
-    rev: v0.11.4
+    rev: 971923581912ef60a6b70dbf0c3e9a39563c9d47 # frozen: v0.11.4
     hooks:
       - id: ruff
 
   - repo: https://github.com/pre-commit/mirrors-prettier
-    rev: v3.1.0
+    rev: ffb6a759a979008c0e6dff86e39f4745a2d9eac4 # frozen: v3.1.0
     hooks:
-    - id: prettier
-      types_or: [html, css, javascript, ts, tsx]
-      language_version: system
+      - id: prettier
+        types_or: [html, css, javascript, ts, tsx]
+        language_version: system
 
   - repo: https://github.com/sirwart/ripsecrets
-    rev: v0.1.11
+    rev: 7d94620933e79b8acaa0cd9e60e9864b07673d86 # frozen: v0.1.11
     hooks:
       - id: ripsecrets
         args:
-        - --additional-pattern
-        - ^sk-[A-Za-z0-9_\-]{20,}$
-
+          - --additional-pattern
+          - ^sk-[A-Za-z0-9_\-]{20,}$
 
   - repo: local
     hooks:
@@ -66,36 +154,29 @@ repos:
         pass_filenames: false
         files: \.tf$
 
-      - id: check-lazy-imports
-        name: Check lazy imports
-        entry: python3 backend/scripts/check_lazy_imports.py
+      - id: npm-install
+        name: npm install
+        description: "Automatically run 'npm install' after a checkout, pull or rebase"
         language: system
-        files: ^backend/(?!\.venv/).*\.py$
+        entry: bash -c 'cd web && npm install --no-save'
+        pass_filenames: false
+        files: ^web/package(-lock)?\.json$
+        stages: [post-checkout, post-merge, post-rewrite]
+      - id: npm-install-check
+        name: npm install --package-lock-only
+        description: "Check the 'web/package-lock.json' is updated"
+        language: system
+        entry: bash -c 'cd web && npm install --package-lock-only'
+        pass_filenames: false
+        files: ^web/package(-lock)?\.json$
 
-  # We would like to have a mypy pre-commit hook, but due to the fact that
-  # pre-commit runs in it's own isolated environment, we would need to install
-  # and keep in sync all dependencies so mypy has access to the appropriate type
-  # stubs. This does not seem worth it at the moment, so for now we will stick to
-  # having mypy run via Github Actions / manually by contributors
-  # - repo: https://github.com/pre-commit/mirrors-mypy
-  #   rev: v1.1.1
-  #   hooks:
-  #     - id: mypy
-  #       exclude: ^tests/
-  #       # below are needed for type stubs since pre-commit runs in it's own
-  #       # isolated environment. Unfortunately, this needs to be kept in sync
-  #       # with requirements/dev.txt + requirements/default.txt
-  #       additional_dependencies: [
-  #         alembic==1.10.4,
-  #         types-beautifulsoup4==4.12.0.3,
-  #         types-html5lib==1.1.11.13,
-  #         types-oauthlib==3.2.0.9,
-  #         types-psycopg2==2.9.21.10,
-  #         types-python-dateutil==2.8.19.13,
-  #         types-regex==2023.3.23.1,
-  #         types-requests==2.28.11.17,
-  #         types-retry==0.9.9.3,
-  #         types-urllib3==1.26.25.11
-  #       ]
-  #       # TODO: add back once errors are addressed
-  #       # args: [--strict]
+      # Uses tsgo (TypeScript's native Go compiler) for ~10x faster type checking.
+      # This is a preview package - if it breaks:
+      #   1. Try updating: cd web && npm update @typescript/native-preview
+      #   2. Or fallback to tsc: replace 'tsgo' with 'tsc' below
+      - id: typescript-check
+        name: TypeScript type check
+        entry: bash -c 'cd web && npx tsgo --noEmit --project tsconfig.types.json'
+        language: system
+        pass_filenames: false
+        files: ^web/.*\.(ts|tsx)$

.vscode/env.web_template.txt

@@ -0,0 +1,16 @@
+# Copy this file to .env.web in the .vscode folder.
+# Fill in the <REPLACE THIS> values as needed
+# Web Server specific environment variables
+# Minimal set needed for Next.js dev server
+
+# Auth
+AUTH_TYPE=basic
+DEV_MODE=true
+
+# Enable the full set of Danswer Enterprise Edition features.
+# NOTE: DO NOT ENABLE THIS UNLESS YOU HAVE A PAID ENTERPRISE LICENSE (or if you
+# are using this for local testing/development).
+ENABLE_PAID_ENTERPRISE_EDITION_FEATURES=false
+
+# Enable Onyx Craft
+ENABLE_CRAFT=true

.vscode/env_template.txt

@@ -1,46 +1,40 @@
-# Copy this file to .env in the .vscode folder
-# Fill in the <REPLACE THIS> values as needed, it is recommended to set the GEN_AI_API_KEY value to avoid having to set up an LLM in the UI
-# Also check out onyx/backend/scripts/restart_containers.sh for a script to restart the containers which Onyx relies on outside of VSCode/Cursor processes
+# Copy this file to .env in the .vscode folder.
+# Fill in the <REPLACE THIS> values as needed; it is recommended to set the
+# GEN_AI_API_KEY value to avoid having to set up an LLM in the UI.
+# Also check out onyx/backend/scripts/restart_containers.sh for a script to
+# restart the containers which Onyx relies on outside of VSCode/Cursor
+# processes.
 
-# For local dev, often user Authentication is not needed
-AUTH_TYPE=disabled
 
-# Skip warm up for dev
-SKIP_WARM_UP=True
+AUTH_TYPE=basic
+DEV_MODE=true
 
-# Always keep these on for Dev
-# Logs all model prompts to stdout
-LOG_ONYX_MODEL_INTERACTIONS=True
+
+# Always keep these on for Dev.
+# Logs model prompts, reasoning, and answer to stdout.
+LOG_ONYX_MODEL_INTERACTIONS=False
 # More verbose logging
 LOG_LEVEL=debug
 
 
-# This passes top N results to LLM an additional time for reranking prior to answer generation
-# This step is quite heavy on token usage so we disable it for dev generally
-DISABLE_LLM_DOC_RELEVANCE=False
-
-
-# Useful if you want to toggle auth on/off (google_oauth/OIDC specifically)
+# Useful if you want to toggle auth on/off (google_oauth/OIDC specifically).
 OAUTH_CLIENT_ID=<REPLACE THIS>
 OAUTH_CLIENT_SECRET=<REPLACE THIS>
 OPENID_CONFIG_URL=<REPLACE THIS>
 SAML_CONF_DIR=/<ABSOLUTE PATH TO ONYX>/onyx/backend/ee/onyx/configs/saml_config
 
-# Generally not useful for dev, we don't generally want to set up an SMTP server for dev
+
+# Generally not useful for dev, we don't generally want to set up an SMTP server
+# for dev.
 REQUIRE_EMAIL_VERIFICATION=False
 
 
-# Set these so if you wipe the DB, you don't end up having to go through the UI every time
+# Set these so if you wipe the DB, you don't end up having to go through the UI
+# every time.
 GEN_AI_API_KEY=<REPLACE THIS>
 OPENAI_API_KEY=<REPLACE THIS>
-# If answer quality isn't important for dev, use gpt-4o-mini since it's cheaper
+# If answer quality isn't important for dev, use gpt-4o-mini since it's cheaper.
 GEN_AI_MODEL_VERSION=gpt-4o
-FAST_GEN_AI_MODEL_VERSION=gpt-4o
-
-# For Onyx Slack Bot, overrides the UI values so no need to set this up via UI every time
-# Only needed if using OnyxBot
-#ONYX_BOT_SLACK_APP_TOKEN=<REPLACE THIS>
-#ONYX_BOT_SLACK_BOT_TOKEN=<REPLACE THIS>
 
 
 # Python stuff
@@ -48,19 +42,11 @@ PYTHONPATH=../backend
 PYTHONUNBUFFERED=1
 
 
-# Internet Search
-EXA_API_KEY=<REPLACE THIS>
-
-
-# Enable the full set of Danswer Enterprise Edition features
-# NOTE: DO NOT ENABLE THIS UNLESS YOU HAVE A PAID ENTERPRISE LICENSE (or if you are using this for local testing/development)
+# Enable the full set of Danswer Enterprise Edition features.
+# NOTE: DO NOT ENABLE THIS UNLESS YOU HAVE A PAID ENTERPRISE LICENSE (or if you
+# are using this for local testing/development).
 ENABLE_PAID_ENTERPRISE_EDITION_FEATURES=False
 
-# Agent Search configs  # TODO: Remove give proper namings
-AGENT_RETRIEVAL_STATS=False   # Note: This setting will incur substantial re-ranking effort
-AGENT_RERANKING_STATS=True
-AGENT_MAX_QUERY_RETRIEVAL_RESULTS=20
-AGENT_RERANKING_MAX_QUERY_RETRIEVAL_RESULTS=20
 
 # S3 File Store Configuration (MinIO for local development)
 S3_ENDPOINT_URL=http://localhost:9004
@@ -68,16 +54,24 @@ S3_FILE_STORE_BUCKET_NAME=onyx-file-store-bucket
 S3_AWS_ACCESS_KEY_ID=minioadmin
 S3_AWS_SECRET_ACCESS_KEY=minioadmin
 
-# Show extra/uncommon connectors
+
+# Show extra/uncommon connectors.
 SHOW_EXTRA_CONNECTORS=True
 
+
 # Local langsmith tracing
 LANGSMITH_TRACING="true"
 LANGSMITH_ENDPOINT="https://api.smith.langchain.com"
 LANGSMITH_API_KEY=<REPLACE_THIS>
 LANGSMITH_PROJECT=<REPLACE_THIS>
 
+
 # Local Confluence OAuth testing
 # OAUTH_CONFLUENCE_CLOUD_CLIENT_ID=<REPLACE_THIS>
 # OAUTH_CONFLUENCE_CLOUD_CLIENT_SECRET=<REPLACE_THIS>
-# NEXT_PUBLIC_TEST_ENV=True
+# NEXT_PUBLIC_TEST_ENV=True
+
+
+# OpenSearch
+# Arbitrary password is fine for local development.
+OPENSEARCH_INITIAL_ADMIN_PASSWORD=<REPLACE THIS>

.vscode/launch.json

@@ -1,5 +1,3 @@
-/* Copy this file into '.vscode/launch.json' or merge its contents into your existing configurations. */
-
 {
   // Use IntelliSense to learn about possible attributes.
   // Hover to view descriptions of existing attributes.
@@ -20,12 +18,14 @@
         "Web Server",
         "Model Server",
         "API Server",
+        "MCP Server",
         "Slack Bot",
         "Celery primary",
         "Celery light",
-        "Celery background",
+        "Celery heavy",
         "Celery docfetching",
         "Celery docprocessing",
+        "Celery user_file_processing",
         "Celery beat"
       ],
       "presentation": {
@@ -87,7 +87,7 @@
       "request": "launch",
       "cwd": "${workspaceRoot}/web",
       "runtimeExecutable": "npm",
-      "envFile": "${workspaceFolder}/.vscode/.env",
+      "envFile": "${workspaceFolder}/.vscode/.env.web",
       "runtimeArgs": ["run", "dev"],
       "presentation": {
         "group": "2"
@@ -122,7 +122,6 @@
       "cwd": "${workspaceFolder}/backend",
       "envFile": "${workspaceFolder}/.vscode/.env",
       "env": {
-        "LOG_ONYX_MODEL_INTERACTIONS": "True",
         "LOG_LEVEL": "DEBUG",
         "PYTHONUNBUFFERED": "1"
       },
@@ -132,8 +131,6 @@
       },
       "consoleTitle": "API Server Console"
     },
-    // For the listener to access the Slack API,
-    // ONYX_BOT_SLACK_APP_TOKEN & ONYX_BOT_SLACK_BOT_TOKEN need to be set in .env file located in the root of the project
     {
       "name": "Slack Bot",
       "consoleName": "Slack Bot",
@@ -152,6 +149,52 @@
       },
       "consoleTitle": "Slack Bot Console"
     },
+    {
+      "name": "Discord Bot",
+      "consoleName": "Discord Bot",
+      "type": "debugpy",
+      "request": "launch",
+      "program": "onyx/onyxbot/discord/client.py",
+      "cwd": "${workspaceFolder}/backend",
+      "envFile": "${workspaceFolder}/.vscode/.env",
+      "env": {
+        "LOG_LEVEL": "DEBUG",
+        "PYTHONUNBUFFERED": "1",
+        "PYTHONPATH": "."
+      },
+      "presentation": {
+        "group": "2"
+      },
+      "consoleTitle": "Discord Bot Console"
+    },
+    {
+      "name": "MCP Server",
+      "consoleName": "MCP Server",
+      "type": "debugpy",
+      "request": "launch",
+      "module": "uvicorn",
+      "cwd": "${workspaceFolder}/backend",
+      "envFile": "${workspaceFolder}/.vscode/.env",
+      "env": {
+        "MCP_SERVER_ENABLED": "true",
+        "MCP_SERVER_PORT": "8090",
+        "MCP_SERVER_CORS_ORIGINS": "http://localhost:*",
+        "LOG_LEVEL": "DEBUG",
+        "PYTHONUNBUFFERED": "1"
+      },
+      "args": [
+        "onyx.mcp_server.api:mcp_app",
+        "--reload",
+        "--port",
+        "8090",
+        "--timeout-graceful-shutdown",
+        "0"
+      ],
+      "presentation": {
+        "group": "2"
+      },
+      "consoleTitle": "MCP Server Console"
+    },
     {
       "name": "Celery primary",
       "type": "debugpy",
@@ -203,7 +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"
@@ -232,7 +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"
@@ -372,12 +415,11 @@
         "onyx.background.celery.versioned_apps.docfetching",
         "worker",
         "--pool=threads",
-        "--concurrency=1",
         "--prefetch-multiplier=1",
         "--loglevel=INFO",
         "--hostname=docfetching@%n",
         "-Q",
-        "connector_doc_fetching,user_files_indexing"
+        "connector_doc_fetching"
       ],
       "presentation": {
         "group": "2"
@@ -403,7 +445,6 @@
         "onyx.background.celery.versioned_apps.docprocessing",
         "worker",
         "--pool=threads",
-        "--concurrency=6",
         "--prefetch-multiplier=1",
         "--loglevel=INFO",
         "--hostname=docprocessing@%n",
@@ -481,7 +522,21 @@
       ],
       "cwd": "${workspaceFolder}",
       "console": "integratedTerminal",
-      "stopOnEntry": true,
+      "presentation": {
+        "group": "3"
+      }
+    },
+    {
+      "name": "Clear and Restart OpenSearch Container",
+      // Generic debugger type, required arg but has no bearing on bash.
+      "type": "node",
+      "request": "launch",
+      "runtimeExecutable": "bash",
+      "runtimeArgs": [
+        "${workspaceFolder}/backend/scripts/restart_opensearch_container.sh"
+      ],
+      "cwd": "${workspaceFolder}",
+      "console": "integratedTerminal",
       "presentation": {
         "group": "3"
       }
@@ -517,7 +572,6 @@
       "cwd": "${workspaceFolder}/backend",
       "envFile": "${workspaceFolder}/.vscode/.env",
       "env": {
-        "LOG_ONYX_MODEL_INTERACTIONS": "True",
         "LOG_LEVEL": "DEBUG",
         "PYTHONUNBUFFERED": "1",
         "PYTHONPATH": "."
@@ -527,10 +581,10 @@
       "name": "Install Python Requirements",
       "type": "node",
       "request": "launch",
-      "runtimeExecutable": "bash",
+      "runtimeExecutable": "uv",
       "runtimeArgs": [
-        "-c",
-        "pip install -r backend/requirements/default.txt && pip install -r backend/requirements/dev.txt && pip install -r backend/requirements/ee.txt && pip install -r backend/requirements/model_server.txt"
+        "sync",
+        "--all-extras"
       ],
       "cwd": "${workspaceFolder}",
       "console": "integratedTerminal",
@@ -539,18 +593,149 @@
       }
     },
     {
-      // script to generate the openapi schema
-      "name": "Onyx OpenAPI Schema Generator",
+      "name": "Build Sandbox Templates",
       "type": "debugpy",
       "request": "launch",
-      "program": "scripts/onyx_openapi_schema.py",
+      "module": "onyx.server.features.build.sandbox.build_templates",
       "cwd": "${workspaceFolder}/backend",
-      "envFile": "${workspaceFolder}/.env",
+      "envFile": "${workspaceFolder}/.vscode/.env",
       "env": {
         "PYTHONUNBUFFERED": "1",
         "PYTHONPATH": "."
       },
-      "args": ["--filename", "generated/openapi.json"]
+      "console": "integratedTerminal",
+      "presentation": {
+        "group": "3"
+      },
+      "consoleTitle": "Build Sandbox Templates"
+    },
+    {
+      // Dummy entry used to label the group
+      "name": "--- Database ---",
+      "type": "node",
+      "request": "launch",
+      "presentation": {
+        "group": "4",
+        "order": 0
+      }
+    },
+    {
+      "name": "Restore seeded database dump",
+      "type": "node",
+      "request": "launch",
+      "runtimeExecutable": "uv",
+      "runtimeArgs": [
+        "run",
+        "--with",
+        "onyx-devtools",
+        "ods",
+        "db",
+        "restore",
+        "--fetch-seeded",
+        "--yes"
+      ],
+      "cwd": "${workspaceFolder}",
+      "console": "integratedTerminal",
+      "presentation": {
+        "group": "4"
+      }
+    },
+    {
+      "name": "Clean restore seeded database dump (destructive)",
+      "type": "node",
+      "request": "launch",
+      "runtimeExecutable": "uv",
+      "runtimeArgs": [
+        "run",
+        "--with",
+        "onyx-devtools",
+        "ods",
+        "db",
+        "restore",
+        "--fetch-seeded",
+        "--clean",
+        "--yes"
+      ],
+      "cwd": "${workspaceFolder}",
+      "console": "integratedTerminal",
+      "presentation": {
+        "group": "4"
+      }
+    },
+    {
+      "name": "Create database snapshot",
+      "type": "node",
+      "request": "launch",
+      "runtimeExecutable": "uv",
+      "runtimeArgs": [
+        "run",
+        "--with",
+        "onyx-devtools",
+        "ods",
+        "db",
+        "dump",
+        "backup.dump"
+      ],
+      "cwd": "${workspaceFolder}",
+      "console": "integratedTerminal",
+      "presentation": {
+        "group": "4"
+      }
+    },
+    {
+      "name": "Clean restore database snapshot (destructive)",
+      "type": "node",
+      "request": "launch",
+      "runtimeExecutable": "uv",
+      "runtimeArgs": [
+        "run",
+        "--with",
+        "onyx-devtools",
+        "ods",
+        "db",
+        "restore",
+        "--clean",
+        "--yes",
+        "backup.dump"
+      ],
+      "cwd": "${workspaceFolder}",
+      "console": "integratedTerminal",
+      "presentation": {
+        "group": "4"
+      }
+    },
+    {
+      "name": "Upgrade database to head revision",
+      "type": "node",
+      "request": "launch",
+      "runtimeExecutable": "uv",
+      "runtimeArgs": [
+        "run",
+        "--with",
+        "onyx-devtools",
+        "ods",
+        "db",
+        "upgrade"
+      ],
+      "cwd": "${workspaceFolder}",
+      "console": "integratedTerminal",
+      "presentation": {
+        "group": "4"
+      }
+    },
+    {
+      // script to generate the openapi schema
+      "name": "Onyx OpenAPI Schema Generator",
+      "type": "debugpy",
+      "request": "launch",
+      "program": "backend/scripts/onyx_openapi_schema.py",
+      "cwd": "${workspaceFolder}",
+      "envFile": "${workspaceFolder}/.env",
+      "env": {
+        "PYTHONUNBUFFERED": "1",
+        "PYTHONPATH": "backend"
+      },
+      "args": ["--filename", "backend/generated/openapi.json", "--generate-python-client"]
     },
     {
       // script to debug multi tenant db issues

