* perf: cut serial round trips from the agent list query path
The agent list was the slowest path on first page load. Three separate
problems compounded:
- `getListAgentsHandler` chained its reads: two ACL lookups, the avatar
refresh cache probe and the viewer skill scope all resolved serially
ahead of the list query, and `attachOwnerContacts` added two more hops
after it. The four independent reads now resolve together, and the
avatar refresh runs alongside the list query instead of before it -
refreshed paths reach the response through `urlCache`, not through
whatever the list query happened to read. Serial hops per request drop
from 7 to 4 on a warm cache.
- The avatar refresh loaded the user's whole accessible agent set (up to
MAX_AVATAR_REFRESH_AGENTS) to discover which entries were S3-backed.
Scoping the query to `avatar.source` means deployments on any other
file strategy match nothing instead of walking the full set.
- `fetchAllAgentPages` walked cursor pages at the server's default size
of 100, and callers consume the flattened result, so every extra page
was a serial round trip for no benefit. It now requests the server
maximum. Measured over a 2,860 agent account: 29 requests / 1.65s
before, 3 requests / 0.29s after.
Also parallelizes the conversation file reads in `initializeAgent`. The
convo file refs and the execute_code thread walk share no inputs, and the
two code-file lookups depend only on `threadFileIds`, so the chain of six
serial reads on every turn collapses to two. This one is time to first
token the user waits through.
* perf: virtualize the model selector agent list
Opening the agents submenu with a large agent set froze the tab and could
kill it outright. With ~10k accessible agents the submenu blocked for over
15 seconds and took the heap from 96MB to 911MB. Four per-row costs were
being multiplied by the full list, which rendered unwindowed:
- `useIsActiveItem` allocated a MutationObserver per row (10,016 of them
for one dropdown). Replaced with an Ariakit store subscription, which
needs no observer at all and returns a boolean so a row only re-renders
when its own active state flips.
- `useFavorites` ran per row, opening a jotai subscription, a query
subscription and a mutation each time. Hoisted to one call per endpoint.
- Each row rescanned `endpoint.models` to recover `isGlobal`, a field the
parent had already discarded from the array it was mapping. The parent
now passes it down from a lookup map.
- The list itself is now windowed above 100 rows. Ariakit's composite only
knows about mounted rows, so arrow-keying to the window edge previously
found no next item and let focus escape the nested menu, closing it;
`handleBoundaryNavigation` scrolls the next index in, waits for it to
mount, then moves the composite onto it. Navigation inside the window is
left to Ariakit.
Open drops from >15s to 96ms, mounted rows from 10,028 to ~18, DOM nodes
from 123,346 to ~1,000, and the heap no longer grows. Verified in browser:
arrow keys track 1:1 to index 238 and back, and click selection works.
* perf: serve the model selector from the shared VIEW agent query
The model selector asked for EDIT-scoped agents whenever the marketplace
is enabled, while `useAgentsMap` and `useMentions` asked for VIEW. Since
the cache key includes the params, that was two distinct entries, so first
page load ran the paginated walk twice and held two copies of the whole
agent list in memory. Measured against a 10k agent account: 22 list handler
invocations per page load, now 11.
Collapsing the two by asking for the same permission everywhere would have
changed what the selector shows - under the marketplace the EDIT scope is
what makes it "My Agents", with discovery handled by the marketplace entry.
So the list endpoint now marks each row with `isEditable`, resolved from an
ACL read folded into the existing parallel batch (no extra serial hop), and
the selector filters the shared VIEW response instead of refetching. A
VIEW-scoped list for a user with 2861 visible / 361 editable agents returns
exactly 360 rows flagged editable, matching what the EDIT query returned.
`AgentSelect` deliberately keeps its own EDIT query: it reads `skills` and
`skills_enabled`, which `sanitizeViewerSkillScope` strips from VIEW-scoped
responses. It also only mounts when the builder panel is open, so it is not
part of the first-load cost.
The field is set unconditionally rather than omitted when false so that a
client talking to an older server sees `undefined`, keeps every agent, and
degrades to showing too many rather than none.
