* 🔱 feat: Simplify Steering Controls to Three Modes
* Preserve Admitted Artifacts During Interrupts
* Preserve Result Admission Across Interrupts
* Gate Interrupt for Provider-Hosted Tools
* Match Interrupt Hints to Availability
---------
Co-authored-by: Lia <lia@librechat.ai>
* 💳 feat: Show Balance in the Context Gauge as Credits, Currency, or Percent
Move the balance out of the account menu into the composer's context gauge,
below the context window, and add `balance.display` (credits | currency |
percent, default credits) to choose how it reads. Currency reuses
`interface.currency` at 1,000,000 credits per USD; percent shows only the
share of the period's allotment spent.
Settings > Account > Billing renders the same summary from the same hook, so
both surfaces show identical figures, bar and refill timing in every mode.
* 🧭 fix: Normalize the Balance Display Mode and Reuse a Fresh Reading on Hover
Admin overrides reach the client without schema validation, so an unknown
`balance.display` now reads as credits instead of being typed as a mode it is
not. Hovering the gauge mounts the balance reader each time the card opens; a
30 s stale window stops every hover from refetching, while the explicit
refetch after each turn still bypasses it.
* 🩹 fix: Restore Gauge Popover Fixes and Tighten Balance States
The popover extraction was written from a pre-sync read of TokenUsage, so it
dropped dev's viewport caps and scrolling, the hideOnInteractOutside close fix,
the Tailwind v4 outline-hidden rename, and the card's max-w-full; restore them.
Refill copy now says when a refill becomes available rather than promising a
deposit, since one lands only once the interval has passed and a charge would
exhaust the balance. An empty balance reads as fully used even without an
allotment, percent mode without one says usage is unavailable instead of
leaving the figure blank, the balance-only ring takes the balance tone (amber
until empty) and is a meter only once it has a value.
* 🪙 fix: Read a Non-Positive Refill Amount as No Auto-Refill in Settings
The server never refills when the amount is not positive, and the balance
summary already says so; Settings showed its load error instead.
* 💸 fix: Show the Insufficient-Funds Error in the Balance Display Mode
The token-balance error still printed raw credit figures, so `percent` leaked
the numbers it hides and `currency` mixed units with the gauge. It now reads
the same display mode and formatter as the balance summary: credits as before,
money in currency mode, no figures in percent mode.
The auto-refill settings row also renders its own loading and failure states,
since settings search can show it without the balance row beside it.
* 🎚️ fix: Keep Fractional Credits and Drop the Moved Popover's Suppression
Credit amounts keep up to two decimals, so an insufficient-funds message no
longer reads 100.4 against 100.3 as 100 against 100; whole amounts still print
without decimals.
The design-rule backlog may not follow code into a new file, so the extracted
popover uses the standard `transition` utility instead of the arbitrary
`transition-[opacity,transform]` (which also misses Tailwind v4's separate
`translate` and `scale` properties) and its suppression is removed. The
composer geometry spec now reads the classes from `Popover.tsx`, where the
gauge button lives.
* 🧭 feat: Let a Parent Choose Its Subagent's Code Machine Per Call
A parent agent can now pass optional `machine` / `workspace` arguments on a
subagent call to pick where the child runs, using the host-argument
extension point added to @librechat/agents.
- Each lazy child declares enums built only from machines it may reach:
admitted in the conversation's sealed codeWorkspaces, on its default or
allowlist, in the requesting principal's tenant-scoped list, and served by
a ready worker. A child the conversation pinned to a machine offers only
that machine; a child with no reachable machine declares nothing.
- On use, a request-scoped routing session in packages/api re-validates the
choice against the current request and live worker status and refuses an
invalid one with a typed, model-visible error instead of falling back. A
routed child is pinned to the chosen machine at every routing site,
overriding parent inheritance.
- Omitted arguments keep inherit-by-default routing, extended so a child
follows the machine a per-call-routed parent runs on (passing through
agents without code). A subagent keeps one machine for the whole request.
- A child whose default workspace is unavailable stays guarded unless it has
per-call choices; then it stays callable and its description asks the
parent to pick a listed machine.
- Routed children keep their tool context per execution for tool loading,
provisioning and artifact handling.
- Paused-approval bindings, the attached-machine policy hook, skill-file
priming and tool-output references account for per-call choices.
The declarations are gated on the installed SDK exporting
SubagentHostArgumentError, so this change is inert until LibreChat depends on
an @librechat/agents release that includes it.
* 🧭 fix: Reserve Default Routes Early and Route a Routed Subagent's Graph Members
- Reserve a subagent's default machine when it is placed, as
initializeAgent will resolve it (including parent inheritance), so a
concurrent call cannot claim another machine during initialization.
- Graph members spawned by a per-call-routed subagent follow its machine
when they may, unless they already initialized on their own route this
request.
