Commit graph

6961 commits

Author SHA1 Message Date
Marco Beretta
8ffdee3b4b 🗂️ feat: Chat List Properties Menu and Project-Scoped Chats (#16246)
* feat(client): Rebuild the chat list filter as a properties menu

The old menu listed every option at once. It now opens on three rows that
state where the list stands, Show, Sort and Filter, each with its current
value and a submenu holding the choices. Reading the list's state no longer
means reading the whole menu.

Filter holds the five facets and a search field that looks inside them, so
typing openai finds the endpoint rather than the category that contains it,
and typing a category name offers everything under it. Reset sits in the
header next to the title, and the active facet count rides on the trigger.

The facets are one derived atom, so the query key and the request are built
from the same description of the filter. Date cutoffs snap to local
midnight: taken from the current instant they would differ on every render
and refetch the list each time.

The panels also fade their content at the foot when a list runs past the
fold, and the chat list's loading label shimmers the way every other
in-flight label in the app does.

* feat(client): Show a project's chats under that project only

A chat assigned to a project was listed twice in one sidebar: once under
the project and once in Chats. The chats list now asks for the chats that
belong to no project, which the list query and its cache helpers already
knew how to answer.

Search and the archived view keep asking for everything. Projects is not
rendered while a search is on, and an archived chat has no project row to
appear under, so excluding them from either would leave a chat with no way
back to it.

* fix(client): Keep facet-filtered caches honest and the facets session-scoped

Cache writers judged list membership only by project, archive, tags and
sort, so an SSE update or a fork could insert a chat the server's filter
had excluded. The endpoint and date facets are decided from the row
itself, and the attachment and sharing facets mark their variants for a
refetch, since only the server can place a row in them.

The date cutoffs now derive from a day anchor a mounted consumer
advances at local midnight, so a tab left open stops serving
yesterday's today. Facets reset at the authentication boundary with the
rest of the session state, the bookmark query stops firing for roles
without BOOKMARKS:USE, an empty Chats section under existing projects
says so instead of claiming the account is empty, and the design-rule
violations this branch had suppressed in Conversations and
ChatFilterMenu are fixed and their entries pruned.

* test(client): Mock the projects query the chats section now reads

* test(e2e): Acceptance scenarios for the chat list properties menu

* fix(client): Call the account empty only once its projects have loaded

An empty Chats list read as "No chats yet" whenever the projects query
had not succeeded, so a slow or failed projects request claimed an
account was empty when its chats may all live under projects. The
account-level wording now needs a loaded, empty project list; otherwise
the section says only that nothing sits outside a project.

* test(e2e): Scenario for the Filter submenu under a role without bookmarks

* fix(client): Drop a cached chat from an endpoint filter it no longer matches

The endpoint facet only guarded insertion, so a chat already in an
endpoint-filtered list stayed there after switching provider until the
next refetch. List membership now includes the endpoint for existing
rows as well; a row with no endpoint stays until the server decides.

* fix(client): List every chat when the projects fail to load

Scoping Chats to unassigned chats hid every project chat behind the
Projects section, which shows nothing when its request fails. A failed
project list without cached data now leaves Chats unscoped, so those
chats stay reachable, and an empty unscoped list reads as an empty
account.

* test(e2e): Scenario for project chats when the projects fail to load

* fix(client): Count the bookmark filter once in the menu trigger

The trigger added one per selected bookmark while the Filter row counts
the whole bookmark group as one, so a screen reader heard two different
totals for the same state. Bookmarks now count once, like the endpoint
facet.

* fix(client): Stop the endpoint filter at the configured limit

The Endpoint facet let a user pick more endpoints than
conversationList.maxEndpointFilters allows, and the list request past it
answered 400, leaving Chats in its error state. The post-login startup
config now publishes the limit, resolved by the same helper the list
parser uses, and the facet disables further endpoints once the
selection reaches it, with a note saying why.

* test(e2e): Scenario for the endpoint filter limit

* fix(client): Hold the endpoint filter until its limit is known

The sidebar renders before the post-login startup config resolves, and
until then the Endpoint facet had no limit to enforce, so a selection
made in that window could pass conversationList.maxEndpointFilters.
Endpoints are now offered disabled until that config has loaded.

* fix(client): Keep a chosen bookmark removable and a failed config unlocked

A selected bookmark whose last chat dropped it fell out of both bookmark
lists, so only Reset could clear it; a selected tag now stays listed.
The Endpoint facet waits only while the startup config is loading, so a
config that failed no longer locks every endpoint without saying why.

* test(e2e): Scenario for a chosen bookmark whose count drops to zero

* fix(client): Keep a chosen endpoint removable when the deployment stops listing it

An endpoint that left the endpoints config, or a config that failed to
load, dropped out of both endpoint lists while it stayed selected, so it
kept narrowing the chats and could not be turned off. Both lists now come
from one helper that keeps the selection listed.

* docs(client): Punctuate the list membership comments without dashes

* fix: Publish the chat list filter limits the list route enforces

The startup config published maxEndpointFilters from the caller's merged
config while the list route reads the deployment's base config, so a
principal override could let the sidebar allow a selection the route
refused, or disable one it accepted; and the endpoint name limit was not
published at all, so a long custom endpoint name could be selected and
turn the list into a 400. Both limits now come from one loader the list
route also uses and are published together as conversationListLimits;
the Endpoint facet leaves out names past the length limit.

* fix(client): Keep a deleted bookmark removable from the filter

A selected bookmark that was deleted no longer came back from the tags
query, so neither bookmark list could show it and only Reset cleared it.
Both lists now come from one helper that keeps every selected bookmark.

* fix(client): Offer a retry when a project's chats fail to load

Chats lists only chats outside any project, so a project whose own chat
request failed hid its chats behind the empty state. The project now says
its chats could not load and offers a retry.

* test(e2e): Scenario for a project whose chats fail to load

(cherry picked from commit 1160c802ed)

Original-PR: https://github.com/LibreChat-AI/LibreChat/pull/16246
2026-10-01 03:46:18 +00:00
Marco Beretta
4406d34419 🪝 feat: AI SDK-Shaped useChat Facade Over the Chat Contract (#16375)
* feat: expose the messages key and the submitted response on the chat contract

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01GQdLgSaTheiBFHYnUDgobw

* fix: keep the submitted response in the chat host instead of reading the submission atom

The contract's initialResponse is now the response ask submitted, held beside
the host's own state and exposed only while the turn is in flight, so a settled
turn and a run restored after a reload report none, and the submission atom
gains no reader.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01GQdLgSaTheiBFHYnUDgobw

* fix: take the submission ask builds as a value and document the empty messages key

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01GQdLgSaTheiBFHYnUDgobw

* fix: scope the submitted response to its chat and promise seeded positions, not identity

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01GQdLgSaTheiBFHYnUDgobw

* docs: note that a new chat's submitted response ends at its saved id

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01GQdLgSaTheiBFHYnUDgobw

* fix: end the submitted response with its turn and note that the stream can continue the last seeded part

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01GQdLgSaTheiBFHYnUDgobw

* refactor: drop the submitted response from the chat contract

A run can be restored, replaced or torn down outside ask, so a copy of the
submitted response kept in the host describes the wrong run on those paths. The
contract keeps messagesKey only.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01GQdLgSaTheiBFHYnUDgobw

* feat: add an AI SDK-shaped useChat facade over the chat contract

useChat reads ChatContext and presents it as @ai-sdk/react@4.0.117 does:
UI-shaped messages, a submitted/streaming/ready/error status derived
from the in-flight flag and the latest message, and sendMessage,
regenerate, stop and setMessages forwarding to the contract. It holds
no state and changes no existing consumer.

* feat: apply the client tool outcome rules in the useChat facade

The parts mapping reads only the markers stored on a tool call; the facade supplies getToolMeta as its resolveToolFailure, so memory failure prose and background task status attachments reach the UI parts view the same way they reach the tool cards.

* fix: make the useChat facade reactive, placeholder-aware and cached per message

messages re-reads getMessages whenever the message query cache is written, through useSyncExternalStore, so setMessages and other cache writes show without an unrelated context update. Views are cached per message reference, so a streamed chunk remaps only the messages it replaced. status ignores placeholder parts through isEmptyContentPart, the error reads an Assistants error part's text, and a message inserted through setMessages joins the active conversation under the message before it.

* fix: remap streamed responses and scope stepless tool calls in the facade

The content handler reuses a response object across frames and replaces its content, so views are cached per message and per snapshot of the fields a view reads rather than by the object alone. The tool outcome resolver passes getToolMeta the step ids a repeated provider id already owns, so a call without a step is not failed by another step's attachment.

