Package changes

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

@@ -335,6 +335,7 @@ jobs:
           # TODO(Nik): https://linear.app/onyx-app/issue/ENG-1/update-test-infra-to-use-test-license
           LICENSE_ENFORCEMENT_ENABLED=false
           CHECK_TTL_MANAGEMENT_TASK_FREQUENCY_IN_HOURS=0.001
+          USE_LIGHTWEIGHT_BACKGROUND_WORKER=false
           EOF
           fi
 

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

@@ -268,11 +268,10 @@ jobs:
           persist-credentials: false
 
       - name: Setup node
-        # zizmor: ignore[cache-poisoning] ephemeral runners; no release artifacts
         uses: actions/setup-node@6044e13b5dc448c55e2357c09f80417699197238 # ratchet:actions/setup-node@v4
         with:
           node-version: 22
-          cache: "npm" # zizmor: ignore[cache-poisoning]
+          cache: "npm"
           cache-dependency-path: ./web/package-lock.json
 
       - name: Install node dependencies
@@ -280,7 +279,6 @@ jobs:
         run: npm ci
 
       - name: Cache playwright cache
-        # zizmor: ignore[cache-poisoning] ephemeral runners; no release artifacts
         uses: runs-on/cache@50350ad4242587b6c8c2baa2e740b1bc11285ff4 # ratchet:runs-on/cache@v4
         with:
           path: ~/.cache/ms-playwright
@@ -592,108 +590,6 @@ jobs:
           name: docker-logs-${{ matrix.project }}-${{ github.run_id }}
           path: ${{ github.workspace }}/docker-compose.log
 
-  playwright-tests-lite:
-    needs: [build-web-image, build-backend-image]
-    name: Playwright Tests (lite)
-    runs-on:
-      - runs-on
-      - runner=4cpu-linux-arm64
-      - "run-id=${{ github.run_id }}-playwright-tests-lite"
-      - "extras=ecr-cache"
-    timeout-minutes: 30
-    steps:
-      - uses: runs-on/action@cd2b598b0515d39d78c38a02d529db87d2196d1e # ratchet:runs-on/action@v2
-
-      - name: Checkout code
-        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # ratchet:actions/checkout@v6
-        with:
-          persist-credentials: false
-
-      - name: Setup node
-        # zizmor: ignore[cache-poisoning] ephemeral runners; no release artifacts
-        uses: actions/setup-node@6044e13b5dc448c55e2357c09f80417699197238 # ratchet:actions/setup-node@v4
-        with:
-          node-version: 22
-          cache: "npm" # zizmor: ignore[cache-poisoning]
-          cache-dependency-path: ./web/package-lock.json
-
-      - name: Install node dependencies
-        working-directory: ./web
-        run: npm ci
-
-      - name: Cache playwright cache
-        # zizmor: ignore[cache-poisoning] ephemeral runners; no release artifacts
-        uses: runs-on/cache@50350ad4242587b6c8c2baa2e740b1bc11285ff4 # ratchet:runs-on/cache@v4
-        with:
-          path: ~/.cache/ms-playwright
-          key: ${{ runner.os }}-playwright-npm-${{ hashFiles('web/package-lock.json') }}
-          restore-keys: |
-            ${{ runner.os }}-playwright-npm-
-
-      - name: Install playwright browsers
-        working-directory: ./web
-        run: npx playwright install --with-deps
-
-      - name: Create .env file for Docker Compose
-        env:
-          OPENAI_API_KEY_VALUE: ${{ env.OPENAI_API_KEY }}
-          ECR_CACHE: ${{ env.RUNS_ON_ECR_CACHE }}
-          RUN_ID: ${{ github.run_id }}
-        run: |
-          cat <<EOF > deployment/docker_compose/.env
-          ENABLE_PAID_ENTERPRISE_EDITION_FEATURES=true
-          LICENSE_ENFORCEMENT_ENABLED=false
-          AUTH_TYPE=basic
-          INTEGRATION_TESTS_MODE=true
-          GEN_AI_API_KEY=${OPENAI_API_KEY_VALUE}
-          MOCK_LLM_RESPONSE=true
-          REQUIRE_EMAIL_VERIFICATION=false
-          DISABLE_TELEMETRY=true
-          ONYX_BACKEND_IMAGE=${ECR_CACHE}:playwright-test-backend-${RUN_ID}
-          ONYX_WEB_SERVER_IMAGE=${ECR_CACHE}:playwright-test-web-${RUN_ID}
-          EOF
-
-      # needed for pulling external images otherwise, we hit the "Unauthenticated users" limit
-      # https://docs.docker.com/docker-hub/usage/
-      - name: Login to Docker Hub
-        uses: docker/login-action@c94ce9fb468520275223c153574b00df6fe4bcc9 # ratchet:docker/login-action@v3
-        with:
-          username: ${{ secrets.DOCKER_USERNAME }}
-          password: ${{ secrets.DOCKER_TOKEN }}
-
-      - name: Start Docker containers (lite)
-        run: |
-          cd deployment/docker_compose
-          docker compose -f docker-compose.yml -f docker-compose.onyx-lite.yml -f docker-compose.dev.yml up -d
-        id: start_docker
-
-      - name: Run Playwright tests (lite)
-        working-directory: ./web
-        run: npx playwright test --project lite
-
-      - uses: actions/upload-artifact@b7c566a772e6b6bfb58ed0dc250532a479d7789f
-        if: always()
-        with:
-          name: playwright-test-results-lite-${{ github.run_id }}
-          path: ./web/output/playwright/
-          retention-days: 30
-
-      - name: Save Docker logs
-        if: success() || failure()
-        env:
-          WORKSPACE: ${{ github.workspace }}
-        run: |
-          cd deployment/docker_compose
-          docker compose logs > docker-compose.log
-          mv docker-compose.log ${WORKSPACE}/docker-compose.log
-
-      - name: Upload logs
-        if: success() || failure()
-        uses: actions/upload-artifact@b7c566a772e6b6bfb58ed0dc250532a479d7789f
-        with:
-          name: docker-logs-lite-${{ github.run_id }}
-          path: ${{ github.workspace }}/docker-compose.log
-
   # Post a single combined visual regression comment after all matrix jobs finish
   visual-regression-comment:
     needs: [playwright-tests]
@@ -790,7 +686,7 @@ jobs:
     # NOTE: Github-hosted runners have about 20s faster queue times and are preferred here.
     runs-on: ubuntu-slim
     timeout-minutes: 45
-    needs: [playwright-tests, playwright-tests-lite]
+    needs: [playwright-tests]
     if: ${{ always() }}
     steps:
       - name: Check job status

.vscode/launch.json

@@ -40,7 +40,19 @@
       }
     },
     {
-      "name": "Celery",
+      "name": "Celery (lightweight mode)",
+      "configurations": [
+        "Celery primary",
+        "Celery background",
+        "Celery beat"
+      ],
+      "presentation": {
+        "group": "1"
+      },
+      "stopAll": true
+    },
+    {
+      "name": "Celery (standard mode)",
       "configurations": [
         "Celery primary",
         "Celery light",
@@ -241,6 +253,35 @@
       },
       "consoleTitle": "Celery light Console"
     },
+    {
+      "name": "Celery background",
+      "type": "debugpy",
+      "request": "launch",
+      "module": "celery",
+      "cwd": "${workspaceFolder}/backend",
+      "envFile": "${workspaceFolder}/.vscode/.env",
+      "env": {
+        "LOG_LEVEL": "INFO",
+        "PYTHONUNBUFFERED": "1",
+        "PYTHONPATH": "."
+      },
+      "args": [
+        "-A",
+        "onyx.background.celery.versioned_apps.background",
+        "worker",
+        "--pool=threads",
+        "--concurrency=20",
+        "--prefetch-multiplier=4",
+        "--loglevel=INFO",
+        "--hostname=background@%n",
+        "-Q",
+        "vespa_metadata_sync,connector_deletion,doc_permissions_upsert,checkpoint_cleanup,index_attempt_cleanup,docprocessing,connector_doc_fetching,connector_pruning,connector_doc_permissions_sync,connector_external_group_sync,csv_generation,kg_processing,monitoring,user_file_processing,user_file_project_sync,user_file_delete,opensearch_migration"
+      ],
+      "presentation": {
+        "group": "2"
+      },
+      "consoleTitle": "Celery background Console"
+    },
     {
       "name": "Celery heavy",
       "type": "debugpy",
@@ -485,6 +526,21 @@
         "group": "3"
       }
     },
+    {
+      "name": "Clear and Restart OpenSearch Container",
+      // Generic debugger type, required arg but has no bearing on bash.
+      "type": "node",
+      "request": "launch",
+      "runtimeExecutable": "bash",
+      "runtimeArgs": [
+        "${workspaceFolder}/backend/scripts/restart_opensearch_container.sh"
+      ],
+      "cwd": "${workspaceFolder}",
+      "console": "integratedTerminal",
+      "presentation": {
+        "group": "3"
+      }
+    },
     {
       "name": "Eval CLI",
       "type": "debugpy",

AGENTS.md

@@ -86,6 +86,37 @@ Onyx uses Celery for asynchronous task processing with multiple specialized work
      - Monitoring tasks (every 5 minutes)
      - Cleanup tasks (hourly)
 
+#### Worker Deployment Modes
+
+Onyx supports two deployment modes for background workers, controlled by the `USE_LIGHTWEIGHT_BACKGROUND_WORKER` environment variable:
+
+**Lightweight Mode** (default, `USE_LIGHTWEIGHT_BACKGROUND_WORKER=true`):
+
+- Runs a single consolidated `background` worker that handles all background tasks:
+  - Light worker tasks (Vespa operations, permissions sync, deletion)
+  - Document processing (indexing pipeline)
+  - Document fetching (connector data retrieval)
+  - Pruning operations (from `heavy` worker)
+  - Knowledge graph processing (from `kg_processing` worker)
+  - Monitoring tasks (from `monitoring` worker)
+  - User file processing (from `user_file_processing` worker)
+- Lower resource footprint (fewer worker processes)
+- Suitable for smaller deployments or development environments
+- Default concurrency: 20 threads (increased to handle combined workload)
+
+**Standard Mode** (`USE_LIGHTWEIGHT_BACKGROUND_WORKER=false`):
+
+- Runs separate specialized workers as documented above (light, docprocessing, docfetching, heavy, kg_processing, monitoring, user_file_processing)
+- Better isolation and scalability
+- Can scale individual workers independently based on workload
+- Suitable for production deployments with higher load
+
+The deployment mode affects:
+
+- **Backend**: Worker processes spawned by supervisord or dev scripts
+- **Helm**: Which Kubernetes deployments are created
+- **Dev Environment**: Which workers `dev_run_background_jobs.py` spawns
+
 #### Key Features
 
 - **Thread-based Workers**: All workers use thread pools (not processes) for stability

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

@@ -0,0 +1,15 @@
+from onyx.background.celery.apps import app_base
+from onyx.background.celery.apps.background import celery_app
+
+
+celery_app.autodiscover_tasks(
+    app_base.filter_task_modules(
+        [
+            "ee.onyx.background.celery.tasks.doc_permission_syncing",
+            "ee.onyx.background.celery.tasks.external_group_syncing",
+            "ee.onyx.background.celery.tasks.cleanup",
+            "ee.onyx.background.celery.tasks.tenant_provisioning",
+            "ee.onyx.background.celery.tasks.query_history",
+        ]
+    )
+)

backend/ee/onyx/db/user_group.py

@@ -15,7 +15,6 @@ from sqlalchemy.orm import Session
 from ee.onyx.server.user_group.models import SetCuratorRequest
 from ee.onyx.server.user_group.models import UserGroupCreate
 from ee.onyx.server.user_group.models import UserGroupUpdate
-from onyx.configs.app_configs import DISABLE_VECTOR_DB
 from onyx.db.connector_credential_pair import get_connector_credential_pair_from_id
 from onyx.db.enums import AccessType
 from onyx.db.enums import ConnectorCredentialPairStatus
@@ -472,9 +471,7 @@ def _add_user_group__cc_pair_relationships__no_commit(
 
 def insert_user_group(db_session: Session, user_group: UserGroupCreate) -> UserGroup:
     db_user_group = UserGroup(
-        name=user_group.name,
-        time_last_modified_by_user=func.now(),
-        is_up_to_date=DISABLE_VECTOR_DB,
+        name=user_group.name, time_last_modified_by_user=func.now()
     )
     db_session.add(db_user_group)
     db_session.flush()  # give the group an ID
@@ -777,7 +774,8 @@ def update_user_group(
             cc_pair_ids=user_group_update.cc_pair_ids,
         )
 
-    if cc_pairs_updated and not DISABLE_VECTOR_DB:
+    # only needs to sync with Vespa if the cc_pairs have been updated
+    if cc_pairs_updated:
         db_user_group.is_up_to_date = False
 
     removed_users = db_session.scalars(

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

@@ -223,15 +223,6 @@ def get_active_scim_token(
     token = dal.get_active_token()
     if not token:
         raise HTTPException(status_code=404, detail="No active SCIM token")
-
-    # Derive the IdP domain from the first synced user as a heuristic.
-    idp_domain: str | None = None
-    mappings, _total = dal.list_user_mappings(start_index=1, count=1)
-    if mappings:
-        user = dal.get_user(mappings[0].user_id)
-        if user and "@" in user.email:
-            idp_domain = user.email.rsplit("@", 1)[1]
-
     return ScimTokenResponse(
         id=token.id,
         name=token.name,
@@ -239,7 +230,6 @@ def get_active_scim_token(
         is_active=token.is_active,
         created_at=token.created_at,
         last_used_at=token.last_used_at,
-        idp_domain=idp_domain,
     )
 
 

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

@@ -365,7 +365,6 @@ class ScimTokenResponse(BaseModel):
     is_active: bool
     created_at: datetime
     last_used_at: datetime | None = None
-    idp_domain: str | None = None
 
 
 class ScimTokenCreatedResponse(ScimTokenResponse):

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

@@ -5,8 +5,6 @@ from sqlalchemy.exc import IntegrityError
 from sqlalchemy.orm import Session
 
 from ee.onyx.db.user_group import add_users_to_user_group
-from ee.onyx.db.user_group import delete_user_group as db_delete_user_group
-from ee.onyx.db.user_group import fetch_user_group
 from ee.onyx.db.user_group import fetch_user_groups
 from ee.onyx.db.user_group import fetch_user_groups_for_user
 from ee.onyx.db.user_group import insert_user_group
@@ -22,7 +20,6 @@ from ee.onyx.server.user_group.models import UserGroupUpdate
 from onyx.auth.users import current_admin_user
 from onyx.auth.users import current_curator_or_admin_user
 from onyx.auth.users import current_user
-from onyx.configs.app_configs import DISABLE_VECTOR_DB
 from onyx.configs.constants import PUBLIC_API_TAGS
 from onyx.db.engine.sql_engine import get_session
 from onyx.db.models import User
@@ -156,8 +153,3 @@ def delete_user_group(
         prepare_user_group_for_deletion(db_session, user_group_id)
     except ValueError as e:
         raise HTTPException(status_code=404, detail=str(e))
-
-    if DISABLE_VECTOR_DB:
-        user_group = fetch_user_group(db_session, user_group_id)
-        if user_group:
-            db_delete_user_group(db_session, user_group)

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

@@ -0,0 +1,142 @@
+from typing import Any
+from typing import cast
+
+from celery import Celery
+from celery import signals
+from celery import Task
+from celery.apps.worker import Worker
+from celery.signals import celeryd_init
+from celery.signals import worker_init
+from celery.signals import worker_process_init
+from celery.signals import worker_ready
+from celery.signals import worker_shutdown
+
+import onyx.background.celery.apps.app_base as app_base
+from onyx.background.celery.celery_utils import httpx_init_vespa_pool
+from onyx.configs.app_configs import MANAGED_VESPA
+from onyx.configs.app_configs import VESPA_CLOUD_CERT_PATH
+from onyx.configs.app_configs import VESPA_CLOUD_KEY_PATH
+from onyx.configs.constants import POSTGRES_CELERY_WORKER_BACKGROUND_APP_NAME
+from onyx.db.engine.sql_engine import SqlEngine
+from onyx.utils.logger import setup_logger
+from shared_configs.configs import MULTI_TENANT
+
+
+logger = setup_logger()
+
+celery_app = Celery(__name__)
+celery_app.config_from_object("onyx.background.celery.configs.background")
+celery_app.Task = app_base.TenantAwareTask  # type: ignore [misc]
+
+
+@signals.task_prerun.connect
+def on_task_prerun(
+    sender: Any | None = None,
+    task_id: str | None = None,
+    task: Task | None = None,
+    args: tuple | None = None,
+    kwargs: dict | None = None,
+    **kwds: Any,
+) -> None:
+    app_base.on_task_prerun(sender, task_id, task, args, kwargs, **kwds)
+
+
+@signals.task_postrun.connect
+def on_task_postrun(
+    sender: Any | None = None,
+    task_id: str | None = None,
+    task: Task | None = None,
+    args: tuple | None = None,
+    kwargs: dict | None = None,
+    retval: Any | None = None,
+    state: str | None = None,
+    **kwds: Any,
+) -> None:
+    app_base.on_task_postrun(sender, task_id, task, args, kwargs, retval, state, **kwds)
+
+
+@celeryd_init.connect
+def on_celeryd_init(sender: str, conf: Any = None, **kwargs: Any) -> None:
+    app_base.on_celeryd_init(sender, conf, **kwargs)
+
+
+@worker_init.connect
+def on_worker_init(sender: Worker, **kwargs: Any) -> None:
+    EXTRA_CONCURRENCY = 8  # small extra fudge factor for connection limits
+
+    logger.info("worker_init signal received for consolidated background worker.")
+
+    SqlEngine.set_app_name(POSTGRES_CELERY_WORKER_BACKGROUND_APP_NAME)
+    pool_size = cast(int, sender.concurrency)  # type: ignore
+    SqlEngine.init_engine(pool_size=pool_size, max_overflow=EXTRA_CONCURRENCY)
+
+    # Initialize Vespa httpx pool (needed for light worker tasks)
+    if MANAGED_VESPA:
+        httpx_init_vespa_pool(
+            sender.concurrency + EXTRA_CONCURRENCY,  # type: ignore
+            ssl_cert=VESPA_CLOUD_CERT_PATH,
+            ssl_key=VESPA_CLOUD_KEY_PATH,
+        )
+    else:
+        httpx_init_vespa_pool(sender.concurrency + EXTRA_CONCURRENCY)  # type: ignore
+
+    app_base.wait_for_redis(sender, **kwargs)
+    app_base.wait_for_db(sender, **kwargs)
+    app_base.wait_for_vespa_or_shutdown(sender, **kwargs)
+
+    # Less startup checks in multi-tenant case
+    if MULTI_TENANT:
+        return
+
+    app_base.on_secondary_worker_init(sender, **kwargs)
+
+
+@worker_ready.connect
+def on_worker_ready(sender: Any, **kwargs: Any) -> None:
+    app_base.on_worker_ready(sender, **kwargs)
+
+
+@worker_shutdown.connect
+def on_worker_shutdown(sender: Any, **kwargs: Any) -> None:
+    app_base.on_worker_shutdown(sender, **kwargs)
+
+
+@worker_process_init.connect
+def init_worker(**kwargs: Any) -> None:  # noqa: ARG001
+    SqlEngine.reset_engine()
+
+
+@signals.setup_logging.connect
+def on_setup_logging(
+    loglevel: Any, logfile: Any, format: Any, colorize: Any, **kwargs: Any
+) -> None:
+    app_base.on_setup_logging(loglevel, logfile, format, colorize, **kwargs)
+
+
+base_bootsteps = app_base.get_bootsteps()
+for bootstep in base_bootsteps:
+    celery_app.steps["worker"].add(bootstep)
+
+celery_app.autodiscover_tasks(
+    app_base.filter_task_modules(
+        [
+            # Original background worker tasks
+            "onyx.background.celery.tasks.pruning",
+            "onyx.background.celery.tasks.monitoring",
+            "onyx.background.celery.tasks.user_file_processing",
+            "onyx.background.celery.tasks.llm_model_update",
+            # Light worker tasks
+            "onyx.background.celery.tasks.shared",
+            "onyx.background.celery.tasks.vespa",
+            "onyx.background.celery.tasks.connector_deletion",
+            "onyx.background.celery.tasks.doc_permission_syncing",
+            "onyx.background.celery.tasks.opensearch_migration",
+            # Docprocessing worker tasks
+            "onyx.background.celery.tasks.docprocessing",
+            # Docfetching worker tasks
+            "onyx.background.celery.tasks.docfetching",
+            # Sandbox cleanup tasks (isolated in build feature)
+            "onyx.server.features.build.sandbox.tasks",
+        ]
+    )
+)

backend/onyx/background/celery/celery_utils.py

@@ -39,13 +39,9 @@ CT = TypeVar("CT", bound=ConnectorCheckpoint)
 
 
 class SlimConnectorExtractionResult(BaseModel):
-    """Result of extracting document IDs and hierarchy nodes from a connector.
+    """Result of extracting document IDs and hierarchy nodes from a connector."""
 
-    raw_id_to_parent maps document ID → parent_hierarchy_raw_node_id (or None).
-    Use raw_id_to_parent.keys() wherever the old set of IDs was needed.
-    """
-
-    raw_id_to_parent: dict[str, str | None]
+    doc_ids: set[str]
     hierarchy_nodes: list[HierarchyNode]
 
 
@@ -97,37 +93,30 @@ def _get_failure_id(failure: ConnectorFailure) -> str | None:
     return None
 
 
-class BatchResult(BaseModel):
-    raw_id_to_parent: dict[str, str | None]
-    hierarchy_nodes: list[HierarchyNode]
-
-
 def _extract_from_batch(
     doc_list: Sequence[Document | SlimDocument | HierarchyNode | ConnectorFailure],
-) -> BatchResult:
-    """Separate a batch into document IDs (with parent mapping) and hierarchy nodes.
+) -> tuple[set[str], list[HierarchyNode]]:
+    """Separate a batch into document IDs and hierarchy nodes.
 
     ConnectorFailure items have their failed document/entity IDs added to the
-    ID dict so that failed-to-retrieve documents are not accidentally pruned.
+    ID set so that failed-to-retrieve documents are not accidentally pruned.
     """
-    ids: dict[str, str | None] = {}
+    ids: set[str] = set()
     hierarchy_nodes: list[HierarchyNode] = []
     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
+            ids.add(item.raw_node_id)
         elif isinstance(item, ConnectorFailure):
             failed_id = _get_failure_id(item)
             if failed_id:
-                ids[failed_id] = None
+                ids.add(failed_id)
             logger.warning(
                 f"Failed to retrieve document {failed_id}: " f"{item.failure_message}"
             )
         else:
-            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)
+            ids.add(item.id)
+    return ids, hierarchy_nodes
 
 
 def extract_ids_from_runnable_connector(
@@ -143,7 +132,7 @@ def extract_ids_from_runnable_connector(
 
     Optionally, a callback can be passed to handle the length of each document batch.
     """
-    all_raw_id_to_parent: dict[str, str | None] = {}
+    all_connector_doc_ids: set[str] = set()
     all_hierarchy_nodes: list[HierarchyNode] = []
 
     # Sequence (covariant) lets all the specific list[...] iterator types unify here
@@ -188,20 +177,15 @@ def extract_ids_from_runnable_connector(
                 "extract_ids_from_runnable_connector: Stop signal detected"
             )
 
-        batch_result = _extract_from_batch(doc_list)
-        batch_ids = batch_result.raw_id_to_parent
-        batch_nodes = batch_result.hierarchy_nodes
-        doc_batch_processing_func(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
+        batch_ids, batch_nodes = _extract_from_batch(doc_list)
+        all_connector_doc_ids.update(doc_batch_processing_func(batch_ids))
         all_hierarchy_nodes.extend(batch_nodes)
 
         if callback:
             callback.progress("extract_ids_from_runnable_connector", len(batch_ids))
 
     return SlimConnectorExtractionResult(
-        raw_id_to_parent=all_raw_id_to_parent,
+        doc_ids=all_connector_doc_ids,
         hierarchy_nodes=all_hierarchy_nodes,
     )
 

backend/onyx/background/celery/configs/background.py

@@ -0,0 +1,23 @@
+import onyx.background.celery.configs.base as shared_config
+from onyx.configs.app_configs import CELERY_WORKER_BACKGROUND_CONCURRENCY
+
+broker_url = shared_config.broker_url
+broker_connection_retry_on_startup = shared_config.broker_connection_retry_on_startup
+broker_pool_limit = shared_config.broker_pool_limit
+broker_transport_options = shared_config.broker_transport_options
+
+redis_socket_keepalive = shared_config.redis_socket_keepalive
+redis_retry_on_timeout = shared_config.redis_retry_on_timeout
+redis_backend_health_check_interval = shared_config.redis_backend_health_check_interval
+
+result_backend = shared_config.result_backend
+result_expires = shared_config.result_expires  # 86400 seconds is the default
+
+task_default_priority = shared_config.task_default_priority
+task_acks_late = shared_config.task_acks_late
+
+worker_concurrency = CELERY_WORKER_BACKGROUND_CONCURRENCY
+worker_pool = "threads"
+# Increased from 1 to 4 to handle fast light worker tasks more efficiently
+# This allows the worker to prefetch multiple tasks per thread
+worker_prefetch_multiplier = 4

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

@@ -29,7 +29,6 @@ from onyx.configs.constants import CELERY_GENERIC_BEAT_LOCK_TIMEOUT
 from onyx.configs.constants import CELERY_PRUNING_LOCK_TIMEOUT
 from onyx.configs.constants import CELERY_TASK_WAIT_FOR_FENCE_TIMEOUT
 from onyx.configs.constants import DANSWER_REDIS_FUNCTION_LOCK_PREFIX
-from onyx.configs.constants import DocumentSource
 from onyx.configs.constants import OnyxCeleryPriority
 from onyx.configs.constants import OnyxCeleryQueues
 from onyx.configs.constants import OnyxCeleryTask
@@ -48,8 +47,6 @@ 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 link_hierarchy_nodes_to_documents
-from onyx.db.hierarchy import update_document_parent_hierarchy_nodes
 from onyx.db.hierarchy import upsert_hierarchy_nodes_batch
 from onyx.db.models import ConnectorCredentialPair
 from onyx.db.sync_record import insert_sync_record
@@ -60,8 +57,6 @@ 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 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
 from onyx.redis.redis_pool import get_redis_client
 from onyx.redis.redis_pool import get_redis_replica_client
@@ -118,38 +113,6 @@ class PruneCallback(IndexingCallbackBase):
         super().progress(tag, amount)
 
 
-def _resolve_and_update_document_parents(
-    db_session: Session,
-    redis_client: Redis,
-    source: DocumentSource,
-    raw_id_to_parent: dict[str, str | None],
-) -> None:
-    """Resolve parent_hierarchy_raw_node_id → parent_hierarchy_node_id for
-    each document and bulk-update the DB. Mirrors the resolution logic in
-    run_docfetching.py."""
-    source_node_id = get_source_node_id_from_cache(redis_client, db_session, source)
-
-    resolved: dict[str, int | None] = {}
-    for doc_id, raw_parent_id in raw_id_to_parent.items():
-        if raw_parent_id is None:
-            continue
-        node_id, found = get_node_id_from_raw_id(redis_client, source, raw_parent_id)
-        resolved[doc_id] = node_id if found else source_node_id
-
-    if not resolved:
-        return
-
-    update_document_parent_hierarchy_nodes(
-        db_session=db_session,
-        doc_parent_map=resolved,
-        commit=True,
-    )
-    task_logger.info(
-        f"Pruning: resolved and updated parent hierarchy for "
-        f"{len(resolved)} documents (source={source.value})"
-    )
-
-
 """Jobs / utils for kicking off pruning tasks."""
 
