feat(llm-provider): fetch litellm models (#8418)

Co-authored-by: Jamison Lahman <jamison@lahman.dev>

.github/workflows/deployment.yml

@@ -151,7 +151,7 @@ jobs:
           fetch-depth: 0
 
       - name: Setup uv
-        uses: astral-sh/setup-uv@5a095e7a2014a4212f075830d4f7277575a9d098 # ratchet:astral-sh/setup-uv@v7
+        uses: astral-sh/setup-uv@61cb8a9741eeb8a550a1b8544337180c0fc8476b # ratchet:astral-sh/setup-uv@v7
         with:
           version: "0.9.9"
           # NOTE: This isn't caching much and zizmor suggests this could be poisoned, so disable.

.github/workflows/post-merge-beta-cherry-pick.yml

@@ -70,7 +70,7 @@ jobs:
 
       - name: Install the latest version of uv
         if: steps.gate.outputs.should_cherrypick == 'true'
-        uses: astral-sh/setup-uv@5a095e7a2014a4212f075830d4f7277575a9d098 # ratchet:astral-sh/setup-uv@v7
+        uses: astral-sh/setup-uv@61cb8a9741eeb8a550a1b8544337180c0fc8476b # ratchet:astral-sh/setup-uv@v7
         with:
           enable-cache: false
           version: "0.9.9"

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

@@ -471,7 +471,7 @@ jobs:
 
       - name: Install the latest version of uv
         if: always()
-        uses: astral-sh/setup-uv@5a095e7a2014a4212f075830d4f7277575a9d098 # ratchet:astral-sh/setup-uv@v7
+        uses: astral-sh/setup-uv@61cb8a9741eeb8a550a1b8544337180c0fc8476b # ratchet:astral-sh/setup-uv@v7
         with:
           enable-cache: false
           version: "0.9.9"
@@ -710,7 +710,7 @@ jobs:
       pull-requests: write
     steps:
       - name: Download visual diff summaries
-        uses: actions/download-artifact@70fc10c6e5e1ce46ad2ea6f2b72d43f7d47b13c3
+        uses: actions/download-artifact@37930b1c2abaa49bbe596cd826c3c89aef350131
         with:
           pattern: screenshot-diff-summary-*
           path: summaries/

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

@@ -28,7 +28,7 @@ jobs:
         with:
           python-version: "3.11"
       - name: Setup Terraform
-        uses: hashicorp/setup-terraform@5e8dbf3c6d9deaf4193ca7a8fb23f2ac83bb6c85 # ratchet:hashicorp/setup-terraform@v4.0.0
+        uses: hashicorp/setup-terraform@b9cd54a3c349d3f38e8881555d616ced269862dd # ratchet:hashicorp/setup-terraform@v3
       - name: Setup node
         uses: actions/setup-node@6044e13b5dc448c55e2357c09f80417699197238 # ratchet:actions/setup-node@v6
         with: # zizmor: ignore[cache-poisoning]

.github/workflows/release-devtools.yml

@@ -26,7 +26,7 @@ jobs:
       - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # ratchet:actions/checkout@v6
         with:
           persist-credentials: false
-      - uses: astral-sh/setup-uv@5a095e7a2014a4212f075830d4f7277575a9d098 # ratchet:astral-sh/setup-uv@v7
+      - uses: astral-sh/setup-uv@61cb8a9741eeb8a550a1b8544337180c0fc8476b # ratchet:astral-sh/setup-uv@v7
         with:
           enable-cache: false
           version: "0.9.9"

.github/workflows/storybook-deploy.yml

@@ -1,69 +0,0 @@
-name: Storybook Deploy
-env:
-  VERCEL_ORG_ID: ${{ secrets.VERCEL_ORG_ID }}
-  VERCEL_PROJECT_ID: prj_sG49mVsA25UsxIPhN2pmBJlikJZM
-  VERCEL_CLI: vercel@50.14.1
-  VERCEL_TOKEN: ${{ secrets.VERCEL_TOKEN }}
-
-concurrency:
-  group: storybook-deploy-production
-  cancel-in-progress: true
-
-on:
-  workflow_dispatch:
-  push:
-    branches:
-      - main
-    paths:
-      - "web/lib/opal/**"
-      - "web/src/refresh-components/**"
-      - "web/.storybook/**"
-      - "web/package.json"
-      - "web/package-lock.json"
-permissions:
-  contents: read
-jobs:
-  Deploy-Storybook:
-    runs-on: ubuntu-latest
-    timeout-minutes: 30
-    steps:
-      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # ratchet:actions/checkout@v4
-        with:
-          persist-credentials: false
-
-      - name: Setup node
-        uses: actions/setup-node@6044e13b5dc448c55e2357c09f80417699197238 # ratchet:actions/setup-node@v4
-        with:
-          node-version: 22
-          cache: "npm"
-          cache-dependency-path: ./web/package-lock.json
-
-      - name: Install dependencies
-        working-directory: web
-        run: npm ci
-
-      - name: Build Storybook
-        working-directory: web
-        run: npm run storybook:build
-
-      - name: Deploy to Vercel (Production)
-        working-directory: web
-        run: npx --yes "$VERCEL_CLI" deploy storybook-static/ --prod --yes --token="$VERCEL_TOKEN"
-
-  notify-slack-on-failure:
-    needs: Deploy-Storybook
-    if: always() && needs.Deploy-Storybook.result == 'failure'
-    runs-on: ubuntu-latest
-    timeout-minutes: 10
-    steps:
-      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # ratchet:actions/checkout@v4
-        with:
-          persist-credentials: false
-          sparse-checkout: .github/actions/slack-notify
-
-      - name: Send Slack notification
-        uses: ./.github/actions/slack-notify
-        with:
-          webhook-url: ${{ secrets.MONITOR_DEPLOYMENTS_WEBHOOK }}
-          failed-jobs: "• Deploy-Storybook"
-          title: "🚨 Storybook Deploy Failed"

.github/workflows/zizmor.yml

@@ -24,7 +24,7 @@ jobs:
           persist-credentials: false
 
       - name: Install the latest version of uv
-        uses: astral-sh/setup-uv@5a095e7a2014a4212f075830d4f7277575a9d098 # ratchet:astral-sh/setup-uv@v7
+        uses: astral-sh/setup-uv@61cb8a9741eeb8a550a1b8544337180c0fc8476b # ratchet:astral-sh/setup-uv@v7
         with:
           enable-cache: false
           version: "0.9.9"

.vscode/env_template.txt

@@ -7,9 +7,6 @@
 
 
 AUTH_TYPE=basic
-# Recommended for basic auth - used for signing password reset and verification tokens
-# Generate a secure value with: openssl rand -hex 32
-USER_AUTH_SECRET=""
 DEV_MODE=true
 
 

backend/Dockerfile

@@ -46,9 +46,7 @@ RUN apt-get update && \
         pkg-config \
         gcc \
         nano \
-        vim \
-        libjemalloc2 \
-        && \
+        vim && \
     rm -rf /var/lib/apt/lists/* && \
     apt-get clean
 
@@ -143,7 +141,6 @@ 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
 COPY --chown=onyx:onyx ./scripts/setup_craft_templates.sh /app/scripts/setup_craft_templates.sh
-COPY --chown=onyx:onyx ./scripts/reencrypt_secrets.py /app/scripts/reencrypt_secrets.py
 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
@@ -167,13 +164,6 @@ ENV PYTHONPATH=/app
 ARG ONYX_VERSION=0.0.0-dev
 ENV ONYX_VERSION=${ONYX_VERSION}
 
-# Use jemalloc instead of glibc malloc to reduce memory fragmentation
-# in long-running Python processes (API server, Celery workers).
-# The soname is architecture-independent; the dynamic linker resolves
-# the correct path from standard library directories.
-# Placed after all RUN steps so build-time processes are unaffected.
-ENV LD_PRELOAD=libjemalloc.so.2
-
 # Default command which does nothing
 # This container is used by api server and background which specify their own CMD
 CMD ["tail", "-f", "/dev/null"]

backend/alembic/versions/27fb147a843f_add_timestamps_to_user_table.py

@@ -1,43 +0,0 @@
-"""add timestamps to user table
-
-Revision ID: 27fb147a843f
-Revises: a3b8d9e2f1c4
-Create Date: 2026-03-08 17:18:40.828644
-
-"""
-
-from alembic import op
-import sqlalchemy as sa
-
-
-# revision identifiers, used by Alembic.
-revision = "27fb147a843f"
-down_revision = "a3b8d9e2f1c4"
-branch_labels = None
-depends_on = None
-
-
-def upgrade() -> None:
-    op.add_column(
-        "user",
-        sa.Column(
-            "created_at",
-            sa.DateTime(timezone=True),
-            server_default=sa.func.now(),
-            nullable=False,
-        ),
-    )
-    op.add_column(
-        "user",
-        sa.Column(
-            "updated_at",
-            sa.DateTime(timezone=True),
-            server_default=sa.func.now(),
-            nullable=False,
-        ),
-    )
-
-
-def downgrade() -> None:
-    op.drop_column("user", "updated_at")
-    op.drop_column("user", "created_at")

backend/alembic/versions/b5c4d7e8f9a1_add_hierarchy_node_cc_pair_table.py

@@ -1,51 +0,0 @@
-"""add hierarchy_node_by_connector_credential_pair table
-
-Revision ID: b5c4d7e8f9a1
-Revises: a3b8d9e2f1c4
-Create Date: 2026-03-04
-
-"""
-
-import sqlalchemy as sa
-from alembic import op
-
-revision = "b5c4d7e8f9a1"
-down_revision = "a3b8d9e2f1c4"
-branch_labels = None
-depends_on = None
-
-
-def upgrade() -> None:
-    op.create_table(
-        "hierarchy_node_by_connector_credential_pair",
-        sa.Column("hierarchy_node_id", sa.Integer(), nullable=False),
-        sa.Column("connector_id", sa.Integer(), nullable=False),
-        sa.Column("credential_id", sa.Integer(), nullable=False),
-        sa.ForeignKeyConstraint(
-            ["hierarchy_node_id"],
-            ["hierarchy_node.id"],
-            ondelete="CASCADE",
-        ),
-        sa.ForeignKeyConstraint(
-            ["connector_id", "credential_id"],
-            [
-                "connector_credential_pair.connector_id",
-                "connector_credential_pair.credential_id",
-            ],
-            ondelete="CASCADE",
-        ),
-        sa.PrimaryKeyConstraint("hierarchy_node_id", "connector_id", "credential_id"),
-    )
-    op.create_index(
-        "ix_hierarchy_node_cc_pair_connector_credential",
-        "hierarchy_node_by_connector_credential_pair",
-        ["connector_id", "credential_id"],
-    )
-
-
-def downgrade() -> None:
-    op.drop_index(
-        "ix_hierarchy_node_cc_pair_connector_credential",
-        table_name="hierarchy_node_by_connector_credential_pair",
-    )
-    op.drop_table("hierarchy_node_by_connector_credential_pair")

backend/alembic_tenants/versions/3b9f09038764_add_read_only_kg_user.py

@@ -11,6 +11,7 @@ from sqlalchemy import text
 from alembic import op
 from onyx.configs.app_configs import DB_READONLY_PASSWORD
 from onyx.configs.app_configs import DB_READONLY_USER
+from shared_configs.configs import MULTI_TENANT
 
 
 # revision identifiers, used by Alembic.
@@ -21,52 +22,59 @@ depends_on = None
 
 
 def upgrade() -> None:
-    # Enable pg_trgm extension if not already enabled
-    op.execute("CREATE EXTENSION IF NOT EXISTS pg_trgm")
+    if MULTI_TENANT:
 
-    # Create the read-only db user if it does not already exist.
-    if not (DB_READONLY_USER and DB_READONLY_PASSWORD):
-        raise Exception("DB_READONLY_USER or DB_READONLY_PASSWORD is not set")
+        # Enable pg_trgm extension if not already enabled
+        op.execute("CREATE EXTENSION IF NOT EXISTS pg_trgm")
 
-    op.execute(
-        text(
-            f"""
-            DO $$
-            BEGIN
-                -- Check if the read-only user already exists
-                IF NOT EXISTS (SELECT FROM pg_catalog.pg_roles WHERE rolname = '{DB_READONLY_USER}') THEN
-                    -- Create the read-only user with the specified password
-                    EXECUTE format('CREATE USER %I WITH PASSWORD %L', '{DB_READONLY_USER}', '{DB_READONLY_PASSWORD}');
-                    -- First revoke all privileges to ensure a clean slate
-                    EXECUTE format('REVOKE ALL ON DATABASE %I FROM %I', current_database(), '{DB_READONLY_USER}');
-                    -- Grant only the CONNECT privilege to allow the user to connect to the database
-                    -- but not perform any operations without additional specific grants
-                    EXECUTE format('GRANT CONNECT ON DATABASE %I TO %I', current_database(), '{DB_READONLY_USER}');
-                END IF;
-            END
-            $$;
-            """
+        # Create read-only db user here only in multi-tenant mode. For single-tenant mode,
+        # the user is created in the standard migration.
+        if not (DB_READONLY_USER and DB_READONLY_PASSWORD):
+            raise Exception("DB_READONLY_USER or DB_READONLY_PASSWORD is not set")
+
+        op.execute(
+            text(
+                f"""
+                DO $$
+                BEGIN
+                    -- Check if the read-only user already exists
+                    IF NOT EXISTS (SELECT FROM pg_catalog.pg_roles WHERE rolname = '{DB_READONLY_USER}') THEN
+                        -- Create the read-only user with the specified password
+                        EXECUTE format('CREATE USER %I WITH PASSWORD %L', '{DB_READONLY_USER}', '{DB_READONLY_PASSWORD}');
+                        -- First revoke all privileges to ensure a clean slate
+                        EXECUTE format('REVOKE ALL ON DATABASE %I FROM %I', current_database(), '{DB_READONLY_USER}');
+                        -- Grant only the CONNECT privilege to allow the user to connect to the database
+                        -- but not perform any operations without additional specific grants
+                        EXECUTE format('GRANT CONNECT ON DATABASE %I TO %I', current_database(), '{DB_READONLY_USER}');
+                    END IF;
+                END
+                $$;
+                """
+            )
         )
-    )
 
 
 def downgrade() -> None:
-    op.execute(
-        text(
-            f"""
-        DO $$
-        BEGIN
-            IF EXISTS (SELECT FROM pg_catalog.pg_roles WHERE rolname = '{DB_READONLY_USER}') THEN
-                -- First revoke all privileges from the database
-                EXECUTE format('REVOKE ALL ON DATABASE %I FROM %I', current_database(), '{DB_READONLY_USER}');
-                -- Then revoke all privileges from the public schema
-                EXECUTE format('REVOKE ALL ON SCHEMA public FROM %I', '{DB_READONLY_USER}');
-                -- Then drop the user
-                EXECUTE format('DROP USER %I', '{DB_READONLY_USER}');
-            END IF;
-        END
-        $$;
-    """
+    if MULTI_TENANT:
+        # Drop read-only db user here only in single tenant mode. For multi-tenant mode,
+        # the user is dropped in the alembic_tenants migration.
+
+        op.execute(
+            text(
+                f"""
+            DO $$
+            BEGIN
+                IF EXISTS (SELECT FROM pg_catalog.pg_roles WHERE rolname = '{DB_READONLY_USER}') THEN
+                    -- First revoke all privileges from the database
+                    EXECUTE format('REVOKE ALL ON DATABASE %I FROM %I', current_database(), '{DB_READONLY_USER}');
+                    -- Then revoke all privileges from the public schema
+                    EXECUTE format('REVOKE ALL ON SCHEMA public FROM %I', '{DB_READONLY_USER}');
+                    -- Then drop the user
+                    EXECUTE format('DROP USER %I', '{DB_READONLY_USER}');
+                END IF;
+            END
+            $$;
+        """
+            )
         )
-    )
-    op.execute(text("DROP EXTENSION IF EXISTS pg_trgm"))
+        op.execute(text("DROP EXTENSION IF EXISTS pg_trgm"))

backend/ee/onyx/access/access.py

@@ -9,15 +9,12 @@ from onyx.access.access import (
     _get_access_for_documents as get_access_for_documents_without_groups,
 )
 from onyx.access.access import _get_acl_for_user as get_acl_for_user_without_groups
-from onyx.access.access import collect_user_file_access
 from onyx.access.models import DocumentAccess
 from onyx.access.utils import prefix_external_group
 from onyx.access.utils import prefix_user_group
 from onyx.db.document import get_document_sources
 from onyx.db.document import get_documents_by_ids
 from onyx.db.models import User
-from onyx.db.models import UserFile
-from onyx.db.user_file import fetch_user_files_with_access_relationships
 from onyx.utils.logger import setup_logger
 
 
@@ -119,68 +116,6 @@ def _get_access_for_documents(
     return access_map
 
 
-def _collect_user_file_group_names(user_file: UserFile) -> set[str]:
-    """Extract user-group names from the already-loaded Persona.groups
-    relationships on a UserFile (skipping deleted personas)."""
-    groups: set[str] = set()
-    for persona in user_file.assistants:
-        if persona.deleted:
-            continue
-        for group in persona.groups:
-            groups.add(group.name)
-    return groups
-
-
-def get_access_for_user_files_impl(
-    user_file_ids: list[str],
-    db_session: Session,
-) -> dict[str, DocumentAccess]:
-    """EE version: extends the MIT user file ACL with user group names
-    from personas shared via user groups.
-
-    Uses a single DB query (via fetch_user_files_with_access_relationships)
-    that eagerly loads both the MIT-needed and EE-needed relationships.
-
-    NOTE: is imported in onyx.access.access by `fetch_versioned_implementation`
-    DO NOT REMOVE."""
-    user_files = fetch_user_files_with_access_relationships(
-        user_file_ids, db_session, eager_load_groups=True
-    )
-    return build_access_for_user_files_impl(user_files)
-
-
-def build_access_for_user_files_impl(
-    user_files: list[UserFile],
-) -> dict[str, DocumentAccess]:
-    """EE version: works on pre-loaded UserFile objects.
-    Expects Persona.groups to be eagerly loaded.
-
-    NOTE: is imported in onyx.access.access by `fetch_versioned_implementation`
-    DO NOT REMOVE."""
-    result: dict[str, DocumentAccess] = {}
-    for user_file in user_files:
-        if user_file.user is None:
-            result[str(user_file.id)] = DocumentAccess.build(
-                user_emails=[],
-                user_groups=[],
-                is_public=True,
-                external_user_emails=[],
-                external_user_group_ids=[],
-            )
-            continue
-
-        emails, is_public = collect_user_file_access(user_file)
-        group_names = _collect_user_file_group_names(user_file)
-        result[str(user_file.id)] = DocumentAccess.build(
-            user_emails=list(emails),
-            user_groups=list(group_names),
-            is_public=is_public,
-            external_user_emails=[],
-            external_user_group_ids=[],
-        )
-    return result
-
-
 def _get_acl_for_user(user: User, db_session: Session) -> set[str]:
     """Returns a list of ACL entries that the user has access to. This is meant to be
     used downstream to filter out documents that the user does not have access to. The

backend/ee/onyx/auth/users.py

@@ -1,4 +1,3 @@
-import os
 from datetime import datetime
 
 import jwt
@@ -21,13 +20,7 @@ logger = setup_logger()
 
 
 def verify_auth_setting() -> None:
-    # All the Auth flows are valid for EE version, but warn about deprecated 'disabled'
-    raw_auth_type = (os.environ.get("AUTH_TYPE") or "").lower()
-    if raw_auth_type == "disabled":
-        logger.warning(
-            "AUTH_TYPE='disabled' is no longer supported. "
-            "Using 'basic' instead. Please update your configuration."
-        )
+    # All the Auth flows are valid for EE version
     logger.notice(f"Using Auth Type: {AUTH_TYPE.value}")
 
 

backend/ee/onyx/db/hierarchy.py

@@ -18,7 +18,7 @@ from onyx.db.models import HierarchyNode
 
 
 def _build_hierarchy_access_filter(
-    user_email: str,
+    user_email: str | None,
     external_group_ids: list[str],
 ) -> ColumnElement[bool]:
     """Build SQLAlchemy filter for hierarchy node access.
@@ -43,7 +43,7 @@ def _build_hierarchy_access_filter(
 def _get_accessible_hierarchy_nodes_for_source(
     db_session: Session,
     source: DocumentSource,
-    user_email: str,
+    user_email: str | None,
     external_group_ids: list[str],
 ) -> list[HierarchyNode]:
     """

backend/ee/onyx/db/persona.py

@@ -7,7 +7,6 @@ from onyx.db.models import Persona
 from onyx.db.models import Persona__User
 from onyx.db.models import Persona__UserGroup
 from onyx.db.notification import create_notification
-from onyx.db.persona import mark_persona_user_files_for_sync
 from onyx.server.features.persona.models import PersonaSharedNotificationData
 
 
@@ -27,9 +26,7 @@ def update_persona_access(
 
     NOTE: Callers are responsible for committing."""
 
-    needs_sync = False
     if is_public is not None:
-        needs_sync = True
         persona = db_session.query(Persona).filter(Persona.id == persona_id).first()
         if persona:
             persona.is_public = is_public
@@ -38,7 +35,6 @@ def update_persona_access(
     # and a non-empty list means "replace with these shares".
 
     if user_ids is not None:
-        needs_sync = True
         db_session.query(Persona__User).filter(
             Persona__User.persona_id == persona_id
         ).delete(synchronize_session="fetch")
@@ -58,7 +54,6 @@ def update_persona_access(
                 )
 
     if group_ids is not None:
-        needs_sync = True
         db_session.query(Persona__UserGroup).filter(
             Persona__UserGroup.persona_id == persona_id
         ).delete(synchronize_session="fetch")
@@ -68,7 +63,3 @@ def update_persona_access(
             db_session.add(
                 Persona__UserGroup(persona_id=persona_id, user_group_id=group_id)
             )
-
-    # When sharing changes, user file ACLs need to be updated in the vector DB
-    if needs_sync:
-        mark_persona_user_files_for_sync(persona_id, db_session)

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

@@ -68,7 +68,6 @@ def get_external_access_for_raw_gdrive_file(
     company_domain: str,
     retriever_drive_service: GoogleDriveService | None,
     admin_drive_service: GoogleDriveService,
-    fallback_user_email: str,
     add_prefix: bool = False,
 ) -> ExternalAccess:
     """
@@ -80,11 +79,6 @@ def get_external_access_for_raw_gdrive_file(
                 set add_prefix to True so group IDs are prefixed with the source type.
                 When invoked from doc_sync (permission sync), use the default (False)
                 since upsert_document_external_perms handles prefixing.
-    fallback_user_email: When we cannot retrieve any permission info for a file
-                (e.g. externally-owned files where the API returns no permissions
-                and permissions.list returns 403), fall back to granting access
-                to this user. This is typically the impersonated org user whose
-                drive contained the file.
     """
     doc_id = file.get("id")
     if not doc_id:
@@ -123,26 +117,6 @@ def get_external_access_for_raw_gdrive_file(
                 [permissions_list, backup_permissions_list]
             )
 
-    # For externally-owned files, the Drive API may return no permissions
-    # and permissions.list may return 403. In this case, fall back to
-    # granting access to the user who found the file in their drive.
-    # Note, even if other users also have access to this file,
-    # they will not be granted access in Onyx.
-    # We check permissions_list (the final result after all fetch attempts)
-    # rather than the raw fields, because permission_ids may be present
-    # but the actual fetch can still return empty due to a 403.
-    if not permissions_list:
-        logger.info(
-            f"No permission info available for file {doc_id} "
-            f"(likely owned by a user outside of your organization). "
-            f"Falling back to granting access to retriever user: {fallback_user_email}"
-        )
-        return ExternalAccess(
-            external_user_emails={fallback_user_email},
-            external_user_group_ids=set(),
-            is_public=False,
-        )
-
     folder_ids_to_inherit_permissions_from: set[str] = set()
     user_emails: set[str] = set()
     group_emails: set[str] = set()

backend/ee/onyx/utils/encryption.py

@@ -14,91 +14,67 @@ from onyx.utils.variable_functionality import fetch_versioned_implementation
 logger = setup_logger()
 
 
-@lru_cache(maxsize=2)
+@lru_cache(maxsize=1)
 def _get_trimmed_key(key: str) -> bytes:
     encoded_key = key.encode()
     key_length = len(encoded_key)
     if key_length < 16:
         raise RuntimeError("Invalid ENCRYPTION_KEY_SECRET - too short")
+    elif key_length > 32:
+        key = key[:32]
+    elif key_length not in (16, 24, 32):
+        valid_lengths = [16, 24, 32]
+        key = key[: min(valid_lengths, key=lambda x: abs(x - key_length))]
 
-    # Trim to the largest valid AES key size that fits
-    valid_lengths = [32, 24, 16]
-    for size in valid_lengths:
-        if key_length >= size:
-            return encoded_key[:size]
-
-    raise AssertionError("unreachable")
+    return encoded_key
 
 
-def _encrypt_string(input_str: str, key: str | None = None) -> bytes:
-    effective_key = key if key is not None else ENCRYPTION_KEY_SECRET
-    if not effective_key:
+def _encrypt_string(input_str: str) -> bytes:
+    if not ENCRYPTION_KEY_SECRET:
         return input_str.encode()
 
-    trimmed = _get_trimmed_key(effective_key)
+    key = _get_trimmed_key(ENCRYPTION_KEY_SECRET)
     iv = urandom(16)
     padder = padding.PKCS7(algorithms.AES.block_size).padder()
     padded_data = padder.update(input_str.encode()) + padder.finalize()
 
-    cipher = Cipher(algorithms.AES(trimmed), modes.CBC(iv), backend=default_backend())
+    cipher = Cipher(algorithms.AES(key), modes.CBC(iv), backend=default_backend())
     encryptor = cipher.encryptor()
     encrypted_data = encryptor.update(padded_data) + encryptor.finalize()
 
     return iv + encrypted_data
 
 
-def _decrypt_bytes(input_bytes: bytes, key: str | None = None) -> str:
-    effective_key = key if key is not None else ENCRYPTION_KEY_SECRET
-    if not effective_key:
+def _decrypt_bytes(input_bytes: bytes) -> str:
+    if not ENCRYPTION_KEY_SECRET:
         return input_bytes.decode()
 
-    trimmed = _get_trimmed_key(effective_key)
-    try:
-        iv = input_bytes[:16]
-        encrypted_data = input_bytes[16:]
+    key = _get_trimmed_key(ENCRYPTION_KEY_SECRET)
+    iv = input_bytes[:16]
+    encrypted_data = input_bytes[16:]
 
-        cipher = Cipher(
-            algorithms.AES(trimmed), modes.CBC(iv), backend=default_backend()
-        )
-        decryptor = cipher.decryptor()
-        decrypted_padded_data = decryptor.update(encrypted_data) + decryptor.finalize()
+    cipher = Cipher(algorithms.AES(key), modes.CBC(iv), backend=default_backend())
+    decryptor = cipher.decryptor()
+    decrypted_padded_data = decryptor.update(encrypted_data) + decryptor.finalize()
 
-        unpadder = padding.PKCS7(algorithms.AES.block_size).unpadder()
-        decrypted_data = unpadder.update(decrypted_padded_data) + unpadder.finalize()
+    unpadder = padding.PKCS7(algorithms.AES.block_size).unpadder()
+    decrypted_data = unpadder.update(decrypted_padded_data) + unpadder.finalize()
 
-        return decrypted_data.decode()
-    except (ValueError, UnicodeDecodeError):
-        if key is not None:
-            # Explicit key was provided — don't fall back silently
-            raise
-        # Read path: attempt raw UTF-8 decode as a fallback for legacy data.
-        # Does NOT handle data encrypted with a different key — that
-        # ciphertext is not valid UTF-8 and will raise below.
-        logger.warning(
-            "AES decryption failed — falling back to raw decode. "
-            "Run the re-encrypt secrets script to rotate to the current key."
-        )
-        try:
-            return input_bytes.decode()
-        except UnicodeDecodeError:
-            raise ValueError(
-                "Data is not valid UTF-8 — likely encrypted with a different key. "
-                "Run the re-encrypt secrets script to rotate to the current key."
-            ) from None
+    return decrypted_data.decode()
 
 
-def encrypt_string_to_bytes(input_str: str, key: str | None = None) -> bytes:
+def encrypt_string_to_bytes(input_str: str) -> bytes:
     versioned_encryption_fn = fetch_versioned_implementation(
         "onyx.utils.encryption", "_encrypt_string"
     )
-    return versioned_encryption_fn(input_str, key=key)
+    return versioned_encryption_fn(input_str)
 
 
-def decrypt_bytes_to_string(input_bytes: bytes, key: str | None = None) -> str:
+def decrypt_bytes_to_string(input_bytes: bytes) -> str:
     versioned_decryption_fn = fetch_versioned_implementation(
         "onyx.utils.encryption", "_decrypt_bytes"
     )
-    return versioned_decryption_fn(input_bytes, key=key)
+    return versioned_decryption_fn(input_bytes)
 
 
 def test_encryption() -> None:

backend/onyx/access/access.py

@@ -1,6 +1,7 @@
 from collections.abc import Callable
 from typing import cast
 
+from sqlalchemy.orm import joinedload
 from sqlalchemy.orm import Session
 
 from onyx.access.models import DocumentAccess
@@ -11,7 +12,6 @@ from onyx.db.document import get_access_info_for_document
 from onyx.db.document import get_access_info_for_documents
 from onyx.db.models import User
 from onyx.db.models import UserFile
-from onyx.db.user_file import fetch_user_files_with_access_relationships
 from onyx.utils.variable_functionality import fetch_ee_implementation_or_noop
 from onyx.utils.variable_functionality import fetch_versioned_implementation
 
@@ -132,61 +132,19 @@ def get_access_for_user_files(
     user_file_ids: list[str],
     db_session: Session,
 ) -> dict[str, DocumentAccess]:
-    versioned_fn = fetch_versioned_implementation(
-        "onyx.access.access", "get_access_for_user_files_impl"
+    user_files = (
+        db_session.query(UserFile)
+        .options(joinedload(UserFile.user))  # Eager load the user relationship
+        .filter(UserFile.id.in_(user_file_ids))
+        .all()
     )
-    return versioned_fn(user_file_ids, db_session)
-
-
-def get_access_for_user_files_impl(
-    user_file_ids: list[str],
-    db_session: Session,
-) -> dict[str, DocumentAccess]:
-    user_files = fetch_user_files_with_access_relationships(user_file_ids, db_session)
-    return build_access_for_user_files_impl(user_files)
-
-
-def build_access_for_user_files(
-    user_files: list[UserFile],
-) -> dict[str, DocumentAccess]:
-    """Compute access from pre-loaded UserFile objects (with relationships).
-    Callers must ensure UserFile.user, Persona.users, and Persona.user are
-    eagerly loaded (and Persona.groups for the EE path)."""
-    versioned_fn = fetch_versioned_implementation(
-        "onyx.access.access", "build_access_for_user_files_impl"
-    )
-    return versioned_fn(user_files)
-
-
-def build_access_for_user_files_impl(
-    user_files: list[UserFile],
-) -> dict[str, DocumentAccess]:
-    result: dict[str, DocumentAccess] = {}
-    for user_file in user_files:
-        emails, is_public = collect_user_file_access(user_file)
-        result[str(user_file.id)] = DocumentAccess.build(
-            user_emails=list(emails),
+    return {
+        str(user_file.id): DocumentAccess.build(
+            user_emails=[user_file.user.email] if user_file.user else [],
             user_groups=[],
-            is_public=is_public,
+            is_public=True if user_file.user is None else False,
             external_user_emails=[],
             external_user_group_ids=[],
         )
-    return result
-
-
-def collect_user_file_access(user_file: UserFile) -> tuple[set[str], bool]:
-    """Collect all user emails that should have access to this user file.
-    Includes the owner plus any users who have access via shared personas.
-    Returns (emails, is_public)."""
-    emails: set[str] = {user_file.user.email}
-    is_public = False
-    for persona in user_file.assistants:
-        if persona.deleted:
-            continue
-        if persona.is_public:
-            is_public = True
-        if persona.user_id is not None and persona.user:
-            emails.add(persona.user.email)
-        for shared_user in persona.users:
-            emails.add(shared_user.email)
-    return emails, is_public
+        for user_file in user_files
+    }

backend/onyx/auth/users.py

@@ -1,5 +1,4 @@
 import json
-import os
 import random
 import secrets
 import string
@@ -146,22 +145,10 @@ def is_user_admin(user: User) -> bool:
 
 
 def verify_auth_setting() -> None:
-    """Log warnings for AUTH_TYPE issues.
-
-    This only runs on app startup not during migrations/scripts.
-    """
-    raw_auth_type = (os.environ.get("AUTH_TYPE") or "").lower()
-
-    if raw_auth_type == "cloud":
+    if AUTH_TYPE == AuthType.CLOUD:
         raise ValueError(
-            "'cloud' is not a valid auth type for self-hosted deployments."
+            f"{AUTH_TYPE.value} is not a valid auth type for self-hosted deployments."
         )
-    if raw_auth_type == "disabled":
-        logger.warning(
-            "AUTH_TYPE='disabled' is no longer supported. "
-            "Using 'basic' instead. Please update your configuration."
-        )
-
     logger.notice(f"Using Auth Type: {AUTH_TYPE.value}")
 
 

backend/onyx/background/celery/celery_utils.py

@@ -115,6 +115,8 @@ def _extract_from_batch(
     for item in doc_list:
         if isinstance(item, HierarchyNode):
             hierarchy_nodes.append(item)
+            if item.raw_node_id not in ids:
+                ids[item.raw_node_id] = None
         elif isinstance(item, ConnectorFailure):
             failed_id = _get_failure_id(item)
             if failed_id:
@@ -123,7 +125,8 @@ def _extract_from_batch(
                 f"Failed to retrieve document {failed_id}: " f"{item.failure_message}"
             )
         else:
-            ids[item.id] = item.parent_hierarchy_raw_node_id
+            parent_raw = getattr(item, "parent_hierarchy_raw_node_id", None)
+            ids[item.id] = parent_raw
     return BatchResult(raw_id_to_parent=ids, hierarchy_nodes=hierarchy_nodes)
 
 
@@ -189,7 +192,9 @@ def extract_ids_from_runnable_connector(
         batch_ids = batch_result.raw_id_to_parent
         batch_nodes = batch_result.hierarchy_nodes
         doc_batch_processing_func(batch_ids)
-        all_raw_id_to_parent.update(batch_ids)
+        for k, v in batch_ids.items():
+            if v is not None or k not in all_raw_id_to_parent:
+                all_raw_id_to_parent[k] = v
         all_hierarchy_nodes.extend(batch_nodes)
 
         if callback:

backend/onyx/background/celery/tasks/hierarchyfetching/tasks.py

@@ -40,7 +40,6 @@ from onyx.db.connector_credential_pair import get_connector_credential_pair_from
 from onyx.db.engine.sql_engine import get_session_with_current_tenant
 from onyx.db.enums import AccessType
 from onyx.db.enums import ConnectorCredentialPairStatus
-from onyx.db.hierarchy import upsert_hierarchy_node_cc_pair_entries
 from onyx.db.hierarchy import upsert_hierarchy_nodes_batch
 from onyx.db.models import ConnectorCredentialPair
 from onyx.redis.redis_hierarchy import cache_hierarchy_nodes_batch
@@ -290,14 +289,6 @@ def _run_hierarchy_extraction(
             is_connector_public=is_connector_public,
         )
 
-        upsert_hierarchy_node_cc_pair_entries(
-            db_session=db_session,
-            hierarchy_node_ids=[n.id for n in upserted_nodes],
-            connector_id=cc_pair.connector_id,
-            credential_id=cc_pair.credential_id,
-            commit=True,
-        )
-
         # Cache in Redis for fast ancestor resolution
         cache_entries = [
             HierarchyNodeCacheEntry.from_db_model(node) for node in upserted_nodes

backend/onyx/background/celery/tasks/opensearch_migration/constants.py

@@ -11,9 +11,6 @@
 # lock after its cleanup which happens at most after its soft timeout.
 
