Commit graph

215 commits

Author SHA1 Message Date
Dustin Healy
a9034aa6a2
🔎 feat: Observe Server Tool Results in Chat Completions (#18450)
* 🔎 feat: Observe Server Tool Results in Chat Completions

* 🐛 fix: Finalize Observed Tools After Model Acceptance
2026-11-19 10:10:02 -05:00
Dustin Healy
b6a07cef0a
🧮 fix: Validate Nullable Responses Numeric Controls (#18477) 2026-11-19 06:40:55 -05:00
Danny Avila
3375bb5c3c
🗝️ feat: Limit an API Key's Runs to the MCP Tools Its Owner Granted It (#18280)
* 🗝️ feat: Store an API Key's MCP Grants on the Key, One per Agent

* 🧬 refactor: Let the Consent Service and Enforcement Act for Any Grant Subject

* 🗝️ feat: Check an API Key Run's MCP Calls Against the Key's Grant for the Agent

* 🗝️ feat: Put Remote API Runs Under Their Key's Grant, Behind a Config Switch

* 🩹 fix: Export the Key Grant Storage the Server Wiring Loads

* 🔌 feat: Let an Owner Grant an API Key Its MCP Access From Settings

* 🗝️ fix: Decide Key Grant Access, Mode and Kind of Key in the TypeScript Host

The agent-access check and the grant-mode lookup lived in the legacy route and service
files. The host now builds the check from an injected agent reader and permission
reader, and the key handlers resolve the mode from an injected configuration reader.

Each authorized call read the owner three times and their configuration twice. The host
now reads both once per call and shares them between the access check, the limits and
the offer; nothing is kept between calls.

A background worker rebuilds its request from the admitted record, which names the key
but not its kind, so a key issued to an integration lost its exemption and its channel
runs were refused. The host asks the key store when the request carries no key itself.

* 🔌 fix: Say When a Key Grant's Agent List Is Loading, Failed or Empty

The key grant dialog turned a failed or pending agent list into an empty picker with an
instruction to choose from it. It now shows a spinner while the list loads, an error
with a retry when it could not be read and nothing is cached, and a plain statement when
the owner has no agent the key could run.

* 🧪 test: Hold the Pin Fences on an API Key's Per-Agent Grants

* 🔌 fix: Offer a Key Grant for the Agents the Key Can Run, and Only for Personal Keys

The grant dialog's picker read the app's agent catalog, which lists agents the owner can
view. Running an agent with a key follows another rule: the agent is shared with the
owner for remote use, or is theirs to share. An agent shared only for remote use could be
run but not granted. A new list, GET /api/api-keys/agents, applies that rule to all
agents, and the picker reads it.

A key issued to an integration holds no grants but showed the MCP access button. The key
list now marks such a key, and the button is not shown for it.
2026-11-18 13:28:39 -05:00
Danny Avila
a0f17e5581
🙋 feat: Let a Schedule's Owner Approve a Tool Before Each Use (#18277)
* 🙋 feat: Let a Schedule's Owner Approve a Tool Before Each Use

* 🧪 test: Drive a Real Run Through a Schedule's Approval Pause and Resume

* 🙋 fix: Keep a Stored Ask-First Choice When a Run Can No Longer Pause

Where pausing became unavailable, the dialog hid the ask-first boxes and renewed the
grant without them, so a tool the owner approved each time started running unattended.
The dialog now starts from the stored choice either way and always sends it. Where a run
cannot pause it shows only the stored questions, with a note that those tools are refused
for now, and the owner can keep or drop them but add none. The server keeps the stored
questions for tools still allowed when a confirmation says nothing about asking, and
refuses only a new question where a run cannot pause.

* 🙋 fix: Say Why a Schedule Asks for Approval in the Reader's Language

The approval card showed an English sentence sent by the server as the request's
description. The server now sends a code, and the card maps it to a localized string.
Any other description is shown as sent.

* 🙋 fix: Never Offer Always Allow for a Tool a Schedule Asks About Each Use

Where the endpoint enables Always allow, a schedule's approval card offered it for a tool
the owner approves on each use. Choosing it stored a conversation allow the schedule
still overrode at the next use. The offer and the recheck at resume now take a predicate
for anything beyond the policy that asks on every use, and the schedule's grant supplies
it, so such a tool is neither offered nor stored.

