.

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Jamison Lahman <jamison@lahman.dev>

.devcontainer/Dockerfile

@@ -0,0 +1,62 @@
+FROM ubuntu:26.04@sha256:cc925e589b7543b910fea57a240468940003fbfc0515245a495dd0ad8fe7cef1
+
+RUN apt-get update && apt-get install -y --no-install-recommends \
+  curl \
+  fd-find \
+  fzf \
+  git \
+  jq \
+  less \
+  make \
+  neovim \
+  openssh-client \
+  python3-venv \
+  ripgrep \
+  sudo \
+  ca-certificates \
+  iptables \
+  ipset \
+  iproute2 \
+  dnsutils \
+  unzip \
+  wget \
+  zsh \
+  && curl -fsSL https://deb.nodesource.com/setup_20.x | bash - \
+  && apt-get install -y nodejs \
+  && install -m 0755 -d /etc/apt/keyrings \
+  && curl -fsSL https://cli.github.com/packages/githubcli-archive-keyring.gpg -o /etc/apt/keyrings/githubcli-archive-keyring.gpg \
+  && chmod go+r /etc/apt/keyrings/githubcli-archive-keyring.gpg \
+  && echo "deb [arch=$(dpkg --print-architecture) signed-by=/etc/apt/keyrings/githubcli-archive-keyring.gpg] https://cli.github.com/packages stable main" > /etc/apt/sources.list.d/github-cli.list \
+  && apt-get update \
+  && apt-get install -y --no-install-recommends gh \
+  && apt-get clean && rm -rf /var/lib/apt/lists/*
+
+# fd-find installs as fdfind on Debian/Ubuntu — symlink to fd
+RUN ln -sf "$(which fdfind)" /usr/local/bin/fd
+
+# Install uv (Python package manager)
+COPY --from=ghcr.io/astral-sh/uv:latest /uv /uvx /usr/local/bin/
+
+# Create non-root dev user with passwordless sudo
+RUN useradd -m -s /bin/zsh dev && \
+  echo "dev ALL=(ALL) NOPASSWD:ALL" > /etc/sudoers.d/dev && \
+  chmod 0440 /etc/sudoers.d/dev
+
+ENV DEVCONTAINER=true
+
+RUN mkdir -p /workspace && \
+  chown -R dev:dev /workspace
+
+WORKDIR /workspace
+
+# Install Claude Code
+ARG CLAUDE_CODE_VERSION=latest
+RUN npm install -g @anthropic-ai/claude-code@${CLAUDE_CODE_VERSION}
+
+# Configure zsh — source the repo-local zshrc so shell customization
+# doesn't require an image rebuild.
+RUN chsh -s /bin/zsh root && \
+  for rc in /root/.zshrc /home/dev/.zshrc; do \
+    echo '[ -f /workspace/.devcontainer/zshrc ] && . /workspace/.devcontainer/zshrc' >> "$rc"; \
+  done && \
+  chown dev:dev /home/dev/.zshrc

.devcontainer/README.md

@@ -0,0 +1,86 @@
+# Onyx Dev Container
+
+A containerized development environment for working on Onyx.
+
+## What's included
+
+- Ubuntu 26.04 base image
+- Node.js 20, uv, Claude Code
+- GitHub CLI (`gh`)
+- Neovim, ripgrep, fd, fzf, jq, make, wget, unzip
+- Zsh as default shell (sources host `~/.zshrc` if available)
+- Python venv auto-activation
+- Network firewall (default-deny, whitelists npm, GitHub, Anthropic APIs, Sentry, and VS Code update servers)
+
+## Usage
+
+### CLI (`ods dev`)
+
+The [`ods` devtools CLI](../tools/ods/README.md) provides workspace-aware wrappers
+for all devcontainer operations (also available as `ods dc`):
+
+```bash
+# Start the container
+ods dev up
+
+# Open a shell
+ods dev into
+
+# Run a command
+ods dev exec npm test
+
+# Stop the container
+ods dev stop
+```
+
+## Restarting the container
+
+```bash
+# Restart the container
+ods dev restart
+
+# Pull the latest published image and recreate
+ods dev rebuild
+```
+
+## Image
+
+The devcontainer uses a prebuilt image published to `onyxdotapp/onyx-devcontainer`.
+The tag is pinned in `devcontainer.json` — no local build is required.
+
+To build the image locally (e.g. while iterating on the Dockerfile):
+
+```bash
+docker buildx bake devcontainer
+```
+
+The `devcontainer` target is defined in `docker-bake.hcl` at the repo root.
+
+## User & permissions
+
+The container runs as the `dev` user by default (`remoteUser` in devcontainer.json).
+An init script (`init-dev-user.sh`) runs at container start to ensure the active
+user has read/write access to the bind-mounted workspace:
+
+- **Standard Docker** — `dev`'s UID/GID is remapped to match the workspace owner,
+  so file permissions work seamlessly.
+- **Rootless Docker** — The workspace appears as root-owned (UID 0) inside the
+  container due to user-namespace mapping. `ods dev up` auto-detects rootless Docker
+  and sets `DEVCONTAINER_REMOTE_USER=root` so the container runs as root — which
+  maps back to your host user via the user namespace. New files are owned by your
+  host UID and no ACL workarounds are needed.
+
+  To override the auto-detection, set `DEVCONTAINER_REMOTE_USER` before running
+  `ods dev up`.
+
+## Firewall
+
+The container starts with a default-deny firewall (`init-firewall.sh`) that only allows outbound traffic to:
+
+- npm registry
+- GitHub
+- Anthropic API
+- Sentry
+- VS Code update servers
+
+This requires the `NET_ADMIN` and `NET_RAW` capabilities, which are added via `runArgs` in `devcontainer.json`.

.devcontainer/devcontainer.json

@@ -0,0 +1,23 @@
+{
+  "name": "Onyx Dev Sandbox",
+  "image": "onyxdotapp/onyx-devcontainer@sha256:12184169c5bcc9cca0388286d5ffe504b569bc9c37bfa631b76ee8eee2064055",
+  "runArgs": ["--cap-add=NET_ADMIN", "--cap-add=NET_RAW"],
+  "mounts": [
+    "source=${localEnv:HOME}/.claude,target=/home/dev/.claude,type=bind",
+    "source=${localEnv:HOME}/.claude.json,target=/home/dev/.claude.json,type=bind",
+    "source=${localEnv:HOME}/.zshrc,target=/home/dev/.zshrc.host,type=bind,readonly",
+    "source=${localEnv:HOME}/.gitconfig,target=/home/dev/.gitconfig,type=bind,readonly",
+    "source=${localEnv:HOME}/.config/nvim,target=/home/dev/.config/nvim,type=bind,readonly",
+    "source=onyx-devcontainer-cache,target=/home/dev/.cache,type=volume",
+    "source=onyx-devcontainer-local,target=/home/dev/.local,type=volume"
+  ],
+  "containerEnv": {
+    "SSH_AUTH_SOCK": "/tmp/ssh-agent.sock"
+  },
+  "remoteUser": "${localEnv:DEVCONTAINER_REMOTE_USER:dev}",
+  "updateRemoteUserUID": false,
+  "workspaceMount": "source=${localWorkspaceFolder},target=/workspace,type=bind,consistency=delegated",
+  "workspaceFolder": "/workspace",
+  "postStartCommand": "sudo bash /workspace/.devcontainer/init-dev-user.sh && sudo bash /workspace/.devcontainer/init-firewall.sh",
+  "waitFor": "postStartCommand"
+}

.devcontainer/init-dev-user.sh

@@ -0,0 +1,107 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+# Remap the dev user's UID/GID to match the workspace owner so that
+# bind-mounted files are accessible without running as root.
+#
+# Standard Docker:   Workspace is owned by the host user's UID (e.g. 1000).
+#                    We remap dev to that UID -- fast and seamless.
+#
+# Rootless Docker:   Workspace appears as root-owned (UID 0) inside the
+#                    container due to user-namespace mapping.  Requires
+#                    DEVCONTAINER_REMOTE_USER=root (set automatically by
+#                    ods dev up).  Container root IS the host user, so
+#                    bind-mounts and named volumes are symlinked into /root.
+
+WORKSPACE=/workspace
+TARGET_USER=dev
+REMOTE_USER="${SUDO_USER:-$TARGET_USER}"
+
+WS_UID=$(stat -c '%u' "$WORKSPACE")
+WS_GID=$(stat -c '%g' "$WORKSPACE")
+DEV_UID=$(id -u "$TARGET_USER")
+DEV_GID=$(id -g "$TARGET_USER")
+
+# devcontainer.json bind-mounts and named volumes target /home/dev regardless
+# of remoteUser.  When running as root ($HOME=/root), Phase 1 bridges the gap
+# with symlinks from ACTIVE_HOME → MOUNT_HOME.
+MOUNT_HOME=/home/"$TARGET_USER"
+
+if [ "$REMOTE_USER" = "root" ]; then
+    ACTIVE_HOME="/root"
+else
+    ACTIVE_HOME="$MOUNT_HOME"
+fi
+
+# ── Phase 1: home directory setup ───────────────────────────────────
+
+# ~/.local and ~/.cache are named Docker volumes mounted under MOUNT_HOME.
+mkdir -p "$MOUNT_HOME"/.local/state "$MOUNT_HOME"/.local/share
+
+# When running as root, symlink bind-mounts and named volumes into /root
+# so that $HOME-relative tools (Claude Code, git, etc.) find them.
+if [ "$ACTIVE_HOME" != "$MOUNT_HOME" ]; then
+    for item in .claude .cache .local; do
+        [ -d "$MOUNT_HOME/$item" ] || continue
+        if [ -e "$ACTIVE_HOME/$item" ] && [ ! -L "$ACTIVE_HOME/$item" ]; then
+            echo "warning: replacing $ACTIVE_HOME/$item with symlink to $MOUNT_HOME/$item" >&2
+            rm -rf "$ACTIVE_HOME/$item"
+        fi
+        ln -sfn "$MOUNT_HOME/$item" "$ACTIVE_HOME/$item"
+    done
+    # Symlink files (not directories).
+    for file in .claude.json .gitconfig .zshrc.host; do
+        [ -f "$MOUNT_HOME/$file" ] && ln -sf "$MOUNT_HOME/$file" "$ACTIVE_HOME/$file"
+    done
+
+    # Nested mount: .config/nvim
+    if [ -d "$MOUNT_HOME/.config/nvim" ]; then
+        mkdir -p "$ACTIVE_HOME/.config"
+        if [ -e "$ACTIVE_HOME/.config/nvim" ] && [ ! -L "$ACTIVE_HOME/.config/nvim" ]; then
+            echo "warning: replacing $ACTIVE_HOME/.config/nvim with symlink" >&2
+            rm -rf "$ACTIVE_HOME/.config/nvim"
+        fi
+        ln -sfn "$MOUNT_HOME/.config/nvim" "$ACTIVE_HOME/.config/nvim"
+    fi
+fi
+
+# ── Phase 2: workspace access ───────────────────────────────────────
+
+# Root always has workspace access; Phase 1 handled home setup.
+if [ "$REMOTE_USER" = "root" ]; then
+    exit 0
+fi
+
+# Already matching -- nothing to do.
+if [ "$WS_UID" = "$DEV_UID" ] && [ "$WS_GID" = "$DEV_GID" ]; then
+    exit 0
+fi
+
+if [ "$WS_UID" != "0" ]; then
+    # ── Standard Docker ──────────────────────────────────────────────
+    # Workspace is owned by a non-root UID (the host user).
+    # Remap dev's UID/GID to match.
+    if [ "$DEV_GID" != "$WS_GID" ]; then
+        if ! groupmod -g "$WS_GID" "$TARGET_USER" 2>&1; then
+            echo "warning: failed to remap $TARGET_USER GID to $WS_GID" >&2
+        fi
+    fi
+    if [ "$DEV_UID" != "$WS_UID" ]; then
+        if ! usermod -u "$WS_UID" -g "$WS_GID" "$TARGET_USER" 2>&1; then
+            echo "warning: failed to remap $TARGET_USER UID to $WS_UID" >&2
+        fi
+    fi
+    if ! chown -R "$TARGET_USER":"$TARGET_USER" "$MOUNT_HOME" 2>&1; then
+        echo "warning: failed to chown $MOUNT_HOME" >&2
+    fi
+else
+    # ── Rootless Docker ──────────────────────────────────────────────
+    # Workspace is root-owned (UID 0) due to user-namespace mapping.
+    # The supported path is remoteUser=root (set DEVCONTAINER_REMOTE_USER=root),
+    # which is handled above.  If we reach here, the user is running as dev
+    # under rootless Docker without the override.
+    echo "error: rootless Docker detected but remoteUser is not root." >&2
+    echo "       Set DEVCONTAINER_REMOTE_USER=root before starting the container," >&2
+    echo "       or use 'ods dev up' which sets it automatically." >&2
+    exit 1
+fi

.devcontainer/init-firewall.sh

@@ -0,0 +1,105 @@
+#!/usr/bin/env bash
+
+set -euo pipefail
+
+echo "Setting up firewall..."
+
+# Preserve docker dns resolution
+DOCKER_DNS_RULES=$(iptables-save | grep -E "^-A.*-d 127.0.0.11/32" || true)
+
+# Flush all rules
+iptables -t nat -F
+iptables -t nat -X
+iptables -t mangle -F
+iptables -t mangle -X
+iptables -F
+iptables -X
+
+# Restore docker dns rules
+if [ -n "$DOCKER_DNS_RULES" ]; then
+    echo "$DOCKER_DNS_RULES" | iptables-restore -n
+fi
+
+# Create ipset for allowed destinations
+ipset create allowed-domains hash:net || true
+ipset flush allowed-domains
+
+# Fetch GitHub IP ranges (IPv4 only -- ipset hash:net and iptables are IPv4)
+GITHUB_IPS=$(curl -s https://api.github.com/meta | jq -r '.api[]' 2>/dev/null | grep -v ':' || echo "")
+for ip in $GITHUB_IPS; do
+    if ! ipset add allowed-domains "$ip" -exist 2>&1; then
+        echo "warning: failed to add GitHub IP $ip to allowlist" >&2
+    fi
+done
+
+# Resolve allowed domains
+ALLOWED_DOMAINS=(
+    "registry.npmjs.org"
+    "api.anthropic.com"
+    "api-staging.anthropic.com"
+    "files.anthropic.com"
+    "sentry.io"
+    "update.code.visualstudio.com"
+    "pypi.org"
+    "files.pythonhosted.org"
+    "go.dev"
+    "storage.googleapis.com"
+    "static.rust-lang.org"
+)
+
+for domain in "${ALLOWED_DOMAINS[@]}"; do
+    IPS=$(getent ahosts "$domain" 2>/dev/null | awk '{print $1}' | grep -v ':' | sort -u || echo "")
+    for ip in $IPS; do
+        if ! ipset add allowed-domains "$ip/32" -exist 2>&1; then
+            echo "warning: failed to add $domain ($ip) to allowlist" >&2
+        fi
+    done
+done
+
+# Allow traffic to the Docker gateway so the container can reach host services
+# (e.g. the Onyx stack at localhost:3000, localhost:8080, etc.)
+DOCKER_GATEWAY=$(ip -4 route show default | awk '{print $3}')
+if [ -n "$DOCKER_GATEWAY" ]; then
+    if ! ipset add allowed-domains "$DOCKER_GATEWAY/32" -exist 2>&1; then
+        echo "warning: failed to add Docker gateway $DOCKER_GATEWAY to allowlist" >&2
+    fi
+fi
+
+# Set default policies to DROP
+iptables -P FORWARD DROP
+iptables -P INPUT DROP
+iptables -P OUTPUT DROP
+
+# Allow established connections
+iptables -A INPUT -m conntrack --ctstate ESTABLISHED,RELATED -j ACCEPT
+iptables -A OUTPUT -m conntrack --ctstate ESTABLISHED,RELATED -j ACCEPT
+
+# Allow loopback
+iptables -A INPUT -i lo -j ACCEPT
+iptables -A OUTPUT -o lo -j ACCEPT
+
+# Allow DNS
+iptables -A OUTPUT -p udp --dport 53 -j ACCEPT
+iptables -A OUTPUT -p tcp --dport 53 -j ACCEPT
+
+# Allow outbound to allowed destinations
+iptables -A OUTPUT -m set --match-set allowed-domains dst -j ACCEPT
+
+# Reject unauthorized outbound
+iptables -A OUTPUT -j REJECT --reject-with icmp-host-unreachable
+
+# Validate firewall configuration
+echo "Validating firewall configuration..."
+
+BLOCKED_SITES=("example.com" "google.com" "facebook.com")
+for site in "${BLOCKED_SITES[@]}"; do
+    if timeout 2 ping -c 1 "$site" &>/dev/null; then
+        echo "Warning: $site is still reachable"
+    fi
+done
+
+if ! timeout 5 curl -s https://api.github.com/meta > /dev/null; then
+    echo "Warning: GitHub API is not accessible"
+fi
+
+echo "Firewall setup complete"

.devcontainer/zshrc

@@ -0,0 +1,10 @@
+# Devcontainer zshrc — sourced automatically for both root and dev users.
+# Edit this file to customize the shell without rebuilding the image.
+
+# Auto-activate Python venv
+if [ -f /workspace/.venv/bin/activate ]; then
+  . /workspace/.venv/bin/activate
+fi
+
+# Source host zshrc if bind-mounted
+[ -f ~/.zshrc.host ] && . ~/.zshrc.host

.github/workflows/deployment.yml

@@ -13,7 +13,7 @@ permissions:
   id-token: write # zizmor: ignore[excessive-permissions]
 
 env:
-  EDGE_TAG: ${{ startsWith(github.ref_name, 'nightly-latest') }}
+  EDGE_TAG: ${{ startsWith(github.ref_name, 'nightly-latest') || github.ref_name == 'edge' }}
 
 jobs:
   # Determine which components to build based on the tag
@@ -156,7 +156,7 @@ jobs:
   check-version-tag:
     runs-on: ubuntu-slim
     timeout-minutes: 10
-    if: ${{ !startsWith(github.ref_name, 'nightly-latest') && github.event_name != 'workflow_dispatch' }}
+    if: ${{ !startsWith(github.ref_name, 'nightly-latest') && github.ref_name != 'edge' && github.event_name != 'workflow_dispatch' }}
     steps:
       - name: Checkout
         uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # ratchet:actions/checkout@v6
@@ -228,7 +228,7 @@ jobs:
 
       - name: Create GitHub Release
         id: create-release
-        uses: softprops/action-gh-release@da05d552573ad5aba039eaac05058a918a7bf631 # ratchet:softprops/action-gh-release@v2
+        uses: softprops/action-gh-release@153bb8e04406b158c6c84fc1615b65b24149a1fe # ratchet:softprops/action-gh-release@v2
         with:
           tag_name: ${{ steps.release-tag.outputs.tag }}
           name: ${{ steps.release-tag.outputs.tag }}

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

@@ -21,7 +21,7 @@ jobs:
           persist-credentials: false
 
       - name: Install Helm CLI
-        uses: azure/setup-helm@1a275c3b69536ee54be43f2070a358922e12c8d4 # ratchet:azure/setup-helm@v4
+        uses: azure/setup-helm@dda3372f752e03dde6b3237bc9431cdc2f7a02a2 # ratchet:azure/setup-helm@v5.0.0
         with:
           version: v3.12.1
 

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

@@ -13,7 +13,7 @@ jobs:
     runs-on: ubuntu-latest
     timeout-minutes: 45
     steps:
-      - uses: actions/stale@997185467fa4f803885201cee163a9f38240193d # ratchet:actions/stale@v10
+      - uses: actions/stale@b5d41d4e1d5dceea10e7104786b73624c18a190f # ratchet:actions/stale@v10
         with:
           stale-issue-message: 'This issue is stale because it has been open 75 days with no activity. Remove stale label or comment or this will be closed in 15 days.'
           stale-pr-message: 'This PR is stale because it has been open 75 days with no activity. Remove stale label or comment or this will be closed in 15 days.'

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

@@ -36,7 +36,7 @@ jobs:
           persist-credentials: false
 
       - name: Set up Helm
-        uses: azure/setup-helm@1a275c3b69536ee54be43f2070a358922e12c8d4 # ratchet:azure/setup-helm@v4.3.1
+        uses: azure/setup-helm@dda3372f752e03dde6b3237bc9431cdc2f7a02a2 # ratchet:azure/setup-helm@v5.0.0
         with:
           version: v3.19.0
 

.gitignore

@@ -59,3 +59,6 @@ node_modules
 
 # plans
 plans/
+
+# Added context for LLMs
+onyx-llm-context/

.pre-commit-config.yaml

@@ -9,7 +9,6 @@ repos:
     rev: d30b4298e4fb63ce8609e29acdbcf4c9018a483c
     hooks:
       - id: uv-sync
-        args: ["--locked", "--all-extras"]
       - id: uv-lock
       - id: uv-export
         name: uv-export default.txt
@@ -18,7 +17,7 @@ repos:
             "--no-emit-project",
             "--no-default-groups",
             "--no-hashes",
-            "--extra",
+            "--group",
             "backend",
             "-o",
             "backend/requirements/default.txt",
@@ -31,7 +30,7 @@ repos:
             "--no-emit-project",
             "--no-default-groups",
             "--no-hashes",
-            "--extra",
+            "--group",
             "dev",
             "-o",
             "backend/requirements/dev.txt",
@@ -44,7 +43,7 @@ repos:
             "--no-emit-project",
             "--no-default-groups",
             "--no-hashes",
-            "--extra",
+            "--group",
             "ee",
             "-o",
             "backend/requirements/ee.txt",
@@ -57,7 +56,7 @@ repos:
             "--no-emit-project",
             "--no-default-groups",
             "--no-hashes",
-            "--extra",
+            "--group",
             "model_server",
             "-o",
             "backend/requirements/model_server.txt",

.vscode/launch.json

@@ -531,8 +531,7 @@
       "request": "launch",
       "runtimeExecutable": "uv",
       "runtimeArgs": [
-        "sync",
-        "--all-extras"
+        "sync"
       ],
       "cwd": "${workspaceFolder}",
       "console": "integratedTerminal",

CONTRIBUTING.md

@@ -117,7 +117,7 @@ If using PowerShell, the command slightly differs:
 Install the required Python dependencies:
 
 ```bash
-uv sync --all-extras
+uv sync
 ```
 
 Install Playwright for Python (headless browser required by the Web Connector):

backend/alembic/env.py

@@ -1,4 +1,4 @@
-from typing import Any, Literal
+from typing import Any
 from onyx.db.engine.iam_auth import get_iam_auth_token
 from onyx.configs.app_configs import USE_IAM_AUTH
 from onyx.configs.app_configs import POSTGRES_HOST
@@ -19,7 +19,6 @@ from logging.config import fileConfig
 
 from alembic import context
 from sqlalchemy.ext.asyncio import create_async_engine
-from sqlalchemy.sql.schema import SchemaItem
 from onyx.configs.constants import SSL_CERT_FILE
 from shared_configs.configs import (
     MULTI_TENANT,
@@ -45,8 +44,6 @@ if config.config_file_name is not None and config.attributes.get(
 
 target_metadata = [Base.metadata, ResultModelBase.metadata]
 
-EXCLUDE_TABLES = {"kombu_queue", "kombu_message"}
-
 logger = logging.getLogger(__name__)
 
 ssl_context: ssl.SSLContext | None = None
@@ -56,25 +53,6 @@ if USE_IAM_AUTH:
     ssl_context = ssl.create_default_context(cafile=SSL_CERT_FILE)
 
 
-def include_object(
-    object: SchemaItem,  # noqa: ARG001
-    name: str | None,
-    type_: Literal[
-        "schema",
-        "table",
-        "column",
-        "index",
-        "unique_constraint",
-        "foreign_key_constraint",
-    ],
-    reflected: bool,  # noqa: ARG001
-    compare_to: SchemaItem | None,  # noqa: ARG001
-) -> bool:
-    if type_ == "table" and name in EXCLUDE_TABLES:
-        return False
-    return True
-
-
 def filter_tenants_by_range(
     tenant_ids: list[str], start_range: int | None = None, end_range: int | None = None
 ) -> list[str]:
@@ -231,7 +209,6 @@ def do_run_migrations(
     context.configure(
         connection=connection,
         target_metadata=target_metadata,  # type: ignore
-        include_object=include_object,
         version_table_schema=schema_name,
         include_schemas=True,
         compare_type=True,
@@ -405,7 +382,6 @@ def run_migrations_offline() -> None:
                 url=url,
                 target_metadata=target_metadata,  # type: ignore
                 literal_binds=True,
-                include_object=include_object,
                 version_table_schema=schema,
                 include_schemas=True,
                 script_location=config.get_main_option("script_location"),
@@ -447,7 +423,6 @@ def run_migrations_offline() -> None:
                 url=url,
                 target_metadata=target_metadata,  # type: ignore
                 literal_binds=True,
-                include_object=include_object,
                 version_table_schema=schema,
                 include_schemas=True,
                 script_location=config.get_main_option("script_location"),
@@ -490,7 +465,6 @@ def run_migrations_online() -> None:
             context.configure(
                 connection=connection,
                 target_metadata=target_metadata,  # type: ignore
-                include_object=include_object,
                 version_table_schema=schema_name,
                 include_schemas=True,
                 compare_type=True,

backend/alembic_tenants/env.py

@@ -1,11 +1,9 @@
 import asyncio
 from logging.config import fileConfig
-from typing import Literal
 
 from sqlalchemy import pool
 from sqlalchemy.engine import Connection
 from sqlalchemy.ext.asyncio import create_async_engine
-from sqlalchemy.schema import SchemaItem
 
 from alembic import context
 from onyx.db.engine.sql_engine import build_connection_string
@@ -35,27 +33,6 @@ target_metadata = [PublicBase.metadata]
 # my_important_option = config.get_main_option("my_important_option")
 # ... etc.
 
-EXCLUDE_TABLES = {"kombu_queue", "kombu_message"}
-
-
-def include_object(
-    object: SchemaItem,  # noqa: ARG001
-    name: str | None,
-    type_: Literal[
-        "schema",
-        "table",
-        "column",
-        "index",
-        "unique_constraint",
-        "foreign_key_constraint",
-    ],
-    reflected: bool,  # noqa: ARG001
-    compare_to: SchemaItem | None,  # noqa: ARG001
-) -> bool:
-    if type_ == "table" and name in EXCLUDE_TABLES:
-        return False
-    return True
-
 
 def run_migrations_offline() -> None:
     """Run migrations in 'offline' mode.
@@ -85,7 +62,6 @@ def do_run_migrations(connection: Connection) -> None:
     context.configure(
         connection=connection,
         target_metadata=target_metadata,  # type: ignore[arg-type]
-        include_object=include_object,
     )
 
     with context.begin_transaction():

backend/ee/onyx/auth/users.py

@@ -10,9 +10,10 @@ from fastapi import status
 from ee.onyx.configs.app_configs import SUPER_CLOUD_API_KEY
 from ee.onyx.configs.app_configs import SUPER_USERS
 from ee.onyx.server.seeding import get_seed_config
-from onyx.auth.users import current_admin_user
+from onyx.auth.permissions import require_permission
 from onyx.configs.app_configs import AUTH_TYPE
 from onyx.configs.app_configs import USER_AUTH_SECRET
+from onyx.db.enums import Permission
 from onyx.db.models import User
 from onyx.utils.logger import setup_logger
 
@@ -39,7 +40,7 @@ def get_default_admin_user_emails_() -> list[str]:
 
 async def current_cloud_superuser(
     request: Request,
-    user: User = Depends(current_admin_user),
+    user: User = Depends(require_permission(Permission.FULL_ADMIN_PANEL_ACCESS)),
 ) -> User:
     api_key = request.headers.get("Authorization", "").replace("Bearer ", "")
     if api_key != SUPER_CLOUD_API_KEY:

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

@@ -5,6 +5,7 @@ from celery import Task
 from celery.exceptions import SoftTimeLimitExceeded
 from redis.lock import Lock as RedisLock
 
+from ee.onyx.server.tenants.product_gating import get_gated_tenants
 from onyx.background.celery.apps.app_base import task_logger
 from onyx.background.celery.tasks.beat_schedule import BEAT_EXPIRES_DEFAULT
 from onyx.configs.constants import CELERY_GENERIC_BEAT_LOCK_TIMEOUT
@@ -30,6 +31,7 @@ def cloud_beat_task_generator(
     queue: str = OnyxCeleryTask.DEFAULT,
     priority: int = OnyxCeleryPriority.MEDIUM,
     expires: int = BEAT_EXPIRES_DEFAULT,
+    skip_gated: bool = True,
 ) -> bool | None:
     """a lightweight task used to kick off individual beat tasks per tenant."""
     time_start = time.monotonic()
@@ -48,20 +50,22 @@ def cloud_beat_task_generator(
     last_lock_time = time.monotonic()
     tenant_ids: list[str] = []
     num_processed_tenants = 0
+    num_skipped_gated = 0
 
     try:
         tenant_ids = get_all_tenant_ids()
 
-        # NOTE: for now, we are running tasks for gated tenants, since we want to allow
-        # connector deletion to run successfully. The new plan is to continously prune
-        # the gated tenants set, so we won't have a build up of old, unused gated tenants.
-        # Keeping this around in case we want to revert to the previous behavior.
-        # gated_tenants = get_gated_tenants()
+        # Per-task control over whether gated tenants are included. Most periodic tasks
+        # do no useful work on gated tenants and just waste DB connections fanning out
+        # to ~10k+ inactive tenants. A small number of cleanup tasks (connector deletion,
+        # checkpoint/index attempt cleanup) need to run on gated tenants and pass
+        # `skip_gated=False` from the beat schedule.
+        gated_tenants: set[str] = get_gated_tenants() if skip_gated else set()
 
         for tenant_id in tenant_ids:
-            # Same comment here as the above NOTE
-            # if tenant_id in gated_tenants:
-            #     continue
+            if tenant_id in gated_tenants:
+                num_skipped_gated += 1
+                continue
 
             current_time = time.monotonic()
             if current_time - last_lock_time >= (CELERY_GENERIC_BEAT_LOCK_TIMEOUT / 4):
@@ -104,6 +108,7 @@ def cloud_beat_task_generator(
         f"cloud_beat_task_generator finished: "
         f"task={task_name} "
         f"num_processed_tenants={num_processed_tenants} "
+        f"num_skipped_gated={num_skipped_gated} "
         f"num_tenants={len(tenant_ids)} "
         f"elapsed={time_elapsed:.2f}"
     )

backend/ee/onyx/db/license.py

@@ -13,6 +13,7 @@ from ee.onyx.server.license.models import LicenseSource
 from onyx.auth.schemas import UserRole
 from onyx.cache.factory import get_cache_backend
 from onyx.configs.constants import ANONYMOUS_USER_EMAIL
+from onyx.db.enums import AccountType
 from onyx.db.models import License
 from onyx.db.models import User
 from onyx.utils.logger import setup_logger
@@ -107,12 +108,13 @@ def get_used_seats(tenant_id: str | None = None) -> int:
     Get current seat usage directly from database.
 
     For multi-tenant: counts users in UserTenantMapping for this tenant.
-    For self-hosted: counts all active users (excludes EXT_PERM_USER role
-    and the anonymous system user).
+    For self-hosted: counts all active users.
 
