feat: no vector db beat tasks (#8865)

Co-authored-by: Raunak Bhagat <r@rabh.io>

.github/actions/build-integration-image/action.yml

@@ -54,6 +54,7 @@ runs:
       shell: bash
       env:
         RUNS_ON_ECR_CACHE: ${{ inputs.runs-on-ecr-cache }}
+        INTEGRATION_REPOSITORY: ${{ inputs.runs-on-ecr-cache }}
         TAG: nightly-llm-it-${{ inputs.run-id }}
         CACHE_SUFFIX: ${{ steps.format-branch.outputs.cache-suffix }}
         HEAD_SHA: ${{ inputs.github-sha }}

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

@@ -114,8 +114,10 @@ jobs:
 
       - name: Mark workflow as failed if cherry-pick failed
         if: steps.gate.outputs.should_cherrypick == 'true' && steps.run_cherry_pick.outputs.status == 'failure'
+        env:
+          CHERRY_PICK_REASON: ${{ steps.run_cherry_pick.outputs.reason }}
         run: |
-          echo "::error::Automated cherry-pick failed (${{ steps.run_cherry_pick.outputs.reason }})."
+          echo "::error::Automated cherry-pick failed (${CHERRY_PICK_REASON})."
           exit 1
 
   notify-slack-on-cherry-pick-failure:

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

@@ -603,7 +603,7 @@ jobs:
       pull-requests: write
     steps:
       - name: Download visual diff summaries
-        uses: actions/download-artifact@95815c38cf2ff2164869cbab79da8d1f422bc89e # ratchet:actions/download-artifact@v4
+        uses: actions/download-artifact@37930b1c2abaa49bbe596cd826c3c89aef350131
         with:
           pattern: screenshot-diff-summary-*
           path: summaries/

backend/alembic/versions/4a1e4b1c89d2_add_indexing_to_userfilestatus.py

@@ -0,0 +1,51 @@
+"""Add INDEXING to UserFileStatus
+
+Revision ID: 4a1e4b1c89d2
+Revises: 6b3b4083c5aa
+Create Date: 2026-02-28 00:00:00.000000
+
+"""
+
+import sqlalchemy as sa
+from alembic import op
+
+revision = "4a1e4b1c89d2"
+down_revision = "6b3b4083c5aa"
+branch_labels = None
+depends_on = None
+
+TABLE = "user_file"
+COLUMN = "status"
+CONSTRAINT_NAME = "ck_user_file_status"
+
+OLD_VALUES = ("PROCESSING", "COMPLETED", "FAILED", "CANCELED", "DELETING")
+NEW_VALUES = ("PROCESSING", "INDEXING", "COMPLETED", "FAILED", "CANCELED", "DELETING")
+
+
+def _drop_status_check_constraint() -> None:
+    """Drop the existing CHECK constraint on user_file.status.
+
+    The constraint name is auto-generated by SQLAlchemy and unknown,
+    so we look it up via the inspector.
+    """
+    inspector = sa.inspect(op.get_bind())
+    for constraint in inspector.get_check_constraints(TABLE):
+        if COLUMN in constraint.get("sqltext", ""):
+            constraint_name = constraint["name"]
+            if constraint_name is not None:
+                op.drop_constraint(constraint_name, TABLE, type_="check")
+
+
+def upgrade() -> None:
+    _drop_status_check_constraint()
+    in_clause = ", ".join(f"'{v}'" for v in NEW_VALUES)
+    op.create_check_constraint(CONSTRAINT_NAME, TABLE, f"{COLUMN} IN ({in_clause})")
+
+
+def downgrade() -> None:
+    op.execute(
+        f"UPDATE {TABLE} SET {COLUMN} = 'PROCESSING' WHERE {COLUMN} = 'INDEXING'"
+    )
+    op.drop_constraint(CONSTRAINT_NAME, TABLE, type_="check")
+    in_clause = ", ".join(f"'{v}'" for v in OLD_VALUES)
+    op.create_check_constraint(CONSTRAINT_NAME, TABLE, f"{COLUMN} IN ({in_clause})")

backend/alembic/versions/57122d037335_add_python_tool_on_default.py

@@ -0,0 +1,69 @@
+"""add python tool on default
+
+Revision ID: 57122d037335
+Revises: c0c937d5c9e5
+Create Date: 2026-02-27 10:10:40.124925
+
+"""
+
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision = "57122d037335"
+down_revision = "c0c937d5c9e5"
+branch_labels = None
+depends_on = None
+
+
+PYTHON_TOOL_NAME = "python"
+
+
+def upgrade() -> None:
+    conn = op.get_bind()
+
+    # Look up the PythonTool id
+    result = conn.execute(
+        sa.text("SELECT id FROM tool WHERE name = :name"),
+        {"name": PYTHON_TOOL_NAME},
+    ).fetchone()
+
+    if not result:
+        return
+
+    tool_id = result[0]
+
+    # Attach to the default persona (id=0) if not already attached
+    conn.execute(
+        sa.text(
+            """
+            INSERT INTO persona__tool (persona_id, tool_id)
+            VALUES (0, :tool_id)
+            ON CONFLICT DO NOTHING
+            """
+        ),
+        {"tool_id": tool_id},
+    )
+
+
+def downgrade() -> None:
+    conn = op.get_bind()
+
+    result = conn.execute(
+        sa.text("SELECT id FROM tool WHERE name = :name"),
+        {"name": PYTHON_TOOL_NAME},
+    ).fetchone()
+
+    if not result:
+        return
+
+    conn.execute(
+        sa.text(
+            """
+            DELETE FROM persona__tool
+            WHERE persona_id = 0 AND tool_id = :tool_id
+            """
+        ),
+        {"tool_id": result[0]},
+    )

backend/alembic/versions/6b3b4083c5aa_persona_cleanup_and_featured.py

@@ -0,0 +1,112 @@
+"""persona cleanup and featured
+
+Revision ID: 6b3b4083c5aa
+Revises: 57122d037335
+Create Date: 2026-02-26 12:00:00.000000
+
+"""
+
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision = "6b3b4083c5aa"
+down_revision = "57122d037335"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    # Add featured column with nullable=True first
+    op.add_column("persona", sa.Column("featured", sa.Boolean(), nullable=True))
+
+    # Migrate data from is_default_persona to featured
+    op.execute("UPDATE persona SET featured = is_default_persona")
+
+    # Make featured non-nullable with default=False
+    op.alter_column(
+        "persona",
+        "featured",
+        existing_type=sa.Boolean(),
+        nullable=False,
+        server_default=sa.false(),
+    )
+
+    # Drop is_default_persona column
+    op.drop_column("persona", "is_default_persona")
+
+    # Drop unused columns
+    op.drop_column("persona", "num_chunks")
+    op.drop_column("persona", "chunks_above")
+    op.drop_column("persona", "chunks_below")
+    op.drop_column("persona", "llm_relevance_filter")
+    op.drop_column("persona", "llm_filter_extraction")
+    op.drop_column("persona", "recency_bias")
+
+
+def downgrade() -> None:
+    # Add back recency_bias column
+    op.add_column(
+        "persona",
+        sa.Column(
+            "recency_bias",
+            sa.VARCHAR(),
+            nullable=False,
+            server_default="base_decay",
+        ),
+    )
+
+    # Add back llm_filter_extraction column
+    op.add_column(
+        "persona",
+        sa.Column(
+            "llm_filter_extraction",
+            sa.Boolean(),
+            nullable=False,
+            server_default=sa.false(),
+        ),
+    )
+
+    # Add back llm_relevance_filter column
+    op.add_column(
+        "persona",
+        sa.Column(
+            "llm_relevance_filter",
+            sa.Boolean(),
+            nullable=False,
+            server_default=sa.false(),
+        ),
+    )
+
+    # Add back chunks_below column
+    op.add_column(
+        "persona",
+        sa.Column("chunks_below", sa.Integer(), nullable=False, server_default="0"),
+    )
+
+    # Add back chunks_above column
+    op.add_column(
+        "persona",
+        sa.Column("chunks_above", sa.Integer(), nullable=False, server_default="0"),
+    )
+
+    # Add back num_chunks column
+    op.add_column("persona", sa.Column("num_chunks", sa.Float(), nullable=True))
+
+    # Add back is_default_persona column
+    op.add_column(
+        "persona",
+        sa.Column(
+            "is_default_persona",
+            sa.Boolean(),
+            nullable=False,
+            server_default=sa.false(),
+        ),
+    )
+
+    # Migrate data from featured to is_default_persona
+    op.execute("UPDATE persona SET is_default_persona = featured")
+
+    # Drop featured column
+    op.drop_column("persona", "featured")

backend/ee/onyx/server/seeding.py

@@ -18,8 +18,8 @@ from ee.onyx.server.enterprise_settings.store import (
     store_settings as store_ee_settings,
 )
 from ee.onyx.server.enterprise_settings.store import upload_logo
-from onyx.context.search.enums import RecencyBiasSetting
 from onyx.db.engine.sql_engine import get_session_with_current_tenant
+from onyx.db.llm import fetch_existing_llm_provider
 from onyx.db.llm import update_default_provider
 from onyx.db.llm import upsert_llm_provider
 from onyx.db.models import Tool
@@ -117,15 +117,38 @@ def _seed_custom_tools(db_session: Session, tools: List[CustomToolSeed]) -> None
 def _seed_llms(
     db_session: Session, llm_upsert_requests: list[LLMProviderUpsertRequest]
 ) -> None:
-    if llm_upsert_requests:
-        logger.notice("Seeding LLMs")
-        seeded_providers = [
-            upsert_llm_provider(llm_upsert_request, db_session)
-            for llm_upsert_request in llm_upsert_requests
-        ]
-        update_default_provider(
-            provider_id=seeded_providers[0].id, db_session=db_session
-        )
+    if not llm_upsert_requests:
+        return
+
+    logger.notice("Seeding LLMs")
+    for request in llm_upsert_requests:
+        existing = fetch_existing_llm_provider(name=request.name, db_session=db_session)
+        if existing:
+            request.id = existing.id
+    seeded_providers = [
+        upsert_llm_provider(llm_upsert_request, db_session)
+        for llm_upsert_request in llm_upsert_requests
+    ]
+
+    default_provider = next(
+        (p for p in seeded_providers if p.model_configurations), None
+    )
+    if not default_provider:
+        return
+
+    visible_configs = [
+        mc for mc in default_provider.model_configurations if mc.is_visible
+    ]
+    default_config = (
+        visible_configs[0]
+        if visible_configs
+        else default_provider.model_configurations[0]
+    )
+    update_default_provider(
+        provider_id=default_provider.id,
+        model_name=default_config.name,
+        db_session=db_session,
+    )
 
 
 def _seed_personas(db_session: Session, personas: list[PersonaUpsertRequest]) -> None:
@@ -137,12 +160,6 @@ def _seed_personas(db_session: Session, personas: list[PersonaUpsertRequest]) ->
                     user=None,  # Seeding is done as admin
                     name=persona.name,
                     description=persona.description,
-                    num_chunks=(
-                        persona.num_chunks if persona.num_chunks is not None else 0.0
-                    ),
-                    llm_relevance_filter=persona.llm_relevance_filter,
-                    llm_filter_extraction=persona.llm_filter_extraction,
-                    recency_bias=RecencyBiasSetting.AUTO,
                     document_set_ids=persona.document_set_ids,
                     llm_model_provider_override=persona.llm_model_provider_override,
                     llm_model_version_override=persona.llm_model_version_override,
@@ -154,6 +171,7 @@ def _seed_personas(db_session: Session, personas: list[PersonaUpsertRequest]) ->
                     system_prompt=persona.system_prompt,
                     task_prompt=persona.task_prompt,
                     datetime_aware=persona.datetime_aware,
+                    featured=persona.featured,
                     commit=False,
                 )
             db_session.commit()

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

@@ -109,6 +109,12 @@ def apply_license_status_to_settings(settings: Settings) -> Settings:
             if metadata.status == _BLOCKING_STATUS:
                 settings.application_status = metadata.status
                 settings.ee_features_enabled = False
+            elif metadata.used_seats > metadata.seats:
+                # License is valid but seat limit exceeded
+                settings.application_status = ApplicationStatus.SEAT_LIMIT_EXCEEDED
+                settings.seat_count = metadata.seats
+                settings.used_seats = metadata.used_seats
+                settings.ee_features_enabled = True
             else:
                 # Has a valid license (GRACE_PERIOD/PAYMENT_REMINDER still allow EE features)
                 settings.ee_features_enabled = True

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

@@ -33,6 +33,7 @@ from onyx.configs.constants import MilestoneRecordType
 from onyx.db.engine.sql_engine import get_session_with_shared_schema
 from onyx.db.engine.sql_engine import get_session_with_tenant
 from onyx.db.image_generation import create_default_image_gen_config_from_api_key
+from onyx.db.llm import fetch_existing_llm_provider
 from onyx.db.llm import update_default_provider
 from onyx.db.llm import upsert_cloud_embedding_provider
 from onyx.db.llm import upsert_llm_provider
@@ -302,12 +303,17 @@ def configure_default_api_keys(db_session: Session) -> None:
 
     has_set_default_provider = False
 
-    def _upsert(request: LLMProviderUpsertRequest) -> None:
+    def _upsert(request: LLMProviderUpsertRequest, default_model: str) -> None:
         nonlocal has_set_default_provider
         try:
+            existing = fetch_existing_llm_provider(
+                name=request.name, db_session=db_session
+            )
+            if existing:
+                request.id = existing.id
             provider = upsert_llm_provider(request, db_session)
             if not has_set_default_provider:
-                update_default_provider(provider.id, db_session)
+                update_default_provider(provider.id, default_model, db_session)
                 has_set_default_provider = True
         except Exception as e:
             logger.error(f"Failed to configure {request.provider} provider: {e}")
@@ -325,14 +331,13 @@ def configure_default_api_keys(db_session: Session) -> None:
             name="OpenAI",
             provider=OPENAI_PROVIDER_NAME,
             api_key=OPENAI_DEFAULT_API_KEY,
-            default_model_name=default_model_name,
             model_configurations=_build_model_configuration_upsert_requests(
                 OPENAI_PROVIDER_NAME, recommendations
             ),
             api_key_changed=True,
             is_auto_mode=True,
         )
-        _upsert(openai_provider)
+        _upsert(openai_provider, default_model_name)
 
         # Create default image generation config using the OpenAI API key
         try:
@@ -361,14 +366,13 @@ def configure_default_api_keys(db_session: Session) -> None:
             name="Anthropic",
             provider=ANTHROPIC_PROVIDER_NAME,
             api_key=ANTHROPIC_DEFAULT_API_KEY,
-            default_model_name=default_model_name,
             model_configurations=_build_model_configuration_upsert_requests(
                 ANTHROPIC_PROVIDER_NAME, recommendations
             ),
             api_key_changed=True,
             is_auto_mode=True,
         )
-        _upsert(anthropic_provider)
+        _upsert(anthropic_provider, default_model_name)
     else:
         logger.info(
             "ANTHROPIC_DEFAULT_API_KEY not set, skipping Anthropic provider configuration"
@@ -393,14 +397,13 @@ def configure_default_api_keys(db_session: Session) -> None:
             name="Google Vertex AI",
             provider=VERTEXAI_PROVIDER_NAME,
             custom_config=custom_config,
-            default_model_name=default_model_name,
             model_configurations=_build_model_configuration_upsert_requests(
                 VERTEXAI_PROVIDER_NAME, recommendations
             ),
             api_key_changed=True,
             is_auto_mode=True,
         )
-        _upsert(vertexai_provider)
+        _upsert(vertexai_provider, default_model_name)
     else:
         logger.info(
             "VERTEXAI_DEFAULT_CREDENTIALS not set, skipping Vertex AI provider configuration"
@@ -432,12 +435,11 @@ def configure_default_api_keys(db_session: Session) -> None:
             name="OpenRouter",
             provider=OPENROUTER_PROVIDER_NAME,
             api_key=OPENROUTER_DEFAULT_API_KEY,
-            default_model_name=default_model_name,
             model_configurations=model_configurations,
             api_key_changed=True,
             is_auto_mode=True,
         )
-        _upsert(openrouter_provider)
+        _upsert(openrouter_provider, default_model_name)
     else:
         logger.info(
             "OPENROUTER_DEFAULT_API_KEY not set, skipping OpenRouter provider configuration"

backend/onyx/auth/users.py

@@ -543,7 +543,7 @@ class UserManager(UUIDIDMixin, BaseUserManager[User, uuid.UUID]):
         result = await db_session.execute(
             select(Persona.id)
             .where(
-                Persona.is_default_persona.is_(True),
+                Persona.featured.is_(True),
                 Persona.is_public.is_(True),
                 Persona.is_visible.is_(True),
                 Persona.deleted.is_(False),

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

@@ -241,8 +241,7 @@ _VECTOR_DB_BEAT_TASK_NAMES: set[str] = {
     "check-for-index-attempt-cleanup",
     "check-for-doc-permissions-sync",
     "check-for-external-group-sync",
-    "check-for-documents-for-opensearch-migration",
-    "migrate-documents-from-vespa-to-opensearch",
+    "migrate-chunks-from-vespa-to-opensearch",
 }
 
 if DISABLE_VECTOR_DB:

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

@@ -414,34 +414,31 @@ def _process_user_file_with_indexing(
         raise RuntimeError(f"Indexing pipeline failed for user file {user_file_id}")
 
 
-@shared_task(
-    name=OnyxCeleryTask.PROCESS_SINGLE_USER_FILE,
-    bind=True,
-    ignore_result=True,
-)
-def process_single_user_file(
-    self: Task, *, user_file_id: str, tenant_id: str  # noqa: ARG001
+def process_user_file_impl(
+    *, user_file_id: str, tenant_id: str, redis_locking: bool
 ) -> None:
-    task_logger.info(f"process_single_user_file - Starting id={user_file_id}")
+    """Core implementation for processing a single user file.
+
+    When redis_locking=True, acquires a per-file Redis lock and clears the
+    queued-key guard (Celery path).  When redis_locking=False, skips all Redis
+    operations (BackgroundTask path).
+    """
+    task_logger.info(f"process_user_file_impl - Starting id={user_file_id}")
     start = time.monotonic()
 
-    redis_client = get_redis_client(tenant_id=tenant_id)
-
-    # Clear the "queued" guard set by the beat generator so that the next beat
-    # cycle can re-enqueue this file if it is still in PROCESSING state after
-    # this task completes or fails.
-    redis_client.delete(_user_file_queued_key(user_file_id))
-
-    file_lock: RedisLock = redis_client.lock(
-        _user_file_lock_key(user_file_id),
-        timeout=CELERY_USER_FILE_PROCESSING_LOCK_TIMEOUT,
-    )
-
-    if not file_lock.acquire(blocking=False):
-        task_logger.info(
-            f"process_single_user_file - Lock held, skipping user_file_id={user_file_id}"
+    file_lock: RedisLock | None = None
+    if redis_locking:
+        redis_client = get_redis_client(tenant_id=tenant_id)
+        redis_client.delete(_user_file_queued_key(user_file_id))
+        file_lock = redis_client.lock(
+            _user_file_lock_key(user_file_id),
+            timeout=CELERY_USER_FILE_PROCESSING_LOCK_TIMEOUT,
         )
-        return None
+        if file_lock is not None and not file_lock.acquire(blocking=False):
+            task_logger.info(
+                f"process_user_file_impl - Lock held, skipping user_file_id={user_file_id}"
+            )
+            return
 
     documents: list[Document] = []
     try:
@@ -449,15 +446,18 @@ def process_single_user_file(
             uf = db_session.get(UserFile, _as_uuid(user_file_id))
             if not uf:
                 task_logger.warning(
-                    f"process_single_user_file - UserFile not found id={user_file_id}"
+                    f"process_user_file_impl - UserFile not found id={user_file_id}"
                 )
-                return None
+                return
 
-            if uf.status != UserFileStatus.PROCESSING:
+            if uf.status not in (
+                UserFileStatus.PROCESSING,
+                UserFileStatus.INDEXING,
+            ):
                 task_logger.info(
-                    f"process_single_user_file - Skipping id={user_file_id} status={uf.status}"
+                    f"process_user_file_impl - Skipping id={user_file_id} status={uf.status}"
                 )
-                return None
+                return
 
             connector = LocalFileConnector(
                 file_locations=[uf.file_id],
@@ -471,7 +471,6 @@ def process_single_user_file(
                         [doc for doc in batch if not isinstance(doc, HierarchyNode)]
                     )
 
-                # update the document id to userfile id in the documents
                 for document in documents:
                     document.id = str(user_file_id)
                     document.source = DocumentSource.USER_FILE
@@ -493,9 +492,8 @@ def process_single_user_file(
 
             except Exception as e:
                 task_logger.exception(
-                    f"process_single_user_file - Error processing file id={user_file_id} - {e.__class__.__name__}"
+                    f"process_user_file_impl - Error processing file id={user_file_id} - {e.__class__.__name__}"
                 )
-                # don't update the status if the user file is being deleted
                 current_user_file = db_session.get(UserFile, _as_uuid(user_file_id))
                 if (
                     current_user_file
@@ -504,33 +502,42 @@ def process_single_user_file(
                     uf.status = UserFileStatus.FAILED
                     db_session.add(uf)
                     db_session.commit()
-                return None
+                return
 
         elapsed = time.monotonic() - start
         task_logger.info(
-            f"process_single_user_file - Finished id={user_file_id} docs={len(documents)} elapsed={elapsed:.2f}s"
+            f"process_user_file_impl - Finished id={user_file_id} docs={len(documents)} elapsed={elapsed:.2f}s"
         )
-        return None
     except Exception as e:
-        # Attempt to mark the file as failed
         with get_session_with_current_tenant() as db_session:
             uf = db_session.get(UserFile, _as_uuid(user_file_id))
             if uf:
-                # don't update the status if the user file is being deleted
                 if uf.status != UserFileStatus.DELETING:
                     uf.status = UserFileStatus.FAILED
                 db_session.add(uf)
                 db_session.commit()
 
         task_logger.exception(
-            f"process_single_user_file - Error processing file id={user_file_id} - {e.__class__.__name__}"
+            f"process_user_file_impl - Error processing file id={user_file_id} - {e.__class__.__name__}"
         )
-        return None
     finally:
-        if file_lock.owned():
+        if file_lock is not None and file_lock.owned():
             file_lock.release()
 
 
+@shared_task(
+    name=OnyxCeleryTask.PROCESS_SINGLE_USER_FILE,
+    bind=True,
+    ignore_result=True,
+)
+def process_single_user_file(
+    self: Task, *, user_file_id: str, tenant_id: str  # noqa: ARG001
+) -> None:
+    process_user_file_impl(
+        user_file_id=user_file_id, tenant_id=tenant_id, redis_locking=True
+    )
+
+
 @shared_task(
     name=OnyxCeleryTask.CHECK_FOR_USER_FILE_DELETE,
     soft_time_limit=300,
@@ -581,36 +588,38 @@ def check_for_user_file_delete(self: Task, *, tenant_id: str) -> None:
     return None
 
 
-@shared_task(
-    name=OnyxCeleryTask.DELETE_SINGLE_USER_FILE,
-    bind=True,
-    ignore_result=True,
-)
-def process_single_user_file_delete(
-    self: Task, *, user_file_id: str, tenant_id: str  # noqa: ARG001
+def delete_user_file_impl(
+    *, user_file_id: str, tenant_id: str, redis_locking: bool
 ) -> None:
-    """Process a single user file delete."""
-    task_logger.info(f"process_single_user_file_delete - Starting id={user_file_id}")
-    redis_client = get_redis_client(tenant_id=tenant_id)
-    file_lock: RedisLock = redis_client.lock(
-        _user_file_delete_lock_key(user_file_id),
-        timeout=CELERY_GENERIC_BEAT_LOCK_TIMEOUT,
-    )
-    if not file_lock.acquire(blocking=False):
-        task_logger.info(
-            f"process_single_user_file_delete - Lock held, skipping user_file_id={user_file_id}"
+    """Core implementation for deleting a single user file.
+
+    When redis_locking=True, acquires a per-file Redis lock (Celery path).
+    When redis_locking=False, skips Redis operations (BackgroundTask path).
+    """
+    task_logger.info(f"delete_user_file_impl - Starting id={user_file_id}")
+
+    file_lock: RedisLock | None = None
+    if redis_locking:
+        redis_client = get_redis_client(tenant_id=tenant_id)
+        file_lock = redis_client.lock(
+            _user_file_delete_lock_key(user_file_id),
+            timeout=CELERY_GENERIC_BEAT_LOCK_TIMEOUT,
         )
-        return None
+        if file_lock is not None and not file_lock.acquire(blocking=False):
+            task_logger.info(
+                f"delete_user_file_impl - Lock held, skipping user_file_id={user_file_id}"
+            )
+            return
+
     try:
         with get_session_with_current_tenant() as db_session:
             user_file = db_session.get(UserFile, _as_uuid(user_file_id))
             if not user_file:
                 task_logger.info(
-                    f"process_single_user_file_delete - User file not found id={user_file_id}"
+                    f"delete_user_file_impl - User file not found id={user_file_id}"
                 )
-                return None
+                return
 
-            # 1) Delete vector DB chunks (skip when disabled)
             if not DISABLE_VECTOR_DB:
                 if MANAGED_VESPA:
                     httpx_init_vespa_pool(
@@ -648,7 +657,6 @@ def process_single_user_file_delete(
                         chunk_count=chunk_count,
                     )
 
-            # 2) Delete the user-uploaded file content from filestore (blob + metadata)
             file_store = get_default_file_store()
             try:
                 file_store.delete_file(user_file.file_id)
@@ -656,26 +664,33 @@ def process_single_user_file_delete(
                     user_file_id_to_plaintext_file_name(user_file.id)
                 )
             except Exception as e:
-                # This block executed only if the file is not found in the filestore
                 task_logger.exception(
-                    f"process_single_user_file_delete - Error deleting file id={user_file.id} - {e.__class__.__name__}"
+                    f"delete_user_file_impl - Error deleting file id={user_file.id} - {e.__class__.__name__}"
                 )
 
-            # 3) Finally, delete the UserFile row
             db_session.delete(user_file)
             db_session.commit()
-            task_logger.info(
-                f"process_single_user_file_delete - Completed id={user_file_id}"
-            )
+            task_logger.info(f"delete_user_file_impl - Completed id={user_file_id}")
     except Exception as e:
         task_logger.exception(
-            f"process_single_user_file_delete - Error processing file id={user_file_id} - {e.__class__.__name__}"
+            f"delete_user_file_impl - Error processing file id={user_file_id} - {e.__class__.__name__}"
         )
-        return None
     finally:
-        if file_lock.owned():
+        if file_lock is not None and file_lock.owned():
             file_lock.release()
-    return None
+
+
+@shared_task(
+    name=OnyxCeleryTask.DELETE_SINGLE_USER_FILE,
+    bind=True,
+    ignore_result=True,
+)
+def process_single_user_file_delete(
+    self: Task, *, user_file_id: str, tenant_id: str  # noqa: ARG001
+) -> None:
+    delete_user_file_impl(
+        user_file_id=user_file_id, tenant_id=tenant_id, redis_locking=True
+    )
 
 
 @shared_task(
@@ -747,32 +762,30 @@ def check_for_user_file_project_sync(self: Task, *, tenant_id: str) -> None:
     return None
 
 
-@shared_task(
-    name=OnyxCeleryTask.PROCESS_SINGLE_USER_FILE_PROJECT_SYNC,
-    bind=True,
-    ignore_result=True,
-)
-def process_single_user_file_project_sync(
-    self: Task, *, user_file_id: str, tenant_id: str  # noqa: ARG001
+def project_sync_user_file_impl(
+    *, user_file_id: str, tenant_id: str, redis_locking: bool
 ) -> None:
-    """Process a single user file project sync."""
-    task_logger.info(
-        f"process_single_user_file_project_sync - Starting id={user_file_id}"
-    )
+    """Core implementation for syncing a user file's project/persona metadata.
 
-    redis_client = get_redis_client(tenant_id=tenant_id)
-    redis_client.delete(_user_file_project_sync_queued_key(user_file_id))
+    When redis_locking=True, acquires a per-file Redis lock and clears the
+    queued-key guard (Celery path).  When redis_locking=False, skips Redis
+    operations (BackgroundTask path).
+    """
+    task_logger.info(f"project_sync_user_file_impl - Starting id={user_file_id}")
 
-    file_lock: RedisLock = redis_client.lock(
-        user_file_project_sync_lock_key(user_file_id),
-        timeout=CELERY_USER_FILE_PROJECT_SYNC_LOCK_TIMEOUT,
-    )
-
-    if not file_lock.acquire(blocking=False):
-        task_logger.info(
-            f"process_single_user_file_project_sync - Lock held, skipping user_file_id={user_file_id}"
+    file_lock: RedisLock | None = None
+    if redis_locking:
+        redis_client = get_redis_client(tenant_id=tenant_id)
+        redis_client.delete(_user_file_project_sync_queued_key(user_file_id))
+        file_lock = redis_client.lock(
+            user_file_project_sync_lock_key(user_file_id),
+            timeout=CELERY_USER_FILE_PROJECT_SYNC_LOCK_TIMEOUT,
         )
-        return None
+        if file_lock is not None and not file_lock.acquire(blocking=False):
+            task_logger.info(
+                f"project_sync_user_file_impl - Lock held, skipping user_file_id={user_file_id}"
+            )
+            return
 
     try:
         with get_session_with_current_tenant() as db_session:
@@ -783,11 +796,10 @@ def process_single_user_file_project_sync(
             ).scalar_one_or_none()
             if not user_file:
                 task_logger.info(
-                    f"process_single_user_file_project_sync - User file not found id={user_file_id}"
+                    f"project_sync_user_file_impl - User file not found id={user_file_id}"
                 )
-                return None
+                return
 
-            # Sync project metadata to vector DB (skip when disabled)
             if not DISABLE_VECTOR_DB:
                 if MANAGED_VESPA:
                     httpx_init_vespa_pool(
@@ -822,7 +834,7 @@ def process_single_user_file_project_sync(
                     )
 
             task_logger.info(
-                f"process_single_user_file_project_sync - User file id={user_file_id}"
+                f"project_sync_user_file_impl - User file id={user_file_id}"
             )
 
             user_file.needs_project_sync = False
@@ -835,11 +847,21 @@ def process_single_user_file_project_sync(
 
     except Exception as e:
         task_logger.exception(
-            f"process_single_user_file_project_sync - Error syncing project for file id={user_file_id} - {e.__class__.__name__}"
+            f"project_sync_user_file_impl - Error syncing project for file id={user_file_id} - {e.__class__.__name__}"
         )
-        return None
     finally:
-        if file_lock.owned():
+        if file_lock is not None and file_lock.owned():
             file_lock.release()
 
-    return None
+
+@shared_task(
+    name=OnyxCeleryTask.PROCESS_SINGLE_USER_FILE_PROJECT_SYNC,
+    bind=True,
+    ignore_result=True,
+)
+def process_single_user_file_project_sync(
+    self: Task, *, user_file_id: str, tenant_id: str  # noqa: ARG001
+) -> None:
+    project_sync_user_file_impl(
+        user_file_id=user_file_id, tenant_id=tenant_id, redis_locking=True
+    )

backend/onyx/background/periodic_poller.py

@@ -0,0 +1,284 @@
+"""Periodic poller for NO_VECTOR_DB deployments.
+
+Replaces Celery Beat and background workers with a lightweight daemon thread
+that runs from the API server process.  Two responsibilities:
+
+1. Recovery polling (every 30 s): re-processes user files stuck in
+   PROCESSING / DELETING / needs_sync states via the drain loops defined
+   in ``task_utils.py``.
+
+2. Periodic task execution (configurable intervals): runs LLM model updates
+   and scheduled evals at their configured cadences, with Postgres advisory
+   lock deduplication across multiple API server instances.
+"""
+
+import threading
+import time
+from collections.abc import Callable
+from dataclasses import dataclass
+from dataclasses import field
+
+from onyx.utils.logger import setup_logger
+
+logger = setup_logger()
+
+RECOVERY_INTERVAL_SECONDS = 30
+PERIODIC_TASK_LOCK_BASE = 20_000
+PERIODIC_TASK_KV_PREFIX = "periodic_poller:last_claimed:"
+
+
+# ------------------------------------------------------------------
+# Periodic task definitions
+# ------------------------------------------------------------------
+
+
+@dataclass
+class _PeriodicTaskDef:
+    name: str
+    interval_seconds: float
+    lock_id: int
+    run_fn: Callable[[], None]
+    last_run_at: float = field(default=0.0)
+
+
+def _run_auto_llm_update() -> None:
+    from onyx.configs.app_configs import AUTO_LLM_CONFIG_URL
+
+    if not AUTO_LLM_CONFIG_URL:
+        return
+
+    from onyx.db.engine.sql_engine import get_session_with_current_tenant
+    from onyx.llm.well_known_providers.auto_update_service import (
+        sync_llm_models_from_github,
+    )
+
+    with get_session_with_current_tenant() as db_session:
+        sync_llm_models_from_github(db_session)
+
+
+def _run_scheduled_eval() -> None:
+    from onyx.configs.app_configs import BRAINTRUST_API_KEY
+    from onyx.configs.app_configs import SCHEDULED_EVAL_DATASET_NAMES
+    from onyx.configs.app_configs import SCHEDULED_EVAL_PERMISSIONS_EMAIL
+    from onyx.configs.app_configs import SCHEDULED_EVAL_PROJECT
+
+    if not all(
+        [
+            BRAINTRUST_API_KEY,
+            SCHEDULED_EVAL_PROJECT,
+            SCHEDULED_EVAL_DATASET_NAMES,
+            SCHEDULED_EVAL_PERMISSIONS_EMAIL,
+        ]
+    ):
+        return
+
+    from datetime import datetime
+    from datetime import timezone
+
+    from onyx.evals.eval import run_eval
+    from onyx.evals.models import EvalConfigurationOptions
+
+    run_timestamp = datetime.now(timezone.utc).strftime("%Y-%m-%d")
+    for dataset_name in SCHEDULED_EVAL_DATASET_NAMES:
+        try:
+            run_eval(
+                configuration=EvalConfigurationOptions(
+                    search_permissions_email=SCHEDULED_EVAL_PERMISSIONS_EMAIL,
+                    dataset_name=dataset_name,
+                    no_send_logs=False,
+                    braintrust_project=SCHEDULED_EVAL_PROJECT,
+                    experiment_name=f"{dataset_name} - {run_timestamp}",
+                ),
+                remote_dataset_name=dataset_name,
+            )
+        except Exception:
+            logger.exception(
+                f"Periodic poller - Failed scheduled eval for dataset {dataset_name}"
+            )
+
+
+def _build_periodic_tasks() -> list[_PeriodicTaskDef]:
+    from onyx.configs.app_configs import AUTO_LLM_CONFIG_URL
+    from onyx.configs.app_configs import AUTO_LLM_UPDATE_INTERVAL_SECONDS
+    from onyx.configs.app_configs import SCHEDULED_EVAL_DATASET_NAMES
+
+    tasks: list[_PeriodicTaskDef] = []
+    if AUTO_LLM_CONFIG_URL:
+        tasks.append(
+            _PeriodicTaskDef(
+                name="auto-llm-update",
+                interval_seconds=AUTO_LLM_UPDATE_INTERVAL_SECONDS,
+                lock_id=PERIODIC_TASK_LOCK_BASE,
+                run_fn=_run_auto_llm_update,
+            )
+        )
+    if SCHEDULED_EVAL_DATASET_NAMES:
+        tasks.append(
+            _PeriodicTaskDef(
+                name="scheduled-eval",
+                interval_seconds=7 * 24 * 3600,
+                lock_id=PERIODIC_TASK_LOCK_BASE + 1,
+                run_fn=_run_scheduled_eval,
+            )
+        )
+    return tasks
+
+
+# ------------------------------------------------------------------
+# Periodic task runner with advisory-lock-guarded claim
+# ------------------------------------------------------------------
+
+
+def _try_claim_task(task_def: _PeriodicTaskDef) -> bool:
+    """Atomically check whether *task_def* should run and record a claim.
+
+    Uses a transaction-scoped advisory lock for atomicity combined with a
+    ``KVStore`` timestamp for cross-instance dedup.  The DB session is held
+    only for this brief claim transaction, not during task execution.
+    """
+    from datetime import datetime
+    from datetime import timezone
+
+    from sqlalchemy import text
+
+    from onyx.db.engine.sql_engine import get_session_with_current_tenant
+    from onyx.db.models import KVStore
+
+    kv_key = PERIODIC_TASK_KV_PREFIX + task_def.name
+
+    with get_session_with_current_tenant() as db_session:
+        acquired = db_session.execute(
+            text("SELECT pg_try_advisory_xact_lock(:id)"),
+            {"id": task_def.lock_id},
+        ).scalar()
+        if not acquired:
+            return False
+
+        row = db_session.query(KVStore).filter_by(key=kv_key).first()
+        if row and row.value is not None:
+            last_claimed = datetime.fromisoformat(str(row.value))
+            elapsed = (datetime.now(timezone.utc) - last_claimed).total_seconds()
+            if elapsed < task_def.interval_seconds:
+                return False
+
+        now_ts = datetime.now(timezone.utc).isoformat()
+        if row:
+            row.value = now_ts
+        else:
+            db_session.add(KVStore(key=kv_key, value=now_ts))
+        db_session.commit()
+
+    return True
+
+
+def _try_run_periodic_task(task_def: _PeriodicTaskDef) -> None:
+    """Run *task_def* if its interval has elapsed and no peer holds the lock."""
+    now = time.monotonic()
+    if now - task_def.last_run_at < task_def.interval_seconds:
+        return
+
+    if not _try_claim_task(task_def):
+        return
+
+    try:
+        task_def.run_fn()
+        task_def.last_run_at = now
+    except Exception:
+        logger.exception(
+            f"Periodic poller - Error running periodic task {task_def.name}"
+        )
+
+
+# ------------------------------------------------------------------
+# Recovery / drain loop runner
+# ------------------------------------------------------------------
+
+
+def _run_drain_loops(tenant_id: str) -> None:
+    from onyx.background.task_utils import drain_delete_loop
+    from onyx.background.task_utils import drain_processing_loop
+    from onyx.background.task_utils import drain_project_sync_loop
+
+    drain_processing_loop(tenant_id)
+    drain_delete_loop(tenant_id)
+    drain_project_sync_loop(tenant_id)
+
+
+# ------------------------------------------------------------------
+# Startup recovery (10g)
+# ------------------------------------------------------------------
+
+
+def recover_stuck_user_files(tenant_id: str) -> None:
+    """Run all drain loops once to re-process files left in intermediate states.
+
+    Called from ``lifespan()`` on startup when ``DISABLE_VECTOR_DB`` is set.
+    """
+    logger.info("recover_stuck_user_files - Checking for stuck user files")
+    try:
+        _run_drain_loops(tenant_id)
+    except Exception:
+        logger.exception("recover_stuck_user_files - Error during recovery")
+
+
+# ------------------------------------------------------------------
+# Daemon thread (10f)
+# ------------------------------------------------------------------
+
+_shutdown_event = threading.Event()
+_poller_thread: threading.Thread | None = None
+
+
+def _poller_loop(tenant_id: str) -> None:
+    from shared_configs.contextvars import CURRENT_TENANT_ID_CONTEXTVAR
+
+    CURRENT_TENANT_ID_CONTEXTVAR.set(tenant_id)
+
+    periodic_tasks = _build_periodic_tasks()
+    logger.info(
+        f"Periodic poller started with {len(periodic_tasks)} periodic task(s): "
+        f"{[t.name for t in periodic_tasks]}"
+    )
+
+    while not _shutdown_event.is_set():
+        try:
+            _run_drain_loops(tenant_id)
+        except Exception:
+            logger.exception("Periodic poller - Error in recovery polling")
+
+        for task_def in periodic_tasks:
+            try:
+                _try_run_periodic_task(task_def)
+            except Exception:
+                logger.exception(
+                    f"Periodic poller - Unhandled error checking task {task_def.name}"
+                )
+
+        _shutdown_event.wait(RECOVERY_INTERVAL_SECONDS)
+
+
+def start_periodic_poller(tenant_id: str) -> None:
+    """Start the periodic poller daemon thread."""
+    global _poller_thread  # noqa: PLW0603
+    _shutdown_event.clear()
+    _poller_thread = threading.Thread(
+        target=_poller_loop,
+        args=(tenant_id,),
+        daemon=True,
+        name="no-vectordb-periodic-poller",
+    )
+    _poller_thread.start()
+    logger.info("Periodic poller thread started")
+
+
+def stop_periodic_poller() -> None:
+    """Signal the periodic poller to stop and wait for it to exit."""
+    global _poller_thread  # noqa: PLW0603
+    if _poller_thread is None:
+        return
+    _shutdown_event.set()
+    _poller_thread.join(timeout=10)
+    if _poller_thread.is_alive():
+        logger.warning("Periodic poller thread did not stop within timeout")
+    _poller_thread = None
+    logger.info("Periodic poller thread stopped")

backend/onyx/background/task_utils.py

@@ -1,3 +1,33 @@
+"""Background task utilities.
+
+Contains query-history report helpers (used by all deployment modes) and
+in-process background task execution helpers for NO_VECTOR_DB mode:
+
+- Atomic claim-and-mark helpers that prevent duplicate processing
+- Drain loops that process all pending user file work
+
+Each claim function runs a short-lived transaction: SELECT ... FOR UPDATE
+SKIP LOCKED, UPDATE the row to remove it from future queries, COMMIT.
+After the commit the row lock is released, but the row is no longer
+eligible for re-claiming.  No long-lived sessions or advisory locks.
+"""
+
+from uuid import UUID
+
+import sqlalchemy as sa
+from sqlalchemy import select
+from sqlalchemy.orm import Session
+
+from onyx.db.enums import UserFileStatus
+from onyx.db.models import UserFile
+from onyx.utils.logger import setup_logger
+
+logger = setup_logger()
+
+# ------------------------------------------------------------------
+# Query-history report helpers (pre-existing, used by all modes)
+# ------------------------------------------------------------------
+
 QUERY_REPORT_NAME_PREFIX = "query-history"
 