* 🙋 fix: Let the Owner Ask First About as Many Tools as They Can Allow

The confirmation accepted up to 25,600 allowed tools per server but only 256 to ask
about, so a large grant could not be confirmed with every tool set to ask first.

* 🙋 fix: Keep a Tool Asking First When the Owner Allows Its Changed Definition

The dialog derived the ask-first boxes from the ticked tools. A tool whose definition
changed starts unticked, so its stored question was dropped, and ticking the tool again
confirmed it as unattended. The ask-first selection is now kept apart from the ticks,
starts from the stored grant, and is narrowed to the ticked tools only when the
confirmation is sent. The owner's edits to it hold only for the grant they were made
against, so a question added to a grant confirmed elsewhere is not dropped unseen.
2026-11-18 12:18:15 -05:00
Danny Avila
e50a30653c
🥤 feat: Let Remote SDK Agents Read Native Chat Attachments (#18419)
* feat: bind native chat attachments to remote SDK file reads

* fix: preserve SDK file settlement and stable storage identity
2026-11-18 11:49:24 -05:00
Danny Avila
b65eadb20b
🧪 test: verify policy rejection billing effects with the real recorder (#18412) 2026-11-18 09:29:21 -05:00
Danny Avila
dd83596e70
🚔 fix: Enforce Host Model Policies for Responses and OpenAI Callers (#18400)
* fix: enforce host model policies for API SDK callers

* refactor: share API model policy assembly in TypeScript
2026-11-18 08:31:19 -05:00
Danny Avila
e7565f28ad
🔷 feat: Declare Turn Shapes in Created Frames (#18401)
* 🪪 feat: State a Turn's Shape in Its Created Frame So an Observer Applies It as Its Sender Does

* 🪪 test: Give the Request Controller Specs the Turn Helper Their Mocks Left Out

* 🪪 fix: Name the Reply an Edited or Continued Turn Starts From, and Build on It, Not the List's Tail

* 🪪 fix: Put a Plain Turn's Reply Last in the List, Where Its First Step Builds
2026-11-18 08:31:01 -05:00
Danny Avila
ff522e0771
🧭 refactor: Build One Execution Context Where a Run Enters (#18255)
* 🧭 refactor: Build One Execution Context Where a Run Enters

Each consumer of a scheduled run's identity (the host token resolver, the
scheduled MCP authority and the resource-bearer host) read the trigger body
and the restored job for itself, and the remote agent API carried a separate
`unattended` flag through tool loading.

The entry point now builds one frozen ExecutionContext: the chat controller
from the verified schedule trigger, the resume host from the saved job, and
the remote controllers from the run envelope. The initializer and tool
loading receive it as an argument. The schedule consumers project their
identity from it, and `unattended` is derived from it at the tool-loading
boundary. No client or model input sets any field.

* 🧭 refactor: Decide Whether a Run Is Unattended in Its Execution Context
2026-11-18 07:39:34 -05:00
Marco Beretta
b075605e98
💧 feat: Add Gemini Hydrogen Support (#18159)
Some checks are pending
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
Frontend Unit Tests / frontend (push) Blocked by required conditions
Playwright E2E Tests / Codegraph select (push) Waiting to run
Playwright E2E Tests / Shard timings (push) Waiting to run
Playwright E2E Tests / e2e () (push) Blocked by required conditions
Playwright E2E Tests / MCP list_changed (replica count 1) (push) Blocked by required conditions
Playwright E2E Tests / MCP list_changed (replica count 2) (push) Blocked by required conditions
Playwright E2E Tests / MCP Apps (browser and server) (push) Waiting to run
Playwright E2E Tests / e2e (push) Blocked by required conditions
Playwright Shard Timings / Record shard timings (push) Waiting to run
* feat: Add Gemini Hydrogen Model Support

* fix: Restore Google History For Reachable Agents

* fix: Preserve Mixed Google Signature History

* refactor: Inject Google billing configuration at application boundary

* fix: Preserve Call Signatures From Unsupported Google Output

* chore: Use Released Agents SDK 4.2.5

---------

Co-authored-by: Lia <lia@librechat.ai>
2026-11-16 10:26:55 -05:00
lia-by-librechat[bot]
73860d71d5
🥼 fix: Keep Runtime MIME State Out of File Inspection (#18216)
* fix: Keep runtime MIME state out of file inspection

