* fix: Bind Role Delete Config Restore to the Role Identity and Audit the Members It Moved
* fix: Reassign Deleted Role Members With Per-Account Conditional Writes
* test: Type the Member Reassignment Race Spy With Mongoose Query Types
* perf: Reassign Deleted Role Members in Stamped Bulk Writes
* test: Type the Bulk Reassignment Race Spy Options
* fix: Attribute Role Deletion Reassignments by a Per-Batch Nonce
* fix: Keep a Role Whose Members Could Not All Be Reassigned and Audit Those Moved
* fix: Report a Reassignment Batch Whose Write Committed Before Rejecting
* fix: Audit Members Moved Before a Concurrent Role Deletion Won
* fix: Hold Role Deletion to Its Identity, Audit, Cache and Retry Invariants on Every Path
* fix: Recheck the Targeted Role Before Every Reassignment Batch
* fix: Resolve the Targeted Role Id When a Role Delete Names Only the Role
* fix: Report Each Reassigned Account Once and Retry a Config Restore Deferred by an Unreadable Role
* fix: Keep the Reassignment Tag When a Failed Batch Cannot Be Read Back
* fix: Keep Each Overlapping Role Deletion's Reassignment Tag on the Accounts It Moved
* 🔎 fix: Keep Scoped Package Frames Out of the Log Email Redactor
The log redactor read node_modules/@scope/pkg/... as an address and replaced
whole stack frame locations with [REDACTED_EMAIL], in file, console and
OpenTelemetry output alike. An @ between path separators now names a scoped
package; addresses beside such frames are still masked.
* 🪪 feat: Name the Build and Loaded Config on OpenTelemetry Records
service.version now defaults to the image's BUILD_COMMIT ahead of the npm
package version. Each successful librechat.yaml load records a short digest
of the parsed file, which exported log records and request spans carry as
librechat.config.digest, and applies telemetry.stackTraceLimit to
Error.stackTraceLimit; unset keeps the process default.
* fix: Publish telemetry settings with the accepted base config
* fix: Initialize process settings before adopting cached config
* fix: Preserve runtime settings when cache writes are refused
* fix: Keep telemetry identity local and propagate Redis write errors
* fix: Partition merged config caches by the local base
* fix: Keep config cache failures recoverable
* test: Verify cache recovery contracts with typed fixtures
---------
Co-authored-by: Lia <lia@librechat.ai>
* refactor: Move Ask State, Approval and File Previews, and Diff View Into the Chat Package
* fix: Point the HITL Edits Spec at the Moved Approval Preview
- Let agents use Langfuse prompts by production label or pinned version,
with the existing permission and usage checks.
- Add a configuration switch, disabled by default. Preserve saved links
while disabled, without resolving them or falling back to inline text.
- Share source-specific production and exact selections across agent
links and the prompt service. Reject source mismatches.
- Add revision lists for the Agent Builder version picker. Resolve
Langfuse instructions on each initialization without caching.
- Improve disabled and unavailable states and test source changes,
revision loading, and permission failures.
* 🥐 chore: Standardize Bun-First Workspace Typechecks
* fix: Preserve Bun 1.4.3 Checker Compatibility
* chore: Pin Bun 1.4.4 for Local and CI Typechecks
---------
Co-authored-by: Lia <lia@librechat.ai>
* perf: Serve JWT Bearer User Lookups From the Auth User Cache
* perf: Batch Agent Permission Reads on the File Access Path
* perf: Remember a Loaded Google Service Key Across Endpoint Config Reads
* perf: Run Independent Startup, Tool, Skill and Erasure Reads Concurrently
* fix: Drop JWT User Cache Writes That Race a User Mutation
Confirm each cache write with a second read and evict when the user changed,
so an in-flight lookup cannot repopulate an entry a credential change just
evicted. The cache mode now arrives through the loader dependencies.
* refactor: Move Agent Skill Access Reads Into packages/api
The chat-completions and Responses controllers call loadSkillAccess instead of
orchestrating the three reads in CJS. The preview route spec mocks the batched
file access helper the middleware now calls.