 
@@ -9,3 +39,142 @@ def construct_query_history_report_name(
 
 def extract_task_id_from_query_history_report_name(name: str) -> str:
     return name.removeprefix(f"{QUERY_REPORT_NAME_PREFIX}-").removesuffix(".csv")
+
+
+# ------------------------------------------------------------------
+# Atomic claim-and-mark helpers
+# ------------------------------------------------------------------
+# Each function runs inside a single short-lived session/transaction:
+#   1. SELECT ... FOR UPDATE SKIP LOCKED  (locks one eligible row)
+#   2. UPDATE the row so it is no longer eligible
+#   3. COMMIT  (releases the row lock)
+# After the commit, no other drain loop can claim the same row.
+
+
+def _claim_next_processing_file(db_session: Session) -> UUID | None:
+    """Claim the next PROCESSING file by transitioning it to INDEXING.
+
+    Returns the file id, or None when no eligible files remain.
+    """
+    file_id = db_session.execute(
+        select(UserFile.id)
+        .where(UserFile.status == UserFileStatus.PROCESSING)
+        .order_by(UserFile.created_at)
+        .limit(1)
+        .with_for_update(skip_locked=True)
+    ).scalar_one_or_none()
+    if file_id is None:
+        return None
+
+    db_session.execute(
+        sa.update(UserFile)
+        .where(UserFile.id == file_id)
+        .values(status=UserFileStatus.INDEXING)
+    )
+    db_session.commit()
+    return file_id
+
+
+def _claim_next_deleting_file(db_session: Session) -> UUID | None:
+    """Claim the next DELETING file.
+
+    No status transition needed — the impl deletes the row on success.
+    The short-lived FOR UPDATE lock prevents concurrent claims.
+    """
+    file_id = db_session.execute(
+        select(UserFile.id)
+        .where(UserFile.status == UserFileStatus.DELETING)
+        .order_by(UserFile.created_at)
+        .limit(1)
+        .with_for_update(skip_locked=True)
+    ).scalar_one_or_none()
+    # Commit to release the row lock promptly.
+    db_session.commit()
+    return file_id
+
+
+def _claim_next_sync_file(db_session: Session) -> UUID | None:
+    """Claim the next file needing project/persona sync.
+
+    No status transition needed — the impl clears the sync flags on
+    success.  The short-lived FOR UPDATE lock prevents concurrent claims.
+    """
+    file_id = db_session.execute(
+        select(UserFile.id)
+        .where(
+            sa.and_(
+                sa.or_(
+                    UserFile.needs_project_sync.is_(True),
+                    UserFile.needs_persona_sync.is_(True),
+                ),
+                UserFile.status == UserFileStatus.COMPLETED,
+            )
+        )
+        .order_by(UserFile.created_at)
+        .limit(1)
+        .with_for_update(skip_locked=True)
+    ).scalar_one_or_none()
+    db_session.commit()
+    return file_id
+
+
+# ------------------------------------------------------------------
+# Drain loops — process *all* pending work of each type
+# ------------------------------------------------------------------
+
+
+def drain_processing_loop(tenant_id: str) -> None:
+    """Process all pending PROCESSING user files."""
+    from onyx.background.celery.tasks.user_file_processing.tasks import (
+        process_user_file_impl,
+    )
+    from onyx.db.engine.sql_engine import get_session_with_current_tenant
+
+    while True:
+        with get_session_with_current_tenant() as session:
+            file_id = _claim_next_processing_file(session)
+        if file_id is None:
+            break
+        process_user_file_impl(
+            user_file_id=str(file_id),
+            tenant_id=tenant_id,
+            redis_locking=False,
+        )
+
+
+def drain_delete_loop(tenant_id: str) -> None:
+    """Delete all pending DELETING user files."""
+    from onyx.background.celery.tasks.user_file_processing.tasks import (
+        delete_user_file_impl,
+    )
+    from onyx.db.engine.sql_engine import get_session_with_current_tenant
+
+    while True:
+        with get_session_with_current_tenant() as session:
+            file_id = _claim_next_deleting_file(session)
+        if file_id is None:
+            break
+        delete_user_file_impl(
+            user_file_id=str(file_id),
+            tenant_id=tenant_id,
+            redis_locking=False,
+        )
+
+
+def drain_project_sync_loop(tenant_id: str) -> None:
+    """Sync all pending project/persona metadata for user files."""
+    from onyx.background.celery.tasks.user_file_processing.tasks import (
+        project_sync_user_file_impl,
+    )
+    from onyx.db.engine.sql_engine import get_session_with_current_tenant
+
+    while True:
+        with get_session_with_current_tenant() as session:
+            file_id = _claim_next_sync_file(session)
+        if file_id is None:
+            break
+        project_sync_user_file_impl(
+            user_file_id=str(file_id),
+            tenant_id=tenant_id,
+            redis_locking=False,
+        )

backend/onyx/chat/llm_loop.py

@@ -1,6 +1,7 @@
 import json
 import time
 from collections.abc import Callable
+from typing import Any
 from typing import Literal
 
 from sqlalchemy.orm import Session
@@ -530,11 +531,13 @@ def _create_file_tool_metadata_message(
     """
     lines = [
         "You have access to the following files. Use the read_file tool to "
-        "read sections of any file:"
+        "read sections of any file. You MUST pass the file_id UUID (not the "
+        "filename) to read_file:"
     ]
     for meta in file_metadata:
         lines.append(
-            f'- {meta.file_id}: "{meta.filename}" (~{meta.approx_char_count:,} chars)'
+            f'- file_id="{meta.file_id}" filename="{meta.filename}" '
+            f"(~{meta.approx_char_count:,} chars)"
         )
 
     message_content = "\n".join(lines)
@@ -558,12 +561,16 @@ def _create_context_files_message(
     # Format as documents JSON as described in README
     documents_list = []
     for idx, file_text in enumerate(context_files.file_texts, start=1):
-        documents_list.append(
-            {
-                "document": idx,
-                "contents": file_text,
-            }
+        title = (
+            context_files.file_metadata[idx - 1].filename
+            if idx - 1 < len(context_files.file_metadata)
+            else None
         )
+        entry: dict[str, Any] = {"document": idx}
+        if title:
+            entry["title"] = title
+        entry["contents"] = file_text
+        documents_list.append(entry)
 
     documents_json = json.dumps({"documents": documents_list}, indent=2)
     message_content = f"Here are some documents provided for context, they may not all be relevant:\n{documents_json}"

backend/onyx/connectors/gong/connector.py

@@ -32,6 +32,8 @@ class GongConnector(LoadConnector, PollConnector):
     BASE_URL = "https://api.gong.io"
     MAX_CALL_DETAILS_ATTEMPTS = 6
     CALL_DETAILS_DELAY = 30  # in seconds
+    # Gong API limit is 3 calls/sec — stay safely under it
+    MIN_REQUEST_INTERVAL = 0.5  # seconds between requests
 
     def __init__(
         self,
@@ -45,9 +47,13 @@ class GongConnector(LoadConnector, PollConnector):
         self.continue_on_fail = continue_on_fail
         self.auth_token_basic: str | None = None
         self.hide_user_info = hide_user_info
+        self._last_request_time: float = 0.0
 
+        # urllib3 Retry already respects the Retry-After header by default
+        # (respect_retry_after_header=True), so on 429 it will sleep for the
+        # duration Gong specifies before retrying.
         retry_strategy = Retry(
-            total=5,
+            total=10,
             backoff_factor=2,
             status_forcelist=[429, 500, 502, 503, 504],
         )
@@ -61,8 +67,24 @@ class GongConnector(LoadConnector, PollConnector):
         url = f"{GongConnector.BASE_URL}{endpoint}"
         return url
 
+    def _throttled_request(
+        self, method: str, url: str, **kwargs: Any
+    ) -> requests.Response:
+        """Rate-limited request wrapper. Enforces MIN_REQUEST_INTERVAL between
+        calls to stay under Gong's 3 calls/sec limit and avoid triggering 429s."""
+        now = time.monotonic()
+        elapsed = now - self._last_request_time
+        if elapsed < self.MIN_REQUEST_INTERVAL:
+            time.sleep(self.MIN_REQUEST_INTERVAL - elapsed)
+
+        response = self._session.request(method, url, **kwargs)
+        self._last_request_time = time.monotonic()
+        return response
+
     def _get_workspace_id_map(self) -> dict[str, str]:
-        response = self._session.get(GongConnector.make_url("/v2/workspaces"))
+        response = self._throttled_request(
+            "GET", GongConnector.make_url("/v2/workspaces")
+        )
         response.raise_for_status()
 
         workspaces_details = response.json().get("workspaces")
@@ -106,8 +128,8 @@ class GongConnector(LoadConnector, PollConnector):
                     del body["filter"]["workspaceId"]
 
             while True:
-                response = self._session.post(
-                    GongConnector.make_url("/v2/calls/transcript"), json=body
+                response = self._throttled_request(
+                    "POST", GongConnector.make_url("/v2/calls/transcript"), json=body
                 )
                 # If no calls in the range, just break out
                 if response.status_code == 404:
@@ -142,8 +164,8 @@ class GongConnector(LoadConnector, PollConnector):
             "contentSelector": {"exposedFields": {"parties": True}},
         }
 
-        response = self._session.post(
-            GongConnector.make_url("/v2/calls/extensive"), json=body
+        response = self._throttled_request(
+            "POST", GongConnector.make_url("/v2/calls/extensive"), json=body
         )
         response.raise_for_status()
 
@@ -194,7 +216,8 @@ class GongConnector(LoadConnector, PollConnector):
             # There's a likely race condition in the API where a transcript will have a
             # call id but the call to v2/calls/extensive will not return all of the id's
             # retry with exponential backoff has been observed to mitigate this
-            # in ~2 minutes
+            # in ~2 minutes. After max attempts, proceed with whatever we have —
+            # the per-call loop below will skip missing IDs gracefully.
             current_attempt = 0
             while True:
                 current_attempt += 1
@@ -213,11 +236,14 @@ class GongConnector(LoadConnector, PollConnector):
                     f"missing_call_ids={missing_call_ids}"
                 )
                 if current_attempt >= self.MAX_CALL_DETAILS_ATTEMPTS:
-                    raise RuntimeError(
-                        f"Attempt count exceeded for _get_call_details_by_ids: "
-                        f"missing_call_ids={missing_call_ids} "
-                        f"max_attempts={self.MAX_CALL_DETAILS_ATTEMPTS}"
+                    logger.error(
+                        f"Giving up on missing call id's after "
+                        f"{self.MAX_CALL_DETAILS_ATTEMPTS} attempts: "
+                        f"missing_call_ids={missing_call_ids} — "
+                        f"proceeding with {len(call_details_map)} of "
+                        f"{len(transcript_call_ids)} calls"
                     )
+                    break
 
                 wait_seconds = self.CALL_DETAILS_DELAY * pow(2, current_attempt - 1)
                 logger.warning(

backend/onyx/db/enums.py

@@ -186,6 +186,7 @@ class EmbeddingPrecision(str, PyEnum):
 
 class UserFileStatus(str, PyEnum):
     PROCESSING = "PROCESSING"
+    INDEXING = "INDEXING"
     COMPLETED = "COMPLETED"
     FAILED = "FAILED"
     CANCELED = "CANCELED"

backend/onyx/db/image_generation.py

@@ -202,7 +202,6 @@ def create_default_image_gen_config_from_api_key(
             api_key=api_key,
             api_base=None,
             api_version=None,
-            default_model_name=model_name,
             deployment_name=None,
             is_public=True,
         )

backend/onyx/db/llm.py

@@ -213,11 +213,29 @@ def upsert_llm_provider(
     llm_provider_upsert_request: LLMProviderUpsertRequest,
     db_session: Session,
 ) -> LLMProviderView:
-    existing_llm_provider = fetch_existing_llm_provider(
-        name=llm_provider_upsert_request.name, db_session=db_session
-    )
+    existing_llm_provider: LLMProviderModel | None = None
+    if llm_provider_upsert_request.id:
+        existing_llm_provider = fetch_existing_llm_provider_by_id(
+            id=llm_provider_upsert_request.id, db_session=db_session
+        )
+        if not existing_llm_provider:
+            raise ValueError(
+                f"LLM provider with id {llm_provider_upsert_request.id} not found"
+            )
 
-    if not existing_llm_provider:
+        if existing_llm_provider.name != llm_provider_upsert_request.name:
+            raise ValueError(
+                f"LLM provider with id {llm_provider_upsert_request.id} name change not allowed"
+            )
+    else:
+        existing_llm_provider = fetch_existing_llm_provider(
+            name=llm_provider_upsert_request.name, db_session=db_session
+        )
+        if existing_llm_provider:
+            raise ValueError(
+                f"LLM provider with name '{llm_provider_upsert_request.name}'"
+                " already exists"
+            )
         existing_llm_provider = LLMProviderModel(name=llm_provider_upsert_request.name)
         db_session.add(existing_llm_provider)
 
@@ -238,11 +256,7 @@ def upsert_llm_provider(
     existing_llm_provider.api_base = api_base
     existing_llm_provider.api_version = llm_provider_upsert_request.api_version
     existing_llm_provider.custom_config = custom_config
-    # TODO: Remove default model name on api change
-    # Needed due to /provider/{id}/default endpoint not disclosing the default model name
-    existing_llm_provider.default_model_name = (
-        llm_provider_upsert_request.default_model_name
-    )
+
     existing_llm_provider.is_public = llm_provider_upsert_request.is_public
     existing_llm_provider.is_auto_mode = llm_provider_upsert_request.is_auto_mode
     existing_llm_provider.deployment_name = llm_provider_upsert_request.deployment_name
@@ -306,15 +320,6 @@ def upsert_llm_provider(
                 display_name=model_config.display_name,
             )
 
-    default_model = fetch_default_model(db_session, LLMModelFlowType.CHAT)
-    if default_model and default_model.llm_provider_id == existing_llm_provider.id:
-        _update_default_model(
-            db_session=db_session,
-            provider_id=existing_llm_provider.id,
-            model=existing_llm_provider.default_model_name,
-            flow_type=LLMModelFlowType.CHAT,
-        )
-
     # Make sure the relationship table stays up to date
     update_group_llm_provider_relationships__no_commit(
         llm_provider_id=existing_llm_provider.id,
@@ -488,6 +493,22 @@ def fetch_existing_llm_provider(
     return provider_model
 
 
+def fetch_existing_llm_provider_by_id(
+    id: int, db_session: Session
+) -> LLMProviderModel | None:
+    provider_model = db_session.scalar(
+        select(LLMProviderModel)
+        .where(LLMProviderModel.id == id)
+        .options(
+            selectinload(LLMProviderModel.model_configurations),
+            selectinload(LLMProviderModel.groups),
+            selectinload(LLMProviderModel.personas),
+        )
+    )
+
+    return provider_model
+
+
 def fetch_embedding_provider(
     db_session: Session, provider_type: EmbeddingProvider
 ) -> CloudEmbeddingProviderModel | None:
@@ -604,22 +625,13 @@ def remove_llm_provider__no_commit(db_session: Session, provider_id: int) -> Non
     db_session.flush()
 
 
-def update_default_provider(provider_id: int, db_session: Session) -> None:
-    # Attempt to get the default_model_name from the provider first
-    # TODO: Remove default_model_name check
-    provider = db_session.scalar(
-        select(LLMProviderModel).where(
-            LLMProviderModel.id == provider_id,
-        )
-    )
-
-    if provider is None:
-        raise ValueError(f"LLM Provider with id={provider_id} does not exist")
-
+def update_default_provider(
+    provider_id: int, model_name: str, db_session: Session
+) -> None:
     _update_default_model(
         db_session,
         provider_id,
-        provider.default_model_name,  # type: ignore[arg-type]
+        model_name,
         LLMModelFlowType.CHAT,
     )
 
@@ -805,12 +817,6 @@ def sync_auto_mode_models(
             )
             changes += 1
 
-    # In Auto mode, default model is always set from GitHub config
-    default_model = llm_recommendations.get_default_model(provider.provider)
-    if default_model and provider.default_model_name != default_model.name:
-        provider.default_model_name = default_model.name
-        changes += 1
-
     db_session.commit()
     return changes
 

backend/onyx/db/models.py

@@ -103,7 +103,6 @@ from onyx.utils.encryption import encrypt_string_to_bytes
 from onyx.utils.sensitive import SensitiveValue
 from onyx.utils.headers import HeaderItemDict
 from shared_configs.enums import EmbeddingProvider
-from onyx.context.search.enums import RecencyBiasSetting
 
 # TODO: After anonymous user migration has been deployed, make user_id columns NOT NULL
 # and update Mapped[User | None] relationships to Mapped[User] where needed.
@@ -3265,19 +3264,6 @@ class Persona(Base):
     )
     name: Mapped[str] = mapped_column(String)
     description: Mapped[str] = mapped_column(String)
-    # Number of chunks to pass to the LLM for generation.
-    num_chunks: Mapped[float | None] = mapped_column(Float, nullable=True)
-    chunks_above: Mapped[int] = mapped_column(Integer)
-    chunks_below: Mapped[int] = mapped_column(Integer)
-    # Pass every chunk through LLM for evaluation, fairly expensive
-    # Can be turned off globally by admin, in which case, this setting is ignored
-    llm_relevance_filter: Mapped[bool] = mapped_column(Boolean)
-    # Enables using LLM to extract time and source type filters
-    # Can also be admin disabled globally
-    llm_filter_extraction: Mapped[bool] = mapped_column(Boolean)
-    recency_bias: Mapped[RecencyBiasSetting] = mapped_column(
-        Enum(RecencyBiasSetting, native_enum=False)
-    )
 
     # Allows the persona to specify a specific default LLM model
     # NOTE: only is applied on the actual response generation - is not used for things like
@@ -3304,11 +3290,8 @@ class Persona(Base):
     # Treated specially (cannot be user edited etc.)
     builtin_persona: Mapped[bool] = mapped_column(Boolean, default=False)
 
-    # Default personas are personas created by admins and are automatically added
-    # to all users' assistants list.
-    is_default_persona: Mapped[bool] = mapped_column(
-        Boolean, default=False, nullable=False
-    )
+    # Featured personas are highlighted in the UI
+    featured: Mapped[bool] = mapped_column(Boolean, default=False)
     # controls whether the persona is available to be selected by users
     is_visible: Mapped[bool] = mapped_column(Boolean, default=True)
     # controls the ordering of personas in the UI

backend/onyx/db/persona.py

@@ -18,11 +18,8 @@ from sqlalchemy.orm import Session
 from onyx.access.hierarchy_access import get_user_external_group_ids
 from onyx.auth.schemas import UserRole
 from onyx.configs.app_configs import CURATORS_CANNOT_VIEW_OR_EDIT_NON_OWNED_ASSISTANTS
-from onyx.configs.chat_configs import CONTEXT_CHUNKS_ABOVE
-from onyx.configs.chat_configs import CONTEXT_CHUNKS_BELOW
 from onyx.configs.constants import DEFAULT_PERSONA_ID
 from onyx.configs.constants import NotificationType
-from onyx.context.search.enums import RecencyBiasSetting
 from onyx.db.constants import SLACK_BOT_PERSONA_PREFIX
 from onyx.db.document_access import get_accessible_documents_by_ids
 from onyx.db.models import ConnectorCredentialPair
@@ -254,13 +251,15 @@ def create_update_persona(
     # Permission to actually use these is checked later
 
     try:
-        # Default persona validation
-        if create_persona_request.is_default_persona:
-            # Curators can edit default personas, but not make them
+        # Featured persona validation
+        if create_persona_request.featured:
+
+            # Curators can edit featured personas, but not make them
+            # TODO this will be reworked soon with RBAC permissions feature
             if user.role == UserRole.CURATOR or user.role == UserRole.GLOBAL_CURATOR:
                 pass
             elif user.role != UserRole.ADMIN:
-                raise ValueError("Only admins can make a default persona")
+                raise ValueError("Only admins can make a featured persona")
 
         # Convert incoming string UUIDs to UUID objects for DB operations
         converted_user_file_ids = None
@@ -281,7 +280,6 @@ def create_update_persona(
             document_set_ids=create_persona_request.document_set_ids,
             tool_ids=create_persona_request.tool_ids,
             is_public=create_persona_request.is_public,
-            recency_bias=create_persona_request.recency_bias,
             llm_model_provider_override=create_persona_request.llm_model_provider_override,
             llm_model_version_override=create_persona_request.llm_model_version_override,
             starter_messages=create_persona_request.starter_messages,
@@ -295,10 +293,7 @@ def create_update_persona(
             remove_image=create_persona_request.remove_image,
             search_start_date=create_persona_request.search_start_date,
             label_ids=create_persona_request.label_ids,
-            num_chunks=create_persona_request.num_chunks,
-            llm_relevance_filter=create_persona_request.llm_relevance_filter,
-            llm_filter_extraction=create_persona_request.llm_filter_extraction,
-            is_default_persona=create_persona_request.is_default_persona,
+            featured=create_persona_request.featured,
             user_file_ids=converted_user_file_ids,
             commit=False,
             hierarchy_node_ids=create_persona_request.hierarchy_node_ids,
@@ -874,10 +869,6 @@ def upsert_persona(
     user: User | None,
     name: str,
     description: str,
-    num_chunks: float,
-    llm_relevance_filter: bool,
-    llm_filter_extraction: bool,
-    recency_bias: RecencyBiasSetting,
     llm_model_provider_override: str | None,
     llm_model_version_override: str | None,
     starter_messages: list[StarterMessage] | None,
@@ -898,13 +889,11 @@ def upsert_persona(
     remove_image: bool | None = None,
     search_start_date: datetime | None = None,
     builtin_persona: bool = False,
-    is_default_persona: bool | None = None,
+    featured: bool | None = None,
     label_ids: list[int] | None = None,
     user_file_ids: list[UUID] | None = None,
     hierarchy_node_ids: list[int] | None = None,
     document_ids: list[str] | None = None,
-    chunks_above: int = CONTEXT_CHUNKS_ABOVE,
-    chunks_below: int = CONTEXT_CHUNKS_BELOW,
     replace_base_system_prompt: bool = False,
 ) -> Persona:
     """
@@ -1015,12 +1004,6 @@ def upsert_persona(
         # `default` and `built-in` properties can only be set when creating a persona.
         existing_persona.name = name
         existing_persona.description = description
-        existing_persona.num_chunks = num_chunks
-        existing_persona.chunks_above = chunks_above
-        existing_persona.chunks_below = chunks_below
-        existing_persona.llm_relevance_filter = llm_relevance_filter
-        existing_persona.llm_filter_extraction = llm_filter_extraction
-        existing_persona.recency_bias = recency_bias
         existing_persona.llm_model_provider_override = llm_model_provider_override
         existing_persona.llm_model_version_override = llm_model_version_override
         existing_persona.starter_messages = starter_messages
@@ -1034,10 +1017,8 @@ def upsert_persona(
         if label_ids is not None:
             existing_persona.labels.clear()
             existing_persona.labels = labels or []
-        existing_persona.is_default_persona = (
-            is_default_persona
-            if is_default_persona is not None
-            else existing_persona.is_default_persona
+        existing_persona.featured = (
+            featured if featured is not None else existing_persona.featured
         )
         # Update embedded prompt fields if provided
         if system_prompt is not None:
@@ -1090,12 +1071,6 @@ def upsert_persona(
             is_public=is_public,
             name=name,
             description=description,
-            num_chunks=num_chunks,
-            chunks_above=chunks_above,
-            chunks_below=chunks_below,
-            llm_relevance_filter=llm_relevance_filter,
-            llm_filter_extraction=llm_filter_extraction,
-            recency_bias=recency_bias,
             builtin_persona=builtin_persona,
             system_prompt=system_prompt or "",
             task_prompt=task_prompt or "",
@@ -1111,9 +1086,7 @@ def upsert_persona(
             display_priority=display_priority,
             is_visible=is_visible,
             search_start_date=search_start_date,
-            is_default_persona=(
-                is_default_persona if is_default_persona is not None else False
-            ),
+            featured=(featured if featured is not None else False),
             user_files=user_files or [],
             labels=labels or [],
             hierarchy_nodes=hierarchy_nodes or [],
@@ -1158,9 +1131,9 @@ def delete_old_default_personas(
     db_session.commit()
 
 
-def update_persona_is_default(
+def update_persona_featured(
     persona_id: int,
-    is_default: bool,
+    featured: bool,
     db_session: Session,
     user: User,
 ) -> None:
@@ -1168,7 +1141,7 @@ def update_persona_is_default(
         db_session=db_session, persona_id=persona_id, user=user, get_editable=True
     )
 
-    persona.is_default_persona = is_default
+    persona.featured = featured
     db_session.commit()
 
 

backend/onyx/db/projects.py

@@ -9,8 +9,9 @@ from pydantic import BaseModel
 from pydantic import ConfigDict
 from sqlalchemy import func
 from sqlalchemy.orm import Session
+from starlette.background import BackgroundTasks
 
-from onyx.background.celery.versioned_apps.client import app as client_app
+from onyx.configs.app_configs import DISABLE_VECTOR_DB
 from onyx.configs.constants import FileOrigin
 from onyx.configs.constants import OnyxCeleryPriority
 from onyx.configs.constants import OnyxCeleryQueues
@@ -105,8 +106,8 @@ def upload_files_to_user_files_with_indexing(
     user: User,
     temp_id_map: dict[str, str] | None,
     db_session: Session,
+    background_tasks: BackgroundTasks | None = None,
 ) -> CategorizedFilesResult:
-    # Validate project ownership if a project_id is provided
     if project_id is not None and user is not None:
         if not check_project_ownership(project_id, user.id, db_session):
             raise HTTPException(status_code=404, detail="Project not found")
@@ -127,16 +128,27 @@ def upload_files_to_user_files_with_indexing(
         logger.warning(
             f"File {rejected_file.filename} rejected for {rejected_file.reason}"
         )
-    for user_file in user_files:
-        task = client_app.send_task(
-            OnyxCeleryTask.PROCESS_SINGLE_USER_FILE,
-            kwargs={"user_file_id": user_file.id, "tenant_id": tenant_id},
-            queue=OnyxCeleryQueues.USER_FILE_PROCESSING,
-            priority=OnyxCeleryPriority.HIGH,
-        )
-        logger.info(
-            f"Triggered indexing for user_file_id={user_file.id} with task_id={task.id}"
-        )
+
+    if DISABLE_VECTOR_DB and background_tasks is not None:
+        from onyx.background.task_utils import drain_processing_loop
+
+        background_tasks.add_task(drain_processing_loop, tenant_id)
+        for user_file in user_files:
+            logger.info(f"Queued in-process processing for user_file_id={user_file.id}")
+    else:
+        from onyx.background.celery.versioned_apps.client import app as client_app
+
+        for user_file in user_files:
+            task = client_app.send_task(
+                OnyxCeleryTask.PROCESS_SINGLE_USER_FILE,
+                kwargs={"user_file_id": user_file.id, "tenant_id": tenant_id},
+                queue=OnyxCeleryQueues.USER_FILE_PROCESSING,
+                priority=OnyxCeleryPriority.HIGH,
+            )
+            logger.info(
+                f"Triggered indexing for user_file_id={user_file.id} "
+                f"with task_id={task.id}"
+            )
 
     return CategorizedFilesResult(
         user_files=user_files,

backend/onyx/db/slack_channel_config.py

@@ -5,8 +5,6 @@ from sqlalchemy import select
 from sqlalchemy.orm import joinedload
 from sqlalchemy.orm import Session
 
-from onyx.configs.chat_configs import MAX_CHUNKS_FED_TO_CHAT
-from onyx.context.search.enums import RecencyBiasSetting
 from onyx.db.constants import DEFAULT_PERSONA_SLACK_CHANNEL_NAME
 from onyx.db.constants import SLACK_BOT_PERSONA_PREFIX
 from onyx.db.models import ChannelConfig
@@ -45,8 +43,6 @@ def create_slack_channel_persona(
     channel_name: str | None,
     document_set_ids: list[int],
     existing_persona_id: int | None = None,
-    num_chunks: float = MAX_CHUNKS_FED_TO_CHAT,
-    enable_auto_filters: bool = False,
 ) -> Persona:
     """NOTE: does not commit changes"""
 
@@ -73,17 +69,13 @@ def create_slack_channel_persona(
         system_prompt="",
         task_prompt="",
         datetime_aware=True,
-        num_chunks=num_chunks,
-        llm_relevance_filter=True,
-        llm_filter_extraction=enable_auto_filters,
-        recency_bias=RecencyBiasSetting.AUTO,
         tool_ids=[search_tool.id],
         document_set_ids=document_set_ids,
         llm_model_provider_override=None,
         llm_model_version_override=None,
         starter_messages=None,
         is_public=True,
-        is_default_persona=False,
+        featured=False,
         db_session=db_session,
         commit=False,
     )

backend/onyx/main.py

@@ -37,6 +37,7 @@ from onyx.configs.app_configs import APP_HOST
 from onyx.configs.app_configs import APP_PORT
 from onyx.configs.app_configs import AUTH_RATE_LIMITING_ENABLED
 from onyx.configs.app_configs import AUTH_TYPE
+from onyx.configs.app_configs import DISABLE_VECTOR_DB
 from onyx.configs.app_configs import LOG_ENDPOINT_LATENCY
 from onyx.configs.app_configs import OAUTH_CLIENT_ID
 from onyx.configs.app_configs import OAUTH_CLIENT_SECRET
@@ -254,8 +255,38 @@ def include_auth_router_with_prefix(
     )
 
 
+def validate_no_vector_db_settings() -> None:
+    """Validate that DISABLE_VECTOR_DB is not combined with incompatible settings.
+
+    Raises RuntimeError if DISABLE_VECTOR_DB is set alongside MULTI_TENANT or ENABLE_CRAFT,
+    since these modes require infrastructure that is removed in no-vector-DB deployments.
+    """
+    if not DISABLE_VECTOR_DB:
+        return
+
+    if MULTI_TENANT:
+        raise RuntimeError(
+            "DISABLE_VECTOR_DB cannot be used with MULTI_TENANT. "
+            "Multi-tenant deployments require the vector database for "
+            "per-tenant document indexing and search. Run in single-tenant "
+            "mode when disabling the vector database."
+        )
+
+    from onyx.server.features.build.configs import ENABLE_CRAFT
+
+    if ENABLE_CRAFT:
+        raise RuntimeError(
+            "DISABLE_VECTOR_DB cannot be used with ENABLE_CRAFT. "
+            "Onyx Craft requires background workers for sandbox lifecycle "
+            "management, which are removed in no-vector-DB deployments. "
+            "Disable Craft (ENABLE_CRAFT=false) when disabling the vector database."
+        )
+
+
 @asynccontextmanager
 async def lifespan(app: FastAPI) -> AsyncGenerator[None, None]:  # noqa: ARG001
+    validate_no_vector_db_settings()
+
     # Set recursion limit
     if SYSTEM_RECURSION_LIMIT is not None:
         sys.setrecursionlimit(SYSTEM_RECURSION_LIMIT)
@@ -324,8 +355,20 @@ async def lifespan(app: FastAPI) -> AsyncGenerator[None, None]:  # noqa: ARG001
     if AUTH_RATE_LIMITING_ENABLED:
         await setup_auth_limiter()
 
+    if DISABLE_VECTOR_DB:
+        from onyx.background.periodic_poller import recover_stuck_user_files
+        from onyx.background.periodic_poller import start_periodic_poller
+
+        recover_stuck_user_files(POSTGRES_DEFAULT_SCHEMA)
+        start_periodic_poller(POSTGRES_DEFAULT_SCHEMA)
+
     yield
 
+    if DISABLE_VECTOR_DB:
+        from onyx.background.periodic_poller import stop_periodic_poller
+
+        stop_periodic_poller()
+
     SqlEngine.reset_engine()
 
     if AUTH_RATE_LIMITING_ENABLED:

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

@@ -32,7 +32,7 @@ from onyx.db.persona import get_persona_snapshots_for_user
 from onyx.db.persona import get_persona_snapshots_paginated
 from onyx.db.persona import mark_persona_as_deleted
 from onyx.db.persona import mark_persona_as_not_deleted
-from onyx.db.persona import update_persona_is_default
+from onyx.db.persona import update_persona_featured
 from onyx.db.persona import update_persona_label
 from onyx.db.persona import update_persona_public_status
 from onyx.db.persona import update_persona_shared
@@ -130,8 +130,8 @@ class IsPublicRequest(BaseModel):
     is_public: bool
 
 
-class IsDefaultRequest(BaseModel):
-    is_default_persona: bool
+class IsFeaturedRequest(BaseModel):
+    featured: bool
 
 
 @admin_router.patch("/{persona_id}/visible")
@@ -168,22 +168,22 @@ def patch_user_persona_public_status(
         raise HTTPException(status_code=403, detail=str(e))
 
 
-@admin_router.patch("/{persona_id}/default")
-def patch_persona_default_status(
+@admin_router.patch("/{persona_id}/featured")
+def patch_persona_featured_status(
     persona_id: int,
-    is_default_request: IsDefaultRequest,
+    is_featured_request: IsFeaturedRequest,
     user: User = Depends(current_curator_or_admin_user),
     db_session: Session = Depends(get_session),
 ) -> None:
     try:
-        update_persona_is_default(
+        update_persona_featured(
             persona_id=persona_id,
-            is_default=is_default_request.is_default_persona,
+            featured=is_featured_request.featured,
             db_session=db_session,
             user=user,
         )
     except ValueError as e:
-        logger.exception("Failed to update persona default status")
+        logger.exception("Failed to update persona featured status")
         raise HTTPException(status_code=403, detail=str(e))
 
 

backend/onyx/server/features/persona/models.py

@@ -5,7 +5,6 @@ from pydantic import BaseModel
 from pydantic import Field
 
 from onyx.configs.constants import DocumentSource
-from onyx.context.search.enums import RecencyBiasSetting
 from onyx.db.enums import HierarchyNodeType
 from onyx.db.models import Document
 from onyx.db.models import HierarchyNode
@@ -108,11 +107,7 @@ class PersonaUpsertRequest(BaseModel):
     name: str
     description: str
     document_set_ids: list[int]
-    num_chunks: float
     is_public: bool
-    recency_bias: RecencyBiasSetting
-    llm_filter_extraction: bool
-    llm_relevance_filter: bool
     llm_model_provider_override: str | None = None
     llm_model_version_override: str | None = None
     starter_messages: list[StarterMessage] | None = None
@@ -128,7 +123,7 @@ class PersonaUpsertRequest(BaseModel):
     )
     search_start_date: datetime | None = None
     label_ids: list[int] | None = None
-    is_default_persona: bool = False
+    featured: bool = False
     display_priority: int | None = None
     # Accept string UUIDs from frontend
     user_file_ids: list[str] | None = None
@@ -155,9 +150,6 @@ class MinimalPersonaSnapshot(BaseModel):
     tools: list[ToolSnapshot]
     starter_messages: list[StarterMessage] | None
 
-    llm_relevance_filter: bool
-    llm_filter_extraction: bool
-
     # only show document sets in the UI that the assistant has access to
     document_sets: list[DocumentSetSummary]
     # Counts for knowledge sources (used to determine if search tool should be enabled)
@@ -175,7 +167,7 @@ class MinimalPersonaSnapshot(BaseModel):
     is_public: bool
     is_visible: bool
     display_priority: int | None
-    is_default_persona: bool
+    featured: bool
     builtin_persona: bool
 
     # Used for filtering
@@ -214,8 +206,6 @@ class MinimalPersonaSnapshot(BaseModel):
                 if should_expose_tool_to_fe(tool)
             ],
             starter_messages=persona.starter_messages,
-            llm_relevance_filter=persona.llm_relevance_filter,
-            llm_filter_extraction=persona.llm_filter_extraction,
             document_sets=[
                 DocumentSetSummary.from_model(document_set)
                 for document_set in persona.document_sets
@@ -230,7 +220,7 @@ class MinimalPersonaSnapshot(BaseModel):
             is_public=persona.is_public,
             is_visible=persona.is_visible,
             display_priority=persona.display_priority,
-            is_default_persona=persona.is_default_persona,
+            featured=persona.featured,
             builtin_persona=persona.builtin_persona,
             labels=[PersonaLabelSnapshot.from_model(label) for label in persona.labels],
             owner=(
@@ -252,11 +242,9 @@ class PersonaSnapshot(BaseModel):
     # Return string UUIDs to frontend for consistency
     user_file_ids: list[str]
     display_priority: int | None
-    is_default_persona: bool
+    featured: bool
     builtin_persona: bool
     starter_messages: list[StarterMessage] | None
-    llm_relevance_filter: bool
-    llm_filter_extraction: bool
     tools: list[ToolSnapshot]
     labels: list["PersonaLabelSnapshot"]
     owner: MinimalUserSnapshot | None
@@ -265,7 +253,6 @@ class PersonaSnapshot(BaseModel):
     document_sets: list[DocumentSetSummary]
     llm_model_provider_override: str | None
     llm_model_version_override: str | None
-    num_chunks: float | None
     # Hierarchy nodes attached for scoped search
     hierarchy_nodes: list[HierarchyNodeSnapshot] = Field(default_factory=list)
     # Individual documents attached for scoped search
@@ -289,11 +276,9 @@ class PersonaSnapshot(BaseModel):
             icon_name=persona.icon_name,
             user_file_ids=[str(file.id) for file in persona.user_files],
             display_priority=persona.display_priority,
-            is_default_persona=persona.is_default_persona,
+            featured=persona.featured,
             builtin_persona=persona.builtin_persona,
             starter_messages=persona.starter_messages,
-            llm_relevance_filter=persona.llm_relevance_filter,
-            llm_filter_extraction=persona.llm_filter_extraction,
             tools=[
                 ToolSnapshot.from_model(tool)
                 for tool in persona.tools
@@ -324,7 +309,6 @@ class PersonaSnapshot(BaseModel):
             ],
             llm_model_provider_override=persona.llm_model_provider_override,
             llm_model_version_override=persona.llm_model_version_override,
-            num_chunks=persona.num_chunks,
             system_prompt=persona.system_prompt,
             replace_base_system_prompt=persona.replace_base_system_prompt,
             task_prompt=persona.task_prompt,
@@ -332,12 +316,10 @@ class PersonaSnapshot(BaseModel):
         )
 
 
-# Model with full context on perona's internal settings
+# Model with full context on persona's internal settings
 # This is used for flows which need to know all settings
 class FullPersonaSnapshot(PersonaSnapshot):
     search_start_date: datetime | None = None
-    llm_relevance_filter: bool = False
-    llm_filter_extraction: bool = False
 
     @classmethod
     def from_model(
@@ -360,7 +342,7 @@ class FullPersonaSnapshot(PersonaSnapshot):
             icon_name=persona.icon_name,
             user_file_ids=[str(file.id) for file in persona.user_files],
             display_priority=persona.display_priority,
-            is_default_persona=persona.is_default_persona,
+            featured=persona.featured,
             builtin_persona=persona.builtin_persona,
             starter_messages=persona.starter_messages,
             users=[
@@ -391,10 +373,7 @@ class FullPersonaSnapshot(PersonaSnapshot):
                 DocumentSetSummary.from_model(document_set_model)
                 for document_set_model in persona.document_sets
             ],
-            num_chunks=persona.num_chunks,
             search_start_date=persona.search_start_date,
-            llm_relevance_filter=persona.llm_relevance_filter,
-            llm_filter_extraction=persona.llm_filter_extraction,
             llm_model_provider_override=persona.llm_model_provider_override,
             llm_model_version_override=persona.llm_model_version_override,
             system_prompt=persona.system_prompt,

