* 📮 fix: Count Undelivered Background Results as Outstanding
* fix: Reconcile delivered tasks, discard exactly, and count pending subagent results
* fix: Settle manually claimed remote deliveries and keep pending controls while wake-ups drain
* fix: Report dead-lettered deliveries as failed and read subagent wake-ups from the durable store
* fix: List restored dead letters and retire deliveries on local durable claims
* 🐢 fix: Back Off Waiting Completion Wake-ups and Deliver Them When Ready
* fix: Signal every readiness path and make the completion wait cap configurable
* 🧷 fix: Wait for Long Dispatch Turns Before Giving Up Background Code Results
* fix: Mark held completion deliveries instead of pipeline expedite, and announce store-won approval expiry
* fix: Keep code tasks protected and wait without a fixed cutoff
* fix: Scope settle expedites to the resumed conversation and close the remaining signal gaps
* style: Format the settlement waiter
* fix: Announce a won approval expiry once and release subagent wake-up registrations
* fix: Outlast terminal persistence before giving up an unanchored code result
* fix: Anchor code results the moment their dispatch turn settles
* fix: Scope harvest epoch pinning to the owning stream
---------
Co-authored-by: Lia <lia@librechat.ai>
* 🐢 fix: Back Off Waiting Completion Wake-ups and Deliver Them When Ready
* fix: Signal every readiness path and make the completion wait cap configurable
* fix: Mark held completion deliveries instead of pipeline expedite, and announce store-won approval expiry
* fix: Scope settle expedites to the resumed conversation and close the remaining signal gaps
* fix: Announce a won approval expiry once and release subagent wake-up registrations
* 🧪 ci: Count System Instructions in Mock Model Usage (#16350)
The e2e fake model reported input tokens for the chat messages alone, because the SDK hands a test override model the pruned messages without the systemRunnable pipe. Once #16301 gave every memory-enabled chat a system prompt, the calibrated context snapshot put used tokens below the instructions and the gauge dropped its Messages row. Count input over the complete prompt, as a real provider bills it.
---------
Co-authored-by: Lia <lia@librechat.ai>
Tokenize budgeting inputs in bounded chunks instead of charging a token per UTF-8 byte above 4 KiB. Subdivide long whitespace/non-whitespace runs to bound BPE merge work and preserve surrogate pairs. Keep strict provider-accounting counts and unavailable-tokenizer fallbacks separate.
Cover both encodings, SDK slice composition, programmatic tool prompts, summarization, real overflow, cache reuse, and failure recovery. Related to #16278.
Co-authored-by: Lia <lia@librechat.ai>
* 🔕 perf: Back Off Idle Durable Agent Recovery Polls
* 🎛️ style: Format Queued-Turn Recovery Test
* fix: Preserve Durable Recovery Wakeups and Discovery Invariants
---------
Co-authored-by: Lia <lia@librechat.ai>
* fix: Surface Persistent Memory Before First Save
* fix: Distinguish Unreadable Memory From Empty Memory
---------
Co-authored-by: Lia <lia@librechat.ai>
Update package repository and bugs URLs, GitHub links in docs, templates and comments, and image references (compose files, deployed-update, Helm values and renovate hints) from danny-avila to LibreChat-AI / librechat-ai. Covers the rag-api repository and its images, which moved to the organization. Sponsor links and the sealed star-history chart are unchanged.
* fix: constrain agent selector to 480px and 10 unsearched agents
The Agents panel selector dropdown now caps at 480px tall with the option
list scrolling inside, and lists at most 10 agents while the search field
is empty; typing lifts the cap so search still reaches every agent.
ControlCombobox gains optional popoverMaxHeight and unsearchedLimit props,
so every other selector keeps its current fixed 300px list.
* fix: make the agent selector cap configurable, viewport-safe, and selection-preserving
The unsearched list cap now reads interface.agentSelectorLimit from
librechat.yaml (default 10), the popover cap yields to Ariakit's
available height so a short viewport never pushes options offscreen,
and a selected agent ranking past the cut keeps the last slot instead
of disappearing until searched for.