* test: Cover Agent File Access, JWT Bursts and Remote Skill Reads End to End
* fix: Serve a Cached JWT User Only While Its updatedAt Is Current
A cache hit now reads the stored updatedAt and deletion fence instead of the
fence alone, so a document cached from a read that raced a user mutation is
never served, even when the write landed after that mutation's eviction.
* refactor: Move Startup Migration Checks Into packages/api
* refactor: Inject the Startup Migration Checks Instead of Mongoose Models
* fix: Serve Cached OpenID Users Only While Their updatedAt Is Current
Moves the freshness check into getCurrentCachedAuthUserDoc and uses it on the
OpenID bearer path as well as the local JWT one, so a document cached from a
read that raced a credential or role change is never served there either.
Fixesberry-13/LibreChat#432
* fix: Compare Authorization Fields on Every Auth Cache Hit
updatedAt has millisecond resolution, so the freshness read also compares the
token retirement stamps, role, tenant and two-factor state.
* fix: Annotate the Auth Freshness Projection for Isolated Declarations
* perf: Reuse the OpenID Cache Freshness Read for Deletion Admission
A cache hit already proved the deletion fence is clear, so only users read from
the database take the separate fence query.
* refactor: Keep the OpenID Cache Freshness and Fence Decisions in packages/api
* test: Exercise JWT Cache Freshness Against Real User Methods in MongoDB
* fix: Stamp the JWT User Lookup So the Cache Write Fence Applies
* fix: Reload a Google Service Key File When It Changes or Disappears
The availability check remembers a loaded key only while the file's mtime and
size are unchanged, and fetches URL sources every time as before.
* fix: Recheck a Service Key File After a Permission Change
* 🚤 fix: Keep Host Tool Loading Independent of Worker Status
* fix: Classify Workspace Tools at the Agent Boundary
---------
Co-authored-by: Lia <lia@librechat.ai>
* fix: Fence Auth User Cache Writes After Eviction and Evict Favorite Holders
An eviction now leaves a per-user fence in the auth user cache that outlives
every document read before it. The reader skips a cached document while its
user is fenced, and a lookup slower than one cache TTL is not cached, so a
request that read the user before a change can no longer repopulate the cache
afterwards, and a document the reverse index lost is hidden as well. Role and
user methods share one bulk eviction helper, and the terms reset only waits
out the TTL when an eviction failed.
Deleting an agent, deleting a user's agents and removing an agent from
favorites now evict the cached auth documents of the users whose favorites
changed.
* fix: Anchor Cached Auth Document Expiry to the Lookup Start
A stalled reverse-index write could land a stale document after the eviction
fence expired, with a fresh TTL. The document now carries an expiry two cache
TTLs after its lookup began; its Redis TTL is computed after the index write
and the reader refuses it past that expiry.
* refactor: Time the Auth User Lookup in the API Package
The lookup start that anchors a cached document's lifetime is now stamped by
timeAuthUserLookup in packages/api, so the OpenID JWT strategy only wires the
lookup through it.
* fix: Wait Out the Full Cached Document Lifetime After Failed Eviction
A document read just before a change can live two cache TTLs from its lookup,
so a credential change or terms reset whose eviction failed now waits that
long before reporting success.
* fix: Recheck Cached Auth Document Expiry After the Fence Read
A fence read that stalls can return after both the fence and the document
expired, so the reader checks the document's expiry again before serving it.
* refactor: Move Pure Part Helpers Into @librechat/chat
Tool output parsers (JSON fields, background handles, wakeups, background
tasks, command results) and the small routing, params and rerun helpers move
from client Content/ into packages/chat/src/core/parts, exported from the
package root. Client importers read them from @librechat/chat; parseJsonField
becomes a named export so the root barrel can carry it.
* test: Cover Wake-Up Turns Rendering as Task Cards
* fix: Point the API Background Spec at the Moved Parsers
* fix: Bound outbound HTTP calls that had no timeout
Add timeouts.toolsMs, speechMs and imageGenerationMs to the timeouts block and apply the
existing budgets to the RAG delete paths, built-in tool APIs, TTS/STT providers (TTS also
aborts when the client closes), Stable Diffusion, Firebase reads and Mailgun. Calls made
before app config exists (remote config, RAG health, service key URL, Google refresh) get a
fixed 10 second budget.
