fix(pruning): GitHub connector pruning timeout via SlimConnector

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 +1,63 @@
+FROM ubuntu:26.04@sha256:cc925e589b7543b910fea57a240468940003fbfc0515245a495dd0ad8fe7cef1
+
+RUN apt-get update && apt-get install -y --no-install-recommends \
+  curl \
+  default-jre \
+  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@sha256:0f02d9299928849c7b15f3b348dcfdcdcb64411ff7a4580cbc026a6ee7aa1554",
+  "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
@@ -44,7 +44,7 @@ jobs:
           fetch-tags: true
 
       - name: Setup uv
-        uses: astral-sh/setup-uv@37802adc94f370d6bfd71619e3f0bf239e1f3b78 # ratchet:astral-sh/setup-uv@v7
+        uses: astral-sh/setup-uv@cec208311dfd045dd5311c1add060b2062131d57 # ratchet:astral-sh/setup-uv@v8.0.0
         with:
           version: "0.9.9"
           enable-cache: false
@@ -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
@@ -165,7 +165,7 @@ jobs:
           fetch-depth: 0
 
       - name: Setup uv
-        uses: astral-sh/setup-uv@37802adc94f370d6bfd71619e3f0bf239e1f3b78 # ratchet:astral-sh/setup-uv@v7
+        uses: astral-sh/setup-uv@cec208311dfd045dd5311c1add060b2062131d57 # ratchet:astral-sh/setup-uv@v8.0.0
         with:
           version: "0.9.9"
           # NOTE: This isn't caching much and zizmor suggests this could be poisoned, so disable.

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

@@ -114,7 +114,7 @@ jobs:
           ref: main
 
       - name: Install the latest version of uv
-        uses: astral-sh/setup-uv@37802adc94f370d6bfd71619e3f0bf239e1f3b78 # ratchet:astral-sh/setup-uv@v7
+        uses: astral-sh/setup-uv@cec208311dfd045dd5311c1add060b2062131d57 # ratchet:astral-sh/setup-uv@v8.0.0
         with:
           enable-cache: false
           version: "0.9.9"

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

@@ -471,7 +471,7 @@ jobs:
 
       - name: Install the latest version of uv
         if: always()
-        uses: astral-sh/setup-uv@37802adc94f370d6bfd71619e3f0bf239e1f3b78 # ratchet:astral-sh/setup-uv@v7
+        uses: astral-sh/setup-uv@cec208311dfd045dd5311c1add060b2062131d57 # ratchet:astral-sh/setup-uv@v8.0.0
         with:
           enable-cache: false
           version: "0.9.9"
@@ -710,7 +710,7 @@ jobs:
       pull-requests: write
     steps:
       - name: Download visual diff summaries
-        uses: actions/download-artifact@70fc10c6e5e1ce46ad2ea6f2b72d43f7d47b13c3
+        uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c
         with:
           pattern: screenshot-diff-summary-*
           path: summaries/

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

@@ -38,7 +38,7 @@ jobs:
       - name: Install node dependencies
         working-directory: ./web
         run: npm ci
-      - uses: j178/prek-action@0bb87d7f00b0c99306c8bcb8b8beba1eb581c037 # ratchet:j178/prek-action@v1
+      - uses: j178/prek-action@cbc2f23eb5539cf20d82d1aabd0d0ecbcc56f4e3
         with:
           prek-version: '0.3.4'
           extra-args: ${{ github.event_name == 'pull_request' && format('--from-ref {0} --to-ref {1}', github.event.pull_request.base.sha, github.event.pull_request.head.sha) || github.event_name == 'merge_group' && format('--from-ref {0} --to-ref {1}', github.event.merge_group.base_sha, github.event.merge_group.head_sha) || github.ref_name == 'main' && '--all-files' || '' }}

.github/workflows/release-cli.yml

@@ -17,7 +17,7 @@ jobs:
       - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # ratchet:actions/checkout@v6
         with:
           persist-credentials: false
-      - uses: astral-sh/setup-uv@37802adc94f370d6bfd71619e3f0bf239e1f3b78 # ratchet:astral-sh/setup-uv@v7
+      - uses: astral-sh/setup-uv@cec208311dfd045dd5311c1add060b2062131d57 # ratchet:astral-sh/setup-uv@v8.0.0
         with:
           enable-cache: false
           version: "0.9.9"

.github/workflows/release-devtools.yml

@@ -26,7 +26,7 @@ jobs:
       - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # ratchet:actions/checkout@v6
         with:
           persist-credentials: false
-      - uses: astral-sh/setup-uv@37802adc94f370d6bfd71619e3f0bf239e1f3b78 # ratchet:astral-sh/setup-uv@v7
+      - uses: astral-sh/setup-uv@cec208311dfd045dd5311c1add060b2062131d57 # ratchet:astral-sh/setup-uv@v8.0.0
         with:
           enable-cache: false
           version: "0.9.9"

.github/workflows/zizmor.yml

@@ -24,7 +24,7 @@ jobs:
           persist-credentials: false
 
       - name: Install the latest version of uv
-        uses: astral-sh/setup-uv@37802adc94f370d6bfd71619e3f0bf239e1f3b78 # ratchet:astral-sh/setup-uv@v7
+        uses: astral-sh/setup-uv@cec208311dfd045dd5311c1add060b2062131d57 # ratchet:astral-sh/setup-uv@v8.0.0
         with:
           enable-cache: false
           version: "0.9.9"

.greptile/config.json

@@ -1,64 +1,57 @@
 {
-    "labels": [],
-    "comment": "",
-    "fixWithAI": true,
-    "hideFooter": false,
-    "strictness": 3,
-    "statusCheck": true,
-    "commentTypes": [
-      "logic",
-      "syntax",
-      "style"
-    ],
-    "instructions": "",
-    "disabledLabels": [],
-    "excludeAuthors": [
-      "dependabot[bot]",
-      "renovate[bot]"
-    ],
-    "ignoreKeywords": "",
-    "ignorePatterns": "",
-    "includeAuthors": [],
-    "summarySection": {
-      "included": true,
-      "collapsible": false,
-      "defaultOpen": false
+  "labels": [],
+  "comment": "",
+  "fixWithAI": true,
+  "hideFooter": false,
+  "strictness": 3,
+  "statusCheck": true,
+  "commentTypes": ["logic", "syntax", "style"],
+  "instructions": "",
+  "disabledLabels": [],
+  "excludeAuthors": ["dependabot[bot]", "renovate[bot]"],
+  "ignoreKeywords": "",
+  "ignorePatterns": "",
+  "includeAuthors": [],
+  "summarySection": {
+    "included": true,
+    "collapsible": false,
+    "defaultOpen": false
+  },
+  "excludeBranches": [],
+  "fileChangeLimit": 300,
+  "includeBranches": [],
+  "includeKeywords": "",
+  "triggerOnUpdates": false,
+  "updateExistingSummaryComment": true,
+  "updateSummaryOnly": false,
+  "issuesTableSection": {
+    "included": true,
+    "collapsible": false,
+    "defaultOpen": false
+  },
+  "statusCommentsEnabled": true,
+  "confidenceScoreSection": {
+    "included": true,
+    "collapsible": false
+  },
+  "sequenceDiagramSection": {
+    "included": true,
+    "collapsible": false,
+    "defaultOpen": false
+  },
+  "shouldUpdateDescription": false,
+  "rules": [
+    {
+      "scope": ["web/**"],
+      "rule": "In Onyx's Next.js app, the `app/ee/admin/` directory is a filesystem convention for Enterprise Edition route overrides — it does NOT add an `/ee/` prefix to the URL. Both `app/admin/groups/page.tsx` and `app/ee/admin/groups/page.tsx` serve the same URL `/admin/groups`. Hardcoded `/admin/...` paths in router.push() calls are correct and do NOT break EE deployments. Do not flag hardcoded admin paths as bugs."
     },
-    "excludeBranches": [],
-    "fileChangeLimit": 300,
-    "includeBranches": [],
-    "includeKeywords": "",
-    "triggerOnUpdates": true,
-    "updateExistingSummaryComment": true,
-    "updateSummaryOnly": false,
-    "issuesTableSection": {
-      "included": true,
-      "collapsible": false,
-      "defaultOpen": false
+    {
+      "scope": ["web/**"],
+      "rule": "In Onyx, each API key creates a unique user row in the database with a unique `user_id` (UUID). There is a 1:1 mapping between API keys and their backing user records. Multiple API keys do NOT share the same `user_id`. Do not flag potential duplicate row IDs when using `user_id` from API key descriptors."
     },
-    "statusCommentsEnabled": true,
-    "confidenceScoreSection": {
-      "included": true,
-      "collapsible": false
-    },
-    "sequenceDiagramSection": {
-      "included": true,
-      "collapsible": false,
-      "defaultOpen": false
-    },
-    "shouldUpdateDescription": false,
-    "rules": [
-      {
-        "scope": ["web/**"],
-        "rule": "In Onyx's Next.js app, the `app/ee/admin/` directory is a filesystem convention for Enterprise Edition route overrides — it does NOT add an `/ee/` prefix to the URL. Both `app/admin/groups/page.tsx` and `app/ee/admin/groups/page.tsx` serve the same URL `/admin/groups`. Hardcoded `/admin/...` paths in router.push() calls are correct and do NOT break EE deployments. Do not flag hardcoded admin paths as bugs."
-      },
-      {
-        "scope": ["web/**"],
-        "rule": "In Onyx, each API key creates a unique user row in the database with a unique `user_id` (UUID). There is a 1:1 mapping between API keys and their backing user records. Multiple API keys do NOT share the same `user_id`. Do not flag potential duplicate row IDs when using `user_id` from API key descriptors."
-      },
-      {
-        "scope": ["backend/**/*.py"],
-        "rule": "Never raise HTTPException directly in business code. Use `raise OnyxError(OnyxErrorCode.XXX, \"message\")` from `onyx.error_handling.exceptions`. A global FastAPI exception handler converts OnyxError into structured JSON responses with {\"error_code\": \"...\", \"detail\": \"...\"}. Error codes are defined in `onyx.error_handling.error_codes.OnyxErrorCode`. For upstream errors with dynamic HTTP status codes, use `status_code_override`: `raise OnyxError(OnyxErrorCode.BAD_GATEWAY, detail, status_code_override=upstream_status)`."
-      }
-    ]
+    {
+      "scope": ["backend/**/*.py"],
+      "rule": "Never raise HTTPException directly in business code. Use `raise OnyxError(OnyxErrorCode.XXX, \"message\")` from `onyx.error_handling.exceptions`. A global FastAPI exception handler converts OnyxError into structured JSON responses with {\"error_code\": \"...\", \"detail\": \"...\"}. Error codes are defined in `onyx.error_handling.error_codes.OnyxErrorCode`. For upstream errors with dynamic HTTP status codes, use `status_code_override`: `raise OnyxError(OnyxErrorCode.BAD_GATEWAY, detail, status_code_override=upstream_status)`."
+    }
+  ]
 }