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 backend/.venv/bin/activate` \
-to assume the python venv.
+- 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@test.com` and password
-`a`. The app can be accessed at `http://localhost:3000`.
+- 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.
+  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
@@ -184,9 +192,291 @@ web/
 └── 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 `tailwind-themes/tailwind.config.js` / `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
@@ -196,6 +486,7 @@ alembic -n schema_private upgrade head
 ```
 
 ### Creating Migrations
+
 ```bash
 # Create migration
 alembic revision -m "description"
@@ -208,13 +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:
@@ -224,13 +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).
 
@@ -243,15 +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`.
@@ -263,8 +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.
 
@@ -276,13 +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
 
@@ -300,15 +593,8 @@ will be tailing their logs to this file.
 - Token management and rate limiting
 - Custom prompts and agent actions
 
-## UI/UX Patterns
-
-- Tailwind CSS with design system in `web/src/components/ui/`
-- Radix UI and Headless UI for accessible components
-- SWR for data fetching and caching
-- Form validation with react-hook-form
-- Error handling with popup notifications
-
 ## Creating a Plan
+
 When creating a plan in the `plans` directory, make sure to include at least these elements:
 
 **Issues to Address**
@@ -321,10 +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

@@ -1,327 +0,0 @@
-# AGENTS.md
-
-This file provides guidance to Codex when working with code in this repository.
-
-## KEY NOTES
-
-- If you run into any missing python dependency errors, try running your command with `source backend/.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@test.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
-```
-
-## 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
-
-## UI/UX Patterns
-
-- Tailwind CSS with design system in `web/src/components/ui/`
-- Radix UI and Headless UI for accessible components
-- SWR for data fetching and caching
-- Form validation with react-hook-form
-- Error handling with popup notifications
-
-## 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

CONTRIBUTING.md

@@ -1,286 +1,31 @@
-<!-- ONYX_METADATA={"link": "https://github.com/onyx-dot-app/onyx/blob/main/CONTRIBUTING.md"} -->
-
 # Contributing to Onyx
-
 Hey there! We are so excited that you're interested in Onyx.
 
-As an open source project in a rapidly changing space, we welcome all contributions.
 
-## 💃 Guidelines
+## Contribution Opportunities
+The [GitHub Issues](https://github.com/onyx-dot-app/onyx/issues) page is a great place to look for and share contribution ideas.
 
-### Contribution Opportunities
+If you have your own feature that you would like to build please create an issue and community members can provide feedback and
+thumb it up if they feel a common need. 
 
-The [GitHub Issues](https://github.com/onyx-dot-app/onyx/issues) page is a great place to start for contribution ideas.
 
-To ensure that your contribution is aligned with the project's direction, please reach out to any maintainer on the Onyx team
-via [Discord](https://discord.gg/4NA5SbzrWb) or [email](mailto:hello@onyx.app).
+## Contributing Code
+Please reference the documents in contributing_guides folder to ensure that the code base is kept to a high standard.
+1. dev_setup.md (start here): gives you a guide to setting up a local development environment.
+2. contribution_process.md: how to ensure you are building valuable features that will get reviewed and merged.
+3. best_practices.md: before asking for reviews, ensure your changes meet the repo code quality standards.
 
-Issues that have been explicitly approved by the maintainers (aligned with the direction of the project)
-will be marked with the `approved by maintainers` label.
-Issues marked `good first issue` are an especially great place to start.
-
-**Connectors** to other tools are another great place to contribute. For details on how, refer to this
-[README.md](https://github.com/onyx-dot-app/onyx/blob/main/backend/onyx/connectors/README.md).
-
-If you have a new/different contribution in mind, we'd love to hear about it!
-Your input is vital to making sure that Onyx moves in the right direction.
-Before starting on implementation, please raise a GitHub issue.
-
-Also, always feel free to message the founders (Chris Weaver / Yuhong Sun) on
-[Discord](https://discord.gg/4NA5SbzrWb) directly about anything at all.
-
-### Contributing Code
-
-To contribute to this project, please follow the
+To contribute, please follow the
 ["fork and pull request"](https://docs.github.com/en/get-started/quickstart/contributing-to-projects) workflow.
-When opening a pull request, mention related issues and feel free to tag relevant maintainers.
 
-Before creating a pull request please make sure that the new changes conform to the formatting and linting requirements.
-See the [Formatting and Linting](#formatting-and-linting) section for how to run these checks locally.
 
-### Getting Help 🙋
+## Getting Help 🙋
+We have support channels and generally interesting discussions on our [Discord](https://discord.gg/4NA5SbzrWb).
 
-Our goal is to make contributing as easy as possible. If you run into any issues please don't hesitate to reach out.
-That way we can help future contributors and users can avoid the same issue.
+See you there!
 
-We also have support channels and generally interesting discussions on our
-[Discord](https://discord.gg/4NA5SbzrWb).
-
-We would love to see you there!
-
-## Get Started 🚀
-
-Onyx being a fully functional app, relies on some external software, specifically:
-
-- [Postgres](https://www.postgresql.org/) (Relational DB)
-- [Vespa](https://vespa.ai/) (Vector DB/Search Engine)
-- [Redis](https://redis.io/) (Cache)
-- [MinIO](https://min.io/) (File Store)
-- [Nginx](https://nginx.org/) (Not needed for development flows generally)
-
-> **Note:**
-> This guide provides instructions to build and run Onyx locally from source with Docker containers providing the above external software. We believe this combination is easier for
-> development purposes. If you prefer to use pre-built container images, we provide instructions on running the full Onyx stack within Docker below.
-
-### Local Set Up
-
-Be sure to use Python version 3.11. For instructions on installing Python 3.11 on macOS, refer to the [CONTRIBUTING_MACOS.md](./CONTRIBUTING_MACOS.md) readme.
-
-If using a lower version, modifications will have to be made to the code.
-If using a higher version, sometimes some libraries will not be available (i.e. we had problems with Tensorflow in the past with higher versions of python).
-
-#### Backend: Python requirements
-
-Currently, we use pip and recommend creating a virtual environment.
-
-For convenience here's a command for it:
-
-```bash
-python -m venv .venv
-source .venv/bin/activate
-```
-
-_For Windows, activate the virtual environment using Command Prompt:_
-
-```bash
-.venv\Scripts\activate
-```
-
-If using PowerShell, the command slightly differs:
-
-```powershell
-.venv\Scripts\Activate.ps1
-```
-
-Install the required python dependencies:
-
-```bash
-pip install -r backend/requirements/combined.txt
-```
-
-or
-
-```bash
-pip install -r backend/requirements/default.txt
-pip install -r backend/requirements/dev.txt
-pip install -r backend/requirements/ee.txt
-pip install -r backend/requirements/model_server.txt
-```
-
-Fix vscode/cursor auto-imports:
-```bash
-pip install -e .
-```
-
-Install Playwright for Python (headless browser required by the Web Connector)
-
-In the activated Python virtualenv, install Playwright for Python by running:
-
-```bash
-playwright install
-```
-
-You may have to deactivate and reactivate your virtualenv for `playwright` to appear on your path.
-
-#### Frontend: Node dependencies
-
-Onyx uses Node v22.20.0. We highly recommend you use [Node Version Manager (nvm)](https://github.com/nvm-sh/nvm)
-to manage your Node installations. Once installed, you can run
-
-```bash
-nvm install 22 && nvm use 22
-node -v # verify your active version
-``` 
-
-Navigate to `onyx/web` and run:
-
-```bash
-npm i
-```
-
-## Formatting and Linting
-
-### Backend
-
-For the backend, you'll need to setup pre-commit hooks (black / reorder-python-imports).
-
-With the virtual environment active, install the pre-commit library with:
-
-```bash
-pip install pre-commit
-```
-
-Then, from the `onyx/backend` directory, run:
-
-```bash
-pre-commit install
-```
-
-Additionally, we use `mypy` for static type checking.
-Onyx is fully type-annotated, and we want to keep it that way!
-To run the mypy checks manually, run `python -m mypy .` from the `onyx/backend` directory.
-
-### Web
-
-We use `prettier` for formatting. The desired version will be installed via a `npm i` from the `onyx/web` directory.
-To run the formatter, use `npx prettier --write .` from the `onyx/web` directory.
-
-Pre-commit will also run prettier automatically on files you've recently touched. If re-formatted, your commit will fail.
-Re-stage your changes and commit again.
-
-# Running the application for development
-
-## Developing using VSCode Debugger (recommended)
-
-**We highly recommend using VSCode debugger for development.**
-See [CONTRIBUTING_VSCODE.md](./CONTRIBUTING_VSCODE.md) for more details.
-
-Otherwise, you can follow the instructions below to run the application for development.
-
-## Manually running the application for development
-### Docker containers for external software
-
-You will need Docker installed to run these containers.
-
-First navigate to `onyx/deployment/docker_compose`, then start up Postgres/Vespa/Redis/MinIO with:
-
-```bash
-docker compose up -d index relational_db cache minio
-```
-
-(index refers to Vespa, relational_db refers to Postgres, and cache refers to Redis)
-
-### Running Onyx locally
-
-To start the frontend, navigate to `onyx/web` and run:
-
-```bash
-npm run dev
-```
-
-Next, start the model server which runs the local NLP models.
-Navigate to `onyx/backend` and run:
-
-```bash
-uvicorn model_server.main:app --reload --port 9000
-```
-
-_For Windows (for compatibility with both PowerShell and Command Prompt):_
-
-```bash
-powershell -Command "uvicorn model_server.main:app --reload --port 9000"
-```
-
-The first time running Onyx, you will need to run the DB migrations for Postgres.
-After the first time, this is no longer required unless the DB models change.
-
-Navigate to `onyx/backend` and with the venv active, run:
-
-```bash
-alembic upgrade head
-```
-
-Next, start the task queue which orchestrates the background jobs.
-Jobs that take more time are run async from the API server.
-
-Still in `onyx/backend`, run:
-
-```bash
-python ./scripts/dev_run_background_jobs.py
-```
-
-To run the backend API server, navigate back to `onyx/backend` and run:
-
-```bash
-AUTH_TYPE=disabled uvicorn onyx.main:app --reload --port 8080
-```
-
-_For Windows (for compatibility with both PowerShell and Command Prompt):_
-
-```bash
-powershell -Command "
-    $env:AUTH_TYPE='disabled'
-    uvicorn onyx.main:app --reload --port 8080
-"
-```
-
-> **Note:**
-> If you need finer logging, add the additional environment variable `LOG_LEVEL=DEBUG` to the relevant services.
-
-#### Wrapping up
-
-You should now have 4 servers running:
-
-- Web server
-- Backend API
-- Model server
-- Background jobs
-
-Now, visit `http://localhost:3000` in your browser. You should see the Onyx onboarding wizard where you can connect your external LLM provider to Onyx.
-
-You've successfully set up a local Onyx instance! 🏁
-
-#### Running the Onyx application in a container
-
-You can run the full Onyx application stack from pre-built images including all external software dependencies.
-
-Navigate to `onyx/deployment/docker_compose` and run:
-
-```bash
-docker compose up -d
-```
-
-After Docker pulls and starts these containers, navigate to `http://localhost:3000` to use Onyx.
-
-If you want to make changes to Onyx and run those changes in Docker, you can also build a local version of the Onyx container images that incorporates your changes like so:
-
-```bash
-docker compose up -d --build
-```
-
-
-### Release Process
 
+## Release Process
 Onyx loosely follows the SemVer versioning standard.
 Major changes are released with a "minor" version bump. Currently we use patch release versions to indicate small feature changes.
 A set of Docker containers will be pushed automatically to DockerHub with every tag.