-    TODO: Exclude API key dummy users from seat counting. API keys create
-    users with emails like `__DANSWER_API_KEY_*` that should not count toward
-    seat limits. See: https://linear.app/onyx-app/issue/ENG-3518
+    Only human accounts count toward seat limits.
+    SERVICE_ACCOUNT (API key dummy users), EXT_PERM_USER, and the
+    anonymous system user are excluded. BOT (Slack users) ARE counted
+    because they represent real humans and get upgraded to STANDARD
+    when they log in via web.
     """
     if MULTI_TENANT:
         from ee.onyx.server.tenants.user_mapping import get_tenant_count
@@ -129,6 +131,7 @@ def get_used_seats(tenant_id: str | None = None) -> int:
                     User.is_active == True,  # type: ignore  # noqa: E712
                     User.role != UserRole.EXT_PERM_USER,
                     User.email != ANONYMOUS_USER_EMAIL,  # type: ignore
+                    User.account_type != AccountType.SERVICE_ACCOUNT,
                 )
             )
             return result.scalar() or 0

backend/ee/onyx/db/user_group.py

@@ -39,6 +39,7 @@ from onyx.db.models import User__UserGroup
 from onyx.db.models import UserGroup
 from onyx.db.models import UserGroup__ConnectorCredentialPair
 from onyx.db.models import UserRole
+from onyx.db.permissions import recompute_permissions_for_group__no_commit
 from onyx.db.permissions import recompute_user_permissions__no_commit
 from onyx.db.users import fetch_user_by_id
 from onyx.utils.logger import setup_logger
@@ -952,3 +953,46 @@ def delete_user_group_cc_pair_relationship__no_commit(
         UserGroup__ConnectorCredentialPair.cc_pair_id == cc_pair_id,
     )
     db_session.execute(delete_stmt)
+
+
+def set_group_permission__no_commit(
+    group_id: int,
+    permission: Permission,
+    enabled: bool,
+    granted_by: UUID,
+    db_session: Session,
+) -> None:
+    """Grant or revoke a single permission for a group using soft-delete.
+
+    Does NOT commit — caller must commit the session.
+    """
+    existing = db_session.execute(
+        select(PermissionGrant)
+        .where(
+            PermissionGrant.group_id == group_id,
+            PermissionGrant.permission == permission,
+        )
+        .with_for_update()
+    ).scalar_one_or_none()
+
+    if enabled:
+        if existing is not None:
+            if existing.is_deleted:
+                existing.is_deleted = False
+                existing.granted_by = granted_by
+                existing.granted_at = func.now()
+        else:
+            db_session.add(
+                PermissionGrant(
+                    group_id=group_id,
+                    permission=permission,
+                    grant_source=GrantSource.USER,
+                    granted_by=granted_by,
+                )
+            )
+    else:
+        if existing is not None and not existing.is_deleted:
+            existing.is_deleted = True
+
+    db_session.flush()
+    recompute_permissions_for_group__no_commit(group_id, db_session)

backend/ee/onyx/main.py

@@ -155,7 +155,7 @@ def get_application() -> FastAPI:
     include_router_with_global_prefix_prepended(application, license_router)
 
     # Unified billing API - always registered in EE.
-    # Each endpoint is protected by the `current_admin_user` dependency (admin auth).
+    # Each endpoint is protected by admin permission checks.
     include_router_with_global_prefix_prepended(application, billing_router)
 
     if MULTI_TENANT:

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

@@ -17,10 +17,10 @@ from ee.onyx.db.analytics import fetch_persona_message_analytics
 from ee.onyx.db.analytics import fetch_persona_unique_users
 from ee.onyx.db.analytics import fetch_query_analytics
 from ee.onyx.db.analytics import user_can_view_assistant_stats
-from onyx.auth.users import current_admin_user
-from onyx.auth.users import current_user
+from onyx.auth.permissions import require_permission
 from onyx.configs.constants import PUBLIC_API_TAGS
 from onyx.db.engine.sql_engine import get_session
+from onyx.db.enums import Permission
 from onyx.db.models import User
 
 router = APIRouter(prefix="/analytics", tags=PUBLIC_API_TAGS)
@@ -40,7 +40,7 @@ class QueryAnalyticsResponse(BaseModel):
 def get_query_analytics(
     start: datetime.datetime | None = None,
     end: datetime.datetime | None = None,
-    _: User = Depends(current_admin_user),
+    _: User = Depends(require_permission(Permission.FULL_ADMIN_PANEL_ACCESS)),
     db_session: Session = Depends(get_session),
 ) -> list[QueryAnalyticsResponse]:
     daily_query_usage_info = fetch_query_analytics(
@@ -71,7 +71,7 @@ class UserAnalyticsResponse(BaseModel):
 def get_user_analytics(
     start: datetime.datetime | None = None,
     end: datetime.datetime | None = None,
-    _: User = Depends(current_admin_user),
+    _: User = Depends(require_permission(Permission.FULL_ADMIN_PANEL_ACCESS)),
     db_session: Session = Depends(get_session),
 ) -> list[UserAnalyticsResponse]:
     daily_query_usage_info_per_user = fetch_per_user_query_analytics(
@@ -105,7 +105,7 @@ class OnyxbotAnalyticsResponse(BaseModel):
 def get_onyxbot_analytics(
     start: datetime.datetime | None = None,
     end: datetime.datetime | None = None,
-    _: User = Depends(current_admin_user),
+    _: User = Depends(require_permission(Permission.FULL_ADMIN_PANEL_ACCESS)),
     db_session: Session = Depends(get_session),
 ) -> list[OnyxbotAnalyticsResponse]:
     daily_onyxbot_info = fetch_onyxbot_analytics(
@@ -141,7 +141,7 @@ def get_persona_messages(
     persona_id: int,
     start: datetime.datetime | None = None,
     end: datetime.datetime | None = None,
-    _: User = Depends(current_admin_user),
+    _: User = Depends(require_permission(Permission.FULL_ADMIN_PANEL_ACCESS)),
     db_session: Session = Depends(get_session),
 ) -> list[PersonaMessageAnalyticsResponse]:
     """Fetch daily message counts for a single persona within the given time range."""
@@ -179,7 +179,7 @@ def get_persona_unique_users(
     persona_id: int,
     start: datetime.datetime,
     end: datetime.datetime,
-    _: User = Depends(current_admin_user),
+    _: User = Depends(require_permission(Permission.FULL_ADMIN_PANEL_ACCESS)),
     db_session: Session = Depends(get_session),
 ) -> list[PersonaUniqueUsersResponse]:
     """Get unique users per day for a single persona."""
@@ -218,7 +218,7 @@ def get_assistant_stats(
     assistant_id: int,
     start: datetime.datetime | None = None,
     end: datetime.datetime | None = None,
-    user: User = Depends(current_user),
+    user: User = Depends(require_permission(Permission.BASIC_ACCESS)),
     db_session: Session = Depends(get_session),
 ) -> AssistantStatsResponse:
     """

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

@@ -29,7 +29,6 @@ from fastapi import Depends
 from pydantic import BaseModel
 from sqlalchemy.orm import Session
 
-from ee.onyx.auth.users import current_admin_user
 from ee.onyx.db.license import get_license
 from ee.onyx.db.license import get_used_seats
 from ee.onyx.server.billing.models import BillingInformationResponse
@@ -51,11 +50,13 @@ from ee.onyx.server.billing.service import (
     get_billing_information as get_billing_service,
 )
 from ee.onyx.server.billing.service import update_seat_count as update_seat_service
+from onyx.auth.permissions import require_permission
 from onyx.auth.users import User
 from onyx.configs.app_configs import STRIPE_PUBLISHABLE_KEY_OVERRIDE
 from onyx.configs.app_configs import STRIPE_PUBLISHABLE_KEY_URL
 from onyx.configs.app_configs import WEB_DOMAIN
 from onyx.db.engine.sql_engine import get_session
+from onyx.db.enums import Permission
 from onyx.error_handling.error_codes import OnyxErrorCode
 from onyx.error_handling.exceptions import OnyxError
 from onyx.redis.redis_pool import get_shared_redis_client
@@ -147,7 +148,7 @@ def _get_tenant_id() -> str | None:
 @router.post("/create-checkout-session")
 async def create_checkout_session(
     request: CreateCheckoutSessionRequest | None = None,
-    _: User = Depends(current_admin_user),
+    _: User = Depends(require_permission(Permission.FULL_ADMIN_PANEL_ACCESS)),
     db_session: Session = Depends(get_session),
 ) -> CreateCheckoutSessionResponse:
     """Create a Stripe checkout session for new subscription or renewal.
@@ -191,7 +192,7 @@ async def create_checkout_session(
 @router.post("/create-customer-portal-session")
 async def create_customer_portal_session(
     request: CreateCustomerPortalSessionRequest | None = None,
-    _: User = Depends(current_admin_user),
+    _: User = Depends(require_permission(Permission.FULL_ADMIN_PANEL_ACCESS)),
     db_session: Session = Depends(get_session),
 ) -> CreateCustomerPortalSessionResponse:
     """Create a Stripe customer portal session for managing subscription.
@@ -216,7 +217,7 @@ async def create_customer_portal_session(
 
 @router.get("/billing-information")
 async def get_billing_information(
-    _: User = Depends(current_admin_user),
+    _: User = Depends(require_permission(Permission.FULL_ADMIN_PANEL_ACCESS)),
     db_session: Session = Depends(get_session),
 ) -> BillingInformationResponse | SubscriptionStatusResponse:
     """Get billing information for the current subscription.
@@ -258,7 +259,7 @@ async def get_billing_information(
 @router.post("/seats/update")
 async def update_seats(
     request: SeatUpdateRequest,
-    _: User = Depends(current_admin_user),
+    _: User = Depends(require_permission(Permission.FULL_ADMIN_PANEL_ACCESS)),
     db_session: Session = Depends(get_session),
 ) -> SeatUpdateResponse:
     """Update the seat count for the current subscription.
@@ -364,7 +365,7 @@ class ResetConnectionResponse(BaseModel):
 
 @router.post("/reset-connection")
 async def reset_stripe_connection(
-    _: User = Depends(current_admin_user),
+    _: User = Depends(require_permission(Permission.FULL_ADMIN_PANEL_ACCESS)),
 ) -> ResetConnectionResponse:
     """Reset the Stripe connection circuit breaker.
 

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

@@ -27,11 +27,12 @@ from ee.onyx.server.scim.auth import generate_scim_token
 from ee.onyx.server.scim.models import ScimTokenCreate
 from ee.onyx.server.scim.models import ScimTokenCreatedResponse
 from ee.onyx.server.scim.models import ScimTokenResponse
-from onyx.auth.users import current_admin_user
+from onyx.auth.permissions import require_permission
 from onyx.auth.users import current_user_with_expired_token
 from onyx.auth.users import get_user_manager
 from onyx.auth.users import UserManager
 from onyx.db.engine.sql_engine import get_session
+from onyx.db.enums import Permission
 from onyx.db.models import User
 from onyx.file_store.file_store import get_default_file_store
 from onyx.server.utils import BasicAuthenticationError
@@ -120,7 +121,8 @@ async def refresh_access_token(
 
 @admin_router.put("")
 def admin_ee_put_settings(
-    settings: EnterpriseSettings, _: User = Depends(current_admin_user)
+    settings: EnterpriseSettings,
+    _: User = Depends(require_permission(Permission.FULL_ADMIN_PANEL_ACCESS)),
 ) -> None:
     store_settings(settings)
 
@@ -139,7 +141,7 @@ def ee_fetch_settings() -> EnterpriseSettings:
 def put_logo(
     file: UploadFile,
     is_logotype: bool = False,
-    _: User = Depends(current_admin_user),
+    _: User = Depends(require_permission(Permission.FULL_ADMIN_PANEL_ACCESS)),
 ) -> None:
     upload_logo(file=file, is_logotype=is_logotype)
 
@@ -196,7 +198,8 @@ def fetch_logo(
 
 @admin_router.put("/custom-analytics-script")
 def upload_custom_analytics_script(
-    script_upload: AnalyticsScriptUpload, _: User = Depends(current_admin_user)
+    script_upload: AnalyticsScriptUpload,
+    _: User = Depends(require_permission(Permission.FULL_ADMIN_PANEL_ACCESS)),
 ) -> None:
     try:
         store_analytics_script(script_upload)
@@ -220,7 +223,7 @@ def _get_scim_dal(db_session: Session = Depends(get_session)) -> ScimDAL:
 
 @admin_router.get("/scim/token")
 def get_active_scim_token(
-    _: User = Depends(current_admin_user),
+    _: User = Depends(require_permission(Permission.FULL_ADMIN_PANEL_ACCESS)),
     dal: ScimDAL = Depends(_get_scim_dal),
 ) -> ScimTokenResponse:
     """Return the currently active SCIM token's metadata, or 404 if none."""
@@ -250,7 +253,7 @@ def get_active_scim_token(
 @admin_router.post("/scim/token", status_code=201)
 def create_scim_token(
     body: ScimTokenCreate,
-    user: User = Depends(current_admin_user),
+    user: User = Depends(require_permission(Permission.FULL_ADMIN_PANEL_ACCESS)),
     dal: ScimDAL = Depends(_get_scim_dal),
 ) -> ScimTokenCreatedResponse:
     """Create a new SCIM bearer token.

backend/ee/onyx/server/features/hooks/api.py

@@ -4,12 +4,13 @@ from fastapi import Depends
 from fastapi import Query
 from sqlalchemy.orm import Session
 
-from onyx.auth.users import current_admin_user
+from onyx.auth.permissions import require_permission
 from onyx.auth.users import User
 from onyx.db.constants import UNSET
 from onyx.db.constants import UnsetType
 from onyx.db.engine.sql_engine import get_session
 from onyx.db.engine.sql_engine import get_session_with_current_tenant
+from onyx.db.enums import Permission
 from onyx.db.hook import create_hook__no_commit
 from onyx.db.hook import delete_hook__no_commit
 from onyx.db.hook import get_hook_by_id
@@ -178,7 +179,7 @@ router = APIRouter(prefix="/admin/hooks")
 
 @router.get("/specs")
 def get_hook_point_specs(
-    _: User = Depends(current_admin_user),
+    _: User = Depends(require_permission(Permission.FULL_ADMIN_PANEL_ACCESS)),
     _hook_enabled: None = Depends(require_hook_enabled),
 ) -> list[HookPointMetaResponse]:
     return [
@@ -199,7 +200,7 @@ def get_hook_point_specs(
 
 @router.get("")
 def list_hooks(
-    _: User = Depends(current_admin_user),
+    _: User = Depends(require_permission(Permission.FULL_ADMIN_PANEL_ACCESS)),
     _hook_enabled: None = Depends(require_hook_enabled),
     db_session: Session = Depends(get_session),
 ) -> list[HookResponse]:
@@ -210,7 +211,7 @@ def list_hooks(
 @router.post("")
 def create_hook(
     req: HookCreateRequest,
-    user: User = Depends(current_admin_user),
+    user: User = Depends(require_permission(Permission.FULL_ADMIN_PANEL_ACCESS)),
     _hook_enabled: None = Depends(require_hook_enabled),
     db_session: Session = Depends(get_session),
 ) -> HookResponse:
@@ -246,7 +247,7 @@ def create_hook(
 @router.get("/{hook_id}")
 def get_hook(
     hook_id: int,
-    _: User = Depends(current_admin_user),
+    _: User = Depends(require_permission(Permission.FULL_ADMIN_PANEL_ACCESS)),
     _hook_enabled: None = Depends(require_hook_enabled),
     db_session: Session = Depends(get_session),
 ) -> HookResponse:
@@ -258,7 +259,7 @@ def get_hook(
 def update_hook(
     hook_id: int,
     req: HookUpdateRequest,
-    _: User = Depends(current_admin_user),
+    _: User = Depends(require_permission(Permission.FULL_ADMIN_PANEL_ACCESS)),
     _hook_enabled: None = Depends(require_hook_enabled),
     db_session: Session = Depends(get_session),
 ) -> HookResponse:
@@ -328,7 +329,7 @@ def update_hook(
 @router.delete("/{hook_id}")
 def delete_hook(
     hook_id: int,
-    _: User = Depends(current_admin_user),
+    _: User = Depends(require_permission(Permission.FULL_ADMIN_PANEL_ACCESS)),
     _hook_enabled: None = Depends(require_hook_enabled),
     db_session: Session = Depends(get_session),
 ) -> None:
@@ -339,7 +340,7 @@ def delete_hook(
 @router.post("/{hook_id}/activate")
 def activate_hook(
     hook_id: int,
-    _: User = Depends(current_admin_user),
+    _: User = Depends(require_permission(Permission.FULL_ADMIN_PANEL_ACCESS)),
     _hook_enabled: None = Depends(require_hook_enabled),
     db_session: Session = Depends(get_session),
 ) -> HookResponse:
@@ -381,7 +382,7 @@ def activate_hook(
 @router.post("/{hook_id}/validate")
 def validate_hook(
     hook_id: int,
-    _: User = Depends(current_admin_user),
+    _: User = Depends(require_permission(Permission.FULL_ADMIN_PANEL_ACCESS)),
     _hook_enabled: None = Depends(require_hook_enabled),
     db_session: Session = Depends(get_session),
 ) -> HookValidateResponse:
@@ -409,7 +410,7 @@ def validate_hook(
 @router.post("/{hook_id}/deactivate")
 def deactivate_hook(
     hook_id: int,
-    _: User = Depends(current_admin_user),
+    _: User = Depends(require_permission(Permission.FULL_ADMIN_PANEL_ACCESS)),
     _hook_enabled: None = Depends(require_hook_enabled),
     db_session: Session = Depends(get_session),
 ) -> HookResponse:
@@ -432,7 +433,7 @@ def deactivate_hook(
 def list_hook_execution_logs(
     hook_id: int,
     limit: int = Query(default=10, ge=1, le=100),
-    _: User = Depends(current_admin_user),
+    _: User = Depends(require_permission(Permission.FULL_ADMIN_PANEL_ACCESS)),
     _hook_enabled: None = Depends(require_hook_enabled),
     db_session: Session = Depends(get_session),
 ) -> list[HookExecutionRecord]:

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

@@ -17,7 +17,6 @@ from fastapi import File
 from fastapi import UploadFile
 from sqlalchemy.orm import Session
 
-from ee.onyx.auth.users import current_admin_user
 from ee.onyx.configs.app_configs import CLOUD_DATA_PLANE_URL
 from ee.onyx.db.license import delete_license as db_delete_license
 from ee.onyx.db.license import get_license
@@ -32,8 +31,10 @@ from ee.onyx.server.license.models import LicenseStatusResponse
 from ee.onyx.server.license.models import LicenseUploadResponse
 from ee.onyx.server.license.models import SeatUsageResponse
 from ee.onyx.utils.license import verify_license_signature
+from onyx.auth.permissions import require_permission
 from onyx.auth.users import User
 from onyx.db.engine.sql_engine import get_session
+from onyx.db.enums import Permission
 from onyx.error_handling.error_codes import OnyxErrorCode
 from onyx.error_handling.exceptions import OnyxError
 from onyx.utils.logger import setup_logger
@@ -60,7 +61,7 @@ def _strip_pem_delimiters(content: str) -> str:
 
 @router.get("")
 async def get_license_status(
-    _: User = Depends(current_admin_user),
+    _: User = Depends(require_permission(Permission.FULL_ADMIN_PANEL_ACCESS)),
     db_session: Session = Depends(get_session),
 ) -> LicenseStatusResponse:
     """Get current license status and seat usage."""
@@ -84,7 +85,7 @@ async def get_license_status(
 
 @router.get("/seats")
 async def get_seat_usage(
-    _: User = Depends(current_admin_user),
+    _: User = Depends(require_permission(Permission.FULL_ADMIN_PANEL_ACCESS)),
     db_session: Session = Depends(get_session),
 ) -> SeatUsageResponse:
     """Get detailed seat usage information."""
@@ -107,7 +108,7 @@ async def get_seat_usage(
 @router.post("/claim")
 async def claim_license(
     session_id: str | None = None,
-    _: User = Depends(current_admin_user),
+    _: User = Depends(require_permission(Permission.FULL_ADMIN_PANEL_ACCESS)),
     db_session: Session = Depends(get_session),
 ) -> LicenseResponse:
     """
@@ -215,7 +216,7 @@ async def claim_license(
 @router.post("/upload")
 async def upload_license(
     license_file: UploadFile = File(...),
-    _: User = Depends(current_admin_user),
+    _: User = Depends(require_permission(Permission.FULL_ADMIN_PANEL_ACCESS)),
     db_session: Session = Depends(get_session),
 ) -> LicenseUploadResponse:
     """
@@ -263,7 +264,7 @@ async def upload_license(
 
 @router.post("/refresh")
 async def refresh_license_cache_endpoint(
-    _: User = Depends(current_admin_user),
+    _: User = Depends(require_permission(Permission.FULL_ADMIN_PANEL_ACCESS)),
     db_session: Session = Depends(get_session),
 ) -> LicenseStatusResponse:
     """
@@ -292,7 +293,7 @@ async def refresh_license_cache_endpoint(
 
 @router.delete("")
 async def delete_license(
-    _: User = Depends(current_admin_user),
+    _: User = Depends(require_permission(Permission.FULL_ADMIN_PANEL_ACCESS)),
     db_session: Session = Depends(get_session),
 ) -> dict[str, bool]:
     """

backend/ee/onyx/server/manage/standard_answer.py

@@ -12,8 +12,9 @@ from ee.onyx.db.standard_answer import insert_standard_answer_category
 from ee.onyx.db.standard_answer import remove_standard_answer
 from ee.onyx.db.standard_answer import update_standard_answer
 from ee.onyx.db.standard_answer import update_standard_answer_category
-from onyx.auth.users import current_admin_user
+from onyx.auth.permissions import require_permission
 from onyx.db.engine.sql_engine import get_session
+from onyx.db.enums import Permission
 from onyx.db.models import User
 from onyx.server.manage.models import StandardAnswer
 from onyx.server.manage.models import StandardAnswerCategory
@@ -27,7 +28,7 @@ router = APIRouter(prefix="/manage")
 def create_standard_answer(
     standard_answer_creation_request: StandardAnswerCreationRequest,
     db_session: Session = Depends(get_session),
-    _: User = Depends(current_admin_user),
+    _: User = Depends(require_permission(Permission.FULL_ADMIN_PANEL_ACCESS)),
 ) -> StandardAnswer:
     standard_answer_model = insert_standard_answer(
         keyword=standard_answer_creation_request.keyword,
@@ -43,7 +44,7 @@ def create_standard_answer(
 @router.get("/admin/standard-answer")
 def list_standard_answers(
     db_session: Session = Depends(get_session),
-    _: User = Depends(current_admin_user),
+    _: User = Depends(require_permission(Permission.FULL_ADMIN_PANEL_ACCESS)),
 ) -> list[StandardAnswer]:
     standard_answer_models = fetch_standard_answers(db_session=db_session)
     return [
@@ -57,7 +58,7 @@ def patch_standard_answer(
     standard_answer_id: int,
     standard_answer_creation_request: StandardAnswerCreationRequest,
     db_session: Session = Depends(get_session),
-    _: User = Depends(current_admin_user),
+    _: User = Depends(require_permission(Permission.FULL_ADMIN_PANEL_ACCESS)),
 ) -> StandardAnswer:
     existing_standard_answer = fetch_standard_answer(
         standard_answer_id=standard_answer_id,
@@ -83,7 +84,7 @@ def patch_standard_answer(
 def delete_standard_answer(
     standard_answer_id: int,
     db_session: Session = Depends(get_session),
-    _: User = Depends(current_admin_user),
+    _: User = Depends(require_permission(Permission.FULL_ADMIN_PANEL_ACCESS)),
 ) -> None:
     return remove_standard_answer(
         standard_answer_id=standard_answer_id,
@@ -95,7 +96,7 @@ def delete_standard_answer(
 def create_standard_answer_category(
     standard_answer_category_creation_request: StandardAnswerCategoryCreationRequest,
     db_session: Session = Depends(get_session),
-    _: User = Depends(current_admin_user),
+    _: User = Depends(require_permission(Permission.FULL_ADMIN_PANEL_ACCESS)),
 ) -> StandardAnswerCategory:
     standard_answer_category_model = insert_standard_answer_category(
         category_name=standard_answer_category_creation_request.name,
@@ -107,7 +108,7 @@ def create_standard_answer_category(
 @router.get("/admin/standard-answer/category")
 def list_standard_answer_categories(
     db_session: Session = Depends(get_session),
-    _: User = Depends(current_admin_user),
+    _: User = Depends(require_permission(Permission.FULL_ADMIN_PANEL_ACCESS)),
 ) -> list[StandardAnswerCategory]:
     standard_answer_category_models = fetch_standard_answer_categories(
         db_session=db_session
@@ -123,7 +124,7 @@ def patch_standard_answer_category(
     standard_answer_category_id: int,
     standard_answer_category_creation_request: StandardAnswerCategoryCreationRequest,
     db_session: Session = Depends(get_session),
-    _: User = Depends(current_admin_user),
+    _: User = Depends(require_permission(Permission.FULL_ADMIN_PANEL_ACCESS)),
 ) -> StandardAnswerCategory:
     existing_standard_answer_category = fetch_standard_answer_category(
         standard_answer_category_id=standard_answer_category_id,

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

@@ -9,9 +9,10 @@ from ee.onyx.server.oauth.api_router import router
 from ee.onyx.server.oauth.confluence_cloud import ConfluenceCloudOAuth
 from ee.onyx.server.oauth.google_drive import GoogleDriveOAuth
 from ee.onyx.server.oauth.slack import SlackOAuth
-from onyx.auth.users import current_admin_user
+from onyx.auth.permissions import require_permission
 from onyx.configs.app_configs import DEV_MODE
 from onyx.configs.constants import DocumentSource
+from onyx.db.enums import Permission
 from onyx.db.models import User
 from onyx.redis.redis_pool import get_redis_client
 from onyx.utils.logger import setup_logger
@@ -24,7 +25,7 @@ logger = setup_logger()
 def prepare_authorization_request(
     connector: DocumentSource,
     redirect_on_success: str | None,
-    user: User = Depends(current_admin_user),
+    user: User = Depends(require_permission(Permission.FULL_ADMIN_PANEL_ACCESS)),
     tenant_id: str | None = Depends(get_current_tenant_id),
 ) -> JSONResponse:
     """Used by the frontend to generate the url for the user's browser during auth request.

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

@@ -15,7 +15,7 @@ from pydantic import ValidationError
 from sqlalchemy.orm import Session
 
 from ee.onyx.server.oauth.api_router import router
-from onyx.auth.users import current_admin_user
+from onyx.auth.permissions import require_permission
 from onyx.configs.app_configs import DEV_MODE
 from onyx.configs.app_configs import OAUTH_CONFLUENCE_CLOUD_CLIENT_ID
 from onyx.configs.app_configs import OAUTH_CONFLUENCE_CLOUD_CLIENT_SECRET
@@ -26,6 +26,7 @@ from onyx.db.credentials import create_credential
 from onyx.db.credentials import fetch_credential_by_id_for_user
 from onyx.db.credentials import update_credential_json
 from onyx.db.engine.sql_engine import get_session
+from onyx.db.enums import Permission
 from onyx.db.models import User
 from onyx.redis.redis_pool import get_redis_client
 from onyx.server.documents.models import CredentialBase
@@ -146,7 +147,7 @@ class ConfluenceCloudOAuth:
 def confluence_oauth_callback(
     code: str,
     state: str,
-    user: User = Depends(current_admin_user),
+    user: User = Depends(require_permission(Permission.FULL_ADMIN_PANEL_ACCESS)),
     db_session: Session = Depends(get_session),
     tenant_id: str | None = Depends(get_current_tenant_id),
 ) -> JSONResponse:
@@ -258,7 +259,7 @@ def confluence_oauth_callback(
 @router.get("/connector/confluence/accessible-resources")
 def confluence_oauth_accessible_resources(
     credential_id: int,
-    user: User = Depends(current_admin_user),
+    user: User = Depends(require_permission(Permission.FULL_ADMIN_PANEL_ACCESS)),
     db_session: Session = Depends(get_session),
     tenant_id: str | None = Depends(get_current_tenant_id),  # noqa: ARG001
 ) -> JSONResponse:
@@ -325,7 +326,7 @@ def confluence_oauth_finalize(
     cloud_id: str,
     cloud_name: str,
     cloud_url: str,
-    user: User = Depends(current_admin_user),
+    user: User = Depends(require_permission(Permission.FULL_ADMIN_PANEL_ACCESS)),
     db_session: Session = Depends(get_session),
     tenant_id: str | None = Depends(get_current_tenant_id),  # noqa: ARG001
 ) -> JSONResponse:

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

@@ -12,7 +12,7 @@ from pydantic import BaseModel
 from sqlalchemy.orm import Session
 
 from ee.onyx.server.oauth.api_router import router
-from onyx.auth.users import current_admin_user
+from onyx.auth.permissions import require_permission
 from onyx.configs.app_configs import DEV_MODE
 from onyx.configs.app_configs import OAUTH_GOOGLE_DRIVE_CLIENT_ID
 from onyx.configs.app_configs import OAUTH_GOOGLE_DRIVE_CLIENT_SECRET
@@ -34,6 +34,7 @@ from onyx.connectors.google_utils.shared_constants import (
 )
 from onyx.db.credentials import create_credential
 from onyx.db.engine.sql_engine import get_session
+from onyx.db.enums import Permission
 from onyx.db.models import User
 from onyx.redis.redis_pool import get_redis_client
 from onyx.server.documents.models import CredentialBase
@@ -114,7 +115,7 @@ class GoogleDriveOAuth:
 def handle_google_drive_oauth_callback(
     code: str,
     state: str,
-    user: User = Depends(current_admin_user),
+    user: User = Depends(require_permission(Permission.FULL_ADMIN_PANEL_ACCESS)),
     db_session: Session = Depends(get_session),
     tenant_id: str | None = Depends(get_current_tenant_id),
 ) -> JSONResponse:

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

@@ -10,7 +10,7 @@ from pydantic import BaseModel
 from sqlalchemy.orm import Session
 
 from ee.onyx.server.oauth.api_router import router
-from onyx.auth.users import current_admin_user
+from onyx.auth.permissions import require_permission
 from onyx.configs.app_configs import DEV_MODE
 from onyx.configs.app_configs import OAUTH_SLACK_CLIENT_ID
 from onyx.configs.app_configs import OAUTH_SLACK_CLIENT_SECRET
@@ -18,6 +18,7 @@ from onyx.configs.app_configs import WEB_DOMAIN
 from onyx.configs.constants import DocumentSource
 from onyx.db.credentials import create_credential
 from onyx.db.engine.sql_engine import get_session
+from onyx.db.enums import Permission
 from onyx.db.models import User
 from onyx.redis.redis_pool import get_redis_client
 from onyx.server.documents.models import CredentialBase
@@ -98,7 +99,7 @@ class SlackOAuth:
 def handle_slack_oauth_callback(
     code: str,
     state: str,
-    user: User = Depends(current_admin_user),
+    user: User = Depends(require_permission(Permission.FULL_ADMIN_PANEL_ACCESS)),
     db_session: Session = Depends(get_session),
     tenant_id: str | None = Depends(get_current_tenant_id),
 ) -> JSONResponse:

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

@@ -8,8 +8,9 @@ from ee.onyx.onyxbot.slack.handlers.handle_standard_answers import (
 )
 from ee.onyx.server.query_and_chat.models import StandardAnswerRequest
 from ee.onyx.server.query_and_chat.models import StandardAnswerResponse
-from onyx.auth.users import current_user
+from onyx.auth.permissions import require_permission
 from onyx.db.engine.sql_engine import get_session
+from onyx.db.enums import Permission
 from onyx.db.models import User
 from onyx.utils.logger import setup_logger
 
@@ -22,7 +23,7 @@ basic_router = APIRouter(prefix="/query")
 def get_standard_answer(
     request: StandardAnswerRequest,
     db_session: Session = Depends(get_session),
-    _: User = Depends(current_user),
+    _: User = Depends(require_permission(Permission.BASIC_ACCESS)),
 ) -> StandardAnswerResponse:
     try:
         standard_answers = oneoff_standard_answers(

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

@@ -19,10 +19,11 @@ from ee.onyx.server.query_and_chat.models import SearchHistoryResponse
 from ee.onyx.server.query_and_chat.models import SearchQueryResponse
 from ee.onyx.server.query_and_chat.models import SendSearchQueryRequest
 from ee.onyx.server.query_and_chat.streaming_models import SearchErrorPacket
-from onyx.auth.users import current_user
+from onyx.auth.permissions import require_permission
 from onyx.configs.app_configs import ONYX_SEARCH_UI_USES_OPENSEARCH_KEYWORD_SEARCH
 from onyx.db.engine.sql_engine import get_session
 from onyx.db.engine.sql_engine import get_session_with_current_tenant
+from onyx.db.enums import Permission
 from onyx.db.models import User
 from onyx.llm.factory import get_default_llm
 from onyx.server.usage_limits import check_llm_cost_limit_for_provider
@@ -39,7 +40,7 @@ router = APIRouter(prefix="/search")
 @router.post("/search-flow-classification")
 def search_flow_classification(
     request: SearchFlowClassificationRequest,
-    _: User = Depends(current_user),
+    _: User = Depends(require_permission(Permission.BASIC_ACCESS)),
     db_session: Session = Depends(get_session),
 ) -> SearchFlowClassificationResponse:
     query = request.user_query
@@ -79,7 +80,7 @@ def search_flow_classification(
 )
 def handle_send_search_message(
     request: SendSearchQueryRequest,
-    user: User = Depends(current_user),
+    user: User = Depends(require_permission(Permission.BASIC_ACCESS)),
     db_session: Session = Depends(get_session),
 ) -> StreamingResponse | SearchFullResponse:
     """
@@ -129,7 +130,7 @@ def handle_send_search_message(
 def get_search_history(
     limit: int = 100,
     filter_days: int | None = None,
-    user: User = Depends(current_user),
+    user: User = Depends(require_permission(Permission.BASIC_ACCESS)),
     db_session: Session = Depends(get_session),
 ) -> SearchHistoryResponse:
     """