.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",

AGENTS.md

@@ -49,12 +49,12 @@ Onyx uses Celery for asynchronous task processing with multiple specialized work
 
 4. **Light Worker** (`light`)
    - Handles lightweight, fast operations
-   - Tasks: vespa operations, document permissions sync, external group sync
+   - Tasks: vespa metadata sync, connector deletion, doc permissions upsert, checkpoint cleanup, index attempt cleanup
    - Higher concurrency for quick tasks
 
 5. **Heavy Worker** (`heavy`)
    - Handles resource-intensive operations
-   - Primary task: document pruning operations
+   - Tasks: connector pruning, document permissions sync, external group sync, CSV generation
    - Runs with 4 threads concurrency
 
 6. **KG Processing Worker** (`kg_processing`)

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/Dockerfile

@@ -1,4 +1,4 @@
-FROM python:3.11.7-slim-bookworm
+FROM python:3.11-slim-bookworm@sha256:9c6f90801e6b68e772b7c0ca74260cbf7af9f320acec894e26fccdaccfbe3b47
 
 LABEL com.danswer.maintainer="founders@onyx.app"
 LABEL com.danswer.description="This image is the web/frontend container of Onyx which \

backend/Dockerfile.model_server

@@ -1,5 +1,5 @@
 # Base stage with dependencies
-FROM python:3.11.7-slim-bookworm AS base
+FROM python:3.11-slim-bookworm@sha256:9c6f90801e6b68e772b7c0ca74260cbf7af9f320acec894e26fccdaccfbe3b47 AS base
 
 ENV DANSWER_RUNNING_IN_DOCKER="true" \
     HF_HOME=/app/.cache/huggingface

backend/alembic/env.py

@@ -208,7 +208,7 @@ def do_run_migrations(
 
     context.configure(
         connection=connection,
-        target_metadata=target_metadata,  # type: ignore
+        target_metadata=target_metadata,
         version_table_schema=schema_name,
         include_schemas=True,
         compare_type=True,
@@ -380,7 +380,7 @@ def run_migrations_offline() -> None:
             logger.info(f"Migrating schema: {schema}")
             context.configure(
                 url=url,
-                target_metadata=target_metadata,  # type: ignore
+                target_metadata=target_metadata,
                 literal_binds=True,
                 version_table_schema=schema,
                 include_schemas=True,
@@ -421,7 +421,7 @@ def run_migrations_offline() -> None:
             logger.info(f"Migrating schema: {schema}")
             context.configure(
                 url=url,
-                target_metadata=target_metadata,  # type: ignore
+                target_metadata=target_metadata,
                 literal_binds=True,
                 version_table_schema=schema,
                 include_schemas=True,
@@ -464,7 +464,7 @@ def run_migrations_online() -> None:
 
             context.configure(
                 connection=connection,
-                target_metadata=target_metadata,  # type: ignore
+                target_metadata=target_metadata,
                 version_table_schema=schema_name,
                 include_schemas=True,
                 compare_type=True,

backend/alembic/versions/351faebd379d_add_curator_fields.py

@@ -25,7 +25,7 @@ def upgrade() -> None:
 
     # Use batch mode to modify the enum type
     with op.batch_alter_table("user", schema=None) as batch_op:
-        batch_op.alter_column(  # type: ignore[attr-defined]
+        batch_op.alter_column(
             "role",
             type_=sa.Enum(
                 "BASIC",
@@ -71,7 +71,7 @@ def downgrade() -> None:
     op.drop_column("user__user_group", "is_curator")
 
     with op.batch_alter_table("user", schema=None) as batch_op:
-        batch_op.alter_column(  # type: ignore[attr-defined]
+        batch_op.alter_column(
             "role",
             type_=sa.Enum(
                 "BASIC", "ADMIN", name="userrole", native_enum=False, length=20

backend/alembic/versions/6d387b3196c2_basic_auth.py

@@ -63,7 +63,7 @@ def upgrade() -> None:
         "time_created",
         existing_type=postgresql.TIMESTAMP(timezone=True),
         nullable=False,
-        existing_server_default=sa.text("now()"),  # type: ignore
+        existing_server_default=sa.text("now()"),
     )
     op.alter_column(
         "index_attempt",
@@ -85,7 +85,7 @@ def downgrade() -> None:
         "time_created",
         existing_type=postgresql.TIMESTAMP(timezone=True),
         nullable=True,
-        existing_server_default=sa.text("now()"),  # type: ignore
+        existing_server_default=sa.text("now()"),
     )
     op.drop_index(op.f("ix_accesstoken_created_at"), table_name="accesstoken")
     op.drop_table("accesstoken")

backend/alembic/versions/800f48024ae9_add_id_to_connectorcredentialpair.py

@@ -19,7 +19,7 @@ depends_on: None = None
 
 def upgrade() -> None:
     sequence = Sequence("connector_credential_pair_id_seq")
-    op.execute(CreateSequence(sequence))  # type: ignore
+    op.execute(CreateSequence(sequence))
     op.add_column(
         "connector_credential_pair",
         sa.Column(

backend/alembic/versions/d129f37b3d87_add_error_tracking_fields_to_index_.py

@@ -0,0 +1,28 @@
+"""add_error_tracking_fields_to_index_attempt_errors
+
+Revision ID: d129f37b3d87
+Revises: 503883791c39
+Create Date: 2026-04-06 19:11:18.261800
+
+"""
+
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision = "d129f37b3d87"
+down_revision = "503883791c39"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    op.add_column(
+        "index_attempt_errors",
+        sa.Column("error_type", sa.String(), nullable=True),
+    )
+
+
+def downgrade() -> None:
+    op.drop_column("index_attempt_errors", "error_type")

backend/alembic_tenants/env.py

@@ -49,7 +49,7 @@ def run_migrations_offline() -> None:
     url = build_connection_string()
     context.configure(
         url=url,
-        target_metadata=target_metadata,  # type: ignore
+        target_metadata=target_metadata,
         literal_binds=True,
         dialect_opts={"paramstyle": "named"},
     )
@@ -61,7 +61,7 @@ def run_migrations_offline() -> None:
 def do_run_migrations(connection: Connection) -> None:
     context.configure(
         connection=connection,
-        target_metadata=target_metadata,  # type: ignore[arg-type]
+        target_metadata=target_metadata,
     )
 
     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/model_server/main.py

@@ -96,11 +96,14 @@ def get_model_app() -> FastAPI:
         title="Onyx Model Server", version=__version__, lifespan=lifespan
     )
     if SENTRY_DSN:
+        from onyx.configs.sentry import _add_instance_tags
+
         sentry_sdk.init(
             dsn=SENTRY_DSN,
             integrations=[StarletteIntegration(), FastApiIntegration()],
             traces_sample_rate=0.1,
             release=__version__,
+            before_send=_add_instance_tags,
         )
         logger.info("Sentry initialized")
     else:

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
@@ -47,33 +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 |
-| `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.
@@ -82,16 +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/app_base.py

@@ -10,6 +10,7 @@ from celery import bootsteps  # type: ignore
 from celery import Task
 from celery.app import trace
 from celery.exceptions import WorkerShutdown
+from celery.signals import before_task_publish
 from celery.signals import task_postrun
 from celery.signals import task_prerun
 from celery.states import READY_STATES
@@ -62,11 +63,14 @@ logger = setup_logger()
 task_logger = get_task_logger(__name__)
 
 if SENTRY_DSN:
+    from onyx.configs.sentry import _add_instance_tags
+
     sentry_sdk.init(
         dsn=SENTRY_DSN,
         integrations=[CeleryIntegration()],
         traces_sample_rate=0.1,
         release=__version__,
+        before_send=_add_instance_tags,
     )
     logger.info("Sentry initialized")
 else:
@@ -94,6 +98,17 @@ class TenantAwareTask(Task):
             CURRENT_TENANT_ID_CONTEXTVAR.set(None)
 
 
+@before_task_publish.connect
+def on_before_task_publish(
+    headers: dict[str, Any] | None = None,
+    **kwargs: Any,  # noqa: ARG001
+) -> None:
+    """Stamp the current wall-clock time into the task message headers so that
+    workers can compute queue wait time (time between publish and execution)."""
+    if headers is not None:
+        headers["enqueued_at"] = time.time()
+
+
 @task_prerun.connect
 def on_task_prerun(
     sender: Any | None = None,  # noqa: ARG001

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/light.py

@@ -16,6 +16,12 @@ from onyx.configs.app_configs import VESPA_CLOUD_CERT_PATH
 from onyx.configs.app_configs import VESPA_CLOUD_KEY_PATH
 from onyx.configs.constants import POSTGRES_CELERY_WORKER_LIGHT_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
 
@@ -36,6 +42,7 @@ 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
@@ -50,6 +57,31 @@ 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
@@ -90,6 +122,7 @@ def on_worker_init(sender: Worker, **kwargs: Any) -> None:
 
 @worker_ready.connect
 def on_worker_ready(sender: Any, **kwargs: Any) -> None:
+    start_metrics_server("light")
     app_base.on_worker_ready(sender, **kwargs)
 
 

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/connector_deletion/tasks.py