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

@@ -2,6 +2,7 @@ import json
 from uuid import UUID
 
 from fastapi import APIRouter
+from fastapi import BackgroundTasks
 from fastapi import Depends
 from fastapi import File
 from fastapi import Form
@@ -12,13 +13,7 @@ from pydantic import BaseModel
 from sqlalchemy.orm import Session
 
 from onyx.auth.users import current_user
-from onyx.background.celery.tasks.user_file_processing.tasks import (
-    enqueue_user_file_project_sync_task,
-)
-from onyx.background.celery.tasks.user_file_processing.tasks import (
-    get_user_file_project_sync_queue_depth,
-)
-from onyx.background.celery.versioned_apps.client import app as client_app
+from onyx.configs.app_configs import DISABLE_VECTOR_DB
 from onyx.configs.constants import OnyxCeleryPriority
 from onyx.configs.constants import OnyxCeleryQueues
 from onyx.configs.constants import OnyxCeleryTask
@@ -34,7 +29,6 @@ from onyx.db.models import UserProject
 from onyx.db.persona import get_personas_by_ids
 from onyx.db.projects import get_project_token_count
 from onyx.db.projects import upload_files_to_user_files_with_indexing
-from onyx.redis.redis_pool import get_redis_client
 from onyx.server.features.projects.models import CategorizedFilesSnapshot
 from onyx.server.features.projects.models import ChatSessionRequest
 from onyx.server.features.projects.models import TokenCountResponse
@@ -55,7 +49,27 @@ class UserFileDeleteResult(BaseModel):
     assistant_names: list[str] = []
 
 
-def _trigger_user_file_project_sync(user_file_id: UUID, tenant_id: str) -> None:
+def _trigger_user_file_project_sync(
+    user_file_id: UUID,
+    tenant_id: str,
+    background_tasks: BackgroundTasks | None = None,
+) -> None:
+    if DISABLE_VECTOR_DB and background_tasks is not None:
+        from onyx.background.task_utils import drain_project_sync_loop
+
+        background_tasks.add_task(drain_project_sync_loop, tenant_id)
+        logger.info(f"Queued in-process project sync for user_file_id={user_file_id}")
+        return
+
+    from onyx.background.celery.tasks.user_file_processing.tasks import (
+        enqueue_user_file_project_sync_task,
+    )
+    from onyx.background.celery.tasks.user_file_processing.tasks import (
+        get_user_file_project_sync_queue_depth,
+    )
+    from onyx.background.celery.versioned_apps.client import app as client_app
+    from onyx.redis.redis_pool import get_redis_client
+
     queue_depth = get_user_file_project_sync_queue_depth(client_app)
     if queue_depth > USER_FILE_PROJECT_SYNC_MAX_QUEUE_DEPTH:
         logger.warning(
@@ -111,6 +125,7 @@ def create_project(
 
 @router.post("/file/upload", tags=PUBLIC_API_TAGS)
 def upload_user_files(
+    bg_tasks: BackgroundTasks,
     files: list[UploadFile] = File(...),
     project_id: int | None = Form(None),
     temp_id_map: str | None = Form(None),  # JSON string mapping hashed key -> temp_id
@@ -137,12 +152,12 @@ def upload_user_files(
             user=user,
             temp_id_map=parsed_temp_id_map,
             db_session=db_session,
+            background_tasks=bg_tasks if DISABLE_VECTOR_DB else None,
         )
 
         return CategorizedFilesSnapshot.from_result(categorized_files_result)
 
     except Exception as e:
-        # Log error with type, message, and stack for easier debugging
         logger.exception(f"Error uploading files - {type(e).__name__}: {str(e)}")
         raise HTTPException(
             status_code=500,
@@ -192,6 +207,7 @@ def get_files_in_project(
 def unlink_user_file_from_project(
     project_id: int,
     file_id: UUID,
+    bg_tasks: BackgroundTasks,
     user: User = Depends(current_user),
     db_session: Session = Depends(get_session),
 ) -> Response:
@@ -208,7 +224,6 @@ def unlink_user_file_from_project(
     if project is None:
         raise HTTPException(status_code=404, detail="Project not found")
 
-    user_id = user.id
     user_file = (
         db_session.query(UserFile)
         .filter(UserFile.id == file_id, UserFile.user_id == user_id)
@@ -224,7 +239,7 @@ def unlink_user_file_from_project(
         db_session.commit()
 
     tenant_id = get_current_tenant_id()
-    _trigger_user_file_project_sync(user_file.id, tenant_id)
+    _trigger_user_file_project_sync(user_file.id, tenant_id, bg_tasks)
 
     return Response(status_code=204)
 
@@ -237,6 +252,7 @@ def unlink_user_file_from_project(
 def link_user_file_to_project(
     project_id: int,
     file_id: UUID,
+    bg_tasks: BackgroundTasks,
     user: User = Depends(current_user),
     db_session: Session = Depends(get_session),
 ) -> UserFileSnapshot:
@@ -268,7 +284,7 @@ def link_user_file_to_project(
         db_session.commit()
 
     tenant_id = get_current_tenant_id()
-    _trigger_user_file_project_sync(user_file.id, tenant_id)
+    _trigger_user_file_project_sync(user_file.id, tenant_id, bg_tasks)
 
     return UserFileSnapshot.from_model(user_file)
 
@@ -335,7 +351,7 @@ def upsert_project_instructions(
 class ProjectPayload(BaseModel):
     project: UserProjectSnapshot
     files: list[UserFileSnapshot] | None = None
-    persona_id_to_is_default: dict[int, bool] | None = None
+    persona_id_to_featured: dict[int, bool] | None = None
 
 
 @router.get(
@@ -354,13 +370,11 @@ def get_project_details(
         if session.persona_id is not None
     ]
     personas = get_personas_by_ids(persona_ids, db_session)
-    persona_id_to_is_default = {
-        persona.id: persona.is_default_persona for persona in personas
-    }
+    persona_id_to_featured = {persona.id: persona.featured for persona in personas}
     return ProjectPayload(
         project=project,
         files=files,
-        persona_id_to_is_default=persona_id_to_is_default,
+        persona_id_to_featured=persona_id_to_featured,
     )
 
 
@@ -426,6 +440,7 @@ def delete_project(
 @router.delete("/file/{file_id}", tags=PUBLIC_API_TAGS)
 def delete_user_file(
     file_id: UUID,
+    bg_tasks: BackgroundTasks,
     user: User = Depends(current_user),
     db_session: Session = Depends(get_session),
 ) -> UserFileDeleteResult:
@@ -458,15 +473,25 @@ def delete_user_file(
     db_session.commit()
 
     tenant_id = get_current_tenant_id()
-    task = client_app.send_task(
-        OnyxCeleryTask.DELETE_SINGLE_USER_FILE,
-        kwargs={"user_file_id": str(user_file.id), "tenant_id": tenant_id},
-        queue=OnyxCeleryQueues.USER_FILE_DELETE,
-        priority=OnyxCeleryPriority.HIGH,
-    )
-    logger.info(
-        f"Triggered delete for user_file_id={user_file.id} with task_id={task.id}"
-    )
+    if DISABLE_VECTOR_DB:
+        from onyx.background.task_utils import drain_delete_loop
+
+        bg_tasks.add_task(drain_delete_loop, tenant_id)
+        logger.info(f"Queued in-process delete for user_file_id={user_file.id}")
+    else:
+        from onyx.background.celery.versioned_apps.client import app as client_app
+
+        task = client_app.send_task(
+            OnyxCeleryTask.DELETE_SINGLE_USER_FILE,
+            kwargs={"user_file_id": str(user_file.id), "tenant_id": tenant_id},
+            queue=OnyxCeleryQueues.USER_FILE_DELETE,
+            priority=OnyxCeleryPriority.HIGH,
+        )
+        logger.info(
+            f"Triggered delete for user_file_id={user_file.id} "
+            f"with task_id={task.id}"
+        )
+
     return UserFileDeleteResult(
         has_associations=False, project_names=[], assistant_names=[]
     )

backend/onyx/server/kg/api.py

@@ -5,7 +5,6 @@ from sqlalchemy.orm import Session
 from onyx.auth.users import current_admin_user
 from onyx.configs.constants import TMP_DRALPHA_PERSONA_NAME
 from onyx.configs.kg_configs import KG_BETA_ASSISTANT_DESCRIPTION
-from onyx.context.search.enums import RecencyBiasSetting
 from onyx.db.engine.sql_engine import get_session
 from onyx.db.entities import get_entity_stats_by_grounded_source_name
 from onyx.db.entity_type import get_configured_entity_types
@@ -134,11 +133,7 @@ def enable_or_disable_kg(
         system_prompt=KG_BETA_ASSISTANT_SYSTEM_PROMPT,
         task_prompt=KG_BETA_ASSISTANT_TASK_PROMPT,
         datetime_aware=False,
-        num_chunks=25,
-        llm_relevance_filter=False,
         is_public=False,
-        llm_filter_extraction=False,
-        recency_bias=RecencyBiasSetting.NO_DECAY,
         document_set_ids=[],
         tool_ids=[search_tool.id, kg_tool.id],
         llm_model_provider_override=None,
@@ -147,7 +142,7 @@ def enable_or_disable_kg(
         users=[user.id],
         groups=[],
         label_ids=[],
-        is_default_persona=False,
+        featured=False,
         display_priority=0,
         user_file_ids=[],
     )

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

@@ -97,7 +97,6 @@ def _build_llm_provider_request(
             ),  # Only this from source
             api_base=api_base,  # From request
             api_version=api_version,  # From request
-            default_model_name=model_name,
             deployment_name=deployment_name,  # From request
             is_public=True,
             groups=[],
@@ -136,7 +135,6 @@ def _build_llm_provider_request(
         api_key=api_key,
         api_base=api_base,
         api_version=api_version,
-        default_model_name=model_name,
         deployment_name=deployment_name,
         is_public=True,
         groups=[],
@@ -168,7 +166,6 @@ def _create_image_gen_llm_provider__no_commit(
         api_key=provider_request.api_key,
         api_base=provider_request.api_base,
         api_version=provider_request.api_version,
-        default_model_name=provider_request.default_model_name,
         deployment_name=provider_request.deployment_name,
         is_public=provider_request.is_public,
         custom_config=provider_request.custom_config,

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

@@ -22,7 +22,10 @@ from onyx.auth.users import current_chat_accessible_user
 from onyx.db.engine.sql_engine import get_session
 from onyx.db.enums import LLMModelFlowType
 from onyx.db.llm import can_user_access_llm_provider
+from onyx.db.llm import fetch_default_llm_model
+from onyx.db.llm import fetch_default_vision_model
 from onyx.db.llm import fetch_existing_llm_provider
+from onyx.db.llm import fetch_existing_llm_provider_by_id
 from onyx.db.llm import fetch_existing_llm_providers
 from onyx.db.llm import fetch_existing_models
 from onyx.db.llm import fetch_persona_with_groups
@@ -52,11 +55,12 @@ from onyx.llm.well_known_providers.llm_provider_options import (
 )
 from onyx.server.manage.llm.models import BedrockFinalModelResponse
 from onyx.server.manage.llm.models import BedrockModelsRequest
+from onyx.server.manage.llm.models import DefaultModel
 from onyx.server.manage.llm.models import LLMCost
 from onyx.server.manage.llm.models import LLMProviderDescriptor
+from onyx.server.manage.llm.models import LLMProviderResponse
 from onyx.server.manage.llm.models import LLMProviderUpsertRequest
 from onyx.server.manage.llm.models import LLMProviderView
-from onyx.server.manage.llm.models import ModelConfigurationUpsertRequest
 from onyx.server.manage.llm.models import OllamaFinalModelResponse
 from onyx.server.manage.llm.models import OllamaModelDetails
 from onyx.server.manage.llm.models import OllamaModelsRequest
@@ -233,12 +237,9 @@ def test_llm_configuration(
 
     test_api_key = test_llm_request.api_key
     test_custom_config = test_llm_request.custom_config
-    if test_llm_request.name:
-        # NOTE: we are querying by name. we probably should be querying by an invariant id, but
-        # as it turns out the name is not editable in the UI and other code also keys off name,
-        # so we won't rock the boat just yet.
-        existing_provider = fetch_existing_llm_provider(
-            name=test_llm_request.name, db_session=db_session
+    if test_llm_request.id:
+        existing_provider = fetch_existing_llm_provider_by_id(
+            id=test_llm_request.id, db_session=db_session
         )
         if existing_provider:
             test_custom_config = _restore_masked_custom_config_values(
@@ -268,7 +269,7 @@ def test_llm_configuration(
 
     llm = get_llm(
         provider=test_llm_request.provider,
-        model=test_llm_request.default_model_name,
+        model=test_llm_request.model,
         api_key=test_api_key,
         api_base=test_llm_request.api_base,
         api_version=test_llm_request.api_version,
@@ -303,7 +304,7 @@ def list_llm_providers(
     include_image_gen: bool = Query(False),
     _: User = Depends(current_admin_user),
     db_session: Session = Depends(get_session),
-) -> list[LLMProviderView]:
+) -> LLMProviderResponse[LLMProviderView]:
     start_time = datetime.now(timezone.utc)
     logger.debug("Starting to fetch LLM providers")
 
@@ -328,7 +329,15 @@ def list_llm_providers(
     duration = (end_time - start_time).total_seconds()
     logger.debug(f"Completed fetching LLM providers in {duration:.2f} seconds")
 
-    return llm_provider_list
+    return LLMProviderResponse[LLMProviderView].from_models(
+        providers=llm_provider_list,
+        default_text=DefaultModel.from_model_config(
+            fetch_default_llm_model(db_session)
+        ),
+        default_vision=DefaultModel.from_model_config(
+            fetch_default_vision_model(db_session)
+        ),
+    )
 
 
 @admin_router.put("/provider")
@@ -344,18 +353,44 @@ def put_llm_provider(
     # validate request (e.g. if we're intending to create but the name already exists we should throw an error)
     # NOTE: may involve duplicate fetching to Postgres, but we're assuming SQLAlchemy is smart enough to cache
     # the result
-    existing_provider = fetch_existing_llm_provider(
+    existing_provider = None
+    if llm_provider_upsert_request.id:
+        existing_provider = fetch_existing_llm_provider_by_id(
+            id=llm_provider_upsert_request.id, db_session=db_session
+        )
+
+    # 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 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 HTTPException(
+            status_code=400,
+            detail=f"Provider with name={llm_provider_upsert_request.name} already exists",
+        )
+
     if existing_provider and is_creation:
         raise HTTPException(
             status_code=400,
-            detail=f"LLM Provider with name {llm_provider_upsert_request.name} already exists",
+            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 HTTPException(
             status_code=400,
-            detail=f"LLM Provider with name {llm_provider_upsert_request.name} does not exist",
+            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
@@ -393,22 +428,6 @@ def put_llm_provider(
                 deduplicated_personas.append(persona_id)
         llm_provider_upsert_request.personas = deduplicated_personas
 
-    default_model_found = False
-
-    for model_configuration in llm_provider_upsert_request.model_configurations:
-        if model_configuration.name == llm_provider_upsert_request.default_model_name:
-            model_configuration.is_visible = True
-            default_model_found = True
-
-    # TODO: Remove this logic on api change
-    # Believed to be a dead pathway but we want to be safe for now
-    if not default_model_found:
-        llm_provider_upsert_request.model_configurations.append(
-            ModelConfigurationUpsertRequest(
-                name=llm_provider_upsert_request.default_model_name, is_visible=True
-            )
-        )
-
     # the llm api key is sanitized when returned to clients, so the only time we
     # should get a real key is when it is explicitly changed
     if existing_provider and not llm_provider_upsert_request.api_key_changed:
@@ -438,8 +457,8 @@ def put_llm_provider(
             config = fetch_llm_recommendations_from_github()
             if config and llm_provider_upsert_request.provider in config.providers:
                 # Refetch the provider to get the updated model
-                updated_provider = fetch_existing_llm_provider(
-                    name=llm_provider_upsert_request.name, db_session=db_session
+                updated_provider = fetch_existing_llm_provider_by_id(
+                    id=result.id, db_session=db_session
                 )
                 if updated_provider:
                     sync_auto_mode_models(
@@ -469,28 +488,29 @@ def delete_llm_provider(
         raise HTTPException(status_code=404, detail=str(e))
 
 
-@admin_router.post("/provider/{provider_id}/default")
+@admin_router.post("/default")
 def set_provider_as_default(
-    provider_id: int,
+    default_model_request: DefaultModel,
     _: User = Depends(current_admin_user),
     db_session: Session = Depends(get_session),
 ) -> None:
-    update_default_provider(provider_id=provider_id, db_session=db_session)
+    update_default_provider(
+        provider_id=default_model_request.provider_id,
+        model_name=default_model_request.model_name,
+        db_session=db_session,
+    )
 
 
-@admin_router.post("/provider/{provider_id}/default-vision")
+@admin_router.post("/default-vision")
 def set_provider_as_default_vision(
-    provider_id: int,
-    vision_model: str | None = Query(
-        None, description="The default vision model to use"
-    ),
+    default_model: DefaultModel,
     _: User = Depends(current_admin_user),
     db_session: Session = Depends(get_session),
 ) -> None:
-    if vision_model is None:
-        raise HTTPException(status_code=404, detail="Vision model not provided")
     update_default_vision_provider(
-        provider_id=provider_id, vision_model=vision_model, db_session=db_session
+        provider_id=default_model.provider_id,
+        vision_model=default_model.model_name,
+        db_session=db_session,
     )
 
 
@@ -516,7 +536,7 @@ def get_auto_config(
 def get_vision_capable_providers(
     _: User = Depends(current_admin_user),
     db_session: Session = Depends(get_session),
-) -> list[VisionProviderResponse]:
+) -> LLMProviderResponse[VisionProviderResponse]:
     """Return a list of LLM providers and their models that support image input"""
     vision_models = fetch_existing_models(
         db_session=db_session, flow_types=[LLMModelFlowType.VISION]
@@ -545,7 +565,13 @@ def get_vision_capable_providers(
     ]
 
     logger.debug(f"Found {len(vision_provider_response)} vision-capable providers")
-    return vision_provider_response
+
+    return LLMProviderResponse[VisionProviderResponse].from_models(
+        providers=vision_provider_response,
+        default_vision=DefaultModel.from_model_config(
+            fetch_default_vision_model(db_session)
+        ),
+    )
 
 
 """Endpoints for all"""
@@ -555,7 +581,7 @@ def get_vision_capable_providers(
 def list_llm_provider_basics(
     user: User = Depends(current_chat_accessible_user),
     db_session: Session = Depends(get_session),
-) -> list[LLMProviderDescriptor]:
+) -> LLMProviderResponse[LLMProviderDescriptor]:
     """Get LLM providers accessible to the current user.
 
     Returns:
@@ -592,7 +618,15 @@ def list_llm_provider_basics(
         f"Completed fetching {len(accessible_providers)} user-accessible providers in {duration:.2f} seconds"
     )
 
-    return accessible_providers
+    return LLMProviderResponse[LLMProviderDescriptor].from_models(
+        providers=accessible_providers,
+        default_text=DefaultModel.from_model_config(
+            fetch_default_llm_model(db_session)
+        ),
+        default_vision=DefaultModel.from_model_config(
+            fetch_default_vision_model(db_session)
+        ),
+    )
 
 
 def get_valid_model_names_for_persona(
@@ -635,7 +669,7 @@ def list_llm_providers_for_persona(
     persona_id: int,
     user: User = Depends(current_chat_accessible_user),
     db_session: Session = Depends(get_session),
-) -> list[LLMProviderDescriptor]:
+) -> LLMProviderResponse[LLMProviderDescriptor]:
     """Get LLM providers for a specific persona.
 
     Returns providers that the user can access when using this persona:
@@ -682,7 +716,51 @@ def list_llm_providers_for_persona(
         f"Completed fetching {len(llm_provider_list)} LLM providers for persona {persona_id} in {duration:.2f} seconds"
     )
 
-    return llm_provider_list
+    # Get the default model and vision model for the persona
+    # TODO: Port persona's over to use ID
+    persona_default_provider = persona.llm_model_provider_override
+    persona_default_model = persona.llm_model_version_override
+
+    default_text_model = fetch_default_llm_model(db_session)
+    default_vision_model = fetch_default_vision_model(db_session)
+
+    # Build default_text and default_vision using persona overrides when available,
+    # falling back to the global defaults.
+    default_text = DefaultModel.from_model_config(default_text_model)
+    default_vision = DefaultModel.from_model_config(default_vision_model)
+
+    if persona_default_provider:
+        provider = fetch_existing_llm_provider(persona_default_provider, db_session)
+        if provider and can_user_access_llm_provider(
+            provider, user_group_ids, persona, is_admin=is_admin
+        ):
+            if persona_default_model:
+                # Persona specifies both provider and model — use them directly
+                default_text = DefaultModel(
+                    provider_id=provider.id,
+                    model_name=persona_default_model,
+                )
+            else:
+                # Persona specifies only the provider — pick a visible (public) model,
+                # falling back to any model on this provider
+                visible_model = next(
+                    (mc for mc in provider.model_configurations if mc.is_visible),
+                    None,
+                )
+                fallback_model = visible_model or next(
+                    iter(provider.model_configurations), None
+                )
+                if fallback_model:
+                    default_text = DefaultModel(
+                        provider_id=provider.id,
+                        model_name=fallback_model.name,
+                    )
+
+    return LLMProviderResponse[LLMProviderDescriptor].from_models(
+        providers=llm_provider_list,
+        default_text=default_text,
+        default_vision=default_vision,
+    )
 
 
 @admin_router.get("/provider-contextual-cost")

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

@@ -1,5 +1,9 @@
+from __future__ import annotations
+
 from typing import Any
+from typing import Generic
 from typing import TYPE_CHECKING
+from typing import TypeVar
 
 from pydantic import BaseModel
 from pydantic import Field
@@ -21,50 +25,22 @@ if TYPE_CHECKING:
         ModelConfiguration as ModelConfigurationModel,
     )
 
-
-# TODO: Clear this up on api refactor
-# There is still logic that requires sending each providers default model name
-# There is no logic that requires sending the providers default vision model name
-# We only send for the one that is actually the default
-def get_default_llm_model_name(llm_provider_model: "LLMProviderModel") -> str:
-    """Find the default conversation model name for a provider.
-
-    Returns the model name if found, otherwise returns empty string.
-    """
-    for model_config in llm_provider_model.model_configurations:
-        for flow in model_config.llm_model_flows:
-            if flow.is_default and flow.llm_model_flow_type == LLMModelFlowType.CHAT:
-                return model_config.name
-    return ""
-
-
-def get_default_vision_model_name(llm_provider_model: "LLMProviderModel") -> str | None:
-    """Find the default vision model name for a provider.
-
-    Returns the model name if found, otherwise returns None.
-    """
-    for model_config in llm_provider_model.model_configurations:
-        for flow in model_config.llm_model_flows:
-            if flow.is_default and flow.llm_model_flow_type == LLMModelFlowType.VISION:
-                return model_config.name
-    return None
+T = TypeVar("T", "LLMProviderDescriptor", "LLMProviderView", "VisionProviderResponse")
 
 
 class TestLLMRequest(BaseModel):
     # provider level
-    name: str | None = None
+    id: int | None = None
     provider: str
+    model: str
     api_key: str | None = None
     api_base: str | None = None
     api_version: str | None = None
     custom_config: dict[str, str] | None = None
 
     # model level
-    default_model_name: str
     deployment_name: str | None = None
 
-    model_configurations: list["ModelConfigurationUpsertRequest"]
-
     # if try and use the existing API/custom config key
     api_key_changed: bool
     custom_config_changed: bool
@@ -80,13 +56,10 @@ class LLMProviderDescriptor(BaseModel):
     """A descriptor for an LLM provider that can be safely viewed by
     non-admin users. Used when giving a list of available LLMs."""
 
+    id: int
     name: str
     provider: str
     provider_display_name: str  # Human-friendly name like "Claude (Anthropic)"
-    default_model_name: str
-    is_default_provider: bool | None
-    is_default_vision_provider: bool | None
-    default_vision_model: str | None
     model_configurations: list["ModelConfigurationView"]
 
     @classmethod
@@ -99,24 +72,12 @@ class LLMProviderDescriptor(BaseModel):
         )
 
         provider = llm_provider_model.provider
-        default_model_name = get_default_llm_model_name(llm_provider_model)
-        default_vision_model = get_default_vision_model_name(llm_provider_model)
-
-        is_default_provider = bool(default_model_name)
-        is_default_vision_provider = default_vision_model is not None
-
-        default_model_name = (
-            default_model_name or llm_provider_model.default_model_name or ""
-        )
 
         return cls(
+            id=llm_provider_model.id,
             name=llm_provider_model.name,
             provider=provider,
             provider_display_name=get_provider_display_name(provider),
-            default_model_name=default_model_name,
-            is_default_provider=is_default_provider,
-            is_default_vision_provider=is_default_vision_provider,
-            default_vision_model=default_vision_model,
             model_configurations=filter_model_configurations(
                 llm_provider_model.model_configurations, provider
             ),
@@ -130,18 +91,17 @@ class LLMProvider(BaseModel):
     api_base: str | None = None
     api_version: str | None = None
     custom_config: dict[str, str] | None = None
-    default_model_name: str
     is_public: bool = True
     is_auto_mode: bool = False
     groups: list[int] = Field(default_factory=list)
     personas: list[int] = Field(default_factory=list)
     deployment_name: str | None = None
-    default_vision_model: str | None = None
 
 
 class LLMProviderUpsertRequest(LLMProvider):
     # should only be used for a "custom" provider
     # for default providers, the built-in model names are used
+    id: int | None = None
     api_key_changed: bool = False
     custom_config_changed: bool = False
     model_configurations: list["ModelConfigurationUpsertRequest"] = []
@@ -157,8 +117,6 @@ class LLMProviderView(LLMProvider):
     """Stripped down representation of LLMProvider for display / limited access info only"""
 
     id: int
-    is_default_provider: bool | None = None
-    is_default_vision_provider: bool | None = None
     model_configurations: list["ModelConfigurationView"]
 
     @classmethod
@@ -180,16 +138,6 @@ class LLMProviderView(LLMProvider):
 
         provider = llm_provider_model.provider
 
-        default_model_name = get_default_llm_model_name(llm_provider_model)
-        default_vision_model = get_default_vision_model_name(llm_provider_model)
-
-        is_default_provider = bool(default_model_name)
-        is_default_vision_provider = default_vision_model is not None
-
-        default_model_name = (
-            default_model_name or llm_provider_model.default_model_name or ""
-        )
-
         return cls(
             id=llm_provider_model.id,
             name=llm_provider_model.name,
@@ -202,10 +150,6 @@ class LLMProviderView(LLMProvider):
             api_base=llm_provider_model.api_base,
             api_version=llm_provider_model.api_version,
             custom_config=llm_provider_model.custom_config,
-            default_model_name=default_model_name,
-            is_default_provider=is_default_provider,
-            is_default_vision_provider=is_default_vision_provider,
-            default_vision_model=default_vision_model,
             is_public=llm_provider_model.is_public,
             is_auto_mode=llm_provider_model.is_auto_mode,
             groups=groups,
@@ -425,3 +369,38 @@ class OpenRouterFinalModelResponse(BaseModel):
         int | None
     )  # From OpenRouter API context_length (may be missing for some models)
     supports_image_input: bool
+
+
+class DefaultModel(BaseModel):
+    provider_id: int
+    model_name: str
+
+    @classmethod
+    def from_model_config(
+        cls, model_config: ModelConfigurationModel | None
+    ) -> DefaultModel | None:
+        if not model_config:
+            return None
+        return cls(
+            provider_id=model_config.llm_provider_id,
+            model_name=model_config.name,
+        )
+
+
+class LLMProviderResponse(BaseModel, Generic[T]):
+    providers: list[T]
+    default_text: DefaultModel | None = None
+    default_vision: DefaultModel | None = None
+
+    @classmethod
+    def from_models(
+        cls,
+        providers: list[T],
+        default_text: DefaultModel | None = None,
+        default_vision: DefaultModel | None = None,
+    ) -> LLMProviderResponse[T]:
+        return cls(
+            providers=providers,
+            default_text=default_text,
+            default_vision=default_vision,
+        )

backend/onyx/server/manage/slack_bot.py

@@ -198,7 +198,6 @@ def patch_slack_channel_config(
             channel_name=channel_config["channel_name"],
             document_set_ids=slack_channel_config_creation_request.document_sets,
             existing_persona_id=existing_persona_id,
-            enable_auto_filters=slack_channel_config_creation_request.enable_auto_filters,
         ).id
 
     slack_channel_config_model = update_slack_channel_config(

backend/onyx/server/settings/models.py

@@ -19,6 +19,7 @@ class ApplicationStatus(str, Enum):
     PAYMENT_REMINDER = "payment_reminder"
     GRACE_PERIOD = "grace_period"
     GATED_ACCESS = "gated_access"
+    SEAT_LIMIT_EXCEEDED = "seat_limit_exceeded"
 
 
 class Notification(BaseModel):
@@ -82,6 +83,10 @@ class Settings(BaseModel):
     # Default Assistant settings
     disable_default_assistant: bool | None = False
 
+    # Seat usage - populated by license enforcement when seat limit is exceeded
+    seat_count: int | None = None
+    used_seats: int | None = None
+
     # OpenSearch migration
     opensearch_indexing_enabled: bool = False
 

backend/onyx/setup.py

@@ -25,6 +25,7 @@ from onyx.db.enums import EmbeddingPrecision
 from onyx.db.index_attempt import cancel_indexing_attempts_past_model
 from onyx.db.index_attempt import expire_index_attempts
 from onyx.db.llm import fetch_default_llm_model
+from onyx.db.llm import fetch_existing_llm_provider
 from onyx.db.llm import update_default_provider
 from onyx.db.llm import upsert_llm_provider
 from onyx.db.search_settings import get_active_search_settings
@@ -254,14 +255,18 @@ def setup_postgres(db_session: Session) -> None:
         logger.notice("Setting up default OpenAI LLM for dev.")
 
         llm_model = GEN_AI_MODEL_VERSION or "gpt-4o-mini"
+        provider_name = "DevEnvPresetOpenAI"
+        existing = fetch_existing_llm_provider(
+            name=provider_name, db_session=db_session
+        )
         model_req = LLMProviderUpsertRequest(
-            name="DevEnvPresetOpenAI",
+            id=existing.id if existing else None,
+            name=provider_name,
             provider=LlmProviderNames.OPENAI,
             api_key=GEN_AI_API_KEY,
             api_base=None,
             api_version=None,
             custom_config=None,
-            default_model_name=llm_model,
             is_public=True,
             groups=[],
             model_configurations=[
@@ -273,7 +278,9 @@ def setup_postgres(db_session: Session) -> None:
         new_llm_provider = upsert_llm_provider(
             llm_provider_upsert_request=model_req, db_session=db_session
         )
-        update_default_provider(provider_id=new_llm_provider.id, db_session=db_session)
+        update_default_provider(
+            provider_id=new_llm_provider.id, model_name=llm_model, db_session=db_session
+        )
 
 
 def update_default_multipass_indexing(db_session: Session) -> None:

backend/requirements/default.txt

@@ -1217,7 +1217,7 @@ websockets==15.0.1
     # via
     #   fastmcp
     #   google-genai
-werkzeug==3.1.5
+werkzeug==3.1.6
     # via sendgrid
 wrapt==1.17.3
     # via

backend/tests/daily/llm/test_bedrock.py

@@ -17,7 +17,7 @@ def test_bedrock_llm_configuration(client: TestClient) -> None:
     # Prepare the test request payload
     test_request: dict[str, Any] = {
         "provider": LlmProviderNames.BEDROCK,
-        "default_model_name": _DEFAULT_BEDROCK_MODEL,
+        "model": _DEFAULT_BEDROCK_MODEL,
         "api_key": None,
         "api_base": None,
         "api_version": None,
@@ -44,7 +44,7 @@ def test_bedrock_llm_configuration_invalid_key(client: TestClient) -> None:
     # Prepare the test request payload with invalid credentials
     test_request: dict[str, Any] = {
         "provider": LlmProviderNames.BEDROCK,
-        "default_model_name": _DEFAULT_BEDROCK_MODEL,
+        "model": _DEFAULT_BEDROCK_MODEL,
         "api_key": None,
         "api_base": None,
         "api_version": None,

backend/tests/external_dependency_unit/answer/conftest.py

@@ -28,7 +28,6 @@ def ensure_default_llm_provider(db_session: Session) -> None:
             provider=LlmProviderNames.OPENAI,
             api_key=os.environ.get("OPENAI_API_KEY", "test"),
             is_public=True,
-            default_model_name="gpt-4o-mini",
             model_configurations=[
                 ModelConfigurationUpsertRequest(
                     name="gpt-4o-mini",
@@ -41,7 +40,7 @@ def ensure_default_llm_provider(db_session: Session) -> None:
             llm_provider_upsert_request=llm_provider_request,
             db_session=db_session,
         )
-        update_default_provider(provider.id, db_session)
+        update_default_provider(provider.id, "gpt-4o-mini", db_session)
     except Exception as exc:  # pragma: no cover - only hits on duplicate setup issues
         # Rollback to clear the pending transaction state
         db_session.rollback()

backend/tests/external_dependency_unit/answer/test_answer_without_openai.py

@@ -47,7 +47,6 @@ def test_answer_with_only_anthropic_provider(
             name=provider_name,
             provider=LlmProviderNames.ANTHROPIC,
             api_key=anthropic_api_key,
-            default_model_name=anthropic_model,
             is_public=True,
             groups=[],
             model_configurations=[
@@ -59,7 +58,7 @@ def test_answer_with_only_anthropic_provider(
     )
 
     try:
-        update_default_provider(anthropic_provider.id, db_session)
+        update_default_provider(anthropic_provider.id, anthropic_model, db_session)
 
         test_user = create_test_user(db_session, email_prefix="anthropic_only")
         chat_session = create_chat_session(

backend/tests/external_dependency_unit/answer/test_stream_chat_message_objects.py

@@ -9,7 +9,6 @@ from onyx.chat.models import AnswerStreamPart
 from onyx.chat.models import StreamingError
 from onyx.chat.process_message import handle_stream_message_objects
 from onyx.db.chat import create_chat_session
-from onyx.db.models import RecencyBiasSetting
 from onyx.db.models import User
 from onyx.db.persona import upsert_persona
 from onyx.server.query_and_chat.models import MessageResponseIDInfo
@@ -74,10 +73,6 @@ def test_stream_chat_message_objects_without_web_search(
         user=None,  # System persona
         name=f"Test Persona {uuid.uuid4()}",
         description="Test persona with no tools for web search test",
-        num_chunks=10.0,
-        llm_relevance_filter=True,
-        llm_filter_extraction=True,
-        recency_bias=RecencyBiasSetting.BASE_DECAY,
         llm_model_provider_override=None,
         llm_model_version_override=None,
         starter_messages=None,

backend/tests/external_dependency_unit/background/test_periodic_task_claim.py

@@ -0,0 +1,257 @@
+"""External dependency unit tests for periodic task claiming.
+
+Tests ``_try_claim_task`` and ``_try_run_periodic_task`` against real
+PostgreSQL, verifying happy-path behavior and concurrent-access safety.
+
+The claim mechanism uses a transaction-scoped advisory lock + a KVStore
+timestamp for cross-instance dedup.  The DB session is released before
+the task runs, so long-running tasks don't hold connections.
+"""
+
+import time
+from collections.abc import Generator
+from concurrent.futures import as_completed
+from concurrent.futures import ThreadPoolExecutor
+from datetime import datetime
+from datetime import timedelta
+from datetime import timezone
+from unittest.mock import MagicMock
+from uuid import uuid4
+
+import pytest
+
+from onyx.background.periodic_poller import _PeriodicTaskDef
+from onyx.background.periodic_poller import _try_claim_task
+from onyx.background.periodic_poller import _try_run_periodic_task
+from onyx.background.periodic_poller import PERIODIC_TASK_KV_PREFIX
+from onyx.db.engine.sql_engine import get_session_with_current_tenant
+from onyx.db.engine.sql_engine import SqlEngine
+from onyx.db.models import KVStore
+from shared_configs.contextvars import CURRENT_TENANT_ID_CONTEXTVAR
+from tests.external_dependency_unit.constants import TEST_TENANT_ID
+
+_TEST_LOCK_BASE = 90_000
+
+
+@pytest.fixture(scope="module", autouse=True)
+def _init_engine() -> None:
+    SqlEngine.init_engine(pool_size=10, max_overflow=5)
+
+
+def _make_task(
+    *,
+    name: str | None = None,
+    interval: float = 3600,
+    lock_id: int | None = None,
+    run_fn: MagicMock | None = None,
+) -> _PeriodicTaskDef:
+    return _PeriodicTaskDef(
+        name=name or f"test-{uuid4().hex[:8]}",
+        interval_seconds=interval,
+        lock_id=lock_id or _TEST_LOCK_BASE,
+        run_fn=run_fn or MagicMock(),
+    )
+
+
+@pytest.fixture(autouse=True)
+def _cleanup_kv(
+    tenant_context: None,  # noqa: ARG001
+) -> Generator[None, None, None]:
+    yield
+    with get_session_with_current_tenant() as db_session:
+        db_session.query(KVStore).filter(
+            KVStore.key.like(f"{PERIODIC_TASK_KV_PREFIX}test-%")
+        ).delete(synchronize_session=False)
+        db_session.commit()
+
+
+# ------------------------------------------------------------------
+# Happy-path: _try_claim_task
+# ------------------------------------------------------------------
+
+
+class TestClaimHappyPath:
+    def test_first_claim_succeeds(self) -> None:
+        assert _try_claim_task(_make_task()) is True
+
+    def test_first_claim_creates_kv_row(self) -> None:
+        task = _make_task()
+        _try_claim_task(task)
+
+        with get_session_with_current_tenant() as db_session:
+            row = (
+                db_session.query(KVStore)
+                .filter_by(key=PERIODIC_TASK_KV_PREFIX + task.name)
+                .first()
+            )
+        assert row is not None
+        assert row.value is not None
+
+    def test_second_claim_within_interval_fails(self) -> None:
+        task = _make_task(interval=3600)
+        assert _try_claim_task(task) is True
+        assert _try_claim_task(task) is False
+
+    def test_claim_after_interval_succeeds(self) -> None:
+        task = _make_task(interval=1)
+        assert _try_claim_task(task) is True
+
+        kv_key = PERIODIC_TASK_KV_PREFIX + task.name
+        with get_session_with_current_tenant() as db_session:
+            row = db_session.query(KVStore).filter_by(key=kv_key).first()
+            assert row is not None
+            row.value = (datetime.now(timezone.utc) - timedelta(seconds=10)).isoformat()
+            db_session.commit()
+
+        assert _try_claim_task(task) is True
+
+
+# ------------------------------------------------------------------
+# Happy-path: _try_run_periodic_task
+# ------------------------------------------------------------------
+
+
+class TestRunHappyPath:
+    def test_runs_task_and_updates_last_run_at(self) -> None:
+        mock_fn = MagicMock()
+        task = _make_task(run_fn=mock_fn)
+
+        _try_run_periodic_task(task)
+
+        mock_fn.assert_called_once()
+        assert task.last_run_at > 0
+
+    def test_skips_when_in_memory_interval_not_elapsed(self) -> None:
+        mock_fn = MagicMock()
+        task = _make_task(run_fn=mock_fn, interval=3600)
+        task.last_run_at = time.monotonic()
+
+        _try_run_periodic_task(task)
+
+        mock_fn.assert_not_called()
+
+    def test_skips_when_db_claim_blocked(self) -> None:
+        name = f"test-{uuid4().hex[:8]}"
+        lock_id = _TEST_LOCK_BASE + 10
+
+        _try_claim_task(_make_task(name=name, lock_id=lock_id, interval=3600))
+
+        mock_fn = MagicMock()
+        task = _make_task(name=name, lock_id=lock_id, interval=3600, run_fn=mock_fn)
+        _try_run_periodic_task(task)
+
+        mock_fn.assert_not_called()
+
+    def test_task_exception_does_not_propagate(self) -> None:
+        task = _make_task(run_fn=MagicMock(side_effect=RuntimeError("boom")))
+        _try_run_periodic_task(task)
+
+    def test_claim_committed_before_task_runs(self) -> None:
+        """The KV claim must be visible in the DB when run_fn executes."""
+        task_name = f"test-order-{uuid4().hex[:8]}"
+        kv_key = PERIODIC_TASK_KV_PREFIX + task_name
+        claim_visible: list[bool] = []
+
+        def check_claim() -> None:
+            with get_session_with_current_tenant() as db_session:
+                row = db_session.query(KVStore).filter_by(key=kv_key).first()
+                claim_visible.append(row is not None and row.value is not None)
+
+        task = _PeriodicTaskDef(
+            name=task_name,
+            interval_seconds=3600,
+            lock_id=_TEST_LOCK_BASE + 11,
+            run_fn=check_claim,
+        )
+
+        _try_run_periodic_task(task)
+
+        assert claim_visible == [True]
+
+
+# ------------------------------------------------------------------
+# Concurrency: only one claimer should win
+# ------------------------------------------------------------------
+
+
+class TestClaimConcurrency:
+    def test_concurrent_claims_single_winner(self) -> None:
+        """Many threads claim the same task — exactly one should succeed."""
+        num_threads = 20
+        task_name = f"test-race-{uuid4().hex[:8]}"
+        lock_id = _TEST_LOCK_BASE + 20
+
+        def claim() -> bool:
+            CURRENT_TENANT_ID_CONTEXTVAR.set(TEST_TENANT_ID)
+            return _try_claim_task(
+                _PeriodicTaskDef(
+                    name=task_name,
+                    interval_seconds=3600,
+                    lock_id=lock_id,
+                    run_fn=lambda: None,
+                )
+            )
+
+        results: list[bool] = []
+        with ThreadPoolExecutor(max_workers=num_threads) as executor:
+            futures = [executor.submit(claim) for _ in range(num_threads)]
+            for future in as_completed(futures):
+                results.append(future.result())
+
+        winners = sum(1 for r in results if r)
+        assert winners == 1, f"Expected 1 winner, got {winners}"
+
+    def test_concurrent_run_single_execution(self) -> None:
+        """Many threads run the same task — run_fn fires exactly once."""
+        num_threads = 20
+        task_name = f"test-run-race-{uuid4().hex[:8]}"
+        lock_id = _TEST_LOCK_BASE + 21
+        counter = MagicMock()
+
+        def run() -> None:
+            CURRENT_TENANT_ID_CONTEXTVAR.set(TEST_TENANT_ID)
+            _try_run_periodic_task(
+                _PeriodicTaskDef(
+                    name=task_name,
+                    interval_seconds=3600,
+                    lock_id=lock_id,
+                    run_fn=counter,
+                )
+            )
+
+        with ThreadPoolExecutor(max_workers=num_threads) as executor:
+            futures = [executor.submit(run) for _ in range(num_threads)]
+            for future in as_completed(futures):
+                future.result()
+
+        assert (
+            counter.call_count == 1
+        ), f"Expected run_fn called once, got {counter.call_count}"
+
+    def test_no_errors_under_contention(self) -> None:
+        """All threads complete without exceptions under high contention."""
+        num_threads = 30
+        task_name = f"test-err-{uuid4().hex[:8]}"
+        lock_id = _TEST_LOCK_BASE + 22
+        errors: list[Exception] = []
+
+        def claim() -> bool:
+            CURRENT_TENANT_ID_CONTEXTVAR.set(TEST_TENANT_ID)
+            return _try_claim_task(
+                _PeriodicTaskDef(
+                    name=task_name,
+                    interval_seconds=3600,
+                    lock_id=lock_id,
+                    run_fn=lambda: None,
+                )
+            )
+
+        with ThreadPoolExecutor(max_workers=num_threads) as executor:
+            futures = [executor.submit(claim) for _ in range(num_threads)]
+            for future in as_completed(futures):
+                try:
+                    future.result()
+                except Exception as e:
+                    errors.append(e)
+
+        assert errors == [], f"Got {len(errors)} errors: {errors}"

