Commit graph

1750 commits

Author SHA1 Message Date
Marco Beretta
84180a87e2
⚙️ feat: Make the Per-User Passkey Cap Configurable (#16259) 2026-09-25 11:34:06 +02:00
Marco Beretta
f1bc07b2c7
🖼️ fix: Paint the Shared Link Tenant's Deployment Theme (#16333) 2026-09-25 08:56:09 +02:00
lia-by-librechat[bot]
fe2b547e64
🫗 fix: Bound MCP App Responses and In-Flight Work (#16300)
* 🫗 fix: Bound MCP App Responses and In-Flight Work

* 🫗 fix: Stop Oversized App SSE Reconnect Loops

* 🫗 fix: Validate and Inject MCP App Operation Budgets

* 🫗 fix: Keep Safe MCP App SSE Streams Open

* 🫗 test: Admit Large Apps Under Configured Byte Caps

* 🫗 fix: Bound SSE-Typed App Error Responses

* 🫗 fix: Share App Admission With Initial Document Reads

* 🫗 fix: Apply App Byte Limits During Tool Discovery

* 🫗 fix: Honor Configured App SSE Line Budgets

---------

Co-authored-by: Lia <lia@librechat.ai>
2026-09-24 22:53:15 -04:00
lia-by-librechat[bot]
6866732a88
🫸 fix: Gate MCP App Views and Actions on User Intent (#16297)
* 🫸 fix: Gate MCP App Views and Actions on User Intent

* 🧪 ci: Run MCP Apps Browser Checks on Repository Bot PRs

* 🧲 test: Open App Before Checking Tool-Call Frames

* 🔎 fix: Wait for Stable App Views in Restored Browser Tests

* 🧪 test: Trace Grouped App View Activation in Browser CI

* 🧪 test: Diagnose Grouped App Click Propagation

* 🧪 test: Distinguish Native and React App Click Delivery

* 🧪 test: Inspect Grouped App Button Hit Target

* 🎟️ test: Open Grouped App Views After Scrolling Into Place

* 🧯 fix: Revoke App Approval Before Teardown Handshake

* 🫸 fix: Configure App Limits and Suspend Denied Actions

* 🧾 test: Expect Configured MCP App Limits in API Suites

* 🧱 fix: Isolate Approved App Messages From Composer Drafts

* 🛟 fix: Suspend Aborted App Actions and Restore View Focus

* 🦮 fix: Preserve Focus on App-Initiated Teardown

* 🧳 fix: Exclude Draft Agent State From App Messages

* 🧭 test: Preserve Legacy Null File Overrides

* 🧰 fix: Retain Selected MCP Tools Across App Messages

* 🧾 fix: Acknowledge Accepted App Turns and Disclose Selected Tools

---------

Co-authored-by: Lia <lia@librechat.ai>
2026-09-24 18:00:13 -04:00
Marco Beretta
c59fb60341
🔐 fix: Revoke Password Reset Credentials Independently (#16320) 2026-09-24 18:41:18 +02:00
Marco Beretta
f0cbc9a3c0
🎨 feat: Pick the Deployment Theme in librechat.yaml (#16286)
* feat: pick the deployment theme in librechat.yaml

Add `interface.theme` to the config schema, accepting a bundled theme name
or an inline theme definition. The interface loader passes it through, the
pre-login config payload carries it so the login page paints it, and a
DeploymentTheme wrapper around ThemeProvider resolves and validates it and
applies it without persisting it over the user's stored theme.

* fix: restore the user theme when the deployment theme is withdrawn

Move the pre-login interface selection out of the /api route into
buildPreLoginInterface in packages/api, so the route only wires it up.

When an authenticated config drops interface.theme (a principal override
tombstoning it), hand ThemeProvider the user's stored theme instead of
clearing to the LibreChat palette. The e2e scenarios now cover inline and
invalid themes, the withdrawn case, and high-contrast precedence.

* fix: read a legacy stored theme behind a corrupt stored definition

* perf: rebind the deployment theme observer on a cache add, not every event

useIsFetching recomputed the fetch count across every query on each cache
event, which slowed streamed renders enough to break the highlight-throttle
scenario. Subscribe to the query cache and re-render only when a startup
config query is rebuilt.

* test: wait for the composer after sign-in so mobile runs pass

* fix: keep deployment themes whole and restore legacy themes as legacy

A principal override with an inline theme merged into the base theme,
keeping the base's other mode, brands and tokens; interfaceConfig.theme
now replaces whole during override merging.

A withdrawn deployment theme restored a legacy-source stored theme as a
versioned definition, dropping its colors in dark mode; it now goes back
through ThemeProvider's legacy color path.

* fix: persist the user's theme changes after the deployment theme is withdrawn

Persistence now stays off only while a deployment theme is applied and for
the render that restores the stored theme, so later changes through the
theme API are saved again.

* refactor: derive deployment theme persistence from the current theme
2026-09-24 17:36:47 +02:00
lia-by-librechat[bot]
411bb5444f
🥢 fix: Fit MCP App Snapshots Within Message Documents (#16299)
* 🥢 fix: Fit MCP App Snapshots Within Message Documents

* 🥢 fix: Resolve Message Model Only at App Write Time

* 🥢 style: Sort MCP App Snapshot Persistence Imports

* 🥢 fix: Centralize MCP App Message Admission Across Writers

* 🥢 fix: Inject the App Budget Reader Without a Config Cycle

* test: Cover App Budget Initialization Across Mocked Hosts

---------

Co-authored-by: Lia <lia@librechat.ai>
2026-09-24 09:56:40 -04:00
Dustin Healy
a98d40f61c
🧩 feat: MCP Apps support (#13831)
* feat: add MCP Apps support

* fix: preserve MCP App results and enforce sandbox policy

* fix: bind persisted MCP Apps to their server configuration

* fix: complete MCP Apps runtime integration

* fix: type the optional MCP App binding codec explicitly

* test: provide MCP Apps policy in bridge mocks

* fix: pass admitted App policy to the tool call owner

* fix: align MCP Apps CI contracts

* test: preserve MCP abort reasons in recovery mocks

* fix: preserve MCP compatibility across policy profiles

* test: use profiled MCP catalog generations

* test: expect the standard MCP session profile

* fix: remove the unused MCP abort import

* test: expect profiled MCP fixture arguments

* test: seed profiled MCP manager fixtures

* Fix request-header bearer resolution after canary merge

* Preserve MCP App views across canary message updates

* Document message-owned MCP App placement

* ci: Recheck MCP Apps Against Canary Base

---------

Co-authored-by: Lia <lia@librechat.ai>
2026-09-23 21:24:50 -04:00
Marco Beretta
59014b53c2
🔑 fix: Keep Passkey Sign-In Reachable When Email Login Is Disabled (#16254)
The passkey login routes sat behind validateEmailLogin, and the client
hid the passkey button unless email login was enabled, so a deployment
with ALLOW_PASSKEY_LOGIN=true and ALLOW_EMAIL_LOGIN=false advertised a
sign-in method it rejected. Gate the routes on the passkey limiter,
same-origin and ban checks only, and render the button on passkey
enablement alone.
2026-09-23 23:56:53 +02:00
Marco Beretta
471abaa64d 🔑 feat: Passkey Authentication with WebAuthn Sign-In and Management (#14715)
* feat: passkey authentication with WebAuthn sign-in and management

* refactor: tighten passkey account protections

Require password confirmation before adding or removing a passkey, and rate
limit those confirmations per user in their own namespace. Restrict passkey
enrollment and sign-in to local accounts, and re-evaluate account status once
the credential owner is resolved. Require user verification on the sign-in
ceremony. Invalidate outstanding access tokens on password reset. Tighten
redirect target validation and sanitize ceremony failure logs.

Adds coverage across the passkey controller, the WebAuthn helpers, the step-up
limiter, both JWT strategies, the redirect utility and the passkey settings UI.

* fix: localize passkey default name and respect router basename

Send a localized default credential label at enrollment so non-English
locales no longer persist the server's English fallback, and route the
passkey post-login and 2FA navigations through the deployment base path
so subdirectory installs stay inside the router.

Also mock syncStaticTools in the server boot specs; without it the
post-listen MCP initialization calls undefined and exits the worker.

* fix: harden passkey counter checks and reach stranded credentials

Make the signature counter write a compare-and-swap so two assertions
that verified against the same stored counter cannot both commit, and
reject the losing one; a cloned authenticator is otherwise accepted
inside that window. Counterless authenticators keep restamping at 0.

Keep the passkey panel reachable for identity-provider accounts, which
already get passwordless removal server-side but had no way in, while
hiding the add control they cannot use. Cascade passkey deletion from
the admin user-deletion path so credential IDs are not stranded.

* fix: reject stale 2FA temp tokens and surface passkey load failures

A temporary 2FA token proves only the first factor, so honouring one
minted before a password reset let anyone holding the second factor
survive account recovery. Apply the same credentials-changed cutoff the
JWT strategy uses.

Also distinguish a failed passkey query from an empty list; the error
state previously rendered as "no passkeys yet", which misreports what
is protecting the account.

* fix: fail closed when the passkey counter write cannot commit

Returning success on a storage error bypassed the compare-and-swap it
exists to enforce, so a cloned authenticator could be accepted while the
stored counter stayed stale. A database that cannot take this write
cannot mint the session either, so little is gained by failing open.
Counterless credentials carry no clone signal and keep their old path.

* fix: keep the passkey 2FA handoff inside the router

A full-page navigation to the 2FA screen remounted AuthContextProvider,
which silent-refreshes on mount; no refresh session exists yet at that
point, so it bounced back to login before the code could be entered.
Route through the router like the password flow does.

Also reveal the removal step-up field when the server refuses a
passwordless attempt, so an account migrated to an identity provider
without its old hash cleared can still clear its credentials; drop the
staged password when the dialog closes; and revoke passkeys in the CLI
password reset, which bypassed the HTTP controller's cleanup.

* fix: apply one email-verification policy across login methods

Accounts predating mandatory verification are marked verified as they
sign in when no email is configured, but only the password strategy did
it, so the same legacy account was admitted by password and refused by
passkey. Extract the rule into a shared helper and call it from both.

* fix: refuse a passkey sign-in when the ban check cannot complete

checkBan defaults next to a no-op, so calling it bare discarded any
internal failure and left req.banned unset, letting the request fall
through and be issued tokens. Capture the error the middleware chain
would have propagated and reject instead.

* fix: refine passkey management dialogs

* test: stabilize passkey tooltip assertions

* test: reconcile passkey specs with the canary reset and deletion flows

The credentialsChangedAt stamp now lives in commitPasswordReset, so its
assertion moves to the passwordReset unit spec. Restores the describe
blocks the rebase merged together.

* test: mock passkey routes in the cross-site login suite

* refactor: move passkey handlers and credential checks into packages/api

The passkey controller, the credentialsChangedAt predicate and the legacy
email-verification grandfathering now live in TypeScript with injected
dependencies; /api keeps only the wiring that builds the handlers.

* style: align passkey UI with Tailwind v4 order and design-rule lint

* fix: revoke earlier access tokens on a CLI password reset

passwordVersion is not a user schema field, so the write was dropped and
tokens issued before the reset kept verifying.

* test: cover passkey sign-in and credential revocation end to end

* fix: hide passkey sign-in when email login is disabled

The passkey endpoints already refuse under ALLOW_EMAIL_LOGIN=false, so
advertising the button only led to a 403.

* fix: let only one concurrent verification consume a passkey challenge

Without a native getDel the challenge was read then deleted, so two
concurrent verifications could both use it. The delete now arbitrates:
only the caller whose delete removed the key gets the challenge.

* test: run passkey ceremonies on the localhost relying party

WebAuthn refuses an IP address as the RP ID, and the harness serves the
app on 127.0.0.1. The reset scenario runs once per project, so the mock
harness lifts the per-IP reset request limit as it does for forks.

* fix: keep passkey management when email login is disabled

Gate only the sign-in button on emailLoginEnabled, since only the sign-in
routes sit behind that gate; list, rename and remove stay reachable.

* fix: build the passkey credential index before the first registration

With MONGO_AUTO_INDEX=false the unique credentialId index was never
created, so concurrent registrations could store the same credential.

* test: enable password reset in the mock harness and cover email-login-off passkeys

* fix: stop re-exporting the passkey cap from data-schemas

The bundler left every import of methods/passkey.ts unlinked while that
module re-exported MAX_PASSKEYS_PER_USER from librechat-data-provider, so
the index build and the counter-failure log threw ReferenceError at
runtime. Consumers now import the cap from librechat-data-provider.

* test: close nested settings dialogs before logging out in passkey scenarios

* fix: reject cross-site passkey assertions

The verify route accepted a form posted from another site, which let an
attacker sign a victim into the attacker's account. It now runs the same
requireSameOrigin guard as password login and the 2FA step.

* fix: end refresh sessions on a CLI password reset

A surviving refresh session could mint an access token issued after the
credentialsChangedAt stamp, so the CLI now deletes sessions like the web
reset does.

* fix: keep the passkey button locked when it supersedes autofill

Starting the modal ceremony aborts the pending autofill one, and the
autofill error path cleared the shared lock and busy state while the
modal ceremony was still running.
2026-09-23 13:19:32 -04:00
Marco Beretta
b947738d0d 🔔 feat: Unseen Reply Indicators, Reply Notifications, and Mark as Unread (#15025)
* feat: add unseen reply indicators, reply notifications, and mark as unread

A reply that lands while the user is elsewhere now leaves a trace. The
conversation carries a durable reply stamp written with the assistant message
that backs it, the sidebar row shows an unread dot until that message is
actually rendered, and an optional tab badge, desktop notification and chime
announce arrivals in a tab that is away. Rows can also be marked unread by hand
from the row menu, in the archived view as well as the main list.

The stamp is written by a compare-and-swap so concurrent replies order on the
database rather than on the application hosts' clocks, and only once output that
a reader can actually see is persisted: a stopped turn with nothing to read, an
empty synchronized row, or a failed message write never lights a dot that cannot
be cleared. Read intent survives archives, metadata edits and preset applies,
and a later read always outranks a delayed unread.

* fix: gate reply alerts on config and announce only readable replies

Three review rounds kept finding the same two shapes, so both are answered once
rather than patched again.

The alert capabilities are now operator-configurable through
`interface.replyNotifications` in `librechat.yaml`: the tab badge, desktop
notifications and the chime each have a gate, and the away poll's page size is a
field rather than a constant, with defaults that reproduce the shipped behavior.
A capability the operator turns off reads as off whatever the device stored, and
its settings toggle is not offered.

Deciding whether a persisted turn may raise an indicator now lives in one place
in `packages/api`, with the Responses API controller, the abort route, the
Assistants thread sync and the client's override path all calling it instead of
carrying their own copy. That closes the last case where a reply nobody can read
lit a dot nothing could clear: a `/v1/responses` completion whose output held
only reasoning or tool calls persists an empty row, and stamping it left an
unread conversation that opening could not settle.

Also: the retention backfill no longer advances `updatedAt` past a reply stamp,
which an away tab reads as a metadata-only promotion and withholds the alert
for; arrival evidence is swept of conversations no cached list still holds, so a
long-lived tab stops growing with its lifetime number of replies; and generated
Lighthouse profile directories are ignored where the runner leaves them.

* test: open the sidebar by what the drawer paints, not by its test ids

The drawer became a mounted, sliding panel on canary, so the controls this
helper read no longer say what it assumed. `close-sidebar-button` answers from
the off-canvas copy before the expanded state commits, which returned the helper
with the conversation list still hidden behind the pane, and the panel's own
`new-chat-button` has a rail copy that a plain locator reaches first. Both
readings passed on the previous drawer, which unmounted when closed.

Settling on the close control's accessible name, and on the first candidate that
is actually painted, is what a reader perceives and survives either drawer. One
click is one toggle and the opener sits in the pane the drawer marks inert for
the whole of its travel, so each attempt is given that travel to itself rather
than reissued into it.

Also serves `interface.replyNotifications` in the operator-gate scenario with a
fresh body instead of the upstream response, since reusing its encoding headers
for a re-serialized payload leaves the client unable to read the config, which
looks exactly like an operator who configured nothing.

* fix: gate the assistant save on renderable output and stop overselling the poll limit

Two gaps this round's own work left behind.

`saveAssistantMessage` still decided to stamp from the message id alone, so an
Assistants run that persisted an empty row raised a dot that opening the
conversation could never clear. It now asks `isAnnounceableReply`, the same
predicate every other persistence path asks, which is the point of having moved
that decision into one place.

`pollLimit` advertised a range up to 1000 while `getConvosByCursor` clamps every
conversation read to a hundred-row page, so an operator who set 500 would have
been told it applied and silently served a hundred. The schema now stops at the
page the server will actually return; covering a deployment whose replies
outpace one page needs the server-side unseen query, not a wider page.

* test: let the mobile scenarios use the surface they are actually asserting on

Three scenarios opened the drawer on a page they only ever send a reply from.
On the mobile project that drawer sits over the composer and marks the pane
inert, so there was nothing left to type in and the run waited out its whole
budget. They ask for the composer now, which is what they were always about.

The two that read a row after leaving the list open it again first. A reply sent
from another tab closes this one's drawer, because `sidebarExpanded` is stored
per browser rather than per tab, and opening a chat closes it the way it does
for a reader. Both are what someone would do to look at the row, and neither
changes what is being asserted.

Mark as unread is dispatched rather than clicked, like the row controls around
it: the menu is portaled, and behind the drawer's scrim it inherits
`pointer-events: none` and goes click-dead.

