* 🪟 feat: Show a Running Subagent's Current Row on Its Card
* 🪟 fix: Draw the Card's Row Live and Skip Label Reservations That Draw Nothing
* 🪟 fix: Show a Card's Row Only While Its Thread Is Followed, and Throttle a Detached Row Too
* 🪟 chore: Sort the Card Spec's Imports
* 🪟 fix: Draw the Card's Row as a Picture That Registers, Claims and Reveals Nothing
* 🪟 test: Give the Artifact Preview Test the Props Its Type Requires
* 🪟 refactor: Keep the Shared Follower Registry in Provider-Scoped Jotai Atoms
* 👀 fix: Look Again for a Run the Caller Knows Of Before Taking It to Have No Stream
* 🗳️ feat: Let a Schedule's Owner Choose Which MCP Tools It May Use
An enrolled scheduled chat could call an MCP tool only when an operator had
listed it in config as read-only, pinned to a hash of its definition. Whether
a tool is safe to run with nobody watching is the owner's call, and read-only
is a poor proxy for it.
The consent offer now lists every MCP tool the agent graph selects on servers
whose recipient the operator declared. The owner ticks servers and tools, and
the grant stores only those. A tool is allowed at run time when the grant
lists it for the calling agent and that agent still selects it; anything else
is refused. Selecting another tool later no longer invalidates the grant.
The operator `mcpConsent.readOnlyPolicy` list is retired: the loader warns
when it is still configured. The stored grant keeps its shape.
* 🗳️ fix: Check the Server Box Only When Every Tool Is Allowed
The shared Checkbox has no partly-selected appearance, so a server with some
tools ticked showed its "allow all" box as checked.
* 🧪 test: Check the Live Catalog at the Manager Boundary Without the Retired Pin
* 🧭 fix: Check Readiness Against What the Owner Allowed, Not What the Agents Select
* 🧭 fix: Turn Away a Tool the Owner Left Out Without Failing the Run
* 🧭 fix: Load Only the MCP Tools the Owner Allowed in a Scheduled Run
* 🪪 feat: State a Turn's Shape in Its Created Frame So an Observer Applies It as Its Sender Does
* 🪪 test: Give the Request Controller Specs the Turn Helper Their Mocks Left Out
* 🪪 fix: Name the Reply an Edited or Continued Turn Starts From, and Build on It, Not the List's Tail
* 🪪 fix: Put a Plain Turn's Reply Last in the List, Where Its First Step Builds
Total blocking time is CPU time, and the hosted runner's CPU is not a constant: Lighthouse's
own benchmark of the runner moves by more than 2x between consecutive runs of one build on a
two-core runner, and blocking time moves with it. A median of three raw measurements against
a fixed budget therefore fails on the runner rather than on the page.
Rescale each run's main-thread tasks by that run's benchmark index to a reference CPU, assert
the lowest run instead of the median, and measure an over-budget batch once more before
failing. Budgets move to their own file so a fork with a heavier client changes numbers only.
* 🧭 refactor: Build One Execution Context Where a Run Enters
Each consumer of a scheduled run's identity (the host token resolver, the
scheduled MCP authority and the resource-bearer host) read the trigger body
and the restored job for itself, and the remote agent API carried a separate
`unattended` flag through tool loading.
The entry point now builds one frozen ExecutionContext: the chat controller
from the verified schedule trigger, the resume host from the saved job, and
the remote controllers from the run envelope. The initializer and tool
loading receive it as an argument. The schedule consumers project their
identity from it, and `unattended` is derived from it at the tool-loading
boundary. No client or model input sets any field.
* 🧭 refactor: Decide Whether a Run Is Unattended in Its Execution Context
* 🪪 fix: Draw a Subagent's Brief as the Dispatching Agent's Turn
* 🪪 fix: Name a Self-Spawn's Brief for Its Own Agent and Drop the Child's Model From the Brief's Heading
* 🧵 feat: Open a Background Subagent's Thread as a Conversation in the Panel
* 🧵 test: Keep the Subagents Host Spec and Add the Follow Cases Beside It
* 🧵 fix: Give the Followed Thread Its Panel Gutter and Assert It in the Browser Specs
* 🧵 test: Do Not Wait on a History Fold That Closed Before It Was Clicked
* 🧵 test: Draw a Steer the Child Took Before the Panel Opened Where It Was Taken
* 🧵 fix: Fall Back to the Durable View Only on a Confirmed Missing Stream or History
* ↩️ feat: Show Guidance a Followed Subagent Has Not Taken Yet, With Its Withdraw
* 🪟 feat: Draw a Followed Chat With Main Chat's Message List
* 🪟 fix: Leave the Page's End Marker and Screenshot Target to the Main List
* 🔒 fix: Make a Followed Thread Read-Only at the View, Not Only in Its Handlers
* 🔒 chore: Sort the Followed Thread Spec's Imports
* 👀 feat: Follow a Conversation's Running Generation With a Chat
* 👀 fix: Reattach a Dropped Follow Instead of Replacing What It Showed
* 👀 fix: Back Off When Attachments Only Fail, and Follow a Run Signalled Mid-Read
* 👀 fix: Read Stored Messages When the Status Cannot Be Read, and Nothing Once Gone
* 🧮 feat: Apply Stream Events in the Chat Class the Way Main Chat Does
* 🧬 fix: Start an Observed Regeneration Beside the Saved Answer
* 🧬 fix: Leave a Compaction's Leaf Alone and Keep a Regeneration Snapshot's User Turn
* 🧬 fix: Settle a Turn That Reused a Row Without Merging Its Request Onto It
A subagent child thread is reachable only through the parent the requester
owns: /api/messages/<threadId> answers 404 by design, and the durable thread
view sends a bounded projection, not messages. A chat pane pointed at a child
thread therefore had nothing to load.