* fix: address review findings on the agent list at scale
Three issues from review, all confirmed against the code before fixing.
Avatar refresh no longer runs alongside the list query. `updateAgent` writes
through `findOneAndUpdate` on a `timestamps: true` schema, so refreshing an
avatar advances `updatedAt` — the field `getListAgentsByAccess` sorts and
cursors on. A write landing after the first page's snapshot moved that agent
ahead of the returned cursor, dropping it from every later page and silently
truncating the caller's flattened list. This was a regression introduced when
the two were parallelized; serializing them costs nothing on the common path,
because a cache hit returns without issuing any query, so only the
once-per-30-minutes miss pays for the ordering. The new test asserts the write
lands before the list snapshot and fails against the parallel version.
The virtualized list no longer inserts a focusable grid into the combobox.
`List` spreads its props onto `Grid`, whose defaults are `role="grid"`,
`containerRole="row"` and `tabIndex={0}`; inside Ariakit's listbox that added a
tab stop ahead of any row and put grid/row semantics between the listbox and its
options. All three are now neutralized so focus and ARIA stay with the combobox
items.
The list also resets to the top when the filter changes. `Grid` keeps its scroll
offset across prop changes and clamps an out-of-range offset to
`totalRowsHeight - height`, the end of the shorter list. Scrolling deep and then
searching landed on the tail: measured at row 626 of 667 matches, with only
those rows mounted and reachable by keyboard. Keying the list on the search
value restores row 0.
* fix: declare option position and set size for the virtualized model list
Once the model list is windowed, only the mounted slice exists in the listbox,
so a screen reader infers position and total from ~19 elements instead of the
real set — announcing "3 of 19" partway through 10,014 agents.
Model rows now carry aria-posinset and aria-setsize. The marketplace entry and
any model specs share the same numbering, because they are options in the same
listbox: declaring the values on some options while leaving others to be
inferred from the DOM would make the set internally inconsistent. Both are
omitted entirely when the list is short enough to render unwindowed, where the
DOM holds every option and the implicit values are already correct.
Verified against a 10,014 agent account: the marketplace entry reports 1 of
10015, the first models 2 and 3, and after scrolling to row 4999 the leading
mounted model reports 5001 of 10015 with 19 options in the DOM.
* 🩹 fix: Address Follow-Ups on the Agent List at Scale
Corrects residual issues in the agent-list perf work, all inside its own scope.
- Forward `idOnTheSource` through `PermissionService.findAccessibleResources`
so `getUserPrincipals` skips the user-document read. The list handler resolves
three permission sets per request and each was paying its own `User.findById`;
the auth strategies already normalize the field to a value or null.
- Gate the editable-set lookup on its own predicate instead of borrowing
`canReturnSkillConfig`. The two answer unrelated questions and only coincide
today, so redefining the skill flag would have marked every agent editable.
- Log mapping failures in the list response instead of swallowing them.
- Apply the walk page size after the caller's params in `fetchAllAgentPages`.
A caller limit only changed page size, never what the flattened walk returned,
so `defaultAgentParams`' `limit: 10` would have turned one request into 301.
- Carry `isEditable` on the agent rows the create and update mutations write
into the list cache. Mutation responses omit the field, so those rows lost it.
- Document `isEditable` as list-only, ACL-derived, and fail-open on absence.
- Restore the truthiness guard on the thread walk in `initializeAgent`. Widening
it to `!= null` made an empty `parentMessageId` issue a full-conversation read
against an anchor that can never match.
- Await `getConvoFiles` directly rather than calling `.then()` on it, restoring
tolerance for synchronous test doubles.
- Correct the avatar-refresh comment: the projection was never full documents,
and the real reason to filter is that an unfiltered budget is self-reinforcing.
Tests: both new `initialize` tests and both new backend tests are
mutation-verified; the concurrency test fails under either serialization order.
* fix: preserve ACL isEditable when merging agent mutation responses
Mutation responses omit list-only isEditable. Inferring true from write
success promoted VIEW-only rows into the editable subset for MANAGE_AGENTS
callers who can PATCH agents their ACL marks non-editable.