* test: dispatch the row menu's unread item like the controls around it

The portaled menu sits under the mobile drawer's scrim, which intercepts the
pointer, so a real click retried until the budget ran out. The sibling scenarios
and the row's own controls already dispatch; these two were the last real
clicks.

* fix: hold reply alerts until the deployment answers, and read the resolved temporary state

The capability gate treated a startup config that had not loaded yet the same as
one that set nothing, so a device that stored "on" could badge, poll or notify in
the window before an operator's `false` arrived. Nothing is permitted now until
the config is in hand; only a loaded config that lacks the field reads as the
shipped default, which is the case a backend predating the setting produces.

The Responses API announcement read the temporary flag from the request body
alone, while the conversation save beside it resolves it from the stored
conversation first. A temporary chat restored or resolved on the server without
the flag in the body would have been announced through the unread indicators;
both completion branches now resolve it the same way the save does.

* fix: route the last reply stamps through the shared owner and hand back failed claims

Moving the announce decision into packages/api left three callers still deciding
for themselves. The agents controller re-stamped an unfinished turn whose
terminal persistence was skipped, and the resumed legacy turn stamped its
directly saved row, both from the message id alone, so a preempted or stopped
turn that persisted nothing readable lit a dot that could never be
acknowledged. Both ask isAnnounceableReply now. The non-agents abort path
carried an inline copy of the same predicate; it calls announceReply instead.
Error turns keep their direct stamp: the error card is what renders them.

A notification claim was written to shared storage before the notification
was constructed, so a constructor that throws left the reply claimed in every
tab with nothing ever shown. The claim is handed back when construction fails,
removed only while it still names that exact stamp.

* fix: judge the normal reply save by the shared predicate and hand back failed chimes

The regular BaseClient save still stamped any assistant reply that persisted,
readable or not, because the conversation write took a bare reply id. It takes
the persisted reply now and asks isAnnounceableReply before it stamps, which
leaves the error turns as the only direct stamps, and those are rendered by the
error card. saveTurnConversation is exercised against a real store in both
directions. announce.ts derives its write-context type locally so the two
modules do not import each other.

The chime claimed its replies before building the tones, so an output that
failed while they were being scheduled left them claimed in every tab with
nothing played. Those claims are handed back on failure, the same way a
notification that could not be constructed now releases its own.

* feat: let operators set the reply polling cadence

The away poll and the focused refresh were fixed at 30 seconds and five minutes,
which are request-rate levers on the conversation list and nothing an operator
could tune. Both are fields on `interface.replyNotifications` now, bounded and
defaulting to the values they had, and the watcher reads them through the same
capability hook as the rest of the block.

* fix: keep reply identity through list merges and drop rows the server no longer has

The list merge carried three of the four read-state fields by hand and left out
`lastResponseMessageId`, so an SSE update on an unseen conversation erased which
branch the reply landed on, and a missing identity reads as visible. It uses the
same `preserveReadState` helper as the other two merge paths now, and the test
that covered the other three fields covers this one too.

A local cache merge was only inspected on a list's first page for new arrivals.
A title or oldest-first sort leaves a replied row where it is, so its first
reply on a later page went into the alerts baseline without an arrival and its
chime or notification was lost. Local merges scan every loaded page; server
responses keep the first-page rule, and only rows already known are considered.

An unread request that matched nothing means the conversation is gone: the
server's owner-scoped update returns the row even for a no-op. The mutation
rolled back the read fields and kept the row; it removes it from the caches now,
as a delete does.

* fix: discard a job completion that resolves after the watcher has gone

The fetch that settles a finished job had no teardown guard, unlike the away
poll. Signing out or switching accounts unmounts the watcher, and a response
still in flight for the previous session would then merge into the caches the
next one reads. The result is dropped once the watcher has unmounted, tracked
on unmount rather than in the jobs effect's cleanup, which re-runs on every
change to the running set while its earlier completions are still wanted.

* fix: move error-turn stamps into packages/api and settle overlapping unread no-matches

Error turns were stamped in CJS: the error middleware checked eligibility, called
the stamp and shaped the event's conversation snapshot itself, and the agents
controller stamped its own. Both call announceErrorTurn now, and the
skipped-persistence restamp goes through announceReply, so no stamp is issued
directly from /api any more. The existing sendError tests pass against the real
helper unchanged.

An unread call that no longer owned the row dropped a server no-match with the
rest of its stale answers, so a deleted conversation could be restored by a newer
call's rollback. The no-match now evicts before ownership is consulted. It stays
after the superseded check: a superseded call never reached the server, and its
synthetic `modified: false` is not a no-match.

Also: Settings offers the reply toggles only once the startup config has loaded,
matching the capability hook; a cancelled reply-discovery snapshot is restarted
even though nothing observes it; and the focused refresh is capped at the five
minutes the discovery snapshot stays authoritative, since that refresh is what
renews it.

* fix: settle the assistant final in packages/api, announce attachment-only replies

Both assistant controllers carried the same persistence barrier: write the
response, check the row and the conversation both persisted, and unwrap the
settled conversation for the final event. That is behaviour, and it was
duplicated in CJS; settleAssistantFinal owns it now and the controllers call
it. Their existing tests pass unchanged.

The announce predicate ignored attachments, so a reply made only of files,
such as a resumed workspace artifact with empty content and text, raised no
dot, badge or alert. The message body renders attachments and acknowledgement
checks the body, so such a reply can be cleared as well as announced; every
announce path now passes them through.

The stopped-reply announcement took the storage engine's own id type in its
exported signature. It takes plain string ids now, and saveConvo accepts them
alongside its own, since the update casts them against the schema; the id type
stays inside data-schemas.

* fix: normalize the stopped reply's written ids in packages/api

The abort route filtered and stringified the ids of the rows it had written
before handing them to announceStoppedReply. That is data shaping, and it sat
in CJS; the announcement takes the ids as the caller holds them and drops the
unwritten ones itself.

* style: order the conversation row classes for Tailwind v4

The v4 upgrade on canary changed the class order Prettier enforces; these
three rows carried the v3 order.

* fix: replay replies a dead tab's focus lease held back, keep the focused refresh at a full page

A tab killed without firing blur or pagehide leaves its focus lease for up to
a minute. A reply arriving under it was baselined and then suppressed, and
nothing reran when the lease lapsed, so its chime and notification were lost.
Arrivals held back only by another tab's lease are kept and rechecked when
that lease expires; a lease the focused tab keeps refreshing still holds them.

The focused refresh reused the away-poll limit, so an operator who lowered it
also shrank the discovery page that keeps the unseen count complete behind a
filtered list. The limit now bounds only the away poll.

* fix: announce a held reply as soon as the focused tab releases its lease

A tab that blurs normally clears its lease long before the lapse, and a reply
held back for it is due as soon as nobody is looking. Lease changes from other
tabs now trigger the recheck, not only the expiry timer.
2026-09-23 13:19:32 -04:00
Marco Beretta
9ff251dd96 📧 feat: add email address change (#14597) 2026-09-23 13:19:32 -04:00
Marco Beretta
1bfaa5f96f ⚖️ refactor: Move Policy Links to the Signup Consent (#16138) 2026-09-23 13:19:32 -04:00
Marco Beretta
18c48f6ff7 🪞 feat: Expand Agent Cards Into Their Detail Dialog (#15798)
* feat: Sort Modes and Mine Filter for the Agent Marketplace List

Adds two query parameters to `GET /api/agents`:

- `sort` — one of newest | oldest | popular | author, validated against
  an allowlist since the value reaches a `$sort`/`$lookup` pipeline.
- `mine=1` — narrows the list to agents authored by the caller, applied
  on top of the ACL-resolved accessible set rather than instead of it.

`newest`/`oldest` remain a plain `.find()` but now order on `createdAt`
instead of `updatedAt`. This endpoint refreshes S3 avatars through
`updateAgent`, which advances `updatedAt` — the very field the cursor
compared against — so an agent could cross a page boundary mid-scroll
and drop out of the caller's flattened list. Two indexes back the new
ordering.

`popular` counts favorites through an equality `$lookup` and validates
tenancy after the join. `author` resolves the same contact the card
renders — support_contact, then the user holding the OWNER ACL grant —
so the ordering matches what the reader actually sees. Both compute
their key inside the pipeline, so the cursor compares against the
computed field and the key is stripped before the rows are returned;
the response shape is unchanged.

Behaviour note: a request that sends no `sort` now comes back ordered by
`createdAt` descending rather than `updatedAt` descending.

* feat: Denser Agent Marketplace Grid with Sort and Mine Controls

Rebuilds the marketplace chrome around a denser grid. The hero block
gives way to a sticky header carrying the title, a live agent count and
a compact search field; category tabs become pills; and the grid follows
the available width instead of a fixed two-column layout, so a wide
window shows more than two agents per row.

Adds two controls to the category header, next to the category they act
on: a sort dropdown and an "only agents I created" switch. Both mirror
into the URL (`?sort=`, `?mine=1`) so a filtered view can be linked and
restored, and the default sort is omitted from the URL to keep it clean.
Switching the filter on inside Top Picks moves to All, where authored
agents can actually appear, since nothing writes `is_promoted` yet.

Since `popular` recomputes its count per request, pinning or unpinning
invalidates only the popular pages, and marks them stale rather than
refetching under a reader who is mid-scroll.

* feat: Agent Marketplace Refresh with Shared-Layout Detail Morph

Clicking an agent card now expands that card into the details dialog instead
of fading an unrelated panel over the grid, and the dialog contracts back into
the card it came from.

The morph is a framer-motion shared-layout handoff with `layoutCrossfade`
disabled, so the projection hides the relegated card nodes itself: the card
keeps its box, the grid never reflows, and no field is ever drawn twice. Card
and dialog keep genuinely different layouts and only the fields they share
travel — surface, avatar, name, category pill, creator row and the blurb.
The pill moves from the card's upper right to the dialog's upper left, the
avatar grows, the name zooms between the two type sizes, the creator moves out
of the footer to under the name, and the blurb is handed over at the dialog's
width so the surface's clip reveals the lines the card had no room for. The
dialog's own controls — close, "About this agent", Pin, Copy Link, Start Chat —
are introduced after the geometry is under way and leave the way they came in.

The dialog's content lives inside the morphing surface, whose sections are
projection nodes, so nothing stretches or spills outside the expanding box.
`layoutDependency` pins measurement to selection changes, which keeps the
virtualized grid's per-scroll rerenders from measuring every card. The page dim
is owned by the grid rather than the dialog's overlay so it can run its full
range across a contraction that outlives the dialog's mount, and the source
card is raised above its neighbours until the surface is home.

`OGDialogContent` gains `bare` and `forceMount` so a caller can own a dialog's
geometry and animation while Radix keeps focus trapping, Escape, the scroll
lock and the aria wiring. Reduced motion skips the morph and opens the dialog
outright; focus still returns to the card that opened it.

Also in the marketplace header: the admin settings trigger takes the bordered
`outline` variant so it matches the search field beside it, and the search
field's clear button declares its own colour instead of inheriting the
document's, which made the glyph invisible in dark mode.

* style: Square Off the Search Clear Button's Hover Fill

Its hover fill inherited the button recipe's `rounded-lg`, which on a 32px
square read as a pill inside the search field; `rounded-md` keeps the chip
subordinate to the field's own 8px corner.

* fix: Adjudicate Review Findings on the Marketplace Refresh

Four demonstrated defects from the review round on a10b31c0:

Surface radius came from a literal 16px repeated at both morph endpoints, so
`--theme-surface-radius` could not move the marketplace's corners even though
every other surface follows it. The card and dialog surfaces now carry
`rounded-theme-surface`, and the projection — which can only hold a corner
steady while it scales if it owns the radius as a number — is fed the resolved
token, read once per morph rather than per card or per frame.

The morph's page dim restated `bg-black/80` in feature code, duplicating an
appearance decision that belongs to the dialog primitive. `OriginalDialog` now
exports `DIALOG_SCRIM_CLASS` and both the Radix overlay and the grid's animated
backdrop consume it, so the scrim has one owner again. The scrim's colour is
still a literal in the primitive: making it a theme role changes every dialog
in the app and is not this PR's to decide.

`ErrorDisplay` narrowed on `Error` and kept only `message`, but an `AxiosError`
*is* an `Error`, so `response.status`, `response.data` and `code` — the fields
the classification runs on — were discarded for every real request failure. A
500 was therefore labelled non-transient `generic` with automatic recovery
disabled, and 404s rendered as errors instead of the neutral empty state. Only
a bare string needs wrapping now. Its regression test delivers the failure the
way axios does, as an `Error` instance, which the previous object-literal
fixtures never exercised.

`useAutoRetry.retryNow` did not cancel the pending backoff: resetting `attempt`
to 0 while it was already 0 is a no-op, so the effect never re-ran, its timer
stayed armed, and the scheduled attempt still fired after a manual or
connectivity-driven retry had gone out — a duplicate request that also spent a
backoff step. The schedule is now a value that changes on every retry, so each
one cancels and restarts it.

* fix: Keep a Morphed Card's Corner on the Radius Token

The resolved radius was handed to the surfaces only for the duration of a
morph. The projection keeps a `borderRadius` once it owns it, so dropping the
value on the way out left a morphed card pinned to whatever the theme was when
it was opened, and a later theme change moved every corner in the grid except
that one. The list resolves the token once for all its cards instead and
re-resolves it when the theme rewrites the root.

* perf: Page the Marketplace's Popular and Author Sorts in the Database

Two demonstrated defects from the review round on a10b31c0.

`sort=popular` loaded every accessible agent into application memory on every
page, queried favorites for that complete id set, sorted the whole array in
JavaScript and then kept the requested slice, so a 32-item page scaled with the
whole marketplace and the next cursor repeated all of it. The ordering is now
split at the only place it can be: agents somebody favorited, which is at most
as large as the favorites themselves, and the count-0 tail, which is ordered by
`_id` alone and therefore pages as an indexed range scan with the limit applied
by the database. The favorite counts no longer carry a marketplace-sized `$in`,
and the count key is per tenant, so a missing and an explicitly null `tenantId`
are one tenant rather than two.

Measured on 300 accessible agents, 4 of them favorited, `limit: 10`: page one
returned 314 documents to the process before and 19 after, page two the same
314 before and 19 after. Walking the whole list at `limit: 7` produces the
identical id order in both implementations.

The `author` pipeline joined the owner ACL entry and the owner user in order to
sort by the resolved display name, projected neither, and left
`getListAgentsHandler` to await `attachOwnerContacts`, which queried the same
ACL entries and the same users again for the page it had just ordered. The
pipeline now resolves `owner_contact` on exactly the tiers
`resolveAgentOwnerContact` applies — a support contact means no owner contact,
and without a joined owner account there is none either, even with a
denormalized `authorName` — and marks the row. `attachOwnerContacts` skips
marked rows, strips the marker, and so performs no query at all for an
author-sorted page.

`$$REMOVE` is rejected by DocumentDB, so "no contact" arrives as an explicit
null the list method drops before the row leaves.

The dropped popular-sort test asserted that a row deleted between the candidate
scan and the full fetch still yielded a usable cursor; it drove that state by
mocking `Agent.find` for one call, which the single ordered segment no longer
performs.

* fix: Keep Throttled Loads Recovering and the Skeleton on the Radius Token

Two findings from the review round on cdb91f4.

The marketplace query deliberately retries a 408 and a 429 twice
(`data-provider/Agents/queries.ts`) and leaves the longer backoff to the error
card, but the card classified both as `generic`, where `autoRetry` is false —
so a throttled or timed-out load stopped recovering after those two attempts
even though every layer above had called it retryable. A 408 now takes the
`timeout` copy that already describes it, and a 429 gets its own transient
kind rather than borrowing "Server Error" for a status the server answered
deliberately.

`GridSkeleton`'s placeholder card kept `rounded-2xl` while the real card moved
to `rounded-theme-surface`, so under any theme that sets a different surface
radius the corners jumped the moment the skeleton was replaced.

* fix: Read the Author Sort's Owner From Agent ACL Entries

The author sort joined every ACL entry sharing the agent's _id and picked the earliest full-bit user entry, so a REMOTE_AGENT owner entry left behind by an ownership transfer decided both the sort key and owner_contact. attachOwnerContacts counts only AGENT entries, so an author-sorted row could name a different owner than the same agent's card in any other sort mode. The filter now asserts the resource type.

* chore: Drop the Marketplace Strings the Refresh Orphaned

The rewritten grid, card and error card no longer render the old detail panel's copy, so com_agents_description_card, com_agents_error_loading, com_agents_error_searching, com_agents_results_for and com_agents_see_more had no reader left and the unused-i18n-keys static check failed. Only the English file is edited; the other locales are automated.

* fix: Recover on Window Focus and Move the Marketplace Query Contract Into packages/api

Three findings from the review at 9f59cad8.\n\nThe list query's sort allowlist and mine normalization were behavior in a CJS controller, which api/ is not supposed to hold; resolveMarketplaceListQuery now owns the contract in packages/api beside AgentSortOption, and v1.js keeps the call.\n\nuseAutoRetry promised recovery when the view is looked at again but only listened for visibilitychange, so a window that lost and regained focus with the tab still visible never recovered - terminal once the backoff was spent. It now also tracks focus/blur, counted once per activation so a tab switch that fires both events retries once.\n\nThe aggregation predicate helpers returned Record<string, unknown>, which the repository prohibits for new code and which accepts any misspelled operator; they return a concrete expression union instead.

