Commit graph

188 commits

Author SHA1 Message Date
Marco Beretta
2ad2c1c14b
🔑 perf: Cache JWT Users and Batch Auth-Path Reads (#17466)
* perf: Serve JWT Bearer User Lookups From the Auth User Cache

* perf: Batch Agent Permission Reads on the File Access Path

* perf: Remember a Loaded Google Service Key Across Endpoint Config Reads

* perf: Run Independent Startup, Tool, Skill and Erasure Reads Concurrently

* fix: Drop JWT User Cache Writes That Race a User Mutation

Confirm each cache write with a second read and evict when the user changed,
so an in-flight lookup cannot repopulate an entry a credential change just
evicted. The cache mode now arrives through the loader dependencies.

* refactor: Move Agent Skill Access Reads Into packages/api

The chat-completions and Responses controllers call loadSkillAccess instead of
orchestrating the three reads in CJS. The preview route spec mocks the batched
file access helper the middleware now calls.

* test: Cover Agent File Access, JWT Bursts and Remote Skill Reads End to End

* fix: Serve a Cached JWT User Only While Its updatedAt Is Current

A cache hit now reads the stored updatedAt and deletion fence instead of the
fence alone, so a document cached from a read that raced a user mutation is
never served, even when the write landed after that mutation's eviction.

* refactor: Move Startup Migration Checks Into packages/api

* refactor: Inject the Startup Migration Checks Instead of Mongoose Models

* fix: Serve Cached OpenID Users Only While Their updatedAt Is Current

Moves the freshness check into getCurrentCachedAuthUserDoc and uses it on the
OpenID bearer path as well as the local JWT one, so a document cached from a
read that raced a credential or role change is never served there either.

Fixes berry-13/LibreChat#432

* fix: Compare Authorization Fields on Every Auth Cache Hit

updatedAt has millisecond resolution, so the freshness read also compares the
token retirement stamps, role, tenant and two-factor state.

* fix: Annotate the Auth Freshness Projection for Isolated Declarations

* perf: Reuse the OpenID Cache Freshness Read for Deletion Admission

A cache hit already proved the deletion fence is clear, so only users read from
the database take the separate fence query.

* refactor: Keep the OpenID Cache Freshness and Fence Decisions in packages/api

* test: Exercise JWT Cache Freshness Against Real User Methods in MongoDB

* fix: Stamp the JWT User Lookup So the Cache Write Fence Applies

* fix: Reload a Google Service Key File When It Changes or Disappears

The availability check remembers a loaded key only while the file's mtime and
size are unchanged, and fetches URL sources every time as before.

* fix: Recheck a Service Key File After a Permission Change
2026-10-30 00:24:08 +01:00
Marco Beretta
01211053f5
🚦 fix: Stop Queued Lookups After the First Concurrent Failure (#17557)
Some checks are pending
Backend Unit Tests / Tests: api (shard 1/3) (push) Blocked by required conditions
Backend Unit Tests / Tests: api (shard 2/3) (push) Blocked by required conditions
Backend Unit Tests / Tests: api (shard 3/3) (push) Blocked by required conditions
Backend Unit Tests / Tests: data-provider (push) Blocked by required conditions
Backend Unit Tests / Tests: data-schemas (push) Blocked by required conditions
Backend Unit Tests / Tests: @librechat/api (shard 1/4) (push) Blocked by required conditions
Backend Unit Tests / Tests: @librechat/api (shard 2/4) (push) Blocked by required conditions
Backend Unit Tests / Tests: @librechat/api (shard 3/4) (push) Blocked by required conditions
Backend Unit Tests / Tests: @librechat/api (shard 4/4) (push) Blocked by required conditions
Codegraph E2E Vote Gate / Gate (push) Waiting to run
Codegraph E2E Votes / vote (shard 1/10) (push) Waiting to run
Codegraph E2E Votes / vote (shard 10/10) (push) Waiting to run
Codegraph E2E Votes / vote (shard 2/10) (push) Waiting to run
Codegraph E2E Votes / vote (shard 3/10) (push) Waiting to run
Codegraph E2E Votes / vote (shard 4/10) (push) Waiting to run
Codegraph E2E Votes / vote (shard 5/10) (push) Waiting to run
Codegraph E2E Votes / vote (shard 6/10) (push) Waiting to run
Codegraph E2E Votes / vote (shard 7/10) (push) Waiting to run
Codegraph E2E Votes / vote (shard 8/10) (push) Waiting to run
Codegraph E2E Votes / vote (shard 9/10) (push) Waiting to run
Docker Dev Branch Images Build / publish (push) Waiting to run
Frontend Unit Tests / Client build recovery regression (push) Waiting to run
Frontend Unit Tests / Codegraph select (push) Waiting to run
Frontend Unit Tests / Build packages (push) Waiting to run
Frontend Unit Tests / TypeScript type checks (client) (push) Blocked by required conditions
Frontend Unit Tests / Tests: @librechat/chat (push) Blocked by required conditions
Frontend Unit Tests / Tests: @librechat/client (push) Blocked by required conditions
Frontend Unit Tests / Tests: Ubuntu (shard 1/2) (push) Blocked by required conditions
Frontend Unit Tests / Tests: Ubuntu (shard 2/2) (push) Blocked by required conditions
Frontend Unit Tests / Vite build verification (push) Blocked by required conditions
2026-10-29 10:04:18 +01:00
Marco Beretta
5b8bb3c31f
⏱️ fix: Bound Remaining Outbound Calls With Timeout Budgets (#17468)
* fix: Bound outbound HTTP calls that had no timeout

Add timeouts.toolsMs, speechMs and imageGenerationMs to the timeouts block and apply the
existing budgets to the RAG delete paths, built-in tool APIs, TTS/STT providers (TTS also
aborts when the client closes), Stable Diffusion, Firebase reads and Mailgun. Calls made
before app config exists (remote config, RAG health, service key URL, Google refresh) get a
fixed 10 second budget.

* fix: Honor configured budgets for RAG deletes and per-chunk TTS deadlines

* refactor: Share one budget helper between speech and image CJS callers

* test: Cover a stalled RAG delete with a mock scenario

* test: Wait for the RAG embed before stalling the delete

* test: Embed at upload so the stalled delete has a vector to remove

* fix: Close a started TTS response on a late chunk timeout and share the service budget helper

* fix: Fail startup when the remote config fetch times out
2026-10-29 09:55:18 +01:00
Marco Beretta
7e7f559ea6
🏎️ perf: Parallelize Independent Agent and Schedule Lookups (#17465)
* perf: Parallelize Serial Lookups on Agent Load, Discovery, Skills, and Schedules

* fix: Address Review Findings on Parallel Lookups

Stage same-level discovery results before collecting edges so a shared sibling is initialized once, bound resume snapshot fetches to small chunks so over-budget graphs stop early, and surface the first ordered image failure without waiting on later reads. Update the skill name test for bounded concurrency.

* test: Tag Existing Mock Specs as Acceptance Scenarios for Parallel Lookups

* feat: Make Parallel Lookup Bounds Configurable

Add a concurrency section to librechat.yaml for MCP catalog, skill name, skill file and resume agent lookups. Defaults equal the previous hard-coded values.

* style: Sort Imports for Configurable Lookup Bounds

* test: Match Model Spec Skill Resolution Args With App Config

* test: Close the Builder Drawer Before Chatting on Narrow Viewports

* fix: Surface Fatal Discovery Errors Without Awaiting Later Siblings

* fix: Reject Discovery on the First Fatal Load Regardless of Queue Order

* fix: Keep Image Encoding Fail-Fast With Parallel Reads

* fix: Reject Resume Snapshot Lookups Without Waiting on the Whole Chunk

* feat: Make Connected Agent Discovery Concurrency Configurable
2026-10-28 18:59:16 +01:00
Marco Beretta
784582850a
🧯 fix: Guard SSE Writes and Interval Cleanups Against Crashes (#17462)
* fix: Harden Timer Sweeps, SSE Writes, and Violation Counters

Guard SSE writes against ended or destroyed responses through one helper, catch and single-flight the job store and TTL cache cleanup timers, serialize in-process counter updates, cap the violation log, prune stale OAuth failure records, batch the active-job lookup, and count Redis keys with DBSIZE.

* refactor: Drop the redundant violation log entry copy

* refactor: Log single-flight sweep failures from the API package

* test: Cover active generation listing and client disconnect mid-stream

* refactor: Configure violation log retention and move title timeout into the API package

* feat: Configure OAuth failure retention through mcpSettings

* fix: Prune OAuth failures promptly under short retention
2026-10-27 23:06:58 +01:00
Danny Avila
aa8e5849e0
⬆️ feat: Migrate to Zod v4 (#17442)
* ⬆️ feat: Migrate to Zod v4 (GHSA-mrhx-c7xc-m3w5), openai 6.49, zod-openapi 6

* 🔒 chore: Regenerate bun.lock

* 🐛 fix: Keep omitted fields absent under Zod 4 partial/optional defaults

* fix: Preserve Config Record-Key Diagnostics After Zod 4 Migration

* fix: Require Agents SDK 4.1.1 for Zod 4 Accounting

---------

Co-authored-by: Lia <lia@librechat.ai>
2026-10-26 14:16:22 +01:00
Atef Bellaaj
585953acf9
🪑 feat: Add Shared Source Author and Distributed Lock Helpers (#17086)
* feat(api): add shared source-author and distributed-lock helpers

Lift makeSourceAuthorId out of the GitHub skill sync into
packages/api/src/utils/author.ts and add createDistributedLock in
packages/api/src/cache/lock.ts (Redis SET NX PX with owner-checked Lua
extend/release, in-process Map fallback without Redis). The skill sync
call site uses the shared helper; author ids are byte-identical.

* refactor(data-schemas): accept hex-string skill author in createSkill

CreateSkillInput.author takes a Types.ObjectId or a 24-hex string, and
createSkill builds the ObjectId once for both the uniqueness check and
the insert. The GitHub skill sync passes the makeSourceAuthorId string
as-is, so no Mongoose conversion remains at that call site in
packages/api.

* fix: validate skill authors and verify lock cleanup and ownership

---------

Co-authored-by: Rebase Probe <probe@example.com>
2026-10-24 13:46:15 +02:00
lia-by-librechat[bot]
f18b16baed
🚿 fix: Bound Chat Message IDs and Remove Backtracking (#17388)
Some checks are pending
Docker Dev Images Build / publish (push) Waiting to run
Sync Helm Chart Tags / Ignore non-main push (push) Waiting to run
Sync Helm Chart Tags / Sync chart tags (push) Waiting to run
* 🚿 fix: Bound Chat Message IDs and Remove Backtracking

* fix: Reserve the Preliminary Response ID Suffix Budget

* fix: Annotate Message ID Limit Exports for Declaration Builds

* fix: Accept Preliminary Response IDs as Compaction Anchors

* fix: Keep Derived Compaction Error IDs Within the Response Bound

* fix: Bound Regeneration Placeholders Across Client and API

* test: Complete Turn Protocol Regression Fixture Contracts

* fix: Validate Effective Turn IDs and Align Queued Parent Bounds

* test: Preserve Shared Constants in OAuth Controller Mocks

---------

Co-authored-by: Lia <lia@librechat.ai>
2026-10-24 10:16:25 +02:00
Danny Avila
db225c0919
🔐 feat: Admin Config Secrets v2 (MCP and Azure Credentials, Re-entry, Env Allowlist, Rebinding) (#17353)
* 🔐 feat: Admin Config Secrets v2 (MCP and Azure Credentials, Re-entry, Env Allowlist, Rebinding)

The admin config API stored MCP server credentials and Azure group keys in plaintext, returned
them to config readers, let an admin who cannot read a stored credential send it to a host of
their choosing, and let override values reference any environment variable. MCP credentials
and Azure keys, in `groups` and in the `groupMap` the Azure clients read, are now encrypted
with masked previews, hidden from every read and decrypted once after the merge. A write that
keeps a stored MCP credential or web search key while changing where it is sent must enter it
again, judged by the value the written document holds. `${VAR}` references in overrides are
limited to an allowlist, named where a change batch leaves them, and the merge drops a
credential a layer moves to a new destination without entering it, listing it in write
responses only for sections the caller can read. A custom endpoint's key is bound to its base
URL, its provider and the destination options in addParams and dropParams (such as the
anthropicApiUrl the native Anthropic client sends to), matched across layers under the name the
merge folds (ollama is Ollama). A restated `${VAR}` counts as entered, so allowlisted names
are not bound to a destination. Azure's `${INSTANCE_NAME}` and `${DEPLOYMENT_NAME}` stay
templates in a group's `baseURL`, and a scheduled job's MCP consent no longer depends on the
masked previews that change when an admin rotates the key in place.

* ♻️ refactor: Move the MCP Key Re-entry Guard Out of the Binding Helpers to Break an Import Cycle

With #17351's OpenID provisioning on dev, the app config service reached itself through the
rebinding guard: app/service -> app/overrides -> app/rebinding -> mcp/registry/binding ->
mcp/errors (and mcp/types) -> mcp/oauth/obo -> utils/identity -> auth/openid -> auth/provision
-> app/resolve -> app/service. The binding helpers are pure diffs; only
requireApiKeyReentryForRebinding needs the MCP error class, so it moves to
mcp/registry/reentry.ts, and the helpers take MCPOptions from librechat-data-provider as
mcp/headers.ts does. No behaviour changes.

* 🧪 test: Drop a Base-Held Endpoint Key That a Lower-Priority Profile Moves

Base merges first since #17352, so a profile below Base's priority still
lands over it. The rebinding guard drops the key Base stores for a custom
endpoint whose baseURL the profile changes, and the PATCH response lists
it in `ignored`.

* 🔐 fix: Serve Admin Azure Group Keys and Keep Deployment Keys at Their Own Destinations

Azure groups a profile writes now take effect: the merge resolves a layer's
`endpoints.azureOpenAI.groups` as AppService resolves librechat.yaml's
(`resolveAzureGroups`, shared with `azureConfigSetup`) into the `groupMap`,
`modelGroupMap`, model list and assistant models the Azure clients read. A
layer's groups replace the groups below whole, as its array does; groups that
do not resolve stay unread with a warning. The rebinding guard judges the
resolved groups like any `groupMap` entry, and an Azure group's destination now
also covers a deployment name its base URL takes its host from and the
destination options of its `addParams`/`dropParams`.