* fix: Preserve attachment-free inspection admission

---------

Co-authored-by: Lia <lia@librechat.ai>
2026-11-16 10:12:36 -05:00
lia-by-librechat[bot]
3376942149
🛒 fix: Correct Agent Admission and Failed-Run Billing (#18157)
Co-authored-by: Lia <lia@librechat.ai>
2026-11-14 12:20:51 -05:00
lia-by-librechat[bot]
f2b4a58b0e
🔦 fix: Skip Unselected Tool Schemas Under Legacy PII (#18158)
Co-authored-by: Lia <lia@librechat.ai>
2026-11-14 12:20:16 -05:00
lia-by-librechat[bot]
1ef7d244b5
🌄 fix: Show Skill Pills When a Turn Starts (#18036)
Co-authored-by: Lia <lia@librechat.ai>
2026-11-11 12:49:50 -05:00
Marco Beretta
2e50ea0993
fix: Guard Mongo Cleanup In Controller And Migration Tests (#17989) 2026-11-11 10:30:38 +01:00
Dustin Healy
8596615d1d
🌐 feat: Wire Responses and Channel Lifecycle APIs (#17611)
* 🌐 feat: Wire Responses and Channel Lifecycle APIs

* fix: Align Channel Application Policy and Source Authority

* fix: Preserve Configured App Budgets in Canonical Response Commits

* Expose Fenced Channel Receipt Reconciliation Routes

* fix: Keep Ordinary Chat Capture In Its Existing Owner

* fix(channels): scope worker authority and defer browser activation

* fix(responses): gate admission on canonical queue readiness

* fix: Recover Durable Response Dispatch Across Queue Shutdown

* fix: Preserve Upstream Endpoint Config Insertions

* test: Align Channel Runtime Configuration Contract
2026-11-10 21:04:03 -08:00
Dustin Healy
a1ac175544
💾 feat: Persist and Continue Stored Agent Responses (#17605)
* 💾 feat: Persist and Continue Stored Agent Responses

* fix: unify response persistence and terminal ownership

* fix: Commit Canonical Responses With Conversation History

* test: Keep Interrupted Erasure Payloads Private

* fix: Fence Canonical Response Materialization During Rolling Upgrades
2026-11-10 21:04:01 -08:00
Dustin Healy
8552368176
🔄 fix: Restore MCP Sign-In Prompts After Reload (#17604)
* 🔄 fix: Restore MCP Sign-In Prompts After Reload

* wip: Separate OAuth Presentation and Publication Lifecycles

* wip: Verify OAuth Publication and Presentation Ownership

* fix: Fence OAuth Publication and Preserve Tool Outcomes

* fix: fence first-turn OAuth recovery by durable identity and retention

* test: Cover Canonical OAuth Recovery Replay in Manager

* fix: Unify Startup OAuth Prompt Lifecycle Ownership
2026-11-10 21:04:00 -08:00
Dustin Healy
7e51963f2b
📊 feat: Preserve Response Accounting and History (#17599)
* 📊 feat: Preserve Response Accounting and History

* fix: preserve accounting completeness and invocation provenance

* fix: retain invocation receipts across repeated contextualization

* feat: Own Foreground Response History and Terminal Publication

* fix: Retain Complete Submitted Response History

* test: Exercise Artifact and Response Completion Together

* chore: Validate Foreground Types and Lint

* style: Use Narrowed Canonical Outcome

* fix: Own Foreground Completion Through Tracked Persistence

* refactor: Keep Foreground Request Contract Storage Independent
2026-11-10 21:03:58 -08:00
Dustin Healy
9d14eb5b35
🛡️ fix: Retain Execution Ownership Until Terminal Persistence (#17598)
* 🛡️ fix: Retain Execution Ownership Until Terminal Persistence

* wip: separate execution attempt and persistence authorities

* test: prove execution ownership and persistence boundaries

* refactor: settle execution before returning its captured outcome

* test: verify signed channel execution at controller ingress

* fix: Unify Source Ingress and Execution Settlement Contracts

* test: Preserve Real Resume Guard in Chat Route Fixtures

* fix: Persist Terminal Journal Ownership and Remove Unused Chat Channel Lane
2026-11-10 21:03:58 -08:00
Dustin Healy
7dd4fafdf3
📬 feat: Persist Channel Events and Delivery Receipts (#17595)
* 📬 feat: Persist Channel Events and Delivery Receipts