 # Constants corresponding to migrate_documents_from_vespa_to_opensearch_task.
-from onyx.configs.app_configs import OPENSEARCH_MIGRATION_GET_VESPA_CHUNKS_PAGE_SIZE
-
-
 MIGRATION_TASK_SOFT_TIME_LIMIT_S = 60 * 5  # 5 minutes.
 MIGRATION_TASK_TIME_LIMIT_S = 60 * 6  # 6 minutes.
 # The maximum time the lock can be held for. Will automatically be released
@@ -47,7 +44,7 @@ TOTAL_ALLOWABLE_DOC_MIGRATION_ATTEMPTS_BEFORE_PERMANENT_FAILURE = 15
 
 # WARNING: Do not change these values without knowing what changes also need to
 # be made to OpenSearchTenantMigrationRecord.
-GET_VESPA_CHUNKS_PAGE_SIZE = OPENSEARCH_MIGRATION_GET_VESPA_CHUNKS_PAGE_SIZE
+GET_VESPA_CHUNKS_PAGE_SIZE = 500
 GET_VESPA_CHUNKS_SLICE_COUNT = 4
 
 # String used to indicate in the vespa_visit_continuation_token mapping that the

backend/onyx/background/celery/tasks/pruning/tasks.py

@@ -48,15 +48,10 @@ from onyx.db.enums import AccessType
 from onyx.db.enums import ConnectorCredentialPairStatus
 from onyx.db.enums import SyncStatus
 from onyx.db.enums import SyncType
-from onyx.db.hierarchy import delete_orphaned_hierarchy_nodes
 from onyx.db.hierarchy import link_hierarchy_nodes_to_documents
-from onyx.db.hierarchy import remove_stale_hierarchy_node_cc_pair_entries
-from onyx.db.hierarchy import reparent_orphaned_hierarchy_nodes
 from onyx.db.hierarchy import update_document_parent_hierarchy_nodes
-from onyx.db.hierarchy import upsert_hierarchy_node_cc_pair_entries
 from onyx.db.hierarchy import upsert_hierarchy_nodes_batch
 from onyx.db.models import ConnectorCredentialPair
-from onyx.db.models import HierarchyNode as DBHierarchyNode
 from onyx.db.sync_record import insert_sync_record
 from onyx.db.sync_record import update_sync_record_status
 from onyx.db.tag import delete_orphan_tags__no_commit
@@ -65,7 +60,6 @@ from onyx.redis.redis_connector_prune import RedisConnectorPrune
 from onyx.redis.redis_connector_prune import RedisConnectorPrunePayload
 from onyx.redis.redis_hierarchy import cache_hierarchy_nodes_batch
 from onyx.redis.redis_hierarchy import ensure_source_node_exists
-from onyx.redis.redis_hierarchy import evict_hierarchy_nodes_from_cache
 from onyx.redis.redis_hierarchy import get_node_id_from_raw_id
 from onyx.redis.redis_hierarchy import get_source_node_id_from_cache
 from onyx.redis.redis_hierarchy import HierarchyNodeCacheEntry
@@ -585,12 +579,11 @@ def connector_pruning_generator_task(
             source = cc_pair.connector.source
             redis_client = get_redis_client(tenant_id=tenant_id)
 
-            ensure_source_node_exists(redis_client, db_session, source)
-
-            upserted_nodes: list[DBHierarchyNode] = []
             if extraction_result.hierarchy_nodes:
                 is_connector_public = cc_pair.access_type == AccessType.PUBLIC
 
+                ensure_source_node_exists(redis_client, db_session, source)
+
                 upserted_nodes = upsert_hierarchy_nodes_batch(
                     db_session=db_session,
                     nodes=extraction_result.hierarchy_nodes,
@@ -599,14 +592,6 @@ def connector_pruning_generator_task(
                     is_connector_public=is_connector_public,
                 )
 
-                upsert_hierarchy_node_cc_pair_entries(
-                    db_session=db_session,
-                    hierarchy_node_ids=[n.id for n in upserted_nodes],
-                    connector_id=connector_id,
-                    credential_id=credential_id,
-                    commit=True,
-                )
-
                 cache_entries = [
                     HierarchyNodeCacheEntry.from_db_model(node)
                     for node in upserted_nodes
@@ -622,6 +607,7 @@ def connector_pruning_generator_task(
                     f"hierarchy nodes for cc_pair={cc_pair_id}"
                 )
 
+            ensure_source_node_exists(redis_client, db_session, source)
             # Resolve parent_hierarchy_raw_node_id → parent_hierarchy_node_id
             # and bulk-update documents, mirroring the docfetching resolution
             _resolve_and_update_document_parents(
@@ -678,43 +664,6 @@ def connector_pruning_generator_task(
             )
 
             redis_connector.prune.generator_complete = tasks_generated
-
-            # --- Hierarchy node pruning ---
-            live_node_ids = {n.id for n in upserted_nodes}
-            stale_removed = remove_stale_hierarchy_node_cc_pair_entries(
-                db_session=db_session,
-                connector_id=connector_id,
-                credential_id=credential_id,
-                live_hierarchy_node_ids=live_node_ids,
-                commit=True,
-            )
-            deleted_raw_ids = delete_orphaned_hierarchy_nodes(
-                db_session=db_session,
-                source=source,
-                commit=True,
-            )
-            reparented_nodes = reparent_orphaned_hierarchy_nodes(
-                db_session=db_session,
-                source=source,
-                commit=True,
-            )
-            if deleted_raw_ids:
-                evict_hierarchy_nodes_from_cache(redis_client, source, deleted_raw_ids)
-            if reparented_nodes:
-                reparented_cache_entries = [
-                    HierarchyNodeCacheEntry.from_db_model(node)
-                    for node in reparented_nodes
-                ]
-                cache_hierarchy_nodes_batch(
-                    redis_client, source, reparented_cache_entries
-                )
-            if stale_removed or deleted_raw_ids or reparented_nodes:
-                task_logger.info(
-                    f"Hierarchy node pruning: cc_pair={cc_pair_id} "
-                    f"stale_entries_removed={stale_removed} "
-                    f"nodes_deleted={len(deleted_raw_ids)} "
-                    f"nodes_reparented={len(reparented_nodes)}"
-                )
     except Exception as e:
         task_logger.exception(
             f"Pruning exceptioned: cc_pair={cc_pair_id} "

backend/onyx/background/celery/tasks/user_file_processing/tasks.py

@@ -12,9 +12,9 @@ from redis import Redis
 from redis.lock import Lock as RedisLock
 from retry import retry
 from sqlalchemy import select
+from sqlalchemy.orm import selectinload
 from sqlalchemy.orm import Session
 
-from onyx.access.access import build_access_for_user_files
 from onyx.background.celery.apps.app_base import task_logger
 from onyx.background.celery.celery_redis import celery_get_queue_length
 from onyx.background.celery.celery_utils import httpx_init_vespa_pool
@@ -43,9 +43,7 @@ from onyx.db.enums import UserFileStatus
 from onyx.db.models import UserFile
 from onyx.db.search_settings import get_active_search_settings
 from onyx.db.search_settings import get_active_search_settings_list
-from onyx.db.user_file import fetch_user_files_with_access_relationships
 from onyx.document_index.factory import get_all_document_indices
-from onyx.document_index.interfaces import VespaDocumentFields
 from onyx.document_index.interfaces import VespaDocumentUserFields
 from onyx.document_index.vespa_constants import DOCUMENT_ID_ENDPOINT
 from onyx.file_store.file_store import get_default_file_store
@@ -56,7 +54,6 @@ from onyx.indexing.adapters.user_file_indexing_adapter import UserFileIndexingAd
 from onyx.indexing.embedder import DefaultIndexingEmbedder
 from onyx.indexing.indexing_pipeline import run_indexing_pipeline
 from onyx.redis.redis_pool import get_redis_client
-from onyx.utils.variable_functionality import global_version
 
 
 def _as_uuid(value: str | UUID) -> UUID:
@@ -794,12 +791,11 @@ def project_sync_user_file_impl(
 
     try:
         with get_session_with_current_tenant() as db_session:
-            user_files = fetch_user_files_with_access_relationships(
-                [user_file_id],
-                db_session,
-                eager_load_groups=global_version.is_ee_version(),
-            )
-            user_file = user_files[0] if user_files else None
+            user_file = db_session.execute(
+                select(UserFile)
+                .where(UserFile.id == _as_uuid(user_file_id))
+                .options(selectinload(UserFile.assistants))
+            ).scalar_one_or_none()
             if not user_file:
                 task_logger.info(
                     f"project_sync_user_file_impl - User file not found id={user_file_id}"
@@ -827,21 +823,12 @@ def project_sync_user_file_impl(
 
                 project_ids = [project.id for project in user_file.projects]
                 persona_ids = [p.id for p in user_file.assistants if not p.deleted]
-
-                file_id_str = str(user_file.id)
-                access_map = build_access_for_user_files([user_file])
-                access = access_map.get(file_id_str)
-
                 for retry_document_index in retry_document_indices:
                     retry_document_index.update_single(
-                        doc_id=file_id_str,
+                        doc_id=str(user_file.id),
                         tenant_id=tenant_id,
                         chunk_count=user_file.chunk_count,
-                        fields=(
-                            VespaDocumentFields(access=access)
-                            if access is not None
-                            else None
-                        ),
+                        fields=None,
                         user_fields=VespaDocumentUserFields(
                             user_projects=project_ids,
                             personas=persona_ids,

backend/onyx/background/indexing/run_docfetching.py

@@ -45,7 +45,6 @@ from onyx.db.enums import ConnectorCredentialPairStatus
 from onyx.db.enums import IndexingStatus
 from onyx.db.enums import IndexModelStatus
 from onyx.db.enums import ProcessingMode
-from onyx.db.hierarchy import upsert_hierarchy_node_cc_pair_entries
 from onyx.db.hierarchy import upsert_hierarchy_nodes_batch
 from onyx.db.index_attempt import create_index_attempt_error
 from onyx.db.index_attempt import get_index_attempt
@@ -588,14 +587,6 @@ def connector_document_extraction(
                             is_connector_public=is_connector_public,
                         )
 
-                        upsert_hierarchy_node_cc_pair_entries(
-                            db_session=db_session,
-                            hierarchy_node_ids=[n.id for n in upserted_nodes],
-                            connector_id=db_connector.id,
-                            credential_id=db_credential.id,
-                            commit=True,
-                        )
-
                         # Cache in Redis for fast ancestor resolution during doc processing
                         redis_client = get_redis_client(tenant_id=tenant_id)
                         cache_entries = [

backend/onyx/chat/llm_step.py

@@ -15,7 +15,6 @@ from onyx.chat.citation_processor import DynamicCitationProcessor
 from onyx.chat.emitter import Emitter
 from onyx.chat.models import ChatMessageSimple
 from onyx.chat.models import LlmStepResult
-from onyx.chat.tool_call_args_streaming import maybe_emit_argument_delta
 from onyx.configs.app_configs import LOG_ONYX_MODEL_INTERACTIONS
 from onyx.configs.app_configs import PROMPT_CACHE_CHAT_HISTORY
 from onyx.configs.constants import MessageType
@@ -55,7 +54,6 @@ from onyx.server.query_and_chat.streaming_models import ReasoningStart
 from onyx.tools.models import ToolCallKickoff
 from onyx.tracing.framework.create import generation_span
 from onyx.utils.b64 import get_image_type_from_bytes
-from onyx.utils.jsonriver import Parser
 from onyx.utils.logger import setup_logger
 from onyx.utils.postgres_sanitization import sanitize_string
 from onyx.utils.text_processing import find_all_json_objects
@@ -1011,7 +1009,6 @@ def run_llm_step_pkt_generator(
         )
 
     id_to_tool_call_map: dict[int, dict[str, Any]] = {}
-    arg_parsers: dict[int, Parser] = {}
     reasoning_start = False
     answer_start = False
     accumulated_reasoning = ""
@@ -1218,14 +1215,7 @@ def run_llm_step_pkt_generator(
                 yield from _close_reasoning_if_active()
 
                 for tool_call_delta in delta.tool_calls:
-                    # maybe_emit depends and update being called first and attaching the delta
                     _update_tool_call_with_delta(id_to_tool_call_map, tool_call_delta)
-                    yield from maybe_emit_argument_delta(
-                        tool_calls_in_progress=id_to_tool_call_map,
-                        tool_call_delta=tool_call_delta,
-                        placement=_current_placement(),
-                        parsers=arg_parsers,
-                    )
 
         # Flush any tail text buffered while checking for split "<function_calls" markers.
         filtered_content_tail = xml_tool_call_content_filter.flush()

backend/onyx/chat/tool_call_args_streaming.py

@@ -1,77 +0,0 @@
-from collections.abc import Generator
-from collections.abc import Mapping
-from typing import Any
-from typing import Type
-
-from onyx.llm.model_response import ChatCompletionDeltaToolCall
-from onyx.server.query_and_chat.placement import Placement
-from onyx.server.query_and_chat.streaming_models import Packet
-from onyx.server.query_and_chat.streaming_models import ToolCallArgumentDelta
-from onyx.tools.built_in_tools import TOOL_NAME_TO_CLASS
-from onyx.tools.interface import Tool
-from onyx.utils.jsonriver import Parser
-
-
-def _get_tool_class(
-    tool_calls_in_progress: Mapping[int, Mapping[str, Any]],
-    tool_call_delta: ChatCompletionDeltaToolCall,
-) -> Type[Tool] | None:
-    """Look up the Tool subclass for a streaming tool call delta."""
-    tool_name = tool_calls_in_progress.get(tool_call_delta.index, {}).get("name")
-    if not tool_name:
-        return None
-    return TOOL_NAME_TO_CLASS.get(tool_name)
-
-
-def maybe_emit_argument_delta(
-    tool_calls_in_progress: Mapping[int, Mapping[str, Any]],
-    tool_call_delta: ChatCompletionDeltaToolCall,
-    placement: Placement,
-    parsers: dict[int, Parser],
-) -> Generator[Packet, None, None]:
-    """Emit decoded tool-call argument deltas to the frontend.
-
-    Uses a ``jsonriver.Parser`` per tool-call index to incrementally parse
-    the JSON argument string and extract only the newly-appended content
-    for each string-valued argument.
-
-    NOTE: Non-string arguments (numbers, booleans, null, arrays, objects)
-    are skipped — they are available in the final tool-call kickoff packet.
-
-    ``parsers`` is a mutable dict keyed by tool-call index. A new
-    ``Parser`` is created automatically for each new index.
-    """
-    tool_cls = _get_tool_class(tool_calls_in_progress, tool_call_delta)
-    if not tool_cls or not tool_cls.should_emit_argument_deltas():
-        return
-
-    fn = tool_call_delta.function
-    delta_fragment = fn.arguments if fn else None
-    if not delta_fragment:
-        return
-
-    idx = tool_call_delta.index
-    if idx not in parsers:
-        parsers[idx] = Parser()
-    parser = parsers[idx]
-
-    deltas = parser.feed(delta_fragment)
-
-    argument_deltas: dict[str, str] = {}
-    for delta in deltas:
-        if isinstance(delta, dict):
-            for key, value in delta.items():
-                if isinstance(value, str):
-                    argument_deltas[key] = argument_deltas.get(key, "") + value
-
-    if not argument_deltas:
-        return
-
-    tc_data = tool_calls_in_progress[tool_call_delta.index]
-    yield Packet(
-        placement=placement,
-        obj=ToolCallArgumentDelta(
-            tool_type=tc_data.get("name", ""),
-            argument_deltas=argument_deltas,
-        ),
-    )

backend/onyx/configs/app_configs.py

@@ -68,10 +68,6 @@ FILE_TOKEN_COUNT_THRESHOLD = int(
     os.environ.get("FILE_TOKEN_COUNT_THRESHOLD", str(_DEFAULT_FILE_TOKEN_LIMIT))
 )
 
-# Maximum upload size for a single user file (chat/projects) in MB.
-USER_FILE_MAX_UPLOAD_SIZE_MB = int(os.environ.get("USER_FILE_MAX_UPLOAD_SIZE_MB") or 50)
-USER_FILE_MAX_UPLOAD_SIZE_BYTES = USER_FILE_MAX_UPLOAD_SIZE_MB * 1024 * 1024
-
 # If set to true, will show extra/uncommon connectors in the "Other" category
 SHOW_EXTRA_CONNECTORS = os.environ.get("SHOW_EXTRA_CONNECTORS", "").lower() == "true"
 
@@ -96,12 +92,19 @@ WEB_DOMAIN = os.environ.get("WEB_DOMAIN") or "http://localhost:3000"
 #####
 # Auth Configs
 #####
-# Silently default to basic - warnings/errors logged in verify_auth_setting()
-# which only runs on app startup, not during migrations/scripts
-_auth_type_str = (os.environ.get("AUTH_TYPE") or "").lower()
-if _auth_type_str in [auth_type.value for auth_type in AuthType]:
+# Upgrades users from disabled auth to basic auth and shows warning.
+_auth_type_str = (os.environ.get("AUTH_TYPE") or "basic").lower()
+if _auth_type_str == "disabled":
+    logger.warning(
+        "AUTH_TYPE='disabled' is no longer supported. "
+        "Defaulting to 'basic'. Please update your configuration. "
+        "Your existing data will be migrated automatically."
+    )
+    _auth_type_str = AuthType.BASIC.value
+try:
     AUTH_TYPE = AuthType(_auth_type_str)
-else:
+except ValueError:
+    logger.error(f"Invalid AUTH_TYPE: {_auth_type_str}. Defaulting to 'basic'.")
     AUTH_TYPE = AuthType.BASIC
 
 PASSWORD_MIN_LENGTH = int(os.getenv("PASSWORD_MIN_LENGTH", 8))
@@ -204,12 +207,6 @@ JWT_PUBLIC_KEY_URL: str | None = os.getenv("JWT_PUBLIC_KEY_URL", None)
 
 USER_AUTH_SECRET = os.environ.get("USER_AUTH_SECRET", "")
 
-if AUTH_TYPE == AuthType.BASIC and not USER_AUTH_SECRET:
-    logger.warning(
-        "USER_AUTH_SECRET is not set. This is required for secure password reset "
-        "and email verification tokens. Please set USER_AUTH_SECRET in production."
-    )
-
 # Duration (in seconds) for which the FastAPI Users JWT token remains valid in the user's browser.
 # By default, this is set to match the Redis expiry time for consistency.
 AUTH_COOKIE_EXPIRE_TIME_SECONDS = int(
@@ -311,12 +308,6 @@ VERIFY_CREATE_OPENSEARCH_INDEX_ON_INIT_MT = (
     os.environ.get("VERIFY_CREATE_OPENSEARCH_INDEX_ON_INIT_MT", "true").lower()
     == "true"
 )
-OPENSEARCH_MIGRATION_GET_VESPA_CHUNKS_PAGE_SIZE = int(
-    os.environ.get("OPENSEARCH_MIGRATION_GET_VESPA_CHUNKS_PAGE_SIZE") or 500
-)
-OPENSEARCH_OVERRIDE_DEFAULT_NUM_HYBRID_SEARCH_CANDIDATES = int(
-    os.environ.get("OPENSEARCH_DEFAULT_NUM_HYBRID_SEARCH_CANDIDATES") or 0
-)
 
 VESPA_HOST = os.environ.get("VESPA_HOST") or "localhost"
 # NOTE: this is used if and only if the vespa config server is accessible via a

backend/onyx/connectors/discord/connector.py

@@ -1,5 +1,4 @@
 import asyncio
-from collections.abc import AsyncGenerator
 from collections.abc import AsyncIterable
 from collections.abc import Iterable
 from datetime import datetime
@@ -205,7 +204,7 @@ def _manage_async_retrieval(
 
     end_time: datetime | None = end
 
-    async def _async_fetch() -> AsyncGenerator[Document, None]:
+    async def _async_fetch() -> AsyncIterable[Document]:
         intents = Intents.default()
         intents.message_content = True
         async with Client(intents=intents) as discord_client:
@@ -228,23 +227,22 @@ def _manage_async_retrieval(
 
     def run_and_yield() -> Iterable[Document]:
         loop = asyncio.new_event_loop()
-        async_gen = _async_fetch()
         try:
+            # Get the async generator
+            async_gen = _async_fetch()
+            # Convert to AsyncIterator
+            async_iter = async_gen.__aiter__()
             while True:
                 try:
-                    doc = loop.run_until_complete(anext(async_gen))
+                    # Create a coroutine by calling anext with the async iterator
+                    next_coro = anext(async_iter)
+                    # Run the coroutine to get the next document
+                    doc = loop.run_until_complete(next_coro)
                     yield doc
                 except StopAsyncIteration:
                     break
         finally:
-            # Must close the async generator before the loop so the Discord
-            # client's `async with` block can await its shutdown coroutine.
-            # The nested try/finally ensures the loop always closes even if
-            # aclose() raises (same pattern as cursor.close() before conn.close()).
-            try:
-                loop.run_until_complete(async_gen.aclose())
-            finally:
-                loop.close()
+            loop.close()
 
     return run_and_yield()
 

backend/onyx/connectors/google_drive/connector.py

@@ -1722,7 +1722,6 @@ class GoogleDriveConnector(
                         primary_admin_email=self.primary_admin_email,
                         google_domain=self.google_domain,
                     ),
-                    retriever_email=file.user_email,
                 ):
                     slim_batch.append(doc)
 

backend/onyx/connectors/google_drive/doc_conversion.py

@@ -476,7 +476,6 @@ def _get_external_access_for_raw_gdrive_file(
     company_domain: str,
     retriever_drive_service: GoogleDriveService | None,
     admin_drive_service: GoogleDriveService,
-    fallback_user_email: str,
     add_prefix: bool = False,
 ) -> ExternalAccess:
     """
@@ -485,8 +484,6 @@ def _get_external_access_for_raw_gdrive_file(
     add_prefix: When True, prefix group IDs with source type (for indexing path).
                When False (default), leave unprefixed (for permission sync path
                where upsert_document_external_perms handles prefixing).
-    fallback_user_email: When permission info can't be retrieved (e.g. externally-owned
-               files), fall back to granting access to this user.
     """
     external_access_fn = cast(
         Callable[
@@ -495,7 +492,6 @@ def _get_external_access_for_raw_gdrive_file(
                 str,
                 GoogleDriveService | None,
                 GoogleDriveService,
-                str,
                 bool,
             ],
             ExternalAccess,
@@ -511,7 +507,6 @@ def _get_external_access_for_raw_gdrive_file(
         company_domain,
         retriever_drive_service,
         admin_drive_service,
-        fallback_user_email,
         add_prefix,
     )
 
@@ -677,7 +672,6 @@ def _convert_drive_item_to_document(
                     creds, user_email=permission_sync_context.primary_admin_email
                 ),
                 add_prefix=True,  # Indexing path - prefix here
-                fallback_user_email=retriever_email,
             )
             if permission_sync_context
             else None
@@ -759,7 +753,6 @@ def build_slim_document(
     # if not specified, we will not sync permissions
     # will also be a no-op if EE is not enabled
     permission_sync_context: PermissionSyncContext | None,
-    retriever_email: str,
 ) -> SlimDocument | None:
     if file.get("mimeType") in [DRIVE_FOLDER_TYPE, DRIVE_SHORTCUT_TYPE]:
         return None
@@ -781,7 +774,6 @@ def build_slim_document(
                 creds,
                 user_email=permission_sync_context.primary_admin_email,
             ),
-            fallback_user_email=retriever_email,
         )
         if permission_sync_context
         else None

backend/onyx/connectors/google_utils/google_kv.py

@@ -44,7 +44,6 @@ from onyx.connectors.google_utils.shared_constants import (
 from onyx.db.credentials import update_credential_json
 from onyx.db.models import User
 from onyx.key_value_store.factory import get_kv_store
-from onyx.key_value_store.interface import unwrap_str
 from onyx.server.documents.models import CredentialBase
 from onyx.server.documents.models import GoogleAppCredentials
 from onyx.server.documents.models import GoogleServiceAccountKey
@@ -90,7 +89,7 @@ def _get_current_oauth_user(creds: OAuthCredentials, source: DocumentSource) ->
 
 
 def verify_csrf(credential_id: int, state: str) -> None:
-    csrf = unwrap_str(get_kv_store().load(KV_CRED_KEY.format(str(credential_id))))
+    csrf = get_kv_store().load(KV_CRED_KEY.format(str(credential_id)))
     if csrf != state:
         raise PermissionError(
             "State from Google Drive Connector callback does not match expected"
@@ -179,9 +178,7 @@ def get_auth_url(credential_id: int, source: DocumentSource) -> str:
     params = parse_qs(parsed_url.query)
 
     get_kv_store().store(
-        KV_CRED_KEY.format(credential_id),
-        {"value": params.get("state", [None])[0]},
-        encrypt=True,
+        KV_CRED_KEY.format(credential_id), params.get("state", [None])[0], encrypt=True
     )
     return str(auth_url)
 

backend/onyx/connectors/sharepoint/connector.py

@@ -258,10 +258,6 @@ class SharepointConnectorCheckpoint(ConnectorCheckpoint):
     # Track yielded hierarchy nodes by their raw_node_id (URLs) to avoid duplicates
     seen_hierarchy_node_raw_ids: set[str] = Field(default_factory=set)
 
-    # Track yielded document IDs to avoid processing the same document twice.
-    # The Microsoft Graph delta API can return the same item on multiple pages.
-    seen_document_ids: set[str] = Field(default_factory=set)
-
 
 class SharepointAuthMethod(Enum):
     CLIENT_SECRET = "client_secret"
@@ -1561,7 +1557,6 @@ class SharepointConnector(
         checkpoint.current_drive_id = None
         checkpoint.current_drive_web_url = None
         checkpoint.current_drive_delta_next_link = None
-        checkpoint.seen_document_ids.clear()
 
     def _fetch_slim_documents_from_sharepoint(self) -> GenerateSlimDocumentOutput:
         site_descriptors = self.site_descriptors or self.fetch_sites()
@@ -2142,14 +2137,6 @@ class SharepointConnector(
             item_count = 0
             for driveitem in driveitems:
                 item_count += 1
-
-                if driveitem.id and driveitem.id in checkpoint.seen_document_ids:
-                    logger.debug(
-                        f"Skipping duplicate document {driveitem.id} "
-                        f"({driveitem.name})"
-                    )
-                    continue
-
                 driveitem_extension = get_file_ext(driveitem.name)
                 if driveitem_extension not in OnyxFileExtensions.ALL_ALLOWED_EXTENSIONS:
                     logger.warning(
@@ -2202,13 +2189,11 @@ class SharepointConnector(
 
                     if isinstance(doc_or_failure, Document):
                         if doc_or_failure.sections:
-                            checkpoint.seen_document_ids.add(doc_or_failure.id)
                             yield doc_or_failure
                         elif should_yield_if_empty:
                             doc_or_failure.sections = [
                                 TextSection(link=driveitem.web_url, text="")
                             ]
-                            checkpoint.seen_document_ids.add(doc_or_failure.id)
                             yield doc_or_failure
                         else:
                             logger.warning(

backend/onyx/db/hierarchy.py

@@ -2,10 +2,7 @@
 
 from collections import defaultdict
 
-from sqlalchemy import delete
 from sqlalchemy import select
-from sqlalchemy.dialects.postgresql import insert as pg_insert
-from sqlalchemy.engine import CursorResult
 from sqlalchemy.orm import Session
 
 from onyx.configs.constants import DocumentSource
@@ -13,7 +10,6 @@ from onyx.connectors.models import HierarchyNode as PydanticHierarchyNode
 from onyx.db.enums import HierarchyNodeType
 from onyx.db.models import Document
 from onyx.db.models import HierarchyNode
-from onyx.db.models import HierarchyNodeByConnectorCredentialPair
 from onyx.utils.logger import setup_logger
 from onyx.utils.variable_functionality import fetch_versioned_implementation
 
@@ -462,7 +458,7 @@ def get_all_hierarchy_nodes_for_source(
 def _get_accessible_hierarchy_nodes_for_source(
     db_session: Session,
     source: DocumentSource,
-    user_email: str,  # noqa: ARG001
+    user_email: str | None,  # noqa: ARG001
     external_group_ids: list[str],  # noqa: ARG001
 ) -> list[HierarchyNode]:
     """
@@ -489,7 +485,7 @@ def _get_accessible_hierarchy_nodes_for_source(
 def get_accessible_hierarchy_nodes_for_source(
     db_session: Session,
     source: DocumentSource,
-    user_email: str,
+    user_email: str | None,
     external_group_ids: list[str],
 ) -> list[HierarchyNode]:
     """
@@ -624,154 +620,3 @@ def update_hierarchy_node_permissions(
         db_session.flush()
 
     return True
-
-
-def upsert_hierarchy_node_cc_pair_entries(
-    db_session: Session,
-    hierarchy_node_ids: list[int],
-    connector_id: int,
-    credential_id: int,
-    commit: bool = True,
-) -> None:
-    """Insert rows into HierarchyNodeByConnectorCredentialPair, ignoring conflicts.
-
-    This records that the given cc_pair "owns" these hierarchy nodes. Used by
-    indexing, pruning, and hierarchy-fetching paths.
-    """
-    if not hierarchy_node_ids:
-        return
-
-    _M = HierarchyNodeByConnectorCredentialPair
-    stmt = pg_insert(_M).values(
-        [
-            {
-                _M.hierarchy_node_id: node_id,
-                _M.connector_id: connector_id,
-                _M.credential_id: credential_id,
-            }
-            for node_id in hierarchy_node_ids
-        ]
-    )
-    stmt = stmt.on_conflict_do_nothing()
-    db_session.execute(stmt)
-
-    if commit:
-        db_session.commit()
-    else:
-        db_session.flush()
-
-
-def remove_stale_hierarchy_node_cc_pair_entries(
-    db_session: Session,
-    connector_id: int,
-    credential_id: int,
-    live_hierarchy_node_ids: set[int],
-    commit: bool = True,
-) -> int:
-    """Delete join-table rows for this cc_pair that are NOT in the live set.
-
-    If ``live_hierarchy_node_ids`` is empty ALL rows for the cc_pair are deleted
-    (i.e. the connector no longer has any hierarchy nodes). Callers that want a
-    no-op when there are no live nodes must guard before calling.
-
-    Returns the number of deleted rows.
-    """
-    stmt = delete(HierarchyNodeByConnectorCredentialPair).where(
-        HierarchyNodeByConnectorCredentialPair.connector_id == connector_id,
-        HierarchyNodeByConnectorCredentialPair.credential_id == credential_id,
-    )
-    if live_hierarchy_node_ids:
-        stmt = stmt.where(
-            HierarchyNodeByConnectorCredentialPair.hierarchy_node_id.notin_(
-                live_hierarchy_node_ids
-            )
-        )
-
-    result: CursorResult = db_session.execute(stmt)  # type: ignore[assignment]
-    deleted = result.rowcount
-
-    if commit:
-        db_session.commit()
-    elif deleted:
-        db_session.flush()
-
-    return deleted
-
-
-def delete_orphaned_hierarchy_nodes(
-    db_session: Session,
-    source: DocumentSource,
-    commit: bool = True,
-) -> list[str]:
-    """Delete hierarchy nodes for a source that have zero cc_pair associations.
-
-    SOURCE-type nodes are excluded (they are synthetic roots).
-
-    Returns the list of raw_node_ids that were deleted (for cache eviction).
-    """
-    # Find orphaned nodes: no rows in the join table
-    orphan_stmt = (
-        select(HierarchyNode.id, HierarchyNode.raw_node_id)
-        .outerjoin(
-            HierarchyNodeByConnectorCredentialPair,
-            HierarchyNode.id
-            == HierarchyNodeByConnectorCredentialPair.hierarchy_node_id,
-        )
-        .where(
-            HierarchyNode.source == source,
-            HierarchyNode.node_type != HierarchyNodeType.SOURCE,
-            HierarchyNodeByConnectorCredentialPair.hierarchy_node_id.is_(None),
-        )
-    )
-    orphans = db_session.execute(orphan_stmt).all()
-    if not orphans:
-        return []
-
-    orphan_ids = [row[0] for row in orphans]
-    deleted_raw_ids = [row[1] for row in orphans]
-
-    db_session.execute(delete(HierarchyNode).where(HierarchyNode.id.in_(orphan_ids)))
-
-    if commit:
-        db_session.commit()
-    else:
-        db_session.flush()
-
-    return deleted_raw_ids
-
-
-def reparent_orphaned_hierarchy_nodes(
-    db_session: Session,
-    source: DocumentSource,
-    commit: bool = True,
-) -> list[HierarchyNode]:
-    """Re-parent hierarchy nodes whose parent_id is NULL to the SOURCE node.
-
-    After pruning deletes stale nodes, their former children get parent_id=NULL
-    via the SET NULL cascade. This function points them back to the SOURCE root.
-
-    Returns the reparented HierarchyNode objects (with updated parent_id)
-    so callers can refresh downstream caches.
-    """
-    source_node = get_source_hierarchy_node(db_session, source)
-    if not source_node:
-        return []
-
-    stmt = select(HierarchyNode).where(
-        HierarchyNode.source == source,
-        HierarchyNode.parent_id.is_(None),
-        HierarchyNode.node_type != HierarchyNodeType.SOURCE,
-    )
-    orphans = list(db_session.execute(stmt).scalars().all())
-    if not orphans:
-        return []
-
-    for node in orphans:
-        node.parent_id = source_node.id
-
-    if commit:
-        db_session.commit()
-    else:
-        db_session.flush()
-
-    return orphans

backend/onyx/db/models.py

@@ -25,7 +25,6 @@ from sqlalchemy import desc
 from sqlalchemy import Enum
 from sqlalchemy import Float
 from sqlalchemy import ForeignKey
-from sqlalchemy import ForeignKeyConstraint
 from sqlalchemy import func
 from sqlalchemy import Index
 from sqlalchemy import Integer
@@ -37,11 +36,9 @@ from sqlalchemy import Text
 from sqlalchemy import text
 from sqlalchemy import UniqueConstraint
 from sqlalchemy.dialects import postgresql
-from sqlalchemy import event
 from sqlalchemy.engine.interfaces import Dialect
 from sqlalchemy.orm import DeclarativeBase
 from sqlalchemy.orm import Mapped
-from sqlalchemy.orm import Mapper
 from sqlalchemy.orm import mapped_column
 from sqlalchemy.orm import relationship
 from sqlalchemy.types import LargeBinary
@@ -120,52 +117,10 @@ class Base(DeclarativeBase):
     __abstract__ = True
 
 
-class _EncryptedBase(TypeDecorator):
-    """Base for encrypted column types that wrap values in SensitiveValue."""
-
+class EncryptedString(TypeDecorator):
     impl = LargeBinary
+    # This type's behavior is fully deterministic and doesn't depend on any external factors.
     cache_ok = True
-    _is_json: bool = False
-
-    def wrap_raw(self, value: Any) -> SensitiveValue:
-        """Encrypt a raw value and wrap it in SensitiveValue.
-
-        Called by the attribute set event so the Python-side type is always
-        SensitiveValue, regardless of whether the value was loaded from the DB
-        or assigned in application code.
-        """
-        if self._is_json:
-            if not isinstance(value, dict):
-                raise TypeError(
-                    f"EncryptedJson column expected dict, got {type(value).__name__}"
-                )
-            raw_str = json.dumps(value)
-        else:
-            if not isinstance(value, str):
-                raise TypeError(
-                    f"EncryptedString column expected str, got {type(value).__name__}"
-                )
-            raw_str = value
-        return SensitiveValue(
-            encrypted_bytes=encrypt_string_to_bytes(raw_str),
-            decrypt_fn=decrypt_bytes_to_string,
-            is_json=self._is_json,
-        )
-
-    def compare_values(self, x: Any, y: Any) -> bool:
-        if x is None or y is None:
-            return x == y
-        if isinstance(x, SensitiveValue):
-            x = x.get_value(apply_mask=False)
-        if isinstance(y, SensitiveValue):
-            y = y.get_value(apply_mask=False)
-        return x == y
-
-
-class EncryptedString(_EncryptedBase):
-    # Must redeclare cache_ok in this child class since we explicitly redeclare _is_json
-    cache_ok = True
-    _is_json: bool = False
 
     def process_bind_param(
         self, value: str | SensitiveValue[str] | None, dialect: Dialect  # noqa: ARG002
@@ -189,10 +144,20 @@ class EncryptedString(_EncryptedBase):
             )
         return None
 
+    def compare_values(self, x: Any, y: Any) -> bool:
+        if x is None or y is None:
+            return x == y
+        if isinstance(x, SensitiveValue):
+            x = x.get_value(apply_mask=False)
+        if isinstance(y, SensitiveValue):
+            y = y.get_value(apply_mask=False)
+        return x == y
 
-class EncryptedJson(_EncryptedBase):
+
+class EncryptedJson(TypeDecorator):
+    impl = LargeBinary
+    # This type's behavior is fully deterministic and doesn't depend on any external factors.
     cache_ok = True
-    _is_json: bool = True
 
     def process_bind_param(
         self,
@@ -200,7 +165,9 @@ class EncryptedJson(_EncryptedBase):
         dialect: Dialect,  # noqa: ARG002
     ) -> bytes | None:
         if value is not None:
+            # Handle both raw dicts and SensitiveValue wrappers
             if isinstance(value, SensitiveValue):
+                # Get raw value for storage
                 value = value.get_value(apply_mask=False)
             json_str = json.dumps(value)
             return encrypt_string_to_bytes(json_str)
@@ -217,40 +184,14 @@ class EncryptedJson(_EncryptedBase):
             )
         return None
 
-
-_REGISTERED_ATTRS: set[str] = set()
-
-
-@event.listens_for(Mapper, "mapper_configured")
-def _register_sensitive_value_set_events(
-    mapper: Mapper,
-    class_: type,
-) -> None:
-    """Auto-wrap raw values in SensitiveValue when assigned to encrypted columns."""
-    for prop in mapper.column_attrs:
-        for col in prop.columns:
-            if isinstance(col.type, _EncryptedBase):
-                col_type = col.type
-                attr = getattr(class_, prop.key)
-
-                # Guard against double-registration (e.g. if mapper is
-                # re-configured in test setups)
-                attr_key = f"{class_.__qualname__}.{prop.key}"
-                if attr_key in _REGISTERED_ATTRS:
-                    continue
-                _REGISTERED_ATTRS.add(attr_key)
-
-                @event.listens_for(attr, "set", retval=True)
-                def _wrap_value(
-                    target: Any,  # noqa: ARG001
-                    value: Any,
-                    oldvalue: Any,  # noqa: ARG001
-                    initiator: Any,  # noqa: ARG001
-                    _col_type: _EncryptedBase = col_type,
-                ) -> Any:
-                    if value is not None and not isinstance(value, SensitiveValue):
-                        return _col_type.wrap_raw(value)
-                    return value
+    def compare_values(self, x: Any, y: Any) -> bool:
+        if x is None or y is None:
+            return x == y
+        if isinstance(x, SensitiveValue):
+            x = x.get_value(apply_mask=False)
+        if isinstance(y, SensitiveValue):
+            y = y.get_value(apply_mask=False)
+        return x == y
 
 
 class NullFilteredString(TypeDecorator):
@@ -339,16 +280,6 @@ class User(SQLAlchemyBaseUserTableUUID, Base):
         TIMESTAMPAware(timezone=True), nullable=True
     )
 
-    created_at: Mapped[datetime.datetime] = mapped_column(
-        DateTime(timezone=True), server_default=func.now(), nullable=False
-    )
-    updated_at: Mapped[datetime.datetime] = mapped_column(
-        DateTime(timezone=True),
-        server_default=func.now(),
-        onupdate=func.now(),
-        nullable=False,
-    )
-
     default_model: Mapped[str] = mapped_column(Text, nullable=True)
     # organized in typical structured fashion
     # formatted as `displayName__provider__modelName`
@@ -2439,38 +2370,6 @@ class SyncRecord(Base):
     )
 
 
-class HierarchyNodeByConnectorCredentialPair(Base):
-    """Tracks which cc_pairs reference each hierarchy node.
-
-    During pruning, stale entries are removed for the current cc_pair.
-    Hierarchy nodes with zero remaining entries are then deleted.
-    """
-
-    __tablename__ = "hierarchy_node_by_connector_credential_pair"
-
-    hierarchy_node_id: Mapped[int] = mapped_column(
-        ForeignKey("hierarchy_node.id", ondelete="CASCADE"), primary_key=True
-    )
-    connector_id: Mapped[int] = mapped_column(primary_key=True)
-    credential_id: Mapped[int] = mapped_column(primary_key=True)
-
-    __table_args__ = (
-        ForeignKeyConstraint(
-            ["connector_id", "credential_id"],
-            [
-                "connector_credential_pair.connector_id",
-                "connector_credential_pair.credential_id",
-            ],
-            ondelete="CASCADE",
-        ),
-        Index(
-            "ix_hierarchy_node_cc_pair_connector_credential",
-            "connector_id",
-            "credential_id",
-        ),
-    )
-
-
 class DocumentByConnectorCredentialPair(Base):
     """Represents an indexing of a document by a specific connector / credential pair"""
 

backend/onyx/db/persona.py

@@ -205,9 +205,7 @@ def update_persona_access(
 
     NOTE: Callers are responsible for committing."""
 