A write that keeps a stored Azure group key (in `groups` or `groupMap`) while
changing where the group sends it answers 400 `CONFIG_SECRET_REENTRY_REQUIRED`
on PUT, PATCH, field deletes, tombstones and change batches, judged as the
document resolves over librechat.yaml and on each `groups` item as written.

OCR fills an empty key from `OCR_API_KEY` only for its default destination (no
base URL, or `${OCR_BASEURL}`), so a key the guard dropped for an override's
`${VAR}` base URL is not replaced by the deployment's. The env reference policy
includes the `${OCR_API_KEY}` loading fills in for an `ocr` section without a
key, so a client can write back what GET `/base` returned.

The custom endpoint guard no longer needs the layer's overrides to name an
entry: an entry changed some other way is judged as inherited (positional
tombstones inside the list are not applied by the merge, so none reached one).

A web search URL a layer points at a `${VAR}` other than librechat.yaml's
without entering its key is set back: web search sends the deployment's key,
or its client's environment default, to any `${VAR}` URL.

* 🔐 fix: Keep Azure Assistants Served, Opaque Keys as Entered and Batch Env Checks on the End State

Azure assistants: a profile's `groups` replace the groups below whole, so
groups with no model that supports assistants under librechat.yaml's
`assistants: true` left `assistants` on with an empty `assistantModels`, and
the Azure Assistants initializer picked `assistantModels[0]` (undefined).
`azureConfigSetup` refuses that combination at startup; the merge now turns
`assistants` off when none of the models it leaves supports them, with a
warning, judged on the merged result so a later layer whose groups serve
assistants keeps them on. The check is `lacksAzureAssistantModels`, shared
with `azureConfigSetup`.

Opaque credentials: every runtime reader of the OCR, speech, web search and
Langfuse keys uses the decrypted value as is (`resolveConfigSecret`,
`resolveStoredConfigSecret`, `decryptConfigSecret`), so a `${...}` inside a
key the write encrypts is part of the key. Those fields are marked `opaque`:
the write-time check skips a value the write encrypts there, and the runtime
pass keeps their ciphertext instead of blanking it. A whole `${VAR}`
reference there, which the field passes through and its reader resolves, is
still checked, and so is stored plaintext. Custom endpoint (`initializeCustom`),
Azure group (`mapModelToAzureConfig`) and MCP (`processMCPEnv`) credentials
are expanded by their clients once decrypted and stay checked; the Assistants
keys have no reader yet and stay checked too.

Change batches: env references are judged on the document the batch leaves,
as its other issues are. An issue counts only when the end state still holds
a disallowed reference (ciphertext by its plaintext) where the batch sent one,
at a location the batch changed, so a value a later op removes or replaces
(`set ocr.baseURL`, then `unset ocr`) is no longer refused, and a stored
reference the batch puts back where it was is left to merge time.

* 🔐 fix: Proxy-Bound OAuth Secrets, Consistent Azure Group State, Batch Issues by Entry Key and Loaded Web Search References

- The MCP proxy is part of the OAuth client secret's binding (user tier, admin re-entry and the
  merge's rebinding guard share `getChangedOAuthSecretBindingFields`): the access token the
  secret obtains travels through it.
- A tombstone of `endpoints.azureOpenAI.groups` resolves the groups to none in the merge (empty
  `groupMap`, `modelGroupMap` and model lists, so the model list does not fall back to the
  environment's defaults), and removes what they resolve to in `applyConfigTombstones`.
- The merged Azure model lists name only models a merged group serves
  (`narrowAzureServedModels`), so an override's `assistantModels` no group serves no longer keeps
  Azure assistants on.
- `/changes` env issues are held by entry identity (`toConfigIdentityPath`), followed through
  renames and resolved on the batch's end state, so a removal or rename no longer shifts them.
- References loading librechat.yaml introduces (OCR's `${OCR_API_KEY}`, the web search defaults)
  are allowed at the location they are loaded at, so GET /base's sections are accepted written
  back, and nowhere else.

* 🔐 fix: Re-entry for Endpoint, OCR and Speech Keys, Own Keys Bound Over Base and User Key Destinations Kept

- The document that stores a custom endpoint, OCR or speech key can no longer
  move its destination without the key: PUT, PATCH, field deletes, tombstones
  and change batches answer CONFIG_SECRET_REENTRY_REQUIRED at the changed field
  (getBoundKeyReentryIssues), judged by value as the document alone sends it.
- A profile's own key for an endpoint, MCP server, OCR or speech service, or
  Azure groupMap group that Base defines is bound to that destination when it
  is entered: the rebinding guard reports a fingerprint of where it goes, the
  write stores it beside the key (<secret>Binding), and the guard keeps the key
  there until a lower layer moves it. Reads and the merged config leave the
  fingerprint out; kept keys carry it; client values are replaced.
- An inherited custom endpoint or MCP server that sends a credential each user
  holds (user_provided, customUserVars, apiKey.source user, OpenID or Graph
  token placeholders) keeps its destination: a layer's move is set back and
  listed in ignored.
2026-10-23 06:37:54 +02:00
lia-by-librechat[bot]
aa67c33aa5
🕛 test: Control the Code API Retry Budget Clock (#17338)
Co-authored-by: Lia <lia@librechat.ai>
2026-10-22 08:35:01 +00:00
Marco Beretta
8718338728
⏱️ fix: Bound Outbound Calls Made Inside a Request (#17263)
Some checks are pending
Backend Unit Tests / Build packages (push) Waiting to run
Backend Unit Tests / Codegraph select (push) Waiting to run
Backend Unit Tests / TypeScript type checks (push) Blocked by required conditions
Backend Unit Tests / Circular dependency checks (push) Waiting to run
Backend Unit Tests / Tests: api (shard 1/3) (push) Blocked by required conditions
Backend Unit Tests / Tests: api (shard 2/3) (push) Blocked by required conditions
Backend Unit Tests / Tests: api (shard 3/3) (push) Blocked by required conditions
Backend Unit Tests / Tests: data-provider (push) Blocked by required conditions
Backend Unit Tests / Tests: data-schemas (push) Blocked by required conditions
Backend Unit Tests / Tests: @librechat/api (shard 1/4) (push) Blocked by required conditions
Backend Unit Tests / Tests: @librechat/api (shard 2/4) (push) Blocked by required conditions
Backend Unit Tests / Tests: @librechat/api (shard 3/4) (push) Blocked by required conditions
Backend Unit Tests / Tests: @librechat/api (shard 4/4) (push) Blocked by required conditions
Codegraph E2E Votes / vote (full suite) (push) Waiting to run
Docker Dev Branch Images Build / publish (push) Waiting to run
Frontend Unit Tests / Client build recovery regression (push) Waiting to run
Frontend Unit Tests / Codegraph select (push) Waiting to run
Frontend Unit Tests / Build packages (push) Waiting to run
Frontend Unit Tests / TypeScript type checks (client) (push) Blocked by required conditions
Frontend Unit Tests / Tests: @librechat/chat (push) Blocked by required conditions
Frontend Unit Tests / Tests: @librechat/client (push) Blocked by required conditions
Frontend Unit Tests / Tests: Ubuntu (shard 1/2) (push) Blocked by required conditions
Frontend Unit Tests / Tests: Ubuntu (shard 2/2) (push) Blocked by required conditions
Frontend Unit Tests / Vite build verification (push) Blocked by required conditions
* fix: Bound Outbound Calls Made Inside a Request

RAG queries for file search and message context, OCR provider calls,
action HTTP calls, the moderation check, the stored-image fetch for
base64 providers, and Flux result polling had no timeout. A stalled
upstream hung the chat turn, the upload or the tool call indefinitely,
and Flux kept polling forever on statuses that never become Ready.

Each now runs under a budget from a new librechat.yaml timeouts block
with finite defaults (getOutboundTimeoutMs in @librechat/api). Action
calls also receive the run's abort signal, so stopping a run closes the
socket.

* test: Cover a Stalled RAG Query in the Mock Harness

* fix: Share One Flux Budget Across Submit and Polls, Bound the Vertex Token Exchange

* refactor: Poll Flux Results Through pollUntilSettled

* refactor: Leave Flux Polling for a Separate Migration

* fix: Cap Configured Timeouts at the Node Timer Limit

* fix: Bound the Action Token Refresh and the Whole Image Download

* fix: Cap Every Outbound Budget by Wall-Clock Time

Axios's timeout only fires on an idle socket, so a RAG, OCR, moderation,
action or token response that keeps trickling bytes never ended.
outboundRequestBudget pairs each timeout with an AbortSignal deadline, and
action calls combine it with the run's own signal.

* fix: Name the Budget That Ran Out and Give Actions Five Minutes

The actions default rises to five minutes, since action endpoints are
arbitrary third-party APIs and the old minute could cut off legitimately
slow ones after an upgrade.

A budget overrun now fails with an error naming the timeouts key and its
value, whether it was the idle timeout or the wall-clock deadline, and
logAxiosError logs it as a warning so operators know what to raise. A
deadline cancellation is no longer read as a user stop, so an action that
runs out of time reports a timeout instead of looking like a stopped run.

* fix: Hold Outbound Deadlines Weakly So Finished Requests Leave No Timers

* fix: Check the Budget Before Reading an Error Message

* fix: Report a Wrapped Deadline as a Failure, Not a Stop

* fix: Bound the OAuth Code Exchange and Keep the OCR Budget Hint When Protected

* chore: Sort Imports in axios.ts After Rebase
2026-10-21 19:10:13 +02:00
Marco Beretta
ded1e734e0
🔕 fix: Quiet Client Disconnects, Fall Back When Hash Workers Fail, Log Speech Truncation (#17278) 2026-10-20 10:47:15 +02:00
Marco Beretta
698ee25fea
🧯 fix: Close Abandoned Download and Speech Streams and Cap Speech Input (#17270)
* fix: Contain Download and Speech Stream Failures and Cap Speech Input

The code output download piped the Code API stream with .pipe, which adds no
error listener, so a body that failed mid-stream (a bad gzip body, a reset)
became an uncaught exception and the process exited. pipeToResponse uses
stream.pipeline, ending the response and destroying the upstream when the
client leaves.

Text-to-speech piped provider streams the same way and waited only for
'end', so a provider error was uncaught and a client disconnect left the
chunk loop waiting. pipeSegment resolves on end and rejects on an error or
a disconnect, which ends the loop.

A speech request had no length cap, so one request could fan out into
thousands of serial paid provider calls. speech.tts.maxInputChars bounds it
(default 20,000 characters).

* docs: Document the Speech Input Cap in the Example Config

* fix: Reject a Speech Segment When the Client Already Left

* fix: Tear Down Both Ends of a Failed Speech Segment and Cap Streamed Speech

A failed provider segment now destroys the response as well as the source,
so a half-written answer cannot hang the client, and a response-side error
rejects the segment instead of going unhandled. Automatic playback reads a
message only up to speech.tts.maxInputChars, so long messages cannot fan
out past the cap either.

The download scenario now checks the behavior .pipe lacked: leaving a code
download closes the upstream connection right away.

* fix: Keep a Late Response Write Error From Going Unhandled

* test: Key Slow Code Downloads by File and Send a Browser User Agent

* fix: Read Speech Up to the Cap Instead of Refusing It

Manual speech now synthesizes the text up to speech.tts.maxInputChars, the
same as automatic playback, through capSpeechInput, so the CJS service only
passes the capped text along and the request keeps its existing error
contract. A streamed message that reaches the cap exactly now finishes, and
a segment that fails before any audio went out leaves the response open for
the caller's HTTP error.

* fix: Count Only Text Against the Speech Cap
2026-10-19 22:20:40 +02:00
Marco Beretta
9649541971
💠 feat: Add Gemini 4 Argon Support (#17200)
* feat: Add Gemini 4 Argon Support

Registers gemini-4-argon (GA 2026-10-13) for both the Gemini API and
Google Cloud Gemini Enterprise Agent Platform, following the Gemini 3.8
Flash integration.

- Model dropdown (config.ts) and both GOOGLE_MODELS examples
- Shared 1,048,576-token context window in googleModels; output stays
  capped at the 65,535 synchronous limit by googleSettings
- Thinking rule: medium default, minimal substituted with low, ignored
  sampling params and rejected thinkingBudget stripped; the allowlisted
  cyber-permissive variant defaults to high
- Introductory rates ($2 in / $10 out / $0.10 implicit cache read per
  1M) with the 2026-12-01 revert to $4 / $20 / $0.20 noted at both
  call sites; no long-context premium tier
- Tests: thinking default and levels, minimal substitution, legacy param
  strip, Vertex eu multi-region, OpenAI-compatible addParams strip,
  context window, value key and rates

Refs #17074

* test: Cover Gemini 4 Argon Request Shape and Billing End to End

Adds a Gemini-compatible mock endpoint whose addParams carry sampling
params, an E2E_REPORT_LLM_CONFIG fake-model marker that reports the
resolved agent request, and scenarios asserting that an Argon turn sends
no ignored sampling params (with gemini-2.5-pro as the control) and is
billed at the Argon rates.

* test: Read the Resolved Agent Request From the Graph in Argon Scenarios

The hook's agents are the unresolved agent configs, so the report now
reads the graph's agent context. The scenarios select the Gemini model
explicitly and key billed rates by model so a mismatch names the model.

* test: Match the Mobile Model Option Name in Argon Scenarios

* fix: Route Gemini 4 Argon to a Multi-Region Vertex Endpoint by Default

Argon is served only from the global, us and eu multi-regions, so with
GOOGLE_LOC unset a Vertex request now uses global instead of the
us-central1 regional default; a configured location is kept as is.
Argon also rejects a candidate count, so candidateCount, candidate_count
and its OpenAI alias n are stripped for Argon on the native and
Gemini-compatible paths.

