* 🧷 fix: Promote Unapplied Steers to Durable Queued Turns at Run End
A steer the server accepted (202) but the run never applied was handed back
in FINAL as `pendingSteers` and re-owned by the browser as a tab-local queued
message. A reload, closed tab, or a predecessor race before the drain lost it.
At terminal publication, a normally completed run now promotes such steers
into server-owned agent queued turns (parent: the ended response, epoch: the
ended generation's createdAt, chained behind any turn already queued against
that epoch). The job store hands the parked copy over atomically
(`promoteSteerLeftover`: parked item removed, receipt settled `recovered`), so
status recovery, lost-ACK retries and legacy recovery starts cannot queue the
same words again. FINAL reports the receipts in `promotedSteers`; the client
adopts them as server rows instead of converting the steer locally.
Promotion is opt-in per steer (`promoteLeftover`, sent only by clients that
adopt receipts and only for steers with no tab-only context), so older
clients keep the legacy path unchanged, and older servers simply never
report `promotedSteers`.
* 🔒 fix: Settle a Promoted Steer's Hand-Off at Admission, Not Only at FINAL
The job-store hand-off of a promoted steer now returns an outcome and stamps
the receipt with the owning queued turn, so it is idempotent for that turn.
The queued-turn resolver repeats it before admitting a promoted turn: it
completes a hand-off a crash interrupted, and cancels the turn when the
parked copy was discarded or recovered elsewhere, so the words never run
twice. At FINAL, a row whose hand-off was refused and whose retirement cannot
be confirmed is withheld from `pendingSteers` and left for that admission
check. The conservative reconcile frame keeps `promotedSteers`, and the
client adopts it there before sweeping local chips.
* 🔏 fix: Give Promoted Steers Durable Ownership, Their Run's Queue Lineage and Approval Mode
A turn promoted from an unapplied steer now records its source on its own
row: the steer's ids, the generation that accepted it, and a mark set only
once the job store handed the parked copy to that row. Admission runs a
promoted turn on that mark or on a hand-off the job store confirms now;
without proof (the store's evidence expired, or the host cannot ask) the
turn is held for review instead of running.
- Hand-off replies that are lost no longer cancel the row. The row stays as
the client's handle and its admission settles ownership, so a committed
hand-off can no longer leave the steer with no runnable copy.
- A replayed promotion never hands the parked copy to a row that was
cancelled or failed.
- Promoted turns join the queue lineage of the generation that accepted
the steer, so a sibling still queued behind that run no longer strands
them with a predecessor mismatch.
- The steer request carries the sender's code approval mode onto the
promoted turn; an unreadable mode keeps the steer on the client path.
- A steer whose quotes its owner stripped stays on the client path.
- The queued-turn receipt names the promoted steer by both ids, and the
receipt list retires a pane's local copies even when it missed FINAL.
* 🚧 fix: Fence Promoted Turns to Workers That Prove Steer Ownership
A promoted row without an approval mode was published under the v1 queued
turn capability, so during a rolling deploy a worker that predates the
ownership check could claim it and run an unsettled row while the parked
steer was still recoverable elsewhere.
Promoted rows now publish under a new agent_queued_turn_v3 capability and a
v3 delivery identity, always reserved before insertion. A replica that
projects an older version can neither publish the reserved delivery nor
claim it, and enqueue refuses a promoted row without a reservation.
* 🪦 fix: Keep a Dead Promoted Turn Answering for Words It Held
A pane that learns of a promoted steer from the receipt list dropped the
mapping for every dead row. A row quarantined as ADMISSION_INDETERMINATE can
still settle as admitted, and a row that died after it was proven the sole
owner of the words is their only surface, so in both cases the pane kept a
chip whose recovery could never run.
The receipt now says whether the turn owned its steer's words, and a dead
receipt keeps answering for them when it did or when its admission is
indeterminate. A replayed promotion applies the same rule to a settled row.