 
@@ -572,22 +535,22 @@ def connector_pruning_generator_task(
             extraction_result = extract_ids_from_runnable_connector(
                 runnable_connector, callback
             )
-            all_connector_doc_ids = extraction_result.raw_id_to_parent
+            all_connector_doc_ids = extraction_result.doc_ids
 
             # Process hierarchy nodes (same as docfetching):
             # upsert to Postgres and cache in Redis
-            source = cc_pair.connector.source
-            redis_client = get_redis_client(tenant_id=tenant_id)
-
             if extraction_result.hierarchy_nodes:
                 is_connector_public = cc_pair.access_type == AccessType.PUBLIC
 
-                ensure_source_node_exists(redis_client, db_session, source)
+                redis_client = get_redis_client(tenant_id=tenant_id)
+                ensure_source_node_exists(
+                    redis_client, db_session, cc_pair.connector.source
+                )
 
                 upserted_nodes = upsert_hierarchy_nodes_batch(
                     db_session=db_session,
                     nodes=extraction_result.hierarchy_nodes,
-                    source=source,
+                    source=cc_pair.connector.source,
                     commit=True,
                     is_connector_public=is_connector_public,
                 )
@@ -598,7 +561,7 @@ def connector_pruning_generator_task(
                 ]
                 cache_hierarchy_nodes_batch(
                     redis_client=redis_client,
-                    source=source,
+                    source=cc_pair.connector.source,
                     entries=cache_entries,
                 )
 
@@ -607,26 +570,6 @@ 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(
-                db_session=db_session,
-                redis_client=redis_client,
-                source=source,
-                raw_id_to_parent=all_connector_doc_ids,
-            )
-
-            # Link hierarchy nodes to documents for sources where pages can be
-            # both hierarchy nodes AND documents (e.g. Notion, Confluence)
-            all_doc_id_list = list(all_connector_doc_ids.keys())
-            link_hierarchy_nodes_to_documents(
-                db_session=db_session,
-                document_ids=all_doc_id_list,
-                source=source,
-                commit=True,
-            )
-
             # a list of docs in our local index
             all_indexed_document_ids = {
                 doc.id
@@ -638,9 +581,7 @@ def connector_pruning_generator_task(
             }
 
             # generate list of docs to remove (no longer in the source)
-            doc_ids_to_remove = list(
-                all_indexed_document_ids - all_connector_doc_ids.keys()
-            )
+            doc_ids_to_remove = list(all_indexed_document_ids - all_connector_doc_ids)
 
             task_logger.info(
                 "Pruning set collected: "

backend/onyx/background/celery/versioned_apps/background.py

@@ -0,0 +1,10 @@
+from celery import Celery
+
+from onyx.utils.variable_functionality import fetch_versioned_implementation
+from onyx.utils.variable_functionality import set_is_ee_based_on_env_variable
+
+set_is_ee_based_on_env_variable()
+app: Celery = fetch_versioned_implementation(
+    "onyx.background.celery.apps.background",
+    "celery_app",
+)

backend/onyx/configs/app_configs.py

@@ -495,7 +495,14 @@ CELERY_WORKER_PRIMARY_POOL_OVERFLOW = int(
     os.environ.get("CELERY_WORKER_PRIMARY_POOL_OVERFLOW") or 4
 )
 
-# Individual worker concurrency settings
+# Consolidated background worker (light, docprocessing, docfetching, heavy, monitoring, user_file_processing)
+# separate workers' defaults: light=24, docprocessing=6, docfetching=1, heavy=4, kg=2, monitoring=1, user_file=2
+# Total would be 40, but we use a more conservative default of 20 for the consolidated worker
+CELERY_WORKER_BACKGROUND_CONCURRENCY = int(
+    os.environ.get("CELERY_WORKER_BACKGROUND_CONCURRENCY") or 20
+)
+
+# Individual worker concurrency settings (used when USE_LIGHTWEIGHT_BACKGROUND_WORKER is False or on Kuberenetes deployments)
 CELERY_WORKER_HEAVY_CONCURRENCY = int(
     os.environ.get("CELERY_WORKER_HEAVY_CONCURRENCY") or 4
 )

backend/onyx/configs/constants.py

@@ -84,6 +84,7 @@ POSTGRES_CELERY_WORKER_LIGHT_APP_NAME = "celery_worker_light"
 POSTGRES_CELERY_WORKER_DOCPROCESSING_APP_NAME = "celery_worker_docprocessing"
 POSTGRES_CELERY_WORKER_DOCFETCHING_APP_NAME = "celery_worker_docfetching"
 POSTGRES_CELERY_WORKER_INDEXING_CHILD_APP_NAME = "celery_worker_indexing_child"
+POSTGRES_CELERY_WORKER_BACKGROUND_APP_NAME = "celery_worker_background"
 POSTGRES_CELERY_WORKER_HEAVY_APP_NAME = "celery_worker_heavy"
 POSTGRES_CELERY_WORKER_MONITORING_APP_NAME = "celery_worker_monitoring"
 POSTGRES_CELERY_WORKER_USER_FILE_PROCESSING_APP_NAME = (

backend/onyx/connectors/confluence/connector.py

@@ -943,9 +943,6 @@ class ConfluenceConnector(
                         if include_permissions
                         else None
                     ),
-                    parent_hierarchy_raw_node_id=self._get_parent_hierarchy_raw_id(
-                        page
-                    ),
                 )
             )
 
@@ -995,7 +992,6 @@ class ConfluenceConnector(
                             if include_permissions
                             else None
                         ),
-                        parent_hierarchy_raw_node_id=page_id,
                     )
                 )
 

backend/onyx/connectors/google_drive/doc_conversion.py

@@ -781,5 +781,4 @@ def build_slim_document(
     return SlimDocument(
         id=onyx_document_id_from_drive_file(file),
         external_access=external_access,
-        parent_hierarchy_raw_node_id=(file.get("parents") or [None])[0],
     )

backend/onyx/connectors/jira/connector.py

@@ -902,11 +902,6 @@ class JiraConnector(
                         external_access=self._get_project_permissions(
                             project_key, add_prefix=False
                         ),
-                        parent_hierarchy_raw_node_id=(
-                            self._get_parent_hierarchy_raw_node_id(issue, project_key)
-                            if project_key
-                            else None
-                        ),
                     )
                 )
                 current_offset += 1

backend/onyx/connectors/models.py

@@ -385,7 +385,6 @@ class IndexingDocument(Document):
 class SlimDocument(BaseModel):
     id: str
     external_access: ExternalAccess | None = None
-    parent_hierarchy_raw_node_id: str | None = None
 
 
 class HierarchyNode(BaseModel):

backend/onyx/connectors/sharepoint/connector.py

@@ -772,7 +772,6 @@ def _convert_driveitem_to_slim_document(
     drive_name: str,
     ctx: ClientContext,
     graph_client: GraphClient,
-    parent_hierarchy_raw_node_id: str | None = None,
 ) -> SlimDocument:
     if driveitem.id is None:
         raise ValueError("DriveItem ID is required")
@@ -788,15 +787,11 @@ def _convert_driveitem_to_slim_document(
     return SlimDocument(
         id=driveitem.id,
         external_access=external_access,
-        parent_hierarchy_raw_node_id=parent_hierarchy_raw_node_id,
     )
 
 
 def _convert_sitepage_to_slim_document(
-    site_page: dict[str, Any],
-    ctx: ClientContext | None,
-    graph_client: GraphClient,
-    parent_hierarchy_raw_node_id: str | None = None,
+    site_page: dict[str, Any], ctx: ClientContext | None, graph_client: GraphClient
 ) -> SlimDocument:
     """Convert a SharePoint site page to a SlimDocument object."""
     if site_page.get("id") is None:
@@ -813,7 +808,6 @@ def _convert_sitepage_to_slim_document(
     return SlimDocument(
         id=id,
         external_access=external_access,
-        parent_hierarchy_raw_node_id=parent_hierarchy_raw_node_id,
     )
 
 
@@ -1600,22 +1594,12 @@ class SharepointConnector(
                             )
                         )
 
-                    parent_hierarchy_url: str | None = None
-                    if drive_web_url:
-                        parent_hierarchy_url = self._get_parent_hierarchy_url(
-                            site_url, drive_web_url, drive_name, driveitem
-                        )
-
                     try:
                         logger.debug(f"Processing: {driveitem.web_url}")
                         ctx = self._create_rest_client_context(site_descriptor.url)
                         doc_batch.append(
                             _convert_driveitem_to_slim_document(
-                                driveitem,
-                                drive_name,
-                                ctx,
-                                self.graph_client,
-                                parent_hierarchy_raw_node_id=parent_hierarchy_url,
+                                driveitem, drive_name, ctx, self.graph_client
                             )
                         )
                     except Exception as e:
@@ -1635,10 +1619,7 @@ class SharepointConnector(
                     ctx = self._create_rest_client_context(site_descriptor.url)
                     doc_batch.append(
                         _convert_sitepage_to_slim_document(
-                            site_page,
-                            ctx,
-                            self.graph_client,
-                            parent_hierarchy_raw_node_id=site_descriptor.url,
+                            site_page, ctx, self.graph_client
                         )
                     )
                     if len(doc_batch) >= SLIM_BATCH_SIZE:

backend/onyx/connectors/slack/connector.py

@@ -565,7 +565,6 @@ def _get_all_doc_ids(
                             channel_id=channel_id, thread_ts=message["ts"]
                         ),
                         external_access=external_access,
-                        parent_hierarchy_raw_node_id=channel_id,
                     )
                 )
 

backend/onyx/db/document_set.py

@@ -13,7 +13,6 @@ from sqlalchemy.orm import aliased
 from sqlalchemy.orm import selectinload
 from sqlalchemy.orm import Session
 
-from onyx.configs.app_configs import DISABLE_VECTOR_DB
 from onyx.db.connector_credential_pair import get_cc_pair_groups_for_ids
 from onyx.db.connector_credential_pair import get_connector_credential_pairs
 from onyx.db.enums import AccessType
@@ -247,7 +246,6 @@ def insert_document_set(
             description=document_set_creation_request.description,
             user_id=user_id,
             is_public=document_set_creation_request.is_public,
-            is_up_to_date=DISABLE_VECTOR_DB,
             time_last_modified_by_user=func.now(),
         )
         db_session.add(new_document_set_row)
@@ -338,8 +336,7 @@ def update_document_set(
             )
 
         document_set_row.description = document_set_update_request.description
-        if not DISABLE_VECTOR_DB:
-            document_set_row.is_up_to_date = False
+        document_set_row.is_up_to_date = False
         document_set_row.is_public = document_set_update_request.is_public
         document_set_row.time_last_modified_by_user = func.now()
         versioned_private_doc_set_fn = fetch_versioned_implementation(

backend/onyx/db/hierarchy.py

@@ -1,7 +1,5 @@
 """CRUD operations for HierarchyNode."""
 
-from collections import defaultdict
-
 from sqlalchemy import select
 from sqlalchemy.orm import Session
 
@@ -527,53 +525,6 @@ def get_document_parent_hierarchy_node_ids(
     return {doc_id: parent_id for doc_id, parent_id in results}
 
 
-def update_document_parent_hierarchy_nodes(
-    db_session: Session,
-    doc_parent_map: dict[str, int | None],
-    commit: bool = True,
-) -> int:
-    """Bulk-update Document.parent_hierarchy_node_id for multiple documents.
-
-    Only updates rows whose current value differs from the desired value to
-    avoid unnecessary writes.
-
-    Args:
-        db_session: SQLAlchemy session
-        doc_parent_map: Mapping of document_id → desired parent_hierarchy_node_id
-        commit: Whether to commit the transaction
-
-    Returns:
-        Number of documents actually updated
-    """
-    if not doc_parent_map:
-        return 0
-
-    doc_ids = list(doc_parent_map.keys())
-    existing = get_document_parent_hierarchy_node_ids(db_session, doc_ids)
-
-    by_parent: dict[int | None, list[str]] = defaultdict(list)
-    for doc_id, desired_parent_id in doc_parent_map.items():
-        current = existing.get(doc_id)
-        if current == desired_parent_id or doc_id not in existing:
-            continue
-        by_parent[desired_parent_id].append(doc_id)
-
-    updated = 0
-    for desired_parent_id, ids in by_parent.items():
-        db_session.query(Document).filter(Document.id.in_(ids)).update(
-            {Document.parent_hierarchy_node_id: desired_parent_id},
-            synchronize_session=False,
-        )
-        updated += len(ids)
-
-    if commit:
-        db_session.commit()
-    elif updated:
-        db_session.flush()
-
-    return updated
-
-
 def update_hierarchy_node_permissions(
     db_session: Session,
     raw_node_id: str,

backend/onyx/db/search_settings.py

@@ -129,7 +129,7 @@ def get_current_search_settings(db_session: Session) -> SearchSettings:
     latest_settings = result.scalars().first()
 
     if not latest_settings:
-        raise RuntimeError("No search settings specified; DB is not in a valid state.")
+        raise RuntimeError("No search settings specified, DB is not in a valid state")
     return latest_settings
 
 

backend/onyx/document_index/document_index_utils.py

@@ -32,6 +32,9 @@ def get_multipass_config(search_settings: SearchSettings) -> MultipassConfig:
     Determines whether to enable multipass and large chunks by examining
     the current search settings and the embedder configuration.
     """
+    if not search_settings:
+        return MultipassConfig(multipass_indexing=False, enable_large_chunks=False)
+
     multipass = should_use_multipass(search_settings)
     enable_large_chunks = SearchSettings.can_use_large_chunks(
         multipass, search_settings.model_name, search_settings.provider_type

backend/onyx/document_index/factory.py

@@ -26,10 +26,11 @@ def get_default_document_index(
     To be used for retrieval only. Indexing should be done through both indices
     until Vespa is deprecated.
 
+    Pre-existing docstring for this function, although secondary indices are not
+    currently supported:
     Primary index is the index that is used for querying/updating etc. Secondary
     index is for when both the currently used index and the upcoming index both
-    need to be updated. Updates are applied to both indices.
-    WARNING: In that case, get_all_document_indices should be used.
+    need to be updated, updates are applied to both indices.
     """
     if DISABLE_VECTOR_DB:
         return DisabledDocumentIndex(
@@ -50,26 +51,11 @@ def get_default_document_index(
     opensearch_retrieval_enabled = get_opensearch_retrieval_state(db_session)
     if opensearch_retrieval_enabled:
         indexing_setting = IndexingSetting.from_db_model(search_settings)
-        secondary_indexing_setting = (
-            IndexingSetting.from_db_model(secondary_search_settings)
-            if secondary_search_settings
-            else None
-        )
         return OpenSearchOldDocumentIndex(
             index_name=search_settings.index_name,
             embedding_dim=indexing_setting.final_embedding_dim,
             embedding_precision=indexing_setting.embedding_precision,
             secondary_index_name=secondary_index_name,
-            secondary_embedding_dim=(
-                secondary_indexing_setting.final_embedding_dim
-                if secondary_indexing_setting
-                else None
-            ),
-            secondary_embedding_precision=(
-                secondary_indexing_setting.embedding_precision
-                if secondary_indexing_setting
-                else None
-            ),
             large_chunks_enabled=search_settings.large_chunks_enabled,
             secondary_large_chunks_enabled=secondary_large_chunks_enabled,
             multitenant=MULTI_TENANT,
@@ -100,7 +86,8 @@ def get_all_document_indices(
     Used for indexing only. Until Vespa is deprecated we will index into both
     document indices. Retrieval is done through only one index however.
 
-    Large chunks are not currently supported so we hardcode appropriate values.
+    Large chunks and secondary indices are not currently supported so we
+    hardcode appropriate values.
 
     NOTE: Make sure the Vespa index object is returned first. In the rare event
     that there is some conflict between indexing and the migration task, it is
@@ -136,36 +123,13 @@ def get_all_document_indices(
     opensearch_document_index: OpenSearchOldDocumentIndex | None = None
     if ENABLE_OPENSEARCH_INDEXING_FOR_ONYX:
         indexing_setting = IndexingSetting.from_db_model(search_settings)
-        secondary_indexing_setting = (
-            IndexingSetting.from_db_model(secondary_search_settings)
-            if secondary_search_settings
-            else None
-        )
         opensearch_document_index = OpenSearchOldDocumentIndex(
             index_name=search_settings.index_name,
             embedding_dim=indexing_setting.final_embedding_dim,
             embedding_precision=indexing_setting.embedding_precision,
-            secondary_index_name=(
-                secondary_search_settings.index_name
-                if secondary_search_settings
-                else None
-            ),
-            secondary_embedding_dim=(
-                secondary_indexing_setting.final_embedding_dim
-                if secondary_indexing_setting
-                else None
-            ),
-            secondary_embedding_precision=(
-                secondary_indexing_setting.embedding_precision
-                if secondary_indexing_setting
-                else None
-            ),
-            large_chunks_enabled=search_settings.large_chunks_enabled,
-            secondary_large_chunks_enabled=(
-                secondary_search_settings.large_chunks_enabled
-                if secondary_search_settings
-                else None
-            ),
+            secondary_index_name=None,
+            large_chunks_enabled=False,
+            secondary_large_chunks_enabled=None,
             multitenant=MULTI_TENANT,
             httpx_client=httpx_client,
         )

backend/onyx/document_index/opensearch/opensearch_document_index.py

@@ -271,9 +271,6 @@ class OpenSearchOldDocumentIndex(OldDocumentIndex):
         embedding_dim: int,
         embedding_precision: EmbeddingPrecision,
         secondary_index_name: str | None,
-        secondary_embedding_dim: int | None,
-        secondary_embedding_precision: EmbeddingPrecision | None,
-        # NOTE: We do not support large chunks right now.
         large_chunks_enabled: bool,  # noqa: ARG002
         secondary_large_chunks_enabled: bool | None,  # noqa: ARG002
         multitenant: bool = False,
@@ -289,25 +286,12 @@ class OpenSearchOldDocumentIndex(OldDocumentIndex):
                 f"Expected {MULTI_TENANT}, got {multitenant}."
             )
         tenant_id = get_current_tenant_id()
-        tenant_state = TenantState(tenant_id=tenant_id, multitenant=multitenant)
         self._real_index = OpenSearchDocumentIndex(
-            tenant_state=tenant_state,
+            tenant_state=TenantState(tenant_id=tenant_id, multitenant=multitenant),
             index_name=index_name,
             embedding_dim=embedding_dim,
             embedding_precision=embedding_precision,
         )
-        self._secondary_real_index: OpenSearchDocumentIndex | None = None
-        if self.secondary_index_name:
-            if secondary_embedding_dim is None or secondary_embedding_precision is None:
-                raise ValueError(
-                    "Bug: Secondary index embedding dimension and precision are not set."
-                )
-            self._secondary_real_index = OpenSearchDocumentIndex(
-                tenant_state=tenant_state,
-                index_name=self.secondary_index_name,
-                embedding_dim=secondary_embedding_dim,
-                embedding_precision=secondary_embedding_precision,
-            )
 
     @staticmethod
     def register_multitenant_indices(
@@ -323,38 +307,19 @@ class OpenSearchOldDocumentIndex(OldDocumentIndex):
         self,
         primary_embedding_dim: int,
         primary_embedding_precision: EmbeddingPrecision,
-        secondary_index_embedding_dim: int | None,
-        secondary_index_embedding_precision: EmbeddingPrecision | None,
+        secondary_index_embedding_dim: int | None,  # noqa: ARG002
+        secondary_index_embedding_precision: EmbeddingPrecision | None,  # noqa: ARG002
     ) -> None:
-        self._real_index.verify_and_create_index_if_necessary(
+        # Only handle primary index for now, ignore secondary.
+        return self._real_index.verify_and_create_index_if_necessary(
             primary_embedding_dim, primary_embedding_precision
         )
-        if self.secondary_index_name:
-            if (
-                secondary_index_embedding_dim is None
-                or secondary_index_embedding_precision is None
-            ):
-                raise ValueError(
-                    "Bug: Secondary index embedding dimension and precision are not set."
-                )
-            assert (
-                self._secondary_real_index is not None
-            ), "Bug: Secondary index is not initialized."
-            self._secondary_real_index.verify_and_create_index_if_necessary(
-                secondary_index_embedding_dim, secondary_index_embedding_precision
-            )
 
     def index(
         self,
         chunks: list[DocMetadataAwareIndexChunk],
         index_batch_params: IndexBatchParams,
     ) -> set[OldDocumentInsertionRecord]:
-        """
-        NOTE: Do NOT consider the secondary index here. A separate indexing
-        pipeline will be responsible for indexing to the secondary index. This
-        design is not ideal and we should reconsider this when revamping index
-        swapping.
-        """
         # Convert IndexBatchParams to IndexingMetadata.
         chunk_counts: dict[str, IndexingMetadata.ChunkCounts] = {}
         for doc_id in index_batch_params.doc_id_to_new_chunk_cnt:
@@ -386,20 +351,7 @@ class OpenSearchOldDocumentIndex(OldDocumentIndex):
         tenant_id: str,  # noqa: ARG002
         chunk_count: int | None,
     ) -> int:
-        """
-        NOTE: Remember to handle the secondary index here. There is no separate
-        pipeline for deleting chunks in the secondary index. This design is not
-        ideal and we should reconsider this when revamping index swapping.
-        """
-        total_chunks_deleted = self._real_index.delete(doc_id, chunk_count)
-        if self.secondary_index_name:
-            assert (
-                self._secondary_real_index is not None
-            ), "Bug: Secondary index is not initialized."
-            total_chunks_deleted += self._secondary_real_index.delete(
-                doc_id, chunk_count
-            )
-        return total_chunks_deleted
+        return self._real_index.delete(doc_id, chunk_count)
 
     def update_single(
         self,
@@ -410,11 +362,6 @@ class OpenSearchOldDocumentIndex(OldDocumentIndex):
         fields: VespaDocumentFields | None,
         user_fields: VespaDocumentUserFields | None,
     ) -> None:
-        """
-        NOTE: Remember to handle the secondary index here. There is no separate
-        pipeline for updating chunks in the secondary index. This design is not
-        ideal and we should reconsider this when revamping index swapping.
-        """
         if fields is None and user_fields is None:
             logger.warning(
                 f"Tried to update document {doc_id} with no updated fields or user fields."
@@ -445,11 +392,6 @@ class OpenSearchOldDocumentIndex(OldDocumentIndex):
 
         try:
             self._real_index.update([update_request])
-            if self.secondary_index_name:
-                assert (
-                    self._secondary_real_index is not None
-                ), "Bug: Secondary index is not initialized."
-                self._secondary_real_index.update([update_request])
         except NotFoundError:
             logger.exception(
                 f"Tried to update document {doc_id} but at least one of its chunks was not found in OpenSearch. "

backend/onyx/document_index/vespa/index.py

@@ -465,12 +465,6 @@ class VespaIndex(DocumentIndex):
         chunks: list[DocMetadataAwareIndexChunk],
         index_batch_params: IndexBatchParams,
     ) -> set[OldDocumentInsertionRecord]:
-        """
-        NOTE: Do NOT consider the secondary index here. A separate indexing
-        pipeline will be responsible for indexing to the secondary index. This
-        design is not ideal and we should reconsider this when revamping index
-        swapping.
-        """
         if len(index_batch_params.doc_id_to_previous_chunk_cnt) != len(
             index_batch_params.doc_id_to_new_chunk_cnt
         ):
@@ -665,10 +659,6 @@ class VespaIndex(DocumentIndex):
         """Note: if the document id does not exist, the update will be a no-op and the
         function will complete with no errors or exceptions.
         Handle other exceptions if you wish to implement retry behavior
-
-        NOTE: Remember to handle the secondary index here. There is no separate
-        pipeline for updating chunks in the secondary index. This design is not
-        ideal and we should reconsider this when revamping index swapping.
         """
         if fields is None and user_fields is None:
             logger.warning(
@@ -689,6 +679,13 @@ class VespaIndex(DocumentIndex):
                 f"Bug: Tenant ID mismatch. Expected {tenant_state.tenant_id}, got {tenant_id}."
             )
 
+        vespa_document_index = VespaDocumentIndex(
+            index_name=self.index_name,
+            tenant_state=tenant_state,
+            large_chunks_enabled=self.large_chunks_enabled,
+            httpx_client=self.httpx_client,
+        )
+
         project_ids: set[int] | None = None
         if user_fields is not None and user_fields.user_projects is not None:
             project_ids = set(user_fields.user_projects)
@@ -708,20 +705,7 @@ class VespaIndex(DocumentIndex):
             persona_ids=persona_ids,
         )
 
-        indices = [self.index_name]
-        if self.secondary_index_name:
-            indices.append(self.secondary_index_name)
-
-        for index_name in indices:
-            vespa_document_index = VespaDocumentIndex(
-                index_name=index_name,
-                tenant_state=tenant_state,
-                large_chunks_enabled=self.index_to_large_chunks_enabled.get(
-                    index_name, False
-                ),
-                httpx_client=self.httpx_client,
-            )
-            vespa_document_index.update([update_request])
+        vespa_document_index.update([update_request])
 
     def delete_single(
         self,
@@ -730,11 +714,6 @@ class VespaIndex(DocumentIndex):
         tenant_id: str,
         chunk_count: int | None,
     ) -> int:
-        """
-        NOTE: Remember to handle the secondary index here. There is no separate
-        pipeline for deleting chunks in the secondary index. This design is not
-        ideal and we should reconsider this when revamping index swapping.
-        """
         tenant_state = TenantState(
             tenant_id=get_current_tenant_id(),
             multitenant=MULTI_TENANT,
@@ -747,25 +726,13 @@ class VespaIndex(DocumentIndex):
             raise ValueError(
                 f"Bug: Tenant ID mismatch. Expected {tenant_state.tenant_id}, got {tenant_id}."
             )
-        indices = [self.index_name]
-        if self.secondary_index_name:
-            indices.append(self.secondary_index_name)
-
-        total_chunks_deleted = 0
-        for index_name in indices:
-            vespa_document_index = VespaDocumentIndex(
-                index_name=index_name,
-                tenant_state=tenant_state,
-                large_chunks_enabled=self.index_to_large_chunks_enabled.get(
-                    index_name, False
-                ),
-                httpx_client=self.httpx_client,
-            )
-            total_chunks_deleted += vespa_document_index.delete(
-                document_id=doc_id, chunk_count=chunk_count
-            )
-
-        return total_chunks_deleted
+        vespa_document_index = VespaDocumentIndex(
+            index_name=self.index_name,
+            tenant_state=tenant_state,
+            large_chunks_enabled=self.large_chunks_enabled,
+            httpx_client=self.httpx_client,
+        )
+        return vespa_document_index.delete(document_id=doc_id, chunk_count=chunk_count)
 
     def id_based_retrieval(
         self,

backend/onyx/onyxbot/slack/formatting.py

@@ -130,7 +130,7 @@ def format_slack_message(message: str | None) -> str:
     message = _transform_outside_code_blocks(message, _sanitize_html)
     message = _convert_slack_links_to_markdown(message)
     normalized_message = _normalize_link_destinations(message)
-    md = create_markdown(renderer=SlackRenderer(), plugins=["strikethrough", "table"])
+    md = create_markdown(renderer=SlackRenderer(), plugins=["strikethrough"])
     result = md(normalized_message)
     # With HTMLRenderer, result is always str (not AST list)
     assert isinstance(result, str)
@@ -146,11 +146,6 @@ class SlackRenderer(HTMLRenderer):
 
     SPECIALS: dict[str, str] = {"&": "&amp;", "<": "&lt;", ">": "&gt;"}
 
-    def __init__(self) -> None:
-        super().__init__()
-        self._table_headers: list[str] = []
-        self._current_row_cells: list[str] = []
-
     def escape_special(self, text: str) -> str:
         for special, replacement in self.SPECIALS.items():
             text = text.replace(special, replacement)
@@ -223,48 +218,5 @@ class SlackRenderer(HTMLRenderer):
         # as literal &quot; text since Slack doesn't recognize that entity.
         return self.escape_special(text)
 
-    # -- Table rendering (converts markdown tables to vertical cards) --
-
-    def table_cell(
-        self, text: str, align: str | None = None, head: bool = False  # noqa: ARG002
-    ) -> str:
-        if head:
-            self._table_headers.append(text.strip())
-        else:
-            self._current_row_cells.append(text.strip())
-        return ""
-
-    def table_head(self, text: str) -> str:  # noqa: ARG002
-        self._current_row_cells = []
-        return ""
-
-    def table_row(self, text: str) -> str:  # noqa: ARG002
-        cells = self._current_row_cells
-        self._current_row_cells = []
-        # First column becomes the bold title, remaining columns are bulleted fields
-        lines: list[str] = []
-        if cells:
-            title = cells[0]
-            if title:
-                # Avoid double-wrapping if cell already contains bold markup
-                if title.startswith("*") and title.endswith("*") and len(title) > 1:
-                    lines.append(title)
-                else:
-                    lines.append(f"*{title}*")
-            for i, cell in enumerate(cells[1:], start=1):
-                if i < len(self._table_headers):
-                    lines.append(f"  • {self._table_headers[i]}: {cell}")
-                else:
-                    lines.append(f"  • {cell}")
-        return "\n".join(lines) + "\n\n"
-
-    def table_body(self, text: str) -> str:
-        return text
-
-    def table(self, text: str) -> str:
-        self._table_headers = []
-        self._current_row_cells = []
-        return text + "\n"
-
     def paragraph(self, text: str) -> str:
         return f"{text}\n\n"

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

@@ -7424,9 +7424,9 @@
       }
     },
     "node_modules/hono": {
-      "version": "4.12.5",
-      "resolved": "https://registry.npmjs.org/hono/-/hono-4.12.5.tgz",
-      "integrity": "sha512-3qq+FUBtlTHhtYxbxheZgY8NIFnkkC/MR8u5TTsr7YZ3wixryQ3cCwn3iZbg8p8B88iDBBAYSfZDS75t8MN7Vg==",
+      "version": "4.11.7",
+      "resolved": "https://registry.npmjs.org/hono/-/hono-4.11.7.tgz",
+      "integrity": "sha512-l7qMiNee7t82bH3SeyUCt9UF15EVmaBvsppY2zQtrbIhl/yzBTny+YUxsVjSjQ6gaqaeVtZmGocom8TzBlA4Yw==",
       "license": "MIT",
       "engines": {
         "node": ">=16.9.0"

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

@@ -11,7 +11,6 @@ from onyx.configs.app_configs import DISABLE_VECTOR_DB
 from onyx.configs.constants import OnyxCeleryPriority
 from onyx.configs.constants import OnyxCeleryTask
 from onyx.db.document_set import check_document_sets_are_public
-from onyx.db.document_set import delete_document_set as db_delete_document_set
 from onyx.db.document_set import fetch_all_document_sets_for_user
 from onyx.db.document_set import get_document_set_by_id
 from onyx.db.document_set import insert_document_set
@@ -143,10 +142,7 @@ def delete_document_set(
     except Exception as e:
         raise HTTPException(status_code=400, detail=str(e))
 
-    if DISABLE_VECTOR_DB:
-        db_session.refresh(document_set)
-        db_delete_document_set(document_set, db_session)
-    else:
+    if not DISABLE_VECTOR_DB:
         client_app.send_task(
             OnyxCeleryTask.CHECK_FOR_VESPA_SYNC_TASK,
             kwargs={"tenant_id": tenant_id},

backend/onyx/server/manage/embedding/api.py

@@ -1,5 +1,6 @@
 from fastapi import APIRouter
 from fastapi import Depends
+from fastapi import HTTPException
 from sqlalchemy.orm import Session
 
 from onyx.auth.users import current_admin_user
@@ -10,8 +11,6 @@ from onyx.db.llm import upsert_cloud_embedding_provider
 from onyx.db.models import User
 from onyx.db.search_settings import get_all_search_settings
 from onyx.db.search_settings import get_current_db_embedding_provider
-from onyx.error_handling.error_codes import OnyxErrorCode
-from onyx.error_handling.exceptions import OnyxError
 from onyx.indexing.models import EmbeddingModelDetail
 from onyx.natural_language_processing.search_nlp_models import EmbeddingModel
 from onyx.server.manage.embedding.models import CloudEmbeddingProvider
@@ -60,7 +59,7 @@ def test_embedding_configuration(
     except Exception as e:
         error_msg = "An error occurred while testing your embedding model. Please check your configuration."
         logger.error(f"{error_msg} Error message: {e}", exc_info=True)
-        raise OnyxError(OnyxErrorCode.VALIDATION_ERROR, error_msg)
+        raise HTTPException(status_code=400, detail=error_msg)
 
 
 @admin_router.get("", response_model=list[EmbeddingModelDetail])
@@ -94,9 +93,8 @@ def delete_embedding_provider(
         embedding_provider is not None
         and provider_type == embedding_provider.provider_type
     ):
-        raise OnyxError(
-            OnyxErrorCode.VALIDATION_ERROR,
-            "You can't delete a currently active model",
+        raise HTTPException(
+            status_code=400, detail="You can't delete a currently active model"
         )
 
     remove_embedding_provider(db_session, provider_type=provider_type)

backend/onyx/server/manage/llm/api.py

@@ -11,6 +11,7 @@ from botocore.exceptions import ClientError
 from botocore.exceptions import NoCredentialsError
 from fastapi import APIRouter
 from fastapi import Depends
+from fastapi import HTTPException
 from fastapi import Query
 from pydantic import ValidationError
 from sqlalchemy.orm import Session
@@ -37,8 +38,6 @@ from onyx.db.llm import upsert_llm_provider
 from onyx.db.llm import validate_persona_ids_exist
 from onyx.db.models import User
 from onyx.db.persona import user_can_access_persona
-from onyx.error_handling.error_codes import OnyxErrorCode
-from onyx.error_handling.exceptions import OnyxError
 from onyx.llm.factory import get_default_llm
 from onyx.llm.factory import get_llm
 from onyx.llm.factory import get_max_input_tokens_from_llm_provider
@@ -187,7 +186,7 @@ def _validate_llm_provider_change(
     Only enforced in MULTI_TENANT mode.
 