* fix: Honor configured budgets for RAG deletes and per-chunk TTS deadlines
* refactor: Share one budget helper between speech and image CJS callers
* test: Cover a stalled RAG delete with a mock scenario
* test: Wait for the RAG embed before stalling the delete
* test: Embed at upload so the stalled delete has a vector to remove
* fix: Close a started TTS response on a late chunk timeout and share the service budget helper
* fix: Fail startup when the remote config fetch times out
* fix: Label Composer Thinking Levels and State the One-Shot Scope
* test: Cover Composer Thinking Labels and One-Shot Scope in E2E
* test: Cover Thinking Focus for Option Lists Without Auto
* test: Wait for the Thinking Popover's Open Focus Before Arrow Keys
* test: Match the High Effort Radio Exactly
* fix: Keep the Composer Thinking Level for the Rest of the Conversation
* fix: Keep a Queued Turn's Picked Level on the Turns Queued After It
* test: Name the Numeric Reasoning Control by Its Thinking Label
* fix: Name the Queued Turn's Level on the Thinking Button
* test: Dismiss the Thinking Tooltip Before Typing on a Phone
* fix: Respect Enforced Specs and Parameters Edits Over the Inherited Thinking Level
* test: Expect the Model Spec Enforcement Flag in Chat Settings
* fix: Keep a Queued Turn Off a Level Its Target No Longer Runs
* fix: Record the Target a Queued Turn's Level Belongs To
* refactor: Inherit the Thinking Level on the Server
* perf: Answer the Branch Level Lookup Without Tree Links When Nothing Was Picked
* fix: Respect the Thinking Switch and Held Queue Rows Over the Inherited Level
* fix: Read the Branch Level Once and Inherit Only on Fresh Turns
* fix: Keep a Parameters Thinking Edit From Turning Thinking On
* fix: Withdraw a Staged Thinking Level When Thinking Is Switched Off
* fix: Scope the Thinking Switch Transition to the Conversation
* test: Drop the One-Shot Thinking Scenario the Conversation Level Replaces
* perf: Parallelize Serial Lookups on Agent Load, Discovery, Skills, and Schedules
* fix: Address Review Findings on Parallel Lookups
Stage same-level discovery results before collecting edges so a shared sibling is initialized once, bound resume snapshot fetches to small chunks so over-budget graphs stop early, and surface the first ordered image failure without waiting on later reads. Update the skill name test for bounded concurrency.
* test: Tag Existing Mock Specs as Acceptance Scenarios for Parallel Lookups
* feat: Make Parallel Lookup Bounds Configurable
Add a concurrency section to librechat.yaml for MCP catalog, skill name, skill file and resume agent lookups. Defaults equal the previous hard-coded values.
* style: Sort Imports for Configurable Lookup Bounds
* test: Match Model Spec Skill Resolution Args With App Config
* test: Close the Builder Drawer Before Chatting on Narrow Viewports
* fix: Surface Fatal Discovery Errors Without Awaiting Later Siblings
* fix: Reject Discovery on the First Fatal Load Regardless of Queue Order
* fix: Keep Image Encoding Fail-Fast With Parallel Reads
* fix: Reject Resume Snapshot Lookups Without Waiting on the Whole Chunk
* feat: Make Connected Agent Discovery Concurrency Configurable
openid-client's Passport Strategy replaces the authorization request's state with a random one
when the IdP's discovery metadata does not list S256 in code_challenge_methods_supported and the
request has no nonce. Azure Entra ID omits that field, so the admin callback could not find the
admin panel's PKCE challenge under pkce:<state> and issued an exchange code that any
code_verifier, or none, could redeem.
The admin strategy now adds a nonce in that case, so openid-client keeps the admin route's state
and checks the nonce against the ID token on the callback. The chat OpenID flow is unchanged.