* fix: enforce channel run identity and fenced recovery

* fix: fence and erase channel state during account deletion

* refactor: share channel owner admission with private persistence

* refactor: name channel account-erasure boundary explicitly

* fix: prove channel identity and delivery authority at storage boundaries

* refactor: enforce channel delivery protocol and terminal lifecycle

* fix: enforce channel tenant and operation boundaries

* fix: initialize channel config from its composition owner

* test: verify config installs channel storage reader

* test: complete config initializer contract in model mocks

* test: include channel config reader in migration fixture

* test: await SSE subscription before advancing keepalive time

* test: Observe and Drain Concurrent Fixture Work
2026-11-10 21:03:57 -08:00
Danny Avila
60a74e6cd4
🧷 fix: Promote Unapplied Steers to Durable Queued Turns at Run End (#18028)
* 🧷 fix: Promote Unapplied Steers to Durable Queued Turns at Run End

A steer the server accepted (202) but the run never applied was handed back
in FINAL as `pendingSteers` and re-owned by the browser as a tab-local queued
message. A reload, closed tab, or a predecessor race before the drain lost it.

At terminal publication, a normally completed run now promotes such steers
into server-owned agent queued turns (parent: the ended response, epoch: the
ended generation's createdAt, chained behind any turn already queued against
that epoch). The job store hands the parked copy over atomically
(`promoteSteerLeftover`: parked item removed, receipt settled `recovered`), so
status recovery, lost-ACK retries and legacy recovery starts cannot queue the
same words again. FINAL reports the receipts in `promotedSteers`; the client
adopts them as server rows instead of converting the steer locally.

Promotion is opt-in per steer (`promoteLeftover`, sent only by clients that
adopt receipts and only for steers with no tab-only context), so older
clients keep the legacy path unchanged, and older servers simply never
report `promotedSteers`.

* 🔒 fix: Settle a Promoted Steer's Hand-Off at Admission, Not Only at FINAL

The job-store hand-off of a promoted steer now returns an outcome and stamps
the receipt with the owning queued turn, so it is idempotent for that turn.
The queued-turn resolver repeats it before admitting a promoted turn: it
completes a hand-off a crash interrupted, and cancels the turn when the
parked copy was discarded or recovered elsewhere, so the words never run
twice. At FINAL, a row whose hand-off was refused and whose retirement cannot
be confirmed is withheld from `pendingSteers` and left for that admission
check. The conservative reconcile frame keeps `promotedSteers`, and the
client adopts it there before sweeping local chips.

* 🔏 fix: Give Promoted Steers Durable Ownership, Their Run's Queue Lineage and Approval Mode

A turn promoted from an unapplied steer now records its source on its own
row: the steer's ids, the generation that accepted it, and a mark set only
once the job store handed the parked copy to that row. Admission runs a
promoted turn on that mark or on a hand-off the job store confirms now;
without proof (the store's evidence expired, or the host cannot ask) the
turn is held for review instead of running.

- Hand-off replies that are lost no longer cancel the row. The row stays as
  the client's handle and its admission settles ownership, so a committed
  hand-off can no longer leave the steer with no runnable copy.
- A replayed promotion never hands the parked copy to a row that was
  cancelled or failed.
- Promoted turns join the queue lineage of the generation that accepted
  the steer, so a sibling still queued behind that run no longer strands
  them with a predecessor mismatch.
- The steer request carries the sender's code approval mode onto the
  promoted turn; an unreadable mode keeps the steer on the client path.
- A steer whose quotes its owner stripped stays on the client path.
- The queued-turn receipt names the promoted steer by both ids, and the
  receipt list retires a pane's local copies even when it missed FINAL.

* 🚧 fix: Fence Promoted Turns to Workers That Prove Steer Ownership

A promoted row without an approval mode was published under the v1 queued
turn capability, so during a rolling deploy a worker that predates the
ownership check could claim it and run an unsettled row while the parked
steer was still recoverable elsewhere.