* 🧭 fix: Settle Concurrent Inherited Routes and Register Routed Graph Members
- Re-read a subagent's inherited route after resolving targets, so two
concurrent calls from differently routed parents settle on one machine.
- Attribute a workspace-only conflict to the workspace argument.
- Register graph members a routed subagent initialized, so each gets the
attached-machine policy of the machine it actually runs on.
* 🧭 fix: Re-read Inherited Routes After Resolving Subagent Targets
- Re-read a subagent's inherited route after the target resolution await,
so two concurrent omitted-machine calls from differently routed parents
settle on one machine.
- Attribute a workspace-only conflict to the workspace argument.
* 🧪 test: Prove a Routed Graph Member Takes Its Machine's Policy Through createRun
- Register a resolved child's graph members inline in the lazy resolver
instead of through an exported generic helper whose test did not
typecheck.
- Drive the check through createRun's real PreToolUse hook: a member
routed to a deny machine flips from its metadata machine's allow to deny
once its parent resolves.
* 🧭 fix: Hold a Lazily Loaded Graph Member's Default Machine While It Initializes
- Pass a graph member's code flags when it initializes on its default
route, so the routing session reserves that machine before the
asynchronous initialization instead of only after it, and a concurrent
call cannot place the same agent on another machine meanwhile.
* 🧭 fix: Validate the Approval Mode Against Every Machine a Subagent May Use
- Collect each agent's default attached route and each attached machine a
parent may route it to per call, and validate the requested approval
mode against that set in createRun and both client checks.
- A child whose default is unavailable but whose per-call machine permits
accept edits no longer fails run creation; full access still requires
every such machine to permit it.
* 🧭 fix: Admit, Prime, and Cancel Per-Call Subagent Routes Conservatively
- Build scheduled pause admission from every attached machine a parent
may route an agent to, so a permissive default does not hide a
per-call machine that asks.
- Walk lazy graph-member metadata when collecting execution routes, so
historical skill files are primed for every machine such a member may
run on.
- Stop placing a canceled call after its target resolution resolves, so
it never claims a machine for an execution that will not initialize.
* 🧭 fix: Release Unused Route Claims and Scope Per-Call Machines to Their Run
- Hold a subagent's route claim per placement: a failed or canceled
initialization gives the machine back unless another execution still
holds it, and a claim is permanent once a child on it attaches.
- Fold an agent's default route into its per-call choice digest, so each
agent contributes at most one paused-approval binding target.
- Use only an agent's route policies for pause admission when it has
them, so a missing default does not make a decided route look asking.
- Drop a routable child's provisional attached-machine membership when it
resolves off attached machines.
- Offer and accept no attached machine per call while run files are
shared, since shared children must run on managed code.
* 🧭 fix: Give Back a Route When Its Placement Verification Fails
- Release a placement's hold when attach finds the child initialized on a
different machine than the one it was routed to, so a retry that
follows the unavailable-machine guidance may name another machine.
* 🧭 fix: Commit a Lazy Child's Routes Only When Its Whole Resolution Succeeds
- Keep the routes a lazy child and its routed graph members hold pending
through the child's entire resolution (settleExecution), committing them
on success and giving them back on failure or cancellation unless
another execution still holds them.
- Placements outside any call (shared graph members) still commit when
they attach.
* 🧭 fix: Drop a Failed Lazy Resolution's Config from the Graph Cache
- When a lazy child's graph resolution fails or is canceled after its
config was cached for graph reuse, remove that entry with its route, so
a later graph never reuses a config for a machine the child gave back.
* 🧭 fix: Follow a Routed Agent Through Self-Spawned Runs and Scope Routed Member Configs
- A call whose parent run was never placed (an allowSelf spawn reuses its
routed inputs) inherits the routed claim of its parent agent, which keeps
one machine per request.
- Never share a graph member initialized for a routed parent's execution
through the graph-member cache, so a failed resolution leaves no config
behind for a route it gave back.
- Race lazy target discovery with the request signal.
* 🧭 fix: Pass a Machine On Through Self-Spawned Runs of Agents Without Code
- Record the machine each agent without stateful code passes on, and let a
call from that agent's unplaced run (an allowSelf spawn) follow it when
the agent passed on exactly one machine this request.
* 🧭 fix: Keep a Pass-Through Route Only When Its Resolution Succeeds
- Record the machine an agent without code passes on with the rest of its
call's routing state: kept when the resolution deciding it succeeds,
dropped when it fails, so a self-spawn never follows a failed attempt.
* 🧭 fix: Settle a Lazy Child's Routing State at the SDK Handoff
- Wrap the run's whole lazy resolution, through the inputs handed to the
SDK, in the descriptor's settle hook, so a cancel after the host
resolver returns still gives the call's routes back.
- Roll back the per-agent tool context a pending placement set (restoring
the entry it replaced) when its resolution fails, so a retry on another
machine seeds its own context.
- Drop a failed call's shared config from the graph cache through the
same settle hook.