* 🧾 fix: Find Promoted Turns by the Steer a Pane Holds, Join Root Lineages, Redact Hand-off Errors
- A promoted turn's request id is now derived from the client steer id, and a
pane asks for the receipts of the steers it still holds a local copy of
(recovery rows and failed chips). A promoted turn that already ran is only
listed when asked for by name, so a pane that missed FINAL now finds it
and retires its copy. A client steer id too long to key a queued turn is
not promoted.
- The lineage lookup includes a generation admitted from a root queued turn,
which has a parent and no epoch. The promoted turn joins that lineage
without an epoch instead of opening a second one.
- A failed hand-off at admission reports a fixed message. The job store's
own error text stays out of the dead-letter record a client can read, and
promotion logs carry safe error metadata instead of error text.
* 🔢 fix: Ask for Held Steers First Under the Receipt Lookup Limit
The receipt list answers for at most 100 request ids, and a pane's server
rows were listed ahead of the steers it still holds, so a full server queue
could push every held steer out of the request. A promoted turn that had
already run was then never found.
Held steers now come first. An active server row is listed whether or not
it is asked for, while a settled promoted turn is found only by name.
* perf: Validate Agent Models Against Their Own Endpoint Catalog
* perf: Share In-Flight Model List Fetches
* test: Cover Agent Model Validation Across Endpoints
* test: Check Agent Model Catalog Parity With the Real Loaders
* perf: Look Up MCP Server Catalogs Concurrently for Tool Definitions
* test: Cover MCP Sign-In Order for Concurrent Catalog Lookups
* docs: Widen the mcpCatalogLookups Comment in the Example Config
* test: Cover the Catalog Lookup Bound Passed to the Definitions Loader
* perf: Read Only the Active Branch for Turn History
* perf: Narrow the History Read Only When It Skips a Tenth of the Rows
* test: Cover Follow-Up Turns After a Regenerated Answer
Bound model-facing Flux images to the 5 MiB base64 budget for standard and finetuned generation. Preserve original image data for attachment storage under the existing resolution policy.
Fixes#6954.
* fix: Read the Account and Session Together and Test Cancel on a Real Database
- Start the setup user and refresh session lookups together in the cancel controller instead of one after the other, as the opt-in confirmation already does
- Run the cancel controller spec on mongodb-memory-server with the real data-schemas methods, so the session and compare-and-swap predicates under test are the production ones, and add a negative case for each
- Keep only a module wiring test in the CJS controller spec, since the database behavior is now covered where it can run for real
* test: Pin the Cancel Response When the Session Lookup Fails
Both lookups now run before any cookie or write, so a failed session lookup answers 500 with the browser and the stored state untouched. Cover that on the real database.
* fix: Keep the Saved Files Draft Until the File List Loads
After a reload the live file map is empty until the server's file list arrives, and the restore that rebuilds it needs that list. The save effect rewrote the stored draft from the empty map in between, so a pasted-text chip or any other attachment was gone before it could be restored. It now waits for the list. This is what turned the composer-attachments restore scenario red on dev.
* fix: Keep the Provider Message on Classified Rate Limit Errors
* fix: Honor maxProviderErrorChars for Classified Generation Errors
* test: Cover Classified Gateway Errors in the Mock Harness
* test: Cover a Zero Provider Detail Limit on Generation Errors
* refactor: Resolve Classified Provider Errors in the TypeScript Backend
* fix: Redact Provider Details Before Truncating Them
* 📏 fix: Measure Usage Percent Against the Allowance Each Period Granted
Store the credits granted at the start of each balance period on the record and measure the usage percent against it, so changing refillAmount or startBalance no longer moves a user's percent until their next grant. Legacy records fall back to the configured amount.
* 🕰️ fix: Ignore a Stored Allotment a Later Refill Has Replaced
Stamp each stored allotment with the time of its grant and measure against it only while no refill is more recent, so a refill by a replica that predates the field falls back to the configured amount instead of reporting usage against the prior period's allowance.
* 🔒 fix: Write the Allotment Grant Atomically and Return Its Period Start
Insert lastRefill with the credit, allotment and grant time when a balance record is created, so a racing creator never moves another's period start past its grant. Return lastRefill even without auto-refill so the client can place a stored allotment in its period, and fall back when it cannot.