* fix: follow in-place stream frames and tolerate empty tool call slots in the facade

The content handler replaces a response's content on the same object, so
structural sharing keeps the cached message array and the external store saw
no change. The snapshot is now keyed by the message cache write count.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01GQdLgSaTheiBFHYnUDgobw

* fix: catch unobserved cache writes, keep inserts in the active chat and report the error part

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01GQdLgSaTheiBFHYnUDgobw

* fix: key the facade snapshot on the active query's own update count

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01GQdLgSaTheiBFHYnUDgobw

* fix: use the filters form of findAll for the facade's messages scan

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01GQdLgSaTheiBFHYnUDgobw

* perf: look up the facade's holder queries once per cached array

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01GQdLgSaTheiBFHYnUDgobw

* fix: read the chat id, first delta and active branch from the chat contract

The facade subscribes to the one message query the contract names instead of
matching cached arrays, reports that query's conversation as the chat id, counts
only parts the submitted response was not seeded with as streamed output, and
parents an appended message to the active branch. A memory call's failure prose
is its error text now that the resolver's reason becomes the part's errorText.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01GQdLgSaTheiBFHYnUDgobw

* fix: keep inserted messages in the active chat, unassigned in a new one

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01GQdLgSaTheiBFHYnUDgobw

* fix: keep stored messages in their conversation and count generated files as streamed

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01GQdLgSaTheiBFHYnUDgobw

* fix: read seeded parts by position and report failed user tails as errors

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01GQdLgSaTheiBFHYnUDgobw

* fix: count a continued last seeded part as streamed and remap views on metadata changes

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01GQdLgSaTheiBFHYnUDgobw

* refactor: read streaming status from content alone now the contract has no submitted response

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01GQdLgSaTheiBFHYnUDgobw

---------

Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
(cherry picked from commit 0967e16ea2)

Original-PR: https://github.com/LibreChat-AI/LibreChat/pull/16375
2026-10-01 03:46:18 +00:00
Lia
3a73e508fc 🛶 fix: Reconcile Canary Server Startup and Static Gates
(cherry picked from commit f510bd7be9)

Original-PR: https://github.com/LibreChat-AI/LibreChat/pull/16361
2026-10-01 03:46:18 +00:00
Marco Beretta
1cc4277d1b 🔑 feat: Expose the Messages Key on the Chat Contract (#16395)
* feat: expose the messages key and the submitted response on the chat contract

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01GQdLgSaTheiBFHYnUDgobw

* fix: keep the submitted response in the chat host instead of reading the submission atom

The contract's initialResponse is now the response ask submitted, held beside
the host's own state and exposed only while the turn is in flight, so a settled
turn and a run restored after a reload report none, and the submission atom
gains no reader.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01GQdLgSaTheiBFHYnUDgobw

* fix: take the submission ask builds as a value and document the empty messages key

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01GQdLgSaTheiBFHYnUDgobw

* fix: scope the submitted response to its chat and promise seeded positions, not identity

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01GQdLgSaTheiBFHYnUDgobw

* docs: note that a new chat's submitted response ends at its saved id

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01GQdLgSaTheiBFHYnUDgobw

* fix: end the submitted response with its turn and note that the stream can continue the last seeded part

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01GQdLgSaTheiBFHYnUDgobw

* refactor: drop the submitted response from the chat contract

A run can be restored, replaced or torn down outside ask, so a copy of the
submitted response kept in the host describes the wrong run on those paths. The
contract keeps messagesKey only.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01GQdLgSaTheiBFHYnUDgobw

* test: cover the messages key across chat switches in the mock e2e harness

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01GQdLgSaTheiBFHYnUDgobw

---------

Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
(cherry picked from commit 77a1cfa31d)

Original-PR: https://github.com/LibreChat-AI/LibreChat/pull/16395
2026-10-01 03:46:18 +00:00
Marco Beretta
e232b1b398 🔅 fix: Quiet Form-Control Outlines in the Stock Palettes (#16400)
* fix: Quiet Form-Control Outlines in the Stock Palettes

The stock light and dark palettes gave border-control a 3:1 value, which
made every field, textarea and dropdown outline far louder than the cards
and separators around them. Both now use their border-light value, while
the high contrast and ClickHouse palettes keep their 3:1 outlines.

A legacy theme without border-control now keeps its own light border on
controls instead of being pushed to a contrast-ranked candidate, which
often landed on a text color. The contrast helper that ranking needed is
removed.

The empty tools and skills cards step up from border-light to
border-medium so their dashed edge reads against the panel.

* fix: Keep a Legacy Medium Border on Controls

A theme that predates border-control and painted only its medium border
drew that edge on selects and OTP slots, so it now falls back to the
medium border after the light one instead of the bundled role.

Adds scenarios for the stock outlines matching the card border, the
legacy medium-border theme, and the empty tools card edge.

* test: Spell Out the Stock Control Outline Scenario Tags

(cherry picked from commit df59d61f77)

Original-PR: https://github.com/LibreChat-AI/LibreChat/pull/16400
2026-10-01 03:46:17 +00:00
Marco Beretta
c0ea79ad12 🔎 feat: Filter the Conversation List by Date, Endpoint, Files, and Sharing (#16245)
* feat(api): Filter the conversation list by date, endpoint, files and sharing

The list query takes five new facets. Dates and endpoints narrow it
directly; hasFiles matches conversations that carry at least one file;
sharedOnly resolves the user's live share links and matches their
conversation ids, since a share expires and a denormalized flag on the
conversation would outlive it.

parseConversationListFilters owns what a valid facet is, so the route keeps
the call and nothing else. A malformed date fails the request rather than
being dropped: a filter that is quietly ignored answers with the
conversations the user asked not to see. The endpoint list is bounded at 50
names of 128 characters to keep an unbounded $in out of the query.

Two indexes back the new paths: user, archived, endpoint, updatedAt on
conversations, and user, conversationId on shares.

Cursor pagination is unchanged, so a filtered list pages the same way an
unfiltered one does.

* fix(api): Read the attachment facet from messages and tighten filter parsing

The hasFiles facet matched only the conversation's own files array, which
the standard send flow never writes: uploads ride on user messages, so an
ordinary chat with an attachment was invisible to the filter. The facet
now OR-matches message-derived conversation IDs alongside the
conversation-level array.

Dates are validated as ISO 8601 before construction, so 2026-02-30 and a
bare year no longer roll over into an unintended cutoff, and a mistyped
hasFiles or sharedOnly value fails with 400 instead of reading as absent.
The endpoint count and name-length limits moved to conversationList in
configSchema and are injected into the parser, so a deployment serving
more endpoints can raise them. The shared filter resolves its IDs with
distinct and reuses the set to mark isShared, dropping the second
SharedLink query on every filtered page.

* test(api): Exercise the real list-filter parser through the convos route

The route mock re-implemented the parser loosely: it ignored the configured
endpoint limits and dropped a mistyped flag, so a route that stopped
forwarding conversationList or stopped answering 400 still passed. The mock
now wraps the real parser, and the facet tests cover a mistyped flag and an
endpoint list over the configured limit.

* test(e2e): Acceptance scenarios for the conversation list facets

Each facet is exercised against the running API with its own endpoint name, so the
rows a test seeds are the only rows the filter can return: date cutoffs on updated
and created time, an OR-matched endpoint list, an attachment that only exists on a
message, shares that are live, expiring or lapsed, malformed facets answering 400,
and a list without facets returning what it did before.

* fix(api): Read the list filter limits from the base config

conversationList never reached the resolved app config: AppService builds it from
an explicit field list and the new knob was not on it, so a configured limit was
silently ignored and the defaults always applied. It is now carried onto AppConfig.

The list route also stops resolving the caller's merged config for it. The limits
are deployment-level, and configMiddleware put principal and override reads in
front of every cache-cold sidebar request, including ones with no facets; the base
config is in memory.

* fix(api): Read a list cutoff without an offset as UTC

A timestamp without Z or an offset was handed to new Date(), which reads it in the
server's local zone, so the same request selected different conversations on hosts
in different zones. It is now UTC, matching how a date-only cutoff is read.

* test(api): Share the base-config mock across the convos route specs

* perf(api): Start the attachment and share lookups together

With hasFiles and sharedOnly both on, the message-attachment lookup finished
before the share lookup began, adding the two latencies on every page. Both are
independent user-scoped reads, so they now run in parallel.

* refactor(api): Resolve the list filter limits in one place

The 50 and 128 defaults lived in both the parser and the schema's comments. They
are now field defaults on conversationListConfigSchema, AppService resolves them
(an invalid block keeps the defaults), and the parser takes the resolved values.

The base-config read moves out of the CJS route into
resolveConversationListFilters, which receives getAppConfig from the route.

* fix(api): Keep the list config read inside the route's error handling

* perf(api): Read the list limits only when a request names endpoints

The base config sits behind the config cache, which can be Redis, so every
sidebar request paid that round trip and could fail on it even though the limits
bound only the endpoint facet. A request without endpoints now reads no config.

* fix(api): Accept list cutoffs with microsecond or finer fractions

The cutoff pattern allowed at most three fractional digits, so a valid ISO 8601
timestamp from a serializer that emits microseconds (Python, most databases)
answered 400. Any fraction is accepted now and Date keeps the milliseconds.

* fix(data-schemas): Count files attached to message content parts in the file facet

A file attached through a mid-run steer is stored on the steer content part
rather than on the message, so hasFiles=true left that conversation out.