* 🧭 fix: Keep Per-Agent Tool Contexts on Live Placements and Queue Target Probes
- Track every pending placement that uses an agent's per-agent tool
context: a committed one sets it, a failed one hands it to a surviving
placement, and only the last failure restores the earlier entry.
- Let an unplaced run of an agent (an allowSelf spawn) defer to the routed
run of the same agent that encloses it when looking up tool contexts.
- Queue live target probes at eight in flight, below the shared status
poller's ceiling, so concurrent descriptors never misreport a healthy
machine as unavailable.
* 🧭 refactor: Load Routed Graph Members Through a packages/api Service
- Move the routed graph-member load (shared reuse, skip list, view check,
execution identity, failure policy) into createRoutedGraphMemberLoader;
the initializer only injects its dependencies.
- Thread the request and call signals into target resolution so queued
probes are skipped once canceled.
- Probe nothing in shared-file runs, where every per-call target is
attached and unusable.
- Retire pending tool-context ownership when a committed placement
installs the per-agent entry.
* 🧭 fix: Share a Lazy Child's Config with Later Graphs Only After It Commits
- Publish a default-placed lazy child's config to the shared graph cache
from the settle hook's commit, so no concurrent graph can borrow a config
whose route may still be given back.
- Resolve a child's own appearance in its graph to the child config itself.
* 🧬 fix: Default Subagents to Their Parent's Code Machine and Workspace
A subagent resolved its code machine from its own saved fields only, so
when a chat routed the parent to an allowlisted machine the subagent fell
back to its own default and whatever workspace the conversation had
selected there, or failed the parent's whole turn when none existed.
Subagents now inherit the parent's resolved attached machine when it is
their own default or on their allowlist where per-chat choice applies,
the principal can use it, the sealed decision already selected it, and no
selection names the subagent as an explicit owner. Inheritance is derived
per request from the sealed decision and current agent configuration and
fed to every routing site; it is never persisted, so existing chats and
older clients get it without a decision change. The composer mirrors it.
A subagent whose machine has no usable workspace is advertised to the
parent as unavailable instead of failing the turn; a locked decision
stays fatal.
* fix: Inherit Across Every Spawning Path, Graph Members and Deferred Code Tools
A subagent now inherits only when every agent that can spawn it, at any
depth, runs on the same machine; spawn cycles keep their own routes.
Subagent graph members inherit like explicit subagents. The deferred
execute_code loader passes inheritance to its fallback resolver. Subagent
reads and VIEW checks move to a packages/api loader shared by inheritance,
lazy descriptors and graph members. The composer lets a draft's subagent
follow its parent's machine before a workspace is picked, and keeps an
inheriting subagent's former selection without asking for a move.
* fix: Prune Spawn Back-Edges, Gate the Composer on an Inheritance Capability
Spawning parents follow the run's path semantics, so a back-edge the
descriptor tree prunes no longer blocks inheritance, and agents that spawn
each other follow their single outside parent machine when it routes them
all there. Only admitted subagents count toward the walk's node limit.
Graph members re-read and re-check VIEW when they initialize. The composer
echoes an inheriting subagent's former selection without gating on that
machine, and mirrors inheritance only when the API advertises
codeWorkspaceInheritanceVersion; approval modes keep intersecting every
machine an agent could use.
* fix: Settle Each Mutually Spawning Group on Its Own
Independent spawn cycles no longer merge into one group, so a pair under
one parent follows that parent even when another pair follows a different
machine. Also types the data-provider spec for its ES5 target.
* fix: Bound the Inheritance Walk, Normalize Parallel Roots, Move Subagent Availability to TS
The walk reads in batches no larger than the remaining node budget, stops
once the limit is reached, and runs through the run's subagent load limiter.
Roots are keyed by saved agent ID, so a parallel root such as id____1 can
never receive an inheritance entry. Resolving a lazy subagent's code route,
reporting it unavailable, and guarding its descriptor now live in
packages/api (resolveSubagentCodeAvailability, guardUnavailableSubagent).
* fix: Keep Missing Subagent Loads Parallel Near the Node Limit
Batches never shrink below eight IDs, so missing or unviewable subagents
near the limit still load in parallel under the injected limiter, and at
most a handful of reads land past the limit.
`mistral-large-2512` (and `mistral-large-latest`, which now points to it)
had no dedicated entry and fell back to the generic `mistral-large` key,
billing at Mistral Large 2 rates ($2 / $6), 4x the actual price.
- Add `mistral-large-2512` and `mistral-large-3` at $0.50 / $1.50
- Point the generic `mistral-large` fallback to the current model's price
- Pin `mistral-large-2411` to its $2 / $6 rate
- Drop the stale Sonnet 5 "revert after 2026-08-31" comments: Anthropic
made the $2 / $10 pricing standard, so the scheduled increase won't happen
Co-authored-by: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
* 🔗 feat(agents): use LibreChat prompt groups as agent instructions
Agents can link a prompt group revision or Production as their instructions. The link resolves at the start of each turn through a cached resolver. The cache clears on promote and delete. Editors without VIEW on the group see a restricted placeholder.