     Raises:
-        OnyxError: If api_base or custom_config changed without changing API key
+        HTTPException: If api_base or custom_config changed without changing API key
     """
     if not MULTI_TENANT or api_key_changed:
         return
@@ -201,9 +200,9 @@ def _validate_llm_provider_change(
     )
 
     if api_base_changed or custom_config_changed:
-        raise OnyxError(
-            OnyxErrorCode.VALIDATION_ERROR,
-            "API base and/or custom config cannot be changed without changing the API key",
+        raise HTTPException(
+            status_code=400,
+            detail="API base and/or custom config cannot be changed without changing the API key",
         )
 
 
@@ -223,7 +222,7 @@ def fetch_llm_provider_options(
     for well_known_llm in well_known_llms:
         if well_known_llm.name == provider_name:
             return well_known_llm
-    raise OnyxError(OnyxErrorCode.NOT_FOUND, f"Provider {provider_name} not found")
+    raise HTTPException(status_code=404, detail=f"Provider {provider_name} not found")
 
 
 @admin_router.post("/test")
@@ -282,7 +281,7 @@ def test_llm_configuration(
     error_msg = test_llm(llm)
 
     if error_msg:
-        raise OnyxError(OnyxErrorCode.VALIDATION_ERROR, error_msg)
+        raise HTTPException(status_code=400, detail=error_msg)
 
 
 @admin_router.post("/test/default")
@@ -293,11 +292,11 @@ def test_default_provider(
         llm = get_default_llm()
     except ValueError:
         logger.exception("Failed to fetch default LLM Provider")
-        raise OnyxError(OnyxErrorCode.VALIDATION_ERROR, "No LLM Provider setup")
+        raise HTTPException(status_code=400, detail="No LLM Provider setup")
 
     error = test_llm(llm)
     if error:
-        raise OnyxError(OnyxErrorCode.VALIDATION_ERROR, str(error))
+        raise HTTPException(status_code=400, detail=str(error))
 
 
 @admin_router.get("/provider")
@@ -363,31 +362,35 @@ def put_llm_provider(
     # Check name constraints
     # TODO: Once port from name to id is complete, unique name will no longer be required
     if existing_provider and llm_provider_upsert_request.name != existing_provider.name:
-        raise OnyxError(
-            OnyxErrorCode.VALIDATION_ERROR,
-            "Renaming providers is not currently supported",
+        raise HTTPException(
+            status_code=400,
+            detail="Renaming providers is not currently supported",
         )
 
     found_provider = fetch_existing_llm_provider(
         name=llm_provider_upsert_request.name, db_session=db_session
     )
     if found_provider is not None and found_provider is not existing_provider:
-        raise OnyxError(
-            OnyxErrorCode.DUPLICATE_RESOURCE,
-            f"Provider with name={llm_provider_upsert_request.name} already exists",
+        raise HTTPException(
+            status_code=400,
+            detail=f"Provider with name={llm_provider_upsert_request.name} already exists",
         )
 
     if existing_provider and is_creation:
-        raise OnyxError(
-            OnyxErrorCode.DUPLICATE_RESOURCE,
-            f"LLM Provider with name {llm_provider_upsert_request.name} and "
-            f"id={llm_provider_upsert_request.id} already exists",
+        raise HTTPException(
+            status_code=400,
+            detail=(
+                f"LLM Provider with name {llm_provider_upsert_request.name} and "
+                f"id={llm_provider_upsert_request.id} already exists"
+            ),
         )
     elif not existing_provider and not is_creation:
-        raise OnyxError(
-            OnyxErrorCode.NOT_FOUND,
-            f"LLM Provider with name {llm_provider_upsert_request.name} and "
-            f"id={llm_provider_upsert_request.id} does not exist",
+        raise HTTPException(
+            status_code=400,
+            detail=(
+                f"LLM Provider with name {llm_provider_upsert_request.name} and "
+                f"id={llm_provider_upsert_request.id} does not exist"
+            ),
         )
 
     # SSRF Protection: Validate api_base and custom_config match stored values
@@ -412,9 +415,9 @@ def put_llm_provider(
             db_session, persona_ids
         )
         if missing_personas:
-            raise OnyxError(
-                OnyxErrorCode.VALIDATION_ERROR,
-                f"Invalid persona IDs: {', '.join(map(str, missing_personas))}",
+            raise HTTPException(
+                status_code=400,
+                detail=f"Invalid persona IDs: {', '.join(map(str, missing_personas))}",
             )
         # Remove duplicates while preserving order
         seen: set[int] = set()
@@ -470,7 +473,7 @@ def put_llm_provider(
         return result
     except ValueError as e:
         logger.exception("Failed to upsert LLM Provider")
-        raise OnyxError(OnyxErrorCode.VALIDATION_ERROR, str(e))
+        raise HTTPException(status_code=400, detail=str(e))
 
 
 @admin_router.delete("/provider/{provider_id}")
@@ -480,19 +483,19 @@ def delete_llm_provider(
     _: User = Depends(current_admin_user),
     db_session: Session = Depends(get_session),
 ) -> None:
-    if not force:
-        model = fetch_default_llm_model(db_session)
-
-        if model and model.llm_provider_id == provider_id:
-            raise OnyxError(
-                OnyxErrorCode.VALIDATION_ERROR,
-                "Cannot delete the default LLM provider",
-            )
-
     try:
+        if not force:
+            model = fetch_default_llm_model(db_session)
+
+            if model and model.llm_provider_id == provider_id:
+                raise HTTPException(
+                    status_code=400,
+                    detail="Cannot delete the default LLM provider",
+                )
+
         remove_llm_provider(db_session, provider_id)
     except ValueError as e:
-        raise OnyxError(OnyxErrorCode.NOT_FOUND, str(e))
+        raise HTTPException(status_code=404, detail=str(e))
 
 
 @admin_router.post("/default")
@@ -532,9 +535,9 @@ def get_auto_config(
     """
     config = fetch_llm_recommendations_from_github()
     if not config:
-        raise OnyxError(
-            OnyxErrorCode.BAD_GATEWAY,
-            "Failed to fetch configuration from GitHub",
+        raise HTTPException(
+            status_code=502,
+            detail="Failed to fetch configuration from GitHub",
         )
     return config.model_dump()
 
@@ -691,13 +694,13 @@ def list_llm_providers_for_persona(
 
     persona = fetch_persona_with_groups(db_session, persona_id)
     if not persona:
-        raise OnyxError(OnyxErrorCode.PERSONA_NOT_FOUND, "Persona not found")
+        raise HTTPException(status_code=404, detail="Persona not found")
 
     # Verify user has access to this persona
     if not user_can_access_persona(db_session, persona_id, user, get_editable=False):
-        raise OnyxError(
-            OnyxErrorCode.INSUFFICIENT_PERMISSIONS,
-            "You don't have access to this assistant",
+        raise HTTPException(
+            status_code=403,
+            detail="You don't have access to this assistant",
         )
 
     is_admin = user.role == UserRole.ADMIN
@@ -851,9 +854,9 @@ def get_bedrock_available_models(
         try:
             bedrock = session.client("bedrock")
         except Exception as e:
-            raise OnyxError(
-                OnyxErrorCode.CREDENTIAL_INVALID,
-                f"Failed to create Bedrock client: {e}. Check AWS credentials and region.",
+            raise HTTPException(
+                status_code=400,
+                detail=f"Failed to create Bedrock client: {e}. Check AWS credentials and region.",
             )
 
         # Build model info dict from foundation models (modelId -> metadata)
@@ -972,14 +975,14 @@ def get_bedrock_available_models(
         return results
 
     except (ClientError, NoCredentialsError, BotoCoreError) as e:
-        raise OnyxError(
-            OnyxErrorCode.CREDENTIAL_INVALID,
-            f"Failed to connect to AWS Bedrock: {e}",
+        raise HTTPException(
+            status_code=400,
+            detail=f"Failed to connect to AWS Bedrock: {e}",
         )
     except Exception as e:
-        raise OnyxError(
-            OnyxErrorCode.INTERNAL_ERROR,
-            f"Unexpected error fetching Bedrock models: {e}",
+        raise HTTPException(
+            status_code=500,
+            detail=f"Unexpected error fetching Bedrock models: {e}",
         )
 
 
@@ -991,9 +994,9 @@ def _get_ollama_available_model_names(api_base: str) -> set[str]:
         response.raise_for_status()
         response_json = response.json()
     except Exception as e:
-        raise OnyxError(
-            OnyxErrorCode.BAD_GATEWAY,
-            f"Failed to fetch Ollama models: {e}",
+        raise HTTPException(
+            status_code=400,
+            detail=f"Failed to fetch Ollama models: {e}",
         )
 
     models = response_json.get("models", [])
@@ -1010,9 +1013,9 @@ def get_ollama_available_models(
 
     cleaned_api_base = request.api_base.strip().rstrip("/")
     if not cleaned_api_base:
-        raise OnyxError(
-            OnyxErrorCode.VALIDATION_ERROR,
-            "API base URL is required to fetch Ollama models.",
+        raise HTTPException(
+            status_code=400,
+            detail="API base URL is required to fetch Ollama models.",
         )
 
     # NOTE: most people run Ollama locally, so we don't disallow internal URLs
@@ -1021,9 +1024,9 @@ def get_ollama_available_models(
     # with the same response format
     model_names = _get_ollama_available_model_names(cleaned_api_base)
     if not model_names:
-        raise OnyxError(
-            OnyxErrorCode.VALIDATION_ERROR,
-            "No models found from your Ollama server",
+        raise HTTPException(
+            status_code=400,
+            detail="No models found from your Ollama server",
         )
 
     all_models_with_context_size_and_vision: list[OllamaFinalModelResponse] = []
@@ -1125,9 +1128,9 @@ def _get_openrouter_models_response(api_base: str, api_key: str) -> dict:
         response.raise_for_status()
         return response.json()
     except Exception as e:
-        raise OnyxError(
-            OnyxErrorCode.BAD_GATEWAY,
-            f"Failed to fetch OpenRouter models: {e}",
+        raise HTTPException(
+            status_code=400,
+            detail=f"Failed to fetch OpenRouter models: {e}",
         )
 
 
@@ -1148,9 +1151,9 @@ def get_openrouter_available_models(
 
     data = response_json.get("data", [])
     if not isinstance(data, list) or len(data) == 0:
-        raise OnyxError(
-            OnyxErrorCode.VALIDATION_ERROR,
-            "No models found from your OpenRouter endpoint",
+        raise HTTPException(
+            status_code=400,
+            detail="No models found from your OpenRouter endpoint",
         )
 
     results: list[OpenRouterFinalModelResponse] = []
@@ -1185,9 +1188,8 @@ def get_openrouter_available_models(
             )
 
     if not results:
-        raise OnyxError(
-            OnyxErrorCode.VALIDATION_ERROR,
-            "No compatible models found from OpenRouter",
+        raise HTTPException(
+            status_code=400, detail="No compatible models found from OpenRouter"
         )
 
     sorted_results = sorted(results, key=lambda m: m.name.lower())

backend/onyx/server/manage/search_settings.py

@@ -6,11 +6,8 @@ from sqlalchemy.orm import Session
 
 from onyx.auth.users import current_admin_user
 from onyx.auth.users import current_user
-from onyx.configs.app_configs import DISABLE_INDEX_UPDATE_ON_SWAP
 from onyx.context.search.models import SavedSearchSettings
 from onyx.context.search.models import SearchSettingsCreationRequest
-from onyx.db.connector_credential_pair import get_connector_credential_pairs
-from onyx.db.connector_credential_pair import resync_cc_pair
 from onyx.db.engine.sql_engine import get_session
 from onyx.db.index_attempt import expire_index_attempts
 from onyx.db.llm import fetch_existing_llm_provider
@@ -18,25 +15,20 @@ from onyx.db.llm import update_default_contextual_model
 from onyx.db.llm import update_no_default_contextual_rag_provider
 from onyx.db.models import IndexModelStatus
 from onyx.db.models import User
-from onyx.db.search_settings import create_search_settings
 from onyx.db.search_settings import delete_search_settings
 from onyx.db.search_settings import get_current_search_settings
-from onyx.db.search_settings import get_embedding_provider_from_provider_type
 from onyx.db.search_settings import get_secondary_search_settings
 from onyx.db.search_settings import update_current_search_settings
 from onyx.db.search_settings import update_search_settings_status
-from onyx.document_index.factory import get_all_document_indices
 from onyx.document_index.factory import get_default_document_index
 from onyx.file_processing.unstructured import delete_unstructured_api_key
 from onyx.file_processing.unstructured import get_unstructured_api_key
 from onyx.file_processing.unstructured import update_unstructured_api_key
-from onyx.natural_language_processing.search_nlp_models import clean_model_name
 from onyx.server.manage.embedding.models import SearchSettingsDeleteRequest
 from onyx.server.manage.models import FullModelVersionResponse
 from onyx.server.models import IdReturn
 from onyx.server.utils_vector_db import require_vector_db
 from onyx.utils.logger import setup_logger
-from shared_configs.configs import ALT_INDEX_SUFFIX
 from shared_configs.configs import MULTI_TENANT
 
 router = APIRouter(prefix="/search-settings")
@@ -49,99 +41,110 @@ def set_new_search_settings(
     _: User = Depends(current_admin_user),
     db_session: Session = Depends(get_session),  # noqa: ARG001
 ) -> IdReturn:
+    """Creates a new EmbeddingModel row and cancels the previous secondary indexing if any
+    Gives an error if the same model name is used as the current or secondary index
     """
-    Creates a new SearchSettings row and cancels the previous secondary indexing
-    if any exists.
-    """
-    if search_settings_new.index_name:
-        logger.warning("Index name was specified by request, this is not suggested")
-
-    # Disallow contextual RAG for cloud deployments.
-    if MULTI_TENANT and search_settings_new.enable_contextual_rag:
-        raise HTTPException(
-            status_code=status.HTTP_400_BAD_REQUEST,
-            detail="Contextual RAG disabled in Onyx Cloud",
-        )
-
-    # Validate cloud provider exists or create new LiteLLM provider.
-    if search_settings_new.provider_type is not None:
-        cloud_provider = get_embedding_provider_from_provider_type(
-            db_session, provider_type=search_settings_new.provider_type
-        )
-
-        if cloud_provider is None:
-            raise HTTPException(
-                status_code=status.HTTP_400_BAD_REQUEST,
-                detail=f"No embedding provider exists for cloud embedding type {search_settings_new.provider_type}",
-            )
-
-    validate_contextual_rag_model(
-        provider_name=search_settings_new.contextual_rag_llm_provider,
-        model_name=search_settings_new.contextual_rag_llm_name,
-        db_session=db_session,
+    # TODO(andrei): Re-enable.
+    # NOTE Enable integration external dependency tests in test_search_settings.py
+    # when this is reenabled. They are currently skipped
+    logger.error("Setting new search settings is temporarily disabled.")
+    raise HTTPException(
+        status_code=status.HTTP_501_NOT_IMPLEMENTED,
+        detail="Setting new search settings is temporarily disabled.",
     )
+    # if search_settings_new.index_name:
+    #     logger.warning("Index name was specified by request, this is not suggested")
 
-    search_settings = get_current_search_settings(db_session)
+    # # Disallow contextual RAG for cloud deployments
+    # if MULTI_TENANT and search_settings_new.enable_contextual_rag:
+    #     raise HTTPException(
+    #         status_code=status.HTTP_400_BAD_REQUEST,
+    #         detail="Contextual RAG disabled in Onyx Cloud",
+    #     )
 
-    if search_settings_new.index_name is None:
-        # We define index name here.
-        index_name = f"danswer_chunk_{clean_model_name(search_settings_new.model_name)}"
-        if (
-            search_settings_new.model_name == search_settings.model_name
-            and not search_settings.index_name.endswith(ALT_INDEX_SUFFIX)
-        ):
-            index_name += ALT_INDEX_SUFFIX
-        search_values = search_settings_new.model_dump()
-        search_values["index_name"] = index_name
-        new_search_settings_request = SavedSearchSettings(**search_values)
-    else:
-        new_search_settings_request = SavedSearchSettings(
-            **search_settings_new.model_dump()
-        )
+    # # Validate cloud provider exists or create new LiteLLM provider
+    # if search_settings_new.provider_type is not None:
+    #     cloud_provider = get_embedding_provider_from_provider_type(
+    #         db_session, provider_type=search_settings_new.provider_type
+    #     )
 
-    secondary_search_settings = get_secondary_search_settings(db_session)
+    #     if cloud_provider is None:
+    #         raise HTTPException(
+    #             status_code=status.HTTP_400_BAD_REQUEST,
+    #             detail=f"No embedding provider exists for cloud embedding type {search_settings_new.provider_type}",
+    #         )
 
-    if secondary_search_settings:
-        # Cancel any background indexing jobs.
-        expire_index_attempts(
-            search_settings_id=secondary_search_settings.id, db_session=db_session
-        )
+    # validate_contextual_rag_model(
+    #     provider_name=search_settings_new.contextual_rag_llm_provider,
+    #     model_name=search_settings_new.contextual_rag_llm_name,
+    #     db_session=db_session,
+    # )
 
-        # Mark previous model as a past model directly.
-        update_search_settings_status(
-            search_settings=secondary_search_settings,
-            new_status=IndexModelStatus.PAST,
-            db_session=db_session,
-        )
+    # search_settings = get_current_search_settings(db_session)
 
-    new_search_settings = create_search_settings(
-        search_settings=new_search_settings_request, db_session=db_session
-    )
+    # if search_settings_new.index_name is None:
+    #     # We define index name here
+    #     index_name = f"danswer_chunk_{clean_model_name(search_settings_new.model_name)}"
+    #     if (
+    #         search_settings_new.model_name == search_settings.model_name
+    #         and not search_settings.index_name.endswith(ALT_INDEX_SUFFIX)
+    #     ):
+    #         index_name += ALT_INDEX_SUFFIX
+    #     search_values = search_settings_new.model_dump()
+    #     search_values["index_name"] = index_name
+    #     new_search_settings_request = SavedSearchSettings(**search_values)
+    # else:
+    #     new_search_settings_request = SavedSearchSettings(
+    #         **search_settings_new.model_dump()
+    #     )
 
-    # Ensure the document indices have the new index immediately.
-    document_indices = get_all_document_indices(search_settings, new_search_settings)
-    for document_index in document_indices:
-        document_index.ensure_indices_exist(
-            primary_embedding_dim=search_settings.final_embedding_dim,
-            primary_embedding_precision=search_settings.embedding_precision,
-            secondary_index_embedding_dim=new_search_settings.final_embedding_dim,
-            secondary_index_embedding_precision=new_search_settings.embedding_precision,
-        )
+    # secondary_search_settings = get_secondary_search_settings(db_session)
 
-    # Pause index attempts for the currently in-use index to preserve resources.
-    if DISABLE_INDEX_UPDATE_ON_SWAP:
-        expire_index_attempts(
-            search_settings_id=search_settings.id, db_session=db_session
-        )
-        for cc_pair in get_connector_credential_pairs(db_session):
-            resync_cc_pair(
-                cc_pair=cc_pair,
-                search_settings_id=new_search_settings.id,
-                db_session=db_session,
-            )
+    # if secondary_search_settings:
+    #     # Cancel any background indexing jobs
+    #     expire_index_attempts(
+    #         search_settings_id=secondary_search_settings.id, db_session=db_session
+    #     )
 
-    db_session.commit()
-    return IdReturn(id=new_search_settings.id)
+    #     # Mark previous model as a past model directly
+    #     update_search_settings_status(
+    #         search_settings=secondary_search_settings,
+    #         new_status=IndexModelStatus.PAST,
+    #         db_session=db_session,
+    #     )
+
+    # new_search_settings = create_search_settings(
+    #     search_settings=new_search_settings_request, db_session=db_session
+    # )
+
+    # # Ensure Vespa has the new index immediately
+    # get_multipass_config(search_settings)
+    # get_multipass_config(new_search_settings)
+    # document_index = get_default_document_index(
+    #     search_settings, new_search_settings, db_session
+    # )
+
+    # document_index.ensure_indices_exist(
+    #     primary_embedding_dim=search_settings.final_embedding_dim,
+    #     primary_embedding_precision=search_settings.embedding_precision,
+    #     secondary_index_embedding_dim=new_search_settings.final_embedding_dim,
+    #     secondary_index_embedding_precision=new_search_settings.embedding_precision,
+    # )
+
+    # # Pause index attempts for the currently in use index to preserve resources
+    # if DISABLE_INDEX_UPDATE_ON_SWAP:
+    #     expire_index_attempts(
+    #         search_settings_id=search_settings.id, db_session=db_session
+    #     )
+    #     for cc_pair in get_connector_credential_pairs(db_session):
+    #         resync_cc_pair(
+    #             cc_pair=cc_pair,
+    #             search_settings_id=new_search_settings.id,
+    #             db_session=db_session,
+    #         )
+
+    # db_session.commit()
+    # return IdReturn(id=new_search_settings.id)
 
 
 @router.post("/cancel-new-embedding", dependencies=[Depends(require_vector_db)])

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

@@ -1,5 +1,3 @@
-from __future__ import annotations
-
 import json
 import time
 from collections.abc import Generator
@@ -86,19 +84,6 @@ class CodeInterpreterClient:
             raise ValueError("CODE_INTERPRETER_BASE_URL not configured")
         self.base_url = base_url.rstrip("/")
         self.session = requests.Session()
-        self._closed = False
-
-    def __enter__(self) -> CodeInterpreterClient:
-        return self
-
-    def __exit__(self, *args: object) -> None:
-        self.close()
-
-    def close(self) -> None:
-        if self._closed:
-            return
-        self.session.close()
-        self._closed = True
 
     def _build_payload(
         self,
@@ -118,13 +103,7 @@ class CodeInterpreterClient:
         return payload
 
     def health(self, use_cache: bool = False) -> bool:
-        """Check if the Code Interpreter service is healthy
-
-        Args:
-            use_cache: When True, return a cached result if available and
-                       within the TTL window. The cache is always populated
-                       after a live request regardless of this flag.
-        """
+        """Check if the Code Interpreter service is healthy"""
         if use_cache:
             cached = _health_cache.get(self.base_url)
             if cached is not None:
@@ -192,11 +171,8 @@ class CodeInterpreterClient:
             yield from self._batch_as_stream(code, stdin, timeout_ms, files)
             return
 
-        try:
-            response.raise_for_status()
-            yield from self._parse_sse(response)
-        finally:
-            response.close()
+        response.raise_for_status()
+        yield from self._parse_sse(response)
 
     def _parse_sse(
         self, response: requests.Response

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

@@ -111,8 +111,8 @@ class PythonTool(Tool[PythonToolOverrideKwargs]):
         if not server.server_enabled:
             return False
 
-        with CodeInterpreterClient() as client:
-            return client.health(use_cache=True)
+        client = CodeInterpreterClient()
+        return client.health(use_cache=True)
 
     def tool_definition(self) -> dict:
         return {
@@ -176,203 +176,196 @@ class PythonTool(Tool[PythonToolOverrideKwargs]):
             )
         )
 
-        # Create Code Interpreter client — context manager ensures
-        # session.close() is called on every exit path.
-        with CodeInterpreterClient() as client:
-            # Stage chat files for execution
-            files_to_stage: list[FileInput] = []
-            for ind, chat_file in enumerate(chat_files):
-                file_name = chat_file.filename or f"file_{ind}"
-                try:
-                    # Upload to Code Interpreter
-                    ci_file_id = client.upload_file(chat_file.content, file_name)
-
-                    # Stage for execution
-                    files_to_stage.append({"path": file_name, "file_id": ci_file_id})
-
-                    logger.info(f"Staged file for Python execution: {file_name}")
-
-                except Exception as e:
-                    logger.warning(f"Failed to stage file {file_name}: {e}")
+        # Create Code Interpreter client
+        client = CodeInterpreterClient()
 
+        # Stage chat files for execution
+        files_to_stage: list[FileInput] = []
+        for ind, chat_file in enumerate(chat_files):
+            file_name = chat_file.filename or f"file_{ind}"
             try:
-                logger.debug(f"Executing code: {code}")
+                # Upload to Code Interpreter
+                ci_file_id = client.upload_file(chat_file.content, file_name)
 
-                # Execute code with streaming (falls back to batch if unavailable)
-                stdout_parts: list[str] = []
-                stderr_parts: list[str] = []
-                result_event: StreamResultEvent | None = None
+                # Stage for execution
+                files_to_stage.append({"path": file_name, "file_id": ci_file_id})
 
-                for event in client.execute_streaming(
-                    code=code,
-                    timeout_ms=CODE_INTERPRETER_DEFAULT_TIMEOUT_MS,
-                    files=files_to_stage or None,
-                ):
-                    if isinstance(event, StreamOutputEvent):
-                        if event.stream == "stdout":
-                            stdout_parts.append(event.data)
-                        else:
-                            stderr_parts.append(event.data)
-                        # Emit incremental delta to frontend
-                        self.emitter.emit(
-                            Packet(
-                                placement=placement,
-                                obj=PythonToolDelta(
-                                    stdout=(
-                                        event.data if event.stream == "stdout" else ""
-                                    ),
-                                    stderr=(
-                                        event.data if event.stream == "stderr" else ""
-                                    ),
-                                ),
-                            )
-                        )
-                    elif isinstance(event, StreamResultEvent):
-                        result_event = event
-                    elif isinstance(event, StreamErrorEvent):
-                        raise RuntimeError(f"Code interpreter error: {event.message}")
+                logger.info(f"Staged file for Python execution: {file_name}")
 
-                if result_event is None:
-                    raise RuntimeError(
-                        "Code interpreter stream ended without a result event"
-                    )
+            except Exception as e:
+                logger.warning(f"Failed to stage file {file_name}: {e}")
 
-                full_stdout = "".join(stdout_parts)
-                full_stderr = "".join(stderr_parts)
+        try:
+            logger.debug(f"Executing code: {code}")
 
-                # Truncate output for LLM consumption
-                truncated_stdout = _truncate_output(
-                    full_stdout, CODE_INTERPRETER_MAX_OUTPUT_LENGTH, "stdout"
-                )
-                truncated_stderr = _truncate_output(
-                    full_stderr, CODE_INTERPRETER_MAX_OUTPUT_LENGTH, "stderr"
-                )
+            # Execute code with streaming (falls back to batch if unavailable)
+            stdout_parts: list[str] = []
+            stderr_parts: list[str] = []
+            result_event: StreamResultEvent | None = None
 
-                # Handle generated files
-                generated_files: list[PythonExecutionFile] = []
-                generated_file_ids: list[str] = []
-                file_ids_to_cleanup: list[str] = []
-                file_store = get_default_file_store()
-
-                for workspace_file in result_event.files:
-                    if workspace_file.kind != "file" or not workspace_file.file_id:
-                        continue
-
-                    try:
-                        # Download file from Code Interpreter
-                        file_content = client.download_file(workspace_file.file_id)
-
-                        # Determine MIME type from file extension
-                        filename = workspace_file.path.split("/")[-1]
-                        mime_type, _ = mimetypes.guess_type(filename)
-                        # Default to binary if we can't determine the type
-                        mime_type = mime_type or "application/octet-stream"
-
-                        # Save to Onyx file store
-                        onyx_file_id = file_store.save_file(
-                            content=BytesIO(file_content),
-                            display_name=filename,
-                            file_origin=FileOrigin.CHAT_UPLOAD,
-                            file_type=mime_type,
-                        )
-
-                        generated_files.append(
-                            PythonExecutionFile(
-                                filename=filename,
-                                file_link=build_full_frontend_file_url(onyx_file_id),
-                            )
-                        )
-                        generated_file_ids.append(onyx_file_id)
-
-                        # Mark for cleanup
-                        file_ids_to_cleanup.append(workspace_file.file_id)
-
-                    except Exception as e:
-                        logger.error(
-                            f"Failed to handle generated file "
-                            f"{workspace_file.path}: {e}"
-                        )
-
-                # Cleanup Code Interpreter files (generated files)
-                for ci_file_id in file_ids_to_cleanup:
-                    try:
-                        client.delete_file(ci_file_id)
-                    except Exception as e:
-                        logger.error(
-                            f"Failed to delete Code Interpreter generated "
-                            f"file {ci_file_id}: {e}"
-                        )
-
-                # Cleanup staged input files
-                for file_mapping in files_to_stage:
-                    try:
-                        client.delete_file(file_mapping["file_id"])
-                    except Exception as e:
-                        logger.error(
-                            f"Failed to delete Code Interpreter staged "
-                            f"file {file_mapping['file_id']}: {e}"
-                        )
-
-                # Emit file_ids once files are processed
-                if generated_file_ids:
+            for event in client.execute_streaming(
+                code=code,
+                timeout_ms=CODE_INTERPRETER_DEFAULT_TIMEOUT_MS,
+                files=files_to_stage or None,
+            ):
+                if isinstance(event, StreamOutputEvent):
+                    if event.stream == "stdout":
+                        stdout_parts.append(event.data)
+                    else:
+                        stderr_parts.append(event.data)
+                    # Emit incremental delta to frontend
                     self.emitter.emit(
                         Packet(
                             placement=placement,
-                            obj=PythonToolDelta(file_ids=generated_file_ids),
+                            obj=PythonToolDelta(
+                                stdout=event.data if event.stream == "stdout" else "",
+                                stderr=event.data if event.stream == "stderr" else "",
+                            ),
                         )
                     )
+                elif isinstance(event, StreamResultEvent):
+                    result_event = event
+                elif isinstance(event, StreamErrorEvent):
+                    raise RuntimeError(f"Code interpreter error: {event.message}")
 
-                # Build result
-                result = LlmPythonExecutionResult(
-                    stdout=truncated_stdout,
-                    stderr=truncated_stderr,
-                    exit_code=result_event.exit_code,
-                    timed_out=result_event.timed_out,
-                    generated_files=generated_files,
-                    error=(None if result_event.exit_code == 0 else truncated_stderr),
+            if result_event is None:
+                raise RuntimeError(
+                    "Code interpreter stream ended without a result event"
                 )
 
-                # Serialize result for LLM
-                adapter = TypeAdapter(LlmPythonExecutionResult)
-                llm_response = adapter.dump_json(result).decode()
+            full_stdout = "".join(stdout_parts)
+            full_stderr = "".join(stderr_parts)
 
-                return ToolResponse(
-                    rich_response=PythonToolRichResponse(
-                        generated_files=generated_files,
-                    ),
-                    llm_facing_response=llm_response,
-                )
+            # Truncate output for LLM consumption
+            truncated_stdout = _truncate_output(
+                full_stdout, CODE_INTERPRETER_MAX_OUTPUT_LENGTH, "stdout"
+            )
+            truncated_stderr = _truncate_output(
+                full_stderr, CODE_INTERPRETER_MAX_OUTPUT_LENGTH, "stderr"
+            )
 
-            except Exception as e:
-                logger.error(f"Python execution failed: {e}")
-                error_msg = str(e)
+            # Handle generated files
+            generated_files: list[PythonExecutionFile] = []
+            generated_file_ids: list[str] = []
+            file_ids_to_cleanup: list[str] = []
+            file_store = get_default_file_store()
 