@@ -59,6 +59,11 @@ from onyx.redis.redis_connector_delete import RedisConnectorDelete
 from onyx.redis.redis_connector_delete import RedisConnectorDeletePayload
 from onyx.redis.redis_pool import get_redis_client
 from onyx.redis.redis_pool import get_redis_replica_client
+from onyx.server.metrics.deletion_metrics import inc_deletion_blocked
+from onyx.server.metrics.deletion_metrics import inc_deletion_completed
+from onyx.server.metrics.deletion_metrics import inc_deletion_fence_reset
+from onyx.server.metrics.deletion_metrics import inc_deletion_started
+from onyx.server.metrics.deletion_metrics import observe_deletion_taskset_duration
 from onyx.utils.variable_functionality import (
     fetch_versioned_implementation_with_fallback,
 )
@@ -102,7 +107,7 @@ def revoke_tasks_blocking_deletion(
                 f"Revoked permissions sync task {permissions_sync_payload.celery_task_id}."
             )
     except Exception:
-        task_logger.exception("Exception while revoking pruning task")
+        task_logger.exception("Exception while revoking permissions sync task")
 
     try:
         prune_payload = redis_connector.prune.payload
@@ -110,7 +115,7 @@ def revoke_tasks_blocking_deletion(
             app.control.revoke(prune_payload.celery_task_id)
             task_logger.info(f"Revoked pruning task {prune_payload.celery_task_id}.")
     except Exception:
-        task_logger.exception("Exception while revoking permissions sync task")
+        task_logger.exception("Exception while revoking pruning task")
 
     try:
         external_group_sync_payload = redis_connector.external_group_sync.payload
@@ -300,6 +305,7 @@ def try_generate_document_cc_pair_cleanup_tasks(
                 recent_index_attempts
                 and recent_index_attempts[0].status == IndexingStatus.IN_PROGRESS
             ):
+                inc_deletion_blocked(tenant_id, "indexing")
                 raise TaskDependencyError(
                     "Connector deletion - Delayed (indexing in progress): "
                     f"cc_pair={cc_pair_id} "
@@ -307,11 +313,13 @@ def try_generate_document_cc_pair_cleanup_tasks(
                 )
 
         if redis_connector.prune.fenced:
+            inc_deletion_blocked(tenant_id, "pruning")
             raise TaskDependencyError(
                 f"Connector deletion - Delayed (pruning in progress): cc_pair={cc_pair_id}"
             )
 
         if redis_connector.permissions.fenced:
+            inc_deletion_blocked(tenant_id, "permissions")
             raise TaskDependencyError(
                 f"Connector deletion - Delayed (permissions in progress): cc_pair={cc_pair_id}"
             )
@@ -359,6 +367,7 @@ def try_generate_document_cc_pair_cleanup_tasks(
         # set this only after all tasks have been added
         fence_payload.num_tasks = tasks_generated
         redis_connector.delete.set_fence(fence_payload)
+        inc_deletion_started(tenant_id)
 
     return tasks_generated
 
@@ -508,7 +517,11 @@ def monitor_connector_deletion_taskset(
                 db_session=db_session,
                 connector_id=connector_id_to_delete,
             )
-            if not connector or not len(connector.credentials):
+            if not connector:
+                task_logger.info(
+                    "Connector deletion - Connector already deleted, skipping connector cleanup"
+                )
+            elif not len(connector.credentials):
                 task_logger.info(
                     "Connector deletion - Found no credentials left for connector, deleting connector"
                 )
@@ -523,6 +536,12 @@ def monitor_connector_deletion_taskset(
                 num_docs_synced=fence_data.num_tasks,
             )
 
+            duration = (
+                datetime.now(timezone.utc) - fence_data.submitted
+            ).total_seconds()
+            observe_deletion_taskset_duration(tenant_id, "success", duration)
+            inc_deletion_completed(tenant_id, "success")
+
         except Exception as e:
             db_session.rollback()
             stack_trace = traceback.format_exc()
@@ -541,6 +560,11 @@ def monitor_connector_deletion_taskset(
                 f"Connector deletion exceptioned: "
                 f"cc_pair={cc_pair_id} connector={connector_id_to_delete} credential={credential_id_to_delete}"
             )
+            duration = (
+                datetime.now(timezone.utc) - fence_data.submitted
+            ).total_seconds()
+            observe_deletion_taskset_duration(tenant_id, "failure", duration)
+            inc_deletion_completed(tenant_id, "failure")
             raise e
 
     task_logger.info(
@@ -717,5 +741,6 @@ def validate_connector_deletion_fence(
         f"fence={fence_key}"
     )
 
+    inc_deletion_fence_reset(tenant_id)
     redis_connector.delete.reset()
     return

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

@@ -135,10 +135,13 @@ def _docfetching_task(
     # Since connector_indexing_proxy_task spawns a new process using this function as
     # the entrypoint, we init Sentry here.
     if SENTRY_DSN:
+        from onyx.configs.sentry import _add_instance_tags
+
         sentry_sdk.init(
             dsn=SENTRY_DSN,
             traces_sample_rate=0.1,
             release=__version__,
+            before_send=_add_instance_tags,
         )
         logger.info("Sentry initialized")
     else:

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

@@ -172,6 +172,10 @@ def migrate_chunks_from_vespa_to_opensearch_task(
             search_settings = get_current_search_settings(db_session)
             indexing_setting = IndexingSetting.from_db_model(search_settings)
 
+            task_logger.debug(
+                "Verified tenant info, migration record, and search settings."
+            )
+
             # 2.e. Build sanitized to original doc ID mapping to check for
             # conflicts in the event we sanitize a doc ID to an
             # already-existing doc ID.
@@ -325,6 +329,7 @@ def migrate_chunks_from_vespa_to_opensearch_task(
     finally:
         if lock.owned():
             lock.release()
+            task_logger.debug("Released the OpenSearch migration lock.")
         else:
             task_logger.warning(
                 "The OpenSearch migration lock was not owned on completion of the migration task."

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

@@ -38,6 +38,7 @@ from onyx.configs.constants import OnyxRedisConstants
 from onyx.configs.constants import OnyxRedisLocks
 from onyx.configs.constants import OnyxRedisSignals
 from onyx.connectors.factory import instantiate_connector
+from onyx.connectors.interfaces import BaseConnector
 from onyx.connectors.models import InputType
 from onyx.db.connector import mark_ccpair_as_pruned
 from onyx.db.connector_credential_pair import get_connector_credential_pair
@@ -72,6 +73,7 @@ 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 +219,7 @@ 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")
 
@@ -524,6 +526,14 @@ def connector_pruning_generator_task(
         return None
 
     try:
+        # Session 1: pre-enumeration — load cc_pair and instantiate the connector.
+        # The session is closed before enumeration so the DB connection is not held
+        # open during the 10–30+ minute connector crawl.
+        connector_source: DocumentSource | None = None
+        connector_type: str = ""
+        is_connector_public: bool = False
+        runnable_connector: BaseConnector | None = None
+
         with get_session_with_current_tenant() as db_session:
             cc_pair = get_connector_credential_pair(
                 db_session=db_session,
@@ -549,48 +559,51 @@ def connector_pruning_generator_task(
             )
             redis_connector.prune.set_fence(new_payload)
 
+            connector_source = cc_pair.connector.source
+            connector_type = connector_source.value
+            is_connector_public = cc_pair.access_type == AccessType.PUBLIC
+
             task_logger.info(
-                f"Pruning generator running connector: cc_pair={cc_pair_id} connector_source={cc_pair.connector.source}"
+                f"Pruning generator running connector: cc_pair={cc_pair_id} connector_source={connector_source}"
             )
 
             runnable_connector = instantiate_connector(
                 db_session,
-                cc_pair.connector.source,
+                connector_source,
                 InputType.SLIM_RETRIEVAL,
                 cc_pair.connector.connector_specific_config,
                 cc_pair.credential,
             )
+        # Session 1 closed here — connection released before enumeration.
 
-            callback = PruneCallback(
-                0,
-                redis_connector,
-                lock,
-                r,
-                timeout_seconds=JOB_TIMEOUT,
-            )
+        callback = PruneCallback(
+            0,
+            redis_connector,
+            lock,
+            r,
+            timeout_seconds=JOB_TIMEOUT,
+        )
 
-            # Extract docs and hierarchy nodes from the source
-            extraction_result = extract_ids_from_runnable_connector(
-                runnable_connector, callback
-            )
-            all_connector_doc_ids = extraction_result.raw_id_to_parent
+        # Extract docs and hierarchy nodes from the source (no DB session held).
+        extraction_result = extract_ids_from_runnable_connector(
+            runnable_connector, callback, connector_type=connector_type
+        )
+        all_connector_doc_ids = extraction_result.raw_id_to_parent
 
-            # Process hierarchy nodes (same as docfetching):
-            # upsert to Postgres and cache in Redis
-            source = cc_pair.connector.source
+        # Session 2: post-enumeration — hierarchy upserts, diff computation, task dispatch.
+        with get_session_with_current_tenant() as db_session:
+            source = connector_source
             redis_client = get_redis_client(tenant_id=tenant_id)
 
             ensure_source_node_exists(redis_client, db_session, source)
 
             upserted_nodes: list[DBHierarchyNode] = []
             if extraction_result.hierarchy_nodes:
-                is_connector_public = cc_pair.access_type == AccessType.PUBLIC
-
                 upserted_nodes = upsert_hierarchy_nodes_batch(
                     db_session=db_session,
                     nodes=extraction_result.hierarchy_nodes,
                     source=source,
-                    commit=True,
+                    commit=False,
                     is_connector_public=is_connector_public,
                 )
 
@@ -599,9 +612,13 @@ def connector_pruning_generator_task(
                     hierarchy_node_ids=[n.id for n in upserted_nodes],
                     connector_id=connector_id,
                     credential_id=credential_id,
-                    commit=True,
+                    commit=False,
                 )
 
+                # Single commit so the FK reference in the join table can never
+                # outrun the parent hierarchy_node insert.
+                db_session.commit()
+
                 cache_entries = [
                     HierarchyNodeCacheEntry.from_db_model(node)
                     for node in upserted_nodes
@@ -636,40 +653,46 @@ 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={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/background/indexing/models.py

@@ -23,6 +23,8 @@ class IndexAttemptErrorPydantic(BaseModel):
 
     index_attempt_id: int
 
+    error_type: str | None = None
+
     @classmethod
     def from_model(cls, model: IndexAttemptError) -> "IndexAttemptErrorPydantic":
         return cls(
@@ -37,4 +39,5 @@ class IndexAttemptErrorPydantic(BaseModel):
             is_resolved=model.is_resolved,
             time_created=model.time_created,
             index_attempt_id=model.index_attempt_id,
+            error_type=model.error_type,
         )

backend/onyx/background/indexing/run_docfetching.py

@@ -5,6 +5,7 @@ from datetime import datetime
 from datetime import timedelta
 from datetime import timezone
 
+import sentry_sdk
 from celery import Celery
 from sqlalchemy.orm import Session
 