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

@@ -20,7 +20,7 @@ from ee.onyx.server.query_history.models import ChatSessionMinimal
 from ee.onyx.server.query_history.models import ChatSessionSnapshot
 from ee.onyx.server.query_history.models import MessageSnapshot
 from ee.onyx.server.query_history.models import QueryHistoryExport
-from onyx.auth.users import current_admin_user
+from onyx.auth.permissions import require_permission
 from onyx.auth.users import get_display_email
 from onyx.background.celery.versioned_apps.client import app as client_app
 from onyx.background.task_utils import construct_query_history_report_name
@@ -39,6 +39,7 @@ from onyx.configs.constants import SessionType
 from onyx.db.chat import get_chat_session_by_id
 from onyx.db.chat import get_chat_sessions_by_user
 from onyx.db.engine.sql_engine import get_session
+from onyx.db.enums import Permission
 from onyx.db.enums import TaskStatus
 from onyx.db.file_record import get_query_history_export_files
 from onyx.db.models import ChatSession
@@ -153,7 +154,7 @@ def snapshot_from_chat_session(
 @router.get("/admin/chat-sessions")
 def admin_get_chat_sessions(
     user_id: UUID,
-    _: User = Depends(current_admin_user),
+    _: User = Depends(require_permission(Permission.FULL_ADMIN_PANEL_ACCESS)),
     db_session: Session = Depends(get_session),
 ) -> ChatSessionsResponse:
     # we specifically don't allow this endpoint if "anonymized" since
@@ -196,7 +197,7 @@ def get_chat_session_history(
     feedback_type: QAFeedbackType | None = None,
     start_time: datetime | None = None,
     end_time: datetime | None = None,
-    _: User = Depends(current_admin_user),
+    _: User = Depends(require_permission(Permission.FULL_ADMIN_PANEL_ACCESS)),
     db_session: Session = Depends(get_session),
 ) -> PaginatedReturn[ChatSessionMinimal]:
     ensure_query_history_is_enabled(disallowed=[QueryHistoryType.DISABLED])
@@ -234,7 +235,7 @@ def get_chat_session_history(
 @router.get("/admin/chat-session-history/{chat_session_id}")
 def get_chat_session_admin(
     chat_session_id: UUID,
-    _: User = Depends(current_admin_user),
+    _: User = Depends(require_permission(Permission.FULL_ADMIN_PANEL_ACCESS)),
     db_session: Session = Depends(get_session),
 ) -> ChatSessionSnapshot:
     ensure_query_history_is_enabled(disallowed=[QueryHistoryType.DISABLED])
@@ -269,7 +270,7 @@ def get_chat_session_admin(
 
 @router.get("/admin/query-history/list")
 def list_all_query_history_exports(
-    _: User = Depends(current_admin_user),
+    _: User = Depends(require_permission(Permission.FULL_ADMIN_PANEL_ACCESS)),
     db_session: Session = Depends(get_session),
 ) -> list[QueryHistoryExport]:
     ensure_query_history_is_enabled(disallowed=[QueryHistoryType.DISABLED])
@@ -297,7 +298,7 @@ def list_all_query_history_exports(
 
 @router.post("/admin/query-history/start-export", tags=PUBLIC_API_TAGS)
 def start_query_history_export(
-    _: User = Depends(current_admin_user),
+    _: User = Depends(require_permission(Permission.FULL_ADMIN_PANEL_ACCESS)),
     db_session: Session = Depends(get_session),
     start: datetime | None = None,
     end: datetime | None = None,
@@ -344,7 +345,7 @@ def start_query_history_export(
 @router.get("/admin/query-history/export-status", tags=PUBLIC_API_TAGS)
 def get_query_history_export_status(
     request_id: str,
-    _: User = Depends(current_admin_user),
+    _: User = Depends(require_permission(Permission.FULL_ADMIN_PANEL_ACCESS)),
     db_session: Session = Depends(get_session),
 ) -> dict[str, str]:
     ensure_query_history_is_enabled(disallowed=[QueryHistoryType.DISABLED])
@@ -378,7 +379,7 @@ def get_query_history_export_status(
 @router.get("/admin/query-history/download", tags=PUBLIC_API_TAGS)
 def download_query_history_csv(
     request_id: str,
-    _: User = Depends(current_admin_user),
+    _: User = Depends(require_permission(Permission.FULL_ADMIN_PANEL_ACCESS)),
     db_session: Session = Depends(get_session),
 ) -> StreamingResponse:
     ensure_query_history_is_enabled(disallowed=[QueryHistoryType.DISABLED])

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

@@ -12,10 +12,11 @@ from sqlalchemy.orm import Session
 from ee.onyx.db.usage_export import get_all_usage_reports
 from ee.onyx.db.usage_export import get_usage_report_data
 from ee.onyx.db.usage_export import UsageReportMetadata
-from onyx.auth.users import current_admin_user
+from onyx.auth.permissions import require_permission
 from onyx.background.celery.versioned_apps.client import app as client_app
 from onyx.configs.constants import OnyxCeleryTask
 from onyx.db.engine.sql_engine import get_session
+from onyx.db.enums import Permission
 from onyx.db.models import User
 from onyx.file_store.constants import STANDARD_CHUNK_SIZE
 from shared_configs.contextvars import get_current_tenant_id
@@ -31,7 +32,7 @@ class GenerateUsageReportParams(BaseModel):
 @router.post("/admin/usage-report", status_code=204)
 def generate_report(
     params: GenerateUsageReportParams,
-    user: User = Depends(current_admin_user),
+    user: User = Depends(require_permission(Permission.FULL_ADMIN_PANEL_ACCESS)),
 ) -> None:
     # Validate period parameters
     if params.period_from and params.period_to:
@@ -58,7 +59,7 @@ def generate_report(
 @router.get("/admin/usage-report/{report_name}")
 def read_usage_report(
     report_name: str,
-    _: User = Depends(current_admin_user),
+    _: User = Depends(require_permission(Permission.FULL_ADMIN_PANEL_ACCESS)),
     db_session: Session = Depends(get_session),  # noqa: ARG001
 ) -> Response:
     try:
@@ -82,7 +83,7 @@ def read_usage_report(
 
 @router.get("/admin/usage-report")
 def fetch_usage_reports(
-    _: User = Depends(current_admin_user),
+    _: User = Depends(require_permission(Permission.FULL_ADMIN_PANEL_ACCESS)),
     db_session: Session = Depends(get_session),
 ) -> list[UsageReportMetadata]:
     try:

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

@@ -11,6 +11,8 @@ require a valid SCIM bearer token.
 
 from __future__ import annotations
 
+import hashlib
+import struct
 from uuid import UUID
 
 from fastapi import APIRouter
@@ -22,6 +24,7 @@ from fastapi import Response
 from fastapi.responses import JSONResponse
 from fastapi_users.password import PasswordHelper
 from sqlalchemy import func
+from sqlalchemy import text
 from sqlalchemy.exc import IntegrityError
 from sqlalchemy.orm import Session
 
@@ -65,12 +68,25 @@ from onyx.db.permissions import recompute_user_permissions__no_commit
 from onyx.db.users import assign_user_to_default_groups__no_commit
 from onyx.utils.logger import setup_logger
 from onyx.utils.variable_functionality import fetch_ee_implementation_or_noop
+from shared_configs.contextvars import get_current_tenant_id
 
 logger = setup_logger()
 
 # Group names reserved for system default groups (seeded by migration).
 _RESERVED_GROUP_NAMES = frozenset({"Admin", "Basic"})
 
+# Namespace prefix for the seat-allocation advisory lock. Hashed together
+# with the tenant ID so the lock is scoped per-tenant (unrelated tenants
+# never block each other) and cannot collide with unrelated advisory locks.
+_SEAT_LOCK_NAMESPACE = "onyx_scim_seat_lock"
+
+
+def _seat_lock_id_for_tenant(tenant_id: str) -> int:
+    """Derive a stable 64-bit signed int lock id for this tenant's seat lock."""
+    digest = hashlib.sha256(f"{_SEAT_LOCK_NAMESPACE}:{tenant_id}".encode()).digest()
+    # pg_advisory_xact_lock takes a signed 8-byte int; unpack as such.
+    return struct.unpack("q", digest[:8])[0]
+
 
 class ScimJSONResponse(JSONResponse):
     """JSONResponse with Content-Type: application/scim+json (RFC 7644 §3.1)."""
@@ -209,12 +225,37 @@ def _apply_exclusions(
 
 
 def _check_seat_availability(dal: ScimDAL) -> str | None:
-    """Return an error message if seat limit is reached, else None."""
+    """Return an error message if seat limit is reached, else None.
+
+    Acquires a transaction-scoped advisory lock so that concurrent
+    SCIM requests are serialized.  IdPs like Okta send provisioning
+    requests in parallel batches — without serialization the check is
+    vulnerable to a TOCTOU race where N concurrent requests each see
+    "seats available", all insert, and the tenant ends up over its
+    seat limit.
+
+    The lock is held until the caller's next COMMIT or ROLLBACK, which
+    means the seat count cannot change between the check here and the
+    subsequent INSERT/UPDATE.  Each call site in this module follows
+    the pattern: _check_seat_availability → write → dal.commit()
+    (which releases the lock for the next waiting request).
+    """
     check_fn = fetch_ee_implementation_or_noop(
         "onyx.db.license", "check_seat_availability", None
     )
     if check_fn is None:
         return None
+
+    # Transaction-scoped advisory lock — released on dal.commit() / dal.rollback().
+    # The lock id is derived from the tenant so unrelated tenants never block
+    # each other, and from a namespace string so it cannot collide with
+    # unrelated advisory locks elsewhere in the codebase.
+    lock_id = _seat_lock_id_for_tenant(get_current_tenant_id())
+    dal.session.execute(
+        text("SELECT pg_advisory_xact_lock(:lock_id)"),
+        {"lock_id": lock_id},
+    )
+
     result = check_fn(dal.session, seats_needed=1)
     if not result.available:
         return result.error_message or "Seat limit reached"

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

@@ -12,12 +12,13 @@ from ee.onyx.server.tenants.anonymous_user_path import (
 from ee.onyx.server.tenants.anonymous_user_path import modify_anonymous_user_path
 from ee.onyx.server.tenants.anonymous_user_path import validate_anonymous_user_path
 from ee.onyx.server.tenants.models import AnonymousUserPath
+from onyx.auth.permissions import require_permission
 from onyx.auth.users import anonymous_user_enabled
-from onyx.auth.users import current_admin_user
 from onyx.auth.users import User
 from onyx.configs.constants import ANONYMOUS_USER_COOKIE_NAME
 from onyx.configs.constants import FASTAPI_USERS_AUTH_COOKIE_NAME
 from onyx.db.engine.sql_engine import get_session_with_shared_schema
+from onyx.db.enums import Permission
 from onyx.utils.logger import setup_logger
 from shared_configs.contextvars import get_current_tenant_id
 
@@ -28,7 +29,7 @@ router = APIRouter(prefix="/tenants")
 
 @router.get("/anonymous-user-path")
 async def get_anonymous_user_path_api(
-    _: User = Depends(current_admin_user),
+    _: User = Depends(require_permission(Permission.FULL_ADMIN_PANEL_ACCESS)),
 ) -> AnonymousUserPath:
     tenant_id = get_current_tenant_id()
 
@@ -44,7 +45,7 @@ async def get_anonymous_user_path_api(
 @router.post("/anonymous-user-path")
 async def set_anonymous_user_path_api(
     anonymous_user_path: str,
-    _: User = Depends(current_admin_user),
+    _: User = Depends(require_permission(Permission.FULL_ADMIN_PANEL_ACCESS)),
 ) -> None:
     tenant_id = get_current_tenant_id()
     try:

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

@@ -22,7 +22,6 @@ import httpx
 from fastapi import APIRouter
 from fastapi import Depends
 
-from ee.onyx.auth.users import current_admin_user
 from ee.onyx.server.tenants.access import control_plane_dep
 from ee.onyx.server.tenants.billing import fetch_billing_information
 from ee.onyx.server.tenants.billing import fetch_customer_portal_session
@@ -38,10 +37,12 @@ from ee.onyx.server.tenants.models import SubscriptionSessionResponse
 from ee.onyx.server.tenants.models import SubscriptionStatusResponse
 from ee.onyx.server.tenants.product_gating import overwrite_full_gated_set
 from ee.onyx.server.tenants.product_gating import store_product_gating
+from onyx.auth.permissions import require_permission
 from onyx.auth.users import User
 from onyx.configs.app_configs import STRIPE_PUBLISHABLE_KEY_OVERRIDE
 from onyx.configs.app_configs import STRIPE_PUBLISHABLE_KEY_URL
 from onyx.configs.app_configs import WEB_DOMAIN
+from onyx.db.enums import Permission
 from onyx.error_handling.error_codes import OnyxErrorCode
 from onyx.error_handling.exceptions import OnyxError
 from onyx.utils.logger import setup_logger
@@ -99,7 +100,7 @@ def gate_product_full_sync(
 
 @router.get("/billing-information")
 async def billing_information(
-    _: User = Depends(current_admin_user),
+    _: User = Depends(require_permission(Permission.FULL_ADMIN_PANEL_ACCESS)),
 ) -> BillingInformation | SubscriptionStatusResponse:
     logger.info("Fetching billing information")
     tenant_id = get_current_tenant_id()
@@ -108,7 +109,7 @@ async def billing_information(
 
 @router.post("/create-customer-portal-session")
 async def create_customer_portal_session(
-    _: User = Depends(current_admin_user),
+    _: User = Depends(require_permission(Permission.FULL_ADMIN_PANEL_ACCESS)),
 ) -> dict:
     """Create a Stripe customer portal session via the control plane."""
     tenant_id = get_current_tenant_id()
@@ -130,7 +131,7 @@ async def create_customer_portal_session(
 @router.post("/create-checkout-session")
 async def create_checkout_session(
     request: CreateCheckoutSessionRequest | None = None,
-    _: User = Depends(current_admin_user),
+    _: User = Depends(require_permission(Permission.FULL_ADMIN_PANEL_ACCESS)),
 ) -> dict:
     """Create a Stripe checkout session via the control plane."""
     tenant_id = get_current_tenant_id()
@@ -153,7 +154,7 @@ async def create_checkout_session(
 @router.post("/create-subscription-session")
 async def create_subscription_session(
     request: CreateSubscriptionSessionRequest | None = None,
-    _: User = Depends(current_admin_user),
+    _: User = Depends(require_permission(Permission.FULL_ADMIN_PANEL_ACCESS)),
 ) -> SubscriptionSessionResponse:
     try:
         tenant_id = CURRENT_TENANT_ID_CONTEXTVAR.get()

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

@@ -6,10 +6,11 @@ from sqlalchemy.orm import Session
 from ee.onyx.server.tenants.provisioning import delete_user_from_control_plane
 from ee.onyx.server.tenants.user_mapping import remove_all_users_from_tenant
 from ee.onyx.server.tenants.user_mapping import remove_users_from_tenant
-from onyx.auth.users import current_admin_user
+from onyx.auth.permissions import require_permission
 from onyx.auth.users import User
 from onyx.db.auth import get_user_count
 from onyx.db.engine.sql_engine import get_session
+from onyx.db.enums import Permission
 from onyx.db.users import delete_user_from_db
 from onyx.db.users import get_user_by_email
 from onyx.server.manage.models import UserByEmail
@@ -24,7 +25,9 @@ router = APIRouter(prefix="/tenants")
 @router.post("/leave-team")
 async def leave_organization(
     user_email: UserByEmail,
-    current_user: User = Depends(current_admin_user),
+    current_user: User = Depends(
+        require_permission(Permission.FULL_ADMIN_PANEL_ACCESS)
+    ),
     db_session: Session = Depends(get_session),
 ) -> None:
     tenant_id = get_current_tenant_id()

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

@@ -3,8 +3,9 @@ from fastapi import Depends
 
 from ee.onyx.server.tenants.models import TenantByDomainResponse
 from ee.onyx.server.tenants.provisioning import get_tenant_by_domain_from_control_plane
-from onyx.auth.users import current_user
+from onyx.auth.permissions import require_permission
 from onyx.auth.users import User
+from onyx.db.enums import Permission
 from onyx.utils.logger import setup_logger
 from shared_configs.contextvars import get_current_tenant_id
 
@@ -26,7 +27,7 @@ FORBIDDEN_COMMON_EMAIL_SUBSTRINGS = [
 
 @router.get("/existing-team-by-domain")
 def get_existing_tenant_by_domain(
-    user: User = Depends(current_user),
+    user: User = Depends(require_permission(Permission.BASIC_ACCESS)),
 ) -> TenantByDomainResponse | None:
     domain = user.email.split("@")[1]
     if any(substring in domain for substring in FORBIDDEN_COMMON_EMAIL_SUBSTRINGS):

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

@@ -10,9 +10,9 @@ from ee.onyx.server.tenants.user_mapping import approve_user_invite
 from ee.onyx.server.tenants.user_mapping import deny_user_invite
 from ee.onyx.server.tenants.user_mapping import invite_self_to_tenant
 from onyx.auth.invited_users import get_pending_users
-from onyx.auth.users import current_admin_user
-from onyx.auth.users import current_user
+from onyx.auth.permissions import require_permission
 from onyx.auth.users import User
+from onyx.db.enums import Permission
 from onyx.utils.logger import setup_logger
 from shared_configs.contextvars import get_current_tenant_id
 
@@ -24,7 +24,7 @@ router = APIRouter(prefix="/tenants")
 @router.post("/users/invite/request")
 async def request_invite(
     invite_request: RequestInviteRequest,
-    user: User = Depends(current_admin_user),
+    user: User = Depends(require_permission(Permission.FULL_ADMIN_PANEL_ACCESS)),
 ) -> None:
     try:
         invite_self_to_tenant(user.email, invite_request.tenant_id)
@@ -37,7 +37,7 @@ async def request_invite(
 
 @router.get("/users/pending")
 def list_pending_users(
-    _: User = Depends(current_admin_user),
+    _: User = Depends(require_permission(Permission.FULL_ADMIN_PANEL_ACCESS)),
 ) -> list[PendingUserSnapshot]:
     pending_emails = get_pending_users()
     return [PendingUserSnapshot(email=email) for email in pending_emails]
@@ -46,7 +46,7 @@ def list_pending_users(
 @router.post("/users/invite/approve")
 async def approve_user(
     approve_user_request: ApproveUserRequest,
-    _: User = Depends(current_admin_user),
+    _: User = Depends(require_permission(Permission.FULL_ADMIN_PANEL_ACCESS)),
 ) -> None:
     tenant_id = get_current_tenant_id()
     approve_user_invite(approve_user_request.email, tenant_id)
@@ -55,7 +55,7 @@ async def approve_user(
 @router.post("/users/invite/accept")
 async def accept_invite(
     invite_request: RequestInviteRequest,
-    user: User = Depends(current_user),
+    user: User = Depends(require_permission(Permission.BASIC_ACCESS)),
 ) -> None:
     """
     Accept an invitation to join a tenant.
@@ -70,7 +70,7 @@ async def accept_invite(
 @router.post("/users/invite/deny")
 async def deny_invite(
     invite_request: RequestInviteRequest,
-    user: User = Depends(current_user),
+    user: User = Depends(require_permission(Permission.BASIC_ACCESS)),
 ) -> None:
     """
     Deny an invitation to join a tenant.

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

@@ -7,10 +7,11 @@ from sqlalchemy.orm import Session
 from ee.onyx.db.token_limit import fetch_all_user_group_token_rate_limits_by_group
 from ee.onyx.db.token_limit import fetch_user_group_token_rate_limits_for_user
 from ee.onyx.db.token_limit import insert_user_group_token_rate_limit
-from onyx.auth.users import current_admin_user
+from onyx.auth.permissions import require_permission
 from onyx.auth.users import current_curator_or_admin_user
 from onyx.configs.constants import PUBLIC_API_TAGS
 from onyx.db.engine.sql_engine import get_session
+from onyx.db.enums import Permission
 from onyx.db.models import User
 from onyx.db.token_limit import fetch_all_user_token_rate_limits
 from onyx.db.token_limit import insert_user_token_rate_limit
@@ -28,7 +29,7 @@ Group Token Limit Settings
 
 @router.get("/user-groups")
 def get_all_group_token_limit_settings(
-    _: User = Depends(current_admin_user),
+    _: User = Depends(require_permission(Permission.FULL_ADMIN_PANEL_ACCESS)),
     db_session: Session = Depends(get_session),
 ) -> dict[str, list[TokenRateLimitDisplay]]:
     user_groups_to_token_rate_limits = fetch_all_user_group_token_rate_limits_by_group(
@@ -64,7 +65,7 @@ def get_group_token_limit_settings(
 def create_group_token_limit_settings(
     group_id: int,
     token_limit_settings: TokenRateLimitArgs,
-    _: User = Depends(current_admin_user),
+    _: User = Depends(require_permission(Permission.FULL_ADMIN_PANEL_ACCESS)),
     db_session: Session = Depends(get_session),
 ) -> TokenRateLimitDisplay:
     rate_limit_display = TokenRateLimitDisplay.from_db(
@@ -86,7 +87,7 @@ User Token Limit Settings
 
 @router.get("/users")
 def get_user_token_limit_settings(
-    _: User = Depends(current_admin_user),
+    _: User = Depends(require_permission(Permission.FULL_ADMIN_PANEL_ACCESS)),
     db_session: Session = Depends(get_session),
 ) -> list[TokenRateLimitDisplay]:
     return [
@@ -98,7 +99,7 @@ def get_user_token_limit_settings(
 @router.post("/users")
 def create_user_token_limit_settings(
     token_limit_settings: TokenRateLimitArgs,
-    _: User = Depends(current_admin_user),
+    _: User = Depends(require_permission(Permission.FULL_ADMIN_PANEL_ACCESS)),
     db_session: Session = Depends(get_session),
 ) -> TokenRateLimitDisplay:
     rate_limit_display = TokenRateLimitDisplay.from_db(

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

@@ -13,22 +13,26 @@ from ee.onyx.db.user_group import fetch_user_groups_for_user
 from ee.onyx.db.user_group import insert_user_group
 from ee.onyx.db.user_group import prepare_user_group_for_deletion
 from ee.onyx.db.user_group import rename_user_group
+from ee.onyx.db.user_group import set_group_permission__no_commit
 from ee.onyx.db.user_group import update_user_curator_relationship
 from ee.onyx.db.user_group import update_user_group
 from ee.onyx.server.user_group.models import AddUsersToUserGroupRequest
 from ee.onyx.server.user_group.models import MinimalUserGroupSnapshot
 from ee.onyx.server.user_group.models import SetCuratorRequest
+from ee.onyx.server.user_group.models import SetPermissionRequest
+from ee.onyx.server.user_group.models import SetPermissionResponse
 from ee.onyx.server.user_group.models import UpdateGroupAgentsRequest
 from ee.onyx.server.user_group.models import UserGroup
 from ee.onyx.server.user_group.models import UserGroupCreate
 from ee.onyx.server.user_group.models import UserGroupRename
 from ee.onyx.server.user_group.models import UserGroupUpdate
-from onyx.auth.users import current_admin_user
+from onyx.auth.permissions import NON_TOGGLEABLE_PERMISSIONS
+from onyx.auth.permissions import require_permission
 from onyx.auth.users import current_curator_or_admin_user
-from onyx.auth.users import current_user
 from onyx.configs.app_configs import DISABLE_VECTOR_DB
 from onyx.configs.constants import PUBLIC_API_TAGS
 from onyx.db.engine.sql_engine import get_session
+from onyx.db.enums import Permission
 from onyx.db.models import User
 from onyx.db.models import UserRole
 from onyx.db.persona import get_persona_by_id
@@ -68,7 +72,7 @@ def list_user_groups(
 @router.get("/user-groups/minimal")
 def list_minimal_user_groups(
     include_default: bool = False,
-    user: User = Depends(current_user),
+    user: User = Depends(require_permission(Permission.BASIC_ACCESS)),
     db_session: Session = Depends(get_session),
 ) -> list[MinimalUserGroupSnapshot]:
     if user.role == UserRole.ADMIN:
@@ -91,23 +95,50 @@ def list_minimal_user_groups(
 @router.get("/admin/user-group/{user_group_id}/permissions")
 def get_user_group_permissions(
     user_group_id: int,
-    _: User = Depends(current_admin_user),
+    _: User = Depends(require_permission(Permission.FULL_ADMIN_PANEL_ACCESS)),
     db_session: Session = Depends(get_session),
-) -> list[str]:
+) -> list[Permission]:
     group = fetch_user_group(db_session, user_group_id)
     if group is None:
         raise OnyxError(OnyxErrorCode.NOT_FOUND, "User group not found")
     return [
-        grant.permission.value
-        for grant in group.permission_grants
-        if not grant.is_deleted
+        grant.permission for grant in group.permission_grants if not grant.is_deleted
     ]
 
 
+@router.put("/admin/user-group/{user_group_id}/permissions")
+def set_user_group_permission(
+    user_group_id: int,
+    request: SetPermissionRequest,
+    user: User = Depends(require_permission(Permission.FULL_ADMIN_PANEL_ACCESS)),
+    db_session: Session = Depends(get_session),
+) -> SetPermissionResponse:
+    group = fetch_user_group(db_session, user_group_id)
+    if group is None:
+        raise OnyxError(OnyxErrorCode.NOT_FOUND, "User group not found")
+
+    if request.permission in NON_TOGGLEABLE_PERMISSIONS:
+        raise OnyxError(
+            OnyxErrorCode.INVALID_INPUT,
+            f"Permission '{request.permission}' cannot be toggled via this endpoint",
+        )
+
+    set_group_permission__no_commit(
+        group_id=user_group_id,
+        permission=request.permission,
+        enabled=request.enabled,
+        granted_by=user.id,
+        db_session=db_session,
+    )
+    db_session.commit()
+
+    return SetPermissionResponse(permission=request.permission, enabled=request.enabled)
+
+
 @router.post("/admin/user-group")
 def create_user_group(
     user_group: UserGroupCreate,
-    _: User = Depends(current_admin_user),
+    _: User = Depends(require_permission(Permission.FULL_ADMIN_PANEL_ACCESS)),
     db_session: Session = Depends(get_session),
 ) -> UserGroup:
     try:
@@ -124,7 +155,7 @@ def create_user_group(
 @router.patch("/admin/user-group/rename")
 def rename_user_group_endpoint(
     rename_request: UserGroupRename,
-    _: User = Depends(current_admin_user),
+    _: User = Depends(require_permission(Permission.FULL_ADMIN_PANEL_ACCESS)),
     db_session: Session = Depends(get_session),
 ) -> UserGroup:
     group = fetch_user_group(db_session, rename_request.id)
@@ -212,7 +243,7 @@ def set_user_curator(
 @router.delete("/admin/user-group/{user_group_id}")
 def delete_user_group(
     user_group_id: int,
-    _: User = Depends(current_admin_user),
+    _: User = Depends(require_permission(Permission.FULL_ADMIN_PANEL_ACCESS)),
     db_session: Session = Depends(get_session),
 ) -> None:
     group = fetch_user_group(db_session, user_group_id)
@@ -233,7 +264,7 @@ def delete_user_group(
 def update_group_agents(
     user_group_id: int,
     request: UpdateGroupAgentsRequest,
-    user: User = Depends(current_admin_user),
+    user: User = Depends(require_permission(Permission.FULL_ADMIN_PANEL_ACCESS)),
     db_session: Session = Depends(get_session),
 ) -> None:
     for agent_id in request.added_agent_ids:

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

@@ -2,6 +2,7 @@ from uuid import UUID
 
 from pydantic import BaseModel
 
+from onyx.auth.permissions import Permission
 from onyx.db.models import UserGroup as UserGroupModel
 from onyx.server.documents.models import ConnectorCredentialPairDescriptor
 from onyx.server.documents.models import ConnectorSnapshot
@@ -121,3 +122,13 @@ class SetCuratorRequest(BaseModel):
 class UpdateGroupAgentsRequest(BaseModel):
     added_agent_ids: list[int]
     removed_agent_ids: list[int]
+
+
+class SetPermissionRequest(BaseModel):
+    permission: Permission
+    enabled: bool
+
+
+class SetPermissionResponse(BaseModel):
+    permission: Permission
+    enabled: bool

backend/onyx/auth/permissions.py

@@ -47,6 +47,20 @@ IMPLIED_PERMISSIONS: dict[str, set[str]] = {
     },
 }
 
+# Permissions that cannot be toggled via the group-permission API.
+# BASIC_ACCESS is always granted, FULL_ADMIN_PANEL_ACCESS is too broad,
+# and READ_* permissions are implied (never stored directly).
+NON_TOGGLEABLE_PERMISSIONS: frozenset[Permission] = frozenset(
+    {
+        Permission.BASIC_ACCESS,
+        Permission.FULL_ADMIN_PANEL_ACCESS,
+        Permission.READ_CONNECTORS,
+        Permission.READ_DOCUMENT_SETS,
+        Permission.READ_AGENTS,
+        Permission.READ_USERS,
+    }
+)
+
 
 def resolve_effective_permissions(granted: set[str]) -> set[str]:
     """Expand granted permissions with their implied permissions.
@@ -107,4 +121,5 @@ def require_permission(
 
         return user
 
+    dependency._is_require_permission = True  # type: ignore[attr-defined]  # sentinel for auth_check detection
     return dependency

backend/onyx/auth/users.py

@@ -127,6 +127,7 @@ from onyx.db.models import User
 from onyx.db.pat import fetch_user_for_pat
 from onyx.db.users import assign_user_to_default_groups__no_commit
 from onyx.db.users import get_user_by_email
+from onyx.db.users import is_limited_user
 from onyx.error_handling.error_codes import OnyxErrorCode
 from onyx.error_handling.exceptions import log_onyx_error
 from onyx.error_handling.exceptions import onyx_error_to_json_response
@@ -1681,9 +1682,9 @@ async def current_user(
 ) -> User:
     user = await double_check_user(user)
 
-    if user.role == UserRole.LIMITED:
+    if is_limited_user(user):
         raise BasicAuthenticationError(
-            detail="Access denied. User role is LIMITED. BASIC or higher permissions are required.",
+            detail="Access denied. User has limited permissions.",
         )
     return user
 
@@ -1700,15 +1701,6 @@ async def current_curator_or_admin_user(
     return user
 
 
-async def current_admin_user(user: User = Depends(current_user)) -> User:
-    if user.role != UserRole.ADMIN:
-        raise BasicAuthenticationError(
-            detail="Access denied. User must be an admin to perform this action.",
-        )
-
-    return user
-
-
 async def _get_user_from_token_data(token_data: dict) -> User | None:
     """Shared logic: token data dict → User object.
 