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/.dockerignore

@@ -15,3 +15,9 @@ build/
 dist/
 .coverage
 htmlcov/
+model_server/legacy/
+
+# Craft: demo_data directory should be unzipped at container startup, not copied
+**/demo_data/
+# Craft: templates/outputs/venv is created at container startup
+**/templates/outputs/venv

backend/.trivyignore

@@ -37,10 +37,6 @@ CVE-2023-50868
 CVE-2023-52425
 CVE-2024-28757
 
-# sqlite, only used by NLTK library to grab word lemmatizer and stopwords
-# No impact in our settings
-CVE-2023-7104
-
 # libharfbuzz0b, O(n^2) growth, worst case is denial of service
 # Accept the risk
 CVE-2023-25193

backend/Dockerfile

@@ -7,11 +7,22 @@ have a contract or agreement with DanswerAI, you are not permitted to use the En
 Edition features outside of personal development or testing purposes. Please reach out to \
 founders@onyx.app for more information. Please visit https://github.com/onyx-dot-app/onyx"
 
+# Build argument for Craft support (disabled by default)
+# Use --build-arg ENABLE_CRAFT=true to include Node.js and opencode CLI
+ARG ENABLE_CRAFT=false
+
 # DO_NOT_TRACK is used to disable telemetry for Unstructured
 ENV DANSWER_RUNNING_IN_DOCKER="true" \
     DO_NOT_TRACK="true" \
     PLAYWRIGHT_BROWSERS_PATH="/app/.cache/ms-playwright"
 
+# Create non-root user for security best practices
+RUN groupadd -g 1001 onyx && \
+    useradd -u 1001 -g onyx -m -s /bin/bash onyx && \
+    mkdir -p /var/log/onyx && \
+    chmod 755 /var/log/onyx && \
+    chown onyx:onyx /var/log/onyx
+
 COPY --from=ghcr.io/astral-sh/uv:0.9.9 /uv /uvx /bin/
 
 # Install system dependencies
@@ -39,7 +50,23 @@ RUN apt-get update && \
     rm -rf /var/lib/apt/lists/* && \
     apt-get clean
 
+# Conditionally install Node.js 20 for Craft (required for Next.js)
+# Only installed when ENABLE_CRAFT=true
+RUN if [ "$ENABLE_CRAFT" = "true" ]; then \
+        echo "Installing Node.js 20 for Craft support..." && \
+        curl -fsSL https://deb.nodesource.com/setup_20.x | bash - && \
+        apt-get install -y nodejs && \
+        rm -rf /var/lib/apt/lists/*; \
+    fi
 
+# Conditionally install opencode CLI for Craft agent functionality
+# Only installed when ENABLE_CRAFT=true
+# TODO: download a specific, versioned release of the opencode CLI
+RUN if [ "$ENABLE_CRAFT" = "true" ]; then \
+        echo "Installing opencode CLI for Craft support..." && \
+        curl -fsSL https://opencode.ai/install | bash; \
+    fi
+ENV PATH="/root/.opencode/bin:${PATH}"
 
 # Install Python dependencies
 # Remove py which is pulled in by retry, py is not needed and is a CVE
@@ -51,6 +78,7 @@ RUN uv pip install --system --no-cache-dir --upgrade \
     pip uninstall -y py && \
     playwright install chromium && \
     playwright install-deps chromium && \
+    chown -R onyx:onyx /app && \
     ln -s /usr/local/bin/supervisord /usr/bin/supervisord && \
     # Cleanup for CVEs and size reduction
     # https://github.com/tornadoweb/tornado/issues/3107
@@ -83,8 +111,8 @@ Tokenizer.from_pretrained('nomic-ai/nomic-embed-text-v1')"
 
 # Pre-downloading NLTK for setups with limited egress
 RUN python -c "import nltk; \
-nltk.download('stopwords', quiet=True); \
-nltk.download('punkt_tab', quiet=True);"
+    nltk.download('stopwords', quiet=True); \
+    nltk.download('punkt_tab', quiet=True);"
 # nltk.download('wordnet', quiet=True); introduce this back if lemmatization is needed
 
 # Pre-downloading tiktoken for setups with limited egress
@@ -94,13 +122,6 @@ tiktoken.get_encoding('cl100k_base')"
 # Set up application files
 WORKDIR /app
 
-# Create non-root user for security best practices
-RUN groupadd -g 1001 onyx && \
-    useradd -u 1001 -g onyx -m -s /bin/bash onyx && \
-    mkdir -p /var/log/onyx && \
-    chmod 755 /var/log/onyx && \
-    chown onyx:onyx /var/log/onyx
-
 # Enterprise Version Files
 COPY --chown=onyx:onyx ./ee /app/ee
 COPY supervisord.conf /etc/supervisor/conf.d/supervisord.conf
@@ -113,12 +134,26 @@ 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
 COPY --chown=onyx:onyx ./scripts/force_delete_connector_by_id.py /app/scripts/force_delete_connector_by_id.py
 COPY --chown=onyx:onyx ./scripts/supervisord_entrypoint.sh /app/scripts/supervisord_entrypoint.sh
-RUN chmod +x /app/scripts/supervisord_entrypoint.sh
+COPY --chown=onyx:onyx ./scripts/setup_craft_templates.sh /app/scripts/setup_craft_templates.sh
+RUN chmod +x /app/scripts/supervisord_entrypoint.sh /app/scripts/setup_craft_templates.sh
+
+# Run Craft template setup at build time when ENABLE_CRAFT=true
+# This pre-bakes demo data, Python venv, and npm dependencies into the image
+RUN if [ "$ENABLE_CRAFT" = "true" ]; then \
+        echo "Running Craft template setup at build time..." && \
+        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

@@ -1,4 +1,29 @@
-FROM python:3.11.7-slim-bookworm
+# Base stage with dependencies
+FROM python:3.11.7-slim-bookworm AS base
+
+ENV DANSWER_RUNNING_IN_DOCKER="true" \
+    HF_HOME=/app/.cache/huggingface
+
+COPY --from=ghcr.io/astral-sh/uv:0.9.9 /uv /uvx /bin/
+
+RUN mkdir -p /app/.cache/huggingface
+
+COPY ./requirements/model_server.txt /tmp/requirements.txt
+RUN uv pip install --system --no-cache-dir --upgrade \
+        -r /tmp/requirements.txt && \
+    rm -rf ~/.cache/uv /tmp/*.txt
+
+# Stage for downloading embedding models
+FROM base AS embedding-models
+RUN python -c "from huggingface_hub import snapshot_download; \
+snapshot_download('nomic-ai/nomic-embed-text-v1');"
+
+# Initialize SentenceTransformer to cache the custom architecture
+RUN python -c "from sentence_transformers import SentenceTransformer; \
+SentenceTransformer(model_name_or_path='nomic-ai/nomic-embed-text-v1', trust_remote_code=True);"
+
+# Final stage - combine all downloads
+FROM base AS final
 
 LABEL com.danswer.maintainer="founders@onyx.app"
 LABEL com.danswer.description="This image is for the Onyx model server which runs all of the \
@@ -6,50 +31,24 @@ AI models for Onyx. This container and all the code is MIT Licensed and free for
 You can find it at https://hub.docker.com/r/onyx/onyx-model-server. For more details, \
 visit https://github.com/onyx-dot-app/onyx."
 
-ENV DANSWER_RUNNING_IN_DOCKER="true" \
-    HF_HOME=/app/.cache/huggingface
-
-COPY --from=ghcr.io/astral-sh/uv:0.9.9 /uv /uvx /bin/
-
 # Create non-root user for security best practices
-RUN mkdir -p /app && \
-    groupadd -g 1001 onyx && \
-    useradd -u 1001 -g onyx -m -s /bin/bash onyx  && \
-    chown -R onyx:onyx /app && \
+RUN groupadd -g 1001 onyx && \
+    useradd -u 1001 -g onyx -m -s /bin/bash onyx && \
     mkdir -p /var/log/onyx && \
     chmod 755 /var/log/onyx && \
     chown onyx:onyx /var/log/onyx
 
-COPY ./requirements/model_server.txt /tmp/requirements.txt
-RUN uv pip install --system --no-cache-dir --upgrade \
-        -r /tmp/requirements.txt && \
-    rm -rf ~/.cache/uv /tmp/*.txt
-
-# Pre-downloading models for setups with limited egress
-# Download tokenizers, distilbert for the Onyx model
-# Download model weights
-# Run Nomic to pull in the custom architecture and have it cached locally
-RUN python -c "from transformers import AutoTokenizer; \
-AutoTokenizer.from_pretrained('distilbert-base-uncased'); \
-AutoTokenizer.from_pretrained('mixedbread-ai/mxbai-rerank-xsmall-v1'); \
-from huggingface_hub import snapshot_download; \
-snapshot_download(repo_id='onyx-dot-app/hybrid-intent-token-classifier'); \
-snapshot_download(repo_id='onyx-dot-app/information-content-model'); \
-snapshot_download('nomic-ai/nomic-embed-text-v1'); \
-snapshot_download('mixedbread-ai/mxbai-rerank-xsmall-v1'); \
-from sentence_transformers import SentenceTransformer; \
-SentenceTransformer(model_name_or_path='nomic-ai/nomic-embed-text-v1', trust_remote_code=True);" && \
-    # In case the user has volumes mounted to /app/.cache/huggingface that they've downloaded while
-    # running Onyx, move the current contents of the cache folder to a temporary location to ensure
-    # it's preserved in order to combine with the user's cache contents
-    mv /app/.cache/huggingface /app/.cache/temp_huggingface && \
-    chown -R onyx:onyx /app
+# In case the user has volumes mounted to /app/.cache/huggingface that they've downloaded while
+# running Onyx, move the current contents of the cache folder to a temporary location to ensure
+# it's preserved in order to combine with the user's cache contents
+COPY --chown=onyx:onyx --from=embedding-models /app/.cache/huggingface /app/.cache/temp_huggingface
 
 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/README.md

@@ -7,8 +7,12 @@ Onyx migrations use a generic single-database configuration with an async dbapi.
 
 ## To generate new migrations:
 
-run from onyx/backend:
-`alembic revision --autogenerate -m <DESCRIPTION_OF_MIGRATION>`
+From onyx/backend, run:
+`alembic revision -m <DESCRIPTION_OF_MIGRATION>`
+
+Note: you cannot use the `--autogenerate` flag as the automatic schema parsing does not work.
+
+Manually populate the upgrade and downgrade in your new migration.
 
 More info can be found here: https://alembic.sqlalchemy.org/en/latest/autogenerate.html
 

backend/alembic/env.py

@@ -39,7 +39,9 @@ config = context.config
 if config.config_file_name is not None and config.attributes.get(
     "configure_logger", True
 ):
-    fileConfig(config.config_file_name)
+    # disable_existing_loggers=False prevents breaking pytest's caplog fixture
+    # See: https://pytest-alembic.readthedocs.io/en/latest/setup.html#caplog-issues
+    fileConfig(config.config_file_name, disable_existing_loggers=False)
 
 target_metadata = [Base.metadata, ResultModelBase.metadata]
 
@@ -55,7 +57,7 @@ if USE_IAM_AUTH:
 
 
 def include_object(
-    object: SchemaItem,
+    object: SchemaItem,  # noqa: ARG001
     name: str | None,
     type_: Literal[
         "schema",
@@ -65,8 +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
@@ -223,7 +225,6 @@ def do_run_migrations(
 ) -> None:
     if create_schema:
         connection.execute(text(f'CREATE SCHEMA IF NOT EXISTS "{schema_name}"'))
-        connection.execute(text("COMMIT"))
 
     connection.execute(text(f'SET search_path TO "{schema_name}"'))
 
@@ -243,7 +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
@@ -307,6 +308,7 @@ async def run_async_migrations() -> None:
                         schema_name=schema,
                         create_schema=create_schema,
                     )
+                    await connection.commit()
             except Exception as e:
                 logger.error(f"Error migrating schema {schema}: {e}")
                 if not continue_on_error:
@@ -344,6 +346,7 @@ async def run_async_migrations() -> None:
                         schema_name=schema,
                         create_schema=create_schema,
                     )
+                    await connection.commit()
             except Exception as e:
                 logger.error(f"Error migrating schema {schema}: {e}")
                 if not continue_on_error:
@@ -460,8 +463,49 @@ def run_migrations_offline() -> None:
 
 
 def run_migrations_online() -> None:
-    logger.info("run_migrations_online starting.")
-    asyncio.run(run_async_migrations())
+    """Run migrations in 'online' mode.
+
+    Supports pytest-alembic by checking for a pre-configured connection
+    in context.config.attributes["connection"]. If present, uses that
+    connection/engine directly instead of creating a new async engine.
+    """
+    # Check if pytest-alembic is providing a connection/engine
+    connectable = context.config.attributes.get("connection", None)
+
+    if connectable is not None:
+        # pytest-alembic is providing an engine - use it directly
+        logger.debug("run_migrations_online starting (pytest-alembic mode).")
+
+        # For pytest-alembic, we use the default schema (public)
+        schema_name = context.config.attributes.get(
+            "schema_name", POSTGRES_DEFAULT_SCHEMA
+        )
+
+        # pytest-alembic passes an Engine, we need to get a connection from it
+        with connectable.connect() as connection:
+            # Set search path for the schema
+            connection.execute(text(f'SET search_path TO "{schema_name}"'))
+
+            context.configure(
+                connection=connection,
+                target_metadata=target_metadata,  # type: ignore
+                include_object=include_object,
+                version_table_schema=schema_name,
+                include_schemas=True,
+                compare_type=True,
+                compare_server_default=True,
+                script_location=config.get_main_option("script_location"),
+            )
+
+            with context.begin_transaction():
+                context.run_migrations()
+
+            # Commit the transaction to ensure changes are visible to next migration
+            connection.commit()
+    else:
+        # Normal operation - use async migrations
+        logger.info("run_migrations_online starting.")
+        asyncio.run(run_async_migrations())
 
 
 if context.is_offline_mode():

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/01f8e6d95a33_populate_flow_mapping_data.py

@@ -0,0 +1,112 @@
+"""Populate flow mapping data
+
+Revision ID: 01f8e6d95a33
+Revises: d5c86e2c6dc6
+Create Date: 2026-01-31 17:37:10.485558
+
+"""
+
+from alembic import op
+
+
+# revision identifiers, used by Alembic.
+revision = "01f8e6d95a33"
+down_revision = "d5c86e2c6dc6"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    # Add each model config to the conversation flow, setting the global default if it exists
+    # Exclude models that are part of ImageGenerationConfig
+    op.execute(
+        """
+        INSERT INTO llm_model_flow (llm_model_flow_type, is_default, model_configuration_id)
+        SELECT
+            'CHAT' AS llm_model_flow_type,
+            COALESCE(
+                (lp.is_default_provider IS TRUE AND lp.default_model_name = mc.name),
+                FALSE
+            ) AS is_default,
+            mc.id AS model_configuration_id
+        FROM model_configuration mc
+        LEFT JOIN llm_provider lp
+            ON lp.id = mc.llm_provider_id
+        WHERE NOT EXISTS (
+            SELECT 1 FROM image_generation_config igc
+            WHERE igc.model_configuration_id = mc.id
+        );
+        """
+    )
+
+    # Add models with supports_image_input to the vision flow
+    op.execute(
+        """
+        INSERT INTO llm_model_flow (llm_model_flow_type, is_default, model_configuration_id)
+        SELECT
+            'VISION' AS llm_model_flow_type,
+            COALESCE(
+                (lp.is_default_vision_provider IS TRUE AND lp.default_vision_model = mc.name),
+                FALSE
+            ) AS is_default,
+            mc.id AS model_configuration_id
+        FROM model_configuration mc
+        LEFT JOIN llm_provider lp
+            ON lp.id = mc.llm_provider_id
+        WHERE mc.supports_image_input IS TRUE;
+        """
+    )
+
+
+def downgrade() -> None:
+    # Populate vision defaults from model_flow
+    op.execute(
+        """
+        UPDATE llm_provider AS lp
+        SET
+            is_default_vision_provider = TRUE,
+            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'
+          AND mf.is_default = TRUE
+          AND mc.llm_provider_id = lp.id;
+        """
+    )
+
+    # Populate conversation defaults from model_flow
+    op.execute(
+        """
+        UPDATE llm_provider AS lp
+        SET
+            is_default_provider = TRUE,
+            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'
+          AND mf.is_default = TRUE
+          AND mc.llm_provider_id = lp.id;
+        """
+    )
+
+    # For providers that have conversation flow mappings but aren't the default,
+    # we still need a default_model_name (it was NOT NULL originally)
+    # Pick the first visible model or any model for that provider
+    op.execute(
+        """
+        UPDATE llm_provider AS lp
+        SET default_model_name = (
+            SELECT mc.name
+            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'
+            ORDER BY mc.is_visible DESC, mc.id ASC
+            LIMIT 1
+        )
+        WHERE lp.default_model_name IS NULL;
+        """
+    )
+
+    # Delete all model_flow entries (reverse the inserts from upgrade)
+    op.execute("DELETE FROM llm_model_flow;")

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/18b5b2524446_add_is_clarification_to_chat_message.py

@@ -0,0 +1,29 @@
+"""add is_clarification to chat_message
+
+Revision ID: 18b5b2524446
+Revises: 87c52ec39f84
+Create Date: 2025-01-16
+
+"""
+
+from alembic import op
+import sqlalchemy as sa
+
+# revision identifiers, used by Alembic.
+revision = "18b5b2524446"
+down_revision = "87c52ec39f84"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    op.add_column(
+        "chat_message",
+        sa.Column(
+            "is_clarification", sa.Boolean(), nullable=False, server_default="false"
+        ),
+    )
+
+
+def downgrade() -> None:
+    op.drop_column("chat_message", "is_clarification")

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/1f2a3b4c5d6e_add_internet_search_and_content_providers.py