Promoted rows now publish under a new agent_queued_turn_v3 capability and a
v3 delivery identity, always reserved before insertion. A replica that
projects an older version can neither publish the reserved delivery nor
claim it, and enqueue refuses a promoted row without a reservation.

* 🪦 fix: Keep a Dead Promoted Turn Answering for Words It Held

A pane that learns of a promoted steer from the receipt list dropped the
mapping for every dead row. A row quarantined as ADMISSION_INDETERMINATE can
still settle as admitted, and a row that died after it was proven the sole
owner of the words is their only surface, so in both cases the pane kept a
chip whose recovery could never run.

The receipt now says whether the turn owned its steer's words, and a dead
receipt keeps answering for them when it did or when its admission is
indeterminate. A replayed promotion applies the same rule to a settled row.

* 🧾 fix: Find Promoted Turns by the Steer a Pane Holds, Join Root Lineages, Redact Hand-off Errors

- A promoted turn's request id is now derived from the client steer id, and a
  pane asks for the receipts of the steers it still holds a local copy of
  (recovery rows and failed chips). A promoted turn that already ran is only
  listed when asked for by name, so a pane that missed FINAL now finds it
  and retires its copy. A client steer id too long to key a queued turn is
  not promoted.
- The lineage lookup includes a generation admitted from a root queued turn,
  which has a parent and no epoch. The promoted turn joins that lineage
  without an epoch instead of opening a second one.
- A failed hand-off at admission reports a fixed message. The job store's
  own error text stays out of the dead-letter record a client can read, and
  promotion logs carry safe error metadata instead of error text.

* 🔢 fix: Ask for Held Steers First Under the Receipt Lookup Limit

The receipt list answers for at most 100 request ids, and a pane's server
rows were listed ahead of the steers it still holds, so a full server queue
could push every held steer out of the request. A promoted turn that had
already run was then never found.

Held steers now come first. An active server row is listed whether or not
it is asked for, while a settled promoted turn is found only by name.
2026-11-10 22:43:32 -05:00
Marco Beretta
91fd4b6833
🧭 perf: Validate Agent Models Against Their Own Endpoint Catalog (#17972)
* perf: Validate Agent Models Against Their Own Endpoint Catalog
* perf: Share In-Flight Model List Fetches
* test: Cover Agent Model Validation Across Endpoints
* test: Check Agent Model Catalog Parity With the Real Loaders
2026-11-10 17:33:29 +01:00
Marco Beretta
9554046d5a
fix: Preserve Unknown-Provider MCP Display Images (#18000) 2026-11-10 17:29:45 +01:00
dvorak33
a3868fdbe8
🖼️ fix: Bound Flux Tool Images and Preserve Original Attachments (#13749)
Bound model-facing Flux images to the 5 MiB base64 budget for standard and finetuned generation. Preserve original image data for attachment storage under the existing resolution policy.

Fixes #6954.
2026-11-09 22:41:29 +01:00
Marco Beretta
9bd44801ec
⏳ fix: Bound Blob Storage Image Reads by the Image Fetch Budget (#17932) 2026-11-09 15:35:11 +01:00
Marco Beretta
d0d9a30327
🧩 fix: Accept Content-Array Tool Outputs in the Responses API (#17900)
* fix: Accept Content-Array Outputs in Responses function_call_output

The Open Responses spec allows function_call_output.output to be a string or
an array of input_text, input_image and input_file parts, but request
validation refused anything that was not a string. Validate the array parts
and convert them with the same part mapping the message path uses, so the
replayed tool result keeps its text and images in order.

* fix: Inspect Tool-Output Media Against File Policies

Image URLs and file names in a function_call_output content array reached the
model without the file-policy fragments the same parts get in a message.
Collect those fragments for both item types in packages/api and call that
from the Responses controller.