* fix: remove duplicate logger import from agent initialization tests
* fix: honor prompt management capabilities for linked agent instructions
* test: seed prompt manager capabilities in authorization fixtures
* fix: clear acknowledged linked prompt edits before version restore
* test: adapt merged chain coverage to prompt-aware payload helper
---------
Co-authored-by: Lia <lia@librechat.ai>
* fix: Sync Spinner Rotation Phase Across Instances
* test: Colocate Spinner Spec In __tests__
* fix: Address Review Findings on Spinner Phase Pinning
* fix: Fall Back To Legacy Media Query Listeners In Spinner
* fix: Repin Recreated Spinner Rotations And Defer Without queueMicrotask
* feat: add app-wide UI scale setting
* test: align dev's new header, drawer and combobox specs with the scaled shell
* fix: keep design-recorded arbitrary values off the same-count swap
* fix: scale composer and reasoning spacing on the spacing scale
* test: reach scaled rows and wait on the composer under the unpainted drawer
* test: cover the scaled composer at both ends of the range
* test: reload the composer scenario at each scale from the live page
* fix: leave the root style untouched at the default scale
* test: align dev's tool output and subagent inset specs with the rem classes
* fix: scale a caller's combobox height cap with its rows
* fix: size the conversation list's row estimate on the scaled drawer breakpoint
* test: align dev's conversation row status spec with the scaled drawer breakpoint
* style: sort the settings dialog imports after the dialog layer merge
* fix: scale the collapsed combobox's fallback popover width
* fix: size the upload glyph on both axes so it grows with the scale
* perf: Async Local File Saves and Compile Hot-Path Regexes Once
* perf: Check Closing Code Fences Without a Per-Length Regex Cache
* test: Build the Delivery Route Config Before Routing Instead of Mutating It
mergeFileConfig now memoizes by config identity, so the CSV fallback tests
must set textFallbackWithoutTools when they build the request config rather
than mutate the object after the agent's routing already merged it.
* fix: Write Local Buffers Atomically So Concurrent Saves Cannot Interleave
Async writeFile calls to one deterministic path (OpenID and SAML avatars)
could truncate and interleave each other. Write through a temp file and a
rename instead, and add scenario specs for local saves and longer closing
fences.
* refactor: Move Local Save Logic Into packages/api
saveLocalBuffer, the temp-upload move and the atomic directory writes now live
in packages/api/src/storage/local.ts and receive their paths from the caller;
the Local strategy in /api keeps its logging and calls through. The traversal
check now runs before any directory is created.
* fix: Copy Moved Uploads Through a Temp File and Rename Into Place
Concurrent async copies to one destination could interleave just like direct
writes, so moveLocalFile now fills a sibling temp file and renames it.
* fix: Contain Every Local Write and Move Inside Its Target Directory
The traversal check that guarded saveLocalBuffer now runs in writeLocalFile
and moveLocalFile too, before any directory is created, and the buffer
save accepts only the images and uploads base paths.
* test: Define the Success Assertion Inside the Local File Saves Scenario
* fix: Give Atomic Write Temp Files a Fixed-Length Name So Long Targets Still Fit
* test: Send Image Dimensions and Read the Message Array in the Local Saves Scenarios
* feat: Return a Navigable Progress Tree When Checking a Running Subagent
check_background_task on a running or finished-but-undelivered subagent now
returns an activity digest: the child's turns, tool calls, and replies folded
to one line each and addressed by stable positional paths. Callers expand one
node or range with expand, and page with since against a settled-node cursor.
The owning process folds the child's update stream into a bounded tree that
keeps only tool names, the model-authored intent label, the tool-authored
outcome label, statuses, timings, and sizes. Routed claims carry the tree to a
poll on any replica, lists carry counts and the node in flight, and a finished
child whose owner is gone is rebuilt from its durable public projection.
The background-task card renders the digest as a foldable tree and links the
existing subagent activity panel.
* fix: Tighten Progress Digest Verdicts, Overflow Bounds, and Rebuilt Trees
Failed reply steps and schema-rejected calls now record as errors, and an
overflowed call is counted once without retaining it in the lookup maps.
A tree rebuilt from the durable projection re-checks completed calls with the
shared failure verdict, carries the projection's truncation, and tells the
caller its paths are a reconstruction. The card localizes folded summaries
instead of rendering the server's English tally.
* fix: Measure Single-Part Message Deltas in the Progress Digest
* fix: Scope Nested Progress Ownership by Run and Count Overflow Once
Nested runs now attach to the call recorded by their own spawning run, since
provider call ids repeat across runs. Only the step that announces a call can
count it as overflow, so later sightings of an unretained or evicted call never
re-count it or reopen history. A zero-valued since cursor is rejected, and the
card labels MCP tools with the configured server names.