backend/tests/external_dependency_unit/background/test_startup_recovery.py

@@ -0,0 +1,219 @@
+"""External dependency unit tests for startup recovery (Step 10g).
+
+Seeds ``UserFile`` records in stuck states (PROCESSING, DELETING,
+needs_project_sync) then calls ``recover_stuck_user_files`` and verifies
+the drain loops pick them up via ``FOR UPDATE SKIP LOCKED``.
+
+Uses real PostgreSQL (via ``db_session`` / ``tenant_context`` fixtures).
+The per-file ``*_impl`` functions are mocked so no real file store or
+connector is needed — we only verify that recovery finds and dispatches
+the correct files.
+"""
+
+from collections.abc import Generator
+from unittest.mock import MagicMock
+from unittest.mock import patch
+from uuid import uuid4
+
+import pytest
+from sqlalchemy.orm import Session
+
+from onyx.background.periodic_poller import recover_stuck_user_files
+from onyx.db.enums import UserFileStatus
+from onyx.db.models import UserFile
+from tests.external_dependency_unit.conftest import create_test_user
+from tests.external_dependency_unit.constants import TEST_TENANT_ID
+
+# ---------------------------------------------------------------------------
+# Helpers
+# ---------------------------------------------------------------------------
+
+_IMPL_MODULE = "onyx.background.celery.tasks.user_file_processing.tasks"
+
+
+def _create_user_file(
+    db_session: Session,
+    user_id: object,
+    *,
+    status: UserFileStatus = UserFileStatus.PROCESSING,
+    needs_project_sync: bool = False,
+    needs_persona_sync: bool = False,
+) -> UserFile:
+    uf = UserFile(
+        id=uuid4(),
+        user_id=user_id,
+        file_id=f"test_file_{uuid4().hex[:8]}",
+        name=f"test_{uuid4().hex[:8]}.txt",
+        file_type="text/plain",
+        status=status,
+        needs_project_sync=needs_project_sync,
+        needs_persona_sync=needs_persona_sync,
+    )
+    db_session.add(uf)
+    db_session.commit()
+    db_session.refresh(uf)
+    return uf
+
+
+@pytest.fixture()
+def _cleanup_user_files(db_session: Session) -> Generator[list[UserFile], None, None]:
+    """Track created UserFile rows and delete them after each test."""
+    created: list[UserFile] = []
+    yield created
+    for uf in created:
+        existing = db_session.get(UserFile, uf.id)
+        if existing:
+            db_session.delete(existing)
+    db_session.commit()
+
+
+# ---------------------------------------------------------------------------
+# Tests
+# ---------------------------------------------------------------------------
+
+
+class TestRecoverProcessingFiles:
+    """Files in PROCESSING status are re-processed via the processing drain loop."""
+
+    def test_processing_files_recovered(
+        self,
+        db_session: Session,
+        tenant_context: None,  # noqa: ARG002
+        _cleanup_user_files: list[UserFile],
+    ) -> None:
+        user = create_test_user(db_session, "recovery_proc")
+        uf = _create_user_file(db_session, user.id, status=UserFileStatus.PROCESSING)
+        _cleanup_user_files.append(uf)
+
+        mock_impl = MagicMock()
+        with patch(f"{_IMPL_MODULE}.process_user_file_impl", mock_impl):
+            recover_stuck_user_files(TEST_TENANT_ID)
+
+        called_ids = [call.kwargs["user_file_id"] for call in mock_impl.call_args_list]
+        assert (
+            str(uf.id) in called_ids
+        ), f"Expected file {uf.id} to be recovered but got: {called_ids}"
+
+    def test_completed_files_not_recovered(
+        self,
+        db_session: Session,
+        tenant_context: None,  # noqa: ARG002
+        _cleanup_user_files: list[UserFile],
+    ) -> None:
+        user = create_test_user(db_session, "recovery_comp")
+        uf = _create_user_file(db_session, user.id, status=UserFileStatus.COMPLETED)
+        _cleanup_user_files.append(uf)
+
+        mock_impl = MagicMock()
+        with patch(f"{_IMPL_MODULE}.process_user_file_impl", mock_impl):
+            recover_stuck_user_files(TEST_TENANT_ID)
+
+        called_ids = [call.kwargs["user_file_id"] for call in mock_impl.call_args_list]
+        assert (
+            str(uf.id) not in called_ids
+        ), f"COMPLETED file {uf.id} should not have been recovered"
+
+
+class TestRecoverDeletingFiles:
+    """Files in DELETING status are recovered via the delete drain loop."""
+
+    def test_deleting_files_recovered(
+        self,
+        db_session: Session,
+        tenant_context: None,  # noqa: ARG002
+        _cleanup_user_files: list[UserFile],
+    ) -> None:
+        user = create_test_user(db_session, "recovery_del")
+        uf = _create_user_file(db_session, user.id, status=UserFileStatus.DELETING)
+        _cleanup_user_files.append(uf)
+
+        mock_impl = MagicMock()
+        with patch(f"{_IMPL_MODULE}.delete_user_file_impl", mock_impl):
+            recover_stuck_user_files(TEST_TENANT_ID)
+
+        called_ids = [call.kwargs["user_file_id"] for call in mock_impl.call_args_list]
+        assert (
+            str(uf.id) in called_ids
+        ), f"Expected file {uf.id} to be recovered for deletion but got: {called_ids}"
+
+
+class TestRecoverSyncFiles:
+    """Files needing project/persona sync are recovered via the sync drain loop."""
+
+    def test_needs_project_sync_recovered(
+        self,
+        db_session: Session,
+        tenant_context: None,  # noqa: ARG002
+        _cleanup_user_files: list[UserFile],
+    ) -> None:
+        user = create_test_user(db_session, "recovery_sync")
+        uf = _create_user_file(
+            db_session,
+            user.id,
+            status=UserFileStatus.COMPLETED,
+            needs_project_sync=True,
+        )
+        _cleanup_user_files.append(uf)
+
+        mock_impl = MagicMock()
+        with patch(f"{_IMPL_MODULE}.project_sync_user_file_impl", mock_impl):
+            recover_stuck_user_files(TEST_TENANT_ID)
+
+        called_ids = [call.kwargs["user_file_id"] for call in mock_impl.call_args_list]
+        assert (
+            str(uf.id) in called_ids
+        ), f"Expected file {uf.id} to be recovered for sync but got: {called_ids}"
+
+    def test_needs_persona_sync_recovered(
+        self,
+        db_session: Session,
+        tenant_context: None,  # noqa: ARG002
+        _cleanup_user_files: list[UserFile],
+    ) -> None:
+        user = create_test_user(db_session, "recovery_psync")
+        uf = _create_user_file(
+            db_session,
+            user.id,
+            status=UserFileStatus.COMPLETED,
+            needs_persona_sync=True,
+        )
+        _cleanup_user_files.append(uf)
+
+        mock_impl = MagicMock()
+        with patch(f"{_IMPL_MODULE}.project_sync_user_file_impl", mock_impl):
+            recover_stuck_user_files(TEST_TENANT_ID)
+
+        called_ids = [call.kwargs["user_file_id"] for call in mock_impl.call_args_list]
+        assert (
+            str(uf.id) in called_ids
+        ), f"Expected file {uf.id} to be recovered for persona sync but got: {called_ids}"
+
+
+class TestRecoveryMultipleFiles:
+    """Recovery processes all stuck files in one pass, not just the first."""
+
+    def test_multiple_processing_files(
+        self,
+        db_session: Session,
+        tenant_context: None,  # noqa: ARG002
+        _cleanup_user_files: list[UserFile],
+    ) -> None:
+        user = create_test_user(db_session, "recovery_multi")
+        files = []
+        for _ in range(3):
+            uf = _create_user_file(
+                db_session, user.id, status=UserFileStatus.PROCESSING
+            )
+            _cleanup_user_files.append(uf)
+            files.append(uf)
+
+        mock_impl = MagicMock()
+        with patch(f"{_IMPL_MODULE}.process_user_file_impl", mock_impl):
+            recover_stuck_user_files(TEST_TENANT_ID)
+
+        called_ids = {call.kwargs["user_file_id"] for call in mock_impl.call_args_list}
+        expected_ids = {str(uf.id) for uf in files}
+        assert expected_ids.issubset(called_ids), (
+            f"Expected all {len(files)} files to be recovered. "
+            f"Missing: {expected_ids - called_ids}"
+        )

backend/tests/external_dependency_unit/celery/test_persona_file_sync.py

@@ -36,7 +36,6 @@ from onyx.background.celery.tasks.user_file_processing.tasks import (
 from onyx.background.celery.tasks.user_file_processing.tasks import (
     user_file_project_sync_lock_key,
 )
-from onyx.context.search.enums import RecencyBiasSetting
 from onyx.db.enums import UserFileStatus
 from onyx.db.models import Persona
 from onyx.db.models import Persona__UserFile
@@ -86,12 +85,6 @@ def _create_test_persona(
     persona = Persona(
         name=f"Test Persona {uuid4().hex[:8]}",
         description="Test persona",
-        num_chunks=10.0,
-        chunks_above=0,
-        chunks_below=0,
-        llm_relevance_filter=False,
-        llm_filter_extraction=False,
-        recency_bias=RecencyBiasSetting.NO_DECAY,
         system_prompt="You are a test assistant",
         task_prompt="Answer the question",
         tools=[],
@@ -410,10 +403,6 @@ class TestUpsertPersonaMarksSyncFlag:
             user=user,
             name=f"persona-{uuid4().hex[:8]}",
             description="test",
-            num_chunks=10.0,
-            llm_relevance_filter=False,
-            llm_filter_extraction=False,
-            recency_bias=RecencyBiasSetting.NO_DECAY,
             llm_model_provider_override=None,
             llm_model_version_override=None,
             starter_messages=None,
@@ -442,10 +431,6 @@ class TestUpsertPersonaMarksSyncFlag:
             user=user,
             name=f"persona-{uuid4().hex[:8]}",
             description="test",
-            num_chunks=10.0,
-            llm_relevance_filter=False,
-            llm_filter_extraction=False,
-            recency_bias=RecencyBiasSetting.NO_DECAY,
             llm_model_provider_override=None,
             llm_model_version_override=None,
             starter_messages=None,
@@ -461,16 +446,11 @@ class TestUpsertPersonaMarksSyncFlag:
         uf_old.needs_persona_sync = False
         db_session.commit()
 
-        assert persona.num_chunks is not None
         # Now update the persona to swap files
         upsert_persona(
             user=user,
             name=persona.name,
             description=persona.description,
-            num_chunks=persona.num_chunks,
-            llm_relevance_filter=persona.llm_relevance_filter,
-            llm_filter_extraction=persona.llm_filter_extraction,
-            recency_bias=persona.recency_bias,
             llm_model_provider_override=None,
             llm_model_version_override=None,
             starter_messages=None,
@@ -501,10 +481,6 @@ class TestUpsertPersonaMarksSyncFlag:
             user=user,
             name=f"persona-{uuid4().hex[:8]}",
             description="test",
-            num_chunks=10.0,
-            llm_relevance_filter=False,
-            llm_filter_extraction=False,
-            recency_bias=RecencyBiasSetting.NO_DECAY,
             llm_model_provider_override=None,
             llm_model_version_override=None,
             starter_messages=None,
@@ -519,15 +495,10 @@ class TestUpsertPersonaMarksSyncFlag:
         uf.needs_persona_sync = False
         db_session.commit()
 
-        assert persona.num_chunks is not None
         upsert_persona(
             user=user,
             name=persona.name,
             description=persona.description,
-            num_chunks=persona.num_chunks,
-            llm_relevance_filter=persona.llm_relevance_filter,
-            llm_filter_extraction=persona.llm_filter_extraction,
-            recency_bias=persona.recency_bias,
             llm_model_provider_override=None,
             llm_model_version_override=None,
             starter_messages=None,

backend/tests/external_dependency_unit/celery/test_user_file_indexing_adapter.py

@@ -18,7 +18,6 @@ from sqlalchemy.orm import Session
 from onyx.configs.constants import DocumentSource
 from onyx.connectors.models import Document
 from onyx.connectors.models import TextSection
-from onyx.context.search.enums import RecencyBiasSetting
 from onyx.db.enums import UserFileStatus
 from onyx.db.models import Persona
 from onyx.db.models import Persona__UserFile
@@ -58,12 +57,6 @@ def _create_persona(db_session: Session, user: User) -> Persona:
     persona = Persona(
         name=f"Test Persona {uuid4().hex[:8]}",
         description="Test persona",
-        num_chunks=10.0,
-        chunks_above=0,
-        chunks_below=0,
-        llm_relevance_filter=False,
-        llm_filter_extraction=False,
-        recency_bias=RecencyBiasSetting.NO_DECAY,
         system_prompt="test",
         task_prompt="test",
         tools=[],

backend/tests/external_dependency_unit/llm/test_llm_provider.py

@@ -29,6 +29,7 @@ from onyx.server.manage.llm.api import (
     test_llm_configuration as run_test_llm_configuration,
 )
 from onyx.server.manage.llm.models import LLMProviderUpsertRequest
+from onyx.server.manage.llm.models import LLMProviderView
 from onyx.server.manage.llm.models import ModelConfigurationUpsertRequest
 from onyx.server.manage.llm.models import TestLLMRequest as LLMTestRequest
 
@@ -44,15 +45,14 @@ def _create_test_provider(
     db_session: Session,
     name: str,
     api_key: str = "sk-test-key-00000000000000000000000000000000000",
-) -> None:
+) -> LLMProviderView:
     """Helper to create a test LLM provider in the database."""
-    upsert_llm_provider(
+    return upsert_llm_provider(
         LLMProviderUpsertRequest(
             name=name,
             provider=LlmProviderNames.OPENAI,
             api_key=api_key,
             api_key_changed=True,
-            default_model_name="gpt-4o-mini",
             model_configurations=[
                 ModelConfigurationUpsertRequest(name="gpt-4o-mini", is_visible=True)
             ],
@@ -102,17 +102,11 @@ class TestLLMConfigurationEndpoint:
                 # This should complete without exception
                 run_test_llm_configuration(
                     test_llm_request=LLMTestRequest(
-                        name=None,  # New provider (not in DB)
                         provider=LlmProviderNames.OPENAI,
                         api_key="sk-new-test-key-0000000000000000000000000000",
                         api_key_changed=True,
                         custom_config_changed=False,
-                        default_model_name="gpt-4o-mini",
-                        model_configurations=[
-                            ModelConfigurationUpsertRequest(
-                                name="gpt-4o-mini", is_visible=True
-                            )
-                        ],
+                        model="gpt-4o-mini",
                     ),
                     _=_create_mock_admin(),
                     db_session=db_session,
@@ -152,17 +146,11 @@ class TestLLMConfigurationEndpoint:
                 with pytest.raises(HTTPException) as exc_info:
                     run_test_llm_configuration(
                         test_llm_request=LLMTestRequest(
-                            name=None,
                             provider=LlmProviderNames.OPENAI,
                             api_key="sk-invalid-key-00000000000000000000000000",
                             api_key_changed=True,
                             custom_config_changed=False,
-                            default_model_name="gpt-4o-mini",
-                            model_configurations=[
-                                ModelConfigurationUpsertRequest(
-                                    name="gpt-4o-mini", is_visible=True
-                                )
-                            ],
+                            model="gpt-4o-mini",
                         ),
                         _=_create_mock_admin(),
                         db_session=db_session,
@@ -194,7 +182,9 @@ class TestLLMConfigurationEndpoint:
 
         try:
             # First, create the provider in the database
-            _create_test_provider(db_session, provider_name, api_key=original_api_key)
+            provider = _create_test_provider(
+                db_session, provider_name, api_key=original_api_key
+            )
 
             with patch(
                 "onyx.server.manage.llm.api.test_llm", side_effect=mock_test_llm_capture
@@ -202,17 +192,12 @@ class TestLLMConfigurationEndpoint:
                 # Test with api_key_changed=False - should use stored key
                 run_test_llm_configuration(
                     test_llm_request=LLMTestRequest(
-                        name=provider_name,  # Existing provider
+                        id=provider.id,
                         provider=LlmProviderNames.OPENAI,
                         api_key=None,  # Not providing a new key
                         api_key_changed=False,  # Using existing key
                         custom_config_changed=False,
-                        default_model_name="gpt-4o-mini",
-                        model_configurations=[
-                            ModelConfigurationUpsertRequest(
-                                name="gpt-4o-mini", is_visible=True
-                            )
-                        ],
+                        model="gpt-4o-mini",
                     ),
                     _=_create_mock_admin(),
                     db_session=db_session,
@@ -246,7 +231,9 @@ class TestLLMConfigurationEndpoint:
 
         try:
             # First, create the provider in the database
-            _create_test_provider(db_session, provider_name, api_key=original_api_key)
+            provider = _create_test_provider(
+                db_session, provider_name, api_key=original_api_key
+            )
 
             with patch(
                 "onyx.server.manage.llm.api.test_llm", side_effect=mock_test_llm_capture
@@ -254,17 +241,12 @@ class TestLLMConfigurationEndpoint:
                 # Test with api_key_changed=True - should use new key
                 run_test_llm_configuration(
                     test_llm_request=LLMTestRequest(
-                        name=provider_name,  # Existing provider
+                        id=provider.id,
                         provider=LlmProviderNames.OPENAI,
                         api_key=new_api_key,  # Providing a new key
                         api_key_changed=True,  # Key is being changed
                         custom_config_changed=False,
-                        default_model_name="gpt-4o-mini",
-                        model_configurations=[
-                            ModelConfigurationUpsertRequest(
-                                name="gpt-4o-mini", is_visible=True
-                            )
-                        ],
+                        model="gpt-4o-mini",
                     ),
                     _=_create_mock_admin(),
                     db_session=db_session,
@@ -297,7 +279,7 @@ class TestLLMConfigurationEndpoint:
 
         try:
             # First, create the provider in the database with custom_config
-            upsert_llm_provider(
+            provider = upsert_llm_provider(
                 LLMProviderUpsertRequest(
                     name=provider_name,
                     provider=LlmProviderNames.OPENAI,
@@ -305,7 +287,6 @@ class TestLLMConfigurationEndpoint:
                     api_key_changed=True,
                     custom_config=original_custom_config,
                     custom_config_changed=True,
-                    default_model_name="gpt-4o-mini",
                     model_configurations=[
                         ModelConfigurationUpsertRequest(
                             name="gpt-4o-mini", is_visible=True
@@ -321,18 +302,13 @@ class TestLLMConfigurationEndpoint:
                 # Test with custom_config_changed=False - should use stored config
                 run_test_llm_configuration(
                     test_llm_request=LLMTestRequest(
-                        name=provider_name,
+                        id=provider.id,
                         provider=LlmProviderNames.OPENAI,
                         api_key=None,
                         api_key_changed=False,
                         custom_config=None,  # Not providing new config
                         custom_config_changed=False,  # Using existing config
-                        default_model_name="gpt-4o-mini",
-                        model_configurations=[
-                            ModelConfigurationUpsertRequest(
-                                name="gpt-4o-mini", is_visible=True
-                            )
-                        ],
+                        model="gpt-4o-mini",
                     ),
                     _=_create_mock_admin(),
                     db_session=db_session,
@@ -368,17 +344,11 @@ class TestLLMConfigurationEndpoint:
                 for model_name in test_models:
                     run_test_llm_configuration(
                         test_llm_request=LLMTestRequest(
-                            name=None,
                             provider=LlmProviderNames.OPENAI,
                             api_key="sk-test-key-00000000000000000000000000000000000",
                             api_key_changed=True,
                             custom_config_changed=False,
-                            default_model_name=model_name,
-                            model_configurations=[
-                                ModelConfigurationUpsertRequest(
-                                    name=model_name, is_visible=True
-                                )
-                            ],
+                            model=model_name,
                         ),
                         _=_create_mock_admin(),
                         db_session=db_session,
@@ -442,7 +412,6 @@ class TestDefaultProviderEndpoint:
                     provider=LlmProviderNames.OPENAI,
                     api_key=provider_1_api_key,
                     api_key_changed=True,
-                    default_model_name=provider_1_initial_model,
                     model_configurations=[
                         ModelConfigurationUpsertRequest(name="gpt-4", is_visible=True),
                         ModelConfigurationUpsertRequest(name="gpt-4o", is_visible=True),
@@ -452,7 +421,7 @@ class TestDefaultProviderEndpoint:
             )
 
             # Set provider 1 as the default provider explicitly
-            update_default_provider(provider_1.id, db_session)
+            update_default_provider(provider_1.id, provider_1_initial_model, db_session)
 
             # Step 2: Call run_test_default_provider - should use provider 1's default model
             with patch(
@@ -472,7 +441,6 @@ class TestDefaultProviderEndpoint:
                     provider=LlmProviderNames.OPENAI,
                     api_key=provider_2_api_key,
                     api_key_changed=True,
-                    default_model_name=provider_2_default_model,
                     model_configurations=[
                         ModelConfigurationUpsertRequest(
                             name="gpt-4o-mini", is_visible=True
@@ -499,11 +467,11 @@ class TestDefaultProviderEndpoint:
             # Step 5: Update provider 1's default model
             upsert_llm_provider(
                 LLMProviderUpsertRequest(
+                    id=provider_1.id,
                     name=provider_1_name,
                     provider=LlmProviderNames.OPENAI,
                     api_key=provider_1_api_key,
                     api_key_changed=True,
-                    default_model_name=provider_1_updated_model,  # Changed
                     model_configurations=[
                         ModelConfigurationUpsertRequest(name="gpt-4", is_visible=True),
                         ModelConfigurationUpsertRequest(name="gpt-4o", is_visible=True),
@@ -512,6 +480,9 @@ class TestDefaultProviderEndpoint:
                 db_session=db_session,
             )
 
+            # Set provider 1's default model to the updated model
+            update_default_provider(provider_1.id, provider_1_updated_model, db_session)
+
             # Step 6: Call run_test_default_provider - should use new model on provider 1
             with patch(
                 "onyx.server.manage.llm.api.test_llm", side_effect=mock_test_llm_capture
@@ -524,7 +495,7 @@ class TestDefaultProviderEndpoint:
             captured_llms.clear()
 
             # Step 7: Change the default provider to provider 2
-            update_default_provider(provider_2.id, db_session)
+            update_default_provider(provider_2.id, provider_2_default_model, db_session)
 
             # Step 8: Call run_test_default_provider - should use provider 2
             with patch(
@@ -596,7 +567,6 @@ class TestDefaultProviderEndpoint:
                     provider=LlmProviderNames.OPENAI,
                     api_key="sk-test-key-00000000000000000000000000000000000",
                     api_key_changed=True,
-                    default_model_name="gpt-4o-mini",
                     model_configurations=[
                         ModelConfigurationUpsertRequest(
                             name="gpt-4o-mini", is_visible=True
@@ -605,7 +575,7 @@ class TestDefaultProviderEndpoint:
                 ),
                 db_session=db_session,
             )
-            update_default_provider(provider.id, db_session)
+            update_default_provider(provider.id, "gpt-4o-mini", db_session)
 
             # Test should fail
             with patch(

backend/tests/external_dependency_unit/llm/test_llm_provider_api_base.py

@@ -49,7 +49,6 @@ def _create_test_provider(
             api_key_changed=True,
             api_base=api_base,
             custom_config=custom_config,
-            default_model_name="gpt-4o-mini",
             model_configurations=[
                 ModelConfigurationUpsertRequest(name="gpt-4o-mini", is_visible=True)
             ],
@@ -91,14 +90,14 @@ class TestLLMProviderChanges:
         the API key should be blocked.
         """
         try:
-            _create_test_provider(db_session, provider_name)
+            provider = _create_test_provider(db_session, provider_name)
 
             with patch("onyx.server.manage.llm.api.MULTI_TENANT", True):
                 update_request = LLMProviderUpsertRequest(
+                    id=provider.id,
                     name=provider_name,
                     provider=LlmProviderNames.OPENAI,
                     api_base="https://attacker.example.com",
-                    default_model_name="gpt-4o-mini",
                 )
 
                 with pytest.raises(HTTPException) as exc_info:
@@ -125,16 +124,16 @@ class TestLLMProviderChanges:
         Changing api_base IS allowed when the API key is also being changed.
         """
         try:
-            _create_test_provider(db_session, provider_name)
+            provider = _create_test_provider(db_session, provider_name)
 
             with patch("onyx.server.manage.llm.api.MULTI_TENANT", True):
                 update_request = LLMProviderUpsertRequest(
+                    id=provider.id,
                     name=provider_name,
                     provider=LlmProviderNames.OPENAI,
                     api_key="sk-new-key-00000000000000000000000000000000000",
                     api_key_changed=True,
                     api_base="https://custom-endpoint.example.com/v1",
-                    default_model_name="gpt-4o-mini",
                 )
 
                 result = put_llm_provider(
@@ -159,14 +158,16 @@ class TestLLMProviderChanges:
         original_api_base = "https://original.example.com/v1"
 
         try:
-            _create_test_provider(db_session, provider_name, api_base=original_api_base)
+            provider = _create_test_provider(
+                db_session, provider_name, api_base=original_api_base
+            )
 
             with patch("onyx.server.manage.llm.api.MULTI_TENANT", True):
                 update_request = LLMProviderUpsertRequest(
+                    id=provider.id,
                     name=provider_name,
                     provider=LlmProviderNames.OPENAI,
                     api_base=original_api_base,
-                    default_model_name="gpt-4o-mini",
                 )
 
                 result = put_llm_provider(
@@ -190,14 +191,14 @@ class TestLLMProviderChanges:
         changes. This allows model-only updates when provider has no custom base URL.
         """
         try:
-            _create_test_provider(db_session, provider_name, api_base=None)
+            view = _create_test_provider(db_session, provider_name, api_base=None)
 
             with patch("onyx.server.manage.llm.api.MULTI_TENANT", True):
                 update_request = LLMProviderUpsertRequest(
+                    id=view.id,
                     name=provider_name,
                     provider=LlmProviderNames.OPENAI,
                     api_base="",
-                    default_model_name="gpt-4o-mini",
                 )
 
                 result = put_llm_provider(
@@ -223,14 +224,16 @@ class TestLLMProviderChanges:
         original_api_base = "https://original.example.com/v1"
 
         try:
-            _create_test_provider(db_session, provider_name, api_base=original_api_base)
+            provider = _create_test_provider(
+                db_session, provider_name, api_base=original_api_base
+            )
 
             with patch("onyx.server.manage.llm.api.MULTI_TENANT", True):
                 update_request = LLMProviderUpsertRequest(
+                    id=provider.id,
                     name=provider_name,
                     provider=LlmProviderNames.OPENAI,
                     api_base=None,
-                    default_model_name="gpt-4o-mini",
                 )
 
                 with pytest.raises(HTTPException) as exc_info:
@@ -259,14 +262,14 @@ class TestLLMProviderChanges:
         users have full control over their deployment.
         """
         try:
-            _create_test_provider(db_session, provider_name)
+            provider = _create_test_provider(db_session, provider_name)
 
             with patch("onyx.server.manage.llm.api.MULTI_TENANT", False):
                 update_request = LLMProviderUpsertRequest(
+                    id=provider.id,
                     name=provider_name,
                     provider=LlmProviderNames.OPENAI,
                     api_base="https://custom.example.com/v1",
-                    default_model_name="gpt-4o-mini",
                 )
 
                 result = put_llm_provider(
@@ -297,7 +300,6 @@ class TestLLMProviderChanges:
                     api_key="sk-new-key-00000000000000000000000000000000000",
                     api_key_changed=True,
                     api_base="https://custom.example.com/v1",
-                    default_model_name="gpt-4o-mini",
                 )
 
                 result = put_llm_provider(
@@ -322,7 +324,7 @@ class TestLLMProviderChanges:
         redirect LLM API requests).
         """
         try:
-            _create_test_provider(
+            provider = _create_test_provider(
                 db_session,
                 provider_name,
                 custom_config={"SOME_CONFIG": "original_value"},
@@ -330,11 +332,11 @@ class TestLLMProviderChanges:
 
             with patch("onyx.server.manage.llm.api.MULTI_TENANT", True):
                 update_request = LLMProviderUpsertRequest(
+                    id=provider.id,
                     name=provider_name,
                     provider=LlmProviderNames.OPENAI,
                     custom_config={"OPENAI_API_BASE": "https://attacker.example.com"},
                     custom_config_changed=True,
-                    default_model_name="gpt-4o-mini",
                 )
 
                 with pytest.raises(HTTPException) as exc_info:
@@ -362,15 +364,15 @@ class TestLLMProviderChanges:
         without changing the API key.
         """
         try:
-            _create_test_provider(db_session, provider_name)
+            provider = _create_test_provider(db_session, provider_name)
 
             with patch("onyx.server.manage.llm.api.MULTI_TENANT", True):
                 update_request = LLMProviderUpsertRequest(
+                    id=provider.id,
                     name=provider_name,
                     provider=LlmProviderNames.OPENAI,
                     custom_config={"OPENAI_API_BASE": "https://attacker.example.com"},
                     custom_config_changed=True,
-                    default_model_name="gpt-4o-mini",
                 )
 
                 with pytest.raises(HTTPException) as exc_info:
@@ -399,7 +401,7 @@ class TestLLMProviderChanges:
         new_config = {"AWS_REGION_NAME": "us-west-2"}
 
         try:
-            _create_test_provider(
+            provider = _create_test_provider(
                 db_session,
                 provider_name,
                 custom_config={"AWS_REGION_NAME": "us-east-1"},
@@ -407,13 +409,13 @@ class TestLLMProviderChanges:
 
             with patch("onyx.server.manage.llm.api.MULTI_TENANT", True):
                 update_request = LLMProviderUpsertRequest(
+                    id=provider.id,
                     name=provider_name,
                     provider=LlmProviderNames.OPENAI,
                     api_key="sk-new-key-00000000000000000000000000000000000",
                     api_key_changed=True,
                     custom_config_changed=True,
                     custom_config=new_config,
-                    default_model_name="gpt-4o-mini",
                 )
 
                 result = put_llm_provider(
@@ -438,17 +440,17 @@ class TestLLMProviderChanges:
         original_config = {"AWS_REGION_NAME": "us-east-1"}
 
         try:
-            _create_test_provider(
+            provider = _create_test_provider(
                 db_session, provider_name, custom_config=original_config
             )
 
             with patch("onyx.server.manage.llm.api.MULTI_TENANT", True):
                 update_request = LLMProviderUpsertRequest(
+                    id=provider.id,
                     name=provider_name,
                     provider=LlmProviderNames.OPENAI,
                     custom_config=original_config,
                     custom_config_changed=True,
-                    default_model_name="gpt-4o-mini",
                 )
 
                 result = put_llm_provider(
@@ -474,7 +476,7 @@ class TestLLMProviderChanges:
         new_config = {"AWS_REGION_NAME": "eu-west-1"}
 
         try:
-            _create_test_provider(
+            provider = _create_test_provider(
                 db_session,
                 provider_name,
                 custom_config={"AWS_REGION_NAME": "us-east-1"},
@@ -482,10 +484,10 @@ class TestLLMProviderChanges:
 
             with patch("onyx.server.manage.llm.api.MULTI_TENANT", False):
                 update_request = LLMProviderUpsertRequest(
+                    id=provider.id,
                     name=provider_name,
                     provider=LlmProviderNames.OPENAI,
                     custom_config=new_config,
-                    default_model_name="gpt-4o-mini",
                     custom_config_changed=True,
                 )
 
@@ -530,14 +532,8 @@ def test_upload_with_custom_config_then_change(
         with patch("onyx.server.manage.llm.api.test_llm", side_effect=capture_test_llm):
             run_llm_config_test(
                 LLMTestRequest(
-                    name=name,
                     provider=provider_name,
-                    default_model_name=default_model_name,
-                    model_configurations=[
-                        ModelConfigurationUpsertRequest(
-                            name=default_model_name, is_visible=True
-                        )
-                    ],
+                    model=default_model_name,
                     api_key_changed=False,
                     custom_config_changed=True,
                     custom_config=custom_config,
@@ -546,11 +542,10 @@ def test_upload_with_custom_config_then_change(
                 db_session=db_session,
             )
 
-            put_llm_provider(
+            provider = put_llm_provider(
                 llm_provider_upsert_request=LLMProviderUpsertRequest(
                     name=name,
                     provider=provider_name,
-                    default_model_name=default_model_name,
                     custom_config=custom_config,
                     model_configurations=[
                         ModelConfigurationUpsertRequest(
@@ -569,14 +564,9 @@ def test_upload_with_custom_config_then_change(
             # Turn auto mode off
             run_llm_config_test(
                 LLMTestRequest(
-                    name=name,
+                    id=provider.id,
                     provider=provider_name,
-                    default_model_name=default_model_name,
-                    model_configurations=[
-                        ModelConfigurationUpsertRequest(
-                            name=default_model_name, is_visible=True
-                        )
-                    ],
+                    model=default_model_name,
                     api_key_changed=False,
                     custom_config_changed=False,
                 ),
@@ -586,9 +576,9 @@ def test_upload_with_custom_config_then_change(
 
             put_llm_provider(
                 llm_provider_upsert_request=LLMProviderUpsertRequest(
+                    id=provider.id,
                     name=name,
                     provider=provider_name,
-                    default_model_name=default_model_name,
                     model_configurations=[
                         ModelConfigurationUpsertRequest(
                             name=default_model_name, is_visible=True
@@ -616,13 +606,13 @@ def test_upload_with_custom_config_then_change(
                 )
 
             # Check inside the database and check that custom_config is the same as the original
-            provider = fetch_existing_llm_provider(name=name, db_session=db_session)
-            if not provider:
+            db_provider = fetch_existing_llm_provider(name=name, db_session=db_session)
+            if not db_provider:
                 assert False, "Provider not found in the database"
 
-            assert provider.custom_config == custom_config, (
+            assert db_provider.custom_config == custom_config, (
                 f"Expected custom_config {custom_config}, "
-                f"but got {provider.custom_config}"
+                f"but got {db_provider.custom_config}"
             )
     finally:
         db_session.rollback()
@@ -642,11 +632,10 @@ def test_preserves_masked_sensitive_custom_config_on_provider_update(
     }
 
     try:
-        put_llm_provider(
+        view = put_llm_provider(
             llm_provider_upsert_request=LLMProviderUpsertRequest(
                 name=name,
                 provider=provider,
-                default_model_name=default_model_name,
                 custom_config=original_custom_config,
                 model_configurations=[
                     ModelConfigurationUpsertRequest(
@@ -665,9 +654,9 @@ def test_preserves_masked_sensitive_custom_config_on_provider_update(
         with patch("onyx.server.manage.llm.api.MULTI_TENANT", False):
             put_llm_provider(
                 llm_provider_upsert_request=LLMProviderUpsertRequest(
+                    id=view.id,
                     name=name,
                     provider=provider,
-                    default_model_name=default_model_name,
                     custom_config={
                         "vertex_credentials": _mask_string(
                             original_custom_config["vertex_credentials"]
@@ -706,7 +695,7 @@ def test_preserves_masked_sensitive_custom_config_on_test_request(
 ) -> None:
     """LLM test should restore masked sensitive custom config values before invocation."""
     name = f"test-provider-vertex-test-{uuid4().hex[:8]}"
-    provider = LlmProviderNames.VERTEX_AI.value
+    provider_name = LlmProviderNames.VERTEX_AI.value
     default_model_name = "gemini-2.5-pro"
     original_custom_config = {
         "vertex_credentials": '{"type":"service_account","private_key":"REAL_PRIVATE_KEY"}',
@@ -719,11 +708,10 @@ def test_preserves_masked_sensitive_custom_config_on_test_request(
         return ""
 
     try:
-        put_llm_provider(
+        provider = put_llm_provider(
             llm_provider_upsert_request=LLMProviderUpsertRequest(
                 name=name,
-                provider=provider,
-                default_model_name=default_model_name,
+                provider=provider_name,
                 custom_config=original_custom_config,
                 model_configurations=[
                     ModelConfigurationUpsertRequest(
@@ -742,14 +730,9 @@ def test_preserves_masked_sensitive_custom_config_on_test_request(
         with patch("onyx.server.manage.llm.api.test_llm", side_effect=capture_test_llm):
             run_llm_config_test(
                 LLMTestRequest(
-                    name=name,
-                    provider=provider,
-                    default_model_name=default_model_name,
-                    model_configurations=[
-                        ModelConfigurationUpsertRequest(
-                            name=default_model_name, is_visible=True
-                        )
-                    ],
+                    id=provider.id,
+                    provider=provider_name,
+                    model=default_model_name,
                     api_key_changed=False,
                     custom_config_changed=True,
                     custom_config={

backend/tests/external_dependency_unit/llm/test_llm_provider_auto_mode.py

@@ -15,9 +15,11 @@ import pytest
 from sqlalchemy.orm import Session
 
 from onyx.db.enums import LLMModelFlowType
+from onyx.db.llm import fetch_auto_mode_providers
 from onyx.db.llm import fetch_default_llm_model
 from onyx.db.llm import fetch_existing_llm_provider
 from onyx.db.llm import fetch_existing_llm_providers
+from onyx.db.llm import fetch_llm_provider_view
 from onyx.db.llm import remove_llm_provider
 from onyx.db.llm import sync_auto_mode_models
 from onyx.db.llm import update_default_provider
@@ -135,7 +137,6 @@ class TestAutoModeSyncFeature:
                         api_key="sk-test-key-00000000000000000000000000000000000",
                         api_key_changed=True,
                         is_auto_mode=True,
-                        default_model_name=expected_default_model,
                         model_configurations=[],  # No model configs provided
                     ),
                     is_creation=True,
@@ -163,13 +164,8 @@ class TestAutoModeSyncFeature:
                 if mc.name in all_expected_models:
                     assert mc.is_visible is True, f"Model '{mc.name}' should be visible"
 