-                # Emit error delta
+            for workspace_file in result_event.files:
+                if workspace_file.kind != "file" or not workspace_file.file_id:
+                    continue
+
+                try:
+                    # Download file from Code Interpreter
+                    file_content = client.download_file(workspace_file.file_id)
+
+                    # Determine MIME type from file extension
+                    filename = workspace_file.path.split("/")[-1]
+                    mime_type, _ = mimetypes.guess_type(filename)
+                    # Default to binary if we can't determine the type
+                    mime_type = mime_type or "application/octet-stream"
+
+                    # Save to Onyx file store
+                    onyx_file_id = file_store.save_file(
+                        content=BytesIO(file_content),
+                        display_name=filename,
+                        file_origin=FileOrigin.CHAT_UPLOAD,
+                        file_type=mime_type,
+                    )
+
+                    generated_files.append(
+                        PythonExecutionFile(
+                            filename=filename,
+                            file_link=build_full_frontend_file_url(onyx_file_id),
+                        )
+                    )
+                    generated_file_ids.append(onyx_file_id)
+
+                    # Mark for cleanup
+                    file_ids_to_cleanup.append(workspace_file.file_id)
+
+                except Exception as e:
+                    logger.error(
+                        f"Failed to handle generated file {workspace_file.path}: {e}"
+                    )
+
+            # Cleanup Code Interpreter files (generated files)
+            for ci_file_id in file_ids_to_cleanup:
+                try:
+                    client.delete_file(ci_file_id)
+                except Exception as e:
+                    logger.error(
+                        f"Failed to delete Code Interpreter generated file {ci_file_id}: {e}"
+                    )
+
+            # Cleanup staged input files
+            for file_mapping in files_to_stage:
+                try:
+                    client.delete_file(file_mapping["file_id"])
+                except Exception as e:
+                    logger.error(
+                        f"Failed to delete Code Interpreter staged file {file_mapping['file_id']}: {e}"
+                    )
+
+            # Emit file_ids once files are processed
+            if generated_file_ids:
                 self.emitter.emit(
                     Packet(
                         placement=placement,
-                        obj=PythonToolDelta(
-                            stdout="",
-                            stderr=error_msg,
-                            file_ids=[],
-                        ),
+                        obj=PythonToolDelta(file_ids=generated_file_ids),
                     )
                 )
 
-                # Return error result
-                result = LlmPythonExecutionResult(
-                    stdout="",
-                    stderr=error_msg,
-                    exit_code=-1,
-                    timed_out=False,
-                    generated_files=[],
-                    error=error_msg,
-                )
+            # Build result
+            result = LlmPythonExecutionResult(
+                stdout=truncated_stdout,
+                stderr=truncated_stderr,
+                exit_code=result_event.exit_code,
+                timed_out=result_event.timed_out,
+                generated_files=generated_files,
+                error=None if result_event.exit_code == 0 else truncated_stderr,
+            )
 
-                adapter = TypeAdapter(LlmPythonExecutionResult)
-                llm_response = adapter.dump_json(result).decode()
+            # Serialize result for LLM
+            adapter = TypeAdapter(LlmPythonExecutionResult)
+            llm_response = adapter.dump_json(result).decode()
 
-                return ToolResponse(
-                    rich_response=None,
-                    llm_facing_response=llm_response,
+            return ToolResponse(
+                rich_response=PythonToolRichResponse(
+                    generated_files=generated_files,
+                ),
+                llm_facing_response=llm_response,
+            )
+
+        except Exception as e:
+            logger.error(f"Python execution failed: {e}")
+            error_msg = str(e)
+
+            # Emit error delta
+            self.emitter.emit(
+                Packet(
+                    placement=placement,
+                    obj=PythonToolDelta(
+                        stdout="",
+                        stderr=error_msg,
+                        file_ids=[],
+                    ),
                 )
+            )
+
+            # Return error result
+            result = LlmPythonExecutionResult(
+                stdout="",
+                stderr=error_msg,
+                exit_code=-1,
+                timed_out=False,
+                generated_files=[],
+                error=error_msg,
+            )
+
+            adapter = TypeAdapter(LlmPythonExecutionResult)
+            llm_response = adapter.dump_json(result).decode()
+
+            return ToolResponse(
+                rich_response=None,
+                llm_facing_response=llm_response,
+            )

backend/requirements/default.txt

@@ -596,7 +596,7 @@ mypy-extensions==1.0.0
     #   typing-inspect
 nest-asyncio==1.6.0
     # via onyx
-nltk==3.9.3
+nltk==3.9.1
     # via unstructured
 numpy==2.4.1
     # via

backend/scripts/dev_run_background_jobs.py

@@ -16,6 +16,10 @@ def monitor_process(process_name: str, process: subprocess.Popen) -> None:
 
 
 def run_jobs() -> None:
+    # Check if we should use lightweight mode, defaults to True, change to False to use separate background workers
+    use_lightweight = True
+
+    # command setup
     cmd_worker_primary = [
         "celery",
         "-A",
@@ -70,48 +74,6 @@ def run_jobs() -> None:
         "--queues=connector_doc_fetching",
     ]
 
-    cmd_worker_heavy = [
-        "celery",
-        "-A",
-        "onyx.background.celery.versioned_apps.heavy",
-        "worker",
-        "--pool=threads",
-        "--concurrency=4",
-        "--prefetch-multiplier=1",
-        "--loglevel=INFO",
-        "--hostname=heavy@%n",
-        "-Q",
-        "connector_pruning,connector_doc_permissions_sync,connector_external_group_sync,csv_generation,sandbox",
-    ]
-
-    cmd_worker_monitoring = [
-        "celery",
-        "-A",
-        "onyx.background.celery.versioned_apps.monitoring",
-        "worker",
-        "--pool=threads",
-        "--concurrency=1",
-        "--prefetch-multiplier=1",
-        "--loglevel=INFO",
-        "--hostname=monitoring@%n",
-        "-Q",
-        "monitoring",
-    ]
-
-    cmd_worker_user_file_processing = [
-        "celery",
-        "-A",
-        "onyx.background.celery.versioned_apps.user_file_processing",
-        "worker",
-        "--pool=threads",
-        "--concurrency=2",
-        "--prefetch-multiplier=1",
-        "--loglevel=INFO",
-        "--hostname=user_file_processing@%n",
-        "-Q",
-        "user_file_processing,user_file_project_sync,user_file_delete",
-    ]
-
     cmd_beat = [
         "celery",
         "-A",
@@ -120,31 +82,144 @@ def run_jobs() -> None:
         "--loglevel=INFO",
     ]
 
-    all_workers = [
-        ("PRIMARY", cmd_worker_primary),
-        ("LIGHT", cmd_worker_light),
-        ("DOCPROCESSING", cmd_worker_docprocessing),
-        ("DOCFETCHING", cmd_worker_docfetching),
-        ("HEAVY", cmd_worker_heavy),
-        ("MONITORING", cmd_worker_monitoring),
-        ("USER_FILE_PROCESSING", cmd_worker_user_file_processing),
-        ("BEAT", cmd_beat),
-    ]
+    # Prepare background worker commands based on mode
+    if use_lightweight:
+        print("Starting workers in LIGHTWEIGHT mode (single background worker)")
+        cmd_worker_background = [
+            "celery",
+            "-A",
+            "onyx.background.celery.versioned_apps.background",
+            "worker",
+            "--pool=threads",
+            "--concurrency=6",
+            "--prefetch-multiplier=1",
+            "--loglevel=INFO",
+            "--hostname=background@%n",
+            "-Q",
+            "connector_pruning,connector_doc_permissions_sync,connector_external_group_sync,csv_generation,monitoring,user_file_processing,user_file_project_sync,user_file_delete,opensearch_migration",
+        ]
+        background_workers = [("BACKGROUND", cmd_worker_background)]
+    else:
+        print("Starting workers in STANDARD mode (separate background workers)")
+        cmd_worker_heavy = [
+            "celery",
+            "-A",
+            "onyx.background.celery.versioned_apps.heavy",
+            "worker",
+            "--pool=threads",
+            "--concurrency=4",
+            "--prefetch-multiplier=1",
+            "--loglevel=INFO",
+            "--hostname=heavy@%n",
+            "-Q",
+            "connector_pruning,sandbox",
+        ]
+        cmd_worker_monitoring = [
+            "celery",
+            "-A",
+            "onyx.background.celery.versioned_apps.monitoring",
+            "worker",
+            "--pool=threads",
+            "--concurrency=1",
+            "--prefetch-multiplier=1",
+            "--loglevel=INFO",
+            "--hostname=monitoring@%n",
+            "-Q",
+            "monitoring",
+        ]
+        cmd_worker_user_file_processing = [
+            "celery",
+            "-A",
+            "onyx.background.celery.versioned_apps.user_file_processing",
+            "worker",
+            "--pool=threads",
+            "--concurrency=2",
+            "--prefetch-multiplier=1",
+            "--loglevel=INFO",
+            "--hostname=user_file_processing@%n",
+            "-Q",
+            "user_file_processing,user_file_project_sync,connector_doc_permissions_sync,connector_external_group_sync,csv_generation,user_file_delete",
+        ]
+        background_workers = [
+            ("HEAVY", cmd_worker_heavy),
+            ("MONITORING", cmd_worker_monitoring),
+            ("USER_FILE_PROCESSING", cmd_worker_user_file_processing),
+        ]
 
-    processes = []
-    for name, cmd in all_workers:
+    # spawn processes
+    worker_primary_process = subprocess.Popen(
+        cmd_worker_primary, stdout=subprocess.PIPE, stderr=subprocess.STDOUT, text=True
+    )
+
+    worker_light_process = subprocess.Popen(
+        cmd_worker_light, stdout=subprocess.PIPE, stderr=subprocess.STDOUT, text=True
+    )
+
+    worker_docprocessing_process = subprocess.Popen(
+        cmd_worker_docprocessing,
+        stdout=subprocess.PIPE,
+        stderr=subprocess.STDOUT,
+        text=True,
+    )
+
+    worker_docfetching_process = subprocess.Popen(
+        cmd_worker_docfetching,
+        stdout=subprocess.PIPE,
+        stderr=subprocess.STDOUT,
+        text=True,
+    )
+
+    beat_process = subprocess.Popen(
+        cmd_beat, stdout=subprocess.PIPE, stderr=subprocess.STDOUT, text=True
+    )
+
+    # Spawn background worker processes based on mode
+    background_processes = []
+    for name, cmd in background_workers:
         process = subprocess.Popen(
             cmd, stdout=subprocess.PIPE, stderr=subprocess.STDOUT, text=True
         )
-        processes.append((name, process))
+        background_processes.append((name, process))
 
-    threads = []
-    for name, process in processes:
+    # monitor threads
+    worker_primary_thread = threading.Thread(
+        target=monitor_process, args=("PRIMARY", worker_primary_process)
+    )
+    worker_light_thread = threading.Thread(
+        target=monitor_process, args=("LIGHT", worker_light_process)
+    )
+    worker_docprocessing_thread = threading.Thread(
+        target=monitor_process, args=("DOCPROCESSING", worker_docprocessing_process)
+    )
+    worker_docfetching_thread = threading.Thread(
+        target=monitor_process, args=("DOCFETCHING", worker_docfetching_process)
+    )
+    beat_thread = threading.Thread(target=monitor_process, args=("BEAT", beat_process))
+
+    # Create monitor threads for background workers
+    background_threads = []
+    for name, process in background_processes:
         thread = threading.Thread(target=monitor_process, args=(name, process))
-        threads.append(thread)
+        background_threads.append(thread)
+
+    # Start all threads
+    worker_primary_thread.start()
+    worker_light_thread.start()
+    worker_docprocessing_thread.start()
+    worker_docfetching_thread.start()
+    beat_thread.start()
+
+    for thread in background_threads:
         thread.start()
 
-    for thread in threads:
+    # Wait for all threads
+    worker_primary_thread.join()
+    worker_light_thread.join()
+    worker_docprocessing_thread.join()
+    worker_docfetching_thread.join()
+    beat_thread.join()
+
+    for thread in background_threads:
         thread.join()
 
 

backend/scripts/restart_containers.sh

@@ -1,20 +1,10 @@
 #!/bin/bash
 set -e
 
-SCRIPT_DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" &> /dev/null && pwd )"
-COMPOSE_FILE="$SCRIPT_DIR/../../deployment/docker_compose/docker-compose.yml"
-COMPOSE_DEV_FILE="$SCRIPT_DIR/../../deployment/docker_compose/docker-compose.dev.yml"
-
-stop_and_remove_containers() {
-  docker stop onyx_postgres onyx_vespa onyx_redis onyx_minio onyx_code_interpreter 2>/dev/null || true
-  docker rm onyx_postgres onyx_vespa onyx_redis onyx_minio onyx_code_interpreter 2>/dev/null || true
-  docker compose -f "$COMPOSE_FILE" -f "$COMPOSE_DEV_FILE" --profile opensearch-enabled stop opensearch 2>/dev/null || true
-  docker compose -f "$COMPOSE_FILE" -f "$COMPOSE_DEV_FILE" --profile opensearch-enabled rm -f opensearch 2>/dev/null || true
-}
-
 cleanup() {
   echo "Error occurred. Cleaning up..."
-  stop_and_remove_containers
+  docker stop onyx_postgres onyx_vespa onyx_redis onyx_minio onyx_code_interpreter 2>/dev/null || true
+  docker rm onyx_postgres onyx_vespa onyx_redis onyx_minio onyx_code_interpreter 2>/dev/null || true
 }
 
 # Trap errors and output a message, then cleanup
@@ -22,26 +12,16 @@ trap 'echo "Error occurred on line $LINENO. Exiting script." >&2; cleanup' ERR
 
 # Usage of the script with optional volume arguments
 # ./restart_containers.sh [vespa_volume] [postgres_volume] [redis_volume]
-# [minio_volume] [--keep-opensearch-data]
 
-KEEP_OPENSEARCH_DATA=false
-POSITIONAL_ARGS=()
-for arg in "$@"; do
-    if [[ "$arg" == "--keep-opensearch-data" ]]; then
-        KEEP_OPENSEARCH_DATA=true
-    else
-        POSITIONAL_ARGS+=("$arg")
-    fi
-done
-
-VESPA_VOLUME=${POSITIONAL_ARGS[0]:-""}
-POSTGRES_VOLUME=${POSITIONAL_ARGS[1]:-""}
-REDIS_VOLUME=${POSITIONAL_ARGS[2]:-""}
-MINIO_VOLUME=${POSITIONAL_ARGS[3]:-""}
+VESPA_VOLUME=${1:-""}  # Default is empty if not provided
+POSTGRES_VOLUME=${2:-""}  # Default is empty if not provided
+REDIS_VOLUME=${3:-""}  # Default is empty if not provided
+MINIO_VOLUME=${4:-""}  # Default is empty if not provided
 
 # Stop and remove the existing containers
 echo "Stopping and removing existing containers..."
-stop_and_remove_containers
+docker stop onyx_postgres onyx_vespa onyx_redis onyx_minio onyx_code_interpreter 2>/dev/null || true
+docker rm onyx_postgres onyx_vespa onyx_redis onyx_minio onyx_code_interpreter 2>/dev/null || true
 
 # Start the PostgreSQL container with optional volume
 echo "Starting PostgreSQL container..."
@@ -59,29 +39,6 @@ else
     docker run --detach --name onyx_vespa --hostname vespa-container --publish 8081:8081 --publish 19071:19071 vespaengine/vespa:8
 fi
 
-# If OPENSEARCH_ADMIN_PASSWORD is not already set, try loading it from
-# .vscode/.env so existing dev setups that stored it there aren't silently
-# broken.
-VSCODE_ENV="$SCRIPT_DIR/../../.vscode/.env"
-if [[ -z "${OPENSEARCH_ADMIN_PASSWORD:-}" && -f "$VSCODE_ENV" ]]; then
-    set -a
-    # shellcheck source=/dev/null
-    source "$VSCODE_ENV"
-    set +a
-fi
-
-# Start the OpenSearch container using the same service from docker-compose that
-# our users use, setting OPENSEARCH_INITIAL_ADMIN_PASSWORD from the env's
-# OPENSEARCH_ADMIN_PASSWORD if it exists, else defaulting to StrongPassword123!.
-# Pass --keep-opensearch-data to preserve the opensearch-data volume across
-# restarts, else the volume is deleted so the container starts fresh.
-if [[ "$KEEP_OPENSEARCH_DATA" == "false" ]]; then
-    echo "Deleting opensearch-data volume..."
-    docker volume rm onyx_opensearch-data 2>/dev/null || true
-fi
-echo "Starting OpenSearch container..."
-docker compose -f "$COMPOSE_FILE" -f "$COMPOSE_DEV_FILE" --profile opensearch-enabled up --force-recreate -d opensearch
-
 # Start the Redis container with optional volume
 echo "Starting Redis container..."
 if [[ -n "$REDIS_VOLUME" ]]; then
@@ -103,6 +60,7 @@ echo "Starting Code Interpreter container..."
 docker run --detach --name onyx_code_interpreter --publish 8000:8000 --user root -v /var/run/docker.sock:/var/run/docker.sock onyxdotapp/code-interpreter:latest bash ./entrypoint.sh code-interpreter-api
 
 # Ensure alembic runs in the correct directory (backend/)
+SCRIPT_DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" &> /dev/null && pwd )"
 PARENT_DIR="$(dirname "$SCRIPT_DIR")"
 cd "$PARENT_DIR"
 

backend/scripts/restart_opensearch_container.sh

@@ -0,0 +1,10 @@
+#!/bin/bash
+
+# We get OPENSEARCH_ADMIN_PASSWORD from the repo .env file.
+source "$(dirname "$0")/../../.vscode/.env"
+
+cd "$(dirname "$0")/../../deployment/docker_compose"
+
+# Start OpenSearch.
+echo "Forcefully starting fresh OpenSearch container..."
+docker compose -f docker-compose.opensearch.yml up --force-recreate -d opensearch

backend/scripts/supervisord_entrypoint.sh

@@ -1,5 +1,23 @@
 #!/bin/sh
-# Entrypoint script for supervisord
+# Entrypoint script for supervisord that sets environment variables
+# for controlling which celery workers to start
+
+# Default to lightweight mode if not set
+if [ -z "$USE_LIGHTWEIGHT_BACKGROUND_WORKER" ]; then
+    export USE_LIGHTWEIGHT_BACKGROUND_WORKER="true"
+fi
+
+# Set the complementary variable for supervisord
+# because it doesn't support %(not ENV_USE_LIGHTWEIGHT_BACKGROUND_WORKER) syntax
+if [ "$USE_LIGHTWEIGHT_BACKGROUND_WORKER" = "true" ]; then
+    export USE_SEPARATE_BACKGROUND_WORKERS="false"
+else
+    export USE_SEPARATE_BACKGROUND_WORKERS="true"
+fi
+
+echo "Worker mode configuration:"
+echo "  USE_LIGHTWEIGHT_BACKGROUND_WORKER=$USE_LIGHTWEIGHT_BACKGROUND_WORKER"
+echo "  USE_SEPARATE_BACKGROUND_WORKERS=$USE_SEPARATE_BACKGROUND_WORKERS"
 
 # Launch supervisord with environment variables available
 exec /usr/bin/supervisord -c /etc/supervisor/conf.d/supervisord.conf

backend/supervisord.conf

@@ -39,6 +39,7 @@ autorestart=true
 startsecs=10
 stopasgroup=true
 
+# Standard mode: Light worker for fast operations
 # NOTE: only allowing configuration here and not in the other celery workers,
 # since this is often the bottleneck for "sync" jobs (e.g. document set syncing,
 # user group syncing, deletion, etc.)
@@ -53,7 +54,26 @@ redirect_stderr=true
 autorestart=true
 startsecs=10
 stopasgroup=true
+autostart=%(ENV_USE_SEPARATE_BACKGROUND_WORKERS)s
 
+# Lightweight mode: single consolidated background worker
+# Used when USE_LIGHTWEIGHT_BACKGROUND_WORKER=true (default)
+# Consolidates: light, docprocessing, docfetching, heavy, monitoring, user_file_processing
+[program:celery_worker_background]
+command=celery -A onyx.background.celery.versioned_apps.background worker
+    --loglevel=INFO
+    --hostname=background@%%n
+    -Q vespa_metadata_sync,connector_deletion,doc_permissions_upsert,checkpoint_cleanup,index_attempt_cleanup,sandbox,docprocessing,connector_doc_fetching,connector_pruning,connector_doc_permissions_sync,connector_external_group_sync,csv_generation,monitoring,user_file_processing,user_file_project_sync,opensearch_migration
+stdout_logfile=/var/log/celery_worker_background.log
+stdout_logfile_maxbytes=16MB
+redirect_stderr=true
+autorestart=true
+startsecs=10
+stopasgroup=true
+autostart=%(ENV_USE_LIGHTWEIGHT_BACKGROUND_WORKER)s
+
+# Standard mode: separate workers for different background tasks
+# Used when USE_LIGHTWEIGHT_BACKGROUND_WORKER=false
 [program:celery_worker_heavy]
 command=celery -A onyx.background.celery.versioned_apps.heavy worker
     --loglevel=INFO
@@ -65,7 +85,9 @@ redirect_stderr=true
 autorestart=true
 startsecs=10
 stopasgroup=true
+autostart=%(ENV_USE_SEPARATE_BACKGROUND_WORKERS)s
 
+# Standard mode: Document processing worker
 [program:celery_worker_docprocessing]
 command=celery -A onyx.background.celery.versioned_apps.docprocessing worker
     --loglevel=INFO
@@ -77,6 +99,7 @@ redirect_stderr=true
 autorestart=true
 startsecs=10
 stopasgroup=true
+autostart=%(ENV_USE_SEPARATE_BACKGROUND_WORKERS)s
 
 [program:celery_worker_user_file_processing]
 command=celery -A onyx.background.celery.versioned_apps.user_file_processing worker
@@ -89,7 +112,9 @@ redirect_stderr=true
 autorestart=true
 startsecs=10
 stopasgroup=true
+autostart=%(ENV_USE_SEPARATE_BACKGROUND_WORKERS)s
 
+# Standard mode: Document fetching worker
 [program:celery_worker_docfetching]
 command=celery -A onyx.background.celery.versioned_apps.docfetching worker
     --loglevel=INFO
@@ -101,6 +126,7 @@ redirect_stderr=true
 autorestart=true
 startsecs=10
 stopasgroup=true
+autostart=%(ENV_USE_SEPARATE_BACKGROUND_WORKERS)s
 
 [program:celery_worker_monitoring]
 command=celery -A onyx.background.celery.versioned_apps.monitoring worker
@@ -113,6 +139,7 @@ redirect_stderr=true
 autorestart=true
 startsecs=10
 stopasgroup=true
+autostart=%(ENV_USE_SEPARATE_BACKGROUND_WORKERS)s
 
 
 # Job scheduler for periodic tasks
@@ -170,6 +197,7 @@ command=tail -qF
     /var/log/celery_beat.log
     /var/log/celery_worker_primary.log
     /var/log/celery_worker_light.log
+    /var/log/celery_worker_background.log
     /var/log/celery_worker_heavy.log
     /var/log/celery_worker_docprocessing.log
     /var/log/celery_worker_monitoring.log

backend/tests/external_dependency_unit/celery/test_pruning_hierarchy_nodes.py

@@ -5,8 +5,6 @@ Verifies that:
 1. extract_ids_from_runnable_connector correctly separates hierarchy nodes from doc IDs
 2. Extracted hierarchy nodes are correctly upserted to Postgres via upsert_hierarchy_nodes_batch
 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
 
 Uses a mock SlimConnectorWithPermSync that yields known hierarchy nodes and slim documents,
 combined with a real PostgreSQL database for verifying persistence.
@@ -29,13 +27,9 @@ from onyx.db.enums import HierarchyNodeType
 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 update_document_parent_hierarchy_nodes
 from onyx.db.hierarchy import upsert_hierarchy_nodes_batch
-from onyx.db.models import Document as DbDocument
 from onyx.db.models import HierarchyNode as DBHierarchyNode
 from onyx.indexing.indexing_heartbeat import IndexingHeartbeatInterface
-from onyx.kg.models import KGStage
 
 # ---------------------------------------------------------------------------
 # Constants
@@ -95,18 +89,8 @@ def _make_hierarchy_nodes() -> list[PydanticHierarchyNode]:
     ]
 
 
-DOC_PARENT_MAP = {
-    "msg-001": CHANNEL_A_ID,
-    "msg-002": CHANNEL_A_ID,
-    "msg-003": CHANNEL_B_ID,
-}
-
-
 def _make_slim_docs() -> list[SlimDocument | PydanticHierarchyNode]:
-    return [
-        SlimDocument(id=doc_id, parent_hierarchy_raw_node_id=DOC_PARENT_MAP.get(doc_id))
-        for doc_id in SLIM_DOC_IDS
-    ]
+    return [SlimDocument(id=doc_id) for doc_id in SLIM_DOC_IDS]
 
 
 class MockSlimConnectorWithPermSync(SlimConnectorWithPermSync):
@@ -142,31 +126,14 @@ class MockSlimConnectorWithPermSync(SlimConnectorWithPermSync):
 # ---------------------------------------------------------------------------
 
 
-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()
+def _cleanup_test_hierarchy_nodes(db_session: Session) -> None:
+    """Remove all hierarchy nodes for TEST_SOURCE to isolate tests."""
     db_session.query(DBHierarchyNode).filter(
         DBHierarchyNode.source == TEST_SOURCE
     ).delete()
     db_session.commit()
 
 
-def _create_test_documents(db_session: Session) -> list[DbDocument]:
-    """Insert minimal Document rows for our test doc IDs."""
-    docs = []
-    for doc_id in SLIM_DOC_IDS:
-        doc = DbDocument(
-            id=doc_id,
-            semantic_id=doc_id,
-            kg_stage=KGStage.NOT_STARTED,
-        )
-        db_session.add(doc)
-        docs.append(doc)
-    db_session.commit()
-    return docs
-
-
 # ---------------------------------------------------------------------------
 # Tests
 # ---------------------------------------------------------------------------
@@ -180,14 +147,14 @@ def test_pruning_extracts_hierarchy_nodes(db_session: Session) -> None:  # noqa:
     result = extract_ids_from_runnable_connector(connector, callback=None)
 
     # 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)
+    # (hierarchy node IDs are added to doc_ids 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
+    assert result.doc_ids == expected_ids
 
     # Hierarchy nodes should be the 3 channels
     assert len(result.hierarchy_nodes) == 3
@@ -198,7 +165,7 @@ def test_pruning_extracts_hierarchy_nodes(db_session: Session) -> None:  # noqa:
 def test_pruning_upserts_hierarchy_nodes_to_db(db_session: Session) -> None:
     """Full flow: extract hierarchy nodes from mock connector, upsert to Postgres,
     then verify the DB state (node count, parent relationships, permissions)."""
-    _cleanup_test_data(db_session)
+    _cleanup_test_hierarchy_nodes(db_session)
 
     # Step 1: ensure the SOURCE node exists (mirrors what the pruning task does)
     source_node = ensure_source_node_exists(db_session, TEST_SOURCE, commit=True)
@@ -263,7 +230,7 @@ def test_pruning_upserts_hierarchy_nodes_public_connector(
 ) -> None:
     """When the connector's access type is PUBLIC, all hierarchy nodes must be
     marked is_public=True regardless of their external_access settings."""
-    _cleanup_test_data(db_session)
+    _cleanup_test_hierarchy_nodes(db_session)
 
     ensure_source_node_exists(db_session, TEST_SOURCE, commit=True)
 
@@ -290,7 +257,7 @@ def test_pruning_upserts_hierarchy_nodes_public_connector(
 def test_pruning_hierarchy_node_upsert_idempotency(db_session: Session) -> None:
     """Upserting the same hierarchy nodes twice must not create duplicates.
     The second call should update existing rows in place."""
-    _cleanup_test_data(db_session)
+    _cleanup_test_hierarchy_nodes(db_session)
 
     ensure_source_node_exists(db_session, TEST_SOURCE, commit=True)
 
@@ -328,7 +295,7 @@ def test_pruning_hierarchy_node_upsert_idempotency(db_session: Session) -> None:
 
 def test_pruning_hierarchy_node_upsert_updates_fields(db_session: Session) -> None:
     """Upserting a hierarchy node with changed fields should update the existing row."""
-    _cleanup_test_data(db_session)
+    _cleanup_test_hierarchy_nodes(db_session)
 
     ensure_source_node_exists(db_session, TEST_SOURCE, commit=True)
 