* test: Cover Content-Array Tool Outputs in the Responses API
2026-11-08 19:22:29 +01:00
lia-by-librechat[bot]
f4154b649e
🦿 chore: Bump Agents SDK to 4.2.1 (#17664)
Some checks failed
Publish `@librechat/client` to NPM / pack (push) Has been cancelled
Publish `librechat-data-provider` to NPM / pack (push) Has been cancelled
Publish `@librechat/data-schemas` to NPM / pack (push) Has been cancelled
Docker Dev Images Build / publish (push) Has been cancelled
Sync Helm Chart Tags / Ignore non-main push (push) Has been cancelled
Sync Helm Chart Tags / Sync chart tags (push) Has been cancelled
Publish `@librechat/client` to NPM / publish-npm (push) Has been cancelled
Publish `librechat-data-provider` to NPM / publish-npm (push) Has been cancelled
Publish `@librechat/data-schemas` to NPM / publish-npm (push) Has been cancelled
* 🦿 chore: Bump Agents SDK to 4.2.0

* test: Adapt Compaction Fixtures to Retained Recent Turns

* test: Preserve the Azure Reasoning Token Contract

* chore: Bump Agents SDK to 4.2.1

---------

Co-authored-by: Lia <lia@librechat.ai>
2026-10-31 15:17:05 -04:00
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
lia-by-librechat[bot]
3d3edaff01
🐘 fix: Preserve Authored Skills Across Approval Resumes (#17630)
* fix: preserve authored skills across approval resumes

* fix: complete authored skill resume contracts

* fix: keep restored skill identity authoritative across batches

* fix: reject replacement skills during authored recovery

---------

Co-authored-by: Lia <lia@librechat.ai>
2026-10-29 22:17:03 +01:00
Marco Beretta
0bcb0aaec1
🛟 fix: Promote Reconciled Compaction Snapshots to the Terminal Row (#16553)
* fix: Keep the Snapshot When the Terminal Write Settled for Reconciliation

* fix: Promote a Reconciled Compaction Snapshot to the Terminal Row

* fix: Anchor and Envelope the Reconciled Snapshot by Its Claim

* test: Cover the Abandoned Compaction Settling After Its Run in E2E

* fix: Withhold the Disconnect Snapshot of Any Durably Settled Turn

* fix: Promote Only a Same-Epoch Reconciled Snapshot and Settle Stopped Compactions

* fix: Plan the Disconnect Snapshot in packages/api and Check the Response Row Before Promoting

* fix: Read the Disconnect Snapshot Rows in the Response Conversation

* fix: Check the Anchor-Derived Error Row Before Promoting a Reconciled Snapshot

* fix: Log a Failed Disconnect Snapshot Plan Instead of Rejecting the Listener

* fix: Let a Reconciled Compaction Promote After an Earlier Live Snapshot

* refactor: Decide the Repeat Disconnect Write in the Snapshot Plan

* refactor: Report Failed Snapshot Row Reads Through the Plan

* fix: Stamp a Promoted Disconnect Snapshot and Read Its Rows Together

* fix: Derive the Compaction Error Row ID Through the Shared Helper

* fix: Plan a Saved Live Compaction Snapshot Again Once Its Turn Settles

* refactor: Queue Disconnect Snapshots and Settle Them in packages/api

* fix: Never Count the Compaction Anchor as Its Own Terminal Row

* fix: Settle Disconnect Snapshots Before Terminal Cleanup Releases the Turn
2026-10-28 11:13:50 +01:00
Marco Beretta
65d0ba8563
🧯 fix: Return Approved Tool and Generation Error Text Instead of Raw Exceptions (#17508)
* fix: Return approved tool and generation error text instead of raw exceptions

* fix: Redact generation error text without the data-schemas helper

* fix: Redact credentials and emails from shown generation errors

* refactor: Move the Wolfram status policy into packages/api

* test: Fix the Wolfram probe constructor and jest summary match

* test: Match the jest pass count through color codes

* fix: Redact credentials a tool input error echoes from its arguments

* fix: Drop free-text fields from typed generation errors under a content policy

* fix: Keep only the code and numeric fields of typed errors under a content policy
2026-10-28 00:39:01 +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
lia-by-librechat[bot]
5cf87548cd
🩰 fix: Keep Subagent Guidance in Main Chat Order (#17394)
* fix: Keep Applied Subagent Guidance in Main Chat Order