@@ -0,0 +1,89 @@
+"""add internet search and content provider tables
+
+Revision ID: 1f2a3b4c5d6e
+Revises: 9drpiiw74ljy
+Create Date: 2025-11-10 19:45:00.000000
+
+"""
+
+from alembic import op
+import sqlalchemy as sa
+from sqlalchemy.dialects import postgresql
+
+
+# revision identifiers, used by Alembic.
+revision = "1f2a3b4c5d6e"
+down_revision = "9drpiiw74ljy"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    op.create_table(
+        "internet_search_provider",
+        sa.Column("id", sa.Integer(), primary_key=True),
+        sa.Column("name", sa.String(), nullable=False, unique=True),
+        sa.Column("provider_type", sa.String(), nullable=False),
+        sa.Column("api_key", sa.LargeBinary(), nullable=True),
+        sa.Column("config", postgresql.JSONB(astext_type=sa.Text()), nullable=True),
+        sa.Column(
+            "is_active", sa.Boolean(), nullable=False, server_default=sa.text("false")
+        ),
+        sa.Column(
+            "time_created",
+            sa.DateTime(timezone=True),
+            nullable=False,
+            server_default=sa.text("now()"),
+        ),
+        sa.Column(
+            "time_updated",
+            sa.DateTime(timezone=True),
+            nullable=False,
+            server_default=sa.text("now()"),
+        ),
+    )
+    op.create_index(
+        "ix_internet_search_provider_is_active",
+        "internet_search_provider",
+        ["is_active"],
+    )
+
+    op.create_table(
+        "internet_content_provider",
+        sa.Column("id", sa.Integer(), primary_key=True),
+        sa.Column("name", sa.String(), nullable=False, unique=True),
+        sa.Column("provider_type", sa.String(), nullable=False),
+        sa.Column("api_key", sa.LargeBinary(), nullable=True),
+        sa.Column("config", postgresql.JSONB(astext_type=sa.Text()), nullable=True),
+        sa.Column(
+            "is_active", sa.Boolean(), nullable=False, server_default=sa.text("false")
+        ),
+        sa.Column(
+            "time_created",
+            sa.DateTime(timezone=True),
+            nullable=False,
+            server_default=sa.text("now()"),
+        ),
+        sa.Column(
+            "time_updated",
+            sa.DateTime(timezone=True),
+            nullable=False,
+            server_default=sa.text("now()"),
+        ),
+    )
+    op.create_index(
+        "ix_internet_content_provider_is_active",
+        "internet_content_provider",
+        ["is_active"],
+    )
+
+
+def downgrade() -> None:
+    op.drop_index(
+        "ix_internet_content_provider_is_active", table_name="internet_content_provider"
+    )
+    op.drop_table("internet_content_provider")
+    op.drop_index(
+        "ix_internet_search_provider_is_active", table_name="internet_search_provider"
+    )
+    op.drop_table("internet_search_provider")

backend/alembic/versions/1f60f60c3401_embedding_model_search_settings.py

@@ -10,8 +10,6 @@ from alembic import op
 import sqlalchemy as sa
 from sqlalchemy.dialects import postgresql
 
-from onyx.configs.chat_configs import NUM_POSTPROCESSED_RESULTS
-
 # revision identifiers, used by Alembic.
 revision = "1f60f60c3401"
 down_revision = "f17bf3b0d9f1"
@@ -66,7 +64,7 @@ def upgrade() -> None:
             "num_rerank",
             sa.Integer(),
             nullable=False,
-            server_default=str(NUM_POSTPROCESSED_RESULTS),
+            server_default=str(20),
         ),
     )
 

backend/alembic/versions/2020d417ec84_single_onyx_craft_migration.py

@@ -0,0 +1,351 @@
+"""single onyx craft migration
+
+Consolidates all buildmode/onyx craft tables into a single migration.
+
+Tables created:
+- build_session: User build sessions with status tracking
+- sandbox: User-owned containerized environments (one per user)
+- artifact: Build output files (web apps, documents, images)
+- snapshot: Sandbox filesystem snapshots
+- build_message: Conversation messages for build sessions
+
+Existing table modified:
+- connector_credential_pair: Added processing_mode column
+
+Revision ID: 2020d417ec84
+Revises: 41fa44bef321
+Create Date: 2026-01-26 14:43:54.641405
+
+"""
+
+from alembic import op
+import sqlalchemy as sa
+from sqlalchemy.dialects import postgresql
+
+
+# revision identifiers, used by Alembic.
+revision = "2020d417ec84"
+down_revision = "41fa44bef321"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    # ==========================================================================
+    # ENUMS
+    # ==========================================================================
+
+    # Build session status enum
+    build_session_status_enum = sa.Enum(
+        "active",
+        "idle",
+        name="buildsessionstatus",
+        native_enum=False,
+    )
+
+    # Sandbox status enum
+    sandbox_status_enum = sa.Enum(
+        "provisioning",
+        "running",
+        "idle",
+        "sleeping",
+        "terminated",
+        "failed",
+        name="sandboxstatus",
+        native_enum=False,
+    )
+
+    # Artifact type enum
+    artifact_type_enum = sa.Enum(
+        "web_app",
+        "pptx",
+        "docx",
+        "markdown",
+        "excel",
+        "image",
+        name="artifacttype",
+        native_enum=False,
+    )
+
+    # ==========================================================================
+    # BUILD_SESSION TABLE
+    # ==========================================================================
+
+    op.create_table(
+        "build_session",
+        sa.Column("id", postgresql.UUID(as_uuid=True), primary_key=True),
+        sa.Column(
+            "user_id",
+            postgresql.UUID(as_uuid=True),
+            sa.ForeignKey("user.id", ondelete="CASCADE"),
+            nullable=True,
+        ),
+        sa.Column("name", sa.String(), nullable=True),
+        sa.Column(
+            "status",
+            build_session_status_enum,
+            nullable=False,
+            server_default="active",
+        ),
+        sa.Column(
+            "created_at",
+            sa.DateTime(timezone=True),
+            server_default=sa.text("now()"),
+            nullable=False,
+        ),
+        sa.Column(
+            "last_activity_at",
+            sa.DateTime(timezone=True),
+            server_default=sa.text("now()"),
+            nullable=False,
+        ),
+        sa.Column("nextjs_port", sa.Integer(), nullable=True),
+        sa.PrimaryKeyConstraint("id"),
+    )
+
+    op.create_index(
+        "ix_build_session_user_created",
+        "build_session",
+        ["user_id", sa.text("created_at DESC")],
+        unique=False,
+    )
+    op.create_index(
+        "ix_build_session_status",
+        "build_session",
+        ["status"],
+        unique=False,
+    )
+
+    # ==========================================================================
+    # SANDBOX TABLE (user-owned, one per user)
+    # ==========================================================================
+
+    op.create_table(
+        "sandbox",
+        sa.Column("id", postgresql.UUID(as_uuid=True), primary_key=True),
+        sa.Column(
+            "user_id",
+            postgresql.UUID(as_uuid=True),
+            sa.ForeignKey("user.id", ondelete="CASCADE"),
+            nullable=False,
+        ),
+        sa.Column("container_id", sa.String(), nullable=True),
+        sa.Column(
+            "status",
+            sandbox_status_enum,
+            nullable=False,
+            server_default="provisioning",
+        ),
+        sa.Column(
+            "created_at",
+            sa.DateTime(timezone=True),
+            server_default=sa.text("now()"),
+            nullable=False,
+        ),
+        sa.Column("last_heartbeat", sa.DateTime(timezone=True), nullable=True),
+        sa.PrimaryKeyConstraint("id"),
+        sa.UniqueConstraint("user_id", name="sandbox_user_id_key"),
+    )
+
+    op.create_index(
+        "ix_sandbox_status",
+        "sandbox",
+        ["status"],
+        unique=False,
+    )
+    op.create_index(
+        "ix_sandbox_container_id",
+        "sandbox",
+        ["container_id"],
+        unique=False,
+    )
+
+    # ==========================================================================
+    # ARTIFACT TABLE
+    # ==========================================================================
+
+    op.create_table(
+        "artifact",
+        sa.Column("id", postgresql.UUID(as_uuid=True), primary_key=True),
+        sa.Column(
+            "session_id",
+            postgresql.UUID(as_uuid=True),
+            sa.ForeignKey("build_session.id", ondelete="CASCADE"),
+            nullable=False,
+        ),
+        sa.Column("type", artifact_type_enum, nullable=False),
+        sa.Column("path", sa.String(), nullable=False),
+        sa.Column("name", sa.String(), 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()"),
+            nullable=False,
+        ),
+        sa.PrimaryKeyConstraint("id"),
+    )
+
+    op.create_index(
+        "ix_artifact_session_created",
+        "artifact",
+        ["session_id", sa.text("created_at DESC")],
+        unique=False,
+    )
+    op.create_index(
+        "ix_artifact_type",
+        "artifact",
+        ["type"],
+        unique=False,
+    )
+
+    # ==========================================================================
+    # SNAPSHOT TABLE
+    # ==========================================================================
+
+    op.create_table(
+        "snapshot",
+        sa.Column("id", postgresql.UUID(as_uuid=True), primary_key=True),
+        sa.Column(
+            "session_id",
+            postgresql.UUID(as_uuid=True),
+            sa.ForeignKey("build_session.id", ondelete="CASCADE"),
+            nullable=False,
+        ),
+        sa.Column("storage_path", sa.String(), nullable=False),
+        sa.Column("size_bytes", sa.BigInteger(), nullable=False, server_default="0"),
+        sa.Column(
+            "created_at",
+            sa.DateTime(timezone=True),
+            server_default=sa.text("now()"),
+            nullable=False,
+        ),
+        sa.PrimaryKeyConstraint("id"),
+    )
+
+    op.create_index(
+        "ix_snapshot_session_created",
+        "snapshot",
+        ["session_id", sa.text("created_at DESC")],
+        unique=False,
+    )
+
+    # ==========================================================================
+    # BUILD_MESSAGE TABLE
+    # ==========================================================================
+
+    op.create_table(
+        "build_message",
+        sa.Column("id", postgresql.UUID(as_uuid=True), primary_key=True),
+        sa.Column(
+            "session_id",
+            postgresql.UUID(as_uuid=True),
+            sa.ForeignKey("build_session.id", ondelete="CASCADE"),
+            nullable=False,
+        ),
+        sa.Column(
+            "turn_index",
+            sa.Integer(),
+            nullable=False,
+        ),
+        sa.Column(
+            "type",
+            sa.Enum(
+                "SYSTEM",
+                "USER",
+                "ASSISTANT",
+                "DANSWER",
+                name="messagetype",
+                create_type=False,
+                native_enum=False,
+            ),
+            nullable=False,
+        ),
+        sa.Column(
+            "message_metadata",
+            postgresql.JSONB(),
+            nullable=False,
+        ),
+        sa.Column(
+            "created_at",
+            sa.DateTime(timezone=True),
+            server_default=sa.text("now()"),
+            nullable=False,
+        ),
+        sa.PrimaryKeyConstraint("id"),
+    )
+
+    op.create_index(
+        "ix_build_message_session_turn",
+        "build_message",
+        ["session_id", "turn_index", sa.text("created_at ASC")],
+        unique=False,
+    )
+
+    # ==========================================================================
+    # CONNECTOR_CREDENTIAL_PAIR MODIFICATION
+    # ==========================================================================
+
+    op.add_column(
+        "connector_credential_pair",
+        sa.Column(
+            "processing_mode",
+            sa.String(),
+            nullable=False,
+            server_default="regular",
+        ),
+    )
+
+
+def downgrade() -> None:
+    # ==========================================================================
+    # CONNECTOR_CREDENTIAL_PAIR MODIFICATION
+    # ==========================================================================
+
+    op.drop_column("connector_credential_pair", "processing_mode")
+
+    # ==========================================================================
+    # BUILD_MESSAGE TABLE
+    # ==========================================================================
+
+    op.drop_index("ix_build_message_session_turn", table_name="build_message")
+    op.drop_table("build_message")
+
+    # ==========================================================================
+    # SNAPSHOT TABLE
+    # ==========================================================================
+
+    op.drop_index("ix_snapshot_session_created", table_name="snapshot")
+    op.drop_table("snapshot")
+
+    # ==========================================================================
+    # ARTIFACT TABLE
+    # ==========================================================================
+
+    op.drop_index("ix_artifact_type", table_name="artifact")
+    op.drop_index("ix_artifact_session_created", table_name="artifact")
+    op.drop_table("artifact")
+    sa.Enum(name="artifacttype").drop(op.get_bind(), checkfirst=True)
+
+    # ==========================================================================
+    # SANDBOX TABLE
+    # ==========================================================================
+
+    op.drop_index("ix_sandbox_container_id", table_name="sandbox")
+    op.drop_index("ix_sandbox_status", table_name="sandbox")
+    op.drop_table("sandbox")
+    sa.Enum(name="sandboxstatus").drop(op.get_bind(), checkfirst=True)
+
+    # ==========================================================================
+    # BUILD_SESSION TABLE
+    # ==========================================================================
+
+    op.drop_index("ix_build_session_status", table_name="build_session")
+    op.drop_index("ix_build_session_user_created", table_name="build_session")
+    op.drop_table("build_session")
+    sa.Enum(name="buildsessionstatus").drop(op.get_bind(), checkfirst=True)

backend/alembic/versions/23957775e5f5_remove_feedback_foreignkey_constraint.py

@@ -12,8 +12,8 @@ import sqlalchemy as sa
 # revision identifiers, used by Alembic.
 revision = "23957775e5f5"
 down_revision = "bc9771dccadf"
-branch_labels = None  # type: ignore
-depends_on = None  # type: ignore
+branch_labels = None
+depends_on = None
 
 
 def upgrade() -> None:

backend/alembic/versions/2a391f840e85_add_last_refreshed_at_mcp_server.py

@@ -0,0 +1,27 @@
+"""add last refreshed at mcp server
+
+Revision ID: 2a391f840e85
+Revises: 4cebcbc9b2ae
+Create Date: 2025-12-06 15:19:59.766066
+
+"""
+
+from alembic import op
+import sqlalchemy as sa
+
+# revision identifiers, used by Alembi.
+revision = "2a391f840e85"
+down_revision = "4cebcbc9b2ae"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    op.add_column(
+        "mcp_server",
+        sa.Column("last_refreshed_at", sa.DateTime(timezone=True), nullable=True),
+    )
+
+
+def downgrade() -> None:
+    op.drop_column("mcp_server", "last_refreshed_at")

backend/alembic/versions/2b90f3af54b8_usage_limits.py

@@ -0,0 +1,46 @@
+"""usage_limits
+
+Revision ID: 2b90f3af54b8
+Revises: 9a0296d7421e
+Create Date: 2026-01-03 16:55:30.449692
+
+"""
+
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision = "2b90f3af54b8"
+down_revision = "9a0296d7421e"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    op.create_table(
+        "tenant_usage",
+        sa.Column("id", sa.Integer(), nullable=False),
+        sa.Column(
+            "window_start", sa.DateTime(timezone=True), nullable=False, index=True
+        ),
+        sa.Column("llm_cost_cents", sa.Float(), nullable=False, server_default="0.0"),
+        sa.Column("chunks_indexed", sa.Integer(), nullable=False, server_default="0"),
+        sa.Column("api_calls", sa.Integer(), nullable=False, server_default="0"),
+        sa.Column(
+            "non_streaming_api_calls", sa.Integer(), nullable=False, server_default="0"
+        ),
+        sa.Column(
+            "updated_at",
+            sa.DateTime(timezone=True),
+            server_default=sa.func.now(),
+            nullable=True,
+        ),
+        sa.PrimaryKeyConstraint("id"),
+        sa.UniqueConstraint("window_start", name="uq_tenant_usage_window"),
+    )
+
+
+def downgrade() -> None:
+    op.drop_index("ix_tenant_usage_window_start", table_name="tenant_usage")
+    op.drop_table("tenant_usage")

backend/alembic/versions/2c2430828bdf_add_unique_constraint_to_inputprompt_.py

@@ -0,0 +1,42 @@
+"""add_unique_constraint_to_inputprompt_prompt_user_id
+
+Revision ID: 2c2430828bdf
+Revises: fb80bdd256de
+Create Date: 2026-01-20 16:01:54.314805
+
+"""
+
+from alembic import op
+
+
+# revision identifiers, used by Alembic.
+revision = "2c2430828bdf"
+down_revision = "fb80bdd256de"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    # Create unique constraint on (prompt, user_id) for user-owned prompts
+    # This ensures each user can only have one shortcut with a given name
+    op.create_unique_constraint(
+        "uq_inputprompt_prompt_user_id",
+        "inputprompt",
+        ["prompt", "user_id"],
+    )
+
+    # Create partial unique index for public prompts (where user_id IS NULL)
+    # PostgreSQL unique constraints don't enforce uniqueness for NULL values,
+    # so we need a partial index to ensure public prompt names are also unique
+    op.execute(
+        """
+        CREATE UNIQUE INDEX uq_inputprompt_prompt_public
+        ON inputprompt (prompt)
+        WHERE user_id IS NULL
+        """
+    )
+
+
+def downgrade() -> None:
+    op.execute("DROP INDEX IF EXISTS uq_inputprompt_prompt_public")
+    op.drop_constraint("uq_inputprompt_prompt_user_id", "inputprompt", type_="unique")