@@ -375,193 +342,3 @@ def test_pruning_hierarchy_node_upsert_updates_fields(db_session: Session) -> No
     assert db_node.is_public is True
     assert db_node.external_user_emails is not None
     assert set(db_node.external_user_emails) == {"new_user@example.com"}
-
-
-# ---------------------------------------------------------------------------
-# Document-to-hierarchy-node linkage tests
-# ---------------------------------------------------------------------------
-
-
-def test_extraction_preserves_parent_hierarchy_raw_node_id(
-    db_session: Session,  # noqa: ARG001
-) -> None:
-    """extract_ids_from_runnable_connector should carry the
-    parent_hierarchy_raw_node_id from SlimDocument into the raw_id_to_parent dict."""
-    connector = MockSlimConnectorWithPermSync()
-    result = extract_ids_from_runnable_connector(connector, callback=None)
-
-    for doc_id, expected_parent in DOC_PARENT_MAP.items():
-        assert (
-            result.raw_id_to_parent[doc_id] == expected_parent
-        ), f"raw_id_to_parent[{doc_id}] should be {expected_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 result.raw_id_to_parent[channel_id] is None
-
-
-def test_update_document_parent_hierarchy_nodes(db_session: Session) -> None:
-    """update_document_parent_hierarchy_nodes should set
-    Document.parent_hierarchy_node_id for each document in the mapping."""
-    _cleanup_test_data(db_session)
-
-    source_node = ensure_source_node_exists(db_session, TEST_SOURCE, commit=True)
-    upserted = upsert_hierarchy_nodes_batch(
-        db_session=db_session,
-        nodes=_make_hierarchy_nodes(),
-        source=TEST_SOURCE,
-        commit=True,
-        is_connector_public=False,
-    )
-    node_id_by_raw = {n.raw_node_id: n.id for n in upserted}
-
-    # Create documents with no parent set
-    docs = _create_test_documents(db_session)
-    for doc in docs:
-        assert doc.parent_hierarchy_node_id is None
-
-    # Build resolved map (same logic as _resolve_and_update_document_parents)
-    resolved: dict[str, int | None] = {}
-    for doc_id, raw_parent in DOC_PARENT_MAP.items():
-        resolved[doc_id] = node_id_by_raw.get(raw_parent, source_node.id)
-
-    updated = update_document_parent_hierarchy_nodes(
-        db_session=db_session,
-        doc_parent_map=resolved,
-        commit=True,
-    )
-    assert updated == len(SLIM_DOC_IDS)
-
-    # Verify each document now points to the correct hierarchy node
-    db_session.expire_all()
-    for doc_id, raw_parent in DOC_PARENT_MAP.items():
-        tmp_doc = db_session.get(DbDocument, doc_id)
-        assert tmp_doc is not None
-        doc = tmp_doc
-        expected_node_id = node_id_by_raw[raw_parent]
-        assert (
-            doc.parent_hierarchy_node_id == expected_node_id
-        ), f"Document {doc_id} should point to node for {raw_parent}"
-
-
-def test_update_document_parent_is_idempotent(db_session: Session) -> None:
-    """Running update_document_parent_hierarchy_nodes a second time with the
-    same mapping should update zero rows."""
-    _cleanup_test_data(db_session)
-
-    ensure_source_node_exists(db_session, TEST_SOURCE, commit=True)
-    upserted = upsert_hierarchy_nodes_batch(
-        db_session=db_session,
-        nodes=_make_hierarchy_nodes(),
-        source=TEST_SOURCE,
-        commit=True,
-        is_connector_public=False,
-    )
-    node_id_by_raw = {n.raw_node_id: n.id for n in upserted}
-    _create_test_documents(db_session)
-
-    resolved: dict[str, int | None] = {
-        doc_id: node_id_by_raw[raw_parent]
-        for doc_id, raw_parent in DOC_PARENT_MAP.items()
-    }
-
-    first_updated = update_document_parent_hierarchy_nodes(
-        db_session=db_session,
-        doc_parent_map=resolved,
-        commit=True,
-    )
-    assert first_updated == len(SLIM_DOC_IDS)
-
-    second_updated = update_document_parent_hierarchy_nodes(
-        db_session=db_session,
-        doc_parent_map=resolved,
-        commit=True,
-    )
-    assert second_updated == 0
-
-
-def test_link_hierarchy_nodes_to_documents_for_confluence(
-    db_session: Session,
-) -> None:
-    """For sources in SOURCES_WITH_HIERARCHY_NODE_DOCUMENTS (e.g. Confluence),
-    link_hierarchy_nodes_to_documents should set HierarchyNode.document_id
-    when a hierarchy node's raw_node_id matches a document ID."""
-    _cleanup_test_data(db_session)
-    confluence_source = DocumentSource.CONFLUENCE
-
-    # Clean up any existing Confluence hierarchy nodes
-    db_session.query(DBHierarchyNode).filter(
-        DBHierarchyNode.source == confluence_source
-    ).delete()
-    db_session.commit()
-
-    ensure_source_node_exists(db_session, confluence_source, commit=True)
-
-    # Create a hierarchy node whose raw_node_id matches a document ID
-    page_node_id = "confluence-page-123"
-    nodes = [
-        PydanticHierarchyNode(
-            raw_node_id=page_node_id,
-            raw_parent_id=None,
-            display_name="Test Page",
-            link="https://wiki.example.com/page/123",
-            node_type=HierarchyNodeType.PAGE,
-        ),
-    ]
-    upsert_hierarchy_nodes_batch(
-        db_session=db_session,
-        nodes=nodes,
-        source=confluence_source,
-        commit=True,
-        is_connector_public=False,
-    )
-
-    # Verify the node exists but has no document_id yet
-    db_node = get_hierarchy_node_by_raw_id(db_session, page_node_id, confluence_source)
-    assert db_node is not None
-    assert db_node.document_id is None
-
-    # Create a document with the same ID as the hierarchy node
-    doc = DbDocument(
-        id=page_node_id,
-        semantic_id="Test Page",
-        kg_stage=KGStage.NOT_STARTED,
-    )
-    db_session.add(doc)
-    db_session.commit()
-
-    # Link nodes to documents
-    linked = link_hierarchy_nodes_to_documents(
-        db_session=db_session,
-        document_ids=[page_node_id],
-        source=confluence_source,
-        commit=True,
-    )
-    assert linked == 1
-
-    # Verify the hierarchy node now has document_id set
-    db_session.expire_all()
-    db_node = get_hierarchy_node_by_raw_id(db_session, page_node_id, confluence_source)
-    assert db_node is not None
-    assert db_node.document_id == page_node_id
-
-    # Cleanup
-    db_session.query(DbDocument).filter(DbDocument.id == page_node_id).delete()
-    db_session.query(DBHierarchyNode).filter(
-        DBHierarchyNode.source == confluence_source
-    ).delete()
-    db_session.commit()
-
-
-def test_link_hierarchy_nodes_skips_non_hierarchy_sources(
-    db_session: Session,
-) -> None:
-    """link_hierarchy_nodes_to_documents should return 0 for sources that
-    don't support hierarchy-node-as-document (e.g. Slack, Google Drive)."""
-    linked = link_hierarchy_nodes_to_documents(
-        db_session=db_session,
-        document_ids=SLIM_DOC_IDS,
-        source=TEST_SOURCE,  # Slack — not in SOURCES_WITH_HIERARCHY_NODE_DOCUMENTS
-        commit=False,
-    )
-    assert linked == 0

backend/tests/external_dependency_unit/llm/test_llm_provider.py

@@ -11,6 +11,7 @@ from unittest.mock import patch
 from uuid import uuid4
 
 import pytest
+from fastapi import HTTPException
 from sqlalchemy.orm import Session
 
 from onyx.db.enums import LLMModelFlowType
@@ -19,8 +20,6 @@ from onyx.db.llm import remove_llm_provider
 from onyx.db.llm import update_default_provider
 from onyx.db.llm import upsert_llm_provider
 from onyx.db.models import UserRole
-from onyx.error_handling.error_codes import OnyxErrorCode
-from onyx.error_handling.exceptions import OnyxError
 from onyx.llm.constants import LlmProviderNames
 from onyx.llm.interfaces import LLM
 from onyx.server.manage.llm.api import (
@@ -123,16 +122,16 @@ class TestLLMConfigurationEndpoint:
         finally:
             db_session.rollback()
 
-    def test_failed_llm_test_raises_onyx_error(
+    def test_failed_llm_test_raises_http_exception(
         self,
         db_session: Session,
         provider_name: str,  # noqa: ARG002
     ) -> None:
         """
-        Test that a failed LLM test raises an OnyxError with VALIDATION_ERROR.
+        Test that a failed LLM test raises an HTTPException with status 400.
 
         When test_llm returns an error message, the endpoint should raise
-        an OnyxError with the error details.
+        an HTTPException with the error details.
         """
         error_message = "Invalid API key: Authentication failed"
 
@@ -144,7 +143,7 @@ class TestLLMConfigurationEndpoint:
             with patch(
                 "onyx.server.manage.llm.api.test_llm", side_effect=mock_test_llm_failure
             ):
-                with pytest.raises(OnyxError) as exc_info:
+                with pytest.raises(HTTPException) as exc_info:
                     run_test_llm_configuration(
                         test_llm_request=LLMTestRequest(
                             provider=LlmProviderNames.OPENAI,
@@ -157,8 +156,9 @@ class TestLLMConfigurationEndpoint:
                         db_session=db_session,
                     )
 
-                assert exc_info.value.error_code == OnyxErrorCode.VALIDATION_ERROR
-                assert exc_info.value.message == error_message
+                # Verify the exception details
+                assert exc_info.value.status_code == 400
+                assert exc_info.value.detail == error_message
 
         finally:
             db_session.rollback()
@@ -536,11 +536,11 @@ class TestDefaultProviderEndpoint:
                 remove_llm_provider(db_session, provider.id)
 
             # Now run_test_default_provider should fail
-            with pytest.raises(OnyxError) as exc_info:
+            with pytest.raises(HTTPException) as exc_info:
                 run_test_default_provider(_=_create_mock_admin())
 
-            assert exc_info.value.error_code == OnyxErrorCode.VALIDATION_ERROR
-            assert "No LLM Provider setup" in exc_info.value.message
+            assert exc_info.value.status_code == 400
+            assert "No LLM Provider setup" in exc_info.value.detail
 
         finally:
             db_session.rollback()
@@ -581,11 +581,11 @@ class TestDefaultProviderEndpoint:
             with patch(
                 "onyx.server.manage.llm.api.test_llm", side_effect=mock_test_llm_failure
             ):
-                with pytest.raises(OnyxError) as exc_info:
+                with pytest.raises(HTTPException) as exc_info:
                     run_test_default_provider(_=_create_mock_admin())
 
-                assert exc_info.value.error_code == OnyxErrorCode.VALIDATION_ERROR
-                assert exc_info.value.message == error_message
+                assert exc_info.value.status_code == 400
+                assert exc_info.value.detail == error_message
 
         finally:
             db_session.rollback()

backend/tests/external_dependency_unit/llm/test_llm_provider_api_base.py

@@ -16,14 +16,13 @@ from unittest.mock import patch
 from uuid import uuid4
 
 import pytest
+from fastapi import HTTPException
 from sqlalchemy.orm import Session
 
 from onyx.db.llm import fetch_existing_llm_provider
 from onyx.db.llm import remove_llm_provider
 from onyx.db.llm import upsert_llm_provider
 from onyx.db.models import UserRole
-from onyx.error_handling.error_codes import OnyxErrorCode
-from onyx.error_handling.exceptions import OnyxError
 from onyx.llm.constants import LlmProviderNames
 from onyx.server.manage.llm.api import _mask_string
 from onyx.server.manage.llm.api import put_llm_provider
@@ -101,7 +100,7 @@ class TestLLMProviderChanges:
                     api_base="https://attacker.example.com",
                 )
 
-                with pytest.raises(OnyxError) as exc_info:
+                with pytest.raises(HTTPException) as exc_info:
                     put_llm_provider(
                         llm_provider_upsert_request=update_request,
                         is_creation=False,
@@ -109,9 +108,9 @@ class TestLLMProviderChanges:
                         db_session=db_session,
                     )
 
-                assert exc_info.value.error_code == OnyxErrorCode.VALIDATION_ERROR
+                assert exc_info.value.status_code == 400
                 assert "cannot be changed without changing the API key" in str(
-                    exc_info.value.message
+                    exc_info.value.detail
                 )
         finally:
             _cleanup_provider(db_session, provider_name)
@@ -237,7 +236,7 @@ class TestLLMProviderChanges:
                     api_base=None,
                 )
 
-                with pytest.raises(OnyxError) as exc_info:
+                with pytest.raises(HTTPException) as exc_info:
                     put_llm_provider(
                         llm_provider_upsert_request=update_request,
                         is_creation=False,
@@ -245,9 +244,9 @@ class TestLLMProviderChanges:
                         db_session=db_session,
                     )
 
-                assert exc_info.value.error_code == OnyxErrorCode.VALIDATION_ERROR
+                assert exc_info.value.status_code == 400
                 assert "cannot be changed without changing the API key" in str(
-                    exc_info.value.message
+                    exc_info.value.detail
                 )
         finally:
             _cleanup_provider(db_session, provider_name)
@@ -340,7 +339,7 @@ class TestLLMProviderChanges:
                     custom_config_changed=True,
                 )
 
-                with pytest.raises(OnyxError) as exc_info:
+                with pytest.raises(HTTPException) as exc_info:
                     put_llm_provider(
                         llm_provider_upsert_request=update_request,
                         is_creation=False,
@@ -348,9 +347,9 @@ class TestLLMProviderChanges:
                         db_session=db_session,
                     )
 
-                assert exc_info.value.error_code == OnyxErrorCode.VALIDATION_ERROR
+                assert exc_info.value.status_code == 400
                 assert "cannot be changed without changing the API key" in str(
-                    exc_info.value.message
+                    exc_info.value.detail
                 )
         finally:
             _cleanup_provider(db_session, provider_name)
@@ -376,7 +375,7 @@ class TestLLMProviderChanges:
                     custom_config_changed=True,
                 )
 
-                with pytest.raises(OnyxError) as exc_info:
+                with pytest.raises(HTTPException) as exc_info:
                     put_llm_provider(
                         llm_provider_upsert_request=update_request,
                         is_creation=False,
@@ -384,9 +383,9 @@ class TestLLMProviderChanges:
                         db_session=db_session,
                     )
 
-                assert exc_info.value.error_code == OnyxErrorCode.VALIDATION_ERROR
+                assert exc_info.value.status_code == 400
                 assert "cannot be changed without changing the API key" in str(
-                    exc_info.value.message
+                    exc_info.value.detail
                 )
         finally:
             _cleanup_provider(db_session, provider_name)

backend/tests/external_dependency_unit/search_settings/test_search_settings.py

@@ -11,7 +11,6 @@ from onyx.context.search.models import SavedSearchSettings
 from onyx.context.search.models import SearchSettingsCreationRequest
 from onyx.db.enums import EmbeddingPrecision
 from onyx.db.llm import fetch_default_contextual_rag_model
-from onyx.db.llm import fetch_existing_llm_provider
 from onyx.db.llm import update_default_contextual_model
 from onyx.db.llm import upsert_llm_provider
 from onyx.db.models import IndexModelStatus
@@ -38,8 +37,6 @@ def _create_llm_provider_and_model(
     model_name: str,
 ) -> None:
     """Insert an LLM provider with a single visible model configuration."""
-    if fetch_existing_llm_provider(name=provider_name, db_session=db_session):
-        return
     upsert_llm_provider(
         LLMProviderUpsertRequest(
             name=provider_name,
@@ -149,8 +146,8 @@ def baseline_search_settings(
     )
 
 
+@pytest.mark.skip(reason="Set new search settings is temporarily disabled.")
 @patch("onyx.db.swap_index.get_all_document_indices")
-@patch("onyx.server.manage.search_settings.get_all_document_indices")
 @patch("onyx.server.manage.search_settings.get_default_document_index")
 @patch("onyx.indexing.indexing_pipeline.get_llm_for_contextual_rag")
 @patch("onyx.indexing.indexing_pipeline.index_doc_batch_with_handler")
@@ -158,7 +155,6 @@ def test_indexing_pipeline_uses_contextual_rag_settings_from_create(
     mock_index_handler: MagicMock,
     mock_get_llm: MagicMock,
     mock_get_doc_index: MagicMock,  # noqa: ARG001
-    mock_get_all_doc_indices_search_settings: MagicMock,  # noqa: ARG001
     mock_get_all_doc_indices: MagicMock,
     baseline_search_settings: None,  # noqa: ARG001
     db_session: Session,
@@ -200,8 +196,8 @@ def test_indexing_pipeline_uses_contextual_rag_settings_from_create(
     )
 
 
+@pytest.mark.skip(reason="Set new search settings is temporarily disabled.")
 @patch("onyx.db.swap_index.get_all_document_indices")
-@patch("onyx.server.manage.search_settings.get_all_document_indices")
 @patch("onyx.server.manage.search_settings.get_default_document_index")
 @patch("onyx.indexing.indexing_pipeline.get_llm_for_contextual_rag")
 @patch("onyx.indexing.indexing_pipeline.index_doc_batch_with_handler")
@@ -209,7 +205,6 @@ def test_indexing_pipeline_uses_updated_contextual_rag_settings(
     mock_index_handler: MagicMock,
     mock_get_llm: MagicMock,
     mock_get_doc_index: MagicMock,  # noqa: ARG001
-    mock_get_all_doc_indices_search_settings: MagicMock,  # noqa: ARG001
     mock_get_all_doc_indices: MagicMock,
     baseline_search_settings: None,  # noqa: ARG001
     db_session: Session,
@@ -271,7 +266,7 @@ def test_indexing_pipeline_uses_updated_contextual_rag_settings(
     )
 
 
-@patch("onyx.server.manage.search_settings.get_all_document_indices")
+@pytest.mark.skip(reason="Set new search settings is temporarily disabled.")
 @patch("onyx.server.manage.search_settings.get_default_document_index")
 @patch("onyx.indexing.indexing_pipeline.get_llm_for_contextual_rag")
 @patch("onyx.indexing.indexing_pipeline.index_doc_batch_with_handler")
@@ -279,7 +274,6 @@ def test_indexing_pipeline_skips_llm_when_contextual_rag_disabled(
     mock_index_handler: MagicMock,
     mock_get_llm: MagicMock,
     mock_get_doc_index: MagicMock,  # noqa: ARG001
-    mock_get_all_doc_indices_search_settings: MagicMock,  # noqa: ARG001
     baseline_search_settings: None,  # noqa: ARG001
     db_session: Session,
 ) -> None:

backend/tests/integration/tests/llm_provider/test_llm_provider.py

@@ -427,7 +427,7 @@ def test_delete_default_llm_provider_rejected(reset: None) -> None:  # noqa: ARG
         headers=admin_user.headers,
     )
     assert delete_response.status_code == 400
-    assert "Cannot delete the default LLM provider" in delete_response.json()["message"]
+    assert "Cannot delete the default LLM provider" in delete_response.json()["detail"]
 
     # Verify provider still exists
     provider_data = _get_provider_by_id(admin_user, created_provider["id"])
@@ -673,8 +673,8 @@ def test_duplicate_provider_name_rejected(reset: None) -> None:  # noqa: ARG001
         headers=admin_user.headers,
         json=base_payload,
     )
-    assert response.status_code == 409
-    assert "already exists" in response.json()["message"]
+    assert response.status_code == 400
+    assert "already exists" in response.json()["detail"]
 
 
 def test_rename_provider_rejected(reset: None) -> None:  # noqa: ARG001
@@ -711,7 +711,7 @@ def test_rename_provider_rejected(reset: None) -> None:  # noqa: ARG001
         json=update_payload,
     )
     assert response.status_code == 400
-    assert "not currently supported" in response.json()["message"]
+    assert "not currently supported" in response.json()["detail"]
 
     # Verify no duplicate was created — only the original provider should exist
     provider = _get_provider_by_id(admin_user, provider_id)

backend/tests/integration/tests/llm_provider/test_llm_provider_persona_access.py

@@ -69,7 +69,7 @@ def test_unauthorized_persona_access_returns_403(
 
     # Should return 403 Forbidden
     assert response.status_code == 403
-    assert "don't have access to this assistant" in response.json()["message"]
+    assert "don't have access to this assistant" in response.json()["detail"]
 
 
 def test_authorized_persona_access_returns_filtered_providers(
@@ -245,4 +245,4 @@ def test_nonexistent_persona_returns_404(
 
     # Should return 404
     assert response.status_code == 404
-    assert "Persona not found" in response.json()["message"]
+    assert "Persona not found" in response.json()["detail"]

backend/tests/integration/tests/llm_workflows/test_nightly_provider_chat_workflow.py

@@ -42,78 +42,6 @@ class NightlyProviderConfig(BaseModel):
     strict: bool
 
 
-def _stringify_custom_config_value(value: object) -> str:
-    if isinstance(value, str):
-        return value
-    if isinstance(value, (dict, list)):
-        return json.dumps(value)
-    return str(value)
-
-
-def _looks_like_vertex_credentials_payload(
-    raw_custom_config: dict[object, object],
-) -> bool:
-    normalized_keys = {str(key).strip().lower() for key in raw_custom_config}
-    provider_specific_keys = {
-        "vertex_credentials",
-        "credentials_file",
-        "vertex_credentials_file",
-        "google_application_credentials",
-        "vertex_location",
-        "location",
-        "vertex_region",
-        "region",
-    }
-    if normalized_keys & provider_specific_keys:
-        return False
-
-    normalized_type = str(raw_custom_config.get("type", "")).strip().lower()
-    if normalized_type not in {"service_account", "external_account"}:
-        return False
-
-    # Service account JSON usually includes private_key/client_email, while external
-    # account JSON includes credential_source. Either shape should be accepted.
-    has_service_account_markers = any(
-        key in normalized_keys for key in {"private_key", "client_email"}
-    )
-    has_external_account_markers = "credential_source" in normalized_keys
-    return has_service_account_markers or has_external_account_markers
-
-
-def _normalize_custom_config(
-    provider: str, raw_custom_config: dict[object, object]
-) -> dict[str, str]:
-    if provider == "vertex_ai" and _looks_like_vertex_credentials_payload(
-        raw_custom_config
-    ):
-        return {"vertex_credentials": json.dumps(raw_custom_config)}
-
-    normalized: dict[str, str] = {}
-    for raw_key, raw_value in raw_custom_config.items():
-        key = str(raw_key).strip()
-        key_lower = key.lower()
-
-        if provider == "vertex_ai":
-            if key_lower in {
-                "vertex_credentials",
-                "credentials_file",
-                "vertex_credentials_file",
-                "google_application_credentials",
-            }:
-                key = "vertex_credentials"
-            elif key_lower in {
-                "vertex_location",
-                "location",
-                "vertex_region",
-                "region",
-            }:
-                key = "vertex_location"
-
-        normalized[key] = _stringify_custom_config_value(raw_value)
-
-    return normalized
-
-
 def _env_true(env_var: str, default: bool = False) -> bool:
     value = os.environ.get(env_var)
     if value is None:
@@ -152,9 +80,7 @@ def _load_provider_config() -> NightlyProviderConfig:
         parsed = json.loads(custom_config_json)
         if not isinstance(parsed, dict):
             raise ValueError(f"{_ENV_CUSTOM_CONFIG_JSON} must be a JSON object")
-        custom_config = _normalize_custom_config(
-            provider=provider, raw_custom_config=parsed
-        )
+        custom_config = {str(key): str(value) for key, value in parsed.items()}
 
     if provider == "ollama_chat" and api_key and not custom_config:
         custom_config = {"OLLAMA_API_KEY": api_key}
@@ -222,23 +148,6 @@ def _validate_provider_config(config: NightlyProviderConfig) -> None:
                 ),
             )
 
-    if config.provider == "vertex_ai":
-        has_vertex_credentials = bool(
-            config.custom_config and config.custom_config.get("vertex_credentials")
-        )
-        if not has_vertex_credentials:
-            configured_keys = (
-                sorted(config.custom_config.keys()) if config.custom_config else []
-            )
-            _skip_or_fail(
-                strict=config.strict,
-                message=(
-                    f"{_ENV_CUSTOM_CONFIG_JSON} must include 'vertex_credentials' "
-                    f"for provider '{config.provider}'. "
-                    f"Found keys: {configured_keys}"
-                ),
-            )
-
 
 def _assert_integration_mode_enabled() -> None:
     assert (
@@ -284,7 +193,6 @@ def _create_provider_payload(
     return {
         "name": provider_name,
         "provider": provider,
-        "model": model_name,
         "api_key": api_key,
         "api_base": api_base,
         "api_version": api_version,
@@ -300,23 +208,24 @@ def _create_provider_payload(
     }
 
 
-def _ensure_provider_is_default(
-    provider_id: int, model_name: str, admin_user: DATestUser
-) -> None:
+def _ensure_provider_is_default(provider_id: int, admin_user: DATestUser) -> None:
     list_response = requests.get(
         f"{API_SERVER_URL}/admin/llm/provider",
         headers=admin_user.headers,
     )
     list_response.raise_for_status()
-    default_text = list_response.json().get("default_text")
-    assert default_text is not None, "Expected a default provider after setting default"
-    assert default_text.get("provider_id") == provider_id, (
-        f"Expected provider {provider_id} to be default, "
-        f"found {default_text.get('provider_id')}"
+    providers = list_response.json()
+
+    current_default = next(
+        (provider for provider in providers if provider.get("is_default_provider")),
+        None,
     )
     assert (
-        default_text.get("model_name") == model_name
-    ), f"Expected default model {model_name}, found {default_text.get('model_name')}"
+        current_default is not None
+    ), "Expected a default provider after setting provider as default"
+    assert (
+        current_default["id"] == provider_id
+    ), f"Expected provider {provider_id} to be default, found {current_default['id']}"
 
 
 def _run_chat_assertions(
@@ -417,9 +326,8 @@ def _create_and_test_provider_for_model(
 
     try:
         set_default_response = requests.post(
-            f"{API_SERVER_URL}/admin/llm/default",
+            f"{API_SERVER_URL}/admin/llm/provider/{provider_id}/default",
             headers=admin_user.headers,
-            json={"provider_id": provider_id, "model_name": model_name},
         )
         assert set_default_response.status_code == 200, (
             f"Setting default provider failed for provider={config.provider} "
@@ -427,9 +335,7 @@ def _create_and_test_provider_for_model(
             f"{set_default_response.text}"
         )
 
-        _ensure_provider_is_default(
-            provider_id=provider_id, model_name=model_name, admin_user=admin_user
-        )
+        _ensure_provider_is_default(provider_id=provider_id, admin_user=admin_user)
         _run_chat_assertions(
             admin_user=admin_user,
             search_tool_id=search_tool_id,

backend/tests/integration/tests/search_settings/test_search_settings.py

@@ -1,3 +1,4 @@
+import pytest
 import requests
 
 from tests.integration.common_utils.constants import API_SERVER_URL
@@ -364,6 +365,7 @@ def test_update_contextual_rag_missing_model_name(
     assert "Provider name and model name are required" in response.json()["detail"]
 
 
+@pytest.mark.skip(reason="Set new search settings is temporarily disabled.")
 def test_set_new_search_settings_with_contextual_rag(
     reset: None,  # noqa: ARG001
     admin_user: DATestUser,
@@ -392,6 +394,7 @@ def test_set_new_search_settings_with_contextual_rag(
     _cancel_new_embedding(admin_user)
 
 
+@pytest.mark.skip(reason="Set new search settings is temporarily disabled.")
 def test_set_new_search_settings_without_contextual_rag(
     reset: None,  # noqa: ARG001
     admin_user: DATestUser,
@@ -416,6 +419,7 @@ def test_set_new_search_settings_without_contextual_rag(
     _cancel_new_embedding(admin_user)
 
 
+@pytest.mark.skip(reason="Set new search settings is temporarily disabled.")
 def test_set_new_then_update_inference_settings(
     reset: None,  # noqa: ARG001
     admin_user: DATestUser,
@@ -453,6 +457,7 @@ def test_set_new_then_update_inference_settings(
     _cancel_new_embedding(admin_user)
 
 
+@pytest.mark.skip(reason="Set new search settings is temporarily disabled.")
 def test_set_new_search_settings_replaces_previous_secondary(
     reset: None,  # noqa: ARG001
     admin_user: DATestUser,

backend/tests/unit/onyx/onyxbot/test_slack_formatting.py

@@ -104,102 +104,3 @@ def test_format_slack_message_ampersand_not_double_escaped() -> None:
 
     assert "&" in formatted
     assert """ not in formatted
-
-
-# -- Table rendering tests --
-
-
-def test_table_renders_as_vertical_cards() -> None:
-    message = (
-        "| Feature | Status | Owner |\n"
-        "|---------|--------|-------|\n"
-        "| Auth | Done | Alice |\n"
-        "| Search | In Progress | Bob |\n"
-    )
-
-    formatted = format_slack_message(message)
-
-    assert "*Auth*\n  • Status: Done\n  • Owner: Alice" in formatted
-    assert "*Search*\n  • Status: In Progress\n  • Owner: Bob" in formatted
-    # Cards separated by blank line
-    assert "Owner: Alice\n\n*Search*" in formatted
-    # No raw pipe-and-dash table syntax
-    assert "---|" not in formatted
-
-
-def test_table_single_column() -> None:
-    message = "| Name |\n|------|\n| Alice |\n| Bob |\n"
-
-    formatted = format_slack_message(message)
-
-    assert "*Alice*" in formatted
-    assert "*Bob*" in formatted
-
-
-def test_table_embedded_in_text() -> None:
-    message = (
-        "Here are the results:\n\n"
-        "| Item | Count |\n"
-        "|------|-------|\n"
-        "| Apples | 5 |\n"
-        "\n"
-        "That's all."
-    )
-
-    formatted = format_slack_message(message)
-
-    assert "Here are the results:" in formatted
-    assert "*Apples*\n  • Count: 5" in formatted
-    assert "That's all." in formatted
-
-
-def test_table_with_formatted_cells() -> None:
-    message = (
-        "| Name | Link |\n"
-        "|------|------|\n"
-        "| **Alice** | [profile](https://example.com) |\n"
-    )
-
-    formatted = format_slack_message(message)
-
-    # Bold cell should not double-wrap: *Alice* not **Alice**
-    assert "*Alice*" in formatted
-    assert "**Alice**" not in formatted
-    assert "<https://example.com|profile>" in formatted
-
-
-def test_table_with_alignment_specifiers() -> None:
-    message = (
-        "| Left | Center | Right |\n" "|:-----|:------:|------:|\n" "| a | b | c |\n"
-    )
-
-    formatted = format_slack_message(message)
-
-    assert "*a*\n  • Center: b\n  • Right: c" in formatted
-
-
-def test_two_tables_in_same_message_use_independent_headers() -> None:
-    message = (
-        "| A | B |\n"
-        "|---|---|\n"
-        "| 1 | 2 |\n"
-        "\n"
-        "| X | Y | Z |\n"
-        "|---|---|---|\n"
-        "| p | q | r |\n"
-    )
-
-    formatted = format_slack_message(message)
-
-    assert "*1*\n  • B: 2" in formatted
-    assert "*p*\n  • Y: q\n  • Z: r" in formatted
-
-
-def test_table_empty_first_column_no_bare_asterisks() -> None:
-    message = "| Name | Status |\n" "|------|--------|\n" "| | Done |\n"
-
-    formatted = format_slack_message(message)
-
-    # Empty title should not produce "**" (bare asterisks)
-    assert "**" not in formatted
-    assert "  • Status: Done" in formatted

backend/tests/unit/onyx/tools/test_python_tool_availability.py

@@ -87,8 +87,7 @@ def test_python_tool_available_when_health_check_passes(
 
     mock_client = MagicMock()
     mock_client.health.return_value = True
-    mock_client_cls.return_value.__enter__ = MagicMock(return_value=mock_client)
-    mock_client_cls.return_value.__exit__ = MagicMock(return_value=False)
+    mock_client_cls.return_value = mock_client
 
     db_session = MagicMock(spec=Session)
     assert PythonTool.is_available(db_session) is True
@@ -110,8 +109,7 @@ def test_python_tool_unavailable_when_health_check_fails(
 
     mock_client = MagicMock()
     mock_client.health.return_value = False
-    mock_client_cls.return_value.__enter__ = MagicMock(return_value=mock_client)
-    mock_client_cls.return_value.__exit__ = MagicMock(return_value=False)
+    mock_client_cls.return_value = mock_client
 
     db_session = MagicMock(spec=Session)
     assert PythonTool.is_available(db_session) is False

deployment/docker_compose/docker-compose.multitenant-dev.yml

@@ -138,6 +138,7 @@ services:
       - indexing_model_server
     restart: unless-stopped
     environment:
+      - USE_LIGHTWEIGHT_BACKGROUND_WORKER=${USE_LIGHTWEIGHT_BACKGROUND_WORKER:-true}
       - ENABLE_PAID_ENTERPRISE_EDITION_FEATURES=true
       - MULTI_TENANT=true
       - LOG_LEVEL=DEBUG

deployment/docker_compose/docker-compose.prod-cloud.yml

@@ -52,6 +52,7 @@ services:
       - indexing_model_server
     restart: unless-stopped
     environment:
+      - USE_LIGHTWEIGHT_BACKGROUND_WORKER=${USE_LIGHTWEIGHT_BACKGROUND_WORKER:-true}
       - AUTH_TYPE=${AUTH_TYPE:-oidc}
       - POSTGRES_HOST=relational_db
       - VESPA_HOST=index

deployment/docker_compose/docker-compose.prod-no-letsencrypt.yml

@@ -65,6 +65,7 @@ services:
       - indexing_model_server
     restart: unless-stopped
     environment:
+      - USE_LIGHTWEIGHT_BACKGROUND_WORKER=${USE_LIGHTWEIGHT_BACKGROUND_WORKER:-true}
       - AUTH_TYPE=${AUTH_TYPE:-oidc}
       - POSTGRES_HOST=relational_db
       - VESPA_HOST=index

deployment/docker_compose/docker-compose.prod.yml

@@ -70,6 +70,7 @@ services:
       - indexing_model_server
     restart: unless-stopped
     environment:
+      - USE_LIGHTWEIGHT_BACKGROUND_WORKER=${USE_LIGHTWEIGHT_BACKGROUND_WORKER:-true}
       - AUTH_TYPE=${AUTH_TYPE:-oidc}
       - POSTGRES_HOST=relational_db
       - VESPA_HOST=index