* fix: forward agentSelectorLimit through the interface loader and guard it at the client
loadDefaultInterface whitelists interface fields, so the new knob never
reached /api/config without explicit forwarding; and values that bypass
interfaceSchema (raw yaml reads, principal-scoped admin overrides) are
normalized back into 1..100 at the client so a bad override cannot empty
the selector.
* 🛝 refactor: Route Packaged Chat Completion Frames Through a Writer
* style: Match Chat Completion Contract Test Import Order
* fix: Avoid ES2022 Array Methods in Protocol Contract Test
---------
Co-authored-by: Lia <lia@librechat.ai>
* Add client side tools
* 🚦 fix: Ask the Model to Call Caller-Executed Tools Alone
* Add client tool continuation replay tests
* Fix clientTools docstring
* fix: return only tools that have been actually applied
* 🔁 fix: Continue a Caller-Executed Tool Exchange Across Requests
* fix: handle null values for tool descriptions and parameters in client tools
* 🧩 fix: Keep the Arguments of Every Tool Call in a Streamed Message
* Fix PR comments
* fix: Preserve client tool handoff across SDK event ordering
---------
Co-authored-by: Lia <lia@librechat.ai>
* 🛍️ feat: Add Programming App to OpenRouter Categories
* style: Format OpenRouter category override test
---------
Co-authored-by: Lia <lia@librechat.ai>
* feat: add GPT-6 Sol and Luna support
* fix: normalize Sol and Luna reasoning requests
* fix: align Sol and Luna effective Responses routing
* fix: honor server routing policy for model uploads
* test: await system grant indexes before writes
* fix: verify model upload policies against runtime initialization
---------
Co-authored-by: Lia <lia@librechat.ai>
* feat: add Claude Opus 5.5 support
* fix: preserve Opus 5.5 settings through provider adapters
* fix: preserve model-hidden settings when pruning parameters
---------
Co-authored-by: Lia <lia@librechat.ai>
* 🌊 fix: Prevent Agent Model Stream Idle Timeouts
* fix: Preserve Default Proxy Dispatcher Construction
* test: Assert Agent Transport Timeout Policy
* test: Cover Direct Model Dispatcher Reuse
* fix: Scope Agent Model Transport Timeouts
* fix: Enforce Agent Timeouts Across Direct and Summary Clients
* fix: Align Model Transport Adapter Types
---------
Co-authored-by: Lia <lia@librechat.ai>
* feat: report dispatch, settlement and elapsed timings from check_background_task
The poll tool described a background task only as running or settled, with no
notion of when: a caller could not tell a task dispatched seconds ago from one
stuck for an hour, and a collected result carried no settlement time.
Ordinary and subagent tasks both already stamp dispatch and last update in the
registry, so the poll payload now serializes them the way the rest of the app
serializes time (ISO-8601), plus the elapsed span because a polling model has no
clock of its own. The durable receipt a poll falls back to after a restart
already stored its settlement time; it is carried through the claim projection so
a recovered poll reports settlement too.
* test: drive the timing assertions from the assigned dispatch stamp
The registry dispatch stamp is strictly increasing and process-global, so it is
not the mocked clock: the poll test now reads the stamp the registry assigned and
drives the clock from it. Four durable-claim assertions admit the settlement
stamp the projection now carries, and the new block is Prettier-formatted.