* chore: Bump @librechat/agents to 4.0.6 for Gemini 4 Argon Input Rules

* fix: Move Regional Vertex Locations to Their Multi-Region for Gemini 4 Argon

A configured regional location such as europe-west1 does not serve
Argon, so it now resolves to the multi-region that contains it (europe-*
to eu, us-* to us) wherever the location comes from, GOOGLE_LOC or
addParams. A region outside us and eu is kept rather than sent to
global, so data never leaves the configured geography silently.

* fix: Route Gemini 4 Argon Past Regional Vertex Endpoint Overrides
2026-10-17 21:44:44 +02:00
Marco Beretta
214362aff9
🎐 feat: Add Claude Haiku 5.5 Support (#17201)
* feat: Add Claude Haiku 5.5 Support

Haiku 5.5 (`claude-haiku-5-5`) matched none of the Claude family gates, so
every endpoint treated it as a legacy Claude 4 model: thinking went out as
`enabled` with a budget (400), sampling parameters were sent, thinking blocks
were not bound to the conversation prefix, and it resolved to a 200K context,
64K output and the default token rate.

Add a Haiku version parser and `hasAdaptiveHaikuThinking` (5.5 or later),
and include it in the adaptive thinking, block binding, omitted display,
sampling omission, explicit disabled, effort cap, 1M context and 128K output
gates. Unlike Sonnet 5.5, Haiku 5.5 still accepts `disabled` at effort high or
below, so "thinking off" sends `disabled` and clamps xhigh/max to high. The
settings panel keeps the thinking toggle and hides budget and sampling.

Register it in the Anthropic, Bedrock (`global.anthropic.claude-haiku-5-5`)
and Vertex default model lists, the 1M context map and the 128K output cap,
and price it at $0.10 / $0.50 up to a 100K prompt and $0.50 / $2.50 above,
with matching cache tiers.

Related to #17078, #16911 and #17025.

* test: Cover Claude Haiku 5.5 Parameter Panel

* test: Pin Haiku Scenarios to Model Specs

* fix: Keep Claude Haiku 5.5 Off Regional Vertex Endpoints
2026-10-17 14:03:20 +02:00
Marco Beretta
ecd6943194
✂️ refactor: Remove Dead Helpers, Classes and Dependencies From packages/api (#17118)
* refactor: Remove Unused Agent Helpers and Superseded Wrappers

* refactor: Remove Dead Auth, Middleware, Protection and Prompt Helpers

* refactor: Remove Dead MCP, File, Skill and Endpoint Code

* refactor: Remove Dead Stream, Telemetry, Utility and Type Exports

* chore: Drop Unused packages/api Dependencies From bun.lock

* refactor: Keep Published Compatibility and Deprecated packages/api Exports
2026-10-16 15:43:12 +02:00
Marco Beretta
d0e253043a
🙈 fix: Mask Emails and Drop Personal Identifiers From Logs (#17048)
* fix: Mask Email Addresses and Drop Personal Identifiers from Logs

* fix: Log User IDs in OpenID Admin Role and LDAP Domain Block Messages

* fix: Mask Unicode Email Addresses in Log Redaction

* test: Add Log Email Masking Scenarios

* fix: Bound the Email Redaction Matcher and Handle Quoted Local Parts

* fix: Mask Quoted and Special-Character Email Local Parts

* fix: Redact Whole Email Tokens, Top-Level Log Fields and Metadata Keys

* fix: Redact Top-Level Metadata Keys and Escaped Quotes in Email Local Parts

* fix: Redact Truncated Emails, Address Literals and Request Paths in Logs

* fix: Redact the Full Log String Before Truncating

* fix: Preserve Colliding and Object Keys When Redacting Log Metadata

* fix: Bound Log Redaction to a Window Past the Truncation Limit

* fix: Redact the Truncation Window Without a Whitespace Cut

* fix: Redact Serialized Quoted Addresses and Keep Key Collisions Linear

* fix: Bound Every Log Redaction Path and the URL Credential Pattern

* fix: Keep Long-Scheme Credential Redaction and Serialized Escaped Quotes

* test: Cover Every Secret Shape Across the Log Truncation Cap

* fix: Drop Unfinished Window Tokens, Mask Short TLDs and Redact Direct Error Stacks

* fix: Treat Input End as a Token Boundary and Mask Parenthesized Identifiers

* fix: Remove the Quoted Local Part Length Cap Without Quadratic Scans

* fix: Drop an Unfinished Quoted Address at the Window Edge

* fix: Check Quoted Locals Before Accepting a Window Delimiter

* fix: Count Only Opening Quotes When Trimming the Window

* fix: Track Unmatched Quoted Locals Instead of Counting Closing Quotes

* fix: Lift Residual Email Caps, Keep Punctuated Credential URIs Masked and Move OBO Log Id to the API Package

* fix: Mask Empty Quoted Locals and Tolerate Read-Only Log Fields

* fix: Return a Sanitized Copy When a Log Field Cannot Be Replaced

* fix: Treat a Failed Key Removal as a Failed Replacement and Guard Stack Writes

* fix: Skip Heavy Error Graphs and Accept Escaped Backslashes in Serialized Locals

* fix: Accept Lone Escaped Backslashes in Serialized Locals Without Rescans

* fix: Compact Axios Request Info Before Redaction and Skip Heavy Splat Error Graphs

* fix: Redact Address Keys on Nested Error Objects

* fix: Materialize and Redact Enumerable Getters on Nested Errors

* fix: Guard Throwing Top-Level Getters and Skip Heavy Fields Only on Error Records

* fix: Skip Serialized Quotes When Trimming an Unfinished Address

* fix: Bound Redaction With a Per-Record Node Budget and Accept JSON Control Escapes

* fix: Match Credential URIs From the Separator So Scheme Length Is Unbounded

* fix: Count Strings Against the Redaction Budget and Guard Nested Getters

* fix: Rebuild the Log Record When a Top-Level Accessor Ignores Writes

* fix: Rebuild the Log Record When a Stack Accessor Ignores Writes

* fix: Guard the Initial Stack Read on Direct Error Logs

* fix: Accept Escaped Solidus and Preserve the Outer Budget on Reentrant Logging

* fix: Guard the Axios Marker and Error-Like Probes Against Throwing Getters

* fix: Guard the Axios Marker on Nested Errors

* fix: Replace Skipped Heavy Fields Up Front, Budget Top-Level Fields and Mask Encoded Emails

* fix: Mask Encoded Address Keys and Guard Nested Axios Config Compaction

* fix: Redact URL Objects in Compact Request Info

* fix: Remove Encoded Email Caps and Strip Serializer Hooks From Clones

* fix: Strip Serializer Hooks From Error Clones and Top-Level Records

* fix: Neutralize Inherited Serializer Hooks on Log Records

* fix: Guard the Serializer Hook Probe

* fix: Replace Function Values in Log Records

* fix: Mask Percent-Encoded Domain Separators in Logged URLs

* fix: Bound the Encoded Email Domain at URL Delimiters

* fix: Shadow Throwing Serializer Getters on Nested Errors

* fix: Rebuild Accessor Messages and Mask Doubly Encoded Addresses

* fix: Redact Multiply Encoded Address Keys

* feat: Make the Log Redaction Node Budget Configurable

* fix: Guard Message and Serializer Property Reads

* fix: Contain Proxy Failures and Redact the Compact Request Method
2026-10-15 15:54:27 +02:00
lia-by-librechat[bot]
0e3c9088f6
🫰 feat: Configure Tool Approval Modes Per Agent (#16707)
* 🫰 feat: Configure Tool Approval Modes Per Agent

* fix: Fence Remembered Tool Approval Authority

* fix: Unify Tool Approval Execution Invariants

* fix: Revalidate Learned Approval at MCP Invocation

* fix: Preserve One-Time MCP Review at Invocation

* fix: Execute Reviewed Calls on Templated MCP Connections

* fix: Scope Approval Witnesses to Executing Agents

* fix: Retain Approval Bindings for Hook-Rewritten Inputs

* fix: Pin Review Authority and Retire Settled Tool Calls

* fix: Fingerprint Effective MCP Request Headers

* fix: Preserve Routing Around Renewable MCP Token Fragments

* fix: Bind Tool Consent to OAuth Credential Generations

* test: Keep Mobile Approval Save Outside Drawer Escape Race

* fix: Fence OAuth Consent at MCP Transport Retries

* fix: Let Shared Agent Viewers Reset Personal Consent

* fix: Preserve Renewed Consent Across Reset Races

* fix: Resolve Verified Aliases for Personal Tool Reset

* fix: Fence Renewed OAuth Consent and Credential Review

* fix: Require Foreground Execution for Review-Only MCP Calls

* fix: Pin Invocation Ownership and Stable MCP Consent

* fix: Fence Superseded Tool Consent Completion Writes

* fix: Scope Consent Epochs to Effective MCP Authentication

* fix: Scope Approval Admission to Reachable Agent Tools

* fix: Preserve Approval Epochs for Runtime-Detected OAuth

* fix: Address Tool Approval Review Findings

* fix: Preserve Captured Consent When Tool Approval Is Inherited

* fix: Preserve Approval Admission Through Lazy Metadata

* fix: Fence Programmatic Reviews and Unresolved Lazy Approval Keys

* fix: Account for Normalized and Skill-Contributed Lazy Tools

* fix: Scope Lazy Approval to Selected Tool Spellings and Servers

* fix: Honor Disabled MCP Capability During Lazy Approval Admission

* test: Preserve Approval Merge Regressions After Rebase

* fix: Preserve One-Time Review During Non-OAuth Grant Outages

* fix: Retain One-Time Consent Across Resume Recovery

* fix: Preserve Reviewed Consent Through Transport Outages

* fix: Preserve Case-Variant Lazy Approval Hook Admission

---------

Co-authored-by: Lia <lia@librechat.ai>
2026-10-04 13:14:48 -04:00
lia-by-librechat[bot]
14f7b28656
🦮 fix: Bind Per-User MCP API Keys to Their Destinations (#16536)
Some checks are pending
Docker Dev Images Build / publish (push) Waiting to run
Sync Helm Chart Tags / Ignore non-main push (push) Waiting to run
Sync Helm Chart Tags / Sync chart tags (push) Waiting to run
* fix: bind per-user MCP API keys to request destinations

* fix: bind user keys after restoring OAuth destinations

* fix: include OAuth revocation endpoints in user key bindings

* fix: preserve MCP key readiness across equivalent requests

* fix: preserve explicit MCP API key-prefixed variables

* test: supply required MCP variable descriptions

---------

Co-authored-by: Lia <lia@librechat.ai>
2026-09-29 21:58:34 -04:00
lia-by-librechat[bot]
f4f36774e1
🦫 fix: Bound Error Text Before URL Redaction (#16532)
* 🦫 fix: Bound Error Text Before URL Redaction

* fix: Redact Overlength URL Scheme Tails

---------

Co-authored-by: Lia <lia@librechat.ai>
2026-09-29 20:50:36 -04:00
Danny Avila
e9d1d330b1
🧬 feat: Resolve GPT Point Releases to Their Family and Add GPT-6.1 Sol (#16526)
* feat: Resolve GPT Point Releases to Their Family, Add GPT-6.1 Sol

gpt-6.1-sol matched no token, pricing or family key, so agents ran with the
default 32K context and summarized constantly. Point releases now inherit
their family's context, output limit, pricing, reasoning options and native
Responses routing until listed explicitly; GPT-6.1 Sol joins the catalog.

* test: Type the point-release routing helper as ResponsesApiRouting
2026-09-29 19:04:06 -04:00
Danny Avila
f624ad0876
🔁 fix: Retry Code API Rate Limits That Reject Before a Workspace Call Starts (#16453)
Some checks are pending
Backend Unit Tests / Build packages (push) Waiting to run
Backend Unit Tests / Codegraph select (push) Waiting to run
Backend Unit Tests / TypeScript type checks (push) Blocked by required conditions
Backend Unit Tests / Circular dependency checks (push) Waiting to run
Backend Unit Tests / Tests: api (shard 1/3) (push) Blocked by required conditions
Backend Unit Tests / Tests: api (shard 2/3) (push) Blocked by required conditions
Backend Unit Tests / Tests: api (shard 3/3) (push) Blocked by required conditions
Backend Unit Tests / Tests: data-provider (push) Blocked by required conditions
Backend Unit Tests / Tests: data-schemas (push) Blocked by required conditions
Backend Unit Tests / Tests: @librechat/api (shard 1/4) (push) Blocked by required conditions
Backend Unit Tests / Tests: @librechat/api (shard 2/4) (push) Blocked by required conditions
Backend Unit Tests / Tests: @librechat/api (shard 3/4) (push) Blocked by required conditions
Backend Unit Tests / Tests: @librechat/api (shard 4/4) (push) Blocked by required conditions
Codegraph E2E Votes / vote (full suite) (push) Waiting to run
Docker Dev Branch Images Build / publish (push) Waiting to run
Frontend Unit Tests / Client build recovery regression (push) Waiting to run
Frontend Unit Tests / Codegraph select (push) Waiting to run
Frontend Unit Tests / Build packages (push) Waiting to run
Frontend Unit Tests / TypeScript type checks (client) (push) Blocked by required conditions
Frontend Unit Tests / Tests: @librechat/client (push) Blocked by required conditions
Frontend Unit Tests / Tests: Ubuntu (shard 1/2) (push) Blocked by required conditions
Frontend Unit Tests / Tests: Ubuntu (shard 2/2) (push) Blocked by required conditions
Frontend Unit Tests / Vite build verification (push) Blocked by required conditions
Sync Locize Translations & Create Translation PR / Sync Translation Keys with Locize (push) Waiting to run
Sync Locize Translations & Create Translation PR / Create Translation PR on Version Published (push) Blocked by required conditions
* 🔁 fix: Retry Code API Rate Limits That Reject Before a Workspace Call Starts

* 🔁 fix: Bound Workspace Rate Limit Retries by Code API Budget

* 🔗 fix: Isolate Code API Retry Default from Utility Graph

* 🧩 fix: Type the Shared Code API Retry Default

* 🔁 fix: Keep Workspace Admission Retry Budgets Independent

---------

Co-authored-by: Lia <lia@librechat.ai>
2026-09-28 15:45:13 -04:00
Danny Avila
40bb16edfd
🎼 feat: Add Claude Sonnet 5.5 Support (#16460)
Some checks are pending
Docker Dev Images Build / publish (push) Waiting to run
Sync Helm Chart Tags / Ignore non-main push (push) Waiting to run
Sync Helm Chart Tags / Sync chart tags (push) Waiting to run
Sonnet 5.5 (`claude-sonnet-5-5`) rejects `thinking.type: disabled` and takes
`between_tools` as its lowest thinking setting, binds thinking blocks to the
conversation prefix, caps effort at `high` while thinking is off, rejects
sampling parameters, supports the `updates` thinking display, and ships with
128k output / 1M context at Sonnet 5 pricing.