* fix: Keep the Snapshot When the Terminal Write Settled for Reconciliation
* fix: Promote a Reconciled Compaction Snapshot to the Terminal Row
* fix: Anchor and Envelope the Reconciled Snapshot by Its Claim
* test: Cover the Abandoned Compaction Settling After Its Run in E2E
* fix: Withhold the Disconnect Snapshot of Any Durably Settled Turn
* fix: Promote Only a Same-Epoch Reconciled Snapshot and Settle Stopped Compactions
* fix: Plan the Disconnect Snapshot in packages/api and Check the Response Row Before Promoting
* fix: Read the Disconnect Snapshot Rows in the Response Conversation
* fix: Check the Anchor-Derived Error Row Before Promoting a Reconciled Snapshot
* fix: Log a Failed Disconnect Snapshot Plan Instead of Rejecting the Listener
* fix: Let a Reconciled Compaction Promote After an Earlier Live Snapshot
* refactor: Decide the Repeat Disconnect Write in the Snapshot Plan
* refactor: Report Failed Snapshot Row Reads Through the Plan
* fix: Stamp a Promoted Disconnect Snapshot and Read Its Rows Together
* fix: Derive the Compaction Error Row ID Through the Shared Helper
* fix: Plan a Saved Live Compaction Snapshot Again Once Its Turn Settles
* refactor: Queue Disconnect Snapshots and Settle Them in packages/api
* fix: Never Count the Compaction Anchor as Its Own Terminal Row
* fix: Settle Disconnect Snapshots Before Terminal Cleanup Releases the Turn
* perf: Index Hot Lookups and Make Message Cursor Pagination Stable
Add narrow indexes for session refresh-token deletes, user-only tool call deletes, queued-turn delivery and reconciliation claims, agent code environment references, and updatedAt message pages. Add a TTL index to the KeyvMongo collection. getMessagesByCursor now sorts and pages on a unique (sortField, _id) tiebreaker with a millisecond-precise cursor while still accepting legacy cursors, and GET /api/messages caps pageSize in a TypeScript helper.
* fix: Keep the Message Id for the Cursor Under the Client Projection
* fix: Declare select on the Message Cursor Method Type
* feat: Make the Message Page Size Ceiling Configurable
* fix: Clamp the Default Message Page Size to the Configured Ceiling
* test: Cover Message Cursor Paging and Page Size Cap End to End
* fix: Continue Message Cursors Whose Sort Value Is Empty
* fix: Include Missing Sort Values When Paging Messages Descending
* perf: Resolve the Message Page Ceiling Beside the Ownership Read
* fix: Observe the Ownership Read While the Page Size Resolves
* style: Sort Imports in the Message Page Module
* refactor: Move Page Size Read Observation Into the API Package
* fix: Keep Missing and Empty Sort Values Distinct in the Message Cursor
* fix: Page Past Messages With a Missing Timestamp
* fix: Return approved tool and generation error text instead of raw exceptions
* fix: Redact generation error text without the data-schemas helper
* fix: Redact credentials and emails from shown generation errors
* refactor: Move the Wolfram status policy into packages/api
* test: Fix the Wolfram probe constructor and jest summary match
* test: Match the jest pass count through color codes
* fix: Redact credentials a tool input error echoes from its arguments
* fix: Drop free-text fields from typed generation errors under a content policy
* fix: Keep only the code and numeric fields of typed errors under a content policy
* fix: Fence ACL Viewers and Surface Revocation Failures When Removing Shared MCP Servers
Account erasure and server deletion now enumerate users the view ACL names
directly or through a group, so viewers without a personal OAuth token are
fenced and disconnected too. Erasure runs the OAuth teardown in strict mode,
which clears local credentials and then fails when the provider refuses a
revocation, keeping the server as the retry anchor, and holds every user's
teardown fence until the server delete commits.
* test: Type the Revocation Failure Cleanup Fixtures
* fix: Renew Retained OAuth Teardown Fences Before Deleting the Server
A teardown lease lasts 15 minutes, so a large erasure could outlive the
first fences it holds. Leases can now be renewed by their owner, and
erasure renews every retained fence right before the delete, failing
without deleting when one lapsed and another writer took it.
* fix: Report Refused MCP Revocations Without Blocking Account Erasure
A provider that refuses revocation, combined with a viewer who signs in
again between attempts, could keep an erasure failing indefinitely. The
strict teardown now throws a coded MCPOAuthRevocationError after clearing
local state and handing over its fence; server removal collects those as
refusals, logs each user and token type whose grant may remain valid, and
proceeds. Local failures (token delete, fence, ACL) still fail closed.