* 🔐 fix: Authorize Restored MCP Tools Before Agent Revert Writes Them
Reverting wrote the version snapshot, including its mcpServerNames, before
filterAuthorizedTools ran. Agent-scoped MCP access is granted from that index,
so a restored server vouched for itself and an editor without access to it
could re-attach it. A snapshot without mcpServerNames also left the current
index in place, keeping agent-scoped access to servers no tool used.
The handler now authorizes the restored tools against the agent as it stands,
treating only its current tools as existing, and passes the authorized tools
and rebuilt index to revertAgentVersion so the restore is one write pinned to
the revision it was checked against. revertAgentVersion always rewrites the
index for the restored tools.
* 🔐 fix: Exclude the Target Agent's Own Grant When Authorizing a Revert
Moves the restore authorization into authorizeAgentRestore in packages/api,
leaving the revert controller as wiring.
A newly restored MCP tool whose server the user reaches only through agents
must now be reachable through an agent other than the one being reverted,
checked fresh against the database. The target's current or cached index
(including one left stale by an earlier revert) no longer vouches for it.
Prior server names are matched through their normalized aliases, and only for
tools the agent already had. When nothing resolves, the pre-restore index is
kept instead of deriving names from tool keys.
A revision-filtered restore that misses is reported as a 409 conflict.
The route spec restores the real ~/config so the MCP registry is consulted
rather than reported unavailable.
* 🔐 fix: Check Newly Restored MCP Servers Against Live Grants
The restore gate now runs for every approved MCP tool, not only consumeOnly
ones. A tool the agent doesn't already have, on a DB-backed server, is
admitted when a current tool still uses that server, or on a live direct
server grant, or through another viewable agent. A grant the registry still
caches after revocation no longer becomes durable through the restored index.
Admission is memoized per server. A snapshot tools array that sanitizes to
nothing restores an explicit empty set. Active-server matching no longer
reuses the index fallback, so a stale entry is never read as in use.
* 🔐 fix: Treat Legacy Cached DB Configs as User-Sourced in the Restore Gate
A config cached before an upgrade may carry a dbId without source. The
restore gate now uses isUserSourced, so such configs get the live access
check instead of passing as operator-managed.
* 🔐 fix: Recheck Unindexed Existing MCP Tools in the Restore Gate
Holding a tool no longer exempts it from the live check. Only a current tool
whose server the agent's index already lists skips it. Otherwise an unindexed
tool on a legacy agent could pass on a revoked grant the registry still
caches, and the restore would add its server to the index.
* ⚡ perf: Run Restore Admission Checks for Distinct Servers Concurrently
filterAuthorizedTools now starts every admission check during its single pass
and awaits them together, so each distinct DB-backed server no longer adds a
serial lookup wave to the revert. Tool order is preserved and server names
are recorded only for admitted tools.
* fix: Only Hand Out OpenID Access Tokens the Bearer Verifier Accepts
The OpenID reuse path in refreshController and the post-refresh fallback in
getOpenIDAppAuthToken returned the cached access token as the app auth token
whenever its exp was in the future. Entra issues Microsoft Graph access tokens
to sign-in clients by default; their aud names Graph, so the bearer verifier
rejects them and every protected request answers 401 until the client loops.
Both paths now require the access token's aud to name the client id or an
OPENID_AUDIENCE entry, the same audiences the verifier accepts. The reuse path
refreshes with the IdP instead, and the post-refresh fallback keeps opaque
tokens as before. Audience parsing is shared with openIdJwtStrategy.
Related to #17791
* test: Exercise Real OpenID Audience Helpers in AuthService Spec
The AuthService spec stubbed the audience helpers as pass-throughs, so it
could not catch a foreign-audience access token escaping the post-refresh
fallback. Use the real exports and cover Graph-audience, configured-audience
and opaque access tokens through setOpenIDAuthTokens.