-            # Verify the default model was set correctly
-            assert (
-                provider.default_model_name == expected_default_model
-            ), f"Default model should be '{expected_default_model}'"
-
             # Step 4: Set the provider as default
-            update_default_provider(provider.id, db_session)
+            update_default_provider(provider.id, expected_default_model, db_session)
 
             # Step 5: Fetch the default provider and verify
             default_model = fetch_default_llm_model(db_session)
@@ -238,7 +234,6 @@ class TestAutoModeSyncFeature:
                         api_key="sk-test-key-00000000000000000000000000000000000",
                         api_key_changed=True,
                         is_auto_mode=True,
-                        default_model_name="gpt-4o",
                         model_configurations=[],
                     ),
                     is_creation=True,
@@ -317,7 +312,6 @@ class TestAutoModeSyncFeature:
                     api_key="sk-test-key-00000000000000000000000000000000000",
                     api_key_changed=True,
                     is_auto_mode=False,  # Not in auto mode initially
-                    default_model_name="gpt-4",
                     model_configurations=initial_models,
                 ),
                 is_creation=True,
@@ -326,13 +320,13 @@ class TestAutoModeSyncFeature:
             )
 
             # Verify initial state: all models are visible
-            provider = fetch_existing_llm_provider(
+            initial_provider = fetch_existing_llm_provider(
                 name=provider_name, db_session=db_session
             )
-            assert provider is not None
-            assert provider.is_auto_mode is False
+            assert initial_provider is not None
+            assert initial_provider.is_auto_mode is False
 
-            for mc in provider.model_configurations:
+            for mc in initial_provider.model_configurations:
                 assert (
                     mc.is_visible is True
                 ), f"Initial model '{mc.name}' should be visible"
@@ -344,12 +338,12 @@ class TestAutoModeSyncFeature:
             ):
                 put_llm_provider(
                     llm_provider_upsert_request=LLMProviderUpsertRequest(
+                        id=initial_provider.id,
                         name=provider_name,
                         provider=LlmProviderNames.OPENAI,
                         api_key=None,  # Not changing API key
                         api_key_changed=False,
                         is_auto_mode=True,  # Now enabling auto mode
-                        default_model_name=auto_mode_default,
                         model_configurations=[],  # Auto mode will sync from config
                     ),
                     is_creation=False,  # This is an update
@@ -360,15 +354,15 @@ class TestAutoModeSyncFeature:
             # Step 3: Verify model visibility after auto mode transition
             # Expire session cache to force fresh fetch after sync_auto_mode_models committed
             db_session.expire_all()
-            provider = fetch_existing_llm_provider(
-                name=provider_name, db_session=db_session
+            provider_view = fetch_llm_provider_view(
+                provider_name=provider_name, db_session=db_session
             )
-            assert provider is not None
-            assert provider.is_auto_mode is True
+            assert provider_view is not None
+            assert provider_view.is_auto_mode is True
 
             # Build a map of model name -> visibility
             model_visibility = {
-                mc.name: mc.is_visible for mc in provider.model_configurations
+                mc.name: mc.is_visible for mc in provider_view.model_configurations
             }
 
             # Models in auto mode config should be visible
@@ -388,9 +382,6 @@ class TestAutoModeSyncFeature:
                         model_visibility[model_name] is False
                     ), f"Model '{model_name}' not in auto config should NOT be visible"
 
-            # Verify the default model was updated
-            assert provider.default_model_name == auto_mode_default
-
         finally:
             db_session.rollback()
             _cleanup_provider(db_session, provider_name)
@@ -432,8 +423,12 @@ class TestAutoModeSyncFeature:
                         api_key="sk-test-key-00000000000000000000000000000000000",
                         api_key_changed=True,
                         is_auto_mode=True,
-                        default_model_name="gpt-4o",
-                        model_configurations=[],
+                        model_configurations=[
+                            ModelConfigurationUpsertRequest(
+                                name="gpt-4o",
+                                is_visible=True,
+                            )
+                        ],
                     ),
                     is_creation=True,
                     _=_create_mock_admin(),
@@ -535,7 +530,6 @@ class TestAutoModeSyncFeature:
                         api_key=provider_1_api_key,
                         api_key_changed=True,
                         is_auto_mode=True,
-                        default_model_name=provider_1_default_model,
                         model_configurations=[],
                     ),
                     is_creation=True,
@@ -549,7 +543,7 @@ class TestAutoModeSyncFeature:
                 name=provider_1_name, db_session=db_session
             )
             assert provider_1 is not None
-            update_default_provider(provider_1.id, db_session)
+            update_default_provider(provider_1.id, provider_1_default_model, db_session)
 
             with patch(
                 "onyx.server.manage.llm.api.fetch_llm_recommendations_from_github",
@@ -563,7 +557,6 @@ class TestAutoModeSyncFeature:
                         api_key=provider_2_api_key,
                         api_key_changed=True,
                         is_auto_mode=True,
-                        default_model_name=provider_2_default_model,
                         model_configurations=[],
                     ),
                     is_creation=True,
@@ -584,7 +577,7 @@ class TestAutoModeSyncFeature:
                 name=provider_2_name, db_session=db_session
             )
             assert provider_2 is not None
-            update_default_provider(provider_2.id, db_session)
+            update_default_provider(provider_2.id, provider_2_default_model, db_session)
 
             # Step 5: Verify provider 2 is now the default
             db_session.expire_all()
@@ -644,7 +637,6 @@ class TestAutoModeMissingFlows:
                     api_key="sk-test-key-00000000000000000000000000000000000",
                     api_key_changed=True,
                     is_auto_mode=True,
-                    default_model_name="gpt-4o",
                     model_configurations=[],
                 ),
                 is_creation=True,
@@ -701,3 +693,364 @@ class TestAutoModeMissingFlows:
         finally:
             db_session.rollback()
             _cleanup_provider(db_session, provider_name)
+
+
+class TestAutoModeTransitionsAndResync:
+    """Tests for auto/manual transitions, config evolution, and sync idempotency."""
+
+    def test_auto_to_manual_mode_preserves_models_and_stops_syncing(
+        self,
+        db_session: Session,
+        provider_name: str,
+    ) -> None:
+        """Disabling auto mode should preserve the current model list and
+        prevent future syncs from altering visibility.
+
+        Steps:
+        1. Create provider in auto mode — models synced from config.
+        2. Update provider to manual mode (is_auto_mode=False).
+        3. Verify all models remain with unchanged visibility.
+        4. Call sync_auto_mode_models with a *different* config.
+        5. Verify fetch_auto_mode_providers excludes this provider, so the
+           periodic task would never call sync on it.
+        """
+        initial_config = _create_mock_llm_recommendations(
+            provider=LlmProviderNames.OPENAI,
+            default_model_name="gpt-4o",
+            additional_models=["gpt-4o-mini"],
+        )
+
+        try:
+            # Step 1: Create in auto mode
+            with patch(
+                "onyx.server.manage.llm.api.fetch_llm_recommendations_from_github",
+                return_value=initial_config,
+            ):
+                put_llm_provider(
+                    llm_provider_upsert_request=LLMProviderUpsertRequest(
+                        name=provider_name,
+                        provider=LlmProviderNames.OPENAI,
+                        api_key="sk-test-key-00000000000000000000000000000000000",
+                        api_key_changed=True,
+                        is_auto_mode=True,
+                        model_configurations=[],
+                    ),
+                    is_creation=True,
+                    _=_create_mock_admin(),
+                    db_session=db_session,
+                )
+
+            db_session.expire_all()
+            provider = fetch_existing_llm_provider(
+                name=provider_name, db_session=db_session
+            )
+            assert provider is not None
+            visibility_before = {
+                mc.name: mc.is_visible for mc in provider.model_configurations
+            }
+            assert visibility_before == {"gpt-4o": True, "gpt-4o-mini": True}
+
+            # Step 2: Switch to manual mode
+            put_llm_provider(
+                llm_provider_upsert_request=LLMProviderUpsertRequest(
+                    id=provider.id,
+                    name=provider_name,
+                    provider=LlmProviderNames.OPENAI,
+                    api_key=None,
+                    api_key_changed=False,
+                    is_auto_mode=False,
+                    model_configurations=[
+                        ModelConfigurationUpsertRequest(name="gpt-4o", is_visible=True),
+                        ModelConfigurationUpsertRequest(
+                            name="gpt-4o-mini", is_visible=True
+                        ),
+                    ],
+                ),
+                is_creation=False,
+                _=_create_mock_admin(),
+                db_session=db_session,
+            )
+
+            # Step 3: Models unchanged
+            db_session.expire_all()
+            provider = fetch_existing_llm_provider(
+                name=provider_name, db_session=db_session
+            )
+            assert provider is not None
+            assert provider.is_auto_mode is False
+            visibility_after = {
+                mc.name: mc.is_visible for mc in provider.model_configurations
+            }
+            assert visibility_after == visibility_before
+
+            # Step 4-5: Provider excluded from auto mode queries
+            auto_providers = fetch_auto_mode_providers(db_session)
+            auto_provider_ids = {p.id for p in auto_providers}
+            assert provider.id not in auto_provider_ids
+
+        finally:
+            db_session.rollback()
+            _cleanup_provider(db_session, provider_name)
+
+    def test_resync_adds_new_and_hides_removed_models(
+        self,
+        db_session: Session,
+        provider_name: str,
+    ) -> None:
+        """When the GitHub config changes between syncs, a subsequent sync
+        should add newly listed models and hide models that were removed.
+
+        Steps:
+        1. Create provider in auto mode with config v1: [gpt-4o, gpt-4o-mini].
+        2. Sync with config v2: [gpt-4o, gpt-4-turbo] (gpt-4o-mini removed,
+           gpt-4-turbo added).
+        3. Verify gpt-4o still visible, gpt-4o-mini hidden, gpt-4-turbo added
+           and visible.
+        """
+        config_v1 = _create_mock_llm_recommendations(
+            provider=LlmProviderNames.OPENAI,
+            default_model_name="gpt-4o",
+            additional_models=["gpt-4o-mini"],
+        )
+        config_v2 = _create_mock_llm_recommendations(
+            provider=LlmProviderNames.OPENAI,
+            default_model_name="gpt-4o",
+            additional_models=["gpt-4-turbo"],
+        )
+
+        try:
+            # Step 1: Create with config v1
+            with patch(
+                "onyx.server.manage.llm.api.fetch_llm_recommendations_from_github",
+                return_value=config_v1,
+            ):
+                put_llm_provider(
+                    llm_provider_upsert_request=LLMProviderUpsertRequest(
+                        name=provider_name,
+                        provider=LlmProviderNames.OPENAI,
+                        api_key="sk-test-key-00000000000000000000000000000000000",
+                        api_key_changed=True,
+                        is_auto_mode=True,
+                        model_configurations=[],
+                    ),
+                    is_creation=True,
+                    _=_create_mock_admin(),
+                    db_session=db_session,
+                )
+
+            # Step 2: Re-sync with config v2
+            db_session.expire_all()
+            provider = fetch_existing_llm_provider(
+                name=provider_name, db_session=db_session
+            )
+            assert provider is not None
+
+            changes = sync_auto_mode_models(
+                db_session=db_session,
+                provider=provider,
+                llm_recommendations=config_v2,
+            )
+            assert changes > 0
+
+            # Step 3: Verify
+            db_session.expire_all()
+            provider = fetch_existing_llm_provider(
+                name=provider_name, db_session=db_session
+            )
+            assert provider is not None
+
+            visibility = {
+                mc.name: mc.is_visible for mc in provider.model_configurations
+            }
+
+            # gpt-4o: still in config -> visible
+            assert visibility["gpt-4o"] is True
+            # gpt-4o-mini: removed from config -> hidden (not deleted)
+            assert "gpt-4o-mini" in visibility, "Removed model should still exist in DB"
+            assert visibility["gpt-4o-mini"] is False
+            # gpt-4-turbo: newly added -> visible
+            assert visibility["gpt-4-turbo"] is True
+
+        finally:
+            db_session.rollback()
+            _cleanup_provider(db_session, provider_name)
+
+    def test_sync_is_idempotent(
+        self,
+        db_session: Session,
+        provider_name: str,
+    ) -> None:
+        """Running sync twice with the same config should produce zero
+        changes on the second call."""
+        config = _create_mock_llm_recommendations(
+            provider=LlmProviderNames.OPENAI,
+            default_model_name="gpt-4o",
+            additional_models=["gpt-4o-mini", "gpt-4-turbo"],
+        )
+
+        try:
+            with patch(
+                "onyx.server.manage.llm.api.fetch_llm_recommendations_from_github",
+                return_value=config,
+            ):
+                put_llm_provider(
+                    llm_provider_upsert_request=LLMProviderUpsertRequest(
+                        name=provider_name,
+                        provider=LlmProviderNames.OPENAI,
+                        api_key="sk-test-key-00000000000000000000000000000000000",
+                        api_key_changed=True,
+                        is_auto_mode=True,
+                        model_configurations=[],
+                    ),
+                    is_creation=True,
+                    _=_create_mock_admin(),
+                    db_session=db_session,
+                )
+
+            db_session.expire_all()
+            provider = fetch_existing_llm_provider(
+                name=provider_name, db_session=db_session
+            )
+            assert provider is not None
+
+            # First explicit sync (may report changes if creation already synced)
+            sync_auto_mode_models(
+                db_session=db_session,
+                provider=provider,
+                llm_recommendations=config,
+            )
+
+            # Snapshot state after first sync
+            db_session.expire_all()
+            provider = fetch_existing_llm_provider(
+                name=provider_name, db_session=db_session
+            )
+            assert provider is not None
+            snapshot = {
+                mc.name: (mc.is_visible, mc.display_name)
+                for mc in provider.model_configurations
+            }
+
+            # Second sync — should be a no-op
+            changes = sync_auto_mode_models(
+                db_session=db_session,
+                provider=provider,
+                llm_recommendations=config,
+            )
+            assert (
+                changes == 0
+            ), f"Expected 0 changes on idempotent re-sync, got {changes}"
+
+            # State should be identical
+            db_session.expire_all()
+            provider = fetch_existing_llm_provider(
+                name=provider_name, db_session=db_session
+            )
+            assert provider is not None
+            current = {
+                mc.name: (mc.is_visible, mc.display_name)
+                for mc in provider.model_configurations
+            }
+            assert current == snapshot
+
+        finally:
+            db_session.rollback()
+            _cleanup_provider(db_session, provider_name)
+
+    def test_default_model_hidden_when_removed_from_config(
+        self,
+        db_session: Session,
+        provider_name: str,
+    ) -> None:
+        """When the current default model is removed from the config, sync
+        should hide it. The default model flow row should still exist (it
+        points at the ModelConfiguration), but the model is no longer visible.
+
+        Steps:
+        1. Create provider with config: default=gpt-4o, additional=[gpt-4o-mini].
+        2. Set gpt-4o as the global default.
+        3. Re-sync with config: default=gpt-4o-mini (gpt-4o removed entirely).
+        4. Verify gpt-4o is hidden, gpt-4o-mini is visible, and
+           fetch_default_llm_model still returns a result (the flow row persists).
+        """
+        config_v1 = _create_mock_llm_recommendations(
+            provider=LlmProviderNames.OPENAI,
+            default_model_name="gpt-4o",
+            additional_models=["gpt-4o-mini"],
+        )
+        config_v2 = _create_mock_llm_recommendations(
+            provider=LlmProviderNames.OPENAI,
+            default_model_name="gpt-4o-mini",
+            additional_models=[],
+        )
+
+        try:
+            with patch(
+                "onyx.server.manage.llm.api.fetch_llm_recommendations_from_github",
+                return_value=config_v1,
+            ):
+                put_llm_provider(
+                    llm_provider_upsert_request=LLMProviderUpsertRequest(
+                        name=provider_name,
+                        provider=LlmProviderNames.OPENAI,
+                        api_key="sk-test-key-00000000000000000000000000000000000",
+                        api_key_changed=True,
+                        is_auto_mode=True,
+                        model_configurations=[],
+                    ),
+                    is_creation=True,
+                    _=_create_mock_admin(),
+                    db_session=db_session,
+                )
+
+            # Step 2: Set gpt-4o as global default
+            db_session.expire_all()
+            provider = fetch_existing_llm_provider(
+                name=provider_name, db_session=db_session
+            )
+            assert provider is not None
+            update_default_provider(provider.id, "gpt-4o", db_session)
+
+            default_before = fetch_default_llm_model(db_session)
+            assert default_before is not None
+            assert default_before.name == "gpt-4o"
+
+            # Step 3: Re-sync with config v2 (gpt-4o removed)
+            db_session.expire_all()
+            provider = fetch_existing_llm_provider(
+                name=provider_name, db_session=db_session
+            )
+            assert provider is not None
+
+            changes = sync_auto_mode_models(
+                db_session=db_session,
+                provider=provider,
+                llm_recommendations=config_v2,
+            )
+            assert changes > 0
+
+            # Step 4: Verify visibility
+            db_session.expire_all()
+            provider = fetch_existing_llm_provider(
+                name=provider_name, db_session=db_session
+            )
+            assert provider is not None
+
+            visibility = {
+                mc.name: mc.is_visible for mc in provider.model_configurations
+            }
+            assert visibility["gpt-4o"] is False, "Removed default should be hidden"
+            assert visibility["gpt-4o-mini"] is True, "New default should be visible"
+
+            # The LLMModelFlow row for gpt-4o still exists (is_default=True),
+            # but the model is hidden. fetch_default_llm_model filters on
+            # is_visible=True, so it should NOT return gpt-4o.
+            db_session.expire_all()
+            default_after = fetch_default_llm_model(db_session)
+            assert (
+                default_after is None or default_after.name != "gpt-4o"
+            ), "Hidden model should not be returned as the default"
+
+        finally:
+            db_session.rollback()
+            _cleanup_provider(db_session, provider_name)

backend/tests/external_dependency_unit/llm/test_llm_provider_called.py

@@ -64,7 +64,6 @@ def _create_provider(
             name=name,
             provider=provider,
             api_key="sk-ant-api03-...",
-            default_model_name="claude-3-5-sonnet-20240620",
             is_public=is_public,
             model_configurations=[
                 ModelConfigurationUpsertRequest(
@@ -154,7 +153,9 @@ def test_user_sends_message_to_private_provider(
     )
     _create_provider(db_session, LlmProviderNames.GOOGLE, "private-provider", False)
 
-    update_default_provider(public_provider_id, db_session)
+    update_default_provider(
+        public_provider_id, "claude-3-5-sonnet-20240620", db_session
+    )
 
     try:
         # Create chat session

backend/tests/external_dependency_unit/search_settings/test_search_settings.py

@@ -42,7 +42,6 @@ def _create_llm_provider_and_model(
             name=provider_name,
             provider="openai",
             api_key="test-api-key",
-            default_model_name=model_name,
             model_configurations=[
                 ModelConfigurationUpsertRequest(
                     name=model_name,

backend/tests/external_dependency_unit/slack_bot/test_slack_bot_federated_search.py

@@ -22,7 +22,6 @@ from sqlalchemy.orm import Session
 from slack_sdk.errors import SlackApiError
 
 from onyx.configs.constants import FederatedConnectorSource
-from onyx.context.search.enums import RecencyBiasSetting
 from onyx.context.search.federated.slack_search import fetch_and_cache_channel_metadata
 from onyx.db.models import DocumentSet
 from onyx.db.models import FederatedConnector
@@ -55,11 +54,6 @@ def _create_test_persona_with_slack_config(db_session: Session) -> Persona | Non
     persona = Persona(
         name=f"test_slack_persona_{unique_id}",
         description="Test persona for Slack federated search",
-        chunks_above=0,
-        chunks_below=0,
-        llm_relevance_filter=True,
-        llm_filter_extraction=True,
-        recency_bias=RecencyBiasSetting.AUTO,
         system_prompt="You are a helpful assistant.",
         task_prompt="Answer the user's question based on the provided context.",
     )
@@ -434,7 +428,6 @@ class TestSlackBotFederatedSearch:
                 name=f"test-llm-provider-{uuid4().hex[:8]}",
                 provider=LlmProviderNames.OPENAI,
                 api_key=api_key,
-                default_model_name="gpt-4o",
                 is_public=True,
                 model_configurations=[
                     ModelConfigurationUpsertRequest(
@@ -448,7 +441,7 @@ class TestSlackBotFederatedSearch:
             db_session=db_session,
         )
 
-        update_default_provider(provider_view.id, db_session)
+        update_default_provider(provider_view.id, "gpt-4o", db_session)
 
     def _teardown_common_mocks(self, patches: list) -> None:
         """Stop all patches"""
@@ -819,11 +812,6 @@ def test_slack_channel_config_eager_loads_persona(db_session: Session) -> None:
     persona = Persona(
         name=f"test_eager_load_persona_{unique_id}",
         description="Test persona for eager loading test",
-        chunks_above=0,
-        chunks_below=0,
-        llm_relevance_filter=True,
-        llm_filter_extraction=True,
-        recency_bias=RecencyBiasSetting.AUTO,
         system_prompt="You are a helpful assistant.",
         task_prompt="Answer the user's question.",
     )

backend/tests/external_dependency_unit/tools/test_mcp_passthrough_oauth.py

@@ -21,7 +21,6 @@ import pytest
 from sqlalchemy.orm import Session
 
 from onyx.chat.emitter import get_default_emitter
-from onyx.context.search.enums import RecencyBiasSetting
 from onyx.db.enums import MCPAuthenticationPerformer
 from onyx.db.enums import MCPAuthenticationType
 from onyx.db.enums import MCPTransport
@@ -47,12 +46,6 @@ def _create_test_persona_with_mcp_tool(
     persona = Persona(
         name=f"Test MCP Persona {uuid4().hex[:8]}",
         description="Test persona with MCP tools",
-        num_chunks=10.0,
-        chunks_above=0,
-        chunks_below=0,
-        llm_relevance_filter=False,
-        llm_filter_extraction=False,
-        recency_bias=RecencyBiasSetting.NO_DECAY,
         system_prompt="You are a helpful assistant",
         task_prompt="Answer the user's question",
         tools=tools,

backend/tests/external_dependency_unit/tools/test_oauth_tool_integration.py

@@ -17,7 +17,6 @@ import pytest
 from sqlalchemy.orm import Session
 
 from onyx.chat.emitter import get_default_emitter
-from onyx.context.search.enums import RecencyBiasSetting
 from onyx.db.models import OAuthAccount
 from onyx.db.models import OAuthConfig
 from onyx.db.models import Persona
@@ -57,12 +56,6 @@ def _create_test_persona(db_session: Session, user: User, tools: list[Tool]) ->
     persona = Persona(
         name=f"Test Persona {uuid4().hex[:8]}",
         description="Test persona",
-        num_chunks=10.0,
-        chunks_above=0,
-        chunks_below=0,
-        llm_relevance_filter=False,
-        llm_filter_extraction=False,
-        recency_bias=RecencyBiasSetting.NO_DECAY,
         system_prompt="You are a helpful assistant",
         task_prompt="Answer the user's question",
         tools=tools,

backend/tests/external_dependency_unit/tools/test_python_tool.py

@@ -933,6 +933,7 @@ from unittest.mock import patch
 
 import pytest
 from fastapi import UploadFile
+from fastapi.background import BackgroundTasks
 from sqlalchemy.orm import Session
 from starlette.datastructures import Headers
 
@@ -1139,6 +1140,7 @@ def test_code_interpreter_receives_chat_files(
     # Upload a test CSV
     csv_content = b"name,age,city\nAlice,30,NYC\nBob,25,SF\n"
     result = upload_user_files(
+        bg_tasks=BackgroundTasks(),
         files=[
             UploadFile(
                 file=io.BytesIO(csv_content),

backend/tests/integration/common_utils/managers/llm_provider.py

@@ -4,10 +4,12 @@ from uuid import uuid4
 import requests
 
 from onyx.llm.constants import LlmProviderNames
+from onyx.server.manage.llm.models import DefaultModel
 from onyx.server.manage.llm.models import LLMProviderUpsertRequest
 from onyx.server.manage.llm.models import LLMProviderView
 from onyx.server.manage.llm.models import ModelConfigurationUpsertRequest
 from tests.integration.common_utils.constants import API_SERVER_URL
+from tests.integration.common_utils.constants import GENERAL_HEADERS
 from tests.integration.common_utils.test_models import DATestLLMProvider
 from tests.integration.common_utils.test_models import DATestUser
 
@@ -32,7 +34,6 @@ class LLMProviderManager:
         llm_provider = LLMProviderUpsertRequest(
             name=name or f"test-provider-{uuid4()}",
             provider=provider or LlmProviderNames.OPENAI,
-            default_model_name=default_model_name or "gpt-4o-mini",
             api_key=api_key or os.environ["OPENAI_API_KEY"],
             api_base=api_base,
             api_version=api_version,
@@ -65,7 +66,7 @@ class LLMProviderManager:
             name=response_data["name"],
             provider=response_data["provider"],
             api_key=response_data["api_key"],
-            default_model_name=response_data["default_model_name"],
+            default_model_name=default_model_name or "gpt-4o-mini",
             is_public=response_data["is_public"],
             is_auto_mode=response_data.get("is_auto_mode", False),
             groups=response_data["groups"],
@@ -75,9 +76,19 @@ class LLMProviderManager:
         )
 
         if set_as_default:
+            if default_model_name is None:
+                default_model_name = "gpt-4o-mini"
             set_default_response = requests.post(
-                f"{API_SERVER_URL}/admin/llm/provider/{llm_response.json()['id']}/default",
-                headers=user_performing_action.headers,
+                f"{API_SERVER_URL}/admin/llm/default",
+                json={
+                    "provider_id": response_data["id"],
+                    "model_name": default_model_name,
+                },
+                headers=(
+                    user_performing_action.headers
+                    if user_performing_action
+                    else GENERAL_HEADERS
+                ),
             )
             set_default_response.raise_for_status()
 
@@ -104,7 +115,7 @@ class LLMProviderManager:
             headers=user_performing_action.headers,
         )
         response.raise_for_status()
-        return [LLMProviderView(**ug) for ug in response.json()]
+        return [LLMProviderView(**p) for p in response.json()["providers"]]
 
     @staticmethod
     def verify(
@@ -113,7 +124,11 @@ class LLMProviderManager:
         verify_deleted: bool = False,
     ) -> None:
         all_llm_providers = LLMProviderManager.get_all(user_performing_action)
+        default_model = LLMProviderManager.get_default_model(user_performing_action)
         for fetched_llm_provider in all_llm_providers:
+            model_names = [
+                model.name for model in fetched_llm_provider.model_configurations
+            ]
             if llm_provider.id == fetched_llm_provider.id:
                 if verify_deleted:
                     raise ValueError(
@@ -126,11 +141,30 @@ class LLMProviderManager:
                 if (
                     fetched_llm_groups == llm_provider_groups
                     and llm_provider.provider == fetched_llm_provider.provider
-                    and llm_provider.default_model_name
-                    == fetched_llm_provider.default_model_name
+                    and (
+                        default_model is None or default_model.model_name in model_names
+                    )
                     and llm_provider.is_public == fetched_llm_provider.is_public
                     and set(fetched_llm_provider.personas) == set(llm_provider.personas)
                 ):
                     return
         if not verify_deleted:
             raise ValueError(f"LLM Provider {llm_provider.id} not found")
+
+    @staticmethod
+    def get_default_model(
+        user_performing_action: DATestUser | None = None,
+    ) -> DefaultModel | None:
+        response = requests.get(
+            f"{API_SERVER_URL}/admin/llm/provider",
+            headers=(
+                user_performing_action.headers
+                if user_performing_action
+                else GENERAL_HEADERS
+            ),
+        )
+        response.raise_for_status()
+        default_text = response.json().get("default_text")
+        if default_text is None:
+            return None
+        return DefaultModel(**default_text)

backend/tests/integration/common_utils/managers/persona.py

@@ -3,7 +3,6 @@ from uuid import uuid4
 
 import requests
 
-from onyx.context.search.enums import RecencyBiasSetting
 from onyx.server.features.persona.models import FullPersonaSnapshot
 from onyx.server.features.persona.models import PersonaUpsertRequest
 from tests.integration.common_utils.constants import API_SERVER_URL
@@ -20,11 +19,7 @@ class PersonaManager:
         description: str | None = None,
         system_prompt: str | None = None,
         task_prompt: str | None = None,
-        num_chunks: float = 5,
-        llm_relevance_filter: bool = True,
         is_public: bool = True,
-        llm_filter_extraction: bool = True,
-        recency_bias: RecencyBiasSetting = RecencyBiasSetting.AUTO,
         datetime_aware: bool = False,
         document_set_ids: list[int] | None = None,
         tool_ids: list[int] | None = None,
@@ -35,6 +30,7 @@ class PersonaManager:
         label_ids: list[int] | None = None,
         user_file_ids: list[str] | None = None,
         display_priority: int | None = None,
+        featured: bool = False,
     ) -> DATestPersona:
         name = name or f"test-persona-{uuid4()}"
         description = description or f"Description for {name}"
@@ -47,11 +43,7 @@ class PersonaManager:
             system_prompt=system_prompt,
             task_prompt=task_prompt,
             datetime_aware=datetime_aware,
-            num_chunks=num_chunks,
-            llm_relevance_filter=llm_relevance_filter,
             is_public=is_public,
-            llm_filter_extraction=llm_filter_extraction,
-            recency_bias=recency_bias,
             document_set_ids=document_set_ids or [],
             tool_ids=tool_ids or [],
             llm_model_provider_override=llm_model_provider_override,
@@ -61,6 +53,7 @@ class PersonaManager:
             label_ids=label_ids or [],
             user_file_ids=user_file_ids or [],
             display_priority=display_priority,
+            featured=featured,
         )
 
         response = requests.post(
@@ -75,11 +68,7 @@ class PersonaManager:
             id=persona_data["id"],
             name=name,
             description=description,
-            num_chunks=num_chunks,
-            llm_relevance_filter=llm_relevance_filter,
             is_public=is_public,
-            llm_filter_extraction=llm_filter_extraction,
-            recency_bias=recency_bias,
             system_prompt=system_prompt,
             task_prompt=task_prompt,
             datetime_aware=datetime_aware,
@@ -90,6 +79,7 @@ class PersonaManager:
             users=users or [],
             groups=groups or [],
             label_ids=label_ids or [],
+            featured=featured,
         )
 
     @staticmethod
@@ -100,11 +90,7 @@ class PersonaManager:
         description: str | None = None,
         system_prompt: str | None = None,
         task_prompt: str | None = None,
-        num_chunks: float | None = None,
-        llm_relevance_filter: bool | None = None,
         is_public: bool | None = None,
-        llm_filter_extraction: bool | None = None,
-        recency_bias: RecencyBiasSetting | None = None,
         datetime_aware: bool = False,
         document_set_ids: list[int] | None = None,
         tool_ids: list[int] | None = None,
@@ -113,6 +99,7 @@ class PersonaManager:
         users: list[str] | None = None,
         groups: list[int] | None = None,
         label_ids: list[int] | None = None,
+        featured: bool | None = None,
     ) -> DATestPersona:
         system_prompt = system_prompt or f"System prompt for {persona.name}"
         task_prompt = task_prompt or f"Task prompt for {persona.name}"
@@ -123,13 +110,7 @@ class PersonaManager:
             system_prompt=system_prompt,
             task_prompt=task_prompt,
             datetime_aware=datetime_aware,
-            num_chunks=num_chunks or persona.num_chunks,
-            llm_relevance_filter=llm_relevance_filter or persona.llm_relevance_filter,
             is_public=persona.is_public if is_public is None else is_public,
-            llm_filter_extraction=(
-                llm_filter_extraction or persona.llm_filter_extraction
-            ),
-            recency_bias=recency_bias or persona.recency_bias,
             document_set_ids=document_set_ids or persona.document_set_ids,
             tool_ids=tool_ids or persona.tool_ids,
             llm_model_provider_override=(
@@ -141,6 +122,7 @@ class PersonaManager:
             users=[UUID(user) for user in (users or persona.users)],
             groups=groups or persona.groups,
             label_ids=label_ids or persona.label_ids,
+            featured=featured if featured is not None else persona.featured,
         )
 
         response = requests.patch(
@@ -155,16 +137,12 @@ class PersonaManager:
             id=updated_persona_data["id"],
             name=updated_persona_data["name"],
             description=updated_persona_data["description"],
-            num_chunks=updated_persona_data["num_chunks"],
-            llm_relevance_filter=updated_persona_data["llm_relevance_filter"],
             is_public=updated_persona_data["is_public"],
-            llm_filter_extraction=updated_persona_data["llm_filter_extraction"],
-            recency_bias=recency_bias or persona.recency_bias,
             system_prompt=system_prompt,
             task_prompt=task_prompt,
             datetime_aware=datetime_aware,
-            document_set_ids=updated_persona_data["document_sets"],
-            tool_ids=updated_persona_data["tools"],
+            document_set_ids=[ds["id"] for ds in updated_persona_data["document_sets"]],
+            tool_ids=[t["id"] for t in updated_persona_data["tools"]],
             llm_model_provider_override=updated_persona_data[
                 "llm_model_provider_override"
             ],
@@ -173,7 +151,8 @@ class PersonaManager:
             ],
             users=[user["email"] for user in updated_persona_data["users"]],
             groups=updated_persona_data["groups"],
-            label_ids=updated_persona_data["labels"],
+            label_ids=[label["id"] for label in updated_persona_data["labels"]],
+            featured=updated_persona_data["featured"],
         )
 
     @staticmethod
@@ -222,32 +201,13 @@ class PersonaManager:
                             fetched_persona.description,
                         )
                     )
-                if fetched_persona.num_chunks != persona.num_chunks:
-                    mismatches.append(
-                        ("num_chunks", persona.num_chunks, fetched_persona.num_chunks)
-                    )
-                if fetched_persona.llm_relevance_filter != persona.llm_relevance_filter:
-                    mismatches.append(
-                        (
-                            "llm_relevance_filter",
-                            persona.llm_relevance_filter,
-                            fetched_persona.llm_relevance_filter,
-                        )
-                    )
                 if fetched_persona.is_public != persona.is_public:
                     mismatches.append(
                         ("is_public", persona.is_public, fetched_persona.is_public)
                     )
-                if (
-                    fetched_persona.llm_filter_extraction
-                    != persona.llm_filter_extraction
-                ):
+                if fetched_persona.featured != persona.featured:
                     mismatches.append(
-                        (
-                            "llm_filter_extraction",
-                            persona.llm_filter_extraction,
-                            fetched_persona.llm_filter_extraction,
-                        )
+                        ("featured", persona.featured, fetched_persona.featured)
                     )
                 if (
                     fetched_persona.llm_model_provider_override

backend/tests/integration/common_utils/test_models.py

@@ -10,7 +10,6 @@ from pydantic import Field
 from onyx.auth.schemas import UserRole
 from onyx.configs.constants import MessageType
 from onyx.configs.constants import QAFeedbackType
-from onyx.context.search.enums import RecencyBiasSetting
 from onyx.context.search.models import SavedSearchDoc
 from onyx.context.search.models import SearchDoc
 from onyx.db.enums import AccessType
@@ -128,7 +127,7 @@ class DATestLLMProvider(BaseModel):
     name: str
     provider: str
     api_key: str
-    default_model_name: str
+    default_model_name: str | None = None
     is_public: bool
     is_auto_mode: bool = False
     groups: list[int]
@@ -162,11 +161,7 @@ class DATestPersona(BaseModel):
     id: int
     name: str
     description: str
-    num_chunks: float
-    llm_relevance_filter: bool
     is_public: bool
-    llm_filter_extraction: bool
-    recency_bias: RecencyBiasSetting
     document_set_ids: list[int]
     tool_ids: list[int]
     llm_model_provider_override: str | None
@@ -174,6 +169,7 @@ class DATestPersona(BaseModel):
     users: list[str]
     groups: list[int]
     label_ids: list[int]
+    featured: bool = False
 
     # Embedded prompt fields (no longer separate prompt_ids)
     system_prompt: str | None = None

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

@@ -8,7 +8,6 @@ from collections.abc import Generator
 import pytest
 from sqlalchemy.orm import Session
 
-from onyx.context.search.enums import RecencyBiasSetting
 from onyx.db.discord_bot import bulk_create_channel_configs
 from onyx.db.discord_bot import create_discord_bot_config
 from onyx.db.discord_bot import create_guild_config
@@ -36,14 +35,8 @@ def _create_test_persona(db_session: Session, persona_id: int, name: str) -> Per
         id=persona_id,
         name=name,
         description="Test persona for Discord bot tests",
-        num_chunks=5.0,
-        chunks_above=1,
-        chunks_below=1,
-        llm_relevance_filter=False,
-        llm_filter_extraction=False,
-        recency_bias=RecencyBiasSetting.FAVOR_RECENT,
         is_visible=True,
-        is_default_persona=False,
+        featured=False,
         deleted=False,
         builtin_persona=False,
     )

backend/tests/integration/tests/indexing/test_checkpointing.py

@@ -414,6 +414,24 @@ def test_mock_connector_checkpoint_recovery(
     )
     assert finished_index_attempt.status == IndexingStatus.FAILED
 
+    # Pause the connector immediately to prevent check_for_indexing from
+    # creating automatic retry attempts while we reset the mock server.
+    # Without this, the INITIAL_INDEXING status causes immediate retries
+    # that would consume (or fail against) the mock server before we can
+    # set up the recovery behavior.
+    CCPairManager.pause_cc_pair(cc_pair, user_performing_action=admin_user)
+
+    # Collect all index attempt IDs created so far (the initial one plus
+    # any automatic retries that may have started before the pause took effect).
+    all_prior_attempt_ids: list[int] = []
+    index_attempts_page = IndexAttemptManager.get_index_attempt_page(
+        cc_pair_id=cc_pair.id,
+        page=0,
+        page_size=100,
+        user_performing_action=admin_user,
+    )
+    all_prior_attempt_ids = [ia.id for ia in index_attempts_page.items]
+
     # Verify initial state: both docs should be indexed
     with get_session_with_current_tenant() as db_session:
         documents = DocumentManager.fetch_documents_for_cc_pair(
@@ -465,17 +483,14 @@ def test_mock_connector_checkpoint_recovery(
     )
     assert response.status_code == 200
 
-    # After the failure, the connector is in repeated error state and paused.
-    # Set the manual indexing trigger first (while paused), then unpause.
-    # This ensures the trigger is set before CHECK_FOR_INDEXING runs, which will
-    # prevent the connector from being re-paused when repeated error state is detected.
+    # Set the manual indexing trigger, then unpause to allow the recovery run.
     CCPairManager.run_once(
         cc_pair, from_beginning=False, user_performing_action=admin_user
     )
     CCPairManager.unpause_cc_pair(cc_pair, user_performing_action=admin_user)
     recovery_index_attempt = IndexAttemptManager.wait_for_index_attempt_start(
         cc_pair_id=cc_pair.id,
-        index_attempts_to_ignore=[initial_index_attempt.id],
+        index_attempts_to_ignore=all_prior_attempt_ids,
         user_performing_action=admin_user,
     )
     IndexAttemptManager.wait_for_index_attempt_completion(

backend/tests/integration/tests/indexing/test_repeated_error_state.py

@@ -130,8 +130,8 @@ def test_repeated_error_state_detection_and_recovery(
                 #     )
                 break
 
-        if time.monotonic() - start_time > 30:
-            assert False, "CC pair did not enter repeated error state within 30 seconds"
+        if time.monotonic() - start_time > 90:
+            assert False, "CC pair did not enter repeated error state within 90 seconds"
 
         time.sleep(2)
 

backend/tests/integration/tests/llm_auto_update/test_auto_llm_update.py

@@ -42,12 +42,10 @@ def _create_provider_with_api(
     llm_provider_data = {
         "name": name,
         "provider": provider_type,
-        "default_model_name": default_model,
         "api_key": "test-api-key-for-auto-mode-testing",
         "api_base": None,
         "api_version": None,
         "custom_config": None,
-        "fast_default_model_name": default_model,
         "is_public": True,
         "is_auto_mode": is_auto_mode,
         "groups": [],
@@ -72,7 +70,7 @@ def _get_provider_by_id(admin_user: DATestUser, provider_id: int) -> dict:
         headers=admin_user.headers,
     )
     response.raise_for_status()
-    for provider in response.json():
+    for provider in response.json()["providers"]:
         if provider["id"] == provider_id:
             return provider
     raise ValueError(f"Provider with id {provider_id} not found")
@@ -219,15 +217,6 @@ def test_auto_mode_provider_gets_synced_from_github_config(
         "is_visible"
     ], "Outdated model should not be visible after sync"
 