backend/alembic/versions/3c9a65f1207f_seed_exa_provider_from_env.py

@@ -0,0 +1,89 @@
+"""seed_exa_provider_from_env
+
+Revision ID: 3c9a65f1207f
+Revises: 1f2a3b4c5d6e
+Create Date: 2025-11-20 19:18:00.000000
+
+"""
+
+from __future__ import annotations
+
+import os
+
+from alembic import op
+import sqlalchemy as sa
+from sqlalchemy.dialects import postgresql
+from dotenv import load_dotenv, find_dotenv
+
+from onyx.utils.encryption import encrypt_string_to_bytes
+
+revision = "3c9a65f1207f"
+down_revision = "1f2a3b4c5d6e"
+branch_labels = None
+depends_on = None
+
+
+EXA_PROVIDER_NAME = "Exa"
+
+
+def _get_internet_search_table(metadata: sa.MetaData) -> sa.Table:
+    return sa.Table(
+        "internet_search_provider",
+        metadata,
+        sa.Column("id", sa.Integer, primary_key=True),
+        sa.Column("name", sa.String),
+        sa.Column("provider_type", sa.String),
+        sa.Column("api_key", sa.LargeBinary),
+        sa.Column("config", postgresql.JSONB),
+        sa.Column("is_active", sa.Boolean),
+        sa.Column(
+            "time_created",
+            sa.DateTime(timezone=True),
+            nullable=False,
+            server_default=sa.text("now()"),
+        ),
+        sa.Column(
+            "time_updated",
+            sa.DateTime(timezone=True),
+            nullable=False,
+            server_default=sa.text("now()"),
+        ),
+    )
+
+
+def upgrade() -> None:
+    load_dotenv(find_dotenv())
+
+    exa_api_key = os.environ.get("EXA_API_KEY")
+    if not exa_api_key:
+        return
+
+    bind = op.get_bind()
+    metadata = sa.MetaData()
+    table = _get_internet_search_table(metadata)
+
+    existing = bind.execute(
+        sa.select(table.c.id).where(table.c.name == EXA_PROVIDER_NAME)
+    ).first()
+    if existing:
+        return
+
+    encrypted_key = encrypt_string_to_bytes(exa_api_key)
+
+    has_active_provider = bind.execute(
+        sa.select(table.c.id).where(table.c.is_active.is_(True))
+    ).first()
+
+    bind.execute(
+        table.insert().values(
+            name=EXA_PROVIDER_NAME,
+            provider_type="exa",
+            api_key=encrypted_key,
+            config=None,
+            is_active=not bool(has_active_provider),
+        )
+    )
+
+
+def downgrade() -> None:
+    return

backend/alembic/versions/41fa44bef321_remove_default_prompt_shortcuts.py

@@ -0,0 +1,29 @@
+"""remove default prompt shortcuts
+
+Revision ID: 41fa44bef321
+Revises: 2c2430828bdf
+Create Date: 2025-01-21
+
+"""
+
+from alembic import op
+
+# revision identifiers, used by Alembic.
+revision = "41fa44bef321"
+down_revision = "2c2430828bdf"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    # Delete any user associations for the default prompts first (foreign key constraint)
+    op.execute(
+        "DELETE FROM inputprompt__user WHERE input_prompt_id IN (SELECT id FROM inputprompt WHERE id < 0)"
+    )
+    # Delete the pre-seeded default prompt shortcuts (they have negative IDs)
+    op.execute("DELETE FROM inputprompt WHERE id < 0")
+
+
+def downgrade() -> None:
+    # We don't restore the default prompts on downgrade
+    pass

backend/alembic/versions/47a07e1a38f1_fix_invalid_model_configurations_state.py

@@ -11,7 +11,7 @@ from pydantic import BaseModel, ConfigDict
 import sqlalchemy as sa
 from sqlalchemy.dialects import postgresql
 
-from onyx.llm.llm_provider_options import (
+from onyx.llm.well_known_providers.llm_provider_options import (
     fetch_model_names_for_provider_as_set,
     fetch_visible_model_names_for_provider_as_set,
 )

backend/alembic/versions/4cebcbc9b2ae_add_tab_index_to_tool_call.py

@@ -0,0 +1,27 @@
+"""add tab_index to tool_call
+
+Revision ID: 4cebcbc9b2ae
+Revises: a1b2c3d4e5f6
+Create Date: 2025-12-16
+
+"""
+
+from alembic import op
+import sqlalchemy as sa
+
+# revision identifiers, used by Alembic.
+revision = "4cebcbc9b2ae"
+down_revision = "a1b2c3d4e5f6"
+branch_labels: None = None
+depends_on: None = None
+
+
+def upgrade() -> None:
+    op.add_column(
+        "tool_call",
+        sa.Column("tab_index", sa.Integer(), nullable=False, server_default="0"),
+    )
+
+
+def downgrade() -> None:
+    op.drop_column("tool_call", "tab_index")

backend/alembic/versions/4ea2c93919c1_add_type_to_credentials.py

@@ -62,6 +62,11 @@ def upgrade() -> None:
     )
     """
     )
+
+    # Drop the temporary table to avoid conflicts if migration runs again
+    # (e.g., during upgrade -> downgrade -> upgrade cycles in tests)
+    op.execute("DROP TABLE IF EXISTS temp_connector_credential")
+
     # If no exception was raised, alter the column
     op.alter_column("credential", "source", nullable=True)  # TODO modify
     # # ### end Alembic commands ###

backend/alembic/versions/4f8a2b3c1d9e_add_open_url_tool.py

@@ -0,0 +1,104 @@
+"""add_open_url_tool
+
+Revision ID: 4f8a2b3c1d9e
+Revises: a852cbe15577
+Create Date: 2025-11-24 12:00:00.000000
+
+"""
+
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision = "4f8a2b3c1d9e"
+down_revision = "a852cbe15577"
+branch_labels = None
+depends_on = None
+
+
+OPEN_URL_TOOL = {
+    "name": "OpenURLTool",
+    "display_name": "Open URL",
+    "description": (
+        "The Open URL Action allows the agent to fetch and read contents of web pages."
+    ),
+    "in_code_tool_id": "OpenURLTool",
+    "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": OPEN_URL_TOOL["in_code_tool_id"]},
+    ).fetchone()
+
+    if existing:
+        tool_id = existing[0]
+        # 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
+                """
+            ),
+            OPEN_URL_TOOL,
+        )
+    else:
+        # Insert new tool
+        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)
+                """
+            ),
+            OPEN_URL_TOOL,
+        )
+        # Get the newly inserted tool's id
+        result = conn.execute(
+            sa.text("SELECT id FROM tool WHERE in_code_tool_id = :in_code_tool_id"),
+            {"in_code_tool_id": OPEN_URL_TOOL["in_code_tool_id"]},
+        ).fetchone()
+        tool_id = result[0]  # type: ignore
+
+    # Associate the tool with all existing personas
+    # Get all persona IDs
+    persona_ids = conn.execute(sa.text("SELECT id FROM persona")).fetchall()
+
+    for (persona_id,) in persona_ids:
+        # Check if association already exists
+        exists = conn.execute(
+            sa.text(
+                """
+                SELECT 1 FROM persona__tool
+                WHERE persona_id = :persona_id AND tool_id = :tool_id
+                """
+            ),
+            {"persona_id": persona_id, "tool_id": tool_id},
+        ).fetchone()
+
+        if not exists:
+            conn.execute(
+                sa.text(
+                    """
+                    INSERT INTO persona__tool (persona_id, tool_id)
+                    VALUES (:persona_id, :tool_id)
+                    """
+                ),
+                {"persona_id": persona_id, "tool_id": tool_id},
+            )
+
+
+def downgrade() -> None:
+    # We don't remove the tool on downgrade since it's fine to have it around.
+    # If we upgrade again, it will be a no-op.
+    pass

backend/alembic/versions/505c488f6662_merge_default_assistants_into_unified.py

@@ -85,103 +85,122 @@ class UserRow(NamedTuple):
 def upgrade() -> None:
     conn = op.get_bind()
 
-    # Start transaction
-    conn.execute(sa.text("BEGIN"))
+    # Step 1: Create or update the unified assistant (ID 0)
+    search_assistant = conn.execute(
+        sa.text("SELECT * FROM persona WHERE id = 0")
+    ).fetchone()
 
-    try:
-        # Step 1: Create or update the unified assistant (ID 0)
-        search_assistant = conn.execute(
-            sa.text("SELECT * FROM persona WHERE id = 0")
-        ).fetchone()
-
-        if search_assistant:
-            # Update existing Search assistant to be the unified assistant
-            conn.execute(
-                sa.text(
-                    """
-                    UPDATE persona
-                    SET name = :name,
-                        description = :description,
-                        system_prompt = :system_prompt,
-                        num_chunks = :num_chunks,
-                        is_default_persona = true,
-                        is_visible = true,
-                        deleted = false,
-                        display_priority = :display_priority,
-                        llm_filter_extraction = :llm_filter_extraction,
-                        llm_relevance_filter = :llm_relevance_filter,
-                        recency_bias = :recency_bias,
-                        chunks_above = :chunks_above,
-                        chunks_below = :chunks_below,
-                        datetime_aware = :datetime_aware,
-                        starter_messages = null
-                    WHERE id = 0
-                """
-                ),
-                INSERT_DICT,
-            )
-        else:
-            # Create new unified assistant with ID 0
-            conn.execute(
-                sa.text(
-                    """
-                    INSERT INTO persona (
-                        id, name, description, system_prompt, num_chunks,
-                        is_default_persona, is_visible, deleted, display_priority,
-                        llm_filter_extraction, llm_relevance_filter, recency_bias,
-                        chunks_above, chunks_below, datetime_aware, starter_messages,
-                        builtin_persona
-                    ) VALUES (
-                        0, :name, :description, :system_prompt, :num_chunks,
-                        true, true, false, :display_priority, :llm_filter_extraction,
-                        :llm_relevance_filter, :recency_bias, :chunks_above, :chunks_below,
-                        :datetime_aware, null, true
-                    )
-                """
-                ),
-                INSERT_DICT,
-            )
-
-        # Step 2: Mark ALL builtin assistants as deleted (except the unified assistant ID 0)
+    if search_assistant:
+        # Update existing Search assistant to be the unified assistant
         conn.execute(
             sa.text(
                 """
                 UPDATE persona
-                SET deleted = true, is_visible = false, is_default_persona = false
-                WHERE builtin_persona = true AND id != 0
+                SET name = :name,
+                    description = :description,
+                    system_prompt = :system_prompt,
+                    num_chunks = :num_chunks,
+                    is_default_persona = true,
+                    is_visible = true,
+                    deleted = false,
+                    display_priority = :display_priority,
+                    llm_filter_extraction = :llm_filter_extraction,
+                    llm_relevance_filter = :llm_relevance_filter,
+                    recency_bias = :recency_bias,
+                    chunks_above = :chunks_above,
+                    chunks_below = :chunks_below,
+                    datetime_aware = :datetime_aware,
+                    starter_messages = null
+                WHERE id = 0
             """
-            )
+            ),
+            INSERT_DICT,
+        )
+    else:
+        # Create new unified assistant with ID 0
+        conn.execute(
+            sa.text(
+                """
+                INSERT INTO persona (
+                    id, name, description, system_prompt, num_chunks,
+                    is_default_persona, is_visible, deleted, display_priority,
+                    llm_filter_extraction, llm_relevance_filter, recency_bias,
+                    chunks_above, chunks_below, datetime_aware, starter_messages,
+                    builtin_persona
+                ) VALUES (
+                    0, :name, :description, :system_prompt, :num_chunks,
+                    true, true, false, :display_priority, :llm_filter_extraction,
+                    :llm_relevance_filter, :recency_bias, :chunks_above, :chunks_below,
+                    :datetime_aware, null, true
+                )
+            """
+            ),
+            INSERT_DICT,
         )
 
-        # Step 3: Add all built-in tools to the unified assistant
-        # First, get the tool IDs for SearchTool, ImageGenerationTool, and WebSearchTool
-        search_tool = conn.execute(
-            sa.text("SELECT id FROM tool WHERE in_code_tool_id = 'SearchTool'")
-        ).fetchone()
+    # Step 2: Mark ALL builtin assistants as deleted (except the unified assistant ID 0)
+    conn.execute(
+        sa.text(
+            """
+            UPDATE persona
+            SET deleted = true, is_visible = false, is_default_persona = false
+            WHERE builtin_persona = true AND id != 0
+        """
+        )
+    )
 
-        if not search_tool:
-            raise ValueError(
-                "SearchTool not found in database. Ensure tools migration has run first."
-            )
+    # Step 3: Add all built-in tools to the unified assistant
+    # First, get the tool IDs for SearchTool, ImageGenerationTool, and WebSearchTool
+    search_tool = conn.execute(
+        sa.text("SELECT id FROM tool WHERE in_code_tool_id = 'SearchTool'")
+    ).fetchone()
 
-        image_gen_tool = conn.execute(
-            sa.text("SELECT id FROM tool WHERE in_code_tool_id = 'ImageGenerationTool'")
-        ).fetchone()
+    if not search_tool:
+        raise ValueError(
+            "SearchTool not found in database. Ensure tools migration has run first."
+        )
 
-        if not image_gen_tool:
-            raise ValueError(
-                "ImageGenerationTool not found in database. Ensure tools migration has run first."
-            )
+    image_gen_tool = conn.execute(
+        sa.text("SELECT id FROM tool WHERE in_code_tool_id = 'ImageGenerationTool'")
+    ).fetchone()
 
-        # WebSearchTool is optional - may not be configured
-        web_search_tool = conn.execute(
-            sa.text("SELECT id FROM tool WHERE in_code_tool_id = 'WebSearchTool'")
-        ).fetchone()
+    if not image_gen_tool:
+        raise ValueError(
+            "ImageGenerationTool not found in database. Ensure tools migration has run first."
+        )
 
-        # Clear existing tool associations for persona 0
-        conn.execute(sa.text("DELETE FROM persona__tool WHERE persona_id = 0"))
+    # WebSearchTool is optional - may not be configured
+    web_search_tool = conn.execute(
+        sa.text("SELECT id FROM tool WHERE in_code_tool_id = 'WebSearchTool'")
+    ).fetchone()
 
-        # Add tools to the unified assistant
+    # Clear existing tool associations for persona 0
+    conn.execute(sa.text("DELETE FROM persona__tool WHERE persona_id = 0"))
+
+    # Add tools to the unified assistant
+    conn.execute(
+        sa.text(
+            """
+            INSERT INTO persona__tool (persona_id, tool_id)
+            VALUES (0, :tool_id)
+            ON CONFLICT DO NOTHING
+        """
+        ),
+        {"tool_id": search_tool[0]},
+    )
+
+    conn.execute(
+        sa.text(
+            """
+            INSERT INTO persona__tool (persona_id, tool_id)
+            VALUES (0, :tool_id)
+            ON CONFLICT DO NOTHING
+        """
+        ),
+        {"tool_id": image_gen_tool[0]},
+    )
+
+    if web_search_tool:
         conn.execute(
             sa.text(
                 """
@@ -190,191 +209,148 @@ def upgrade() -> None:
                 ON CONFLICT DO NOTHING
             """
             ),
-            {"tool_id": search_tool[0]},
+            {"tool_id": web_search_tool[0]},
         )
 
-        conn.execute(
-            sa.text(
-                """
-                INSERT INTO persona__tool (persona_id, tool_id)
-                VALUES (0, :tool_id)
-                ON CONFLICT DO NOTHING
+    # Step 4: Migrate existing chat sessions from all builtin assistants to unified assistant
+    conn.execute(
+        sa.text(
             """
-            ),
-            {"tool_id": image_gen_tool[0]},
+            UPDATE chat_session
+            SET persona_id = 0
+            WHERE persona_id IN (
+                SELECT id FROM persona WHERE builtin_persona = true AND id != 0
+            )
+        """
         )
+    )
 