@@ -556,6 +557,27 @@ def connector_document_extraction(
 
                 # save record of any failures at the connector level
                 if failure is not None:
+                    if failure.exception is not None:
+                        with sentry_sdk.new_scope() as scope:
+                            scope.set_tag("stage", "connector_fetch")
+                            scope.set_tag("connector_source", db_connector.source.value)
+                            scope.set_tag("cc_pair_id", str(cc_pair_id))
+                            scope.set_tag("index_attempt_id", str(index_attempt_id))
+                            scope.set_tag("tenant_id", tenant_id)
+                            if failure.failed_document:
+                                scope.set_tag(
+                                    "doc_id", failure.failed_document.document_id
+                                )
+                            if failure.failed_entity:
+                                scope.set_tag(
+                                    "entity_id", failure.failed_entity.entity_id
+                                )
+                            scope.fingerprint = [
+                                "connector-fetch-failure",
+                                db_connector.source.value,
+                                type(failure.exception).__name__,
+                            ]
+                            sentry_sdk.capture_exception(failure.exception)
                     total_failures += 1
                     with get_session_with_current_tenant() as db_session:
                         create_index_attempt_error(

backend/onyx/chat/chat_utils.py

@@ -364,7 +364,7 @@ def _get_or_extract_plaintext(
         plaintext_io = file_store.read_file(plaintext_key, mode="b")
         return plaintext_io.read().decode("utf-8")
     except Exception:
-        logger.exception(f"Error when reading file, id={file_id}")
+        logger.info(f"Cache miss for file with id={file_id}")
 
     # Cache miss — extract and store.
     content_text = extract_fn()

backend/onyx/chat/llm_loop.py

@@ -4,8 +4,6 @@ from collections.abc import Callable
 from typing import Any
 from typing import Literal
 
-from sqlalchemy.orm import Session
-
 from onyx.chat.chat_state import ChatStateContainer
 from onyx.chat.chat_utils import create_tool_call_failure_messages
 from onyx.chat.citation_processor import CitationMapping
@@ -635,7 +633,6 @@ def run_llm_loop(
     user_memory_context: UserMemoryContext | None,
     llm: LLM,
     token_counter: Callable[[str], int],
-    db_session: Session,
     forced_tool_id: int | None = None,
     user_identity: LLMUserIdentity | None = None,
     chat_session_id: str | None = None,
@@ -1020,20 +1017,16 @@ def run_llm_loop(
                     persisted_memory_id: int | None = None
                     if user_memory_context and user_memory_context.user_id:
                         if tool_response.rich_response.index_to_replace is not None:
-                            memory = update_memory_at_index(
+                            persisted_memory_id = update_memory_at_index(
                                 user_id=user_memory_context.user_id,
                                 index=tool_response.rich_response.index_to_replace,
                                 new_text=tool_response.rich_response.memory_text,
-                                db_session=db_session,
                             )
-                            persisted_memory_id = memory.id if memory else None
                         else:
-                            memory = add_memory(
+                            persisted_memory_id = add_memory(
                                 user_id=user_memory_context.user_id,
                                 memory_text=tool_response.rich_response.memory_text,
-                                db_session=db_session,
                             )
-                            persisted_memory_id = memory.id
                     operation: Literal["add", "update"] = (
                         "update"
                         if tool_response.rich_response.index_to_replace is not None

backend/onyx/chat/process_message.py

@@ -67,7 +67,6 @@ from onyx.db.chat import get_chat_session_by_id
 from onyx.db.chat import get_or_create_root_message
 from onyx.db.chat import reserve_message_id
 from onyx.db.chat import reserve_multi_model_message_ids
-from onyx.db.engine.sql_engine import get_session_with_current_tenant
 from onyx.db.enums import HookPoint
 from onyx.db.memory import get_memories
 from onyx.db.models import ChatMessage
@@ -996,6 +995,7 @@ 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,
@@ -1005,93 +1005,86 @@ def _run_models(
         model_llm = setup.llms[model_idx]
 
         try:
-            # Each worker opens its own session — SQLAlchemy sessions are not thread-safe.
-            # Do NOT write to the outer db_session (or any shared DB state) from here;
-            # all DB writes in this thread must go through thread_db_session.
-            with get_session_with_current_tenant() as thread_db_session:
-                thread_tool_dict = construct_tools(
-                    persona=setup.persona,
-                    db_session=thread_db_session,
-                    emitter=model_emitter,
-                    user=user,
-                    llm=model_llm,
-                    search_tool_config=SearchToolConfig(
-                        user_selected_filters=setup.new_msg_req.internal_search_filters,
-                        project_id_filter=setup.search_params.project_id_filter,
-                        persona_id_filter=setup.search_params.persona_id_filter,
-                        bypass_acl=setup.bypass_acl,
-                        slack_context=setup.slack_context,
-                        enable_slack_search=_should_enable_slack_search(
-                            setup.persona, setup.new_msg_req.internal_search_filters
-                        ),
+            # Each function opens short-lived DB sessions on demand.
+            # Do NOT pass a long-lived session here — it would hold a
+            # connection for the entire LLM loop (minutes), and cloud
+            # infrastructure may drop idle connections.
+            thread_tool_dict = construct_tools(
+                persona=setup.persona,
+                emitter=model_emitter,
+                user=user,
+                llm=model_llm,
+                search_tool_config=SearchToolConfig(
+                    user_selected_filters=setup.new_msg_req.internal_search_filters,
+                    project_id_filter=setup.search_params.project_id_filter,
+                    persona_id_filter=setup.search_params.persona_id_filter,
+                    bypass_acl=setup.bypass_acl,
+                    slack_context=setup.slack_context,
+                    enable_slack_search=_should_enable_slack_search(
+                        setup.persona, setup.new_msg_req.internal_search_filters
                     ),
-                    custom_tool_config=CustomToolConfig(
-                        chat_session_id=setup.chat_session.id,
-                        message_id=setup.user_message.id,
-                        additional_headers=setup.custom_tool_additional_headers,
-                        mcp_headers=setup.mcp_headers,
-                    ),
-                    file_reader_tool_config=FileReaderToolConfig(
-                        user_file_ids=setup.available_files.user_file_ids,
-                        chat_file_ids=setup.available_files.chat_file_ids,
-                    ),
-                    allowed_tool_ids=setup.new_msg_req.allowed_tool_ids,
-                    search_usage_forcing_setting=setup.search_params.search_usage,
+                ),
+                custom_tool_config=CustomToolConfig(
+                    chat_session_id=setup.chat_session.id,
+                    message_id=setup.user_message.id,
+                    additional_headers=setup.custom_tool_additional_headers,
+                    mcp_headers=setup.mcp_headers,
+                ),
+                file_reader_tool_config=FileReaderToolConfig(
+                    user_file_ids=setup.available_files.user_file_ids,
+                    chat_file_ids=setup.available_files.chat_file_ids,
+                ),
+                allowed_tool_ids=setup.new_msg_req.allowed_tool_ids,
+                search_usage_forcing_setting=setup.search_params.search_usage,
+            )
+            model_tools = [
+                tool for tool_list in thread_tool_dict.values() for tool in tool_list
+            ]
+
+            if setup.forced_tool_id and setup.forced_tool_id not in {
+                tool.id for tool in model_tools
+            }:
+                raise ValueError(
+                    f"Forced tool {setup.forced_tool_id} not found in tools"
                 )
-                model_tools = [
-                    tool
-                    for tool_list in thread_tool_dict.values()
-                    for tool in tool_list
-                ]
 
-                if setup.forced_tool_id and setup.forced_tool_id not in {
-                    tool.id for tool in model_tools
-                }:
-                    raise ValueError(
-                        f"Forced tool {setup.forced_tool_id} not found in tools"
-                    )
-
-                # Per-thread copy: run_llm_loop mutates simple_chat_history in-place.
-                if n_models == 1 and setup.new_msg_req.deep_research:
-                    if setup.chat_session.project_id:
-                        raise RuntimeError(
-                            "Deep research is not supported for projects"
-                        )
-                    run_deep_research_llm_loop(
-                        emitter=model_emitter,
-                        state_container=sc,
-                        simple_chat_history=list(setup.simple_chat_history),
-                        tools=model_tools,
-                        custom_agent_prompt=setup.custom_agent_prompt,
-                        llm=model_llm,
-                        token_counter=get_llm_token_counter(model_llm),
-                        db_session=thread_db_session,
-                        skip_clarification=setup.skip_clarification,
-                        user_identity=setup.user_identity,
-                        chat_session_id=str(setup.chat_session.id),
-                        all_injected_file_metadata=setup.all_injected_file_metadata,
-                    )
-                else:
-                    run_llm_loop(
-                        emitter=model_emitter,
-                        state_container=sc,
-                        simple_chat_history=list(setup.simple_chat_history),
-                        tools=model_tools,
-                        custom_agent_prompt=setup.custom_agent_prompt,
-                        context_files=setup.extracted_context_files,
-                        persona=setup.persona,
-                        user_memory_context=setup.user_memory_context,
-                        llm=model_llm,
-                        token_counter=get_llm_token_counter(model_llm),
-                        db_session=thread_db_session,
-                        forced_tool_id=setup.forced_tool_id,
-                        user_identity=setup.user_identity,
-                        chat_session_id=str(setup.chat_session.id),
-                        chat_files=setup.chat_files_for_tools,
-                        include_citations=setup.new_msg_req.include_citations,
-                        all_injected_file_metadata=setup.all_injected_file_metadata,
-                        inject_memories_in_prompt=user.use_memories,
-                    )
+            # Per-thread copy: run_llm_loop mutates simple_chat_history in-place.
+            if n_models == 1 and setup.new_msg_req.deep_research:
+                if setup.chat_session.project_id:
+                    raise RuntimeError("Deep research is not supported for projects")
+                run_deep_research_llm_loop(
+                    emitter=model_emitter,
+                    state_container=sc,
+                    simple_chat_history=list(setup.simple_chat_history),
+                    tools=model_tools,
+                    custom_agent_prompt=setup.custom_agent_prompt,
+                    llm=model_llm,
+                    token_counter=get_llm_token_counter(model_llm),
+                    skip_clarification=setup.skip_clarification,
+                    user_identity=setup.user_identity,
+                    chat_session_id=str(setup.chat_session.id),
+                    all_injected_file_metadata=setup.all_injected_file_metadata,
+                )
+            else:
+                run_llm_loop(
+                    emitter=model_emitter,
+                    state_container=sc,
+                    simple_chat_history=list(setup.simple_chat_history),
+                    tools=model_tools,
+                    custom_agent_prompt=setup.custom_agent_prompt,
+                    context_files=setup.extracted_context_files,
+                    persona=setup.persona,
+                    user_memory_context=setup.user_memory_context,
+                    llm=model_llm,
+                    token_counter=get_llm_token_counter(model_llm),
+                    forced_tool_id=setup.forced_tool_id,
+                    user_identity=setup.user_identity,
+                    chat_session_id=str(setup.chat_session.id),
+                    chat_files=setup.chat_files_for_tools,
+                    include_citations=setup.new_msg_req.include_citations,
+                    all_injected_file_metadata=setup.all_injected_file_metadata,
+                    inject_memories_in_prompt=user.use_memories,
+                )
 
             model_succeeded[model_idx] = True
 
@@ -1102,33 +1095,33 @@ 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 +1138,7 @@ 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 +1204,7 @@ 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 +1257,7 @@ 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/sentry.py