* 🫗 perf: Release Message Histories of Conversations the User Has Left
Long agent conversations hold 12-18 MB of message JSON each in the React Query cache, and the default 5-minute cacheTime kept every conversation visited in that window. Switching between a few of them on mobile Safari grew the JS heap past 300 MB and crashed the tab.
retainMessages tracks when each per-conversation history loses its last observer and releases it once it has no observers, is not fetching, is not pinned, and is either older than 60 s or beyond the single most recently left conversation. The routed conversation, conversations with a running job, and conversations awaiting an approval decision stay pinned; releases wait while any mutation is pending. Returning to a released conversation refetches its history.
* 🫗 fix: Own History Collection, Configure the Grace, and Pin by Server State
Per-conversation histories get an infinite cacheTime while retention runs, so React Query's own five-minute collection can no longer drop a history a running job still pins; newly seeded histories schedule a pass; the grace and recent count come from interface.historyCacheTtlMs and interface.historyCacheRecent; the approval pin is replaced by the active-jobs set, which already lists jobs paused for a live approval; and Assistants histories stay pinned because deletion reads their thread id from the cache.
* 🫗 fix: Re-arm Collection for Histories Already Counting Down and Recheck Pins Promptly
A history left before retention started still had React Query's five-minute GC timer; a momentary observer now re-arms it under the infinite cacheTime. Histories kept only because they are pinned or fetching are judged again after 5 s instead of a full TTL, so a run that ends releases its transcript promptly.
* 🫗 fix: Exempt Assistants Histories Without Polling and Leave Fetching Histories Alone
Assistants histories are now exempt rather than pinned, so they are kept without a recurring recheck timer. The startup re-arm skips histories with a fetch in flight, since detaching a momentary last observer would cancel the request; settling the fetch re-arms collection on its own.
* 🔭 feat: Recover Stale Chunks Without the Error Page and Ship Client Logs to RUM
Stale chunks: a tab left open across a deploy that opens a code-split panel
requests a hashed chunk the new deploy removed. Vite's preload handler hands
the failure to the stale-asset recovery, which reloads, but the import then
resolves to `undefined` and `React.lazy` throws a TypeError into the route
error boundary, so the error page flashes before the reload. Lazy imports now
go through `lazyWithRecovery`/`importWithRecovery`, which turn that result into
a `ChunkLoadError`; the route boundary recognizes chunk failures (and any error
while a recovery reload is underway), asks the page recovery once, and renders
a localized "Updating to the latest version…" status. When the loop guard
declines, the normal error page with its reload action shows instead. The
page recovery is now idempotent within a page, so concurrent callers join the
in-flight reload rather than tripping the guard.
Client logs: with RUM in proxy mode, the client logger's warn/error calls,
error-boundary catches and stale-asset recovery events are exported as OTLP
log records through the authenticated `/api/rum/v1/logs` proxy. Records carry
allowlisted, scrubbed fields only, follow RUM session sampling, dedupe repeats
with a count, are budgeted per minute and per page, batch with backoff, flush
with keepalive on page hide, and stop after persistent failures. The proxy
now refuses non-OTLP content types and applies a per-user rate limit.
`RUM_CLIENT_LOGS=false` turns the export off.
* 🔒 fix: Keep Client Logs Opt-In and Drop Application Error Messages
- RUM_CLIENT_LOGS now defaults to off, like console capture, so enabling
RUM proxy mode never starts a new log stream on its own.
- Error messages are exported only for engine, browser and library
generated types (TypeError, SyntaxError, DOMException, AxiosError,
chunk failures); application errors keep type, status and stack only,
since their messages can echo prompt or response text. All quoted
fragments are now redacted.
- Batches are measured in encoded UTF-8 bytes of the exact request body,
and page hide drains every queued record that fits the keepalive quota.
- Queued stale-asset events are delivered as soon as the log exporter
starts, independent of the RUM SDK loading, and marked so they are
never logged twice.
* 🔒 fix: Export Only Known Generated Error Messages and Ack Queued Events
- Error messages are exported only when the whole text matches a known
engine, browser or library message shape (property access on
undefined, "x is not a function", fetch/abort/axios status, chunk and
CSS preload failures). The error class alone no longer qualifies, since
any code can throw a TypeError carrying arbitrary text.
- Queued stale-asset events are marked logged only after the collector
accepts the record carrying them, so an undelivered event replays on the
next page; in-flight events are skipped by the SDK path.
- A fractional RUM_PROXY_USER_MAX below one falls back to the default
instead of flooring to a limit of zero.
* 🔒 fix: Hold Unacknowledged Asset Events, Re-send In-Flight Logs on Hide
- The RUM SDK flush no longer drops queued stale-asset events whose client
log record is still unacknowledged: they stay queued and persisted,
flagged so their SDK action is not repeated, and leave the queue once
the collector accepts the record.