Family gates in data-provider now use "5.5 or later" semantics so Opus 5.6+,
Sonnet 5.6+ and the Mythos-class line (Fable) inherit the newest contract
instead of falling back to the Opus 5 / Sonnet 5 paths.
2026-09-28 15:35:42 -04:00
lia-by-librechat[bot]
56301c1b5a
🪚 fix: Count Large Prompts in Bounded Tokenizer Chunks (#16305)
Some checks are pending
Backend Unit Tests / Build packages (push) Waiting to run
Backend Unit Tests / Codegraph select (push) Waiting to run
Backend Unit Tests / TypeScript type checks (push) Blocked by required conditions
Backend Unit Tests / Circular dependency checks (push) Waiting to run
Backend Unit Tests / Tests: api (shard 1/3) (push) Blocked by required conditions
Backend Unit Tests / Tests: api (shard 2/3) (push) Blocked by required conditions
Backend Unit Tests / Tests: api (shard 3/3) (push) Blocked by required conditions
Backend Unit Tests / Tests: data-provider (push) Blocked by required conditions
Backend Unit Tests / Tests: data-schemas (push) Blocked by required conditions
Backend Unit Tests / Tests: @librechat/api (shard 1/4) (push) Blocked by required conditions
Backend Unit Tests / Tests: @librechat/api (shard 2/4) (push) Blocked by required conditions
Backend Unit Tests / Tests: @librechat/api (shard 3/4) (push) Blocked by required conditions
Backend Unit Tests / Tests: @librechat/api (shard 4/4) (push) Blocked by required conditions
Codegraph E2E Votes / vote (full suite) (push) Waiting to run
Docker Dev Branch Images Build / publish (push) Waiting to run
Frontend Unit Tests / Client build recovery regression (push) Waiting to run
Frontend Unit Tests / Codegraph select (push) Waiting to run
Frontend Unit Tests / Build packages (push) Waiting to run
Frontend Unit Tests / TypeScript type checks (client) (push) Blocked by required conditions
Frontend Unit Tests / Tests: @librechat/client (push) Blocked by required conditions
Frontend Unit Tests / Tests: Ubuntu (shard 1/2) (push) Blocked by required conditions
Frontend Unit Tests / Tests: Ubuntu (shard 2/2) (push) Blocked by required conditions
Frontend Unit Tests / Vite build verification (push) Blocked by required conditions
Sync Locize Translations & Create Translation PR / Sync Translation Keys with Locize (push) Waiting to run
Sync Locize Translations & Create Translation PR / Create Translation PR on Version Published (push) Blocked by required conditions
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>
2026-09-24 10:10:42 -04:00
lia-by-librechat[bot]
6a58bf1e36
🎈 fix: Restore Bedrock GPT Context for Long Prompts (#16284)
Co-authored-by: Lia <lia@librechat.ai>
2026-09-24 06:09:24 -04:00
lia-by-librechat[bot]
feba26360b
🌞 feat: Add GPT-6 Sol and Luna Support (#16221)
* 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>
2026-09-22 22:37:08 -04:00
Danny Avila
6500e22026
🎹 feat: Add Claude Opus 5.5 Support (#16215)
* 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>
2026-09-22 15:00:33 -04:00
lia-by-librechat[bot]
45300a67b1
⛲ fix: Prevent Agent Model Stream Idle Timeouts (#16201)
* 🌊 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>
2026-09-22 08:30:32 -04:00
lia-by-librechat[bot]
cae9afd807
🧑‍🚀 feat: Add Grok 4.7 Support Through xAI (#16173)
Co-authored-by: Lia <lia@librechat.ai>
2026-09-21 22:36:28 -04:00
lia-by-librechat[bot]
c692357dc1
🥢 fix: Exclude Prompt Inputs From Terminal Events (#16112)
* 🥢 fix: Exclude Prompt Inputs From Terminal Events

Terminal events carried prompt-building inputs into every place a FINAL is
kept: the runtime cache, the durable Redis job hash, Pub/Sub publication and
late/cross-replica replay. Neither terminal producer projected the payload, so
a 706 KiB attachment-heavy FINAL was stored and published at full size.

sanitizeMessageForTransmit removed fileContext and files[].text from
requestMessage at the controller, but never image_urls, and responseMessage
was not sanitized at all.

projectTerminalEvent is one shared, schema-aware projection applied at both
GenerationJobManager.emitDone() and publishTerminalClaim(), and on read where
a stored record may predate it. It excludes fileContext, image_urls and
embedded file bodies from requestMessage, responseMessage and every
runMessages entry, while preserving message content, attachment references and
display metadata, and the terminal/reconciliation protocol fields.

publishTerminalClaim compared publicationEvent !== finalEvent to decide
persistenceFailed. Projection allocates a new object, so that identity check
now compares against the projected intendedEvent; a successfully persisted
FINAL would otherwise have been reported as a persistence failure.

* fix: Preserve Output Attachment Text and Project Live Terminal Frames

Addresses three review findings at 9e5f6f8ce.

Output attachment text was excluded as if it were a prompt input. `files`
carries the user's uploads, whose `text` is the body extracted for the prompt,
but `attachments` holds resolved artifactPromises that BaseClient assigns onto
responseMessage, so its `text` is model-generated output rendered inline by
TextAttachment from `file.text ?? ''`. Excluding it was also unrecoverable:
useAttachmentPreviewSync polls the preview endpoint only while status is
'pending', and an absent status reads as 'ready', so a late or cross-replica
subscriber whose only source is the stored FINAL rendered a blank preview.
Each collection now carries its own exclusion set; storage bookkeeping (_id,
__v) is still excluded from both.

A live Pub/Sub FINAL from an older replica bypassed projection. The store-read
paths were covered, but during a rolling deploy an old generation owner
publishes an unprojected frame that a new subscriber cached on its runtime and
forwarded to the browser. queueDone is the one choke point every terminal
delivery to a subscriber passes through, so the projection now runs there.

The declared return type was the input type T, so the exported projected
contract was never enforced. FinalMessageFields carries an index signature,
which makes Omit alone a no-op, so ProjectedMessageFields now maps the
transient fields to `?: never` and overloads return the projected contract for
a FinalEvent, the exact type for a non-terminal event, and ServerSentEvent for
the union every manager call site passes.

* fix: Spell Out Transient File Fields for isolatedDeclarations

tsdown builds packages/api with --isolatedDeclarations, which rejects a spread
element in an inferred array type (TS9018), so composing TRANSIENT_FILE_FIELDS
from a shared bookkeeping tuple broke Build packages and every lane that
depends on a built package. tsc --noEmit does not use that flag and passed,
which is why this reached CI.

Both tuples are now spelled out, with a comment recording the constraint.

---------

Co-authored-by: Lia <lia@librechat.ai>
2026-09-20 05:59:58 -04:00
lia-by-librechat[bot]
a26a6709ff
📪 feat: Send Per-Request MCP Headers Without Hiding the Tool Catalog (#15988)
* 📪 feat: Send Per-Request MCP Headers Without Hiding the Tool Catalog

A `{{LIBRECHAT_BODY_*}}` placeholder in an MCP server's `headers` marks the
server request-scoped, and catalog discovery has no conversation to resolve it
against, so LibreChat skipped tool discovery and the server appeared with no
individual tools.

Operators can now declare those headers separately in `requestHeaders`, which
discovery omits and chat turns resolve and merge over `headers`.

* fix: normalize requestHeaders at each resolution entry point

Registering the new field in every consumer that enumerates header-bearing
config fields left five gaps: startup inspection, case-insensitive override,
the admin-configurable comparison surface, Graph token preprocessing, and
direct-bearer recovery.

Fold `requestHeaders` into `headers` at the entry of each resolution pipeline
instead, so Graph preprocessing, direct-bearer detection, `processMCPEnv` and
the transports keep reading one header map and never learn a second exists.
Catalog paths strip it at the same boundary, startup inspection included.

* fix: keep servers with chat-only headers off the shared app connection

A static `requestHeaders` map left a server eligible for app-level sharing, and
`ConnectionsRepository.loadConnection` handed the raw config to the factory, so
the shared session's own `initialize` and `tools/list` carried headers
documented as chat-only — and every later catalog read reused that session.

One session cannot serve both sides of the field. Exclude such configs from
`canUseAppConnection`, the single predicate both `connectAppServers` and the
repository's own app-level gate already consult, so the chat turn keeps its
headers on a user-scoped connection while catalog work never sees them.

* fix: normalize requestHeaders before the manager's bearer decisions

`createUserConnectionInternal` reads `usesDirectOpenIDBearerRecovery` and
`resolveDirectOpenIDBearerConfig` on the config it receives, while the merge sat
in `resolveRuntimeConfig`, a leaf helper below those calls. An `Authorization`
template declared in `requestHeaders` therefore never entered direct-bearer
mode: a `tools/list` 401 skipped the force-refresh and the connection was
returned with a stale bearer.

Normalize at the birth of that pipeline's config instead, ahead of all four
decisions, and make `getMCPAppToolsPublicationGeneration` normalize before
hashing. Connection paths hold a merged config while cache paths hold the
declared one, so without a canonical hash the two would address different
catalog slices.

* fix: Preserve MCP request header ownership across lifecycle boundaries

* fix: Narrow remote header identity before rebuilding config

* fix: Preserve request header precedence over catalog API keys

* docs: Synchronize generated agent API schemas

* fix: Ignore shadowed generated MCP user key requirements

---------

Co-authored-by: Lia <lia@librechat.ai>
Co-authored-by: Danny Avila <danny@librechat.ai>
2026-09-16 15:16:40 -04:00
Danny Avila
2f8bc3dfcd
🎞️ fix: Deliver Opted-In Custom Endpoint Media Safely (#15937)
* feat: send video/audio to custom endpoints that opt in via supportedMimeTypes

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

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

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

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

* fix: canonicalize input_audio format from MIME type

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

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

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

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

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

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

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

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

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

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

* fix: reject unsupported provider audio during upload

---------

Co-authored-by: Renato Garita Figueiredo <renato.garitafigueiredo@uni-osnabrueck.de>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-09-14 16:38:51 -04:00
Joseph Licata
27acf97ad9
📫 fix: Route Azure Astra Through Responses API (#15845)
Some checks are pending
Backend Unit Tests / Build packages (push) Waiting to run
Backend Unit Tests / Codegraph select (push) Waiting to run
Backend Unit Tests / TypeScript type checks (push) Blocked by required conditions
Backend Unit Tests / Circular dependency checks (push) Waiting to run
Backend Unit Tests / Tests: api (shard 1/3) (push) Blocked by required conditions
Backend Unit Tests / Tests: api (shard 2/3) (push) Blocked by required conditions
Backend Unit Tests / Tests: api (shard 3/3) (push) Blocked by required conditions
Backend Unit Tests / Tests: data-provider (push) Blocked by required conditions
Backend Unit Tests / Tests: data-schemas (push) Blocked by required conditions
Backend Unit Tests / Tests: @librechat/api (shard 1/4) (push) Blocked by required conditions
Backend Unit Tests / Tests: @librechat/api (shard 2/4) (push) Blocked by required conditions
Backend Unit Tests / Tests: @librechat/api (shard 3/4) (push) Blocked by required conditions
Backend Unit Tests / Tests: @librechat/api (shard 4/4) (push) Blocked by required conditions
Codegraph E2E Votes / vote (full suite) (push) Waiting to run
Docker Dev Branch Images Build / publish (push) Waiting to run
Frontend Unit Tests / Client build recovery regression (push) Waiting to run
Frontend Unit Tests / Codegraph select (push) Waiting to run
Frontend Unit Tests / Build packages (push) Waiting to run
Frontend Unit Tests / TypeScript type checks (client) (push) Blocked by required conditions
Frontend Unit Tests / Tests: @librechat/client (push) Blocked by required conditions
Frontend Unit Tests / Tests: Ubuntu (shard 1/2) (push) Blocked by required conditions
Frontend Unit Tests / Tests: Ubuntu (shard 2/2) (push) Blocked by required conditions
Frontend Unit Tests / Vite build verification (push) Blocked by required conditions
Sync Locize Translations & Create Translation PR / Sync Translation Keys with Locize (push) Waiting to run
Sync Locize Translations & Create Translation PR / Create Translation PR on Version Published (push) Blocked by required conditions
* fix: route Azure Astra through Responses API

* fix: keep Azure Astra deployment alias out of summarizer overrides

The Azure deployment alias in `modelKwargs.model` is spread after `model`
by langchain, so the SDK's same-provider summarizer, which copies the
agent's client options and overrides only `model`, still reached the Astra
deployment when configured with a different model. Hand the summarizer the
agent's kwargs without the alias whenever its model differs.

Also derive the Astra routing decision once, reuse the first-party OpenAI
predicate in the GPT-5.6 rule, pin the opt-out shape in the Azure spec, and
expect `firstPartyEndpoint` for canonical Azure hosts in the backward-compat
spec.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>

* fix: resolve Azure request URLs and summarizer deployments

* fix: honor explicit OpenAI summarization for Azure agents

* 🧭 fix: Degrade Unresolvable Azure Summarizers Without Failing the Run

Summarization target resolution for Azure agents threw inside createRun, so a
summarization setting that could not be resolved failed every agent run before
any model call, not just compaction. The documented `summarization.provider:
openAI` block with the `.env.example` default `OPENAI_API_KEY=user_provided`
broke all Azure agents, and a summary model missing from the Azure
configuration did the same.