* fix: Skip Attachments Deleted by Storage Retention Instead of Failing the Turn
A file that storage retention removed from an earlier message made every
later turn of the conversation fail, because the encoders rethrew the
storage miss and the user has no way to remove an attachment from history.
History replay now passes a handler to the encoders, which leave missing
files out of the request and report them; the message's file context tells
the model which files were deleted and were not read. Current-turn
attachments keep the strict error, since the user can remove and re-upload
them. Code Interpreter priming names files missing from storage in the
tool context and only requires resource recovery for other failures.
* refactor: Keep Code Reupload Failure Policy in packages/api
Tally priming reupload failures in createCodeReuploadFailures so the
decision that a file deleted from storage is named instead of requiring
resource recovery lives in TypeScript, and add mock e2e scenarios for a
follow-up after an attachment is deleted from storage.
* fix: Classify Code Files as Deleted Only at the Storage Read
A 404 from the Code API upload was counted as a source file deleted from
storage, which skipped resource recovery. openCodeFileSource marks a miss
where the stored object is read, and only that error counts as deleted.
Move the history replay of attachments with tolerated misses into
replayMessageAttachments so BaseClient only calls it.
* fix: Name Local Code Files Whose Stream Reports a Missing Object
Local storage returns a read stream that raises ENOENT only once read, so
openCodeFileSource now holds a stream until its first chunk or error and
names a miss there. The missing-files context assignment moves into
setMissingCodeFilesContext so both tool loaders only call it.
* fix: Close a Held Code File Stream When Priming Is Cancelled
openCodeFileSource waits for a source stream's first chunk; when that
wait fails, as on cancellation, the caller never receives the stream, so
destroy it before rethrowing instead of leaking its file descriptor.
* fix: Accept Content-Array Outputs in Responses function_call_output
The Open Responses spec allows function_call_output.output to be a string or
an array of input_text, input_image and input_file parts, but request
validation refused anything that was not a string. Validate the array parts
and convert them with the same part mapping the message path uses, so the
replayed tool result keeps its text and images in order.
* fix: Inspect Tool-Output Media Against File Policies
Image URLs and file names in a function_call_output content array reached the
model without the file-policy fragments the same parts get in a message.
Collect those fragments for both item types in packages/api and call that
from the Responses controller.
* test: Cover Content-Array Tool Outputs in the Responses API
* fix: Count Memory Tokens After the o200k Encoding Loads
Memory create and update routes, the by-id handler, and the memory agent's
set_memory tool persisted Tokenizer.getTokenCount, which returns the UTF-8
byte length for long text while o200k_base is still loading. Await
countTokens instead so the stored tokenCount is the real count.
Related to #17842
* test: Cover Memory Token Counts Saved Before the Tokenizer Loads
* test: Mock countTokens in Memory Tool and Route Specs
Multer assumes latin1 for multipart filenames, and the skills routes have no decode step, so a non-ASCII name reached the handlers garbled. A file name content filter could not match it on import, and the file upload route stored the garbled name.
* fix: Retire Credentials by Their Committing Write and on Opt-In 2FA
Re-date password reset and enrollment cutoffs once the write that set them commits, so a credential minted while the write is in flight is retired. Opt-in 2FA confirmation now stamps twoFactorEnrolledAt and rotates the session like required enrollment. OpenID refresh ends a session established before a reset or enrollment instead of spending its IdP grant.
* fix: Bind Opt-In 2FA Rotation to the Caller's Refresh Session
Confirmation now requires the refresh session the request was issued with, rotates it in place and revokes only the others, so an access token on its own cannot trade enrollment for a long-lived session. The OpenID retirement check moves into the refresh recovery service and ends the session through the existing session-missing path, leaving the CJS controller unchanged.
* fix: Clear a Retired OpenID Session Against the User It Was Checked For
* refactor: Inject the Refresh Secret Into OpenID Recovery
* fix: Report a Reset Whose Cutoff Could Not Be Re-Dated
A failed re-stamp now propagates as RETIREMENT_RESTAMP_FAILED. The reset controller still revokes sessions and passkeys and answers CREDENTIAL_RETIREMENT_INCOMPLETE; the CLI re-stamps after its revocations and exits non-zero; enrollment revokes sessions before the re-stamp and mints nothing when it fails.