* fix(data-schemas): Match every content-part file shape in the file facet

Replay reads a file on a content part as files[], file.file_id,
image_file.file_id or a bare file_id; the facet matched only files[].

* fix(data-schemas): Count tool and assistant attachments in the file facet

A file a tool produces is persisted on message.attachments, the one place
on a message the facet did not read, so a chat whose only file was
generated output was left out of hasFiles=true.

* fix(data-schemas): Count download-only attachments in the file facet

A code or tool result can persist an attachment with a filepath and no
file_id; the client renders any attachment with a filepath as a file,
so the facet now uses the same rule.

(cherry picked from commit d1cf27e78e)

Original-PR: https://github.com/LibreChat-AI/LibreChat/pull/16245
2026-10-01 03:46:17 +00:00
Marco Beretta
7f4bde8352 🧩 feat: Map Message Content Parts to a UI Parts Union (#16374)
* feat: map message content parts to a UI parts union

Adds a UIMessage-shaped view of TMessage modelled on the AI SDK
(ai@7.0.114): content parts map one-to-one onto text, reasoning,
tool-<name>, file and data-* parts, holes map to step-start, and the
reverse restores the stored content so a view round-trips.

* fix: carry text, files and metadata through the reverse message mapping

An empty content array with text now views as contentless, an edited text part updates the stored text, attachment file parts reconcile message files, and metadata fields restore a message rebuilt without a stored base.

* fix: read durable tool markers and apply view edits in the parts mapping

Tool parts fall back from an empty id to the host step id, surface approval pauses and background-cancel or validation failures, and treat an empty legacy function output as submitted. The reverse mapping writes file and attachment edits over the stored records, keeps an explicit null parent, carries non-derived message text and absent text fields, persists hand-built tool failures, and collects text, content and attachments in one pass. Web search sources include link references and take message-wide ids. UIMessage drops the system role it could not round-trip. Adds mock-harness scenarios that view persisted replies, reasoning and tool turns and map them back.

* fix: view persisted reasoning without its think tags

Persisted reasoning is stored inside <think> tags that every renderer strips; the reasoning part now exposes the text alone and keeps the exact wrapper so the reverse mapping restores it. The tool-turn scenario skips mobile, where the composer MCP picker is not offered.

* fix: give view attachments a stable identity and read legacy tool outcomes

Attachment file parts carry the stored path they were viewed with, so an edited url still matches its file. Reverse slots advance only for content parts, audio takes its format from an edited media type, a null model survives a base-less rebuild, legacy retrieval outputs count as submitted, and error-prefixed outputs map to output-error through isToolErrorOutput, the predicate the tool output renderers use.

* fix: keep attachments, empty content and hand-built tool results through a rebuild

A base-less rebuild restores the stored attachments and an explicit empty content array from metadata. Hand-built tool parts record a completed status for output-available and keep an array output as a code interpreter call. Files the view never showed keep their stored positions while visible files fill the others in view order.

* feat: let the caller supply tool outcome rules to the parts mapping

Some tool outcomes are decided by rules the client owns, such as memory failure prose and background status attachments. toUIMessage, toUIParts and toUIPart take a resolveToolFailure option instead of copying those rules. Text deltas keep their ownership metadata, an empty hand-built array output is marked completed, and fromUIMessage documents that a stored message round-trips only with its base.

* fix: map untyped lane placeholders to step-start

A dual-conversation turn seeds type '' placeholder slots, which fell through the part switch and crashed toUIMessage. Any slot without a known type now maps to step-start, and the reverse leaves a hole, the same thing persistence compaction does.

* fix: identify view attachments by position and keep content added to plain messages

Attachment parts carry their index in message.files beside the path, so two files sharing a path stay distinct, and a hand-built part claims the first unclaimed match. Content parts added to a view of a plain message are written as content. Tool arguments that parse to a JSON primitive stay their string, inside the declared input type.

* fix: derive fallback tool ids from the streamed index and drop stale annotations

A tool call with neither a provider id nor a step id takes its fallback id from the streamed index the settled message keeps, so its identity survives compaction. Annotations on object-form text are dropped once the view's text no longer matches the value they index into.

* fix: map tool call slots without a call to step-start and keep text delta object shape

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_017snqTCuA2LHsoKuC335HFG

* fix: report background and caller-resolved tool failures by their reason

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_017snqTCuA2LHsoKuC335HFG

---------

Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
(cherry picked from commit 6ac941eff3)

Original-PR: https://github.com/LibreChat-AI/LibreChat/pull/16374
2026-10-01 03:46:17 +00:00
Marco Beretta
5eed7d5ff2 🎛️ feat: Close the Data-Level Click UI Gaps in the ClickHouse Theme (#16379)
* feat: close the data-level Click UI gaps in the ClickHouse theme

Set the theme values Click UI defines that the ClickHouse theme still left
at LibreChat defaults:

- controlHeight 2rem (genericMenu.panel.size.height), spaceCompact 0.5rem
  (button.basic.space.gap), spaceNormal 1rem (button.basic.space.x) and
  motionFast 100ms (transition.default).
- Light ring-primary to outline.default #437eef, matching the dark mode
  ring, which already used outline.default.
- Light surface-overlay to dialog.color.opaqueBackground #151515.
- Dark surface-inverted to Click UI's primary fill #faff69 with its hover
  and #1f1f1c label, which is also its checked checkbox and switch colour.

* fix: keep the shared spacing roles at LibreChat's values in the ClickHouse theme

spaceNormal and spaceCompact are not control-only: spaceNormal pads the user
message and queued-steer bubbles, and spaceCompact is the composer send
button's inner padding. Raising them to Click UI's button padding and gap
widened the bubbles and shrank the send icon's box. Keep both at the defaults;
0.75rem is already Click UI's field padding.

(cherry picked from commit 6d54d07ac1)

Original-PR: https://github.com/LibreChat-AI/LibreChat/pull/16379
2026-10-01 03:46:17 +00:00
Marco Beretta
bdd2d4ef8d 🔤 feat: Bundle Inconsolata for the ClickHouse Theme (#16376)
* feat: bundle Inconsolata for the ClickHouse theme

The ClickHouse theme names Inconsolata as its mono family, but the app did
not ship the face, so code fell back to the system monospace. Self-host the
latin 400 and 700 woff2 faces from Fontsource 5.3.0 with their OFL licence,
declared with font-display: swap in a stylesheet of theme-opt-in faces. The
browser fetches a declared face only when text renders in it, so the default
theme never downloads them.

* fix: ship the Inconsolata licence with the production build

Production builds disable publicDir, so the woff2 faces reached dist through
the $fonts alias while the OFL text next to them in public/fonts did not. The
build now copies the licence texts from public/fonts into assets/fonts, beside
the faces they cover.

(cherry picked from commit 57da77c60f)

Original-PR: https://github.com/LibreChat-AI/LibreChat/pull/16376
2026-10-01 03:46:17 +00:00
Marco Beretta
c5c01dffe3 🔌 refactor: Drive the Resumable Stream Through the ChatTransport (#16378)
* refactor: drive the resumable stream through the ChatTransport

Add reconnectToStream to ChatTransport and the sse.js transport: a GET
attach with request headers, a token refresh on every 401, a cancel the
caller did not issue reported as a dropped connection (status 0), and a
closed flag for the foreground check. useResumableSSE now consumes
normalized ChatEvents instead of opening sse.js and parsing frames
itself; resume, steer and queue bookkeeping are unchanged.

* fix: bound the resume 401 refresh and keep plain-text server errors

Refresh the token once per attachment and report a second 401, so the
hook's reconnect budget bounds a stream that keeps answering 401. A
server-written error event that is not JSON keeps its raw text instead
of reading as a dropped connection.

(cherry picked from commit df01dba657)

Original-PR: https://github.com/LibreChat-AI/LibreChat/pull/16378
2026-10-01 03:46:17 +00:00
Marco Beretta
bedfa785cb 🔲 a11y: Form-Control Outlines Clear 3:1 in Every Palette (#16377)
* fix(client): Give form-control outlines their own 3:1 border role

border-medium and border-light were the only visible edge on the shared
form controls, and neither clears the WCAG 1.4.11 3:1 non-text floor in
any palette. Raising them would also darken every separator and card edge,
which the quieter dark borders deliberately keep one step off the page.

border-control is a new theme role for the outline of a field, select
trigger, dropdown, combobox trigger and OTP slot. Every bundled palette
gives it a value that clears 3:1 on each canvas a form can sit on, the
package ships the stock light and dark defaults so the outline holds before
and without a theme definition, and a custom theme that paints its own
medium border but not the new role keeps the outline it drew.

semanticTokens.spec.ts holds the 3:1 floor for the role in all six modes.

* fix(client): Keep a legacy control outline only when it clears 3:1

A theme that paints its own borders but predates border-control took its
medium border as the control outline, and a quiet one left every field
without a visible edge. The fallback now keeps that border only where it
clears 3:1 on the theme's own canvases and otherwise uses the theme's
secondary text, in both resolveTheme and the legacy applyTheme adapter.