@@ -1817,11 +1809,11 @@ async def current_user_from_websocket(
     # Apply same checks as HTTP auth (verification, OIDC expiry, role)
     user = await double_check_user(user)
 
-    # Block LIMITED users (same as current_user)
-    if user.role == UserRole.LIMITED:
-        logger.warning(f"WS auth: user {user.email} has LIMITED role")
+    # Block limited users (same as current_user)
+    if is_limited_user(user):
+        logger.warning(f"WS auth: user {user.email} is limited")
         raise BasicAuthenticationError(
-            detail="Access denied. User role is LIMITED. BASIC or higher permissions are required.",
+            detail="Access denied. User has limited permissions.",
         )
 
     logger.debug(f"WS auth: authenticated {user.email}")

backend/onyx/background/README.md

@@ -1,6 +1,7 @@
 # Overview of Onyx Background Jobs
 
 The background jobs take care of:
+
 1. Pulling/Indexing documents (from connectors)
 2. Updating document metadata (from connectors)
 3. Cleaning up checkpoints and logic around indexing work (indexing indexing checkpoints and index attempt metadata)
@@ -9,37 +10,41 @@ The background jobs take care of:
 
 ## Worker → Queue Mapping
 
-| Worker | File | Queues |
-|--------|------|--------|
-| Primary | `apps/primary.py` | `celery` |
-| Light | `apps/light.py` | `vespa_metadata_sync`, `connector_deletion`, `doc_permissions_upsert`, `checkpoint_cleanup`, `index_attempt_cleanup` |
-| Heavy | `apps/heavy.py` | `connector_pruning`, `connector_doc_permissions_sync`, `connector_external_group_sync`, `csv_generation`, `sandbox` |
-| Docprocessing | `apps/docprocessing.py` | `docprocessing` |
-| Docfetching | `apps/docfetching.py` | `connector_doc_fetching` |
-| User File Processing | `apps/user_file_processing.py` | `user_file_processing`, `user_file_project_sync`, `user_file_delete` |
-| Monitoring | `apps/monitoring.py` | `monitoring` |
-| Background (consolidated) | `apps/background.py` | All queues above except `celery` |
+| Worker                    | File                           | Queues                                                                                                               |
+| ------------------------- | ------------------------------ | -------------------------------------------------------------------------------------------------------------------- |
+| Primary                   | `apps/primary.py`              | `celery`                                                                                                             |
+| Light                     | `apps/light.py`                | `vespa_metadata_sync`, `connector_deletion`, `doc_permissions_upsert`, `checkpoint_cleanup`, `index_attempt_cleanup` |
+| Heavy                     | `apps/heavy.py`                | `connector_pruning`, `connector_doc_permissions_sync`, `connector_external_group_sync`, `csv_generation`, `sandbox`  |
+| Docprocessing             | `apps/docprocessing.py`        | `docprocessing`                                                                                                      |
+| Docfetching               | `apps/docfetching.py`          | `connector_doc_fetching`                                                                                             |
+| User File Processing      | `apps/user_file_processing.py` | `user_file_processing`, `user_file_project_sync`, `user_file_delete`                                                 |
+| Monitoring                | `apps/monitoring.py`           | `monitoring`                                                                                                         |
+| Background (consolidated) | `apps/background.py`           | All queues above except `celery`                                                                                     |
 
 ## Non-Worker Apps
-| App | File | Purpose |
-|-----|------|---------|
-| **Beat** | `beat.py` | Celery beat scheduler with `DynamicTenantScheduler` that generates per-tenant periodic task schedules |
-| **Client** | `client.py` | Minimal app for task submission from non-worker processes (e.g., API server) |
+
+| App        | File        | Purpose                                                                                               |
+| ---------- | ----------- | ----------------------------------------------------------------------------------------------------- |
+| **Beat**   | `beat.py`   | Celery beat scheduler with `DynamicTenantScheduler` that generates per-tenant periodic task schedules |
+| **Client** | `client.py` | Minimal app for task submission from non-worker processes (e.g., API server)                          |
 
 ### Shared Module
+
 `app_base.py` provides:
+
 - `TenantAwareTask` - Base task class that sets tenant context
 - Signal handlers for logging, cleanup, and lifecycle events
 - Readiness probes and health checks
 
-
 ## Worker Details
 
 ### Primary (Coordinator and task dispatcher)
+
 It is the single worker which handles tasks from the default celery queue. It is a singleton worker ensured by the `PRIMARY_WORKER` Redis lock
 which it touches every `CELERY_PRIMARY_WORKER_LOCK_TIMEOUT / 8` seconds (using Celery Bootsteps)
 
 On startup:
+
 - waits for redis, postgres, document index to all be healthy
 - acquires the singleton lock
 - cleans all the redis states associated with background jobs
@@ -47,34 +52,34 @@ On startup:
 
 Then it cycles through its tasks as scheduled by Celery Beat:
 
-| Task | Frequency | Description |
-|------|-----------|-------------|
-| `check_for_indexing` | 15s | Scans for connectors needing indexing → dispatches to `DOCFETCHING` queue |
-| `check_for_vespa_sync_task` | 20s | Finds stale documents/document sets → dispatches sync tasks to `VESPA_METADATA_SYNC` queue |
-| `check_for_pruning` | 20s | Finds connectors due for pruning → dispatches to `CONNECTOR_PRUNING` queue |
-| `check_for_connector_deletion` | 20s | Processes deletion requests → dispatches to `CONNECTOR_DELETION` queue |
-| `check_for_user_file_processing` | 20s | Checks for user uploads → dispatches to `USER_FILE_PROCESSING` queue |
-| `check_for_checkpoint_cleanup` | 1h | Cleans up old indexing checkpoints |
-| `check_for_index_attempt_cleanup` | 30m | Cleans up old index attempts |
-| `kombu_message_cleanup_task` | periodic | Cleans orphaned Kombu messages from DB (Kombu being the messaging framework used by Celery) |
-| `celery_beat_heartbeat` | 1m | Heartbeat for Beat watchdog |
+| Task                              | Frequency | Description                                                                                |
+| --------------------------------- | --------- | ------------------------------------------------------------------------------------------ |
+| `check_for_indexing`              | 15s       | Scans for connectors needing indexing → dispatches to `DOCFETCHING` queue                  |
+| `check_for_vespa_sync_task`       | 20s       | Finds stale documents/document sets → dispatches sync tasks to `VESPA_METADATA_SYNC` queue |
+| `check_for_pruning`               | 20s       | Finds connectors due for pruning → dispatches to `CONNECTOR_PRUNING` queue                 |
+| `check_for_connector_deletion`    | 20s       | Processes deletion requests → dispatches to `CONNECTOR_DELETION` queue                     |
+| `check_for_user_file_processing`  | 20s       | Checks for user uploads → dispatches to `USER_FILE_PROCESSING` queue                       |
+| `check_for_checkpoint_cleanup`    | 1h        | Cleans up old indexing checkpoints                                                         |
+| `check_for_index_attempt_cleanup` | 30m       | Cleans up old index attempts                                                               |
+| `celery_beat_heartbeat`           | 1m        | Heartbeat for Beat watchdog                                                                |
 
 Watchdog is a separate Python process managed by supervisord which runs alongside celery workers. It checks the ONYX_CELERY_BEAT_HEARTBEAT_KEY in
 Redis to ensure Celery Beat is not dead. Beat schedules the celery_beat_heartbeat for Primary to touch the key and share that it's still alive.
 See supervisord.conf for watchdog config.
 
-
 ### Light
+
 Fast and short living tasks that are not resource intensive. High concurrency:
 Can have 24 concurrent workers, each with a prefetch of 8 for a total of 192 tasks in flight at once.
 
 Tasks it handles:
+
 - Syncs access/permissions, document sets, boosts, hidden state
 - Deletes documents that are marked for deletion in Postgres
 - Cleanup of checkpoints and index attempts
 
-
 ### Heavy
+
 Long running, resource intensive tasks, handles pruning and sandbox operations. Low concurrency - max concurrency of 4 with 1 prefetch.
 
 Does not interact with the Document Index, it handles the syncs with external systems. Large volume API calls to handle pruning and fetching permissions, etc.
@@ -83,16 +88,24 @@ Generates CSV exports which may take a long time with significant data in Postgr
 
 Sandbox (new feature) for running Next.js, Python virtual env, OpenCode AI Agent, and access to knowledge files
 
-
 ### Docprocessing, Docfetching, User File Processing
-Docprocessing and Docfetching are for indexing documents:
-- Docfetching runs connectors to pull documents from external APIs (Google Drive, Confluence, etc.), stores batches to file storage, and dispatches docprocessing tasks
-- Docprocessing retrieves batches, runs the indexing pipeline (chunking, embedding), and indexes into the Document Index 
-User Files come from uploads directly via the input bar
 
+Docprocessing and Docfetching are for indexing documents:
+
+- Docfetching runs connectors to pull documents from external APIs (Google Drive, Confluence, etc.), stores batches to file storage, and dispatches docprocessing tasks
+- Docprocessing retrieves batches, runs the indexing pipeline (chunking, embedding), and indexes into the Document Index
+- User Files come from uploads directly via the input bar
 
 ### Monitoring
+
 Observability and metrics collections:
-- Queue lengths, connector success/failure, lconnector latencies
+
+- Queue lengths, connector success/failure, connector latencies
 - Memory of supervisor managed processes (workers, beat, slack)
 - Cloud and multitenant specific monitorings
+
+## Prometheus Metrics
+
+Workers can expose Prometheus metrics via a standalone HTTP server. Currently docfetching and docprocessing have push-based task lifecycle metrics; the monitoring worker runs pull-based collectors for queue depth and connector health.
+
+For the full metric reference, integration guide, and PromQL examples, see [`docs/METRICS.md`](../../../docs/METRICS.md#celery-worker-metrics).

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

@@ -13,6 +13,12 @@ from celery.signals import worker_shutdown
 import onyx.background.celery.apps.app_base as app_base
 from onyx.configs.constants import POSTGRES_CELERY_WORKER_HEAVY_APP_NAME
 from onyx.db.engine.sql_engine import SqlEngine
+from onyx.server.metrics.celery_task_metrics import on_celery_task_postrun
+from onyx.server.metrics.celery_task_metrics import on_celery_task_prerun
+from onyx.server.metrics.celery_task_metrics import on_celery_task_rejected
+from onyx.server.metrics.celery_task_metrics import on_celery_task_retry
+from onyx.server.metrics.celery_task_metrics import on_celery_task_revoked
+from onyx.server.metrics.metrics_server import start_metrics_server
 from onyx.utils.logger import setup_logger
 from shared_configs.configs import MULTI_TENANT
 
@@ -34,6 +40,7 @@ def on_task_prerun(
     **kwds: Any,
 ) -> None:
     app_base.on_task_prerun(sender, task_id, task, args, kwargs, **kwds)
+    on_celery_task_prerun(task_id, task)
 
 
 @signals.task_postrun.connect
@@ -48,6 +55,31 @@ def on_task_postrun(
     **kwds: Any,
 ) -> None:
     app_base.on_task_postrun(sender, task_id, task, args, kwargs, retval, state, **kwds)
+    on_celery_task_postrun(task_id, task, state)
+
+
+@signals.task_retry.connect
+def on_task_retry(sender: Any | None = None, **kwargs: Any) -> None:  # noqa: ARG001
+    task_id = getattr(getattr(sender, "request", None), "id", None)
+    on_celery_task_retry(task_id, sender)
+
+
+@signals.task_revoked.connect
+def on_task_revoked(sender: Any | None = None, **kwargs: Any) -> None:
+    task_name = getattr(sender, "name", None) or str(sender)
+    on_celery_task_revoked(kwargs.get("task_id"), task_name)
+
+
+@signals.task_rejected.connect
+def on_task_rejected(sender: Any | None = None, **kwargs: Any) -> None:  # noqa: ARG001
+    message = kwargs.get("message")
+    task_name: str | None = None
+    if message is not None:
+        headers = getattr(message, "headers", None) or {}
+        task_name = headers.get("task")
+    if task_name is None:
+        task_name = "unknown"
+    on_celery_task_rejected(None, task_name)
 
 
 @celeryd_init.connect
@@ -76,6 +108,7 @@ def on_worker_init(sender: Worker, **kwargs: Any) -> None:
 
 @worker_ready.connect
 def on_worker_ready(sender: Any, **kwargs: Any) -> None:
+    start_metrics_server("heavy")
     app_base.on_worker_ready(sender, **kwargs)
 
 

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

@@ -317,7 +317,6 @@ celery_app.autodiscover_tasks(
             "onyx.background.celery.tasks.docprocessing",
             "onyx.background.celery.tasks.evals",
             "onyx.background.celery.tasks.hierarchyfetching",
-            "onyx.background.celery.tasks.periodic",
             "onyx.background.celery.tasks.pruning",
             "onyx.background.celery.tasks.shared",
             "onyx.background.celery.tasks.vespa",

backend/onyx/background/celery/celery_utils.py

@@ -1,3 +1,4 @@
+import time
 from collections.abc import Generator
 from collections.abc import Iterator
 from collections.abc import Sequence
@@ -30,6 +31,8 @@ from onyx.connectors.models import HierarchyNode
 from onyx.connectors.models import SlimDocument
 from onyx.httpx.httpx_pool import HttpxPool
 from onyx.indexing.indexing_heartbeat import IndexingHeartbeatInterface
+from onyx.server.metrics.pruning_metrics import inc_pruning_rate_limit_error
+from onyx.server.metrics.pruning_metrics import observe_pruning_enumeration_duration
 from onyx.utils.logger import setup_logger
 
 
@@ -130,6 +133,7 @@ def _extract_from_batch(
 def extract_ids_from_runnable_connector(
     runnable_connector: BaseConnector,
     callback: IndexingHeartbeatInterface | None = None,
+    connector_type: str = "unknown",
 ) -> SlimConnectorExtractionResult:
     """
     Extract document IDs and hierarchy nodes from a runnable connector.
@@ -179,21 +183,38 @@ def extract_ids_from_runnable_connector(
     )
 
     # process raw batches to extract both IDs and hierarchy nodes
-    for doc_list in raw_batch_generator:
-        if callback and callback.should_stop():
-            raise RuntimeError(
-                "extract_ids_from_runnable_connector: Stop signal detected"
-            )
+    enumeration_start = time.monotonic()
+    try:
+        for doc_list in raw_batch_generator:
+            if callback and callback.should_stop():
+                raise RuntimeError(
+                    "extract_ids_from_runnable_connector: Stop signal detected"
+                )
 
-        batch_result = _extract_from_batch(doc_list)
-        batch_ids = batch_result.raw_id_to_parent
-        batch_nodes = batch_result.hierarchy_nodes
-        doc_batch_processing_func(batch_ids)
-        all_raw_id_to_parent.update(batch_ids)
-        all_hierarchy_nodes.extend(batch_nodes)
+            batch_result = _extract_from_batch(doc_list)
+            batch_ids = batch_result.raw_id_to_parent
+            batch_nodes = batch_result.hierarchy_nodes
+            doc_batch_processing_func(batch_ids)
+            all_raw_id_to_parent.update(batch_ids)
+            all_hierarchy_nodes.extend(batch_nodes)
 
-        if callback:
-            callback.progress("extract_ids_from_runnable_connector", len(batch_ids))
+            if callback:
+                callback.progress("extract_ids_from_runnable_connector", len(batch_ids))
+    except Exception as e:
+        # Best-effort rate limit detection via string matching.
+        # Connectors surface rate limits inconsistently — some raise HTTP 429,
+        # some use SDK-specific exceptions (e.g. google.api_core.exceptions.ResourceExhausted)
+        # that may or may not include "rate limit" or "429" in the message.
+        # TODO(Bo): replace with a standard ConnectorRateLimitError exception that all
+        # connectors raise when rate limited, making this check precise.
+        error_str = str(e)
+        if "rate limit" in error_str.lower() or "429" in error_str:
+            inc_pruning_rate_limit_error(connector_type)
+        raise
+    finally:
+        observe_pruning_enumeration_duration(
+            time.monotonic() - enumeration_start, connector_type
+        )
 
     return SlimConnectorExtractionResult(
         raw_id_to_parent=all_raw_id_to_parent,

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

@@ -75,6 +75,8 @@ beat_task_templates: list[dict] = [
         "options": {
             "priority": OnyxCeleryPriority.LOW,
             "expires": BEAT_EXPIRES_DEFAULT,
+            # Run on gated tenants too — they may still have stale checkpoints to clean.
+            "skip_gated": False,
         },
     },
     {
@@ -84,6 +86,8 @@ beat_task_templates: list[dict] = [
         "options": {
             "priority": OnyxCeleryPriority.MEDIUM,
             "expires": BEAT_EXPIRES_DEFAULT,
+            # Run on gated tenants too — they may still have stale index attempts.
+            "skip_gated": False,
         },
     },
     {
@@ -93,6 +97,8 @@ beat_task_templates: list[dict] = [
         "options": {
             "priority": OnyxCeleryPriority.MEDIUM,
             "expires": BEAT_EXPIRES_DEFAULT,
+            # Gated tenants may still have connectors awaiting deletion.
+            "skip_gated": False,
         },
     },
     {
@@ -136,7 +142,14 @@ beat_task_templates: list[dict] = [
     {
         "name": "cleanup-idle-sandboxes",
         "task": OnyxCeleryTask.CLEANUP_IDLE_SANDBOXES,
-        "schedule": timedelta(minutes=1),
+        # SANDBOX_IDLE_TIMEOUT_SECONDS defaults to 1 hour, so there is no
+        # functional reason to scan more often than every ~15 minutes. In the
+        # cloud this is multiplied by CLOUD_BEAT_MULTIPLIER_DEFAULT (=8) so
+        # the effective cadence becomes ~2 hours, which still meets the
+        # idle-detection SLA. The previous 1-minute base schedule produced
+        # an 8-minute per-tenant fan-out and was the dominant source of
+        # background DB load on the cloud cluster.
+        "schedule": timedelta(minutes=15),
         "options": {
             "priority": OnyxCeleryPriority.LOW,
             "expires": BEAT_EXPIRES_DEFAULT,
@@ -266,7 +279,7 @@ def make_cloud_generator_task(task: dict[str, Any]) -> dict[str, Any]:
     cloud_task["kwargs"] = {}
     cloud_task["kwargs"]["task_name"] = task["task"]
 
-    optional_fields = ["queue", "priority", "expires"]
+    optional_fields = ["queue", "priority", "expires", "skip_gated"]
     for field in optional_fields:
         if field in task["options"]:
             cloud_task["kwargs"][field] = task["options"][field]
@@ -359,7 +372,13 @@ if not MULTI_TENANT:
         ]
     )
 
-    tasks_to_schedule.extend(beat_task_templates)
+    # `skip_gated` is a cloud-only hint consumed by `cloud_beat_task_generator`. Strip
+    # it before extending the self-hosted schedule so it doesn't leak into apply_async
+    # as an unrecognised option on every fired task message.
+    for _template in beat_task_templates:
+        _self_hosted_template = copy.deepcopy(_template)
+        _self_hosted_template["options"].pop("skip_gated", None)
+        tasks_to_schedule.append(_self_hosted_template)
 
 
 def generate_cloud_tasks(

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

@@ -1,138 +0,0 @@
-#####
-# Periodic Tasks
-#####
-import json
-from typing import Any
-
-from celery import shared_task
-from celery.contrib.abortable import AbortableTask  # type: ignore
-from celery.exceptions import TaskRevokedError
-from sqlalchemy import inspect
-from sqlalchemy import text
-from sqlalchemy.orm import Session
-
-from onyx.background.celery.apps.app_base import task_logger
-from onyx.configs.app_configs import JOB_TIMEOUT
-from onyx.configs.constants import OnyxCeleryTask
-from onyx.configs.constants import PostgresAdvisoryLocks
-from onyx.db.engine.sql_engine import get_session_with_current_tenant
-
-
-@shared_task(
-    name=OnyxCeleryTask.KOMBU_MESSAGE_CLEANUP_TASK,
-    soft_time_limit=JOB_TIMEOUT,
-    bind=True,
-    base=AbortableTask,
-)
-def kombu_message_cleanup_task(self: Any, tenant_id: str) -> int:  # noqa: ARG001
-    """Runs periodically to clean up the kombu_message table"""
-
-    # we will select messages older than this amount to clean up
-    KOMBU_MESSAGE_CLEANUP_AGE = 7  # days
-    KOMBU_MESSAGE_CLEANUP_PAGE_LIMIT = 1000
-
-    ctx = {}
-    ctx["last_processed_id"] = 0
-    ctx["deleted"] = 0
-    ctx["cleanup_age"] = KOMBU_MESSAGE_CLEANUP_AGE
-    ctx["page_limit"] = KOMBU_MESSAGE_CLEANUP_PAGE_LIMIT
-    with get_session_with_current_tenant() as db_session:
-        # Exit the task if we can't take the advisory lock
-        result = db_session.execute(
-            text("SELECT pg_try_advisory_lock(:id)"),
-            {"id": PostgresAdvisoryLocks.KOMBU_MESSAGE_CLEANUP_LOCK_ID.value},
-        ).scalar()
-        if not result:
-            return 0
-
-        while True:
-            if self.is_aborted():
-                raise TaskRevokedError("kombu_message_cleanup_task was aborted.")
-
-            b = kombu_message_cleanup_task_helper(ctx, db_session)
-            if not b:
-                break
-
-            db_session.commit()
-
-    if ctx["deleted"] > 0:
-        task_logger.info(
-            f"Deleted {ctx['deleted']} orphaned messages from kombu_message."
-        )
-
-    return ctx["deleted"]
-
-
-def kombu_message_cleanup_task_helper(ctx: dict, db_session: Session) -> bool:
-    """
-    Helper function to clean up old messages from the `kombu_message` table that are no longer relevant.
-
-    This function retrieves messages from the `kombu_message` table that are no longer visible and
-    older than a specified interval. It checks if the corresponding task_id exists in the
-    `celery_taskmeta` table. If the task_id does not exist, the message is deleted.
-
-    Args:
-        ctx (dict): A context dictionary containing configuration parameters such as:
-            - 'cleanup_age' (int): The age in days after which messages are considered old.
-            - 'page_limit' (int): The maximum number of messages to process in one batch.
-            - 'last_processed_id' (int): The ID of the last processed message to handle pagination.
-            - 'deleted' (int): A counter to track the number of deleted messages.
-        db_session (Session): The SQLAlchemy database session for executing queries.
-
-    Returns:
-        bool: Returns True if there are more rows to process, False if not.
-    """
-
-    inspector = inspect(db_session.bind)
-    if not inspector:
-        return False
-
-    # With the move to redis as celery's broker and backend, kombu tables may not even exist.
-    # We can fail silently.
-    if not inspector.has_table("kombu_message"):
-        return False
-
-    query = text(
-        """
-    SELECT id, timestamp, payload
-    FROM kombu_message WHERE visible = 'false'
-    AND timestamp < CURRENT_TIMESTAMP - INTERVAL :interval_days
-    AND id > :last_processed_id
-    ORDER BY id
-    LIMIT :page_limit
-"""
-    )
-    kombu_messages = db_session.execute(
-        query,
-        {
-            "interval_days": f"{ctx['cleanup_age']} days",
-            "page_limit": ctx["page_limit"],
-            "last_processed_id": ctx["last_processed_id"],
-        },
-    ).fetchall()
-
-    if len(kombu_messages) == 0:
-        return False
-
-    for msg in kombu_messages:
-        payload = json.loads(msg[2])
-        task_id = payload["headers"]["id"]
-
-        # Check if task_id exists in celery_taskmeta
-        task_exists = db_session.execute(
-            text("SELECT 1 FROM celery_taskmeta WHERE task_id = :task_id"),
-            {"task_id": task_id},
-        ).fetchone()
-
-        # If task_id does not exist, delete the message
-        if not task_exists:
-            result = db_session.execute(
-                text("DELETE FROM kombu_message WHERE id = :message_id"),
-                {"message_id": msg[0]},
-            )
-            if result.rowcount > 0:  # type: ignore
-                ctx["deleted"] += 1
-
-        ctx["last_processed_id"] = msg[0]
-
-    return True

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

@@ -72,6 +72,7 @@ from onyx.redis.redis_hierarchy import get_source_node_id_from_cache
 from onyx.redis.redis_hierarchy import HierarchyNodeCacheEntry
 from onyx.redis.redis_pool import get_redis_client
 from onyx.redis.redis_pool import get_redis_replica_client
+from onyx.server.metrics.pruning_metrics import observe_pruning_diff_duration
 from onyx.server.runtime.onyx_runtime import OnyxRuntime
 from onyx.server.utils import make_short_id
 from onyx.utils.logger import format_error_for_logging
@@ -217,7 +218,7 @@ def check_for_pruning(self: Task, *, tenant_id: str) -> bool | None:
     try:
         # the entire task needs to run frequently in order to finalize pruning
 
-        # but pruning only kicks off once per hour
+        # but pruning only kicks off once per min
         if not r.exists(OnyxRedisSignals.BLOCK_PRUNING):
             task_logger.info("Checking for pruning due")
 
@@ -570,8 +571,9 @@ def connector_pruning_generator_task(
             )
 
             # Extract docs and hierarchy nodes from the source
+            connector_type = cc_pair.connector.source.value
             extraction_result = extract_ids_from_runnable_connector(
-                runnable_connector, callback
+                runnable_connector, callback, connector_type=connector_type
             )
             all_connector_doc_ids = extraction_result.raw_id_to_parent
 
@@ -636,40 +638,46 @@ def connector_pruning_generator_task(
                 commit=True,
             )
 
-            # a list of docs in our local index
-            all_indexed_document_ids = {
-                doc.id
-                for doc in get_documents_for_connector_credential_pair(
-                    db_session=db_session,
-                    connector_id=connector_id,
-                    credential_id=credential_id,
+            diff_start = time.monotonic()
+            try:
+                # a list of docs in our local index
+                all_indexed_document_ids = {
+                    doc.id
+                    for doc in get_documents_for_connector_credential_pair(
+                        db_session=db_session,
+                        connector_id=connector_id,
+                        credential_id=credential_id,
+                    )
+                }
+
+                # generate list of docs to remove (no longer in the source)
+                doc_ids_to_remove = list(
+                    all_indexed_document_ids - all_connector_doc_ids.keys()
                 )
-            }
 
-            # generate list of docs to remove (no longer in the source)
-            doc_ids_to_remove = list(
-                all_indexed_document_ids - all_connector_doc_ids.keys()
-            )
+                task_logger.info(
+                    "Pruning set collected: "
+                    f"cc_pair={cc_pair_id} "
+                    f"connector_source={cc_pair.connector.source} "
+                    f"docs_to_remove={len(doc_ids_to_remove)}"
+                )
 
-            task_logger.info(
-                "Pruning set collected: "
-                f"cc_pair={cc_pair_id} "
-                f"connector_source={cc_pair.connector.source} "
-                f"docs_to_remove={len(doc_ids_to_remove)}"
-            )
+                task_logger.info(
+                    f"RedisConnector.prune.generate_tasks starting. cc_pair={cc_pair_id}"
+                )
+                tasks_generated = redis_connector.prune.generate_tasks(
+                    set(doc_ids_to_remove), self.app, db_session, None
+                )
+                if tasks_generated is None:
+                    return None
 
-            task_logger.info(
-                f"RedisConnector.prune.generate_tasks starting. cc_pair={cc_pair_id}"
-            )
-            tasks_generated = redis_connector.prune.generate_tasks(
-                set(doc_ids_to_remove), self.app, db_session, None
-            )
-            if tasks_generated is None:
-                return None
-
-            task_logger.info(
-                f"RedisConnector.prune.generate_tasks finished. cc_pair={cc_pair_id} tasks_generated={tasks_generated}"
-            )
+                task_logger.info(
+                    f"RedisConnector.prune.generate_tasks finished. cc_pair={cc_pair_id} tasks_generated={tasks_generated}"
+                )
+            finally:
+                observe_pruning_diff_duration(
+                    time.monotonic() - diff_start, connector_type
+                )
 
             redis_connector.prune.generator_complete = tasks_generated
 

backend/onyx/chat/process_message.py

@@ -996,6 +996,7 @@ def _run_models(
 
     def _run_model(model_idx: int) -> None:
         """Run one LLM loop inside a worker thread, writing packets to ``merged_queue``."""
+
         model_emitter = Emitter(
             model_idx=model_idx,
             merged_queue=merged_queue,
@@ -1102,33 +1103,33 @@ def _run_models(
         finally:
             merged_queue.put((model_idx, _MODEL_DONE))
 
-    def _delete_orphaned_message(model_idx: int, context: str) -> None:
-        """Delete a reserved ChatMessage that was never populated due to a model error."""
+    def _save_errored_message(model_idx: int, context: str) -> None:
+        """Save an error message to a reserved ChatMessage that failed during execution."""
         try:
-            orphaned = db_session.get(
-                ChatMessage, setup.reserved_messages[model_idx].id
-            )
-            if orphaned is not None:
-                db_session.delete(orphaned)
+            msg = db_session.get(ChatMessage, setup.reserved_messages[model_idx].id)
+            if msg is not None:
+                error_text = f"Error from {setup.model_display_names[model_idx]}: model encountered an error during generation."
+                msg.message = error_text
+                msg.error = error_text
                 db_session.commit()
         except Exception:
             logger.exception(
-                "%s orphan cleanup failed for model %d (%s)",
+                "%s error save failed for model %d (%s)",
                 context,
                 model_idx,
                 setup.model_display_names[model_idx],
             )
 
-    # Copy contextvars before submitting futures — ThreadPoolExecutor does NOT
-    # auto-propagate contextvars in Python 3.11; threads would inherit a blank context.
-    worker_context = contextvars.copy_context()
+    # Each worker thread needs its own Context copy — a single Context object
+    # cannot be entered concurrently by multiple threads (RuntimeError).
     executor = ThreadPoolExecutor(
         max_workers=n_models, thread_name_prefix="multi-model"
     )
     completion_persisted: bool = False
     try:
         for i in range(n_models):
-            executor.submit(worker_context.run, _run_model, i)
+            ctx = contextvars.copy_context()
+            executor.submit(ctx.run, _run_model, i)
 
         # ── Main thread: merge and yield packets ────────────────────────────
         models_remaining = n_models
@@ -1145,7 +1146,7 @@ def _run_models(
                     #   save "stopped by user" for a model that actually threw an exception.
                     for i in range(n_models):
                         if model_errored[i]:
-                            _delete_orphaned_message(i, "stop-button")
+                            _save_errored_message(i, "stop-button")
                             continue
                         try:
                             succeeded = model_succeeded[i]
@@ -1211,7 +1212,7 @@ def _run_models(
         for i in range(n_models):
             if not model_succeeded[i]:
                 # Model errored — delete its orphaned reserved message.
-                _delete_orphaned_message(i, "normal")
+                _save_errored_message(i, "normal")
                 continue
             try:
                 llm_loop_completion_handle(
@@ -1264,7 +1265,7 @@ def _run_models(
                             setup.model_display_names[i],
                         )
                 elif model_errored[i]:
-                    _delete_orphaned_message(i, "disconnect")
+                    _save_errored_message(i, "disconnect")
             # 4. Drain buffered packets from memory — no consumer is running.
             while not merged_queue.empty():
                 try:

backend/onyx/configs/app_configs.py

@@ -379,6 +379,14 @@ POSTGRES_HOST = os.environ.get("POSTGRES_HOST") or "127.0.0.1"
 POSTGRES_PORT = os.environ.get("POSTGRES_PORT") or "5432"
 POSTGRES_DB = os.environ.get("POSTGRES_DB") or "postgres"
 AWS_REGION_NAME = os.environ.get("AWS_REGION_NAME") or "us-east-2"
+# Comma-separated replica / multi-host list. If unset, defaults to POSTGRES_HOST
+# only.
+_POSTGRES_HOSTS_STR = os.environ.get("POSTGRES_HOSTS", "").strip()
+POSTGRES_HOSTS: list[str] = (
+    [h.strip() for h in _POSTGRES_HOSTS_STR.split(",") if h.strip()]
+    if _POSTGRES_HOSTS_STR
+    else [POSTGRES_HOST]
+)
 
 POSTGRES_API_SERVER_POOL_SIZE = int(
     os.environ.get("POSTGRES_API_SERVER_POOL_SIZE") or 40

backend/onyx/configs/constants.py

@@ -12,6 +12,11 @@ SLACK_USER_TOKEN_PREFIX = "xoxp-"
 SLACK_BOT_TOKEN_PREFIX = "xoxb-"
 ONYX_EMAILABLE_LOGO_MAX_DIM = 512
 
+# The mask_string() function in encryption.py uses "•" (U+2022 BULLET) to mask secrets.
+MASK_CREDENTIAL_CHAR = "\u2022"
+# Pattern produced by mask_string for strings >= 14 chars: "abcd...wxyz" (exactly 11 chars)
+MASK_CREDENTIAL_LONG_RE = re.compile(r"^.{4}\.{3}.{4}$")
+
 SOURCE_TYPE = "source_type"
 # stored in the `metadata` of a chunk. Used to signify that this chunk should
 # not be used for QA. For example, Google Drive file types which can't be parsed
@@ -391,10 +396,6 @@ class MilestoneRecordType(str, Enum):
     REQUESTED_CONNECTOR = "requested_connector"
 