* fix: Move Owner-Contact Resolution Out of the CJS Service and Open Mine Links on All

`api/server/services/Agents/ownerContact.js` had grown the resolved-row filtering, the
marker cleanup and the owner ACL pipeline, all behaviour, inside `/api`. The service is
now the wiring the boundary asks for: `attachAgentOwnerContacts`
(`packages/api/src/agents/ownerContact.ts`) takes its database reads from the caller, and
the owner query itself is a data-schemas method, `getFirstOwnerIdsByResource`, beside the
`OWNER_ACL_PERMISSION_BITS` the marketplace's author sort already resolves against. The
aggregation casts stringified ids, because `$match` does no schema casting and a caller
outside data-schemas has no Mongoose ObjectId to hand it.

A restored or shared `/agents?mine=1` carries no path category, so it resolved to
`promoted` and answered the caller's own agents with the near-always-empty
promoted-and-mine intersection; turning the same filter on from Top Picks navigates to
`/agents/all`. It now defaults to `all` whenever the filter is on, so both routes to the
intent agree.

The conversation-starter buttons dropped their hard-coded `rounded-xl`, so they take the
shared `Button`'s shape like the dialog's other controls instead of mixing two.

`e2e/specs/mock/scenarios/` carries one tagged Playwright test per acceptance scenario:
sorting and paging, the mine filter and its link, failure recovery, and the card-to-dialog
morph, its focus return, its single scrim and its radius.

* feat: Morph the Agent Description Word by Word and Retime the Whole Transition

The card clamps the description to three lines and the dialog shows all of it,
so handing the paragraph over as one block slid the card's wrapping into place
and then swapped it for the dialog's. Every word the card showed now travels
from where that paragraph wrapped it to where this one does, and the lines the
clamp hid fade in where they land. The words are written to directly through CSS
transitions rather than re-rendered: a description is hundreds of independently
positioned spans, the compositor can carry them without a frame of JavaScript
each, and a transition can be interrupted mid-flight where a keyframe animation
restarts. Assistive technology still reads the copy once, from a flat string;
the spans are decoration and are hidden from it.

The identity block moved into the scroll region, the contact took the old
Pin/Copy Link corner, and those two controls moved next to Start Chat. Title and
description centre on the avatar while the copy is shorter than it, and top-align
once it outgrows it - pure CSS, no measurement.

Timings collapse onto one clock. A single ease-out-cubic and one open budget
drive the surface, the page dim, the identity fields and the words, so nothing
reads as a second animation that happens to have been started alongside the
first:

  open        300ms   surface, identity fields, dim
  words        210ms  (0.7 of the open: a word crosses a fraction of the box's
                       distance, and sliding copy cannot be read)
  close        280ms  70ms handover, then a 210ms contraction
  word return   70ms  the whole handover; nothing else is moving on the way back

The close is two phases because the surface cannot contract until this dialog
unmounts and gives it back. Only the handover is spent with the box still, so it
stays short, and the dim now leaves on the click rather than on the unmount -
that is what answers the click while the geometry is still waiting. The dim
ramps linearly across each direction: an ease-out on an alpha spends two thirds
of its range in the first third of its time, and a scrim at 80% black already
looks black at half of it, so the page read as fully dim while the box was still
growing.

The words move and only move - no blur, no per-word delay, no scaling. A word
broken across two lines has no single box to fly from, so it is left to the
fade, and a paragraph showing different copy than the card (a background refresh
can land one) is refused outright rather than flying every word in from the
wrong place. Reopening inside the handover turns the words around instead of
leaving them parked in the card's wrapping.

* fix: Keep the Loaded Rows Mounted While the Marketplace Retries

A failure or an empty result was rendered in place of the list. With pages
already loaded that collapsed the list's scrollable height, so the browser
clamped the scroll position to the shorter document, and the remount that
followed a recovery ran the layout effect again and started the list at the
top: a transient cursor-page failure sent someone browsing deep in the
marketplace back to the first row.

The rows now stay mounted and the placeholder follows them, which also means
the end of the list stays reachable while a failure is held — so paging is
suspended until it clears, leaving the retry and its backoff to the error card
instead of re-requesting the page that just failed on the next scroll.

* test: State the Morph and Retry Scenarios as What the Reader Sees

Two scenario assertions described the implementation rather than the behaviour.

The detail-dialog description is now painted per word beside one screen-reader
copy of the same text, so matching the copy exactly resolved to both nodes. The
scenario asserts the paragraph that carries the description instead of counting
the nodes that spell it out.

The retry scenario pinned the scroll position to the pixel, which moves by
whatever the card rendered below the list occupies. It now anchors on the row
the reader had reached still being on screen, with the position staying deep
rather than clamped back to the first row.

* fix: Show the Retry Instead of a Skeleton, and Keep Cursors Readable

Two failures a marketplace reader could hit.

A held failure has no data of its own, so the retry that clears it made the
list pending again and filled the viewport with skeleton cards above the error
card. The card's status, countdown and action ended up below the fold, so the
recovery the card was reporting was the one thing not on screen. The skeleton
is now suppressed while a failure is held: the card owns the waiting state for
the request it describes.

The sort cursor carries `primary` and `secondary`, which an instance predating
sort modes cannot read - it reads `updatedAt` and `_id`, builds an Invalid Date
from their absence, and the query Mongo rejects surfaces as a 500 in the middle
of someone's scroll during a rolling deployment. Cursors now carry that pair as
well, describing the same row, so an older instance continues its own
updated-time ordering from where the page ended. The popular mode built its
cursor from a synthetic row, so it now carries the projected document instead.

* fix: Keep a Cursor Readable Only by a Server That Implements Its Order

Four review findings, and one rule behind three of them: state belongs to
whoever owns it, and a cursor belongs to the ordering it describes.

A sort cursor carried a legacy `updatedAt`/`_id` pair unconditionally, so an
older instance reached during a rolling deployment could parse a cursor from
`oldest`, `popular` or `author` and resume its own `updatedAt` walk from a
boundary row that ordering never produced - skipping agents and repeating
others. The pair is now emitted only for `recent`, whose `updatedAt` descending
plus `_id` ascending order is exactly what the legacy decoder implements. Every
other sort omits it and an old instance rejects the cursor outright, which is
the same argument the surrounding comment already made about not inventing a
date.

Marketplace avatars were refreshed from a separate newest-sorted query capped at
1,000 rows, run before the page the caller actually asked for. A user with more
accessible S3-backed agents than that cap saw broken avatars on every
`oldest`, `popular` or `author` page, and the 30-minute cache suppressed the
next attempt. The requested page is now queried first and its own uncovered
S3-backed rows are refreshed; the cache records which ids it covered, so an
entry written for one page no longer stands in for rows it never touched. The
selection, the cap and the cache merge live in `packages/api/src/agents`, with
the controller reduced to the call.

The detail dialog reached into `~/store` to clear the conversations a
multi-conversation session left open. That state is the app's, not the
marketplace's, so `MarketplaceProvider` performs the reset and the dialog asks
for it through the host context; the hook throws rather than defaulting to a
no-op, because a silent miss is the bug it exists to prevent.

With rows kept mounted, a failed background or cursor page put its retry card at
the end of a list several viewports tall - a marketplace that had quietly
stopped loading looked healthy. The card is now pinned to the bottom of the
scroll frame while rows exist, so its status, countdown, retry and reload link
are on screen wherever the reader is; with no rows there is nothing to pin it
over and it remains the whole of the page.

Two findings are rejected rather than patched. Popularity pagination recomputes
counts per request, so an agent that gains favourites mid-walk can cross above
the cursor and be missed; the walk is stable within a count, and backward drift
is deduplicated by the client. Making it exact requires a ranking snapshot, and
the favourites subdocument carries no per-favourite timestamp to snapshot from
(`packages/data-schemas/src/schema/user.ts:163-171`), so the fix is the
materialized counter tracked in berry-13/LibreChat#11; the guarantee is now
stated in the method instead of implied. Author sorting computes its key from
the ACL and user joins, so its cursor predicate cannot move ahead of them
without a stored sortable owner key - a schema change with a backfill, not a
pipeline reordering.

* docs: Track the Popularity Walk's Skipped Row as Its Own Issue\n\nThe method pointed only at the materialised-counter issue, which tracks the cost\nof recounting favourites per page. The row an upward drift drops from the rest of\nthe walk is a correctness problem that survives whether or not the cost is ever\naddressed, so it is tracked separately and the comment cites both: what can be\nmissed, and what pinning a ranking would take.

* fix: Let a Cursor Be Read by the Version That Implements Its Order

The previous round gated cursor *encoding* so only `recent` emits the legacy
`updatedAt`/`_id` pair, and left decoding rejecting it. That breaks the opposite
rollout direction: a page served by an older instance, followed by a request
reaching this one, produced an unreadable cursor, so the walk restarted at page
one - and `fetchAllAgentPages` concatenates without cycle detection, so
alternating instances can loop without finishing. Decoding now accepts the
legacy pair for `recent`, whose ordering this version implements, and still
rejects it for the sorts whose ordering it does not. The invariant is the same
one, read from the other side.

Refreshing a presigned avatar URL went through a timestamped update, so
maintenance advanced `updatedAt` - the sort key of the default walk - and an
agent below an active cursor could cross above it and vanish from the rest of
that walk. Avatar writes now go through `updateAgentAvatar`, which sets the
avatar alone with timestamps disabled.

The avatar orchestration the last round left in the controller - the
page-coverage cache decision, the refresh failure policy, the cache merge and
the persistence call - moved to `packages/api/src/agents/avatars.ts` with the
cache, the refresh and the update injected. The CJS controller holds the wiring
and one call.

On the client, the retry card was pinned to the bottom of the scroll frame and
rendered after the whole list, so it was visible but last in keyboard order:
`handleKeyDown` mounts and focuses each next card, so reaching Retry meant
traversing every loaded agent. It now renders before the rows and pins to the
top of the frame. A bottom pin cannot survive the move - sticky bottom only
holds an element whose flow position is below the viewport - so the pin
direction follows the DOM order rather than the reverse.

Two more from the same reading. `keepPreviousData` leaves the previous scope's
pages in `data` while a replacement loads or fails, and the failure branch
bypasses the pending guard, so a failed "My agents" request could render its
error over clickable agents from the scope the user had left; those rows are no
longer treated as current. And because a virtual row is keyed by its first
agent, a refetch that reorders the list unmounts the focused card: focus is now
restored to the same agent, and only when the unmount is what dropped it.

* fix: Make a Cursor Name Its Ordering, and Refuse the Ones It Cannot Honor

Third round on the same seam, so this stops patching it. A cursor now names the
ordering it was produced under, and is honored only by a reader that implements
that ordering; one that cannot be honored is an error rather than a silent
restart. `recent` keeps emitting the legacy `updatedAt`/`_id` pair, so old
instances still read its cursors, and a legacy-only payload counts as the
`recent` ordering: usable there, a mismatch everywhere else. Decoding reports
usable, ordering-mismatch or unreadable; `getListAgentsByAccess` raises instead
of paging from the start, and the controller answers 409
`{"error":"cursor_ordering_mismatch"}` through a mapper in `packages/api`.

That closes the direction this round found: a first page served by an old
instance for `sort=newest` produced a cursor this version rejected, and the
rejection fell back to page one, so the infinite query appended a second first
page - duplicated and out of order. The client now treats the 409 as "this walk
came from another ordering", drops the pages it holds and refetches from the
first page in the ordering the user asked for, once per request signature so a
mixed-version deployment cannot loop.

The author sort ordered by raw display name, so `Zoe` came before `alice` in a
list whose whole purpose is alphabetical. It sorts on a `$toLower` key now, and
the cursor carries that same normalized value - otherwise the ordering and the
pagination boundary disagree about where the page ended.

Avatar refresh coverage was a flat id list under one renewing TTL, so a page
refreshed at minute 0 stayed marked covered until minute 59 if another page was
refreshed at minute 29, and the set grew for the length of the walk. Coverage is
now a per-id deadline map: an id is covered only while its own deadline holds,
expired ids are dropped on read and write, the retained set is bounded with
nearest-expiry eviction, and the entry's TTL follows the furthest deadline it
still holds.

On the client, the retry card was pinned but in flow, so it displaced every
loaded row by its own height when a late page failed and put them back on
recovery. It sits in a zero-height sticky host now, keeping the three
constraints that pull against each other: first in keyboard order, visible at
any scroll position, and no layout space. Both of the traps that shape it are
written down - a flex child stretches to its container's cross size, so the
card's background collapses without `items-start`, and the stacking level has
to clear the cards' own click overlay.

An agent removed from the list while its dialog was open kept Pin, Copy Link,
the starters and Start Chat live, so Start Chat could navigate to a deleted
agent and Pin could persist a stale id. Absence from the loaded pages is not
proof of deletion - paging and sorting move rows out of the window - so the
captured id is revalidated against the per-agent endpoint, which enforces
access; only 403 and 404 mark it unavailable, the dialog says so, and its
actions go with it. A transient failure leaves the agent actionable.

* fix: Version an Ordering When Its Comparison Changes

Normalizing the author sort changed what "ordered by creator name" means while
still calling that ordering `author`, so the immediately previous
implementation would accept a cursor from this head and resume under
case-sensitive comparison: page one ending at `alice` let a later page skip
`Zoe`, which compares before the cursor under the old rules. The ordering
identity now carries a version alongside the mode - `author` at 2, everything
else at 1 - matched exactly on decode, with an absent version read as 1 so
cursors already in flight keep working for every mode whose semantics did not
change. The rule is written where the version lives and where it is encoded:
bump it when a comparison changes, or an older reader resumes a walk under
semantics that no longer exist. `popular` and `recent` were audited and left at
1; their comparisons are untouched.

A next-page request answering `cursor_ordering_mismatch` reset the walk
correctly, but the grid had already filed that error as a next-page failure,
and it clears those only when the replacement holds more pages than the prefix
it replaced. A restart yields exactly one page, so the error card stayed up over
a perfectly good first page, and its retry called `fetchNextPage`, which does
nothing when that page has no cursor. The query layer now reports the reset it
performed, and the grid drops the held failure when that reset's page-one
request succeeds. Ordinary failures keep the hold-until-success rule that stops
the card from remounting and resetting its own backoff on every attempt.

The dialog revalidates the selected agent when its row leaves the loaded
window, and that request is authoritative - but the dialog kept rendering the
snapshot it opened with, so a refresh that both edited an agent and moved it out
of the window left a stale description and stale starters on screen, and a
starter could launch with text the owner had replaced. It now prefers the row
the list holds, then the revalidated agent, and keeps the snapshot only for the
case neither can answer.

While that check was in flight the action controls were unmounted, so focus on
Pin, Copy Link, Start Chat or a starter fell to a detached element outside the
modal and was not restored afterwards. They stay mounted and are marked
`aria-disabled` for the duration, which is also why they are not natively
disabled: disabling the focused element blurs it, reaching the same bug by
another route. `CopyLink` takes that state and guards its activation, so the
control keeps focus, announces as disabled, and cannot copy a link to an agent
whose existence is still being checked.

* fix: Put a Bumped Ordering's Boundary Where an Old Reader Cannot Find It

Versioning the ordering identity only protects a reader that knows to look at
the version. An instance deployed before versioning existed ignores unknown
fields and reads `primary`/`secondary` straight out of the payload, so an
author cursor from this version - whose boundary is a lowercased name - was
still resumable under the case-sensitive comparison it replaced: page one
ending at `alice` let that reader skip `Zoe`.

An ordering past version 1 now nests its boundary under `boundary`. A reader
that predates versioning finds no boundary it recognizes and fails closed
instead of walking the wrong comparison, and a reader that knows about versions
knows where to look. Version 1 keeps the flat shape, which is what keeps every
cursor already in flight readable across a deployment, and `recent` keeps its
legacy pair. A flat boundary claiming a version past 1 did not come from this
encoder, so it is unreadable rather than trusted.

Verified against the running API: an author page emits
`{sort, version: 2, boundary: {primary, secondary}}` with no top-level boundary
fields, the next page continues it with no overlap, and both a flattened
boundary and a version-1 author cursor answer 409 `cursor_ordering_mismatch`.

* fix: Let an Author Cursor Carry the Key the Database Ordered By

The author sort orders on `authorSortKey`, the `$toLower` of the display name,
and the row handed to the encoder already carries that key. The encoder
lowercased it a second time in JavaScript, which normalizes what the database
does not: `$toLower` is defined over ASCII and leaves `Émile` (U+00C9)
uppercase, so the boundary was written as `émile` (U+00E9) and the next page's
`$match` skipped every key in between - `Üwe` (U+00DC) disappeared from the
walk entirely, with `has_more` false and an empty page to show for it.

The computed key is now serialized as it stands. The ordering's comparison is
untouched - `$sort` still reads the same `$toLower` key - so the version stays
at 2: a cursor already in flight from the previous head decodes to the same
boundary it did before and resumes the same walk, rather than being refused for
an ordering change that did not happen.

Reproduced and verified in `agent.spec.ts`: two agents whose contact names are
`Émile` and `Üwe`, paged one at a time, lost the second row before this change
and both pages now return their row; 231 tests in that suite pass.

* fix: Give the Recovery Card Its Own Band Instead of the Rows' Space

The retry card was a zero-height sticky host painted over the list, so whatever
it covered was still focusable with nothing to show for it: a focus ring under
an opaque card is no focus ring, and on a narrow viewport the card covers the
first row entirely. Reproduced across desktop light, desktop dark and mobile -
the focused card's box intersected the card's box at the top of the list and
again halfway down it.