The palette scenarios spell out their tags so the runner can find them.

* fix(client): Map legacy light and medium borders onto the control outline

Controls drew border-light (fields, dropdowns, comboboxes) or border-medium
(select, OTP) before border-control existed, so a stored theme that painted
either, or the canvases they sit on, takes the first of its light border,
its medium border, the bundled role or its secondary text that clears 3:1
on its own canvases. A theme that names none of them keeps the bundled role.

* fix(client): Never settle for a control outline that fails when a better one exists

Secondary and primary text join the candidates for a legacy theme's control
outline, and when none clears 3:1 on the theme's canvases the one that
comes closest is used rather than the secondary text by default.

(cherry picked from commit 85910e97b4)

Original-PR: https://github.com/LibreChat-AI/LibreChat/pull/16377
2026-10-01 03:46:17 +00:00
Marco Beretta
a7bdfa761c 🧩 feat: Let Theme Readers Ignore Unknown Appearance Tokens (#16373)
A definition naming an appearance token this build does not know now
resolves with that token dropped and reported, instead of being rejected
whole. Unknown colours, invalid values for known tokens, and CSS or markup
carried by an unknown token still reject the definition.

(cherry picked from commit 0ea3e27c8e)

Original-PR: https://github.com/LibreChat-AI/LibreChat/pull/16373
2026-10-01 03:46:17 +00:00
Lia
57e26fae44 🛶 style: Match CI Tailwind Formatting in Canary Sync
(cherry picked from commit b9b82d75cf)

Original-PR: https://github.com/LibreChat-AI/LibreChat/pull/16361
2026-10-01 03:46:17 +00:00
Lia
733f5e678c 🛶 test: Isolate Marketplace Retries and MCP OAuth Ownership
(cherry picked from commit c4fbffb380)

Original-PR: https://github.com/LibreChat-AI/LibreChat/pull/16361
2026-10-01 03:46:17 +00:00
Lia
3ae115785e 🛶 fix: Reconcile Canary Sync Checks
(cherry picked from commit 09c12b98a4)

Original-PR: https://github.com/LibreChat-AI/LibreChat/pull/16361
2026-10-01 03:46:17 +00:00
Marco Beretta
fd1ca77edb 🟨 feat: ClickHouse Theme Shape Parity (#16342)
* feat: ClickHouse Theme Shape Parity

The ClickHouse reference theme now sets the radius scale from Click UI's
`border.radii`, the mono family to Inconsolata over a real fallback stack,
and its shadow scale and surface elevation from Click UI's `shadow.1`
(0.15 alpha in light, 0.6 in dark), so selecting it changes shape and not
only colour. The divergence spec asserts the new tokens differ from
LibreChat's, and the theme README documents the appearance scales.

* test: Compare the ClickHouse Small Radius by Rendering, Not by String

* test: Scenarios for the ClickHouse Theme Shape

(cherry picked from commit 631fa64b39)

Original-PR: https://github.com/LibreChat-AI/LibreChat/pull/16342
2026-10-01 03:46:17 +00:00
Marco Beretta
33871c39be 🌫️ feat: Shadow Scale Follows the Theme (#16341)
* feat: Shadow Scale Follows the Theme

Map Tailwind's shadow scale (xs through 2xl, plus bare `shadow`) to
theme-owned appearance properties in the app's `@theme inline` block, with
Tailwind's own values as defaults. `--theme-elevation-surface` stays the
separate role behind `shadow-theme-surface`.

* fix: Validate Theme Shadows and Keep Disabled Ones Composable

A theme shadow must now parse as a box-shadow list or none, so a
malformed value is rejected instead of voiding every shadow-* call site.
none resolves to a transparent layer, since Tailwind lists --tw-shadow
after the ring layers where a bare none invalidates the declaration.

* feat: Theme the Smallest Shadow Step Too

* test: Cover the Theme Shadow Scale in the Browser

* fix: Let the Browser Reject Unknown Shadow Colors

* fix: Keep var() and Other Length Units Valid in Theme Shadows

* fix: Keep Defaults for Appearance Keys Present but Undefined

* fix: Classify Shadow Tokens Instead of Deferring var() Values to the Browser

* fix: Reject Empty Layers in a Theme Shadow List

* fix: Require Concrete Theme Shadows So the Browser Can Validate Them

* fix: Reject env() and attr() in Theme Shadows Like var()

Both are substitution functions, so the browser only checks a value that
holds one at computed-value time. A missing environment variable without a
fallback then invalidated the composed box-shadow, ring layers included,
instead of rejecting the theme and keeping the default.

* fix: Keep Loading Released Themes With a Variable-Backed Surface Elevation

The released validator accepted var() in elevationSurface, and a theme that
fails validation is dropped as a whole. Only the new shadow scale steps need
to be concrete, so elevationSurface keeps its original check.

(cherry picked from commit 89f4a62dcf)

Original-PR: https://github.com/LibreChat-AI/LibreChat/pull/16341
2026-10-01 03:46:17 +00:00
Marco Beretta
1dc4e0d278 🪶 style: Quieter Primitives, Shared Panel Headers, and Flat Management Lists (#16244)
* style: Quieten the shared primitives and the dark borders

The primitives carried the weight the screens then inherited: boxed empty
states, outlined table shells, raised composer pills. Softening them here
means a screen gets the quieter treatment by composing what it already
composes rather than by overriding it.

Dark moves its border roles one step off the page instead of two, so an
edge separates a surface from the one behind it without reading as a seam.
The values live in style.css for the pre-hydration paint and in dark.ts for
the runtime theme, so both change together.

Checkbox gains CheckboxGlyph, the presentational half of the control, for
rows that are already a button and must not nest a second one inside it.

* feat(client): Panel header and scroll fade for the side panels

Every management panel was building its own title row, so the title, the
search field and the create button sat at a different size and spacing in
each one. PanelHeader is that row, and the panels adopt it next.

PanelContent gains a fade at its foot, fed by useScrollFade, which watches
the viewport and its content and reports whether anything sits below the
fold. A list that is exactly as tall as its box shows no fade, and the
gradient is dropped under prefers-reduced-motion.

The sidebar keeps a right edge in every theme now that it shares a surface
with the content beside it, rather than only in high contrast.

* style: Apply the quieter layout to the panels and management pages

The main content now sits on the same surface as the sidebar, so the app
reads as one plane instead of a page floating on a backdrop. With the fill
gone the containers had nothing left to justify them: cards, outlines and
double borders come off the MCP, Skills, Bookmarks, Memory, Prompts and
Scheduled Chats lists, and spacing and weight carry the hierarchy instead.

The management screens adopt PanelHeader, so title, search and create sit
at one size and one rhythm across all of them, and Schedules gains the
search its siblings already had. Secondary row actions appear on hover and
focus rather than resting in the row.

Two rows also stop nesting interactive controls: the skills row splits into
sibling buttons under a focus-within ring, and the memory and prompt toggles
render CheckboxGlyph inside their button rather than a second control.

* fix(client): Keep the schedules quota and skeleton honest under filtering

The footer counted the filtered list while the create limit is enforced
against all schedules, so filtering made a full account look under quota.
The skeleton reserved a switch, a menu and three text rows the flattened
row no longer has, so the panel visibly collapsed on load; it now mirrors
the healthy row. The skill file expander announced "Show files" even
while expanded, so its label is now a neutral toggle.

* fix(client): Restore schedule row actions and settle the panels' design debt

A schedule row's actions sat in the hover-revealing slot other lists use,
but this panel's rows end at the sidebar's resize handle and a slot
collapsed to zero width put the switch's clickable point outside the
panel, under the handle, where no hover could ever reveal it; the slot
now keeps its width and the menu trigger fades in on row hover alone.

The design-rule violations this branch had suppressed are paid instead:
the tables drop restatements the Table primitives own and take a compact
header size, FilterInput gains the dialog surface instead of a
caller-side color, the projects entries move to the section-action
variant, the MCP cancel cross fades via a wrapper the caller owns, and
the panel group's backdrop moves to its host. The counts this branch had
raised come back down with the entries pruned.

* fix(client): Preserve Shared Row Actions and Verify Panel States

* fix(client): Match Schedule Skeleton Action Height

* fix(client): Preserve Panel Overflow and Schedule History Actions

* refactor(client): Derive Row Action Classes From the Reveal Variant

The reveal recipe was spelled out both in the row-action-reveal Button variant
and in rowActionClasses. The helper now starts from the variant and only adds
the open and always-visible states, and the MCP card spec asserts classes the
real recipe renders instead of a mocked string.

* fix(client): Announce Panel Filter Results and Usage Changes

The schedule filter now reports its match count through a polite live
region, as the prompt filter does. The memory usage badge keeps a status
region beside its toggle so a changed usage is announced while focus is
elsewhere, and the search count reads as a floor while more pages remain.

* fix(client): Keep Row Focus Visible and Warn on Balance-Skipped Runs

The row action slot clipped its overflow even while focus was inside it,
cutting off the focused action's ring. It now clips only while collapsed.