- An explicit OpenAI summarizer without server credentials now disables
  summarization for that Azure agent with a one-time warning instead of
  throwing; the agent's own client is not a fallback because Azure Responses
  shares the `openAI` provider.
- A summary model the Azure configuration cannot resolve warns once and keeps
  the agent's client, as before this branch.
- A summary group without a base URL no longer inherits the agent group's
  `azureOpenAIBasePath`, which sent the summary key and deployment to the
  agent's resource.
- Serverless summary groups without a version send no empty `api-version`.

* 🧪 test: Assert No Summary Request Leaves a Disabled OpenAI Summarizer

* 🧯 fix: Disable Summaries Whose Azure Deployment Cannot Be Resolved

When the Azure configuration could not resolve a summary model, the summarizer
fell back to the agent's own client. On an Azure Responses agent that stripped
the deployment alias and sent the logical model name where Azure expects a
deployment, so every compaction failed; on a chat agent the URL-pinned
deployment silently served a different model than the one configured.

An unresolvable Azure summary target now disables summarization for that agent
with a one-time warning, matching the unreachable OpenAI target: the run
proceeds on context pruning and no summary request is sent.

* 🔑 fix: Treat an Empty Azure Summary Key as Unavailable

`azureBaseSchema` accepts `apiKey: ''`, and `mapModelToAzureConfig` passes it
through, so a summary group with an empty key kept summarization enabled and
built a client with no credential. The agent flow already rejects an empty
Azure key during initialization; the summary resolver now disables
summarization for that target with the same one-time warning as a
user-provided key or base URL.

* 🧭 fix: Resolve Azure Summaries From Every Supported Azure Configuration

Three Azure configuration shapes the summary resolver and URL builders did not
cover:

- Legacy `AZURE_*` environment credentials: without an `azureOpenAI` block the
  resolver skipped Azure, so an Astra agent's summarizer reused the agent's
  Responses client and sent the logical summary model where a deployment
  belongs. The target now resolves from the environment the way
  `initializeOpenAI` does (including `AZURE_USE_MODEL_AS_DEPLOYMENT_NAME`) and
  is disabled when those credentials are user-provided or missing.
- `summarization.parameters` `baseURL` and `apiKey` overrides now apply to Azure
  summary targets, as they already did for explicit OpenAI targets, through one
  shared helper.
- A full Azure hostname used as the instance name (as `genAzureEndpoint`
  accepts) is used as the host for both the default Responses URL and the chat
  deployments path, instead of being suffixed into
  `<host>.openai.azure.com`.

* 🔐 fix: Expand Summarizer Credential Placeholders and Bound Warnings

Admin-authored `summarization.parameters` `apiKey` and `baseURL` values were
forwarded verbatim, so `${SUMMARY_KEY}` reached the client as a literal key
while Azure groups and custom endpoints expand the same syntax. They are now
expanded once through `extractEnvVariable` (keeping its sensitive-variable
denylist) before resolution and before the parameters are layered over the
client, and a credential or base URL that still holds an unresolved
placeholder disables summarization like a missing one. Azure base URL
templates (`${INSTANCE_NAME}`, `${DEPLOYMENT_NAME}`) are not treated as
unresolved.

The one-time warning set is now keyed per tenant, so one tenant's report no
longer hides another's, and resets after 256 distinct entries so changing
configurations cannot grow it without bound.

* 🧩 fix: Keep Azure URL Templates Out of Summarizer Env Expansion

Expanding `summarization.parameters.baseURL` through `extractEnvVariable`
also replaced Azure's reserved `${INSTANCE_NAME}` and `${DEPLOYMENT_NAME}`
templates whenever the host environment happened to define those names, so a
template override could route compaction to the host's instance or deployment
instead of the summary group's. Expansion now skips those two templates and
leaves them for `constructAzureURL`, and the unresolved-placeholder check reads
the same segments.

The warning deduplication set now evicts the least recently seen entry at its
bound instead of clearing, so warnings for problems that are still recurring
are not all logged again at once.

* 🔀 fix: Reset Inherited API Mode for Custom-Endpoint Summarizers

A custom OpenAI-compatible summarization endpoint resolves to the same `openAI`
provider as an Azure Responses agent, so the SDK layered its overrides over the
agent's client options and kept the agent's `useResponsesApi`,
`firstPartyEndpoint`, reasoning and request kwargs. An Azure Astra agent
therefore sent its compaction to the gateway's `/responses` with Astra shaping.
When the resolved custom provider matches the agent's, those fields are now
replaced from the target's own configuration, and explicit summarization
parameters can still opt back in.

Azure's reserved `${INSTANCE_NAME}`/`${DEPLOYMENT_NAME}` URL templates are now
preserved only for Azure summarization targets, so an OpenAI or custom base URL
can reference environment variables with those names.

* fix: Resolve Azure Summary Identity, Transport, and Token Limits 🧭

* fix: Resolve Headers Before Building Summary Clients 📨

---------

Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
Co-authored-by: Danny Avila <danny@librechat.ai>
2026-09-14 15:06:35 -04:00
Marco Beretta
f077e8c967
🗯️ fix: Give Failed Turns Actionable Guidance (#15896)
* 🧯 refactor: State Failed Turns in Copy a Reader Can Act On

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

---------

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

* fix(schedules): require unattended MCP credentials

* fix(schedules): resolve MCP credentials during execution

* refactor(schedules): inject unattended credentials

* fix(schedules): scope renewable credential resolution

* fix: isolate lazy scheduled OBO credentials across MCP lifecycle

* fix: preserve MCP cancellation and retryable credential lookup

* fix: bind MCP cancellation to the owning run signal

* test: supply flow manager in OBO cancellation regression

* fix: preserve MCP cancellation across exchange and API ingress

* style: sort MCP manager imports

* fix: propagate cancellation through agent discovery

* test: preserve agent discovery edge literals

* fix: propagate agent initialization cancellation

* fix: expose initialization signal in OpenAI adapter
2026-09-14 10:27:47 -04:00
Marco Beretta
e95e696d70
🧾 fix: Count the Tool Results a Tool-Limit Stop Retains (#15893)
Some checks are pending
Backend Unit Tests / Build packages (push) Waiting to run
Backend Unit Tests / Codegraph select (push) Waiting to run
Backend Unit Tests / TypeScript type checks (push) Blocked by required conditions
Backend Unit Tests / Circular dependency checks (push) Waiting to run
Backend Unit Tests / Tests: api (shard 1/3) (push) Blocked by required conditions
Backend Unit Tests / Tests: api (shard 2/3) (push) Blocked by required conditions
Backend Unit Tests / Tests: api (shard 3/3) (push) Blocked by required conditions
Backend Unit Tests / Tests: data-provider (push) Blocked by required conditions
Backend Unit Tests / Tests: data-schemas (push) Blocked by required conditions
Backend Unit Tests / Tests: @librechat/api (shard 1/4) (push) Blocked by required conditions
Backend Unit Tests / Tests: @librechat/api (shard 2/4) (push) Blocked by required conditions
Backend Unit Tests / Tests: @librechat/api (shard 3/4) (push) Blocked by required conditions
Backend Unit Tests / Tests: @librechat/api (shard 4/4) (push) Blocked by required conditions
Codegraph E2E Votes / vote (full suite) (push) Waiting to run
Docker Dev Branch Images Build / publish (push) Waiting to run
Frontend Unit Tests / Client build recovery regression (push) Waiting to run
Frontend Unit Tests / Codegraph select (push) Waiting to run
Frontend Unit Tests / Build packages (push) Waiting to run
Frontend Unit Tests / TypeScript type checks (client) (push) Blocked by required conditions
Frontend Unit Tests / Tests: @librechat/client (push) Blocked by required conditions
Frontend Unit Tests / Tests: Ubuntu (shard 1/2) (push) Blocked by required conditions
Frontend Unit Tests / Tests: Ubuntu (shard 2/2) (push) Blocked by required conditions
Frontend Unit Tests / Vite build verification (push) Blocked by required conditions
Docker Dev Images Build / publish (push) Waiting to run
Sync Helm Chart Tags / Ignore non-main push (push) Waiting to run
Sync Helm Chart Tags / Sync chart tags (push) Waiting to run
* 🧾 fix: Count the Tool Results a Tool-Limit Stop Retains

Context snapshots reach the client only through the SDK's pre-invoke
`ON_CONTEXT_USAGE`, so the results of the tools a call requests are never in that
call's snapshot — the next call's snapshot carries them as kept-message context.
A run that stops at the tool-call limit makes no next call, so the tool result it
retains lives in the response and in no snapshot: the gauge reported
`(budget − remaining) + completedOutputTokens` and left the retained result out
of used tokens and out of the tool-call share until the following turn.

The save path now counts those results with the run's own tokenizer and persists
them as `retainedToolTokens`, a second post-snapshot delta alongside
`completedOutputTokens` rather than a number folded into the provider-reconciled
`messageTokens`. `resolveRetainedToolTokens` owns the rule that only a tool-limit
stop retains anything, and the snapshot handler records where its content ended
so the count starts at the right boundary.

Counting had to avoid `Tokenizer.getTokenCount`, whose fallbacks would have put a
guess inside exact accounting: above 4 KiB it returns byte length, several times
the real count on ordinary text, and it estimates from character length while an
encoding loads. `countExactTokens` tokenizes in bounded slices cut on code-point
boundaries and returns nothing at all when the encoding is cold, so an
uncountable result withdraws the figure instead of inflating it.

The client adds the field to used tokens, subtracts it from the runway headroom
and widens the tool-call share, in the live snapshot after finalization and in
the persisted blob after a reload.

* 🧹 style: Wrap the Retained-Counter Assertion as Prettier Requires

* 🧮 fix: Address the Review of the Retained-Tool Count

Three findings from the first round, each a real defect in how the figure was
produced rather than a style point.

The boundary was a content index recorded mid-run, but completion reshapes the
array — skill cards are unshifted onto the front and `hide_sequential_outputs`
replaces it with a filtered one — so a saved index no longer means the same
position. The snapshot now records the tool-call ids it already accounts for, and
the save path counts the results of the calls missing from that set: ids survive
every reshape, and a filtered-away call is correctly left out.

Counting in 4 KiB slices was not exact either: a BPE merge spanning a seam is
charged twice, measured at ~1 token per slice, and the field exists precisely to
be an exact addend. `countExactTokens` now tokenizes the whole input — ~60 ms/MB,
paid once at the end of a stopped turn — and refuses content past 8 MiB rather
than estimating it.

The counter takes its exact-count function instead of reaching for the tokenizer
singleton, so `resolveRetainedToolTokens` owns the default (the run's own
encoding) and a caller or test can supply another. That also removes the mock of
global state from the specs.

`compactionReclaim` now includes the retained result in the total it subtracts the
kept exchange from. `latestExchangeTokens` already counts that result on the
other side, so leaving it out subtracted content the total never carried and
understated the savings — to zero on a large final result.

* 🧯 fix: Bound One Turn's Retained-Result Tokenization

The tokenizer refuses a single result past 8 MiB, but a final call that requested
several tools in parallel would pay that bound once per result. The counter now
holds a budget for the whole turn and withdraws its figure past it, so the save
path cannot be made to tokenize an unbounded pile of output.

* 🎚️ feat: Configure the Retained-Result Tokenization Budget

The exact count the gauge adds costs ~60 ms/MB of retained tool output, and the
ceiling on that work was hard-coded in two places. It is now one lever:
`endpoints.agents.maxRetainedToolCountChars`, defaulting to the 8 MiB that
reproduces today's behavior, shared by the schema and the save path through
`DEFAULT_MAX_RETAINED_TOOL_COUNT_CHARS`. Deployments whose tools legitimately
return more can raise it; slower hardware can lower it, or set `0` to withhold
the figure entirely.

`Tokenizer.countExactTokens` no longer carries a bound of its own — the caller
owns the budget — and `resolveRetainedToolTokens` passes the configured value to
the counter, which spends it across all of a final call's parallel results.

---------

Co-authored-by: Danny Avila <danny@librechat.ai>
2026-09-13 22:20:25 -04:00
Marco Beretta
5b4ec6bfe2
🔎 feat: Filter and Sort the Sidebar Chats List (#15842)
* 🔎 feat: Filter and Sort the Sidebar Chats List

The sidebar could only list every unarchived chat by last activity. Archived chats
lived behind a settings modal, sorting was not exposed at all, and the only filter
was a bookmark dropdown squeezed next to the search field.

A single control beside the Chats heading now carries the status (active or
archived), the sort field and direction, and the bookmark filter, each scoped to
that list alone: Projects, Pinned and Favorites are untouched by it.

* 🧹 fix: Answer Review Round on Sidebar Chat Filters

Rows derive their archive action from `conversation.isArchived`, which the list
projection now carries, instead of from the sidebar's filter mode: the archive view
keeps the unarchived pins beside it, and its previous page's rows outlive a status
switch, so the list mode offered to restore chats that were never archived.

Mutations reconcile the archived list caches they can now reach — rename, pin,
tags, project assignment, shared links — and archiving refetches the archived
query instead of inserting into page one, which dropped the row whenever the
active sort placed it later.

Title grouping keeps the order the server paged, heads each group with the title's
first code point, and the archive's legacy group falls back to `createdAt` the way
the cursor orders it. A failed list request renders an error with Retry rather
than "No chats yet", the status setter sanitizes a malformed stored sort, and
signing into another account no longer inherits the previous one's filters.

* 🧵 fix: Keep Sidebar Cache Writes Inside the Chosen Sort

Title groups are emitted as contiguous runs, so a `#` heading that the server's
order places either side of a letter no longer merges and drags a row across the
cursor boundary the next page continues from.

The live cache writers only reproduce newest-first, which is the one order they can
place a row in without the server's keyset. A title, created-at or ascending variant
now takes the field update in place and is refetched instead of having rows moved to
or seeded at the front of page one.

Archive and restore refetch every loaded page of the lists they touch — the archive
preserves `updatedAt`, so a restored chat can belong on a later active page — while
inactive variants are left stale rather than eagerly refetched. Archiving everything
still refetches them all, because every cached list is wrong afterwards. Renaming or
deleting a bookmark now rewrites the sidebar's selected tags, which otherwise kept
filtering by a name no menu could uncheck.