-    # Verify default model was set from GitHub config
-    expected_default = (
-        default_model["name"] if isinstance(default_model, dict) else default_model
-    )
-    assert synced_provider["default_model_name"] == expected_default, (
-        f"Default model should be {expected_default}, "
-        f"got {synced_provider['default_model_name']}"
-    )
-
 
 def test_manual_mode_provider_not_affected_by_auto_sync(
     reset: None,  # noqa: ARG001
@@ -273,7 +262,3 @@ def test_manual_mode_provider_not_affected_by_auto_sync(
         f"Manual mode provider models should not change. "
         f"Initial: {initial_models}, Current: {current_models}"
     )
-
-    assert (
-        updated_provider["default_model_name"] == custom_model
-    ), f"Manual mode default model should remain {custom_model}"

backend/tests/integration/tests/llm_provider/test_llm_provider_access_control.py

@@ -4,22 +4,22 @@ import pytest
 import requests
 from sqlalchemy.orm import Session
 
-from onyx.context.search.enums import RecencyBiasSetting
 from onyx.db.engine.sql_engine import get_session_with_current_tenant
-from onyx.db.enums import LLMModelFlowType
 from onyx.db.llm import can_user_access_llm_provider
 from onyx.db.llm import fetch_user_group_ids
-from onyx.db.models import LLMModelFlow
+from onyx.db.llm import update_default_provider
+from onyx.db.llm import upsert_llm_provider
 from onyx.db.models import LLMProvider as LLMProviderModel
 from onyx.db.models import LLMProvider__Persona
 from onyx.db.models import LLMProvider__UserGroup
-from onyx.db.models import ModelConfiguration
 from onyx.db.models import Persona
 from onyx.db.models import User
 from onyx.db.models import User__UserGroup
 from onyx.db.models import UserGroup
 from onyx.llm.constants import LlmProviderNames
 from onyx.llm.factory import get_llm_for_persona
+from onyx.server.manage.llm.models import LLMProviderUpsertRequest
+from onyx.server.manage.llm.models import ModelConfigurationUpsertRequest
 from tests.integration.common_utils.constants import API_SERVER_URL
 from tests.integration.common_utils.managers.llm_provider import LLMProviderManager
 from tests.integration.common_utils.managers.persona import PersonaManager
@@ -41,24 +41,30 @@ def _create_llm_provider(
     is_public: bool,
     is_default: bool,
 ) -> LLMProviderModel:
-    provider = LLMProviderModel(
-        name=name,
-        provider=LlmProviderNames.OPENAI,
-        api_key=None,
-        api_base=None,
-        api_version=None,
-        custom_config=None,
-        default_model_name=default_model_name,
-        deployment_name=None,
-        is_public=is_public,
-        # Use None instead of False to avoid unique constraint violation
-        # The is_default_provider column has unique=True, so only one True and one False allowed
-        is_default_provider=is_default if is_default else None,
-        is_default_vision_provider=False,
-        default_vision_model=None,
+    _provider = upsert_llm_provider(
+        llm_provider_upsert_request=LLMProviderUpsertRequest(
+            name=name,
+            provider=LlmProviderNames.OPENAI,
+            api_key=None,
+            api_base=None,
+            api_version=None,
+            custom_config=None,
+            is_public=is_public,
+            model_configurations=[
+                ModelConfigurationUpsertRequest(
+                    name=default_model_name,
+                    is_visible=True,
+                )
+            ],
+        ),
+        db_session=db_session,
     )
-    db_session.add(provider)
-    db_session.flush()
+    if is_default:
+        update_default_provider(_provider.id, default_model_name, db_session)
+
+    provider = db_session.get(LLMProviderModel, _provider.id)
+    if not provider:
+        raise ValueError(f"Provider {name} not found")
     return provider
 
 
@@ -71,12 +77,6 @@ def _create_persona(
     persona = Persona(
         name=name,
         description=f"{name} description",
-        num_chunks=5,
-        chunks_above=2,
-        chunks_below=2,
-        llm_relevance_filter=True,
-        llm_filter_extraction=True,
-        recency_bias=RecencyBiasSetting.AUTO,
         llm_model_provider_override=provider_name,
         llm_model_version_override="gpt-4o-mini",
         system_prompt="System prompt",
@@ -270,24 +270,6 @@ def test_get_llm_for_persona_falls_back_when_access_denied(
             provider_name=restricted_provider.name,
         )
 
-        # Set up ModelConfiguration + LLMModelFlow so get_default_llm() can
-        # resolve the default provider when the fallback path is triggered.
-        default_model_config = ModelConfiguration(
-            llm_provider_id=default_provider.id,
-            name=default_provider.default_model_name,
-            is_visible=True,
-        )
-        db_session.add(default_model_config)
-        db_session.flush()
-        db_session.add(
-            LLMModelFlow(
-                model_configuration_id=default_model_config.id,
-                llm_model_flow_type=LLMModelFlowType.CHAT,
-                is_default=True,
-            )
-        )
-        db_session.flush()
-
         access_group = UserGroup(name="persona-group")
         db_session.add(access_group)
         db_session.flush()
@@ -321,13 +303,19 @@ def test_get_llm_for_persona_falls_back_when_access_denied(
             persona=persona,
             user=admin_model,
         )
-        assert allowed_llm.config.model_name == restricted_provider.default_model_name
+        assert (
+            allowed_llm.config.model_name
+            == restricted_provider.model_configurations[0].name
+        )
 
         fallback_llm = get_llm_for_persona(
             persona=persona,
             user=basic_model,
         )
-        assert fallback_llm.config.model_name == default_provider.default_model_name
+        assert (
+            fallback_llm.config.model_name
+            == default_provider.model_configurations[0].name
+        )
 
 
 def test_list_llm_provider_basics_excludes_non_public_unrestricted(
@@ -346,6 +334,7 @@ def test_list_llm_provider_basics_excludes_non_public_unrestricted(
         name="public-provider",
         is_public=True,
         set_as_default=True,
+        default_model_name="gpt-4o",
         user_performing_action=admin_user,
     )
 
@@ -365,7 +354,7 @@ def test_list_llm_provider_basics_excludes_non_public_unrestricted(
         headers=basic_user.headers,
     )
     assert response.status_code == 200
-    providers = response.json()
+    providers = response.json()["providers"]
     provider_names = [p["name"] for p in providers]
 
     # Public provider should be visible
@@ -380,7 +369,7 @@ def test_list_llm_provider_basics_excludes_non_public_unrestricted(
         headers=admin_user.headers,
     )
     assert admin_response.status_code == 200
-    admin_providers = admin_response.json()
+    admin_providers = admin_response.json()["providers"]
     admin_provider_names = [p["name"] for p in admin_providers]
 
     assert public_provider.name in admin_provider_names
@@ -396,6 +385,7 @@ def test_provider_delete_clears_persona_references(reset: None) -> None:  # noqa
         name="default-provider",
         is_public=True,
         set_as_default=True,
+        default_model_name="gpt-4o",
         user_performing_action=admin_user,
     )
 

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

@@ -107,7 +107,7 @@ def test_authorized_persona_access_returns_filtered_providers(
 
     # Should succeed
     assert response.status_code == 200
-    providers = response.json()
+    providers = response.json()["providers"]
 
     # Should include the restricted provider since basic_user can access the persona
     provider_names = [p["name"] for p in providers]
@@ -140,7 +140,7 @@ def test_persona_id_zero_applies_rbac(
 
     # Should succeed (persona_id=0 refers to default persona, which is public)
     assert response.status_code == 200
-    providers = response.json()
+    providers = response.json()["providers"]
 
     # Should NOT include the restricted provider since basic_user is not in group2
     provider_names = [p["name"] for p in providers]
@@ -182,7 +182,7 @@ def test_admin_can_query_any_persona(
 
     # Should succeed - admins can access any persona
     assert response.status_code == 200
-    providers = response.json()
+    providers = response.json()["providers"]
 
     # Should include the restricted provider
     provider_names = [p["name"] for p in providers]
@@ -223,7 +223,7 @@ def test_public_persona_accessible_to_all(
 
     # Should succeed
     assert response.status_code == 200
-    providers = response.json()
+    providers = response.json()["providers"]
 
     # Should return the public provider
     assert len(providers) > 0

backend/tests/integration/tests/migrations/test_assistant_consolidation_migration.py

@@ -25,7 +25,7 @@ def test_cold_startup_default_assistant() -> None:
         result = db_session.execute(
             text(
                 """
-                SELECT id, name, builtin_persona, is_default_persona, deleted
+                SELECT id, name, builtin_persona, featured, deleted
                 FROM persona
                 WHERE builtin_persona = true
                 ORDER BY id
@@ -40,7 +40,7 @@ def test_cold_startup_default_assistant() -> None:
         assert default[0] == 0, "Default assistant should have ID 0"
         assert default[1] == "Assistant", "Should be named 'Assistant'"
         assert default[2] is True, "Should be builtin"
-        assert default[3] is True, "Should be default"
+        assert default[3] is True, "Should be featured"
         assert default[4] is False, "Should not be deleted"
 
         # Check tools are properly associated
@@ -72,6 +72,9 @@ def test_cold_startup_default_assistant() -> None:
         assert (
             "read_file" in tool_names
         ), "Default assistant should have FileReaderTool attached"
+        assert (
+            "python" in tool_names
+        ), "Default assistant should have PythonTool attached"
 
         # Also verify by display names for clarity
         assert (
@@ -86,8 +89,11 @@ def test_cold_startup_default_assistant() -> None:
         assert (
             "File Reader" in tool_display_names
         ), "Default assistant should have File Reader tool"
-
-        # Should have exactly 5 tools
         assert (
-            len(tool_associations) == 5
-        ), f"Default assistant should have exactly 5 tools attached, got {len(tool_associations)}"
+            "Code Interpreter" in tool_display_names
+        ), "Default assistant should have Code Interpreter tool"
+
+        # Should have exactly 6 tools
+        assert (
+            len(tool_associations) == 6
+        ), f"Default assistant should have exactly 6 tools attached, got {len(tool_associations)}"

backend/tests/integration/tests/no_vectordb/test_no_vectordb_chat.py

@@ -195,11 +195,7 @@ def _base_persona_body(**overrides: object) -> dict:
         "description": "test",
         "system_prompt": "test",
         "task_prompt": "",
-        "num_chunks": 5,
         "is_public": True,
-        "recency_bias": "auto",
-        "llm_filter_extraction": False,
-        "llm_relevance_filter": False,
         "datetime_aware": False,
         "document_set_ids": [],
         "tool_ids": [],

backend/tests/integration/tests/personas/test_persona_creation.py

@@ -40,7 +40,6 @@ def test_persona_create_update_share_delete(
         expected_persona,
         name=f"updated-{expected_persona.name}",
         description=f"updated-{expected_persona.description}",
-        num_chunks=expected_persona.num_chunks + 1,
         is_public=False,
         user_performing_action=admin_user,
     )

backend/tests/integration/tests/personas/test_persona_label_updates.py

@@ -31,11 +31,7 @@ def test_update_persona_with_null_label_ids_preserves_labels(
         task_prompt=persona.task_prompt or "",
         datetime_aware=persona.datetime_aware,
         document_set_ids=persona.document_set_ids,
-        num_chunks=persona.num_chunks,
         is_public=persona.is_public,
-        recency_bias=persona.recency_bias,
-        llm_filter_extraction=persona.llm_filter_extraction,
-        llm_relevance_filter=persona.llm_relevance_filter,
         llm_model_provider_override=persona.llm_model_provider_override,
         llm_model_version_override=persona.llm_model_version_override,
         tool_ids=persona.tool_ids,

backend/tests/integration/tests/personas/test_unified_assistant.py

@@ -31,9 +31,8 @@ def test_unified_assistant(reset: None, admin_user: DATestUser) -> None:  # noqa
         "search, web browsing, and image generation"
         in unified_assistant.description.lower()
     )
-    assert unified_assistant.is_default_persona is True
+    assert unified_assistant.featured is True
     assert unified_assistant.is_visible is True
-    assert unified_assistant.num_chunks == 25
 
     # Verify tools
     tools = unified_assistant.tools

backend/tests/unit/ee/onyx/server/settings/test_license_enforcement_settings.py

@@ -9,6 +9,19 @@ from redis.exceptions import RedisError
 from onyx.server.settings.models import ApplicationStatus
 from onyx.server.settings.models import Settings
 
+# Fields we assert on across all tests
+_ASSERT_FIELDS = {
+    "application_status",
+    "ee_features_enabled",
+    "seat_count",
+    "used_seats",
+}
+
+
+def _pick(settings: Settings) -> dict:
+    """Extract only the fields under test from a Settings object."""
+    return settings.model_dump(include=_ASSERT_FIELDS)
+
 
 @pytest.fixture
 def base_settings() -> Settings:
@@ -27,17 +40,17 @@ class TestApplyLicenseStatusToSettings:
     def test_enforcement_disabled_enables_ee_features(
         self, base_settings: Settings
     ) -> None:
-        """When LICENSE_ENFORCEMENT_ENABLED=False, EE features are enabled.
-
-        If we're running the EE apply function, EE code was loaded via
-        ENABLE_PAID_ENTERPRISE_EDITION_FEATURES, so features should be on.
-        """
+        """When LICENSE_ENFORCEMENT_ENABLED=False, EE features are enabled."""
         from ee.onyx.server.settings.api import apply_license_status_to_settings
 
         assert base_settings.ee_features_enabled is False
         result = apply_license_status_to_settings(base_settings)
-        assert result.application_status == ApplicationStatus.ACTIVE
-        assert result.ee_features_enabled is True
+        assert _pick(result) == {
+            "application_status": ApplicationStatus.ACTIVE,
+            "ee_features_enabled": True,
+            "seat_count": None,
+            "used_seats": None,
+        }
 
     @patch("ee.onyx.server.settings.api.LICENSE_ENFORCEMENT_ENABLED", True)
     @patch("ee.onyx.server.settings.api.MULTI_TENANT", True)
@@ -46,13 +59,60 @@ class TestApplyLicenseStatusToSettings:
         from ee.onyx.server.settings.api import apply_license_status_to_settings
 
         result = apply_license_status_to_settings(base_settings)
-        assert result.ee_features_enabled is True
+        assert _pick(result) == {
+            "application_status": ApplicationStatus.ACTIVE,
+            "ee_features_enabled": True,
+            "seat_count": None,
+            "used_seats": None,
+        }
 
     @pytest.mark.parametrize(
-        "license_status,expected_app_status,expected_ee_enabled",
+        "license_status,used_seats,seats,expected",
         [
-            (ApplicationStatus.GATED_ACCESS, ApplicationStatus.GATED_ACCESS, False),
-            (ApplicationStatus.ACTIVE, ApplicationStatus.ACTIVE, True),
+            (
+                ApplicationStatus.GATED_ACCESS,
+                3,
+                10,
+                {
+                    "application_status": ApplicationStatus.GATED_ACCESS,
+                    "ee_features_enabled": False,
+                    "seat_count": None,
+                    "used_seats": None,
+                },
+            ),
+            (
+                ApplicationStatus.ACTIVE,
+                3,
+                10,
+                {
+                    "application_status": ApplicationStatus.ACTIVE,
+                    "ee_features_enabled": True,
+                    "seat_count": None,
+                    "used_seats": None,
+                },
+            ),
+            (
+                ApplicationStatus.ACTIVE,
+                10,
+                10,
+                {
+                    "application_status": ApplicationStatus.ACTIVE,
+                    "ee_features_enabled": True,
+                    "seat_count": None,
+                    "used_seats": None,
+                },
+            ),
+            (
+                ApplicationStatus.GRACE_PERIOD,
+                3,
+                10,
+                {
+                    "application_status": ApplicationStatus.ACTIVE,
+                    "ee_features_enabled": True,
+                    "seat_count": None,
+                    "used_seats": None,
+                },
+            ),
         ],
     )
     @patch("ee.onyx.server.settings.api.LICENSE_ENFORCEMENT_ENABLED", True)
@@ -63,25 +123,80 @@ class TestApplyLicenseStatusToSettings:
         self,
         mock_get_metadata: MagicMock,
         mock_get_tenant: MagicMock,
-        license_status: ApplicationStatus | None,
-        expected_app_status: ApplicationStatus,
-        expected_ee_enabled: bool,
+        license_status: ApplicationStatus,
+        used_seats: int,
+        seats: int,
+        expected: dict,
         base_settings: Settings,
     ) -> None:
         """Self-hosted: license status controls both application_status and ee_features_enabled."""
         from ee.onyx.server.settings.api import apply_license_status_to_settings
 
         mock_get_tenant.return_value = "test_tenant"
-        if license_status is None:
-            mock_get_metadata.return_value = None
-        else:
-            mock_metadata = MagicMock()
-            mock_metadata.status = license_status
-            mock_get_metadata.return_value = mock_metadata
+        mock_metadata = MagicMock()
+        mock_metadata.status = license_status
+        mock_metadata.used_seats = used_seats
+        mock_metadata.seats = seats
+        mock_get_metadata.return_value = mock_metadata
 
         result = apply_license_status_to_settings(base_settings)
-        assert result.application_status == expected_app_status
-        assert result.ee_features_enabled is expected_ee_enabled
+        assert _pick(result) == expected
+
+    @patch("ee.onyx.server.settings.api.LICENSE_ENFORCEMENT_ENABLED", True)
+    @patch("ee.onyx.server.settings.api.MULTI_TENANT", False)
+    @patch("ee.onyx.server.settings.api.get_current_tenant_id")
+    @patch("ee.onyx.server.settings.api.get_cached_license_metadata")
+    def test_seat_limit_exceeded_sets_status_and_counts(
+        self,
+        mock_get_metadata: MagicMock,
+        mock_get_tenant: MagicMock,
+        base_settings: Settings,
+    ) -> None:
+        """Seat limit exceeded sets SEAT_LIMIT_EXCEEDED with counts, keeps EE enabled."""
+        from ee.onyx.server.settings.api import apply_license_status_to_settings
+
+        mock_get_tenant.return_value = "test_tenant"
+        mock_metadata = MagicMock()
+        mock_metadata.status = ApplicationStatus.ACTIVE
+        mock_metadata.used_seats = 15
+        mock_metadata.seats = 10
+        mock_get_metadata.return_value = mock_metadata
+
+        result = apply_license_status_to_settings(base_settings)
+        assert _pick(result) == {
+            "application_status": ApplicationStatus.SEAT_LIMIT_EXCEEDED,
+            "ee_features_enabled": True,
+            "seat_count": 10,
+            "used_seats": 15,
+        }
+
+    @patch("ee.onyx.server.settings.api.LICENSE_ENFORCEMENT_ENABLED", True)
+    @patch("ee.onyx.server.settings.api.MULTI_TENANT", False)
+    @patch("ee.onyx.server.settings.api.get_current_tenant_id")
+    @patch("ee.onyx.server.settings.api.get_cached_license_metadata")
+    def test_expired_license_takes_precedence_over_seat_limit(
+        self,
+        mock_get_metadata: MagicMock,
+        mock_get_tenant: MagicMock,
+        base_settings: Settings,
+    ) -> None:
+        """Expired license (GATED_ACCESS) takes precedence over seat limit exceeded."""
+        from ee.onyx.server.settings.api import apply_license_status_to_settings
+
+        mock_get_tenant.return_value = "test_tenant"
+        mock_metadata = MagicMock()
+        mock_metadata.status = ApplicationStatus.GATED_ACCESS
+        mock_metadata.used_seats = 15
+        mock_metadata.seats = 10
+        mock_get_metadata.return_value = mock_metadata
+
+        result = apply_license_status_to_settings(base_settings)
+        assert _pick(result) == {
+            "application_status": ApplicationStatus.GATED_ACCESS,
+            "ee_features_enabled": False,
+            "seat_count": None,
+            "used_seats": None,
+        }
 
     @patch("ee.onyx.server.settings.api.ENTERPRISE_EDITION_ENABLED", True)
     @patch("ee.onyx.server.settings.api.LICENSE_ENFORCEMENT_ENABLED", True)
@@ -105,8 +220,12 @@ class TestApplyLicenseStatusToSettings:
         mock_get_metadata.return_value = None
 
         result = apply_license_status_to_settings(base_settings)
-        assert result.application_status == ApplicationStatus.GATED_ACCESS
-        assert result.ee_features_enabled is False
+        assert _pick(result) == {
+            "application_status": ApplicationStatus.GATED_ACCESS,
+            "ee_features_enabled": False,
+            "seat_count": None,
+            "used_seats": None,
+        }
 
     @patch("ee.onyx.server.settings.api.ENTERPRISE_EDITION_ENABLED", False)
     @patch("ee.onyx.server.settings.api.LICENSE_ENFORCEMENT_ENABLED", True)
@@ -130,8 +249,12 @@ class TestApplyLicenseStatusToSettings:
         mock_get_metadata.return_value = None
 
         result = apply_license_status_to_settings(base_settings)
-        assert result.application_status == ApplicationStatus.ACTIVE
-        assert result.ee_features_enabled is False
+        assert _pick(result) == {
+            "application_status": ApplicationStatus.ACTIVE,
+            "ee_features_enabled": False,
+            "seat_count": None,
+            "used_seats": None,
+        }
 
     @patch("ee.onyx.server.settings.api.LICENSE_ENFORCEMENT_ENABLED", True)
     @patch("ee.onyx.server.settings.api.MULTI_TENANT", False)
@@ -150,8 +273,12 @@ class TestApplyLicenseStatusToSettings:
         mock_get_metadata.side_effect = RedisError("Connection failed")
 
         result = apply_license_status_to_settings(base_settings)
-        assert result.application_status == ApplicationStatus.ACTIVE
-        assert result.ee_features_enabled is False
+        assert _pick(result) == {
+            "application_status": ApplicationStatus.ACTIVE,
+            "ee_features_enabled": False,
+            "seat_count": None,
+            "used_seats": None,
+        }
 
 
 class TestSettingsDefaultEEDisabled:

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

@@ -0,0 +1,291 @@
+"""Tests for the _impl functions' redis_locking parameter.
+
+Verifies that:
+- redis_locking=True acquires/releases Redis locks and clears queued keys
+- redis_locking=False skips all Redis operations entirely
+- Both paths execute the same business logic (DB lookup, status check)
+"""
+
+from unittest.mock import MagicMock
+from unittest.mock import patch
+from uuid import uuid4
+
+from onyx.background.celery.tasks.user_file_processing.tasks import (
+    delete_user_file_impl,
+)
+from onyx.background.celery.tasks.user_file_processing.tasks import (
+    process_user_file_impl,
+)
+from onyx.background.celery.tasks.user_file_processing.tasks import (
+    project_sync_user_file_impl,
+)
+
+TASKS_MODULE = "onyx.background.celery.tasks.user_file_processing.tasks"
+
+
+def _mock_session_returning_none() -> MagicMock:
+    """Return a mock session whose .get() returns None (file not found)."""
+    session = MagicMock()
+    session.get.return_value = None
+    session.execute.return_value.scalar_one_or_none.return_value = None
+    return session
+
+
+# ------------------------------------------------------------------
+# process_user_file_impl
+# ------------------------------------------------------------------
+
+
+class TestProcessUserFileImpl:
+    @patch(f"{TASKS_MODULE}.get_session_with_current_tenant")
+    @patch(f"{TASKS_MODULE}.get_redis_client")
+    def test_redis_locking_true_acquires_and_releases_lock(
+        self,
+        mock_get_redis: MagicMock,
+        mock_get_session: MagicMock,
+    ) -> None:
+        redis_client = MagicMock()
+        lock = MagicMock()
+        lock.acquire.return_value = True
+        lock.owned.return_value = True
+        redis_client.lock.return_value = lock
+        mock_get_redis.return_value = redis_client
+
+        session = _mock_session_returning_none()
+        mock_get_session.return_value.__enter__.return_value = session
+
+        user_file_id = str(uuid4())
+        process_user_file_impl(
+            user_file_id=user_file_id,
+            tenant_id="test-tenant",
+            redis_locking=True,
+        )
+
+        mock_get_redis.assert_called_once_with(tenant_id="test-tenant")
+        redis_client.delete.assert_called_once()
+        lock.acquire.assert_called_once_with(blocking=False)
+        lock.release.assert_called_once()
+
+    @patch(f"{TASKS_MODULE}.get_session_with_current_tenant")
+    @patch(f"{TASKS_MODULE}.get_redis_client")
+    def test_redis_locking_true_skips_when_lock_held(
+        self,
+        mock_get_redis: MagicMock,
+        mock_get_session: MagicMock,
+    ) -> None:
+        redis_client = MagicMock()
+        lock = MagicMock()
+        lock.acquire.return_value = False
+        redis_client.lock.return_value = lock
+        mock_get_redis.return_value = redis_client
+
+        process_user_file_impl(
+            user_file_id=str(uuid4()),
+            tenant_id="test-tenant",
+            redis_locking=True,
+        )
+
+        lock.acquire.assert_called_once()
+        mock_get_session.assert_not_called()
+
+    @patch(f"{TASKS_MODULE}.get_session_with_current_tenant")
+    @patch(f"{TASKS_MODULE}.get_redis_client")
+    def test_redis_locking_false_skips_redis_entirely(
+        self,
+        mock_get_redis: MagicMock,
+        mock_get_session: MagicMock,
+    ) -> None:
+        session = _mock_session_returning_none()
+        mock_get_session.return_value.__enter__.return_value = session
+
+        process_user_file_impl(
+            user_file_id=str(uuid4()),
+            tenant_id="test-tenant",
+            redis_locking=False,
+        )
+
+        mock_get_redis.assert_not_called()
+        mock_get_session.assert_called_once()
+
+    @patch(f"{TASKS_MODULE}.get_session_with_current_tenant")
+    @patch(f"{TASKS_MODULE}.get_redis_client")
+    def test_both_paths_call_db_get(
+        self,
+        mock_get_redis: MagicMock,
+        mock_get_session: MagicMock,
+    ) -> None:
+        """Both redis_locking=True and False should call db_session.get(UserFile, ...)."""
+        redis_client = MagicMock()
+        lock = MagicMock()
+        lock.acquire.return_value = True
+        lock.owned.return_value = True
+        redis_client.lock.return_value = lock
+        mock_get_redis.return_value = redis_client
+
+        session = _mock_session_returning_none()
+        mock_get_session.return_value.__enter__.return_value = session
+
+        uid = str(uuid4())
+
+        process_user_file_impl(user_file_id=uid, tenant_id="t", redis_locking=True)
+        call_count_true = session.get.call_count
+
+        session.reset_mock()
+        mock_get_session.reset_mock()
+        mock_get_session.return_value.__enter__.return_value = session
+
+        process_user_file_impl(user_file_id=uid, tenant_id="t", redis_locking=False)
+        call_count_false = session.get.call_count
+
+        assert call_count_true == call_count_false == 1
+
+
+# ------------------------------------------------------------------
+# delete_user_file_impl
+# ------------------------------------------------------------------
+
+
+class TestDeleteUserFileImpl:
+    @patch(f"{TASKS_MODULE}.get_session_with_current_tenant")
+    @patch(f"{TASKS_MODULE}.get_redis_client")
+    def test_redis_locking_true_acquires_and_releases_lock(
+        self,
+        mock_get_redis: MagicMock,
+        mock_get_session: MagicMock,
+    ) -> None:
+        redis_client = MagicMock()
+        lock = MagicMock()
+        lock.acquire.return_value = True
+        lock.owned.return_value = True
+        redis_client.lock.return_value = lock
+        mock_get_redis.return_value = redis_client
+
+        session = _mock_session_returning_none()
+        mock_get_session.return_value.__enter__.return_value = session
+
+        delete_user_file_impl(
+            user_file_id=str(uuid4()),
+            tenant_id="test-tenant",
+            redis_locking=True,
+        )
+
+        mock_get_redis.assert_called_once()
+        lock.acquire.assert_called_once_with(blocking=False)
+        lock.release.assert_called_once()
+
+    @patch(f"{TASKS_MODULE}.get_session_with_current_tenant")
+    @patch(f"{TASKS_MODULE}.get_redis_client")
+    def test_redis_locking_true_skips_when_lock_held(
+        self,
+        mock_get_redis: MagicMock,
+        mock_get_session: MagicMock,
+    ) -> None:
+        redis_client = MagicMock()
+        lock = MagicMock()
+        lock.acquire.return_value = False
+        redis_client.lock.return_value = lock
+        mock_get_redis.return_value = redis_client
+
+        delete_user_file_impl(
+            user_file_id=str(uuid4()),
+            tenant_id="test-tenant",
+            redis_locking=True,
+        )
+
+        lock.acquire.assert_called_once()
+        mock_get_session.assert_not_called()
+
+    @patch(f"{TASKS_MODULE}.get_session_with_current_tenant")
+    @patch(f"{TASKS_MODULE}.get_redis_client")
+    def test_redis_locking_false_skips_redis_entirely(
+        self,
+        mock_get_redis: MagicMock,
+        mock_get_session: MagicMock,
+    ) -> None:
+        session = _mock_session_returning_none()
+        mock_get_session.return_value.__enter__.return_value = session
+
+        delete_user_file_impl(
+            user_file_id=str(uuid4()),
+            tenant_id="test-tenant",
+            redis_locking=False,
+        )
+
+        mock_get_redis.assert_not_called()
+        mock_get_session.assert_called_once()
+
+
+# ------------------------------------------------------------------
+# project_sync_user_file_impl
+# ------------------------------------------------------------------
+
+
+class TestProjectSyncUserFileImpl:
+    @patch(f"{TASKS_MODULE}.get_session_with_current_tenant")
+    @patch(f"{TASKS_MODULE}.get_redis_client")
+    def test_redis_locking_true_acquires_and_releases_lock(
+        self,
+        mock_get_redis: MagicMock,
+        mock_get_session: MagicMock,
+    ) -> None:
+        redis_client = MagicMock()
+        lock = MagicMock()
+        lock.acquire.return_value = True
+        lock.owned.return_value = True
+        redis_client.lock.return_value = lock
+        mock_get_redis.return_value = redis_client
+
+        session = _mock_session_returning_none()
+        mock_get_session.return_value.__enter__.return_value = session
+
+        project_sync_user_file_impl(
+            user_file_id=str(uuid4()),
+            tenant_id="test-tenant",
+            redis_locking=True,
+        )
+
+        mock_get_redis.assert_called_once()
+        redis_client.delete.assert_called_once()
+        lock.acquire.assert_called_once_with(blocking=False)
+        lock.release.assert_called_once()
+
+    @patch(f"{TASKS_MODULE}.get_session_with_current_tenant")
+    @patch(f"{TASKS_MODULE}.get_redis_client")
+    def test_redis_locking_true_skips_when_lock_held(
+        self,
+        mock_get_redis: MagicMock,
+        mock_get_session: MagicMock,
+    ) -> None:
+        redis_client = MagicMock()
+        lock = MagicMock()
+        lock.acquire.return_value = False
+        redis_client.lock.return_value = lock
+        mock_get_redis.return_value = redis_client
+
+        project_sync_user_file_impl(
+            user_file_id=str(uuid4()),
+            tenant_id="test-tenant",
+            redis_locking=True,
+        )
+
+        lock.acquire.assert_called_once()
+        mock_get_session.assert_not_called()
+
+    @patch(f"{TASKS_MODULE}.get_session_with_current_tenant")
+    @patch(f"{TASKS_MODULE}.get_redis_client")
+    def test_redis_locking_false_skips_redis_entirely(
+        self,
+        mock_get_redis: MagicMock,
+        mock_get_session: MagicMock,
+    ) -> None:
+        session = _mock_session_returning_none()
+        mock_get_session.return_value.__enter__.return_value = session
+
+        project_sync_user_file_impl(
+            user_file_id=str(uuid4()),
+            tenant_id="test-tenant",
+            redis_locking=False,
+        )
+
+        mock_get_redis.assert_not_called()
+        mock_get_session.assert_called_once()

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

@@ -0,0 +1,421 @@
+"""Tests for no-vector-DB user file processing paths.
+
+Verifies that when DISABLE_VECTOR_DB is True:
+- process_user_file_impl calls _process_user_file_without_vector_db (not indexing)
+- _process_user_file_without_vector_db extracts text, counts tokens, stores plaintext,
+  sets status=COMPLETED and chunk_count=0
+- delete_user_file_impl skips vector DB chunk deletion
+- project_sync_user_file_impl skips vector DB metadata update
+"""
+
+from unittest.mock import MagicMock
+from unittest.mock import patch
+from uuid import uuid4
+
+from onyx.background.celery.tasks.user_file_processing.tasks import (
+    _process_user_file_without_vector_db,
+)
+from onyx.background.celery.tasks.user_file_processing.tasks import (
+    delete_user_file_impl,
+)
+from onyx.background.celery.tasks.user_file_processing.tasks import (
+    process_user_file_impl,
+)
+from onyx.background.celery.tasks.user_file_processing.tasks import (
+    project_sync_user_file_impl,
+)
+from onyx.configs.constants import DocumentSource
+from onyx.connectors.models import Document
+from onyx.connectors.models import TextSection
+from onyx.db.enums import UserFileStatus
+
+TASKS_MODULE = "onyx.background.celery.tasks.user_file_processing.tasks"
+LLM_FACTORY_MODULE = "onyx.llm.factory"
+
+
+def _make_documents(texts: list[str]) -> list[Document]:
+    """Build a list of Document objects with the given section texts."""
+    return [
+        Document(
+            id=str(uuid4()),
+            source=DocumentSource.USER_FILE,
+            sections=[TextSection(text=t)],
+            semantic_identifier=f"test-doc-{i}",
+            metadata={},
+        )
+        for i, t in enumerate(texts)
+    ]
+
+
+def _make_user_file(
+    *,
+    status: UserFileStatus = UserFileStatus.PROCESSING,
+    file_id: str = "test-file-id",
+    name: str = "test.txt",
+) -> MagicMock:
+    """Return a MagicMock mimicking a UserFile ORM instance."""
+    uf = MagicMock()
+    uf.id = uuid4()
+    uf.file_id = file_id
+    uf.name = name
+    uf.status = status
+    uf.token_count = None
+    uf.chunk_count = None
+    uf.last_project_sync_at = None
+    uf.projects = []
+    uf.assistants = []
+    uf.needs_project_sync = True
+    uf.needs_persona_sync = True
+    return uf
+
+
+# ------------------------------------------------------------------
+# _process_user_file_without_vector_db — direct tests
+# ------------------------------------------------------------------
+
+
+class TestProcessUserFileWithoutVectorDb:
+    @patch(f"{TASKS_MODULE}.store_user_file_plaintext")
+    @patch(f"{LLM_FACTORY_MODULE}.get_llm_tokenizer_encode_func")
+    @patch(f"{LLM_FACTORY_MODULE}.get_default_llm")
+    def test_extracts_and_combines_text(
+        self,
+        mock_get_llm: MagicMock,  # noqa: ARG002
+        mock_get_encode: MagicMock,
+        mock_store_plaintext: MagicMock,
+    ) -> None:
+        mock_encode = MagicMock(return_value=[1, 2, 3, 4, 5])
+        mock_get_encode.return_value = mock_encode
+
+        uf = _make_user_file()
+        docs = _make_documents(["hello world", "foo bar"])
+        db_session = MagicMock()
+
+        _process_user_file_without_vector_db(uf, docs, db_session)
+
+        stored_text = mock_store_plaintext.call_args.kwargs["plaintext_content"]
+        assert "hello world" in stored_text
+        assert "foo bar" in stored_text
+
+    @patch(f"{TASKS_MODULE}.store_user_file_plaintext")
+    @patch(f"{LLM_FACTORY_MODULE}.get_llm_tokenizer_encode_func")
+    @patch(f"{LLM_FACTORY_MODULE}.get_default_llm")
+    def test_computes_token_count(
+        self,
+        mock_get_llm: MagicMock,  # noqa: ARG002
+        mock_get_encode: MagicMock,
+        mock_store_plaintext: MagicMock,  # noqa: ARG002
+    ) -> None:
+        mock_encode = MagicMock(return_value=list(range(42)))
+        mock_get_encode.return_value = mock_encode
+
+        uf = _make_user_file()
+        docs = _make_documents(["some text content"])
+        db_session = MagicMock()
+
+        _process_user_file_without_vector_db(uf, docs, db_session)
+
+        assert uf.token_count == 42
+
+    @patch(f"{TASKS_MODULE}.store_user_file_plaintext")
+    @patch(f"{LLM_FACTORY_MODULE}.get_llm_tokenizer_encode_func")
+    @patch(f"{LLM_FACTORY_MODULE}.get_default_llm")
+    def test_token_count_falls_back_to_none_on_error(
+        self,
+        mock_get_llm: MagicMock,
+        mock_get_encode: MagicMock,  # noqa: ARG002
+        mock_store_plaintext: MagicMock,  # noqa: ARG002
+    ) -> None:
+        mock_get_llm.side_effect = RuntimeError("No LLM configured")
+
+        uf = _make_user_file()
+        docs = _make_documents(["text"])
+        db_session = MagicMock()
+
+        _process_user_file_without_vector_db(uf, docs, db_session)
+
+        assert uf.token_count is None
+
+    @patch(f"{TASKS_MODULE}.store_user_file_plaintext")
+    @patch(f"{LLM_FACTORY_MODULE}.get_llm_tokenizer_encode_func")
+    @patch(f"{LLM_FACTORY_MODULE}.get_default_llm")
+    def test_stores_plaintext(
+        self,
+        mock_get_llm: MagicMock,  # noqa: ARG002
+        mock_get_encode: MagicMock,
+        mock_store_plaintext: MagicMock,
+    ) -> None:
+        mock_get_encode.return_value = MagicMock(return_value=[1])
+
+        uf = _make_user_file()
+        docs = _make_documents(["content to store"])
+        db_session = MagicMock()
+
+        _process_user_file_without_vector_db(uf, docs, db_session)
+
+        mock_store_plaintext.assert_called_once_with(
+            user_file_id=uf.id,
+            plaintext_content="content to store",
+        )
+
+    @patch(f"{TASKS_MODULE}.store_user_file_plaintext")
+    @patch(f"{LLM_FACTORY_MODULE}.get_llm_tokenizer_encode_func")
+    @patch(f"{LLM_FACTORY_MODULE}.get_default_llm")
+    def test_sets_completed_status_and_zero_chunk_count(
+        self,
+        mock_get_llm: MagicMock,  # noqa: ARG002
+        mock_get_encode: MagicMock,
+        mock_store_plaintext: MagicMock,  # noqa: ARG002
+    ) -> None:
+        mock_get_encode.return_value = MagicMock(return_value=[1])
+
+        uf = _make_user_file()
+        docs = _make_documents(["text"])
+        db_session = MagicMock()
+
+        _process_user_file_without_vector_db(uf, docs, db_session)
+
+        assert uf.status == UserFileStatus.COMPLETED
+        assert uf.chunk_count == 0
+        assert uf.last_project_sync_at is not None
+        db_session.add.assert_called_once_with(uf)
+        db_session.commit.assert_called_once()
+
+    @patch(f"{TASKS_MODULE}.store_user_file_plaintext")
+    @patch(f"{LLM_FACTORY_MODULE}.get_llm_tokenizer_encode_func")
+    @patch(f"{LLM_FACTORY_MODULE}.get_default_llm")
+    def test_preserves_deleting_status(
+        self,
+        mock_get_llm: MagicMock,  # noqa: ARG002
+        mock_get_encode: MagicMock,
+        mock_store_plaintext: MagicMock,  # noqa: ARG002
+    ) -> None:
+        mock_get_encode.return_value = MagicMock(return_value=[1])
+
+        uf = _make_user_file(status=UserFileStatus.DELETING)
+        docs = _make_documents(["text"])
+        db_session = MagicMock()
+
+        _process_user_file_without_vector_db(uf, docs, db_session)
+
+        assert uf.status == UserFileStatus.DELETING
+        assert uf.chunk_count == 0
+
+
+# ------------------------------------------------------------------
+# process_user_file_impl — branching on DISABLE_VECTOR_DB
+# ------------------------------------------------------------------
+
+
+class TestProcessImplBranching:
+    @patch(f"{TASKS_MODULE}._process_user_file_without_vector_db")
+    @patch(f"{TASKS_MODULE}._process_user_file_with_indexing")
+    @patch(f"{TASKS_MODULE}.DISABLE_VECTOR_DB", True)
+    @patch(f"{TASKS_MODULE}.get_session_with_current_tenant")
+    def test_calls_without_vector_db_when_disabled(
+        self,
+        mock_get_session: MagicMock,
+        mock_with_indexing: MagicMock,
+        mock_without_vdb: MagicMock,
+    ) -> None:
+        uf = _make_user_file()
+        session = MagicMock()
+        session.get.return_value = uf
+        mock_get_session.return_value.__enter__.return_value = session
+
+        connector_mock = MagicMock()
+        connector_mock.load_from_state.return_value = [_make_documents(["hello"])]
+
+        with patch(f"{TASKS_MODULE}.LocalFileConnector", return_value=connector_mock):
+            process_user_file_impl(
+                user_file_id=str(uf.id),
+                tenant_id="test-tenant",
+                redis_locking=False,
+            )
+
+        mock_without_vdb.assert_called_once()
+        mock_with_indexing.assert_not_called()
+
+    @patch(f"{TASKS_MODULE}._process_user_file_without_vector_db")
+    @patch(f"{TASKS_MODULE}._process_user_file_with_indexing")
+    @patch(f"{TASKS_MODULE}.DISABLE_VECTOR_DB", False)
+    @patch(f"{TASKS_MODULE}.get_session_with_current_tenant")
+    def test_calls_with_indexing_when_vector_db_enabled(
+        self,
+        mock_get_session: MagicMock,
+        mock_with_indexing: MagicMock,
+        mock_without_vdb: MagicMock,
+    ) -> None:
+        uf = _make_user_file()
+        session = MagicMock()
+        session.get.return_value = uf
+        mock_get_session.return_value.__enter__.return_value = session
+
+        connector_mock = MagicMock()
+        connector_mock.load_from_state.return_value = [_make_documents(["hello"])]
+
+        with patch(f"{TASKS_MODULE}.LocalFileConnector", return_value=connector_mock):
+            process_user_file_impl(
+                user_file_id=str(uf.id),
+                tenant_id="test-tenant",
+                redis_locking=False,
+            )
+
+        mock_with_indexing.assert_called_once()
+        mock_without_vdb.assert_not_called()
+
+    @patch(f"{TASKS_MODULE}.run_indexing_pipeline")
+    @patch(f"{TASKS_MODULE}.store_user_file_plaintext")
+    @patch(f"{TASKS_MODULE}.DISABLE_VECTOR_DB", True)
+    @patch(f"{TASKS_MODULE}.get_session_with_current_tenant")
+    def test_indexing_pipeline_not_called_when_disabled(
+        self,
+        mock_get_session: MagicMock,
+        mock_store_plaintext: MagicMock,  # noqa: ARG002
+        mock_run_pipeline: MagicMock,
+    ) -> None:
+        """End-to-end: verify run_indexing_pipeline is never invoked."""
+        uf = _make_user_file()
+        session = MagicMock()
+        session.get.return_value = uf
+        mock_get_session.return_value.__enter__.return_value = session
+
+        connector_mock = MagicMock()
+        connector_mock.load_from_state.return_value = [_make_documents(["content"])]
+
+        with (
+            patch(f"{TASKS_MODULE}.LocalFileConnector", return_value=connector_mock),
+            patch(f"{LLM_FACTORY_MODULE}.get_default_llm"),
+            patch(
+                f"{LLM_FACTORY_MODULE}.get_llm_tokenizer_encode_func",
+                return_value=MagicMock(return_value=[1, 2, 3]),
+            ),
+        ):
+            process_user_file_impl(
+                user_file_id=str(uf.id),
+                tenant_id="test-tenant",
+                redis_locking=False,
+            )
+
+        mock_run_pipeline.assert_not_called()
+
+
+# ------------------------------------------------------------------
+# delete_user_file_impl — vector DB skip
+# ------------------------------------------------------------------
+
+
+class TestDeleteImplNoVectorDb:
+    @patch(f"{TASKS_MODULE}.DISABLE_VECTOR_DB", True)
+    @patch(f"{TASKS_MODULE}.get_default_file_store")
+    @patch(f"{TASKS_MODULE}.get_session_with_current_tenant")
+    def test_skips_vector_db_deletion(
+        self,
+        mock_get_session: MagicMock,
+        mock_get_file_store: MagicMock,
+    ) -> None:
+        uf = _make_user_file(status=UserFileStatus.DELETING)
+        session = MagicMock()
+        session.get.return_value = uf
+        mock_get_session.return_value.__enter__.return_value = session
+        mock_get_file_store.return_value = MagicMock()
+
+        with (
+            patch(f"{TASKS_MODULE}.get_all_document_indices") as mock_get_indices,
+            patch(f"{TASKS_MODULE}.get_active_search_settings") as mock_get_ss,
+            patch(f"{TASKS_MODULE}.httpx_init_vespa_pool") as mock_vespa_pool,
+        ):
+            delete_user_file_impl(
+                user_file_id=str(uf.id),
+                tenant_id="test-tenant",
+                redis_locking=False,
+            )
+
+            mock_get_indices.assert_not_called()
+            mock_get_ss.assert_not_called()
+            mock_vespa_pool.assert_not_called()
+
+        session.delete.assert_called_once_with(uf)
+        session.commit.assert_called_once()
+
+    @patch(f"{TASKS_MODULE}.DISABLE_VECTOR_DB", True)
+    @patch(f"{TASKS_MODULE}.get_default_file_store")
+    @patch(f"{TASKS_MODULE}.get_session_with_current_tenant")
+    def test_still_deletes_file_store_and_db_record(
+        self,
+        mock_get_session: MagicMock,
+        mock_get_file_store: MagicMock,
+    ) -> None:
+        uf = _make_user_file(status=UserFileStatus.DELETING)
+        session = MagicMock()
+        session.get.return_value = uf
+        mock_get_session.return_value.__enter__.return_value = session
+
+        file_store = MagicMock()
+        mock_get_file_store.return_value = file_store
+
+        delete_user_file_impl(
+            user_file_id=str(uf.id),
+            tenant_id="test-tenant",
+            redis_locking=False,
+        )
+
+        assert file_store.delete_file.call_count == 2
+        session.delete.assert_called_once_with(uf)
+        session.commit.assert_called_once()
+
+
+# ------------------------------------------------------------------
+# project_sync_user_file_impl — vector DB skip
+# ------------------------------------------------------------------
+
+
+class TestProjectSyncImplNoVectorDb:
+    @patch(f"{TASKS_MODULE}.DISABLE_VECTOR_DB", True)
+    @patch(f"{TASKS_MODULE}.get_session_with_current_tenant")
+    def test_skips_vector_db_update(
+        self,
+        mock_get_session: MagicMock,
+    ) -> None:
+        uf = _make_user_file(status=UserFileStatus.COMPLETED)
+        session = MagicMock()
+        session.execute.return_value.scalar_one_or_none.return_value = uf
+        mock_get_session.return_value.__enter__.return_value = session
+
+        with (
+            patch(f"{TASKS_MODULE}.get_all_document_indices") as mock_get_indices,
+            patch(f"{TASKS_MODULE}.get_active_search_settings") as mock_get_ss,
+            patch(f"{TASKS_MODULE}.httpx_init_vespa_pool") as mock_vespa_pool,
+        ):
+            project_sync_user_file_impl(
+                user_file_id=str(uf.id),
+                tenant_id="test-tenant",
+                redis_locking=False,
+            )
+
+            mock_get_indices.assert_not_called()
+            mock_get_ss.assert_not_called()
+            mock_vespa_pool.assert_not_called()
+
+    @patch(f"{TASKS_MODULE}.DISABLE_VECTOR_DB", True)
+    @patch(f"{TASKS_MODULE}.get_session_with_current_tenant")
+    def test_still_clears_sync_flags(
+        self,
+        mock_get_session: MagicMock,
+    ) -> None:
+        uf = _make_user_file(status=UserFileStatus.COMPLETED)
+        session = MagicMock()
+        session.execute.return_value.scalar_one_or_none.return_value = uf
+        mock_get_session.return_value.__enter__.return_value = session
+
+        project_sync_user_file_impl(
+            user_file_id=str(uf.id),
+            tenant_id="test-tenant",
+            redis_locking=False,
+        )
+
+        assert uf.needs_project_sync is False
+        assert uf.needs_persona_sync is False
+        assert uf.last_project_sync_at is not None
+        session.add.assert_called_once_with(uf)
+        session.commit.assert_called_once()