-    needs_sync = False
     if is_public is not None:
-        needs_sync = True
         persona = db_session.query(Persona).filter(Persona.id == persona_id).first()
         if persona:
             persona.is_public = is_public
@@ -215,7 +213,6 @@ def update_persona_access(
     # NOTE: For user-ids and group-ids, `None` means "leave unchanged", `[]` means "clear all shares",
     # and a non-empty list means "replace with these shares".
     if user_ids is not None:
-        needs_sync = True
         db_session.query(Persona__User).filter(
             Persona__User.persona_id == persona_id
         ).delete(synchronize_session="fetch")
@@ -236,7 +233,6 @@ def update_persona_access(
     # MIT doesn't support group-based sharing, so we allow clearing (no-op since
     # there shouldn't be any) but raise an error if trying to add actual groups.
     if group_ids is not None:
-        needs_sync = True
         db_session.query(Persona__UserGroup).filter(
             Persona__UserGroup.persona_id == persona_id
         ).delete(synchronize_session="fetch")
@@ -244,10 +240,6 @@ def update_persona_access(
         if group_ids:
             raise NotImplementedError("Onyx MIT does not support group-based sharing")
 
-    # When sharing changes, user file ACLs need to be updated in the vector DB
-    if needs_sync:
-        mark_persona_user_files_for_sync(persona_id, db_session)
-
 
 def create_update_persona(
     persona_id: int | None,
@@ -859,24 +851,6 @@ def update_personas_display_priority(
         db_session.commit()
 
 
-def mark_persona_user_files_for_sync(
-    persona_id: int,
-    db_session: Session,
-) -> None:
-    """When persona sharing changes, mark all of its user files for sync
-    so that their ACLs get updated in the vector DB."""
-    persona = (
-        db_session.query(Persona)
-        .options(selectinload(Persona.user_files))
-        .filter(Persona.id == persona_id)
-        .first()
-    )
-    if not persona:
-        return
-    file_ids = [uf.id for uf in persona.user_files]
-    _mark_files_need_persona_sync(db_session, file_ids)
-
-
 def _mark_files_need_persona_sync(
     db_session: Session,
     user_file_ids: list[UUID],

backend/onyx/db/rotate_encryption_key.py

@@ -1,161 +0,0 @@
-"""Rotate encryption key for all encrypted columns.
-
-Dynamically discovers all columns using EncryptedString / EncryptedJson,
-decrypts each value with the old key, and re-encrypts with the current
-ENCRYPTION_KEY_SECRET.
-
-The operation is idempotent: rows already encrypted with the current key
-are skipped. Commits are made in batches so a crash mid-rotation can be
-safely resumed by re-running.
-"""
-
-import json
-from typing import Any
-
-from sqlalchemy import LargeBinary
-from sqlalchemy import select
-from sqlalchemy import update
-from sqlalchemy.orm import Session
-
-from onyx.configs.app_configs import ENCRYPTION_KEY_SECRET
-from onyx.db.models import Base
-from onyx.db.models import EncryptedJson
-from onyx.db.models import EncryptedString
-from onyx.utils.encryption import decrypt_bytes_to_string
-from onyx.utils.logger import setup_logger
-from onyx.utils.variable_functionality import global_version
-
-logger = setup_logger()
-
-_BATCH_SIZE = 500
-
-
-def _can_decrypt_with_current_key(data: bytes) -> bool:
-    """Check if data is already encrypted with the current key.
-
-    Passes the key explicitly so the fallback-to-raw-decode path in
-    _decrypt_bytes is NOT triggered — a clean success/failure signal.
-    """
-    try:
-        decrypt_bytes_to_string(data, key=ENCRYPTION_KEY_SECRET)
-        return True
-    except Exception:
-        return False
-
-
-def _discover_encrypted_columns() -> list[tuple[type, str, list[str], bool]]:
-    """Walk all ORM models and find columns using EncryptedString/EncryptedJson.
-
-    Returns list of (ModelClass, column_attr_name, [pk_attr_names], is_json).
-    """
-    results: list[tuple[type, str, list[str], bool]] = []
-
-    for mapper in Base.registry.mappers:
-        model_cls = mapper.class_
-        pk_names = [col.key for col in mapper.primary_key]
-
-        for prop in mapper.column_attrs:
-            for col in prop.columns:
-                if isinstance(col.type, EncryptedJson):
-                    results.append((model_cls, prop.key, pk_names, True))
-                elif isinstance(col.type, EncryptedString):
-                    results.append((model_cls, prop.key, pk_names, False))
-
-    return results
-
-
-def rotate_encryption_key(
-    db_session: Session,
-    old_key: str | None,
-    dry_run: bool = False,
-) -> dict[str, int]:
-    """Decrypt all encrypted columns with old_key and re-encrypt with the current key.
-
-    Args:
-        db_session: Active database session.
-        old_key: The previous encryption key. Pass None or "" if values were
-                 not previously encrypted with a key.
-        dry_run: If True, count rows that need rotation without modifying data.
-
-    Returns:
-        Dict of "table.column" -> number of rows re-encrypted (or would be).
-
-    Commits every _BATCH_SIZE rows so that locks are held briefly and progress
-    is preserved on crash. Already-rotated rows are detected and skipped,
-    making the operation safe to re-run.
-    """
-    if not global_version.is_ee_version():
-        raise RuntimeError("EE mode is not enabled — rotation requires EE encryption.")
-
-    if not ENCRYPTION_KEY_SECRET:
-        raise RuntimeError(
-            "ENCRYPTION_KEY_SECRET is not set — cannot rotate. "
-            "Set the target encryption key in the environment before running."
-        )
-
-    encrypted_columns = _discover_encrypted_columns()
-    totals: dict[str, int] = {}
-
-    for model_cls, col_name, pk_names, is_json in encrypted_columns:
-        table_name: str = model_cls.__tablename__  # type: ignore[attr-defined]
-        col_attr = getattr(model_cls, col_name)
-        pk_attrs = [getattr(model_cls, pk) for pk in pk_names]
-
-        # Read raw bytes directly, bypassing the TypeDecorator
-        raw_col = col_attr.property.columns[0]
-
-        stmt = select(*pk_attrs, raw_col.cast(LargeBinary)).where(col_attr.is_not(None))
-        rows = db_session.execute(stmt).all()
-
-        reencrypted = 0
-        batch_pending = 0
-        for row in rows:
-            raw_bytes: bytes | None = row[-1]
-            if raw_bytes is None:
-                continue
-
-            if _can_decrypt_with_current_key(raw_bytes):
-                continue
-
-            try:
-                if not old_key:
-                    decrypted_str = raw_bytes.decode("utf-8")
-                else:
-                    decrypted_str = decrypt_bytes_to_string(raw_bytes, key=old_key)
-
-                # For EncryptedJson, parse back to dict so the TypeDecorator
-                # can json.dumps() it cleanly (avoids double-encoding).
-                value: Any = json.loads(decrypted_str) if is_json else decrypted_str
-            except (ValueError, UnicodeDecodeError) as e:
-                pk_vals = [row[i] for i in range(len(pk_names))]
-                logger.warning(
-                    f"Could not decrypt/parse {table_name}.{col_name} "
-                    f"row {pk_vals} — skipping: {e}"
-                )
-                continue
-
-            if not dry_run:
-                pk_filters = [pk_attr == row[i] for i, pk_attr in enumerate(pk_attrs)]
-                update_stmt = (
-                    update(model_cls).where(*pk_filters).values({col_name: value})
-                )
-                db_session.execute(update_stmt)
-                batch_pending += 1
-
-                if batch_pending >= _BATCH_SIZE:
-                    db_session.commit()
-                    batch_pending = 0
-            reencrypted += 1
-
-        # Flush remaining rows in this column
-        if batch_pending > 0:
-            db_session.commit()
-
-        if reencrypted > 0:
-            totals[f"{table_name}.{col_name}"] = reencrypted
-            logger.info(
-                f"{'[DRY RUN] Would re-encrypt' if dry_run else 'Re-encrypted'} "
-                f"{reencrypted} value(s) in {table_name}.{col_name}"
-            )
-
-    return totals

backend/onyx/db/user_file.py

@@ -3,11 +3,9 @@ from uuid import UUID
 
 from sqlalchemy import func
 from sqlalchemy import select
-from sqlalchemy.orm import joinedload
 from sqlalchemy.orm import selectinload
 from sqlalchemy.orm import Session
 
-from onyx.db.models import Persona
 from onyx.db.models import Project__UserFile
 from onyx.db.models import UserFile
 
@@ -120,31 +118,3 @@ def get_file_ids_by_user_file_ids(
 ) -> list[str]:
     user_files = db_session.query(UserFile).filter(UserFile.id.in_(user_file_ids)).all()
     return [user_file.file_id for user_file in user_files]
-
-
-def fetch_user_files_with_access_relationships(
-    user_file_ids: list[str],
-    db_session: Session,
-    eager_load_groups: bool = False,
-) -> list[UserFile]:
-    """Fetch user files with the owner and assistant relationships
-    eagerly loaded (needed for computing access control).
-
-    When eager_load_groups is True, Persona.groups is also loaded so that
-    callers can extract user-group names without a second DB round-trip."""
-    persona_sub_options = [
-        selectinload(Persona.users),
-        selectinload(Persona.user),
-    ]
-    if eager_load_groups:
-        persona_sub_options.append(selectinload(Persona.groups))
-
-    return (
-        db_session.query(UserFile)
-        .options(
-            joinedload(UserFile.user),
-            selectinload(UserFile.assistants).options(*persona_sub_options),
-        )
-        .filter(UserFile.id.in_(user_file_ids))
-        .all()
-    )

backend/onyx/db/users.py

@@ -11,7 +11,6 @@ from sqlalchemy.orm import Session
 from sqlalchemy.sql import expression
 from sqlalchemy.sql.elements import ColumnElement
 from sqlalchemy.sql.elements import KeyedColumnElement
-from sqlalchemy.sql.expression import or_
 
 from onyx.auth.invited_users import remove_user_from_invited_users
 from onyx.auth.schemas import UserRole
@@ -25,7 +24,6 @@ from onyx.db.models import Persona__User
 from onyx.db.models import SamlAccount
 from onyx.db.models import User
 from onyx.db.models import User__UserGroup
-from onyx.db.models import UserGroup
 from onyx.utils.variable_functionality import fetch_ee_implementation_or_noop
 
 
@@ -164,13 +162,7 @@ def _get_accepted_user_where_clause(
         where_clause.append(User.role != UserRole.EXT_PERM_USER)
 
     if email_filter_string is not None:
-        personal_name_col: KeyedColumnElement[Any] = User.__table__.c.personal_name
-        where_clause.append(
-            or_(
-                email_col.ilike(f"%{email_filter_string}%"),
-                personal_name_col.ilike(f"%{email_filter_string}%"),
-            )
-        )
+        where_clause.append(email_col.ilike(f"%{email_filter_string}%"))
 
     if roles_filter:
         where_clause.append(User.role.in_(roles_filter))
@@ -181,30 +173,6 @@ def _get_accepted_user_where_clause(
     return where_clause
 
 
-def get_all_accepted_users(
-    db_session: Session,
-    include_external: bool = False,
-) -> Sequence[User]:
-    """Returns all accepted users without pagination.
-    Uses the same filtering as the paginated endpoint but without
-    search, role, or active filters."""
-    stmt = select(User)
-    where_clause = _get_accepted_user_where_clause(
-        include_external=include_external,
-    )
-    stmt = stmt.where(*where_clause)
-    return db_session.scalars(stmt).unique().all()
-
-
-_USER_SORTABLE_COLUMNS: dict[str, KeyedColumnElement[Any]] = {
-    "email": User.email,
-    "role": User.role,
-    "is_active": User.is_active,
-    "created_at": User.created_at,
-    "updated_at": User.updated_at,
-}
-
-
 def get_page_of_filtered_users(
     db_session: Session,
     page_size: int,
@@ -213,8 +181,6 @@ def get_page_of_filtered_users(
     is_active_filter: bool | None = None,
     roles_filter: list[UserRole] = [],
     include_external: bool = False,
-    sort_by: str | None = None,
-    sort_dir: str | None = None,
 ) -> Sequence[User]:
     users_stmt = select(User)
 
@@ -224,18 +190,10 @@ def get_page_of_filtered_users(
         include_external=include_external,
         is_active_filter=is_active_filter,
     )
-    # Apply filtering
-    users_stmt = users_stmt.where(*where_clause)
-
-    # Apply sorting
-    col = _USER_SORTABLE_COLUMNS.get(sort_by) if sort_by else None
-    if col is not None:
-        users_stmt = users_stmt.order_by(
-            col.desc() if sort_dir == "desc" else col.asc()
-        )
-
     # Apply pagination
     users_stmt = users_stmt.offset((page_num) * page_size).limit(page_size)
+    # Apply filtering
+    users_stmt = users_stmt.where(*where_clause)
 
     return db_session.scalars(users_stmt).unique().all()
 
@@ -260,36 +218,6 @@ def get_total_filtered_users_count(
     return db_session.scalar(total_count_stmt) or 0
 
 
-def get_user_counts_by_role_and_status(
-    db_session: Session,
-) -> dict[str, dict[str, int]]:
-    """Returns user counts grouped by role and by active/inactive status.
-
-    Excludes API key users, anonymous users, and no-auth placeholder users.
-    """
-    base_where = _get_accepted_user_where_clause()
-
-    # Counts by role
-    role_col = User.__table__.c.role
-    role_stmt = select(role_col, func.count()).where(*base_where).group_by(role_col)
-    role_counts: dict[str, int] = {}
-    for role_val, count in db_session.execute(role_stmt).all():
-        key = role_val.value if hasattr(role_val, "value") else str(role_val)
-        role_counts[key] = count
-
-    # Counts by is_active
-    is_active_col = User.__table__.c.is_active
-    status_stmt = (
-        select(is_active_col, func.count()).where(*base_where).group_by(is_active_col)
-    )
-    status_counts: dict[str, int] = {}
-    for is_active_val, count in db_session.execute(status_stmt).all():
-        key = "active" if is_active_val else "inactive"
-        status_counts[key] = count
-
-    return {"role_counts": role_counts, "status_counts": status_counts}
-
-
 def get_user_by_email(email: str, db_session: Session) -> User | None:
     user = (
         db_session.query(User)
@@ -430,28 +358,3 @@ def delete_user_from_db(
     # NOTE: edge case may exist with race conditions
     # with this `invited user` scheme generally.
     remove_user_from_invited_users(user_to_delete.email)
-
-
-def batch_get_user_groups(
-    db_session: Session,
-    user_ids: list[UUID],
-) -> dict[UUID, list[tuple[int, str]]]:
-    """Fetch group memberships for a batch of users in a single query.
-    Returns a mapping of user_id -> list of (group_id, group_name) tuples."""
-    if not user_ids:
-        return {}
-
-    rows = db_session.execute(
-        select(
-            User__UserGroup.user_id,
-            UserGroup.id,
-            UserGroup.name,
-        )
-        .join(UserGroup, UserGroup.id == User__UserGroup.user_group_id)
-        .where(User__UserGroup.user_id.in_(user_ids))
-    ).all()
-
-    result: dict[UUID, list[tuple[int, str]]] = {uid: [] for uid in user_ids}
-    for user_id, group_id, group_name in rows:
-        result[user_id].append((group_id, group_name))
-    return result

backend/onyx/document_index/opensearch/constants.py

@@ -1,10 +1,5 @@
 # Default value for the maximum number of tokens a chunk can hold, if none is
 # specified when creating an index.
-from onyx.configs.app_configs import (
-    OPENSEARCH_OVERRIDE_DEFAULT_NUM_HYBRID_SEARCH_CANDIDATES,
-)
-
-
 DEFAULT_MAX_CHUNK_SIZE = 512
 
 # Size of the dynamic list used to consider elements during kNN graph creation.
@@ -15,43 +10,27 @@ EF_CONSTRUCTION = 256
 # quality but increase memory footprint. Values typically range between 12 - 48.
 M = 32  # Set relatively high for better accuracy.
 
-# When performing hybrid search, we need to consider more candidates than the
-# number of results to be returned. This is because the scoring is hybrid and
-# the results are reordered due to the hybrid scoring. Higher = more candidates
-# for hybrid fusion = better retrieval accuracy, but results in more computation
-# per query. Imagine a simple case with a single keyword query and a single
-# vector query and we want 10 final docs. If we only fetch 10 candidates from
-# each of keyword and vector, they would have to have perfect overlap to get a
-# good hybrid ranking for the 10 results. If we fetch 1000 candidates from each,
-# we have a much higher chance of all 10 of the final desired docs showing up
-# and getting scored. In worse situations, the final 10 docs don't even show up
-# as the final 10 (worse than just a miss at the reranking step).
-DEFAULT_NUM_HYBRID_SEARCH_CANDIDATES = (
-    OPENSEARCH_OVERRIDE_DEFAULT_NUM_HYBRID_SEARCH_CANDIDATES
-    if OPENSEARCH_OVERRIDE_DEFAULT_NUM_HYBRID_SEARCH_CANDIDATES > 0
-    else 750
-)
+# When performing hybrid search, we need to consider more candidates than the number of results to be returned.
+# This is because the scoring is hybrid and the results are reordered due to the hybrid scoring.
+# Higher = more candidates for hybrid fusion = better retrieval accuracy, but results in more computation per query.
+# Imagine a simple case with a single keyword query and a single vector query and we want 10 final docs.
+# If we only fetch 10 candidates from each of keyword and vector, they would have to have perfect overlap to get a good hybrid
+# ranking for the 10 results. If we fetch 1000 candidates from each, we have a much higher chance of all 10 of the final desired
+# docs showing up and getting scored. In worse situations, the final 10 docs don't even show up as the final 10 (worse than just
+# a miss at the reranking step).
+DEFAULT_NUM_HYBRID_SEARCH_CANDIDATES = 750
 
-# Number of vectors to examine to decide the top k neighbors for the HNSW
-# method.
-# NOTE: "When creating a search query, you must specify k. If you provide both k
-# and ef_search, then the larger value is passed to the engine. If ef_search is
-# larger than k, you can provide the size parameter to limit the final number of
-# results to k." from
-# https://docs.opensearch.org/latest/query-dsl/specialized/k-nn/index/#ef_search
+# Number of vectors to examine for top k neighbors for the HNSW method.
 EF_SEARCH = DEFAULT_NUM_HYBRID_SEARCH_CANDIDATES
 
-# Since the titles are included in the contents, the embedding matches are
-# heavily downweighted as they act as a boost rather than an independent scoring
-# component.
+# Since the titles are included in the contents, they are heavily downweighted as they act as a boost
+# rather than an independent scoring component.
 SEARCH_TITLE_VECTOR_WEIGHT = 0.1
 SEARCH_CONTENT_VECTOR_WEIGHT = 0.45
-# Single keyword weight for both title and content (merged from former title
-# keyword + content keyword).
+# Single keyword weight for both title and content (merged from former title keyword + content keyword).
 SEARCH_KEYWORD_WEIGHT = 0.45
 
-# NOTE: It is critical that the order of these weights matches the order of the
-# sub-queries in the hybrid search.
+# NOTE: it is critical that the order of these weights matches the order of the sub-queries in the hybrid search.
 HYBRID_SEARCH_NORMALIZATION_WEIGHTS = [
     SEARCH_TITLE_VECTOR_WEIGHT,
     SEARCH_CONTENT_VECTOR_WEIGHT,

backend/onyx/document_index/opensearch/opensearch_document_index.py

@@ -433,16 +433,12 @@ class OpenSearchOldDocumentIndex(OldDocumentIndex):
             hidden=fields.hidden if fields else None,
             project_ids=(
                 set(user_fields.user_projects)
-                # NOTE: Empty user_projects is semantically different from None
-                # user_projects.
-                if user_fields and user_fields.user_projects is not None
+                if user_fields and user_fields.user_projects
                 else None
             ),
             persona_ids=(
                 set(user_fields.personas)
-                # NOTE: Empty personas is semantically different from None
-                # personas.
-                if user_fields and user_fields.personas is not None
+                if user_fields and user_fields.personas
                 else None
             ),
         )

backend/onyx/document_index/opensearch/search.py

@@ -255,12 +255,8 @@ class DocumentQuery:
                 f"result window ({DEFAULT_OPENSEARCH_MAX_RESULT_WINDOW})."
             )
 
-        # TODO(andrei, yuhong): We can tune this more dynamically based on
-        # num_hits.
-        max_results_per_subquery = DEFAULT_NUM_HYBRID_SEARCH_CANDIDATES
-
         hybrid_search_subqueries = DocumentQuery._get_hybrid_search_subqueries(
-            query_text, query_vector, vector_candidates=max_results_per_subquery
+            query_text, query_vector
         )
         hybrid_search_filters = DocumentQuery._get_search_filters(
             tenant_state=tenant_state,
@@ -289,16 +285,13 @@ class DocumentQuery:
         hybrid_search_query: dict[str, Any] = {
             "hybrid": {
                 "queries": hybrid_search_subqueries,
-                # Max results per subquery per shard before aggregation. Ensures
-                # keyword and vector subqueries contribute equally to the
-                # candidate pool for hybrid fusion.
+                # Max results per subquery per shard before aggregation. Ensures keyword and vector
+                # subqueries contribute equally to the candidate pool for hybrid fusion.
                 # Sources:
                 # https://docs.opensearch.org/latest/vector-search/ai-search/hybrid-search/pagination/
                 # https://opensearch.org/blog/navigating-pagination-in-hybrid-queries-with-the-pagination_depth-parameter/
-                "pagination_depth": max_results_per_subquery,
-                # Applied to all the sub-queries independently (this avoids
-                # subqueries having a lot of results thrown out during
-                # aggregation).
+                "pagination_depth": DEFAULT_NUM_HYBRID_SEARCH_CANDIDATES,
+                # Applied to all the sub-queries independently (this avoids having subqueries having a lot of results thrown out).
                 # Sources:
                 # https://docs.opensearch.org/latest/query-dsl/compound/hybrid/
                 # https://opensearch.org/blog/introducing-common-filter-support-for-hybrid-search-queries
@@ -381,10 +374,9 @@ class DocumentQuery:
     def _get_hybrid_search_subqueries(
         query_text: str,
         query_vector: list[float],
-        # The default number of neighbors to consider for knn vector similarity
-        # search. This is higher than the number of results because the scoring
-        # is hybrid. For a detailed breakdown, see where the default value is
-        # set.
+        # The default number of neighbors to consider for knn vector similarity search.
+        # This is higher than the number of results because the scoring is hybrid.
+        # for a detailed breakdown, see where the default value is set.
         vector_candidates: int = DEFAULT_NUM_HYBRID_SEARCH_CANDIDATES,
     ) -> list[dict[str, Any]]:
         """Returns subqueries for hybrid search.
@@ -408,27 +400,20 @@ class DocumentQuery:
         in a single hybrid query. Source:
         https://docs.opensearch.org/latest/query-dsl/compound/hybrid/
 
-        NOTE: Each query is independent during the search phase, there is no
-        backfilling of scores for missing query components. What this means is
-        that if a document was a good vector match but did not show up for
-        keyword, it gets a score of 0 for the keyword component of the hybrid
-        scoring. This is not as bad as just disregarding a score though as there
-        is normalization applied after. So really it is "increasing" the missing
-        score compared to if it was included and the range was renormalized.
-        This does however mean that between docs that have high scores for say
-        the vector field, the keyword scores between them are completely ignored
-        unless they also showed up in the keyword query as a reasonably high
-        match. TLDR, this is a bit of unique funky behavior but it seems ok.
+        NOTE: Each query is independent during the search phase, there is no backfilling of scores for missing query components.
+        What this means is that if a document was a good vector match but did not show up for keyword, it gets a score of 0 for
+        the keyword component of the hybrid scoring. This is not as bad as just disregarding a score though as there is
+        normalization applied after. So really it is "increasing" the missing score compared to if it was included and the range
+        was renormalized. This does however mean that between docs that have high scores for say the vector field, the keyword
+        scores between them are completely ignored unless they also showed up in the keyword query as a reasonably high match.
+        TLDR, this is a bit of unique funky behavior but it seems ok.
 
         NOTE: Options considered and rejected:
-        - minimum_should_match: Since it's hybrid search and users often provide
-          semantic queries, there is often a lot of terms, and very low number
-          of meaningful keywords (and a low ratio of keywords).
-        - fuzziness AUTO: Typo tolerance (0/1/2 edit distance by term length).
-          It's mostly for typos as the analyzer ("english" by default) already
-          does some stemming and tokenization. In testing datasets, this makes
-          recall slightly worse. It also is less performant so not really any
-          reason to do it.
+        - minimum_should_match: Since it's hybrid search and users often provide semantic queries, there is often a lot of terms,
+          and very low number of meaningful keywords (and a low ratio of keywords).
+        - fuzziness AUTO: typo tolerance (0/1/2 edit distance by term length). It's mostly for typos as the analyzer ("english by
+          default") already does some stemming and tokenization. In testing datasets, this makes recall slightly worse. It also is
+          less performant so not really any reason to do it.
 
         Args:
             query_text: The text of the query to search for.
@@ -738,13 +723,14 @@ class DocumentQuery:
             # document's metadata list.
             filter_clauses.append(_get_tag_filter(tags))
 
-        # Knowledge scope: explicit knowledge attachments restrict what an
-        # assistant can see. When none are set the assistant searches
-        # everything.
+        # Knowledge scope: explicit knowledge attachments restrict what
+        # an assistant can see.  When none are set the assistant
+        # searches everything.
         #
-        # project_id / persona_id are additive: they make overflowing user files
-        # findable but must NOT trigger the restriction on their own (an agent
-        # with no explicit knowledge should search everything).
+        # project_id / persona_id are additive: they make overflowing
+        # user files findable but must NOT trigger the restriction on
+        # their own (an agent with no explicit knowledge should search
+        # everything).
         has_knowledge_scope = (
             attached_document_ids
             or hierarchy_node_ids
@@ -772,8 +758,9 @@ class DocumentQuery:
                 knowledge_filter["bool"]["should"].append(
                     _get_document_set_filter(document_sets)
                 )
-            # Additive: widen scope to also cover overflowing user files, but
-            # only when an explicit restriction is already in effect.
+            # Additive: widen scope to also cover overflowing user
+            # files, but only when an explicit restriction is already
+            # in effect.
             if project_id is not None:
                 knowledge_filter["bool"]["should"].append(
                     _get_user_project_filter(project_id)

backend/onyx/document_index/vespa/index.py

@@ -690,12 +690,9 @@ class VespaIndex(DocumentIndex):
             )
 
         project_ids: set[int] | None = None
-        # NOTE: Empty user_projects is semantically different from None
-        # user_projects.
         if user_fields is not None and user_fields.user_projects is not None:
             project_ids = set(user_fields.user_projects)
         persona_ids: set[int] | None = None
-        # NOTE: Empty personas is semantically different from None personas.
         if user_fields is not None and user_fields.personas is not None:
             persona_ids = set(user_fields.personas)
         update_request = MetadataUpdateRequest(

backend/onyx/file_processing/file_types.py

@@ -19,16 +19,12 @@ class OnyxMimeTypes:
         PLAIN_TEXT_MIME_TYPE,
         "text/markdown",
         "text/x-markdown",
-        "text/x-log",
         "text/x-config",
         "text/tab-separated-values",
         "application/json",
         "application/xml",
         "text/xml",
         "application/x-yaml",
-        "application/yaml",
-        "text/yaml",
-        "text/x-yaml",
     }
     DOCUMENT_MIME_TYPES = {
         PDF_MIME_TYPE,

backend/onyx/key_value_store/interface.py

@@ -1,5 +1,4 @@
 import abc
-from typing import cast
 
 from onyx.utils.special_types import JSON_ro
 
@@ -8,19 +7,6 @@ class KvKeyNotFoundError(Exception):
     pass
 
 
-def unwrap_str(val: JSON_ro) -> str:
-    """Unwrap a string stored as {"value": str} in the encrypted KV store.
-    Also handles legacy plain-string values cached in Redis."""
-    if isinstance(val, dict):
-        try:
-            return cast(str, val["value"])
-        except KeyError:
-            raise ValueError(
-                f"Expected dict with 'value' key, got keys: {list(val.keys())}"
-            )
-    return cast(str, val)
-
-
 class KeyValueStore:
     # In the Multi Tenant case, the tenant context is picked up automatically, it does not need to be passed in
     # It's read from the global thread level variable

backend/onyx/llm/constants.py

@@ -43,7 +43,6 @@ WELL_KNOWN_PROVIDER_NAMES = [
     LlmProviderNames.AZURE,
     LlmProviderNames.OLLAMA_CHAT,
     LlmProviderNames.LM_STUDIO,
-    LlmProviderNames.LITELLM_PROXY,
 ]
 
 
@@ -60,7 +59,6 @@ PROVIDER_DISPLAY_NAMES: dict[str, str] = {
     "ollama": "Ollama",
     LlmProviderNames.OLLAMA_CHAT: "Ollama",
     LlmProviderNames.LM_STUDIO: "LM Studio",
-    LlmProviderNames.LITELLM_PROXY: "LiteLLM Proxy",
     "groq": "Groq",
     "anyscale": "Anyscale",
     "deepseek": "DeepSeek",
@@ -111,7 +109,6 @@ AGGREGATOR_PROVIDERS: set[str] = {
     LlmProviderNames.LM_STUDIO,
     LlmProviderNames.VERTEX_AI,
     LlmProviderNames.AZURE,
-    LlmProviderNames.LITELLM_PROXY,
 }
 
 # Model family name mappings for display name generation

backend/onyx/llm/well_known_providers/constants.py

@@ -11,8 +11,6 @@ OLLAMA_API_KEY_CONFIG_KEY = "OLLAMA_API_KEY"
 LM_STUDIO_PROVIDER_NAME = "lm_studio"
 LM_STUDIO_API_KEY_CONFIG_KEY = "LM_STUDIO_API_KEY"
 
-LITELLM_PROXY_PROVIDER_NAME = "litellm_proxy"
-
 # Providers that use optional Bearer auth from custom_config
 PROVIDERS_WITH_SPECIAL_API_KEY_HANDLING: dict[str, str] = {
     LlmProviderNames.OLLAMA_CHAT: OLLAMA_API_KEY_CONFIG_KEY,

backend/onyx/llm/well_known_providers/llm_provider_options.py

@@ -15,7 +15,6 @@ from onyx.llm.well_known_providers.auto_update_service import (
 from onyx.llm.well_known_providers.constants import ANTHROPIC_PROVIDER_NAME
 from onyx.llm.well_known_providers.constants import AZURE_PROVIDER_NAME
 from onyx.llm.well_known_providers.constants import BEDROCK_PROVIDER_NAME
-from onyx.llm.well_known_providers.constants import LITELLM_PROXY_PROVIDER_NAME
 from onyx.llm.well_known_providers.constants import LM_STUDIO_PROVIDER_NAME
 from onyx.llm.well_known_providers.constants import OLLAMA_PROVIDER_NAME
 from onyx.llm.well_known_providers.constants import OPENAI_PROVIDER_NAME
@@ -48,7 +47,6 @@ def _get_provider_to_models_map() -> dict[str, list[str]]:
         OLLAMA_PROVIDER_NAME: [],  # Dynamic - fetched from Ollama API
         LM_STUDIO_PROVIDER_NAME: [],  # Dynamic - fetched from LM Studio API
         OPENROUTER_PROVIDER_NAME: [],  # Dynamic - fetched from OpenRouter API
-        LITELLM_PROXY_PROVIDER_NAME: [],  # Dynamic - fetched from LiteLLM proxy API
     }
 
 
@@ -333,7 +331,6 @@ def get_provider_display_name(provider_name: str) -> str:
         BEDROCK_PROVIDER_NAME: "Amazon Bedrock",
         VERTEXAI_PROVIDER_NAME: "Google Vertex AI",
         OPENROUTER_PROVIDER_NAME: "OpenRouter",
-        LITELLM_PROXY_PROVIDER_NAME: "LiteLLM Proxy",
     }
 
     if provider_name in _ONYX_PROVIDER_DISPLAY_NAMES:

backend/onyx/mcp_server/tools/search.py

@@ -10,7 +10,6 @@ from onyx.mcp_server.utils import get_indexed_sources
 from onyx.mcp_server.utils import require_access_token
 from onyx.utils.logger import setup_logger
 from onyx.utils.variable_functionality import build_api_server_url_for_http_requests
-from onyx.utils.variable_functionality import global_version
 
 logger = setup_logger()
 
@@ -27,14 +26,6 @@ async def search_indexed_documents(
     Use this tool for information that is not public knowledge and specific to the user,
     their team, their work, or their organization/company.
 