* fix: Preserve Pending Controls and Unmatched Legacy Guidance

* fix: Type Retained Control Read Parameters

* fix: Keep Guidance Receipts Truthful Across Delivery States

* fix: Retain Projected Steering Client Identities

* fix: Retain Ordered Guidance Across Terminal Child States

* style: Keep Public Observation Parsing Flat

* fix: Preserve Usable Legacy Activity During Reprojection

* test: Type the Legacy Recovery View Adapter

* fix: Preserve Shared Progress Identity and Public Reasoning

* fix: Forward Host Steering Through Shared Progress

* fix: Replace Tool Argument Placeholders Before Streaming

* fix: Retain Late Child Calls and Parent Steering Content

---------

Co-authored-by: Lia <lia@librechat.ai>
2026-10-24 12:12:57 +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
lia-by-librechat[bot]
a51c45bbf3
🌳 fix: Preserve Primary Files Until Secondary Cleanup Succeeds (#17228)
* fix: Preserve primary files until secondary cleanup succeeds

* test: Use a flat deletion-strategy lookup

* fix: Preserve erasure retries and reconcile removed embeddings

* test: Match deletion regression formatting

* fix: Preserve search intent after vector cleanup

* fix: Repair retained project search files before tool execution

* fix: Normalize Retained Project File Runtime Types

* test: Use the Storage Source Enum in Project Repair Coverage

* fix: Confirm Secondary Cleanup and Preserve Repair Policy

* test: Correct Repair Fixture Types and Cleanup Retry Assertions

* fix: Reconcile Code Copies Compatibly and Charge Shared File Budgets

* fix: Reserve Admitted File Budgets Before Deferred Screening

* fix: Retain Concurrent File Copies and Scope Cleanup by Tenant

* fix: Bound Erasure File Checks and Correct Cleanup Fixtures

* fix: Preserve Provider-Only Assistant File Deletion

* fix: Reconcile Primary Vector Deletions Before Finalization

* fix: Finalize Successful Files in Mixed Cleanup Batches

* test: Load Real File Finalizer in Cleanup Integration Tests

* fix: Preserve Project Routing MIME and Fence File Storage Operations

* fix: Validate Provisioning Principal and Type Project Repair Fixtures

* fix: Recover Provisioning Claims and Retain Uncertain Storage Outcomes

* fix: Normalize File Recovery Results and Reconcile Transport Attempts

* test: Preserve Deployment Routes in Host Provisioning Fixtures

* fix: Recover Deletion Claims and Fence Generated Output Writes

* fix: Preserve Generated Output Commit Snapshots

* test: Use Persisted Owner Type in Generated File Fixture

* test: Type Generated Output Fixture with Its Commit Contract

* fix: Preserve Publication Error Handling and Cleanup Test Boundaries

---------

Co-authored-by: Lia <lia@librechat.ai>
2026-10-23 07:00:20 +02:00
Marco Beretta
472d29a3ee
🪙 fix: Price 1-Hour Prompt Cache Writes at the 1-Hour Rate (#17208)
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: Price 1-Hour Prompt Cache Writes at the 1-Hour Rate

* test: Cover 1-Hour Cache Write Pricing End to End

* test: Price Cache Scenario on the Configured Mock Model

* fix: Accept a 1-Hour Cache Write Rate in Endpoint Token Configs
2026-10-17 15:43:57 +02:00
Marco Beretta
ab8dc9d3d2
🕶️ fix: Keep Temporary Chats Out of Langfuse (#17202)
* fix: Keep Temporary Chats Out of Langfuse

* fix: Gate Forced-Ephemeral and Open Responses Turns From Langfuse

* fix: Treat Legacy and Chat Completion Temporary Turns as Untraced

---------

Co-authored-by: Joel Hirzel <joel.hirzel@eps.ch>
2026-10-17 11:57:35 +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
5fc4371c6a
🪦 refactor: Remove Dead Legacy API Modules and Root Tooling (#17114) 2026-10-15 12:25:24 +02:00
Marco Beretta
20d2c0d43d
🧹 fix: Run the Full Erasure Cascade When an Admin Deletes a User (#17050)
* fix: Run the Erasure Cascade in Admin User Deletion

* refactor: Share Generation Stop Logic Between Self-Service and Admin Deletion

* refactor: Move Admin Erasure Dependency Assembly Into packages/api

* fix: Bind getCleanupJob When Waiting for Generation Persistence

* test: Pin the Deletion Fence Before Admin Generation Stop

* fix: Resolve the Erasure Target Config Fail Closed

* fix: Carry the Target Profile Into Admin Erasure Storage Cleanup

* fix: Keep the Erasure Target Contract Storage Neutral and Reuse the Loaded Identity