* fix: Annotate the Revocation Error Code for Isolated Declarations
* perf: Bound client hygiene paths (lodash imports, timeouts, listener cleanup, upload concurrency)
* feat: Make client request timeouts configurable
* test: Cover the configured refresh deadline end to end
* feat: Rename client timeouts to client limits and expose upload concurrency
* fix: Keep the published refresh deadline for the next page load
* fix: Harden Timer Sweeps, SSE Writes, and Violation Counters
Guard SSE writes against ended or destroyed responses through one helper, catch and single-flight the job store and TTL cache cleanup timers, serialize in-process counter updates, cap the violation log, prune stale OAuth failure records, batch the active-job lookup, and count Redis keys with DBSIZE.
* refactor: Drop the redundant violation log entry copy
* refactor: Log single-flight sweep failures from the API package
* test: Cover active generation listing and client disconnect mid-stream
* refactor: Configure violation log retention and move title timeout into the API package
* feat: Configure OAuth failure retention through mcpSettings
* fix: Prune OAuth failures promptly under short retention
* fix(agents): skip the empty-memory notice for agents that cannot use memory
Since #16301 formatMemoryContext('') returns the bare memory instructions sentence, and
prepareRuntimeAgent applied it to the primary agent whenever the user had no saved memories.
An agent with no memory tools and no automatic memory extraction can neither read nor write
memory, so the sentence told the model nothing it could act on, yet it reached the model as
per-turn context. The empty-store notice is now added only when the agent has memory tools or
automatic extraction is on. Saved memories are still injected as before.
* fix(agents): distinguish relocated context from user input
* fix(agents): narrow runtime context types
---------
Co-authored-by: shars <32410570+Shabonasar@users.noreply.github.com>
Co-authored-by: Lia <lia@librechat.ai>
- GET /resolved resolves a group or user profile in the partition its document belongs to, as
writes judge it: for an admin without a tenant reading a tenant's profile, that tenant's
librechat.yaml and __base__. GET /catalog resolves such a scope there too, instead of
answering 404, and GET /effective finds a user by id the way profiles are addressed and
resolves them in their own tenant: their role, groups and documents there.
- findPartitionUser becomes findPrincipalUser, which also returns the user's tenant.
- Admin role operations address the role of the caller's tenant partition: the role lookup
(getPartitionRole), listing, creation's name check, the members a rename migrates or a deletion
reassigns, the members listed and counted, and the ACL entries (deletePrincipalAclEntries) and
grants a deletion removes. A member added or removed by id must be a user of that partition.
- getRoleByName, which every request's permission checks read, reads the role of the caller's
partition too: outside a tenant and under the system context the platform-level one, never an
older tenant role of the same name. updateRoleByName without an id and updateAccessPermissions
for a role read without its _id write that role, so the legacy permission route changes the
platform role. The grants route checks a role exists with getPartitionRole.
- runInPartition moves a read into another partition only from outside a tenant, and rejects
leaving an active one.
- deleteGrantsForPrincipal and findGrantsForPrincipal without a tenantId reach only
platform-level grants, as moveGrantsToPrincipal does.
- updateRoleByName takes { id } to change one role document; renames, their rollback,
description updates and updateAccessPermissions write the document they read.
- The exported keyed rename helpers (applyConfigChange rename, renameConfigEntryTombstones)
refuse a new name no keyed path can address, as the admin routes do.
Move every local prompt group and native-revision read and write behind
one PromptStore (createPromptStore) and reduce the native adapter to
resolvePrompt, the contract the Langfuse adapter already has. The
service receives { store, sources } and dispatches resolution by group
source. Service behavior, errors (including unsupported), database
calls and result shapes are unchanged.
Co-authored-by: Rebase Probe <probe@example.com>
* chore: Update package dependencies across multiple modules
- Upgraded `@azure/identity` to version 4.14.0 in package.json files.
- Updated `multer` to version 2.5.0 and `nodemailer` to version 10.2.1.
- Incremented `undici` to version 7.30.1.
- Updated `@happy-dom/jest-environment` to version 21.0.4.
- Incremented `qs` to version 6.16.1 and `fast-uri` to version 3.1.9.