-    Note: In CE mode, this tool uses the chat endpoint internally which invokes an LLM
-    on every call, consuming tokens and adding latency.
-    Additionally, CE callers receive a truncated snippet (blurb) instead of a full document chunk,
-    but this should still be sufficient for most use cases. CE mode functionality should be swapped
-    when a dedicated CE search endpoint is implemented.
-
-    In EE mode, the dedicated search endpoint is used instead.
-
     To find a list of available sources, use the `indexed_sources` resource.
     Returns chunks of text as search results with snippets, scores, and metadata.
 
@@ -120,72 +111,47 @@ async def search_indexed_documents(
         if time_cutoff_dt:
             filters["time_cutoff"] = time_cutoff_dt.isoformat()
 
-    is_ee = global_version.is_ee_version()
-    base_url = build_api_server_url_for_http_requests(respect_env_override_if_set=True)
-    auth_headers = {"Authorization": f"Bearer {access_token.token}"}
-
-    search_request: dict[str, Any]
-    if is_ee:
-        # EE: use the dedicated search endpoint (no LLM invocation)
-        search_request = {
-            "search_query": query,
-            "filters": filters,
-            "num_docs_fed_to_llm_selection": limit,
-            "run_query_expansion": False,
-            "include_content": True,
-            "stream": False,
-        }
-        endpoint = f"{base_url}/search/send-search-message"
-        error_key = "error"
-        docs_key = "search_docs"
-        content_field = "content"
-    else:
-        # CE: fall back to the chat endpoint (invokes LLM, consumes tokens)
-        search_request = {
-            "message": query,
-            "stream": False,
-            "chat_session_info": {},
-        }
-        if filters:
-            search_request["internal_search_filters"] = filters
-        endpoint = f"{base_url}/chat/send-chat-message"
-        error_key = "error_msg"
-        docs_key = "top_documents"
-        content_field = "blurb"
+    # Build the search request using the new SendSearchQueryRequest format
+    search_request = {
+        "search_query": query,
+        "filters": filters,
+        "num_docs_fed_to_llm_selection": limit,
+        "run_query_expansion": False,
+        "include_content": True,
+        "stream": False,
+    }
 
+    # Call the API server using the new send-search-message route
     try:
         response = await get_http_client().post(
-            endpoint,
+            f"{build_api_server_url_for_http_requests(respect_env_override_if_set=True)}/search/send-search-message",
             json=search_request,
-            headers=auth_headers,
+            headers={"Authorization": f"Bearer {access_token.token}"},
         )
         response.raise_for_status()
         result = response.json()
 
         # Check for error in response
-        if result.get(error_key):
+        if result.get("error"):
             return {
                 "documents": [],
                 "total_results": 0,
                 "query": query,
-                "error": result.get(error_key),
+                "error": result.get("error"),
             }
 
-        documents = [
-            {
-                "semantic_identifier": doc.get("semantic_identifier"),
-                "content": doc.get(content_field),
-                "source_type": doc.get("source_type"),
-                "link": doc.get("link"),
-                "score": doc.get("score"),
-            }
-            for doc in result.get(docs_key, [])
+        # Return simplified format for MCP clients
+        fields_to_return = [
+            "semantic_identifier",
+            "content",
+            "source_type",
+            "link",
+            "score",
+        ]
+        documents = [
+            {key: doc.get(key) for key in fields_to_return}
+            for doc in result.get("search_docs", [])
         ]
-
-        # NOTE: search depth is controlled by the backend persona defaults, not `limit`.
-        # `limit` only caps the returned list; fewer results may be returned if the
-        # backend retrieves fewer documents than requested.
-        documents = documents[:limit]
 
         logger.info(
             f"Onyx MCP Server: Internal search returned {len(documents)} results"
@@ -194,6 +160,7 @@ async def search_indexed_documents(
             "documents": documents,
             "total_results": len(documents),
             "query": query,
+            "executed_queries": result.get("all_executed_queries", [query]),
         }
     except Exception as e:
         logger.error(f"Onyx MCP Server: Document search error: {e}", exc_info=True)

backend/onyx/redis/redis_hierarchy.py

@@ -16,7 +16,6 @@ Cache Strategy:
   using only the SOURCE-type node as the ancestor
 """
 
-from typing import cast
 from typing import TYPE_CHECKING
 
 from pydantic import BaseModel
@@ -205,30 +204,6 @@ def cache_hierarchy_nodes_batch(
     redis_client.expire(raw_id_key, HIERARCHY_CACHE_TTL_SECONDS)
 
 
-def evict_hierarchy_nodes_from_cache(
-    redis_client: Redis,
-    source: DocumentSource,
-    raw_node_ids: list[str],
-) -> None:
-    """Remove specific hierarchy nodes from the Redis cache.
-
-    Deletes entries from both the parent-chain hash and the raw_id→node_id hash.
-    """
-    if not raw_node_ids:
-        return
-
-    cache_key = _cache_key(source)
-    raw_id_key = _raw_id_cache_key(source)
-
-    # Look up node_ids so we can remove them from the parent-chain hash
-    raw_values = cast(list[str | None], redis_client.hmget(raw_id_key, raw_node_ids))
-    node_id_strs = [v for v in raw_values if v is not None]
-
-    if node_id_strs:
-        redis_client.hdel(cache_key, *node_id_strs)
-    redis_client.hdel(raw_id_key, *raw_node_ids)
-
-
 def get_node_id_from_raw_id(
     redis_client: Redis,
     source: DocumentSource,

backend/onyx/server/documents/connector.py

@@ -1905,7 +1905,7 @@ def get_connector_by_id(
 @router.post("/connector-request")
 def submit_connector_request(
     request_data: ConnectorRequestSubmission,
-    user: User = Depends(current_user),
+    user: User | None = Depends(current_user),
 ) -> StatusResponse:
     """
     Submit a connector request for Cloud deployments.
@@ -1918,7 +1918,7 @@ def submit_connector_request(
         raise HTTPException(status_code=400, detail="Connector name cannot be empty")
 
     # Get user identifier for telemetry
-    user_email = user.email
+    user_email = user.email if user else None
     distinct_id = user_email or tenant_id
 
     # Track connector request via PostHog telemetry (Cloud only)

backend/onyx/server/features/build/api/messages_api.py

@@ -57,6 +57,9 @@ def list_messages(
     db_session: Session = Depends(get_session),
 ) -> MessageListResponse:
     """Get all messages for a build session."""
+    if user is None:
+        raise HTTPException(status_code=401, detail="Authentication required")
+
     session_manager = SessionManager(db_session)
 
     messages = session_manager.list_messages(session_id, user.id)

backend/onyx/server/features/build/sandbox/kubernetes/docker/templates/outputs/web/package-lock.json

@@ -7424,9 +7424,9 @@
       }
     },
     "node_modules/hono": {
-      "version": "4.12.7",
-      "resolved": "https://registry.npmjs.org/hono/-/hono-4.12.7.tgz",
-      "integrity": "sha512-jq9l1DM0zVIvsm3lv9Nw9nlJnMNPOcAtsbsgiUhWcFzPE99Gvo6yRTlszSLLYacMeQ6quHD6hMfId8crVHvexw==",
+      "version": "4.12.5",
+      "resolved": "https://registry.npmjs.org/hono/-/hono-4.12.5.tgz",
+      "integrity": "sha512-3qq+FUBtlTHhtYxbxheZgY8NIFnkkC/MR8u5TTsr7YZ3wixryQ3cCwn3iZbg8p8B88iDBBAYSfZDS75t8MN7Vg==",
       "license": "MIT",
       "engines": {
         "node": ">=16.9.0"

backend/onyx/server/features/hierarchy/api.py

@@ -54,14 +54,18 @@ def _require_opensearch(db_session: Session) -> None:
         )
 
 
-def _get_user_access_info(user: User, db_session: Session) -> tuple[str, list[str]]:
+def _get_user_access_info(
+    user: User | None, db_session: Session
+) -> tuple[str | None, list[str]]:
+    if not user:
+        return None, []
     return user.email, get_user_external_group_ids(db_session, user)
 
 
 @router.get(HIERARCHY_NODES_LIST_PATH)
 def list_accessible_hierarchy_nodes(
     source: DocumentSource,
-    user: User = Depends(current_user),
+    user: User | None = Depends(current_user),
     db_session: Session = Depends(get_session),
 ) -> HierarchyNodesResponse:
     _require_opensearch(db_session)
@@ -88,7 +92,7 @@ def list_accessible_hierarchy_nodes(
 @router.post(HIERARCHY_NODE_DOCUMENTS_PATH)
 def list_accessible_hierarchy_node_documents(
     documents_request: HierarchyNodeDocumentsRequest,
-    user: User = Depends(current_user),
+    user: User | None = Depends(current_user),
     db_session: Session = Depends(get_session),
 ) -> HierarchyNodeDocumentsResponse:
     _require_opensearch(db_session)

backend/onyx/server/features/mcp/api.py

@@ -1013,7 +1013,7 @@ def get_mcp_servers_for_assistant(
 @router.get("/servers", response_model=MCPServersResponse)
 def get_mcp_servers_for_user(
     db: Session = Depends(get_session),
-    user: User = Depends(current_user),
+    user: User | None = Depends(current_user),
 ) -> MCPServersResponse:
     """List all MCP servers for use in agent configuration and chat UI.
 

backend/onyx/server/features/projects/projects_file_utils.py

@@ -10,8 +10,6 @@ from pydantic import Field
 from sqlalchemy.orm import Session
 
 from onyx.configs.app_configs import FILE_TOKEN_COUNT_THRESHOLD
-from onyx.configs.app_configs import USER_FILE_MAX_UPLOAD_SIZE_BYTES
-from onyx.configs.app_configs import USER_FILE_MAX_UPLOAD_SIZE_MB
 from onyx.db.llm import fetch_default_llm_model
 from onyx.file_processing.extract_file_text import extract_file_text
 from onyx.file_processing.extract_file_text import get_file_ext
@@ -37,38 +35,6 @@ def get_safe_filename(upload: UploadFile) -> str:
     return upload.filename
 
 
-def get_upload_size_bytes(upload: UploadFile) -> int | None:
-    """Best-effort file size in bytes without consuming the stream."""
-    if upload.size is not None:
-        return upload.size
-
-    try:
-        current_pos = upload.file.tell()
-        upload.file.seek(0, 2)
-        size = upload.file.tell()
-        upload.file.seek(current_pos)
-        return size
-    except Exception as e:
-        logger.warning(
-            "Could not determine upload size via stream seek "
-            f"(filename='{get_safe_filename(upload)}', "
-            f"error_type={type(e).__name__}, error={e})"
-        )
-        return None
-
-
-def is_upload_too_large(upload: UploadFile, max_bytes: int) -> bool:
-    """Return True when upload size is known and exceeds max_bytes."""
-    size_bytes = get_upload_size_bytes(upload)
-    if size_bytes is None:
-        logger.warning(
-            "Could not determine upload size; skipping size-limit check for "
-            f"'{get_safe_filename(upload)}'"
-        )
-        return False
-    return size_bytes > max_bytes
-
-
 # Guard against extremely large images
 Image.MAX_IMAGE_PIXELS = 12000 * 12000
 
@@ -193,18 +159,6 @@ def categorize_uploaded_files(
     for upload in files:
         try:
             filename = get_safe_filename(upload)
-
-            # Size limit is a hard safety cap and is enforced even when token
-            # threshold checks are skipped via SKIP_USERFILE_THRESHOLD settings.
-            if is_upload_too_large(upload, USER_FILE_MAX_UPLOAD_SIZE_BYTES):
-                results.rejected.append(
-                    RejectedFile(
-                        filename=filename,
-                        reason=f"Exceeds {USER_FILE_MAX_UPLOAD_SIZE_MB} MB file size limit",
-                    )
-                )
-                continue
-
             extension = get_file_ext(filename)
 
             # If image, estimate tokens via dedicated method first

backend/onyx/server/manage/users.py

@@ -5,7 +5,6 @@ from datetime import datetime
 from datetime import timedelta
 from datetime import timezone
 from typing import cast
-from uuid import UUID
 
 import jwt
 from email_validator import EmailNotValidError
@@ -19,7 +18,6 @@ from fastapi import Query
 from fastapi import Request
 from fastapi.responses import StreamingResponse
 from pydantic import BaseModel
-from sqlalchemy import select
 from sqlalchemy.orm import Session
 
 from onyx.auth.anonymous_user import fetch_anonymous_user_info
@@ -69,14 +67,11 @@ from onyx.db.user_preferences import update_user_role
 from onyx.db.user_preferences import update_user_shortcut_enabled
 from onyx.db.user_preferences import update_user_temperature_override_enabled
 from onyx.db.user_preferences import update_user_theme_preference
-from onyx.db.users import batch_get_user_groups
 from onyx.db.users import delete_user_from_db
-from onyx.db.users import get_all_accepted_users
 from onyx.db.users import get_all_users
 from onyx.db.users import get_page_of_filtered_users
 from onyx.db.users import get_total_filtered_users_count
 from onyx.db.users import get_user_by_email
-from onyx.db.users import get_user_counts_by_role_and_status
 from onyx.db.users import validate_user_role_update
 from onyx.key_value_store.factory import get_kv_store
 from onyx.redis.redis_pool import get_raw_redis_client
@@ -103,7 +98,6 @@ from onyx.server.manage.models import UserSpecificAssistantPreferences
 from onyx.server.models import FullUserSnapshot
 from onyx.server.models import InvitedUserSnapshot
 from onyx.server.models import MinimalUserSnapshot
-from onyx.server.models import UserGroupInfo
 from onyx.server.usage_limits import is_tenant_on_trial_fn
 from onyx.server.utils import BasicAuthenticationError
 from onyx.utils.logger import setup_logger
@@ -183,8 +177,6 @@ def list_accepted_users(
     page_size: int = Query(10, ge=1, le=1000),
     roles: list[UserRole] = Query(default=[]),
     is_active: bool | None = Query(default=None),
-    sort_by: str | None = Query(default=None),
-    sort_dir: str | None = Query(default=None),
     _: User = Depends(current_admin_user),
     db_session: Session = Depends(get_session),
 ) -> PaginatedReturn[FullUserSnapshot]:
@@ -195,8 +187,6 @@ def list_accepted_users(
         email_filter_string=q,
         is_active_filter=is_active,
         roles_filter=roles,
-        sort_by=sort_by,
-        sort_dir=sort_dir,
     )
 
     total_accepted_users_count = get_total_filtered_users_count(
@@ -213,75 +203,14 @@ def list_accepted_users(
             total_items=0,
         )
 
-    user_ids = [user.id for user in filtered_accepted_users]
-    groups_by_user = batch_get_user_groups(db_session, user_ids)
-
-    # Batch-fetch SCIM mappings to mark synced users
-    scim_synced_ids: set[UUID] = set()
-    try:
-        from onyx.db.models import ScimUserMapping
-
-        scim_mappings = db_session.scalars(
-            select(ScimUserMapping.user_id).where(ScimUserMapping.user_id.in_(user_ids))
-        ).all()
-        scim_synced_ids = set(scim_mappings)
-    except Exception:
-        logger.warning(
-            "Failed to fetch SCIM mappings; marking all users as non-synced",
-            exc_info=True,
-        )
-
     return PaginatedReturn(
         items=[
-            FullUserSnapshot.from_user_model(
-                user,
-                groups=[
-                    UserGroupInfo(id=gid, name=gname)
-                    for gid, gname in groups_by_user.get(user.id, [])
-                ],
-                is_scim_synced=user.id in scim_synced_ids,
-            )
-            for user in filtered_accepted_users
+            FullUserSnapshot.from_user_model(user) for user in filtered_accepted_users
         ],
         total_items=total_accepted_users_count,
     )
 
 
-@router.get("/manage/users/accepted/all", tags=PUBLIC_API_TAGS)
-def list_all_accepted_users(
-    _: User = Depends(current_admin_user),
-    db_session: Session = Depends(get_session),
-) -> list[FullUserSnapshot]:
-    """Returns all accepted users without pagination.
-    Used by the admin Users page for client-side filtering/sorting."""
-    users = get_all_accepted_users(db_session=db_session)
-
-    if not users:
-        return []
-
-    user_ids = [user.id for user in users]
-    groups_by_user = batch_get_user_groups(db_session, user_ids)
-
-    return [
-        FullUserSnapshot.from_user_model(
-            user,
-            groups=[
-                UserGroupInfo(id=gid, name=gname)
-                for gid, gname in groups_by_user.get(user.id, [])
-            ],
-        )
-        for user in users
-    ]
-
-
-@router.get("/manage/users/counts")
-def get_user_counts(
-    _: User = Depends(current_admin_user),
-    db_session: Session = Depends(get_session),
-) -> dict[str, dict[str, int]]:
-    return get_user_counts_by_role_and_status(db_session)
-
-
 @router.get("/manage/users/invited", tags=PUBLIC_API_TAGS)
 def list_invited_users(
     _: User = Depends(current_admin_user),
@@ -340,10 +269,24 @@ def list_all_users(
     if accepted_page is None or invited_page is None or slack_users_page is None:
         return AllUsersResponse(
             accepted=[
-                FullUserSnapshot.from_user_model(user) for user in accepted_users
+                FullUserSnapshot(
+                    id=user.id,
+                    email=user.email,
+                    role=user.role,
+                    is_active=user.is_active,
+                    password_configured=user.password_configured,
+                )
+                for user in accepted_users
             ],
             slack_users=[
-                FullUserSnapshot.from_user_model(user) for user in slack_users
+                FullUserSnapshot(
+                    id=user.id,
+                    email=user.email,
+                    role=user.role,
+                    is_active=user.is_active,
+                    password_configured=user.password_configured,
+                )
+                for user in slack_users
             ],
             invited=[InvitedUserSnapshot(email=email) for email in invited_emails],
             accepted_pages=1,
@@ -353,10 +296,26 @@ def list_all_users(
 
     # Otherwise, return paginated results
     return AllUsersResponse(
-        accepted=[FullUserSnapshot.from_user_model(user) for user in accepted_users][
-            accepted_page * USERS_PAGE_SIZE : (accepted_page + 1) * USERS_PAGE_SIZE
-        ],
-        slack_users=[FullUserSnapshot.from_user_model(user) for user in slack_users][
+        accepted=[
+            FullUserSnapshot(
+                id=user.id,
+                email=user.email,
+                role=user.role,
+                is_active=user.is_active,
+                password_configured=user.password_configured,
+            )
+            for user in accepted_users
+        ][accepted_page * USERS_PAGE_SIZE : (accepted_page + 1) * USERS_PAGE_SIZE],
+        slack_users=[
+            FullUserSnapshot(
+                id=user.id,
+                email=user.email,
+                role=user.role,
+                is_active=user.is_active,
+                password_configured=user.password_configured,
+            )
+            for user in slack_users
+        ][
             slack_users_page
             * USERS_PAGE_SIZE : (slack_users_page + 1)
             * USERS_PAGE_SIZE

backend/onyx/server/models.py

@@ -1,4 +1,3 @@
-import datetime
 from typing import Generic
 from typing import Optional
 from typing import TypeVar
@@ -32,41 +31,21 @@ class MinimalUserSnapshot(BaseModel):
     email: str
 
 
-class UserGroupInfo(BaseModel):
-    id: int
-    name: str
-
-
 class FullUserSnapshot(BaseModel):
     id: UUID
     email: str
     role: UserRole
     is_active: bool
     password_configured: bool
-    personal_name: str | None
-    created_at: datetime.datetime
-    updated_at: datetime.datetime
-    groups: list[UserGroupInfo]
-    is_scim_synced: bool
 
     @classmethod
-    def from_user_model(
-        cls,
-        user: User,
-        groups: list[UserGroupInfo] | None = None,
-        is_scim_synced: bool = False,
-    ) -> "FullUserSnapshot":
+    def from_user_model(cls, user: User) -> "FullUserSnapshot":
         return cls(
             id=user.id,
             email=user.email,
             role=user.role,
             is_active=user.is_active,
             password_configured=user.password_configured,
-            personal_name=user.personal_name,
-            created_at=user.created_at,
-            updated_at=user.updated_at,
-            groups=groups or [],
-            is_scim_synced=is_scim_synced,
         )
 
 

backend/onyx/server/query_and_chat/streaming_models.py

@@ -42,7 +42,6 @@ class StreamingType(Enum):
     REASONING_DONE = "reasoning_done"
     CITATION_INFO = "citation_info"
     TOOL_CALL_DEBUG = "tool_call_debug"
-    TOOL_CALL_ARGUMENT_DELTA = "tool_call_argument_delta"
 
     MEMORY_TOOL_START = "memory_tool_start"
     MEMORY_TOOL_DELTA = "memory_tool_delta"
@@ -277,15 +276,6 @@ class CustomToolDelta(BaseObj):
     error: CustomToolErrorInfo | None = None
 
 
-class ToolCallArgumentDelta(BaseObj):
-    type: Literal["tool_call_argument_delta"] = (
-        StreamingType.TOOL_CALL_ARGUMENT_DELTA.value
-    )
-
-    tool_type: str
-    argument_deltas: dict[str, Any]
-
-
 ################################################
 # File Reader Packets
 ################################################
@@ -407,7 +397,6 @@ PacketObj = Union[
     # Citation Packets
     CitationInfo,
     ToolCallDebug,
-    ToolCallArgumentDelta,
     # Deep Research Packets
     DeepResearchPlanStart,
     DeepResearchPlanDelta,

backend/onyx/server/settings/models.py

@@ -78,7 +78,6 @@ class Settings(BaseModel):
 
     # User Knowledge settings
     user_knowledge_enabled: bool | None = True
-    user_file_max_upload_size_mb: int | None = None
 
     # Connector settings
     show_extra_connectors: bool | None = True

backend/onyx/server/settings/store.py

@@ -3,7 +3,6 @@ from onyx.configs.app_configs import DISABLE_USER_KNOWLEDGE
 from onyx.configs.app_configs import ENABLE_OPENSEARCH_INDEXING_FOR_ONYX
 from onyx.configs.app_configs import ONYX_QUERY_HISTORY_TYPE
 from onyx.configs.app_configs import SHOW_EXTRA_CONNECTORS
-from onyx.configs.app_configs import USER_FILE_MAX_UPLOAD_SIZE_MB
 from onyx.configs.constants import KV_SETTINGS_KEY
 from onyx.configs.constants import OnyxRedisLocks
 from onyx.key_value_store.factory import get_kv_store
@@ -51,7 +50,6 @@ def load_settings() -> Settings:
     if DISABLE_USER_KNOWLEDGE:
         settings.user_knowledge_enabled = False
 
-    settings.user_file_max_upload_size_mb = USER_FILE_MAX_UPLOAD_SIZE_MB
     settings.show_extra_connectors = SHOW_EXTRA_CONNECTORS
     settings.opensearch_indexing_enabled = ENABLE_OPENSEARCH_INDEXING_FOR_ONYX
     return settings

backend/onyx/tools/built_in_tools.py

@@ -56,23 +56,3 @@ def get_built_in_tool_ids() -> list[str]:
 
 def get_built_in_tool_by_id(in_code_tool_id: str) -> Type[BUILT_IN_TOOL_TYPES]:
     return BUILT_IN_TOOL_MAP[in_code_tool_id]
-
-
-def _build_tool_name_to_class() -> dict[str, Type[BUILT_IN_TOOL_TYPES]]:
-    """Build a mapping from LLM-facing tool name to tool class."""
-    result: dict[str, Type[BUILT_IN_TOOL_TYPES]] = {}
-    for cls in BUILT_IN_TOOL_MAP.values():
-        name_attr = cls.__dict__.get("name")
-        if isinstance(name_attr, property) and name_attr.fget is not None:
-            tool_name = name_attr.fget(cls)
-        elif isinstance(name_attr, str):
-            tool_name = name_attr
-        else:
-            raise ValueError(
-                f"Built-in tool {cls.__name__} must define a valid LLM-facing tool name"
-            )
-        result[tool_name] = cls
-    return result
-
-
-TOOL_NAME_TO_CLASS: dict[str, Type[BUILT_IN_TOOL_TYPES]] = _build_tool_name_to_class()

backend/onyx/tools/interface.py

@@ -92,7 +92,3 @@ class Tool(abc.ABC, Generic[TOverride]):
         **llm_kwargs: Any,
     ) -> ToolResponse:
         raise NotImplementedError
-
-    @classmethod
-    def should_emit_argument_deltas(cls) -> bool:
-        return False

backend/onyx/tools/tool_implementations/python/python_tool.py

@@ -376,8 +376,3 @@ class PythonTool(Tool[PythonToolOverrideKwargs]):
                     rich_response=None,
                     llm_facing_response=llm_response,
                 )
-
-    @classmethod
-    @override
-    def should_emit_argument_deltas(cls) -> bool:
-        return True

backend/onyx/utils/encryption.py

@@ -11,20 +11,16 @@ logger = setup_logger()
 
 
 # IMPORTANT DO NOT DELETE, THIS IS USED BY fetch_versioned_implementation
-def _encrypt_string(input_str: str, key: str | None = None) -> bytes:  # noqa: ARG001
+def _encrypt_string(input_str: str) -> bytes:
     if ENCRYPTION_KEY_SECRET:
         logger.warning("MIT version of Onyx does not support encryption of secrets.")
-    elif key is not None:
-        logger.debug("MIT encrypt called with explicit key — key ignored.")
     return input_str.encode()
 
 
 # IMPORTANT DO NOT DELETE, THIS IS USED BY fetch_versioned_implementation
-def _decrypt_bytes(input_bytes: bytes, key: str | None = None) -> str:  # noqa: ARG001
-    if ENCRYPTION_KEY_SECRET:
-        logger.warning("MIT version of Onyx does not support decryption of secrets.")
-    elif key is not None:
-        logger.debug("MIT decrypt called with explicit key — key ignored.")
+def _decrypt_bytes(input_bytes: bytes) -> str:
+    # No need to double warn. If you wish to learn more about encryption features
+    # refer to the Onyx EE code
     return input_bytes.decode()
 
 
@@ -90,15 +86,15 @@ def _mask_list(items: list[Any]) -> list[Any]:
     return masked
 
 
-def encrypt_string_to_bytes(intput_str: str, key: str | None = None) -> bytes:
+def encrypt_string_to_bytes(intput_str: str) -> bytes:
     versioned_encryption_fn = fetch_versioned_implementation(
         "onyx.utils.encryption", "_encrypt_string"
     )
-    return versioned_encryption_fn(intput_str, key=key)
+    return versioned_encryption_fn(intput_str)
 
 
-def decrypt_bytes_to_string(intput_bytes: bytes, key: str | None = None) -> str:
+def decrypt_bytes_to_string(intput_bytes: bytes) -> str:
     versioned_decryption_fn = fetch_versioned_implementation(
         "onyx.utils.encryption", "_decrypt_bytes"
     )
-    return versioned_decryption_fn(intput_bytes, key=key)
+    return versioned_decryption_fn(intput_bytes)

backend/onyx/utils/sensitive.py

@@ -128,8 +128,6 @@ class SensitiveValue(Generic[T]):
         value = self._decrypt()
 
         if not apply_mask:
-            # Callers must not mutate the returned dict — doing so would
-            # desync the cache from the encrypted bytes and the DB.
             return value
 
         # Apply masking
@@ -176,20 +174,18 @@ class SensitiveValue(Generic[T]):
         )
 
     def __eq__(self, other: Any) -> bool:
-        """Compare SensitiveValues by their decrypted content."""
-        # NOTE: if you attempt to compare a string/dict to a SensitiveValue,
-        # this comparison will return NotImplemented, which then evaluates to False.
-        # This is the convention and required for SQLAlchemy's attribute tracking.
-        if not isinstance(other, SensitiveValue):
-            return NotImplemented
-        return self._decrypt() == other._decrypt()
+        """Prevent direct comparison which might expose value."""
+        if isinstance(other, SensitiveValue):
+            # Compare encrypted bytes for equality check
+            return self._encrypted_bytes == other._encrypted_bytes
+        raise SensitiveAccessError(
+            "Cannot compare SensitiveValue with non-SensitiveValue. "
+            "Use .get_value(apply_mask=True/False) to access the value for comparison."
+        )
 
     def __hash__(self) -> int:
-        """Hash based on decrypted content."""
-        value = self._decrypt()
-        if isinstance(value, dict):
-            return hash(json.dumps(value, sort_keys=True))
-        return hash(value)
+        """Allow hashing based on encrypted bytes."""
+        return hash(self._encrypted_bytes)
 
     # Prevent JSON serialization
     def __json__(self) -> Any:

backend/onyx/utils/telemetry.py

@@ -2,6 +2,7 @@ import contextvars
 import threading
 import uuid
 from enum import Enum
+from typing import cast
 
 import requests
 
@@ -14,7 +15,6 @@ from onyx.db.engine.sql_engine import get_session_with_current_tenant
 from onyx.db.models import User
 from onyx.key_value_store.factory import get_kv_store
 from onyx.key_value_store.interface import KvKeyNotFoundError
-from onyx.key_value_store.interface import unwrap_str
 from onyx.utils.logger import setup_logger
 from onyx.utils.variable_functionality import (
     fetch_versioned_implementation_with_fallback,
@@ -25,7 +25,6 @@ from shared_configs.contextvars import get_current_tenant_id
 
 logger = setup_logger()
 
-
 _DANSWER_TELEMETRY_ENDPOINT = "https://telemetry.onyx.app/anonymous_telemetry"
 _CACHED_UUID: str | None = None
 _CACHED_INSTANCE_DOMAIN: str | None = None
@@ -63,10 +62,10 @@ def get_or_generate_uuid() -> str:
     kv_store = get_kv_store()
 
     try:
-        _CACHED_UUID = unwrap_str(kv_store.load(KV_CUSTOMER_UUID_KEY))
+        _CACHED_UUID = cast(str, kv_store.load(KV_CUSTOMER_UUID_KEY))
     except KvKeyNotFoundError:
         _CACHED_UUID = str(uuid.uuid4())
-        kv_store.store(KV_CUSTOMER_UUID_KEY, {"value": _CACHED_UUID}, encrypt=True)
+        kv_store.store(KV_CUSTOMER_UUID_KEY, _CACHED_UUID, encrypt=True)
 
     return _CACHED_UUID
 
@@ -80,16 +79,14 @@ def _get_or_generate_instance_domain() -> str | None:  #
     kv_store = get_kv_store()
 
     try:
-        _CACHED_INSTANCE_DOMAIN = unwrap_str(kv_store.load(KV_INSTANCE_DOMAIN_KEY))
+        _CACHED_INSTANCE_DOMAIN = cast(str, kv_store.load(KV_INSTANCE_DOMAIN_KEY))
     except KvKeyNotFoundError:
         with get_session_with_current_tenant() as db_session:
             first_user = db_session.query(User).first()
             if first_user:
                 _CACHED_INSTANCE_DOMAIN = first_user.email.split("@")[-1]
                 kv_store.store(
-                    KV_INSTANCE_DOMAIN_KEY,
-                    {"value": _CACHED_INSTANCE_DOMAIN},
-                    encrypt=True,
+                    KV_INSTANCE_DOMAIN_KEY, _CACHED_INSTANCE_DOMAIN, encrypt=True
                 )
 
     return _CACHED_INSTANCE_DOMAIN

backend/scripts/decrypt.py

@@ -1,93 +1,48 @@
-"""Decrypt a raw hex-encoded credential value.
-
-Usage:
-    python -m scripts.decrypt <hex_value>
-    python -m scripts.decrypt <hex_value> --key "my-encryption-key"
-    python -m scripts.decrypt <hex_value> --key ""
-
-Pass --key "" to skip decryption and just decode the raw bytes as UTF-8.
-Omit --key to use the current ENCRYPTION_KEY_SECRET from the environment.
-"""
-
-import argparse
 import binascii
 import json
-import os
 import sys
 
-parent_dir = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
-sys.path.append(parent_dir)
-
-from onyx.utils.encryption import decrypt_bytes_to_string  # noqa: E402
-from onyx.utils.variable_functionality import global_version  # noqa: E402
+from onyx.utils.encryption import decrypt_bytes_to_string
 
 
-def decrypt_raw_credential(encrypted_value: str, key: str | None = None) -> None:
-    """Decrypt and display a raw encrypted credential value.
+def decrypt_raw_credential(encrypted_value: str) -> None:
+    """Decrypt and display a raw encrypted credential value
 
     Args:
-        encrypted_value: The hex-encoded encrypted credential value.
-        key: Encryption key to use. None means use ENCRYPTION_KEY_SECRET,
-             empty string means just decode as UTF-8.
+        encrypted_value: The hex encoded encrypted credential value
     """
-    # Strip common hex prefixes
-    if encrypted_value.startswith("\\x"):
-        encrypted_value = encrypted_value[2:]
-    elif encrypted_value.startswith("x"):
-        encrypted_value = encrypted_value[1:]
-    print(encrypted_value)
-
     try:
-        raw_bytes = binascii.unhexlify(encrypted_value)
+        # If string starts with 'x', remove it as it's just a prefix indicating hex
+        if encrypted_value.startswith("x"):
+            encrypted_value = encrypted_value[1:]
+        elif encrypted_value.startswith("\\x"):
+            encrypted_value = encrypted_value[2:]
+
+        # Convert hex string to bytes
+        encrypted_bytes = binascii.unhexlify(encrypted_value)
+
+        # Decrypt the bytes
+        decrypted_str = decrypt_bytes_to_string(encrypted_bytes)
+
+        # Parse and pretty print the decrypted JSON
+        decrypted_json = json.loads(decrypted_str)
+        print("Decrypted credential value:")
+        print(json.dumps(decrypted_json, indent=2))
+
     except binascii.Error:
-        print("Error: Invalid hex-encoded string")
-        sys.exit(1)
+        print("Error: Invalid hex encoded string")
 
-    if key == "":
-        # Empty key → just decode as UTF-8, no decryption
-        try:
-            decrypted_str = raw_bytes.decode("utf-8")
-        except UnicodeDecodeError as e:
-            print(f"Error decoding bytes as UTF-8: {e}")
-            sys.exit(1)
-    else:
-        print(key)
-        try:
-            decrypted_str = decrypt_bytes_to_string(raw_bytes, key=key)
-        except Exception as e:
-            print(f"Error decrypting value: {e}")
-            sys.exit(1)
+    except json.JSONDecodeError as e:
+        print(f"Decrypted raw value (not JSON): {e}")
 