-        if web_search_tool:
+    # Step 5: Migrate user preferences - remove references to all builtin assistants
+    # First, get all builtin assistant IDs (except 0)
+    builtin_assistants_result = conn.execute(
+        sa.text(
+            """
+            SELECT id FROM persona
+            WHERE builtin_persona = true AND id != 0
+        """
+        )
+    ).fetchall()
+    builtin_assistant_ids = [row[0] for row in builtin_assistants_result]
+
+    # Get all users with preferences
+    users_result = conn.execute(
+        sa.text(
+            """
+            SELECT id, chosen_assistants, visible_assistants,
+                   hidden_assistants, pinned_assistants
+            FROM "user"
+        """
+        )
+    ).fetchall()
+
+    for user_row in users_result:
+        user = UserRow(*user_row)
+        user_id: UUID = user.id
+        updates: dict[str, Any] = {}
+
+        # Remove all builtin assistants from chosen_assistants
+        if user.chosen_assistants:
+            new_chosen: list[int] = [
+                assistant_id
+                for assistant_id in user.chosen_assistants
+                if assistant_id not in builtin_assistant_ids
+            ]
+            if new_chosen != user.chosen_assistants:
+                updates["chosen_assistants"] = json.dumps(new_chosen)
+
+        # Remove all builtin assistants from visible_assistants
+        if user.visible_assistants:
+            new_visible: list[int] = [
+                assistant_id
+                for assistant_id in user.visible_assistants
+                if assistant_id not in builtin_assistant_ids
+            ]
+            if new_visible != user.visible_assistants:
+                updates["visible_assistants"] = json.dumps(new_visible)
+
+        # Add all builtin assistants to hidden_assistants
+        if user.hidden_assistants:
+            new_hidden: list[int] = list(user.hidden_assistants)
+            for old_id in builtin_assistant_ids:
+                if old_id not in new_hidden:
+                    new_hidden.append(old_id)
+            if new_hidden != user.hidden_assistants:
+                updates["hidden_assistants"] = json.dumps(new_hidden)
+        else:
+            updates["hidden_assistants"] = json.dumps(builtin_assistant_ids)
+
+        # Remove all builtin assistants from pinned_assistants
+        if user.pinned_assistants:
+            new_pinned: list[int] = [
+                assistant_id
+                for assistant_id in user.pinned_assistants
+                if assistant_id not in builtin_assistant_ids
+            ]
+            if new_pinned != user.pinned_assistants:
+                updates["pinned_assistants"] = json.dumps(new_pinned)
+
+        # Apply updates if any
+        if updates:
+            set_clause = ", ".join([f"{k} = :{k}" for k in updates.keys()])
+            updates["user_id"] = str(user_id)  # Convert UUID to string for SQL
             conn.execute(
-                sa.text(
-                    """
-                    INSERT INTO persona__tool (persona_id, tool_id)
-                    VALUES (0, :tool_id)
-                    ON CONFLICT DO NOTHING
-                """
-                ),
-                {"tool_id": web_search_tool[0]},
+                sa.text(f'UPDATE "user" SET {set_clause} WHERE id = :user_id'),
+                updates,
             )
 
-        # Step 4: Migrate existing chat sessions from all builtin assistants to unified assistant
-        conn.execute(
-            sa.text(
-                """
-                UPDATE chat_session
-                SET persona_id = 0
-                WHERE persona_id IN (
-                    SELECT id FROM persona WHERE builtin_persona = true AND id != 0
-                )
-            """
-            )
-        )
-
-        # Step 5: Migrate user preferences - remove references to all builtin assistants
-        # First, get all builtin assistant IDs (except 0)
-        builtin_assistants_result = conn.execute(
-            sa.text(
-                """
-                SELECT id FROM persona
-                WHERE builtin_persona = true AND id != 0
-            """
-            )
-        ).fetchall()
-        builtin_assistant_ids = [row[0] for row in builtin_assistants_result]
-
-        # Get all users with preferences
-        users_result = conn.execute(
-            sa.text(
-                """
-                SELECT id, chosen_assistants, visible_assistants,
-                       hidden_assistants, pinned_assistants
-                FROM "user"
-            """
-            )
-        ).fetchall()
-
-        for user_row in users_result:
-            user = UserRow(*user_row)
-            user_id: UUID = user.id
-            updates: dict[str, Any] = {}
-
-            # Remove all builtin assistants from chosen_assistants
-            if user.chosen_assistants:
-                new_chosen: list[int] = [
-                    assistant_id
-                    for assistant_id in user.chosen_assistants
-                    if assistant_id not in builtin_assistant_ids
-                ]
-                if new_chosen != user.chosen_assistants:
-                    updates["chosen_assistants"] = json.dumps(new_chosen)
-
-            # Remove all builtin assistants from visible_assistants
-            if user.visible_assistants:
-                new_visible: list[int] = [
-                    assistant_id
-                    for assistant_id in user.visible_assistants
-                    if assistant_id not in builtin_assistant_ids
-                ]
-                if new_visible != user.visible_assistants:
-                    updates["visible_assistants"] = json.dumps(new_visible)
-
-            # Add all builtin assistants to hidden_assistants
-            if user.hidden_assistants:
-                new_hidden: list[int] = list(user.hidden_assistants)
-                for old_id in builtin_assistant_ids:
-                    if old_id not in new_hidden:
-                        new_hidden.append(old_id)
-                if new_hidden != user.hidden_assistants:
-                    updates["hidden_assistants"] = json.dumps(new_hidden)
-            else:
-                updates["hidden_assistants"] = json.dumps(builtin_assistant_ids)
-
-            # Remove all builtin assistants from pinned_assistants
-            if user.pinned_assistants:
-                new_pinned: list[int] = [
-                    assistant_id
-                    for assistant_id in user.pinned_assistants
-                    if assistant_id not in builtin_assistant_ids
-                ]
-                if new_pinned != user.pinned_assistants:
-                    updates["pinned_assistants"] = json.dumps(new_pinned)
-
-            # Apply updates if any
-            if updates:
-                set_clause = ", ".join([f"{k} = :{k}" for k in updates.keys()])
-                updates["user_id"] = str(user_id)  # Convert UUID to string for SQL
-                conn.execute(
-                    sa.text(f'UPDATE "user" SET {set_clause} WHERE id = :user_id'),
-                    updates,
-                )
-
-        # Commit transaction
-        conn.execute(sa.text("COMMIT"))
-
-    except Exception as e:
-        # Rollback on error
-        conn.execute(sa.text("ROLLBACK"))
-        raise e
-
 
 def downgrade() -> None:
     conn = op.get_bind()
 
-    # Start transaction
-    conn.execute(sa.text("BEGIN"))
-
-    try:
-        # Only restore General (ID -1) and Art (ID -3) assistants
-        # Step 1: Keep Search assistant (ID 0) as default but restore original state
-        conn.execute(
-            sa.text(
-                """
-                UPDATE persona
-                SET is_default_persona = true,
-                    is_visible = true,
-                    deleted = false
-                WHERE id = 0
+    # Only restore General (ID -1) and Art (ID -3) assistants
+    # Step 1: Keep Search assistant (ID 0) as default but restore original state
+    conn.execute(
+        sa.text(
             """
-            )
+            UPDATE persona
+            SET is_default_persona = true,
+                is_visible = true,
+                deleted = false
+            WHERE id = 0
+        """
         )
+    )
 
-        # Step 2: Restore General assistant (ID -1)
-        conn.execute(
-            sa.text(
-                """
-                UPDATE persona
-                SET deleted = false,
-                    is_visible = true,
-                    is_default_persona = true
-                WHERE id = :general_assistant_id
+    # Step 2: Restore General assistant (ID -1)
+    conn.execute(
+        sa.text(
             """
-            ),
-            {"general_assistant_id": GENERAL_ASSISTANT_ID},
-        )
+            UPDATE persona
+            SET deleted = false,
+                is_visible = true,
+                is_default_persona = true
+            WHERE id = :general_assistant_id
+        """
+        ),
+        {"general_assistant_id": GENERAL_ASSISTANT_ID},
+    )
 
-        # Step 3: Restore Art assistant (ID -3)
-        conn.execute(
-            sa.text(
-                """
-                UPDATE persona
-                SET deleted = false,
-                    is_visible = true,
-                    is_default_persona = true
-                WHERE id = :art_assistant_id
+    # Step 3: Restore Art assistant (ID -3)
+    conn.execute(
+        sa.text(
             """
-            ),
-            {"art_assistant_id": ART_ASSISTANT_ID},
-        )
+            UPDATE persona
+            SET deleted = false,
+                is_visible = true,
+                is_default_persona = true
+            WHERE id = :art_assistant_id
+        """
+        ),
+        {"art_assistant_id": ART_ASSISTANT_ID},
+    )
 
-        # Note: We don't restore the original tool associations, names, or descriptions
-        # as those would require more complex logic to determine original state.
-        # We also cannot restore original chat session persona_ids as we don't
-        # have the original mappings.
-        # Other builtin assistants remain deleted as per the requirement.
-
-        # Commit transaction
-        conn.execute(sa.text("COMMIT"))
-
-    except Exception as e:
-        # Rollback on error
-        conn.execute(sa.text("ROLLBACK"))
-        raise e
+    # Note: We don't restore the original tool associations, names, or descriptions
+    # as those would require more complex logic to determine original state.
+    # We also cannot restore original chat session persona_ids as we don't
+    # have the original mappings.
+    # Other builtin assistants remain deleted as per the requirement.

backend/alembic/versions/5c3dca366b35_backend_driven_notification_details.py

@@ -0,0 +1,35 @@
+"""backend driven notification details
+
+Revision ID: 5c3dca366b35
+Revises: 9087b548dd69
+Create Date: 2026-01-06 16:03:11.413724
+
+"""
+
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision = "5c3dca366b35"
+down_revision = "9087b548dd69"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    op.add_column(
+        "notification",
+        sa.Column(
+            "title", sa.String(), nullable=False, server_default="New Notification"
+        ),
+    )
+    op.add_column(
+        "notification",
+        sa.Column("description", sa.String(), nullable=True, server_default=""),
+    )
+
+
+def downgrade() -> None:
+    op.drop_column("notification", "title")
+    op.drop_column("notification", "description")

backend/alembic/versions/5e6f7a8b9c0d_update_default_persona_prompt.py

@@ -0,0 +1,55 @@
+"""update_default_persona_prompt
+
+Revision ID: 5e6f7a8b9c0d
+Revises: 4f8a2b3c1d9e
+Create Date: 2025-11-30 12:00:00.000000
+
+"""
+
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision = "5e6f7a8b9c0d"
+down_revision = "4f8a2b3c1d9e"
+branch_labels = None
+depends_on = None
+
+
+DEFAULT_PERSONA_ID = 0
+
+# ruff: noqa: E501, W605 start
+DEFAULT_SYSTEM_PROMPT = """
+You are a highly capable, thoughtful, and precise assistant. Your goal is to deeply understand the user's intent, ask clarifying questions when needed, think step-by-step through complex problems, provide clear and accurate answers, and proactively anticipate helpful follow-up information. Always prioritize being truthful, nuanced, insightful, and efficient.
+
+The current date is [[CURRENT_DATETIME]].{citation_reminder_or_empty}
+
+# Response Style
+You use different text styles, bolding, emojis (sparingly), block quotes, and other formatting to make your responses more readable and engaging.
+You use proper Markdown and LaTeX to format your responses for math, scientific, and chemical formulas, symbols, etc.: '$$\\n[expression]\\n$$' for standalone cases and '\\( [expression] \\)' when inline.
+For code you prefer to use Markdown and specify the language.
+You can use horizontal rules (---) to separate sections of your responses.
+You can use Markdown tables to format your responses for data, lists, and other structured information.
+""".lstrip()
+# ruff: noqa: E501, W605 end
+
+
+def upgrade() -> None:
+    conn = op.get_bind()
+    conn.execute(
+        sa.text(
+            """
+            UPDATE persona
+            SET system_prompt = :system_prompt
+            WHERE id = :persona_id
+            """
+        ),
+        {"system_prompt": DEFAULT_SYSTEM_PROMPT, "persona_id": DEFAULT_PERSONA_ID},
+    )
+
+
+def downgrade() -> None:
+    # We don't revert the system prompt on downgrade since we don't know
+    # what the previous value was. The new prompt is a reasonable default.
+    pass

backend/alembic/versions/631fd2504136_add_approx_chunk_count_in_vespa_to_.py

@@ -0,0 +1,32 @@
+"""add approx_chunk_count_in_vespa to opensearch tenant migration
+
+Revision ID: 631fd2504136
+Revises: c7f2e1b4a9d3
+Create Date: 2026-02-18 21:07:52.831215
+
+"""
+
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision = "631fd2504136"
+down_revision = "c7f2e1b4a9d3"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    op.add_column(
+        "opensearch_tenant_migration_record",
+        sa.Column(
+            "approx_chunk_count_in_vespa",
+            sa.Integer(),
+            nullable=True,
+        ),
+    )
+
+
+def downgrade() -> None:
+    op.drop_column("opensearch_tenant_migration_record", "approx_chunk_count_in_vespa")

backend/alembic/versions/6436661d5b65_add_created_at_in_project_userfile.py

@@ -0,0 +1,44 @@
+"""add_created_at_in_project_userfile
+
+Revision ID: 6436661d5b65
+Revises: c7e9f4a3b2d1
+Create Date: 2025-11-24 11:50:24.536052
+
+"""
+
+from alembic import op
+import sqlalchemy as sa
+
+# revision identifiers, used by Alembic.
+revision = "6436661d5b65"
+down_revision = "c7e9f4a3b2d1"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    # Add created_at column to project__user_file table
+    op.add_column(
+        "project__user_file",
+        sa.Column(
+            "created_at",
+            sa.DateTime(timezone=True),
+            server_default=sa.text("now()"),
+            nullable=False,
+        ),
+    )
+    # Add composite index on (project_id, created_at DESC)
+    op.create_index(
+        "ix_project__user_file_project_id_created_at",
+        "project__user_file",
+        ["project_id", sa.text("created_at DESC")],
+    )
+
+
+def downgrade() -> None:
+    # Remove composite index on (project_id, created_at)
+    op.drop_index(
+        "ix_project__user_file_project_id_created_at", table_name="project__user_file"
+    )
+    # Remove created_at column from project__user_file table
+    op.drop_column("project__user_file", "created_at")

backend/alembic/versions/699221885109_nullify_default_task_prompt.py

@@ -0,0 +1,75 @@
+"""nullify_default_task_prompt
+
+Revision ID: 699221885109
+Revises: 7e490836d179
+Create Date: 2025-12-30 10:00:00.000000
+
+"""
+
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision = "699221885109"
+down_revision = "7e490836d179"
+branch_labels = None
+depends_on = None
+
+DEFAULT_PERSONA_ID = 0
+
+
+def upgrade() -> None:
+    # Make task_prompt column nullable
+    # Note: The model had nullable=True but the DB column was NOT NULL until this point
+    op.alter_column(
+        "persona",
+        "task_prompt",
+        nullable=True,
+    )
+
+    # Set task_prompt to NULL for the default persona
+    conn = op.get_bind()
+    conn.execute(
+        sa.text(
+            """
+            UPDATE persona
+            SET task_prompt = NULL
+            WHERE id = :persona_id
+            """
+        ),
+        {"persona_id": DEFAULT_PERSONA_ID},
+    )
+
+
+def downgrade() -> None:
+    # Restore task_prompt to empty string for the default persona
+    conn = op.get_bind()
+    conn.execute(
+        sa.text(
+            """
+            UPDATE persona
+            SET task_prompt = ''
+            WHERE id = :persona_id AND task_prompt IS NULL
+            """
+        ),
+        {"persona_id": DEFAULT_PERSONA_ID},
+    )
+
+    # Set any remaining NULL task_prompts to empty string before making non-nullable
+    conn.execute(
+        sa.text(
+            """
+            UPDATE persona
+            SET task_prompt = ''
+            WHERE task_prompt IS NULL
+            """
+        )
+    )
+
+    # Revert task_prompt column to not nullable
+    op.alter_column(
+        "persona",
+        "task_prompt",
+        nullable=False,
+    )