Skill rows drew one focus ring around the whole row, so moving between the
open and disclosure buttons changed nothing on screen. Each button now draws
its own ring.

A run skipped for balance keeps its schedule enabled only until the skip
count disables it, so the row now shows it as a warning instead of reading
as healthy.

* test(e2e): Match the always-applied skill row's full button name

* refactor(client): Render MCP Row Actions Through the Button Primitive

The MCP row actions passed a computed class string to TooltipAnchor, which
the design rules cannot check, and the file carried a new static-classes
suppression for it. They now render the shared Button with the row-action
variants, like the bookmark and memory rows, and the suppression is gone.

* fix(client): Paint Field Notches With the Page Surface and Respect IME Escape

The marketplace, skills and prompts pages moved to the primary-alt surface,
but the floating labels on their fields still painted the presentation
surface, leaving a patch across each field's border in both themes. The
labels now paint the surface they sit on. The create-skill name label is a
plain label like the edit form's, since the Label primitive owns its color
and a notch has to paint its own backdrop.

Escape in the sidebar search cleared the query even while an IME was
composing, where Escape only cancels the composition.

* fix(client): Keep the Chat Column Within the Viewport Beside the Sidebar

Moving the surface off ResizablePanelGroup put a new flex item around it
with the default auto minimum width, so a reply with a wide table grew the
chat column past the viewport and cut its right edge off. The host now
allows itself to shrink, as the group did.

Also covers the sidebar search's IME Escape guard with a unit test, since
the search field is not mounted without a search backend.

(cherry picked from commit 7d4a3f00fe)

Original-PR: https://github.com/LibreChat-AI/LibreChat/pull/16244
2026-10-01 03:46:17 +00:00
Marco Beretta
6e460b7ca7 📐 feat: Radius and Font Scales Follow the Theme (#16340)
* feat: Radius and Font Scales Follow the Theme

Map Tailwind's radius scale (sm through 3xl, plus bare `rounded`) and the
sans and mono families to theme-owned appearance properties in the app's
`@theme inline` block, so a theme definition reshapes the existing plain
utilities instead of only the `theme-*` roles. Defaults reproduce the
values those utilities resolved to before, and the JS config entries and
the bare `--radius` they replace are removed.

* fix: Keep the Pixel Offsets in the Small Radius Defaults

The old `rounded-sm` and `rounded-md` were `calc(var(--radius) - 4px)`
and `calc(var(--radius) - 2px)`. Rem-only defaults matched them only at a
16px root, so keep the calc form and match at every root font size.

* test: Resolve Custom Properties Before Comparing the Code Font

`code` and `.font-mono` now both reach the mono stack through custom
properties, so compare the resolved stacks rather than the raw
declarations.

* fix: Leave Bare rounded on Its Fixed Radius

Bare `rounded` was a fixed 0.25rem, which the `sm` default only equals
at a 16px root now that it keeps its px offset, so it no longer follows
the `sm` step.

* fix: Accept the calc() Radius Defaults the Registry Exports

* test: Cover the Theme Radius and Font Scales in the Browser

* fix: Require Units on Both Operands of a calc() Radius

(cherry picked from commit 50ff19829a)

Original-PR: https://github.com/LibreChat-AI/LibreChat/pull/16340
2026-10-01 03:46:17 +00:00
Marco Beretta
eefeb2a7f9 ⚙️ feat: Make the Per-User Passkey Cap Configurable (#16259)
(cherry picked from commit 84180a87e2)

Original-PR: https://github.com/LibreChat-AI/LibreChat/pull/16259
2026-10-01 03:46:17 +00:00
Marco Beretta
4fb238d5fe 🔌 refactor: Drive useSSE Through the ChatTransport (#16336)
* refactor: drive useSSE through the ChatTransport

Move the sse.js connection, frame parsing, the named attachment and
error events, the 401 refresh-and-retry and the cancel-on-close signal
into client/src/hooks/SSE/transport. normalizeFrame tags each message
frame by the keys the hooks already checked, in the same order, and
createSSETransport emits the resulting ChatEvent union. useSSE now
switches on event.type and calls the same handlers with the same
arguments; its signature is unchanged.

A frame that is not JSON is now logged and skipped. Previously the
parse error escaped the listener and dropped every frame behind it in
the same chunk.

createdHandler never read its first argument, so it is typed as the
created frame it actually receives instead of TResData.

* fix: keep the stream closed when a 401 refresh settles after abort

A refresh that resolved after the caller aborted called sse.stream()
again, reopening the request with the unmounted consumer's handlers; a
refresh that failed after abort dispatched the error path. Both now
return once the signal is aborted.

* fix: refresh the token at most once per stream

A retried connection that drew another 401 refreshed and reconnected
again with no bound, so a server rejecting the refreshed token looped.
The second 401 now reaches the error path.

* refactor: consume the widened content frame type

The content handler never read userMessageId, which Assistants content
frames do not send, so it now takes ChatContentFrame.

* refactor: bridge the wider step and attachment frames to their handlers

The handlers accept narrower payload types than the wire frames now
admit. useSSE narrows at the call, where these frames already reached
the handlers unchanged before the transport existed.

* fix: cancel a turn aborted while its 401 refresh is pending

sse.js marks the connection closed on the 401, so an abort during the
refresh skipped the cancel path and nothing reset the submitting state.
The stream now counts as open until the refresh settles.

(cherry picked from commit a3541da463)

Original-PR: https://github.com/LibreChat-AI/LibreChat/pull/16336
2026-10-01 03:46:17 +00:00
Marco Beretta
13b62283fc 📐 refactor: Normalize Stream Events Behind a ChatTransport Type (#16335)
* refactor: normalize stream events behind a ChatTransport type

Add the ChatTransport interface and a ChatEvent union discriminated by
type, covering every frame the client handles today: the created, sync
and final control frames, the step and side-channel { event, data }
frames, legacy content and text frames, attachments, errors, open and
abort. Types only; nothing consumes them yet.

* fix: type the stream frames the server actually sends

Assistants final frames carry a partial requestMessage, aborts can send
title: null, Assistants content frames omit userMessageId, and the error
event body can be a bare string or { error, generationProtocolVersion }.
Widen the frame types to admit each.

* fix: admit the remaining step, attachment and error payloads

on_agent_update also carries a { runId, message } status line when
sequential outputs are hidden, on_run_step_completed can arrive without
a result, a published run artifact is a plain TFile, and sendError marks
its body with error: true. The frame types now admit each.

(cherry picked from commit 2f8a207317)

Original-PR: https://github.com/LibreChat-AI/LibreChat/pull/16335
2026-10-01 03:46:17 +00:00
Marco Beretta
3c4aa1a784 🖼️ fix: Paint the Shared Link Tenant's Deployment Theme (#16333)
(cherry picked from commit f1bc07b2c7)

Original-PR: https://github.com/LibreChat-AI/LibreChat/pull/16333
2026-10-01 03:46:17 +00:00
lia-by-librechat[bot]
36ba2d3ce0 🫗 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>
(cherry picked from commit fe2b547e64)

Original-PR: https://github.com/LibreChat-AI/LibreChat/pull/16300
2026-10-01 03:46:17 +00:00
Marco Beretta
62a4e3b486 🎨 feat: Theme the Shared Code Block With surface-code and a New surface-code-body Role (#16334)
(cherry picked from commit ecce519b68)

Original-PR: https://github.com/LibreChat-AI/LibreChat/pull/16334
2026-10-01 03:46:17 +00:00
Marco Beretta
c1fbeac4e7 🖌️ refactor: Read Theme Roles in Prose, Settings Dialog and Composer Surfaces (#16332)
(cherry picked from commit e79ed0ab37)

Original-PR: https://github.com/LibreChat-AI/LibreChat/pull/16332
2026-10-01 03:46:17 +00:00
Marco Beretta
91f78cd430 ♿ fix: Keep Identity Badge Labels at Text Contrast (#16337)
* fix: keep identity badge labels on a text role and move the series hue to a dot

Action method and principal type badges painted 11-12px labels in a
categorical series slot over its own tint. The series scale is contracted
at the 3:1 mark floor, so that text fell below 4.5:1 in every palette.
The label now uses text-secondary and the hue rides on a decorative
leading dot, and semanticTokens.spec.ts floors both halves of the pairing
on the surfaces these badges sit on.

* test: cover identity badge label contrast across palettes and modes

* refactor: share the identity label treatment as a SeriesLabel primitive

Both badges composed the same neutral label and series dot by hand. The
treatment now lives in @librechat/client so a later contrast or appearance
change lands once. It renders the caller's text, so it joins the text
primitives whose typography belongs to the caller.

The principal scenario also waits for each query's own option before
reading paint, since the picker keeps the previous result on screen while
the debounced search is in flight.