The host now takes the card's own measured height, so the rows begin below the
band rather than under it, and the scroll position absorbs that reserve: someone
reading deep in the list keeps the row they were on, and at the top - where
there is nothing to absorb it with - the rows are what moves, which is the point.
`scroll-padding-top` covers keyboard navigation, so a Tab into a row the card
would cover scrolls it clear, and a row the reader had already scrolled past is
pulled out from under the card when it takes focus. Only the focused card moves;
the reader's scroll position is otherwise left alone.

The card's height is measured rather than assumed because it grows with its
status, its countdown and its eventual reload link, and the reserve follows it.

Verified on this head with a rebuilt client: `@scenario:focused-card-stays-visible-under-the-retry`
fails before this change and passes after it in all three projects, with
`@scenario:pagination-failure-keeps-the-loaded-rows` and
`@scenario:retry-keeps-the-error-card-on-screen` still passing beside it -
the rows, their height, the reader's place and keyboard order are unchanged.
`client/src/components/Agents`: 13 suites / 155 tests pass; `npx tsc --noEmit` clean.

* fix: Keep the Grid Under an Open Dialog, and the Author Boundary a String

Three findings on one head, two of them variants of the same rule - a recovery
state must not take away what the reader is using.

The pending-results branch replaced the whole grid with the loading skeleton,
and the grid is what owns the detail dialog and the element focus returns to. A
refresh with no data of its own - a reset cache, a revalidation after the rows
were dropped - therefore tore an open dialog down mid-flight. The skeleton is
now one of the placeholders the grid renders *inside* itself, beside the
recovery card and the empty state, so the host stays mounted and the dialog
survives its own results being refetched.

A scope change is different: the grid is keyed on the query scope, so a
debounced search or a restored history entry legitimately remounts the rows and
the dialog goes with the list it belonged to. What must not go with it is the
focus it held: the browser drops focus on `document.body`, so the next Tab
starts at the top of the page rather than at the marketplace. The panel takes
focus in exactly that case - focus already elsewhere, the search field being
typed in, is left alone, because only `body` means nobody holds it.

The dialog also read the revalidated agent as the whole agent, and the per-agent
VIEW response carries no `category` (`api/server/controllers/agents/v1.js`), so
an agent that moved out of the loaded window lost its badge. The revalidated
fields are laid over the captured row instead: fresh where the endpoint speaks,
captured where it is silent.

Last, an author cursor's boundary was coerced with `String()`, and coercion is
not validation: a missing or non-string `primary` became the ordinary key
`'undefined'` and resumed the walk partway through the alphabet instead of
answering 409. The date and number modes fail on their own casts; the string
mode now requires a string.

Each is pinned by a regression that fails on the parent commit: the dialog
surviving a refresh and the panel taking focus back
(`AgentGrid.integration.spec.tsx`), the category surviving revalidation
(`VirtualizedAgentGrid.test.tsx`), and four non-string author boundaries
answering `unreadable` (`agent.spec.ts`). `client/src/components/Agents`:
13 suites / 157 tests pass; `packages/data-schemas` `agent.spec.ts`: 232 tests
pass; `npx tsc --noEmit` clean in both workspaces.

* fix: Merge an Avatar Refresh Into the Entry That Is There, Not the One It Read

Every list page for one user reads the refresh entry before its list query, then
spends the S3 round trips of a whole page before writing back. Two pages in
flight together therefore merge into the same snapshot, and the later write drops
the coverage and refreshed URLs the other one added, so the next response that
contains those agents presigns and persists them again.

The merge now re-reads the entry immediately before the write, which narrows the
overlap to that gap instead of the whole refresh. A read that fails keeps the
caller's snapshot, leaving the previous behaviour in place rather than losing the
refresh that just succeeded.

* docs: Say Which Default the Sort Contract Actually Describes

Both the shared type and the grid prop claimed the server falls back to `newest`
when a request omits `sort`. It does not: `resolveMarketplaceListQuery` leaves an
absent or unknown mode undefined, and `getListAgentsByAccess` then serves
`recent`, the most-recently-edited order the agent selector and the mention menu
depend on. `newest` is the marketplace's default, which is why the grid sends it
explicitly.

The grid now names the constant the dropdown already exports instead of
repeating the literal, so the marketplace default has one definition.

* fix: Keep Rich Agent Descriptions Rendering After the Marketplace Rewrite

The rewrite replaced the card and detail views that `Description` had just been
wired into, so an agent whose description is markup lost it: the card printed the
tags as text and the dialog no longer rendered the links or images at all.

The card strips the copy with `getPlainDescription`, which is what it showed
before and what the word morph can measure, since that morph walks text nodes.
The dialog renders markup through `Description` again and hands the paragraph
over whole rather than word by word, because there are no words to measure in a
sanitized fragment. A plain description still morphs.

* fix: Answer a Marketplace Failure Without Taking Away What Is in Use

Twelve findings over three rounds, and most of them are one rule: a recovery
state must not remove what the reader is holding, and a lever the code invents
belongs to whoever runs the deployment.

Focus, three times. The effect that takes focus back after a scope change fired
on the initial marketplace mount as well, because a fresh navigation also leaves
`document.body` focused - so arriving at the page started reading below the
heading, the search field and the filters. It now compares the scope key against
the previous render and never acts on the first one. A successful Retry removes
the recovery card with the focused button inside it; focus moves to the results
panel first, and only when it was inside the card, so a reader who has moved on
is not yanked back. And when the access check settles 403/404, the dialog's
actions are removed under the same rule: focus goes to the status that explains
why they are gone, which is now programmatically focusable, rather than to the
document.

A dialog opened after the owner edited an agent used to keep the cached copy
while re-enabling its actions, so a conversation starter could launch a chat with
text that had already been replaced. Both selected-agent branches now lay the
revalidated fields over the captured row through one helper - fresh where the
per-agent response speaks, captured where it is silent, which is why it is a
merge and not a replacement.

Two operator levers ship as configuration, each defaulting to today's behaviour:
`endpoints.agents.avatarRefresh.coverageLimit` for how many per-agent S3 refresh
deadlines one user's pages remember, and `interface.marketplace.retryDelaysMs`
for the recovery cadence - an empty sequence leaves only the manual Retry, which
is why the reload affordance goes with it. That closes berry-13/LibreChat#24,
which had deferred the retry policy.

The avatar path also stopped losing work and stopped overwriting owners. Two
pages refreshing the same user's avatars both read before either wrote, so the
later write dropped the other's coverage and both pages re-signed inside the
advertised window; merges for one key are serialized, with the re-read left in
the critical section because that is what makes separate processes converge. A
rejecting cache write used to discard URLs that had been signed successfully and
answer with the expired paths; it is best-effort now. And a viewer's in-flight
refresh could land after the owner replaced that avatar: `updateAgentAvatar`
takes the avatar the caller read and only writes while the stored one still
matches, with the skipped agent's stale URL left out of the response.

Two smaller ones. A malformed `popular` cursor carrying `-1` or `1.5` passed
validation and walked an incomplete or duplicated page instead of answering 409;
counts are discrete, so the boundary must be a non-negative integer. And a rich
description rendered inside the paragraph the plain text morphs in, which is
invalid nesting once the sanitized markup carries blocks of its own - the rich
branch is a block, and both share one set of motion props.

Last, `attachAgentOwnerContacts` took a Mongo `$in` filter and a projection
string, which put the storage engine in `packages/api`'s public contract. It now
takes owner ids, and `findOwnerContactUsers` in `packages/data-schemas` owns the
query.

Every fix is pinned by a regression that fails on the parent commit. Locally:
`client/src/components/Agents` 13 suites / 170 tests, `packages/api`
`src/agents/{avatars,ownerContact}` 29 tests, `packages/data-schemas`
`{agent,user}.methods` 330 tests, `api/server/controllers/agents/v1` 146 tests;
`npx tsc --noEmit` clean in `client`, `packages/api`, `packages/data-schemas` and
`packages/data-provider`.

* fix: Hand Focus Back When a Removal Takes It, Not When a Retry Starts

Recovery moved focus at the moment the request went out, which is the wrong
event: a retry that fails again leaves the card on screen, so the reader lost the
button they were still using. Focus is only in danger when the thing holding it
is removed - and the DOM says so plainly, because the browser drops focus on
`document.body` in that commit.

The grid now watches for that: one effect recovers focus when a scope change
remounted the rows or a cleared failure removed the recovery card, and only while
nobody holds focus. The card's retry goes back to being just a retry, and the
recovery band is the measured wrapper again, its bottom gap included.

Two regressions in `AgentGrid.integration.spec.tsx` pin the distinction: focus
lands on the results when a successful retry removes the focused button, and
stays on the button when the attempt fails again - the latter fails on the
previous commit, which yanked focus to the panel while the card was still there.
`@scenario:recovery-hands-focus-back-to-the-results` states it in a real browser,
where focus after a removal is the browser's decision rather than jsdom's.

`client/src/components/Agents`: 13 suites / 171 tests pass; `npx tsc --noEmit`
clean in `client` and `e2e`.

* style: Declare the Serialization Test's Cache as the Constant It Is

The forward reference the mock cache needed while it was assembled in two steps
is gone, so `let` only tripped `prefer-const` in CI's ESLint lane.

* fix: Bind a Cached Avatar URL, a Joined Owner and a Morph's Styles to What They Describe

Four defects from one round, each in a subsystem this branch introduced, and each
the same shape: a value was keyed by the thing it was near rather than the thing
it was about.

A signed URL belongs to an avatar, not to an agent. Coverage keyed on the agent
id alone meant that when an owner replaced one S3 image with another, the viewer's
page was skipped as covered and the controller pasted the cached URL for the old
file over the freshly loaded path - so that viewer kept seeing a removed avatar
for the rest of the window, while the owner saw the new one. Entries now carry the
filepath they were signed for, coverage only counts while that filepath is still
the one on the row, and a refresh pass records what it checked. Entries written
before the binding existed cannot be checked, so they are treated as uncovered
and signed again rather than replayed.

An owner belongs to a tenant. The author sort joins `aclentries` and `users` with
`$lookup`, which does not run the models' tenant middleware, so a stale or
imported principal id resolved to another tenant's user and that name came back as
`owner_contact` - a name the ordinary resolver, which goes through tenant-scoped
methods, never returns. Both joins now match the agent's tenant, with missing and
null treated as the one tenantless scope this file already uses for favourite
counts.

`support_contact` is `Schema.Types.Mixed`, and `$ifNull` passes a number or an
object straight into `$trim`, which rejects it and fails the whole aggregation. A
single malformed legacy row therefore turned every author-sorted page in that
scope into a 500, while `attachAgentOwnerContacts` shrugged the same value off.
Every display operand is now checked for BSON string type first, which leaves the
tier logic unchanged because it already rejects the empty string as a name.

A compositor hint belongs to the animation that needed it. When revalidated copy
arrived mid-morph, the previous effect's cleanup cancelled the settle timer and
the same-phase guard returned before clearing anything, so every reused word kept
`will-change: transform` and its transition for the lifetime of the dialog. One
cleanup now clears the spans it owns on every path - a same-phase change, a phase
change, an unmount - and the refreshed copy arrives at rest instead of replaying
an opening morph.

Two further reports on this round are accepted rather than fixed, with the
reasoning on their threads: the coverage merge is serialized per key inside a
process and not across replicas, because a dropped merge costs signing work the
next page redoes and never a wrong URL - the comment that claimed convergence now
says so - and the rolling-deployment window where a parent-version server ignores
`sort` and `mine` is transient, read-only and self-correcting, while the capability
handshake its remedy needs does not exist in this platform.

Each fix is pinned by a regression that fails on the parent commit:
`refreshes covered agents when their avatar filepath changes` and two siblings in
`packages/api/src/agents/avatars.spec.ts`, `does not resolve an owner user from
another tenant during author sorting` and `tolerates non-string support contact
values while sorting and paging` in `packages/data-schemas`, and `clears word
animation styles when refreshed copy changes during the morph` in
`AgentDetailContent.spec.tsx`. Locally: `client/src/components/Agents` 13 suites /
172 tests, `packages/api` avatars 26, `packages/data-schemas` agent + documentdb
298, `api/server/controllers/agents/v1` 146; `npx tsc --noEmit` clean in `client`,
`packages/api` and `packages/data-schemas`.

* fix: Cover the Path the Refresh Wrote, and Keep Pin Focusable While It Saves

Two findings, both about state that moved on while something kept pointing at
where it used to be.

Coverage recorded the filepath a refresh *started* from, while the write that
followed stored the newly signed one. The next page therefore loaded a row whose
path no coverage entry named, so a successful re-sign guaranteed another
per-agent pass and another cache write inside the window it had just claimed -
the opposite of what coverage is for. Coverage now names the path that was
persisted, because that is what a later page reads, and the cached URL keeps the
path the page in hand still carries, because that is the row it applies to. The
merge no longer requires those two to agree: they are different questions, and
insisting they match is what dropped the freshly signed URL.

A refresh that found nothing to change writes nothing, so its coverage keeps the
path the row already had; that case is now stated as its own test rather than
standing in for the one above.

Pin stayed a control while it worked. Activating it from the keyboard used to set
`disabled` on the button that had focus, and a disabled control leaves focus
navigation, so focus fell to the document until the favourite mutation settled.
It keeps `aria-disabled` and `aria-busy` with a guarded handler instead - the same
shape Copy link, Start chat and the starters already use - so the reader stays on
the control they pressed and a second Enter cannot queue a duplicate toggle.

Both are pinned by regressions that fail on the parent commit: `covers the path
it persisted, so the row it wrote is not signed again` in
`packages/api/src/agents/avatars.spec.ts` (two signing calls where one is
correct), and `keeps focus on Pin while the favorite mutation is busy and ignores
repeated activation` in `AgentDetailContent.spec.tsx` (focus on the document, no
`aria-disabled`). Locally: `client/src/components/Agents` 13 suites / 173 tests,
`packages/api` avatars 27, `api/server/controllers/agents/v1` 146; `npx tsc
--noEmit` clean in `client` and `packages/api`.

* fix: Join the Author's Owner the Way DocumentDB Can, and Leave Retry Focusable

Two findings, and the first is a compatibility rule this branch already carries as
an invariant. Scoping the author joins to the tenant used `$lookup` with
`let`/`pipeline`, which Amazon DocumentDB 5.0 rejects — this repository records
that in `prompt.getPromptGroup.spec.ts` — so selecting Author on such a
deployment would have failed the aggregation and answered 500. The joins are
plain `localField`/`foreignField` again, and the tenant scope is applied to the
joined arrays with `$filter` afterwards: the same isolation, expressed in
operators that survive the target. `documentdb.spec.ts` now fails if either
marketplace lookup goes back to the correlated form, so the next person to reach
for it is told by a test rather than by production.

The shared retry control had the focus fault the pin control just lost.
Activating Retry sets `isRetrying`, whose native `disabled` drops the focused
button out of focus navigation; when that attempt fails the card stays mounted,
the grid's handoff never runs — it only fires when a cleared failure removes the
card — and the reader is left with focus nowhere, beside a card they cannot Tab
into. `RetryableError` keeps the button focusable with `aria-disabled`,
`aria-busy` and a guarded handler, same label, spinner and dimming as before.

The marketplace's existing assertion that the control is `disabled` while
retrying pinned the mechanism rather than the behaviour, so it now states what a
reader gets: busy, still focusable, and a second press that does nothing.
`@scenario:recovery-hands-focus-back-to-the-results` covers both outcomes in a
real browser — focus stays on Retry when the attempt fails, and moves to the
results when the success removes the card — because jsdom blurs neither and that
is exactly how this escaped.

Pinned by `keeps marketplace author lookups in the DocumentDB-compatible form`
and `flags a correlated $lookup let/pipeline form` in
`packages/data-schemas/src/methods/documentdb.spec.ts`, which report four
offending stages on the parent commit, and by `keeps the retry control focusable
and blocks a second activation while retrying` in
`packages/client/src/components/RetryableError.spec.tsx`. Locally:
`packages/data-schemas` agent + documentdb 300 tests, `packages/client`
components + hooks 292, `client/src/components/Agents` 13 suites / 173 tests;
`npx tsc --noEmit` clean in `client`, `packages/client`, `packages/data-schemas`
and `e2e`.

* test: Ask Where Focus Is, Not Which Box It Sits In

The failed-attempt half of the recovery focus scenario asserted that focus was
inside the card's `role="alert"`, which the retry control has never been in: the
alert is the icon, title and detail, and the actions are its sibling, so the
assertion described the DOM rather than the behaviour and failed on all three
projects.

It now asks the only question that matters - the control the reader pressed still
has focus - and lets whichever attempt lands next, theirs or the card's backoff,
be the removal that hands focus to the results.

* test: Count the Morph's Scrim by the Class Both Layers Carry

The base moved OGDialog's scrim from a literal `bg-black/80` to the
`surface-overlay` role, so the morph's backdrop follows it through the shared
constant. The scenario counted layers by the old literal and by black channels,
which after the move would have found no scrim at all, and could only ever have
caught a duplicate dim in the themes whose overlay is black.

It now counts the class the overlay and the morph's backdrop both carry, and
treats any full-viewport layer at alpha 0.3 or above as a second dim, so the
light theme's gray scrim is covered by the same assertion.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01EFLKexs5HyzqT6H8B9oQqJ

* fix: Keep the Avatar Cache Contract in packages/api, and the Grid Mounted

The list controller was reading the avatar cache entry itself: it checked that a
cached value carried both a filepath and a url, that the row still named S3, and
that the filepath still matched, then wrote the signed URL onto the row. That is
behaviour in a CJS file under /api, and it split the cache contract across two
layers, so a later change to the entry shape would have had to be made in both.
`applyCachedAvatarUrl` now owns that decision beside the code that writes the
entry, and the controller passes the entry through.

