* 🪪 feat: State a Turn's Shape in Its Created Frame So an Observer Applies It as Its Sender Does
* 🪪 test: Give the Request Controller Specs the Turn Helper Their Mocks Left Out
* 🪪 fix: Name the Reply an Edited or Continued Turn Starts From, and Build on It, Not the List's Tail
* 🪪 fix: Put a Plain Turn's Reply Last in the List, Where Its First Step Builds
* 🧭 refactor: Build One Execution Context Where a Run Enters
Each consumer of a scheduled run's identity (the host token resolver, the
scheduled MCP authority and the resource-bearer host) read the trigger body
and the restored job for itself, and the remote agent API carried a separate
`unattended` flag through tool loading.
The entry point now builds one frozen ExecutionContext: the chat controller
from the verified schedule trigger, the resume host from the saved job, and
the remote controllers from the run envelope. The initializer and tool
loading receive it as an argument. The schedule consumers project their
identity from it, and `unattended` is derived from it at the tool-loading
boundary. No client or model input sets any field.
* 🧭 refactor: Decide Whether a Run Is Unattended in Its Execution Context
* fix: prevent Action writes from expanding MCP access
* fix: fence MCP grant snapshots before Action token cleanup
* fix: reject Action writes after concurrent agent deletion
* fix: enforce MCP grant provenance across saves and server replacement
* test: expect reserved MCP names after server replacement
* feat: Add Gemini Hydrogen Model Support
* fix: Restore Google History For Reachable Agents
* fix: Preserve Mixed Google Signature History
* refactor: Inject Google billing configuration at application boundary
* fix: Preserve Call Signatures From Unsupported Google Output
* chore: Use Released Agents SDK 4.2.5
---------
Co-authored-by: Lia <lia@librechat.ai>
* fix: Keep runtime MIME state out of file inspection
* fix: Preserve attachment-free inspection admission
---------
Co-authored-by: Lia <lia@librechat.ai>
* feat: resolve executing agent ids in MCP header templates
* test: preserve MCP config source literal types
* 🪪 feat: Forward the Active Agent Id in Request Header Placeholders
A gateway in front of LibreChat sees the user, the conversation and the
message, but not which agent is running — so it cannot attribute spend per
agent, apply per-agent limits, or tell agent traffic from plain chat. Adds
`{{LIBRECHAT_AGENT_ID}}` as its own namespace beside the user / body / OpenID
ones, resolving wherever the existing request placeholders already work.
The value is the primary agent's, derived once per run, so subagent steps and
auxiliary calls (summarization, titles, activity labels, memory extraction)
forward the id of the turn they belong to rather than their own. Only
persisted agents resolve: ephemeral ids embed user-authored preset text that
is unsafe in a header value, so ephemeral runs and non-agent requests resolve
to an empty value rather than forwarding literal template text.
No behaviour change unless the placeholder is configured. The MCP surface
(#14303) is not covered — its connection classification derives from
`ALLOWED_BODY_FIELDS`, so a new namespace needs a follow-up.
(cherry picked from commit 8a3f1016f0)
* test: cover shared provider and MCP agent header resolution
* docs: clarify absent agent placeholder resolution
* fix: preserve agent header boundaries across transport lifecycles
* fix: retain Google header provenance during agent resolution
---------
Co-authored-by: Jiří Krejčí <51734696+krejcji@users.noreply.github.com>
* 🚪 fix: Refuse Interactive MCP Sign-in on Remote Agent API Runs
A run started through the remote agent API (API key or OIDC bearer) has no
signed-in browser reading its response. When one of the agent's MCP servers
needed OAuth, the run still published LibreChat's sign-in prompt into the
OpenAI-compatible response and waited up to two minutes for a sign-in the
caller could not complete.
The remote auth middleware now marks the response it admits. The prompt
emitters refuse to write to a marked response, and tool loading skips the
turn-start wait when no reader exists. Background Responses keep their
prompts: those go to the generation stream the owner follows in LibreChat.
* 🧭 refactor: Pass the Unattended Fact Explicitly and Release Unattended Callers From Shared Sign-in
Review feedback on the first commit:
- The response registry coupled the auth middleware to MCP through module
state. The remote controllers now supply `unattended` as an argument
(chat completions always; Responses through the runtime's tool context,
foreground only) and it is passed through tool loading to the manager and
the prompt transports. The registry and the middleware side effect are gone.
- A remote run that reached a server while its owner had a sign-in open in a
browser joined that recovery and waited for the person. The manager now
guards an unattended caller at its two entry points: the first sign-in
prompt, from the caller's own flow or from a recovery it waits on, ends that
caller's wait with a typed error and leaves a shared recovery running for
its other waiters. A recovery announces a sign-in request so waiters that
registered no prompt handler are released too.
* 🧪 test: Cover Unattended Sign-in Through the Real MCP SDK
The shared-sign-in tests replaced the production OAuth handler with a
synthetic listener, so they did not exercise the SDK lifecycle whose
cancellation and shared-recovery behaviour the change depends on.
They now run against the real Streamable HTTP test server, the real
connection factory handler and the real flow manager: an unattended tool
call alone, alongside the owner's open sign-in, joining a recovery that
then stops being silent, recovering through a silent refresh, and opening
a connection that needs sign-in. The synthetic-handler versions are removed.
* 🧷 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
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: 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: 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: 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
The check for files already carried by an earlier message now ignores the
latest message's own entry, so the latest message map entry is replaced as
before and regenerating a message with files behaves as it did. Add a test
that an image refreshed by a tool stays in the message that carries it.
With execute_code and resendFiles, a code-environment file is loaded into
the turn's attachments on every turn. addPreviousAttachments treated every
attachment as submitted by the current request, so the file's text was cut
from the message it was attached to and added to the newest message. The
bytes in the middle of the history changed each turn and the provider cache
stopped at that point.
Only files named in req.body.files move to the current message. A refreshed
tool file stays in its own message, and the latest message skips files an
earlier message already carries, so the text appears once and the attachment
limits count it once.
Reported-by: FFourtyTwo
- 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.
* 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 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
* 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: 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>