(cherry picked from commit 2443095fcc)

Original-PR: https://github.com/LibreChat-AI/LibreChat/pull/16337
2026-10-01 03:46:17 +00:00
Marco Beretta
8239583f9d 🔇 fix: Mute the Create Assistant Empty State in the Assistant Picker (#16338)
* fix: mute the Create Assistant empty state in the assistant picker

AssistantSelect passed its "Create Assistant" label as the dropdown value,
so it rendered in the primary value tone. Pass it as the placeholder with an
empty value instead, which SelectDropDown already renders in
text-text-secondary. SelectDropDown no longer checkmarks an option whose
value is empty when nothing is selected, so the loading row stays unmarked.

* test: reach the assistant builder through the mobile control panel

(cherry picked from commit ea2b5f756d)

Original-PR: https://github.com/LibreChat-AI/LibreChat/pull/16338
2026-10-01 03:46:17 +00:00
Marco Beretta
c04bc7c693 🧩 fix: Keep Streamed Parts Intact Across Replays and Early Completions (#16331)
- Carry the in-flight summary's agentId/groupId onto the finalized part
  when the completed summary omits them.
- Write the incoming image_url into a new image slot instead of cloning
  the empty placeholder.
- Leave a settled tool call alone when its tool_calls run step is
  announced again, as the resume path does for every known run step.
- Buffer an ON_RUN_STEP_COMPLETED that arrives before its run step and
  apply it when the step lands, like the other pre-step events.

(cherry picked from commit 3fa4cf1925)

Original-PR: https://github.com/LibreChat-AI/LibreChat/pull/16331
2026-10-01 03:46:17 +00:00
lia-by-librechat[bot]
41d76505a1 🛩️ ci: Allow More Time for Chrome Startup in Client Build Recovery (#16330)
Co-authored-by: Lia <lia@librechat.ai>
(cherry picked from commit 094179f754)

Original-PR: https://github.com/LibreChat-AI/LibreChat/pull/16330
2026-10-01 03:46:17 +00:00
lia-by-librechat[bot]
e396ea9c7b 🫸 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>
(cherry picked from commit 6866732a88)

Original-PR: https://github.com/LibreChat-AI/LibreChat/pull/16297
2026-10-01 03:46:17 +00:00
Marco Beretta
b0783e8085 🔑 fix: Invalidate the Auth User Cache After a CLI Password Reset (#16257)
* fix: invalidate the auth user cache after a CLI password reset

The reset CLI wrote the new password and credentialsChangedAt with
User.updateOne, which bypasses the auth user document cache
invalidation the data-schemas user methods perform. With
AUTH_USER_CACHE_MODE=on a cached document without the new stamp could
keep pre-reset access tokens verifying for up to the cache TTL after
the reset. Route the write through updateUser with the shared cache
factory, the same wiring config/delete-user.js uses, so the cached
entries for the user are deleted as part of the reset.

* test: cover CLI password reset token revocation in the mock harness

* test: verify CLI reset evicts the shared Redis auth cache

* fix: preserve pending account expiry during CLI resets

* test: assert pending account verification after CLI reset

(cherry picked from commit 6f903fc9e5)

Original-PR: https://github.com/LibreChat-AI/LibreChat/pull/16257
2026-10-01 03:46:17 +00:00
Marco Beretta
0173047549 🧰 refactor: Pure Step Reducer for Tool Call Events (#16290)
* refactor: lift tool call step transitions into pure reducers

Add pure reducers for tool_calls run steps, argument deltas, completions
and run-step closures, and move the skill-authoring detection with them.
useStepHandler keeps the step-to-tool-call-id map and records the id each
reducer returns.

* test: cover tool call rendering order with an e2e scenario

* test: anchor the tool call scenario on the code execution card

* test: state the tool reducer guarantees the tests actually cover

Drop the claim that a replayed run step is idempotent after completion and
that a completion may arrive before its run step; cover re-announcing an
open step instead. Match the code card by its name prefix, since a slow
run appends its duration.

(cherry picked from commit 9c7555ab0d)

Original-PR: https://github.com/LibreChat-AI/LibreChat/pull/16290
2026-10-01 03:46:17 +00:00
Marco Beretta
ccae933e6d 🔐 fix: Revoke Password Reset Credentials Independently (#16320)
(cherry picked from commit c59fb60341)

Original-PR: https://github.com/LibreChat-AI/LibreChat/pull/16320
2026-10-01 03:46:17 +00:00
Marco Beretta
b89ed0a32c 🧹 chore: Remove the Unmounted Files Component Tree (#16243)
* chore: Remove the unmounted Files component tree

Nothing outside client/src/components/Files imported anything inside it:
the four views at its root (FilesListView, FileDashboardView, VectorStoreView,
FilesSectionSelector) are not routed and not referenced, so the whole subtree
below them was unreachable. The live file manager lives under
Chat/Input/Files and SidePanel/Files, and the FilePreview and ActionButton
still in use are different files in those trees.

Takes 49 eslint errors with it, all of them literal strings in screens no
one could open. The client is left with 14, none in code this branch
touches.

* test(e2e): Cover the live file surfaces after the tree removal

* test(e2e): State the viewport the files surfaces scenario means

(cherry picked from commit 7402197317)

Original-PR: https://github.com/LibreChat-AI/LibreChat/pull/16243
2026-10-01 03:46:17 +00:00
Marco Beretta
27f78bc3c7 🎨 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

(cherry picked from commit f0cbc9a3c0)

Original-PR: https://github.com/LibreChat-AI/LibreChat/pull/16286
2026-10-01 03:46:17 +00:00
Marco Beretta
be1178d1dc 🧮 refactor: Pure Step Reducer Behind useStepHandler (#16289)
* refactor: lift text and reasoning step transitions into pure reducers

Move the content-part primitives (updateContent, content index and edit
prefix resolution, step metadata, reasoning label reset) out of
useStepHandler into hooks/SSE/steps, and add pure reducers for message,
reasoning, agent update and summary events. The hook keeps its refs,
message lookup, buffering and cache writes and calls the reducers; its
public signature is unchanged. Tool call events follow in the next change.

* test: cover reasoning order and live compaction with e2e scenarios

* fix: tolerate a message step without message_creation details

The inline handler read the phase through optional chaining; keep that in
applyMessageDelta so a bare MESSAGE_CREATION step still streams.

* test: assert the reset reasoning part without an untyped cast

(cherry picked from commit 1c5e8ee7bf)

Original-PR: https://github.com/LibreChat-AI/LibreChat/pull/16289
2026-10-01 03:46:17 +00:00
Marco Beretta
07bbbc0d4d 📜 refactor: Declare the Chat Context Contract (#16288)
* refactor: declare the chat context contract

Replace the inferred ReturnType<typeof useChatHelpers> context type with an
explicit ChatContract grouped by responsibility, and move the added-chat
context shape to AddedChatContract. useChatHelpers and useAddedResponse
annotate their memoized value with the contract, and contract.check.ts
asserts two-way equality against the hooks each member is forwarded from.

* test: cover the chat context behaviors with e2e scenarios

* refactor: derive newConversation options from NewConversationParams

useNewConvo now takes the contract's NewConversationOptions instead of
restating the shared params inline, so there is one definition.

* test: skip the added pane scenario where the control is hidden

* refactor: type contract setters as React dispatchers

Keep the chat contract free of Recoil types, and tighten the regenerate
and stop scenarios to assert the regenerated sibling's content and that
the stopped reply stays partial after reload.

(cherry picked from commit 0d4627b387)

Original-PR: https://github.com/LibreChat-AI/LibreChat/pull/16288
2026-10-01 03:46:17 +00:00
Marco Beretta
55ca9116a3 🎨 style: Semantic Colour Roles for Builder, Tools and Sharing Surfaces (#16294)
* style: move builder, tools and sharing surfaces onto semantic colour roles

Replace raw palette utilities and dark: colour overrides in the Assistants
builder, agent tool rows, principal avatars, SharePoint picker, code-analysis
block, in-flight steers, prompt variables and the skill file editor with
theme roles, so custom themes repaint them. Where a shared primitive owns
its colour, the local override is dropped so the primitive's tokens apply.

* test: cover semantic colour roles on builder, tools and sharing surfaces under a reference theme

* fix: keep the theme focus ring, let steer text beat prose, clean up seeded messages

Restore the ring-ring-primary focus role on the actions panel buttons so a
theme's own focus colour applies, give the in-flight steer body an important
text role so the unlayered .prose colour no longer wins, delete the messages
the code-analysis scenarios seed, and read the v4 placeholder reference from
the root --gray-400 triplet now that no source generates text-gray-400.