 
-class PostgresAdvisoryLocks(Enum):
-    KOMBU_MESSAGE_CLEANUP_LOCK_ID = auto()
-
-
 class OnyxCeleryQueues:
     # "celery" is the default queue defined by celery and also the queue
     # we are running in the primary worker to run system tasks
@@ -577,7 +578,6 @@ class OnyxCeleryTask:
     MONITOR_PROCESS_MEMORY = "monitor_process_memory"
     CELERY_BEAT_HEARTBEAT = "celery_beat_heartbeat"
 
-    KOMBU_MESSAGE_CLEANUP_TASK = "kombu_message_cleanup_task"
     CONNECTOR_PERMISSION_SYNC_GENERATOR_TASK = (
         "connector_permission_sync_generator_task"
     )

backend/onyx/connectors/google_drive/connector.py

@@ -42,6 +42,9 @@ from onyx.connectors.google_drive.file_retrieval import (
     get_all_files_in_my_drive_and_shared,
 )
 from onyx.connectors.google_drive.file_retrieval import get_external_access_for_folder
+from onyx.connectors.google_drive.file_retrieval import (
+    get_files_by_web_view_links_batch,
+)
 from onyx.connectors.google_drive.file_retrieval import get_files_in_shared_drive
 from onyx.connectors.google_drive.file_retrieval import get_folder_metadata
 from onyx.connectors.google_drive.file_retrieval import get_root_folder_id
@@ -70,11 +73,13 @@ from onyx.connectors.interfaces import CheckpointedConnectorWithPermSync
 from onyx.connectors.interfaces import CheckpointOutput
 from onyx.connectors.interfaces import GenerateSlimDocumentOutput
 from onyx.connectors.interfaces import NormalizationResult
+from onyx.connectors.interfaces import Resolver
 from onyx.connectors.interfaces import SecondsSinceUnixEpoch
 from onyx.connectors.interfaces import SlimConnectorWithPermSync
 from onyx.connectors.models import ConnectorFailure
 from onyx.connectors.models import ConnectorMissingCredentialError
 from onyx.connectors.models import Document
+from onyx.connectors.models import DocumentFailure
 from onyx.connectors.models import EntityFailure
 from onyx.connectors.models import HierarchyNode
 from onyx.connectors.models import SlimDocument
@@ -202,7 +207,9 @@ class DriveIdStatus(Enum):
 
 
 class GoogleDriveConnector(
-    SlimConnectorWithPermSync, CheckpointedConnectorWithPermSync[GoogleDriveCheckpoint]
+    SlimConnectorWithPermSync,
+    CheckpointedConnectorWithPermSync[GoogleDriveCheckpoint],
+    Resolver,
 ):
     def __init__(
         self,
@@ -1665,6 +1672,82 @@ class GoogleDriveConnector(
             start, end, checkpoint, include_permissions=True
         )
 
+    @override
+    def resolve_errors(
+        self,
+        errors: list[ConnectorFailure],
+        include_permissions: bool = False,
+    ) -> Generator[Document | ConnectorFailure | HierarchyNode, None, None]:
+        if self._creds is None or self._primary_admin_email is None:
+            raise RuntimeError(
+                "Credentials missing, should not call this method before calling load_credentials"
+            )
+
+        logger.info(f"Resolving {len(errors)} errors")
+        doc_ids = [
+            failure.failed_document.document_id
+            for failure in errors
+            if failure.failed_document
+        ]
+        service = get_drive_service(self.creds, self.primary_admin_email)
+        field_type = (
+            DriveFileFieldType.WITH_PERMISSIONS
+            if include_permissions or self.exclude_domain_link_only
+            else DriveFileFieldType.STANDARD
+        )
+        batch_result = get_files_by_web_view_links_batch(service, doc_ids, field_type)
+
+        for doc_id, error in batch_result.errors.items():
+            yield ConnectorFailure(
+                failed_document=DocumentFailure(
+                    document_id=doc_id,
+                    document_link=doc_id,
+                ),
+                failure_message=f"Failed to retrieve file during error resolution: {error}",
+                exception=error,
+            )
+
+        permission_sync_context = (
+            PermissionSyncContext(
+                primary_admin_email=self.primary_admin_email,
+                google_domain=self.google_domain,
+            )
+            if include_permissions
+            else None
+        )
+
+        retrieved_files = [
+            RetrievedDriveFile(
+                drive_file=file,
+                user_email=self.primary_admin_email,
+                completion_stage=DriveRetrievalStage.DONE,
+            )
+            for file in batch_result.files.values()
+        ]
+
+        yield from self._get_new_ancestors_for_files(
+            files=retrieved_files,
+            seen_hierarchy_node_raw_ids=ThreadSafeSet(),
+            fully_walked_hierarchy_node_raw_ids=ThreadSafeSet(),
+            permission_sync_context=permission_sync_context,
+            add_prefix=True,
+        )
+
+        func_with_args = [
+            (
+                self._convert_retrieved_file_to_document,
+                (rf, permission_sync_context),
+            )
+            for rf in retrieved_files
+        ]
+        results = cast(
+            list[Document | ConnectorFailure | None],
+            run_functions_tuples_in_parallel(func_with_args, max_workers=8),
+        )
+        for result in results:
+            if result is not None:
+                yield result
+
     def _extract_slim_docs_from_google_drive(
         self,
         checkpoint: GoogleDriveCheckpoint,

backend/onyx/connectors/google_drive/file_retrieval.py

@@ -9,6 +9,7 @@ from urllib.parse import urlparse
 
 from googleapiclient.discovery import Resource  # type: ignore
 from googleapiclient.errors import HttpError  # type: ignore
+from googleapiclient.http import BatchHttpRequest  # type: ignore
 
 from onyx.access.models import ExternalAccess
 from onyx.connectors.google_drive.constants import DRIVE_FOLDER_TYPE
@@ -60,6 +61,8 @@ SLIM_FILE_FIELDS = (
 )
 FOLDER_FIELDS = "nextPageToken, files(id, name, permissions, modifiedTime, webViewLink, shortcutDetails)"
 
+MAX_BATCH_SIZE = 100
+
 HIERARCHY_FIELDS = "id, name, parents, webViewLink, mimeType, driveId"
 
 HIERARCHY_FIELDS_WITH_PERMISSIONS = (
@@ -216,7 +219,7 @@ def get_external_access_for_folder(
 
 
 def _get_fields_for_file_type(field_type: DriveFileFieldType) -> str:
-    """Get the appropriate fields string based on the field type enum"""
+    """Get the appropriate fields string for files().list() based on the field type enum."""
     if field_type == DriveFileFieldType.SLIM:
         return SLIM_FILE_FIELDS
     elif field_type == DriveFileFieldType.WITH_PERMISSIONS:
@@ -225,6 +228,25 @@ def _get_fields_for_file_type(field_type: DriveFileFieldType) -> str:
         return FILE_FIELDS
 
 
+def _extract_single_file_fields(list_fields: str) -> str:
+    """Convert a files().list() fields string to one suitable for files().get().
+
+    List fields look like "nextPageToken, files(field1, field2, ...)"
+    Single-file fields should be just "field1, field2, ..."
+    """
+    start = list_fields.find("files(")
+    if start == -1:
+        return list_fields
+    inner_start = start + len("files(")
+    inner_end = list_fields.rfind(")")
+    return list_fields[inner_start:inner_end]
+
+
+def _get_single_file_fields(field_type: DriveFileFieldType) -> str:
+    """Get the appropriate fields string for files().get() based on the field type enum."""
+    return _extract_single_file_fields(_get_fields_for_file_type(field_type))
+
+
 def _get_files_in_parent(
     service: Resource,
     parent_id: str,
@@ -536,3 +558,74 @@ def get_file_by_web_view_link(
         )
         .execute()
     )
+
+
+class BatchRetrievalResult:
+    """Result of a batch file retrieval, separating successes from errors."""
+
+    def __init__(self) -> None:
+        self.files: dict[str, GoogleDriveFileType] = {}
+        self.errors: dict[str, Exception] = {}
+
+
+def get_files_by_web_view_links_batch(
+    service: GoogleDriveService,
+    web_view_links: list[str],
+    field_type: DriveFileFieldType,
+) -> BatchRetrievalResult:
+    """Retrieve multiple Google Drive files by webViewLink using the batch API.
+
+    Returns a BatchRetrievalResult containing successful file retrievals
+    and errors for any files that could not be fetched.
+    Automatically splits into chunks of MAX_BATCH_SIZE.
+    """
+    fields = _get_single_file_fields(field_type)
+    if len(web_view_links) <= MAX_BATCH_SIZE:
+        return _get_files_by_web_view_links_batch(service, web_view_links, fields)
+
+    combined = BatchRetrievalResult()
+    for i in range(0, len(web_view_links), MAX_BATCH_SIZE):
+        chunk = web_view_links[i : i + MAX_BATCH_SIZE]
+        chunk_result = _get_files_by_web_view_links_batch(service, chunk, fields)
+        combined.files.update(chunk_result.files)
+        combined.errors.update(chunk_result.errors)
+    return combined
+
+
+def _get_files_by_web_view_links_batch(
+    service: GoogleDriveService,
+    web_view_links: list[str],
+    fields: str,
+) -> BatchRetrievalResult:
+    """Single-batch implementation."""
+
+    result = BatchRetrievalResult()
+
+    def callback(
+        request_id: str,
+        response: GoogleDriveFileType,
+        exception: Exception | None,
+    ) -> None:
+        if exception:
+            logger.warning(f"Error retrieving file {request_id}: {exception}")
+            result.errors[request_id] = exception
+        else:
+            result.files[request_id] = response
+
+    batch = cast(BatchHttpRequest, service.new_batch_http_request(callback=callback))
+
+    for web_view_link in web_view_links:
+        try:
+            file_id = _extract_file_id_from_web_view_link(web_view_link)
+            request = service.files().get(
+                fileId=file_id,
+                supportsAllDrives=True,
+                fields=fields,
+            )
+            batch.add(request, request_id=web_view_link)
+        except ValueError as e:
+            logger.warning(f"Failed to extract file ID from {web_view_link}: {e}")
+            result.errors[web_view_link] = e
+
+    batch.execute()
+    return result

backend/onyx/connectors/interfaces.py

@@ -298,6 +298,22 @@ class CheckpointedConnectorWithPermSync(CheckpointedConnector[CT]):
         raise NotImplementedError
 
 
+class Resolver(BaseConnector):
+    @abc.abstractmethod
+    def resolve_errors(
+        self,
+        errors: list[ConnectorFailure],
+        include_permissions: bool = False,
+    ) -> Generator[Document | ConnectorFailure | HierarchyNode, None, None]:
+        """Attempts to yield back ALL the documents described by the errors, no checkpointing.
+
+        Caller's responsibility is to delete the old ConnectorFailures and replace with the new ones.
+        If include_permissions is True, the documents will have permissions synced.
+        May also yield HierarchyNode objects for ancestor folders of resolved documents.
+        """
+        raise NotImplementedError
+
+
 class HierarchyConnector(BaseConnector):
     @abc.abstractmethod
     def load_hierarchy(

backend/onyx/connectors/jira/connector.py

@@ -60,8 +60,10 @@ logger = setup_logger()
 
 ONE_HOUR = 3600
 
-_MAX_RESULTS_FETCH_IDS = 5000  # 5000
+_MAX_RESULTS_FETCH_IDS = 5000
 _JIRA_FULL_PAGE_SIZE = 50
+# https://developer.atlassian.com/cloud/jira/platform/rest/v3/api-group-issues/
+_JIRA_BULK_FETCH_LIMIT = 100
 
 # Constants for Jira field names
 _FIELD_REPORTER = "reporter"
@@ -255,15 +257,13 @@ def _bulk_fetch_request(
     return resp.json()["issues"]
 
 
-def bulk_fetch_issues(
-    jira_client: JIRA, issue_ids: list[str], fields: str | None = None
-) -> list[Issue]:
-    # TODO(evan): move away from this jira library if they continue to not support
-    # the endpoints we need. Using private fields is not ideal, but
-    # is likely fine for now since we pin the library version
-
+def _bulk_fetch_batch(
+    jira_client: JIRA, issue_ids: list[str], fields: str | None
+) -> list[dict[str, Any]]:
+    """Fetch a single batch (must be <= _JIRA_BULK_FETCH_LIMIT).
+    On JSONDecodeError, recursively bisects until it succeeds or reaches size 1."""
     try:
-        raw_issues = _bulk_fetch_request(jira_client, issue_ids, fields)
+        return _bulk_fetch_request(jira_client, issue_ids, fields)
     except requests.exceptions.JSONDecodeError:
         if len(issue_ids) <= 1:
             logger.exception(
@@ -277,12 +277,25 @@ def bulk_fetch_issues(
             f"Jira bulk-fetch JSON decode failed for batch of {len(issue_ids)} issues. "
             f"Splitting into sub-batches of {mid} and {len(issue_ids) - mid}."
         )
-        left = bulk_fetch_issues(jira_client, issue_ids[:mid], fields)
-        right = bulk_fetch_issues(jira_client, issue_ids[mid:], fields)
+        left = _bulk_fetch_batch(jira_client, issue_ids[:mid], fields)
+        right = _bulk_fetch_batch(jira_client, issue_ids[mid:], fields)
         return left + right
-    except Exception as e:
-        logger.error(f"Error fetching issues: {e}")
-        raise
+
+
+def bulk_fetch_issues(
+    jira_client: JIRA, issue_ids: list[str], fields: str | None = None
+) -> list[Issue]:
+    # TODO(evan): move away from this jira library if they continue to not support
+    # the endpoints we need. Using private fields is not ideal, but
+    # is likely fine for now since we pin the library version
+
+    raw_issues: list[dict[str, Any]] = []
+    for batch in chunked(issue_ids, _JIRA_BULK_FETCH_LIMIT):
+        try:
+            raw_issues.extend(_bulk_fetch_batch(jira_client, list(batch), fields))
+        except Exception as e:
+            logger.error(f"Error fetching issues: {e}")
+            raise
 
     return [
         Issue(jira_client._options, jira_client._session, raw=issue)

backend/onyx/context/search/federated/models.py

@@ -1,3 +1,4 @@
+from dataclasses import dataclass
 from datetime import datetime
 from typing import TypedDict
 
@@ -6,6 +7,14 @@ from pydantic import BaseModel
 from onyx.onyxbot.slack.models import ChannelType
 
 
+@dataclass(frozen=True)
+class DirectThreadFetch:
+    """Request to fetch a Slack thread directly by channel and timestamp."""
+
+    channel_id: str
+    thread_ts: str
+
+
 class ChannelMetadata(TypedDict):
     """Type definition for cached channel metadata."""
 

backend/onyx/context/search/federated/slack_search.py

@@ -19,6 +19,7 @@ from onyx.configs.chat_configs import DOC_TIME_DECAY
 from onyx.connectors.models import IndexingDocument
 from onyx.connectors.models import TextSection
 from onyx.context.search.federated.models import ChannelMetadata
+from onyx.context.search.federated.models import DirectThreadFetch
 from onyx.context.search.federated.models import SlackMessage
 from onyx.context.search.federated.slack_search_utils import ALL_CHANNEL_TYPES
 from onyx.context.search.federated.slack_search_utils import build_channel_query_filter
@@ -49,7 +50,6 @@ from onyx.server.federated.models import FederatedConnectorDetail
 from onyx.utils.logger import setup_logger
 from onyx.utils.threadpool_concurrency import run_functions_tuples_in_parallel
 from onyx.utils.timing import log_function_time
-from shared_configs.configs import DOC_EMBEDDING_CONTEXT_SIZE
 
 logger = setup_logger()
 
@@ -58,7 +58,6 @@ HIGHLIGHT_END_CHAR = "\ue001"
 
 CHANNEL_METADATA_CACHE_TTL = 60 * 60 * 24  # 24 hours
 USER_PROFILE_CACHE_TTL = 60 * 60 * 24  # 24 hours
-SLACK_THREAD_CONTEXT_WINDOW = 3  # Number of messages before matched message to include
 CHANNEL_METADATA_MAX_RETRIES = 3  # Maximum retry attempts for channel metadata fetching
 CHANNEL_METADATA_RETRY_DELAY = 1  # Initial retry delay in seconds (exponential backoff)
 
@@ -421,6 +420,94 @@ class SlackQueryResult(BaseModel):
     filtered_channels: list[str]  # Channels filtered out during this query
 
 
+def _fetch_thread_from_url(
+    thread_fetch: DirectThreadFetch,
+    access_token: str,
+    channel_metadata_dict: dict[str, ChannelMetadata] | None = None,
+) -> SlackQueryResult:
+    """Fetch a thread directly from a Slack URL via conversations.replies."""
+    channel_id = thread_fetch.channel_id
+    thread_ts = thread_fetch.thread_ts
+
+    slack_client = WebClient(token=access_token)
+    try:
+        response = slack_client.conversations_replies(
+            channel=channel_id,
+            ts=thread_ts,
+        )
+        response.validate()
+        messages: list[dict[str, Any]] = response.get("messages", [])
+    except SlackApiError as e:
+        logger.warning(
+            f"Failed to fetch thread from URL (channel={channel_id}, ts={thread_ts}): {e}"
+        )
+        return SlackQueryResult(messages=[], filtered_channels=[])
+
+    if not messages:
+        logger.warning(
+            f"No messages found for URL override (channel={channel_id}, ts={thread_ts})"
+        )
+        return SlackQueryResult(messages=[], filtered_channels=[])
+
+    # Build thread text from all messages
+    thread_text = _build_thread_text(messages, access_token, None, slack_client)
+
+    # Get channel name from metadata cache or API
+    channel_name = "unknown"
+    if channel_metadata_dict and channel_id in channel_metadata_dict:
+        channel_name = channel_metadata_dict[channel_id].get("name", "unknown")
+    else:
+        try:
+            ch_response = slack_client.conversations_info(channel=channel_id)
+            ch_response.validate()
+            channel_info: dict[str, Any] = ch_response.get("channel", {})
+            channel_name = channel_info.get("name", "unknown")
+        except SlackApiError:
+            pass
+
+    # Build the SlackMessage
+    parent_msg = messages[0]
+    message_ts = parent_msg.get("ts", thread_ts)
+    username = parent_msg.get("user", "unknown_user")
+    parent_text = parent_msg.get("text", "")
+    snippet = (
+        parent_text[:50].rstrip() + "..." if len(parent_text) > 50 else parent_text
+    ).replace("\n", " ")
+
+    doc_time = datetime.fromtimestamp(float(message_ts))
+    decay_factor = DOC_TIME_DECAY
+    doc_age_years = (datetime.now() - doc_time).total_seconds() / (365 * 24 * 60 * 60)
+    recency_bias = max(1 / (1 + decay_factor * doc_age_years), 0.75)
+
+    permalink = (
+        f"https://slack.com/archives/{channel_id}/p{message_ts.replace('.', '')}"
+    )
+
+    slack_message = SlackMessage(
+        document_id=f"{channel_id}_{message_ts}",
+        channel_id=channel_id,
+        message_id=message_ts,
+        thread_id=None,  # Prevent double-enrichment in thread context fetch
+        link=permalink,
+        metadata={
+            "channel": channel_name,
+            "time": doc_time.isoformat(),
+        },
+        timestamp=doc_time,
+        recency_bias=recency_bias,
+        semantic_identifier=f"{username} in #{channel_name}: {snippet}",
+        text=thread_text,
+        highlighted_texts=set(),
+        slack_score=100000.0,  # High priority — user explicitly asked for this thread
+    )
+
+    logger.info(
+        f"URL override: fetched thread from channel={channel_id}, ts={thread_ts}, {len(messages)} messages"
+    )
+
+    return SlackQueryResult(messages=[slack_message], filtered_channels=[])
+
+
 def query_slack(
     query_string: str,
     access_token: str,
@@ -432,7 +519,6 @@ def query_slack(
     available_channels: list[str] | None = None,
     channel_metadata_dict: dict[str, ChannelMetadata] | None = None,
 ) -> SlackQueryResult:
-
     # Check if query has channel override (user specified channels in query)
     has_channel_override = query_string.startswith("__CHANNEL_OVERRIDE__")
 
@@ -662,7 +748,6 @@ def _fetch_thread_context(
     """
     channel_id = message.channel_id
     thread_id = message.thread_id
-    message_id = message.message_id
 
     # If not a thread, return original text as success
     if thread_id is None:
@@ -695,62 +780,37 @@ def _fetch_thread_context(
     if len(messages) <= 1:
         return ThreadContextResult.success(message.text)
 
-    # Build thread text from thread starter + context window around matched message
-    thread_text = _build_thread_text(
-        messages, message_id, thread_id, access_token, team_id, slack_client
-    )
+    # Build thread text from thread starter + all replies
+    thread_text = _build_thread_text(messages, access_token, team_id, slack_client)
     return ThreadContextResult.success(thread_text)
 
 
 def _build_thread_text(
     messages: list[dict[str, Any]],
-    message_id: str,
-    thread_id: str,
     access_token: str,
     team_id: str | None,
     slack_client: WebClient,
 ) -> str:
-    """Build the thread text from messages."""
+    """Build thread text including all replies.
+
+    Includes the thread parent message followed by all replies in order.
+    """
     msg_text = messages[0].get("text", "")
     msg_sender = messages[0].get("user", "")
     thread_text = f"<@{msg_sender}>: {msg_text}"
 
+    # All messages after index 0 are replies
+    replies = messages[1:]
+    if not replies:
+        return thread_text
+
+    logger.debug(f"Thread {messages[0].get('ts')}: {len(replies)} replies included")
     thread_text += "\n\nReplies:"
-    if thread_id == message_id:
-        message_id_idx = 0
-    else:
-        message_id_idx = next(
-            (i for i, msg in enumerate(messages) if msg.get("ts") == message_id), 0
-        )
-        if not message_id_idx:
-            return thread_text
 
-        start_idx = max(1, message_id_idx - SLACK_THREAD_CONTEXT_WINDOW)
-
-        if start_idx > 1:
-            thread_text += "\n..."
-
-        for i in range(start_idx, message_id_idx):
-            msg_text = messages[i].get("text", "")
-            msg_sender = messages[i].get("user", "")
-            thread_text += f"\n\n<@{msg_sender}>: {msg_text}"
-
-        msg_text = messages[message_id_idx].get("text", "")
-        msg_sender = messages[message_id_idx].get("user", "")
-        thread_text += f"\n\n<@{msg_sender}>: {msg_text}"
-
-    # Add following replies
-    len_replies = 0
-    for msg in messages[message_id_idx + 1 :]:
+    for msg in replies:
         msg_text = msg.get("text", "")
         msg_sender = msg.get("user", "")
-        reply = f"\n\n<@{msg_sender}>: {msg_text}"
-        thread_text += reply
-
-        len_replies += len(reply)
-        if len_replies >= DOC_EMBEDDING_CONTEXT_SIZE * 4:
-            thread_text += "\n..."
-            break
+        thread_text += f"\n\n<@{msg_sender}>: {msg_text}"
 
     # Replace user IDs with names using cached lookups
     userids: set[str] = set(re.findall(r"<@([A-Z0-9]+)>", thread_text))
@@ -976,7 +1036,16 @@ def slack_retrieval(
 
     # Query slack with entity filtering
     llm = get_default_llm()
-    query_strings = build_slack_queries(query, llm, entities, available_channels)
+    query_items = build_slack_queries(query, llm, entities, available_channels)
+
+    # Partition into direct thread fetches and search query strings
+    direct_fetches: list[DirectThreadFetch] = []
+    query_strings: list[str] = []
+    for item in query_items:
+        if isinstance(item, DirectThreadFetch):
+            direct_fetches.append(item)
+        else:
+            query_strings.append(item)
 
     # Determine filtering based on entities OR context (bot)
     include_dm = False
@@ -993,8 +1062,16 @@ def slack_retrieval(
                 f"Private channel context: will only allow messages from {allowed_private_channel} + public channels"
             )
 
-    # Build search tasks
-    search_tasks = [
+    # Build search tasks — direct thread fetches + keyword searches
+    search_tasks: list[tuple] = [
+        (
+            _fetch_thread_from_url,
+            (fetch, access_token, channel_metadata_dict),
+        )
+        for fetch in direct_fetches
+    ]
+
+    search_tasks.extend(
         (
             query_slack,
             (
@@ -1010,7 +1087,7 @@ def slack_retrieval(
             ),
         )
         for query_string in query_strings
-    ]
+    )
 
     # If include_dm is True AND we're not already searching all channels,
     # add additional searches without channel filters.

backend/onyx/context/search/federated/slack_search_utils.py

@@ -10,6 +10,7 @@ from pydantic import ValidationError
 
 from onyx.configs.app_configs import MAX_SLACK_QUERY_EXPANSIONS
 from onyx.context.search.federated.models import ChannelMetadata
+from onyx.context.search.federated.models import DirectThreadFetch
 from onyx.context.search.models import ChunkIndexRequest
 from onyx.federated_connectors.slack.models import SlackEntities
 from onyx.llm.interfaces import LLM
@@ -638,12 +639,38 @@ def expand_query_with_llm(query_text: str, llm: LLM) -> list[str]:
         return [query_text]
 
 
+SLACK_URL_PATTERN = re.compile(
+    r"https?://[a-z0-9-]+\.slack\.com/archives/([A-Z0-9]+)/p(\d{16})"
+)
+
+
+def extract_slack_message_urls(
+    query_text: str,
+) -> list[tuple[str, str]]:
+    """Extract Slack message URLs from query text.
+
+    Parses URLs like:
+      https://onyx-company.slack.com/archives/C097NBWMY8Y/p1775491616524769
+
+    Returns list of (channel_id, thread_ts) tuples.
+    The 16-digit timestamp is converted to Slack ts format (with dot).
+    """
+    results = []
+    for match in SLACK_URL_PATTERN.finditer(query_text):
+        channel_id = match.group(1)
+        raw_ts = match.group(2)
+        # Convert p1775491616524769 -> 1775491616.524769
+        thread_ts = f"{raw_ts[:10]}.{raw_ts[10:]}"
+        results.append((channel_id, thread_ts))
+    return results
+
+
 def build_slack_queries(
     query: ChunkIndexRequest,
     llm: LLM,
     entities: dict[str, Any] | None = None,
     available_channels: list[str] | None = None,
-) -> list[str]:
+) -> list[str | DirectThreadFetch]:
     """Build Slack query strings with date filtering and query expansion."""
     default_search_days = 30
     if entities:
@@ -668,6 +695,15 @@ def build_slack_queries(
             cutoff_date = datetime.now(timezone.utc) - timedelta(days=days_back)
             time_filter = f" after:{cutoff_date.strftime('%Y-%m-%d')}"
 
+    # Check for Slack message URLs — if found, add direct fetch requests
+    url_fetches: list[DirectThreadFetch] = []
+    slack_urls = extract_slack_message_urls(query.query)
+    for channel_id, thread_ts in slack_urls:
+        url_fetches.append(
+            DirectThreadFetch(channel_id=channel_id, thread_ts=thread_ts)
+        )
+        logger.info(f"Detected Slack URL: channel={channel_id}, ts={thread_ts}")
+
     # ALWAYS extract channel references from the query (not just for recency queries)
     channel_references = extract_channel_references_from_query(query.query)
 
@@ -684,7 +720,9 @@ def build_slack_queries(
 
             # If valid channels detected, use ONLY those channels with NO keywords
             # Return query with ONLY time filter + channel filter (no keywords)
-            return [build_channel_override_query(channel_references, time_filter)]
+            return url_fetches + [
+                build_channel_override_query(channel_references, time_filter)
+            ]
         except ValueError as e:
             # If validation fails, log the error and continue with normal flow
             logger.warning(f"Channel reference validation failed: {e}")
@@ -702,7 +740,8 @@ def build_slack_queries(
         rephrased_queries = expand_query_with_llm(query.query, llm)
 
     # Build final query strings with time filters
-    return [
+    search_queries = [
         rephrased_query.strip() + time_filter
         for rephrased_query in rephrased_queries[:MAX_SLACK_QUERY_EXPANSIONS]
     ]
+    return url_fetches + search_queries

backend/onyx/db/api_key.py

@@ -110,8 +110,8 @@ def insert_api_key(
 
     # Assign the API key virtual user to the appropriate default group
     # before commit so everything is atomic.
-    # LIMITED role service accounts should have no group membership.
-    if api_key_args.role != UserRole.LIMITED:
+    # Only ADMIN and BASIC roles get default group membership.
+    if api_key_args.role in (UserRole.ADMIN, UserRole.BASIC):
         assign_user_to_default_groups__no_commit(
             db_session,
             api_key_user_row,
@@ -161,8 +161,8 @@ def update_api_key(
         )
         db_session.execute(delete_stmt)
 
-        # Re-assign to the correct default group (skip for LIMITED).
-        if api_key_args.role != UserRole.LIMITED:
+        # Re-assign to the correct default group (only for ADMIN/BASIC).
+        if api_key_args.role in (UserRole.ADMIN, UserRole.BASIC):
             assign_user_to_default_groups__no_commit(
                 db_session,
                 api_key_user,

backend/onyx/db/federated.py

@@ -8,6 +8,8 @@ from sqlalchemy.orm import selectinload
 from sqlalchemy.orm import Session
 
 from onyx.configs.constants import FederatedConnectorSource
+from onyx.configs.constants import MASK_CREDENTIAL_CHAR
+from onyx.configs.constants import MASK_CREDENTIAL_LONG_RE
 from onyx.db.engine.sql_engine import get_session_with_current_tenant
 from onyx.db.models import DocumentSet
 from onyx.db.models import FederatedConnector
@@ -45,6 +47,23 @@ def fetch_all_federated_connectors_parallel() -> list[FederatedConnector]:
         return fetch_all_federated_connectors(db_session)
 
 
+def _reject_masked_credentials(credentials: dict[str, Any]) -> None:
+    """Raise if any credential string value contains mask placeholder characters.
+
+    mask_string() has two output formats:
+    - Short strings (< 14 chars): "••••••••••••" (U+2022 BULLET)
+    - Long strings (>= 14 chars): "abcd...wxyz" (first4 + "..." + last4)
+    Both must be rejected.
+    """
+    for key, val in credentials.items():
+        if isinstance(val, str) and (
+            MASK_CREDENTIAL_CHAR in val or MASK_CREDENTIAL_LONG_RE.match(val)
+        ):
+            raise ValueError(
+                f"Credential field '{key}' contains masked placeholder characters. Please provide the actual credential value."
+            )
+
+
 def validate_federated_connector_credentials(
     source: FederatedConnectorSource,
     credentials: dict[str, Any],
@@ -66,6 +85,8 @@ def create_federated_connector(
     config: dict[str, Any] | None = None,
 ) -> FederatedConnector:
     """Create a new federated connector with credential and config validation."""
+    _reject_masked_credentials(credentials)
+
     # Validate credentials before creating
     if not validate_federated_connector_credentials(source, credentials):
         raise ValueError(
@@ -277,6 +298,8 @@ def update_federated_connector(
     )
 
     if credentials is not None:
+        _reject_masked_credentials(credentials)
+
         # Validate credentials before updating
         if not validate_federated_connector_credentials(
             federated_connector.source, credentials

backend/onyx/db/llm.py

@@ -236,14 +236,15 @@ def upsert_llm_provider(
         db_session.add(existing_llm_provider)
 
     # Filter out empty strings and None values from custom_config to allow
-    # providers like Bedrock to fall back to IAM roles when credentials are not provided
+    # providers like Bedrock to fall back to IAM roles when credentials are not provided.
+    # NOTE: An empty dict ({}) is preserved as-is — it signals that the provider was
+    # created via the custom modal and must be reopened with CustomModal, not a
+    # provider-specific modal. Only None means "no custom config at all".
     custom_config = llm_provider_upsert_request.custom_config
     if custom_config:
         custom_config = {
             k: v for k, v in custom_config.items() if v is not None and v.strip() != ""
         }
-        # Set to None if the dict is empty after filtering
-        custom_config = custom_config or None
 
     api_base = llm_provider_upsert_request.api_base or None
     existing_llm_provider.provider = llm_provider_upsert_request.provider
@@ -303,16 +304,7 @@ def upsert_llm_provider(
         ).delete(synchronize_session="fetch")
         db_session.flush()
 