@@ -0,0 +1,48 @@
+from typing import Any
+
+from sentry_sdk.types import Event
+
+from onyx.utils.logger import setup_logger
+
+logger = setup_logger()
+
+_instance_id_resolved = False
+
+
+def _add_instance_tags(
+    event: Event,
+    hint: dict[str, Any],  # noqa: ARG001
+) -> Event | None:
+    """Sentry before_send hook that lazily attaches instance identification tags.
+
+    On the first event, resolves the instance UUID from the KV store (requires DB)
+    and sets it as a global Sentry tag. Subsequent events pick it up automatically.
+    """
+    global _instance_id_resolved
+
+    if _instance_id_resolved:
+        return event
+
+    try:
+        import sentry_sdk
+
+        from shared_configs.configs import MULTI_TENANT
+
+        if MULTI_TENANT:
+            instance_id = "multi-tenant-cloud"
+        else:
+            from onyx.utils.telemetry import get_or_generate_uuid
+
+            instance_id = get_or_generate_uuid()
+
+        sentry_sdk.set_tag("instance_id", instance_id)
+
+        # Also set on this event since set_tag won't retroactively apply
+        event.setdefault("tags", {})["instance_id"] = instance_id
+
+        # Only mark resolved after success — if DB wasn't ready, retry next event
+        _instance_id_resolved = True
+    except Exception:
+        logger.debug("Failed to resolve instance_id for Sentry tagging")
+
+    return event

backend/onyx/connectors/clickup/connector.py

@@ -171,7 +171,10 @@ class ClickupConnector(LoadConnector, PollConnector):
                         document.metadata[extra_field] = task[extra_field]
 
                 if self.retrieve_task_comments:
-                    document.sections.extend(self._get_task_comments(task["id"]))
+                    document.sections = [
+                        *document.sections,
+                        *self._get_task_comments(task["id"]),
+                    ]
 
                 doc_batch.append(document)
 

backend/onyx/connectors/confluence/onyx_confluence.py

@@ -61,6 +61,9 @@ _USER_NOT_FOUND = "Unknown Confluence User"
 _USER_ID_TO_DISPLAY_NAME_CACHE: dict[str, str | None] = {}
 _USER_EMAIL_CACHE: dict[str, str | None] = {}
 _DEFAULT_PAGINATION_LIMIT = 1000
+_MINIMUM_PAGINATION_LIMIT = 5
+
+_SERVER_ERROR_CODES = {500, 502, 503, 504}
 
 _CONFLUENCE_SPACES_API_V1 = "rest/api/space"
 _CONFLUENCE_SPACES_API_V2 = "wiki/api/v2/spaces"
@@ -569,7 +572,8 @@ class OnyxConfluence:
         if not limit:
             limit = _DEFAULT_PAGINATION_LIMIT
 
-        url_suffix = update_param_in_path(url_suffix, "limit", str(limit))
+        current_limit = limit
+        url_suffix = update_param_in_path(url_suffix, "limit", str(current_limit))
 
         while url_suffix:
             logger.debug(f"Making confluence call to {url_suffix}")
@@ -609,40 +613,61 @@ class OnyxConfluence:
                     )
                     continue
 
-                # If we fail due to a 500, try one by one.
-                # NOTE: this iterative approach only works for server, since cloud uses cursor-based
-                # pagination
-                if raw_response.status_code == 500 and not self._is_cloud:
-                    initial_start = get_start_param_from_url(url_suffix)
-                    if initial_start is None:
-                        # can't handle this if we don't have offset-based pagination
-                        raise
+                if raw_response.status_code in _SERVER_ERROR_CODES:
+                    # Try reducing the page size -- Confluence often times out
+                    # on large result sets (especially Cloud 504s).
+                    if current_limit > _MINIMUM_PAGINATION_LIMIT:
+                        old_limit = current_limit
+                        current_limit = max(
+                            current_limit // 2, _MINIMUM_PAGINATION_LIMIT
+                        )
+                        logger.warning(
+                            f"Confluence returned {raw_response.status_code}. "
+                            f"Reducing limit from {old_limit} to {current_limit} "
+                            f"and retrying."
+                        )
+                        url_suffix = update_param_in_path(
+                            url_suffix, "limit", str(current_limit)
+                        )
+                        continue
 
-                    # this will just yield the successful items from the batch
-                    new_url_suffix = yield from self._try_one_by_one_for_paginated_url(
-                        url_suffix,
-                        initial_start=initial_start,
-                        limit=limit,
-                    )
+                    # Limit reduction exhausted -- for Server, fall back to
+                    # one-by-one offset pagination as a last resort.
+                    if not self._is_cloud:
+                        initial_start = get_start_param_from_url(url_suffix)
+                        # this will just yield the successful items from the batch
+                        new_url_suffix = (
+                            yield from self._try_one_by_one_for_paginated_url(
+                                url_suffix,
+                                initial_start=initial_start,
+                                limit=current_limit,
+                            )
+                        )
+                        # this means we ran into an empty page
+                        if new_url_suffix is None:
+                            if next_page_callback:
+                                next_page_callback("")
+                            break
 
-                    # this means we ran into an empty page
-                    if new_url_suffix is None:
-                        if next_page_callback:
-                            next_page_callback("")
-                        break
+                        url_suffix = new_url_suffix
+                        continue
 
-                    url_suffix = new_url_suffix
-                    continue
-
-                else:
                     logger.exception(
-                        f"Error in confluence call to {url_suffix} \n"
-                        f"Raw Response Text: {raw_response.text} \n"
-                        f"Full Response: {raw_response.__dict__} \n"
-                        f"Error: {e} \n"
+                        f"Error in confluence call to {url_suffix} "
+                        f"after reducing limit to {current_limit}.\n"
+                        f"Raw Response Text: {raw_response.text}\n"
+                        f"Error: {e}\n"
                     )
                     raise
 
+                logger.exception(
+                    f"Error in confluence call to {url_suffix} \n"
+                    f"Raw Response Text: {raw_response.text} \n"
+                    f"Full Response: {raw_response.__dict__} \n"
+                    f"Error: {e} \n"
+                )
+                raise
+
             try:
                 next_response = raw_response.json()
             except Exception as e:
@@ -680,6 +705,10 @@ class OnyxConfluence:
             old_url_suffix = url_suffix
             updated_start = get_start_param_from_url(old_url_suffix)
             url_suffix = cast(str, next_response.get("_links", {}).get("next", ""))
+            if url_suffix and current_limit != limit:
+                url_suffix = update_param_in_path(
+                    url_suffix, "limit", str(current_limit)
+                )
             for i, result in enumerate(results):
                 updated_start += 1
                 if url_suffix and next_page_callback and i == len(results) - 1:

backend/onyx/connectors/cross_connector_utils/tabular_section_utils.py

@@ -0,0 +1,65 @@
+import csv
+import io
+from typing import IO
+
+from onyx.connectors.models import TabularSection
+from onyx.file_processing.extract_file_text import file_io_to_text
+from onyx.file_processing.extract_file_text import xlsx_sheet_extraction
+from onyx.file_processing.file_types import OnyxFileExtensions
+from onyx.utils.logger import setup_logger
+
+logger = setup_logger()
+
+
+def is_tabular_file(file_name: str) -> bool:
+    lowered = file_name.lower()
+    return any(lowered.endswith(ext) for ext in OnyxFileExtensions.TABULAR_EXTENSIONS)
+
+
+def _tsv_to_csv(tsv_text: str) -> str:
+    """Re-serialize tab-separated text as CSV so downstream parsers that
+    assume the default Excel dialect read the columns correctly."""
+    out = io.StringIO()
+    csv.writer(out, lineterminator="\n").writerows(
+        csv.reader(io.StringIO(tsv_text), dialect="excel-tab")
+    )
+    return out.getvalue().rstrip("\n")
+
+
+def tabular_file_to_sections(
+    file: IO[bytes],
+    file_name: str,
+    link: str = "",
+) -> list[TabularSection]:
+    """Convert a tabular file into one or more TabularSections.
+
+    - .xlsx → one TabularSection per non-empty sheet.
+    - .csv / .tsv → a single TabularSection containing the full decoded
+      file.
+
+    Returns an empty list when the file yields no extractable content.
+    """
+    lowered = file_name.lower()
+
+    if lowered.endswith(".xlsx"):
+        return [
+            TabularSection(link=f"sheet:{sheet_title}", text=csv_text)
+            for csv_text, sheet_title in xlsx_sheet_extraction(
+                file, file_name=file_name
+            )
+        ]
+
+    if not lowered.endswith((".csv", ".tsv")):
+        raise ValueError(f"{file_name!r} is not a tabular file")
+
+    try:
+        text = file_io_to_text(file).strip()
+    except Exception:
+        logger.exception(f"Failure decoding {file_name}")
+        raise
+
+    if not text:
+        return []
+    if lowered.endswith(".tsv"):
+        text = _tsv_to_csv(text)
+    return [TabularSection(link=link or file_name, text=text)]

backend/onyx/connectors/github/connector.py

@@ -35,10 +35,16 @@ from onyx.connectors.interfaces import CheckpointedConnectorWithPermSync
 from onyx.connectors.interfaces import CheckpointOutput
 from onyx.connectors.interfaces import ConnectorCheckpoint
 from onyx.connectors.interfaces import ConnectorFailure
+from onyx.connectors.interfaces import GenerateSlimDocumentOutput
+from onyx.connectors.interfaces import IndexingHeartbeatInterface
 from onyx.connectors.interfaces import SecondsSinceUnixEpoch
+from onyx.connectors.interfaces import SlimConnector
+from onyx.connectors.interfaces import SlimConnectorWithPermSync
 from onyx.connectors.models import ConnectorMissingCredentialError
 from onyx.connectors.models import Document
 from onyx.connectors.models import DocumentFailure
+from onyx.connectors.models import HierarchyNode
+from onyx.connectors.models import SlimDocument
 from onyx.connectors.models import TextSection
 from onyx.utils.logger import setup_logger
 