The grid was keyed on the active category. Its own scope key already carries the
category, so the key only forced a remount that the scope change was about to
handle anyway, and it took the open detail dialog and its focus-return target
with it. The replacement grid starts with an empty previousScopeKeyRef, so it
reads its first render as a mount rather than a scope change and never hands
focus back, leaving it on the document.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01EFLKexs5HyzqT6H8B9oQqJ

* fix: Supply the Marketplace Host From the Shell, and Order Two Keys by What Reads Them

The marketplace provider took the app's conversation reset from `~/store` itself.
Wrapping that in a context did not make it a host boundary, because the feature
was still the side reaching for shell state, and the feature could not have moved
to its own workspace without the conversation store coming along. The route now
builds the reset and passes it in, and the provider only carries it. The base did
not have this coupling; it arrived with the host context.

The favourites index led with `favorites.agentId`, a multikey field the popular
sort only ever tests for existence. With it first, the count could not seek into
the caller's tenant and scanned favourites across all of them, which is the work
proportional to the whole corpus that a page is supposed to avoid. Tenant first
bounds it.

The author aggregation compared ACL timestamps through raw field paths. The
resolver it has to agree with sorts the same three keys, where a missing field
reads as null, but a missing field path in a comparison expression is undefined,
which BSON orders below null. An imported entry that omitted `grantedAt` would
therefore win outright and hand the author page a different owner than every
other list order. The timestamps are now read through `$ifNull`.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01EFLKexs5HyzqT6H8B9oQqJ

---------

Co-authored-by: hoangtrongthai-dtvn <thai.hoang2@dac-datatech.vn>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-09-23 13:19:31 -04:00
Alexey Korepanov
cb52198b44
✨ feat: Client-Executed Function Tools for the Responses API (#16078)
* Add client side tools

* 🚦 fix: Ask the Model to Call Caller-Executed Tools Alone

* Add client tool continuation replay tests

* Fix clientTools docstring

* fix: return only tools that have been actually applied

* 🔁 fix: Continue a Caller-Executed Tool Exchange Across Requests

* fix: handle null values for tool descriptions and parameters in client tools

* 🧩 fix: Keep the Arguments of Every Tool Call in a Streamed Message

* Fix PR comments

* fix: Preserve client tool handoff across SDK event ordering

---------

Co-authored-by: Lia <lia@librechat.ai>
2026-09-22 23:09:07 -04:00
lia-by-librechat[bot]
ef89fbd5b3
🎽 fix: Give Each Streamed Tool Call a Stable Outward Index (#16209)
Some checks are pending
Backend Unit Tests / Build packages (push) Waiting to run
Backend Unit Tests / Codegraph select (push) Waiting to run
Backend Unit Tests / TypeScript type checks (push) Blocked by required conditions
Backend Unit Tests / Circular dependency checks (push) Waiting to run
Backend Unit Tests / Tests: api (shard 1/3) (push) Blocked by required conditions
Backend Unit Tests / Tests: api (shard 2/3) (push) Blocked by required conditions
Backend Unit Tests / Tests: api (shard 3/3) (push) Blocked by required conditions
Backend Unit Tests / Tests: data-provider (push) Blocked by required conditions
Backend Unit Tests / Tests: data-schemas (push) Blocked by required conditions
Backend Unit Tests / Tests: @librechat/api (shard 1/4) (push) Blocked by required conditions
Backend Unit Tests / Tests: @librechat/api (shard 2/4) (push) Blocked by required conditions
Backend Unit Tests / Tests: @librechat/api (shard 3/4) (push) Blocked by required conditions
Backend Unit Tests / Tests: @librechat/api (shard 4/4) (push) Blocked by required conditions
Codegraph E2E Votes / vote (full suite) (push) Waiting to run
Docker Dev Branch Images Build / publish (push) Waiting to run
Frontend Unit Tests / Client build recovery regression (push) Waiting to run
Frontend Unit Tests / Codegraph select (push) Waiting to run
Frontend Unit Tests / Build packages (push) Waiting to run
Frontend Unit Tests / TypeScript type checks (client) (push) Blocked by required conditions
Frontend Unit Tests / Tests: @librechat/client (push) Blocked by required conditions
Frontend Unit Tests / Tests: Ubuntu (shard 1/2) (push) Blocked by required conditions
Frontend Unit Tests / Tests: Ubuntu (shard 2/2) (push) Blocked by required conditions
Frontend Unit Tests / Vite build verification (push) Blocked by required conditions
Docker Dev Images Build / publish (push) Waiting to run
Sync Helm Chart Tags / Ignore non-main push (push) Waiting to run
Sync Helm Chart Tags / Sync chart tags (push) Waiting to run
* fix: give each streamed tool call a stable outward index

* fix: scope tool-call fragments and preserve completed answers

* fix: finalize agent tool-call snapshots without duplicating deltas

* fix: assemble complete tool identities before response publication

---------

Co-authored-by: Lia <lia@librechat.ai>
2026-09-22 11:00:01 -04:00
lia-by-librechat[bot]
1e2142e52a
🚥 fix: Preserve Insights With Guarded ACL Role Updates (#16170)
* fix: preserve Insights with guarded ACL role updates

* test: settle ACL index builds before opening the transaction

* fix: replace ACL mask partitions with single-operator bit writes

* style: drop the now-unused RoleBits import

* fix: make ACL role replacement one atomic guarded write

* fix: export the permission write retry ceiling

* fix: retry ACL mutations per document and preserve atomic permissions

---------

Co-authored-by: Lia <lia@librechat.ai>
2026-09-21 23:40:52 -04:00
lia-by-librechat[bot]
e4024052e0
✒️ fix: Persist a Generated Title Before the Turn Ends (#16137)
* ✒️ fix: Persist a Generated Title Before the Turn Ends

* 🧷 fix: Keep the Early Title Save From Rewriting Message References

* 🩹 fix: Carry the Recovered User Message Reference

* 🧵 fix: Reference Every Recovered Message Row

* 🪢 fix: Reference Paused and Resumed Response Rows

---------

Co-authored-by: Lia <lia@librechat.ai>
2026-09-21 06:40:38 -04:00
Marco Beretta
5f4a07f40b
⚡ perf: Exclude Agent Version History From Default getAgent Reads (#16070)
* ⚡ perf: Exclude Agent Version History From Default `getAgent` Reads

getAgent now defaults its projection to { versions: 0 }; loadAgent/loadAddedAgent
and canAccessAgentFromBody use getAgentWithVersionCount so the version count stays
exact without transferring the unbounded versions array on every chat request.
Callers that need history (v1 update/revert handlers) request it explicitly.

* fix: tighten agent version projection types

* fix: type projected agent version counts

* fix: type default agent projection

* style: format agent projection overload

* fix: expose projected agent return type
2026-09-20 19:27:21 -04:00
Danny Avila
1e0076376c
🪢 fix: Bind Preserved MCP API Keys to Server Configuration (#16136)
* fix: bind preserved MCP API keys to server configuration

* fix: surface MCP API key rebinding errors

* test: use typed MCP OAuth re-entry error
2026-09-20 12:33:20 -04:00
lia-by-librechat[bot]
16a7e116ef
💌 feat: Authenticate RUM Proxy Exports (#16114)
Co-authored-by: Lia <lia@librechat.ai>
2026-09-20 05:25:26 -04:00
Danny Avila
2df937dd06
🌳 feat: Isolate Attached Workspaces by Conversation (#16107)
Some checks are pending
Backend Unit Tests / Build packages (push) Waiting to run
Backend Unit Tests / Codegraph select (push) Waiting to run
Backend Unit Tests / TypeScript type checks (push) Blocked by required conditions
Backend Unit Tests / Circular dependency checks (push) Waiting to run
Backend Unit Tests / Tests: api (shard 1/3) (push) Blocked by required conditions
Backend Unit Tests / Tests: api (shard 2/3) (push) Blocked by required conditions
Backend Unit Tests / Tests: api (shard 3/3) (push) Blocked by required conditions
Backend Unit Tests / Tests: data-provider (push) Blocked by required conditions
Backend Unit Tests / Tests: data-schemas (push) Blocked by required conditions
Backend Unit Tests / Tests: @librechat/api (shard 1/4) (push) Blocked by required conditions
Backend Unit Tests / Tests: @librechat/api (shard 2/4) (push) Blocked by required conditions
Backend Unit Tests / Tests: @librechat/api (shard 3/4) (push) Blocked by required conditions
Backend Unit Tests / Tests: @librechat/api (shard 4/4) (push) Blocked by required conditions
Codegraph E2E Votes / vote (full suite) (push) Waiting to run
Docker Dev Branch Images Build / publish (push) Waiting to run
Frontend Unit Tests / Client build recovery regression (push) Waiting to run
Frontend Unit Tests / Codegraph select (push) Waiting to run
Frontend Unit Tests / Build packages (push) Waiting to run
Frontend Unit Tests / TypeScript type checks (client) (push) Blocked by required conditions
Frontend Unit Tests / Tests: @librechat/client (push) Blocked by required conditions
Frontend Unit Tests / Tests: Ubuntu (shard 1/2) (push) Blocked by required conditions
Frontend Unit Tests / Tests: Ubuntu (shard 2/2) (push) Blocked by required conditions
Frontend Unit Tests / Vite build verification (push) Blocked by required conditions
Sync Locize Translations & Create Translation PR / Sync Translation Keys with Locize (push) Waiting to run
Sync Locize Translations & Create Translation PR / Create Translation PR on Version Published (push) Blocked by required conditions
* feat: bind attached workspaces to conversations

* ⬆️ chore: bump agents to 3.8.8
2026-09-19 23:19:26 -04:00
Danny Avila
36efc7b4e2
🧺 fix: Bound Background Completion Batches (#16102)
* 🧺 fix: Coalesce Durable Background Wakeups

* fix: Bound replayed background result claims

* fix: Harden background result coalescing controls

* fix: Reconcile background result claims

* fix: close background batch ownership races

* fix: Keep completion batching atomic and bound serialized metadata

* refactor: Reuse canonical background claim contracts

* fix: Expose serialized claim budget in the persistence contract

* test: Preserve claimed V1 results across later background batches
2026-09-19 21:17:32 -04:00
Danny Avila
8a3ab43965
📬 fix: Persist Background Results Before Parent Rows (#16101)
* 📬 fix: Persist Background Results Before Parent Rows

* fix: Harden durable background result delivery

* fix: Fence durable background completion ownership

* fix: reconcile durable background receipt ownership

* test: align background receipt mocks with contracts

* fix: Fence durable result ownership and recover interrupted cleanup

* fix: Mark independent receipt projections for task-local ownership

* fix: Carry receipt provenance through message patch inputs

* fix: Preserve resumed receipt delivery during mutual claim yielding

* fix: Preserve conversation cleanup for non-receipt owner identities

* fix: Preserve receipt recovery across cleanup and retry exhaustion
2026-09-19 20:26:58 -04:00
GokayAI
f80f0be90e
🔑 fix: Stringify Ban Cache Keys When Redis Is Off (#16039)
Some checks are pending
Backend Unit Tests / Build packages (push) Waiting to run
Backend Unit Tests / Codegraph select (push) Waiting to run
Backend Unit Tests / TypeScript type checks (push) Blocked by required conditions
Backend Unit Tests / Circular dependency checks (push) Waiting to run
Backend Unit Tests / Tests: api (shard 1/3) (push) Blocked by required conditions
Backend Unit Tests / Tests: api (shard 2/3) (push) Blocked by required conditions
Backend Unit Tests / Tests: api (shard 3/3) (push) Blocked by required conditions
Backend Unit Tests / Tests: data-provider (push) Blocked by required conditions
Backend Unit Tests / Tests: data-schemas (push) Blocked by required conditions
Backend Unit Tests / Tests: @librechat/api (shard 1/4) (push) Blocked by required conditions
Backend Unit Tests / Tests: @librechat/api (shard 2/4) (push) Blocked by required conditions
Backend Unit Tests / Tests: @librechat/api (shard 3/4) (push) Blocked by required conditions
Backend Unit Tests / Tests: @librechat/api (shard 4/4) (push) Blocked by required conditions
Codegraph E2E Votes / vote (full suite) (push) Waiting to run
Docker Dev Branch Images Build / publish (push) Waiting to run
* 🔑 fix: Stringify Ban Cache Keys When Redis Is Off

Keyv/Mongo throws when checkBan passes a raw ObjectId as the cache key
with Redis disabled, which 500s every social OAuth login.

Fixes #16025

Signed-off-by: GokayAI <60583610+gokay-ai@users.noreply.github.com>

* 🔑 fix: Stringify Violation Log Keys and Cover Bans With Real Keyv

logViolation keyed its violation and ban logs by the raw
`req.user.id ?? req.user._id`, the same shape checkBan used, so a lean
user document would hit the same keyv 5.6 `key.startsWith` TypeError on
the namespaced violation stores and record its ban under an ObjectId.

The new spec drives checkBan and logViolation through real namespaced
Keyv instances (Mongo-backed ban store, in-memory violation logs) with
an ObjectId-only OAuth user: an unbanned user passes, and a ban logged
from one address is enforced for the same user from another.

* 🎯 refactor: Stringify Only the ObjectId Fallback for Ban Keys

The id is converted once, where a non-string can enter: the lean
document's `_id` fallback. `req.user.id` is already a string on every
path that sets it (the JWT strategies, Mongoose's `id` virtual, the 2FA
limiter's temp-token id), and the email lookup already stringifies, so
`getBanCacheKey` and that line go back to their dev form.

---------

Signed-off-by: GokayAI <60583610+gokay-ai@users.noreply.github.com>
Co-authored-by: Danny Avila <danny@librechat.ai>
2026-09-19 15:52:06 -04:00
Danny Avila
aacf1de9da
🗂️ fix: Keep a Running Attachment Chat in the Sidebar (#16104)
* 🗂️ fix: Keep a Running Attachment Chat in the Sidebar

Since #15694, a turn with model-bound attachments defers its user-message
write until the model admits the payload. That write was also what created
a new conversation's row, so for the whole first model call, which with a
long generated script or extended thinking can run for minutes, the
conversation did not exist. Any conversation-list refetch in that window
(starting another chat, deleting one, reloading) dropped the running chat
from the sidebar until its run finished, and GET /api/convos/:id answered
404 for it.

When attachments are the only reason to defer, the new conversation's row
is now written as the run starts, carrying the same fields the message
write would set but no message. The message itself stays deferred until
admission, and its write waits for a seed still in flight so the two
upserts never race. A content policy still holds back every write, the
row included, as #14425 intended.

The conversation half of saveMessageToDatabase moves into
saveConversationToDatabase so the seed and the message write share one
path.

* 🧱 refactor: Own Turn Conversation Writes in packages/api

The conversation half of a turn's writes (the row a message save
upserts, the retention context it stamps, and the new seed ahead of a
deferred first message) moves into `conversations/save.ts`, which takes
`getConvo`/`saveConvo` from the caller. BaseClient keeps only the
wiring: the retention lookup that must stay synchronous for Stop, the
message save, and the calls into the module.

The seed passes an empty `appendMessageIds`, which tells `saveConvo`
the row holds no messages yet, so it no longer reads the message list
before the upsert. It also resolves the conversation once and leaves it
on the request, so the deferred message save reuses it instead of
looking the conversation up again.

save.spec.ts drives the real data-schemas methods against an in-memory
MongoDB: the seed creates an empty row without reading messages, the
message save appends to it without a second lookup, an existing chat and
a subagent thread are left alone, a temporary chat keeps its retention,
and a failed lookup settles instead of rejecting.
2026-09-19 15:51:02 -04:00
Danny Avila
13c74c9574
⛽ feat: Negotiate Background Command Timeouts (#16100)
* ⏳ feat: Negotiate BYOM Background Command Timeouts

* ⏱️ fix: Preserve Foreground Programmatic Timeout
2026-09-19 15:01:41 -04:00
lia-by-librechat[bot]
1080f90bed
🎱 fix: Stop Sealing a Code Environment Decision a Chat Never Made (#16056)
* fix: Stop Sealing a Code Environment Decision a Chat Never Made

Switching an existing chat to a coding agent left the composer unable to
send. The chat had no workspace to select, Send stayed disabled, and the
workspace chip was a read-only status with a recovery hint.

Both layers treated "no decision recorded" as "decided to run without an
attached environment". `readPersistedDecision` documented that a stored
conversation always carries a decision and inferred `without_attached`
whenever `codeEnvironmentMode` and `codeWorkspaces` were both absent,
which is the ordinary state of a chat whose turns never involved a
code-capable agent. `resolveConversationCodeEnvironmentDecision` then
sealed that inference, so the first workspace its owner picked came back
as `locked`. The client mirrored the same premise: `locked` was any saved
chat, so `useCodeWorkspace` withheld agent defaults, a remembered
selection, and a sole workspace, and `CodeWorkspaceMenu` rendered its
non-interactive locked branch.

Only a recorded decision is sealed now. A conversation holding neither
field is undecided, so its first coding turn establishes the decision,
and `resolvePersistableCodeEnvironmentDecision` records that decision
with its selections; writing the mode alone would leave `attached`
without the selections the next turn validates. On the client the same
predicate drives `locked`, and the selection defaults that already
applied to a new chat now apply to any chat that has not decided.