-    # Import here to avoid circular imports
-    from onyx.llm.utils import get_max_input_tokens
-
     for model_config in llm_provider_upsert_request.model_configurations:
-        max_input_tokens = model_config.max_input_tokens
-        if max_input_tokens is None:
-            max_input_tokens = get_max_input_tokens(
-                model_name=model_config.name,
-                model_provider=llm_provider_upsert_request.provider,
-            )
 
         supported_flows = [LLMModelFlowType.CHAT]
         if model_config.supports_image_input:
@@ -325,7 +317,7 @@ def upsert_llm_provider(
                 model_configuration_id=existing.id,
                 supported_flows=supported_flows,
                 is_visible=model_config.is_visible,
-                max_input_tokens=max_input_tokens,
+                max_input_tokens=model_config.max_input_tokens,
                 display_name=model_config.display_name,
             )
         else:
@@ -335,7 +327,7 @@ def upsert_llm_provider(
                 model_name=model_config.name,
                 supported_flows=supported_flows,
                 is_visible=model_config.is_visible,
-                max_input_tokens=max_input_tokens,
+                max_input_tokens=model_config.max_input_tokens,
                 display_name=model_config.display_name,
             )
 

backend/onyx/db/user_preferences.py

@@ -20,6 +20,7 @@ from onyx.db.models import User__UserGroup
 from onyx.db.models import UserGroup
 from onyx.db.permissions import recompute_user_permissions__no_commit
 from onyx.db.users import assign_user_to_default_groups__no_commit
+from onyx.db.users import is_limited_user
 from onyx.server.manage.models import MemoryItem
 from onyx.server.manage.models import UserSpecificAssistantPreference
 from onyx.utils.logger import setup_logger
@@ -65,8 +66,11 @@ def update_user_role(
             )
         )
 
-        # Re-assign to the correct default group (skip for LIMITED).
-        if new_role != UserRole.LIMITED:
+        # Re-assign to the correct default group.
+        # assign_user_to_default_groups__no_commit internally skips
+        # ANONYMOUS, BOT, and EXT_PERM_USER account types.
+        # Also skip limited users (no group assignment).
+        if not is_limited_user(user):
             assign_user_to_default_groups__no_commit(
                 db_session,
                 user,
@@ -98,7 +102,10 @@ def activate_user(
     created while inactive or deactivated before the backfill migration.
     """
     user.is_active = True
-    if user.role != UserRole.LIMITED:
+    # assign_user_to_default_groups__no_commit internally skips
+    # ANONYMOUS, BOT, and EXT_PERM_USER account types.
+    # Also skip limited users (no group assignment).
+    if not is_limited_user(user):
         assign_user_to_default_groups__no_commit(
             db_session, user, is_admin=(user.role == UserRole.ADMIN)
         )

backend/onyx/db/users.py

@@ -34,9 +34,27 @@ from onyx.utils.variable_functionality import fetch_ee_implementation_or_noop
 logger = setup_logger()
 
 
+def is_limited_user(user: User) -> bool:
+    """Check if a user is effectively limited — i.e. should be denied
+    access by ``current_user`` and should not receive default-group
+    membership.
+
+    A user is limited when they are:
+    * an anonymous user, or
+    * a service account with no effective permissions (no group membership).
+    """
+    if user.account_type == AccountType.ANONYMOUS:
+        return True
+    if (
+        user.account_type == AccountType.SERVICE_ACCOUNT
+        and not user.effective_permissions
+    ):
+        return True
+    return False
+
+
 def validate_user_role_update(
     requested_role: UserRole,
-    current_role: UserRole,
     current_account_type: AccountType,
     explicit_override: bool = False,
 ) -> None:
@@ -50,7 +68,7 @@ def validate_user_role_update(
     - requested role is a limited user
     - current account type is BOT (slack user)
     - current account type is EXT_PERM_USER
-    - current role is a limited user
+    - current account type is ANONYMOUS or SERVICE_ACCOUNT
     """
 
     if current_account_type == AccountType.BOT:
@@ -65,10 +83,10 @@ def validate_user_role_update(
             detail="To change an External Permissioned User's role, they must first login to Onyx via the web app.",
         )
 
-    if current_role == UserRole.LIMITED:
+    if current_account_type in (AccountType.ANONYMOUS, AccountType.SERVICE_ACCOUNT):
         raise HTTPException(
             status_code=400,
-            detail="To change a Limited User's role, they must first login to Onyx via the web app.",
+            detail="Cannot change the role of an anonymous or service account user.",
         )
 
     if explicit_override:

backend/onyx/file_processing/extract_file_text.py

@@ -52,9 +52,21 @@ KNOWN_OPENPYXL_BUGS = [
 
 def get_markitdown_converter() -> "MarkItDown":
     global _MARKITDOWN_CONVERTER
-    from markitdown import MarkItDown
 
     if _MARKITDOWN_CONVERTER is None:
+        from markitdown import MarkItDown
+
+        # Patch this function to effectively no-op because we were seeing this
+        # module take an inordinate amount of time to convert charts to markdown,
+        # making some powerpoint files with many or complicated charts nearly
+        # unindexable.
+        from markitdown.converters._pptx_converter import PptxConverter
+
+        setattr(
+            PptxConverter,
+            "_convert_chart_to_markdown",
+            lambda self, chart: "\n\n[chart omitted]\n\n",  # noqa: ARG005
+        )
         _MARKITDOWN_CONVERTER = MarkItDown(enable_plugins=False)
     return _MARKITDOWN_CONVERTER
 
@@ -205,18 +217,26 @@ def read_pdf_file(
     try:
         pdf_reader = PdfReader(file)
 
-        if pdf_reader.is_encrypted and pdf_pass is not None:
+        if pdf_reader.is_encrypted:
+            # Try the explicit password first, then fall back to an empty
+            # string.  Owner-password-only PDFs (permission restrictions but
+            # no open password) decrypt successfully with "".
+            # See https://github.com/onyx-dot-app/onyx/issues/9754
+            passwords = [p for p in [pdf_pass, ""] if p is not None]
             decrypt_success = False
-            try:
-                decrypt_success = pdf_reader.decrypt(pdf_pass) != 0
-            except Exception:
-                logger.error("Unable to decrypt pdf")
+            for pw in passwords:
+                try:
+                    if pdf_reader.decrypt(pw) != 0:
+                        decrypt_success = True
+                        break
+                except Exception:
+                    pass
 
             if not decrypt_success:
+                logger.error(
+                    "Encrypted PDF could not be decrypted, returning empty text."
+                )
                 return "", metadata, []
-        elif pdf_reader.is_encrypted:
-            logger.warning("No Password for an encrypted PDF, returning empty text.")
-            return "", metadata, []
 
         # Basic PDF metadata
         if pdf_reader.metadata is not None:

backend/onyx/file_processing/password_validation.py

@@ -33,8 +33,20 @@ def is_pdf_protected(file: IO[Any]) -> bool:
 
     with preserve_position(file):
         reader = PdfReader(file)
+        if not reader.is_encrypted:
+            return False
 
-    return bool(reader.is_encrypted)
+        # PDFs with only an owner password (permission restrictions like
+        # print/copy disabled) use an empty user password — any viewer can open
+        # them without prompting.  decrypt("") returns 0 only when a real user
+        # password is required.  See https://github.com/onyx-dot-app/onyx/issues/9754
+        try:
+            return reader.decrypt("") == 0
+        except Exception:
+            logger.exception(
+                "Failed to evaluate PDF encryption; treating as password protected"
+            )
+            return True
 
 
 def is_docx_protected(file: IO[Any]) -> bool:

backend/onyx/indexing/chunker.py

@@ -1,5 +1,3 @@
-from typing import cast
-
 from chonkie import SentenceChunker
 
 from onyx.configs.app_configs import AVERAGE_SUMMARY_EMBEDDINGS
@@ -15,17 +13,15 @@ from onyx.configs.constants import SECTION_SEPARATOR
 from onyx.connectors.cross_connector_utils.miscellaneous_utils import (
     get_metadata_keys_to_ignore,
 )
+from onyx.indexing.document_chunker.document_chunker import DocumentChunker
+from onyx.indexing.document_chunker.section_chunker import extract_blurb
 from onyx.connectors.models import IndexingDocument
-from onyx.connectors.models import Section
 from onyx.indexing.indexing_heartbeat import IndexingHeartbeatInterface
 from onyx.indexing.models import DocAwareChunk
 from onyx.llm.utils import MAX_CONTEXT_TOKENS
 from onyx.natural_language_processing.utils import BaseTokenizer
 from onyx.utils.logger import setup_logger
-from onyx.utils.text_processing import clean_text
-from onyx.utils.text_processing import shared_precompare_cleanup
 from shared_configs.configs import DOC_EMBEDDING_CONTEXT_SIZE
-from shared_configs.configs import STRICT_CHUNK_TOKEN_LIMIT
 
 # Not supporting overlaps, we need a clean combination of chunks and it is unclear if overlaps
 # actually help quality at all
@@ -154,9 +150,6 @@ class Chunker:
         self.tokenizer = tokenizer
         self.callback = callback
 
-        self.max_context = 0
-        self.prompt_tokens = 0
-
         # Create a token counter function that returns the count instead of the tokens
         def token_counter(text: str) -> int:
             return len(tokenizer.encode(text))
@@ -186,234 +179,12 @@ class Chunker:
             else None
         )
 
-    def _split_oversized_chunk(self, text: str, content_token_limit: int) -> list[str]:
-        """
-        Splits the text into smaller chunks based on token count to ensure
-        no chunk exceeds the content_token_limit.
-        """
-        tokens = self.tokenizer.tokenize(text)
-        chunks = []
-        start = 0
-        total_tokens = len(tokens)
-        while start < total_tokens:
-            end = min(start + content_token_limit, total_tokens)
-            token_chunk = tokens[start:end]
-            chunk_text = " ".join(token_chunk)
-            chunks.append(chunk_text)
-            start = end
-        return chunks
-
-    def _extract_blurb(self, text: str) -> str:
-        """
-        Extract a short blurb from the text (first chunk of size `blurb_size`).
-        """
-        # chunker is in `text` mode
-        texts = cast(list[str], self.blurb_splitter.chunk(text))
-        if not texts:
-            return ""
-        return texts[0]
-
-    def _get_mini_chunk_texts(self, chunk_text: str) -> list[str] | None:
-        """
-        For "multipass" mode: additional sub-chunks (mini-chunks) for use in certain embeddings.
-        """
-        if self.mini_chunk_splitter and chunk_text.strip():
-            # chunker is in `text` mode
-            return cast(list[str], self.mini_chunk_splitter.chunk(chunk_text))
-        return None
-
-    # ADDED: extra param image_url to store in the chunk
-    def _create_chunk(
-        self,
-        document: IndexingDocument,
-        chunks_list: list[DocAwareChunk],
-        text: str,
-        links: dict[int, str],
-        is_continuation: bool = False,
-        title_prefix: str = "",
-        metadata_suffix_semantic: str = "",
-        metadata_suffix_keyword: str = "",
-        image_file_id: str | None = None,
-    ) -> None:
-        """
-        Helper to create a new DocAwareChunk, append it to chunks_list.
-        """
-        new_chunk = DocAwareChunk(
-            source_document=document,
-            chunk_id=len(chunks_list),
-            blurb=self._extract_blurb(text),
-            content=text,
-            source_links=links or {0: ""},
-            image_file_id=image_file_id,
-            section_continuation=is_continuation,
-            title_prefix=title_prefix,
-            metadata_suffix_semantic=metadata_suffix_semantic,
-            metadata_suffix_keyword=metadata_suffix_keyword,
-            mini_chunk_texts=self._get_mini_chunk_texts(text),
-            large_chunk_id=None,
-            doc_summary="",
-            chunk_context="",
-            contextual_rag_reserved_tokens=0,  # set per-document in _handle_single_document
+        self._document_chunker = DocumentChunker(
+            tokenizer=tokenizer,
+            blurb_splitter=self.blurb_splitter,
+            chunk_splitter=self.chunk_splitter,
+            mini_chunk_splitter=self.mini_chunk_splitter,
         )
-        chunks_list.append(new_chunk)
-
-    def _chunk_document_with_sections(
-        self,
-        document: IndexingDocument,
-        sections: list[Section],
-        title_prefix: str,
-        metadata_suffix_semantic: str,
-        metadata_suffix_keyword: str,
-        content_token_limit: int,
-    ) -> list[DocAwareChunk]:
-        """
-        Loops through sections of the document, converting them into one or more chunks.
-        Works with processed sections that are base Section objects.
-        """
-        chunks: list[DocAwareChunk] = []
-        link_offsets: dict[int, str] = {}
-        chunk_text = ""
-
-        for section_idx, section in enumerate(sections):
-            # Get section text and other attributes
-            section_text = clean_text(str(section.text or ""))
-            section_link_text = section.link or ""
-            image_url = section.image_file_id
-
-            # If there is no useful content, skip
-            if not section_text and (not document.title or section_idx > 0):
-                logger.warning(
-                    f"Skipping empty or irrelevant section in doc {document.semantic_identifier}, link={section_link_text}"
-                )
-                continue
-
-            # CASE 1: If this section has an image, force a separate chunk
-            if image_url:
-                # First, if we have any partially built text chunk, finalize it
-                if chunk_text.strip():
-                    self._create_chunk(
-                        document,
-                        chunks,
-                        chunk_text,
-                        link_offsets,
-                        is_continuation=False,
-                        title_prefix=title_prefix,
-                        metadata_suffix_semantic=metadata_suffix_semantic,
-                        metadata_suffix_keyword=metadata_suffix_keyword,
-                    )
-                    chunk_text = ""
-                    link_offsets = {}
-
-                # Create a chunk specifically for this image section
-                # (Using the text summary that was generated during processing)
-                self._create_chunk(
-                    document,
-                    chunks,
-                    section_text,
-                    links={0: section_link_text} if section_link_text else {},
-                    image_file_id=image_url,
-                    title_prefix=title_prefix,
-                    metadata_suffix_semantic=metadata_suffix_semantic,
-                    metadata_suffix_keyword=metadata_suffix_keyword,
-                )
-                # Continue to next section
-                continue
-
-            # CASE 2: Normal text section
-            section_token_count = len(self.tokenizer.encode(section_text))
-
-            # If the section is large on its own, split it separately
-            if section_token_count > content_token_limit:
-                if chunk_text.strip():
-                    self._create_chunk(
-                        document,
-                        chunks,
-                        chunk_text,
-                        link_offsets,
-                        False,
-                        title_prefix,
-                        metadata_suffix_semantic,
-                        metadata_suffix_keyword,
-                    )
-                    chunk_text = ""
-                    link_offsets = {}
-
-                # chunker is in `text` mode
-                split_texts = cast(list[str], self.chunk_splitter.chunk(section_text))
-                for i, split_text in enumerate(split_texts):
-                    # If even the split_text is bigger than strict limit, further split
-                    if (
-                        STRICT_CHUNK_TOKEN_LIMIT
-                        and len(self.tokenizer.encode(split_text)) > content_token_limit
-                    ):
-                        smaller_chunks = self._split_oversized_chunk(
-                            split_text, content_token_limit
-                        )
-                        for j, small_chunk in enumerate(smaller_chunks):
-                            self._create_chunk(
-                                document,
-                                chunks,
-                                small_chunk,
-                                {0: section_link_text},
-                                is_continuation=(j != 0),
-                                title_prefix=title_prefix,
-                                metadata_suffix_semantic=metadata_suffix_semantic,
-                                metadata_suffix_keyword=metadata_suffix_keyword,
-                            )
-                    else:
-                        self._create_chunk(
-                            document,
-                            chunks,
-                            split_text,
-                            {0: section_link_text},
-                            is_continuation=(i != 0),
-                            title_prefix=title_prefix,
-                            metadata_suffix_semantic=metadata_suffix_semantic,
-                            metadata_suffix_keyword=metadata_suffix_keyword,
-                        )
-                continue
-
-            # If we can still fit this section into the current chunk, do so
-            current_token_count = len(self.tokenizer.encode(chunk_text))
-            current_offset = len(shared_precompare_cleanup(chunk_text))
-            next_section_tokens = (
-                len(self.tokenizer.encode(SECTION_SEPARATOR)) + section_token_count
-            )
-
-            if next_section_tokens + current_token_count <= content_token_limit:
-                if chunk_text:
-                    chunk_text += SECTION_SEPARATOR
-                chunk_text += section_text
-                link_offsets[current_offset] = section_link_text
-            else:
-                # finalize the existing chunk
-                self._create_chunk(
-                    document,
-                    chunks,
-                    chunk_text,
-                    link_offsets,
-                    False,
-                    title_prefix,
-                    metadata_suffix_semantic,
-                    metadata_suffix_keyword,
-                )
-                # start a new chunk
-                link_offsets = {0: section_link_text}
-                chunk_text = section_text
-
-        # finalize any leftover text chunk
-        if chunk_text.strip() or not chunks:
-            self._create_chunk(
-                document,
-                chunks,
-                chunk_text,
-                link_offsets or {0: ""},  # safe default
-                False,
-                title_prefix,
-                metadata_suffix_semantic,
-                metadata_suffix_keyword,
-            )
-        return chunks
 
     def _handle_single_document(
         self, document: IndexingDocument
@@ -423,7 +194,10 @@ class Chunker:
             logger.debug(f"Chunking {document.semantic_identifier}")
 
         # Title prep
-        title = self._extract_blurb(document.get_title_for_document_index() or "")
+        title = extract_blurb(
+            document.get_title_for_document_index() or "",
+            self.blurb_splitter,
+        )
         title_prefix = title + RETURN_SEPARATOR if title else ""
         title_tokens = len(self.tokenizer.encode(title_prefix))
 
@@ -491,7 +265,7 @@ class Chunker:
         # Use processed_sections if available (IndexingDocument), otherwise use original sections
         sections_to_chunk = document.processed_sections
 
-        normal_chunks = self._chunk_document_with_sections(
+        normal_chunks = self._document_chunker.chunk(
             document,
             sections_to_chunk,
             title_prefix,

backend/onyx/indexing/document_chunker/document_chunker.py

@@ -0,0 +1,107 @@
+from chonkie import SentenceChunker
+
+from onyx.connectors.models import IndexingDocument
+from onyx.connectors.models import Section
+from onyx.indexing.document_chunker.image_section_chunker import ImageChunker
+from onyx.indexing.document_chunker.section_chunker import AccumulatorState
+from onyx.indexing.document_chunker.section_chunker import ChunkPayload
+from onyx.indexing.document_chunker.section_chunker import SectionChunker
+from onyx.indexing.document_chunker.text_section_chunker import TextChunker
+from onyx.indexing.models import DocAwareChunk
+from onyx.natural_language_processing.utils import BaseTokenizer
+from onyx.utils.logger import setup_logger
+from onyx.utils.text_processing import clean_text
+
+logger = setup_logger()
+
+
+class DocumentChunker:
+    """Converts a document's processed sections into DocAwareChunks.
+
+    Drop-in replacement for `Chunker._chunk_document_with_sections`.
+    """
+
+    def __init__(
+        self,
+        tokenizer: BaseTokenizer,
+        blurb_splitter: SentenceChunker,
+        chunk_splitter: SentenceChunker,
+        mini_chunk_splitter: SentenceChunker | None = None,
+    ) -> None:
+        self.blurb_splitter = blurb_splitter
+        self.mini_chunk_splitter = mini_chunk_splitter
+
+        self._text_chunker = TextChunker(
+            tokenizer=tokenizer,
+            chunk_splitter=chunk_splitter,
+        )
+        self._image_chunker = ImageChunker()
+
+    def chunk(
+        self,
+        document: IndexingDocument,
+        sections: list[Section],
+        title_prefix: str,
+        metadata_suffix_semantic: str,
+        metadata_suffix_keyword: str,
+        content_token_limit: int,
+    ) -> list[DocAwareChunk]:
+        payloads = self._collect_section_payloads(
+            document=document,
+            sections=sections,
+            content_token_limit=content_token_limit,
+        )
+
+        if not payloads:
+            payloads.append(ChunkPayload(text="", links={0: ""}))
+
+        return [
+            payload.to_doc_aware_chunk(
+                document=document,
+                chunk_id=idx,
+                blurb_splitter=self.blurb_splitter,
+                mini_chunk_splitter=self.mini_chunk_splitter,
+                title_prefix=title_prefix,
+                metadata_suffix_semantic=metadata_suffix_semantic,
+                metadata_suffix_keyword=metadata_suffix_keyword,
+            )
+            for idx, payload in enumerate(payloads)
+        ]
+
+    def _collect_section_payloads(
+        self,
+        document: IndexingDocument,
+        sections: list[Section],
+        content_token_limit: int,
+    ) -> list[ChunkPayload]:
+        accumulator = AccumulatorState()
+        payloads: list[ChunkPayload] = []
+
+        for section_idx, section in enumerate(sections):
+            section_text = clean_text(str(section.text or ""))
+
+            if not section_text and (
+                not document.title or section_idx > 0
+            ):
+                logger.warning(
+                    f"Skipping empty or irrelevant section in doc "
+                    f"{document.semantic_identifier}, link={section.link}"
+                )
+                continue
+
+            chunker = self._select_chunker(section)
+            result = chunker.chunk_section(
+                section=section,
+                accumulator=accumulator,
+                content_token_limit=content_token_limit,
+            )
+            payloads.extend(result.payloads)
+            accumulator = result.accumulator
+
+        payloads.extend(accumulator.flush_to_list())
+        return payloads
+
+    def _select_chunker(self, section: Section) -> SectionChunker:
+        if section.image_file_id is not None:
+            return self._image_chunker
+        return self._text_chunker

backend/onyx/indexing/document_chunker/image_section_chunker.py

@@ -0,0 +1,34 @@
+from onyx.connectors.models import Section
+from onyx.indexing.document_chunker.section_chunker import AccumulatorState
+from onyx.indexing.document_chunker.section_chunker import ChunkPayload
+from onyx.indexing.document_chunker.section_chunker import SectionChunker
+from onyx.indexing.document_chunker.section_chunker import SectionChunkerOutput
+from onyx.utils.text_processing import clean_text
+
+
+class ImageChunker(SectionChunker):
+    def chunk_section(
+        self,
+        section: Section,
+        accumulator: AccumulatorState,
+        content_token_limit: int,  # noqa: ARG002
+    ) -> SectionChunkerOutput:
+        assert section.image_file_id is not None
+
+        section_text = clean_text(str(section.text or ""))
+        section_link = section.link or ""
+
+        payloads = accumulator.flush_to_list()
+        payloads.append(
+            ChunkPayload(
+                text=section_text,
+                links={0: section_link} if section_link else {},
+                image_file_id=section.image_file_id,
+                is_continuation=False,
+            )
+        )
+
+        return SectionChunkerOutput(
+            payloads=payloads,
+            accumulator=AccumulatorState(),
+        )

backend/onyx/indexing/document_chunker/section_chunker.py

@@ -0,0 +1,102 @@
+from abc import ABC
+from abc import abstractmethod
+from typing import cast
+
+from chonkie import SentenceChunker
+from pydantic import BaseModel
+from pydantic import Field
+
+from onyx.connectors.models import IndexingDocument
+from onyx.connectors.models import Section
+from onyx.indexing.models import DocAwareChunk
+
+
+def extract_blurb(text: str, blurb_splitter: SentenceChunker) -> str:
+    texts = cast(list[str], blurb_splitter.chunk(text))
+    if not texts:
+        return ""
+    return texts[0]
+
+
+def get_mini_chunk_texts(
+    chunk_text: str,
+    mini_chunk_splitter: SentenceChunker | None,
+) -> list[str] | None:
+    if mini_chunk_splitter and chunk_text.strip():
+        return cast(list[str], mini_chunk_splitter.chunk(chunk_text))
+    return None
+
+
+class ChunkPayload(BaseModel):
+    """Section-local chunk content without document-scoped fields.
+
+    The orchestrator upgrades these to DocAwareChunks via
+    `to_doc_aware_chunk` after assigning chunk_ids and attaching
+    title/metadata.
+    """
+
+    text: str
+    links: dict[int, str]
+    is_continuation: bool = False
+    image_file_id: str | None = None
+
+    def to_doc_aware_chunk(
+        self,
+        document: IndexingDocument,
+        chunk_id: int,
+        blurb_splitter: SentenceChunker,
+        title_prefix: str = "",
+        metadata_suffix_semantic: str = "",
+        metadata_suffix_keyword: str = "",
+        mini_chunk_splitter: SentenceChunker | None = None,
+    ) -> DocAwareChunk:
+        return DocAwareChunk(
+            source_document=document,
+            chunk_id=chunk_id,
+            blurb=extract_blurb(self.text, blurb_splitter),
+            content=self.text,
+            source_links=self.links or {0: ""},
+            image_file_id=self.image_file_id,
+            section_continuation=self.is_continuation,
+            title_prefix=title_prefix,
+            metadata_suffix_semantic=metadata_suffix_semantic,
+            metadata_suffix_keyword=metadata_suffix_keyword,
+            mini_chunk_texts=get_mini_chunk_texts(
+                self.text, mini_chunk_splitter
+            ),
+            large_chunk_id=None,
+            doc_summary="",
+            chunk_context="",
+            contextual_rag_reserved_tokens=0,
+        )
+
+
+class AccumulatorState(BaseModel):
+    """Cross-section text buffer threaded through SectionChunkers."""
+
+    text: str = ""
+    link_offsets: dict[int, str] = Field(default_factory=dict)
+
+    def is_empty(self) -> bool:
+        return not self.text.strip()
+
+    def flush_to_list(self) -> list["ChunkPayload"]:
+        if self.is_empty():
+            return []
+        return [ChunkPayload(text=self.text, links=self.link_offsets)]
+
+
+class SectionChunkerOutput(BaseModel):
+    payloads: list[ChunkPayload]
+    accumulator: AccumulatorState
+
+
+class SectionChunker(ABC):
+    @abstractmethod
+    def chunk_section(
+        self,
+        section: Section,
+        accumulator: AccumulatorState,
+        content_token_limit: int,
+    ) -> SectionChunkerOutput:
+        ...

backend/onyx/indexing/document_chunker/text_section_chunker.py

@@ -0,0 +1,129 @@
+from typing import cast
+
+from chonkie import SentenceChunker
+
+from onyx.configs.constants import SECTION_SEPARATOR
+from onyx.connectors.models import Section
+from onyx.indexing.document_chunker.section_chunker import AccumulatorState
+from onyx.indexing.document_chunker.section_chunker import ChunkPayload
+from onyx.indexing.document_chunker.section_chunker import SectionChunker
+from onyx.indexing.document_chunker.section_chunker import SectionChunkerOutput
+from onyx.natural_language_processing.utils import BaseTokenizer
+from onyx.utils.text_processing import clean_text
+from onyx.utils.text_processing import shared_precompare_cleanup
+from shared_configs.configs import STRICT_CHUNK_TOKEN_LIMIT
+
+
+class TextChunker(SectionChunker):
+    def __init__(
+        self,
+        tokenizer: BaseTokenizer,
+        chunk_splitter: SentenceChunker,
+    ) -> None:
+        self.tokenizer = tokenizer
+        self.chunk_splitter = chunk_splitter
+
+    def chunk_section(
+        self,
+        section: Section,
+        accumulator: AccumulatorState,
+        content_token_limit: int,
+    ) -> SectionChunkerOutput:
+        section_text = clean_text(str(section.text or ""))
+        section_link = section.link or ""
+        section_token_count = len(self.tokenizer.encode(section_text))
+
+        # Oversized — flush buffer and split the section
+        if section_token_count > content_token_limit:
+            return self._handle_oversized_section(
+                section_text=section_text,
+                section_link=section_link,
+                accumulator=accumulator,
+                content_token_limit=content_token_limit,
+            )
+
+        current_token_count = len(self.tokenizer.encode(accumulator.text))
+        next_section_tokens = (
+            len(self.tokenizer.encode(SECTION_SEPARATOR)) + section_token_count
+        )
+
+        # Fits — extend the accumulator
+        if next_section_tokens + current_token_count <= content_token_limit:
+            offset = len(shared_precompare_cleanup(accumulator.text))
+            new_text = accumulator.text
+            if new_text:
+                new_text += SECTION_SEPARATOR
+            new_text += section_text
+            return SectionChunkerOutput(
+                payloads=[],
+                accumulator=AccumulatorState(
+                    text=new_text,
+                    link_offsets={**accumulator.link_offsets, offset: section_link},
+                ),
+            )
+
+        # Doesn't fit — flush buffer and restart with this section
+        return SectionChunkerOutput(
+            payloads=accumulator.flush_to_list(),
+            accumulator=AccumulatorState(
+                text=section_text,
+                link_offsets={0: section_link},
+            ),
+        )
+
+    def _handle_oversized_section(
+        self,
+        section_text: str,
+        section_link: str,
+        accumulator: AccumulatorState,
+        content_token_limit: int,
+    ) -> SectionChunkerOutput:
+        payloads = accumulator.flush_to_list()
+
+        split_texts = cast(
+            list[str], self.chunk_splitter.chunk(section_text)
+        )
+        for i, split_text in enumerate(split_texts):
+            if (
+                STRICT_CHUNK_TOKEN_LIMIT
+                and len(self.tokenizer.encode(split_text)) > content_token_limit
+            ):
+                smaller_chunks = self._split_oversized_chunk(
+                    split_text, content_token_limit
+                )
+                for j, small_chunk in enumerate(smaller_chunks):
+                    payloads.append(
+                        ChunkPayload(
+                            text=small_chunk,
+                            links={0: section_link},
+                            is_continuation=(j != 0),
+                        )
+                    )
+            else:
+                payloads.append(
+                    ChunkPayload(
+                        text=split_text,
+                        links={0: section_link},
+                        is_continuation=(i != 0),
+                    )
+                )
+
+        return SectionChunkerOutput(
+            payloads=payloads,
+            accumulator=AccumulatorState(),
+        )
+
+    def _split_oversized_chunk(
+        self, text: str, content_token_limit: int
+    ) -> list[str]:
+        tokens = self.tokenizer.tokenize(text)
+        chunks: list[str] = []
+        start = 0
+        total_tokens = len(tokens)
+        while start < total_tokens:
+            end = min(start + content_token_limit, total_tokens)
+            token_chunk = tokens[start:end]
+            chunk_text = " ".join(token_chunk)
+            chunks.append(chunk_text)
+            start = end
+        return chunks

backend/onyx/llm/constants.py

@@ -26,6 +26,7 @@ class LlmProviderNames(str, Enum):
     MISTRAL = "mistral"
     LITELLM_PROXY = "litellm_proxy"
     BIFROST = "bifrost"
+    OPENAI_COMPATIBLE = "openai_compatible"
 
     def __str__(self) -> str:
         """Needed so things like:
@@ -46,6 +47,7 @@ WELL_KNOWN_PROVIDER_NAMES = [
     LlmProviderNames.LM_STUDIO,
     LlmProviderNames.LITELLM_PROXY,
     LlmProviderNames.BIFROST,
+    LlmProviderNames.OPENAI_COMPATIBLE,
 ]
 
 
@@ -64,6 +66,7 @@ PROVIDER_DISPLAY_NAMES: dict[str, str] = {
     LlmProviderNames.LM_STUDIO: "LM Studio",
     LlmProviderNames.LITELLM_PROXY: "LiteLLM Proxy",
     LlmProviderNames.BIFROST: "Bifrost",
+    LlmProviderNames.OPENAI_COMPATIBLE: "OpenAI-Compatible",
     "groq": "Groq",
     "anyscale": "Anyscale",
     "deepseek": "DeepSeek",
@@ -84,6 +87,44 @@ PROVIDER_DISPLAY_NAMES: dict[str, str] = {
     "gemini": "Gemini",
     "stability": "Stability",
     "writer": "Writer",
+    # Custom provider display names (used in the custom provider picker)
+    "aiml": "AI/ML",
+    "assemblyai": "AssemblyAI",
+    "aws_polly": "AWS Polly",
+    "azure_ai": "Azure AI",
+    "chatgpt": "ChatGPT",
+    "cohere_chat": "Cohere Chat",
+    "datarobot": "DataRobot",
+    "deepgram": "Deepgram",
+    "deepinfra": "DeepInfra",
+    "elevenlabs": "ElevenLabs",
+    "fal_ai": "fal.ai",
+    "featherless_ai": "Featherless AI",
+    "fireworks_ai": "Fireworks AI",
+    "friendliai": "FriendliAI",
+    "gigachat": "GigaChat",
+    "github_copilot": "GitHub Copilot",
+    "gradient_ai": "Gradient AI",
+    "huggingface": "HuggingFace",
+    "jina_ai": "Jina AI",
+    "lambda_ai": "Lambda AI",
+    "llamagate": "LlamaGate",
+    "meta_llama": "Meta Llama",
+    "minimax": "MiniMax",
+    "nlp_cloud": "NLP Cloud",
+    "nvidia_nim": "NVIDIA NIM",
+    "oci": "OCI",
+    "ovhcloud": "OVHcloud",
+    "palm": "PaLM",
+    "publicai": "PublicAI",
+    "runwayml": "RunwayML",
+    "sambanova": "SambaNova",
+    "together_ai": "Together AI",
+    "vercel_ai_gateway": "Vercel AI Gateway",
+    "volcengine": "Volcengine",
+    "wandb": "W&B",
+    "watsonx": "IBM watsonx",
+    "zai": "ZAI",
 }
 