---------
Co-authored-by: Lia <lia@librechat.ai>
* fix: preserve Insights with guarded ACL role updates
* fix: reject combined $bit operators in ACL permission writes
* test: type the permission-bit spies without never casts
* test: settle ACL index builds before opening the transaction
* fix: replace ACL mask partitions with single-operator bit writes
* style: drop the now-unused RoleBits import
* fix: split two-sided permission bit writes into single operators
* fix: make ACL role replacement one atomic guarded write
* fix: export the permission write retry ceiling
* fix: retry ACL mutations per document and preserve atomic permissions
---------
Co-authored-by: Lia <lia@librechat.ai>
* fix: preserve Insights with guarded ACL role updates
* test: settle ACL index builds before opening the transaction
* fix: replace ACL mask partitions with single-operator bit writes
* style: drop the now-unused RoleBits import
* fix: make ACL role replacement one atomic guarded write
* fix: export the permission write retry ceiling
* fix: retry ACL mutations per document and preserve atomic permissions
---------
Co-authored-by: Lia <lia@librechat.ai>
* ⚡ perf: Throttle Code Highlighting While a Message Streams
* fix: harden streamed code highlight throttling
* test: cover wall clock changes during highlighting
* style: tidy highlight regression test
* fix: restart highlight work across lifecycle changes
* style: avoid nested highlight timing ternary
* fix: propagate highlight throttle to startup config
* fix: share and validate highlight throttle
* fix: keep streamed code visible during highlighting
* test: stream highlight tool arguments
* fix: preserve highlights when cadence config resolves
* fix: reschedule highlights when cadence changes
* test: preserve default fake tool chunking
* fix: prevent stale streamed highlights
* test: open the tool pane before asserting streamed highlights
Every scenario in this file waited for highlight tokens without opening the
card. Dev's #16143 stopped passing a closed pane any code at all, so the four
runs polled a card that renders raw text and had nothing to find: the failed
traces show the disclosure at aria-expanded="false" for the whole run, with no
click against it and no tokens in the code element.
Highlighting is now asserted through the card's disclosure, which ProgressText
owns and which carries an aria-expanded state only once the card has input to
show, so waiting on it also waits for the first streamed argument chunk. The
open happens inside expectHighlightedCode, so a scenario cannot assert tokens
without it, and it lands while arguments are still streaming, which is the only
window where the throttle is under test at all.
* test: reopen the rebuilt card for the settled highlight
Opening the pane got the streaming assertions passing and the traces show 240
highlight spans mid-stream, so the throttle itself lands. The settled check
still failed because persisting the streamed message rebuilds the card, and a
rebuilt card starts closed while autoExpandTools is off: the disclosure goes
back to aria-expanded="false" and a closed pane renders raw text.
The settled and cancelled states now assert through the same open-then-wait
helper, so each one measures the card the reader would actually be looking at
instead of the tokens the streaming card happened to leave behind.
* test: leave a window to cancel a streaming highlight
With the settled assertions fixed, the cancellation scenario timed out on the
Stop button instead: it waited for a highlight before stopping, and the ~40
argument chunks it streams at 35 ms are gone in under two seconds, so the run
had already finished and there was nothing left to cancel. It failed on all
three attempts.
The card is now opened and the run stopped before any token is awaited, since
tokens after cancellation are what the scenario is about, and the cancel
variant streams its arguments at a wider cadence so the window does not depend
on how loaded the runner is. Only that label changes cadence; every other
scenario keeps the timing it had.
* fix: preserve initial highlights and honor shared-page cadence
---------
Co-authored-by: Lia <lia@librechat.ai>
* ✒️ fix: Persist a Generated Title Before the Turn Ends
* 🧷 fix: Keep the Early Title Save From Rewriting Message References
* 🩹 fix: Carry the Recovered User Message Reference
* 🧵 fix: Reference Every Recovered Message Row
* 🪢 fix: Reference Paused and Resumed Response Rows
---------
Co-authored-by: Lia <lia@librechat.ai>
* ⚡ perf: Exclude Agent Version History From Default `getAgent` Reads
getAgent now defaults its projection to { versions: 0 }; loadAgent/loadAddedAgent
and canAccessAgentFromBody use getAgentWithVersionCount so the version count stays
exact without transferring the unbounded versions array on every chat request.
Callers that need history (v1 update/revert handlers) request it explicitly.
* fix: tighten agent version projection types
* fix: type projected agent version counts
* fix: type default agent projection
* style: format agent projection overload
* fix: expose projected agent return type