* 🗂️ fix: Treat the Archived List as a Live Conversation Cache

* 🔍 fix: Refetch List Variants Whose Membership the Client Cannot Decide

A cached search result is evaluated by the server, so a newly created row may or may
not belong in it. Skipping those variants left a mounted search list missing a row
it should show — forking from an archived search result being the case that exposed
it. The insert decision is now three-valued: insert into a variant whose membership
and order the client can reproduce, skip one the row provably does not belong to,
and refetch anything undecidable.

Forks, duplicates and imports inherit the source's archive state, so their
invalidations cover the archived list too, and the delete path reads `chatProjectId`
from archived caches as well.

* 🔎 fix: Reconcile Searched List Variants on Every Write

* 📣 fix: Announce Archive and Restore From the App Live Region

* 🧹 fix: Drop Unmounted Lists on Archive-All and Fill a Missing Archive State

Archive-all refetched every loaded page of every cached list, mounted or not, so a
session that had visited several sort, bookmark or search combinations paid a burst of
requests for lists nobody was looking at. Mounted variants still refetch all pages;
the rest are dropped, which reconciles them more thoroughly than a refetch and costs
nothing until something mounts them.

A row's own `isArchived` decides whether its menu offers Archive or Restore, and this
branch is what adds that field to the list projection — so mid-rollout, an archived
row from an older backend would offer Archive and submit a no-op. The list query now
fills a missing value from what the variant asked for, leaving an explicit one alone.

* 🧭 fix: Give Callers One Way to Reconcile Both Conversation Lists

Callers that cannot say what changed — a stream recovered after a disconnect, a
schedule whose run moved a chat, a project that took its chats' fields with it — were
invalidating the active list by hand, so a mounted archive kept a row the server had
already changed. `invalidateConversationLists` reaches both prefixes and is now the
only way those paths reconcile; `findConversationListQueries` shares its key list, so
adding a prefix is one edit rather than a sweep.

* 🔤 fix: Follow the Server Order, Index the Created Sort, and Tell the Truth When Empty

* 🎯 fix: Identify the Open Chat When a Restore Resolves

A restore leaves the chat open, so its success callback writes the new archive state
into the active conversation — but the callback captured that conversation when the
menu item was clicked. Open another chat before the request lands and the identity
check still matched the captured row, replacing the conversation the user had just
opened while the URL kept pointing at it.

The write is now a functional update that compares `conversationId` against current
state, so a stale callback leaves the open chat alone. Reading the conversation value
is no longer needed either, which also stops every row's menu from re-rendering on
conversation updates.

* 🧷 fix: Recheck the Open Route When an Archive Resolves
2026-09-12 15:56:10 -04:00
Hao
bd08a363c4
🔣 fix: Encode Images From Storage Keys (#15851)
* fix: Prefer storage keys for image encoding

* fix: Sanitize assistant image errors

* fix: Sanitize agent image storage errors

* fix: Move blob image encoding into API package

* fix: Complete image encoder TypeScript migration

* fix: Keep request-boundary error logs diagnosable

getSafeErrorMetadata reduces an error to { type: 'Error' } and an optional
status. That is the right bound where an error may echo submitted content, and
it stays in place at getS3FileStream, getAzureFileStream and
getFirebaseFileStream, where a signed URL reaches the log.

Applied at ResumableAgentController's initialization catch and the chatV1
generic branch it blinded the whole route: a missing key, an agent that fails to
load and a database error all logged as { type: 'Error' }, with no message,
name, code or stack.

getSafeErrorText keeps the error's own description and stack, reduces every URL
to its origin so an object path and signature cannot ride along, and strips
bearer credentials. It returns text so the two handlers log it inside the
message and pass no winston metadata, which is what stops an SDK error's own
enumerable properties (request.url, config, response.headers) from being
promoted onto the record.

---------

Co-authored-by: Danny Avila <danny@librechat.ai>
2026-09-12 12:39:26 -04:00
Zsanz3
b356c3d87e
🈳 fix: Treat Blank Mongo Index Settings as Unset (#15809)
Some checks failed
Backend Unit Tests / Build packages (push) Waiting to run
Backend Unit Tests / Codegraph select (push) Waiting to run
Backend Unit Tests / TypeScript type checks (push) Blocked by required conditions
Backend Unit Tests / Circular dependency checks (push) Waiting to run
Backend Unit Tests / Tests: api (shard 1/3) (push) Blocked by required conditions
Backend Unit Tests / Tests: api (shard 2/3) (push) Blocked by required conditions
Backend Unit Tests / Tests: api (shard 3/3) (push) Blocked by required conditions
Backend Unit Tests / Tests: data-provider (push) Blocked by required conditions
Backend Unit Tests / Tests: data-schemas (push) Blocked by required conditions
Backend Unit Tests / Tests: @librechat/api (shard 1/4) (push) Blocked by required conditions
Backend Unit Tests / Tests: @librechat/api (shard 2/4) (push) Blocked by required conditions
Backend Unit Tests / Tests: @librechat/api (shard 3/4) (push) Blocked by required conditions
Backend Unit Tests / Tests: @librechat/api (shard 4/4) (push) Blocked by required conditions
Codegraph E2E Votes / vote (full suite) (push) Waiting to run
Docker Dev Branch Images Build / publish (push) Waiting to run
Frontend Unit Tests / Client build recovery regression (push) Waiting to run
Frontend Unit Tests / Codegraph select (push) Waiting to run
Frontend Unit Tests / Build packages (push) Waiting to run
Frontend Unit Tests / TypeScript type checks (client) (push) Blocked by required conditions
Frontend Unit Tests / Tests: @librechat/client (push) Blocked by required conditions
Frontend Unit Tests / Tests: Ubuntu (shard 1/2) (push) Blocked by required conditions
Frontend Unit Tests / Tests: Ubuntu (shard 2/2) (push) Blocked by required conditions
Frontend Unit Tests / Vite build verification (push) Blocked by required conditions
Docker Dev Images Build / publish (push) Waiting to run
Sync Helm Chart Tags / Ignore non-main push (push) Waiting to run
Sync Helm Chart Tags / Sync chart tags (push) Waiting to run
Sync Locize Translations & Create Translation PR / Sync Translation Keys with Locize (push) Has been cancelled
Sync Locize Translations & Create Translation PR / Create Translation PR on Version Published (push) Has been cancelled
* 📭 fix: Treat Empty Mongo Auto-Index Env as Unset

Empty or whitespace MONGO_AUTO_INDEX / MONGO_AUTO_CREATE values are now
treated as unset so Mongoose keeps its defaults instead of receiving false.

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

* fix: Format optional Mongo index setting helper

---------

Co-authored-by: Cursor Agent <cursoragent@cursor.com>
Co-authored-by: Zsanz3 <Zsanz3@users.noreply.github.com>
Co-authored-by: Danny Avila <danny@librechat.ai>
2026-09-09 23:24:18 -04:00
Danny Avila
65bb64bc68
🛟 fix: Recover CodeAPI File Uploads After Throttling (#15784)
* fix: recover CodeAPI uploads after throttling

* fix: cover eager CodeAPI uploads

* fix: scope CodeAPI upload recovery

* test: clarify upload recovery deadlines

* fix: isolate CodeAPI recovery state

* fix: cancel CodeAPI recovery waits

* test: provide CodeAPI registry in handler fixture

* fix: propagate CodeAPI recovery controls

* fix: bound CodeAPI recovery by run

* fix: preserve skill upload cancellation

* test: update deferred loader signal contract

* fix: preserve recovery cancellation

* fix: cancel recovery source reads

* fix: classify Axios upload cancellation

* fix: preserve lazy provisioning cancellation

* fix: close resource recovery boundaries

* fix: preserve provisioning failures compatibly
2026-09-09 15:48:11 -04:00
aeyeopsdev
e504128e8d
🫙 fix: Surface Document Extraction Failures (#15651)
Co-authored-by: aeyeopsdev <275853971+aeyeopsdev@users.noreply.github.com>
2026-09-06 19:09:49 -04:00
Danny Avila
c00acb36a0
🌌 feat: Add GPT-6 Astra Support (#15567)
* 🌌 feat: Add GPT-6 Astra Support

Registers OpenAI's GPT-6 Astra (`gpt-6-astra`) as a first-class model on the
canonical OpenAI endpoint.

Every model-specific behavior Astra requires — Responses routing for tool
calls, stripping the sampling and logprob parameters it rejects, and
substituting the `none`/`minimal` reasoning efforts it does not accept — lands
in `@librechat/agents` (danny-avila/agents#506) rather than here. None of it is
expressible at configuration time: tools bind after `getOpenAIConfig` runs, and
LangChain's request builders emit `temperature`/`top_p` from instance fields
regardless of what this layer sets. Keeping it in the SDK also means the
routing gate can be the documented rule (tools present) instead of the
over-approximation the config-time GPT-5.6 path is forced into.

What is left here is registration:

- 1,050,000-token context window and 128K max output
- Model dropdown (config.ts) and the `OPENAI_MODELS` example
- Standard pricing: $10/M input, $1/M cached input, $12.50/M cache writes,
  $50/M output
- The >272K long-context tier, which LibreChat already supports through
  `premiumTokenValues`/`premiumCacheTokenValues`: 2x input and cache rates and
  1.5x output for the full request

Batch/Flex (50%) and Fast mode (2x) have no representation in the pricing
model today and are not introduced here; they apply per-request rather than
per-model, so they need a request-shape signal this layer does not yet carry.

Tests pin the pricing against the documented multipliers rather than restating
the literals — cache writes as 1.25x input, and the premium tier as 2x/1.5x of
standard — plus threshold behavior either side of 272K, and that `gpt-6-astra`
resolves to its own key for snapshots and provider-prefixed ids instead of
collapsing onto a shorter `gpt-6` match.

Resolves #15560

Ref: https://developers.openai.com/api/docs/models/gpt-6-astra
Ref: https://developers.openai.com/api/docs/guides/latest-model

* 🧪 test: Guard the GPT-6 Astra Max Output Entry

[Copilot] The Astra tests asserted the context window but not the 128K max
output added alongside it in `anthropicMaxOutputs`' OpenAI counterpart, so that
entry could regress silently. The gpt-5.6 tier test above covers both, and the
delete-the-fix check showed the gap: removing the source entries failed only
the context assertions.

Assert `getModelMaxOutputTokens` alongside `getModelMaxTokens`, and fold the
snapshot/prefix cases into one loop so both dimensions are covered for every id
shape rather than only the bare one. Verified by deleting just the max-output
entry: both Astra tests now fail where previously neither did.

* 🪧 feat: Declare the First-Party OpenAI Endpoint to the Agents SDK

The agents SDK gates GPT-6 Astra's request constraints — Responses-only tool
calls, rejected sampling parameters, unsupported reasoning efforts — on knowing
it is talking to the first-party OpenAI surface, and defaults them off. It takes
that as a declaration rather than inferring it, because a base URL cannot answer
the question: only this layer knows whether a URL is a faithful first-party
route, a gateway, or a proxy with its own semantics.

That decision already exists here, in `isCanonicalOpenAIBaseURL`, used by the
GPT-5.6 Responses default. Declaring it from the same checks keeps it in one
place instead of duplicating it downstream where the two could drift — and if
the endpoint logic ever moves, it moves once.

`firstPartyEndpoint` is declared on `OAIClientOptions` alongside the other agents
SDK fields this layer already sets (`promptCache`, `_lc_stream_delay`,
`includeReasoningContent`), so it typechecks against the current published SDK
and is consumed once the SDK release lands.

Two backward-compatibility expectations gain the field. That is the intended
signal: they assert the full emitted config precisely so a new field cannot slip
through unnoticed.

* 🗂 fix: Keep GPT-6 Astra Out of the Assistants Catalogs

[Codex P2] `sharedOpenAIModels` feeds `defaultModels[assistants]` and
`[azureAssistants]` as well as the OpenAI and agents catalogs. Astra serves tool
calls only from the Responses API, and the Assistants endpoints do not route
through `getOpenAILLMConfig`, so listing it there offered a configuration the
provider rejects.

Astra now sits in its own `responsesOnlyOpenAIModels` list, spread into the
OpenAI and agents catalogs only. Agents keeps it deliberately: that path does go
through `getOpenAILLMConfig`.

* 🎚 fix: Route GPT-6 Astra to the Responses API at Config Time

[Codex P1] `max_tokens` was shaped into `max_completion_tokens` here, from
`llmConfig.useResponsesApi`, while the agents SDK switched Astra to the
Responses API later at invocation time — so the request reached an endpoint
expecting `max_output_tokens` and was rejected.

Deciding the API here fixes that, and generalizes: any field whose shape depends
on the endpoint has the same problem, so the choice has to precede the shaping.
It also lands before Azure replaces `llmConfig.model` with a deployment name,
which is the only point that still knows the real model id.

Unlike the GPT-5.6 rule above, this does not depend on reasoning parameters.
Astra serves tool calls only from Responses, and OpenAI recommends Responses for
it generally, so a static decision loses nothing — which was the reason the SDK
was deciding it dynamically. The existing guards carry over: OpenRouter, custom
gateways, and an explicit `dropParams` opt-out keep their configured path.

The agents SDK is still required, for the request shaping Astra needs on either
API (danny-avila/agents#506); it no longer decides routing.

* 🏷 fix: Record the Served Model Before Azure Overwrites It

[Codex P1] `llmConfig.model` is unconditionally replaced with the Azure
deployment name, so the agents SDK received an alias and could not tell which
model it was talking to — a deployment not literally named `gpt-6-astra` got
none of the request shaping Astra requires.

Records the real id in `servedModel` immediately before the overwrite, which is
the last point that still knows it. The SDK prefers it over `model` when
deciding which model-specific constraints apply (danny-avila/agents#506).

Set for every first-party Azure request rather than only Astra: "what this
deployment serves" is a fact this layer knows and the SDK decides what to do
with, and keeping model-specific knowledge out of here is the point of the
split. The backward-compatibility expectation gains the field, which is that
test doing its job.