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

@@ -58,6 +58,7 @@ services:
     env_file:
       - .env_eval
     environment:
+      - USE_LIGHTWEIGHT_BACKGROUND_WORKER=${USE_LIGHTWEIGHT_BACKGROUND_WORKER:-true}
       - AUTH_TYPE=disabled
       - POSTGRES_HOST=relational_db
       - VESPA_HOST=index

deployment/docker_compose/docker-compose.yml

@@ -146,6 +146,7 @@ services:
       - indexing_model_server
     restart: unless-stopped
     environment:
+      - USE_LIGHTWEIGHT_BACKGROUND_WORKER=${USE_LIGHTWEIGHT_BACKGROUND_WORKER:-true}
       - FILE_STORE_BACKEND=${FILE_STORE_BACKEND:-s3}
       - POSTGRES_HOST=${POSTGRES_HOST:-relational_db}
       - VESPA_HOST=${VESPA_HOST:-index}

deployment/docker_compose/install.sh

@@ -1,8 +1,8 @@
 #!/bin/bash
 
-set -euo pipefail
+set -e
 
-# Expected resource requirements (overridden below if --lite)
+# Expected resource requirements
 EXPECTED_DOCKER_RAM_GB=10
 EXPECTED_DISK_GB=32
 
@@ -10,10 +10,6 @@ EXPECTED_DISK_GB=32
 SHUTDOWN_MODE=false
 DELETE_DATA_MODE=false
 INCLUDE_CRAFT=false  # Disabled by default, use --include-craft to enable
-LITE_MODE=false       # Disabled by default, use --lite to enable
-NO_PROMPT=false
-DRY_RUN=false
-VERBOSE=false
 
 while [[ $# -gt 0 ]]; do
     case $1 in
@@ -29,22 +25,6 @@ while [[ $# -gt 0 ]]; do
             INCLUDE_CRAFT=true
             shift
             ;;
-        --lite)
-            LITE_MODE=true
-            shift
-            ;;
-        --no-prompt)
-            NO_PROMPT=true
-            shift
-            ;;
-        --dry-run)
-            DRY_RUN=true
-            shift
-            ;;
-        --verbose)
-            VERBOSE=true
-            shift
-            ;;
         --help|-h)
             echo "Onyx Installation Script"
             echo ""
@@ -52,21 +32,15 @@ while [[ $# -gt 0 ]]; do
             echo ""
             echo "Options:"
             echo "  --include-craft  Enable Onyx Craft (AI-powered web app building)"
-            echo "  --lite           Deploy Onyx Lite (no Vespa, Redis, or model servers)"
             echo "  --shutdown       Stop (pause) Onyx containers"
             echo "  --delete-data    Remove all Onyx data (containers, volumes, and files)"
-            echo "  --no-prompt      Run non-interactively with defaults (for CI/automation)"
-            echo "  --dry-run        Show what would be done without making changes"
-            echo "  --verbose        Show detailed output for debugging"
             echo "  --help, -h       Show this help message"
             echo ""
             echo "Examples:"
             echo "  $0                    # Install Onyx"
-            echo "  $0 --lite             # Install Onyx Lite (minimal deployment)"
             echo "  $0 --include-craft    # Install Onyx with Craft enabled"
             echo "  $0 --shutdown         # Pause Onyx services"
             echo "  $0 --delete-data      # Completely remove Onyx and all data"
-            echo "  $0 --no-prompt        # Non-interactive install with defaults"
             exit 0
             ;;
         *)
@@ -77,116 +51,8 @@ while [[ $# -gt 0 ]]; do
     esac
 done
 
-if [[ "$VERBOSE" = true ]]; then
-    set -x
-fi
-
-if [[ "$LITE_MODE" = true ]] && [[ "$INCLUDE_CRAFT" = true ]]; then
-    echo "ERROR: --lite and --include-craft cannot be used together."
-    echo "Craft requires services (Vespa, Redis, background workers) that lite mode disables."
-    exit 1
-fi
-
-# Lite mode needs far fewer resources (no Vespa, Redis, or model servers)
-if [[ "$LITE_MODE" = true ]]; then
-    EXPECTED_DOCKER_RAM_GB=4
-    EXPECTED_DISK_GB=16
-fi
-
 INSTALL_ROOT="${INSTALL_PREFIX:-onyx_data}"
 
-LITE_COMPOSE_FILE="docker-compose.onyx-lite.yml"
-
-# Build the -f flags for docker compose. For shutdown/delete-data we auto-detect
-# whether the lite overlay was previously downloaded; for install we use --lite.
-compose_file_args() {
-    local args="-f docker-compose.yml"
-    if [[ "$LITE_MODE" = true ]] || [[ -f "${INSTALL_ROOT}/deployment/${LITE_COMPOSE_FILE}" ]]; then
-        args="$args -f ${LITE_COMPOSE_FILE}"
-    fi
-    echo "$args"
-}
-
-# --- Temp file cleanup ---
-TMPFILES=()
-cleanup_tmpfiles() {
-    local f
-    for f in "${TMPFILES[@]:-}"; do
-        rm -rf "$f" 2>/dev/null || true
-    done
-}
-trap cleanup_tmpfiles EXIT
-
-mktempfile() {
-    local f
-    f="$(mktemp)"
-    TMPFILES+=("$f")
-    echo "$f"
-}
-
-# --- Downloader detection (curl with wget fallback) ---
-DOWNLOADER=""
-detect_downloader() {
-    if command -v curl &> /dev/null; then
-        DOWNLOADER="curl"
-        return 0
-    fi
-    if command -v wget &> /dev/null; then
-        DOWNLOADER="wget"
-        return 0
-    fi
-    echo "ERROR: Neither curl nor wget found. Please install one and retry."
-    exit 1
-}
-detect_downloader
-
-download_file() {
-    local url="$1"
-    local output="$2"
-    if [[ "$DOWNLOADER" == "curl" ]]; then
-        curl -fsSL --retry 3 --retry-delay 2 --retry-connrefused -o "$output" "$url"
-    else
-        wget -q --tries=3 --timeout=20 -O "$output" "$url"
-    fi
-}
-
-# --- Interactive prompt helpers ---
-is_interactive() {
-    [[ "$NO_PROMPT" = false ]] && [[ -t 0 ]]
-}
-
-prompt_or_default() {
-    local prompt_text="$1"
-    local default_value="$2"
-    if is_interactive; then
-        read -p "$prompt_text" -r REPLY
-        if [[ -z "$REPLY" ]]; then
-            REPLY="$default_value"
-        fi
-    else
-        REPLY="$default_value"
-    fi
-}
-
-prompt_yn_or_default() {
-    local prompt_text="$1"
-    local default_value="$2"
-    if is_interactive; then
-        read -p "$prompt_text" -n 1 -r
-        echo ""
-    else
-        REPLY="$default_value"
-    fi
-}
-
-prompt_enter_or_skip() {
-    local prompt_text="$1"
-    if is_interactive; then
-        echo -e "$prompt_text"
-        read -r
-    fi
-}
-
 # Colors for output
 RED='\033[0;31m'
 GREEN='\033[0;32m'
@@ -245,7 +111,7 @@ if [ "$SHUTDOWN_MODE" = true ]; then
             fi
 
             # Stop containers (without removing them)
-            (cd "${INSTALL_ROOT}/deployment" && $COMPOSE_CMD $(compose_file_args) stop)
+            (cd "${INSTALL_ROOT}/deployment" && $COMPOSE_CMD -f docker-compose.yml stop)
             if [ $? -eq 0 ]; then
                 print_success "Onyx containers stopped (paused)"
             else
@@ -274,17 +140,12 @@ if [ "$DELETE_DATA_MODE" = true ]; then
     echo "  • All downloaded files and configurations"
     echo "  • All user data and documents"
     echo ""
-    if is_interactive; then
-        read -p "Are you sure you want to continue? Type 'DELETE' to confirm: " -r
-        echo ""
-        if [ "$REPLY" != "DELETE" ]; then
-            print_info "Operation cancelled."
-            exit 0
-        fi
-    else
-        print_error "Cannot confirm destructive operation in non-interactive mode."
-        print_info "Run interactively or remove the ${INSTALL_ROOT} directory manually."
-        exit 1
+    read -p "Are you sure you want to continue? Type 'DELETE' to confirm: " -r
+    echo ""
+
+    if [ "$REPLY" != "DELETE" ]; then
+        print_info "Operation cancelled."
+        exit 0
     fi
 
     print_info "Removing Onyx containers and volumes..."
@@ -303,7 +164,7 @@ if [ "$DELETE_DATA_MODE" = true ]; then
             fi
 
             # Stop and remove containers with volumes
-            (cd "${INSTALL_ROOT}/deployment" && $COMPOSE_CMD $(compose_file_args) down -v)
+            (cd "${INSTALL_ROOT}/deployment" && $COMPOSE_CMD -f docker-compose.yml down -v)
             if [ $? -eq 0 ]; then
                 print_success "Onyx containers and volumes removed"
             else
@@ -337,13 +198,8 @@ echo " \____/|_| |_|\__, /_/\_\ "
 echo "               __/ |      "
 echo "              |___/       "
 echo -e "${NC}"
-if [[ "$LITE_MODE" = true ]]; then
-    echo "Welcome to Onyx Lite Installation Script"
-    echo "========================================="
-else
-    echo "Welcome to Onyx Installation Script"
-    echo "===================================="
-fi
+echo "Welcome to Onyx Installation Script"
+echo "===================================="
 echo ""
 
 # User acknowledgment section
@@ -351,14 +207,10 @@ echo -e "${YELLOW}${BOLD}This script will:${NC}"
 echo "1. Download deployment files for Onyx into a new '${INSTALL_ROOT}' directory"
 echo "2. Check your system resources (Docker, memory, disk space)"
 echo "3. Guide you through deployment options (version, authentication)"
-if [[ "$LITE_MODE" = true ]]; then
-    echo ""
-    echo -e "${YELLOW}${BOLD}Lite mode:${NC} Vespa, Redis, and model servers will NOT be started."
-    echo "This gives you the core chat experience with lower resource requirements."
-fi
 echo ""
 
-if is_interactive; then
+# Only prompt for acknowledgment if running interactively
+if [ -t 0 ]; then
     echo -e "${YELLOW}${BOLD}Please acknowledge and press Enter to continue...${NC}"
     read -r
     echo ""
@@ -367,26 +219,6 @@ else
     echo ""
 fi
 
-# Detect OS (including WSL)
-IS_WSL=false
-if [[ -n "${WSL_DISTRO_NAME:-}" ]] || grep -qi microsoft /proc/version 2>/dev/null; then
-    IS_WSL=true
-fi
-
-# Dry-run: show plan and exit
-if [[ "$DRY_RUN" = true ]]; then
-    print_info "Dry run mode — showing what would happen:"
-    echo "  • Install root: ${INSTALL_ROOT}"
-    echo "  • Lite mode: ${LITE_MODE}"
-    echo "  • Include Craft: ${INCLUDE_CRAFT}"
-    echo "  • OS type: ${OSTYPE:-unknown} (WSL: ${IS_WSL})"
-    echo "  • Downloader: ${DOWNLOADER}"
-    echo "  • Min RAM: ${EXPECTED_DOCKER_RAM_GB}GB, Min disk: ${EXPECTED_DISK_GB}GB"
-    echo ""
-    print_success "Dry run complete (no changes made)"
-    exit 0
-fi
-
 # GitHub repo base URL - using main branch
 GITHUB_RAW_URL="https://raw.githubusercontent.com/onyx-dot-app/onyx/main/deployment/docker_compose"
 
@@ -428,35 +260,41 @@ else
     exit 1
 fi
 
-# Returns 0 if $1 <= $2, 1 if $1 > $2
-# Handles missing or non-numeric parts gracefully (treats them as 0)
+# Function to compare version numbers
 version_compare() {
-    local version1="${1:-0.0.0}"
-    local version2="${2:-0.0.0}"
+    # Returns 0 if $1 <= $2, 1 if $1 > $2
+    local version1=$1
+    local version2=$2
 
-    local v1_major v1_minor v1_patch v2_major v2_minor v2_patch
-    v1_major=$(echo "$version1" | cut -d. -f1)
-    v1_minor=$(echo "$version1" | cut -d. -f2)
-    v1_patch=$(echo "$version1" | cut -d. -f3)
-    v2_major=$(echo "$version2" | cut -d. -f1)
-    v2_minor=$(echo "$version2" | cut -d. -f2)
-    v2_patch=$(echo "$version2" | cut -d. -f3)
+    # Split versions into components
+    local v1_major=$(echo $version1 | cut -d. -f1)
+    local v1_minor=$(echo $version1 | cut -d. -f2)
+    local v1_patch=$(echo $version1 | cut -d. -f3)
 
-    # Default non-numeric or empty parts to 0
-    [[ "$v1_major" =~ ^[0-9]+$ ]] || v1_major=0
-    [[ "$v1_minor" =~ ^[0-9]+$ ]] || v1_minor=0
-    [[ "$v1_patch" =~ ^[0-9]+$ ]] || v1_patch=0
-    [[ "$v2_major" =~ ^[0-9]+$ ]] || v2_major=0
-    [[ "$v2_minor" =~ ^[0-9]+$ ]] || v2_minor=0
-    [[ "$v2_patch" =~ ^[0-9]+$ ]] || v2_patch=0
+    local v2_major=$(echo $version2 | cut -d. -f1)
+    local v2_minor=$(echo $version2 | cut -d. -f2)
+    local v2_patch=$(echo $version2 | cut -d. -f3)
 
-    if [ "$v1_major" -lt "$v2_major" ]; then return 0
-    elif [ "$v1_major" -gt "$v2_major" ]; then return 1; fi
+    # Compare major version
+    if [ "$v1_major" -lt "$v2_major" ]; then
+        return 0
+    elif [ "$v1_major" -gt "$v2_major" ]; then
+        return 1
+    fi
 
-    if [ "$v1_minor" -lt "$v2_minor" ]; then return 0
-    elif [ "$v1_minor" -gt "$v2_minor" ]; then return 1; fi
+    # Compare minor version
+    if [ "$v1_minor" -lt "$v2_minor" ]; then
+        return 0
+    elif [ "$v1_minor" -gt "$v2_minor" ]; then
+        return 1
+    fi
 
-    [ "$v1_patch" -le "$v2_patch" ]
+    # Compare patch version
+    if [ "$v1_patch" -le "$v2_patch" ]; then
+        return 0
+    else
+        return 1
+    fi
 }
 
 # Check Docker daemon
@@ -533,7 +371,8 @@ if [ "$RESOURCE_WARNING" = true ]; then
     echo ""
     print_warning "Onyx recommends at least ${EXPECTED_DOCKER_RAM_GB}GB RAM and ${EXPECTED_DISK_GB}GB disk space for optimal performance."
     echo ""
-    prompt_yn_or_default "Do you want to continue anyway? (y/N): " "y"
+    read -p "Do you want to continue anyway? (y/N): " -n 1 -r
+    echo ""
     if [[ ! $REPLY =~ ^[Yy]$ ]]; then
         print_info "Installation cancelled. Please allocate more resources and try again."
         exit 1
@@ -558,9 +397,6 @@ print_info "This step downloads all necessary configuration files from GitHub...
 echo ""
 print_info "Downloading the following files:"
 echo "  • docker-compose.yml - Main Docker Compose configuration"
-if [[ "$LITE_MODE" = true ]]; then
-    echo "  • ${LITE_COMPOSE_FILE} - Lite mode overlay"
-fi
 echo "  • env.template - Environment variables template"
 echo "  • nginx/app.conf.template - Nginx web server configuration"
 echo "  • nginx/run-nginx.sh - Nginx startup script"
@@ -570,7 +406,7 @@ echo ""
 # Download Docker Compose file
 COMPOSE_FILE="${INSTALL_ROOT}/deployment/docker-compose.yml"
 print_info "Downloading docker-compose.yml..."
-if download_file "${GITHUB_RAW_URL}/docker-compose.yml" "$COMPOSE_FILE" 2>/dev/null; then
+if curl -fsSL -o "$COMPOSE_FILE" "${GITHUB_RAW_URL}/docker-compose.yml" 2>/dev/null; then
     print_success "Docker Compose file downloaded successfully"
 
     # Check if Docker Compose version is older than 2.24.0 and show warning
@@ -595,7 +431,8 @@ if download_file "${GITHUB_RAW_URL}/docker-compose.yml" "$COMPOSE_FILE" 2>/dev/n
         echo ""
         print_warning "The installation will continue, but may fail if Docker Compose cannot parse the file."
         echo ""
-        prompt_yn_or_default "Do you want to continue anyway? (y/N): " "y"
+        read -p "Do you want to continue anyway? (y/N): " -n 1 -r
+        echo ""
         if [[ ! $REPLY =~ ^[Yy]$ ]]; then
             print_info "Installation cancelled. Please upgrade Docker Compose or manually edit the docker-compose.yml file."
             exit 1
@@ -608,23 +445,10 @@ else
     exit 1
 fi
 
-# Download lite overlay if --lite was requested
-if [[ "$LITE_MODE" = true ]]; then
-    LITE_FILE="${INSTALL_ROOT}/deployment/${LITE_COMPOSE_FILE}"
-    print_info "Downloading ${LITE_COMPOSE_FILE} (lite overlay)..."
-    if download_file "${GITHUB_RAW_URL}/${LITE_COMPOSE_FILE}" "$LITE_FILE" 2>/dev/null; then
-        print_success "Lite overlay downloaded successfully"
-    else
-        print_error "Failed to download lite overlay"
-        print_info "Please ensure you have internet connection and try again"
-        exit 1
-    fi
-fi
-
 # Download env.template file
 ENV_TEMPLATE="${INSTALL_ROOT}/deployment/env.template"
 print_info "Downloading env.template..."
-if download_file "${GITHUB_RAW_URL}/env.template" "$ENV_TEMPLATE" 2>/dev/null; then
+if curl -fsSL -o "$ENV_TEMPLATE" "${GITHUB_RAW_URL}/env.template" 2>/dev/null; then
     print_success "Environment template downloaded successfully"
 else
     print_error "Failed to download env.template"
@@ -638,7 +462,7 @@ NGINX_BASE_URL="https://raw.githubusercontent.com/onyx-dot-app/onyx/main/deploym
 # Download app.conf.template
 NGINX_CONFIG="${INSTALL_ROOT}/data/nginx/app.conf.template"
 print_info "Downloading nginx configuration template..."
-if download_file "$NGINX_BASE_URL/app.conf.template" "$NGINX_CONFIG" 2>/dev/null; then
+if curl -fsSL -o "$NGINX_CONFIG" "$NGINX_BASE_URL/app.conf.template" 2>/dev/null; then
     print_success "Nginx configuration template downloaded"
 else
     print_error "Failed to download nginx configuration template"
@@ -649,7 +473,7 @@ fi
 # Download run-nginx.sh script
 NGINX_RUN_SCRIPT="${INSTALL_ROOT}/data/nginx/run-nginx.sh"
 print_info "Downloading nginx startup script..."
-if download_file "$NGINX_BASE_URL/run-nginx.sh" "$NGINX_RUN_SCRIPT" 2>/dev/null; then
+if curl -fsSL -o "$NGINX_RUN_SCRIPT" "$NGINX_BASE_URL/run-nginx.sh" 2>/dev/null; then
     chmod +x "$NGINX_RUN_SCRIPT"
     print_success "Nginx startup script downloaded and made executable"
 else
@@ -661,7 +485,7 @@ fi
 # Download README file
 README_FILE="${INSTALL_ROOT}/README.md"
 print_info "Downloading README.md..."
-if download_file "${GITHUB_RAW_URL}/README.md" "$README_FILE" 2>/dev/null; then
+if curl -fsSL -o "$README_FILE" "${GITHUB_RAW_URL}/README.md" 2>/dev/null; then
     print_success "README.md downloaded successfully"
 else
     print_error "Failed to download README.md"
@@ -689,7 +513,7 @@ if [ -d "${INSTALL_ROOT}/deployment" ] && [ -f "${INSTALL_ROOT}/deployment/docke
 
     if [ -n "$COMPOSE_CMD" ]; then
         # Check if any containers are running
-        RUNNING_CONTAINERS=$(cd "${INSTALL_ROOT}/deployment" && $COMPOSE_CMD $(compose_file_args) ps -q 2>/dev/null | wc -l)
+        RUNNING_CONTAINERS=$(cd "${INSTALL_ROOT}/deployment" && $COMPOSE_CMD -f docker-compose.yml ps -q 2>/dev/null | wc -l)
         if [ "$RUNNING_CONTAINERS" -gt 0 ]; then
             print_error "Onyx services are currently running!"
             echo ""
@@ -710,7 +534,7 @@ if [ -f "$ENV_FILE" ]; then
     echo "• Press Enter to restart with current configuration"
     echo "• Type 'update' to update to a newer version"
     echo ""
-    prompt_or_default "Choose an option [default: restart]: " ""
+    read -p "Choose an option [default: restart]: " -r
     echo ""
 
     if [ "$REPLY" = "update" ]; then
@@ -719,19 +543,22 @@ if [ -f "$ENV_FILE" ]; then
         echo "• Press Enter for latest (recommended)"
         echo "• Type a specific tag (e.g., v0.1.0)"
         echo ""
+        # If --include-craft was passed, default to craft-latest
         if [ "$INCLUDE_CRAFT" = true ]; then
-            prompt_or_default "Enter tag [default: craft-latest]: " "craft-latest"
-            VERSION="$REPLY"
+            read -p "Enter tag [default: craft-latest]: " -r VERSION
         else
-            prompt_or_default "Enter tag [default: latest]: " "latest"
-            VERSION="$REPLY"
+            read -p "Enter tag [default: latest]: " -r VERSION
         fi
         echo ""
 
-        if [ "$INCLUDE_CRAFT" = true ] && [ "$VERSION" = "craft-latest" ]; then
-            print_info "Selected: craft-latest (Craft enabled)"
-        elif [ "$VERSION" = "latest" ]; then
-            print_info "Selected: Latest version"
+        if [ -z "$VERSION" ]; then
+            if [ "$INCLUDE_CRAFT" = true ]; then
+                VERSION="craft-latest"
+                print_info "Selected: craft-latest (Craft enabled)"
+            else
+                VERSION="latest"
+                print_info "Selected: Latest version"
+            fi
         else
             print_info "Selected: $VERSION"
         fi
@@ -768,21 +595,23 @@ else
         echo "• Press Enter for craft-latest (recommended for Craft)"
         echo "• Type a specific tag (e.g., craft-v1.0.0)"
         echo ""
-        prompt_or_default "Enter tag [default: craft-latest]: " "craft-latest"
-        VERSION="$REPLY"
+        read -p "Enter tag [default: craft-latest]: " -r VERSION
     else
         echo "• Press Enter for latest (recommended)"
         echo "• Type a specific tag (e.g., v0.1.0)"
         echo ""
-        prompt_or_default "Enter tag [default: latest]: " "latest"
-        VERSION="$REPLY"
+        read -p "Enter tag [default: latest]: " -r VERSION
     fi
     echo ""
 
-    if [ "$INCLUDE_CRAFT" = true ] && [ "$VERSION" = "craft-latest" ]; then
-        print_info "Selected: craft-latest (Craft enabled)"
-    elif [ "$VERSION" = "latest" ]; then
-        print_info "Selected: Latest tag"
+    if [ -z "$VERSION" ]; then
+        if [ "$INCLUDE_CRAFT" = true ]; then
+            VERSION="craft-latest"
+            print_info "Selected: craft-latest (Craft enabled)"
+        else
+            VERSION="latest"
+            print_info "Selected: Latest tag"
+        fi
     else
         print_info "Selected: $VERSION"
     fi
@@ -857,13 +686,6 @@ else
     echo ""
 fi
 
-# Reject craft image tags when running in lite mode
-if [[ "$LITE_MODE" = true ]] && [[ "${VERSION:-}" == craft-* ]]; then
-    print_error "Cannot use a craft image tag (${VERSION}) with --lite."
-    print_info "Craft requires services (Vespa, Redis, background workers) that lite mode disables."
-    exit 1
-fi
-
 # Function to check if a port is available
 is_port_available() {
     local port=$1
@@ -949,7 +771,7 @@ print_step "Pulling Docker images"
 print_info "This may take several minutes depending on your internet connection..."
 echo ""
 print_info "Downloading Docker images (this may take a while)..."
-(cd "${INSTALL_ROOT}/deployment" && $COMPOSE_CMD $(compose_file_args) pull --quiet)
+(cd "${INSTALL_ROOT}/deployment" && $COMPOSE_CMD -f docker-compose.yml pull --quiet)
 if [ $? -eq 0 ]; then
     print_success "Docker images downloaded successfully"
 else
@@ -963,9 +785,9 @@ print_info "Launching containers..."
 echo ""
 if [ "$USE_LATEST" = true ]; then
     print_info "Force pulling latest images and recreating containers..."
-    (cd "${INSTALL_ROOT}/deployment" && $COMPOSE_CMD $(compose_file_args) up -d --pull always --force-recreate)
+    (cd "${INSTALL_ROOT}/deployment" && $COMPOSE_CMD -f docker-compose.yml up -d --pull always --force-recreate)
 else
-    (cd "${INSTALL_ROOT}/deployment" && $COMPOSE_CMD $(compose_file_args) up -d)
+    (cd "${INSTALL_ROOT}/deployment" && $COMPOSE_CMD -f docker-compose.yml up -d)
 fi
 if [ $? -ne 0 ]; then
     print_error "Failed to start Onyx services"
@@ -987,7 +809,7 @@ echo ""
 # Check for restart loops
 print_info "Checking container health status..."
 RESTART_ISSUES=false
-CONTAINERS=$(cd "${INSTALL_ROOT}/deployment" && $COMPOSE_CMD $(compose_file_args) ps -q 2>/dev/null)
+CONTAINERS=$(cd "${INSTALL_ROOT}/deployment" && $COMPOSE_CMD -f docker-compose.yml ps -q 2>/dev/null)
 
 for CONTAINER in $CONTAINERS; do
     PROJECT_NAME="$(basename "$INSTALL_ROOT")_deployment_"
@@ -1016,7 +838,7 @@ if [ "$RESTART_ISSUES" = true ]; then
     print_error "Some containers are experiencing issues!"
     echo ""
     print_info "Please check the logs for more information:"
-    echo "  (cd \"${INSTALL_ROOT}/deployment\" && $COMPOSE_CMD $(compose_file_args) logs)"
+    echo "  (cd \"${INSTALL_ROOT}/deployment\" && $COMPOSE_CMD -f docker-compose.yml logs)"
 
     echo ""
     print_info "If the issue persists, please contact: founders@onyx.app"
@@ -1035,12 +857,8 @@ check_onyx_health() {
     echo ""
 
     while [ $attempt -le $max_attempts ]; do
-        local http_code=""
-        if [[ "$DOWNLOADER" == "curl" ]]; then
-            http_code=$(curl -s -o /dev/null -w "%{http_code}" "http://localhost:$port" 2>/dev/null || echo "000")
-        else
-            http_code=$(wget -q --spider -S "http://localhost:$port" 2>&1 | grep "HTTP/" | tail -1 | awk '{print $2}' || echo "000")
-        fi
+        # Check for successful HTTP responses (200, 301, 302, etc.)
+        local http_code=$(curl -s -o /dev/null -w "%{http_code}" "http://localhost:$port")
         if echo "$http_code" | grep -qE "^(200|301|302|303|307|308)$"; then
             return 0
         fi
@@ -1096,18 +914,6 @@ print_info "If authentication is enabled, you can create your admin account here
 echo "   • Visit http://localhost:${HOST_PORT}/auth/signup to create your admin account"
 echo "   • The first user created will automatically have admin privileges"
 echo ""
-if [[ "$LITE_MODE" = true ]]; then
-    echo ""
-    print_info "Running in Lite mode — the following services are NOT started:"
-    echo "  • Vespa (vector database)"
-    echo "  • Redis (cache)"
-    echo "  • Model servers (embedding/inference)"
-    echo "  • Background workers (Celery)"
-    echo ""
-    print_info "Connectors and RAG search are disabled. LLM chat, tools, user file"
-    print_info "uploads, Projects, Agent knowledge, and code interpreter still work."
-fi
-echo ""
 print_info "Refer to the README in the ${INSTALL_ROOT} directory for more information."
 echo ""
 print_info "For help or issues, contact: founders@onyx.app"

desktop/README.md

@@ -14,32 +14,30 @@ Built with [Tauri](https://tauri.app) for minimal bundle size (~10MB vs Electron
 
 ## Keyboard Shortcuts
 
-| Shortcut | Action           |
-| -------- | ---------------- |
-| `⌘ N`    | New Chat         |
-| `⌘ ⇧ N`  | New Window       |
-| `⌘ R`    | Reload           |
-| `⌘ [`    | Go Back          |
-| `⌘ ]`    | Go Forward       |
-| `⌘ ,`    | Open Config File |
-| `⌘ W`    | Close Window     |
-| `⌘ Q`    | Quit             |
+| Shortcut | Action |
+|----------|--------|
+| `⌘ N` | New Chat |
+| `⌘ ⇧ N` | New Window |
+| `⌘ R` | Reload |
+| `⌘ [` | Go Back |
+| `⌘ ]` | Go Forward |
+| `⌘ ,` | Open Config File |
+| `⌘ W` | Close Window |
+| `⌘ Q` | Quit |
 
 ## Prerequisites
 
 1. **Rust** (latest stable)
-
    ```bash
    curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh
    source $HOME/.cargo/env
    ```
 
 2. **Node.js** (18+)
-
    ```bash
    # Using homebrew
    brew install node
-
+   
    # Or using nvm
    nvm install 18
    ```
@@ -57,21 +55,16 @@ npm install
 
 # Run in development mode
 npm run dev
-
-# Run in debug mode
-npm run debug
 ```
 
 ## Building
 
 ### Build for current architecture
-
 ```bash
 npm run build
 ```
 
 ### Build Universal Binary (Intel + Apple Silicon)
-
 ```bash
 # First, add the targets
 rustup target add x86_64-apple-darwin
@@ -110,7 +103,6 @@ Before building, add your app icons to `src-tauri/icons/`:
 - `icon.ico` (Windows, optional)
 
 You can generate these from a 1024x1024 source image using:
-
 ```bash
 # Using tauri's icon generator
 npm run tauri icon path/to/your-icon.png
@@ -123,7 +115,6 @@ npm run tauri icon path/to/your-icon.png
 The app defaults to `https://cloud.onyx.app` but supports any Onyx instance.
 
 **Config file location:**
-
 - macOS: `~/Library/Application Support/app.onyx.desktop/config.json`
 - Linux: `~/.config/app.onyx.desktop/config.json`
 - Windows: `%APPDATA%/app.onyx.desktop/config.json`
@@ -144,7 +135,6 @@ The app defaults to `https://cloud.onyx.app` but supports any Onyx instance.
 4. Restart the app
 
 **Quick edit via terminal:**
-
 ```bash
 # macOS
 open -t ~/Library/Application\ Support/app.onyx.desktop/config.json
@@ -156,7 +146,6 @@ code ~/Library/Application\ Support/app.onyx.desktop/config.json
 ### Change the default URL in build
 