@@ -427,7 +433,11 @@ def make_cursor_url_callback(
     return cursor_url_callback
 
 
-class GithubConnector(CheckpointedConnectorWithPermSync[GithubConnectorCheckpoint]):
+class GithubConnector(
+    CheckpointedConnectorWithPermSync[GithubConnectorCheckpoint],
+    SlimConnector,
+    SlimConnectorWithPermSync,
+):
     def __init__(
         self,
         repo_owner: str,
@@ -803,6 +813,87 @@ class GithubConnector(CheckpointedConnectorWithPermSync[GithubConnectorCheckpoin
             start, end, checkpoint, include_permissions=True
         )
 
+    def _iter_slim_docs(
+        self,
+        include_permissions: bool,
+        callback: IndexingHeartbeatInterface | None = None,
+    ) -> GenerateSlimDocumentOutput:
+        if self.github_client is None:
+            raise ConnectorMissingCredentialError("GitHub")
+
+        repos = self.fetch_configured_repos()
+        batch: list[SlimDocument | HierarchyNode] = []
+
+        for repo in repos:
+            external_access = (
+                get_external_access_permission(repo, self.github_client)
+                if include_permissions
+                else None
+            )
+
+            if self.include_prs:
+                try:
+                    for pr in repo.get_pulls(
+                        state=self.state_filter, sort="updated", direction="desc"
+                    ):
+                        batch.append(
+                            SlimDocument(
+                                id=pr.html_url, external_access=external_access
+                            )
+                        )
+                        if len(batch) >= SLIM_BATCH_SIZE:
+                            yield batch
+                            batch = []
+                            if callback and callback.should_stop():
+                                raise RuntimeError(
+                                    "github_slim_docs: Stop signal detected"
+                                )
+                except RateLimitExceededException:
+                    sleep_after_rate_limit_exception(self.github_client)
+
+            if self.include_issues:
+                try:
+                    for issue in repo.get_issues(
+                        state=self.state_filter, sort="updated", direction="desc"
+                    ):
+                        if issue.pull_request is not None:
+                            continue
+                        batch.append(
+                            SlimDocument(
+                                id=issue.html_url, external_access=external_access
+                            )
+                        )
+                        if len(batch) >= SLIM_BATCH_SIZE:
+                            yield batch
+                            batch = []
+                            if callback and callback.should_stop():
+                                raise RuntimeError(
+                                    "github_slim_docs: Stop signal detected"
+                                )
+                except RateLimitExceededException:
+                    sleep_after_rate_limit_exception(self.github_client)
+
+        if batch:
+            yield batch
+
+    @override
+    def retrieve_all_slim_docs(
+        self,
+        start: SecondsSinceUnixEpoch | None = None,
+        end: SecondsSinceUnixEpoch | None = None,
+        callback: IndexingHeartbeatInterface | None = None,
+    ) -> GenerateSlimDocumentOutput:
+        return self._iter_slim_docs(include_permissions=False, callback=callback)
+
+    @override
+    def retrieve_all_slim_docs_perm_sync(
+        self,
+        start: SecondsSinceUnixEpoch | None = None,
+        end: SecondsSinceUnixEpoch | None = None,
+        callback: IndexingHeartbeatInterface | None = None,
+    ) -> GenerateSlimDocumentOutput:
+        return self._iter_slim_docs(include_permissions=True, callback=callback)
+
     def validate_connector_settings(self) -> None:
         if self.github_client is None:
             raise ConnectorMissingCredentialError("GitHub credentials not loaded.")

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 +73,14 @@ 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 SlimConnector
 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 +208,10 @@ class DriveIdStatus(Enum):
 
 
 class GoogleDriveConnector(
-    SlimConnectorWithPermSync, CheckpointedConnectorWithPermSync[GoogleDriveCheckpoint]
+    SlimConnector,
+    SlimConnectorWithPermSync,
+    CheckpointedConnectorWithPermSync[GoogleDriveCheckpoint],
+    Resolver,
 ):
     def __init__(
         self,
@@ -1665,12 +1674,89 @@ 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,
         start: SecondsSinceUnixEpoch | None = None,
         end: SecondsSinceUnixEpoch | None = None,
         callback: IndexingHeartbeatInterface | None = None,
+        include_permissions: bool = True,
     ) -> GenerateSlimDocumentOutput:
         files_batch: list[RetrievedDriveFile] = []
         slim_batch: list[SlimDocument | HierarchyNode] = []
@@ -1680,9 +1766,13 @@ class GoogleDriveConnector(
             nonlocal files_batch, slim_batch
 
             # Get new ancestor hierarchy nodes first
-            permission_sync_context = PermissionSyncContext(
-                primary_admin_email=self.primary_admin_email,
-                google_domain=self.google_domain,
+            permission_sync_context = (
+                PermissionSyncContext(
+                    primary_admin_email=self.primary_admin_email,
+                    google_domain=self.google_domain,
+                )
+                if include_permissions
+                else None
             )
             new_ancestors = self._get_new_ancestors_for_files(
                 files=files_batch,
@@ -1696,10 +1786,7 @@ class GoogleDriveConnector(
                 if doc := build_slim_document(
                     self.creds,
                     file.drive_file,
-                    PermissionSyncContext(
-                        primary_admin_email=self.primary_admin_email,
-                        google_domain=self.google_domain,
-                    ),
+                    permission_sync_context,
                     retriever_email=file.user_email,
                 ):
                     slim_batch.append(doc)
@@ -1739,11 +1826,12 @@ class GoogleDriveConnector(
         if files_batch:
             yield _yield_slim_batch()
 
-    def retrieve_all_slim_docs_perm_sync(
+    def _retrieve_all_slim_docs_impl(
         self,
         start: SecondsSinceUnixEpoch | None = None,
         end: SecondsSinceUnixEpoch | None = None,
         callback: IndexingHeartbeatInterface | None = None,
+        include_permissions: bool = True,
     ) -> GenerateSlimDocumentOutput:
         try:
             checkpoint = self.build_dummy_checkpoint()
@@ -1753,13 +1841,34 @@ class GoogleDriveConnector(
                     start=start,
                     end=end,
                     callback=callback,
+                    include_permissions=include_permissions,
                 )
-            logger.info("Drive perm sync: Slim doc retrieval complete")
-
+            logger.info("Drive slim doc retrieval complete")
         except Exception as e:
             if MISSING_SCOPES_ERROR_STR in str(e):
                 raise PermissionError(ONYX_SCOPE_INSTRUCTIONS) from e
-            raise e
+            raise
+
+    @override
+    def retrieve_all_slim_docs(
+        self,
+        start: SecondsSinceUnixEpoch | None = None,
+        end: SecondsSinceUnixEpoch | None = None,
+        callback: IndexingHeartbeatInterface | None = None,
+    ) -> GenerateSlimDocumentOutput:
+        return self._retrieve_all_slim_docs_impl(
+            start=start, end=end, callback=callback, include_permissions=False
+        )
+
+    def retrieve_all_slim_docs_perm_sync(
+        self,
+        start: SecondsSinceUnixEpoch | None = None,
+        end: SecondsSinceUnixEpoch | None = None,
+        callback: IndexingHeartbeatInterface | None = None,
+    ) -> GenerateSlimDocumentOutput:
+        return self._retrieve_all_slim_docs_impl(
+            start=start, end=end, callback=callback, include_permissions=True
+        )
 
     def validate_connector_settings(self) -> None:
         if self._creds is None:

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/google_utils/google_kv.py

@@ -1,4 +1,5 @@
 import json
+from typing import Any
 from typing import cast
 from urllib.parse import parse_qs
 from urllib.parse import ParseResult
@@ -53,6 +54,21 @@ from onyx.utils.logger import setup_logger
 logger = setup_logger()
 
 
+def _load_google_json(raw: object) -> dict[str, Any]:
+    """Accept both the current (dict) and legacy (JSON string) KV payload shapes.
+
+    Payloads written before the fix for serializing Google credentials into
+    ``EncryptedJson`` columns are stored as JSON strings; new writes store dicts.
+    Once every install has re-uploaded their Google credentials the legacy
+    ``str`` branch can be removed.
+    """
+    if isinstance(raw, dict):
+        return raw
+    if isinstance(raw, str):
+        return json.loads(raw)
+    raise ValueError(f"Unexpected Google credential payload type: {type(raw)!r}")
+
+
 def _build_frontend_google_drive_redirect(source: DocumentSource) -> str:
     if source == DocumentSource.GOOGLE_DRIVE:
         return f"{WEB_DOMAIN}/admin/connectors/google-drive/auth/callback"
@@ -162,12 +178,13 @@ def build_service_account_creds(
 
 def get_auth_url(credential_id: int, source: DocumentSource) -> str:
     if source == DocumentSource.GOOGLE_DRIVE:
-        creds_str = str(get_kv_store().load(KV_GOOGLE_DRIVE_CRED_KEY))
+        credential_json = _load_google_json(
+            get_kv_store().load(KV_GOOGLE_DRIVE_CRED_KEY)
+        )
     elif source == DocumentSource.GMAIL:
-        creds_str = str(get_kv_store().load(KV_GMAIL_CRED_KEY))
+        credential_json = _load_google_json(get_kv_store().load(KV_GMAIL_CRED_KEY))
     else:
         raise ValueError(f"Unsupported source: {source}")
-    credential_json = json.loads(creds_str)
     flow = InstalledAppFlow.from_client_config(
         credential_json,
         scopes=GOOGLE_SCOPES[source],
@@ -188,12 +205,12 @@ def get_auth_url(credential_id: int, source: DocumentSource) -> str:
 
 def get_google_app_cred(source: DocumentSource) -> GoogleAppCredentials:
     if source == DocumentSource.GOOGLE_DRIVE:
-        creds_str = str(get_kv_store().load(KV_GOOGLE_DRIVE_CRED_KEY))
+        creds = _load_google_json(get_kv_store().load(KV_GOOGLE_DRIVE_CRED_KEY))
     elif source == DocumentSource.GMAIL:
-        creds_str = str(get_kv_store().load(KV_GMAIL_CRED_KEY))
+        creds = _load_google_json(get_kv_store().load(KV_GMAIL_CRED_KEY))
     else:
         raise ValueError(f"Unsupported source: {source}")
-    return GoogleAppCredentials(**json.loads(creds_str))
+    return GoogleAppCredentials(**creds)
 
 
 def upsert_google_app_cred(
@@ -201,10 +218,14 @@ def upsert_google_app_cred(
 ) -> None:
     if source == DocumentSource.GOOGLE_DRIVE:
         get_kv_store().store(
-            KV_GOOGLE_DRIVE_CRED_KEY, app_credentials.json(), encrypt=True
+            KV_GOOGLE_DRIVE_CRED_KEY,
+            app_credentials.model_dump(mode="json"),
+            encrypt=True,
         )
     elif source == DocumentSource.GMAIL:
-        get_kv_store().store(KV_GMAIL_CRED_KEY, app_credentials.json(), encrypt=True)
+        get_kv_store().store(
+            KV_GMAIL_CRED_KEY, app_credentials.model_dump(mode="json"), encrypt=True
+        )
     else:
         raise ValueError(f"Unsupported source: {source}")
 