An explicit `without_attached` stays sealed, a legacy row still infers
`attached` from the selections it stores, and a sealed decision is still
replaced only by its owner's move.

* fix: Record the first code environment decision on an existing chat

A saved chat that holds no decision may record the one a run establishes,
but every caller persists through `saveConvo`, which carries those fields
only in `$setOnInsert`. On a row that already exists the write was dropped,
so the choice never survived a reload and a later turn could resolve a
different workspace.

`saveConvo` now fills a whole decision onto a row that holds none, by
compare-and-set on that absence: a writer that decided first keeps its
decision, a chat that already holds one is untouched, and bare selections
never seed a row.

* fix: Record the decision a failed turn of a saved chat ran under

`saveErrorTurn` built its conversation fields only when it was seeding a new
row, so an existing chat kept the stored error turn without the decision that
turn ran under: a retry could then pick a different workspace than the failure
already recorded. The validated decision now travels on both branches, where
the conditional write in `saveConvo` keeps it from replacing a stored one.

* refactor: Resolve the error turn's decision fields in `packages/api`

The error-turn save derived its own decision fields, putting persistence
policy in a CJS controller where `/api` is meant to hold wiring only. It now
calls `resolvePersistableCodeEnvironmentDecision`, the resolver the streaming
saves already use, so one rule decides what a turn may record: a chat that
holds a decision keeps it and receives no decision fields at all.

* fix: Keep the legacy code environment lock until the protocol is advertised

The composer unlocked a saved chat that holds no decision without consulting
`codeEnvironmentDecisionVersion`, so during the rollout window it could attach
an agent default and submit it to a replica that still reads a field-less row
as a sealed `without_attached` and rejects the turn as `locked`.

The unlock now waits for the deployment to advertise the protocol, which makes
the hook identical to its previous behavior while the flag is unset. Nothing is
lost by waiting: the unmade decision is only reported once that flag is on.

---------

Co-authored-by: Lia <lia@librechat.ai>
2026-09-19 13:13:24 -04:00
lia-by-librechat[bot]
9acf9f0ac8
🫗 fix: Roll Back Incomplete Skill Archive Imports (#16052)
* 🫗 fix: Roll Back Incomplete Skill Archive Imports

A .zip or .skill import created the skill first and persisted its bundled
files one by one, keeping the skill and answering 201 when a file failed
validation, a size limit, storage, or its database row. The client never
read the internal `_importSummary`, so it showed "Skill created" and
navigated to a skill that silently lacked the resources SKILL.md names.

Import is now atomic: any failed bundled file rolls back the skill, its
file rows, the ACL grant, and the blobs already written to storage, and
the request answers 422 `skill_import_incomplete` with the failed paths
and reasons. The upload dialog stays open and lists them.

* fix: Localize Import Failure Reasons and Report Every Lost File

Addresses the first review round on the archive import rollback.

Failure reasons are now stable codes (`invalid_path`, `file_too_large`,
`archive_too_large`, `archive_entry_changed`, `persistence_failed`) that
the client localizes, so a non-English locale no longer sees English text
and storage or driver messages stay in the server log.

The decompression budget stops the scan mid-archive, and the entries it
never reached were missing from the response, telling the user they had
seen the whole failure set. Those paths are now reported too.

Rollback deletes stored blobs only once `deleteSkill` confirms the skill
is gone; otherwise the blobs stay and the request answers 500
`skill_import_rollback_failed`, because a surviving skill pointing at
deleted files is worse than unreferenced storage.

The failure list scrolls instead of overflowing the dialog, and a
response that resolves after the dialog was dismissed no longer
repopulates it for the next session.

* fix: Ignore Late Skill Import Successes

* fix: Make Skill Import Rollback Retryable

* fix: Propagate Incomplete Skill Cleanup

* fix: Settle Rollback Blob Cleanup

* test: Type Partial Cleanup Fixture

* fix: Preserve Settled Skill Cleanup Steps

* fix: Export Skill Cleanup Step Type

* fix: Reconcile Partially Deleted Skills

* fix: Reconcile Skill Rollback Caches

* style: format cleanup reconciliation changes

* fix: complete skill rollback cleanup

* chore: leave generated locale catalogs unchanged

* fix: preserve synced skill blob cleanup

* test: type synced blob cleanup mock

* fix: Validate Archive Paths and Bound Rollback Cleanup

---------

Co-authored-by: Lia <lia@librechat.ai>
Co-authored-by: Danny Avila <danny@librechat.ai>
2026-09-19 12:41:30 -04:00
Danny Avila
c0affede00
🎟️ fix: Preserve BYOM Tool Calls Through Capacity Windows (#16060)
* ⏳ fix: Keep BYOM tools queued across capacity windows

* ⏳ fix: Configure the admission budget and refresh queued credentials

Addresses the Codex review on #16060:

- Add `limits.maxQueueWaitMs` to the code environment config schema so a
  deployment can shorten or disable the five-minute admission budget from
  `librechat.yaml`; omission keeps the merged behavior, `0` surfaces the
  first capacity expiry to the model. Resolved through
  `resolveAttachedWorkspaceQueueWaitMs` and passed by ToolService, matching
  how `maxCommandTimeoutMs` already flows.
- Accept an auth-header supplier in `executeWorkspaceTool` and mint it per
  admission attempt, so a call queued past the Code API token TTL presents
  fresh credentials instead of failing permanently with 401. The attached
  Bash tool and the workspace file operations now pass suppliers.
- Recheck the deadline after a clamped wait and throw the saved rejection
  rather than opening an admission window that could still be admitted
  once the budget is spent.

* fix: Complete workspace admission wiring and caller regressions

* fix: Share protected edit retry budgets and schema limits

---------

Co-authored-by: Lia <lia@librechat.ai>
2026-09-19 09:03:06 -04:00
lia-by-librechat[bot]
94fed5bcd5
🥡 fix: Delete Storage and Embeddings With Owned Agent Files (#16007)
Some checks are pending
Backend Unit Tests / Build packages (push) Waiting to run
Backend Unit Tests / Codegraph select (push) Waiting to run
Backend Unit Tests / TypeScript type checks (push) Blocked by required conditions
Backend Unit Tests / Circular dependency checks (push) Waiting to run
Backend Unit Tests / Tests: api (shard 1/3) (push) Blocked by required conditions
Backend Unit Tests / Tests: api (shard 2/3) (push) Blocked by required conditions
Backend Unit Tests / Tests: api (shard 3/3) (push) Blocked by required conditions
Backend Unit Tests / Tests: data-provider (push) Blocked by required conditions
Backend Unit Tests / Tests: data-schemas (push) Blocked by required conditions
Backend Unit Tests / Tests: @librechat/api (shard 1/4) (push) Blocked by required conditions
Backend Unit Tests / Tests: @librechat/api (shard 2/4) (push) Blocked by required conditions
Backend Unit Tests / Tests: @librechat/api (shard 3/4) (push) Blocked by required conditions
Backend Unit Tests / Tests: @librechat/api (shard 4/4) (push) Blocked by required conditions
Codegraph E2E Votes / vote (full suite) (push) Waiting to run
Docker Dev Branch Images Build / publish (push) Waiting to run
The agent tool-resource branch of DELETE /files removed a file's association
from the agent and answered 200 without reaching processDeleteRequest, so the
bytes on disk and the RAG chunks of a file the caller owned survived the delete.
A replaced File Search document kept answering from its old chunks (#15930).

An attached file now goes through the full delete pass, but only when nothing
else holds it: a file the caller does not own, and a file any other
(agent, tool_resource) pair still references, are unlinked and left whole.
Nothing is unlinked until the destroy it depends on has succeeded.

- packages/api/src/files/deletion.ts: deleteAgentResourceFiles owns the
  operation with its db methods and delete pass injected.
- packages/data-schemas: getSharedResourceFileIds answers the last-reference
  question, excluding the pair being removed by the agent's _id.
- Local/crud.js: unlinkFile propagates non-ENOENT, so a file whose bytes
  survive is no longer reported as deleted.

Co-authored-by: Mohammed Alshyakh <mohmedmm@users.noreply.github.com>
2026-09-17 02:59:25 +00:00
Artyom Bogachenko
12d78909d3
👛 fix: Drop Unread Credentials From MCP Domain Validation (#16035)
Some checks failed
Docker Dev Images Build / publish (push) Has been cancelled
Sync Helm Chart Tags / Ignore non-main push (push) Has been cancelled
Sync Helm Chart Tags / Sync chart tags (push) Has been cancelled
* fix: Resolve live OpenID bearer before the MCP early domain gate

* fix: Drop unread credentials from the MCP early domain gate

The early domain gate resolves the whole server config through
`processMCPEnv`, but decides from the URL alone. A credential placeholder in
any other field therefore raised `OpenIDReauthRequiredError` from a stale
request-time OpenID snapshot, before the connection path could refresh that
bearer, and the tool was dropped from the agent's toolset.

`buildMCPDomainValidationConfig` narrows the config to what the decision reads,
so the gate needs no live credential. A URL placeholder still fails closed, and
the argument is never mutated, so direct-bearer recovery keeps the placeholder
it knows how to refresh.

Replaces the per-tool `upstreamTokenProvider` call the gate would otherwise
make (1 + N per request per server) and covers every credential-bearing field,
not only `Authorization`.

Co-authored-by: Artyom Bogachenko <SpectralOne@users.noreply.github.com>

---------

Co-authored-by: Lia <lia@librechat.ai>
Co-authored-by: Artyom Bogachenko <SpectralOne@users.noreply.github.com>
2026-09-16 22:13:49 -04:00
lia-by-librechat[bot]
2452f499a8
🗼 fix: Serialize MCP OAuth Token Refresh Across Replicas (#15993)
Some checks failed
Backend Unit Tests / Build packages (push) Waiting to run
Backend Unit Tests / Codegraph select (push) Waiting to run
Backend Unit Tests / TypeScript type checks (push) Blocked by required conditions
Backend Unit Tests / Circular dependency checks (push) Waiting to run
Backend Unit Tests / Tests: api (shard 1/3) (push) Blocked by required conditions
Backend Unit Tests / Tests: api (shard 2/3) (push) Blocked by required conditions
Backend Unit Tests / Tests: api (shard 3/3) (push) Blocked by required conditions
Backend Unit Tests / Tests: data-provider (push) Blocked by required conditions
Backend Unit Tests / Tests: data-schemas (push) Blocked by required conditions
Backend Unit Tests / Tests: @librechat/api (shard 1/4) (push) Blocked by required conditions
Backend Unit Tests / Tests: @librechat/api (shard 2/4) (push) Blocked by required conditions
Backend Unit Tests / Tests: @librechat/api (shard 3/4) (push) Blocked by required conditions
Backend Unit Tests / Tests: @librechat/api (shard 4/4) (push) Blocked by required conditions
Codegraph E2E Votes / vote (full suite) (push) Waiting to run
Docker Dev Branch Images Build / publish (push) Waiting to run
Docker Dev Images Build / publish (push) Waiting to run
Sync Helm Chart Tags / Ignore non-main push (push) Waiting to run
Sync Helm Chart Tags / Sync chart tags (push) Waiting to run
Frontend Unit Tests / Client build recovery regression (push) Has been cancelled
Frontend Unit Tests / Codegraph select (push) Has been cancelled
Frontend Unit Tests / Build packages (push) Has been cancelled
Sync Locize Translations & Create Translation PR / Sync Translation Keys with Locize (push) Has been cancelled
Frontend Unit Tests / TypeScript type checks (client) (push) Has been cancelled
Frontend Unit Tests / Tests: @librechat/client (push) Has been cancelled
Frontend Unit Tests / Tests: Ubuntu (shard 1/2) (push) Has been cancelled
Frontend Unit Tests / Tests: Ubuntu (shard 2/2) (push) Has been cancelled
Frontend Unit Tests / Vite build verification (push) Has been cancelled
Sync Locize Translations & Create Translation PR / Create Translation PR on Version Published (push) Has been cancelled
* fix: Serialize MCP OAuth token refresh across replicas

`MCPTokenStorage.inflightRefreshes` coalesces refresh-token redemptions
inside one Node process. Behind a load balancer without session affinity,
one user's concurrent requests land on different replicas, each reads the
same not-yet-rotated refresh token and redeems it. RFC 9700 servers treat
the second redemption as replay and revoke the whole grant family, so the
user is asked to authorize the MCP server again.

`forceRefreshTokens` now takes a cross-replica refresh flight before
redeeming, using the same `FlowStateManager.acquireLease` primitive the
OAuth teardown fence uses under a distinct key. A replica that waited for
the flight adopts the tokens the holder rotated instead of redeeming
again; when the flight is still held after the wait window it falls back
to the unfenced redemption every earlier release performed.

* fix: Redeem unfenced when the refresh flight lease store fails

* fix: Fence MCP refresh waiters instead of redeeming unfenced

A waiter that could not take the cross-replica refresh flight fell through to
an unfenced redemption after 10s, while the holder's own stale abort does not
fire until 60s. A refresh taking 11 to 60 seconds therefore still let two
replicas redeem one refresh token, the replay this fence exists to prevent.

The waiter now polls until it either adopts the tokens the holder rotated or
acquires the flight, and fails as MCPTokenRefreshUnavailableError rather than
redeeming beside a live holder. `getTokens` callers defer connection recovery
on that error, and the stored credential is left intact for a later attempt.

The flight is keyed by the stored credential (tenant, user, server name)
rather than the caller's OAuth binding digest, so a rolling config change
cannot hand two replicas different locks over one stored token. The wait is
an operator lever, `oauthRefreshWaitTimeout`, clamped to half the stale
window. An adoption read that fails no longer gives up the held flight.

* fix: Annotate derived refresh-flight constants for isolatedDeclarations

* fix: Recapture the credential generation a peer published on adoption

* fix: Hold the MCP refresh flight until redemption settles

Four corrections to the cross-replica refresh flight.

The flight lease equalled the window that aborts a stalled redemption, on
the claim that an expired flight could never belong to a redemption still
able to reach the token endpoint. Aborting proves no such thing: the
request may have been processed with its response lost, and a stalled
event loop can delay the abort past its own deadline. The lease now
outlives the abort, so a peer cannot redeem a credential the provider has
already rotated. A live replica still releases on settle, so the margin is
paid only by one that died holding the flight.

The credential snapshot was taken after the first failed acquisition, so a
holder that stored and released in that gap was snapshotted post-rotation:
the next attempt saw an unchanged record and redeemed the credential it
should have adopted. It is taken before the first attempt now.

`oauthRefreshWaitTimeout` accepted zero while the runtime mapped every
non-positive value to the default, so the config validated and then
behaved contrary to its value. Zero is rejected at load.

Adoption announced a second credential change through
`handleOAuthRefreshSuccess`, whose `onOAuthCredentialsChanged` advances
authorization state after persistence this replica did not perform. That
retired the generation recaptured beside it and fenced the build against
its own tool publication. Adoption now updates the local token-flow cache
and recaptures, without announcing.

* fix: Check every held MCP refresh flight for a peer's rotation

Four corrections, two of them consequences of moving the credential
observation ahead of the first lease attempt.

That move created a storage read inside `beginRefreshFlight`, and its
failure reached a handler written for a lease-store outage, so a transient
read error became an unfenced redemption beside a live peer. The flight
now handles its own reads: losing the observation costs adoption and
nothing else, and only the lease store failing may redeem unfenced.

The observation was also never compared when the first acquisition
succeeded. A peer that rotated and released before this replica contended
left an acquisition that looked uncontended, and its fresh credential was
redeemed a second time. Every acquisition now runs one rotation check,
which also collapses two code paths into one.

`getTokens` already loads the refresh record to decide a refresh is
needed, so it is passed on as the observation baseline instead of read
again, and the read taken under the flight is reused as the credential
redeemed. Two reads on a latency-counted path where there were three.

`runSilentRefresh` collapsed contention into null, sending the 401 path to
interactive OAuth, so a slow peer prompted the user to authorize a server
whose credential was about to be valid. The retryable outcome now travels
through the silent-refresh layers and the connection defers, matched by
name as well as identity because these errors cross the package boundary.

* chore: Regenerate the Agents OpenAPI spec for repositoryInstructions

The drift check added by #15928 fails on dev: #16008 added
`repositoryInstructions` to the agent schema without regenerating the
committed spec, so every branch merging dev inherits the failure. This is
the remedy the check itself prescribes and carries no hand-written change.
Drop this commit if dev regenerates first.

* fix: preserve MCP refresh outcomes across replica boundaries

* fix: keep MCP adoption fenced through publication

* fix: anchor MCP refresh adoption to rejected credentials

* fix: Complete OAuth Adoption Adapters and Isolate Legacy Flow Readers

* fix: Preserve OAuth Request Identity Through Recovery and Discovery

* fix: Fence OAuth Adoption Against All Credential Writers

* fix: Gate Coordinated OAuth Rollout and Preserve Unauthenticated Identity

* fix: Preserve OAuth Coalescing Across the Staged Rollout

* style: Sort OAuth Timeout Constant Import

* fix: Invalidate Both OAuth Token Flow Protocols on Rotation

* test: Complete the Rollback Token Flow Fixture

---------

Co-authored-by: Lia <lia@librechat.ai>
Co-authored-by: Danny Avila <danny@librechat.ai>
2026-09-16 21:58:23 -04:00
Marco Beretta
9633edcb88
🗣️ fix: Keep Provider Error Text on Unclassified Agent Failures (#16034)
* 🗣️ fix: Keep Provider Error Text on Unclassified Agent Failures

An upstream failure LangChain does not classify discarded the provider's own
message and answered with the generic upstream sentence plus a status, so a
gateway or privacy-proxy rejection lost the only account of what happened.