-    # Try to pretty-print as JSON, otherwise print raw
-    try:
-        parsed = json.loads(decrypted_str)
-        print(json.dumps(parsed, indent=2))
-    except json.JSONDecodeError:
-        print(decrypted_str)
-
-
-def main() -> None:
-    parser = argparse.ArgumentParser(
-        description="Decrypt a hex-encoded credential value."
-    )
-    parser.add_argument(
-        "value",
-        help="Hex-encoded encrypted value to decrypt.",
-    )
-    parser.add_argument(
-        "--key",
-        default=None,
-        help=(
-            "Encryption key. Omit to use ENCRYPTION_KEY_SECRET from env. "
-            'Pass "" (empty) to just decode as UTF-8 without decryption.'
-        ),
-    )
-    args = parser.parse_args()
-
-    global_version.set_ee()
-    decrypt_raw_credential(args.value, key=args.key)
-    global_version.unset_ee()
+    except Exception as e:
+        print(f"Error decrypting value: {e}")
 
 
 if __name__ == "__main__":
-    main()
+    if len(sys.argv) != 2:
+        print("Usage: python decrypt.py <hex_encoded_encrypted_value>")
+        sys.exit(1)
+
+    encrypted_value = sys.argv[1]
+    decrypt_raw_credential(encrypted_value)

backend/scripts/reencrypt_secrets.py

@@ -1,107 +0,0 @@
-"""Re-encrypt secrets under the current ENCRYPTION_KEY_SECRET.
-
-Decrypts all encrypted columns using the old key (or raw decode if the old key
-is empty), then re-encrypts them with the current ENCRYPTION_KEY_SECRET.
-
-Usage (docker):
-    docker exec -it onyx-api_server-1 \
-        python -m scripts.reencrypt_secrets --old-key "previous-key"
-
-Usage (kubernetes):
-    kubectl exec -it <pod> -- \
-        python -m scripts.reencrypt_secrets --old-key "previous-key"
-
-Omit --old-key (or pass "") if secrets were not previously encrypted.
-
-For multi-tenant deployments, pass --tenant-id to target a specific tenant,
-or --all-tenants to iterate every tenant.
-"""
-
-import argparse
-import os
-import sys
-
-parent_dir = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
-sys.path.append(parent_dir)
-
-from onyx.db.rotate_encryption_key import rotate_encryption_key  # noqa: E402
-from onyx.db.engine.sql_engine import get_session_with_tenant  # noqa: E402
-from onyx.db.engine.sql_engine import SqlEngine  # noqa: E402
-from onyx.db.engine.tenant_utils import get_all_tenant_ids  # noqa: E402
-from onyx.utils.variable_functionality import global_version  # noqa: E402
-from shared_configs.configs import POSTGRES_DEFAULT_SCHEMA  # noqa: E402
-
-
-def _run_for_tenant(tenant_id: str, old_key: str | None, dry_run: bool = False) -> None:
-    print(f"Re-encrypting secrets for tenant: {tenant_id}")
-    with get_session_with_tenant(tenant_id=tenant_id) as db_session:
-        results = rotate_encryption_key(db_session, old_key=old_key, dry_run=dry_run)
-
-    if results:
-        for col, count in results.items():
-            print(
-                f"  {col}: {count} row(s) {'would be ' if dry_run else ''}re-encrypted"
-            )
-    else:
-        print("No rows needed re-encryption.")
-
-
-def main() -> None:
-    parser = argparse.ArgumentParser(
-        description="Re-encrypt secrets under the current encryption key."
-    )
-    parser.add_argument(
-        "--old-key",
-        default=None,
-        help="Previous encryption key. Omit or pass empty string if not applicable.",
-    )
-    parser.add_argument(
-        "--dry-run",
-        action="store_true",
-        help="Show what would be re-encrypted without making changes.",
-    )
-
-    tenant_group = parser.add_mutually_exclusive_group()
-    tenant_group.add_argument(
-        "--tenant-id",
-        default=None,
-        help="Target a specific tenant schema.",
-    )
-    tenant_group.add_argument(
-        "--all-tenants",
-        action="store_true",
-        help="Iterate all tenants.",
-    )
-
-    args = parser.parse_args()
-
-    old_key = args.old_key if args.old_key else None
-
-    global_version.set_ee()
-    SqlEngine.init_engine(pool_size=5, max_overflow=2)
-
-    if args.dry_run:
-        print("DRY RUN — no changes will be made")
-
-    if args.all_tenants:
-        tenant_ids = get_all_tenant_ids()
-        print(f"Found {len(tenant_ids)} tenant(s)")
-        failed_tenants: list[str] = []
-        for tid in tenant_ids:
-            try:
-                _run_for_tenant(tid, old_key, dry_run=args.dry_run)
-            except Exception as e:
-                print(f"  ERROR for tenant {tid}: {e}")
-                failed_tenants.append(tid)
-        if failed_tenants:
-            print(f"FAILED tenants ({len(failed_tenants)}): {failed_tenants}")
-            sys.exit(1)
-    else:
-        tenant_id = args.tenant_id or POSTGRES_DEFAULT_SCHEMA
-        _run_for_tenant(tenant_id, old_key, dry_run=args.dry_run)
-
-    print("Done.")
-
-
-if __name__ == "__main__":
-    main()

backend/tests/daily/conftest.py

@@ -19,7 +19,7 @@ from fastapi.testclient import TestClient
 from onyx.auth.users import current_admin_user
 from onyx.db.engine.sql_engine import get_session
 from onyx.db.models import UserRole
-from onyx.main import get_application
+from onyx.main import fetch_versioned_implementation
 from onyx.utils.logger import setup_logger
 
 logger = setup_logger()
@@ -51,8 +51,11 @@ def client() -> Generator[TestClient, None, None]:
     # Patch out prometheus metrics setup to avoid "Duplicated timeseries in
     # CollectorRegistry" errors when multiple tests each create a new app
     # (prometheus registers metrics globally and rejects duplicate names).
+    get_app = fetch_versioned_implementation(
+        module="onyx.main", attribute="get_application"
+    )
     with patch("onyx.main.setup_prometheus_metrics"):
-        app: FastAPI = get_application(lifespan_override=test_lifespan)
+        app: FastAPI = get_app(lifespan_override=test_lifespan)
 
     # Override the database session dependency with a mock
     # (these tests don't actually need DB access)

backend/tests/daily/connectors/gitlab/test_gitlab_basic.py

@@ -48,7 +48,7 @@ def test_gitlab_connector_basic(gitlab_connector: GitlabConnector) -> None:
 
     # --- Specific Document Details to Validate ---
     target_mr_id = f"https://{gitlab_base_url}/{project_path}/-/merge_requests/1"
-    target_issue_id = f"https://{gitlab_base_url}/{project_path}/-/work_items/2"
+    target_issue_id = f"https://{gitlab_base_url}/{project_path}/-/issues/2"
     target_code_file_semantic_id = "README.md"
     # ---
 

backend/tests/external_dependency_unit/celery/test_pruning_hierarchy_nodes.py

@@ -7,8 +7,6 @@ Verifies that:
 3. Upserting is idempotent (running twice doesn't duplicate nodes)
 4. Document-to-hierarchy-node linkage is updated during pruning
 5. link_hierarchy_nodes_to_documents links nodes that are also documents
-6. HierarchyNodeByConnectorCredentialPair join table population and pruning
-7. Orphaned hierarchy node deletion and re-parenting
 
 Uses a mock SlimConnectorWithPermSync that yields known hierarchy nodes and slim documents,
 combined with a real PostgreSQL database for verifying persistence.
@@ -26,27 +24,16 @@ from onyx.connectors.interfaces import GenerateSlimDocumentOutput
 from onyx.connectors.interfaces import SecondsSinceUnixEpoch
 from onyx.connectors.interfaces import SlimConnectorWithPermSync
 from onyx.connectors.models import HierarchyNode as PydanticHierarchyNode
-from onyx.connectors.models import InputType
 from onyx.connectors.models import SlimDocument
-from onyx.db.enums import AccessType
-from onyx.db.enums import ConnectorCredentialPairStatus
 from onyx.db.enums import HierarchyNodeType
-from onyx.db.hierarchy import delete_orphaned_hierarchy_nodes
 from onyx.db.hierarchy import ensure_source_node_exists
 from onyx.db.hierarchy import get_all_hierarchy_nodes_for_source
 from onyx.db.hierarchy import get_hierarchy_node_by_raw_id
 from onyx.db.hierarchy import link_hierarchy_nodes_to_documents
-from onyx.db.hierarchy import remove_stale_hierarchy_node_cc_pair_entries
-from onyx.db.hierarchy import reparent_orphaned_hierarchy_nodes
 from onyx.db.hierarchy import update_document_parent_hierarchy_nodes
-from onyx.db.hierarchy import upsert_hierarchy_node_cc_pair_entries
 from onyx.db.hierarchy import upsert_hierarchy_nodes_batch
-from onyx.db.models import Connector
-from onyx.db.models import ConnectorCredentialPair
-from onyx.db.models import Credential
 from onyx.db.models import Document as DbDocument
 from onyx.db.models import HierarchyNode as DBHierarchyNode
-from onyx.db.models import HierarchyNodeByConnectorCredentialPair
 from onyx.indexing.indexing_heartbeat import IndexingHeartbeatInterface
 from onyx.kg.models import KGStage
 
@@ -155,80 +142,13 @@ class MockSlimConnectorWithPermSync(SlimConnectorWithPermSync):
 # ---------------------------------------------------------------------------
 
 
-def _create_cc_pair(
-    db_session: Session,
-    source: DocumentSource = TEST_SOURCE,
-) -> ConnectorCredentialPair:
-    """Create a real Connector + Credential + ConnectorCredentialPair for testing."""
-    connector = Connector(
-        name=f"Test {source.value} Connector",
-        source=source,
-        input_type=InputType.LOAD_STATE,
-        connector_specific_config={},
-    )
-    db_session.add(connector)
-    db_session.flush()
-
-    credential = Credential(
-        source=source,
-        credential_json={},
-        admin_public=True,
-    )
-    db_session.add(credential)
-    db_session.flush()
-    db_session.expire(credential)
-
-    cc_pair = ConnectorCredentialPair(
-        connector_id=connector.id,
-        credential_id=credential.id,
-        name=f"Test {source.value} CC Pair",
-        status=ConnectorCredentialPairStatus.ACTIVE,
-        access_type=AccessType.PUBLIC,
-    )
-    db_session.add(cc_pair)
-    db_session.commit()
-    db_session.refresh(cc_pair)
-    return cc_pair
-
-
 def _cleanup_test_data(db_session: Session) -> None:
     """Remove all test hierarchy nodes and documents to isolate tests."""
     for doc_id in SLIM_DOC_IDS:
         db_session.query(DbDocument).filter(DbDocument.id == doc_id).delete()
-
-    test_connector_ids_q = db_session.query(Connector.id).filter(
-        Connector.source == TEST_SOURCE,
-        Connector.name.like("Test %"),
-    )
-
-    db_session.query(HierarchyNodeByConnectorCredentialPair).filter(
-        HierarchyNodeByConnectorCredentialPair.connector_id.in_(test_connector_ids_q)
-    ).delete(synchronize_session="fetch")
     db_session.query(DBHierarchyNode).filter(
         DBHierarchyNode.source == TEST_SOURCE
     ).delete()
-    db_session.flush()
-
-    # Collect credential IDs before deleting cc_pairs (bulk query.delete()
-    # bypasses ORM-level cascade, so credentials won't be auto-removed).
-    credential_ids = [
-        row[0]
-        for row in db_session.query(ConnectorCredentialPair.credential_id)
-        .filter(ConnectorCredentialPair.connector_id.in_(test_connector_ids_q))
-        .all()
-    ]
-
-    db_session.query(ConnectorCredentialPair).filter(
-        ConnectorCredentialPair.connector_id.in_(test_connector_ids_q)
-    ).delete(synchronize_session="fetch")
-    db_session.query(Connector).filter(
-        Connector.source == TEST_SOURCE,
-        Connector.name.like("Test %"),
-    ).delete(synchronize_session="fetch")
-    if credential_ids:
-        db_session.query(Credential).filter(Credential.id.in_(credential_ids)).delete(
-            synchronize_session="fetch"
-        )
     db_session.commit()
 
 
@@ -259,8 +179,15 @@ def test_pruning_extracts_hierarchy_nodes(db_session: Session) -> None:  # noqa:
 
     result = extract_ids_from_runnable_connector(connector, callback=None)
 
-    # raw_id_to_parent should contain ONLY document IDs, not hierarchy node IDs
-    assert result.raw_id_to_parent.keys() == set(SLIM_DOC_IDS)
+    # Doc IDs should include both slim doc IDs and hierarchy node raw_node_ids
+    # (hierarchy node IDs are added to raw_id_to_parent so they aren't pruned)
+    expected_ids = {
+        CHANNEL_A_ID,
+        CHANNEL_B_ID,
+        CHANNEL_C_ID,
+        *SLIM_DOC_IDS,
+    }
+    assert result.raw_id_to_parent.keys() == expected_ids
 
     # Hierarchy nodes should be the 3 channels
     assert len(result.hierarchy_nodes) == 3
@@ -468,9 +395,9 @@ def test_extraction_preserves_parent_hierarchy_raw_node_id(
             result.raw_id_to_parent[doc_id] == expected_parent
         ), f"raw_id_to_parent[{doc_id}] should be {expected_parent}"
 
-    # Hierarchy node IDs should NOT be in raw_id_to_parent
+    # Hierarchy node entries have None parent (they aren't documents)
     for channel_id in [CHANNEL_A_ID, CHANNEL_B_ID, CHANNEL_C_ID]:
-        assert channel_id not in result.raw_id_to_parent
+        assert result.raw_id_to_parent[channel_id] is None
 
 
 def test_update_document_parent_hierarchy_nodes(db_session: Session) -> None:
@@ -638,241 +565,3 @@ def test_link_hierarchy_nodes_skips_non_hierarchy_sources(
         commit=False,
     )
     assert linked == 0
-
-
-# ---------------------------------------------------------------------------
-# Join table + pruning tests
-# ---------------------------------------------------------------------------
-
-
-def test_upsert_hierarchy_node_cc_pair_entries(db_session: Session) -> None:
-    """upsert_hierarchy_node_cc_pair_entries should insert rows and be idempotent."""
-    _cleanup_test_data(db_session)
-    ensure_source_node_exists(db_session, TEST_SOURCE, commit=True)
-    cc_pair = _create_cc_pair(db_session)
-
-    upserted = upsert_hierarchy_nodes_batch(
-        db_session=db_session,
-        nodes=_make_hierarchy_nodes(),
-        source=TEST_SOURCE,
-        commit=True,
-        is_connector_public=False,
-    )
-    node_ids = [n.id for n in upserted]
-
-    # First call — should insert rows
-    upsert_hierarchy_node_cc_pair_entries(
-        db_session=db_session,
-        hierarchy_node_ids=node_ids,
-        connector_id=cc_pair.connector_id,
-        credential_id=cc_pair.credential_id,
-        commit=True,
-    )
-
-    rows = (
-        db_session.query(HierarchyNodeByConnectorCredentialPair)
-        .filter(
-            HierarchyNodeByConnectorCredentialPair.connector_id == cc_pair.connector_id,
-            HierarchyNodeByConnectorCredentialPair.credential_id
-            == cc_pair.credential_id,
-        )
-        .all()
-    )
-    assert len(rows) == 3
-
-    # Second call — idempotent, same count
-    upsert_hierarchy_node_cc_pair_entries(
-        db_session=db_session,
-        hierarchy_node_ids=node_ids,
-        connector_id=cc_pair.connector_id,
-        credential_id=cc_pair.credential_id,
-        commit=True,
-    )
-    rows_after = (
-        db_session.query(HierarchyNodeByConnectorCredentialPair)
-        .filter(
-            HierarchyNodeByConnectorCredentialPair.connector_id == cc_pair.connector_id,
-            HierarchyNodeByConnectorCredentialPair.credential_id
-            == cc_pair.credential_id,
-        )
-        .all()
-    )
-    assert len(rows_after) == 3
-
-
-def test_remove_stale_entries_and_delete_orphans(db_session: Session) -> None:
-    """After removing stale join-table entries, orphaned hierarchy nodes should
-    be deleted and the SOURCE node should survive."""
-    _cleanup_test_data(db_session)
-    source_node = ensure_source_node_exists(db_session, TEST_SOURCE, commit=True)
-    cc_pair = _create_cc_pair(db_session)
-
-    upserted = upsert_hierarchy_nodes_batch(
-        db_session=db_session,
-        nodes=_make_hierarchy_nodes(),
-        source=TEST_SOURCE,
-        commit=True,
-        is_connector_public=False,
-    )
-    all_ids = [n.id for n in upserted]
-    upsert_hierarchy_node_cc_pair_entries(
-        db_session=db_session,
-        hierarchy_node_ids=all_ids,
-        connector_id=cc_pair.connector_id,
-        credential_id=cc_pair.credential_id,
-        commit=True,
-    )
-
-    # Now simulate a pruning run where only channel A survived
-    channel_a = get_hierarchy_node_by_raw_id(db_session, CHANNEL_A_ID, TEST_SOURCE)
-    assert channel_a is not None
-    live_ids = {channel_a.id}
-
-    stale_removed = remove_stale_hierarchy_node_cc_pair_entries(
-        db_session=db_session,
-        connector_id=cc_pair.connector_id,
-        credential_id=cc_pair.credential_id,
-        live_hierarchy_node_ids=live_ids,
-        commit=True,
-    )
-    assert stale_removed == 2
-
-    # Delete orphaned nodes
-    deleted_raw_ids = delete_orphaned_hierarchy_nodes(
-        db_session=db_session,
-        source=TEST_SOURCE,
-        commit=True,
-    )
-    assert set(deleted_raw_ids) == {CHANNEL_B_ID, CHANNEL_C_ID}
-
-    # Verify only channel A + SOURCE remain
-    remaining = get_all_hierarchy_nodes_for_source(db_session, TEST_SOURCE)
-    remaining_raw = {n.raw_node_id for n in remaining}
-    assert remaining_raw == {CHANNEL_A_ID, source_node.raw_node_id}
-
-
-def test_multi_cc_pair_prevents_premature_deletion(db_session: Session) -> None:
-    """A hierarchy node shared by two cc_pairs should NOT be deleted when only
-    one cc_pair removes its association."""
-    _cleanup_test_data(db_session)
-    ensure_source_node_exists(db_session, TEST_SOURCE, commit=True)
-    cc_pair_1 = _create_cc_pair(db_session)
-    cc_pair_2 = _create_cc_pair(db_session)
-
-    upserted = upsert_hierarchy_nodes_batch(
-        db_session=db_session,
-        nodes=_make_hierarchy_nodes(),
-        source=TEST_SOURCE,
-        commit=True,
-        is_connector_public=False,
-    )
-    all_ids = [n.id for n in upserted]
-
-    # cc_pair 1 owns all 3
-    upsert_hierarchy_node_cc_pair_entries(
-        db_session=db_session,
-        hierarchy_node_ids=all_ids,
-        connector_id=cc_pair_1.connector_id,
-        credential_id=cc_pair_1.credential_id,
-        commit=True,
-    )
-    # cc_pair 2 also owns all 3
-    upsert_hierarchy_node_cc_pair_entries(
-        db_session=db_session,
-        hierarchy_node_ids=all_ids,
-        connector_id=cc_pair_2.connector_id,
-        credential_id=cc_pair_2.credential_id,
-        commit=True,
-    )
-
-    # cc_pair 1 prunes — keeps none
-    remove_stale_hierarchy_node_cc_pair_entries(
-        db_session=db_session,
-        connector_id=cc_pair_1.connector_id,
-        credential_id=cc_pair_1.credential_id,
-        live_hierarchy_node_ids=set(),
-        commit=True,
-    )
-
-    # Orphan deletion should find nothing because cc_pair 2 still references them
-    deleted = delete_orphaned_hierarchy_nodes(
-        db_session=db_session,
-        source=TEST_SOURCE,
-        commit=True,
-    )
-    assert deleted == []
-
-    # All 3 nodes + SOURCE should still exist
-    remaining = get_all_hierarchy_nodes_for_source(db_session, TEST_SOURCE)
-    assert len(remaining) == 4
-
-
-def test_reparent_orphaned_children(db_session: Session) -> None:
-    """After deleting a parent hierarchy node, its children should be
-    re-parented to the SOURCE node."""
-    _cleanup_test_data(db_session)
-    source_node = ensure_source_node_exists(db_session, TEST_SOURCE, commit=True)
-    cc_pair = _create_cc_pair(db_session)
-
-    # Create a parent node and a child node
-    parent_node = PydanticHierarchyNode(
-        raw_node_id="PARENT",
-        raw_parent_id=None,
-        display_name="Parent",
-        node_type=HierarchyNodeType.CHANNEL,
-    )
-    child_node = PydanticHierarchyNode(
-        raw_node_id="CHILD",
-        raw_parent_id="PARENT",
-        display_name="Child",
-        node_type=HierarchyNodeType.CHANNEL,
-    )
-    upserted = upsert_hierarchy_nodes_batch(
-        db_session=db_session,
-        nodes=[parent_node, child_node],
-        source=TEST_SOURCE,
-        commit=True,
-        is_connector_public=False,
-    )
-    assert len(upserted) == 2
-
-    parent_db = get_hierarchy_node_by_raw_id(db_session, "PARENT", TEST_SOURCE)
-    child_db = get_hierarchy_node_by_raw_id(db_session, "CHILD", TEST_SOURCE)
-    assert parent_db is not None and child_db is not None
-    assert child_db.parent_id == parent_db.id
-
-    # Associate only the child with a cc_pair (parent is orphaned)
-    upsert_hierarchy_node_cc_pair_entries(
-        db_session=db_session,
-        hierarchy_node_ids=[child_db.id],
-        connector_id=cc_pair.connector_id,
-        credential_id=cc_pair.credential_id,
-        commit=True,
-    )
-
-    # Delete orphaned nodes (parent has no cc_pair entry)
-    deleted = delete_orphaned_hierarchy_nodes(
-        db_session=db_session,
-        source=TEST_SOURCE,
-        commit=True,
-    )
-    assert "PARENT" in deleted
-
-    # Child should now have parent_id=NULL (SET NULL cascade)
-    db_session.expire_all()
-    child_db = get_hierarchy_node_by_raw_id(db_session, "CHILD", TEST_SOURCE)
-    assert child_db is not None
-    assert child_db.parent_id is None
-
-    # Re-parent orphans to SOURCE
-    reparented = reparent_orphaned_hierarchy_nodes(
-        db_session=db_session,
-        source=TEST_SOURCE,
-        commit=True,
-    )
-    assert len(reparented) == 1
-
-    db_session.expire_all()
-    child_db = get_hierarchy_node_by_raw_id(db_session, "CHILD", TEST_SOURCE)
-    assert child_db is not None
-    assert child_db.parent_id == source_node.id

backend/tests/external_dependency_unit/db/test_credential_sensitive_value.py

@@ -1,90 +0,0 @@
-"""Test that Credential with nested JSON round-trips through SensitiveValue correctly.
-
-Exercises the full encrypt → store → read → decrypt → SensitiveValue path
-with realistic nested OAuth credential data, and verifies SQLAlchemy dirty
-tracking works with nested dict comparison.
-
-Requires a running Postgres instance.
-"""
-
-from sqlalchemy.orm import Session
-
-from onyx.configs.constants import DocumentSource
-from onyx.db.models import Credential
-from onyx.utils.sensitive import SensitiveValue
-
-# NOTE: this is not the real shape of a Drive credential,
-# but it is intended to test nested JSON credential handling
-
-_NESTED_CRED_JSON = {
-    "oauth_tokens": {
-        "access_token": "ya29.abc123",
-        "refresh_token": "1//xEg-def456",
-    },
-    "scopes": ["read", "write", "admin"],
-    "client_config": {
-        "client_id": "123.apps.googleusercontent.com",
-        "client_secret": "GOCSPX-secret",
-    },
-}
-
-
-def test_nested_credential_json_round_trip(db_session: Session) -> None:
-    """Nested OAuth credential survives encrypt → store → read → decrypt."""
-    credential = Credential(
-        source=DocumentSource.GOOGLE_DRIVE,
-        credential_json=_NESTED_CRED_JSON,
-    )
-    db_session.add(credential)
-    db_session.flush()
-
-    # Immediate read (no DB round-trip) — tests the set event wrapping
-    assert isinstance(credential.credential_json, SensitiveValue)
-    assert credential.credential_json.get_value(apply_mask=False) == _NESTED_CRED_JSON
-
-    # DB round-trip — tests process_result_value
-    db_session.expire(credential)
-    reloaded = credential.credential_json
-    assert isinstance(reloaded, SensitiveValue)
-    assert reloaded.get_value(apply_mask=False) == _NESTED_CRED_JSON
-
-    db_session.rollback()
-
-
-def test_reassign_same_nested_json_not_dirty(db_session: Session) -> None:
-    """Re-assigning the same nested dict should not mark the session dirty."""
-    credential = Credential(
-        source=DocumentSource.GOOGLE_DRIVE,
-        credential_json=_NESTED_CRED_JSON,
-    )
-    db_session.add(credential)
-    db_session.flush()
-
-    # Clear dirty state from the insert
-    db_session.expire(credential)
-    _ = credential.credential_json  # force reload
-
-    # Re-assign identical value
-    credential.credential_json = _NESTED_CRED_JSON  # type: ignore[assignment]
-    assert not db_session.is_modified(credential)
-
-    db_session.rollback()
-
-
-def test_assign_different_nested_json_is_dirty(db_session: Session) -> None:
-    """Assigning a different nested dict should mark the session dirty."""
-    credential = Credential(
-        source=DocumentSource.GOOGLE_DRIVE,
-        credential_json=_NESTED_CRED_JSON,
-    )
-    db_session.add(credential)
-    db_session.flush()
-
-    db_session.expire(credential)
-    _ = credential.credential_json  # force reload
-
-    modified_cred = {**_NESTED_CRED_JSON, "scopes": ["read"]}
-    credential.credential_json = modified_cred  # type: ignore[assignment]
-    assert db_session.is_modified(credential)
-
-    db_session.rollback()

backend/tests/external_dependency_unit/db/test_rotate_encryption_key.py

@@ -1,305 +0,0 @@
-"""Tests for rotate_encryption_key against real Postgres.
-
-Uses real ORM models (Credential, InternetSearchProvider) and the actual
-Postgres database. Discovery is mocked in rotation tests to scope mutations
-to only the test rows — the real _discover_encrypted_columns walk is tested
-separately in TestDiscoverEncryptedColumns.
-
-Requires a running Postgres instance. Run with::
-
-    python -m dotenv -f .vscode/.env run -- pytest tests/external_dependency_unit/db/test_rotate_encryption_key.py
-"""
-
-import json
-from collections.abc import Generator
-from unittest.mock import patch
-
-import pytest
-from sqlalchemy import LargeBinary
-from sqlalchemy import select
-from sqlalchemy import text
-from sqlalchemy.orm import Session
-
-from ee.onyx.utils.encryption import _decrypt_bytes
-from ee.onyx.utils.encryption import _encrypt_string
-from ee.onyx.utils.encryption import _get_trimmed_key
-from onyx.configs.constants import DocumentSource
-from onyx.db.models import Credential
-from onyx.db.models import EncryptedJson
-from onyx.db.models import EncryptedString
-from onyx.db.models import InternetSearchProvider
-from onyx.db.rotate_encryption_key import _discover_encrypted_columns
-from onyx.db.rotate_encryption_key import rotate_encryption_key
-from onyx.utils.variable_functionality import fetch_versioned_implementation
-from onyx.utils.variable_functionality import global_version
-
-EE_MODULE = "ee.onyx.utils.encryption"
-ROTATE_MODULE = "onyx.db.rotate_encryption_key"
-
-OLD_KEY = "o" * 16
-NEW_KEY = "n" * 16
-
-
-@pytest.fixture(autouse=True)
-def _enable_ee() -> Generator[None, None, None]:
-    prev = global_version._is_ee
-    global_version.set_ee()
-    fetch_versioned_implementation.cache_clear()
-    yield
-    global_version._is_ee = prev
-    fetch_versioned_implementation.cache_clear()
-
-
-@pytest.fixture(autouse=True)
-def _clear_key_cache() -> None:
-    _get_trimmed_key.cache_clear()
-
-
-def _raw_credential_bytes(db_session: Session, credential_id: int) -> bytes | None:
-    """Read raw bytes from credential_json, bypassing the TypeDecorator."""
-    col = Credential.__table__.c.credential_json
-    stmt = select(col.cast(LargeBinary)).where(
-        Credential.__table__.c.id == credential_id
-    )
-    return db_session.execute(stmt).scalar()
-
-
-def _raw_isp_bytes(db_session: Session, isp_id: int) -> bytes | None:
-    """Read raw bytes from InternetSearchProvider.api_key."""
-    col = InternetSearchProvider.__table__.c.api_key
-    stmt = select(col.cast(LargeBinary)).where(
-        InternetSearchProvider.__table__.c.id == isp_id
-    )
-    return db_session.execute(stmt).scalar()
-
-
-class TestDiscoverEncryptedColumns:
-    """Verify _discover_encrypted_columns finds real production models."""
-
-    def test_discovers_credential_json(self) -> None:
-        results = _discover_encrypted_columns()
-        found = {
-            (model_cls.__tablename__, col_name, is_json)  # type: ignore[attr-defined]
-            for model_cls, col_name, _, is_json in results
-        }
-        assert ("credential", "credential_json", True) in found
-
-    def test_discovers_internet_search_provider_api_key(self) -> None:
-        results = _discover_encrypted_columns()
-        found = {
-            (model_cls.__tablename__, col_name, is_json)  # type: ignore[attr-defined]
-            for model_cls, col_name, _, is_json in results
-        }
-        assert ("internet_search_provider", "api_key", False) in found
-
-    def test_all_encrypted_string_columns_are_not_json(self) -> None:
-        results = _discover_encrypted_columns()
-        for model_cls, col_name, _, is_json in results:
-            col = getattr(model_cls, col_name).property.columns[0]
-            if isinstance(col.type, EncryptedString):
-                assert not is_json, (
-                    f"{model_cls.__tablename__}.{col_name} is EncryptedString "  # type: ignore[attr-defined]
-                    f"but is_json={is_json}"
-                )
-
-    def test_all_encrypted_json_columns_are_json(self) -> None:
-        results = _discover_encrypted_columns()
-        for model_cls, col_name, _, is_json in results:
-            col = getattr(model_cls, col_name).property.columns[0]
-            if isinstance(col.type, EncryptedJson):
-                assert is_json, (
-                    f"{model_cls.__tablename__}.{col_name} is EncryptedJson "  # type: ignore[attr-defined]
-                    f"but is_json={is_json}"
-                )
-
-
-class TestRotateCredential:
-    """Test rotation against the real Credential table (EncryptedJson).
-
-    Discovery is scoped to only the Credential model to avoid mutating
-    other tables in the test database.
-    """
-
-    @pytest.fixture(autouse=True)
-    def _limit_discovery(self) -> Generator[None, None, None]:
-        with patch(
-            f"{ROTATE_MODULE}._discover_encrypted_columns",
-            return_value=[(Credential, "credential_json", ["id"], True)],
-        ):
-            yield
-
-    @pytest.fixture()
-    def credential_id(
-        self, db_session: Session, tenant_context: None  # noqa: ARG002
-    ) -> Generator[int, None, None]:
-        """Insert a Credential row with raw encrypted bytes, clean up after."""
-        config = {"api_key": "sk-test-1234", "endpoint": "https://example.com"}
-        encrypted = _encrypt_string(json.dumps(config), key=OLD_KEY)
-
-        result = db_session.execute(
-            text(
-                "INSERT INTO credential "
-                "(source, credential_json, admin_public, curator_public) "
-                "VALUES (:source, :cred_json, true, false) "
-                "RETURNING id"
-            ),
-            {"source": DocumentSource.INGESTION_API.value, "cred_json": encrypted},
-        )
-        cred_id = result.scalar_one()
-        db_session.commit()
-
-        yield cred_id
-
-        db_session.execute(
-            text("DELETE FROM credential WHERE id = :id"), {"id": cred_id}
-        )
-        db_session.commit()
-
-    def test_rotates_credential_json(
-        self, db_session: Session, credential_id: int
-    ) -> None:
-        with (
-            patch(f"{ROTATE_MODULE}.ENCRYPTION_KEY_SECRET", NEW_KEY),
-            patch(f"{EE_MODULE}.ENCRYPTION_KEY_SECRET", NEW_KEY),
-        ):
-            totals = rotate_encryption_key(db_session, old_key=OLD_KEY)
-
-        assert totals.get("credential.credential_json", 0) >= 1
-
-        raw = _raw_credential_bytes(db_session, credential_id)
-        assert raw is not None
-        decrypted = json.loads(_decrypt_bytes(raw, key=NEW_KEY))
-        assert decrypted["api_key"] == "sk-test-1234"
-        assert decrypted["endpoint"] == "https://example.com"
-
-    def test_skips_already_rotated(
-        self, db_session: Session, credential_id: int
-    ) -> None:
-        with (
-            patch(f"{ROTATE_MODULE}.ENCRYPTION_KEY_SECRET", NEW_KEY),
-            patch(f"{EE_MODULE}.ENCRYPTION_KEY_SECRET", NEW_KEY),
-        ):
-            rotate_encryption_key(db_session, old_key=OLD_KEY)
-            _ = rotate_encryption_key(db_session, old_key=OLD_KEY)
-
-        raw = _raw_credential_bytes(db_session, credential_id)
-        assert raw is not None
-        decrypted = json.loads(_decrypt_bytes(raw, key=NEW_KEY))
-        assert decrypted["api_key"] == "sk-test-1234"
-
-    def test_dry_run_does_not_modify(
-        self, db_session: Session, credential_id: int
-    ) -> None:
-        original = _raw_credential_bytes(db_session, credential_id)
-
-        with (
-            patch(f"{ROTATE_MODULE}.ENCRYPTION_KEY_SECRET", NEW_KEY),
-            patch(f"{EE_MODULE}.ENCRYPTION_KEY_SECRET", NEW_KEY),
-        ):
-            totals = rotate_encryption_key(db_session, old_key=OLD_KEY, dry_run=True)
-
-        assert totals.get("credential.credential_json", 0) >= 1
-
-        raw_after = _raw_credential_bytes(db_session, credential_id)
-        assert raw_after == original
-
-
-class TestRotateInternetSearchProvider:
-    """Test rotation against the real InternetSearchProvider table (EncryptedString).
-
-    Discovery is scoped to only the InternetSearchProvider model to avoid
-    mutating other tables in the test database.
-    """
-
-    @pytest.fixture(autouse=True)
-    def _limit_discovery(self) -> Generator[None, None, None]:
-        with patch(
-            f"{ROTATE_MODULE}._discover_encrypted_columns",
-            return_value=[
-                (InternetSearchProvider, "api_key", ["id"], False),
-            ],
-        ):
-            yield
-
-    @pytest.fixture()
-    def isp_id(
-        self, db_session: Session, tenant_context: None  # noqa: ARG002
-    ) -> Generator[int, None, None]:
-        """Insert an InternetSearchProvider row with raw encrypted bytes."""
-        encrypted = _encrypt_string("sk-secret-api-key", key=OLD_KEY)
-
-        result = db_session.execute(
-            text(
-                "INSERT INTO internet_search_provider "
-                "(name, provider_type, api_key, is_active) "
-                "VALUES (:name, :ptype, :api_key, false) "
-                "RETURNING id"
-            ),
-            {
-                "name": f"test-rotation-{id(self)}",
-                "ptype": "test",
-                "api_key": encrypted,
-            },
-        )
-        isp_id = result.scalar_one()
-        db_session.commit()
-
-        yield isp_id
-
-        db_session.execute(
-            text("DELETE FROM internet_search_provider WHERE id = :id"),
-            {"id": isp_id},
-        )
-        db_session.commit()
-
-    def test_rotates_api_key(self, db_session: Session, isp_id: int) -> None:
-        with (
-            patch(f"{ROTATE_MODULE}.ENCRYPTION_KEY_SECRET", NEW_KEY),
-            patch(f"{EE_MODULE}.ENCRYPTION_KEY_SECRET", NEW_KEY),
-        ):
-            totals = rotate_encryption_key(db_session, old_key=OLD_KEY)
-
-        assert totals.get("internet_search_provider.api_key", 0) >= 1
-
-        raw = _raw_isp_bytes(db_session, isp_id)
-        assert raw is not None
-        assert _decrypt_bytes(raw, key=NEW_KEY) == "sk-secret-api-key"
-
-    def test_rotates_from_unencrypted(
-        self, db_session: Session, tenant_context: None  # noqa: ARG002
-    ) -> None:
-        """Test rotating data that was stored without any encryption key."""
-        result = db_session.execute(
-            text(
-                "INSERT INTO internet_search_provider "
-                "(name, provider_type, api_key, is_active) "
-                "VALUES (:name, :ptype, :api_key, false) "
-                "RETURNING id"
-            ),
-            {
-                "name": f"test-raw-{id(self)}",
-                "ptype": "test",
-                "api_key": b"raw-api-key",
-            },
-        )
-        isp_id = result.scalar_one()
-        db_session.commit()
-
-        try:
-            with (
-                patch(f"{ROTATE_MODULE}.ENCRYPTION_KEY_SECRET", NEW_KEY),
-                patch(f"{EE_MODULE}.ENCRYPTION_KEY_SECRET", NEW_KEY),
-            ):
-                totals = rotate_encryption_key(db_session, old_key=None)
-
-            assert totals.get("internet_search_provider.api_key", 0) >= 1
-
-            raw = _raw_isp_bytes(db_session, isp_id)
-            assert raw is not None
-            assert _decrypt_bytes(raw, key=NEW_KEY) == "raw-api-key"
-        finally:
-            db_session.execute(
-                text("DELETE FROM internet_search_provider WHERE id = :id"),
-                {"id": isp_id},
-            )
-            db_session.commit()