@@ -220,12 +241,14 @@ def delete_google_app_cred(source: DocumentSource) -> None:
 
 def get_service_account_key(source: DocumentSource) -> GoogleServiceAccountKey:
     if source == DocumentSource.GOOGLE_DRIVE:
-        creds_str = str(get_kv_store().load(KV_GOOGLE_DRIVE_SERVICE_ACCOUNT_KEY))
+        creds = _load_google_json(
+            get_kv_store().load(KV_GOOGLE_DRIVE_SERVICE_ACCOUNT_KEY)
+        )
     elif source == DocumentSource.GMAIL:
-        creds_str = str(get_kv_store().load(KV_GMAIL_SERVICE_ACCOUNT_KEY))
+        creds = _load_google_json(get_kv_store().load(KV_GMAIL_SERVICE_ACCOUNT_KEY))
     else:
         raise ValueError(f"Unsupported source: {source}")
-    return GoogleServiceAccountKey(**json.loads(creds_str))
+    return GoogleServiceAccountKey(**creds)
 
 
 def upsert_service_account_key(
@@ -234,12 +257,14 @@ def upsert_service_account_key(
     if source == DocumentSource.GOOGLE_DRIVE:
         get_kv_store().store(
             KV_GOOGLE_DRIVE_SERVICE_ACCOUNT_KEY,
-            service_account_key.json(),
+            service_account_key.model_dump(mode="json"),
             encrypt=True,
         )
     elif source == DocumentSource.GMAIL:
         get_kv_store().store(
-            KV_GMAIL_SERVICE_ACCOUNT_KEY, service_account_key.json(), encrypt=True
+            KV_GMAIL_SERVICE_ACCOUNT_KEY,
+            service_account_key.model_dump(mode="json"),
+            encrypt=True,
         )
     else:
         raise ValueError(f"Unsupported source: {source}")

backend/onyx/connectors/interfaces.py

@@ -123,6 +123,9 @@ class SlimConnector(BaseConnector):
     @abc.abstractmethod
     def retrieve_all_slim_docs(
         self,
+        start: SecondsSinceUnixEpoch | None = None,
+        end: SecondsSinceUnixEpoch | None = None,
+        callback: IndexingHeartbeatInterface | None = None,
     ) -> GenerateSlimDocumentOutput:
         raise NotImplementedError
 
@@ -298,6 +301,22 @@ 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/connectors/models.py

@@ -1,8 +1,10 @@
 import sys
+from collections.abc import Sequence
 from datetime import datetime
 from enum import Enum
 from typing import Any
 from typing import cast
+from typing import Literal
 
 from pydantic import BaseModel
 from pydantic import Field
@@ -33,9 +35,18 @@ class ConnectorMissingCredentialError(PermissionError):
         )
 
 
+class SectionType(str, Enum):
+    """Discriminator for Section subclasses."""
+
+    TEXT = "text"
+    IMAGE = "image"
+    TABULAR = "tabular"
+
+
 class Section(BaseModel):
     """Base section class with common attributes"""
 
+    type: SectionType
     link: str | None = None
     text: str | None = None
     image_file_id: str | None = None
@@ -44,6 +55,7 @@ class Section(BaseModel):
 class TextSection(Section):
     """Section containing text content"""
 
+    type: Literal[SectionType.TEXT] = SectionType.TEXT
     text: str
 
     def __sizeof__(self) -> int:
@@ -53,12 +65,25 @@ class TextSection(Section):
 class ImageSection(Section):
     """Section containing an image reference"""
 
+    type: Literal[SectionType.IMAGE] = SectionType.IMAGE
     image_file_id: str
 
     def __sizeof__(self) -> int:
         return sys.getsizeof(self.image_file_id) + sys.getsizeof(self.link)
 
 
+class TabularSection(Section):
+    """Section containing tabular data (csv/tsv content, or one sheet of
+    an xlsx workbook rendered as CSV)."""
+
+    type: Literal[SectionType.TABULAR] = SectionType.TABULAR
+    text: str  # CSV representation in a string
+    link: str
+
+    def __sizeof__(self) -> int:
+        return sys.getsizeof(self.text) + sys.getsizeof(self.link)
+
+
 class BasicExpertInfo(BaseModel):
     """Basic Information for the owner of a document, any of the fields can be left as None
     Display fallback goes as follows:
@@ -134,7 +159,6 @@ class BasicExpertInfo(BaseModel):
 
     @classmethod
     def from_dict(cls, model_dict: dict[str, Any]) -> "BasicExpertInfo":
-
         first_name = cast(str, model_dict.get("FirstName"))
         last_name = cast(str, model_dict.get("LastName"))
         email = cast(str, model_dict.get("Email"))
@@ -161,7 +185,7 @@ class DocumentBase(BaseModel):
     """Used for Onyx ingestion api, the ID is inferred before use if not provided"""
 
     id: str | None = None
-    sections: list[TextSection | ImageSection]
+    sections: Sequence[TextSection | ImageSection | TabularSection]
     source: DocumentSource | None = None
     semantic_identifier: str  # displayed in the UI as the main identifier for the doc
     # TODO(andrei): Ideally we could improve this to where each value is just a
@@ -371,12 +395,9 @@ class IndexingDocument(Document):
             )
         else:
             section_len = sum(
-                (
-                    len(section.text)
-                    if isinstance(section, TextSection) and section.text is not None
-                    else 0
-                )
+                len(section.text) if section.text is not None else 0
                 for section in self.sections
+                if isinstance(section, (TextSection, TabularSection))
             )
 
         return title_len + section_len

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/document_set.py

@@ -335,6 +335,7 @@ def update_document_set(
                 "Cannot update document set while it is syncing. Please wait for it to finish syncing, and then try again."
             )
 
+        document_set_row.name = document_set_update_request.name
         document_set_row.description = document_set_update_request.description
         if not DISABLE_VECTOR_DB:
             document_set_row.is_up_to_date = False

backend/onyx/db/engine/sql_engine.py

@@ -11,6 +11,7 @@ from sqlalchemy import event
 from sqlalchemy import pool
 from sqlalchemy.engine import create_engine
 from sqlalchemy.engine import Engine
+from sqlalchemy.exc import DBAPIError
 from sqlalchemy.orm import Session
 
 from onyx.configs.app_configs import DB_READONLY_PASSWORD
@@ -346,6 +347,25 @@ def get_session_with_shared_schema() -> Generator[Session, None, None]:
     CURRENT_TENANT_ID_CONTEXTVAR.reset(token)
 
 
+def _safe_close_session(session: Session) -> None:
+    """Close a session, catching connection-closed errors during cleanup.
+
+    Long-running operations (e.g. multi-model LLM loops) can hold a session
+    open for minutes.  If the underlying connection is dropped by cloud
+    infrastructure (load-balancer timeouts, PgBouncer, idle-in-transaction
+    timeouts, etc.), the implicit rollback in Session.close() raises
+    OperationalError or InterfaceError.  Since the work is already complete,
+    we log and move on — SQLAlchemy internally invalidates the connection
+    for pool recycling.
+    """
+    try:
+        session.close()
+    except DBAPIError:
+        logger.warning(
+            "DB connection lost during session cleanup — the connection will be invalidated and recycled by the pool."
+        )
+
+
 @contextmanager
 def get_session_with_tenant(*, tenant_id: str) -> Generator[Session, None, None]:
     """
@@ -358,8 +378,11 @@ def get_session_with_tenant(*, tenant_id: str) -> Generator[Session, None, None]
 
     # no need to use the schema translation map for self-hosted + default schema
     if not MULTI_TENANT and tenant_id == POSTGRES_DEFAULT_SCHEMA_STANDARD_VALUE:
-        with Session(bind=engine, expire_on_commit=False) as session:
+        session = Session(bind=engine, expire_on_commit=False)
+        try:
             yield session
+        finally:
+            _safe_close_session(session)
         return
 
     # Create connection with schema translation to handle querying the right schema
@@ -367,8 +390,11 @@ def get_session_with_tenant(*, tenant_id: str) -> Generator[Session, None, None]
     with engine.connect().execution_options(
         schema_translate_map=schema_translate_map
     ) as connection:
-        with Session(bind=connection, expire_on_commit=False) as session:
+        session = Session(bind=connection, expire_on_commit=False)
+        try:
             yield session
+        finally:
+            _safe_close_session(session)
 
 
 def get_session() -> Generator[Session, None, None]:

backend/onyx/db/index_attempt.py

@@ -899,6 +899,7 @@ def create_index_attempt_error(
     failure: ConnectorFailure,
     db_session: Session,
 ) -> int:
+    exc = failure.exception
     new_error = IndexAttemptError(
         index_attempt_id=index_attempt_id,
         connector_credential_pair_id=connector_credential_pair_id,
@@ -921,6 +922,7 @@ def create_index_attempt_error(
         ),
         failure_message=failure.failure_message,
         is_resolved=False,
+        error_type=type(exc).__name__ if exc else None,
     )
     db_session.add(new_error)
     db_session.commit()

backend/onyx/db/memory.py

@@ -5,6 +5,7 @@ from pydantic import ConfigDict
 from sqlalchemy import select
 from sqlalchemy.orm import Session
 
+from onyx.db.engine.sql_engine import get_session_with_current_tenant_if_none
 from onyx.db.models import Memory
 from onyx.db.models import User
 
@@ -83,47 +84,51 @@ def get_memories(user: User, db_session: Session) -> UserMemoryContext:
 def add_memory(
     user_id: UUID,
     memory_text: str,
-    db_session: Session,
-) -> Memory:
+    db_session: Session | None = None,
+) -> int:
     """Insert a new Memory row for the given user.
 