* fix: Re-Date the Reset Cutoff Only After the Link Is Consumed
The web reset re-stamps credentialsChangedAt in the controller once resetPassword has committed, consumed the token and sent the notice, so a failed re-stamp can no longer leave the link replayable. Revocations still run and the response reports CREDENTIAL_RETIREMENT_INCOMPLETE.
* fix: Retire Credentials on Every Exit Path After a Reset Commits
resetPasswordWithToken owns the post-commit steps: deleting the link and sending the notice no longer throw, and a link issued before the account's last credentialsChangedAt is refused, so it is spent even when its deletion fails. The reset write is conditioned on the cutoff it read, so one link commits once. The controller re-dates the cutoff and revokes sessions and passkeys whenever the password changed, and answers CREDENTIAL_RETIREMENT_INCOMPLETE if any of that fails.
* fix: Spend Undated Reset Links and Move the Reset Notice Into TypeScript
* fix: Tell the User When a Reset Could Not Sign Out Every Session
The reset page now recognizes CREDENTIAL_RETIREMENT_INCOMPLETE, shared from librechat-data-provider, and shows a localized warning that the new password is active with a sign-in action, instead of reporting the spent link as invalid.
* perf: Re-Date the Reset Cutoff From the Committed Write
The committed reset hands its credentialsChangedAt back through PasswordResetResult, so the controller re-stamps without a second user read.
* fix: Retire Every Superseded Credential Before Minting on 2FA Enrollment
Opt-in confirmation and setup finalization now revoke sessions, re-date twoFactorEnrolledAt and wait for the auth cache to drop the pre-enrollment document, running every step even when one fails. If any step fails they mint nothing and answer CREDENTIAL_RETIREMENT_INCOMPLETE; the settings dialog keeps 2FA on with a warning and the setup screen sends the user back to sign in with the new factor.
* test: Cover the Settings Warning When 2FA Enrollment Leaves Sessions Behind
* fix: Send the User Back to Sign In After an Incomplete Opt-In Enrollment
Enrollment retires the confirming tab's bearer, and an incomplete retirement mints no replacement, so the settings dialog now shows the backup codes and then signs out to the login page, whether the user completes setup or closes the dialog.
* test: Run the Retirement Warning Scenarios Against Their Own Signed-Out or Fresh Accounts
* test: Open the Sidebar Drawer Before the Account Menu on Phones
* fix: Report a Committed Opt-In Enrollment When Rotating the Session Fails
Once 2FA is promoted, a later failure in confirm2FA withdraws whatever session it may have minted and answers CREDENTIAL_RETIREMENT_INCOMPLETE, so the settings dialog hands over the backup codes and signs the user in again instead of reporting an invalid code.
* test: Prove an Incomplete Reset Does Not Resume the Retired Session
The Sign in action sends a browser with a live session through /login for about 150 ms before it lands in chat, so the signed-in version of the warning scenario only passed when the URL check caught that window. The warning scenario runs signed out, and a new scenario holds a pre-reset session and asserts its refresh is refused and the user stays on the login page.
* fix: Settle the Auth Cache After the CLI Reset's Final Cutoff Write
* test: Require the Login Form After Signing In From a Signed-Out Reset
* fix: Explain an Incomplete Session Retirement Before Restarting Sign-In After Required 2FA Setup
* perf: Start the Opt-In Enrollment User and Session Reads Together
* 🔎 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>
- 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.
The login tests reach getAppConfig through the balance middleware, which
loads librechat.yaml from the repository root by default. The file is
gitignored, so a developer who keeps one locally runs the spec against
their own config; an unresolved `${VAR}` MCP URL in it makes
configSchema.safeParse throw and every login returns 500. Point
CONFIG_PATH at a missing file so the spec runs with no config, as CI does.
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
* 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: 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