 Edit `src-tauri/tauri.conf.json`:
-
 ```json
 {
   "app": {
@@ -176,7 +165,6 @@ Edit `src-tauri/src/main.rs` in the `setup_shortcuts` function.
 ### Window appearance
 
 Modify the window configuration in `src-tauri/tauri.conf.json`:
-
 - `titleBarStyle`: `"Overlay"` (macOS native) or `"Visible"`
 - `decorations`: Window chrome
 - `transparent`: For custom backgrounds
@@ -184,20 +172,16 @@ Modify the window configuration in `src-tauri/tauri.conf.json`:
 ## Troubleshooting
 
 ### "Unable to resolve host"
-
 Make sure you have an internet connection. The app loads content from `cloud.onyx.app`.
 
 ### Build fails on M1/M2 Mac
-
 ```bash
 # Ensure you have the right target
 rustup target add aarch64-apple-darwin
 ```
 
 ### Code signing for distribution
-
 For distributing outside the App Store, you'll need to:
-
 1. Get an Apple Developer certificate
 2. Sign the app: `codesign --deep --force --sign "Developer ID" target/release/bundle/macos/Onyx.app`
 3. Notarize with Apple

desktop/package.json

@@ -4,7 +4,6 @@
   "description": "Lightweight desktop app for Onyx Cloud",
   "scripts": {
     "dev": "tauri dev",
-    "debug": "tauri dev -- -- --debug",
     "build": "tauri build",
     "build:dmg": "tauri build --target universal-apple-darwin",
     "build:linux": "tauri build --bundles deb,rpm"

desktop/src-tauri/Cargo.toml

@@ -23,4 +23,3 @@ url = "2.5"
 [features]
 default = ["custom-protocol"]
 custom-protocol = ["tauri/custom-protocol"]
-devtools = ["tauri/devtools"]

desktop/src-tauri/src/main.rs

@@ -6,9 +6,7 @@ use serde::{Deserialize, Serialize};
 use std::fs;
 use std::path::PathBuf;
 use std::process::Command;
-use std::sync::{Mutex, RwLock};
-use std::io::Write as IoWrite;
-use std::time::SystemTime;
+use std::sync::RwLock;
 #[cfg(target_os = "macos")]
 use std::time::Duration;
 use tauri::image::Image;
@@ -232,63 +230,6 @@ const MENU_KEY_HANDLER_SCRIPT: &str = r#"
 })();
 "#;
 
-const CONSOLE_CAPTURE_SCRIPT: &str = r#"
-(() => {
-  if (window.__ONYX_CONSOLE_CAPTURE__) return;
-  window.__ONYX_CONSOLE_CAPTURE__ = true;
-
-  const levels = ['log', 'warn', 'error', 'info', 'debug'];
-  const originals = {};
-
-  levels.forEach(level => {
-    originals[level] = console[level];
-    console[level] = function(...args) {
-      originals[level].apply(console, args);
-      try {
-        const invoke =
-          window.__TAURI__?.core?.invoke || window.__TAURI_INTERNALS__?.invoke;
-        if (typeof invoke === 'function') {
-          const message = args.map(a => {
-            try { return typeof a === 'string' ? a : JSON.stringify(a); }
-            catch { return String(a); }
-          }).join(' ');
-          invoke('log_from_frontend', { level, message });
-        }
-      } catch {}
-    };
-  });
-
-  window.addEventListener('error', (event) => {
-    try {
-      const invoke =
-        window.__TAURI__?.core?.invoke || window.__TAURI_INTERNALS__?.invoke;
-      if (typeof invoke === 'function') {
-        invoke('log_from_frontend', {
-          level: 'error',
-          message: `[uncaught] ${event.message} at ${event.filename}:${event.lineno}:${event.colno}`
-        });
-      }
-    } catch {}
-  });
-
-  window.addEventListener('unhandledrejection', (event) => {
-    try {
-      const invoke =
-        window.__TAURI__?.core?.invoke || window.__TAURI_INTERNALS__?.invoke;
-      if (typeof invoke === 'function') {
-        invoke('log_from_frontend', {
-          level: 'error',
-          message: `[unhandled rejection] ${event.reason}`
-        });
-      }
-    } catch {}
-  });
-})();
-"#;
-
-const MENU_TOGGLE_DEVTOOLS_ID: &str = "toggle_devtools";
-const MENU_OPEN_DEBUG_LOG_ID: &str = "open_debug_log";
-
 #[derive(Debug, Clone, Serialize, Deserialize)]
 pub struct AppConfig {
     pub server_url: String,
@@ -370,87 +311,12 @@ fn save_config(config: &AppConfig) -> Result<(), String> {
     Ok(())
 }
 
-// ============================================================================
-// Debug Mode
-// ============================================================================
-
-fn is_debug_mode() -> bool {
-    std::env::args().any(|arg| arg == "--debug") || std::env::var("ONYX_DEBUG").is_ok()
-}
-
-fn get_debug_log_path() -> Option<PathBuf> {
-    get_config_dir().map(|dir| dir.join("frontend_debug.log"))
-}
-
-fn init_debug_log_file() -> Option<fs::File> {
-    let log_path = get_debug_log_path()?;
-    if let Some(parent) = log_path.parent() {
-        let _ = fs::create_dir_all(parent);
-    }
-    fs::OpenOptions::new()
-        .create(true)
-        .append(true)
-        .open(&log_path)
-        .ok()
-}
-
-fn format_utc_timestamp() -> String {
-    let now = SystemTime::now()
-        .duration_since(SystemTime::UNIX_EPOCH)
-        .unwrap_or_default();
-    let total_secs = now.as_secs();
-    let millis = now.subsec_millis();
-
-    let days = total_secs / 86400;
-    let secs_of_day = total_secs % 86400;
-    let hours = secs_of_day / 3600;
-    let mins = (secs_of_day % 3600) / 60;
-    let secs = secs_of_day % 60;
-
-    // Days since Unix epoch -> Y/M/D via civil calendar arithmetic
-    let z = days as i64 + 719468;
-    let era = z / 146097;
-    let doe = z - era * 146097;
-    let yoe = (doe - doe / 1460 + doe / 36524 - doe / 146096) / 365;
-    let y = yoe + era * 400;
-    let doy = doe - (365 * yoe + yoe / 4 - yoe / 100);
-    let mp = (5 * doy + 2) / 153;
-    let d = doy - (153 * mp + 2) / 5 + 1;
-    let m = if mp < 10 { mp + 3 } else { mp - 9 };
-    let y = if m <= 2 { y + 1 } else { y };
-
-    format!(
-        "{:04}-{:02}-{:02}T{:02}:{:02}:{:02}.{:03}Z",
-        y, m, d, hours, mins, secs, millis
-    )
-}
-
-fn inject_console_capture(webview: &Webview) {
-    let _ = webview.eval(CONSOLE_CAPTURE_SCRIPT);
-}
-
-fn maybe_open_devtools(app: &AppHandle, window: &tauri::WebviewWindow) {
-    #[cfg(any(debug_assertions, feature = "devtools"))]
-    {
-        let state = app.state::<ConfigState>();
-        if state.debug_mode {
-            window.open_devtools();
-        }
-    }
-    #[cfg(not(any(debug_assertions, feature = "devtools")))]
-    {
-        let _ = (app, window);
-    }
-}
-
 // Global config state
 struct ConfigState {
     config: RwLock<AppConfig>,
     config_initialized: RwLock<bool>,
     app_base_url: RwLock<Option<Url>>,
     menu_temporarily_visible: RwLock<bool>,
-    debug_mode: bool,
-    debug_log_file: Mutex<Option<fs::File>>,
 }
 
 fn focus_main_window(app: &AppHandle) {
@@ -506,7 +372,6 @@ fn trigger_new_window(app: &AppHandle) {
             }
 
             apply_settings_to_window(&handle, &window);
-            maybe_open_devtools(&handle, &window);
             let _ = window.set_focus();
         }
     });
@@ -602,65 +467,10 @@ fn inject_chat_link_intercept(webview: &Webview) {
     let _ = webview.eval(CHAT_LINK_INTERCEPT_SCRIPT);
 }
 
-fn handle_toggle_devtools(app: &AppHandle) {
-    #[cfg(any(debug_assertions, feature = "devtools"))]
-    {
-        let windows: Vec<_> = app.webview_windows().into_values().collect();
-        let any_open = windows.iter().any(|w| w.is_devtools_open());
-        for window in &windows {
-            if any_open {
-                window.close_devtools();
-            } else {
-                window.open_devtools();
-            }
-        }
-    }
-    #[cfg(not(any(debug_assertions, feature = "devtools")))]
-    {
-        let _ = app;
-    }
-}
-
-fn handle_open_debug_log() {
-    let log_path = match get_debug_log_path() {
-        Some(p) => p,
-        None => return,
-    };
-
-    if !log_path.exists() {
-        eprintln!("[ONYX DEBUG] Log file does not exist yet: {:?}", log_path);
-        return;
-    }
-
-    let url_path = log_path.to_string_lossy().replace('\\', "/");
-    let _ = open_in_default_browser(&format!(
-        "file:///{}",
-        url_path.trim_start_matches('/')
-    ));
-}
-
 // ============================================================================
 // Tauri Commands
 // ============================================================================
 
-#[tauri::command]
-fn log_from_frontend(level: String, message: String, state: tauri::State<ConfigState>) {
-    if !state.debug_mode {
-        return;
-    }
-    let timestamp = format_utc_timestamp();
-    let log_line = format!("[{}] [{}] {}", timestamp, level.to_uppercase(), message);
-
-    eprintln!("{}", log_line);
-
-    if let Ok(mut guard) = state.debug_log_file.lock() {
-        if let Some(ref mut file) = *guard {
-            let _ = writeln!(file, "{}", log_line);
-            let _ = file.flush();
-        }
-    }
-}
-
 /// Get the current server URL
 #[tauri::command]
 fn get_server_url(state: tauri::State<ConfigState>) -> String {
@@ -847,7 +657,6 @@ async fn new_window(app: AppHandle, state: tauri::State<'_, ConfigState>) -> Res
     }
 
     apply_settings_to_window(&app, &window);
-    maybe_open_devtools(&app, &window);
 
     Ok(())
 }
@@ -1127,30 +936,6 @@ fn setup_app_menu(app: &AppHandle) -> tauri::Result<()> {
         menu.append(&help_menu)?;
     }
 
-    let state = app.state::<ConfigState>();
-    if state.debug_mode {
-        let toggle_devtools_item = MenuItem::with_id(
-            app,
-            MENU_TOGGLE_DEVTOOLS_ID,
-            "Toggle DevTools",
-            true,
-            Some("F12"),
-        )?;
-        let open_log_item = MenuItem::with_id(
-            app,
-            MENU_OPEN_DEBUG_LOG_ID,
-            "Open Debug Log",
-            true,
-            None::<&str>,
-        )?;
-
-        let debug_menu = SubmenuBuilder::new(app, "Debug")
-            .item(&toggle_devtools_item)
-            .item(&open_log_item)
-            .build()?;
-        menu.append(&debug_menu)?;
-    }
-
     app.set_menu(menu)?;
     Ok(())
 }
@@ -1242,20 +1027,8 @@ fn setup_tray_icon(app: &AppHandle) -> tauri::Result<()> {
 // ============================================================================
 
 fn main() {
+    // Load config at startup
     let (config, config_initialized) = load_config();
-    let debug_mode = is_debug_mode();
-
-    let debug_log_file = if debug_mode {
-        eprintln!("[ONYX DEBUG] Debug mode enabled");
-        if let Some(path) = get_debug_log_path() {
-            eprintln!("[ONYX DEBUG] Frontend logs: {}", path.display());
-        }
-        eprintln!("[ONYX DEBUG] DevTools will open automatically");
-        eprintln!("[ONYX DEBUG] Capturing console.log/warn/error/info/debug from webview");
-        init_debug_log_file()
-    } else {
-        None
-    };
 
     tauri::Builder::default()
         .plugin(tauri_plugin_shell::init())
@@ -1286,8 +1059,6 @@ fn main() {
             config_initialized: RwLock::new(config_initialized),
             app_base_url: RwLock::new(None),
             menu_temporarily_visible: RwLock::new(false),
-            debug_mode,
-            debug_log_file: Mutex::new(debug_log_file),
         })
         .invoke_handler(tauri::generate_handler![
             get_server_url,
@@ -1306,8 +1077,7 @@ fn main() {
             start_drag_window,
             toggle_menu_bar,
             show_menu_bar_temporarily,
-            hide_menu_bar_temporary,
-            log_from_frontend
+            hide_menu_bar_temporary
         ])
         .on_menu_event(|app, event| match event.id().as_ref() {
             "open_docs" => open_docs(),
@@ -1316,8 +1086,6 @@ fn main() {
             "open_settings" => open_settings(app),
             "show_menu_bar" => handle_menu_bar_toggle(app),
             "hide_window_decorations" => handle_decorations_toggle(app),
-            MENU_TOGGLE_DEVTOOLS_ID => handle_toggle_devtools(app),
-            MENU_OPEN_DEBUG_LOG_ID => handle_open_debug_log(),
             _ => {}
         })
         .setup(move |app| {
@@ -1351,7 +1119,6 @@ fn main() {
                 inject_titlebar(window.clone());
 
                 apply_settings_to_window(&app_handle, &window);
-                maybe_open_devtools(&app_handle, &window);
 
                 let _ = window.set_focus();
             }
@@ -1361,14 +1128,6 @@ fn main() {
         .on_page_load(|webview: &Webview, _payload: &PageLoadPayload| {
             inject_chat_link_intercept(webview);
 
-            {
-                let app = webview.app_handle();
-                let state = app.state::<ConfigState>();
-                if state.debug_mode {
-                    inject_console_capture(webview);
-                }
-            }
-
             #[cfg(not(target_os = "macos"))]
             {
                 let _ = webview.eval(MENU_KEY_HANDLER_SCRIPT);

uv.lock

@@ -4106,7 +4106,7 @@ wheels = [
 
 [[package]]
 name = "nltk"
-version = "3.9.3"
+version = "3.9.1"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "click" },
@@ -4114,9 +4114,9 @@ dependencies = [
     { name = "regex" },
     { name = "tqdm" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/e1/8f/915e1c12df07c70ed779d18ab83d065718a926e70d3ea33eb0cd66ffb7c0/nltk-3.9.3.tar.gz", hash = "sha256:cb5945d6424a98d694c2b9a0264519fab4363711065a46aa0ae7a2195b92e71f", size = 2923673, upload-time = "2026-02-24T12:05:53.833Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/3c/87/db8be88ad32c2d042420b6fd9ffd4a149f9a0d7f0e86b3f543be2eeeedd2/nltk-3.9.1.tar.gz", hash = "sha256:87d127bd3de4bd89a4f81265e5fa59cb1b199b27440175370f7417d2bc7ae868", size = 2904691, upload-time = "2024-08-18T19:48:37.769Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/c2/7e/9af5a710a1236e4772de8dfcc6af942a561327bb9f42b5b4a24d0cf100fd/nltk-3.9.3-py3-none-any.whl", hash = "sha256:60b3db6e9995b3dd976b1f0fa7dec22069b2677e759c28eb69b62ddd44870522", size = 1525385, upload-time = "2026-02-24T12:05:46.54Z" },
+    { url = "https://files.pythonhosted.org/packages/4d/66/7d9e26593edda06e8cb531874633f7c2372279c3b0f46235539fe546df8b/nltk-3.9.1-py3-none-any.whl", hash = "sha256:4fa26829c5b00715afe3061398a8989dc643b92ce7dd93fb4585a70930d168a1", size = 1505442, upload-time = "2024-08-18T19:48:21.909Z" },
 ]
 
 [[package]]

web/jest.config.js

@@ -143,7 +143,6 @@ module.exports = {
         "**/src/app/**/utils/*.test.ts",
         "**/src/app/**/hooks/*.test.ts", // Pure packet processor tests
         "**/src/refresh-components/**/*.test.ts",
-        "**/src/sections/**/*.test.ts",
         // Add more patterns here as you add more unit tests
       ],
     },
@@ -157,8 +156,6 @@ module.exports = {
         "**/src/components/**/*.test.tsx",
         "**/src/lib/**/*.test.tsx",
         "**/src/refresh-components/**/*.test.tsx",
-        "**/src/hooks/**/*.test.tsx",
-        "**/src/sections/**/*.test.tsx",
         // Add more patterns here as you add more integration tests
       ],
     },

web/lib/opal/src/core/index.ts

@@ -11,8 +11,6 @@ export {
   Interactive,
   type InteractiveBaseProps,
   type InteractiveBaseVariantProps,
-  type InteractiveBaseSidebarVariantProps,
-  type InteractiveBaseSidebarProminenceTypes,
   type InteractiveContainerProps,
   type InteractiveContainerRoundingVariant,
 } from "@opal/core/interactive/components";

web/lib/opal/src/core/interactive/README.md

@@ -104,44 +104,6 @@ The foundational layer for all clickable surfaces in the design system. Defines
 | **Active** | `action-link-05` | `action-link-05` |
 | **Disabled** | `action-link-03` | `action-link-03` |
 
-### Sidebar (unselected)
-
-> No CSS `:active` state — only hover/transient and selected.
-
-**Background**
-
-| | Light |
-|---|---|
-| **Rest** | `transparent` |
-| **Hover / Transient** | `background-tint-03` |
-| **Disabled** | `transparent` |
-
-**Foreground**
-
-| | Light |
-|---|---|
-| **Rest** | `text-03` |
-| **Hover / Transient** | `text-04` |
-| **Disabled** | `text-01` |
-
-### Sidebar (selected)
-
-> Completely static — hover and transient have no effect.
-
-**Background**
-
-| | Light |
-|---|---|
-| **All states** | `background-tint-00` |
-| **Disabled** | `transparent` |
-
-**Foreground**
-
-| | Light |
-|---|---|
-| **All states** | `text-03` (icon: `text-02`) |
-| **Disabled** | `text-01` |
-
 ## Sub-components
 
 | Sub-component | Role |

web/lib/opal/src/core/interactive/components.tsx

@@ -1,5 +1,3 @@
-import Link from "next/link";
-import type { Route } from "next";
 import "@opal/core/interactive/styles.css";
 import React from "react";
 import { Slot } from "@radix-ui/react-slot";
@@ -28,28 +26,18 @@ type InteractiveBaseSelectVariantProps = {
   selected?: boolean;
 };
 
-type InteractiveBaseSidebarProminenceTypes = "light";
-type InteractiveBaseSidebarVariantProps = {
-  variant: "sidebar";
-  prominence?: InteractiveBaseSidebarProminenceTypes;
-  selected?: boolean;
-};
-
 /**
  * Discriminated union tying `variant` to `prominence`.
  *
  * - `"none"` accepts no prominence (`prominence` must not be provided)
  * - `"select"` accepts an optional prominence (defaults to `"light"`) and
  *   an optional `selected` boolean that switches foreground to action-link colours
- * - `"sidebar"` accepts an optional prominence (defaults to `"light"`) and
- *   an optional `selected` boolean for the focused/active-item state
  * - `"default"`, `"action"`, and `"danger"` accept an optional prominence
  *   (defaults to `"primary"`)
  */
 type InteractiveBaseVariantProps =
   | { variant?: "none"; prominence?: never; selected?: never }
   | InteractiveBaseSelectVariantProps
-  | InteractiveBaseSidebarVariantProps
   | {
       variant?: InteractiveBaseVariantTypes;
       prominence?: InteractiveBaseProminenceTypes;
@@ -230,8 +218,7 @@ function InteractiveBase({
   ...props
 }: InteractiveBaseProps) {
   const effectiveProminence =
-    prominence ??
-    (variant === "select" || variant === "sidebar" ? "light" : "primary");
+    prominence ?? (variant === "select" ? "light" : "primary");
   const classes = cn(
     "interactive",
     !props.onClick && !href && "!cursor-default !select-auto",
@@ -430,9 +417,9 @@ function InteractiveContainer({
   // so all styling (backgrounds, rounding, overflow) lives on one element.
   if (href) {
     return (
-      <Link
+      <a
         ref={ref as React.Ref<HTMLAnchorElement>}
-        href={href as Route}
+        href={href}
         target={target}
         rel={rel}
         {...(sharedProps as React.HTMLAttributes<HTMLAnchorElement>)}
@@ -495,8 +482,6 @@ export {
   type InteractiveBaseProps,
   type InteractiveBaseVariantProps,
   type InteractiveBaseSelectVariantProps,
-  type InteractiveBaseSidebarVariantProps,
-  type InteractiveBaseSidebarProminenceTypes,
   type InteractiveContainerProps,
   type InteractiveContainerRoundingVariant,
 };

web/lib/opal/src/core/interactive/styles.css

@@ -419,23 +419,3 @@
   ) {
   @apply bg-background-tint-00;
 }
-
-/* ---------------------------------------------------------------------------
-   Sidebar + Light
-   --------------------------------------------------------------------------- */
-.interactive[data-interactive-base-variant="sidebar"][data-interactive-base-prominence="light"] {
-  @apply bg-transparent;
-}
-.interactive[data-interactive-base-variant="sidebar"][data-interactive-base-prominence="light"]:hover:not(
-    [data-disabled]
-  ),
-.interactive[data-interactive-base-variant="sidebar"][data-interactive-base-prominence="light"][data-transient="true"]:not(
-    [data-disabled]
-  ) {
-  @apply bg-background-tint-03;
-}
-.interactive[data-interactive-base-variant="sidebar"][data-interactive-base-prominence="light"][data-selected="true"]:not(
-    [data-disabled]
-  ) {
-  @apply bg-background-tint-00;
-}

web/lib/opal/src/icons/column.tsx

@@ -1,22 +0,0 @@
-import type { IconProps } from "@opal/types";
-
-const SvgColumn = ({ size, ...props }: IconProps) => (
-  <svg
-    width={size}
-    height={size}
-    viewBox="0 0 16 16"
-    fill="none"
-    xmlns="http://www.w3.org/2000/svg"
-    stroke="currentColor"
-    {...props}
-  >
-    <path
-      d="M6 14H3.33333C2.59695 14 2 13.403 2 12.6667V3.33333C2 2.59695 2.59695 2 3.33333 2H6M6 14V2M6 14H10M6 2H10M10 2H12.6667C13.403 2 14 2.59695 14 3.33333V12.6667C14 13.403 13.403 14 12.6667 14H10M10 2V14"
-      strokeWidth={1.5}
-      strokeLinecap="round"
-      strokeLinejoin="round"
-    />
-  </svg>
-);
-
-export default SvgColumn;

web/lib/opal/src/icons/handle.tsx

@@ -1,20 +0,0 @@
-import type { IconProps } from "@opal/types";
-
-const SvgHandle = ({ size = 16, ...props }: IconProps) => (
-  <svg
-    width={Math.round((size * 3) / 17)}
-    height={size}
-    viewBox="0 0 3 17"
-    fill="none"
-    xmlns="http://www.w3.org/2000/svg"
-    {...props}
-  >
-    <path
-      d="M0.5 0.5V16.5M2.5 0.5V16.5"
-      stroke="currentColor"
-      strokeLinecap="round"
-    />
-  </svg>
-);
-
-export default SvgHandle;

web/lib/opal/src/icons/index.ts

@@ -49,7 +49,6 @@ export { default as SvgClock } from "@opal/icons/clock";
 export { default as SvgClockHandsSmall } from "@opal/icons/clock-hands-small";
 export { default as SvgCloud } from "@opal/icons/cloud";
 export { default as SvgCode } from "@opal/icons/code";
-export { default as SvgColumn } from "@opal/icons/column";
 export { default as SvgCopy } from "@opal/icons/copy";
 export { default as SvgCornerRightUpDot } from "@opal/icons/corner-right-up-dot";
 export { default as SvgCpu } from "@opal/icons/cpu";
@@ -80,7 +79,6 @@ export { default as SvgFolderPartialOpen } from "@opal/icons/folder-partial-open
 export { default as SvgFolderPlus } from "@opal/icons/folder-plus";
 export { default as SvgGemini } from "@opal/icons/gemini";
 export { default as SvgGlobe } from "@opal/icons/globe";
-export { default as SvgHandle } from "@opal/icons/handle";
 export { default as SvgHardDrive } from "@opal/icons/hard-drive";
 export { default as SvgHashSmall } from "@opal/icons/hash-small";
 export { default as SvgHash } from "@opal/icons/hash";
@@ -148,8 +146,6 @@ export { default as SvgSlack } from "@opal/icons/slack";
 export { default as SvgSlash } from "@opal/icons/slash";
 export { default as SvgSliders } from "@opal/icons/sliders";
 export { default as SvgSlidersSmall } from "@opal/icons/sliders-small";
-export { default as SvgSort } from "@opal/icons/sort";
-export { default as SvgSortOrder } from "@opal/icons/sort-order";
 export { default as SvgSparkle } from "@opal/icons/sparkle";
 export { default as SvgStar } from "@opal/icons/star";
 export { default as SvgStep1 } from "@opal/icons/step1";
@@ -173,7 +169,6 @@ export { default as SvgUploadCloud } from "@opal/icons/upload-cloud";
 export { default as SvgUser } from "@opal/icons/user";
 export { default as SvgUserManage } from "@opal/icons/user-manage";
 export { default as SvgUserPlus } from "@opal/icons/user-plus";
-export { default as SvgUserSync } from "@opal/icons/user-sync";
 export { default as SvgUsers } from "@opal/icons/users";
 export { default as SvgWallet } from "@opal/icons/wallet";
 export { default as SvgWorkflow } from "@opal/icons/workflow";

web/lib/opal/src/icons/sort-order.tsx

@@ -1,21 +0,0 @@
-import type { IconProps } from "@opal/types";
-
-const SvgSortOrder = ({ size, ...props }: IconProps) => (
-  <svg
-    width={size}
-    height={size}
-    viewBox="0 0 16 16"
-    fill="none"
-    xmlns="http://www.w3.org/2000/svg"
-    stroke="currentColor"
-    {...props}
-  >
-    <path
-      d="M2.66675 12L7.67009 12.0001M2.66675 8H10.5001M2.66675 4H13.3334"
-      strokeWidth={1.5}
-      strokeLinecap="round"
-      strokeLinejoin="round"
-    />
-  </svg>
-);
-export default SvgSortOrder;

web/lib/opal/src/icons/sort.tsx

@@ -1,27 +0,0 @@
-import type { IconProps } from "@opal/types";
-
-const SvgSort = ({ size, ...props }: IconProps) => (
-  <svg
-    width={size}
-    height={size}
-    viewBox="0 0 16 16"
-    fill="none"
-    xmlns="http://www.w3.org/2000/svg"
-    stroke="currentColor"
-    {...props}
-  >
-    <path
-      d="M2 4.5H10M2 8H7M2 11.5H5"
-      strokeWidth={1.5}
-      strokeLinecap="round"
-      strokeLinejoin="round"
-    />
-    <path
-      d="M12 5V12M12 12L14 10M12 12L10 10"
-      strokeWidth={1.5}
-      strokeLinecap="round"
-      strokeLinejoin="round"
-    />
-  </svg>
-);
-export default SvgSort;

web/lib/opal/src/icons/user-sync.tsx

@@ -1,22 +0,0 @@
-import type { IconProps } from "@opal/types";
-
-const SvgUserSync = ({ size, ...props }: IconProps) => (
-  <svg
-    width={size}
-    height={size}
-    viewBox="0 0 16 16"
-    fill="none"
-    xmlns="http://www.w3.org/2000/svg"
-    stroke="currentColor"
-    {...props}
-  >
-    <path
-      d="M1 14C1 13.6667 1 13.3333 1 13C1 11.3431 2.34316 10 4.00002 10H7M11 8.5L9.5 10L14.5 9.99985M13 14L14.5 12.5L9.5 12.5M8.75 4.75C8.75 6.26878 7.51878 7.5 6 7.5C4.48122 7.5 3.25 6.26878 3.25 4.75C3.25 3.23122 4.48122 2 6 2C7.51878 2 8.75 3.23122 8.75 4.75Z"
-      strokeWidth={1.5}
-      strokeLinecap="round"
-      strokeLinejoin="round"
-    />
-  </svg>
-);
-
-export default SvgUserSync;

web/lib/opal/src/layouts/Content/ContentSm.tsx

@@ -9,7 +9,7 @@ import { cn } from "@opal/utils";
 
 type ContentSmSizePreset = "main-content" | "main-ui" | "secondary";
 type ContentSmOrientation = "vertical" | "inline" | "reverse";
-type ContentSmProminence = "default" | "muted" | "muted-2x";
+type ContentSmProminence = "default" | "muted";
 
 interface ContentSmPresetConfig {
   /** Icon width/height (CSS value). */
@@ -82,12 +82,13 @@ function ContentSm({
   prominence = "default",
 }: ContentSmProps) {
   const config = CONTENT_SM_PRESETS[sizePreset];
+  const titleColorClass =
+    prominence === "muted" ? "text-text-03" : "text-text-04";
 
   return (
     <div
       className="opal-content-sm"
       data-orientation={orientation}
-      data-prominence={prominence}
       style={{ gap: config.gap }}
     >
       {Icon && (
@@ -99,14 +100,18 @@ function ContentSm({
           style={{ minHeight: config.lineHeight }}
         >
           <Icon
-            className="opal-content-sm-icon"
+            className="opal-content-sm-icon text-text-03"
             style={{ width: config.iconSize, height: config.iconSize }}
           />
         </div>
       )}
 
       <span
-        className={cn("opal-content-sm-title", config.titleFont)}
+        className={cn(
+          "opal-content-sm-title",
+          config.titleFont,
+          titleColorClass
+        )}
         style={{ height: config.lineHeight }}
       >
         {title}

web/lib/opal/src/layouts/Content/styles.css

@@ -323,7 +323,7 @@
      reverse : flex-row-reverse — title left, icon right
 
    Icon color is always text-03. Title color varies by prominence
-   (text-04 default, text-03 muted, text-02 muted-2x) via data-prominence.
+   (text-04 default, text-03 muted) and is applied via Tailwind class.
    =========================================================================== */
 
 /* ---------------------------------------------------------------------------
@@ -331,8 +331,7 @@
    --------------------------------------------------------------------------- */
 
 .opal-content-sm {
-  /* since `ContentSm` doesn't have a description, it's possible to center-align the icon and text */
-  @apply flex items-center;
+  @apply flex items-start;
 }
 
 .opal-content-sm[data-orientation="inline"] {
@@ -357,31 +356,15 @@
   justify-content: center;
 }
 
-.opal-content-sm-icon {
-  @apply text-text-03;
-}
-
-.opal-content-sm[data-prominence="muted-2x"] .opal-content-sm-icon {
-  @apply text-text-02 stroke-text-02;
-}
-
 /* ---------------------------------------------------------------------------
    Title
    --------------------------------------------------------------------------- */
 
 .opal-content-sm-title {
-  @apply text-left overflow-hidden text-text-04 truncate;
+  @apply text-left overflow-hidden;
   display: -webkit-box;
   -webkit-box-orient: vertical;
   -webkit-line-clamp: 1;
   padding: 0 0.125rem;
   min-width: 0.0625rem;
 }
-
-.opal-content-sm[data-prominence="muted"] .opal-content-sm-title {
-  @apply text-text-03;
-}
-
-.opal-content-sm[data-prominence="muted-2x"] .opal-content-sm-title {
-  @apply text-text-02;
-}

web/lib/opal/src/layouts/IllustrationContent/README.md

@@ -1,87 +0,0 @@
-# IllustrationContent
-
-**Import:** `import { IllustrationContent, type IllustrationContentProps } from "@opal/layouts";`
-
-A vertically-stacked, center-aligned layout for empty states, error pages, and informational placeholders. Pairs a large illustration with a title and optional description.
-
-## Why IllustrationContent?
-
-Empty states and placeholder screens share a recurring pattern: a large illustration centered above a title and description. `IllustrationContent` standardises that pattern so every empty state looks consistent without hand-rolling flex containers and spacing each time.
-
-## Layout Structure
-
-```
-┌─────────────────────────────────┐
-│          (1.25rem pad)          │
-│     ┌───────────────────┐       │
-│     │   illustration    │       │
-│     │   7.5rem × 7.5rem │       │
-│     └───────────────────┘       │
-│         (0.75rem gap)           │
-│          title (center)         │
-│         (0.75rem gap)           │
-│      description (center)       │
-│          (1.25rem pad)          │
-└─────────────────────────────────┘
-```
-
-- Outer container: `flex flex-col items-center gap-3 p-5 text-center`.
-- Illustration: `w-[7.5rem] h-[7.5rem]` (120px), no extra padding.
-- Title: `<p>` with `font-main-content-emphasis text-text-04`.
-- Description: `<p>` with `font-secondary-body text-text-03`.
-
-## Props
-
-| Prop | Type | Default | Description |
-|---|---|---|---|
-| `illustration` | `IconFunctionComponent` | — | Optional illustration component rendered at 7.5rem × 7.5rem, centered. Works with any `@opal/illustrations` SVG. |
-| `title` | `string` | **(required)** | Main title text, center-aligned. |
-| `description` | `string` | — | Optional description below the title, center-aligned. |
-
-## Usage Examples
-
-### Empty search results
-
-```tsx
-import { IllustrationContent } from "@opal/layouts";
-import SvgNoResult from "@opal/illustrations/no-result";
-
-<IllustrationContent
-  illustration={SvgNoResult}
-  title="No results found"
-  description="Try adjusting your search or filters."
-/>
-```
-
-### Not found page
-
-```tsx
-import { IllustrationContent } from "@opal/layouts";
-import SvgNotFound from "@opal/illustrations/not-found";
-
-<IllustrationContent
-  illustration={SvgNotFound}
-  title="Page not found"
-  description="The page you're looking for doesn't exist or has been moved."
-/>
-```
-
-### Title only (no illustration, no description)
-
-```tsx
-import { IllustrationContent } from "@opal/layouts";
-
-<IllustrationContent title="Nothing here yet" />
-```
-
-### Empty state with illustration and title (no description)
-
-```tsx
-import { IllustrationContent } from "@opal/layouts";
-import SvgEmpty from "@opal/illustrations/empty";
-
-<IllustrationContent
-  illustration={SvgEmpty}
-  title="No items"
-/>
-```

web/lib/opal/src/layouts/IllustrationContent/components.tsx

@@ -1,84 +0,0 @@
-import type { IconFunctionComponent } from "@opal/types";
-
-// ---------------------------------------------------------------------------
-// Types
-// ---------------------------------------------------------------------------
-
-interface IllustrationContentProps {
-  /** Optional illustration rendered at 7.5rem × 7.5rem (120px), centered. */
-  illustration?: IconFunctionComponent;
-
-  /** Main title text, center-aligned. Uses `font-main-content-emphasis`. */
-  title: string;
-
-  /** Optional description below the title, center-aligned. Uses `font-secondary-body`. */
-  description?: string;
-}
-
-// ---------------------------------------------------------------------------
-// IllustrationContent
-// ---------------------------------------------------------------------------
-
-/**
- * A vertically-stacked, center-aligned layout for empty states, error pages,
- * and informational placeholders.
- *
- * Renders an optional illustration on top, followed by a title and an optional
- * description — all center-aligned with consistent spacing.
- *
- * **Layout structure:**
- *
- * ```
- * ┌─────────────────────────────────┐
- * │          (1.25rem pad)          │
- * │     ┌───────────────────┐       │
- * │     │   illustration    │       │
- * │     │   7.5rem × 7.5rem │       │
- * │     └───────────────────┘       │
- * │         (0.75rem gap)           │
- * │          title (center)         │
- * │      description (center)       │
- * │          (1.25rem pad)          │
- * └─────────────────────────────────┘
- * ```
- *
- * @example
- * ```tsx
- * import { IllustrationContent } from "@opal/layouts";
- * import SvgNoResult from "@opal/illustrations/no-result";
- *
- * <IllustrationContent
- *   illustration={SvgNoResult}
- *   title="No results found"
- *   description="Try adjusting your search or filters."
- * />
- * ```
- */
-function IllustrationContent({
-  illustration: Illustration,
-  title,
-  description,
-}: IllustrationContentProps) {
-  return (
-    <div className="flex flex-col items-center gap-3 p-5 text-center">
-      {Illustration && (
-        <Illustration
-          aria-hidden="true"
-          className="shrink-0 w-[7.5rem] h-[7.5rem]"
-        />
-      )}
-      <div className="flex flex-col items-center text-center">
-        <p className="font-main-content-emphasis text-text-04">{title}</p>
-        {description && (
-          <p className="font-secondary-body text-text-03">{description}</p>
-        )}
-      </div>
-    </div>
-  );
-}
-
-// ---------------------------------------------------------------------------
-// Exports
-// ---------------------------------------------------------------------------
-
-export { IllustrationContent, type IllustrationContentProps };

web/lib/opal/src/layouts/README.md

@@ -1,8 +1,8 @@
 # @opal/layouts
 
-**Import:** `import { Content, ContentAction, IllustrationContent } from "@opal/layouts";`
+**Import:** `import { Content, ContentAction } from "@opal/layouts";`
 
-Layout primitives for composing content blocks. These components handle sizing, font selection, icon alignment, and optional inline editing — things that are tedious to get right by hand and easy to get wrong.
+Layout primitives for composing icon + title + description rows. These components handle sizing, font selection, icon alignment, and optional inline editing — things that are tedious to get right by hand and easy to get wrong.
 
 ## Components
 
@@ -10,15 +10,13 @@ Layout primitives for composing content blocks. These components handle sizing,
 |---|---|---|
 | [`Content`](./Content/README.md) | Icon + title + description row. Routes to an internal layout (`ContentXl`, `ContentLg`, `ContentMd`, or `ContentSm`) based on `sizePreset` and `variant`. | [Content README](./Content/README.md) |
 | [`ContentAction`](./ContentAction/README.md) | Wraps `Content` in a flex-row with an optional `rightChildren` slot for action buttons. Adds padding alignment via the shared `SizeVariant` scale. | [ContentAction README](./ContentAction/README.md) |
-| [`IllustrationContent`](./IllustrationContent/README.md) | Center-aligned illustration + title + description stack for empty states, error pages, and placeholders. | [IllustrationContent README](./IllustrationContent/README.md) |
 
 ## Quick Start
 