 # Map vendors to their brand names (used for provider_display_name generation)
@@ -116,6 +157,7 @@ AGGREGATOR_PROVIDERS: set[str] = {
     LlmProviderNames.AZURE,
     LlmProviderNames.LITELLM_PROXY,
     LlmProviderNames.BIFROST,
+    LlmProviderNames.OPENAI_COMPATIBLE,
 }
 
 # Model family name mappings for display name generation

backend/onyx/llm/multi_llm.py

@@ -327,12 +327,19 @@ class LitellmLLM(LLM):
         ):
             model_kwargs[VERTEX_LOCATION_KWARG] = "global"
 
-        # Bifrost: OpenAI-compatible proxy that expects model names in
-        # provider/model format (e.g. "anthropic/claude-sonnet-4-6").
-        # We route through LiteLLM's openai provider with the Bifrost base URL,
-        # and ensure /v1 is appended.
-        if model_provider == LlmProviderNames.BIFROST:
+        # Bifrost and OpenAI-compatible: OpenAI-compatible proxies that send
+        # model names directly to the endpoint. We route through LiteLLM's
+        # openai provider with the server's base URL, and ensure /v1 is appended.
+        if model_provider in (
+            LlmProviderNames.BIFROST,
+            LlmProviderNames.OPENAI_COMPATIBLE,
+        ):
             self._custom_llm_provider = "openai"
+            # LiteLLM's OpenAI client requires an api_key to be set.
+            # Many OpenAI-compatible servers don't need auth, so supply a
+            # placeholder to prevent LiteLLM from raising AuthenticationError.
+            if not self._api_key:
+                model_kwargs.setdefault("api_key", "not-needed")
             if self._api_base is not None:
                 base = self._api_base.rstrip("/")
                 self._api_base = base if base.endswith("/v1") else f"{base}/v1"
@@ -449,17 +456,20 @@ class LitellmLLM(LLM):
         optional_kwargs: dict[str, Any] = {}
 
         # Model name
-        is_bifrost = self._model_provider == LlmProviderNames.BIFROST
+        is_openai_compatible_proxy = self._model_provider in (
+            LlmProviderNames.BIFROST,
+            LlmProviderNames.OPENAI_COMPATIBLE,
+        )
         model_provider = (
             f"{self.config.model_provider}/responses"
             if is_openai_model  # Uses litellm's completions -> responses bridge
             else self.config.model_provider
         )
-        if is_bifrost:
-            # Bifrost expects model names in provider/model format
-            # (e.g. "anthropic/claude-sonnet-4-6") sent directly to its
-            # OpenAI-compatible endpoint. We use custom_llm_provider="openai"
-            # so LiteLLM doesn't try to route based on the provider prefix.
+        if is_openai_compatible_proxy:
+            # OpenAI-compatible proxies (Bifrost, generic OpenAI-compatible
+            # servers) expect model names sent directly to their endpoint.
+            # We use custom_llm_provider="openai" so LiteLLM doesn't try
+            # to route based on the provider prefix.
             model = self.config.deployment_name or self.config.model_name
         else:
             model = f"{model_provider}/{self.config.deployment_name or self.config.model_name}"
@@ -550,7 +560,10 @@ class LitellmLLM(LLM):
         if structured_response_format:
             optional_kwargs["response_format"] = structured_response_format
 
-        if not (is_claude_model or is_ollama or is_mistral) or is_bifrost:
+        if (
+            not (is_claude_model or is_ollama or is_mistral)
+            or is_openai_compatible_proxy
+        ):
             # Litellm bug: tool_choice is dropped silently if not specified here for OpenAI
             # However, this param breaks Anthropic and Mistral models,
             # so it must be conditionally included unless the request is

backend/onyx/llm/well_known_providers/constants.py

@@ -15,6 +15,8 @@ LITELLM_PROXY_PROVIDER_NAME = "litellm_proxy"
 
 BIFROST_PROVIDER_NAME = "bifrost"
 
+OPENAI_COMPATIBLE_PROVIDER_NAME = "openai_compatible"
+
 # Providers that use optional Bearer auth from custom_config
 PROVIDERS_WITH_SPECIAL_API_KEY_HANDLING: dict[str, str] = {
     LlmProviderNames.OLLAMA_CHAT: OLLAMA_API_KEY_CONFIG_KEY,

backend/onyx/llm/well_known_providers/llm_provider_options.py

@@ -19,6 +19,7 @@ from onyx.llm.well_known_providers.constants import BIFROST_PROVIDER_NAME
 from onyx.llm.well_known_providers.constants import LITELLM_PROXY_PROVIDER_NAME
 from onyx.llm.well_known_providers.constants import LM_STUDIO_PROVIDER_NAME
 from onyx.llm.well_known_providers.constants import OLLAMA_PROVIDER_NAME
+from onyx.llm.well_known_providers.constants import OPENAI_COMPATIBLE_PROVIDER_NAME
 from onyx.llm.well_known_providers.constants import OPENAI_PROVIDER_NAME
 from onyx.llm.well_known_providers.constants import OPENROUTER_PROVIDER_NAME
 from onyx.llm.well_known_providers.constants import VERTEXAI_PROVIDER_NAME
@@ -51,6 +52,7 @@ def _get_provider_to_models_map() -> dict[str, list[str]]:
         OPENROUTER_PROVIDER_NAME: [],  # Dynamic - fetched from OpenRouter API
         LITELLM_PROXY_PROVIDER_NAME: [],  # Dynamic - fetched from LiteLLM proxy API
         BIFROST_PROVIDER_NAME: [],  # Dynamic - fetched from Bifrost API
+        OPENAI_COMPATIBLE_PROVIDER_NAME: [],  # Dynamic - fetched from OpenAI-compatible API
     }
 
 
@@ -336,6 +338,7 @@ def get_provider_display_name(provider_name: str) -> str:
         VERTEXAI_PROVIDER_NAME: "Google Vertex AI",
         OPENROUTER_PROVIDER_NAME: "OpenRouter",
         LITELLM_PROXY_PROVIDER_NAME: "LiteLLM Proxy",
+        OPENAI_COMPATIBLE_PROVIDER_NAME: "OpenAI-Compatible",
     }
 
     if provider_name in _ONYX_PROVIDER_DISPLAY_NAMES:

backend/onyx/mcp_server_main.py

@@ -6,6 +6,7 @@ from onyx.configs.app_configs import MCP_SERVER_ENABLED
 from onyx.configs.app_configs import MCP_SERVER_HOST
 from onyx.configs.app_configs import MCP_SERVER_PORT
 from onyx.utils.logger import setup_logger
+from onyx.utils.variable_functionality import set_is_ee_based_on_env_variable
 
 logger = setup_logger()
 
@@ -16,6 +17,7 @@ def main() -> None:
         logger.info("MCP server is disabled (MCP_SERVER_ENABLED=false)")
         return
 
+    set_is_ee_based_on_env_variable()
     logger.info(f"Starting MCP server on {MCP_SERVER_HOST}:{MCP_SERVER_PORT}")
 
     from onyx.mcp_server.api import mcp_app

backend/onyx/onyxbot/slack/listener.py

@@ -90,6 +90,7 @@ from onyx.onyxbot.slack.utils import respond_in_thread_or_channel
 from onyx.onyxbot.slack.utils import TenantSocketModeClient
 from onyx.redis.redis_pool import get_redis_client
 from onyx.server.manage.models import SlackBotTokens
+from onyx.tracing.setup import setup_tracing
 from onyx.utils.logger import setup_logger
 from onyx.utils.variable_functionality import fetch_ee_implementation_or_noop
 from onyx.utils.variable_functionality import set_is_ee_based_on_env_variable
@@ -1206,6 +1207,7 @@ if __name__ == "__main__":
     tenant_handler = SlackbotHandler()
 
     set_is_ee_based_on_env_variable()
+    setup_tracing()
 
     try:
         # Keep the main thread alive

backend/onyx/server/api_key/api.py

@@ -2,7 +2,7 @@ from fastapi import APIRouter
 from fastapi import Depends
 from sqlalchemy.orm import Session
 
-from onyx.auth.users import current_admin_user
+from onyx.auth.permissions import require_permission
 from onyx.db.api_key import ApiKeyDescriptor
 from onyx.db.api_key import fetch_api_keys
 from onyx.db.api_key import insert_api_key
@@ -10,6 +10,7 @@ from onyx.db.api_key import regenerate_api_key
 from onyx.db.api_key import remove_api_key
 from onyx.db.api_key import update_api_key
 from onyx.db.engine.sql_engine import get_session
+from onyx.db.enums import Permission
 from onyx.db.models import User
 from onyx.server.api_key.models import APIKeyArgs
 
@@ -19,7 +20,7 @@ router = APIRouter(prefix="/admin/api-key")
 
 @router.get("")
 def list_api_keys(
-    _: User = Depends(current_admin_user),
+    _: User = Depends(require_permission(Permission.FULL_ADMIN_PANEL_ACCESS)),
     db_session: Session = Depends(get_session),
 ) -> list[ApiKeyDescriptor]:
     return fetch_api_keys(db_session)
@@ -28,7 +29,7 @@ def list_api_keys(
 @router.post("")
 def create_api_key(
     api_key_args: APIKeyArgs,
-    user: User = Depends(current_admin_user),
+    user: User = Depends(require_permission(Permission.FULL_ADMIN_PANEL_ACCESS)),
     db_session: Session = Depends(get_session),
 ) -> ApiKeyDescriptor:
     return insert_api_key(db_session, api_key_args, user.id)
@@ -37,7 +38,7 @@ def create_api_key(
 @router.post("/{api_key_id}/regenerate")
 def regenerate_existing_api_key(
     api_key_id: int,
-    _: User = Depends(current_admin_user),
+    _: User = Depends(require_permission(Permission.FULL_ADMIN_PANEL_ACCESS)),
     db_session: Session = Depends(get_session),
 ) -> ApiKeyDescriptor:
     return regenerate_api_key(db_session, api_key_id)
@@ -47,7 +48,7 @@ def regenerate_existing_api_key(
 def update_existing_api_key(
     api_key_id: int,
     api_key_args: APIKeyArgs,
-    _: User = Depends(current_admin_user),
+    _: User = Depends(require_permission(Permission.FULL_ADMIN_PANEL_ACCESS)),
     db_session: Session = Depends(get_session),
 ) -> ApiKeyDescriptor:
     return update_api_key(db_session, api_key_id, api_key_args)
@@ -56,7 +57,7 @@ def update_existing_api_key(
 @router.delete("/{api_key_id}")
 def delete_api_key(
     api_key_id: int,
-    _: User = Depends(current_admin_user),
+    _: User = Depends(require_permission(Permission.FULL_ADMIN_PANEL_ACCESS)),
     db_session: Session = Depends(get_session),
 ) -> None:
     remove_api_key(db_session, api_key_id)

backend/onyx/server/auth_check.py

@@ -4,7 +4,6 @@ from fastapi import FastAPI
 from fastapi.dependencies.models import Dependant
 from starlette.routing import BaseRoute
 
-from onyx.auth.users import current_admin_user
 from onyx.auth.users import current_chat_accessible_user
 from onyx.auth.users import current_curator_or_admin_user
 from onyx.auth.users import current_limited_user
@@ -91,6 +90,11 @@ def is_route_in_spec_list(
     return False
 
 
+def _is_require_permission_dependency(fn: object) -> bool:
+    """Detect closures generated by ``require_permission()``."""
+    return bool(getattr(fn, "_is_require_permission", False))
+
+
 def check_router_auth(
     application: FastAPI,
     public_endpoint_specs: list[tuple[str, set[str]]] = PUBLIC_ENDPOINT_SPECS,
@@ -126,7 +130,6 @@ def check_router_auth(
                 if (
                     depends_fn == current_limited_user
                     or depends_fn == current_user
-                    or depends_fn == current_admin_user
                     or depends_fn == current_curator_or_admin_user
                     or depends_fn == current_user_with_expired_token
                     or depends_fn == current_chat_accessible_user
@@ -134,6 +137,7 @@ def check_router_auth(
                     or depends_fn == control_plane_dep
                     or depends_fn == current_cloud_superuser
                     or depends_fn == verify_scim_token
+                    or _is_require_permission_dependency(depends_fn)
                 ):
                     found_auth = True
                     break

backend/onyx/server/documents/cc_pair.py

@@ -10,8 +10,8 @@ from sqlalchemy import select
 from sqlalchemy.exc import IntegrityError
 from sqlalchemy.orm import Session
 
+from onyx.auth.permissions import require_permission
 from onyx.auth.users import current_curator_or_admin_user
-from onyx.auth.users import current_user
 from onyx.background.celery.tasks.pruning.tasks import (
     try_creating_prune_generator_task,
 )
@@ -38,6 +38,7 @@ from onyx.db.engine.sql_engine import get_session
 from onyx.db.enums import AccessType
 from onyx.db.enums import ConnectorCredentialPairStatus
 from onyx.db.enums import IndexingStatus
+from onyx.db.enums import Permission
 from onyx.db.enums import PermissionSyncStatus
 from onyx.db.index_attempt import count_index_attempt_errors_for_cc_pair
 from onyx.db.index_attempt import count_index_attempts_for_cc_pair
@@ -622,7 +623,7 @@ def associate_credential_to_connector(
 def dissociate_credential_from_connector(
     connector_id: int,
     credential_id: int,
-    user: User = Depends(current_user),
+    user: User = Depends(require_permission(Permission.BASIC_ACCESS)),
     db_session: Session = Depends(get_session),
 ) -> StatusResponse[int]:
     return remove_credential_from_connector(

backend/onyx/server/documents/connector.py

@@ -22,10 +22,9 @@ from pydantic import BaseModel
 from sqlalchemy.orm import Session
 
 from onyx.auth.email_utils import send_email
-from onyx.auth.users import current_admin_user
+from onyx.auth.permissions import require_permission
 from onyx.auth.users import current_chat_accessible_user
 from onyx.auth.users import current_curator_or_admin_user
-from onyx.auth.users import current_user
 from onyx.background.celery.tasks.pruning.tasks import (
     try_creating_prune_generator_task,
 )
@@ -105,6 +104,7 @@ from onyx.db.engine.sql_engine import get_session
 from onyx.db.enums import AccessType
 from onyx.db.enums import ConnectorCredentialPairStatus
 from onyx.db.enums import IndexingMode
+from onyx.db.enums import Permission
 from onyx.db.enums import ProcessingMode
 from onyx.db.federated import fetch_all_federated_connectors_parallel
 from onyx.db.index_attempt import get_index_attempts_for_cc_pair
@@ -189,7 +189,8 @@ def check_google_app_gmail_credentials_exist(
 
 @router.put("/admin/connector/gmail/app-credential")
 def upsert_google_app_gmail_credentials(
-    app_credentials: GoogleAppCredentials, _: User = Depends(current_admin_user)
+    app_credentials: GoogleAppCredentials,
+    _: User = Depends(require_permission(Permission.FULL_ADMIN_PANEL_ACCESS)),
 ) -> StatusResponse:
     try:
         upsert_google_app_cred(app_credentials, DocumentSource.GMAIL)
@@ -203,7 +204,7 @@ def upsert_google_app_gmail_credentials(
 
 @router.delete("/admin/connector/gmail/app-credential")
 def delete_google_app_gmail_credentials(
-    _: User = Depends(current_admin_user),
+    _: User = Depends(require_permission(Permission.FULL_ADMIN_PANEL_ACCESS)),
     db_session: Session = Depends(get_session),
 ) -> StatusResponse:
     try:
@@ -231,7 +232,8 @@ def check_google_app_credentials_exist(
 
 @router.put("/admin/connector/google-drive/app-credential")
 def upsert_google_app_credentials(
-    app_credentials: GoogleAppCredentials, _: User = Depends(current_admin_user)
+    app_credentials: GoogleAppCredentials,
+    _: User = Depends(require_permission(Permission.FULL_ADMIN_PANEL_ACCESS)),
 ) -> StatusResponse:
     try:
         upsert_google_app_cred(app_credentials, DocumentSource.GOOGLE_DRIVE)
@@ -245,7 +247,7 @@ def upsert_google_app_credentials(
 
 @router.delete("/admin/connector/google-drive/app-credential")
 def delete_google_app_credentials(
-    _: User = Depends(current_admin_user),
+    _: User = Depends(require_permission(Permission.FULL_ADMIN_PANEL_ACCESS)),
     db_session: Session = Depends(get_session),
 ) -> StatusResponse:
     try:
@@ -277,7 +279,8 @@ def check_google_service_gmail_account_key_exist(
 
 @router.put("/admin/connector/gmail/service-account-key")
 def upsert_google_service_gmail_account_key(
-    service_account_key: GoogleServiceAccountKey, _: User = Depends(current_admin_user)
+    service_account_key: GoogleServiceAccountKey,
+    _: User = Depends(require_permission(Permission.FULL_ADMIN_PANEL_ACCESS)),
 ) -> StatusResponse:
     try:
         upsert_service_account_key(service_account_key, DocumentSource.GMAIL)
@@ -291,7 +294,7 @@ def upsert_google_service_gmail_account_key(
 
 @router.delete("/admin/connector/gmail/service-account-key")
 def delete_google_service_gmail_account_key(
-    _: User = Depends(current_admin_user),
+    _: User = Depends(require_permission(Permission.FULL_ADMIN_PANEL_ACCESS)),
     db_session: Session = Depends(get_session),
 ) -> StatusResponse:
     try:
@@ -323,7 +326,8 @@ def check_google_service_account_key_exist(
 
 @router.put("/admin/connector/google-drive/service-account-key")
 def upsert_google_service_account_key(
-    service_account_key: GoogleServiceAccountKey, _: User = Depends(current_admin_user)
+    service_account_key: GoogleServiceAccountKey,
+    _: User = Depends(require_permission(Permission.FULL_ADMIN_PANEL_ACCESS)),
 ) -> StatusResponse:
     try:
         upsert_service_account_key(service_account_key, DocumentSource.GOOGLE_DRIVE)
@@ -337,7 +341,7 @@ def upsert_google_service_account_key(
 
 @router.delete("/admin/connector/google-drive/service-account-key")
 def delete_google_service_account_key(
-    _: User = Depends(current_admin_user),
+    _: User = Depends(require_permission(Permission.FULL_ADMIN_PANEL_ACCESS)),
     db_session: Session = Depends(get_session),
 ) -> StatusResponse:
     try:
@@ -407,7 +411,7 @@ def upsert_gmail_service_account_credential(
 @router.get("/admin/connector/google-drive/check-auth/{credential_id}")
 def check_drive_tokens(
     credential_id: int,
-    user: User = Depends(current_admin_user),
+    user: User = Depends(require_permission(Permission.FULL_ADMIN_PANEL_ACCESS)),
     db_session: Session = Depends(get_session),
 ) -> AuthStatus:
     db_credentials = fetch_credential_by_id_for_user(credential_id, user, db_session)
@@ -1794,7 +1798,9 @@ def connector_run_once(
 
 @router.get("/connector/gmail/authorize/{credential_id}")
 def gmail_auth(
-    response: Response, credential_id: str, _: User = Depends(current_user)
+    response: Response,
+    credential_id: str,
+    _: User = Depends(require_permission(Permission.BASIC_ACCESS)),
 ) -> AuthUrl:
     # set a cookie that we can read in the callback (used for `verify_csrf`)
     response.set_cookie(
@@ -1808,7 +1814,9 @@ def gmail_auth(
 
 @router.get("/connector/google-drive/authorize/{credential_id}")
 def google_drive_auth(
-    response: Response, credential_id: str, _: User = Depends(current_user)
+    response: Response,
+    credential_id: str,
+    _: User = Depends(require_permission(Permission.BASIC_ACCESS)),
 ) -> AuthUrl:
     # set a cookie that we can read in the callback (used for `verify_csrf`)
     response.set_cookie(
@@ -1826,7 +1834,7 @@ def google_drive_auth(
 def gmail_callback(
     request: Request,
     callback: GmailCallback = Depends(),
-    user: User = Depends(current_user),
+    user: User = Depends(require_permission(Permission.BASIC_ACCESS)),
     db_session: Session = Depends(get_session),
 ) -> StatusResponse:
     credential_id_cookie = request.cookies.get(_GMAIL_CREDENTIAL_ID_COOKIE_NAME)
@@ -1856,7 +1864,7 @@ def gmail_callback(
 def google_drive_callback(
     request: Request,
     callback: GDriveCallback = Depends(),
-    user: User = Depends(current_user),
+    user: User = Depends(require_permission(Permission.BASIC_ACCESS)),
     db_session: Session = Depends(get_session),
 ) -> StatusResponse:
     credential_id_cookie = request.cookies.get(_GOOGLE_DRIVE_CREDENTIAL_ID_COOKIE_NAME)
@@ -1885,7 +1893,7 @@ def google_drive_callback(
 
 @router.get("/connector", tags=PUBLIC_API_TAGS)
 def get_connectors(
-    _: User = Depends(current_user),
+    _: User = Depends(require_permission(Permission.BASIC_ACCESS)),
     db_session: Session = Depends(get_session),
 ) -> list[ConnectorSnapshot]:
     connectors = fetch_connectors(db_session)
@@ -1900,7 +1908,7 @@ def get_connectors(
 
 @router.get("/indexed-sources", tags=PUBLIC_API_TAGS)
 def get_indexed_sources(
-    _: User = Depends(current_user),
+    _: User = Depends(require_permission(Permission.BASIC_ACCESS)),
     db_session: Session = Depends(get_session),
 ) -> IndexedSourcesResponse:
     sources = sorted(
@@ -1912,7 +1920,7 @@ def get_indexed_sources(
 @router.get("/connector/{connector_id}", tags=PUBLIC_API_TAGS)
 def get_connector_by_id(
     connector_id: int,
-    _: User = Depends(current_user),
+    _: User = Depends(require_permission(Permission.BASIC_ACCESS)),
     db_session: Session = Depends(get_session),
 ) -> ConnectorSnapshot | StatusResponse[int]:
     connector = fetch_connector_by_id(connector_id, db_session)
@@ -1941,7 +1949,7 @@ def get_connector_by_id(
 @router.post("/connector-request")
 def submit_connector_request(
     request_data: ConnectorRequestSubmission,
-    user: User = Depends(current_user),
+    user: User = Depends(require_permission(Permission.BASIC_ACCESS)),
 ) -> StatusResponse:
     """
     Submit a connector request for Cloud deployments.

backend/onyx/server/documents/credential.py

@@ -9,9 +9,8 @@ from fastapi import Query
 from fastapi import UploadFile
 from sqlalchemy.orm import Session
 
-from onyx.auth.users import current_admin_user
+from onyx.auth.permissions import require_permission
 from onyx.auth.users import current_curator_or_admin_user
-from onyx.auth.users import current_user
 from onyx.configs.constants import PUBLIC_API_TAGS
 from onyx.connectors.factory import validate_ccpair_for_user
 from onyx.db.credentials import alter_credential
@@ -26,6 +25,7 @@ from onyx.db.credentials import fetch_credentials_for_user
 from onyx.db.credentials import swap_credentials_connector
 from onyx.db.credentials import update_credential
 from onyx.db.engine.sql_engine import get_session
+from onyx.db.enums import Permission
 from onyx.db.models import DocumentSource
 from onyx.db.models import User
 from onyx.server.documents.models import CredentialBase
@@ -95,7 +95,7 @@ def get_cc_source_full_info(
 @router.delete("/admin/credential/{credential_id}")
 def delete_credential_by_id_admin(
     credential_id: int,
-    _: User = Depends(current_admin_user),
+    _: User = Depends(require_permission(Permission.FULL_ADMIN_PANEL_ACCESS)),
     db_session: Session = Depends(get_session),
 ) -> StatusResponse:
     """Same as the user endpoint, but can delete any credential (not just the user's own)"""
@@ -108,7 +108,7 @@ def delete_credential_by_id_admin(
 @router.put("/admin/credential/swap")
 def swap_credentials_for_connector(
     credential_swap_req: CredentialSwapRequest,
-    user: User = Depends(current_user),
+    user: User = Depends(require_permission(Permission.BASIC_ACCESS)),
     db_session: Session = Depends(get_session),
 ) -> StatusResponse:
     validate_ccpair_for_user(
@@ -228,7 +228,7 @@ def create_credential_with_private_key(
 
 @router.get("/credential")
 def list_credentials(
-    user: User = Depends(current_user),
+    user: User = Depends(require_permission(Permission.BASIC_ACCESS)),
     db_session: Session = Depends(get_session),
 ) -> list[CredentialSnapshot]:
     credentials = fetch_credentials_for_user(db_session=db_session, user=user)
@@ -241,7 +241,7 @@ def list_credentials(
 @router.get("/credential/{credential_id}")
 def get_credential_by_id(
     credential_id: int,
-    user: User = Depends(current_user),
+    user: User = Depends(require_permission(Permission.BASIC_ACCESS)),
     db_session: Session = Depends(get_session),
 ) -> CredentialSnapshot | StatusResponse[int]:
     credential = fetch_credential_by_id_for_user(
@@ -263,7 +263,7 @@ def get_credential_by_id(
 def update_credential_data(
     credential_id: int,
     credential_update: CredentialDataUpdateRequest,
-    user: User = Depends(current_user),
+    user: User = Depends(require_permission(Permission.BASIC_ACCESS)),
     db_session: Session = Depends(get_session),
 ) -> CredentialBase:
     credential = alter_credential(
@@ -291,7 +291,7 @@ def update_credential_private_key(
     uploaded_file: UploadFile = File(...),
     field_key: str = Form(...),
     type_definition_key: str = Form(...),
-    user: User = Depends(current_user),
+    user: User = Depends(require_permission(Permission.BASIC_ACCESS)),
     db_session: Session = Depends(get_session),
 ) -> CredentialBase:
     try:
@@ -334,7 +334,7 @@ def update_credential_private_key(
 def update_credential_from_model(
     credential_id: int,
     credential_data: CredentialBase,
-    user: User = Depends(current_user),
+    user: User = Depends(require_permission(Permission.BASIC_ACCESS)),
     db_session: Session = Depends(get_session),
 ) -> CredentialSnapshot | StatusResponse[int]:
     updated_credential = update_credential(
@@ -369,7 +369,7 @@ def update_credential_from_model(
 @router.delete("/credential/{credential_id}")
 def delete_credential_by_id(
     credential_id: int,
-    user: User = Depends(current_user),
+    user: User = Depends(require_permission(Permission.BASIC_ACCESS)),
     db_session: Session = Depends(get_session),
 ) -> StatusResponse:
     delete_credential_for_user(
@@ -386,7 +386,7 @@ def delete_credential_by_id(
 @router.delete("/credential/force/{credential_id}")
 def force_delete_credential_by_id(
     credential_id: int,
-    user: User = Depends(current_user),
+    user: User = Depends(require_permission(Permission.BASIC_ACCESS)),
     db_session: Session = Depends(get_session),
 ) -> StatusResponse:
     delete_credential_for_user(credential_id, user, db_session, True)

backend/onyx/server/documents/document.py

@@ -4,12 +4,13 @@ from fastapi import HTTPException
 from fastapi import Query
 from sqlalchemy.orm import Session
 
-from onyx.auth.users import current_user
+from onyx.auth.permissions import require_permission
 from onyx.context.search.models import IndexFilters
 from onyx.context.search.preprocessing.access_filters import (
     build_access_filters_for_user,
 )
 from onyx.db.engine.sql_engine import get_session
+from onyx.db.enums import Permission
 from onyx.db.models import User
 from onyx.db.search_settings import get_current_search_settings
 from onyx.document_index.factory import get_default_document_index
@@ -29,7 +30,7 @@ router = APIRouter(prefix="/document")
 @router.get("/document-size-info", dependencies=[Depends(require_vector_db)])
 def get_document_info(
     document_id: str = Query(...),
-    user: User = Depends(current_user),
+    user: User = Depends(require_permission(Permission.BASIC_ACCESS)),
     db_session: Session = Depends(get_session),
 ) -> DocumentInfo:
     search_settings = get_current_search_settings(db_session)
@@ -74,7 +75,7 @@ def get_document_info(
 def get_chunk_info(
     document_id: str = Query(...),
     chunk_id: int = Query(...),
-    user: User = Depends(current_user),
+    user: User = Depends(require_permission(Permission.BASIC_ACCESS)),
     db_session: Session = Depends(get_session),
 ) -> ChunkInfo:
     search_settings = get_current_search_settings(db_session)

backend/onyx/server/documents/standard_oauth.py

@@ -12,12 +12,13 @@ from pydantic import BaseModel
 from pydantic import ValidationError
 from sqlalchemy.orm import Session
 
-from onyx.auth.users import current_user
+from onyx.auth.permissions import require_permission
 from onyx.configs.app_configs import WEB_DOMAIN
 from onyx.configs.constants import DocumentSource
 from onyx.connectors.interfaces import OAuthConnector
 from onyx.db.credentials import create_credential
 from onyx.db.engine.sql_engine import get_session
+from onyx.db.enums import Permission
 from onyx.db.models import User
 from onyx.redis.redis_pool import get_redis_client
 from onyx.server.documents.models import CredentialBase
@@ -89,7 +90,7 @@ def oauth_authorize(
     request: Request,
     source: DocumentSource,
     desired_return_url: Annotated[str | None, Query()] = None,
-    _: User = Depends(current_user),
+    _: User = Depends(require_permission(Permission.BASIC_ACCESS)),
 ) -> AuthorizeResponse:
     """Initiates the OAuth flow by redirecting to the provider's auth page"""
 
@@ -141,7 +142,7 @@ def oauth_callback(
     code: Annotated[str, Query()],
     state: Annotated[str, Query()],
     db_session: Session = Depends(get_session),
-    user: User = Depends(current_user),
+    user: User = Depends(require_permission(Permission.BASIC_ACCESS)),
 ) -> CallbackResponse:
     """Handles the OAuth callback and exchanges the code for tokens"""
     oauth_connectors = _discover_oauth_connectors()
@@ -201,7 +202,7 @@ class OAuthDetails(BaseModel):
 @router.get("/details/{source}")
 def oauth_details(
     source: DocumentSource,
-    _: User = Depends(current_user),
+    _: User = Depends(require_permission(Permission.BASIC_ACCESS)),
 ) -> OAuthDetails:
     oauth_connectors = _discover_oauth_connectors()
 

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

@@ -13,13 +13,14 @@ from fastapi.responses import RedirectResponse
 from fastapi.responses import StreamingResponse
 from sqlalchemy.orm import Session
 
-from onyx.auth.users import current_user
+from onyx.auth.permissions import require_permission
 from onyx.auth.users import optional_user
 from onyx.configs.constants import DocumentSource
 from onyx.db.connector_credential_pair import get_connector_credential_pairs_for_user
 from onyx.db.engine.sql_engine import get_session
 from onyx.db.enums import ConnectorCredentialPairStatus
 from onyx.db.enums import IndexingStatus
+from onyx.db.enums import Permission
 from onyx.db.enums import ProcessingMode
 from onyx.db.enums import SharingScope
 from onyx.db.index_attempt import get_latest_index_attempt_for_cc_pair_id
@@ -45,7 +46,9 @@ _TEMPLATES_DIR = Path(__file__).parent / "templates"
 _WEBAPP_HMR_FIXER_TEMPLATE = (_TEMPLATES_DIR / "webapp_hmr_fixer.js").read_text()
 
 
-def require_onyx_craft_enabled(user: User = Depends(current_user)) -> User:
+def require_onyx_craft_enabled(
+    user: User = Depends(require_permission(Permission.BASIC_ACCESS)),
+) -> User:
     """
     Dependency that checks if Onyx Craft is enabled for the user.
     Raises HTTP 403 if Onyx Craft is disabled via feature flag.
@@ -73,7 +76,7 @@ router.include_router(user_library_router, tags=["build"])
 
 @router.get("/limit", response_model=RateLimitResponse)
 def get_rate_limit(
-    user: User = Depends(current_user),
+    user: User = Depends(require_permission(Permission.BASIC_ACCESS)),
     db_session: Session = Depends(get_session),
 ) -> RateLimitResponse:
     """Get rate limit information for the current user."""
@@ -87,7 +90,7 @@ def get_rate_limit(
 
 @router.get("/connectors", response_model=BuildConnectorListResponse)
 def get_build_connectors(
-    user: User = Depends(current_user),
+    user: User = Depends(require_permission(Permission.BASIC_ACCESS)),
     db_session: Session = Depends(get_session),
 ) -> BuildConnectorListResponse:
     """Get all connectors for the build admin panel.
@@ -518,7 +521,7 @@ def get_webapp(
 
 @router.post("/sandbox/reset", response_model=None)
 def reset_sandbox(
-    user: User = Depends(current_user),
+    user: User = Depends(require_permission(Permission.BASIC_ACCESS)),
     db_session: Session = Depends(get_session),
 ) -> Response:
     """Reset the user's sandbox by terminating it and cleaning up all sessions.