(cherry picked from commit 5960f84a21)

Original-PR: https://github.com/LibreChat-AI/LibreChat/pull/16294
2026-10-01 03:46:17 +00:00
lia-by-librechat[bot]
55f3187296 🥢 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>
(cherry picked from commit 411bb5444f)

Original-PR: https://github.com/LibreChat-AI/LibreChat/pull/16299
2026-10-01 03:46:17 +00:00
Marco Beretta
a9571ee13f 🧹 refactor: Keep Mongoose Types Out of the Passkey Handler Contract (#16263)
(cherry picked from commit fea7c17a56)

Original-PR: https://github.com/LibreChat-AI/LibreChat/pull/16263
2026-10-01 03:46:17 +00:00
lia-by-librechat[bot]
627ded714b 🥼 ci: Gate MCP Apps on Executed Browser Tests (#16283)
Co-authored-by: Lia <lia@librechat.ai>
(cherry picked from commit 1c54ffa411)

Original-PR: https://github.com/LibreChat-AI/LibreChat/pull/16283
2026-10-01 03:46:17 +00:00
Marco Beretta
7c60a20275 🟨 feat: Add a ClickHouse Reference Theme (#16262)
(cherry picked from commit c737753066)

Original-PR: https://github.com/LibreChat-AI/LibreChat/pull/16262
2026-10-01 03:46:17 +00:00
Dustin Healy
7b27e7941e 🧩 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>
(cherry picked from commit a98d40f61c)

Original-PR: https://github.com/LibreChat-AI/LibreChat/pull/13831
2026-10-01 03:46:16 +00:00
Marco Beretta
a27d6ec35a 🔑 fix: Refresh the Stored Passkey Backup State on Each Sign-In (#16255)
verifyPasskeyAuthentication discarded credentialBackedUp, and
recordPasskeyUse updated only the counter and lastUsedAt, so the
stored backedUp flag kept its registration-time value and the Synced
badge in account settings could go stale after an authenticator
started or stopped syncing. Return the flag from the verification
helper and persist it in the same compare-and-swap update that
advances the counter, so a replayed assertion cannot flip it.

(cherry picked from commit eae6b4816d)

Original-PR: https://github.com/LibreChat-AI/LibreChat/pull/16255
2026-10-01 03:46:16 +00:00
Marco Beretta
f903cf36bf 🔑 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.

(cherry picked from commit 59014b53c2)

Original-PR: https://github.com/LibreChat-AI/LibreChat/pull/16254
2026-10-01 03:46:16 +00:00
lia-by-librechat[bot]
33a11f3e6a 🥧 feat: Show Last-Turn Token Usage Beside Conversation Totals (#16230)
* 🥧 feat: Show Last-Turn Token Usage Beside Conversation Totals

* fix: Keep Token Usage Scoped to the Viewed Response

* fix: Bind Waiting Token Usage and Preserve Server Response IDs

* style: Sort Responses SDK Test Imports

* fix: Reconcile Token Usage at Stream Lifecycle Boundaries

* fix: Retain Stopped Context and Migrate Usage at Conversation Handoff

* docs: Capture Token Usage Panel Before and After

---------

Co-authored-by: Lia <lia@librechat.ai>
(cherry picked from commit 33f02f1148)

Original-PR: https://github.com/LibreChat-AI/LibreChat/pull/16230
2026-10-01 03:46:16 +00:00
Marco Beretta
1e7b4a9bbd 🎨 feat: Check Color Tokens and Class Existence (#16041)
* 🎨 feat: Check Color Tokens and Class Existence

Moves the Tailwind colors out of createTailwindColors() and into
packages/client/src/theme/tokens.css as `@theme inline`, published as
@librechat/client/theme.css and imported by the app's stylesheet. Runtime theme
switching is unchanged: each token still resolves to the custom property
ThemeProvider rewrites, and `@theme inline` is what keeps it out of a frozen
variable. The palette scales are closed, so an undeclared shade is no longer a
color.

Reading the tokens is what lets @shadcn/lint check them, so no-unknown-classes
goes on and no-raw-colors gains undeclared-token detection. Between them they
found dead classes the app has been shipping: 59 `token-`-prefixed color
classes that generate nothing, `transition-color`, `scrollbar-hide`,
`pointer-cursor`, `mt-text-sm`, `dark:gpt-dark-gray`, `-ml-0.9`, `-mt-0.8`,
`transition-width` and `overflow-anchor-none`, all repaired or removed here.

The library's own config gains tailwindcss-animate, since its components write
`animate-in` and the accordion keyframes.

* 🧽 refactor: Delete the Plain `*-token-*` Rules the Tokens Replace

`client/src/style.css` defined `.text-token-text-{primary,secondary,tertiary}`,
`.border-token-border-{light,medium}` and `.bg-token-surface-secondary` as plain rules,
so the 63 call sites this pull request renamed were painting their token rather than
nothing. The rules have no consumer left once the names are gone, and they sat outside
`@layer utilities`, where an unlayered rule beats every utility on the same property:
keeping them would hold that cascade for any class attribute that reintroduced a name.
Deleting them is what lets the variants written beside those classes apply — the entity
avatars take `dark:bg-surface-tertiary` in dark mode, and the two action-header fields
take `hover:border-border-heavy` on hover.

Two files the rename touches carried lint debt the changed-file gate attributes to this
pull request once they appear in the diff: `ActiveSetting.tsx` was an unreferenced mock
component whose hard-coded copy fails `i18next/no-literal-string`, and `Retrieval.tsx`
computed a `vectorStores` value nothing reads. Both are removed. `tokens.spec.ts` takes
its `structuredClone` polyfill and its Tailwind module loader through imports, which
`@typescript-eslint/no-require-imports` requires of a TS file.

* ✅ test: Cover the Token Utilities From a Browser

Whether an element still takes its token color after the plain rules are gone is only
answerable in a rendered page, so the four behaviours this change turns on get a tagged
scenario in the mock harness: the account-menu email resolves `--text-secondary` instead
of inheriting the menu's primary text color, a theme definition installed at load
recolors that same row to its own value (what `@theme inline` exists for), the mention
menu's frame resolves `--border-light` rather than falling back to `currentColor`, and
the login email field transitions `color`/`border-color` for 200 ms instead of `all`,
which is what `transition-color` left it doing. Each reads the theme's custom properties
through the browser rather than restating a hex, so the same assertions hold in light
mode, dark mode and mobile emulation.

* 🩹 test: Settle the Shell Before Locating the Account Button

Probing `nav-user` visibility straight after `goto` reports the desktop sidebar as absent,
because nothing has rendered yet, and the fallback then waited on the mobile-only header
toggle until the test timed out — the two account-menu scenarios failed that way on both
desktop projects while passing on mobile. Waiting for the composer first settles the shell,
and the fallback click carries a timeout so a missing toggle fails fast instead of hanging.

* 🩹 test: Open the Drawer Before Reaching the Account Button

Below `md` the account button renders inside the drawer's own header, off-canvas until
the toggle opens it: a locator calls it visible, a click waits for it to stop moving, and
the two account-menu scenarios timed out on the mobile project. The toggle is `md:hidden`,
so its own visibility is the layout probe — click it when it is there, then the button is
reachable in both layouts.

* 📝 docs: Point the Theme Setup and the Lint Contract at What Ships

The theme README's setup still told a consumer to rebuild the color map in
`theme.extend.colors` — the map this change deletes — and never mentioned the published
stylesheet, so following it leaves the semantic utilities ungenerated. Steps 3 and 4 now
import `@librechat/client/theme.css` and the config keeps only content, dark mode and the
preset, with the removal called out as the breaking change it is.

`CLAUDE.md` said five design rules run and that `no-unknown-classes` stays off because the
repository is on Tailwind 3.4; this change enables it. That section now describes six rules,
what the rule cannot see and therefore what the `allow` list is for, that `no-raw-colors`
also reports an undeclared token, and the distinction a reviewer needs for this diff: a
raised suppression count usually means a new override, but a rule that starts resolving
class names it used to skip reports styling the tree already carried.

* 🩹 fix: Publish the Token Stylesheet as a File, Not a Folder

tsdown's `copy` reads `to` as a destination directory, so `{ from: 'src/theme/tokens.css',
to: 'dist/theme.css' }` produced `dist/theme.css/tokens.css` — a directory where the
package's `./theme.css` export pointed, which makes
`@import '@librechat/client/theme.css'` fail for every consumer of the published package.
The copy now keeps the file's name in `dist` and the export maps `./theme.css` onto
`./dist/tokens.css`; `require.resolve('@librechat/client/theme.css')` answers with that
file after a build. The app is unaffected either way, because `client/src/style.css`
imports the tokens from source so a lint or CI run needs no prior build — which is exactly
why nothing here noticed.

* 🎨 fix: Give the Bash Command Pane the Code Surface Role

Repairing `dark:bg-gray-950` by swapping in this palette's darkest shade kept the pane on a
raw value: `gray-900` is a scale entry, so no theme — custom, high contrast, or a future
one — can recolor a surface that every other code pane takes from `surface-code`
(`DiffView`, the user-turn code bars). It now takes that role in both modes, which also
drops the light/dark split the element carried for no reason.

Appearance moves with it: dark goes to `#212121` instead of `#0d0d0d`, light to `#f7f7f8`
instead of `#ececec`, matching the diff pane directly above it in the same card.