GET /api/convos/:parent/subagents/:thread/messages returns the thread's rows
with the conversation route's projection and tool-call previews, after the
thread view's parent, lineage and tenant check. An event thread's input is
the raw payload of an external event, so its row is sent with empty text, as
the thread view already does. A second route reads the full tool call behind
a preview, reusing the conversation route's reader.
* fix: repair duplicate authorization records and revoke every matching grant
* test: verify standalone authorization repair command and keep bootstrap isolated
* test: distinguish supported aggregate disk options in DocumentDB guard
* 🗓️ feat: Align Balance Resets to Fixed Calendar Boundaries
Add balance.refillAnchor, an ISO timestamp with a fixed offset that periods align to: a refill or reset is due at the first anchor-plus-whole-intervals boundary after the last one, so every user resets at the same moment (e.g. each Monday at 00:00 UTC, or the 1st of each month). Omitted, periods keep running from each user's last refill. The gauge names the reset date for anchored periods.
* 🧭 fix: Clear a Removed Reset Anchor During Admission and Shape Balance Responses in TS
A policy built without a record now always carries refillAnchor, null when unset, so removing the setting clears a stored anchor instead of looping admission until its retry bound throws. Balance response shaping moves to toBalanceResponse in packages/api; the CJS controller delegates to it.
* fix: prevent Action writes from expanding MCP access
* fix: fence MCP grant snapshots before Action token cleanup
* fix: reject Action writes after concurrent agent deletion
* fix: enforce MCP grant provenance across saves and server replacement
* test: expect reserved MCP names after server replacement
* feat: Add Gemini Hydrogen Model Support
* fix: Restore Google History For Reachable Agents
* fix: Preserve Mixed Google Signature History
* refactor: Inject Google billing configuration at application boundary
* fix: Preserve Call Signatures From Unsupported Google Output
* chore: Use Released Agents SDK 4.2.5
---------
Co-authored-by: Lia <lia@librechat.ai>
* fix: Keep runtime MIME state out of file inspection
* fix: Preserve attachment-free inspection admission
---------
Co-authored-by: Lia <lia@librechat.ai>
* 🪟 perf: Skip Thread Rows Far From the Viewport
Opening or closing the sidebar beside a long thread laid out and painted
every row of it on every frame of the 300 ms slide, because the slide
changes the chat pane's width. In a 246-row thread that was 17 ms of main
thread per frame, 55 ms on a CPU four times slower, where the slide ran at
about a dozen frames a second with tasks over 100 ms.
A row more than a screen from the thread's viewport is now skipped by the
browser (`content-visibility: auto`), so a change that touches the whole
thread costs only the rows near the reader. Rows within a screen are left
exactly as they were: none of them gains the clipping and containment that
skipping implies. A skipped row keeps the size it was last laid out at, so
the scrollbar, the navigation rail and the mount anchor see the same
thread, and it stays reachable by find-in-page, focus and anchors.
The skip sits on the row element the rail and the mount anchor measure:
reading the box of an element inside a skipped row makes the browser lay
that row out again. Screenshot export lays every row out before it clones
the thread, since a clone has no remembered size.
The navigation rail measured every row on each frame of a width change.
It now waits for the width to hold still and measures once; a height
change, which is what a streaming reply is, is still followed frame by
frame. Alone that saved nothing, because its reads forced a layout the
frame needed anyway; with rows skipped it is a fifth of what remains.
* 🧮 fix: Keep Rows Laid Out Until Every Overlapping Capture Is Done
`revealOffscreenRows` handed each caller the thread's `watch` function as
its resume. Two captures that overlap (a second screenshot export started
before the first finished) each got one: the first to finish resumed
skipping while the second was still cloning the thread, and the second
then created another observer without disconnecting the first, which no
cleanup released. A resume called after the thread had unmounted created
an observer for a thread that was gone.
Each thread now counts its outstanding reveals. Skipping resumes when the
last one is done, a resume counts once however often it is called, and
does nothing once the thread has unmounted.
Select mutants from changed lines and ignore logging-only mutants; rank survivors by risk topic from whole-word identifier matches.
Publish one quality report comment, edited in place, with the verdict, change risk (coverage gaps and CRAP refactor hints) and mutation survivors grouped by line.
Bundle the report data into one quality-report artifact; shard artifacts are internal.
Map api/ source aliases into coverage evidence and enforce a per-shard execution budget.
Move Redis cluster runtime files out of the checkout.
Move the existing streaming fade engine into @librechat/chat and its waiting-dot, cursor and fade styles into the shared client stylesheet.
Use the effective host smoothing policy consistently in Markdown, including nested subagent content, while preserving optional renderer callbacks and raw fallback behavior.