backend/tests/external_dependency_unit/document_index/test_document_index_old.py

@@ -1,398 +0,0 @@
-"""External dependency tests for the old DocumentIndex interface.
-
-These tests assume Vespa and OpenSearch are running.
-
-TODO(ENG-3764)(andrei): Consolidate some of these test fixtures.
-"""
-
-import os
-import time
-import uuid
-from collections.abc import Generator
-from unittest.mock import patch
-
-import httpx
-import pytest
-
-from onyx.access.models import DocumentAccess
-from onyx.configs.constants import DocumentSource
-from onyx.connectors.models import Document
-from onyx.context.search.models import IndexFilters
-from onyx.db.enums import EmbeddingPrecision
-from onyx.document_index.interfaces import DocumentIndex
-from onyx.document_index.interfaces import IndexBatchParams
-from onyx.document_index.interfaces import VespaChunkRequest
-from onyx.document_index.interfaces import VespaDocumentUserFields
-from onyx.document_index.opensearch.client import wait_for_opensearch_with_timeout
-from onyx.document_index.opensearch.opensearch_document_index import (
-    OpenSearchOldDocumentIndex,
-)
-from onyx.document_index.vespa.index import VespaIndex
-from onyx.document_index.vespa.shared_utils.utils import get_vespa_http_client
-from onyx.document_index.vespa.shared_utils.utils import wait_for_vespa_with_timeout
-from onyx.indexing.models import ChunkEmbedding
-from onyx.indexing.models import DocMetadataAwareIndexChunk
-from shared_configs.configs import MULTI_TENANT
-from shared_configs.contextvars import CURRENT_TENANT_ID_CONTEXTVAR
-from shared_configs.contextvars import get_current_tenant_id
-from tests.external_dependency_unit.constants import TEST_TENANT_ID
-
-
-@pytest.fixture(scope="module")
-def opensearch_available() -> Generator[None, None, None]:
-    """Verifies OpenSearch is running, fails the test if not."""
-    if not wait_for_opensearch_with_timeout():
-        pytest.fail("OpenSearch is not available.")
-    yield  # Test runs here.
-
-
-@pytest.fixture(scope="module")
-def test_index_name() -> Generator[str, None, None]:
-    yield f"test_index_{uuid.uuid4().hex[:8]}"  # Test runs here.
-
-
-@pytest.fixture(scope="module")
-def tenant_context() -> Generator[None, None, None]:
-    """Sets up tenant context for testing."""
-    token = CURRENT_TENANT_ID_CONTEXTVAR.set(TEST_TENANT_ID)
-    try:
-        yield  # Test runs here.
-    finally:
-        # Reset the tenant context after the test
-        CURRENT_TENANT_ID_CONTEXTVAR.reset(token)
-
-
-@pytest.fixture(scope="module")
-def httpx_client() -> Generator[httpx.Client, None, None]:
-    client = get_vespa_http_client()
-    try:
-        yield client
-    finally:
-        client.close()
-
-
-@pytest.fixture(scope="module")
-def vespa_document_index(
-    httpx_client: httpx.Client,
-    tenant_context: None,  # noqa: ARG001
-    test_index_name: str,
-) -> Generator[VespaIndex, None, None]:
-    vespa_index = VespaIndex(
-        index_name=test_index_name,
-        secondary_index_name=None,
-        large_chunks_enabled=False,
-        secondary_large_chunks_enabled=None,
-        multitenant=MULTI_TENANT,
-        httpx_client=httpx_client,
-    )
-    backend_dir = os.path.abspath(
-        os.path.join(os.path.dirname(__file__), "..", "..", "..")
-    )
-    with patch("os.getcwd", return_value=backend_dir):
-        vespa_index.ensure_indices_exist(
-            primary_embedding_dim=128,
-            primary_embedding_precision=EmbeddingPrecision.FLOAT,
-            secondary_index_embedding_dim=None,
-            secondary_index_embedding_precision=None,
-        )
-    # Verify Vespa is running, fails the test if not. Try 90 seconds for testing
-    # in CI. We have to do this here because this endpoint only becomes live
-    # once we create an index.
-    if not wait_for_vespa_with_timeout(wait_limit=90):
-        pytest.fail("Vespa is not available.")
-
-    # Wait until the schema is actually ready for writes on content nodes. We
-    # probe by attempting a PUT; 200 means the schema is live, 400 means not
-    # yet. This is so scuffed but running the test is really flakey otherwise;
-    # this is only temporary until we entirely move off of Vespa.
-    probe_doc = {
-        "fields": {
-            "document_id": "__probe__",
-            "chunk_id": 0,
-            "blurb": "",
-            "title": "",
-            "skip_title": True,
-            "content": "",
-            "content_summary": "",
-            "source_type": "file",
-            "source_links": "null",
-            "semantic_identifier": "",
-            "section_continuation": False,
-            "large_chunk_reference_ids": [],
-            "metadata": "{}",
-            "metadata_list": [],
-            "metadata_suffix": "",
-            "chunk_context": "",
-            "doc_summary": "",
-            "embeddings": {"full_chunk": [1.0] + [0.0] * 127},
-            "access_control_list": {},
-            "document_sets": {},
-            "image_file_name": None,
-            "user_project": [],
-            "personas": [],
-            "boost": 0.0,
-            "aggregated_chunk_boost_factor": 0.0,
-            "primary_owners": [],
-            "secondary_owners": [],
-        }
-    }
-    schema_ready = False
-    probe_url = (
-        f"http://localhost:8081/document/v1/default/{test_index_name}/docid/__probe__"
-    )
-    for _ in range(60):
-        resp = httpx_client.post(probe_url, json=probe_doc)
-        if resp.status_code == 200:
-            schema_ready = True
-            # Clean up the probe document.
-            httpx_client.delete(probe_url)
-            break
-        time.sleep(1)
-    if not schema_ready:
-        pytest.fail(f"Vespa schema '{test_index_name}' did not become ready in time.")
-
-    yield vespa_index  # Test runs here.
-
-    # TODO(ENG-3765)(andrei): Explicitly cleanup index. Not immediately
-    # pressing; in CI we should be using fresh instances of dependencies each
-    # time anyway.
-
-
-@pytest.fixture(scope="module")
-def opensearch_document_index(
-    opensearch_available: None,  # noqa: ARG001
-    tenant_context: None,  # noqa: ARG001
-    test_index_name: str,
-) -> Generator[OpenSearchOldDocumentIndex, None, None]:
-    opensearch_index = OpenSearchOldDocumentIndex(
-        index_name=test_index_name,
-        embedding_dim=128,
-        embedding_precision=EmbeddingPrecision.FLOAT,
-        secondary_index_name=None,
-        secondary_embedding_dim=None,
-        secondary_embedding_precision=None,
-        large_chunks_enabled=False,
-        secondary_large_chunks_enabled=None,
-        multitenant=MULTI_TENANT,
-    )
-    opensearch_index.ensure_indices_exist(
-        primary_embedding_dim=128,
-        primary_embedding_precision=EmbeddingPrecision.FLOAT,
-        secondary_index_embedding_dim=None,
-        secondary_index_embedding_precision=None,
-    )
-
-    yield opensearch_index  # Test runs here.
-
-    # TODO(ENG-3765)(andrei): Explicitly cleanup index. Not immediately
-    # pressing; in CI we should be using fresh instances of dependencies each
-    # time anyway.
-
-
-@pytest.fixture(scope="module")
-def document_indices(
-    vespa_document_index: VespaIndex,
-    opensearch_document_index: OpenSearchOldDocumentIndex,
-) -> Generator[list[DocumentIndex], None, None]:
-    # Ideally these are parametrized; doing so with pytest fixtures is tricky.
-    yield [opensearch_document_index, vespa_document_index]  # Test runs here.
-
-
-@pytest.fixture(scope="function")
-def chunks(
-    tenant_context: None,  # noqa: ARG001
-) -> Generator[list[DocMetadataAwareIndexChunk], None, None]:
-    result = []
-    chunk_count = 5
-    doc_id = "test_doc"
-    tenant_id = get_current_tenant_id()
-    access = DocumentAccess.build(
-        user_emails=[],
-        user_groups=[],
-        external_user_emails=[],
-        external_user_group_ids=[],
-        is_public=True,
-    )
-    document_sets: set[str] = set()
-    user_project: list[int] = list()
-    personas: list[int] = list()
-    boost = 0
-    blurb = "blurb"
-    content = "content"
-    title_prefix = ""
-    doc_summary = ""
-    chunk_context = ""
-    title_embedding = [1.0] + [0] * 127
-    # Full 0 vectors are not supported for cos similarity.
-    embeddings = ChunkEmbedding(
-        full_embedding=[1.0] + [0] * 127, mini_chunk_embeddings=[]
-    )
-    source_document = Document(
-        id=doc_id,
-        semantic_identifier="semantic identifier",
-        source=DocumentSource.FILE,
-        sections=[],
-        metadata={},
-        title="title",
-    )
-    metadata_suffix_keyword = ""
-    image_file_id = None
-    source_links: dict[int, str] = {0: ""}
-    ancestor_hierarchy_node_ids: list[int] = []
-    for i in range(chunk_count):
-        result.append(
-            DocMetadataAwareIndexChunk(
-                tenant_id=tenant_id,
-                access=access,
-                document_sets=document_sets,
-                user_project=user_project,
-                personas=personas,
-                boost=boost,
-                aggregated_chunk_boost_factor=0,
-                ancestor_hierarchy_node_ids=ancestor_hierarchy_node_ids,
-                embeddings=embeddings,
-                title_embedding=title_embedding,
-                source_document=source_document,
-                title_prefix=title_prefix,
-                metadata_suffix_keyword=metadata_suffix_keyword,
-                metadata_suffix_semantic="",
-                contextual_rag_reserved_tokens=0,
-                doc_summary=doc_summary,
-                chunk_context=chunk_context,
-                mini_chunk_texts=None,
-                large_chunk_id=None,
-                chunk_id=i,
-                blurb=blurb,
-                content=content,
-                source_links=source_links,
-                image_file_id=image_file_id,
-                section_continuation=False,
-            )
-        )
-    yield result  # Test runs here.
-
-
-@pytest.fixture(scope="function")
-def index_batch_params(
-    tenant_context: None,  # noqa: ARG001
-) -> Generator[IndexBatchParams, None, None]:
-    # WARNING: doc_id_to_previous_chunk_cnt={"test_doc": 0} is hardcoded to 0,
-    # which is only correct on the very first index call. The document_indices
-    # fixture is scope="module", meaning the same OpenSearch and Vespa backends
-    # persist across all test functions in this module. When a second test
-    # function uses this fixture and calls document_index.index(...), the
-    # backend already has 5 chunks for "test_doc" from the previous test run,
-    # but the batch params still claim 0 prior chunks exist. This can lead to
-    # orphaned/duplicate chunks that make subsequent assertions incorrect.
-    # TODO: Whenever adding a second test, either change this or cleanup the
-    # index between test cases.
-    yield IndexBatchParams(
-        doc_id_to_previous_chunk_cnt={"test_doc": 0},
-        doc_id_to_new_chunk_cnt={"test_doc": 5},
-        tenant_id=get_current_tenant_id(),
-        large_chunks_enabled=False,
-    )
-
-
-class TestDocumentIndexOld:
-    """Tests the old DocumentIndex interface."""
-
-    def test_update_single_can_clear_user_projects_and_personas(
-        self,
-        document_indices: list[DocumentIndex],
-        # This test case assumes all these chunks correspond to one document.
-        chunks: list[DocMetadataAwareIndexChunk],
-        index_batch_params: IndexBatchParams,
-    ) -> None:
-        """
-        Tests that update_single can clear user_projects and personas.
-        """
-        for document_index in document_indices:
-            # Precondition.
-            # Ensure there is some non-empty value for user project and
-            # personas.
-            for chunk in chunks:
-                chunk.user_project = [1]
-                chunk.personas = [2]
-            document_index.index(chunks, index_batch_params)
-
-            # Ensure that we can get chunks as expected with filters.
-            doc_id = chunks[0].source_document.id
-            chunk_count = len(chunks)
-            tenant_id = get_current_tenant_id()
-            # We need to specify the chunk index range and specify
-            # batch_retrieval=True below to trigger the codepath for Vespa's
-            # search API, which uses the expected additive filtering for
-            # project_id and persona_id. Otherwise we would use the codepath for
-            # the visit API, which does not have this kind of filtering
-            # implemented.
-            chunk_request = VespaChunkRequest(
-                document_id=doc_id, min_chunk_ind=0, max_chunk_ind=chunk_count - 1
-            )
-            project_persona_filters = IndexFilters(
-                access_control_list=None,
-                tenant_id=tenant_id,
-                project_id=1,
-                persona_id=2,
-                # We need this even though none of the chunks belong to a
-                # document set because project_id and persona_id are only
-                # additive filters in the event the agent has knowledge scope;
-                # if the agent does not, it is implied that it can see
-                # everything it is allowed to.
-                document_set=["1"],
-            )
-            # Not best practice here but the API for refreshing the index to
-            # ensure that the latest data is present is not exposed in this
-            # class and is not the same for Vespa and OpenSearch, so we just
-            # tolerate a sleep for now. As a consequence the number of tests in
-            # this suite should be small. We only need to tolerate this for as
-            # long as we continue to use Vespa, we can consider exposing
-            # something for OpenSearch later.
-            time.sleep(1)
-            inference_chunks = document_index.id_based_retrieval(
-                chunk_requests=[chunk_request],
-                filters=project_persona_filters,
-                batch_retrieval=True,
-            )
-            assert len(inference_chunks) == chunk_count
-            # Sort by chunk id to easily test if we have all chunks.
-            for i, inference_chunk in enumerate(
-                sorted(inference_chunks, key=lambda x: x.chunk_id)
-            ):
-                assert inference_chunk.chunk_id == i
-                assert inference_chunk.document_id == doc_id
-
-            # Under test.
-            # Explicitly set empty fields here.
-            user_fields = VespaDocumentUserFields(user_projects=[], personas=[])
-            document_index.update_single(
-                doc_id=doc_id,
-                chunk_count=chunk_count,
-                tenant_id=tenant_id,
-                fields=None,
-                user_fields=user_fields,
-            )
-
-            # Postcondition.
-            filters = IndexFilters(access_control_list=None, tenant_id=tenant_id)
-            # We should expect to get back all expected chunks with no filters.
-            # Again, not best practice here.
-            time.sleep(1)
-            inference_chunks = document_index.id_based_retrieval(
-                chunk_requests=[chunk_request], filters=filters, batch_retrieval=True
-            )
-            assert len(inference_chunks) == chunk_count
-            # Sort by chunk id to easily test if we have all chunks.
-            for i, inference_chunk in enumerate(
-                sorted(inference_chunks, key=lambda x: x.chunk_id)
-            ):
-                assert inference_chunk.chunk_id == i
-                assert inference_chunk.document_id == doc_id
-            # Now, we should expect to not get any chunks if we specify the user
-            # project and personas filters.
-            inference_chunks = document_index.id_based_retrieval(
-                chunk_requests=[chunk_request],
-                filters=project_persona_filters,
-                batch_retrieval=True,
-            )
-            assert len(inference_chunks) == 0

backend/tests/external_dependency_unit/hierarchy/test_hierarchy_access_filter.py

@@ -85,7 +85,7 @@ def test_group_overlap_filter(
     results = _get_accessible_hierarchy_nodes_for_source(
         db_session,
         source=DocumentSource.GOOGLE_DRIVE,
-        user_email="",
+        user_email=None,
         external_group_ids=["group_engineering"],
     )
     result_ids = {n.raw_node_id for n in results}
@@ -124,7 +124,7 @@ def test_no_credentials_returns_only_public(
     results = _get_accessible_hierarchy_nodes_for_source(
         db_session,
         source=DocumentSource.GOOGLE_DRIVE,
-        user_email="",
+        user_email=None,
         external_group_ids=[],
     )
     result_ids = {n.raw_node_id for n in results}

backend/tests/external_dependency_unit/opensearch_migration/test_opensearch_migration_tasks.py

@@ -17,9 +17,6 @@ from unittest.mock import patch
 import pytest
 from sqlalchemy.orm import Session
 
-from onyx.background.celery.tasks.opensearch_migration.constants import (
-    GET_VESPA_CHUNKS_SLICE_COUNT,
-)
 from onyx.background.celery.tasks.opensearch_migration.tasks import (
     is_continuation_token_done_for_all_slices,
 )
@@ -239,8 +236,6 @@ def full_deployment_setup() -> Generator[None, None, None]:
     NOTE: We deliberately duplicate this logic from
     backend/tests/external_dependency_unit/conftest.py because we need to set
     opensearch_available just for this module, not the entire test session.
-
-    TODO(ENG-3764)(andrei): Consolidate some of these test fixtures.
     """
     # Patch ENABLE_OPENSEARCH_INDEXING_FOR_ONYX just for this test because we
     # don't yet want that enabled for all tests.
@@ -325,15 +320,9 @@ def test_embedding_dimension(db_session: Session) -> Generator[int, None, None]:
 @pytest.fixture(scope="function")
 def patch_get_vespa_chunks_page_size() -> Generator[int, None, None]:
     test_page_size = 5
-    with (
-        patch(
-            "onyx.background.celery.tasks.opensearch_migration.tasks.GET_VESPA_CHUNKS_PAGE_SIZE",
-            test_page_size,
-        ),
-        patch(
-            "onyx.background.celery.tasks.opensearch_migration.constants.GET_VESPA_CHUNKS_PAGE_SIZE",
-            test_page_size,
-        ),
+    with patch(
+        "onyx.background.celery.tasks.opensearch_migration.tasks.GET_VESPA_CHUNKS_PAGE_SIZE",
+        test_page_size,
     ):
         yield test_page_size  # Test runs here.
 
@@ -593,175 +582,6 @@ class TestMigrateChunksFromVespaToOpenSearchTask:
                     document_chunks[document.id][opensearch_chunk.chunk_index],
                 )
 
-    def test_chunk_migration_visits_all_chunks_even_when_batch_size_varies(
-        self,
-        db_session: Session,
-        test_documents: list[Document],
-        vespa_document_index: VespaDocumentIndex,
-        opensearch_client: OpenSearchIndexClient,
-        test_embedding_dimension: int,
-        clean_migration_tables: None,  # noqa: ARG002
-        enable_opensearch_indexing_for_onyx: None,  # noqa: ARG002
-    ) -> None:
-        """
-        Tests that chunk migration works correctly even when the batch size
-        changes halfway through a migration.
-
-        Simulates task time running out my mocking the locking behavior.
-        """
-        # Precondition.
-        # Index chunks into Vespa.
-        document_chunks: dict[str, list[dict[str, Any]]] = {
-            document.id: [
-                _create_raw_document_chunk(
-                    document_id=document.id,
-                    chunk_index=i,
-                    content=f"Test content {i} for {document.id}",
-                    embedding=_generate_test_vector(test_embedding_dimension),
-                    now=datetime.now(),
-                    title=f"Test title {document.id}",
-                    title_embedding=_generate_test_vector(test_embedding_dimension),
-                )
-                for i in range(CHUNK_COUNT)
-            ]
-            for document in test_documents
-        }
-        all_chunks: list[dict[str, Any]] = []
-        for chunks in document_chunks.values():
-            all_chunks.extend(chunks)
-        vespa_document_index.index_raw_chunks(all_chunks)
-
-        # Run the initial batch. To simulate partial progress we will mock the
-        # redis lock to return True for the first invocation of .owned() and
-        # False subsequently.
-        # NOTE: The batch size is currently set to 5 in
-        # patch_get_vespa_chunks_page_size.
-        mock_redis_client = Mock()
-        mock_lock = Mock()
-        mock_lock.owned.side_effect = [True, False, False]
-        mock_lock.acquire.return_value = True
-        mock_redis_client.lock.return_value = mock_lock
-        with patch(
-            "onyx.background.celery.tasks.opensearch_migration.tasks.get_redis_client",
-            return_value=mock_redis_client,
-        ):
-            result_1 = migrate_chunks_from_vespa_to_opensearch_task(
-                tenant_id=get_current_tenant_id()
-            )
-
-        assert result_1 is True
-        # Expire the session cache to see the committed changes from the task.
-        db_session.expire_all()
-
-        # Verify partial progress was saved.
-        tenant_record = db_session.query(OpenSearchTenantMigrationRecord).first()
-        assert tenant_record is not None
-        partial_chunks_migrated = tenant_record.total_chunks_migrated
-        assert partial_chunks_migrated > 0
-        # page_size applies per slice, so one iteration can fetch up to
-        # page_size * GET_VESPA_CHUNKS_SLICE_COUNT chunks total.
-        assert partial_chunks_migrated <= 5 * GET_VESPA_CHUNKS_SLICE_COUNT
-        assert tenant_record.vespa_visit_continuation_token is not None
-        # Slices are not necessarily evenly distributed across all document
-        # chunks so we can't test that every token is non-None, but certainly at
-        # least one must be.
-        assert any(json.loads(tenant_record.vespa_visit_continuation_token).values())
-        assert tenant_record.migration_completed_at is None
-        assert tenant_record.approx_chunk_count_in_vespa is not None
-
-        # Under test.
-        # Now patch the batch size to be some other number, like 2.
-        mock_redis_client = Mock()
-        mock_lock = Mock()
-        mock_lock.owned.side_effect = [True, False, False]
-        mock_lock.acquire.return_value = True
-        mock_redis_client.lock.return_value = mock_lock
-        with (
-            patch(
-                "onyx.background.celery.tasks.opensearch_migration.tasks.GET_VESPA_CHUNKS_PAGE_SIZE",
-                2,
-            ),
-            patch(
-                "onyx.background.celery.tasks.opensearch_migration.constants.GET_VESPA_CHUNKS_PAGE_SIZE",
-                2,
-            ),
-            patch(
-                "onyx.background.celery.tasks.opensearch_migration.tasks.get_redis_client",
-                return_value=mock_redis_client,
-            ),
-        ):
-            result_2 = migrate_chunks_from_vespa_to_opensearch_task(
-                tenant_id=get_current_tenant_id()
-            )
-
-        # Postcondition.
-        assert result_2 is True
-        # Expire the session cache to see the committed changes from the task.
-        db_session.expire_all()
-
-        # Verify next partial progress was saved.
-        tenant_record = db_session.query(OpenSearchTenantMigrationRecord).first()
-        assert tenant_record is not None
-        new_partial_chunks_migrated = tenant_record.total_chunks_migrated
-        assert new_partial_chunks_migrated > partial_chunks_migrated
-        # page_size applies per slice, so one iteration can fetch up to
-        # page_size * GET_VESPA_CHUNKS_SLICE_COUNT chunks total.
-        assert new_partial_chunks_migrated <= (5 + 2) * GET_VESPA_CHUNKS_SLICE_COUNT
-        assert tenant_record.vespa_visit_continuation_token is not None
-        # Slices are not necessarily evenly distributed across all document
-        # chunks so we can't test that every token is non-None, but certainly at
-        # least one must be.
-        assert any(json.loads(tenant_record.vespa_visit_continuation_token).values())
-        assert tenant_record.migration_completed_at is None
-        assert tenant_record.approx_chunk_count_in_vespa is not None
-
-        # Under test.
-        # Run the remainder of the migration.
-        with (
-            patch(
-                "onyx.background.celery.tasks.opensearch_migration.tasks.GET_VESPA_CHUNKS_PAGE_SIZE",
-                2,
-            ),
-            patch(
-                "onyx.background.celery.tasks.opensearch_migration.constants.GET_VESPA_CHUNKS_PAGE_SIZE",
-                2,
-            ),
-        ):
-            result_3 = migrate_chunks_from_vespa_to_opensearch_task(
-                tenant_id=get_current_tenant_id()
-            )
-
-        # Postcondition.
-        assert result_3 is True
-        # Expire the session cache to see the committed changes from the task.
-        db_session.expire_all()
-
-        # Verify completion.
-        tenant_record = db_session.query(OpenSearchTenantMigrationRecord).first()
-        assert tenant_record is not None
-        assert tenant_record.total_chunks_migrated > new_partial_chunks_migrated
-        assert tenant_record.total_chunks_migrated == len(all_chunks)
-        # Visit is complete so continuation token should be None.
-        assert tenant_record.vespa_visit_continuation_token is not None
-        assert is_continuation_token_done_for_all_slices(
-            json.loads(tenant_record.vespa_visit_continuation_token)
-        )
-        assert tenant_record.migration_completed_at is not None
-        assert tenant_record.approx_chunk_count_in_vespa == len(all_chunks)
-
-        # Verify chunks were indexed in OpenSearch.
-        for document in test_documents:
-            opensearch_chunks = _get_document_chunks_from_opensearch(
-                opensearch_client, document.id, get_current_tenant_id()
-            )
-            assert len(opensearch_chunks) == CHUNK_COUNT
-            opensearch_chunks.sort(key=lambda x: x.chunk_index)
-            for opensearch_chunk in opensearch_chunks:
-                _assert_chunk_matches_vespa_chunk(
-                    opensearch_chunk,
-                    document_chunks[document.id][opensearch_chunk.chunk_index],
-                )
-
     def test_chunk_migration_empty_vespa(
         self,
         db_session: Session,

backend/tests/external_dependency_unit/slack_bot/test_slack_bot_crud.py

@@ -1,85 +0,0 @@
-"""Tests that SlackBot CRUD operations return properly typed SensitiveValue fields.
-
-Regression test for the bug where insert_slack_bot/update_slack_bot returned
-objects with raw string tokens instead of SensitiveValue wrappers, causing
-'str object has no attribute get_value' errors in SlackBot.from_model().
-"""
-
-from uuid import uuid4
-
-from sqlalchemy.orm import Session
-
-from onyx.db.slack_bot import insert_slack_bot
-from onyx.db.slack_bot import update_slack_bot
-from onyx.server.manage.models import SlackBot
-from onyx.utils.sensitive import SensitiveValue
-
-
-def _unique(prefix: str) -> str:
-    return f"{prefix}-{uuid4().hex[:8]}"
-
-
-def test_insert_slack_bot_returns_sensitive_values(db_session: Session) -> None:
-    bot_token = _unique("xoxb-insert")
-    app_token = _unique("xapp-insert")
-    user_token = _unique("xoxp-insert")
-
-    slack_bot = insert_slack_bot(
-        db_session=db_session,
-        name=_unique("test-bot-insert"),
-        enabled=True,
-        bot_token=bot_token,
-        app_token=app_token,
-        user_token=user_token,
-    )
-
-    assert isinstance(slack_bot.bot_token, SensitiveValue)
-    assert isinstance(slack_bot.app_token, SensitiveValue)
-    assert isinstance(slack_bot.user_token, SensitiveValue)
-
-    assert slack_bot.bot_token.get_value(apply_mask=False) == bot_token
-    assert slack_bot.app_token.get_value(apply_mask=False) == app_token
-    assert slack_bot.user_token.get_value(apply_mask=False) == user_token
-
-    # Verify from_model works without error
-    pydantic_bot = SlackBot.from_model(slack_bot)
-    assert pydantic_bot.bot_token  # masked, but not empty
-    assert pydantic_bot.app_token
-
-
-def test_update_slack_bot_returns_sensitive_values(db_session: Session) -> None:
-    slack_bot = insert_slack_bot(
-        db_session=db_session,
-        name=_unique("test-bot-update"),
-        enabled=True,
-        bot_token=_unique("xoxb-update"),
-        app_token=_unique("xapp-update"),
-    )
-
-    new_bot_token = _unique("xoxb-update-new")
-    new_app_token = _unique("xapp-update-new")
-    new_user_token = _unique("xoxp-update-new")
-
-    updated = update_slack_bot(
-        db_session=db_session,
-        slack_bot_id=slack_bot.id,
-        name=_unique("test-bot-updated"),
-        enabled=False,
-        bot_token=new_bot_token,
-        app_token=new_app_token,
-        user_token=new_user_token,
-    )
-
-    assert isinstance(updated.bot_token, SensitiveValue)
-    assert isinstance(updated.app_token, SensitiveValue)
-    assert isinstance(updated.user_token, SensitiveValue)
-
-    assert updated.bot_token.get_value(apply_mask=False) == new_bot_token
-    assert updated.app_token.get_value(apply_mask=False) == new_app_token
-    assert updated.user_token.get_value(apply_mask=False) == new_user_token
-
-    # Verify from_model works without error
-    pydantic_bot = SlackBot.from_model(updated)
-    assert pydantic_bot.bot_token
-    assert pydantic_bot.app_token
-    assert pydantic_bot.user_token is not None

backend/tests/external_dependency_unit/tools/test_oauth_config_crud.py

@@ -148,16 +148,8 @@ class TestOAuthConfigCRUD:
         )
 
         # Secrets should be preserved
-        assert updated_config.client_id is not None
-        assert original_client_id is not None
-        assert updated_config.client_id.get_value(
-            apply_mask=False
-        ) == original_client_id.get_value(apply_mask=False)
-        assert updated_config.client_secret is not None
-        assert original_client_secret is not None
-        assert updated_config.client_secret.get_value(
-            apply_mask=False
-        ) == original_client_secret.get_value(apply_mask=False)
+        assert updated_config.client_id == original_client_id
+        assert updated_config.client_secret == original_client_secret
         # But name should be updated
         assert updated_config.name == new_name
 
@@ -181,14 +173,9 @@ class TestOAuthConfigCRUD:
         )
 
         # client_id should be cleared (empty string)
-        assert updated_config.client_id is not None
-        assert updated_config.client_id.get_value(apply_mask=False) == ""
+        assert updated_config.client_id == ""
         # client_secret should be preserved
-        assert updated_config.client_secret is not None
-        assert original_client_secret is not None
-        assert updated_config.client_secret.get_value(
-            apply_mask=False
-        ) == original_client_secret.get_value(apply_mask=False)
+        assert updated_config.client_secret == original_client_secret
 
     def test_update_oauth_config_clear_client_secret(self, db_session: Session) -> None:
         """Test clearing client_secret while preserving client_id"""
@@ -203,14 +190,9 @@ class TestOAuthConfigCRUD:
         )
 
         # client_secret should be cleared (empty string)
-        assert updated_config.client_secret is not None
-        assert updated_config.client_secret.get_value(apply_mask=False) == ""
+        assert updated_config.client_secret == ""
         # client_id should be preserved
-        assert updated_config.client_id is not None
-        assert original_client_id is not None
-        assert updated_config.client_id.get_value(
-            apply_mask=False
-        ) == original_client_id.get_value(apply_mask=False)
+        assert updated_config.client_id == original_client_id
 
     def test_update_oauth_config_clear_both_secrets(self, db_session: Session) -> None:
         """Test clearing both client_id and client_secret"""
@@ -225,10 +207,8 @@ class TestOAuthConfigCRUD:
         )
 
         # Both should be cleared (empty strings)
-        assert updated_config.client_id is not None
-        assert updated_config.client_id.get_value(apply_mask=False) == ""
-        assert updated_config.client_secret is not None
-        assert updated_config.client_secret.get_value(apply_mask=False) == ""
+        assert updated_config.client_id == ""
+        assert updated_config.client_secret == ""
 
     def test_update_oauth_config_authorization_url(self, db_session: Session) -> None:
         """Test updating authorization_url"""
@@ -295,8 +275,7 @@ class TestOAuthConfigCRUD:
         assert updated_config.token_url == new_token_url
         assert updated_config.scopes == new_scopes
         assert updated_config.additional_params == new_params
-        assert updated_config.client_id is not None
-        assert updated_config.client_id.get_value(apply_mask=False) == new_client_id
+        assert updated_config.client_id == new_client_id
 
     def test_delete_oauth_config(self, db_session: Session) -> None:
         """Test deleting an OAuth configuration"""
@@ -437,8 +416,7 @@ class TestOAuthUserTokenCRUD:
         assert user_token.id is not None
         assert user_token.oauth_config_id == oauth_config.id
         assert user_token.user_id == user.id
-        assert user_token.token_data is not None
-        assert user_token.token_data.get_value(apply_mask=False) == token_data
+        assert user_token.token_data == token_data
         assert user_token.created_at is not None
         assert user_token.updated_at is not None
 
@@ -468,13 +446,8 @@ class TestOAuthUserTokenCRUD:
 
         # Should be the same token record (updated, not inserted)
         assert updated_token.id == initial_token_id
-        assert updated_token.token_data is not None
-        assert (
-            updated_token.token_data.get_value(apply_mask=False) == updated_token_data
-        )
-        assert (
-            updated_token.token_data.get_value(apply_mask=False) != initial_token_data
-        )
+        assert updated_token.token_data == updated_token_data
+        assert updated_token.token_data != initial_token_data
 
     def test_get_user_oauth_token(self, db_session: Session) -> None:
         """Test retrieving a user's OAuth token"""
@@ -490,8 +463,7 @@ class TestOAuthUserTokenCRUD:
 
         assert retrieved_token is not None
         assert retrieved_token.id == created_token.id
-        assert retrieved_token.token_data is not None
-        assert retrieved_token.token_data.get_value(apply_mask=False) == token_data
+        assert retrieved_token.token_data == token_data
 
     def test_get_user_oauth_token_not_found(self, db_session: Session) -> None:
         """Test retrieving a non-existent user token returns None"""
@@ -547,8 +519,7 @@ class TestOAuthUserTokenCRUD:
         retrieved_token = get_user_oauth_token(oauth_config.id, user.id, db_session)
         assert retrieved_token is not None
         assert retrieved_token.id == updated_token.id
-        assert retrieved_token.token_data is not None
-        assert retrieved_token.token_data.get_value(apply_mask=False) == token_data2
+        assert retrieved_token.token_data == token_data2
 
     def test_cascade_delete_user_tokens_on_config_deletion(
         self, db_session: Session

backend/tests/external_dependency_unit/tools/test_oauth_token_manager.py

@@ -374,14 +374,8 @@ class TestOAuthTokenManagerCodeExchange:
         assert call_args[0][0] == oauth_config.token_url
         assert call_args[1]["data"]["grant_type"] == "authorization_code"
         assert call_args[1]["data"]["code"] == "auth_code_123"
-        assert oauth_config.client_id is not None
-        assert oauth_config.client_secret is not None
-        assert call_args[1]["data"]["client_id"] == oauth_config.client_id.get_value(
-            apply_mask=False
-        )
-        assert call_args[1]["data"][
-            "client_secret"
-        ] == oauth_config.client_secret.get_value(apply_mask=False)
+        assert call_args[1]["data"]["client_id"] == oauth_config.client_id
+        assert call_args[1]["data"]["client_secret"] == oauth_config.client_secret
         assert call_args[1]["data"]["redirect_uri"] == "https://example.com/callback"
 