- Page hide re-sends the records of an unanswered regular request with
keepalive; each record belongs to the latest request carrying it, so a
late response to the original request neither marks nor requeues it.
- Client-log export stops when the authenticated layout unmounts.
- The proxy refuses /v1/logs while client logs, console capture and replay
are all off, so turning RUM_CLIENT_LOGS off also stops tabs that still
hold an older startup config.
* 🔒 fix: Export Only Complete Stack Frames, Never the Message Header
Stack reduction now strips the V8 `name: message` header (including every
line of a multi-line message) and keeps only lines with a complete V8,
Gecko or WebKit frame shape that ends in a URL or absolute path with a
line number. A message ending in a source-position-like suffix can no
longer pass as a frame.
* fix: centralize RUM delivery and asset recovery lifecycle
* fix: preserve RUM page lifetime and collector acknowledgements
* fix: retain page transport quotas and recover functional chunks
* fix: scope RUM client sessions to authenticated identity
---------
Co-authored-by: Lia <lia@librechat.ai>
* fix: Separate workspace admission and transport budgets
* fix: Validate workspace run reserves and retry test types
---------
Co-authored-by: Lia <lia@librechat.ai>
Each mirrored skill now records a sync fingerprint in its sourceMetadata, hashing the mapping version, the upstream identity (source coordinates, skill path and SKILL.md blob id) and the stored definition. When a later run finds the fingerprint still matching and the stored files matching the discovered blobs, it neither downloads SKILL.md nor re-reads and updates the skill; the public viewer grant, name-conflict cleanup, stale-skill reconciliation and status counts run as before. Mirrors without a fingerprint take the full path once and record it.
- Running chats ring their avatar instead of a trailing spinner, so the row menu stays reachable mid-run.
- A reply that lands unseen lifts its chat into a Finished group under Running until it is opened; chats marked unread by hand keep their date.
- Running and Finished headings show their counts and announce them.
- Project chats now list under Chats with their folder badge; a persisted Show project chats toggle in the chat list menu restores the project-only view.
- Badges read project names from the loaded project list before fetching one by id.
- Spinner takes a strokeWidth for the thin ring.
* perf: Batch Prompt Group Permissions in the Sidebar
* perf: Skip the Prompt Permission Batch When the List Is Empty
Add scenario coverage for batched prompt row permissions.
* test: Retry Opening Prompt Row Menus Until Their Items Render
* fix: Warn When interface.webSearch Blocks Native Search in Model Specs
interface.webSearch syncs the WEB_SEARCH permission, which also gates
provider-native search since #15875. A deployment that set it to false to
hide LibreChat's search tool silently lost native search on its model
specs. Startup now names the affected specs, describes the native-only
configuration, and notes that removing the key keeps the stored permission.
Related to #16673
* fix: Warn When a Stored Role Denies Native Search With interface.webSearch Unset
* perf: Trim Per-Token and Per-Render Work in Streaming and Lists
* test: Assert Rendered Diff Rows Alongside Render Counts
* refactor: Read the Active Sidebar Row Through the Existing Index Selector
Drops the new Recoil selector: conversationIdByIndex(0) already yields a primitive id, so rows still skip re-renders on every conversation write. The DiffView row test keeps the real cn behind a spy and derives the per-row cost from the first render.
* test: Cover the Sidebar Active Row Across Chat Switches and New Chat
The Settings dialog is a Headless UI panel at z-50, not an OGDialog, so it set no dialog depth and its Select lists kept their z-40 layer, opening invisibly behind the panel. A new DialogLayer counts it as one dialog level, so popovers inside it take the depth-aware z-index they get inside an OGDialog.
* feat: Size Roles for the Select List
The Select list drew a fixed max-h-96 and min-w-[8rem], the last hard-coded sizes among the ten shared primitives. They are now the listMaxHeight and listMinWidth appearance roles, defaulting to 24rem and 8rem. The ClickHouse theme sizes the list by its trigger and keeps the 24rem cap, since Click UI caps it only at the viewport's available height.
* test: Resize the Select List From a Reference Theme
* fix: persist approval provenance in the resume claim and publish the pre-claim paths from any unapplied abort
The claim CAS now records the provenance it replaces. An abort that lands
before the resumed provider crosses its start CAS publishes those paths, so
schedule deletion, account deletion and user stops no longer label
model-authored chunks as user-submitted.
* test: add approval provenance scenario on the shared approval e2e helpers
* test: seed an earlier started segment before the unapplied abort case
* fix: label abort provenance by the published content and persist the same selection
A path the approval claim added is user-authored only once its tool call
carries output in the abort content, so an abort between the provider
start CAS and the resumed tool keeps the pre-claim labels, and an ask
answer stamped by the abort route keeps its own. AbortResult.jobData
carries the selection so the persisted row matches the final event.