backend/alembic/versions/7206234e012a_add_image_generation_config_table.py

@@ -0,0 +1,54 @@
+"""add image generation config table
+
+Revision ID: 7206234e012a
+Revises: 699221885109
+Create Date: 2025-12-21 00:00:00.000000
+
+"""
+
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision = "7206234e012a"
+down_revision = "699221885109"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    op.create_table(
+        "image_generation_config",
+        sa.Column("image_provider_id", sa.String(), primary_key=True),
+        sa.Column("model_configuration_id", sa.Integer(), nullable=False),
+        sa.Column("is_default", sa.Boolean(), nullable=False),
+        sa.ForeignKeyConstraint(
+            ["model_configuration_id"],
+            ["model_configuration.id"],
+            ondelete="CASCADE",
+        ),
+    )
+    op.create_index(
+        "ix_image_generation_config_is_default",
+        "image_generation_config",
+        ["is_default"],
+        unique=False,
+    )
+    op.create_index(
+        "ix_image_generation_config_model_configuration_id",
+        "image_generation_config",
+        ["model_configuration_id"],
+        unique=False,
+    )
+
+
+def downgrade() -> None:
+    op.drop_index(
+        "ix_image_generation_config_model_configuration_id",
+        table_name="image_generation_config",
+    )
+    op.drop_index(
+        "ix_image_generation_config_is_default", table_name="image_generation_config"
+    )
+    op.drop_table("image_generation_config")

backend/alembic/versions/72aa7de2e5cf_make_processing_mode_default_all_caps.py

@@ -0,0 +1,45 @@
+"""make processing mode default all caps
+
+Revision ID: 72aa7de2e5cf
+Revises: 2020d417ec84
+Create Date: 2026-01-26 18:58:47.705253
+
+This migration fixes the ProcessingMode enum value mismatch:
+- SQLAlchemy's Enum with native_enum=False uses enum member NAMES as valid values
+- The original migration stored lowercase VALUES ('regular', 'file_system')
+- This converts existing data to uppercase NAMES ('REGULAR', 'FILE_SYSTEM')
+- Also drops any spurious native PostgreSQL enum type that may have been auto-created
+"""
+
+from alembic import op
+
+
+# revision identifiers, used by Alembic.
+revision = "72aa7de2e5cf"
+down_revision = "2020d417ec84"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    # Convert existing lowercase values to uppercase to match enum member names
+    op.execute(
+        "UPDATE connector_credential_pair SET processing_mode = 'REGULAR' "
+        "WHERE processing_mode = 'regular'"
+    )
+    op.execute(
+        "UPDATE connector_credential_pair SET processing_mode = 'FILE_SYSTEM' "
+        "WHERE processing_mode = 'file_system'"
+    )
+
+    # Update the server default to use uppercase
+    op.alter_column(
+        "connector_credential_pair",
+        "processing_mode",
+        server_default="REGULAR",
+    )
+
+
+def downgrade() -> None:
+    # State prior to this was broken, so we don't want to revert back to it
+    pass

backend/alembic/versions/73e9983e5091_add_search_query_table.py

@@ -0,0 +1,47 @@
+"""add_search_query_table
+
+Revision ID: 73e9983e5091
+Revises: d1b637d7050a
+Create Date: 2026-01-14 14:16:52.837489
+
+"""
+
+from alembic import op
+import sqlalchemy as sa
+from sqlalchemy.dialects import postgresql
+
+# revision identifiers, used by Alembic.
+revision = "73e9983e5091"
+down_revision = "d1b637d7050a"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    op.create_table(
+        "search_query",
+        sa.Column("id", postgresql.UUID(as_uuid=True), primary_key=True),
+        sa.Column(
+            "user_id",
+            postgresql.UUID(as_uuid=True),
+            sa.ForeignKey("user.id"),
+            nullable=False,
+        ),
+        sa.Column("query", sa.String(), nullable=False),
+        sa.Column("query_expansions", postgresql.ARRAY(sa.String()), nullable=True),
+        sa.Column(
+            "created_at",
+            sa.DateTime(timezone=True),
+            nullable=False,
+            server_default=sa.func.now(),
+        ),
+    )
+
+    op.create_index("ix_search_query_user_id", "search_query", ["user_id"])
+    op.create_index("ix_search_query_created_at", "search_query", ["created_at"])
+
+
+def downgrade() -> None:
+    op.drop_index("ix_search_query_created_at", table_name="search_query")
+    op.drop_index("ix_search_query_user_id", table_name="search_query")
+    op.drop_table("search_query")

backend/alembic/versions/776b3bbe9092_remove_remaining_enums.py

@@ -10,8 +10,7 @@ from alembic import op
 import sqlalchemy as sa
 
 from onyx.db.models import IndexModelStatus
-from onyx.context.search.enums import RecencyBiasSetting
-from onyx.context.search.enums import SearchType
+from onyx.context.search.enums import RecencyBiasSetting, SearchType
 
 # revision identifiers, used by Alembic.
 revision = "776b3bbe9092"

backend/alembic/versions/78ebc66946a0_remove_reranking_from_search_settings.py

@@ -0,0 +1,58 @@
+"""remove reranking from search_settings
+
+Revision ID: 78ebc66946a0
+Revises: 849b21c732f8
+Create Date: 2026-01-28
+
+"""
+
+from alembic import op
+import sqlalchemy as sa
+
+# revision identifiers, used by Alembic.
+revision = "78ebc66946a0"
+down_revision = "849b21c732f8"
+branch_labels: None = None
+depends_on: None = None
+
+
+def upgrade() -> None:
+    op.drop_column("search_settings", "disable_rerank_for_streaming")
+    op.drop_column("search_settings", "rerank_model_name")
+    op.drop_column("search_settings", "rerank_provider_type")
+    op.drop_column("search_settings", "rerank_api_key")
+    op.drop_column("search_settings", "rerank_api_url")
+    op.drop_column("search_settings", "num_rerank")
+
+
+def downgrade() -> None:
+    op.add_column(
+        "search_settings",
+        sa.Column(
+            "disable_rerank_for_streaming",
+            sa.Boolean(),
+            nullable=False,
+            server_default="false",
+        ),
+    )
+    op.add_column(
+        "search_settings", sa.Column("rerank_model_name", sa.String(), nullable=True)
+    )
+    op.add_column(
+        "search_settings", sa.Column("rerank_provider_type", sa.String(), nullable=True)
+    )
+    op.add_column(
+        "search_settings", sa.Column("rerank_api_key", sa.String(), nullable=True)
+    )
+    op.add_column(
+        "search_settings", sa.Column("rerank_api_url", sa.String(), nullable=True)
+    )
+    op.add_column(
+        "search_settings",
+        sa.Column(
+            "num_rerank",
+            sa.Integer(),
+            nullable=False,
+            server_default=str(20),
+        ),
+    )

backend/alembic/versions/7a70b7664e37_add_model_configuration_table.py

@@ -10,7 +10,7 @@ from alembic import op
 import sqlalchemy as sa
 from sqlalchemy.dialects import postgresql
 
-from onyx.llm.llm_provider_options import (
+from onyx.llm.well_known_providers.llm_provider_options import (
     fetch_model_names_for_provider_as_set,
     fetch_visible_model_names_for_provider_as_set,
 )

backend/alembic/versions/7bd55f264e1b_add_display_name_to_model_configuration.py

@@ -0,0 +1,27 @@
+"""Add display_name to model_configuration
+
+Revision ID: 7bd55f264e1b
+Revises: e8f0d2a38171
+Create Date: 2025-12-04
+
+"""
+
+from alembic import op
+import sqlalchemy as sa
+
+# revision identifiers, used by Alembic.
+revision = "7bd55f264e1b"
+down_revision = "e8f0d2a38171"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    op.add_column(
+        "model_configuration",
+        sa.Column("display_name", sa.String(), nullable=True),
+    )
+
+
+def downgrade() -> None:
+    op.drop_column("model_configuration", "display_name")

backend/alembic/versions/7e490836d179_nullify_default_system_prompt.py

@@ -0,0 +1,80 @@
+"""nullify_default_system_prompt
+
+Revision ID: 7e490836d179
+Revises: c1d2e3f4a5b6
+Create Date: 2025-12-29 16:54:36.635574
+
+"""
+
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision = "7e490836d179"
+down_revision = "c1d2e3f4a5b6"
+branch_labels = None
+depends_on = None
+
+
+# This is the default system prompt from the previous migration (87c52ec39f84)
+# ruff: noqa: E501, W605 start
+PREVIOUS_DEFAULT_SYSTEM_PROMPT = """
+You are a highly capable, thoughtful, and precise assistant. Your goal is to deeply understand the user's intent, ask clarifying questions when needed, think step-by-step through complex problems, provide clear and accurate answers, and proactively anticipate helpful follow-up information. Always prioritize being truthful, nuanced, insightful, and efficient.
+
+The current date is [[CURRENT_DATETIME]].[[CITATION_GUIDANCE]]
+
+# Response Style
+You use different text styles, bolding, emojis (sparingly), block quotes, and other formatting to make your responses more readable and engaging.
+You use proper Markdown and LaTeX to format your responses for math, scientific, and chemical formulas, symbols, etc.: '$$\\n[expression]\\n$$' for standalone cases and '\\( [expression] \\)' when inline.
+For code you prefer to use Markdown and specify the language.
+You can use horizontal rules (---) to separate sections of your responses.
+You can use Markdown tables to format your responses for data, lists, and other structured information.
+""".lstrip()
+# ruff: noqa: E501, W605 end
+
+
+def upgrade() -> None:
+    # Make system_prompt column nullable (model already has nullable=True but DB doesn't)
+    op.alter_column(
+        "persona",
+        "system_prompt",
+        nullable=True,
+    )
+
+    # Set system_prompt to NULL where it matches the previous default
+    conn = op.get_bind()
+    conn.execute(
+        sa.text(
+            """
+            UPDATE persona
+            SET system_prompt = NULL
+            WHERE system_prompt = :previous_default
+            """
+        ),
+        {"previous_default": PREVIOUS_DEFAULT_SYSTEM_PROMPT},
+    )
+
+
+def downgrade() -> None:
+    # Restore the default system prompt for personas that have NULL
+    # Note: This may restore the prompt to personas that originally had NULL
+    # before this migration, but there's no way to distinguish them
+    conn = op.get_bind()
+    conn.execute(
+        sa.text(
+            """
+            UPDATE persona
+            SET system_prompt = :previous_default
+            WHERE system_prompt IS NULL
+            """
+        ),
+        {"previous_default": PREVIOUS_DEFAULT_SYSTEM_PROMPT},
+    )
+
+    # Revert system_prompt column to not nullable
+    op.alter_column(
+        "persona",
+        "system_prompt",
+        nullable=False,
+    )

backend/alembic/versions/7ed603b64d5a_add_mcp_server_and_connection_config_.py

@@ -42,13 +42,13 @@ def upgrade() -> None:
         sa.Column(
             "created_at",
             sa.DateTime(timezone=True),
-            server_default=sa.text("now()"),  # type: ignore
+            server_default=sa.text("now()"),
             nullable=False,
         ),
         sa.Column(
             "updated_at",
             sa.DateTime(timezone=True),
-            server_default=sa.text("now()"),  # type: ignore
+            server_default=sa.text("now()"),
             nullable=False,
         ),
     )
@@ -63,13 +63,13 @@ def upgrade() -> None:
         sa.Column(
             "created_at",
             sa.DateTime(timezone=True),
-            server_default=sa.text("now()"),  # type: ignore
+            server_default=sa.text("now()"),
             nullable=False,
         ),
         sa.Column(
             "updated_at",
             sa.DateTime(timezone=True),
-            server_default=sa.text("now()"),  # type: ignore
+            server_default=sa.text("now()"),
             nullable=False,
         ),
         sa.ForeignKeyConstraint(