     @patch("onyx.auth.oauth_token_manager.requests.post")

backend/tests/external_dependency_unit/tools/test_python_tool.py

@@ -950,7 +950,6 @@ from onyx.server.query_and_chat.streaming_models import Packet
 from onyx.server.query_and_chat.streaming_models import PythonToolDelta
 from onyx.server.query_and_chat.streaming_models import PythonToolStart
 from onyx.server.query_and_chat.streaming_models import SectionEnd
-from onyx.server.query_and_chat.streaming_models import ToolCallArgumentDelta
 from onyx.tools.tool_implementations.python.python_tool import PythonTool
 from tests.external_dependency_unit.answer.stream_test_builder import StreamTestBuilder
 from tests.external_dependency_unit.answer.stream_test_utils import create_chat_session
@@ -1292,21 +1291,12 @@ def test_code_interpreter_replay_packets_include_code_and_output(
                     tool_call_id="call_replay_test",
                     tool_call_argument_tokens=[json.dumps({"code": code})],
                 )
-            ).expect(
-                Packet(
-                    placement=create_placement(0),
-                    obj=ToolCallArgumentDelta(
-                        tool_type="python",
-                        argument_deltas={"code": code},
-                    ),
-                ),
-                forward=2,
             ).expect(
                 Packet(
                     placement=create_placement(0),
                     obj=PythonToolStart(code=code),
                 ),
-                forward=False,
+                forward=2,
             ).expect(
                 Packet(
                     placement=create_placement(0),

backend/tests/integration/tests/discord_bot/test_discord_bot_db.py

@@ -64,8 +64,7 @@ class TestBotConfigAPI:
         db_session.commit()
 
         assert config is not None
-        assert config.bot_token is not None
-        assert config.bot_token.get_value(apply_mask=False) == "test_token_123"
+        assert config.bot_token == "test_token_123"
 
         # Cleanup
         delete_discord_bot_config(db_session)

backend/tests/unit/ee/onyx/utils/test_encryption.py

@@ -1,165 +0,0 @@
-"""Tests for EE AES-CBC encryption/decryption with explicit key support.
-
-With EE mode enabled (via conftest), fetch_versioned_implementation resolves
-to the EE implementations, so no patching of the MIT layer is needed.
-"""
-
-from unittest.mock import patch
-
-import pytest
-
-from ee.onyx.utils.encryption import _decrypt_bytes
-from ee.onyx.utils.encryption import _encrypt_string
-from ee.onyx.utils.encryption import _get_trimmed_key
-from ee.onyx.utils.encryption import decrypt_bytes_to_string
-from ee.onyx.utils.encryption import encrypt_string_to_bytes
-
-EE_MODULE = "ee.onyx.utils.encryption"
-
-# Keys must be exactly 16, 24, or 32 bytes for AES
-KEY_16 = "a" * 16
-KEY_16_ALT = "b" * 16
-KEY_24 = "d" * 24
-KEY_32 = "c" * 32
-
-
-@pytest.fixture(autouse=True)
-def _clear_key_cache() -> None:
-    _get_trimmed_key.cache_clear()
-
-
-class TestEncryptDecryptRoundTrip:
-    def test_roundtrip_with_env_key(self) -> None:
-        with patch(f"{EE_MODULE}.ENCRYPTION_KEY_SECRET", KEY_16):
-            encrypted = _encrypt_string("hello world")
-            assert encrypted != b"hello world"
-            assert _decrypt_bytes(encrypted) == "hello world"
-
-    def test_roundtrip_with_explicit_key(self) -> None:
-        encrypted = _encrypt_string("secret data", key=KEY_32)
-        assert encrypted != b"secret data"
-        assert _decrypt_bytes(encrypted, key=KEY_32) == "secret data"
-
-    def test_roundtrip_no_key(self) -> None:
-        """Without any key, data is raw-encoded (no encryption)."""
-        with patch(f"{EE_MODULE}.ENCRYPTION_KEY_SECRET", ""):
-            encrypted = _encrypt_string("plain text")
-            assert encrypted == b"plain text"
-            assert _decrypt_bytes(encrypted) == "plain text"
-
-    def test_explicit_key_overrides_env(self) -> None:
-        with patch(f"{EE_MODULE}.ENCRYPTION_KEY_SECRET", KEY_16):
-            encrypted = _encrypt_string("data", key=KEY_16_ALT)
-            with pytest.raises(ValueError):
-                _decrypt_bytes(encrypted, key=KEY_16)
-            assert _decrypt_bytes(encrypted, key=KEY_16_ALT) == "data"
-
-    def test_different_encryptions_produce_different_bytes(self) -> None:
-        """Each encryption uses a random IV, so results differ."""
-        a = _encrypt_string("same", key=KEY_16)
-        b = _encrypt_string("same", key=KEY_16)
-        assert a != b
-
-    def test_roundtrip_empty_string(self) -> None:
-        encrypted = _encrypt_string("", key=KEY_16)
-        assert encrypted != b""
-        assert _decrypt_bytes(encrypted, key=KEY_16) == ""
-
-    def test_roundtrip_unicode(self) -> None:
-        text = "日本語テスト 🔐 émojis"
-        encrypted = _encrypt_string(text, key=KEY_16)
-        assert _decrypt_bytes(encrypted, key=KEY_16) == text
-
-
-class TestDecryptFallbackBehavior:
-    def test_wrong_env_key_falls_back_to_raw_decode(self) -> None:
-        """Default key path: AES fails on non-AES data → fallback to raw decode."""
-        raw = "readable text".encode()
-        with patch(f"{EE_MODULE}.ENCRYPTION_KEY_SECRET", KEY_16):
-            assert _decrypt_bytes(raw) == "readable text"
-
-    def test_explicit_wrong_key_raises(self) -> None:
-        """Explicit key path: AES fails → raises, no fallback."""
-        encrypted = _encrypt_string("secret", key=KEY_16)
-        with pytest.raises(ValueError):
-            _decrypt_bytes(encrypted, key=KEY_16_ALT)
-
-    def test_explicit_none_key_with_no_env(self) -> None:
-        """key=None with empty env → raw decode."""
-        with patch(f"{EE_MODULE}.ENCRYPTION_KEY_SECRET", ""):
-            assert _decrypt_bytes(b"hello", key=None) == "hello"
-
-    def test_explicit_empty_string_key(self) -> None:
-        """key='' means no encryption."""
-        encrypted = _encrypt_string("test", key="")
-        assert encrypted == b"test"
-        assert _decrypt_bytes(encrypted, key="") == "test"
-
-
-class TestKeyValidation:
-    def test_key_too_short_raises(self) -> None:
-        with pytest.raises(RuntimeError, match="too short"):
-            _encrypt_string("data", key="short")
-
-    def test_16_byte_key(self) -> None:
-        encrypted = _encrypt_string("data", key=KEY_16)
-        assert _decrypt_bytes(encrypted, key=KEY_16) == "data"
-
-    def test_24_byte_key(self) -> None:
-        encrypted = _encrypt_string("data", key=KEY_24)
-        assert _decrypt_bytes(encrypted, key=KEY_24) == "data"
-
-    def test_32_byte_key(self) -> None:
-        encrypted = _encrypt_string("data", key=KEY_32)
-        assert _decrypt_bytes(encrypted, key=KEY_32) == "data"
-
-    def test_long_key_truncated_to_32(self) -> None:
-        """Keys longer than 32 bytes are truncated to 32."""
-        long_key = "e" * 64
-        encrypted = _encrypt_string("data", key=long_key)
-        assert _decrypt_bytes(encrypted, key=long_key) == "data"
-
-    def test_20_byte_key_trimmed_to_16(self) -> None:
-        """A 20-byte key is trimmed to the largest valid AES size that fits (16)."""
-        key_20 = "f" * 20
-        encrypted = _encrypt_string("data", key=key_20)
-        assert _decrypt_bytes(encrypted, key=key_20) == "data"
-
-        # Verify it was trimmed to 16 by checking that the first 16 bytes
-        # of the key can also decrypt it
-        key_16_same_prefix = "f" * 16
-        assert _decrypt_bytes(encrypted, key=key_16_same_prefix) == "data"
-
-    def test_25_byte_key_trimmed_to_24(self) -> None:
-        """A 25-byte key is trimmed to the largest valid AES size that fits (24)."""
-        key_25 = "g" * 25
-        encrypted = _encrypt_string("data", key=key_25)
-        assert _decrypt_bytes(encrypted, key=key_25) == "data"
-
-        key_24_same_prefix = "g" * 24
-        assert _decrypt_bytes(encrypted, key=key_24_same_prefix) == "data"
-
-    def test_30_byte_key_trimmed_to_24(self) -> None:
-        """A 30-byte key is trimmed to the largest valid AES size that fits (24)."""
-        key_30 = "h" * 30
-        encrypted = _encrypt_string("data", key=key_30)
-        assert _decrypt_bytes(encrypted, key=key_30) == "data"
-
-        key_24_same_prefix = "h" * 24
-        assert _decrypt_bytes(encrypted, key=key_24_same_prefix) == "data"
-
-
-class TestWrapperFunctions:
-    """Test encrypt_string_to_bytes / decrypt_bytes_to_string pass key through.
-
-    With EE mode enabled, the wrappers resolve to EE implementations automatically.
-    """
-
-    def test_wrapper_passes_key(self) -> None:
-        encrypted = encrypt_string_to_bytes("payload", key=KEY_16)
-        assert decrypt_bytes_to_string(encrypted, key=KEY_16) == "payload"
-
-    def test_wrapper_no_key_uses_env(self) -> None:
-        with patch(f"{EE_MODULE}.ENCRYPTION_KEY_SECRET", KEY_32):
-            encrypted = encrypt_string_to_bytes("payload")
-            assert decrypt_bytes_to_string(encrypted) == "payload"

backend/tests/unit/onyx/access/test_user_file_access.py

@@ -1,163 +0,0 @@
-"""Tests for user file ACL computation, including shared persona access."""
-
-from unittest.mock import MagicMock
-from unittest.mock import patch
-from uuid import uuid4
-
-from onyx.access.access import collect_user_file_access
-from onyx.access.access import get_access_for_user_files_impl
-from onyx.access.utils import prefix_user_email
-from onyx.configs.constants import PUBLIC_DOC_PAT
-
-
-def _make_user(email: str) -> MagicMock:
-    user = MagicMock()
-    user.email = email
-    user.id = uuid4()
-    return user
-
-
-def _make_persona(
-    *,
-    owner: MagicMock | None = None,
-    shared_users: list[MagicMock] | None = None,
-    is_public: bool = False,
-    deleted: bool = False,
-) -> MagicMock:
-    persona = MagicMock()
-    persona.deleted = deleted
-    persona.is_public = is_public
-    persona.user_id = owner.id if owner else None
-    persona.user = owner
-    persona.users = shared_users or []
-    return persona
-
-
-def _make_user_file(
-    *,
-    owner: MagicMock,
-    assistants: list[MagicMock] | None = None,
-) -> MagicMock:
-    uf = MagicMock()
-    uf.id = uuid4()
-    uf.user = owner
-    uf.user_id = owner.id
-    uf.assistants = assistants or []
-    return uf
-
-
-class TestCollectUserFileAccess:
-    def test_owner_only(self) -> None:
-        owner = _make_user("owner@test.com")
-        uf = _make_user_file(owner=owner)
-
-        emails, is_public = collect_user_file_access(uf)
-
-        assert emails == {"owner@test.com"}
-        assert is_public is False
-
-    def test_shared_persona_adds_users(self) -> None:
-        owner = _make_user("owner@test.com")
-        shared = _make_user("shared@test.com")
-        persona = _make_persona(owner=owner, shared_users=[shared])
-        uf = _make_user_file(owner=owner, assistants=[persona])
-
-        emails, is_public = collect_user_file_access(uf)
-
-        assert emails == {"owner@test.com", "shared@test.com"}
-        assert is_public is False
-
-    def test_persona_owner_added(self) -> None:
-        """Persona owner (different from file owner) gets access too."""
-        file_owner = _make_user("file-owner@test.com")
-        persona_owner = _make_user("persona-owner@test.com")
-        persona = _make_persona(owner=persona_owner)
-        uf = _make_user_file(owner=file_owner, assistants=[persona])
-
-        emails, is_public = collect_user_file_access(uf)
-
-        assert "file-owner@test.com" in emails
-        assert "persona-owner@test.com" in emails
-
-    def test_public_persona_makes_file_public(self) -> None:
-        owner = _make_user("owner@test.com")
-        persona = _make_persona(owner=owner, is_public=True)
-        uf = _make_user_file(owner=owner, assistants=[persona])
-
-        emails, is_public = collect_user_file_access(uf)
-
-        assert is_public is True
-        assert "owner@test.com" in emails
-
-    def test_deleted_persona_ignored(self) -> None:
-        owner = _make_user("owner@test.com")
-        shared = _make_user("shared@test.com")
-        persona = _make_persona(owner=owner, shared_users=[shared], deleted=True)
-        uf = _make_user_file(owner=owner, assistants=[persona])
-
-        emails, is_public = collect_user_file_access(uf)
-
-        assert emails == {"owner@test.com"}
-        assert is_public is False
-
-    def test_multiple_personas_combine(self) -> None:
-        owner = _make_user("owner@test.com")
-        user_a = _make_user("a@test.com")
-        user_b = _make_user("b@test.com")
-        p1 = _make_persona(owner=owner, shared_users=[user_a])
-        p2 = _make_persona(owner=owner, shared_users=[user_b])
-        uf = _make_user_file(owner=owner, assistants=[p1, p2])
-
-        emails, is_public = collect_user_file_access(uf)
-
-        assert emails == {"owner@test.com", "a@test.com", "b@test.com"}
-
-    def test_deduplication(self) -> None:
-        owner = _make_user("owner@test.com")
-        shared = _make_user("shared@test.com")
-        p1 = _make_persona(owner=owner, shared_users=[shared])
-        p2 = _make_persona(owner=owner, shared_users=[shared])
-        uf = _make_user_file(owner=owner, assistants=[p1, p2])
-
-        emails, _ = collect_user_file_access(uf)
-
-        assert emails == {"owner@test.com", "shared@test.com"}
-
-
-class TestGetAccessForUserFiles:
-    def test_shared_user_in_acl(self) -> None:
-        """Shared persona users should appear in the ACL."""
-        owner = _make_user("owner@test.com")
-        shared = _make_user("shared@test.com")
-        persona = _make_persona(owner=owner, shared_users=[shared])
-        uf = _make_user_file(owner=owner, assistants=[persona])
-
-        db_session = MagicMock()
-        with patch(
-            "onyx.access.access.fetch_user_files_with_access_relationships",
-            return_value=[uf],
-        ):
-            result = get_access_for_user_files_impl([str(uf.id)], db_session)
-
-        access = result[str(uf.id)]
-        acl = access.to_acl()
-        assert prefix_user_email("owner@test.com") in acl
-        assert prefix_user_email("shared@test.com") in acl
-        assert access.is_public is False
-
-    def test_public_persona_sets_public_acl(self) -> None:
-        owner = _make_user("owner@test.com")
-        persona = _make_persona(owner=owner, is_public=True)
-        uf = _make_user_file(owner=owner, assistants=[persona])
-
-        db_session = MagicMock()
-        with patch(
-            "onyx.access.access.fetch_user_files_with_access_relationships",
-            return_value=[uf],
-        ):
-            result = get_access_for_user_files_impl([str(uf.id)], db_session)
-
-        access = result[str(uf.id)]
-        assert access.is_public is True
-        acl = access.to_acl()
-        assert PUBLIC_DOC_PAT in acl

backend/tests/unit/onyx/auth/test_verify_auth_setting.py

@@ -1,54 +0,0 @@
-from unittest.mock import MagicMock
-
-import pytest
-
-import onyx.auth.users as users
-from onyx.auth.users import verify_auth_setting
-from onyx.configs.constants import AuthType
-
-
-def test_verify_auth_setting_raises_for_cloud(
-    monkeypatch: pytest.MonkeyPatch,
-) -> None:
-    """Cloud auth type is not valid for self-hosted deployments."""
-    monkeypatch.setenv("AUTH_TYPE", "cloud")
-
-    with pytest.raises(ValueError, match="'cloud' is not a valid auth type"):
-        verify_auth_setting()
-
-
-def test_verify_auth_setting_warns_for_disabled(
-    monkeypatch: pytest.MonkeyPatch,
-) -> None:
-    """Disabled auth type logs a deprecation warning."""
-    monkeypatch.setenv("AUTH_TYPE", "disabled")
-
-    mock_logger = MagicMock()
-    monkeypatch.setattr(users, "logger", mock_logger)
-    monkeypatch.setattr(users, "AUTH_TYPE", AuthType.BASIC)
-
-    verify_auth_setting()
-
-    mock_logger.warning.assert_called_once()
-    assert "no longer supported" in mock_logger.warning.call_args[0][0]
-
-
-@pytest.mark.parametrize(
-    "auth_type",
-    [AuthType.BASIC, AuthType.GOOGLE_OAUTH, AuthType.OIDC, AuthType.SAML],
-)
-def test_verify_auth_setting_valid_auth_types(
-    monkeypatch: pytest.MonkeyPatch,
-    auth_type: AuthType,
-) -> None:
-    """Valid auth types work without errors or warnings."""
-    monkeypatch.setenv("AUTH_TYPE", auth_type.value)
-
-    mock_logger = MagicMock()
-    monkeypatch.setattr(users, "logger", mock_logger)
-    monkeypatch.setattr(users, "AUTH_TYPE", auth_type)
-
-    verify_auth_setting()
-
-    mock_logger.warning.assert_not_called()
-    mock_logger.notice.assert_called_once_with(f"Using Auth Type: {auth_type.value}")

backend/tests/unit/onyx/background/celery/tasks/test_user_file_impl_redis_locking.py

@@ -27,6 +27,7 @@ def _mock_session_returning_none() -> MagicMock:
     """Return a mock session whose .get() returns None (file not found)."""
     session = MagicMock()
     session.get.return_value = None
+    session.execute.return_value.scalar_one_or_none.return_value = None
     return session
 
 
@@ -219,10 +220,6 @@ class TestDeleteUserFileImpl:
 # ------------------------------------------------------------------
 
 
-@patch(
-    f"{TASKS_MODULE}.fetch_user_files_with_access_relationships",
-    return_value=[],
-)
 class TestProjectSyncUserFileImpl:
     @patch(f"{TASKS_MODULE}.get_session_with_current_tenant")
     @patch(f"{TASKS_MODULE}.get_redis_client")
@@ -230,7 +227,6 @@ class TestProjectSyncUserFileImpl:
         self,
         mock_get_redis: MagicMock,
         mock_get_session: MagicMock,
-        _mock_fetch: MagicMock,
     ) -> None:
         redis_client = MagicMock()
         lock = MagicMock()
@@ -259,7 +255,6 @@ class TestProjectSyncUserFileImpl:
         self,
         mock_get_redis: MagicMock,
         mock_get_session: MagicMock,
-        _mock_fetch: MagicMock,
     ) -> None:
         redis_client = MagicMock()
         lock = MagicMock()
@@ -282,7 +277,6 @@ class TestProjectSyncUserFileImpl:
         self,
         mock_get_redis: MagicMock,
         mock_get_session: MagicMock,
-        _mock_fetch: MagicMock,
     ) -> None:
         session = _mock_session_returning_none()
         mock_get_session.return_value.__enter__.return_value = session

backend/tests/unit/onyx/background/celery/tasks/test_user_file_processing_no_vectordb.py

@@ -379,13 +379,10 @@ class TestProjectSyncImplNoVectorDb:
     ) -> None:
         uf = _make_user_file(status=UserFileStatus.COMPLETED)
         session = MagicMock()
+        session.execute.return_value.scalar_one_or_none.return_value = uf
         mock_get_session.return_value.__enter__.return_value = session
 
         with (
-            patch(
-                f"{TASKS_MODULE}.fetch_user_files_with_access_relationships",
-                return_value=[uf],
-            ),
             patch(f"{TASKS_MODULE}.get_all_document_indices") as mock_get_indices,
             patch(f"{TASKS_MODULE}.get_active_search_settings") as mock_get_ss,
             patch(f"{TASKS_MODULE}.httpx_init_vespa_pool") as mock_vespa_pool,
@@ -408,17 +405,14 @@ class TestProjectSyncImplNoVectorDb:
     ) -> None:
         uf = _make_user_file(status=UserFileStatus.COMPLETED)
         session = MagicMock()
+        session.execute.return_value.scalar_one_or_none.return_value = uf
         mock_get_session.return_value.__enter__.return_value = session
 
-        with patch(
-            f"{TASKS_MODULE}.fetch_user_files_with_access_relationships",
-            return_value=[uf],
-        ):
-            project_sync_user_file_impl(
-                user_file_id=str(uf.id),
-                tenant_id="test-tenant",
-                redis_locking=False,
-            )
+        project_sync_user_file_impl(
+            user_file_id=str(uf.id),
+            tenant_id="test-tenant",
+            redis_locking=False,
+        )
 
         assert uf.needs_project_sync is False
         assert uf.needs_persona_sync is False

backend/tests/unit/onyx/chat/test_argument_delta_streaming.py

@@ -1,630 +0,0 @@
-from typing import Any
-from unittest.mock import MagicMock
-from unittest.mock import patch
-
-from onyx.chat.tool_call_args_streaming import maybe_emit_argument_delta
-from onyx.server.query_and_chat.placement import Placement
-from onyx.server.query_and_chat.streaming_models import ToolCallArgumentDelta
-from onyx.utils.jsonriver import Parser
-
-
-def _make_tool_call_delta(
-    index: int = 0,
-    name: str | None = None,
-    arguments: str | None = None,
-    function_is_none: bool = False,
-) -> MagicMock:
-    """Create a mock tool_call_delta matching the LiteLLM streaming shape."""
-    delta = MagicMock()
-    delta.index = index
-    if function_is_none:
-        delta.function = None
-    else:
-        delta.function = MagicMock()
-        delta.function.name = name
-        delta.function.arguments = arguments
-    return delta
-
-
-def _make_placement() -> Placement:
-    return Placement(turn_index=0, tab_index=0)
-
-
-def _mock_tool_class(emit: bool = True) -> MagicMock:
-    cls = MagicMock()
-    cls.should_emit_argument_deltas.return_value = emit
-    return cls
-
-
-def _collect(
-    tc_map: dict[int, dict[str, Any]],
-    delta: MagicMock,
-    placement: Placement | None = None,
-    parsers: dict[int, Parser] | None = None,
-) -> list[Any]:
-    """Run maybe_emit_argument_delta and return the yielded packets."""
-    return list(
-        maybe_emit_argument_delta(
-            tc_map,
-            delta,
-            placement or _make_placement(),
-            parsers if parsers is not None else {},
-        )
-    )
-
-
-def _stream_fragments(
-    fragments: list[str],
-    tc_map: dict[int, dict[str, Any]],
-    placement: Placement | None = None,
-) -> list[str]:
-    """Feed fragments into maybe_emit_argument_delta one by one, returning
-    all emitted content values concatenated per-key as a flat list."""
-    pl = placement or _make_placement()
-    parsers: dict[int, Parser] = {}
-    emitted: list[str] = []
-    for frag in fragments:
-        tc_map[0]["arguments"] += frag
-        delta = _make_tool_call_delta(arguments=frag)
-        for packet in maybe_emit_argument_delta(tc_map, delta, pl, parsers=parsers):
-            obj = packet.obj
-            assert isinstance(obj, ToolCallArgumentDelta)
-            for value in obj.argument_deltas.values():
-                emitted.append(value)
-    return emitted
-
-
-class TestMaybeEmitArgumentDeltaGuards:
-    """Tests for conditions that cause no packet to be emitted."""
-
-    @patch("onyx.chat.tool_call_args_streaming._get_tool_class")
-    def test_no_emission_when_tool_does_not_opt_in(
-        self, mock_get_tool: MagicMock
-    ) -> None:
-        """Tools that return False from should_emit_argument_deltas emit nothing."""
-        mock_get_tool.return_value = _mock_tool_class(emit=False)
-
-        tc_map: dict[int, dict[str, Any]] = {
-            0: {"id": "tc_1", "name": "python", "arguments": '{"code": "x'}
-        }
-        assert _collect(tc_map, _make_tool_call_delta(arguments="x")) == []
-
-    @patch("onyx.chat.tool_call_args_streaming._get_tool_class")
-    def test_no_emission_when_tool_class_unknown(
-        self, mock_get_tool: MagicMock
-    ) -> None:
-        mock_get_tool.return_value = None
-
-        tc_map: dict[int, dict[str, Any]] = {
-            0: {"id": "tc_1", "name": "unknown", "arguments": '{"code": "x'}
-        }
-        assert _collect(tc_map, _make_tool_call_delta(arguments="x")) == []
-
-    @patch("onyx.chat.tool_call_args_streaming._get_tool_class")
-    def test_no_emission_when_no_argument_fragment(
-        self, mock_get_tool: MagicMock
-    ) -> None:
-        mock_get_tool.return_value = _mock_tool_class()
-
-        tc_map: dict[int, dict[str, Any]] = {
-            0: {"id": "tc_1", "name": "python", "arguments": '{"code": "x'}
-        }
-        assert _collect(tc_map, _make_tool_call_delta(arguments=None)) == []
-
-    @patch("onyx.chat.tool_call_args_streaming._get_tool_class")
-    def test_no_emission_when_key_value_not_started(
-        self, mock_get_tool: MagicMock
-    ) -> None:
-        """Key exists in JSON but its string value hasn't begun yet."""
-        mock_get_tool.return_value = _mock_tool_class()
-
-        tc_map: dict[int, dict[str, Any]] = {
-            0: {"id": "tc_1", "name": "python", "arguments": '{"code":'}
-        }
-        assert _collect(tc_map, _make_tool_call_delta(arguments=":")) == []
-
-    @patch("onyx.chat.tool_call_args_streaming._get_tool_class")
-    def test_no_emission_before_any_key(self, mock_get_tool: MagicMock) -> None:
-        """Only the opening brace has arrived — no key to stream yet."""
-        mock_get_tool.return_value = _mock_tool_class()
-
-        tc_map: dict[int, dict[str, Any]] = {
-            0: {"id": "tc_1", "name": "python", "arguments": "{"}
-        }
-        assert _collect(tc_map, _make_tool_call_delta(arguments="{")) == []
-
-
-class TestMaybeEmitArgumentDeltaBasic:
-    """Tests for correct packet content and incremental emission."""
-
-    @patch("onyx.chat.tool_call_args_streaming._get_tool_class")
-    def test_emits_packet_with_correct_fields(self, mock_get_tool: MagicMock) -> None:
-        mock_get_tool.return_value = _mock_tool_class()
-
-        tc_map: dict[int, dict[str, Any]] = {
-            0: {"id": "tc_1", "name": "python", "arguments": ""}
-        }
-        fragments = ['{"code": "', "print(1)", '"}']
-
-        pl = _make_placement()
-        parsers: dict[int, Parser] = {}
-        all_packets = []
-        for frag in fragments:
-            tc_map[0]["arguments"] += frag
-            packets = _collect(
-                tc_map, _make_tool_call_delta(arguments=frag), pl, parsers
-            )
-            all_packets.extend(packets)
-
-        assert len(all_packets) >= 1
-        # Verify packet structure
-        obj = all_packets[0].obj
-        assert isinstance(obj, ToolCallArgumentDelta)
-        assert obj.tool_type == "python"
-        # All emitted content should reconstruct the value
-        full_code = ""
-        for p in all_packets:
-            assert isinstance(p.obj, ToolCallArgumentDelta)
-            if "code" in p.obj.argument_deltas:
-                full_code += p.obj.argument_deltas["code"]
-        assert full_code == "print(1)"
-
-    @patch("onyx.chat.tool_call_args_streaming._get_tool_class")
-    def test_emits_only_new_content_on_subsequent_call(
-        self, mock_get_tool: MagicMock
-    ) -> None:
-        """After a first emission, subsequent calls emit only the diff."""
-        mock_get_tool.return_value = _mock_tool_class()
-
-        tc_map: dict[int, dict[str, Any]] = {
-            0: {"id": "tc_1", "name": "python", "arguments": ""}
-        }
-        parsers: dict[int, Parser] = {}
-        pl = _make_placement()
-
-        # First fragment opens the string
-        tc_map[0]["arguments"] = '{"code": "abc'
-        packets_1 = _collect(
-            tc_map, _make_tool_call_delta(arguments='{"code": "abc'), pl, parsers
-        )
-        code_1 = ""
-        for p in packets_1:
-            assert isinstance(p.obj, ToolCallArgumentDelta)
-            code_1 += p.obj.argument_deltas.get("code", "")
-        assert code_1 == "abc"
-
-        # Second fragment appends more
-        tc_map[0]["arguments"] = '{"code": "abcdef'
-        packets_2 = _collect(
-            tc_map, _make_tool_call_delta(arguments="def"), pl, parsers
-        )
-        code_2 = ""
-        for p in packets_2:
-            assert isinstance(p.obj, ToolCallArgumentDelta)
-            code_2 += p.obj.argument_deltas.get("code", "")
-        assert code_2 == "def"
-
-    @patch("onyx.chat.tool_call_args_streaming._get_tool_class")
-    def test_handles_multiple_keys_sequentially(self, mock_get_tool: MagicMock) -> None:
-        """When a second key starts, emissions switch to that key."""
-        mock_get_tool.return_value = _mock_tool_class()
-
-        tc_map: dict[int, dict[str, Any]] = {
-            0: {"id": "tc_1", "name": "python", "arguments": ""}
-        }
-        fragments = [
-            '{"code": "x',
-            '", "output": "hello',
-            '"}',
-        ]
-
-        emitted = _stream_fragments(fragments, tc_map)
-        full = "".join(emitted)
-        assert "x" in full
-        assert "hello" in full
-
-    @patch("onyx.chat.tool_call_args_streaming._get_tool_class")
-    def test_delta_spans_key_boundary(self, mock_get_tool: MagicMock) -> None:
-        """A single delta contains the end of one value and the start of the next key."""
-        mock_get_tool.return_value = _mock_tool_class()
-
-        tc_map: dict[int, dict[str, Any]] = {
-            0: {"id": "tc_1", "name": "python", "arguments": ""}
-        }
-        fragments = [
-            '{"code": "x',
-            'y", "lang": "py',
-            '"}',
-        ]
-
-        emitted = _stream_fragments(fragments, tc_map)
-        full = "".join(emitted)
-        assert "xy" in full
-        assert "py" in full
-
-    @patch("onyx.chat.tool_call_args_streaming._get_tool_class")
-    def test_empty_value_emits_nothing(self, mock_get_tool: MagicMock) -> None:
-        """An empty string value has nothing to emit."""
-        mock_get_tool.return_value = _mock_tool_class()
-
-        tc_map: dict[int, dict[str, Any]] = {
-            0: {"id": "tc_1", "name": "python", "arguments": ""}
-        }
-        # Opening quote just arrived, value is empty
-        tc_map[0]["arguments"] = '{"code": "'
-        packets = _collect(tc_map, _make_tool_call_delta(arguments='{"code": "'))
-        # No string content yet, so either no packet or empty deltas
-        for p in packets:
-            assert isinstance(p.obj, ToolCallArgumentDelta)
-            assert p.obj.argument_deltas.get("code", "") == ""
-
-
-class TestMaybeEmitArgumentDeltaDecoding:
-    """Tests verifying that JSON escape sequences are properly decoded."""
-
-    @patch("onyx.chat.tool_call_args_streaming._get_tool_class")
-    def test_decodes_newlines(self, mock_get_tool: MagicMock) -> None:
-        mock_get_tool.return_value = _mock_tool_class()
-
-        tc_map: dict[int, dict[str, Any]] = {
-            0: {"id": "tc_1", "name": "python", "arguments": ""}
-        }
-        fragments = ['{"code": "line1\\nline2"}']
-
-        emitted = _stream_fragments(fragments, tc_map)
-        assert "".join(emitted) == "line1\nline2"
-
-    @patch("onyx.chat.tool_call_args_streaming._get_tool_class")
-    def test_decodes_tabs(self, mock_get_tool: MagicMock) -> None:
-        mock_get_tool.return_value = _mock_tool_class()
-
-        tc_map: dict[int, dict[str, Any]] = {
-            0: {"id": "tc_1", "name": "python", "arguments": ""}
-        }
-        fragments = ['{"code": "\\tindented"}']
-
-        emitted = _stream_fragments(fragments, tc_map)
-        assert "".join(emitted) == "\tindented"
-
-    @patch("onyx.chat.tool_call_args_streaming._get_tool_class")
-    def test_decodes_escaped_quotes(self, mock_get_tool: MagicMock) -> None:
-        mock_get_tool.return_value = _mock_tool_class()
-
-        tc_map: dict[int, dict[str, Any]] = {
-            0: {"id": "tc_1", "name": "python", "arguments": ""}
-        }
-        fragments = ['{"code": "say \\"hi\\""}']
-
-        emitted = _stream_fragments(fragments, tc_map)
-        assert "".join(emitted) == 'say "hi"'
-
-    @patch("onyx.chat.tool_call_args_streaming._get_tool_class")
-    def test_decodes_escaped_backslashes(self, mock_get_tool: MagicMock) -> None:
-        mock_get_tool.return_value = _mock_tool_class()
-
-        tc_map: dict[int, dict[str, Any]] = {
-            0: {"id": "tc_1", "name": "python", "arguments": ""}
-        }
-        fragments = ['{"code": "path\\\\dir"}']
-
-        emitted = _stream_fragments(fragments, tc_map)
-        assert "".join(emitted) == "path\\dir"
-
-    @patch("onyx.chat.tool_call_args_streaming._get_tool_class")
-    def test_decodes_unicode_escape(self, mock_get_tool: MagicMock) -> None:
-        mock_get_tool.return_value = _mock_tool_class()
-
-        tc_map: dict[int, dict[str, Any]] = {
-            0: {"id": "tc_1", "name": "python", "arguments": ""}
-        }
-        fragments = ['{"code": "\\u0041"}']
-
-        emitted = _stream_fragments(fragments, tc_map)
-        assert "".join(emitted) == "A"
-
-    @patch("onyx.chat.tool_call_args_streaming._get_tool_class")
-    def test_incomplete_escape_at_end_decoded_on_next_chunk(
-        self, mock_get_tool: MagicMock
-    ) -> None:
-        """A trailing backslash (incomplete escape) is completed in the next chunk."""
-        mock_get_tool.return_value = _mock_tool_class()
-
-        tc_map: dict[int, dict[str, Any]] = {
-            0: {"id": "tc_1", "name": "python", "arguments": ""}
-        }
-        fragments = ['{"code": "hello\\', 'n"}']
-
-        emitted = _stream_fragments(fragments, tc_map)
-        assert "".join(emitted) == "hello\n"
-
-    @patch("onyx.chat.tool_call_args_streaming._get_tool_class")
-    def test_incomplete_unicode_escape_completed_on_next_chunk(
-        self, mock_get_tool: MagicMock
-    ) -> None:
-        """A partial \\uXX sequence is completed in the next chunk."""
-        mock_get_tool.return_value = _mock_tool_class()
-
-        tc_map: dict[int, dict[str, Any]] = {
-            0: {"id": "tc_1", "name": "python", "arguments": ""}
-        }
-        fragments = ['{"code": "hello\\u00', '41"}']
-
-        emitted = _stream_fragments(fragments, tc_map)
-        assert "".join(emitted) == "helloA"
-
-
-class TestArgumentDeltaStreamingE2E:
-    """Simulates realistic sequences of LLM argument deltas to verify
-    the full pipeline produces correct decoded output."""
-
-    @patch("onyx.chat.tool_call_args_streaming._get_tool_class")
-    def test_realistic_python_code_streaming(self, mock_get_tool: MagicMock) -> None:
-        """Streams: {"code": "print('hello')\\nprint('world')"}"""
-        mock_get_tool.return_value = _mock_tool_class()
-
-        tc_map: dict[int, dict[str, Any]] = {
-            0: {"id": "tc_1", "name": "python", "arguments": ""}
-        }
-        fragments = [
-            '{"',
-            "code",
-            '": "',
-            "print(",
-            "'hello')",
-            "\\n",
-            "print(",
-            "'world')",
-            '"}',
-        ]
-
-        full = "".join(_stream_fragments(fragments, tc_map))
-        assert full == "print('hello')\nprint('world')"
-
-    @patch("onyx.chat.tool_call_args_streaming._get_tool_class")
-    def test_streaming_with_tabs_and_newlines(self, mock_get_tool: MagicMock) -> None:
-        """Streams code with tabs and newlines."""
-        mock_get_tool.return_value = _mock_tool_class()
-
-        tc_map: dict[int, dict[str, Any]] = {
-            0: {"id": "tc_1", "name": "python", "arguments": ""}
-        }
-        fragments = [
-            '{"code": "',
-            "if True:",
-            "\\n",
-            "\\t",
-            "pass",
-            '"}',
-        ]
-
-        full = "".join(_stream_fragments(fragments, tc_map))
-        assert full == "if True:\n\tpass"
-
-    @patch("onyx.chat.tool_call_args_streaming._get_tool_class")
-    def test_split_escape_sequence(self, mock_get_tool: MagicMock) -> None:
-        """An escape sequence split across two fragments (backslash in one,
-        'n' in the next) should still decode correctly."""
-        mock_get_tool.return_value = _mock_tool_class()
-
-        tc_map: dict[int, dict[str, Any]] = {
-            0: {"id": "tc_1", "name": "python", "arguments": ""}
-        }
-        fragments = [
-            '{"code": "hello',
-            "\\",
-            "n",
-            'world"}',
-        ]
-
-        full = "".join(_stream_fragments(fragments, tc_map))
-        assert full == "hello\nworld"
-
-    @patch("onyx.chat.tool_call_args_streaming._get_tool_class")
-    def test_multiple_newlines_and_indentation(self, mock_get_tool: MagicMock) -> None:
-        """Streams a multi-line function with multiple escape sequences."""
-        mock_get_tool.return_value = _mock_tool_class()
-
-        tc_map: dict[int, dict[str, Any]] = {
-            0: {"id": "tc_1", "name": "python", "arguments": ""}
-        }
-        fragments = [
-            '{"code": "',
-            "def foo():",
-            "\\n",
-            "\\t",
-            "x = 1",
-            "\\n",
-            "\\t",
-            "return x",
-            '"}',
-        ]
-
-        full = "".join(_stream_fragments(fragments, tc_map))
-        assert full == "def foo():\n\tx = 1\n\treturn x"
-
-    @patch("onyx.chat.tool_call_args_streaming._get_tool_class")
-    def test_two_keys_streamed_sequentially(self, mock_get_tool: MagicMock) -> None:
-        """Streams code first, then a second key (language) — both decoded."""
-        mock_get_tool.return_value = _mock_tool_class()
-
-        tc_map: dict[int, dict[str, Any]] = {
-            0: {"id": "tc_1", "name": "python", "arguments": ""}
-        }
-        fragments = [
-            '{"code": "',
-            "x = 1",
-            '", "language": "',
-            "python",
-            '"}',
-        ]
-
-        emitted = _stream_fragments(fragments, tc_map)
-        # Should have emissions for both keys
-        full = "".join(emitted)
-        assert "x = 1" in full
-        assert "python" in full
-
-    @patch("onyx.chat.tool_call_args_streaming._get_tool_class")
-    def test_code_containing_dict_literal(self, mock_get_tool: MagicMock) -> None:
-        """Python code like `x = {"key": "val"}` contains JSON-like patterns.
-        The escaped quotes inside the *outer* JSON value should prevent the
-        inner `"key":` from being mistaken for a top-level JSON key."""
-        mock_get_tool.return_value = _mock_tool_class()
-
-        tc_map: dict[int, dict[str, Any]] = {
-            0: {"id": "tc_1", "name": "python", "arguments": ""}
-        }
-        # The LLM sends: {"code": "x = {\"key\": \"val\"}"}
-        # The inner quotes are escaped as \" in the JSON value.
-        fragments = [
-            '{"code": "',
-            "x = {",
-            '\\"key\\"',
-            ": ",
-            '\\"val\\"',
-            "}",
-            '"}',
-        ]
-
-        full = "".join(_stream_fragments(fragments, tc_map))
-        assert full == 'x = {"key": "val"}'
-
-    @patch("onyx.chat.tool_call_args_streaming._get_tool_class")
-    def test_code_with_colon_in_value(self, mock_get_tool: MagicMock) -> None:
-        """Colons inside the string value should not confuse key detection."""
-        mock_get_tool.return_value = _mock_tool_class()
-
-        tc_map: dict[int, dict[str, Any]] = {
-            0: {"id": "tc_1", "name": "python", "arguments": ""}
-        }
-        fragments = [
-            '{"code": "',
-            "url = ",
-            '\\"https://example.com\\"',
-            '"}',
-        ]
-
-        full = "".join(_stream_fragments(fragments, tc_map))
-        assert full == 'url = "https://example.com"'
-
-
-class TestMaybeEmitArgumentDeltaEdgeCases:
-    """Edge cases not covered by the standard test classes."""
-
-    @patch("onyx.chat.tool_call_args_streaming._get_tool_class")
-    def test_no_emission_when_function_is_none(self, mock_get_tool: MagicMock) -> None:
-        """Some delta chunks have function=None (e.g. role-only deltas)."""
-        mock_get_tool.return_value = _mock_tool_class()
-
-        tc_map: dict[int, dict[str, Any]] = {
-            0: {"id": "tc_1", "name": "python", "arguments": '{"code": "x'}
-        }
-        delta = _make_tool_call_delta(arguments=None, function_is_none=True)
-        assert _collect(tc_map, delta) == []
-
-    @patch("onyx.chat.tool_call_args_streaming._get_tool_class")
-    def test_multiple_concurrent_tool_calls(self, mock_get_tool: MagicMock) -> None:
-        """Two tool calls streaming at different indices in parallel."""
-        mock_get_tool.return_value = _mock_tool_class()
-
-        tc_map: dict[int, dict[str, Any]] = {
-            0: {"id": "tc_1", "name": "python", "arguments": ""},
-            1: {"id": "tc_2", "name": "python", "arguments": ""},
-        }
-
-        parsers: dict[int, Parser] = {}
-        pl = _make_placement()
-
-        # Feed full JSON to index 0
-        tc_map[0]["arguments"] = '{"code": "aaa"}'
-        packets_0 = _collect(
-            tc_map,
-            _make_tool_call_delta(index=0, arguments='{"code": "aaa"}'),
-            pl,
-            parsers,
-        )
-        code_0 = ""
-        for p in packets_0:
-            assert isinstance(p.obj, ToolCallArgumentDelta)
-            code_0 += p.obj.argument_deltas.get("code", "")
-        assert code_0 == "aaa"
-
-        # Feed full JSON to index 1
-        tc_map[1]["arguments"] = '{"code": "bbb"}'
-        packets_1 = _collect(
-            tc_map,
-            _make_tool_call_delta(index=1, arguments='{"code": "bbb"}'),
-            pl,
-            parsers,
-        )
-        code_1 = ""
-        for p in packets_1:
-            assert isinstance(p.obj, ToolCallArgumentDelta)
-            code_1 += p.obj.argument_deltas.get("code", "")
-        assert code_1 == "bbb"
-
-    @patch("onyx.chat.tool_call_args_streaming._get_tool_class")
-    def test_delta_with_four_arguments(self, mock_get_tool: MagicMock) -> None:
-        """A single delta contains four complete key-value pairs."""
-        mock_get_tool.return_value = _mock_tool_class()
-
-        full = '{"a": "one", "b": "two", "c": "three", "d": "four"}'
-        tc_map: dict[int, dict[str, Any]] = {
-            0: {"id": "tc_1", "name": "python", "arguments": ""}
-        }
-        tc_map[0]["arguments"] = full
-        parsers: dict[int, Parser] = {}
-        packets = _collect(
-            tc_map, _make_tool_call_delta(arguments=full), parsers=parsers
-        )
-
-        # Collect all argument deltas across packets
-        all_deltas: dict[str, str] = {}
-        for p in packets:
-            assert isinstance(p.obj, ToolCallArgumentDelta)
-            for k, v in p.obj.argument_deltas.items():
-                all_deltas[k] = all_deltas.get(k, "") + v
-
-        assert all_deltas == {
-            "a": "one",
-            "b": "two",
-            "c": "three",
-            "d": "four",
-        }
-
-    @patch("onyx.chat.tool_call_args_streaming._get_tool_class")
-    def test_delta_on_second_arg_after_first_complete(
-        self, mock_get_tool: MagicMock
-    ) -> None:
-        """First argument is fully complete; delta only adds to the second."""
-        mock_get_tool.return_value = _mock_tool_class()
-
-        tc_map: dict[int, dict[str, Any]] = {
-            0: {"id": "tc_1", "name": "python", "arguments": ""}
-        }
-
-        fragments = [
-            '{"code": "print(1)", "lang": "py',
-            '"}',
-        ]
-
-        emitted = _stream_fragments(fragments, tc_map)
-        full = "".join(emitted)
-        assert "print(1)" in full
-        assert "py" in full
-
-    @patch("onyx.chat.tool_call_args_streaming._get_tool_class")
-    def test_non_string_values_skipped(self, mock_get_tool: MagicMock) -> None:
-        """Non-string values (numbers, booleans, null) are skipped — they are
-        available in the final tool-call kickoff packet. String arguments
-        following them are still emitted."""
-        mock_get_tool.return_value = _mock_tool_class()
-
-        tc_map: dict[int, dict[str, Any]] = {
-            0: {"id": "tc_1", "name": "python", "arguments": ""}
-        }
-        fragments = ['{"timeout": 30, "code": "hello"}']
-
-        emitted = _stream_fragments(fragments, tc_map)
-        full = "".join(emitted)
-        assert full == "hello"