* 🎛 fix: Do Not Let a reasoning_effort Drop Disable Astra Routing

[Codex P1] The Astra routing reused the GPT-5.6 opt-out wholesale, which treats
`dropParams: ['reasoning_effort']` as opting out of the Responses API. That
holds for the 5.6 default, which routes *because* of reasoning — removing the
effort removes its reason to route. Astra's routing is not reasoning-driven, so
a rule clearing an unsupported stored effort silently put it back on Chat
Completions, where its tool calls fail.

Astra now honors only an explicit `useResponsesApi` drop. Reusing the guard
without re-deriving whether each clause applied was the error.

* ✂️ fix: Scope GPT-6 Astra to the First-Party OpenAI Endpoint

[Codex P1 + P2] Two findings, both Azure, resolved by removing the Azure support
rather than extending it.

Azure's first-party hosts do not satisfy `isCanonicalOpenAIBaseURL`, so a
configured `*.openai.azure.com` was neither routed to Responses nor declared
first-party; and moving Astra out of `sharedOpenAIModels` also removed it from
the Azure chat fallback, since `getOpenAIModels({ azure: true })` resolves
through `defaultModels[azureAssistants]`.

Both are moot once the scope is right: OpenAI does not document Astra as
available on Azure OpenAI. Its model page lists the API and OpenAI's own
subscription plans, with no third-party cloud surface. The Azure handling was
support for a deployment the model is not documented to reach, and it produced
most of the review findings on this branch and its agents SDK counterpart.

Routing and the first-party declaration are now scoped to
`EModelEndpoint.openAI`, and the Azure-only `servedModel` recording is gone
along with its SDK counterpart. Astra staying out of the Azure catalogs is now
the intended outcome rather than a regression.

* 🚫 fix: Keep Astra Out of the Initial Azure Catalog

[Codex P1] `initialModelsConfig` feeds the OpenAI catalog to Azure OpenAI as
well, so scoping Astra to the first-party OpenAI endpoint left it advertised on
Azure anyway — and being first in the list, it could become the default
selection where no prior choice exists. The server's Azure fallback already
excludes it, so the client would offer a model the server then rejects.

The Azure initial catalog now uses the OpenAI list minus the Responses-only
models, following the same scoping decision the routing guard makes.

The initial Assistants catalog was already safe: `fitlerAssistantModels`
requires `gpt-4` or `gpt-3.5`, which Astra does not match. Pinned that in a test
rather than leaving it to a regex written for another purpose.

* ⬆️ chore: Bump `@librechat/agents` to 3.7.20 for GPT-6 Astra Constraints
2026-09-04 10:23:29 -04:00
Danny Avila
78b320cbbc
🗜️ fix: Bound Conversation Page Size (#15576)
`GET /api/convos` read its page size as `parseInt(req.query.limit, 10) || 25`
and handed it to `getConvosByCursor` unclamped, where it becomes
`.limit(limit + 1)`. `?limit=-1` therefore issued `.limit(0)`, which MongoDB
reads as no limit at all, and the route returned the caller's entire
conversation list in one response; `?limit=999999999` forced the same unbounded
fetch. `attachSharedFlags` then amplified it with a second query whose `$in`
carried every returned id.

Every other list route already clamps, so the fix reuses that shape: the
projects handler's local `normalizeLimit` moves to `packages/api/src/utils/query`
and both routes share it, and `getConvosByCursor` bounds its own page size so
the invariant holds for any caller.
2026-09-03 23:52:36 -04:00
Danny Avila
790f2b3153
⚡ feat: Add Gemini 3.8 Flash Support (#15519)
Some checks failed
Backend Unit Tests / Build packages (push) Waiting to run
Backend Unit Tests / Codegraph select (push) Waiting to run
Backend Unit Tests / TypeScript type checks (push) Blocked by required conditions
Backend Unit Tests / Circular dependency checks (push) Waiting to run
Backend Unit Tests / Tests: api (shard 1/3) (push) Blocked by required conditions
Backend Unit Tests / Tests: api (shard 2/3) (push) Blocked by required conditions
Backend Unit Tests / Tests: api (shard 3/3) (push) Blocked by required conditions
Backend Unit Tests / Tests: data-provider (push) Blocked by required conditions
Backend Unit Tests / Tests: data-schemas (push) Blocked by required conditions
Backend Unit Tests / Tests: @librechat/api (shard 1/4) (push) Blocked by required conditions
Backend Unit Tests / Tests: @librechat/api (shard 2/4) (push) Blocked by required conditions
Backend Unit Tests / Tests: @librechat/api (shard 3/4) (push) Blocked by required conditions
Backend Unit Tests / Tests: @librechat/api (shard 4/4) (push) Blocked by required conditions
Codegraph E2E Votes / vote (full suite) (push) Waiting to run
Docker Dev Branch Images Build / publish (push) Waiting to run
Frontend Unit Tests / Codegraph select (push) Waiting to run
Frontend Unit Tests / Build packages (push) Waiting to run
Frontend Unit Tests / TypeScript type checks (client) (push) Blocked by required conditions
Frontend Unit Tests / Tests: @librechat/client (push) Blocked by required conditions
Frontend Unit Tests / Tests: Ubuntu (shard 1/2) (push) Blocked by required conditions
Frontend Unit Tests / Tests: Ubuntu (shard 2/2) (push) Blocked by required conditions
Frontend Unit Tests / Vite build verification (push) Blocked by required conditions
Sync Locize Translations & Create Translation PR / Sync Translation Keys with Locize (push) Has been cancelled
Sync Locize Translations & Create Translation PR / Create Translation PR on Version Published (push) Has been cancelled
* ⚡ feat: Add Gemini 3.8 Flash Support

Adds first-class support for Google's Gemini 3.8 Flash (`gemini-3.8-flash`,
GA 2026-09-02) for both the Gemini API (AI Studio) and Google Cloud Gemini
Enterprise Agent Platform, following the Gemini 3.7 Flash integration (#14818).

The Flash-family handler that PR generalized already carries the shape 3.8
needs, so registering the model is a one-line rule rather than new behavior:
it inherits the strip of deprecated sampling params (temperature/topP/topK),
the rejected penalty params, and `thinkingBudget`, defaults to `medium`
thinking, and — like 3.7 — errors on `minimal`, so an explicit `minimal` is
substituted with the nearest supported level, `low`.

- Context window (1,048,576) in googleModels; API + cache pricing in tx.ts
- Model dropdown (config.ts) and GOOGLE_MODELS examples for both integrations
- Register the model in the Flash-family thinking-rule table
- Apply the same introductory pricing as 3.6/3.7 Flash ($0.75 in / $3.75 out /
  $0.075 cached, per 1M), reverting to $1.50 / $7.50 / $0.15 on 2027-01-01;
  the existing comments at both call sites now name 3.8 alongside 3.6/3.7
- Tests mirroring the 3.7 Flash coverage: thinking default, legacy-param strip,
  explicit level pass-through, `minimal` substitution, versioned aliases,
  context window, model-key mapping, and rates

Refs #15516

Ref: https://ai.google.dev/gemini-api/docs/models/gemini-3.8-flash
Ref: https://ai.google.dev/gemini-api/docs/pricing

* 🔧 chore: Update @librechat/agents dependency to version 3.7.15 in package-lock.json and related package.json files
2026-09-02 15:06:40 -04:00
Danny Avila
0219513115
🛑 fix: Forward Run Abort Signal to Foreground Tool Calls (#15517)
* 🛑 fix: Forward Run Abort Signal to Foreground Tool Calls

Stopping a generation left in-flight tool calls running on the far side.
For MCP over streamable-http the external server kept burning CPU until
the tool finished or timed out, with no `notifications/cancelled` ever
sent.

The MCP layer was never the problem: `MCPManager.callTool` already
spreads `options.signal` into `client.request`, and the SDK's
`Protocol.request` sends `notifications/cancelled` the moment that signal
aborts. The signal simply never arrived.

Agent tools do not execute inside LangGraph's ToolNode — `eventDrivenMode`
dispatches `on_tool_execute` and `createToolExecuteHandler` invokes them.
The agents SDK puts the run's abort signal on the batch request
(`ToolExecuteBatchRequest.signal`, documented as one handlers should
forward), but the handler destructured every field except `signal` and
built its invoke config without it. `config.signal` was therefore
`undefined` in every foreground tool, so `createMCPTool` derived no
signal and the SDK registered no abort listener.

Forward it. This restores cancellation for all signal-aware foreground
tools, not just MCP. The detached background invoke keeps its own
controller, since that work deliberately outlives the turn.

An aborted call now rejects promptly and resolves an error result rather
than hanging, so the abort is logged at debug instead of as a tool error
— a user pressing Stop should not spray the error log.

* 🔇 fix: Keep Cancelled Tool Calls on the Filtered Path and Out of Error Logs

Addresses both findings from the Codex review of 48fded564a.

P1 — the cancellation branch returned before `filteredToolOutputResult`,
so with tool-output filtering configured an aborted call's error text
reached the turn uninspected. Worse, `runSignal.aborted` says the run is
over, not that this rejection was the cancellation: an unrelated failure
racing the Stop took the same unfiltered exit. Cancellation now only
selects the log level; filtering and the result shape are unchanged.

P2 — `createMCPTool` logs its own error before wrapping and rethrowing,
so every Stop during an MCP call still emitted an error-level MCP entry
and could pollute operational alerts. That catch now recognizes the abort
and logs at debug; the wrapped message still reaches the turn.

Both are covered by tests that fail against the previous commit.

* 🎯 fix: Require an Abort-Shaped Error and Spare Shared OAuth Flows

Addresses both findings from the Codex review of b3c67082cd.

An aborted run signal proves the turn is over, not that the rejection in
hand was the cancellation — a permission, OAuth, or upstream failure can
reject in the same tick a user presses Stop. Both quiet-log branches now
require the error to look like an abort as well, so a real failure racing
the Stop stays at error level and visible to operational alerts.
`isAbortError` moves to `@librechat/api` and the copy in
`abortMiddleware` is retired, keeping one implementation. Its spec pulls
the real function through its partial package mock rather than asserting
a stub.

Forwarding the run signal also reached ActionService, where two of the
three OAuth flows are keyed `userId:action_id` and so outlive the run
that opened them: a second run for the same action joins the very same
record, and the browser's OAuth callback reads its metadata to exchange
the code. `monitorFlow` deletes the key when a waiter's signal aborts, so
one Stop could strand a concurrent run and discard an authorization the
user had already granted. Those two flows no longer take the signal; the
run-scoped login flow, keyed by thread and run, still does.

Every guard is covered by a test that fails when the guard is removed.

* 🧷 fix: Detach the Stopped OAuth Waiter Instead of Dropping Its Signal

Addresses the Codex review of d53ff170ab.

Withholding the run signal from the shared Action OAuth flows protected
concurrent runs and the browser callback, but left this invocation
attached to the flow after the Stop. A callback landing late then resumed
`_call` straight into `preparedExecutor.execute` — a consequential API
request running after the user had already stopped the turn. Handing the
signal back is not the answer either, since `monitorFlow` deletes the
shared `userId:action_id` key on abort.

`detachOnAbort` separates the two: the caller stops waiting the moment
the signal aborts, while the shared flow runs on for whoever else needs
it — another run, or the callback exchanging its code. Late settlement of
the detached work is swallowed rather than surfacing as an unhandled
rejection.

Both shared flows now use it. The run-scoped login flow keeps the signal
directly, as nothing outside its run observes it.

* 🪪 fix: Keep an Action OAuth Abort an Abort

Addresses two of the three findings from the Codex review of 70fc0782b1.

Detaching the stopped waiter left the rejection to be misread on the way
out. The refresh catch treated it as a failed refresh and called
`requestLogin()`, emitting an OAuth prompt and opening pending
authorization state for a turn that had already ended. `requestLogin` and
the surrounding auth catch relabelled it `Failed to authenticate OAuth
tool` / `Authentication failed`, and the outer catch handed that to
`logAxiosError` — so an ordinary Stop produced two error-level entries
and returned failure text as the tool's result. Each boundary now lets an
abort through unchanged, and the outer catch logs it at debug and
rethrows so it stays a cancellation end to end.

Deferred: waiter-only cancellation in `FlowStateManager`, so a detached
`monitorFlow` stops polling instead of running out the flow's TTL. That
poller is bounded at three minutes and lives exactly as long as it does
for a waiter that never left, so it changes no lifetime this branch
introduced; giving `FlowStateManager` a non-destructive abort mode is its
own change, shared with MCP and indexSync.

* 🤫 fix: Classify the Abort at the MCPManager Boundary Too

Addresses the Codex review of 9bcf1aa57e.

`MCPManager.callTool` logs every rejection at error level before
rethrowing to `createMCPTool`, so a user Stop still emitted an MCP error
from the inner boundary even after the outer one learned to recognize it.
The same signal-plus-abort-shape classification now applies here.

The review also noted, correctly, that the existing test could not have
caught this: it replaces `getMCPManager` wholesale, so it only ever
exercised the outer logger. The new cases drive the real manager with a
connection whose `client.request` rejects the way the SDK does once a
request signal aborts, and cover both the cancellation and a genuine
failure racing the Stop.

* 🧹 chore: Restore Import Order in the Agents Tool Handler
2026-09-02 13:32:33 -04:00
Dustin Healy
0b96fb9f70
🪪 feat: Propagate Tenant to Agent Model Headers (#15521)
* fix: propagate tenant to agent model headers

* fix: propagate tenant across agent model calls
2026-09-02 13:25:38 -04:00
Danny Avila
d5b2a8580e
📖 feat: Add Claude Fable 5.1 Support (#15512)
Some checks are pending
Docker Dev Images Build / publish (push) Waiting to run
Sync Helm Chart Tags / Ignore non-main push (push) Waiting to run
Sync Helm Chart Tags / Sync chart tags (push) Waiting to run
Claude Fable 5.1 (`claude-fable-5-1`, GA 2026-09-01) succeeds Claude Fable 5
at the same input/output prices, with a 1M context window and 128K max output.
The Mythos-class helpers added for Fable 5 already match it — `isMythosClassModel`
tests `claude-(?:fable|mythos)[-.]?\d`, so adaptive thinking, summarized-display
opt-in, sampling omission, 1M context, the 128K output clamp, prompt caching,
the Vertex multi-region gate, and the Bedrock PDF exemption all cover 5.1
without a code change. What was missing was registration and pricing.