backend/tests/unit/onyx/llm/test_factory.py

@@ -44,7 +44,6 @@ def _build_provider_view(
         id=1,
         name="test-provider",
         provider=provider,
-        default_model_name="test-model",
         model_configurations=[
             ModelConfigurationView(
                 name="test-model",
@@ -62,7 +61,6 @@ def _build_provider_view(
         groups=[],
         personas=[],
         deployment_name=None,
-        default_vision_model=None,
     )
 
 

backend/tests/unit/onyx/test_startup_validation.py

@@ -0,0 +1,52 @@
+"""Tests for startup validation in no-vector-DB mode.
+
+Verifies that DISABLE_VECTOR_DB raises RuntimeError when combined with
+incompatible settings (MULTI_TENANT, ENABLE_CRAFT).
+"""
+
+from unittest.mock import patch
+
+import pytest
+
+
+class TestValidateNoVectorDbSettings:
+    @patch("onyx.main.DISABLE_VECTOR_DB", False)
+    def test_no_error_when_vector_db_enabled(self) -> None:
+        from onyx.main import validate_no_vector_db_settings
+
+        validate_no_vector_db_settings()
+
+    @patch("onyx.main.DISABLE_VECTOR_DB", True)
+    @patch("onyx.main.MULTI_TENANT", False)
+    @patch("onyx.server.features.build.configs.ENABLE_CRAFT", False)
+    def test_no_error_when_no_conflicts(self) -> None:
+        from onyx.main import validate_no_vector_db_settings
+
+        validate_no_vector_db_settings()
+
+    @patch("onyx.main.DISABLE_VECTOR_DB", True)
+    @patch("onyx.main.MULTI_TENANT", True)
+    def test_raises_on_multi_tenant(self) -> None:
+        from onyx.main import validate_no_vector_db_settings
+
+        with pytest.raises(RuntimeError, match="MULTI_TENANT"):
+            validate_no_vector_db_settings()
+
+    @patch("onyx.main.DISABLE_VECTOR_DB", True)
+    @patch("onyx.main.MULTI_TENANT", False)
+    @patch("onyx.server.features.build.configs.ENABLE_CRAFT", True)
+    def test_raises_on_enable_craft(self) -> None:
+        from onyx.main import validate_no_vector_db_settings
+
+        with pytest.raises(RuntimeError, match="ENABLE_CRAFT"):
+            validate_no_vector_db_settings()
+
+    @patch("onyx.main.DISABLE_VECTOR_DB", True)
+    @patch("onyx.main.MULTI_TENANT", True)
+    @patch("onyx.server.features.build.configs.ENABLE_CRAFT", True)
+    def test_multi_tenant_checked_before_craft(self) -> None:
+        """MULTI_TENANT is checked first, so it should be the error raised."""
+        from onyx.main import validate_no_vector_db_settings
+
+        with pytest.raises(RuntimeError, match="MULTI_TENANT"):
+            validate_no_vector_db_settings()

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

@@ -0,0 +1,196 @@
+"""Tests for tool construction when DISABLE_VECTOR_DB is True.
+
+Verifies that:
+- SearchTool.is_available() returns False when vector DB is disabled
+- OpenURLTool.is_available() returns False when vector DB is disabled
+- The force-add SearchTool block is suppressed when DISABLE_VECTOR_DB
+- FileReaderTool.is_available() returns True when vector DB is disabled
+"""
+
+from unittest.mock import MagicMock
+from unittest.mock import patch
+
+from onyx.tools.tool_implementations.file_reader.file_reader_tool import FileReaderTool
+
+APP_CONFIGS_MODULE = "onyx.configs.app_configs"
+FILE_READER_MODULE = "onyx.tools.tool_implementations.file_reader.file_reader_tool"
+
+
+# ------------------------------------------------------------------
+# SearchTool.is_available()
+# ------------------------------------------------------------------
+
+
+class TestSearchToolAvailability:
+    @patch(f"{APP_CONFIGS_MODULE}.DISABLE_VECTOR_DB", True)
+    def test_unavailable_when_vector_db_disabled(self) -> None:
+        from onyx.tools.tool_implementations.search.search_tool import SearchTool
+
+        assert SearchTool.is_available(MagicMock()) is False
+
+    @patch("onyx.db.connector.check_user_files_exist", return_value=True)
+    @patch(
+        "onyx.tools.tool_implementations.search.search_tool.check_federated_connectors_exist",
+        return_value=False,
+    )
+    @patch(
+        "onyx.tools.tool_implementations.search.search_tool.check_connectors_exist",
+        return_value=False,
+    )
+    @patch(f"{APP_CONFIGS_MODULE}.DISABLE_VECTOR_DB", False)
+    def test_available_when_vector_db_enabled_and_files_exist(
+        self,
+        mock_connectors: MagicMock,  # noqa: ARG002
+        mock_federated: MagicMock,  # noqa: ARG002
+        mock_user_files: MagicMock,  # noqa: ARG002
+    ) -> None:
+        from onyx.tools.tool_implementations.search.search_tool import SearchTool
+
+        assert SearchTool.is_available(MagicMock()) is True
+
+
+# ------------------------------------------------------------------
+# OpenURLTool.is_available()
+# ------------------------------------------------------------------
+
+
+class TestOpenURLToolAvailability:
+    @patch(f"{APP_CONFIGS_MODULE}.DISABLE_VECTOR_DB", True)
+    def test_unavailable_when_vector_db_disabled(self) -> None:
+        from onyx.tools.tool_implementations.open_url.open_url_tool import OpenURLTool
+
+        assert OpenURLTool.is_available(MagicMock()) is False
+
+    @patch(f"{APP_CONFIGS_MODULE}.DISABLE_VECTOR_DB", False)
+    def test_available_when_vector_db_enabled(self) -> None:
+        from onyx.tools.tool_implementations.open_url.open_url_tool import OpenURLTool
+
+        assert OpenURLTool.is_available(MagicMock()) is True
+
+
+# ------------------------------------------------------------------
+# FileReaderTool.is_available()
+# ------------------------------------------------------------------
+
+
+class TestFileReaderToolAvailability:
+    @patch(f"{FILE_READER_MODULE}.DISABLE_VECTOR_DB", True)
+    def test_available_when_vector_db_disabled(self) -> None:
+        assert FileReaderTool.is_available(MagicMock()) is True
+
+    @patch(f"{FILE_READER_MODULE}.DISABLE_VECTOR_DB", False)
+    def test_unavailable_when_vector_db_enabled(self) -> None:
+        assert FileReaderTool.is_available(MagicMock()) is False
+
+
+# ------------------------------------------------------------------
+# Force-add SearchTool suppression
+# ------------------------------------------------------------------
+
+
+class TestForceAddSearchToolGuard:
+    def test_force_add_block_checks_disable_vector_db(self) -> None:
+        """The force-add SearchTool block in construct_tools should include
+        `not DISABLE_VECTOR_DB` so that forced search is also suppressed
+        without a vector DB."""
+        import inspect
+
+        from onyx.tools.tool_constructor import construct_tools
+
+        source = inspect.getsource(construct_tools)
+        assert "DISABLE_VECTOR_DB" in source, (
+            "construct_tools should reference DISABLE_VECTOR_DB "
+            "to suppress force-adding SearchTool"
+        )
+
+
+# ------------------------------------------------------------------
+# Persona API — _validate_vector_db_knowledge
+# ------------------------------------------------------------------
+
+
+class TestValidateVectorDbKnowledge:
+    @patch(
+        "onyx.server.features.persona.api.DISABLE_VECTOR_DB",
+        True,
+    )
+    def test_rejects_document_set_ids(self) -> None:
+        from fastapi import HTTPException
+
+        from onyx.server.features.persona.api import _validate_vector_db_knowledge
+
+        request = MagicMock()
+        request.document_set_ids = [1]
+        request.hierarchy_node_ids = []
+        request.document_ids = []
+
+        with __import__("pytest").raises(HTTPException) as exc_info:
+            _validate_vector_db_knowledge(request)
+        assert exc_info.value.status_code == 400
+        assert "document sets" in exc_info.value.detail
+
+    @patch(
+        "onyx.server.features.persona.api.DISABLE_VECTOR_DB",
+        True,
+    )
+    def test_rejects_hierarchy_node_ids(self) -> None:
+        from fastapi import HTTPException
+
+        from onyx.server.features.persona.api import _validate_vector_db_knowledge
+
+        request = MagicMock()
+        request.document_set_ids = []
+        request.hierarchy_node_ids = [1]
+        request.document_ids = []
+
+        with __import__("pytest").raises(HTTPException) as exc_info:
+            _validate_vector_db_knowledge(request)
+        assert exc_info.value.status_code == 400
+        assert "hierarchy nodes" in exc_info.value.detail
+
+    @patch(
+        "onyx.server.features.persona.api.DISABLE_VECTOR_DB",
+        True,
+    )
+    def test_rejects_document_ids(self) -> None:
+        from fastapi import HTTPException
+
+        from onyx.server.features.persona.api import _validate_vector_db_knowledge
+
+        request = MagicMock()
+        request.document_set_ids = []
+        request.hierarchy_node_ids = []
+        request.document_ids = ["doc-abc"]
+
+        with __import__("pytest").raises(HTTPException) as exc_info:
+            _validate_vector_db_knowledge(request)
+        assert exc_info.value.status_code == 400
+        assert "documents" in exc_info.value.detail
+
+    @patch(
+        "onyx.server.features.persona.api.DISABLE_VECTOR_DB",
+        True,
+    )
+    def test_allows_user_files_only(self) -> None:
+        from onyx.server.features.persona.api import _validate_vector_db_knowledge
+
+        request = MagicMock()
+        request.document_set_ids = []
+        request.hierarchy_node_ids = []
+        request.document_ids = []
+
+        _validate_vector_db_knowledge(request)
+
+    @patch(
+        "onyx.server.features.persona.api.DISABLE_VECTOR_DB",
+        False,
+    )
+    def test_allows_everything_when_vector_db_enabled(self) -> None:
+        from onyx.server.features.persona.api import _validate_vector_db_knowledge
+
+        request = MagicMock()
+        request.document_set_ids = [1, 2]
+        request.hierarchy_node_ids = [3]
+        request.document_ids = ["doc-x"]
+
+        _validate_vector_db_knowledge(request)

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

@@ -0,0 +1,237 @@
+"""Tests for the FileReaderTool.
+
+Verifies:
+- Tool definition schema is well-formed
+- File ID validation (allowlist, UUID format)
+- Character range extraction and clamping
+- Error handling for missing parameters and non-text files
+- is_available() reflects DISABLE_VECTOR_DB
+"""
+
+from unittest.mock import MagicMock
+from unittest.mock import patch
+from uuid import uuid4
+
+import pytest
+
+from onyx.file_store.models import ChatFileType
+from onyx.file_store.models import InMemoryChatFile
+from onyx.server.query_and_chat.placement import Placement
+from onyx.tools.models import ToolCallException
+from onyx.tools.tool_implementations.file_reader.file_reader_tool import FILE_ID_FIELD
+from onyx.tools.tool_implementations.file_reader.file_reader_tool import FileReaderTool
+from onyx.tools.tool_implementations.file_reader.file_reader_tool import MAX_NUM_CHARS
+from onyx.tools.tool_implementations.file_reader.file_reader_tool import NUM_CHARS_FIELD
+from onyx.tools.tool_implementations.file_reader.file_reader_tool import (
+    START_CHAR_FIELD,
+)
+
+TOOL_MODULE = "onyx.tools.tool_implementations.file_reader.file_reader_tool"
+_PLACEMENT = Placement(turn_index=0)
+
+
+def _make_tool(
+    user_file_ids: list | None = None,
+    chat_file_ids: list | None = None,
+) -> FileReaderTool:
+    emitter = MagicMock()
+    return FileReaderTool(
+        tool_id=99,
+        emitter=emitter,
+        user_file_ids=user_file_ids or [],
+        chat_file_ids=chat_file_ids or [],
+    )
+
+
+def _text_file(content: str, filename: str = "test.txt") -> InMemoryChatFile:
+    return InMemoryChatFile(
+        file_id="some-file-id",
+        content=content.encode("utf-8"),
+        file_type=ChatFileType.PLAIN_TEXT,
+        filename=filename,
+    )
+
+
+# ------------------------------------------------------------------
+# Tool metadata
+# ------------------------------------------------------------------
+
+
+class TestToolMetadata:
+    def test_tool_name(self) -> None:
+        tool = _make_tool()
+        assert tool.name == "read_file"
+
+    def test_tool_definition_schema(self) -> None:
+        tool = _make_tool()
+        defn = tool.tool_definition()
+        assert defn["type"] == "function"
+        func = defn["function"]
+        assert func["name"] == "read_file"
+        props = func["parameters"]["properties"]
+        assert FILE_ID_FIELD in props
+        assert START_CHAR_FIELD in props
+        assert NUM_CHARS_FIELD in props
+        assert func["parameters"]["required"] == [FILE_ID_FIELD]
+
+
+# ------------------------------------------------------------------
+# File ID validation
+# ------------------------------------------------------------------
+
+
+class TestFileIdValidation:
+    def test_rejects_invalid_uuid(self) -> None:
+        tool = _make_tool()
+        with pytest.raises(ToolCallException, match="Invalid file_id"):
+            tool._validate_file_id("not-a-uuid")
+
+    def test_rejects_file_not_in_allowlist(self) -> None:
+        tool = _make_tool(user_file_ids=[uuid4()])
+        other_id = uuid4()
+        with pytest.raises(ToolCallException, match="not in available files"):
+            tool._validate_file_id(str(other_id))
+
+    def test_accepts_user_file_id(self) -> None:
+        uid = uuid4()
+        tool = _make_tool(user_file_ids=[uid])
+        assert tool._validate_file_id(str(uid)) == uid
+
+    def test_accepts_chat_file_id(self) -> None:
+        cid = uuid4()
+        tool = _make_tool(chat_file_ids=[cid])
+        assert tool._validate_file_id(str(cid)) == cid
+
+
+# ------------------------------------------------------------------
+# run() — character range extraction
+# ------------------------------------------------------------------
+
+
+class TestRun:
+    @patch(f"{TOOL_MODULE}.get_session_with_current_tenant")
+    @patch(f"{TOOL_MODULE}.load_user_file")
+    def test_returns_full_content_by_default(
+        self,
+        mock_load_user_file: MagicMock,
+        mock_get_session: MagicMock,
+    ) -> None:
+        uid = uuid4()
+        content = "Hello, world!"
+        mock_load_user_file.return_value = _text_file(content)
+        mock_get_session.return_value.__enter__.return_value = MagicMock()
+
+        tool = _make_tool(user_file_ids=[uid])
+        resp = tool.run(
+            placement=_PLACEMENT,
+            override_kwargs=MagicMock(),
+            **{FILE_ID_FIELD: str(uid)},
+        )
+        assert content in resp.llm_facing_response
+
+    @patch(f"{TOOL_MODULE}.get_session_with_current_tenant")
+    @patch(f"{TOOL_MODULE}.load_user_file")
+    def test_respects_start_char_and_num_chars(
+        self,
+        mock_load_user_file: MagicMock,
+        mock_get_session: MagicMock,
+    ) -> None:
+        uid = uuid4()
+        content = "abcdefghijklmnop"
+        mock_load_user_file.return_value = _text_file(content)
+        mock_get_session.return_value.__enter__.return_value = MagicMock()
+
+        tool = _make_tool(user_file_ids=[uid])
+        resp = tool.run(
+            placement=_PLACEMENT,
+            override_kwargs=MagicMock(),
+            **{FILE_ID_FIELD: str(uid), START_CHAR_FIELD: 4, NUM_CHARS_FIELD: 6},
+        )
+        assert "efghij" in resp.llm_facing_response
+
+    @patch(f"{TOOL_MODULE}.get_session_with_current_tenant")
+    @patch(f"{TOOL_MODULE}.load_user_file")
+    def test_clamps_num_chars_to_max(
+        self,
+        mock_load_user_file: MagicMock,
+        mock_get_session: MagicMock,
+    ) -> None:
+        uid = uuid4()
+        content = "x" * (MAX_NUM_CHARS + 500)
+        mock_load_user_file.return_value = _text_file(content)
+        mock_get_session.return_value.__enter__.return_value = MagicMock()
+
+        tool = _make_tool(user_file_ids=[uid])
+        resp = tool.run(
+            placement=_PLACEMENT,
+            override_kwargs=MagicMock(),
+            **{FILE_ID_FIELD: str(uid), NUM_CHARS_FIELD: MAX_NUM_CHARS + 9999},
+        )
+        assert f"Characters 0-{MAX_NUM_CHARS}" in resp.llm_facing_response
+
+    @patch(f"{TOOL_MODULE}.get_session_with_current_tenant")
+    @patch(f"{TOOL_MODULE}.load_user_file")
+    def test_includes_continuation_hint(
+        self,
+        mock_load_user_file: MagicMock,
+        mock_get_session: MagicMock,
+    ) -> None:
+        uid = uuid4()
+        content = "x" * 100
+        mock_load_user_file.return_value = _text_file(content)
+        mock_get_session.return_value.__enter__.return_value = MagicMock()
+
+        tool = _make_tool(user_file_ids=[uid])
+        resp = tool.run(
+            placement=_PLACEMENT,
+            override_kwargs=MagicMock(),
+            **{FILE_ID_FIELD: str(uid), NUM_CHARS_FIELD: 10},
+        )
+        assert "use start_char=10 to continue reading" in resp.llm_facing_response
+
+    def test_raises_on_missing_file_id(self) -> None:
+        tool = _make_tool()
+        with pytest.raises(ToolCallException, match="Missing required"):
+            tool.run(
+                placement=_PLACEMENT,
+                override_kwargs=MagicMock(),
+            )
+
+    @patch(f"{TOOL_MODULE}.get_session_with_current_tenant")
+    @patch(f"{TOOL_MODULE}.load_user_file")
+    def test_raises_on_non_text_file(
+        self,
+        mock_load_user_file: MagicMock,
+        mock_get_session: MagicMock,
+    ) -> None:
+        uid = uuid4()
+        mock_load_user_file.return_value = InMemoryChatFile(
+            file_id="img",
+            content=b"\x89PNG",
+            file_type=ChatFileType.IMAGE,
+            filename="photo.png",
+        )
+        mock_get_session.return_value.__enter__.return_value = MagicMock()
+
+        tool = _make_tool(user_file_ids=[uid])
+        with pytest.raises(ToolCallException, match="not a text file"):
+            tool.run(
+                placement=_PLACEMENT,
+                override_kwargs=MagicMock(),
+                **{FILE_ID_FIELD: str(uid)},
+            )
+
+
+# ------------------------------------------------------------------
+# is_available()
+# ------------------------------------------------------------------
+
+
+class TestIsAvailable:
+    @patch(f"{TOOL_MODULE}.DISABLE_VECTOR_DB", True)
+    def test_available_when_vector_db_disabled(self) -> None:
+        assert FileReaderTool.is_available(MagicMock()) is True
+
+    @patch(f"{TOOL_MODULE}.DISABLE_VECTOR_DB", False)
+    def test_unavailable_when_vector_db_enabled(self) -> None:
+        assert FileReaderTool.is_available(MagicMock()) is False

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

@@ -468,7 +468,7 @@ services:
       - minio_data:/data
     command: server /data --console-address ":9001"
     healthcheck:
-      test: ["CMD", "curl", "-f", "http://localhost:9000/minio/health/live"]
+      test: ["CMD", "mc", "ready", "local"]
       interval: 30s
       timeout: 20s
       retries: 3

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

@@ -293,7 +293,7 @@ services:
       - minio_data:/data
     command: server /data --console-address ":9001"
     healthcheck:
-      test: ["CMD", "curl", "-f", "http://localhost:9000/minio/health/live"]
+      test: ["CMD", "mc", "ready", "local"]
       interval: 30s
       timeout: 20s
       retries: 3

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

@@ -298,7 +298,7 @@ services:
       - minio_data:/data
     command: server /data --console-address ":9001"
     healthcheck:
-      test: ["CMD", "curl", "-f", "http://localhost:9000/minio/health/live"]
+      test: ["CMD", "mc", "ready", "local"]
       interval: 30s
       timeout: 20s
       retries: 3

deployment/docker_compose/docker-compose.prod.yml

@@ -335,7 +335,7 @@ services:
       - minio_data:/data
     command: server /data --console-address ":9001"
     healthcheck:
-      test: ["CMD", "curl", "-f", "http://localhost:9000/minio/health/live"]
+      test: ["CMD", "mc", "ready", "local"]
       interval: 30s
       timeout: 20s
       retries: 3

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

@@ -232,7 +232,7 @@ services:
       - minio_data:/data
     command: server /data --console-address ":9001"
     healthcheck:
-      test: ["CMD", "curl", "-f", "http://localhost:9000/minio/health/live"]
+      test: ["CMD", "mc", "ready", "local"]
       interval: 30s
       timeout: 20s
       retries: 3

deployment/docker_compose/docker-compose.yml

@@ -520,7 +520,7 @@ services:
       - minio_data:/data
     command: server /data --console-address ":9001"
     healthcheck:
-      test: ["CMD", "curl", "-f", "http://localhost:9000/minio/health/live"]
+      test: ["CMD", "mc", "ready", "local"]
       interval: 30s
       timeout: 20s
       retries: 3

uv.lock

@@ -8080,14 +8080,14 @@ wheels = [
 
 [[package]]
 name = "werkzeug"
-version = "3.1.5"
+version = "3.1.6"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "markupsafe" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/5a/70/1469ef1d3542ae7c2c7b72bd5e3a4e6ee69d7978fa8a3af05a38eca5becf/werkzeug-3.1.5.tar.gz", hash = "sha256:6a548b0e88955dd07ccb25539d7d0cc97417ee9e179677d22c7041c8f078ce67", size = 864754, upload-time = "2026-01-08T17:49:23.247Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/61/f1/ee81806690a87dab5f5653c1f146c92bc066d7f4cebc603ef88eb9e13957/werkzeug-3.1.6.tar.gz", hash = "sha256:210c6bede5a420a913956b4791a7f4d6843a43b6fcee4dfa08a65e93007d0d25", size = 864736, upload-time = "2026-02-19T15:17:18.884Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/ad/e4/8d97cca767bcc1be76d16fb76951608305561c6e056811587f36cb1316a8/werkzeug-3.1.5-py3-none-any.whl", hash = "sha256:5111e36e91086ece91f93268bb39b4a35c1e6f1feac762c9c822ded0a4e322dc", size = 225025, upload-time = "2026-01-08T17:49:21.859Z" },
+    { url = "https://files.pythonhosted.org/packages/4d/ec/d58832f89ede95652fd01f4f24236af7d32b70cab2196dfcc2d2fd13c5c2/werkzeug-3.1.6-py3-none-any.whl", hash = "sha256:7ddf3357bb9564e407607f988f683d72038551200c704012bb9a4c523d42f131", size = 225166, upload-time = "2026-02-19T15:17:17.475Z" },
 ]
 
 [[package]]

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

@@ -1,6 +1,6 @@
 /* Hoverable — item transitions */
 .hoverable-item {
-  transition: opacity 200ms ease-in-out;
+  transition: opacity 150ms ease-in-out;
 }
 
 .hoverable-item[data-hoverable-variant="opacity-on-hover"] {

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

@@ -58,7 +58,7 @@ function ContentAction({
 
   return (
     <div className="flex flex-row items-stretch w-full">
-      <div className={cn("flex-1 min-w-0", padding)}>
+      <div className={cn("flex-1 min-w-0 self-center", padding)}>
         <Content {...contentProps} />
       </div>
       {rightChildren && (