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

@@ -9,10 +9,11 @@ from fastapi import HTTPException
 from fastapi.responses import StreamingResponse
 from sqlalchemy.orm import Session
 
-from onyx.auth.users import current_user
+from onyx.auth.permissions import require_permission
 from onyx.configs.constants import PUBLIC_API_TAGS
 from onyx.db.engine.sql_engine import get_session
 from onyx.db.engine.sql_engine import get_session_with_current_tenant
+from onyx.db.enums import Permission
 from onyx.db.models import User
 from onyx.server.features.build.api.models import MessageListResponse
 from onyx.server.features.build.api.models import MessageRequest
@@ -30,7 +31,7 @@ router = APIRouter()
 
 
 def check_build_rate_limits(
-    user: User = Depends(current_user),
+    user: User = Depends(require_permission(Permission.BASIC_ACCESS)),
     db_session: Session = Depends(get_session),
 ) -> None:
     """
@@ -53,7 +54,7 @@ def check_build_rate_limits(
 @router.get("/sessions/{session_id}/messages", tags=PUBLIC_API_TAGS)
 def list_messages(
     session_id: UUID,
-    user: User = Depends(current_user),
+    user: User = Depends(require_permission(Permission.BASIC_ACCESS)),
     db_session: Session = Depends(get_session),
 ) -> MessageListResponse:
     """Get all messages for a build session."""
@@ -73,7 +74,7 @@ def list_messages(
 def send_message(
     session_id: UUID,
     request: MessageRequest,
-    user: User = Depends(current_user),
+    user: User = Depends(require_permission(Permission.BASIC_ACCESS)),
     _rate_limit_check: None = Depends(check_build_rate_limits),
 ) -> StreamingResponse:
     """

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

@@ -11,9 +11,10 @@ from fastapi import UploadFile
 from sqlalchemy import exists
 from sqlalchemy.orm import Session
 
-from onyx.auth.users import current_user
+from onyx.auth.permissions import require_permission
 from onyx.db.engine.sql_engine import get_session
 from onyx.db.enums import BuildSessionStatus
+from onyx.db.enums import Permission
 from onyx.db.enums import SandboxStatus
 from onyx.db.models import BuildMessage
 from onyx.db.models import User
@@ -65,7 +66,7 @@ router = APIRouter(prefix="/sessions")
 
 @router.get("", response_model=SessionListResponse)
 def list_sessions(
-    user: User = Depends(current_user),
+    user: User = Depends(require_permission(Permission.BASIC_ACCESS)),
     db_session: Session = Depends(get_session),
 ) -> SessionListResponse:
     """List all build sessions for the current user."""
@@ -88,7 +89,7 @@ SESSION_CREATE_LOCK_TIMEOUT_SECONDS = 300
 @router.post("", response_model=DetailedSessionResponse)
 def create_session(
     request: SessionCreateRequest,
-    user: User = Depends(current_user),
+    user: User = Depends(require_permission(Permission.BASIC_ACCESS)),
     db_session: Session = Depends(get_session),
 ) -> DetailedSessionResponse:
     """
@@ -157,7 +158,7 @@ def create_session(
 @router.get("/{session_id}", response_model=DetailedSessionResponse)
 def get_session_details(
     session_id: UUID,
-    user: User = Depends(current_user),
+    user: User = Depends(require_permission(Permission.BASIC_ACCESS)),
     db_session: Session = Depends(get_session),
 ) -> DetailedSessionResponse:
     """
@@ -195,7 +196,7 @@ def get_session_details(
 )
 def check_pre_provisioned_session(
     session_id: UUID,
-    user: User = Depends(current_user),
+    user: User = Depends(require_permission(Permission.BASIC_ACCESS)),
     db_session: Session = Depends(get_session),
 ) -> PreProvisionedCheckResponse:
     """
@@ -228,7 +229,7 @@ def check_pre_provisioned_session(
 @router.post("/{session_id}/generate-name", response_model=SessionNameGenerateResponse)
 def generate_session_name(
     session_id: UUID,
-    user: User = Depends(current_user),
+    user: User = Depends(require_permission(Permission.BASIC_ACCESS)),
     db_session: Session = Depends(get_session),
 ) -> SessionNameGenerateResponse:
     """Generate a session name using LLM based on the first user message."""
@@ -248,7 +249,7 @@ def generate_session_name(
 def generate_suggestions(
     session_id: UUID,
     request: GenerateSuggestionsRequest,
-    user: User = Depends(current_user),
+    user: User = Depends(require_permission(Permission.BASIC_ACCESS)),
     db_session: Session = Depends(get_session),
 ) -> GenerateSuggestionsResponse:
     """Generate follow-up suggestions based on the first exchange in a session."""
@@ -281,7 +282,7 @@ def generate_suggestions(
 def update_session_name(
     session_id: UUID,
     request: SessionUpdateRequest,
-    user: User = Depends(current_user),
+    user: User = Depends(require_permission(Permission.BASIC_ACCESS)),
     db_session: Session = Depends(get_session),
 ) -> SessionResponse:
     """Update the name of a build session."""
@@ -301,7 +302,7 @@ def update_session_name(
 def set_session_public(
     session_id: UUID,
     request: SetSessionSharingRequest,
-    user: User = Depends(current_user),
+    user: User = Depends(require_permission(Permission.BASIC_ACCESS)),
     db_session: Session = Depends(get_session),
 ) -> SetSessionSharingResponse:
     """Set the sharing scope of a build session's webapp."""
@@ -319,7 +320,7 @@ def set_session_public(
 @router.delete("/{session_id}", response_model=None)
 def delete_session(
     session_id: UUID,
-    user: User = Depends(current_user),
+    user: User = Depends(require_permission(Permission.BASIC_ACCESS)),
     db_session: Session = Depends(get_session),
 ) -> Response:
     """Delete a build session and all associated data.
@@ -356,7 +357,7 @@ RESTORE_LOCK_TIMEOUT_SECONDS = 300
 @router.post("/{session_id}/restore", response_model=DetailedSessionResponse)
 def restore_session(
     session_id: UUID,
-    user: User = Depends(current_user),
+    user: User = Depends(require_permission(Permission.BASIC_ACCESS)),
     db_session: Session = Depends(get_session),
 ) -> DetailedSessionResponse:
     """Restore sandbox and load session snapshot. Blocks until complete.
@@ -536,7 +537,7 @@ def restore_session(
 )
 def list_artifacts(
     session_id: UUID,
-    user: User = Depends(current_user),
+    user: User = Depends(require_permission(Permission.BASIC_ACCESS)),
     db_session: Session = Depends(get_session),
 ) -> list[dict]:
     """List artifacts generated in the session."""
@@ -554,7 +555,7 @@ def list_artifacts(
 def list_directory(
     session_id: UUID,
     path: str = "",
-    user: User = Depends(current_user),
+    user: User = Depends(require_permission(Permission.BASIC_ACCESS)),
     db_session: Session = Depends(get_session),
 ) -> DirectoryListing:
     """
@@ -592,7 +593,7 @@ def list_directory(
 def download_artifact(
     session_id: UUID,
     path: str,
-    user: User = Depends(current_user),
+    user: User = Depends(require_permission(Permission.BASIC_ACCESS)),
     db_session: Session = Depends(get_session),
 ) -> Response:
     """Download a specific artifact file."""
@@ -643,7 +644,7 @@ def download_artifact(
 def export_docx(
     session_id: UUID,
     path: str,
-    user: User = Depends(current_user),
+    user: User = Depends(require_permission(Permission.BASIC_ACCESS)),
     db_session: Session = Depends(get_session),
 ) -> Response:
     """Export a markdown file as DOCX."""
@@ -685,7 +686,7 @@ def export_docx(
 def get_pptx_preview(
     session_id: UUID,
     path: str,
-    user: User = Depends(current_user),
+    user: User = Depends(require_permission(Permission.BASIC_ACCESS)),
     db_session: Session = Depends(get_session),
 ) -> PptxPreviewResponse:
     """Generate slide image previews for a PPTX file."""
@@ -711,7 +712,7 @@ def get_pptx_preview(
 @router.get("/{session_id}/webapp-info", response_model=WebappInfo)
 def get_webapp_info(
     session_id: UUID,
-    user: User = Depends(current_user),
+    user: User = Depends(require_permission(Permission.BASIC_ACCESS)),
     db_session: Session = Depends(get_session),
 ) -> WebappInfo:
     """
@@ -733,7 +734,7 @@ def get_webapp_info(
 @router.get("/{session_id}/webapp-download")
 def download_webapp(
     session_id: UUID,
-    user: User = Depends(current_user),
+    user: User = Depends(require_permission(Permission.BASIC_ACCESS)),
     db_session: Session = Depends(get_session),
 ) -> Response:
     """
@@ -764,7 +765,7 @@ def download_webapp(
 def download_directory(
     session_id: UUID,
     path: str,
-    user: User = Depends(current_user),
+    user: User = Depends(require_permission(Permission.BASIC_ACCESS)),
     db_session: Session = Depends(get_session),
 ) -> Response:
     """
@@ -801,7 +802,7 @@ def download_directory(
 def upload_file_endpoint(
     session_id: UUID,
     file: UploadFile = File(...),
-    user: User = Depends(current_user),
+    user: User = Depends(require_permission(Permission.BASIC_ACCESS)),
     db_session: Session = Depends(get_session),
 ) -> UploadResponse:
     """Upload a file to the session's sandbox.
@@ -852,7 +853,7 @@ def upload_file_endpoint(
 def delete_file_endpoint(
     session_id: UUID,
     path: str,
-    user: User = Depends(current_user),
+    user: User = Depends(require_permission(Permission.BASIC_ACCESS)),
     db_session: Session = Depends(get_session),
 ) -> Response:
     """Delete a file from the session's sandbox.

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

@@ -38,7 +38,7 @@ from fastapi import UploadFile
 from pydantic import BaseModel
 from sqlalchemy.orm import Session
 
-from onyx.auth.users import current_user
+from onyx.auth.permissions import require_permission
 from onyx.background.celery.versioned_apps.client import app as celery_app
 from onyx.configs.constants import DocumentSource
 from onyx.configs.constants import OnyxCeleryQueues
@@ -48,6 +48,7 @@ from onyx.db.document import upsert_document_by_connector_credential_pair
 from onyx.db.document import upsert_documents
 from onyx.db.engine.sql_engine import get_session
 from onyx.db.enums import ConnectorCredentialPairStatus
+from onyx.db.enums import Permission
 from onyx.db.models import User
 from onyx.document_index.interfaces import DocumentMetadata
 from onyx.server.features.build.configs import USER_LIBRARY_MAX_FILE_SIZE_BYTES
@@ -281,7 +282,7 @@ def _store_and_track_file(
 
 @router.get("/tree")
 def get_library_tree(
-    user: User = Depends(current_user),
+    user: User = Depends(require_permission(Permission.BASIC_ACCESS)),
     db_session: Session = Depends(get_session),
 ) -> list[LibraryEntryResponse]:
     """Get user's uploaded files as a tree structure.
@@ -322,7 +323,7 @@ def get_library_tree(
 async def upload_files(
     files: list[UploadFile] = File(...),
     path: str = Form("/"),
-    user: User = Depends(current_user),
+    user: User = Depends(require_permission(Permission.BASIC_ACCESS)),
     db_session: Session = Depends(get_session),
 ) -> UploadResponse:
     """Upload files directly to S3 and track in PostgreSQL.
@@ -439,7 +440,7 @@ async def upload_files(
 async def upload_zip(
     file: UploadFile = File(...),
     path: str = Form("/"),
-    user: User = Depends(current_user),
+    user: User = Depends(require_permission(Permission.BASIC_ACCESS)),
     db_session: Session = Depends(get_session),
 ) -> UploadResponse:
     """Upload and extract a zip file, storing each extracted file to S3.
@@ -608,7 +609,7 @@ async def upload_zip(
 @router.post("/directories")
 def create_directory(
     request: CreateDirectoryRequest,
-    user: User = Depends(current_user),
+    user: User = Depends(require_permission(Permission.BASIC_ACCESS)),
     db_session: Session = Depends(get_session),
 ) -> LibraryEntryResponse:
     """Create a virtual directory.
@@ -658,7 +659,7 @@ def create_directory(
 def toggle_file_sync(
     document_id: str,
     enabled: bool = Query(...),
-    user: User = Depends(current_user),
+    user: User = Depends(require_permission(Permission.BASIC_ACCESS)),
     db_session: Session = Depends(get_session),
 ) -> ToggleSyncResponse:
     """Enable/disable syncing a file to sandboxes.
@@ -710,7 +711,7 @@ def toggle_file_sync(
 @router.delete("/files/{document_id}")
 def delete_file(
     document_id: str,
-    user: User = Depends(current_user),
+    user: User = Depends(require_permission(Permission.BASIC_ACCESS)),
     db_session: Session = Depends(get_session),
 ) -> DeleteFileResponse:
     """Delete a file from both S3 and the document table."""

backend/onyx/server/features/build/sandbox/kubernetes/docker/README.md

@@ -58,7 +58,7 @@ docker buildx build --platform linux/amd64,linux/arm64 \
 
 1. **Build and push** the new image (see above)
 
-2. **Update the ConfigMap** in `cloud-deployment-yamls/danswer/configmap/env-configmap.yaml`:
+2. **Update the ConfigMap** in in the internal repo
    ```yaml
    SANDBOX_CONTAINER_IMAGE: "onyxdotapp/sandbox:v0.1.x"
    ```

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

@@ -5,8 +5,9 @@ from fastapi import Depends
 from fastapi import HTTPException
 from sqlalchemy.orm import Session
 
-from onyx.auth.users import current_admin_user
+from onyx.auth.permissions import require_permission
 from onyx.db.engine.sql_engine import get_session
+from onyx.db.enums import Permission
 from onyx.db.models import User
 from onyx.db.persona import get_default_assistant
 from onyx.db.persona import update_default_assistant_configuration
@@ -22,7 +23,7 @@ router = APIRouter(prefix="/admin/default-assistant")
 
 @router.get("/configuration")
 def get_default_assistant_configuration(
-    _: User = Depends(current_admin_user),
+    _: User = Depends(require_permission(Permission.FULL_ADMIN_PANEL_ACCESS)),
     db_session: Session = Depends(get_session),
 ) -> DefaultAssistantConfiguration:
     """Get the current default assistant configuration.
@@ -47,7 +48,7 @@ def get_default_assistant_configuration(
 @router.patch("")
 def update_default_assistant(
     update_request: DefaultAssistantUpdateRequest,
-    _: User = Depends(current_admin_user),
+    _: User = Depends(require_permission(Permission.FULL_ADMIN_PANEL_ACCESS)),
     db_session: Session = Depends(get_session),
 ) -> DefaultAssistantConfiguration:
     """Update the default assistant configuration.

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

@@ -4,8 +4,8 @@ from fastapi import HTTPException
 from fastapi import Query
 from sqlalchemy.orm import Session
 
+from onyx.auth.permissions import require_permission
 from onyx.auth.users import current_curator_or_admin_user
-from onyx.auth.users import current_user
 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
@@ -18,6 +18,7 @@ from onyx.db.document_set import insert_document_set
 from onyx.db.document_set import mark_document_set_as_to_be_deleted
 from onyx.db.document_set import update_document_set
 from onyx.db.engine.sql_engine import get_session
+from onyx.db.enums import Permission
 from onyx.db.models import User
 from onyx.server.features.document_set.models import CheckDocSetPublicRequest
 from onyx.server.features.document_set.models import CheckDocSetPublicResponse
@@ -159,7 +160,7 @@ def delete_document_set(
 
 @router.get("/document-set")
 def list_document_sets_for_user(
-    user: User = Depends(current_user),
+    user: User = Depends(require_permission(Permission.BASIC_ACCESS)),
     db_session: Session = Depends(get_session),
     get_editable: bool = Query(
         False, description="If true, return editable document sets"
@@ -174,7 +175,7 @@ def list_document_sets_for_user(
 @router.get("/document-set-public")
 def document_set_public(
     check_public_request: CheckDocSetPublicRequest,
-    _: User = Depends(current_user),
+    _: User = Depends(require_permission(Permission.BASIC_ACCESS)),
     db_session: Session = Depends(get_session),
 ) -> CheckDocSetPublicResponse:
     is_public = check_document_sets_are_public(

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

@@ -4,11 +4,12 @@ from fastapi import HTTPException
 from sqlalchemy.orm import Session
 
 from onyx.access.hierarchy_access import get_user_external_group_ids
-from onyx.auth.users import current_user
+from onyx.auth.permissions import require_permission
 from onyx.configs.app_configs import ENABLE_OPENSEARCH_INDEXING_FOR_ONYX
 from onyx.configs.constants import DocumentSource
 from onyx.db.document import get_accessible_documents_for_hierarchy_node_paginated
 from onyx.db.engine.sql_engine import get_session
+from onyx.db.enums import Permission
 from onyx.db.hierarchy import get_accessible_hierarchy_nodes_for_source
 from onyx.db.models import User
 from onyx.db.opensearch_migration import get_opensearch_retrieval_state
@@ -58,7 +59,7 @@ def _get_user_access_info(user: User, db_session: Session) -> tuple[str, list[st
 @router.get(HIERARCHY_NODES_LIST_PATH)
 def list_accessible_hierarchy_nodes(
     source: DocumentSource,
-    user: User = Depends(current_user),
+    user: User = Depends(require_permission(Permission.BASIC_ACCESS)),
     db_session: Session = Depends(get_session),
 ) -> HierarchyNodesResponse:
     _require_opensearch(db_session)
@@ -85,7 +86,7 @@ def list_accessible_hierarchy_nodes(
 @router.post(HIERARCHY_NODE_DOCUMENTS_PATH)
 def list_accessible_hierarchy_node_documents(
     documents_request: HierarchyNodeDocumentsRequest,
-    user: User = Depends(current_user),
+    user: User = Depends(require_permission(Permission.BASIC_ACCESS)),
     db_session: Session = Depends(get_session),
 ) -> HierarchyNodeDocumentsResponse:
     _require_opensearch(db_session)

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

@@ -3,9 +3,9 @@ from fastapi import Depends
 from fastapi import HTTPException
 from sqlalchemy.orm import Session
 
-from onyx.auth.users import current_admin_user
-from onyx.auth.users import current_user
+from onyx.auth.permissions import require_permission
 from onyx.db.engine.sql_engine import get_session
+from onyx.db.enums import Permission
 from onyx.db.input_prompt import disable_input_prompt_for_user
 from onyx.db.input_prompt import fetch_input_prompt_by_id
 from onyx.db.input_prompt import fetch_input_prompts_by_user
@@ -28,7 +28,7 @@ admin_router = APIRouter(prefix="/admin/input_prompt")
 
 @basic_router.get("")
 def list_input_prompts(
-    user: User = Depends(current_user),
+    user: User = Depends(require_permission(Permission.BASIC_ACCESS)),
     include_public: bool = True,
     db_session: Session = Depends(get_session),
 ) -> list[InputPromptSnapshot]:
@@ -43,7 +43,7 @@ def list_input_prompts(
 @basic_router.get("/{input_prompt_id}")
 def get_input_prompt(
     input_prompt_id: int,
-    user: User = Depends(current_user),
+    user: User = Depends(require_permission(Permission.BASIC_ACCESS)),
     db_session: Session = Depends(get_session),
 ) -> InputPromptSnapshot:
     input_prompt = fetch_input_prompt_by_id(
@@ -58,7 +58,7 @@ def get_input_prompt(
 @basic_router.post("")
 def create_input_prompt(
     create_input_prompt_request: CreateInputPromptRequest,
-    user: User = Depends(current_user),
+    user: User = Depends(require_permission(Permission.BASIC_ACCESS)),
     db_session: Session = Depends(get_session),
 ) -> InputPromptSnapshot:
     input_prompt = insert_input_prompt(
@@ -82,7 +82,7 @@ def create_input_prompt(
 def patch_input_prompt(
     input_prompt_id: int,
     update_input_prompt_request: UpdateInputPromptRequest,
-    user: User = Depends(current_user),
+    user: User = Depends(require_permission(Permission.BASIC_ACCESS)),
     db_session: Session = Depends(get_session),
 ) -> InputPromptSnapshot:
     try:
@@ -105,7 +105,7 @@ def patch_input_prompt(
 @basic_router.delete("/{input_prompt_id}")
 def delete_input_prompt(
     input_prompt_id: int,
-    user: User = Depends(current_user),
+    user: User = Depends(require_permission(Permission.BASIC_ACCESS)),
     db_session: Session = Depends(get_session),
     delete_public: bool = False,
 ) -> None:
@@ -123,7 +123,7 @@ def delete_input_prompt(
 @admin_router.delete("/{input_prompt_id}")
 def delete_public_input_prompt(
     input_prompt_id: int,
-    _: User = Depends(current_admin_user),
+    _: User = Depends(require_permission(Permission.FULL_ADMIN_PANEL_ACCESS)),
     db_session: Session = Depends(get_session),
 ) -> None:
     try:
@@ -138,7 +138,7 @@ def delete_public_input_prompt(
 @basic_router.post("/{input_prompt_id}/hide")
 def hide_input_prompt_for_user(
     input_prompt_id: int,
-    user: User = Depends(current_user),
+    user: User = Depends(require_permission(Permission.BASIC_ACCESS)),
     db_session: Session = Depends(get_session),
 ) -> None:
     """

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

@@ -25,9 +25,9 @@ from pydantic import AnyUrl
 from pydantic import BaseModel
 from sqlalchemy.orm import Session
 
+from onyx.auth.permissions import require_permission
 from onyx.auth.schemas import UserRole
 from onyx.auth.users import current_curator_or_admin_user
-from onyx.auth.users import current_user
 from onyx.configs.app_configs import WEB_DOMAIN
 from onyx.db.engine.sql_engine import get_session
 from onyx.db.engine.sql_engine import get_session_with_current_tenant
@@ -35,6 +35,7 @@ from onyx.db.enums import MCPAuthenticationPerformer
 from onyx.db.enums import MCPAuthenticationType
 from onyx.db.enums import MCPServerStatus
 from onyx.db.enums import MCPTransport
+from onyx.db.enums import Permission
 from onyx.db.mcp import create_connection_config
 from onyx.db.mcp import create_mcp_server__no_commit
 from onyx.db.mcp import delete_all_user_connection_configs_for_server_no_commit
@@ -95,6 +96,32 @@ def _truncate_description(description: str | None, max_length: int = 500) -> str
     return description[: max_length - 3] + "..."
 
 
+# TODO: Replace mask-comparison approach with an explicit Unset sentinel from the
+# frontend indicating whether each credential field was actually modified. The current
+# approach is brittle (e.g. short credentials produce a fixed-length mask that could
+# collide) and mutates request values, which is surprising. The frontend should signal
+# "unchanged" vs "new value" directly rather than relying on masked-string equality.
+def _restore_masked_oauth_credentials(
+    request_client_id: str | None,
+    request_client_secret: str | None,
+    existing_client: OAuthClientInformationFull,
+) -> tuple[str | None, str | None]:
+    """If the frontend sent back masked credentials, restore the real stored values."""
+    if (
+        request_client_id
+        and existing_client.client_id
+        and request_client_id == mask_string(existing_client.client_id)
+    ):
+        request_client_id = existing_client.client_id
+    if (
+        request_client_secret
+        and existing_client.client_secret
+        and request_client_secret == mask_string(existing_client.client_secret)
+    ):
+        request_client_secret = existing_client.client_secret
+    return request_client_id, request_client_secret
+
+
 router = APIRouter(prefix="/mcp")
 admin_router = APIRouter(prefix="/admin/mcp")
 STATE_TTL_SECONDS = 60 * 5  # 5 minutes
@@ -360,7 +387,7 @@ async def connect_admin_oauth(
 async def connect_user_oauth(
     request: MCPUserOAuthConnectRequest,
     db: Session = Depends(get_session),
-    user: User = Depends(current_user),
+    user: User = Depends(require_permission(Permission.BASIC_ACCESS)),
 ) -> MCPUserOAuthConnectResponse:
     return await _connect_oauth(request, db, is_admin=False, user=user)
 
@@ -391,6 +418,26 @@ async def _connect_oauth(
             detail=f"Server was configured with authentication type {auth_type_str}",
         )
 
+    # If the frontend sent back masked credentials (unchanged by the user),
+    # restore the real stored values so we don't overwrite them with masks.
+    if mcp_server.admin_connection_config:
+        existing_data = extract_connection_data(
+            mcp_server.admin_connection_config, apply_mask=False
+        )
+        existing_client_raw = existing_data.get(MCPOAuthKeys.CLIENT_INFO.value)
+        if existing_client_raw:
+            existing_client = OAuthClientInformationFull.model_validate(
+                existing_client_raw
+            )
+            (
+                request.oauth_client_id,
+                request.oauth_client_secret,
+            ) = _restore_masked_oauth_credentials(
+                request.oauth_client_id,
+                request.oauth_client_secret,
+                existing_client,
+            )
+
     # Create admin config with client info if provided
     config_data = MCPConnectionData(headers={})
     if request.oauth_client_id and request.oauth_client_secret:
@@ -572,7 +619,7 @@ async def _connect_oauth(
 async def process_oauth_callback(
     request: Request,
     db_session: Session = Depends(get_session),
-    user: User = Depends(current_user),
+    user: User = Depends(require_permission(Permission.BASIC_ACCESS)),
 ) -> MCPOAuthCallbackResponse:
     """Complete OAuth flow by exchanging code for tokens and storing them.
 
@@ -655,7 +702,7 @@ async def process_oauth_callback(
 def save_user_credentials(
     request: MCPUserCredentialsRequest,
     db_session: Session = Depends(get_session),
-    user: User = Depends(current_user),
+    user: User = Depends(require_permission(Permission.BASIC_ACCESS)),
 ) -> MCPApiKeyResponse:
     """Save user credentials for template-based MCP server authentication"""
 
@@ -983,7 +1030,7 @@ def _db_mcp_server_to_api_mcp_server(
 def get_mcp_servers_for_assistant(
     assistant_id: str,
     db: Session = Depends(get_session),
-    user: User = Depends(current_user),
+    user: User = Depends(require_permission(Permission.BASIC_ACCESS)),
 ) -> MCPServersResponse:
     """Get MCP servers for an assistant"""
 
@@ -1011,7 +1058,7 @@ def get_mcp_servers_for_assistant(
 @router.get("/servers", response_model=MCPServersResponse)
 def get_mcp_servers_for_user(
     db: Session = Depends(get_session),
-    user: User = Depends(current_user),
+    user: User = Depends(require_permission(Permission.BASIC_ACCESS)),
 ) -> MCPServersResponse:
     """List all MCP servers for use in agent configuration and chat UI.
 
@@ -1140,7 +1187,7 @@ def get_mcp_server_tools_snapshots(
 def user_list_mcp_tools_by_id(
     server_id: int,
     db: Session = Depends(get_session),
-    user: User = Depends(current_user),
+    user: User = Depends(require_permission(Permission.BASIC_ACCESS)),
 ) -> MCPToolListResponse:
     return _list_mcp_tools_by_id(server_id, db, False, user)
 
@@ -1355,6 +1402,19 @@ def _upsert_mcp_server(
             if client_info_raw:
                 client_info = OAuthClientInformationFull.model_validate(client_info_raw)
 
+        # If the frontend sent back masked credentials (unchanged by the user),
+        # restore the real stored values so the comparison below sees no change
+        # and the credentials aren't overwritten with masked strings.
+        if client_info and request.auth_type == MCPAuthenticationType.OAUTH:
+            (
+                request.oauth_client_id,
+                request.oauth_client_secret,
+            ) = _restore_masked_oauth_credentials(
+                request.oauth_client_id,
+                request.oauth_client_secret,
+                client_info,
+            )
+
         changing_connection_config = (
             not mcp_server.admin_connection_config
             or (

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

@@ -3,8 +3,9 @@ from fastapi import Depends
 from fastapi import HTTPException
 from sqlalchemy.orm import Session
 
-from onyx.auth.users import current_user
+from onyx.auth.permissions import require_permission
 from onyx.db.engine.sql_engine import get_session
+from onyx.db.enums import Permission
 from onyx.db.models import User
 from onyx.db.notification import dismiss_notification
 from onyx.db.notification import get_notification_by_id
@@ -22,7 +23,7 @@ router = APIRouter(prefix="/notifications")
 
 @router.get("")
 def get_notifications_api(
-    user: User = Depends(current_user),
+    user: User = Depends(require_permission(Permission.BASIC_ACCESS)),
     db_session: Session = Depends(get_session),
 ) -> list[NotificationModel]:
     """
@@ -58,7 +59,7 @@ def get_notifications_api(
 @router.post("/{notification_id}/dismiss")
 def dismiss_notification_endpoint(
     notification_id: int,
-    user: User = Depends(current_user),
+    user: User = Depends(require_permission(Permission.BASIC_ACCESS)),
     db_session: Session = Depends(get_session),
 ) -> None:
     try:

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

@@ -6,10 +6,11 @@ from fastapi import HTTPException
 from sqlalchemy.orm import Session
 
 from onyx.auth.oauth_token_manager import OAuthTokenManager
+from onyx.auth.permissions import require_permission
 from onyx.auth.users import current_curator_or_admin_user
-from onyx.auth.users import current_user
 from onyx.configs.app_configs import WEB_DOMAIN
 from onyx.db.engine.sql_engine import get_session
+from onyx.db.enums import Permission
 from onyx.db.models import OAuthConfig
 from onyx.db.models import User
 from onyx.db.oauth_config import create_oauth_config
@@ -155,7 +156,7 @@ def delete_oauth_config_endpoint(
 def initiate_oauth_flow(
     request: OAuthInitiateRequest,
     db_session: Session = Depends(get_session),
-    user: User = Depends(current_user),
+    user: User = Depends(require_permission(Permission.BASIC_ACCESS)),
 ) -> OAuthInitiateResponse:
     """
     Initiate OAuth flow for the current user.
@@ -192,7 +193,7 @@ def handle_oauth_callback(
     code: str,
     state: str,
     db_session: Session = Depends(get_session),
-    user: User = Depends(current_user),
+    user: User = Depends(require_permission(Permission.BASIC_ACCESS)),
 ) -> OAuthCallbackResponse:
     """
     Handle OAuth callback after user authorizes the application.
@@ -253,7 +254,7 @@ def handle_oauth_callback(
 def revoke_oauth_token(
     oauth_config_id: int,
     db_session: Session = Depends(get_session),
-    user: User = Depends(current_user),
+    user: User = Depends(require_permission(Permission.BASIC_ACCESS)),
 ) -> dict[str, str]:
     """
     Revoke (delete) the current user's OAuth token for a specific OAuth config.