backend/alembic/versions/81c22b1e2e78_hierarchy_nodes_v1.py

@@ -0,0 +1,349 @@
+"""hierarchy_nodes_v1
+
+Revision ID: 81c22b1e2e78
+Revises: 72aa7de2e5cf
+Create Date: 2026-01-13 18:10:01.021451
+
+"""
+
+from alembic import op
+import sqlalchemy as sa
+from sqlalchemy.dialects import postgresql
+
+from onyx.configs.constants import DocumentSource
+
+
+# revision identifiers, used by Alembic.
+revision = "81c22b1e2e78"
+down_revision = "72aa7de2e5cf"
+branch_labels = None
+depends_on = None
+
+
+# Human-readable display names for each source
+SOURCE_DISPLAY_NAMES: dict[str, str] = {
+    "ingestion_api": "Ingestion API",
+    "slack": "Slack",
+    "web": "Web",
+    "google_drive": "Google Drive",
+    "gmail": "Gmail",
+    "requesttracker": "Request Tracker",
+    "github": "GitHub",
+    "gitbook": "GitBook",
+    "gitlab": "GitLab",
+    "guru": "Guru",
+    "bookstack": "BookStack",
+    "outline": "Outline",
+    "confluence": "Confluence",
+    "jira": "Jira",
+    "slab": "Slab",
+    "productboard": "Productboard",
+    "file": "File",
+    "coda": "Coda",
+    "notion": "Notion",
+    "zulip": "Zulip",
+    "linear": "Linear",
+    "hubspot": "HubSpot",
+    "document360": "Document360",
+    "gong": "Gong",
+    "google_sites": "Google Sites",
+    "zendesk": "Zendesk",
+    "loopio": "Loopio",
+    "dropbox": "Dropbox",
+    "sharepoint": "SharePoint",
+    "teams": "Teams",
+    "salesforce": "Salesforce",
+    "discourse": "Discourse",
+    "axero": "Axero",
+    "clickup": "ClickUp",
+    "mediawiki": "MediaWiki",
+    "wikipedia": "Wikipedia",
+    "asana": "Asana",
+    "s3": "S3",
+    "r2": "R2",
+    "google_cloud_storage": "Google Cloud Storage",
+    "oci_storage": "OCI Storage",
+    "xenforo": "XenForo",
+    "not_applicable": "Not Applicable",
+    "discord": "Discord",
+    "freshdesk": "Freshdesk",
+    "fireflies": "Fireflies",
+    "egnyte": "Egnyte",
+    "airtable": "Airtable",
+    "highspot": "Highspot",
+    "drupal_wiki": "Drupal Wiki",
+    "imap": "IMAP",
+    "bitbucket": "Bitbucket",
+    "testrail": "TestRail",
+    "mock_connector": "Mock Connector",
+    "user_file": "User File",
+}
+
+
+def upgrade() -> None:
+    # 1. Create hierarchy_node table
+    op.create_table(
+        "hierarchy_node",
+        sa.Column("id", sa.Integer(), nullable=False),
+        sa.Column("raw_node_id", sa.String(), nullable=False),
+        sa.Column("display_name", sa.String(), nullable=False),
+        sa.Column("link", sa.String(), nullable=True),
+        sa.Column("source", sa.String(), nullable=False),
+        sa.Column("node_type", sa.String(), nullable=False),
+        sa.Column("document_id", sa.String(), nullable=True),
+        sa.Column("parent_id", sa.Integer(), nullable=True),
+        # Permission fields - same pattern as Document table
+        sa.Column(
+            "external_user_emails",
+            postgresql.ARRAY(sa.String()),
+            nullable=True,
+        ),
+        sa.Column(
+            "external_user_group_ids",
+            postgresql.ARRAY(sa.String()),
+            nullable=True,
+        ),
+        sa.Column("is_public", sa.Boolean(), nullable=False, server_default="false"),
+        sa.PrimaryKeyConstraint("id"),
+        # When document is deleted, just unlink (node can exist without document)
+        sa.ForeignKeyConstraint(["document_id"], ["document.id"], ondelete="SET NULL"),
+        # When parent node is deleted, orphan children (cleanup via pruning)
+        sa.ForeignKeyConstraint(
+            ["parent_id"], ["hierarchy_node.id"], ondelete="SET NULL"
+        ),
+        sa.UniqueConstraint(
+            "raw_node_id", "source", name="uq_hierarchy_node_raw_id_source"
+        ),
+    )
+    op.create_index("ix_hierarchy_node_parent_id", "hierarchy_node", ["parent_id"])
+    op.create_index(
+        "ix_hierarchy_node_source_type", "hierarchy_node", ["source", "node_type"]
+    )
+
+    # Add partial unique index to ensure only one SOURCE-type node per source
+    # This prevents duplicate source root nodes from being created
+    # NOTE: node_type stores enum NAME ('SOURCE'), not value ('source')
+    op.execute(
+        sa.text(
+            """
+            CREATE UNIQUE INDEX uq_hierarchy_node_one_source_per_type
+            ON hierarchy_node (source)
+            WHERE node_type = 'SOURCE'
+            """
+        )
+    )
+
+    # 2. Create hierarchy_fetch_attempt table
+    op.create_table(
+        "hierarchy_fetch_attempt",
+        sa.Column("id", postgresql.UUID(as_uuid=True), nullable=False),
+        sa.Column("connector_credential_pair_id", sa.Integer(), nullable=False),
+        sa.Column("status", sa.String(), nullable=False),
+        sa.Column("nodes_fetched", sa.Integer(), nullable=True, server_default="0"),
+        sa.Column("nodes_updated", sa.Integer(), nullable=True, server_default="0"),
+        sa.Column("error_msg", sa.Text(), nullable=True),
+        sa.Column("full_exception_trace", sa.Text(), nullable=True),
+        sa.Column(
+            "time_created",
+            sa.DateTime(timezone=True),
+            server_default=sa.func.now(),
+            nullable=False,
+        ),
+        sa.Column("time_started", sa.DateTime(timezone=True), nullable=True),
+        sa.Column(
+            "time_updated",
+            sa.DateTime(timezone=True),
+            server_default=sa.func.now(),
+            nullable=False,
+        ),
+        sa.PrimaryKeyConstraint("id"),
+        sa.ForeignKeyConstraint(
+            ["connector_credential_pair_id"],
+            ["connector_credential_pair.id"],
+            ondelete="CASCADE",
+        ),
+    )
+    op.create_index(
+        "ix_hierarchy_fetch_attempt_status", "hierarchy_fetch_attempt", ["status"]
+    )
+    op.create_index(
+        "ix_hierarchy_fetch_attempt_time_created",
+        "hierarchy_fetch_attempt",
+        ["time_created"],
+    )
+    op.create_index(
+        "ix_hierarchy_fetch_attempt_cc_pair",
+        "hierarchy_fetch_attempt",
+        ["connector_credential_pair_id"],
+    )
+
+    # 3. Insert SOURCE-type hierarchy nodes for each DocumentSource
+    # We insert these so every existing document can have a parent hierarchy node
+    # NOTE: SQLAlchemy's Enum with native_enum=False stores the enum NAME (e.g., 'GOOGLE_DRIVE'),
+    # not the VALUE (e.g., 'google_drive'). We must use .name for source and node_type columns.
+    # SOURCE nodes are always public since they're just categorical roots.
+    for source in DocumentSource:
+        source_name = (
+            source.name
+        )  # e.g., 'GOOGLE_DRIVE' - what SQLAlchemy stores/expects
+        source_value = source.value  # e.g., 'google_drive' - the raw_node_id
+        display_name = SOURCE_DISPLAY_NAMES.get(
+            source_value, source_value.replace("_", " ").title()
+        )
+        op.execute(
+            sa.text(
+                """
+                INSERT INTO hierarchy_node (raw_node_id, display_name, source, node_type, parent_id, is_public)
+                VALUES (:raw_node_id, :display_name, :source, 'SOURCE', NULL, true)
+                ON CONFLICT (raw_node_id, source) DO NOTHING
+                """
+            ).bindparams(
+                raw_node_id=source_value,  # Use .value for raw_node_id (human-readable identifier)
+                display_name=display_name,
+                source=source_name,  # Use .name for source column (SQLAlchemy enum storage)
+            )
+        )
+
+    # 4. Add parent_hierarchy_node_id column to document table
+    op.add_column(
+        "document",
+        sa.Column("parent_hierarchy_node_id", sa.Integer(), nullable=True),
+    )
+    # When hierarchy node is deleted, just unlink the document (SET NULL)
+    op.create_foreign_key(
+        "fk_document_parent_hierarchy_node",
+        "document",
+        "hierarchy_node",
+        ["parent_hierarchy_node_id"],
+        ["id"],
+        ondelete="SET NULL",
+    )
+    op.create_index(
+        "ix_document_parent_hierarchy_node_id",
+        "document",
+        ["parent_hierarchy_node_id"],
+    )
+
+    # 5. Set all existing documents' parent_hierarchy_node_id to their source's SOURCE node
+    # For documents with multiple connectors, we pick one source deterministically (MIN connector_id)
+    # NOTE: Both connector.source and hierarchy_node.source store enum NAMEs (e.g., 'GOOGLE_DRIVE')
+    # because SQLAlchemy Enum(native_enum=False) uses the enum name for storage.
+    op.execute(
+        sa.text(
+            """
+            UPDATE document d
+            SET parent_hierarchy_node_id = hn.id
+            FROM (
+                -- Get the source for each document (pick MIN connector_id for determinism)
+                SELECT DISTINCT ON (dbcc.id)
+                    dbcc.id as doc_id,
+                    c.source as source
+                FROM document_by_connector_credential_pair dbcc
+                JOIN connector c ON dbcc.connector_id = c.id
+                ORDER BY dbcc.id, dbcc.connector_id
+            ) doc_source
+            JOIN hierarchy_node hn ON hn.source = doc_source.source AND hn.node_type = 'SOURCE'
+            WHERE d.id = doc_source.doc_id
+            """
+        )
+    )
+
+    # Create the persona__hierarchy_node association table
+    op.create_table(
+        "persona__hierarchy_node",
+        sa.Column("persona_id", sa.Integer(), nullable=False),
+        sa.Column("hierarchy_node_id", sa.Integer(), nullable=False),
+        sa.ForeignKeyConstraint(
+            ["persona_id"],
+            ["persona.id"],
+            ondelete="CASCADE",
+        ),
+        sa.ForeignKeyConstraint(
+            ["hierarchy_node_id"],
+            ["hierarchy_node.id"],
+            ondelete="CASCADE",
+        ),
+        sa.PrimaryKeyConstraint("persona_id", "hierarchy_node_id"),
+    )
+
+    # Add index for efficient lookups
+    op.create_index(
+        "ix_persona__hierarchy_node_hierarchy_node_id",
+        "persona__hierarchy_node",
+        ["hierarchy_node_id"],
+    )
+
+    # Create the persona__document association table for attaching individual
+    # documents directly to assistants
+    op.create_table(
+        "persona__document",
+        sa.Column("persona_id", sa.Integer(), nullable=False),
+        sa.Column("document_id", sa.String(), nullable=False),
+        sa.ForeignKeyConstraint(
+            ["persona_id"],
+            ["persona.id"],
+            ondelete="CASCADE",
+        ),
+        sa.ForeignKeyConstraint(
+            ["document_id"],
+            ["document.id"],
+            ondelete="CASCADE",
+        ),
+        sa.PrimaryKeyConstraint("persona_id", "document_id"),
+    )
+
+    # Add index for efficient lookups by document_id
+    op.create_index(
+        "ix_persona__document_document_id",
+        "persona__document",
+        ["document_id"],
+    )
+
+    # 6. Add last_time_hierarchy_fetch column to connector_credential_pair table
+    op.add_column(
+        "connector_credential_pair",
+        sa.Column(
+            "last_time_hierarchy_fetch", sa.DateTime(timezone=True), nullable=True
+        ),
+    )
+
+
+def downgrade() -> None:
+    # Remove last_time_hierarchy_fetch from connector_credential_pair
+    op.drop_column("connector_credential_pair", "last_time_hierarchy_fetch")
+
+    # Drop persona__document table
+    op.drop_index("ix_persona__document_document_id", table_name="persona__document")
+    op.drop_table("persona__document")
+
+    # Drop persona__hierarchy_node table
+    op.drop_index(
+        "ix_persona__hierarchy_node_hierarchy_node_id",
+        table_name="persona__hierarchy_node",
+    )
+    op.drop_table("persona__hierarchy_node")
+
+    # Remove parent_hierarchy_node_id from document
+    op.drop_index("ix_document_parent_hierarchy_node_id", table_name="document")
+    op.drop_constraint(
+        "fk_document_parent_hierarchy_node", "document", type_="foreignkey"
+    )
+    op.drop_column("document", "parent_hierarchy_node_id")
+
+    # Drop hierarchy_fetch_attempt table
+    op.drop_index(
+        "ix_hierarchy_fetch_attempt_cc_pair", table_name="hierarchy_fetch_attempt"
+    )
+    op.drop_index(
+        "ix_hierarchy_fetch_attempt_time_created", table_name="hierarchy_fetch_attempt"
+    )
+    op.drop_index(
+        "ix_hierarchy_fetch_attempt_status", table_name="hierarchy_fetch_attempt"
+    )
+    op.drop_table("hierarchy_fetch_attempt")
+
+    # Drop hierarchy_node table
+    op.drop_index("uq_hierarchy_node_one_source_per_type", table_name="hierarchy_node")
+    op.drop_index("ix_hierarchy_node_source_type", table_name="hierarchy_node")
+    op.drop_index("ix_hierarchy_node_parent_id", table_name="hierarchy_node")
+    op.drop_table("hierarchy_node")

backend/alembic/versions/8405ca81cc83_notifications_constraint.py

@@ -0,0 +1,49 @@
+"""notifications constraint, sort index, and cleanup old notifications
+
+Revision ID: 8405ca81cc83
+Revises: a3c1a7904cd0
+Create Date: 2026-01-07 16:43:44.855156
+
+"""
+
+from alembic import op
+
+
+# revision identifiers, used by Alembic.
+revision = "8405ca81cc83"
+down_revision = "a3c1a7904cd0"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    # Create unique index for notification deduplication.
+    # This enables atomic ON CONFLICT DO NOTHING inserts in batch_create_notifications.
+    #
+    # Uses COALESCE to handle NULL additional_data (NULLs are normally distinct
+    # in unique constraints, but we want NULL == NULL for deduplication).
+    # The '{}' represents an empty JSONB object as the NULL replacement.
+
+    # Clean up legacy notifications first
+    op.execute("DELETE FROM notification WHERE title = 'New Notification'")
+
+    op.execute(
+        """
+        CREATE UNIQUE INDEX IF NOT EXISTS ix_notification_user_type_data
+        ON notification (user_id, notif_type, COALESCE(additional_data, '{}'::jsonb))
+        """
+    )
+
+    # Create index for efficient notification sorting by user
+    # Covers: WHERE user_id = ? ORDER BY dismissed, first_shown DESC
+    op.execute(
+        """
+        CREATE INDEX IF NOT EXISTS ix_notification_user_sort
+        ON notification (user_id, dismissed, first_shown DESC)
+        """
+    )
+
+
+def downgrade() -> None:
+    op.execute("DROP INDEX IF EXISTS ix_notification_user_type_data")
+    op.execute("DROP INDEX IF EXISTS ix_notification_user_sort")

backend/alembic/versions/849b21c732f8_add_demo_data_enabled_to_build_session.py

@@ -0,0 +1,32 @@
+"""add demo_data_enabled to build_session
+
+Revision ID: 849b21c732f8
+Revises: 81c22b1e2e78
+Create Date: 2026-01-28 10:00:00.000000
+
+"""
+
+from alembic import op
+import sqlalchemy as sa
+
+# revision identifiers, used by Alembic.
+revision = "849b21c732f8"
+down_revision = "81c22b1e2e78"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    op.add_column(
+        "build_session",
+        sa.Column(
+            "demo_data_enabled",
+            sa.Boolean(),
+            nullable=False,
+            server_default=sa.text("true"),
+        ),
+    )
+
+
+def downgrade() -> None:
+    op.drop_column("build_session", "demo_data_enabled")

backend/alembic/versions/87c52ec39f84_update_default_system_prompt.py

@@ -0,0 +1,55 @@
+"""update_default_system_prompt
+
+Revision ID: 87c52ec39f84
+Revises: 7bd55f264e1b
+Create Date: 2025-12-05 15:54:06.002452
+
+"""
+
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision = "87c52ec39f84"
+down_revision = "7bd55f264e1b"
+branch_labels = None
+depends_on = None
+
+
+DEFAULT_PERSONA_ID = 0
+
+# ruff: noqa: E501, W605 start
+DEFAULT_SYSTEM_PROMPT = """
+You are a highly capable, thoughtful, and precise assistant. Your goal is to deeply understand the user's intent, ask clarifying questions when needed, think step-by-step through complex problems, provide clear and accurate answers, and proactively anticipate helpful follow-up information. Always prioritize being truthful, nuanced, insightful, and efficient.
+
+The current date is [[CURRENT_DATETIME]].[[CITATION_GUIDANCE]]
+
+# Response Style
+You use different text styles, bolding, emojis (sparingly), block quotes, and other formatting to make your responses more readable and engaging.
+You use proper Markdown and LaTeX to format your responses for math, scientific, and chemical formulas, symbols, etc.: '$$\\n[expression]\\n$$' for standalone cases and '\\( [expression] \\)' when inline.
+For code you prefer to use Markdown and specify the language.
+You can use horizontal rules (---) to separate sections of your responses.
+You can use Markdown tables to format your responses for data, lists, and other structured information.
+""".lstrip()
+# ruff: noqa: E501, W605 end
+
+
+def upgrade() -> None:
+    conn = op.get_bind()
+    conn.execute(
+        sa.text(
+            """
+            UPDATE persona
+            SET system_prompt = :system_prompt
+            WHERE id = :persona_id
+            """
+        ),
+        {"system_prompt": DEFAULT_SYSTEM_PROMPT, "persona_id": DEFAULT_PERSONA_ID},
+    )
+
+
+def downgrade() -> None:
+    # We don't revert the system prompt on downgrade since we don't know
+    # what the previous value was. The new prompt is a reasonable default.
+    pass

backend/alembic/versions/8b5ce697290e_add_discord_bot_tables.py

@@ -0,0 +1,116 @@
+"""Add Discord bot tables
+
+Revision ID: 8b5ce697290e
+Revises: a1b2c3d4e5f7
+Create Date: 2025-01-14
+
+"""
+
+from alembic import op
+import sqlalchemy as sa
+
+# revision identifiers, used by Alembic.
+revision = "8b5ce697290e"
+down_revision = "a1b2c3d4e5f7"
+branch_labels: None = None
+depends_on: None = None
+
+
+def upgrade() -> None:
+    # DiscordBotConfig (singleton table - one per tenant)
+    op.create_table(
+        "discord_bot_config",
+        sa.Column(
+            "id",
+            sa.String(),
+            primary_key=True,
+            server_default=sa.text("'SINGLETON'"),
+        ),
+        sa.Column("bot_token", sa.LargeBinary(), nullable=False),  # EncryptedString
+        sa.Column(
+            "created_at",
+            sa.DateTime(timezone=True),
+            server_default=sa.func.now(),
+            nullable=False,
+        ),
+        sa.CheckConstraint("id = 'SINGLETON'", name="ck_discord_bot_config_singleton"),
+    )
+
+    # DiscordGuildConfig
+    op.create_table(
+        "discord_guild_config",
+        sa.Column("id", sa.Integer(), primary_key=True),
+        sa.Column("guild_id", sa.BigInteger(), nullable=True, unique=True),
+        sa.Column("guild_name", sa.String(), nullable=True),
+        sa.Column("registration_key", sa.String(), nullable=False, unique=True),
+        sa.Column("registered_at", sa.DateTime(timezone=True), nullable=True),
+        sa.Column(
+            "default_persona_id",
+            sa.Integer(),
+            sa.ForeignKey("persona.id", ondelete="SET NULL"),
+            nullable=True,
+        ),
+        sa.Column(
+            "enabled", sa.Boolean(), server_default=sa.text("true"), nullable=False
+        ),
+    )
+
+    # DiscordChannelConfig
+    op.create_table(
+        "discord_channel_config",
+        sa.Column("id", sa.Integer(), primary_key=True),
+        sa.Column(
+            "guild_config_id",
+            sa.Integer(),
+            sa.ForeignKey("discord_guild_config.id", ondelete="CASCADE"),
+            nullable=False,
+        ),
+        sa.Column("channel_id", sa.BigInteger(), nullable=False),
+        sa.Column("channel_name", sa.String(), nullable=False),
+        sa.Column(
+            "channel_type",
+            sa.String(20),
+            server_default=sa.text("'text'"),
+            nullable=False,
+        ),
+        sa.Column(
+            "is_private",
+            sa.Boolean(),
+            server_default=sa.text("false"),
+            nullable=False,
+        ),
+        sa.Column(
+            "thread_only_mode",
+            sa.Boolean(),
+            server_default=sa.text("false"),
+            nullable=False,
+        ),
+        sa.Column(
+            "require_bot_invocation",
+            sa.Boolean(),
+            server_default=sa.text("true"),
+            nullable=False,
+        ),
+        sa.Column(
+            "persona_override_id",
+            sa.Integer(),
+            sa.ForeignKey("persona.id", ondelete="SET NULL"),
+            nullable=True,
+        ),
+        sa.Column(
+            "enabled", sa.Boolean(), server_default=sa.text("false"), nullable=False
+        ),
+    )
+
+    # Unique constraint: one config per channel per guild
+    op.create_unique_constraint(
+        "uq_discord_channel_guild_channel",
+        "discord_channel_config",
+        ["guild_config_id", "channel_id"],
+    )
+
+
+def downgrade() -> None:
+    op.drop_table("discord_channel_config")
+    op.drop_table("discord_guild_config")
+    op.drop_table("discord_bot_config")