Cache reads are the one rate that differs, and the substring matcher would have
silently gotten it wrong: `claude-fable-5-1` falls through to the `claude-fable-5`
key, which prices cache hits at the usual 0.1x base input ($1/MTok). Fable 5.1
and Mythos 5.1 price them at 0.025x ($0.25/MTok), so every cache read would have
billed 4x — on exactly the long agentic sessions this model is built for.

- Register `claude-fable-5-1` in the shared Anthropic list and
  `global.anthropic.claude-fable-5-1` in the Bedrock list
- Add 1M context / 128K output entries for `claude-fable-5-1` and
  `claude-mythos-5-1`
- Add $10/$50 rates and `{ write: 12.5, read: 0.25 }` cache rates for both
- Update the `.env.example` and Vertex `librechat.example.yaml` examples
- Test that 5.1 resolves to its own key rather than collapsing onto 5.0, across
  token maps, pricing, cache rates, and Mythos-class detection

The three documented breaking changes from Fable 5 need no handling here:
LibreChat never sends a forced `tool_choice` on the Anthropic path (the agents
SDK omits the param when unset, so the API default `auto` applies); thinking
blocks an earlier model can't read are dropped server-side, unbilled; and
history is rebuilt from stored content parts rather than replayed signed
thinking blocks, so the prefix-binding check has nothing to reject.

Refs #15506
2026-09-02 10:45:54 -04:00
Danny Avila
67e2107d74
🔐 fix: Keep OpenID Metadata Out of Logs and Traces (#15470)
Some checks are pending
Backend Unit Tests / Build packages (push) Waiting to run
Backend Unit Tests / Codegraph select (push) Waiting to run
Backend Unit Tests / TypeScript type checks (push) Blocked by required conditions
Backend Unit Tests / Circular dependency checks (push) Waiting to run
Backend Unit Tests / Tests: api (shard 1/3) (push) Blocked by required conditions
Backend Unit Tests / Tests: api (shard 2/3) (push) Blocked by required conditions
Backend Unit Tests / Tests: api (shard 3/3) (push) Blocked by required conditions
Backend Unit Tests / Tests: data-provider (push) Blocked by required conditions
Backend Unit Tests / Tests: data-schemas (push) Blocked by required conditions
Backend Unit Tests / Tests: @librechat/api (shard 1/4) (push) Blocked by required conditions
Backend Unit Tests / Tests: @librechat/api (shard 2/4) (push) Blocked by required conditions
Backend Unit Tests / Tests: @librechat/api (shard 3/4) (push) Blocked by required conditions
Backend Unit Tests / Tests: @librechat/api (shard 4/4) (push) Blocked by required conditions
Codegraph E2E Votes / vote (full suite) (push) Waiting to run
Docker Dev Branch Images Build / publish (push) Waiting to run
Frontend Unit Tests / Codegraph select (push) Waiting to run
Frontend Unit Tests / Build packages (push) Waiting to run
Frontend Unit Tests / TypeScript type checks (client) (push) Blocked by required conditions
Frontend Unit Tests / Tests: @librechat/client (push) Blocked by required conditions
Frontend Unit Tests / Tests: Ubuntu (shard 1/2) (push) Blocked by required conditions
Frontend Unit Tests / Tests: Ubuntu (shard 2/2) (push) Blocked by required conditions
Frontend Unit Tests / Vite build verification (push) Blocked by required conditions
* 🔒 fix: Keep Secrets Out of Debug Logs and Spans

* 🧯 fix: Derive Safe Exception Types

* 🛡️ fix: Close Diagnostic Redaction Gaps

* 🧼 fix: Redact Escaped JSON Secrets
2026-09-01 13:22:12 -04:00
Danny Avila
8f6228095f
🖼️ fix: Stop Reporting a Failed Sandbox Image Read as an Unreadable Format (#15453)
* 🖼️ fix: Stop Reporting a Failed Sandbox Image Read as an Unreadable Format

`read_file` on a `/mnt/data` image collapsed every failure — rate limit,
missing path, truncated transfer, transport error — into the binary-file
hint, whose image branch reads as a permanent capability limit ("is an
image file and cannot be read as text"). The model stopped retrying, and
the operator had no way to tell which failure had actually occurred.

The failure that surfaced it: the reader windows the bytes through
`/exec` stdout, one call per window, against the Code API's per-user
execution limiter (20 requests / 30s in the reference deployment). At a
fixed 32KB window a 122KB chart cost 4 calls and a 1MB image cost 33 —
more than a whole limiter window, so anything over ~640KB could never
complete. A turn that generates several charts and reads them back
exhausts the budget partway through and reports the 429s as unreadable
images.

- `handlers.ts`: failed reads name the real cause and the affordance that
  matches it — rate-limited waits and retries, a missing path lists the
  directory, a truncated transfer retries. The "cannot be read as text"
  phrasing is now reserved for bytes that are not a supported image. An
  image past the inline budget says to downscale and read the smaller
  copy rather than pointing at `bash_tool`, which cannot show an image.
- `process.js`: the window is derived from the runner's stdout budget
  (48,960B vs 32,768B, so a 122KB chart is 3 calls and 1MB is 22), halves
  and re-reads the same offset when a runner truncates anyway (remembered
  per Code API, with the env remedy logged), waits out a rate limit it
  can afford instead of discarding the bytes already pulled, and stops at
  a 24-call ceiling so no read stalls a turn across limiter windows.
- `utils/code.ts`: shared `getCodeApiRetryAfterMs` (header, then the
  `retry_after_seconds` body); `skillFiles.ts` drops its private copy.

* ♻️ refactor: Move the Sandbox Image Reader Into TypeScript

Addresses the review round on #15453.

- P1: windowing, window sizing, the in-sandbox reader script, response
  parsing and byte assembly move to `packages/api/src/files/code/image.ts`,
  and the Code API rate-limit policy to `packages/api/src/utils/code.ts`.
  `process.js` keeps only the `/exec` transport it owns. Both new modules
  are tested against their real implementations (19 + 13 cases), including
  the round-trip ceiling, the changed-file guard and the shell-injection
  guard on the reader script.
- P2: a configured stdout budget below the old 8KB window floor produced a
  window the runner could never emit, and narrowing was pinned to the same
  floor, so no retry could succeed. The window now aligns to the base64
  group size instead, and the round-trip ceiling bounds what a small budget
  costs.
- P2: `.env.example` documented a 32,768-byte default that no longer holds
  and never mentioned the stdout budget. It now describes
  `LIBRECHAT_CODE_SANDBOX_OUTPUT_MAX_SIZE` as the setting to tune, with the
  chunk override as the escape hatch.
- P3: `process.spec.js` no longer reimplements the retry parser in its
  module mock. Behaviour is tested where it lives; the mock is a declared
  passthrough and the spec covers what the transport still owns — session
  forwarding, the profile header, parser hand-off and error logging.
- P3: `getCodeApiRetryAfterMs` reads the response body through `in`
  narrowing rather than an `as` assertion.
- P3: the window-sizing JSDoc no longer claims a multiple of 3 in the one
  case that is not — an explicit `LIBRECHAT_CODE_IMAGE_CHUNK_BYTES`.

* 🎯 fix: Size Sandbox Image Reads to What the Limiter Can Deliver

Addresses review round 2 on #15453.

- Narrowing now halves the caller's own failing window instead of the
  shared learned value, and the learned value only moves down to the
  narrowest size any read needed. Reads run concurrently (one per tool
  call), so two reads failing at the same size were compounding into a
  window two steps smaller than the runner would have accepted, and
  persisting it for every later read.
- Narrowing continues until a runner accepts a window or a floor below
  which no runner could serve an image at all. Two halvings stopped at
  12,240 bytes — still ~16KB of base64 — so an 8-10KB stdout cap that was
  not configured up front stayed unreachable.
- The round-trip ceiling is now one limiter window (20), and a read that
  cannot finish within it says so from the FIRST response rather than
  spending the whole budget rediscovering it: the first window reveals
  both the file size and what a call really delivers. A near-limit image
  no longer drains the turn's executions before failing, which is what
  made the wait budget look too small.
- The round-trip message names the size this deployment can actually
  inline, so the model has a downscale target instead of a guess.
- `python3: not found` from the sandbox reader was matching the generic
  "not found" in `isSandboxMissingFileError` and being reported as a
  missing image path, sending the model to `ls /mnt/data` while hiding a
  runner dependency. Image reads now classify only path-specific ENOENT
  forms as a missing file.

* 📐 fix: Size a Truncated Read's Retry From the Cap It Revealed

Addresses review round 3 on #15453.

A ~1KB sandbox stdout cap is a real runner default, and the 1,536-byte
narrowing floor sat above it: discovery stopped one step short and
declared every image unreadable, even though small ones fit comfortably
in the 576-byte window the configured path already derives.

Narrowing now runs until no smaller window exists. It also no longer has
to grope its way down: a truncated response emitted exactly as much as
the runner allows, so its length measures the cap this deployment never
declared, and the retry is derived from it directly — one round-trip
instead of the eight blind halvings it takes to fall from ~49KB to ~1KB.
Blind halving remains the fallback and bounds the result either way, so
every retry is strictly smaller than the window that just failed.
2026-09-01 09:08:01 -04:00
Danny Avila
224512851a
🗂️ fix: Resolve Code Interpreter Destination Collisions (#15449)
* 🗂️ fix: Resolve Code Interpreter Destination Collisions

Codeapi mounts each `/exec` input at a destination derived from its `name`
and rejects the whole request when two entries land on one. LibreChat never
enforced that: `primeFiles` sent `name: file.filename` verbatim, and the
graph seed deduped by `(storage_session_id, id)` — identity, not destination.

Two conversation files sharing a filename therefore killed code execution for
the rest of the conversation. The rejected request never reaches the sandbox,
so no result comes back to collapse the pair, and every later turn re-primes
both and fails identically. Only code-generated outputs are covered by the
`(filename, conversationId, context, tenantId)` partial unique index; uploads
carry `context: message_attachment`, so one conversation can hold several
records sharing a filename — two uploads of `image.png`, or an upload whose
name a later execution wrote back in place.

`packages/api/src/files/code/destinations.ts` now owns the name → destination
mapping for every contributor to an `/exec` file list, mirroring codeapi's
conflict rule including directory-prefix conflicts:

- `primeFiles` claims per pushed file, disambiguating with a `-2`, `-3`
  counter and echoing the resolved path into the tool context, so the model
  is told where each file actually mounts. Claim order comes from immutable
  `createdAt`, not `getFiles`'s `updatedAt` sort, which usage accounting and
  re-upload both bump — order-dependent destinations would silently repoint
  a path an earlier turn had already handed the model. Newest wins the bare
  name, matching `ToolNode.updateCodeSession` and giving an in-place rewrite
  precedence over the original it superseded.
- `seedCodeFilesIntoSessions` drops a later file whose destination is already
  claimed. Renaming there would invent a path nothing told the model about,
  and a conflict at that layer means one logical file arrived twice under
  different storage pointers.

Fixes #15443

* 🧹 chore: Tolerate Holes in the Destination Priority Sort

`primeFiles` sorts the raw `getFiles` result before its own per-entry guard
runs, so the comparator has to survive a null row rather than throw ahead of
the loop that was already defending against one.

Also tightens the tool-context assertion in the upload-vs-output case, which
was passing on a trailing space rather than on the path.

* 🔁 fix: Address Codex Review on Destination Assignment

Four findings from the review of `b0f61d0`.

**Identity-derived suffixes instead of a collision counter.** A counter is
assigned from whatever is in the set, so a third file arriving under the
literal name a displaced file had been given pushed that file along, and code
the model wrote in an earlier turn would silently start reading the newcomer.
The fallback now hashes the file's own `file_id`, so a displaced file keeps
its destination for the life of the conversation and only the winner of the
bare name can change. A trailing counter still guards a hash collision so the
search terminates on any input.

**Rank by last content write, not record creation.** `processCodeOutput`
claims one row per `(filename, conversationId)` and rewrites it in place, so
a repeatedly written output keeps its original `createdAt` while recording the
latest writer in `metadata.sourceDispatchedAt`. Ranking on `createdAt` alone
handed the bare path to an upload the output had since been rewritten over.
Recency is now `max(sourceDispatchedAt, createdAt)` — still never `updatedAt`,
which usage accounting bumps without any content changing.

**Advertise a displaced generated output.** Generated files are left out of
the tool context because the model already knows what it wrote — which stops
being true once a newer same-named file takes the bare path and the output
mounts somewhere the model has never seen. Displaced outputs are now listed
with the name they were written as, and displaced uploads name their original
too.

**Rank conversation files above an agent's private ones.** Each agent claims
destinations over its own candidate set — the conversation's files plus its
own — so a private file taking a bare name from a shared file in one agent but
not in another left two agents advertising different paths for the same file
into one shared mount namespace. Shared files now rank first, so the majority
that every agent sees resolves identically. The private-versus-private case
still drops at the merge and is documented there; closing it needs one
assignment across contributors, made before any agent renders its context.

* 📌 test: Pin Alias Ownership on an In-Place Rewrite

Codex round 2 flagged that the identity alias still falls back to a counter
when the alias itself is literally claimed, so a displaced file can move after
all. The mechanism is real and my JSDoc overstated the guarantee, which this
corrects.

The behaviour stays as it is. The realistic way a file arrives under another
file's alias is the model rewriting the displaced file in place: it was told
`<stem>-<hash>.ext`, wrote back to it, and `processCodeOutput` registered an
output under that literal name. Keeping the alias with the newest holder is
what makes the model's familiar path resolve to its own edit; reserving it
against the newcomer would hand that path back to the bytes it replaced. The
test pins that ordering so a later change cannot invert it silently.
2026-09-01 00:55:54 -04:00