- Updated `serialize-javascript` to version 7.1.4.
- Updated `zod` to version 4.6.7 in multiple modules.
These updates ensure compatibility with the latest features and security improvements.
* chore: update bun.lock file
PromptService gains importSourceGroup, which finds or creates a source
pointer group, grants the PUBLIC viewer role and rolls the group back if
the grant fails. The Langfuse catalog sync calls it instead of four
storage callbacks and two Mongo error predicates, and the prompt service
is composed once in api/server/services/Prompts.js and passed to the
prompt routes, linked instructions, instructions prompt access and the
Langfuse sync runner.
Co-authored-by: Rebase Probe <probe@example.com>
* feat(prompts): sync Langfuse prompts into the catalog
* refactor(prompts): compose the Langfuse prompt sync runner outside the admin handler
Add createLangfusePromptSyncRunner, which binds the lock, the prompt-group
methods, the ACL grant and the Mongo error predicates once and returns a
runner that takes the per-request source, connection-bound listPrompts,
lock lease and page cap. The admin handler receives that runner as one
dependency instead of forwarding its parts, and its config method
signatures return a LangfuseAdminConfig interface in place of Mongoose
document types.
In api, api/cache/distributedLock.js creates the one DistributedLock for
the process and api/server/services/LangfusePromptSync.js composes the
runner once with it; the admin route imports the composed runner.
* fix(prompts): report incomplete Langfuse syncs and gate the sync action
- Refresh the prompt-group and effective-permission queries after a failed
sync too, because earlier imports can already be committed.
- Return `complete: false` when the page limit stops a sync before the last
upstream page, and show a warning instead of the success message.
- Show the Sync prompts action only to users with `manage:prompts`, the
capability the sync route requires. Resolve the Langfuse startup-config
capabilities in one batched lookup.
- Document that an interrupted import can leave a group without its initial
PUBLIC grant, and that a page in progress can outlast an expired lease.
---------
Co-authored-by: Rebase Probe <probe@example.com>
Reject edits, deletes, new revisions, promotion and revision deletes on
prompt groups whose source is not native with a read_only service error,
mapped to 403 "Externally managed prompts are read-only". The guard reads
the stored group, so the MANAGE_PROMPTS bypass is covered. Sharing,
usage counts and resolution are unchanged.
The client hides Edit and Delete for external groups, shows a read-only
detail view with a Langfuse notice and keeps Share.
The prompt service dispatches resolvePrompt by group.source. A read-only
Langfuse adapter fetches the text prompt on each use, with no cache, after
a resolver checks the deployment gate, the tenant, prompt sync, the
connection and the stored source identity. GET
/api/prompts/groups/:groupId/resolve returns resolved content for native
and Langfuse groups, with a per-user limit set by rateLimits.promptResolve
(default 60 per minute). Agent-instruction links stay native only.
* feat(prompts): add source identity to prompt groups
Add source, sourcePromptName, sourceProjectId and sourceDestination to
PromptGroup. productionId is required only for native groups. A unique
partial index on the source identity covers only groups that have
sourcePromptName, so native groups need no migration.
The create path drops client-supplied source fields, and the native
create upsert does not match langfuse groups. Records map a missing
source to native.
* fix(prompts): centralize sources and restrict native group matching
* feat(langfuse): test prompt listing and resolution from settings
Add a dry-run dialog in Settings > Langfuse that lists Langfuse prompts
and resolves one text prompt (production label or an exact version)
through the tenant's Langfuse connection. Nothing is written. A tenant
user's prompt reads never use the central env keys, even while
TENANT_ISOLATION_STRICT is off.
DevOps makes the feature available with LANGFUSE_PROMPT_SYNC_AVAILABLE
(timeout LANGFUSE_PROMPT_SYNC_TIMEOUT_MS). The tenant admin turns it on
with langfuse.promptSync.enabled.
Related: Linear AI-2271, ClickHouse/ai#4032
* fix(langfuse): isolate prompt credentials and expose prompt settings
Use stored credentials with deployment headers for prompt reads.
Show the settings tab when connection editing or prompt sync is available.
Keep connection controls and trace links under their existing gates.
Audit prompt-sync updates and reuse shared prompt response types.