backend/tests/unit/onyx/connectors/sharepoint/test_delta_checkpointing.py

@@ -6,7 +6,6 @@ Validates that:
 - Crash + resume skips already-processed pages
 - BFS (folder-scoped) drives process all items in one call
 - 410 Gone triggers a full-resync URL in the checkpoint
-- Duplicate document IDs across delta pages are deduplicated
 """
 
 from __future__ import annotations
@@ -458,228 +457,3 @@ class TestDeltaPageFetchFailure:
         assert final_cp.current_drive_name is None
         assert final_cp.current_drive_id is None
         assert final_cp.current_drive_delta_next_link is None
-
-
-class TestDeltaDuplicateDocumentDedup:
-    """The Microsoft Graph delta API can return the same item on multiple
-    pages.  Documents already yielded should be skipped via
-    checkpoint.seen_document_ids."""
-
-    def test_duplicate_across_pages_is_skipped(
-        self, monkeypatch: pytest.MonkeyPatch
-    ) -> None:
-        """Item 'dup' appears on both page 1 and page 2.  It should only be
-        yielded once."""
-        connector = _setup_connector(monkeypatch)
-        _mock_convert(monkeypatch)
-
-        call_count = 0
-
-        def fake_fetch_page(
-            self: SharepointConnector,  # noqa: ARG001
-            page_url: str,  # noqa: ARG001
-            drive_id: str,  # noqa: ARG001
-            start: datetime | None = None,  # noqa: ARG001
-            end: datetime | None = None,  # noqa: ARG001
-            page_size: int = 200,  # noqa: ARG001
-        ) -> tuple[list[DriveItemData], str | None]:
-            nonlocal call_count
-            call_count += 1
-            if call_count == 1:
-                return [_make_item("a"), _make_item("dup")], "https://next2"
-            return [_make_item("dup"), _make_item("b")], None
-
-        monkeypatch.setattr(
-            SharepointConnector, "_fetch_one_delta_page", fake_fetch_page
-        )
-
-        checkpoint = _build_ready_checkpoint()
-
-        # Page 1: yields a, dup
-        gen = connector._load_from_checkpoint(
-            _START_TS, _END_TS, checkpoint, include_permissions=False
-        )
-        yielded, checkpoint = _consume_generator(gen)
-        docs = _docs_from(yielded)
-        assert [d.id for d in docs] == ["a", "dup"]
-        assert "dup" in checkpoint.seen_document_ids
-
-        # Page 2: dup should be skipped, only b yielded
-        gen = connector._load_from_checkpoint(
-            _START_TS, _END_TS, checkpoint, include_permissions=False
-        )
-        yielded, checkpoint = _consume_generator(gen)
-        docs = _docs_from(yielded)
-        assert [d.id for d in docs] == ["b"]
-
-    def test_duplicate_within_same_page_is_skipped(
-        self, monkeypatch: pytest.MonkeyPatch
-    ) -> None:
-        """If the same item appears twice on a single delta page, only the
-        first occurrence should be yielded."""
-        connector = _setup_connector(monkeypatch)
-        _mock_convert(monkeypatch)
-
-        def fake_fetch_page(
-            self: SharepointConnector,  # noqa: ARG001
-            page_url: str,  # noqa: ARG001
-            drive_id: str,  # noqa: ARG001
-            start: datetime | None = None,  # noqa: ARG001
-            end: datetime | None = None,  # noqa: ARG001
-            page_size: int = 200,  # noqa: ARG001
-        ) -> tuple[list[DriveItemData], str | None]:
-            return [_make_item("x"), _make_item("x"), _make_item("y")], None
-
-        monkeypatch.setattr(
-            SharepointConnector, "_fetch_one_delta_page", fake_fetch_page
-        )
-
-        checkpoint = _build_ready_checkpoint()
-        gen = connector._load_from_checkpoint(
-            _START_TS, _END_TS, checkpoint, include_permissions=False
-        )
-        yielded, checkpoint = _consume_generator(gen)
-        docs = _docs_from(yielded)
-        assert [d.id for d in docs] == ["x", "y"]
-
-    def test_seen_ids_survive_checkpoint_serialization(
-        self, monkeypatch: pytest.MonkeyPatch
-    ) -> None:
-        """seen_document_ids must survive JSON serialization so that
-        dedup works across crash + resume."""
-        connector = _setup_connector(monkeypatch)
-        _mock_convert(monkeypatch)
-
-        call_count = 0
-
-        def fake_fetch_page(
-            self: SharepointConnector,  # noqa: ARG001
-            page_url: str,  # noqa: ARG001
-            drive_id: str,  # noqa: ARG001
-            start: datetime | None = None,  # noqa: ARG001
-            end: datetime | None = None,  # noqa: ARG001
-            page_size: int = 200,  # noqa: ARG001
-        ) -> tuple[list[DriveItemData], str | None]:
-            nonlocal call_count
-            call_count += 1
-            if call_count == 1:
-                return [_make_item("a")], "https://next2"
-            return [_make_item("a"), _make_item("b")], None
-
-        monkeypatch.setattr(
-            SharepointConnector, "_fetch_one_delta_page", fake_fetch_page
-        )
-
-        checkpoint = _build_ready_checkpoint()
-
-        # Page 1
-        gen = connector._load_from_checkpoint(
-            _START_TS, _END_TS, checkpoint, include_permissions=False
-        )
-        _, checkpoint = _consume_generator(gen)
-        assert "a" in checkpoint.seen_document_ids
-
-        # Simulate crash: round-trip through JSON
-        restored = SharepointConnectorCheckpoint.model_validate_json(
-            checkpoint.model_dump_json()
-        )
-        assert "a" in restored.seen_document_ids
-
-        # Page 2 with restored checkpoint: 'a' should be skipped
-        connector2 = _setup_connector(monkeypatch)
-        _mock_convert(monkeypatch)
-        monkeypatch.setattr(
-            SharepointConnector, "_fetch_one_delta_page", fake_fetch_page
-        )
-
-        gen = connector2._load_from_checkpoint(
-            _START_TS, _END_TS, restored, include_permissions=False
-        )
-        yielded, final_cp = _consume_generator(gen)
-        docs = _docs_from(yielded)
-        assert [d.id for d in docs] == ["b"]
-
-    def test_no_dedup_across_separate_indexing_runs(
-        self, monkeypatch: pytest.MonkeyPatch
-    ) -> None:
-        """A fresh checkpoint (new indexing run) should have an empty
-        seen_document_ids, so previously-indexed docs are re-processed."""
-        connector = _setup_connector(monkeypatch)
-        _mock_convert(monkeypatch)
-
-        def fake_fetch_page(
-            self: SharepointConnector,  # noqa: ARG001
-            page_url: str,  # noqa: ARG001
-            drive_id: str,  # noqa: ARG001
-            start: datetime | None = None,  # noqa: ARG001
-            end: datetime | None = None,  # noqa: ARG001
-            page_size: int = 200,  # noqa: ARG001
-        ) -> tuple[list[DriveItemData], str | None]:
-            return [_make_item("a")], None
-
-        monkeypatch.setattr(
-            SharepointConnector, "_fetch_one_delta_page", fake_fetch_page
-        )
-
-        # First run
-        cp1 = _build_ready_checkpoint()
-        gen = connector._load_from_checkpoint(
-            _START_TS, _END_TS, cp1, include_permissions=False
-        )
-        yielded, _ = _consume_generator(gen)
-        assert len(_docs_from(yielded)) == 1
-
-        # Second run with a fresh checkpoint — same doc should appear again
-        cp2 = _build_ready_checkpoint()
-        assert len(cp2.seen_document_ids) == 0
-        gen = connector._load_from_checkpoint(
-            _START_TS, _END_TS, cp2, include_permissions=False
-        )
-        yielded, _ = _consume_generator(gen)
-        assert len(_docs_from(yielded)) == 1
-
-    def test_same_id_across_drives_not_skipped(
-        self, monkeypatch: pytest.MonkeyPatch
-    ) -> None:
-        """Graph item IDs are only unique within a drive.  An item in drive B
-        that happens to share an ID with an item already seen in drive A must
-        NOT be skipped."""
-        connector = _setup_connector(monkeypatch)
-        _mock_convert(monkeypatch)
-
-        def fake_fetch_page(
-            self: SharepointConnector,  # noqa: ARG001
-            page_url: str,  # noqa: ARG001
-            drive_id: str,  # noqa: ARG001
-            start: datetime | None = None,  # noqa: ARG001
-            end: datetime | None = None,  # noqa: ARG001
-            page_size: int = 200,  # noqa: ARG001
-        ) -> tuple[list[DriveItemData], str | None]:
-            return [_make_item("shared-id")], None
-
-        monkeypatch.setattr(
-            SharepointConnector, "_fetch_one_delta_page", fake_fetch_page
-        )
-
-        checkpoint = _build_ready_checkpoint(drive_names=["DriveA", "DriveB"])
-
-        # Drive A: yields the item
-        gen = connector._load_from_checkpoint(
-            _START_TS, _END_TS, checkpoint, include_permissions=False
-        )
-        yielded, checkpoint = _consume_generator(gen)
-        docs = _docs_from(yielded)
-        assert len(docs) == 1
-        assert docs[0].id == "shared-id"
-
-        # seen_document_ids should have been cleared when drive A finished
-        assert len(checkpoint.seen_document_ids) == 0
-
-        # Drive B: same ID must be yielded again (different drive)
-        gen = connector._load_from_checkpoint(
-            _START_TS, _END_TS, checkpoint, include_permissions=False
-        )
-        yielded, checkpoint = _consume_generator(gen)
-        docs = _docs_from(yielded)
-        assert len(docs) == 1
-        assert docs[0].id == "shared-id"

backend/tests/unit/onyx/server/features/hierarchy/test_user_access_info.py

@@ -1,43 +0,0 @@
-"""Unit tests for _get_user_access_info helper function.
-
-These tests mock all database operations and don't require a real database.
-"""
-
-from unittest.mock import MagicMock
-from unittest.mock import patch
-
-from sqlalchemy.orm import Session
-
-from onyx.server.features.hierarchy.api import _get_user_access_info
-
-
-def test_get_user_access_info_returns_email_and_groups() -> None:
-    """_get_user_access_info returns the user's email and external group IDs."""
-    mock_user = MagicMock()
-    mock_user.email = "test@example.com"
-    mock_db_session = MagicMock(spec=Session)
-
-    with patch(
-        "onyx.server.features.hierarchy.api.get_user_external_group_ids",
-        return_value=["group1", "group2"],
-    ):
-        email, groups = _get_user_access_info(mock_user, mock_db_session)
-
-    assert email == "test@example.com"
-    assert groups == ["group1", "group2"]
-
-
-def test_get_user_access_info_with_no_groups() -> None:
-    """User with no external groups returns empty list."""
-    mock_user = MagicMock()
-    mock_user.email = "solo@example.com"
-    mock_db_session = MagicMock(spec=Session)
-
-    with patch(
-        "onyx.server.features.hierarchy.api.get_user_external_group_ids",
-        return_value=[],
-    ):
-        email, groups = _get_user_access_info(mock_user, mock_db_session)
-
-    assert email == "solo@example.com"
-    assert groups == []

backend/tests/unit/onyx/server/test_full_user_snapshot.py

@@ -1,54 +0,0 @@
-import datetime
-from unittest.mock import MagicMock
-from uuid import uuid4
-
-from onyx.auth.schemas import UserRole
-from onyx.server.models import FullUserSnapshot
-from onyx.server.models import UserGroupInfo
-
-
-def _mock_user(
-    personal_name: str | None = "Test User",
-    created_at: datetime.datetime | None = None,
-    updated_at: datetime.datetime | None = None,
-) -> MagicMock:
-    user = MagicMock()
-    user.id = uuid4()
-    user.email = "test@example.com"
-    user.role = UserRole.BASIC
-    user.is_active = True
-    user.password_configured = True
-    user.personal_name = personal_name
-    user.created_at = created_at or datetime.datetime(
-        2025, 1, 1, tzinfo=datetime.timezone.utc
-    )
-    user.updated_at = updated_at or datetime.datetime(
-        2025, 6, 15, tzinfo=datetime.timezone.utc
-    )
-    return user
-
-
-def test_from_user_model_includes_new_fields() -> None:
-    user = _mock_user(personal_name="Alice")
-    groups = [UserGroupInfo(id=1, name="Engineering")]
-
-    snapshot = FullUserSnapshot.from_user_model(user, groups=groups)
-
-    assert snapshot.personal_name == "Alice"
-    assert snapshot.created_at == user.created_at
-    assert snapshot.updated_at == user.updated_at
-    assert snapshot.groups == groups
-
-
-def test_from_user_model_defaults_groups_to_empty() -> None:
-    user = _mock_user()
-    snapshot = FullUserSnapshot.from_user_model(user)
-
-    assert snapshot.groups == []
-
-
-def test_from_user_model_personal_name_none() -> None:
-    user = _mock_user(personal_name=None)
-    snapshot = FullUserSnapshot.from_user_model(user)
-
-    assert snapshot.personal_name is None

backend/tests/unit/onyx/server/test_projects_file_utils.py

@@ -1,188 +0,0 @@
-from io import BytesIO
-from unittest.mock import MagicMock
-
-import pytest
-from fastapi import UploadFile
-
-from onyx.server.features.projects import projects_file_utils as utils
-
-
-class _Tokenizer:
-    def encode(self, text: str) -> list[int]:
-        return [1] * len(text)
-
-
-class _NonSeekableFile(BytesIO):
-    def tell(self) -> int:
-        raise OSError("tell not supported")
-
-    def seek(self, *_args: object, **_kwargs: object) -> int:
-        raise OSError("seek not supported")
-
-
-def _make_upload(filename: str, size: int, content: bytes | None = None) -> UploadFile:
-    payload = content if content is not None else (b"x" * size)
-    return UploadFile(filename=filename, file=BytesIO(payload), size=size)
-
-
-def _make_upload_no_size(filename: str, content: bytes) -> UploadFile:
-    return UploadFile(filename=filename, file=BytesIO(content), size=None)
-
-
-def _patch_common_dependencies(monkeypatch: pytest.MonkeyPatch) -> None:
-    monkeypatch.setattr(utils, "fetch_default_llm_model", lambda _db: None)
-    monkeypatch.setattr(utils, "get_tokenizer", lambda **_kwargs: _Tokenizer())
-    monkeypatch.setattr(utils, "is_file_password_protected", lambda **_kwargs: False)
-
-
-def test_get_upload_size_bytes_falls_back_to_stream_size() -> None:
-    upload = UploadFile(filename="example.txt", file=BytesIO(b"abcdef"), size=None)
-    upload.file.seek(2)
-
-    size = utils.get_upload_size_bytes(upload)
-
-    assert size == 6
-    assert upload.file.tell() == 2
-
-
-def test_get_upload_size_bytes_logs_warning_when_stream_size_unavailable(
-    caplog: pytest.LogCaptureFixture,
-) -> None:
-    upload = UploadFile(filename="non_seekable.txt", file=_NonSeekableFile(), size=None)
-
-    caplog.set_level("WARNING")
-    size = utils.get_upload_size_bytes(upload)
-
-    assert size is None
-    assert "Could not determine upload size via stream seek" in caplog.text
-    assert "non_seekable.txt" in caplog.text
-
-
-def test_is_upload_too_large_logs_warning_when_size_unknown(
-    monkeypatch: pytest.MonkeyPatch,
-    caplog: pytest.LogCaptureFixture,
-) -> None:
-    upload = _make_upload("size_unknown.txt", size=1)
-    monkeypatch.setattr(utils, "get_upload_size_bytes", lambda _upload: None)
-
-    caplog.set_level("WARNING")
-    is_too_large = utils.is_upload_too_large(upload, max_bytes=100)
-
-    assert is_too_large is False
-    assert "Could not determine upload size; skipping size-limit check" in caplog.text
-    assert "size_unknown.txt" in caplog.text
-
-
-def test_categorize_uploaded_files_accepts_size_under_limit(
-    monkeypatch: pytest.MonkeyPatch,
-) -> None:
-    _patch_common_dependencies(monkeypatch)
-    monkeypatch.setattr(utils, "USER_FILE_MAX_UPLOAD_SIZE_BYTES", 100)
-    monkeypatch.setattr(utils, "USER_FILE_MAX_UPLOAD_SIZE_MB", 1)
-    monkeypatch.setattr(utils, "estimate_image_tokens_for_upload", lambda _upload: 10)
-
-    upload = _make_upload("small.png", size=99)
-    result = utils.categorize_uploaded_files([upload], MagicMock())
-
-    assert len(result.acceptable) == 1
-    assert len(result.rejected) == 0
-
-
-def test_categorize_uploaded_files_uses_seek_fallback_when_upload_size_missing(
-    monkeypatch: pytest.MonkeyPatch,
-) -> None:
-    _patch_common_dependencies(monkeypatch)
-    monkeypatch.setattr(utils, "USER_FILE_MAX_UPLOAD_SIZE_BYTES", 100)
-    monkeypatch.setattr(utils, "USER_FILE_MAX_UPLOAD_SIZE_MB", 1)
-    monkeypatch.setattr(utils, "estimate_image_tokens_for_upload", lambda _upload: 10)
-
-    upload = _make_upload_no_size("small.png", content=b"x" * 99)
-    result = utils.categorize_uploaded_files([upload], MagicMock())
-
-    assert len(result.acceptable) == 1
-    assert len(result.rejected) == 0
-
-
-def test_categorize_uploaded_files_accepts_size_at_limit(
-    monkeypatch: pytest.MonkeyPatch,
-) -> None:
-    _patch_common_dependencies(monkeypatch)
-    monkeypatch.setattr(utils, "USER_FILE_MAX_UPLOAD_SIZE_BYTES", 100)
-    monkeypatch.setattr(utils, "USER_FILE_MAX_UPLOAD_SIZE_MB", 1)
-    monkeypatch.setattr(utils, "estimate_image_tokens_for_upload", lambda _upload: 10)
-
-    upload = _make_upload("edge.png", size=100)
-    result = utils.categorize_uploaded_files([upload], MagicMock())
-
-    assert len(result.acceptable) == 1
-    assert len(result.rejected) == 0
-
-
-def test_categorize_uploaded_files_rejects_size_over_limit_with_reason(
-    monkeypatch: pytest.MonkeyPatch,
-) -> None:
-    _patch_common_dependencies(monkeypatch)
-    monkeypatch.setattr(utils, "USER_FILE_MAX_UPLOAD_SIZE_BYTES", 100)
-    monkeypatch.setattr(utils, "USER_FILE_MAX_UPLOAD_SIZE_MB", 1)
-    monkeypatch.setattr(utils, "estimate_image_tokens_for_upload", lambda _upload: 10)
-
-    upload = _make_upload("large.png", size=101)
-    result = utils.categorize_uploaded_files([upload], MagicMock())
-
-    assert len(result.acceptable) == 0
-    assert len(result.rejected) == 1
-    assert result.rejected[0].reason == "Exceeds 1 MB file size limit"
-
-
-def test_categorize_uploaded_files_mixed_batch_keeps_valid_and_rejects_oversized(
-    monkeypatch: pytest.MonkeyPatch,
-) -> None:
-    _patch_common_dependencies(monkeypatch)
-    monkeypatch.setattr(utils, "USER_FILE_MAX_UPLOAD_SIZE_BYTES", 100)
-    monkeypatch.setattr(utils, "USER_FILE_MAX_UPLOAD_SIZE_MB", 1)
-    monkeypatch.setattr(utils, "estimate_image_tokens_for_upload", lambda _upload: 10)
-
-    small = _make_upload("small.png", size=50)
-    large = _make_upload("large.png", size=101)
-
-    result = utils.categorize_uploaded_files([small, large], MagicMock())
-
-    assert [file.filename for file in result.acceptable] == ["small.png"]
-    assert len(result.rejected) == 1
-    assert result.rejected[0].filename == "large.png"
-    assert result.rejected[0].reason == "Exceeds 1 MB file size limit"
-
-
-def test_categorize_uploaded_files_enforces_size_limit_even_when_threshold_is_skipped(
-    monkeypatch: pytest.MonkeyPatch,
-) -> None:
-    _patch_common_dependencies(monkeypatch)
-    monkeypatch.setattr(utils, "SKIP_USERFILE_THRESHOLD", True)
-    monkeypatch.setattr(utils, "USER_FILE_MAX_UPLOAD_SIZE_BYTES", 100)
-    monkeypatch.setattr(utils, "USER_FILE_MAX_UPLOAD_SIZE_MB", 1)
-
-    upload = _make_upload("oversized.pdf", size=101)
-    result = utils.categorize_uploaded_files([upload], MagicMock())
-
-    assert len(result.acceptable) == 0
-    assert len(result.rejected) == 1
-    assert result.rejected[0].reason == "Exceeds 1 MB file size limit"
-
-
-def test_categorize_uploaded_files_checks_size_before_text_extraction(
-    monkeypatch: pytest.MonkeyPatch,
-) -> None:
-    _patch_common_dependencies(monkeypatch)
-    monkeypatch.setattr(utils, "USER_FILE_MAX_UPLOAD_SIZE_BYTES", 100)
-    monkeypatch.setattr(utils, "USER_FILE_MAX_UPLOAD_SIZE_MB", 1)
-
-    extract_mock = MagicMock(return_value="this should not run")
-    monkeypatch.setattr(utils, "extract_file_text", extract_mock)
-
-    oversized_doc = _make_upload("oversized.pdf", size=101)
-    result = utils.categorize_uploaded_files([oversized_doc], MagicMock())
-
-    extract_mock.assert_not_called()
-    assert len(result.acceptable) == 0
-    assert len(result.rejected) == 1
-    assert result.rejected[0].reason == "Exceeds 1 MB file size limit"

backend/tests/unit/onyx/server/test_settings_store.py

@@ -1,32 +0,0 @@
-import pytest
-
-from onyx.key_value_store.interface import KvKeyNotFoundError
-from onyx.server.settings import store as settings_store
-
-
-class _FakeKvStore:
-    def load(self, _key: str) -> dict:
-        raise KvKeyNotFoundError()
-
-
-class _FakeCache:
-    def __init__(self) -> None:
-        self._vals: dict[str, bytes] = {}
-
-    def get(self, key: str) -> bytes | None:
-        return self._vals.get(key)
-
-    def set(self, key: str, value: str, ex: int | None = None) -> None:  # noqa: ARG002
-        self._vals[key] = value.encode("utf-8")
-
-
-def test_load_settings_includes_user_file_max_upload_size_mb(
-    monkeypatch: pytest.MonkeyPatch,
-) -> None:
-    monkeypatch.setattr(settings_store, "get_kv_store", lambda: _FakeKvStore())
-    monkeypatch.setattr(settings_store, "get_cache_backend", lambda: _FakeCache())
-    monkeypatch.setattr(settings_store, "USER_FILE_MAX_UPLOAD_SIZE_MB", 77)
-
-    settings = settings_store.load_settings()
-
-    assert settings.user_file_max_upload_size_mb == 77

backend/tests/unit/onyx/utils/test_sensitive.py

@@ -147,18 +147,15 @@ class TestSensitiveValueString:
         )
         assert sensitive1 != sensitive2
 
-    def test_equality_with_non_sensitive_returns_not_equal(self) -> None:
-        """Test that comparing with non-SensitiveValue is always not-equal.
-
-        Returns NotImplemented so Python falls back to identity comparison.
-        This is required for compatibility with SQLAlchemy's attribute tracking.
-        """
+    def test_equality_with_non_sensitive_raises(self) -> None:
+        """Test that comparing with non-SensitiveValue raises error."""
         sensitive = SensitiveValue(
             encrypted_bytes=_encrypt_string("secret"),
             decrypt_fn=_decrypt_string,
             is_json=False,
         )
-        assert not (sensitive == "secret")
+        with pytest.raises(SensitiveAccessError):
+            _ = sensitive == "secret"
 
 
 class TestSensitiveValueJson:

contributing_guides/dev_setup.md

@@ -158,14 +158,14 @@ python ./scripts/dev_run_background_jobs.py
 To run the backend API server, navigate back to `onyx/backend` and run:
 
 ```bash
-AUTH_TYPE=basic uvicorn onyx.main:app --reload --port 8080
+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='basic'
+    $env:AUTH_TYPE='disabled'
     uvicorn onyx.main:app --reload --port 8080
 "
 ```

deployment/docker_compose/docker-compose.search-testing.yml

@@ -21,7 +21,7 @@ services:
     env_file:
       - .env_eval
     environment:
-      - AUTH_TYPE=basic
+      - AUTH_TYPE=disabled
       - POSTGRES_HOST=relational_db
       - VESPA_HOST=index
       - REDIS_HOST=cache
@@ -58,7 +58,7 @@ services:
     env_file:
       - .env_eval
     environment:
-      - AUTH_TYPE=basic
+      - AUTH_TYPE=disabled
       - POSTGRES_HOST=relational_db
       - VESPA_HOST=index
       - REDIS_HOST=cache

deployment/docker_compose/env.template

@@ -20,12 +20,8 @@ IMAGE_TAG=latest
 
 ## Auth Settings
 ### https://docs.onyx.app/deployment/authentication
-AUTH_TYPE=basic
+AUTH_TYPE=disabled
 # SESSION_EXPIRE_TIME_SECONDS=
-### Recommended for basic auth - used for signing password reset and verification tokens
-### If using install.sh, this will be auto-generated
-### If setting manually, run: openssl rand -hex 32
-USER_AUTH_SECRET=""
 ### Recommend to set this for security
 # ENCRYPTION_KEY_SECRET=
 ### Optional

deployment/docker_compose/install.sh

@@ -654,20 +654,17 @@ else
     sed -i.bak "s/^IMAGE_TAG=.*/IMAGE_TAG=$VERSION/" "$ENV_FILE"
     print_success "IMAGE_TAG set to $VERSION"
 
-    # Configure basic authentication (default)
-    sed -i.bak 's/^AUTH_TYPE=.*/AUTH_TYPE=basic/' "$ENV_FILE" 2>/dev/null || true
-    print_success "Basic authentication enabled in configuration"
-
-    # Check if openssl is available
-    if ! command -v openssl &> /dev/null; then
-        print_error "openssl is required to generate secure secrets but was not found."
-        exit 1
+    # Configure authentication settings based on selection
+    if [ "$AUTH_SCHEMA" = "disabled" ]; then
+        # Disable authentication in .env file
+        sed -i.bak 's/^AUTH_TYPE=.*/AUTH_TYPE=disabled/' "$ENV_FILE" 2>/dev/null || true
+        print_success "Authentication disabled in configuration"
+    else
+        # Enable basic authentication
+        sed -i.bak 's/^AUTH_TYPE=.*/AUTH_TYPE=basic/' "$ENV_FILE" 2>/dev/null || true
+        print_success "Basic authentication enabled in configuration"
     fi
 
-    # Generate a secure USER_AUTH_SECRET
-    USER_AUTH_SECRET=$(openssl rand -hex 32)
-    sed -i.bak "s/^USER_AUTH_SECRET=.*/USER_AUTH_SECRET=\"$USER_AUTH_SECRET\"/" "$ENV_FILE" 2>/dev/null || true
-
     # Configure Craft based on flag or if using a craft-* image tag
     # By default, env.template has Craft commented out (disabled)
     if [ "$INCLUDE_CRAFT" = true ] || [[ "$VERSION" == craft-* ]]; then