* 🩹 fix: Stop Hand-Copied Tailwind Rules From Outranking Their Utilities

`client/src/style.css` carried a block of Tailwind's own v2/v3 output copied in by
hand — `.hidden`, `.overflow-y-auto`, `.overflow-x-auto`, `.truncate`,
`.text-ellipsis`, `.animate-spin`, `.grow` and a `--tw-*`-based `.transform`. Under
v3 those sat beside the generated utilities and lost to anything later in the sheet.
Under v4 the utilities live in `@layer utilities` and these rules do not, so they beat
every utility for their property, variants included: `hidden sm:flex` and
`hidden md:flex` resolve to `display: none` at every width.

Two surfaces were gone because of it. The welcome screen's disclaimer
(`Chat/Footer.tsx`, `hidden … sm:flex`) never appeared, and the header's right-hand
control cluster (`hidden items-center gap-2 md:flex`) took the bookmark menu and the
temporary-chat toggle with it. `scenarios/welcome-disclaimer.spec.ts`,
`scenarios/temporary-chat-icon.spec.ts` and `bookmarks.spec.ts` fail on the parent
branch's build and pass here; nothing else in the style-sensitive e2e set changes.

Tailwind generates every declaration removed here, so the only behavioural difference
is `overflow: overlay`, which the copies set and which Chrome has aliased to `auto`
for years and other engines never implemented.

* 📝 docs: Load the Documented Tailwind Config From the Documented Stylesheet

v4 reads no config file unless a stylesheet says so, and the setup's step 3 imported the
tokens without an `@config` line, so the config step 4 tells a consumer to write — the
preset, the `content` globs, class-based dark mode — never applied. Both of this
repository's own entries carry the directive (`client/src/style.css`,
`packages/client/src/theme/theme.css`); the example now does too, and step 4 says that the
file only takes effect through it.

* ✅ test: Cover the Token Checks and the Published Stylesheet From a Browser

Two `@scenario`-tagged specs for what this change turned on. The first asks the
flat config, through a stdin probe, what a caller hears for a class Tailwind
cannot generate (`transition-color`) and for a colour token nobody declared
(`bg-surfce-primary`): both rules report, both name the spelling the author
meant, and the correctly spelled neighbours stay silent, which is what makes the
report about those two classes rather than about the probe. The second resolves
the `./theme.css` export the way a bundler does and asserts it lands on a file
that declares the `@theme inline` tokens and ships inside the package's `files`
— the export resolved to a directory once, and a consumer's `@import` is where
that failed.

* 🩹 fix: Record the Backlog the Rebase Brought Into the Enabled Rules

The 28 `dev` commits this stack caught up with added styling to three files the
full-tree sweep lints, and the recorded counts predate them: `ToolApproval.tsx`,
`Chat/Trace/Viewer.tsx` and the `TemplateTable.tsx` mockup reported through the
baseline, which is what the ESLint config regression gate compares. Those
violations are `dev`'s existing styling arriving in the rules' scope, so they
are recorded rather than restyled, and the count in CLAUDE.md follows.

* 🩹 fix: Ship the Animation Plugin With the Preset Consumers Load

The components published here write `animate-in`, `fade-in-0`, `zoom-in-95` and
`slide-in-from-*` — dialogs, popovers and dropdowns — and those are
`tailwindcss-animate` utilities. The plugin was registered only in
`packages/client/tailwind.config.js`, which is neither exported nor in the
package's `files`, so a consumer following the documented setup loaded the
preset and got no CSS for any of them: the surfaces appeared without their
motion and nothing said why.

The preset registers the plugin, `tailwindcss-animate` joins `tailwindcss` and
`tailwind-merge` as a peer dependency, and the consumer contract says so. The
new `@scenario:the-published-preset-generates-the-components-animations`
compiles the preset the way a consumer's build does — no app config — and
requires CSS and keyframes for each of those classes, with `p-4` as the control.

* 🩹 fix: Point the Documented Consumer Globs at the Files That Ship

Step 4 of the theme README handed a consumer
`./node_modules/@librechat/client/dist/**/*.js` as the content glob that reaches
this package. `tsdown.config.mjs` sets `fixedExtension: true`, so `dist` holds
`index.mjs` and `index.cjs` and never a `.js` — the glob matched zero files. A
consumer following the documented setup scanned only their own `src`, so every
utility that appears exclusively in a published component (dialog, menu, button
surfaces) was generated for nobody. The SPA never saw it: `client/tailwind.config.cjs`
scans `../packages/client/src`, the source, not the built package.

The glob now reads `dist/**/*.{js,mjs,cjs}`, and a scenario reads it back out of
the README rather than restating it, so the prose and the shipped file names
cannot drift apart again: it resolves the globs against the built package and
asserts they match every javascript module the export map points into `dist`,
and that those modules really do carry class names to find.

Against the previous README the same glob expansion matches `[]`; against this
one it matches `dist/index.mjs` and `dist/index.cjs`.

* 🩹 fix: Settle the Baseline, the Peer Metadata and the Comment the Rules Left

Three records that disagreed with the code they describe, all of them surfaced
by this pull request's own CI lane on a81c4a3.

`eslint-suppressions.json` recorded 10 `no-restyle` violations for
`client/src/components/Chat/AddMultiConvo.tsx` while the file has 9: the base
branch repaired one (`blur-sm` → `blur-xs` in a3e450de) without re-recording,
and this branch's baseline commit replayed the stale count over it. The
suppressions validator reads the whole baseline once the file is in the diff, so
it failed the Static Checks job with exactly that line. `npm run lint:design:prune`
drops the unused one; the trailing newline the runner strips is restored.

`package-lock.json` never received the two peers `packages/client/package.json`
declares: `tailwindcss` (added on the base branch) and `tailwindcss-animate`
(added here). The resolved tree was already correct — `tailwindcss-animate@1.0.7`
is hoisted — but the workspace entry's `peerDependencies` block disagreed with
its manifest. `npm install --package-lock-only` adds the two lines and changes
nothing else.

`eslint.config.mjs` still explained, four lines above the rule, that
`no-unknown-classes` "is deliberately not enabled" because "this repo runs
tailwindcss 3.4 with a JS preset". It is enabled at error on line 268, and the
comment beside the rule already says why that is now answerable.

* 🩹 fix: Import the Token Stylesheet Where the Consumer Probe Compiles

The standalone-consumer scenario compiled `@import 'tailwindcss'` plus the
package's config and nothing else, which is where the colours used to come from:
`createTailwindColors()` spread them into `theme.extend.colors`. They are
declared in `tokens.css` as `@theme inline` now, so that entry emitted no
`border-border-light` at all — compiled here, the class count is 0 — and the
divider fell back to `currentColor`, failing the e2e lane on shard 3 with the
text ink (`rgb(200, 0, 0)`) where the border role belongs.

The probe now imports the published token stylesheet between Tailwind and the
config, which is step 3 of the theme README and what a consumer following it
writes; the path comes from the package's own `./theme.css` export so it cannot
drift from what ships, and the build guard requires that file too. With the
import the utility compiles as
`border-color: rgb(var(--border-light) / var(--border-light-alpha, 1))`, and the
radius assertions are untouched: `rounded-sm` still resolves
`calc(var(--radius, 0.5rem) - 0.375rem)`.

The scenario joins this change's acceptance contract, because the invariant it
now protects is this one's: a consumer gets the package's colours from the
stylesheet, not from a config block.

* 🧽 refactor: Stop the Dashed Avatar Border From Depending on Emission Order

Both avatar placeholders carried `border-border-medium` and `border-black` on
one element. Same specificity, so the winner is whichever Tailwind emits last,
and compiling this tree's own config puts `.border-black` at line 3021 and
`.border-border-medium` at 3042 — the token wins today, which is why the
placeholders looked unchanged through the rename. Nothing states that order,
so a change in how Tailwind sorts utilities would silently turn the border
black.

`border-black` is deleted at both sites. The border keeps painting
`border-border-medium` exactly as it does now, and the recorded counts do not
move: neither file has a `no-raw-colors` entry, and the suppressions validator
stays green over the 74-file diff.

* 🎞️ fix: Preserve Component Animations When Integrating Canary

* 🎛️ fix: Let Shared Primitives Own Input and Tab Styling

* 🔗 fix: Preserve Auth Link Color Transitions

* 🧪 test: Verify Auth Link Color Transitions

* fix: Preserve Semantic Color Enforcement and Consumer Setup

* fix: Preserve Consumer Tailwind Palettes

* fix: Copy the Compatibility Palette Into the Docker Client Build

---------

Co-authored-by: berry-13 <berry-13@users.noreply.github.com>
(cherry picked from commit 78694f8c1e)

Original-PR: https://github.com/LibreChat-AI/LibreChat/pull/16041
2026-10-01 03:46:16 +00:00
Marco Beretta
4617302116 🔑 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.

(cherry picked from commit 471abaa64d)

Original-PR: https://github.com/LibreChat-AI/LibreChat/pull/14715
2026-10-01 03:46:16 +00:00
Marco Beretta
cd44344647 🔔 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.

(cherry picked from commit b947738d0d)

Original-PR: https://github.com/LibreChat-AI/LibreChat/pull/15025
2026-10-01 03:46:16 +00:00