The provider text now rides along in the persisted payload as `message`,
withheld only where a content policy inspects the traffic — the same condition
`getUserFacingProviderError` and `getUserFacingRequestError` already decide by.

* fix: Harden Provider Error Detail Retention

---------

Co-authored-by: Danny Avila <danny@librechat.ai>
2026-09-16 21:32:41 -04:00
lia-by-librechat[bot]
9e83b10545
📭 fix: Deliver Attachment Text Until a File Tool Holds It (#16027)
* 📭 fix: Deliver Attachment Text Until a File Tool Holds It

A `none`-routed upload had its extracted text withheld whenever a file tool was
enabled, on the assumption the tool would serve the file. A plain chat with the
File Search toggle runs an ephemeral agent, so the upload is filed under no tool
resource and never embedded: the text was withheld for a vector store that never
received the file, and the attachment reached nothing.

Withholding now requires the record to show the tool holds the file, which is the
same evidence deferred provisioning reads before queueing it. `resources.ts`
delegates to that shared predicate so the two cannot disagree again.

* test: Give the Code-Running Primary Agent a Sandbox Copy

---------

Co-authored-by: Lia <lia@librechat.ai>
2026-09-16 15:46:35 -04:00
Dustin Healy
44af4d3789
📖 fix: Verify Agents OpenAPI contracts and disable external reporting (#16028) 2026-09-16 15:17:56 -04:00
Atef Bellaaj
69f0dd2a12
🔌 feat: OpenAPI spec and docs for the public Agents API (#15928)
Some checks are pending
Backend Unit Tests / Build packages (push) Waiting to run
Backend Unit Tests / Codegraph select (push) Waiting to run
Backend Unit Tests / TypeScript type checks (push) Blocked by required conditions
Backend Unit Tests / Circular dependency checks (push) Waiting to run
Backend Unit Tests / Tests: api (shard 1/3) (push) Blocked by required conditions
Backend Unit Tests / Tests: api (shard 2/3) (push) Blocked by required conditions
Backend Unit Tests / Tests: api (shard 3/3) (push) Blocked by required conditions
Backend Unit Tests / Tests: data-provider (push) Blocked by required conditions
Backend Unit Tests / Tests: data-schemas (push) Blocked by required conditions
Backend Unit Tests / Tests: @librechat/api (shard 1/4) (push) Blocked by required conditions
Backend Unit Tests / Tests: @librechat/api (shard 2/4) (push) Blocked by required conditions
Backend Unit Tests / Tests: @librechat/api (shard 3/4) (push) Blocked by required conditions
Backend Unit Tests / Tests: @librechat/api (shard 4/4) (push) Blocked by required conditions
Codegraph E2E Votes / vote (full suite) (push) Waiting to run
Docker Dev Branch Images Build / publish (push) Waiting to run
Frontend Unit Tests / Client build recovery regression (push) Waiting to run
Frontend Unit Tests / Codegraph select (push) Waiting to run
Frontend Unit Tests / Build packages (push) Waiting to run
Frontend Unit Tests / TypeScript type checks (client) (push) Blocked by required conditions
Frontend Unit Tests / Tests: @librechat/client (push) Blocked by required conditions
Frontend Unit Tests / Tests: Ubuntu (shard 1/2) (push) Blocked by required conditions
Frontend Unit Tests / Tests: Ubuntu (shard 2/2) (push) Blocked by required conditions
Frontend Unit Tests / Vite build verification (push) Blocked by required conditions
* 🔌 feat: OpenAPI spec and docs for the public Agents API

* 🔧 fix: address review on Agents API OpenAPI spec and docs:

- adapter: mark JSON request bodies as required
- openapi.js: move gate, config read and spec serving into packages/api
  as an injected router factory; leave /api as wiring only
- docs: compute URLs in-browser and use a relative servers url so docs
  work under a base path (e.g. /chat)
- build: copy the generated spec into dist so the multi-stage image ships it
- agents: reuse the enforced list envelope for the docs so the AgentList
  schema cannot drift from the runtime cursor and strictness

* 🔧 fix: align Agents API OpenAPI contract with enforced runtime

Second review round on the public Agents API spec. Three cases where the
published contract described something the server does not do, so generated
clients would fail against the live API:

- Upload form: document the `purpose` field (enum: file_search, execute_code,
  context) that POST /agents/{id}/files actually requires, instead of the
  internal-only `tool_resource`; requests following the old form were rejected
  with 400 because `purpose` was absent.
- Auth: drop the `apiKeyBearer` scheme from the management and skill endpoints.
  They gate on OIDC/M2M via requireAgentManagementAuth and deliberately reject
  the API-key fallback; the API key belongs to the out-of-scope
  OpenAI-compatible endpoints and returns when those are documented.
- Skill update: document the 409 conflict PATCH /skills/{id} returns on a stale
  expectedVersion. The agent update path collapses its internal 409 to 400, so
  it correctly keeps no 409.

* 🔧 fix: serve docs on experimental server and document the 401

Third review round on the public Agents API spec.

- Experimental server: mount routes.openapi in api/server/experimental.js before its /api 404 handler. Without it, npm run backend:experimental returns 404 for /api/docs and /api/openapi.json even when openapi.enabled is true, because that server never mounted the router.
- Auth failure: document the 401 that requireAgentManagementAuth returns on a missing, expired, malformed, or unbound token. Its body is { "error": "Unauthorized" }, a flatter shape than the management error schema, so add a dedicated UnauthorizedError schema and a shared 401 response to the agent and skill contracts rather than reusing the standard error schema.

* 🔧 fix: document skill-update, auth-conflict, upload-limit, and watch-copy gaps

* 🔧 fix: added error shapes for permission denied and internal server errors in API responses docs

* fix: cover the auth-layer 500 shape and pin the account-deletion code

* fix: update OpenApiRouterDeps documentation and simplify request handling in isEnabled function

* 🔧 fix: gate the Swagger asset mount behind the OpenAPI toggle

* 🔧 fix: accept the malformed-JSON 400 envelope in the contract

* fix: accept the tenant-isolation 403 envelope in the contract

* fix: add description for content property in SkillFileUpdateRequest to clarify byte limit
2026-09-16 13:50:05 -04:00
Danny Avila
299dbc6075
📖 Load Repository Instructions for Attached Workspaces (#16008)
* Load authorized workspace repository instructions into agent context

* Unify repository instruction loading across agent ingresses

* Await cancellation regression assertion directly

* Annotate the shared instruction loader for declaration builds

* Expose repository read budget and inject the host-owned cache
2026-09-16 09:00:35 -04:00
lia-by-librechat[bot]
be54587d14
🪒 fix: Strip Cache-Bust Suffixes From Every Local File Read (#15991)
* 🧼 fix: Strip Cache-Bust Query Before Local Vision Encode

Reused code-interpreter images persist filepath with a ?v= suffix.
prepareImagesLocal now strips it before disk encode, matching crud/share.

Co-authored-by: Zsanz3 <Zsanz3@users.noreply.github.com>

* 🧪 test: Isolate prepareImagesLocal query-strip coverage

Mock sharp and resize so the local vision-encode test does not load
the rest of the file-strategy graph.

Co-authored-by: Zsanz3 <Zsanz3@users.noreply.github.com>

* 🪒 fix: Strip Cache-Bust Suffixes From Every Local File Read

Reused code-interpreter outputs persist a `?v=<timestamp>` suffix on the file
document's filepath, and local storage resolves that field into a filesystem path.
prepareImagesLocal already handled it after the cherry-picked commits; getLocalFileStream
did not, so every download-stream consumer (the download route, provisioning, agent and
skill file reads) still hit ENOENT for a regenerated image.

Move the strip into one documented helper and call it from all three local read paths.

* 🧱 refactor: Move Cache-Bust Stripping Into the Storage Package

`/api` holds wiring, not behavior, so `stripCacheBust` moves out of a new CJS helper and
into `packages/api/src/storage/path.ts`, beside `resolveDownloadPath` — the function that
already decides what a stored filepath means to a download. Its doc comment now states why
the two differ: a remote strategy's query string can carry a presigned signature, so only
the local paths may strip.

The local storage modules keep just the call into it. Semantics are covered by the storage
package's own test; the `/api` specs pin the wiring.

Addresses the Codex P1 finding on 5f8dbf3cf.

---------

Co-authored-by: Cursor Agent <cursoragent@cursor.com>
Co-authored-by: Zsanz3 <Zsanz3@users.noreply.github.com>
Co-authored-by: Lia <lia@librechat.ai>
2026-09-16 08:28:32 -04:00
Danny Avila
4d08bcf203
⛓️ fix: Bind Programmatic Bash to Selected Workspaces (#15992)
* fix: Enable programmatic Bash in selected attached workspaces

* Centralize project PTC construction and preserve recognized capabilities

* Prevent stale list refreshes from restoring removed pins
2026-09-16 07:46:16 -04:00
lia-by-librechat[bot]
35d5a70b21
🧦 fix: Restore OpenID Refresh After the Session Store TTL Expires (#15983)
* 🧦 fix: Restore OpenID Refresh After the Session Store TTL Expires

express-session raises `failed to load session` only when the store holds no
record for the session id. #15655 treated that as terminal, so a refresh whose
cookie refresh token was still valid ended in 401 OPENID_SESSION_MISSING once
the OpenID session store TTL (15 minutes by default) elapsed before the IdP
access token (~1 hour with Entra ID).

Reload the persisted record through one tolerant helper: an absent record is an
empty session, not a session that advanced past this result, so publication
seeds a new record. Store outages still propagate, and logout still fails a
retired refresh token through its durable revoked publication flight.

* 🧪 test: Pin the logout fence around the tolerated session reload

Tolerating an absent session record leaves the durable revoked publication
flight as the only thing between a logged-out refresh token and a resurrected
session, so cover both of its checks with an expired record: the tombstone read
that precedes the reload, and the completion that follows it.

Drop a needless optional chain in publishResolvedSessionTokens, whose `req`
parameter is not optional.

---------

Co-authored-by: Lia <lia@librechat.ai>
2026-09-15 23:54:42 -04:00
Danny Avila
ed95a9b802
🍯 fix: Stop Approval Pauses From Unsealing Code Environments (#15963)
* fix: Preserve Code Environments Across Approval Pauses 🧷

* test: Match Agent Request Conversation Identity 🪪
2026-09-15 12:30:37 -04:00
Danny Avila
21a9edbe74
🪪 feat: Pass Schedule Identity to MCP Token Providers (#15962)
* feat: carry schedule context into MCP token providers

* fix: restore scheduled token context after approval pauses

* fix: make scheduled identity boundaries explicit

* test: keep owner-drain leases live through CI delays
2026-09-15 10:46:13 -04:00
Danny Avila
dea7346d72
🧷 feat: Carry Ask User Answers Past Compaction (#15944)
* 🧷 feat: Carry Ask User Answers Past Compaction

The user's answers to `ask_user_question` lived only in the tool result that
received them. A checkpoint summary, the tool-output pruner or a full context
window could remove that message, and the agent then asked again or acted on
a summary's paraphrase.

Every answered ask on the conversation branch is now rendered verbatim into
the run's dynamic instructions, on the first request and on every resume,
where the answer just given is read from the seeded content. Older answers
drop first past a token budget; the newest set is always kept.

New lever: `endpoints.agents.askUserQuestion.retainedAnswers` (`enabled`,
`maxTokens`), on by default with a 4096-token budget.

* 🧷 feat: Carry Ask User Answers Past Compaction

The user's answers to `ask_user_question` lived only in the tool result that
received them. A checkpoint summary, the tool-output pruner or a full context
window could remove that message, and the agent then asked again or acted on
a summary's paraphrase.

Every answered ask on the conversation branch is now quoted verbatim at the
top of the current user turn's prompt copy, in the user's own role: rebuilt
from the stored rows every turn, never persisted, excluded from the memory
copy, and counted in the prompt total with the active encoding. A warm
event-actor turn reads the branch on demand. Older answers drop first past a
token budget that includes separators; the newest set is always kept.

New lever: `endpoints.agents.askUserQuestion.retainedAnswers` (`enabled`,
`maxTokens`), on by default with a 4096-token budget.

* 🧷 refactor: Read The Warm Branch Inside The Module

The warm event-actor read lived as a conditional and a `getMessages` call in
the CJS client. The typed module now takes `historyLoaded`, the identity and
the query as dependencies, decides when to read, and owns the failure policy
for both the read and the block itself; the client passes plumbing only.

* 🧷 fix: Complete The Branch Behind A Summary Cut

`loadHistory` already stops its walk at a checkpoint summary, so the rows
`buildMessages` receives never held the answers this feature carries. The
module now detects a branch that stops short of its root, whatever cut it,
and completes it through the injected stored-row query, stored rows winning.

The block goes on the latest user-authored row so a continued generation
keeps it, and the render measures the whole block before reserving the
omission note, so a set is only dropped when something truly has to go.

* 🧷 fix: Reuse Loaded History And Read Every Ask Stamp

A post-compaction turn read the conversation twice: once in `loadHistory`,
which cuts at the checkpoint summary, and again in the module to complete
the branch. The loader now keeps the rows it read and the module prefers
them, querying only for a turn that made no history read.

Two stored shapes were missed: a pause record whose `args` is the bare
question string, now read as the legacy question, and a call whose input
failed validation, whose persisted error output is no longer quoted as an
answer.

* 🧷 fix: Keep The Block Off The Stored Row And Out Of Memory Copies

Array-form content is replaced instead of edited through the array the
stored row shares, the block's cost is measured as two fresh counts of the
same copy rather than against a possibly calibrated stored count, the
memory copy is only built when memory extraction will read it, the loaded
rows reach the agents client through a hook and are released once the block
exists, and the tool-call-id merge is gone: rows are unique by message id
and providers may reuse ids across turns.

* 🧷 refactor: Apply The Answers Block Inside The Module

The placement lookup, the prepend, the count delta and the memory-copy
decision lived in the client after the context kickoff. They now live in
`applyRetainedAnswers`, which receives the rows, the prompt copies, the
count map, the counter and the memory dependency; the client keeps one
call and passes plumbing.

* fix: Apply Retained Answers After Summary Replay 🧷

* perf: Count Retained Context Exactly Within Its Budget 🧮

* fix: Preserve Retained Counts Across Checkpoint Recounts 🧾

* fix: Isolate Retained Context Counting and Provenance 🧵

* fix: Replace Warm Retained Context and Verify Answer Provenance 🪪

* fix: Use Workspace-Compatible Array Traversal 🧭

* fix: Refresh Retained Context at the Warm Turn Boundary 🧲
2026-09-14 21:35:07 -04:00
Danny Avila
2ffee7e143
🪂 feat: Opt-In Text Fallback for Files No Tool Can Read (#15940)
* 🪂 feat: Opt-In Text Fallback for Files No Tool Can Read

An upload routed to tools (`llmDeliveryPath: none`) reaches nothing when the
agent handling the turn runs neither Run Code nor File Search, or runs one that
cannot read the type. With `fileConfig.endpoints.<endpoint>.textFallbackWithoutTools`
(also accepted at the top level and inherited from `default`), such a turn
delivers the text extracted at upload instead. The setting is off by default,
which keeps today's behavior.

- Upload: when the setting is on and an inferred `none` route finds no reading
  tool, the built-in document parser or native text reader stores the text on
  the file, best effort, under the extracted-text size cap and content policy.
- Turn: `resolveTurnLLMDeliveryPath` re-resolves each inferred route against
  the tools the agent runs, and `applyTurnTextFallback` marks copies of the
  records a turn loads, so endpoint filtering, limits, inspection, history
  replay and steer media all see the text the turn delivers. The stored route
  is never rewritten.
- Explicit destinations, records predating routing, and turns whose tools are
  unknown are left as they are.

* 🧪 test: Resolve Custom Endpoint Fallback Under the Endpoint Name

Uploads route a custom endpoint agent by its saved provider, the endpoint name. initializeAgent marks turn copies before getProviderConfig swaps the provider for the backing client, and the endpoint keeps the name afterward, so the client and child encoders resolve the opt-in under the same endpoint. Cover both the initialization path and the post-initialization agent shape.

* ♻️ refactor: Share One Extracted-Text Storage Cap Across Uploads

The fallback defined its own copy of the 15 MiB cap context uploads already apply to extracted text. Export MAX_STORED_EXTRACTED_TEXT_BYTES from files/extract and use it in both places, documenting that it bounds what a MongoDB file document can hold rather than operator policy.

* 🧭 fix: Keep Fallback Text Wherever a Later Turn Can Deliver It

Extraction skipped uploads filed under a reading tool, so a handoff agent
without that tool, or the same agent after its tools or grants changed, had
no text to fall back to. Store fallback text for every inferred route on a
message attachment; files kept on an agent's tool resources never reach a
prompt and still skip it.

Turn marking only ran while the fallback was enabled, so a stored tool-routed
record whose type the endpoint now routes to text stayed marked `none` and
`extractFileContext` skipped it. applyTurnTextDelivery (renamed from
applyTurnTextFallback) now marks any stored `none` record with text that the
turn resolves to text, and returns early when no such record is loaded.

* 🚦 fix: Admit Every Attachment by the Route Its Turn Delivers

A record upload routed to tools that the current endpoint sends to the
provider stayed marked `none` on the turn copy, so admission skipped it while
BaseClient encoded its bytes, bypassing attachment count and size limits.
applyTurnDelivery (renamed from applyTurnTextDelivery) now gives every record
whose route upload inferred the route the turn resolves, before endpoint
filtering, limits and inspection, matching the run-file encoder.
hasInferredLLMDeliveryPath shares the inferred-route rule with the resolver.