 ```tsx
-import { Content, ContentAction, IllustrationContent } from "@opal/layouts";
+import { Content, ContentAction } from "@opal/layouts";
 import { Button } from "@opal/components";
 import SvgSettings from "@opal/icons/settings";
-import SvgNoResult from "@opal/illustrations/no-result";
 
 // Simple heading
 <Content
@@ -51,13 +49,6 @@ import SvgNoResult from "@opal/illustrations/no-result";
     <Button icon={SvgSettings} prominence="tertiary" />
   }
 />
-
-// Empty state with illustration
-<IllustrationContent
-  illustration={SvgNoResult}
-  title="No results found"
-  description="Try adjusting your search or filters."
-/>
 ```
 
 ## Architecture
@@ -83,12 +74,10 @@ From `@opal/layouts`:
 // Components
 Content
 ContentAction
-IllustrationContent
 
 // Types
 ContentProps
 ContentActionProps
-IllustrationContentProps
 SizePreset
 ContentVariant
 ```

web/lib/opal/src/layouts/index.ts

@@ -11,9 +11,3 @@ export {
   ContentAction,
   type ContentActionProps,
 } from "@opal/layouts/ContentAction/components";
-
-/* IllustrationContent */
-export {
-  IllustrationContent,
-  type IllustrationContentProps,
-} from "@opal/layouts/IllustrationContent/components";

web/package-lock.json

@@ -48,6 +48,7 @@
         "cmdk": "^1.0.0",
         "cookies-next": "^5.1.0",
         "date-fns": "^3.6.0",
+        "docx-preview": "^0.3.7",
         "favicon-fetch": "^1.0.0",
         "formik": "^2.2.9",
         "highlight.js": "^11.11.1",
@@ -7958,6 +7959,15 @@
         "node": ">=0.10.0"
       }
     },
+    "node_modules/docx-preview": {
+      "version": "0.3.7",
+      "resolved": "https://registry.npmjs.org/docx-preview/-/docx-preview-0.3.7.tgz",
+      "integrity": "sha512-Lav69CTA/IYZPJTsKH7oYeoZjyg96N0wEJMNslGJnZJ+dMUZK85Lt5ASC79yUlD48ecWjuv+rkcmFt6EVPV0Xg==",
+      "license": "Apache-2.0",
+      "dependencies": {
+        "jszip": ">=3.0.0"
+      }
+    },
     "node_modules/dom-accessibility-api": {
       "version": "0.6.3",
       "dev": true,

web/package.json

@@ -64,6 +64,7 @@
     "cmdk": "^1.0.0",
     "cookies-next": "^5.1.0",
     "date-fns": "^3.6.0",
+    "docx-preview": "^0.3.7",
     "favicon-fetch": "^1.0.0",
     "formik": "^2.2.9",
     "highlight.js": "^11.11.1",

web/playwright.config.ts

@@ -41,7 +41,7 @@ export default defineConfig({
         viewport: { width: 1280, height: 720 },
         storageState: "admin_auth.json",
       },
-      grepInvert: [/@exclusive/, /@lite/],
+      grepInvert: /@exclusive/,
     },
     {
       // this suite runs independently and serially + slower
@@ -55,15 +55,5 @@ export default defineConfig({
       grep: /@exclusive/,
       workers: 1,
     },
-    {
-      // runs against the Onyx Lite stack (DISABLE_VECTOR_DB=true, no Vespa/Redis)
-      name: "lite",
-      use: {
-        ...devices["Desktop Chrome"],
-        viewport: { width: 1280, height: 720 },
-        storageState: "admin_auth.json",
-      },
-      grep: /@lite/,
-    },
   ],
 });

web/src/app/admin/add-connector/page.tsx

@@ -2,7 +2,7 @@
 import * as SettingsLayouts from "@/layouts/settings-layouts";
 import { SourceCategory, SourceMetadata } from "@/lib/search/interfaces";
 import { listSourceMetadata } from "@/lib/sources";
-import { Button } from "@opal/components";
+import Button from "@/refresh-components/buttons/Button";
 import {
   useCallback,
   useContext,
@@ -254,7 +254,9 @@ export default function Page() {
         icon={route.icon}
         title={route.title}
         rightChildren={
-          <Button href="/admin/indexing/status">See Connectors</Button>
+          <Button href="/admin/indexing/status" primary>
+            See Connectors
+          </Button>
         }
         separator
       />

web/src/app/admin/agents/PersonaTable.tsx

@@ -16,8 +16,9 @@ import {
 } from "./lib";
 import { FiEdit2 } from "react-icons/fi";
 import { useUser } from "@/providers/UserProvider";
-import { Button } from "@opal/components";
+import { Button as OpalButton } from "@opal/components";
 import ConfirmationModalLayout from "@/refresh-components/layouts/ConfirmationModalLayout";
+import Button from "@/refresh-components/buttons/Button";
 import { SvgAlertCircle, SvgTrash } from "@opal/icons";
 import type { Route } from "next";
 
@@ -299,7 +300,7 @@ export function PersonasTable({
               <div key="edit" className="flex">
                 <div className="mr-auto my-auto">
                   {!persona.builtin_persona && isEditable ? (
-                    <Button
+                    <OpalButton
                       icon={SvgTrash}
                       prominence="tertiary"
                       onClick={() => openDeleteModal(persona)}

web/src/app/admin/api-key/OnyxApiKeyForm.tsx

@@ -2,7 +2,7 @@ import { Form, Formik } from "formik";
 import { toast } from "@/hooks/useToast";
 import { createApiKey, updateApiKey } from "./lib";
 import Modal from "@/refresh-components/Modal";
-import { Button } from "@opal/components";
+import Button from "@/refresh-components/buttons/Button";
 import Text from "@/refresh-components/texts/Text";
 import InputTypeIn from "@/refresh-components/inputs/InputTypeIn";
 import InputComboBox from "@/refresh-components/inputs/InputComboBox";

web/src/app/admin/api-key/page.tsx

@@ -27,7 +27,7 @@ import {
   DISCORD_SERVICE_API_KEY_NAME,
 } from "@/app/admin/api-key/types";
 import CreateButton from "@/refresh-components/buttons/CreateButton";
-import { Button } from "@opal/components";
+import Button from "@/refresh-components/buttons/Button";
 import CopyIconButton from "@/refresh-components/buttons/CopyIconButton";
 import Text from "@/refresh-components/texts/Text";
 import { SvgEdit, SvgKey, SvgRefreshCw } from "@opal/icons";
@@ -161,11 +161,11 @@ function Main() {
                 <TableRow key={apiKey.api_key_id}>
                   <TableCell>
                     <Button
-                      prominence="internal"
+                      internal
                       onClick={() => handleEdit(apiKey)}
-                      icon={SvgEdit}
+                      leftIcon={SvgEdit}
                     >
-                      {apiKey.api_key_name || "null"}
+                      {apiKey.api_key_name || <i>null</i>}
                     </Button>
                   </TableCell>
                   <TableCell className="max-w-64">
@@ -176,8 +176,8 @@ function Main() {
                   </TableCell>
                   <TableCell>
                     <Button
-                      prominence="internal"
-                      icon={SvgRefreshCw}
+                      internal
+                      leftIcon={SvgRefreshCw}
                       onClick={async () => {
                         setKeyIsGenerating(true);
                         const response = await regenerateApiKey(apiKey);

web/src/app/admin/billing/BillingDetailsView.tsx

@@ -7,7 +7,6 @@ import { Content } from "@opal/layouts";
 import * as InputLayouts from "@/layouts/input-layouts";
 import Card from "@/refresh-components/cards/Card";
 import Button from "@/refresh-components/buttons/Button";
-import { Button as OpalButton } from "@opal/components";
 import Text from "@/refresh-components/texts/Text";
 import Message from "@/refresh-components/messages/Message";
 import InfoBlock from "@/refresh-components/messages/InfoBlock";
@@ -245,20 +244,25 @@ function SubscriptionCard({
               to make changes.
             </Text>
           ) : disabled ? (
-            <OpalButton
-              prominence="secondary"
+            <Button
+              main
+              secondary
               onClick={handleReconnect}
               rightIcon={SvgArrowRight}
               disabled={isReconnecting}
             >
               {isReconnecting ? "Connecting..." : "Connect to Stripe"}
-            </OpalButton>
+            </Button>
           ) : (
-            <OpalButton onClick={handleManagePlan} rightIcon={SvgExternalLink}>
+            <Button
+              main
+              primary
+              onClick={handleManagePlan}
+              rightIcon={SvgExternalLink}
+            >
               Manage Plan
-            </OpalButton>
+            </Button>
           )}
-          {/* TODO(@raunakab): migrate to opal Button once className/iconClassName is resolved */}
           <Button tertiary onClick={onViewPlans} className="billing-text-link">
             <Text secondaryBody text03>
               View Plan Details
@@ -375,13 +379,9 @@ function SeatsCard({
             sizePreset="main-content"
             variant="section"
           />
-          <OpalButton
-            prominence="secondary"
-            onClick={handleCancel}
-            disabled={isSubmitting}
-          >
+          <Button main secondary onClick={handleCancel} disabled={isSubmitting}>
             Cancel
-          </OpalButton>
+          </Button>
         </Section>
 
         <div className="billing-content-area">
@@ -463,14 +463,16 @@ function SeatsCard({
               No changes to your billing.
             </Text>
           )}
-          <OpalButton
+          <Button
+            main
+            primary
             onClick={handleConfirm}
             disabled={
               isSubmitting || newSeatCount === totalSeats || isBelowMinimum
             }
           >
             {isSubmitting ? "Saving..." : "Confirm Change"}
-          </OpalButton>
+          </Button>
         </Section>
       </Card>
     );
@@ -500,22 +502,19 @@ function SeatsCard({
           height="auto"
           width="auto"
         >
-          <OpalButton
-            prominence="tertiary"
-            href="/admin/users"
-            icon={SvgExternalLink}
-          >
+          <Button main tertiary href="/admin/users" leftIcon={SvgExternalLink}>
             View Users
-          </OpalButton>
+          </Button>
           {!hideUpdateSeats && (
-            <OpalButton
-              prominence="secondary"
+            <Button
+              main
+              secondary
               onClick={handleStartEdit}
-              icon={SvgPlus}
+              leftIcon={SvgPlus}
               disabled={isLoadingUsers || disabled || !billing}
             >
               Update Seats
-            </OpalButton>
+            </Button>
           )}
         </Section>
       </Section>
@@ -567,13 +566,14 @@ function PaymentSection({ billing }: { billing: BillingInformation }) {
                 title="Visa ending in 1234"
                 description="Payment method"
               />
-              <OpalButton
-                prominence="tertiary"
+              <Button
+                main
+                tertiary
                 onClick={handleOpenPortal}
                 rightIcon={SvgExternalLink}
               >
                 Update
-              </OpalButton>
+              </Button>
             </Section>
           </Card>
           {lastPaymentDate && (
@@ -589,13 +589,14 @@ function PaymentSection({ billing }: { billing: BillingInformation }) {
                   title={lastPaymentDate}
                   description="Last payment"
                 />
-                <OpalButton
-                  prominence="tertiary"
+                <Button
+                  main
+                  tertiary
                   onClick={handleOpenPortal}
                   rightIcon={SvgExternalLink}
                 >
                   View Invoice
-                </OpalButton>
+                </Button>
               </Section>
             </Card>
           )}

web/src/app/admin/billing/CheckoutView.tsx

@@ -3,7 +3,7 @@
 import { useState, useMemo, useEffect } from "react";
 import { Section } from "@/layouts/general-layouts";
 import * as InputLayouts from "@/layouts/input-layouts";
-import { Button } from "@opal/components";
+import Button from "@/refresh-components/buttons/Button";
 import Text from "@/refresh-components/texts/Text";
 import Card from "@/refresh-components/cards/Card";
 import Separator from "@/refresh-components/Separator";
@@ -176,7 +176,7 @@ export default function CheckoutView({ onAdjustPlan }: CheckoutViewProps) {
             Business
           </Text>
         </Section>
-        <Button prominence="secondary" onClick={onAdjustPlan}>
+        <Button secondary onClick={onAdjustPlan}>
           Adjust Plan
         </Button>
       </Section>
@@ -262,7 +262,7 @@ export default function CheckoutView({ onAdjustPlan }: CheckoutViewProps) {
           // Empty div to maintain space-between alignment
           <div></div>
         )}
-        <Button onClick={handleSubmit} disabled={isSubmitting}>
+        <Button main primary onClick={handleSubmit} disabled={isSubmitting}>
           {isSubmitting ? "Loading..." : "Continue to Payment"}
         </Button>
       </Section>

web/src/app/admin/billing/LicenseActivationCard.tsx

@@ -2,7 +2,7 @@
 
 import { useState } from "react";
 import Card from "@/refresh-components/cards/Card";
-import { Button } from "@opal/components";
+import Button from "@/refresh-components/buttons/Button";
 import Text from "@/refresh-components/texts/Text";
 import InputFile from "@/refresh-components/inputs/InputFile";
 import { Section } from "@/layouts/general-layouts";
@@ -119,11 +119,11 @@ export default function LicenseActivationCard({
             </Text>
           </Section>
           <Section flexDirection="row" gap={0.5} height="auto" width="auto">
-            <Button prominence="secondary" onClick={() => setShowInput(true)}>
+            <Button main secondary onClick={() => setShowInput(true)}>
               Update Key
             </Button>
             {!hideClose && (
-              <Button prominence="tertiary" onClick={handleClose}>
+              <Button main tertiary onClick={handleClose}>
                 Close
               </Button>
             )}
@@ -146,11 +146,7 @@ export default function LicenseActivationCard({
           <Text headingH3>
             {hasLicense ? "Update License Key" : "Activate License Key"}
           </Text>
-          <Button
-            prominence="secondary"
-            onClick={handleClose}
-            disabled={isActivating}
-          >
+          <Button secondary onClick={handleClose} disabled={isActivating}>
             Cancel
           </Button>
         </Section>
@@ -223,6 +219,8 @@ export default function LicenseActivationCard({
       {/* Footer */}
       <Section flexDirection="row" justifyContent="end" padding={1}>
         <Button
+          main
+          primary
           onClick={handleActivate}
           disabled={isActivating || !licenseKey.trim() || success}
         >

web/src/app/admin/billing/PlansView.tsx

@@ -21,7 +21,6 @@ import "@/app/admin/billing/billing.css";
 import type { IconProps } from "@opal/types";
 import Card from "@/refresh-components/cards/Card";
 import Button from "@/refresh-components/buttons/Button";
-import { Button as OpalButton } from "@opal/components";
 import Text from "@/refresh-components/texts/Text";
 import { Section } from "@/layouts/general-layouts";
 
@@ -147,27 +146,26 @@ function PlanCard({
         {/* Button */}
         <div className="plan-card-button">
           {isCurrentPlan ? (
-            // TODO(@raunakab): migrate to opal Button once className/iconClassName is resolved
             <Button tertiary transient className="pointer-events-none">
               <Text mainUiAction text03>
                 Your Current Plan
               </Text>
             </Button>
           ) : href ? (
-            <OpalButton
-              prominence="secondary"
+            <Button
+              main
+              secondary
               href={href}
               target="_blank"
               rel="noopener noreferrer"
             >
               {buttonLabel}
-            </OpalButton>
+            </Button>
           ) : onClick ? (
-            <OpalButton onClick={onClick} icon={ButtonIcon}>
+            <Button main primary onClick={onClick} leftIcon={ButtonIcon}>
               {buttonLabel}
-            </OpalButton>
+            </Button>
           ) : (
-            // TODO(@raunakab): migrate to opal Button once className/iconClassName is resolved
             <Button tertiary transient className="pointer-events-none">
               <Text mainUiAction text03>
                 Included in your plan

web/src/app/admin/billing/page.tsx

@@ -66,7 +66,6 @@ function FooterLinks({
           <Text secondaryBody text03>
             Have a license key?
           </Text>
-          {/* TODO(@raunakab): migrate to opal Button once className/iconClassName is resolved */}
           <Button action tertiary onClick={onActivateLicense}>
             <Text secondaryBody text05 className="underline">
               {licenseText}
@@ -74,7 +73,6 @@ function FooterLinks({
           </Button>
         </>
       )}
-      {/* TODO(@raunakab): migrate to opal Button once className/iconClassName is resolved */}
       <Button
         action
         tertiary

web/src/app/admin/bots/SlackBotUpdateForm.tsx

@@ -10,7 +10,7 @@ import { SourceIcon } from "@/components/SourceIcon";
 import { EditableStringFieldDisplay } from "@/components/EditableStringFieldDisplay";
 import { deleteSlackBot } from "./new/lib";
 import GenericConfirmModal from "@/components/modals/GenericConfirmModal";
-import { Button } from "@opal/components";
+import Button from "@/refresh-components/buttons/Button";
 import { cn } from "@/lib/utils";
 import { SvgChevronDownSmall, SvgTrash } from "@opal/icons";
 
@@ -106,20 +106,20 @@ export const ExistingSlackBotForm = ({
         <div className="flex flex-col" ref={dropdownRef}>
           <div className="flex items-center gap-4">
             <Button
-              prominence="secondary"
-              icon={({ className }) => (
+              leftIcon={({ className }) => (
                 <SvgChevronDownSmall
                   className={cn(className, !isExpanded && "-rotate-90")}
                 />
               )}
               onClick={() => setIsExpanded(!isExpanded)}
+              secondary
             >
               Update Tokens
             </Button>
             <Button
-              variant="danger"
+              danger
               onClick={() => setShowDeleteModal(true)}
-              icon={SvgTrash}
+              leftIcon={SvgTrash}
             >
               Delete
             </Button>

web/src/app/admin/bots/SlackTokensForm.tsx

@@ -4,7 +4,7 @@ import { TextFormField } from "@/components/Field";
 import { Form, Formik } from "formik";
 import * as Yup from "yup";
 import { createSlackBot, updateSlackBot } from "./new/lib";
-import { Button } from "@opal/components";
+import Button from "@/refresh-components/buttons/Button";
 import Separator from "@/refresh-components/Separator";
 import { useEffect } from "react";
 import { DOCS_ADMINS_PATH } from "@/lib/constants";

web/src/app/admin/bots/[bot-id]/SlackChannelConfigsTable.tsx

@@ -17,8 +17,9 @@ import type { Route } from "next";
 import { useState } from "react";
 import { deleteSlackChannelConfig, isPersonaASlackBotPersona } from "./lib";
 import { Card } from "@/components/ui/card";
+import Button from "@/refresh-components/buttons/Button";
 import CreateButton from "@/refresh-components/buttons/CreateButton";
-import { Button } from "@opal/components";
+import { Button as OpalButton } from "@opal/components";
 import { SvgSettings, SvgTrash } from "@opal/icons";
 const numToDisplay = 50;
 
@@ -44,11 +45,11 @@ export default function SlackChannelConfigsTable({
     <div className="space-y-8">
       <div className="flex justify-between items-center mb-6">
         <Button
-          prominence="secondary"
           onClick={() => {
             window.location.href = `/admin/bots/${slackBotId}/channels/${defaultConfig?.id}`;
           }}
-          icon={SvgSettings}
+          secondary
+          leftIcon={SvgSettings}
         >
           Edit Default Configuration
         </Button>
@@ -120,7 +121,7 @@ export default function SlackChannelConfigsTable({
                         </div>
                       </TableCell>
                       <TableCell onClick={(e) => e.stopPropagation()}>
-                        <Button
+                        <OpalButton
                           onClick={async (e) => {
                             e.stopPropagation();
                             const response = await deleteSlackChannelConfig(

web/src/app/admin/bots/[bot-id]/channels/SlackChannelConfigFormFields.tsx

@@ -11,7 +11,7 @@ import {
   TextArrayField,
   TextFormField,
 } from "@/components/Field";
-import { Button } from "@opal/components";
+import Button from "@/refresh-components/buttons/Button";
 import { MinimalPersonaSnapshot } from "@/app/admin/agents/interfaces";
 import DocumentSetCard from "@/sections/cards/DocumentSetCard";
 import CollapsibleSection from "@/app/admin/agents/CollapsibleSection";
@@ -598,7 +598,7 @@ export function SlackChannelConfigFormFields({
           </TooltipProvider>
         )}
         <Button type="submit">{isUpdate ? "Update" : "Create"}</Button>
-        <Button prominence="secondary" onClick={() => router.back()}>
+        <Button secondary onClick={() => router.back()}>
           Cancel
         </Button>
       </div>

web/src/app/admin/configuration/document-processing/page.tsx

@@ -2,7 +2,7 @@
 
 import { useState } from "react";
 import CardSection from "@/components/admin/CardSection";
-import { Button } from "@opal/components";
+import Button from "@/refresh-components/buttons/Button";
 import InputTypeIn from "@/refresh-components/inputs/InputTypeIn";
 import useSWR from "swr";
 import { ThreeDotsLoader } from "@/components/Loading";
@@ -129,7 +129,7 @@ function Main() {
             <div className="flex flex-col gap-2 desktop:flex-row desktop:items-center desktop:gap-2">
               {isApiKeySet ? (
                 <>
-                  <Button variant="danger" onClick={handleDelete}>
+                  <Button onClick={handleDelete} danger>
                     Delete API Key
                   </Button>
                   <Text as="p" mainContentBody text04 className="desktop:mt-0">
@@ -137,7 +137,7 @@ function Main() {
                   </Text>
                 </>
               ) : (
-                <Button variant="action" onClick={handleSave}>
+                <Button onClick={handleSave} action>
                   Save API Key
                 </Button>
               )}

web/src/app/admin/configuration/search/UpgradingPage.tsx

@@ -10,7 +10,6 @@ import {
 import Text from "@/components/ui/text";
 import Title from "@/components/ui/title";
 import Button from "@/refresh-components/buttons/Button";
-import { Button as OpalButton } from "@opal/components";
 import { useMemo, useState } from "react";
 import useSWR, { mutate } from "swr";
 import { ReindexingProgressTable } from "../../../../components/embedding/ReindexingProgressTable";
@@ -24,7 +23,6 @@ import { FailedReIndexAttempts } from "@/components/embedding/FailedReIndexAttem
 import { useConnectorIndexingStatusWithPagination } from "@/lib/hooks";
 import { SvgX } from "@opal/icons";
 import { ConnectorCredentialPairStatus } from "@/app/admin/connector/[ccPairId]/types";
-import { useVectorDbEnabled } from "@/providers/SettingsProvider";
 
 export default function UpgradingPage({
   futureEmbeddingModel,
@@ -32,12 +30,11 @@ export default function UpgradingPage({
   futureEmbeddingModel: CloudEmbeddingModel | HostedEmbeddingModel;
 }) {
   const [isCancelling, setIsCancelling] = useState<boolean>(false);
-  const vectorDbEnabled = useVectorDbEnabled();
 
   const { data: connectors, isLoading: isLoadingConnectors } = useSWR<
     Connector<any>[]
-  >(vectorDbEnabled ? "/api/manage/connector" : null, errorHandlingFetcher, {
-    refreshInterval: 5000,
+  >("/api/manage/connector", errorHandlingFetcher, {
+    refreshInterval: 5000, // 5 seconds
   });
 
   const {
@@ -45,8 +42,7 @@ export default function UpgradingPage({
     isLoading: isLoadingOngoingReIndexingStatus,
   } = useConnectorIndexingStatusWithPagination(
     { secondary_index: true, get_all_connectors: true },
-    5000,
-    vectorDbEnabled
+    5000
   ) as {
     data: ConnectorIndexingStatusLiteResponse[];
     isLoading: boolean;
@@ -55,11 +51,9 @@ export default function UpgradingPage({
   const { data: failedIndexingStatus } = useSWR<
     FailedConnectorIndexingStatus[]
   >(
-    vectorDbEnabled
-      ? "/api/manage/admin/connector/failed-indexing-status?secondary_index=true"
-      : null,
+    "/api/manage/admin/connector/failed-indexing-status?secondary_index=true",
     errorHandlingFetcher,
-    { refreshInterval: 5000 }
+    { refreshInterval: 5000 } // 5 seconds
   );
 
   const onCancel = async () => {
@@ -146,13 +140,10 @@ export default function UpgradingPage({
               </div>
             </Modal.Body>
             <Modal.Footer>
-              <OpalButton onClick={onCancel}>Confirm</OpalButton>
-              <OpalButton
-                prominence="secondary"
-                onClick={() => setIsCancelling(false)}
-              >
+              <Button onClick={onCancel}>Confirm</Button>
+              <Button onClick={() => setIsCancelling(false)} secondary>
                 Cancel
-              </OpalButton>
+              </Button>
             </Modal.Footer>
           </Modal.Content>
         </Modal>
@@ -167,7 +158,6 @@ export default function UpgradingPage({
               {futureEmbeddingModel.model_name}
             </div>
 
-            {/* TODO(@raunakab): migrate to opal Button once className/iconClassName is resolved */}
             <Button
               danger
               className="mt-4"