* fix: sort imports in agent mutations test
ESLint import-order check failed on the isEditable cache-preservation test.
* 🧷 fix: Carry isEditable Onto Duplicated Agent List Rows
`useDuplicateAgentMutation` prepended the raw duplicate response to the cached
list, and mutation responses omit the list-only `isEditable` field. The row
survived the "My Agents" filter only by failing open on `undefined`, so it would
disappear the moment a consumer read the flag strictly.
Duplicating grants the caller ownership, so the new row is editable outright;
this is the create case rather than the merge case `mergeAgentListRow` handles.
Last cache write on this path that did not carry the field.
---------
Co-authored-by: Danny Avila <danny@librechat.ai>
* 🔒 fix: Skip revoke for principals also being granted (owner-lockout guard)
bulkUpdateResourcePermissions flushes grants (upserts) before revokes (deletes).
If a principal appears in both updatedPrincipals and revokedPrincipals, the ACL
entry is granted and then immediately deleted, stripping access the caller just
set. This can strip a resource owner's own grant when the share dialog places
the owner in both lists from a client id/idOnTheSource mismatch (OpenID/Entra).
Add a server-side guard: track principals granted in the same request and skip
any revoke for the same principal, so granting wins and owner lockout is
impossible regardless of how the client computes the share diff. Complements the
client-side keying fix in #14317.
Refs #14316
* 🔒 fix: Exclude PUBLIC from grant-wins guard so public-disable is honored
The grant-wins guard must not apply to PrincipalType.PUBLIC. An explicit
public: false disable adds the public principal to the revoke list; a
contradictory payload that also grants public (public in the updated list) would
otherwise skip the revoke and leave the resource public. Disabling public access
must always win. User/group owner-lockout protection is unchanged.
Addresses Codex P2 on #14347.
* 🔒 fix: Move revoke guard inside per-principal try (tolerate malformed entries)
The grant-wins guard read principal.type before the per-principal try/catch, so
a malformed revoke entry (e.g. removed: [null]) would throw out of
bulkUpdateResourcePermissions after grants were already flushed on
non-transactional MongoDB, leaving partial permission changes. Move the guard
inside the try so a malformed entry is recorded in results.errors and skipped,
matching prior behavior.
Addresses Codex P2 on #14347.
* 🗃️ perf: Cache Group Memberships for ACL Principal Resolution
Continues #14069: caches resolved group-membership ids per member key in a
new USER_PRINCIPALS namespace so repeated permission checks skip the group
query, with exact invalidation on every membership mutation, same-process
build dedup, and optional Redis cross-container build locks.
Co-authored-by: Peter Rothlaender <peter.rothlaender@ginkgo.com>
Co-authored-by: Joachim Keltsch <joachim.keltsch@daimlertruck.com>
* 🧵 fix: Defer Transactional Invalidation and Gate No-Op Bulk Clears
Codex round-2 findings on the principals cache: membership writes inside a
transaction now defer cache invalidation until the session ends so concurrent
readers cannot re-cache pre-commit state with no later correction, and
bulkUpdateGroups skips invalidation entirely when MongoDB reports no modified
or upserted documents. userGroup.spec.ts now runs on a single-node replica set
so the deferral is covered by a real transaction.
* 🌐 fix: Evict Cross-Process Stale Rewrites and Scope Entra Sync to Tenant
Codex round-3 findings: a delayed second invalidation pass (lock wait plus a
short grace) now evicts membership entries that a build in another container
re-cached after the first delete, and syncUserEntraGroupMemberships establishes
the user's tenant ALS context when the OAuth callback runs it pre-middleware,
so tenant-scoped principal keys are invalidated (and sync queries and created
groups are scoped) exactly like authenticated reads. Deferred transactional
invalidations snapshot the caller's ALS so they keep tenant scoping.