     If the user already has MAX_MEMORIES_PER_USER memories, the oldest
     one (lowest id) is deleted before inserting the new one.
+
+    Returns the id of the newly created Memory row.
     """
-    existing = db_session.scalars(
-        select(Memory).where(Memory.user_id == user_id).order_by(Memory.id.asc())
-    ).all()
+    with get_session_with_current_tenant_if_none(db_session) as db_session:
+        existing = db_session.scalars(
+            select(Memory).where(Memory.user_id == user_id).order_by(Memory.id.asc())
+        ).all()
 
-    if len(existing) >= MAX_MEMORIES_PER_USER:
-        db_session.delete(existing[0])
+        if len(existing) >= MAX_MEMORIES_PER_USER:
+            db_session.delete(existing[0])
 
-    memory = Memory(
-        user_id=user_id,
-        memory_text=memory_text,
-    )
-    db_session.add(memory)
-    db_session.commit()
-    return memory
+        memory = Memory(
+            user_id=user_id,
+            memory_text=memory_text,
+        )
+        db_session.add(memory)
+        db_session.commit()
+        return memory.id
 
 
 def update_memory_at_index(
     user_id: UUID,
     index: int,
     new_text: str,
-    db_session: Session,
-) -> Memory | None:
+    db_session: Session | None = None,
+) -> int | None:
     """Update the memory at the given 0-based index (ordered by id ASC, matching get_memories()).
 
-    Returns the updated Memory row, or None if the index is out of range.
+    Returns the id of the updated Memory row, or None if the index is out of range.
     """
-    memory_rows = db_session.scalars(
-        select(Memory).where(Memory.user_id == user_id).order_by(Memory.id.asc())
-    ).all()
+    with get_session_with_current_tenant_if_none(db_session) as db_session:
+        memory_rows = db_session.scalars(
+            select(Memory).where(Memory.user_id == user_id).order_by(Memory.id.asc())
+        ).all()
 
-    if index < 0 or index >= len(memory_rows):
-        return None
+        if index < 0 or index >= len(memory_rows):
+            return None
 
-    memory = memory_rows[index]
-    memory.memory_text = new_text
-    db_session.commit()
-    return memory
+        memory = memory_rows[index]
+        memory.memory_text = new_text
+        db_session.commit()
+        return memory.id

backend/onyx/db/models.py

@@ -2422,6 +2422,8 @@ class IndexAttemptError(Base):
     failure_message: Mapped[str] = mapped_column(Text)
     is_resolved: Mapped[bool] = mapped_column(Boolean, default=False)
 
+    error_type: Mapped[str | None] = mapped_column(String, nullable=True)
+
     time_created: Mapped[datetime.datetime] = mapped_column(
         DateTime(timezone=True),
         server_default=func.now(),

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/deep_research/dr_loop.py

@@ -7,8 +7,6 @@ import time
 from collections.abc import Callable
 from typing import cast
 
-from sqlalchemy.orm import Session
-
 from onyx.chat.chat_state import ChatStateContainer
 from onyx.chat.citation_processor import CitationMapping
 from onyx.chat.citation_processor import DynamicCitationProcessor
@@ -22,6 +20,7 @@ from onyx.chat.models import LlmStepResult
 from onyx.chat.models import ToolCallSimple
 from onyx.configs.chat_configs import SKIP_DEEP_RESEARCH_CLARIFICATION
 from onyx.configs.constants import MessageType
+from onyx.db.engine.sql_engine import get_session_with_current_tenant
 from onyx.db.tools import get_tool_by_name
 from onyx.deep_research.dr_mock_tools import get_clarification_tool_definitions
 from onyx.deep_research.dr_mock_tools import get_orchestrator_tools
@@ -184,6 +183,14 @@ def generate_final_report(
         return has_reasoned
 
 
+def _get_research_agent_tool_id() -> int:
+    with get_session_with_current_tenant() as db_session:
+        return get_tool_by_name(
+            tool_name=RESEARCH_AGENT_TOOL_NAME,
+            db_session=db_session,
+        ).id
+
+
 @log_function_time(print_only=True)
 def run_deep_research_llm_loop(
     emitter: Emitter,
@@ -193,7 +200,6 @@ def run_deep_research_llm_loop(
     custom_agent_prompt: str | None,  # noqa: ARG001
     llm: LLM,
     token_counter: Callable[[str], int],
-    db_session: Session,
     skip_clarification: bool = False,
     user_identity: LLMUserIdentity | None = None,
     chat_session_id: str | None = None,
@@ -717,6 +723,7 @@ def run_deep_research_llm_loop(
                     simple_chat_history.append(assistant_with_tools)
 
                     # Now add TOOL_CALL_RESPONSE messages and tool call info for each result
+                    research_agent_tool_id = _get_research_agent_tool_id()
                     for tab_index, report in enumerate(
                         research_results.intermediate_reports
                     ):
@@ -737,10 +744,7 @@ def run_deep_research_llm_loop(
                             tab_index=tab_index,
                             tool_name=current_tool_call.tool_name,
                             tool_call_id=current_tool_call.tool_call_id,
-                            tool_id=get_tool_by_name(
-                                tool_name=RESEARCH_AGENT_TOOL_NAME,
-                                db_session=db_session,
-                            ).id,
+                            tool_id=research_agent_tool_id,
                             reasoning_tokens=llm_step_result.reasoning
                             or most_recent_reasoning,
                             tool_call_arguments=current_tool_call.tool_args,

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
 
@@ -451,29 +463,13 @@ def _remove_empty_runs(
     return result
 
 
-def xlsx_to_text(file: IO[Any], file_name: str = "") -> str:
-    # TODO: switch back to this approach in a few months when markitdown
-    # fixes their handling of excel files
+def xlsx_sheet_extraction(file: IO[Any], file_name: str = "") -> list[tuple[str, str]]:
+    """
+    Converts each sheet in the excel file to a csv condensed string.
+    Returns a string and the worksheet title for each worksheet
 
-    # md = get_markitdown_converter()
-    # stream_info = StreamInfo(
-    #     mimetype=SPREADSHEET_MIME_TYPE, filename=file_name or None, extension=".xlsx"
-    # )
-    # try:
-    #     workbook = md.convert(to_bytesio(file), stream_info=stream_info)
-    # except (
-    #     BadZipFile,
-    #     ValueError,
-    #     FileConversionException,
-    #     UnsupportedFormatException,
-    # ) as e:
-    #     error_str = f"Failed to extract text from {file_name or 'xlsx file'}: {e}"
-    #     if file_name.startswith("~"):
-    #         logger.debug(error_str + " (this is expected for files with ~)")
-    #     else:
-    #         logger.warning(error_str)
-    #     return ""
-    # return workbook.markdown
+    Returns a list of (csv_text, sheet)
+    """
     try:
         workbook = openpyxl.load_workbook(file, read_only=True)
     except BadZipFile as e:
@@ -482,23 +478,30 @@ def xlsx_to_text(file: IO[Any], file_name: str = "") -> str:
             logger.debug(error_str + " (this is expected for files with ~)")
         else:
             logger.warning(error_str)
-        return ""
+        return []
     except Exception as e:
         if any(s in str(e) for s in KNOWN_OPENPYXL_BUGS):
             logger.error(
                 f"Failed to extract text from {file_name or 'xlsx file'}. This happens due to a bug in openpyxl. {e}"
             )
-            return ""
+            return []
         raise
 
-    text_content = []
+    sheets: list[tuple[str, str]] = []
     for sheet in workbook.worksheets:
         sheet_matrix = _clean_worksheet_matrix(_worksheet_to_matrix(sheet))
         buf = io.StringIO()
         writer = csv.writer(buf, lineterminator="\n")
         writer.writerows(sheet_matrix)
-        text_content.append(buf.getvalue().rstrip("\n"))
-    return TEXT_SECTION_SEPARATOR.join(text_content)
+        csv_text = buf.getvalue().rstrip("\n")
+        if csv_text.strip():
+            sheets.append((csv_text, sheet.title))
+    return sheets
+
+
+def xlsx_to_text(file: IO[Any], file_name: str = "") -> str:
+    sheets = xlsx_sheet_extraction(file, file_name)
+    return TEXT_SECTION_SEPARATOR.join(csv_text for csv_text, _title in sheets)
 
 
 def eml_to_text(file: IO[Any]) -> str:

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
@@ -16,16 +14,14 @@ from onyx.connectors.cross_connector_utils.miscellaneous_utils import (
     get_metadata_keys_to_ignore,
 )
 from onyx.connectors.models import IndexingDocument
-from onyx.connectors.models import Section
+from onyx.indexing.chunking import DocumentChunker
+from onyx.indexing.chunking import extract_blurb
 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/chunking/__init__.py

@@ -0,0 +1,7 @@
+from onyx.indexing.chunking.document_chunker import DocumentChunker
+from onyx.indexing.chunking.section_chunker import extract_blurb
+
+__all__ = [
+    "DocumentChunker",
+    "extract_blurb",
+]

backend/onyx/indexing/chunking/document_chunker.py

@@ -0,0 +1,111 @@
+from chonkie import SentenceChunker
+
+from onyx.connectors.models import IndexingDocument
+from onyx.connectors.models import Section
+from onyx.connectors.models import SectionType
+from onyx.indexing.chunking.image_section_chunker import ImageChunker
+from onyx.indexing.chunking.section_chunker import AccumulatorState
+from onyx.indexing.chunking.section_chunker import ChunkPayload
+from onyx.indexing.chunking.section_chunker import SectionChunker
+from onyx.indexing.chunking.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._dispatch: dict[SectionType, SectionChunker] = {
+            SectionType.TEXT: TextChunker(
+                tokenizer=tokenizer,
+                chunk_splitter=chunk_splitter,
+            ),
+            SectionType.IMAGE: 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
+
+        # Final flush — any leftover buffered text becomes one last payload.
+        payloads.extend(accumulator.flush_to_list())
+
+        return payloads
+
+    def _select_chunker(self, section: Section) -> SectionChunker:
+        try:
+            return self._dispatch[section.type]
+        except KeyError:
+            raise ValueError(f"No SectionChunker registered for type={section.type}")

backend/onyx/indexing/chunking/image_section_chunker.py

@@ -0,0 +1,35 @@
+from onyx.connectors.models import Section
+from onyx.indexing.chunking.section_chunker import AccumulatorState
+from onyx.indexing.chunking.section_chunker import ChunkPayload
+from onyx.indexing.chunking.section_chunker import SectionChunker
+from onyx.indexing.chunking.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 ""
+
+        # Flush any partially built text chunks
+        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(),
+        )