* fix: keep claimed non-tool provenance paths on an abort
Only tool-call paths wait for their resumed call to complete; a steer the
claim already found in the seed content needs no decision to apply.
* fix: count a completed tool call with an empty output as applied in abort provenance
* fix: check abort provenance on the unfiltered content and remap it onto the published parts
* test: type the abort provenance overrides with the job store field names
* test: assert the preserved paths when an unanswered ask aborts
* refactor: Move Select and Menu Pointer Events to Classes
DropdownPopup and SelectContent re-enabled pointer events inside modal dialogs through inline style, which kept a no-inline-styles suppression on both primitives. Both now apply pointer-events-auto as a class and keep only the runtime z-index inline. The Select item indicator box takes the icon size role instead of a fixed h-3.5 w-3.5.
* test: Cover Popover Picks Inside Modal Dialogs
* test: Open Settings From the Drawer and Tag Indicator Scenarios
* test: Let Each Verify Project Set the Color Mode
* test: Measure the Select Indicator After the List Settles
* test: Drop the Settings Select Pick That Never Reached a Dialog
* fix: Read Theme Roles for the Last Artifact and Agent Chip Colours
The artifact mobile backdrop now reads surface-overlay like the dialog scrims, the refresh overlay over the rendered preview reads surface-media-overlay, and the agent builder's provider chip reads surface-primary and text-primary like the conversation icon chip. Monaco's built-in vs-dark canvas joins the third-party surfaces allowlist entry, and the allowlist no longer points at a closed sweep issue.
* test: Cover Theme Roles on the Provider Chip and Artifact Overlays
* 📍 feat: Show the Current Text Where a Missing Workspace Edit Belongs
Render the current-text excerpt that LibreChat-AI/code-interpreter#300 workers append to a missing edit's EDIT_CONFLICT diagnosis: a strict parse keeps it only when every row is well formed (contiguous numbers matching the stated range, a known mark, a bounded single line), and LibreChat renders it as a numbered block under its edit with a summary of which lines differ. The excerpt passes the file-content policy like a read_file result and reaches only the model; logs keep the excerpt-free message.
Also stop rendering every 409 as a text mismatch: a Code API rejection such as WORKSPACE_QUARANTINED now passes through with its own reason, and the worker's repetitive-candidate refusal is recognized.
* 🔒 fix: Name Other Attached Edit 409s by Code Instead of Forwarding Their Body
A 409 whose code is not EDIT_CONFLICT (a quarantined workspace) now gets a host-worded message naming only its validated code, with recovery guidance for WORKSPACE_QUARANTINED, and logs keep a body of just that code.
* 🧾 fix: Present Quoted Edit Excerpts as Partial Context, Not Text to Copy
A worker excerpt can window a long region and shorten wide lines with an ellipsis, so the guidance now asks the model to correct old_text against it and use read_file for lines it leaves out or shortens, here and in the attached edit_file descriptions.
* 🔐 fix: Quote Edit Excerpts Only Where the Workspace Allows read_file
A workspace that offers edit_file without read_file now never receives the worker's current-text excerpt, so a failing edit cannot read file content the operation policy withholds.
---------
Co-authored-by: Lia <lia@librechat.ai>
* feat: Remember Tool Approvals Per Conversation
Adds an opt-in "Always allow" choice to the tool approval card. When
endpoints.agents.toolApproval.allowAlways is true, the server marks eligible
paused calls with allow_always; approving with scope "session" stores that
exact tool name on the conversation, and later runs in the same conversation
fold the stored names into the policy as exact-name allow entries.
The server enforces every step: the resume route rejects a session scope the
pause did not offer, eligibility is rechecked against the live policy before
storing, the list is written only through an owner-scoped bounded method, and
generic saves and imports cannot set or clear it. Admin deny and ask rules and
programmatic hooks still win, stored names are ignored under dontAsk or when
the flag is off, and native code tools stay under the code approval picker.
The flag defaults to false, so existing deployments keep prompting.
* fix: Share the Effective Approval Policy and Persist Allows After Resume Fences
Offering, resume re-check, scheduled admission and createRun now read one
policy from buildEffectiveToolApprovalPolicy: endpoint rules healed against
MCP alias spellings, then the conversation's remembered tools. A call held by
a healed ask rule is no longer offered "Always allow", and a scheduled fire
whose known tools are all remembered is no longer rejected as pause capable.
The remembered-tools cap and name length cap move to
toolApproval.allowAlwaysMaxTools and allowAlwaysMaxToolNameLength (defaults
64 and 256). The card stops offering the choice for new tools once the cap is
reached instead of silently approving once.
The resume route stores remembered tools only after the schedule and project
context fences pass; a storage failure still approves the call once.