---------
Co-authored-by: Peter Rothlaender <peter.rothlaender@ginkgo.com>
Co-authored-by: Joachim Keltsch <joachim.keltsch@daimlertruck.com>
* feat: implement optimized Entra group sync with auto-creation
## Changes
### MUST FIX (Critical Issues) - RESOLVED
1. **BUG FIX: Prevent unintended user removal from existing groups**
- ISSUE: db.syncUserEntraGroups() was called with only missing groups, causing removal
from all existing Entra groups (full bidirectional sync behavior)
- SOLUTION: Replaced with db.upsertGroupByExternalId() for each missing group followed
by single bulkUpdateGroups() to add memberships (race-safe, idempotent)
- BENEFIT: User memberships correctly maintained for mix of existing + new groups
2. **JSDoc @throws contradiction**
- ISSUE: JSDoc declared function throws, but implementation catches all errors
- SOLUTION: Removed @throws from JSDoc - function is best-effort
- BENEFIT: Prevents unnecessary try/catch in caller code
3. **Missing test for group creation flow**
- ISSUE: Auto-creating missing Entra groups had no test coverage
- SOLUTION: Added regression test for mix of existing + new groups scenario
- BENEFIT: Prevents future regressions on critical path
### SHOULD FIX (Important Improvements) - RESOLVED
4. **E11000 race condition handling**
- SOLUTION: Upserts are idempotent and race-safe by design
- BENEFIT: Concurrent logins no longer race each other
5. **Direct Mongoose access instead of db layer**
- SOLUTION: Added findGroupsByExternalIds() helper to userGroup.ts
- BENEFIT: Centralized data access, easier to add tenant scoping
6. **Serial DB round-trips on login path**
- ISSUE: 40+ queries for user with 20 new groups
- SOLUTION: Promise.all() for parallel upserts + single bulkUpdate
- BENEFIT: ~10x performance improvement
7. **Graph API 429/503 throttling unhandled**
- SOLUTION: Retry logic with exponential backoff (1s, 2s delays)
- BENEFIT: Temporary API issues no longer cause permanent membership loss
8. **Sequential batch requests slow**
- ISSUE: 200 groups = 10 batches × 200ms = ~2s sequential
- SOLUTION: Promise.all() with concurrency limit (5 parallel batches)
- BENEFIT: ~400ms total time
## Minor Fixes
- Removed dead code check
- PII removal: user._id instead of user.email in logs
- ES6 shorthand fixes
- Style consistency (blank lines)
- Projection optimization
## Verification
✅ npm run build - success
✅ npm run test:api - 61/61 passing (+ new regression test)
✅ npm run lint - no errors
✅ All feedback from danny-avila resolved
* docs: better JSDoc for the syncUserEntraGroupMemberships method
---------
Co-authored-by: Airam Hernández Hernández <airam.hernandez@intelequia.com>
* feat: replace unsupported MongoDB aggregation operators for FerretDB compatibility
Replace $lookup, $unwind, $sample, $replaceRoot, and $addFields aggregation
stages which are unsupported on FerretDB v2.x (postgres-documentdb backend).
- Prompt.js: Replace $lookup/$unwind/$project pipelines with find().select().lean()
+ attachProductionPrompts() batch helper. Replace $group/$replaceRoot/$sample
in getRandomPromptGroups with distinct() + Fisher-Yates shuffle.
- Agent/Prompt migration scripts: Replace $lookup anti-join pattern with
distinct() + $nin two-step queries for finding un-migrated resources.
All replacement patterns verified against FerretDB v2.7.0.
* fix: use $pullAll for simple array removals, fix memberIds type mismatches
Replace $pull with $pullAll for exact-value scalar array removals. Both
operators work on MongoDB and FerretDB, but $pullAll is more explicit for
exact matching (no condition expressions).
Fix critical type mismatch bugs where ObjectId values were used against
String[] memberIds arrays in Group queries:
- config/delete-user.js: use string uid instead of ObjectId user._id
- e2e/setup/cleanupUser.ts: convert userId.toString() before query
Harden PermissionService.bulkUpdateResourcePermissions abort handling to
prevent crash when abortTransaction is called after commitTransaction.
All changes verified against FerretDB v2.7.0 and MongoDB Memory Server.