Fallback extraction selected the document parser inside the CJS upload path.
resolveUploadFallbackText now takes the upload and picks parseDocument or
parseTextNative itself, with the extractors injectable, so process.js passes
request data only. Its tests run the real parser against the xlsx fixture and
the real native reader against temporary files.

* 🎚️ fix: Read Custom Endpoint Dialect From Config on Both Sides of Init

initializeAgent materializes turn routes before getProviderConfig swaps the
saved custom endpoint name in agent.provider for its backing client, so
routing read that name as a non-OpenAI dialect. Media a custom endpoint opted
into could then be materialized off the provider path, skipping admission,
while the finalized client still sent the bytes. resolveAgentDeliveryRouting
now reads the dialect with getCustomEndpointProvider, as upload does, which
holds before and after the swap.

The upload fallback plan now keys on the chosen-destination marker the turn
resolver reads, so an upload recorded as chosen, including every legacy
chooser upload, never pays for text a turn cannot deliver.

* 🛡️ fix: Apply Turn Routes Only While the Record Stays Admitted

Resolution while initializing and at delivery can disagree: delivery reads a
Responses API choice only the finished client config holds. Applying a route
that takes a record out of admission, off the model path or to text it never
stored, would then skip the limits for a file the client still sends.
applyTurnDelivery now applies a route only while the record stays model-bound;
admitting a record the turn leaves out cannot slip past a limit.

* 🕹️ feat: Run Declared Project Actions on Attached Workers (#15943)

* feat: use declared attached project actions

* Complete named action definitions and approval previews

* Sort named environment imports

* Sort native environment fixture imports

* 🔓 fix: Keep Code Approval Mode Selectable Mid-Run (#15938)

* 🔓 fix: Keep Code Approval Mode Selectable Mid-Run

The composer's code approval mode selector was disabled while a run streamed, and a mode picked during a run was reverted when the final or abort event merged the server conversation back. The selector now stays usable in flight and both merges retain a mid-run selection, which the next send carries.

* 🔓 fix: Retain Mid-Run Approval Mode Across Cache and Recovery

Stamp the live approval mode onto the submission conversation at send so the retention baseline matches what was read, keep a retained mode in the conversation query cache on final and cancel, and rebuild failed or aborted conversations from a preset that carries the mid-run pick.

* 🔓 fix: Scope Retained Approval Mode to the Submitted Conversation

Retention now requires the live conversation to be the one the run submitted, or the id the server assigned to a new chat, so navigating elsewhere mid-run cannot write that conversation's mode back. A single recovery helper rebuilds failed or aborted conversations from the retained preset and patches the detail cache for every recovery site.

* 🔓 refactor: Keep the Local Approval Mode on Every Server Merge

Replace per-path retention with one rule: a locally picked code approval mode is newer than any server copy of the same conversation, so the final and abort merges and the error recovery preset keep it. The selector writes the pick into the conversation's detail cache, which navigation rebuilds from, so the pick is conversation-scoped without reading the index-global atom from the SSE handlers.

* 🔓 fix: Prefer the Live Conversation When Caching the Final Merge

The final handler's detail-cache merge now takes the local approval mode from the open conversation when it is the one that finished, falling back to the cached record only for a conversation that is no longer on screen.

* 🔓 fix: Keep the Local Approval Mode Through Settled-Start Reconciliation

The resumable transport's settled-start reconciliation and replacement handoff wrote a fetched conversation straight into conversation state and the detail cache. Both now apply the same local-mode rule as the event handlers, treating a new chat's pending id as the settled conversation's own.

* 🔓 fix: Seed the Detail Record When a Mode Is Picked

A conversation that has its id but no detail record yet now gets one from the live conversation when a mode is picked, the same key the resumable transport seeds optimistically, so recovery and navigation find the pick. A chat with no id yet still keeps the pick in conversation state alone.

* ⬆️ chore: bump agents to 3.8.7 (#15947)

* 🧭 refactor: Settle Turn Delivery Routing Once in Agent Initialization

`initializeAgent` resolved the provider and its client options only after the
turn's files were loaded and admitted, and the two delivery readers each rebuilt
the attachment routing from the agent object at their own moment: `BaseClient`
took the custom-endpoint dialect from the already-swapped `agent.provider`, the
run-file encoder from whatever child config it was handed.

Move `getProviderConfig`/`getOptions` ahead of file discovery, where nothing in
between fed them, and settle one `deliveryRouting` value with every input final:
the file policy under the endpoint's own name, the dialect its config declares,
the Responses API decision the model call uses, and the transcription setting.
`InitializedAgent`, the child encoder and `BaseClient` consume that value;
`resolveTurnLLMDeliveryPath` is the one place a stored route is resolved again.

* fix: Preserve attachment reachability across handoffs and late steers

* test: Type the untrusted attachment reference fixture

---------

Co-authored-by: Ravi Kumar L <upman@users.noreply.github.com>
2026-09-14 21:02:54 -04:00
Danny Avila
bc12fad6f1
🕹️ feat: Run Declared Project Actions on Attached Workers (#15943)
* feat: use declared attached project actions

* Complete named action definitions and approval previews

* Sort named environment imports

* Sort native environment fixture imports
2026-09-14 18:35:33 -04:00
Danny Avila
2f8bc3dfcd
🎞️ fix: Deliver Opted-In Custom Endpoint Media Safely (#15937)
* feat: send video/audio to custom endpoints that opt in via supportedMimeTypes

The video and audio encoders only emitted OpenAI-format parts (video_url,
input_audio) for OpenRouter, and Google's media part for Google/Vertex. For
every other provider the file was validated and then silently dropped, so a
custom OpenAI-compatible endpoint (vLLM, LiteLLM, ...) never received the
attachment even though the wire format is identical to OpenRouter's.

Emit the OpenAI-format part for OpenAI-like providers when the endpoint's
fileConfig supportedMimeTypes explicitly allows the file's type. The inherited
default list does not count as opting in (isExplicitMimeConfig, keyed on
referential identity like the client's picker), so endpoints whose gateway
cannot handle media are unaffected.

* feat: let a configured custom endpoint pick and attach video/audio

The attach menu's Upload to Provider filter and the drag-drop viability check
only opened video/audio for Google and OpenRouter, or for a custom endpoint
with a fully permissive (.*) supportedMimeTypes. Honor any admin-configured
allowlist on a custom endpoint instead, so a finite list that includes
video/.* or audio/.* is enough, matching the server-side encoders.

* fix: canonicalize input_audio format from MIME type

The `input_audio.format` value was derived from the filename extension via
`filename.split('.').pop()`, which produces values providers reject:

- `clip.wave` (audio/wave) emitted `wave`, but the accepted format is `wav`
- a file with no extension (`recording`) emitted the whole filename, since
  splitting a dotless string yields a single-element array, so the existing
  non-empty guard never fired
- `clip.mpeg` (audio/mpeg) emitted `mpeg` rather than `mp3`

All of these pass MIME validation and then fail at the provider. Derive the
format from the MIME type instead, mirroring the canonicalization already in
STTService, and fall back to the filename extension only when it is itself a
supported format. Throws when neither source yields one rather than sending an
unsupported value.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>

* fix: route opted-in custom endpoint media to the provider path

In unified upload mode an upload carries no tool resource, so its delivery path is
inferred by resolveDefaultLLMDeliveryPath. That resolver judged audio and video for any
named endpoint with isMediaSupportedProvider, which lists only Google, Vertex and
OpenRouter, so a custom endpoint that opted into media through supportedMimeTypes still
recorded video as none and audio as text, and the encoder branch was never reached.

The upload resolver already holds the endpoint's file config, so it now passes the
endpoint's supportedMimeTypes through, and an explicit match on an OpenAI-compatible or
custom endpoint counts as provider-capable, mirroring isConfiguredProviderMediaType on
the encoder side. The inherited default list is still not an opt-in, and known providers
whose encoders emit nothing for media are unchanged. BaseClient re-resolves per turn with
the same function, so the turn path follows.

* fix: scope the media opt-in to custom endpoints that run as OpenAI

The opt-in applied to the built-in openAI and azureOpenAI endpoints too, but the picker
and drag-drop only open media for custom endpoints, so that was a route the client could
not send to. It is now limited to endpoints that are not a known provider.

A custom endpoint may also declare provider: anthropic, in which case initialization runs
it as Anthropic and the encoders emit no media part for it. getCustomEndpointProvider
reads that declaration off the app config, the upload callers pass it as endpointProvider,
the agent encoder and BaseClient pass the agent's resolved provider, and an endpoint known
to run as something other than OpenAI keeps its previous route: video stays off the model
path and audio still reaches transcription.

* fix: reject unsupported provider audio during upload

---------

Co-authored-by: Renato Garita Figueiredo <renato.garitafigueiredo@uni-osnabrueck.de>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-09-14 16:38:51 -04:00
Danny Avila
b1f6f6df2f
👯 fix: Reject Duplicate Tool Approval Identities (#15933)
* fix: Reject aliased tool approval identities

* fix: Keep approval validation in TypeScript

* style: Format approval validation
2026-09-14 15:08:26 -04:00
Marco Beretta
f077e8c967
🗯️ fix: Give Failed Turns Actionable Guidance (#15896)
* 🧯 refactor: State Failed Turns in Copy a Reader Can Act On

Every client-facing error code now has authored copy, so no failed turn renders
raw JSON, an unresolved `com_error_*` key, or a provider message cut at 512
characters. `client/src/components/Messages/Content/Error.tsx` becomes a module
directory: a dispatcher resolving `json.code ?? json.type`, a registry splitting
one-sentence copy from payload-aware renderers, and shared parts that resolve the
provider, model, user-key ownership and compaction capability behind the failure.

Message-limit violations persist `resetAt`/`retryAfterSeconds`, so the row counts
down to the window's reset instead of naming a window length alone.

* 📸 chore: pin before/after error copy screenshots for the pull request

* 🧹 chore: drop the pinned pull request screenshots from the tree

* 🔻 style: Trail the error disclosure chevron after its label

* ⏱️ refactor: Derive Limiter Resets in packages/api, Stamp Key Expiry as ISO

The message limiter's reset fallback and retry arithmetic move out of the
CJS middleware into `getRateLimitReset` in packages/api, which both the
message and agent-event handlers now call, so /api keeps only the wiring.

`checkUserKeyExpiry` persists `expiredAt` with `toISOString()` instead of
the server's `toLocaleString()`, which a client in another locale could
parse with day and month swapped.

* 🪪 fix: Attribute Failed Turns to the Row, Agent and Payload That Failed

Error content parts render through `Part` without their message, so their
copy named the conversation's current endpoint and model rather than the
ones that failed. The chat, flat-thread and search row renderers now supply
the row's identity through `ErrorSourceProvider`, and the dispatcher reads
it whenever no row is passed directly.

A saved agent's row carries the `agents` endpoint and the agent id as its
model, so identity, key ownership and the key dialog resolve against the
agent's own provider and model; an endpoint named by the payload (an
expired key) outranks both. The agent builder is only suggested where the
side panel would offer it: agents configured, builder not disabled, USE and
CREATE held, and an EDIT grant or administrator role.

Also in the renderers:
- structured refusals read Anthropic's `stop_details.explanation`
- provider bodies nesting their message under `error` keep that message
- upstream model failures name the provider when it is known
- `INVALID_USER_KEY` offers the key dialog on a user-provided endpoint
- an oversized message is never told to compact the conversation
- the countdown is bounded by the limiter's window, not a fixed day, and its
  ticking text is hidden from the assertive live region
- an expiry persisted in a server locale is shown as written
- search rows that failed render through the dispatcher, not as markdown
- the payload type is an explicit JSON value type

* 🧪 chore: Seed Real Refusal, Legacy Expiry and Nested Provider Error Shapes

The gallery's refusal case used a string `info` no producer writes; it now
carries Anthropic's stop metadata and a Bedrock content filter. It also
seeds an expiry stamped in a server locale, an unreadable key on a
user-provided endpoint, and a provider body nesting its message under
`error`, and removes whatever it inserted when a write fails.

* 🧵 fix: Keep the Reason From a Provider Body Embedded in Failed-Run Text

A failed run persists a provider error as `<base message>: <SDK message>`,
and Anthropic's SDK message embeds the response body, so the persisted text
reads `…request: 400 {"type":"error","error":{"message":…}}`. The
fallback renderer dropped that body and kept only the prefix, losing the
reason. It now swaps the body for the message it carries.

* 🔀 fix: Resolve Handoff Agents, URL-Owned Credentials and Nested Error Codes

An error part after an `AGENT_UPDATE` belongs to the agent the run was
handed to. `ErrorSourceProvider` now records where a row's handoffs sit,
and an error part resolves the agent active at its own `partIndex`; search
and shared rows give error parts that position too. A handoff the agents
map cannot resolve names no provider instead of the agent that handed off.

A user-provided base URL makes the reader's own record hold the key as
well, so key failures on such an endpoint offer the key dialog. `NO_BASE_URL`
and `INVALID_BASE_URL`, which only a user-provided URL produces, render
through the same renderer with named copy and an add or update action.

OpenAI-compatible bodies nest `code` and `type` under `error`; when the top
level names neither, the dispatcher reads the envelope, so a nested
`invalid_api_key` reaches the key renderer.

* 🕰️ fix: Keep Unknown Key Ownership Generic, Measure Resets From the Row

A shared link's viewer has no endpoint configuration, so whether the reader
or the deployment owns a key is unknown; key copy there read that as
deployment-owned and told the viewer to ask an administrator. Ownership is
now undefined without a configuration, and the copy stays generic.

The countdown's window bound used this device's clock, so a device running
behind the server could drop a valid reset. The window now runs from the
row's own timestamp, which the server stamped alongside `resetAt`.

* 🗜️ fix: Suggest Compaction Only Where the Compact Action Is Offered

Manual compaction is only reachable from the context usage popover, which
`interface.contextUsage: false` removes. Context errors on such a deployment
suggested compacting anyway; they now fall back to the standard next steps.

* 🧭 fix: Keep Row Identity Authoritative and Every Generation Charge Visible

A row's own endpoint and model now stand even where it lacks them, so a
restored failure no longer borrows whatever the conversation selected since;
only an error rendered with no row reads the conversation, and an agents row
with no stored agent id (the live row of a turn that just failed) still
resolves the conversation's agent.

Also:
- a token-balance row lists every generation instead of the first 20
- search rows re-render when their `error` flag changes
- `AUTH_CROSS_ORIGIN`, added since this branch began, renders the login
  page's copy and has a gallery case, so the seed's completeness check runs;
  a table test now fails for any enum member without authored copy
- upstream model failures keep the provider-neutral sentence the server
  persists as their text, which the e2e suite reads the row by

* 🪞 fix: Resolve Ephemeral Agent Ids and Keep an Agents Row's Model Name

An agents row whose model is a model name, as an ephemeral agent's is,
lost both its provider and its model whenever no saved agent resolved.
Agent ids now resolve the way sibling headers resolve them: a saved agent
through the map without the parallel `____N` suffix, an ephemeral agent
through the endpoint and model its id encodes. A row that still resolves
nothing keeps the model name it recorded; an agent id is never shown.

* 🛤️ fix: Attribute Lane Errors to Their Agent, Count Live Retries Relatively

A parallel run stamps each part with the agent of its lane, and an error
part in one lane was attributed to whichever handoff last preceded it. The
row now records error parts' own agents alongside its handoff positions,
and an error part's own agent comes first.

A live countdown subtracted this device's clock from the server's
`resetAt`, so a device running fast could report the limit already over.
`retryAfterSeconds` is now counted from the row's own timestamp, which the
device stamps on a live row and the server on a restored one.

Search results read a cached startup config but have no compact control, so
compaction guidance now also requires the chat surface.

* 🧷 fix: Resolve an Agents Row From Its Own Model, Never the Current Agent

An agents row that stored a model name, as an ephemeral agent's does, fell
back to the conversation's current agent when no saved agent resolved, so
switching the conversation to a saved agent later rewrote who produced the
old failure. The fallback served no real row: the client's live placeholder
for an agents turn stores the conversation's agent id as `model`, as
persisted rows do. The row's `model` now decides on its own — a saved or
encoded ephemeral id resolves, a model name is kept, and the `ephemeral`
placeholder names nothing; only an error with no row reads the conversation.

---------

Co-authored-by: Danny Avila <danny@librechat.ai>
2026-09-14 10:37:22 -04:00
Danny Avila
345cf8877f
🍵 fix: Support Renewable MCP Credentials for Schedules (#15908)
* fix(schedules): forward renewable MCP credentials

* fix(schedules): require unattended MCP credentials

* fix(schedules): resolve MCP credentials during execution

* refactor(schedules): inject unattended credentials

* fix(schedules): scope renewable credential resolution

* fix: isolate lazy scheduled OBO credentials across MCP lifecycle

* fix: preserve MCP cancellation and retryable credential lookup

* fix: bind MCP cancellation to the owning run signal

* test: supply flow manager in OBO cancellation regression

* fix: preserve MCP cancellation across exchange and API ingress

* style: sort MCP manager imports

* fix: propagate cancellation through agent discovery

* test: preserve agent discovery edge literals

* fix: propagate agent initialization cancellation

* fix: expose initialization signal in OpenAI adapter
2026-09-14 10:27:47 -04:00