* fix: Offer Always Allow Only When It Will Hold
Offer allow_always only when storing the name would auto-approve the next
identical call on the run's own path: every MCP spelling of the tool passes
the healed static policy and no programmatic or plugin approval hook can
apply to it (the pause payload does not record which hook asked).
Remembered names now expand to every alias spelling of the same tool, and a
deny or ask on any spelling keeps the tool ineligible. A table-driven spec
walks the invariant through the real hook wiring.
* fix: Recheck Approval Hooks Before Remembering a Resumed Approval
The resume-time eligibility recheck now applies the same programmatic and
plugin PreToolUse hook check as marking, with a hook context built from the
resume request and the live plugin hook source. A hook registered after the
pause turns the choice into a one-time approval: nothing is stored and the
resume continues.
Document that toolApproval.allowAlways should be enabled only once every
replica supports it, since older replicas ignore the choice.
* fix: Judge Always Allow Offers Against the Run's Live Aliases and Active Cap
* fix: Charge Only New Tool Names Against the Remembered Approval Cap
* fix: Recheck Remembered Approvals Against the Paused Run's Aliases
* chore: Sort Imports in Agent Run After Rebase
* 📝 docs: Describe Attached-Workspace Lanes, Sandbox Scratch, and Skill Files in Tool Descriptions
- Lane-mode `cwd` now states that any call outside `.worktrees/<name>` (with or
without cwd, and file tools on such paths) is checkout-wide: it waits for
running worktree calls and blocks new ones until it finishes, so checkout-wide
calls are reserved for creating, pruning or removing worktrees.
- `command`/`cwd` state that the command starts in cwd, so the model does not
also cd into it; the lane-mode cd hint says the call ran checkout-wide.
- Workers advertising the native SRT sandbox profile (`anthropic-srt`,
`anthropic-srt:<preset>`) get a bash bullet that / and /tmp are read-only and
scratch files belong in $TMPDIR or the workspace. Carried as
`codeWorkspace.nativeSandbox` into tool definitions and the bash tool.
- The attached skill-aware `read_file` description says skill files are not on
the attached machine and must be written into the workspace to run there.
- Tightened the attached bash description so the native variant stays within
the 1024-character tool description limit.
* 📝 fix: Keep the Skill-Copy Warning on the Command-Only Workspace's Skill read_file
A workspace that offers execute_command but not read_file falls back to the
skill-only read_file definition. It now carries the same sentence as the
attached skill-aware definition, so the model knows bash_tool cannot reach
skill files by path there.
* 📝 fix: Name bash_tool in the Skill-File Warning Only When It Is Registered
The skill-copy sentence on attached read_file definitions now depends on the
attached bash_tool being registered beside it (includeBash and an advertised
execute_command), for the attached skill-aware definition, its custom
line-limit variant, and the skill-only fallback. Workspaces without commands
keep the plain skill description.
Attached workspace file tools now append a short, specific explanation when
the worker rejects a path with 422:
- NOT_FOUND from a current worker, or INVALID_PATH carrying its
"Workspace path does not exist" message through an older Code API, says
the path does not exist: wait for a command still writing it, or list the
directory to find the right path. For create_file it names the missing
parent directory.
- An older worker's bare INVALID_PATH on read_file, create_file or
edit_file, which it also returns for a missing file, lists the possible
causes: not written yet, a directory or symlink, or a missing parent
directory for create_file.
Other rejections are unchanged.
* 🏃 fix: List Every Running Chat in the Sidebar's Running Group
The Running group partitioned the Chats list's own rows, so a running chat
filed in a project, a pinned chat, or one past the loaded pages never
appeared in it. Running chats the loaded rows do not hold are now fetched
by id and merged in newest first, with a project badge on filed chats.
Narrowed lists (search, filters, facets, archive) keep only their own rows.
* fix: Keep Fetched Running Rows Current, Accessible, and Scoped
- Fetch only under the newest-first sort that shows the Running group.
- Re-ask within two seconds for a record not written yet, so a short
run is not missed; keep the 15-second refresh once it exists.
- Leave archived chats out of Running.
- Patch and clear the fetched rows through updateConvoInAllQueries and
removeConvoFromAllQueries, so renames, pins and removals show at once.
- Carry the shared-link state the list endpoints derive.
- Seed an empty conversation cache with the fetched record for navigation.
- Describe the focusable row with its project name.
* fix: Preserve Running Chat Cache Updates and Picker Keyboard Activation
* fix: Open the Assistant Picker Through Its Supported Keyboard Handler
* test: Keep SSE Cleanup Query Client Cancellation Compatible
* fix: Keep Temporary Chats Out of the Running Sidebar
* fix: Preserve Running Rows Across Initial Fetch Cancellation
* fix: Preserve Running Removal and Server Read Authority
* fix: Record Running Removal Before Query Creation
* test: Type Running Query Regression Props Explicitly
* fix: Keep Chat Settings Out of Running Sidebar Rows
---------
Co-authored-by: Lia <lia@librechat.ai>