web/package-lock.json

@@ -4127,9 +4127,9 @@
       }
     },
     "node_modules/@rollup/rollup-android-arm-eabi": {
-      "version": "4.52.5",
-      "resolved": "https://registry.npmjs.org/@rollup/rollup-android-arm-eabi/-/rollup-android-arm-eabi-4.52.5.tgz",
-      "integrity": "sha512-8c1vW4ocv3UOMp9K+gToY5zL2XiiVw3k7f1ksf4yO1FlDFQ1C2u72iACFnSOceJFsWskc2WZNqeRhFRPzv+wtQ==",
+      "version": "4.59.0",
+      "resolved": "https://registry.npmjs.org/@rollup/rollup-android-arm-eabi/-/rollup-android-arm-eabi-4.59.0.tgz",
+      "integrity": "sha512-upnNBkA6ZH2VKGcBj9Fyl9IGNPULcjXRlg0LLeaioQWueH30p6IXtJEbKAgvyv+mJaMxSm1l6xwDXYjpEMiLMg==",
       "cpu": [
         "arm"
       ],
@@ -4140,9 +4140,9 @@
       ]
     },
     "node_modules/@rollup/rollup-android-arm64": {
-      "version": "4.52.5",
-      "resolved": "https://registry.npmjs.org/@rollup/rollup-android-arm64/-/rollup-android-arm64-4.52.5.tgz",
-      "integrity": "sha512-mQGfsIEFcu21mvqkEKKu2dYmtuSZOBMmAl5CFlPGLY94Vlcm+zWApK7F/eocsNzp8tKmbeBP8yXyAbx0XHsFNA==",
+      "version": "4.59.0",
+      "resolved": "https://registry.npmjs.org/@rollup/rollup-android-arm64/-/rollup-android-arm64-4.59.0.tgz",
+      "integrity": "sha512-hZ+Zxj3SySm4A/DylsDKZAeVg0mvi++0PYVceVyX7hemkw7OreKdCvW2oQ3T1FMZvCaQXqOTHb8qmBShoqk69Q==",
       "cpu": [
         "arm64"
       ],
@@ -4153,7 +4153,9 @@
       ]
     },
     "node_modules/@rollup/rollup-darwin-arm64": {
-      "version": "4.52.5",
+      "version": "4.59.0",
+      "resolved": "https://registry.npmjs.org/@rollup/rollup-darwin-arm64/-/rollup-darwin-arm64-4.59.0.tgz",
+      "integrity": "sha512-W2Psnbh1J8ZJw0xKAd8zdNgF9HRLkdWwwdWqubSVk0pUuQkoHnv7rx4GiF9rT4t5DIZGAsConRE3AxCdJ4m8rg==",
       "cpu": [
         "arm64"
       ],
@@ -4164,9 +4166,9 @@
       ]
     },
     "node_modules/@rollup/rollup-darwin-x64": {
-      "version": "4.52.5",
-      "resolved": "https://registry.npmjs.org/@rollup/rollup-darwin-x64/-/rollup-darwin-x64-4.52.5.tgz",
-      "integrity": "sha512-W901Pla8Ya95WpxDn//VF9K9u2JbocwV/v75TE0YIHNTbhqUTv9w4VuQ9MaWlNOkkEfFwkdNhXgcLqPSmHy0fA==",
+      "version": "4.59.0",
+      "resolved": "https://registry.npmjs.org/@rollup/rollup-darwin-x64/-/rollup-darwin-x64-4.59.0.tgz",
+      "integrity": "sha512-ZW2KkwlS4lwTv7ZVsYDiARfFCnSGhzYPdiOU4IM2fDbL+QGlyAbjgSFuqNRbSthybLbIJ915UtZBtmuLrQAT/w==",
       "cpu": [
         "x64"
       ],
@@ -4177,9 +4179,9 @@
       ]
     },
     "node_modules/@rollup/rollup-freebsd-arm64": {
-      "version": "4.52.5",
-      "resolved": "https://registry.npmjs.org/@rollup/rollup-freebsd-arm64/-/rollup-freebsd-arm64-4.52.5.tgz",
-      "integrity": "sha512-QofO7i7JycsYOWxe0GFqhLmF6l1TqBswJMvICnRUjqCx8b47MTo46W8AoeQwiokAx3zVryVnxtBMcGcnX12LvA==",
+      "version": "4.59.0",
+      "resolved": "https://registry.npmjs.org/@rollup/rollup-freebsd-arm64/-/rollup-freebsd-arm64-4.59.0.tgz",
+      "integrity": "sha512-EsKaJ5ytAu9jI3lonzn3BgG8iRBjV4LxZexygcQbpiU0wU0ATxhNVEpXKfUa0pS05gTcSDMKpn3Sx+QB9RlTTA==",
       "cpu": [
         "arm64"
       ],
@@ -4190,9 +4192,9 @@
       ]
     },
     "node_modules/@rollup/rollup-freebsd-x64": {
-      "version": "4.52.5",
-      "resolved": "https://registry.npmjs.org/@rollup/rollup-freebsd-x64/-/rollup-freebsd-x64-4.52.5.tgz",
-      "integrity": "sha512-jr21b/99ew8ujZubPo9skbrItHEIE50WdV86cdSoRkKtmWa+DDr6fu2c/xyRT0F/WazZpam6kk7IHBerSL7LDQ==",
+      "version": "4.59.0",
+      "resolved": "https://registry.npmjs.org/@rollup/rollup-freebsd-x64/-/rollup-freebsd-x64-4.59.0.tgz",
+      "integrity": "sha512-d3DuZi2KzTMjImrxoHIAODUZYoUUMsuUiY4SRRcJy6NJoZ6iIqWnJu9IScV9jXysyGMVuW+KNzZvBLOcpdl3Vg==",
       "cpu": [
         "x64"
       ],
@@ -4203,9 +4205,9 @@
       ]
     },
     "node_modules/@rollup/rollup-linux-arm-gnueabihf": {
-      "version": "4.52.5",
-      "resolved": "https://registry.npmjs.org/@rollup/rollup-linux-arm-gnueabihf/-/rollup-linux-arm-gnueabihf-4.52.5.tgz",
-      "integrity": "sha512-PsNAbcyv9CcecAUagQefwX8fQn9LQ4nZkpDboBOttmyffnInRy8R8dSg6hxxl2Re5QhHBf6FYIDhIj5v982ATQ==",
+      "version": "4.59.0",
+      "resolved": "https://registry.npmjs.org/@rollup/rollup-linux-arm-gnueabihf/-/rollup-linux-arm-gnueabihf-4.59.0.tgz",
+      "integrity": "sha512-t4ONHboXi/3E0rT6OZl1pKbl2Vgxf9vJfWgmUoCEVQVxhW6Cw/c8I6hbbu7DAvgp82RKiH7TpLwxnJeKv2pbsw==",
       "cpu": [
         "arm"
       ],
@@ -4216,9 +4218,9 @@
       ]
     },
     "node_modules/@rollup/rollup-linux-arm-musleabihf": {
-      "version": "4.52.5",
-      "resolved": "https://registry.npmjs.org/@rollup/rollup-linux-arm-musleabihf/-/rollup-linux-arm-musleabihf-4.52.5.tgz",
-      "integrity": "sha512-Fw4tysRutyQc/wwkmcyoqFtJhh0u31K+Q6jYjeicsGJJ7bbEq8LwPWV/w0cnzOqR2m694/Af6hpFayLJZkG2VQ==",
+      "version": "4.59.0",
+      "resolved": "https://registry.npmjs.org/@rollup/rollup-linux-arm-musleabihf/-/rollup-linux-arm-musleabihf-4.59.0.tgz",
+      "integrity": "sha512-CikFT7aYPA2ufMD086cVORBYGHffBo4K8MQ4uPS/ZnY54GKj36i196u8U+aDVT2LX4eSMbyHtyOh7D7Zvk2VvA==",
       "cpu": [
         "arm"
       ],
@@ -4229,9 +4231,9 @@
       ]
     },
     "node_modules/@rollup/rollup-linux-arm64-gnu": {
-      "version": "4.52.5",
-      "resolved": "https://registry.npmjs.org/@rollup/rollup-linux-arm64-gnu/-/rollup-linux-arm64-gnu-4.52.5.tgz",
-      "integrity": "sha512-a+3wVnAYdQClOTlyapKmyI6BLPAFYs0JM8HRpgYZQO02rMR09ZcV9LbQB+NL6sljzG38869YqThrRnfPMCDtZg==",
+      "version": "4.59.0",
+      "resolved": "https://registry.npmjs.org/@rollup/rollup-linux-arm64-gnu/-/rollup-linux-arm64-gnu-4.59.0.tgz",
+      "integrity": "sha512-jYgUGk5aLd1nUb1CtQ8E+t5JhLc9x5WdBKew9ZgAXg7DBk0ZHErLHdXM24rfX+bKrFe+Xp5YuJo54I5HFjGDAA==",
       "cpu": [
         "arm64"
       ],
@@ -4242,9 +4244,9 @@
       ]
     },
     "node_modules/@rollup/rollup-linux-arm64-musl": {
-      "version": "4.52.5",
-      "resolved": "https://registry.npmjs.org/@rollup/rollup-linux-arm64-musl/-/rollup-linux-arm64-musl-4.52.5.tgz",
-      "integrity": "sha512-AvttBOMwO9Pcuuf7m9PkC1PUIKsfaAJ4AYhy944qeTJgQOqJYJ9oVl2nYgY7Rk0mkbsuOpCAYSs6wLYB2Xiw0Q==",
+      "version": "4.59.0",
+      "resolved": "https://registry.npmjs.org/@rollup/rollup-linux-arm64-musl/-/rollup-linux-arm64-musl-4.59.0.tgz",
+      "integrity": "sha512-peZRVEdnFWZ5Bh2KeumKG9ty7aCXzzEsHShOZEFiCQlDEepP1dpUl/SrUNXNg13UmZl+gzVDPsiCwnV1uI0RUA==",
       "cpu": [
         "arm64"
       ],
@@ -4255,9 +4257,22 @@
       ]
     },
     "node_modules/@rollup/rollup-linux-loong64-gnu": {
-      "version": "4.52.5",
-      "resolved": "https://registry.npmjs.org/@rollup/rollup-linux-loong64-gnu/-/rollup-linux-loong64-gnu-4.52.5.tgz",
-      "integrity": "sha512-DkDk8pmXQV2wVrF6oq5tONK6UHLz/XcEVow4JTTerdeV1uqPeHxwcg7aFsfnSm9L+OO8WJsWotKM2JJPMWrQtA==",
+      "version": "4.59.0",
+      "resolved": "https://registry.npmjs.org/@rollup/rollup-linux-loong64-gnu/-/rollup-linux-loong64-gnu-4.59.0.tgz",
+      "integrity": "sha512-gbUSW/97f7+r4gHy3Jlup8zDG190AuodsWnNiXErp9mT90iCy9NKKU0Xwx5k8VlRAIV2uU9CsMnEFg/xXaOfXg==",
+      "cpu": [
+        "loong64"
+      ],
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "linux"
+      ]
+    },
+    "node_modules/@rollup/rollup-linux-loong64-musl": {
+      "version": "4.59.0",
+      "resolved": "https://registry.npmjs.org/@rollup/rollup-linux-loong64-musl/-/rollup-linux-loong64-musl-4.59.0.tgz",
+      "integrity": "sha512-yTRONe79E+o0FWFijasoTjtzG9EBedFXJMl888NBEDCDV9I2wGbFFfJQQe63OijbFCUZqxpHz1GzpbtSFikJ4Q==",
       "cpu": [
         "loong64"
       ],
@@ -4268,9 +4283,22 @@
       ]
     },
     "node_modules/@rollup/rollup-linux-ppc64-gnu": {
-      "version": "4.52.5",
-      "resolved": "https://registry.npmjs.org/@rollup/rollup-linux-ppc64-gnu/-/rollup-linux-ppc64-gnu-4.52.5.tgz",
-      "integrity": "sha512-W/b9ZN/U9+hPQVvlGwjzi+Wy4xdoH2I8EjaCkMvzpI7wJUs8sWJ03Rq96jRnHkSrcHTpQe8h5Tg3ZzUPGauvAw==",
+      "version": "4.59.0",
+      "resolved": "https://registry.npmjs.org/@rollup/rollup-linux-ppc64-gnu/-/rollup-linux-ppc64-gnu-4.59.0.tgz",
+      "integrity": "sha512-sw1o3tfyk12k3OEpRddF68a1unZ5VCN7zoTNtSn2KndUE+ea3m3ROOKRCZxEpmT9nsGnogpFP9x6mnLTCaoLkA==",
+      "cpu": [
+        "ppc64"
+      ],
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "linux"
+      ]
+    },
+    "node_modules/@rollup/rollup-linux-ppc64-musl": {
+      "version": "4.59.0",
+      "resolved": "https://registry.npmjs.org/@rollup/rollup-linux-ppc64-musl/-/rollup-linux-ppc64-musl-4.59.0.tgz",
+      "integrity": "sha512-+2kLtQ4xT3AiIxkzFVFXfsmlZiG5FXYW7ZyIIvGA7Bdeuh9Z0aN4hVyXS/G1E9bTP/vqszNIN/pUKCk/BTHsKA==",
       "cpu": [
         "ppc64"
       ],
@@ -4281,9 +4309,9 @@
       ]
     },
     "node_modules/@rollup/rollup-linux-riscv64-gnu": {
-      "version": "4.52.5",
-      "resolved": "https://registry.npmjs.org/@rollup/rollup-linux-riscv64-gnu/-/rollup-linux-riscv64-gnu-4.52.5.tgz",
-      "integrity": "sha512-sjQLr9BW7R/ZiXnQiWPkErNfLMkkWIoCz7YMn27HldKsADEKa5WYdobaa1hmN6slu9oWQbB6/jFpJ+P2IkVrmw==",
+      "version": "4.59.0",
+      "resolved": "https://registry.npmjs.org/@rollup/rollup-linux-riscv64-gnu/-/rollup-linux-riscv64-gnu-4.59.0.tgz",
+      "integrity": "sha512-NDYMpsXYJJaj+I7UdwIuHHNxXZ/b/N2hR15NyH3m2qAtb/hHPA4g4SuuvrdxetTdndfj9b1WOmy73kcPRoERUg==",
       "cpu": [
         "riscv64"
       ],
@@ -4294,9 +4322,9 @@
       ]
     },
     "node_modules/@rollup/rollup-linux-riscv64-musl": {
-      "version": "4.52.5",
-      "resolved": "https://registry.npmjs.org/@rollup/rollup-linux-riscv64-musl/-/rollup-linux-riscv64-musl-4.52.5.tgz",
-      "integrity": "sha512-hq3jU/kGyjXWTvAh2awn8oHroCbrPm8JqM7RUpKjalIRWWXE01CQOf/tUNWNHjmbMHg/hmNCwc/Pz3k1T/j/Lg==",
+      "version": "4.59.0",
+      "resolved": "https://registry.npmjs.org/@rollup/rollup-linux-riscv64-musl/-/rollup-linux-riscv64-musl-4.59.0.tgz",
+      "integrity": "sha512-nLckB8WOqHIf1bhymk+oHxvM9D3tyPndZH8i8+35p/1YiVoVswPid2yLzgX7ZJP0KQvnkhM4H6QZ5m0LzbyIAg==",
       "cpu": [
         "riscv64"
       ],
@@ -4307,9 +4335,9 @@
       ]
     },
     "node_modules/@rollup/rollup-linux-s390x-gnu": {
-      "version": "4.52.5",
-      "resolved": "https://registry.npmjs.org/@rollup/rollup-linux-s390x-gnu/-/rollup-linux-s390x-gnu-4.52.5.tgz",
-      "integrity": "sha512-gn8kHOrku8D4NGHMK1Y7NA7INQTRdVOntt1OCYypZPRt6skGbddska44K8iocdpxHTMMNui5oH4elPH4QOLrFQ==",
+      "version": "4.59.0",
+      "resolved": "https://registry.npmjs.org/@rollup/rollup-linux-s390x-gnu/-/rollup-linux-s390x-gnu-4.59.0.tgz",
+      "integrity": "sha512-oF87Ie3uAIvORFBpwnCvUzdeYUqi2wY6jRFWJAy1qus/udHFYIkplYRW+wo+GRUP4sKzYdmE1Y3+rY5Gc4ZO+w==",
       "cpu": [
         "s390x"
       ],
@@ -4320,9 +4348,9 @@
       ]
     },
     "node_modules/@rollup/rollup-linux-x64-gnu": {
-      "version": "4.52.5",
-      "resolved": "https://registry.npmjs.org/@rollup/rollup-linux-x64-gnu/-/rollup-linux-x64-gnu-4.52.5.tgz",
-      "integrity": "sha512-hXGLYpdhiNElzN770+H2nlx+jRog8TyynpTVzdlc6bndktjKWyZyiCsuDAlpd+j+W+WNqfcyAWz9HxxIGfZm1Q==",
+      "version": "4.59.0",
+      "resolved": "https://registry.npmjs.org/@rollup/rollup-linux-x64-gnu/-/rollup-linux-x64-gnu-4.59.0.tgz",
+      "integrity": "sha512-3AHmtQq/ppNuUspKAlvA8HtLybkDflkMuLK4DPo77DfthRb71V84/c4MlWJXixZz4uruIH4uaa07IqoAkG64fg==",
       "cpu": [
         "x64"
       ],
@@ -4333,9 +4361,9 @@
       ]
     },
     "node_modules/@rollup/rollup-linux-x64-musl": {
-      "version": "4.52.5",
-      "resolved": "https://registry.npmjs.org/@rollup/rollup-linux-x64-musl/-/rollup-linux-x64-musl-4.52.5.tgz",
-      "integrity": "sha512-arCGIcuNKjBoKAXD+y7XomR9gY6Mw7HnFBv5Rw7wQRvwYLR7gBAgV7Mb2QTyjXfTveBNFAtPt46/36vV9STLNg==",
+      "version": "4.59.0",
+      "resolved": "https://registry.npmjs.org/@rollup/rollup-linux-x64-musl/-/rollup-linux-x64-musl-4.59.0.tgz",
+      "integrity": "sha512-2UdiwS/9cTAx7qIUZB/fWtToJwvt0Vbo0zmnYt7ED35KPg13Q0ym1g442THLC7VyI6JfYTP4PiSOWyoMdV2/xg==",
       "cpu": [
         "x64"
       ],
@@ -4345,10 +4373,23 @@
         "linux"
       ]
     },
+    "node_modules/@rollup/rollup-openbsd-x64": {
+      "version": "4.59.0",
+      "resolved": "https://registry.npmjs.org/@rollup/rollup-openbsd-x64/-/rollup-openbsd-x64-4.59.0.tgz",
+      "integrity": "sha512-M3bLRAVk6GOwFlPTIxVBSYKUaqfLrn8l0psKinkCFxl4lQvOSz8ZrKDz2gxcBwHFpci0B6rttydI4IpS4IS/jQ==",
+      "cpu": [
+        "x64"
+      ],
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "openbsd"
+      ]
+    },
     "node_modules/@rollup/rollup-openharmony-arm64": {
-      "version": "4.52.5",
-      "resolved": "https://registry.npmjs.org/@rollup/rollup-openharmony-arm64/-/rollup-openharmony-arm64-4.52.5.tgz",
-      "integrity": "sha512-QoFqB6+/9Rly/RiPjaomPLmR/13cgkIGfA40LHly9zcH1S0bN2HVFYk3a1eAyHQyjs3ZJYlXvIGtcCs5tko9Cw==",
+      "version": "4.59.0",
+      "resolved": "https://registry.npmjs.org/@rollup/rollup-openharmony-arm64/-/rollup-openharmony-arm64-4.59.0.tgz",
+      "integrity": "sha512-tt9KBJqaqp5i5HUZzoafHZX8b5Q2Fe7UjYERADll83O4fGqJ49O1FsL6LpdzVFQcpwvnyd0i+K/VSwu/o/nWlA==",
       "cpu": [
         "arm64"
       ],
@@ -4359,9 +4400,9 @@
       ]
     },
     "node_modules/@rollup/rollup-win32-arm64-msvc": {
-      "version": "4.52.5",
-      "resolved": "https://registry.npmjs.org/@rollup/rollup-win32-arm64-msvc/-/rollup-win32-arm64-msvc-4.52.5.tgz",
-      "integrity": "sha512-w0cDWVR6MlTstla1cIfOGyl8+qb93FlAVutcor14Gf5Md5ap5ySfQ7R9S/NjNaMLSFdUnKGEasmVnu3lCMqB7w==",
+      "version": "4.59.0",
+      "resolved": "https://registry.npmjs.org/@rollup/rollup-win32-arm64-msvc/-/rollup-win32-arm64-msvc-4.59.0.tgz",
+      "integrity": "sha512-V5B6mG7OrGTwnxaNUzZTDTjDS7F75PO1ae6MJYdiMu60sq0CqN5CVeVsbhPxalupvTX8gXVSU9gq+Rx1/hvu6A==",
       "cpu": [
         "arm64"
       ],
@@ -4372,9 +4413,9 @@
       ]
     },
     "node_modules/@rollup/rollup-win32-ia32-msvc": {
-      "version": "4.52.5",
-      "resolved": "https://registry.npmjs.org/@rollup/rollup-win32-ia32-msvc/-/rollup-win32-ia32-msvc-4.52.5.tgz",
-      "integrity": "sha512-Aufdpzp7DpOTULJCuvzqcItSGDH73pF3ko/f+ckJhxQyHtp67rHw3HMNxoIdDMUITJESNE6a8uh4Lo4SLouOUg==",
+      "version": "4.59.0",
+      "resolved": "https://registry.npmjs.org/@rollup/rollup-win32-ia32-msvc/-/rollup-win32-ia32-msvc-4.59.0.tgz",
+      "integrity": "sha512-UKFMHPuM9R0iBegwzKF4y0C4J9u8C6MEJgFuXTBerMk7EJ92GFVFYBfOZaSGLu6COf7FxpQNqhNS4c4icUPqxA==",
       "cpu": [
         "ia32"
       ],
@@ -4385,9 +4426,9 @@
       ]
     },
     "node_modules/@rollup/rollup-win32-x64-gnu": {
-      "version": "4.52.5",
-      "resolved": "https://registry.npmjs.org/@rollup/rollup-win32-x64-gnu/-/rollup-win32-x64-gnu-4.52.5.tgz",
-      "integrity": "sha512-UGBUGPFp1vkj6p8wCRraqNhqwX/4kNQPS57BCFc8wYh0g94iVIW33wJtQAx3G7vrjjNtRaxiMUylM0ktp/TRSQ==",
+      "version": "4.59.0",
+      "resolved": "https://registry.npmjs.org/@rollup/rollup-win32-x64-gnu/-/rollup-win32-x64-gnu-4.59.0.tgz",
+      "integrity": "sha512-laBkYlSS1n2L8fSo1thDNGrCTQMmxjYY5G0WFWjFFYZkKPjsMBsgJfGf4TLxXrF6RyhI60L8TMOjBMvXiTcxeA==",
       "cpu": [
         "x64"
       ],
@@ -4398,9 +4439,9 @@
       ]
     },
     "node_modules/@rollup/rollup-win32-x64-msvc": {
-      "version": "4.52.5",
-      "resolved": "https://registry.npmjs.org/@rollup/rollup-win32-x64-msvc/-/rollup-win32-x64-msvc-4.52.5.tgz",
-      "integrity": "sha512-TAcgQh2sSkykPRWLrdyy2AiceMckNf5loITqXxFI5VuQjS5tSuw3WlwdN8qv8vzjLAUTvYaH/mVjSFpbkFbpTg==",
+      "version": "4.59.0",
+      "resolved": "https://registry.npmjs.org/@rollup/rollup-win32-x64-msvc/-/rollup-win32-x64-msvc-4.59.0.tgz",
+      "integrity": "sha512-2HRCml6OztYXyJXAvdDXPKcawukWY2GpR5/nxKp4iBgiO3wcoEGkAaqctIbZcNB6KlUQBIqt8VYkNSj2397EfA==",
       "cpu": [
         "x64"
       ],
@@ -14464,7 +14505,9 @@
       }
     },
     "node_modules/rollup": {
-      "version": "4.52.5",
+      "version": "4.59.0",
+      "resolved": "https://registry.npmjs.org/rollup/-/rollup-4.59.0.tgz",
+      "integrity": "sha512-2oMpl67a3zCH9H79LeMcbDhXW/UmWG/y2zuqnF2jQq5uq9TbM9TVyXvA4+t+ne2IIkBdrLpAaRQAvo7YI/Yyeg==",
       "license": "MIT",
       "dependencies": {
         "@types/estree": "1.0.8"
@@ -14477,28 +14520,31 @@
         "npm": ">=8.0.0"
       },
       "optionalDependencies": {
-        "@rollup/rollup-android-arm-eabi": "4.52.5",
-        "@rollup/rollup-android-arm64": "4.52.5",
-        "@rollup/rollup-darwin-arm64": "4.52.5",
-        "@rollup/rollup-darwin-x64": "4.52.5",
-        "@rollup/rollup-freebsd-arm64": "4.52.5",
-        "@rollup/rollup-freebsd-x64": "4.52.5",
-        "@rollup/rollup-linux-arm-gnueabihf": "4.52.5",
-        "@rollup/rollup-linux-arm-musleabihf": "4.52.5",
-        "@rollup/rollup-linux-arm64-gnu": "4.52.5",
-        "@rollup/rollup-linux-arm64-musl": "4.52.5",
-        "@rollup/rollup-linux-loong64-gnu": "4.52.5",
-        "@rollup/rollup-linux-ppc64-gnu": "4.52.5",
-        "@rollup/rollup-linux-riscv64-gnu": "4.52.5",
-        "@rollup/rollup-linux-riscv64-musl": "4.52.5",
-        "@rollup/rollup-linux-s390x-gnu": "4.52.5",
-        "@rollup/rollup-linux-x64-gnu": "4.52.5",
-        "@rollup/rollup-linux-x64-musl": "4.52.5",
-        "@rollup/rollup-openharmony-arm64": "4.52.5",
-        "@rollup/rollup-win32-arm64-msvc": "4.52.5",
-        "@rollup/rollup-win32-ia32-msvc": "4.52.5",
-        "@rollup/rollup-win32-x64-gnu": "4.52.5",
-        "@rollup/rollup-win32-x64-msvc": "4.52.5",
+        "@rollup/rollup-android-arm-eabi": "4.59.0",
+        "@rollup/rollup-android-arm64": "4.59.0",
+        "@rollup/rollup-darwin-arm64": "4.59.0",
+        "@rollup/rollup-darwin-x64": "4.59.0",
+        "@rollup/rollup-freebsd-arm64": "4.59.0",
+        "@rollup/rollup-freebsd-x64": "4.59.0",
+        "@rollup/rollup-linux-arm-gnueabihf": "4.59.0",
+        "@rollup/rollup-linux-arm-musleabihf": "4.59.0",
+        "@rollup/rollup-linux-arm64-gnu": "4.59.0",
+        "@rollup/rollup-linux-arm64-musl": "4.59.0",
+        "@rollup/rollup-linux-loong64-gnu": "4.59.0",
+        "@rollup/rollup-linux-loong64-musl": "4.59.0",
+        "@rollup/rollup-linux-ppc64-gnu": "4.59.0",
+        "@rollup/rollup-linux-ppc64-musl": "4.59.0",
+        "@rollup/rollup-linux-riscv64-gnu": "4.59.0",
+        "@rollup/rollup-linux-riscv64-musl": "4.59.0",
+        "@rollup/rollup-linux-s390x-gnu": "4.59.0",
+        "@rollup/rollup-linux-x64-gnu": "4.59.0",
+        "@rollup/rollup-linux-x64-musl": "4.59.0",
+        "@rollup/rollup-openbsd-x64": "4.59.0",
+        "@rollup/rollup-openharmony-arm64": "4.59.0",
+        "@rollup/rollup-win32-arm64-msvc": "4.59.0",
+        "@rollup/rollup-win32-ia32-msvc": "4.59.0",
+        "@rollup/rollup-win32-x64-gnu": "4.59.0",
+        "@rollup/rollup-win32-x64-msvc": "4.59.0",
         "fsevents": "~2.3.2"
       }
     },

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

@@ -11,7 +11,7 @@ import { DraggableTable } from "@/components/table/DraggableTable";
 import {
   deletePersona,
   personaComparator,
-  togglePersonaDefault,
+  togglePersonaFeatured,
   togglePersonaVisibility,
 } from "./lib";
 import { FiEdit2 } from "react-icons/fi";
@@ -27,8 +27,8 @@ function PersonaTypeDisplay({ persona }: { persona: Persona }) {
     return <Text as="p">Built-In</Text>;
   }
 
-  if (persona.is_default_persona) {
-    return <Text as="p">Default</Text>;
+  if (persona.featured) {
+    return <Text as="p">Featured</Text>;
   }
 
   if (persona.is_public) {
@@ -152,9 +152,9 @@ export function PersonasTable({
 
   const handleToggleDefault = async () => {
     if (personaToToggleDefault) {
-      const response = await togglePersonaDefault(
+      const response = await togglePersonaFeatured(
         personaToToggleDefault.id,
-        personaToToggleDefault.is_default_persona
+        personaToToggleDefault.featured
       );
       if (response.ok) {
         refreshPersonas();
@@ -180,7 +180,7 @@ export function PersonasTable({
       {defaultModalOpen &&
         personaToToggleDefault &&
         (() => {
-          const isDefault = personaToToggleDefault.is_default_persona;
+          const isDefault = personaToToggleDefault.featured;
 
           const title = isDefault
             ? "Remove Featured Agent"
@@ -252,7 +252,7 @@ export function PersonasTable({
               </p>,
               <PersonaTypeDisplay key={persona.id} persona={persona} />,
               <div
-                key="is_default_persona"
+                key="featured"
                 onClick={() => {
                   openDefaultModal(persona);
                 }}
@@ -261,13 +261,13 @@ export function PersonasTable({
                   `}
               >
                 <div className="my-auto flex-none w-22">
-                  {!persona.is_default_persona ? (
+                  {!persona.featured ? (
                     <div className="text-error">Not Featured</div>
                   ) : (
                     "Featured"
                   )}
                 </div>
-                <Checkbox checked={persona.is_default_persona} />
+                <Checkbox checked={persona.featured} />
               </div>,
               <div
                 key="is_visible"

web/src/app/admin/assistants/interfaces.ts

@@ -53,7 +53,7 @@ export interface MinimalPersonaSnapshot {
   is_public: boolean;
   is_visible: boolean;
   display_priority: number | null;
-  is_default_persona: boolean;
+  featured: boolean;
   builtin_persona: boolean;
 
   labels?: PersonaLabel[];
@@ -64,7 +64,6 @@ export interface Persona extends MinimalPersonaSnapshot {
   user_file_ids: string[];
   users: MinimalUserSnapshot[];
   groups: number[];
-  num_chunks?: number;
   // Hierarchy nodes (folders, spaces, channels) attached for scoped search
   hierarchy_nodes?: HierarchyNodeSnapshot[];
   // Individual documents attached for scoped search
@@ -79,8 +78,6 @@ export interface Persona extends MinimalPersonaSnapshot {
 
 export interface FullPersona extends Persona {
   search_start_date: string | null;
-  llm_relevance_filter?: boolean;
-  llm_filter_extraction?: boolean;
 }
 
 export interface PersonaLabel {

web/src/app/admin/assistants/lib.ts

@@ -11,11 +11,7 @@ interface PersonaUpsertRequest {
   task_prompt: string;
   datetime_aware: boolean;
   document_set_ids: number[];
-  num_chunks: number | null;
   is_public: boolean;
-  recency_bias: string;
-  llm_filter_extraction: boolean;
-  llm_relevance_filter: boolean | null;
   llm_model_provider_override: string | null;
   llm_model_version_override: string | null;
   starter_messages: StarterMessage[] | null;
@@ -26,7 +22,7 @@ interface PersonaUpsertRequest {
   uploaded_image_id: string | null;
   icon_name: string | null;
   search_start_date: Date | null;
-  is_default_persona: boolean;
+  featured: boolean;
   display_priority: number | null;
   label_ids: number[] | null;
   user_file_ids: string[] | null;
@@ -45,9 +41,7 @@ export interface PersonaUpsertParameters {
   task_prompt: string;
   datetime_aware: boolean;
   document_set_ids: number[];
-  num_chunks: number | null;
   is_public: boolean;
-  llm_relevance_filter: boolean | null;
   llm_model_provider_override: string | null;
   llm_model_version_override: string | null;
   starter_messages: StarterMessage[] | null;
@@ -58,7 +52,7 @@ export interface PersonaUpsertParameters {
   search_start_date: Date | null;
   uploaded_image_id: string | null;
   icon_name: string | null;
-  is_default_persona: boolean;
+  featured: boolean;
   label_ids: number[] | null;
   user_file_ids: string[];
   // Hierarchy nodes (folders, spaces, channels) for scoped search
@@ -73,7 +67,6 @@ function buildPersonaUpsertRequest({
   system_prompt,
   task_prompt,
   document_set_ids,
-  num_chunks,
   is_public,
   groups,
   datetime_aware,
@@ -86,8 +79,7 @@ function buildPersonaUpsertRequest({
   document_ids,
   icon_name,
   uploaded_image_id,
-  is_default_persona,
-  llm_relevance_filter,
+  featured,
   llm_model_provider_override,
   llm_model_version_override,
   starter_messages,
@@ -100,7 +92,6 @@ function buildPersonaUpsertRequest({
     system_prompt,
     task_prompt,
     document_set_ids,
-    num_chunks,
     is_public,
     uploaded_image_id,
     icon_name,
@@ -110,10 +101,7 @@ function buildPersonaUpsertRequest({
     remove_image,
     search_start_date,
     datetime_aware,
-    is_default_persona: is_default_persona ?? false,
-    recency_bias: "base_decay",
-    llm_filter_extraction: false,
-    llm_relevance_filter: llm_relevance_filter ?? null,
+    featured: featured ?? false,
     llm_model_provider_override: llm_model_provider_override ?? null,
     llm_model_version_override: llm_model_version_override ?? null,
     starter_messages: starter_messages ?? null,
@@ -226,17 +214,17 @@ export function personaComparator(
   return closerToZeroNegativesFirstComparator(a.id, b.id);
 }
 
-export async function togglePersonaDefault(
+export async function togglePersonaFeatured(
   personaId: number,
-  isDefault: boolean
+  featured: boolean
 ) {
-  const response = await fetch(`/api/admin/persona/${personaId}/default`, {
+  const response = await fetch(`/api/admin/persona/${personaId}/featured`, {
     method: "PATCH",
     headers: {
       "Content-Type": "application/json",
     },
     body: JSON.stringify({
-      is_default_persona: !isDefault,
+      featured: !featured,
     }),
     credentials: "include",
   });

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

@@ -2,7 +2,8 @@
 
 import { useState } from "react";
 import Link from "next/link";
-import { Section, LineItemLayout } from "@/layouts/general-layouts";
+import { Section } from "@/layouts/general-layouts";
+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";
@@ -372,9 +373,11 @@ function SeatsCard({
           padding={1}
           height="auto"
         >
-          <LineItemLayout
+          <Content
             title="Update Seats"
             description="Add or remove seats to reflect your team size."
+            sizePreset="main-content"
+            variant="section"
           />
           <Button main secondary onClick={handleCancel} disabled={isSubmitting}>
             Cancel

web/src/app/admin/configuration/image-generation/ImageGenerationConnectionModal.tsx

@@ -2,7 +2,7 @@
 
 import { ModalCreationInterface } from "@/refresh-components/contexts/ModalContext";
 import { ImageProvider } from "@/app/admin/configuration/image-generation/constants";
-import { LLMProviderView } from "@/app/admin/configuration/llm/interfaces";
+import { LLMProviderView } from "@/interfaces/llm";
 import { ImageGenerationConfigView } from "@/lib/configuration/imageConfigurationService";
 import { getImageGenForm } from "./forms";
 

web/src/app/admin/configuration/image-generation/ImageGenerationContent.tsx

@@ -7,7 +7,7 @@ import { Select } from "@/refresh-components/cards";
 import { useCreateModal } from "@/refresh-components/contexts/ModalContext";
 import { toast } from "@/hooks/useToast";
 import { errorHandlingFetcher } from "@/lib/fetcher";
-import { LLMProviderView } from "@/app/admin/configuration/llm/interfaces";
+import { LLMProviderResponse, LLMProviderView } from "@/interfaces/llm";
 import {
   IMAGE_PROVIDER_GROUPS,
   ImageProvider,
@@ -23,13 +23,14 @@ import Message from "@/refresh-components/messages/Message";
 
 export default function ImageGenerationContent() {
   const {
-    data: llmProviders = [],
+    data: llmProviderResponse,
     error: llmError,
     mutate: refetchProviders,
-  } = useSWR<LLMProviderView[]>(
+  } = useSWR<LLMProviderResponse<LLMProviderView>>(
     "/api/admin/llm/provider?include_image_gen=true",
     errorHandlingFetcher
   );
+  const llmProviders = llmProviderResponse?.providers ?? [];
 
   const {
     data: configs = [],

web/src/app/admin/configuration/image-generation/forms/types.ts

@@ -1,6 +1,6 @@
 import { FormikProps } from "formik";
 import { ImageProvider } from "../constants";
-import { LLMProviderView } from "@/app/admin/configuration/llm/interfaces";
+import { LLMProviderView } from "@/interfaces/llm";
 import {
   ImageGenerationConfigView,
   ImageGenerationCredentials,

web/src/app/admin/configuration/llm/LLMConfiguration.tsx

@@ -1,84 +0,0 @@
-"use client";
-
-import { errorHandlingFetcher } from "@/lib/fetcher";
-import useSWR from "swr";
-import { Callout } from "@/components/ui/callout";
-import Text from "@/refresh-components/texts/Text";
-import Title from "@/components/ui/title";
-import { ThreeDotsLoader } from "@/components/Loading";
-import { LLMProviderView } from "./interfaces";
-import { LLM_PROVIDERS_ADMIN_URL } from "./constants";
-import { OpenAIForm } from "./forms/OpenAIForm";
-import { AnthropicForm } from "./forms/AnthropicForm";
-import { OllamaForm } from "./forms/OllamaForm";
-import { AzureForm } from "./forms/AzureForm";
-import { BedrockForm } from "./forms/BedrockForm";
-import { VertexAIForm } from "./forms/VertexAIForm";
-import { OpenRouterForm } from "./forms/OpenRouterForm";
-import { getFormForExistingProvider } from "./forms/getForm";
-import { CustomForm } from "./forms/CustomForm";
-
-export function LLMConfiguration() {
-  const { data: existingLlmProviders } = useSWR<LLMProviderView[]>(
-    LLM_PROVIDERS_ADMIN_URL,
-    errorHandlingFetcher
-  );
-
-  if (!existingLlmProviders) {
-    return <ThreeDotsLoader />;
-  }
-
-  const isFirstProvider = existingLlmProviders.length === 0;
-
-  return (
-    <>
-      <Title className="mb-2">Enabled LLM Providers</Title>
-
-      {existingLlmProviders.length > 0 ? (
-        <>
-          <Text as="p" className="mb-4">
-            If multiple LLM providers are enabled, the default provider will be
-            used for all &quot;Default&quot; Assistants. For user-created
-            Assistants, you can select the LLM provider/model that best fits the
-            use case!
-          </Text>
-          <div className="flex flex-col gap-y-4">
-            {[...existingLlmProviders]
-              .sort((a, b) => {
-                if (a.is_default_provider && !b.is_default_provider) return -1;
-                if (!a.is_default_provider && b.is_default_provider) return 1;
-                return 0;
-              })
-              .map((llmProvider) => (
-                <div key={llmProvider.id}>
-                  {getFormForExistingProvider(llmProvider)}
-                </div>
-              ))}
-          </div>
-        </>
-      ) : (
-        <Callout type="warning" title="No LLM providers configured yet">
-          Please set one up below in order to start using Onyx!
-        </Callout>
-      )}
-
-      <Title className="mb-2 mt-6">Add LLM Provider</Title>
-      <Text as="p" className="mb-4">
-        Add a new LLM provider by either selecting from one of the default
-        providers or by specifying your own custom LLM provider.
-      </Text>
-
-      <div className="flex flex-col gap-y-4">
-        <OpenAIForm shouldMarkAsDefault={isFirstProvider} />
-        <AnthropicForm shouldMarkAsDefault={isFirstProvider} />
-        <OllamaForm shouldMarkAsDefault={isFirstProvider} />
-        <AzureForm shouldMarkAsDefault={isFirstProvider} />
-        <BedrockForm shouldMarkAsDefault={isFirstProvider} />
-        <VertexAIForm shouldMarkAsDefault={isFirstProvider} />
-        <OpenRouterForm shouldMarkAsDefault={isFirstProvider} />
-
-        <CustomForm shouldMarkAsDefault={isFirstProvider} />
-      </div>
-    </>
-  );
-}

web/src/app/admin/configuration/llm/ModelConfigurationField.tsx

@@ -1,13 +1,14 @@
 "use client";
 
 import { ArrayHelpers, FieldArray, FormikProps, useField } from "formik";
-import { ModelConfiguration } from "./interfaces";
+import { ModelConfiguration } from "@/interfaces/llm";
 import { ManualErrorMessage, TextFormField } from "@/components/Field";
 import { useEffect, useState } from "react";
 import CreateButton from "@/refresh-components/buttons/CreateButton";
 import { Button } from "@opal/components";
 import { SvgX } from "@opal/icons";
 import Text from "@/refresh-components/texts/Text";
+
 function ModelConfigurationRow({
   name,
   index,

web/src/app/admin/configuration/llm/forms/getForm.tsx

@@ -1,44 +0,0 @@
-import { LLMProviderName, LLMProviderView } from "../interfaces";
-import { AnthropicForm } from "./AnthropicForm";
-import { OpenAIForm } from "./OpenAIForm";
-import { OllamaForm } from "./OllamaForm";
-import { AzureForm } from "./AzureForm";
-import { VertexAIForm } from "./VertexAIForm";
-import { OpenRouterForm } from "./OpenRouterForm";
-import { CustomForm } from "./CustomForm";
-import { BedrockForm } from "./BedrockForm";
-
-export function detectIfRealOpenAIProvider(provider: LLMProviderView) {
-  return (
-    provider.provider === LLMProviderName.OPENAI &&
-    provider.api_key &&
-    !provider.api_base &&
-    Object.keys(provider.custom_config || {}).length === 0
-  );
-}
-
-export const getFormForExistingProvider = (provider: LLMProviderView) => {
-  switch (provider.provider) {
-    case LLMProviderName.OPENAI:
-      // "openai" as a provider name can be used for litellm proxy / any OpenAI-compatible provider
-      if (detectIfRealOpenAIProvider(provider)) {
-        return <OpenAIForm existingLlmProvider={provider} />;
-      } else {
-        return <CustomForm existingLlmProvider={provider} />;
-      }
-    case LLMProviderName.ANTHROPIC:
-      return <AnthropicForm existingLlmProvider={provider} />;
-    case LLMProviderName.OLLAMA_CHAT:
-      return <OllamaForm existingLlmProvider={provider} />;
-    case LLMProviderName.AZURE:
-      return <AzureForm existingLlmProvider={provider} />;
-    case LLMProviderName.VERTEX_AI:
-      return <VertexAIForm existingLlmProvider={provider} />;
-    case LLMProviderName.BEDROCK:
-      return <BedrockForm existingLlmProvider={provider} />;
-    case LLMProviderName.OPENROUTER:
-      return <OpenRouterForm existingLlmProvider={provider} />;
-    default:
-      return <CustomForm existingLlmProvider={provider} />;
-  }
-};

web/src/app/admin/configuration/llm/page.tsx

@@ -1,14 +1,7 @@
 "use client";
 
-import { AdminPageTitle } from "@/components/admin/Title";
-import { LLMConfiguration } from "./LLMConfiguration";
-import { SvgCpu } from "@opal/icons";
-export default function Page() {
-  return (
-    <>
-      <AdminPageTitle title="LLM Setup" icon={SvgCpu} />
+import LLMConfigurationPage from "@/refresh-pages/admin/LLMConfigurationPage";
 
-      <LLMConfiguration />
-    </>
-  );
+export default function Page() {
+  return <LLMConfigurationPage />;
 }

web/src/app/admin/configuration/llm/utils.ts

@@ -24,7 +24,7 @@ import {
   BedrockFetchParams,
   OllamaFetchParams,
   OpenRouterFetchParams,
-} from "./interfaces";
+} from "@/interfaces/llm";
 import { SvgAws, SvgOpenrouter } from "@opal/icons";
 
 // Aggregator providers that host models from multiple vendors
@@ -106,8 +106,9 @@ export const getProviderIcon = (
   return CPUIcon;
 };
 
-export const isAnthropic = (provider: string, modelName: string) =>
-  provider === "anthropic" || modelName.toLowerCase().includes("claude");
+export const isAnthropic = (provider: string, modelName?: string) =>
+  provider === LLMProviderName.ANTHROPIC ||
+  !!modelName?.toLowerCase().includes("claude");
 
 /**
  * Fetches Bedrock models directly without any form state dependencies.
@@ -153,6 +154,7 @@ export const fetchBedrockModels = async (
       is_visible: false,
       max_input_tokens: modelData.max_input_tokens,
       supports_image_input: modelData.supports_image_input,
+      supports_reasoning: false,
     }));
 
     return { models };
@@ -205,6 +207,7 @@ export const fetchOllamaModels = async (
       is_visible: true,
       max_input_tokens: modelData.max_input_tokens,
       supports_image_input: modelData.supports_image_input,
+      supports_reasoning: false,
     }));
 
     return { models };
@@ -262,6 +265,7 @@ export const fetchOpenRouterModels = async (
       is_visible: true,
       max_input_tokens: modelData.max_input_tokens,
       supports_image_input: modelData.supports_image_input,
+      supports_reasoning: false,
     }));
 
     return { models };

web/src/app/admin/connectors/[connector]/pages/FieldRendering.tsx

@@ -12,6 +12,7 @@ import Tabs from "@/refresh-components/Tabs";
 import { useFormikContext } from "formik";
 import * as GeneralLayouts from "@/layouts/general-layouts";
 import * as InputLayouts from "@/layouts/input-layouts";
+import { Content } from "@opal/layouts";
 import CheckboxField from "@/refresh-components/form/LabeledCheckboxField";
 import InputTextAreaField from "@/refresh-components/form/InputTextAreaField";
 import Text from "@/refresh-components/texts/Text";
@@ -46,9 +47,11 @@ const TabsField: FC<TabsFieldProps> = ({
   return (
     <GeneralLayouts.Section gap={0.5} alignItems="start">
       {tabField.label && (
-        <InputLayouts.Title
+        <Content
           title={resolvedLabel ?? ""}
           description={resolvedDescription}
+          sizePreset="main-content"
+          variant="section"
         />
       )}
 

web/src/app/admin/discord-bot/[guild-id]/page.tsx

@@ -5,7 +5,8 @@ import { cn } from "@/lib/utils";
 import { ThreeDotsLoader } from "@/components/Loading";
 import { ErrorCallout } from "@/components/ErrorCallout";
 import { toast } from "@/hooks/useToast";
-import { Section, LineItemLayout } from "@/layouts/general-layouts";
+import { Section } from "@/layouts/general-layouts";
+import { ContentAction } from "@opal/layouts";
 import * as SettingsLayouts from "@/layouts/settings-layouts";
 import Text from "@/refresh-components/texts/Text";
 import Card from "@/refresh-components/cards/Card";
@@ -89,9 +90,11 @@ function GuildDetailContent({
       )}
 
       <Card variant={disabled ? "disabled" : "primary"}>
-        <LineItemLayout
+        <ContentAction
           title="Channel Configuration"
           description="Run !sync-channels in Discord to update the channel list."
+          sizePreset="main-content"
+          variant="section"
           rightChildren={
             isRegistered && !channelsLoading && !channelsError ? (
               <Section
@@ -339,9 +342,11 @@ export default function Page({ params }: Props) {
       <SettingsLayouts.Body>
         {/* Default Persona Selector */}
         <Card variant={!guild?.enabled ? "disabled" : "primary"}>
-          <LineItemLayout
+          <ContentAction
             title="Default Agent"
             description="The agent used by the bot in all channels unless overridden."
+            sizePreset="main-content"
+            variant="section"
             rightChildren={
               <InputSelect
                 value={guild?.default_persona_id?.toString() ?? "default"}

web/src/app/admin/document-index-migration/page.tsx

@@ -5,7 +5,7 @@ import useSWR from "swr";
 import { SvgArrowExchange } from "@opal/icons";
 import * as SettingsLayouts from "@/layouts/settings-layouts";
 import Card from "@/refresh-components/cards/Card";
-import { LineItemLayout } from "@/layouts/general-layouts";
+import { Content, ContentAction } from "@opal/layouts";
 import Text from "@/refresh-components/texts/Text";
 import InputSelect from "@/refresh-components/inputs/InputSelect";
 import Button from "@/refresh-components/buttons/Button";
@@ -72,9 +72,10 @@ function MigrationStatusSection() {
     <Card>
       <Text headingH3>Migration Status</Text>
 
-      <LineItemLayout
+      <ContentAction
         title="Started"
-        variant="secondary"
+        sizePreset="main-ui"
+        variant="section"
         rightChildren={
           <Text mainUiBody>
             {hasStarted ? formatTimestamp(data.created_at!) : "Not started"}
@@ -82,9 +83,10 @@ function MigrationStatusSection() {
         }
       />
 
-      <LineItemLayout
+      <ContentAction
         title="Chunks Migrated"
-        variant="secondary"
+        sizePreset="main-ui"
+        variant="section"
         rightChildren={
           <Text mainUiBody>
             {progressPercentage !== null
@@ -96,9 +98,10 @@ function MigrationStatusSection() {
         }
       />
 
-      <LineItemLayout
+      <ContentAction
         title="Completed"
-        variant="secondary"
+        sizePreset="main-ui"
+        variant="section"
         rightChildren={
           <Text mainUiBody>
             {hasCompleted
@@ -174,10 +177,11 @@ function RetrievalSourceSection() {
 
   return (
     <Card>
-      <LineItemLayout
+      <Content
         title="Retrieval Source"
         description="Controls which document index is used for retrieval."
-        variant="secondary"
+        sizePreset="main-ui"
+        variant="section"
       />
 
       <InputSelect

web/src/app/admin/embeddings/EmbeddingModelSelectionForm.tsx

@@ -25,7 +25,7 @@ import { ModelOption } from "@/components/embedding/ModelSelector";
 import {
   EMBEDDING_MODELS_ADMIN_URL,
   EMBEDDING_PROVIDERS_ADMIN_URL,
-} from "@/app/admin/configuration/llm/constants";
+} from "@/lib/llmConfig/constants";
 import { AdvancedSearchConfiguration } from "@/app/admin/embeddings/interfaces";
 import Button from "@/refresh-components/buttons/Button";