* fix: harden transaction support probe for FerretDB compatibility
Commit the transaction before aborting in supportsTransactions probe, and
wrap abortTransaction in try-catch to prevent crashes when abort is called
after a successful commit (observed behavior on FerretDB).
* feat: add FerretDB compatibility test suite, retry utilities, and CI config
Add comprehensive FerretDB integration test suite covering:
- $pullAll scalar array operations
- $pull with subdocument conditions
- $lookup replacement (find + manual join)
- $sample replacement (distinct + Fisher-Yates)
- $bit and $bitsAllSet operations
- Migration anti-join pattern
- Multi-tenancy (useDb, scaling, write amplification)
- Sharding proof-of-concept
- Production operations (backup/restore, schema migration, deadlock retry)
Add production retryWithBackoff utility for deadlock recovery during
concurrent index creation on FerretDB/DocumentDB backends.
Add UserController.spec.js tests for deleteUserController (runs in CI).
Configure jest and eslint to isolate FerretDB tests from CI pipelines:
- packages/data-schemas/jest.config.mjs: ignore misc/ directory
- eslint.config.mjs: ignore packages/data-schemas/misc/
Include Docker Compose config for local FerretDB v2.7 + postgres-documentdb,
dedicated jest/tsconfig for the test files, and multi-tenancy findings doc.
* style: brace formatting in aclEntry.ts modifyPermissionBits
* refactor: reorganize retry utilities and update imports
- Moved retryWithBackoff utility to a new file `retry.ts` for better structure.
- Updated imports in `orgOperations.ferretdb.spec.ts` to reflect the new location of retry utilities.
- Removed old import statement for retryWithBackoff from index.ts to streamline exports.
* test: add $pullAll coverage for ConversationTag and PermissionService
Add integration tests for deleteConversationTag verifying $pullAll
removes tags from conversations correctly, and for
syncUserEntraGroupMemberships verifying $pullAll removes user from
non-matching Entra groups while preserving local group membership.
---------
* Feature: Dynamic MCP Server with Full UI Management
* 🚦 feat: Add MCP Connection Status icons to MCPBuilder panel (#10805)
* feature: Add MCP server connection status icons to MCPBuilder panel
* refactor: Simplify MCPConfigDialog rendering in MCPBuilderPanel
---------
Co-authored-by: Atef Bellaaj <slalom.bellaaj@external.daimlertruck.com>
Co-authored-by: Danny Avila <danny@librechat.ai>
* fix: address code review feedback for MCP server management
- Fix OAuth secret preservation to avoid mutating input parameter
by creating a merged config copy in ServerConfigsDB.update()
- Improve error handling in getResourcePermissionsMap to propagate
critical errors instead of silently returning empty Map
- Extract duplicated MCP server filter logic by exposing selectableServers
from useMCPServerManager hook and using it in MCPSelect component
* test: Update PermissionService tests to throw errors on invalid resource types
- Changed the test for handling invalid resource types to ensure it throws an error instead of returning an empty permissions map.
- Updated the expectation to check for the specific error message when an invalid resource type is provided.
* feat: Implement retry logic for MCP server creation to handle race conditions
- Enhanced the createMCPServer method to include retry logic with exponential backoff for handling duplicate key errors during concurrent server creation.
- Updated tests to verify that all concurrent requests succeed and that unique server names are generated.
- Added a helper function to identify MongoDB duplicate key errors, improving error handling during server creation.
* refactor: StatusIcon to use CircleCheck for connected status
- Replaced the PlugZap icon with CircleCheck in the ConnectedStatusIcon component to better represent the connected state.
- Ensured consistent icon usage across the component for improved visual clarity.
* test: Update AccessControlService tests to throw errors on invalid resource types
- Modified the test for invalid resource types to ensure it throws an error with a specific message instead of returning an empty permissions map.
- This change enhances error handling and improves test coverage for the AccessControlService.
* fix: Update error message for missing server name in MCP server retrieval
- Changed the error message returned when the server name is not provided from 'MCP ID is required' to 'Server name is required' for better clarity and accuracy in the API response.
---------
Co-authored-by: Atef Bellaaj <slalom.bellaaj@external.daimlertruck.com>
Co-authored-by: Danny Avila <danny@librechat.ai>
WIP: Role as Permission Principal Type
WIP: add user role check optimization to user principal check, update type comparisons
WIP: cover edge cases for string vs ObjectId handling in permission granting and checking
chore: Update people picker access middleware to use PrincipalType constants
feat: Enhance people picker access control to include roles permissions
chore: add missing default role schema values for people picker perms, cleanup typing
feat: Enhance PeoplePicker component with role-specific UI and localization updates
chore: Add missing `VIEW_ROLES` permission to role schema
- Replaced string literals for principal models ('User', 'Group') with the new PrincipalModel enum across various models, services, and tests to enhance type safety and consistency.
- Updated permission handling in multiple files to utilize the PrincipalModel enum, improving maintainability and reducing potential errors.
- Ensured all relevant tests reflect these changes to maintain coverage and functionality.
- Replaced string literals for principal types ('user', 'group', 'public') with the new PrincipalType enum across various models, services, and tests for improved type safety and consistency.
- Updated permission handling in multiple files to utilize the PrincipalType enum, enhancing maintainability and reducing potential errors.
- Ensured all relevant tests reflect these changes to maintain coverage and functionality.
- Refactor tests to use PromptGroup roles instead of Project roles.
- Initialize models and seed default roles in test setup.
- Update error handling for non-existent resource types.
- Ensure proper cleanup of test data while retaining seeded roles.
refactor: organize Sharing/Agent components, improve type safety for resource types and access role ids, rename enums to PascalCase
refactor: organize Sharing/Agent components, improve type safety for resource types and access role ids
chore: move sharing related components to dedicated "Sharing" directory
chore: remove PublicSharingToggle component and update index exports
chore: move non-sidepanel agent components to `~/components/Agents`
chore: move AgentCategoryDisplay component with tests
chore: remove commented out code
refactor: change PERMISSION_BITS from const to enum for better type safety
refactor: reorganize imports in GenericGrantAccessDialog and update index exports for hooks
refactor: update type definitions to use ACCESS_ROLE_IDS for improved type safety
refactor: remove unused canAccessPromptResource middleware and related code
refactor: remove unused prompt access roles from createAccessRoleMethods
refactor: update resourceType in AclEntry type definition to remove unused 'prompt' value
refactor: introduce ResourceType enum and update resourceType usage across data provider files for improved type safety
refactor: update resourceType usage to ResourceType enum across sharing and permissions components for improved type safety
refactor: standardize resourceType usage to ResourceType enum across agent and prompt models, permissions controller, and middleware for enhanced type safety
refactor: update resourceType references from PROMPT_GROUP to PROMPTGROUP for consistency across models, middleware, and components
refactor: standardize access role IDs and resource type usage across agent, file, and prompt models for improved type safety and consistency
chore: add typedefs for TUpdateResourcePermissionsRequest and TUpdateResourcePermissionsResponse to enhance type definitions
chore: move SearchPicker to PeoplePicker dir
refactor: implement debouncing for query changes in SearchPicker for improved performance
chore: fix typing, import order for agent admin settings
fix: agent admin settings, prevent agent form submission
refactor: rename `ACCESS_ROLE_IDS` to `AccessRoleIds`
refactor: replace PermissionBits with PERMISSION_BITS
refactor: replace PERMISSION_BITS with PermissionBits
WIP: pre-granular-permissions commit
feat: Add category and support contact fields to Agent schema and UI components
Revert "feat: Add category and support contact fields to Agent schema and UI components"
This reverts commit c43a52b4c9.
Fix: Update import for renderHook in useAgentCategories.spec.tsx
fix: Update icon rendering in AgentCategoryDisplay tests to use empty spans
refactor: Improve category synchronization logic and clean up AgentConfig component
refactor: Remove unused UI flow translations from translation.json
feat: agent marketplace features
🔐 feat: Granular Role-based Permissions + Entra ID Group Discovery (#7804)