* fix: Refuse New Generations Once Account Deletion Has Begun

* fix: Enforce Account Deletion Admission Once in createJob and Narrow the Erasure File Type

* fix: Install the Admission Guard in Every Entrypoint and Purge Refused Jobs

* fix: Guarantee Refused Job Purge and Sanitize Admission Failures

* fix: Route Remote Admission Through createJob and Keep Refusal Cleanup Sanitized

* fix: Log Admission Cleanup Failures With Safe Error Metadata

* refactor: Check Account Deletion Before Creating a Generation and Drain Twice

* refactor: Order Admission Against the Deletion Marker Without a Grace Period

* fix: Sanitize Post-Commit Admission Retirement Failures

* fix: Wire Shared-Server MCP OAuth Cleanup Into Admin Erasure

* fix: Scope Admin Erasure Lookups to the Target Tenant and Await Shared-Link Cleanup

* fix: Resolve the Erasure Target Config Under the Target Tenant

* fix: Run Admin Erasure OAuth Fencing in the Target Tenant

* fix: Match the Split OAuth Invalidate and Disconnect Hooks in Admin Erasure

* refactor: Inject the Tenant Executor Into the Erasure Resolver
2026-10-14 23:54:32 +02:00
Marco Beretta
6e6dc1be11
🪢 fix: Settle Compaction Rows Past Anchor Collisions and Legacy Parts (#16552)
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
* 📴 fix: Stamp Legacy Failure Parts When Settling a Compaction Row

* 📴 fix: Redirect the Collision Error Row to the Live Response Id

* 📴 fix: Withhold the Anchor-Colliding Error Row and Keep Pending Rows Fallbacks

* 📴 fix: Scope the Settled-Job Guard to Compactions and Copy Stamped Parts

* test: Cover the Underscore-Leaf Compaction Failure and Abandoned Replies in E2E

* test: Fail the Underscore-Leaf Compaction Through the Blank Summarizer

* refactor: Return the Final Error Row Id From the Settlement
2026-10-08 23:03:58 +02:00
Marco Beretta
cac13c42e7
🧷 fix: Finalize Stopped Compactions and Verify Their Anchor (#16551)
* 📴 fix: Finalize Compaction Snapshots and Move Abort Policy Into packages/api

* 🔕 fix: Inspect Every Part When Finalizing and Reuse the Loaded Row

* 📴 fix: Settle Finalized Compaction Rows and Verify Their Anchor

* 📴 fix: Withhold the Unanchored Abort Final and Settle Marked Snapshots

* 📴 fix: Consolidate the Compaction Abort Policy Into One Injected Operation

* 📴 fix: Settle the Live Compaction Row Past an Anchor-Shaped Collision

* 📴 fix: Lift the Failed-Turn Settlement Into the Compaction Module

* 📴 fix: Keep a Removed Round's Failure and Guard Settled Jobs From Snapshots

* ⚡ perf: Read Only the Anchor Id in the Abort Existence Check

* 📴 fix: Withhold the Abort Final Only When a Row Needed Writing

* test: Cover Stopped Compaction Finalization and the Missing Anchor in E2E

* fix: Withhold a Stopped Compaction That Carries No Anchor Id

* fix: Settle Stopped Compactions, Announce Finalized Rows, and Own the Abort Read in packages/api

* test: Accept the Model Spec Query on the Stopped Reply Conversation URL

* fix: Report the Anchor Read Failure Beside a Withheld Compaction Abort

* fix: Synthesize a Compaction Failure Only for a Round After the Latest Outcome

* fix: Skip the Anchor Read When a Stopped Turn Writes No Row

* fix: Decide the Disconnect Snapshot Gate in packages/api

The last-subscriber partial save now asks resolveDisconnectSnapshotMode for
the settled-job decision instead of branching on the job record in the CJS
controller.

* fix: Leave an Already Settled Compaction Row to the Path That Settled It
2026-10-05 21:38:22 +02:00
Marco Beretta
edc96d549e
📴 fix: Persist Cancelled Compactions With Their Identity (#16436)
* 📴 fix: Persist Cancelled Compactions With Their Identity

* 🧪 test: Build the Cancelled-Compaction Leaf on a Real Conversation

* 🧪 test: Assert the Withheld Controls on the Live Cancelled Compaction

* 📴 fix: Keep Live Disconnect Compaction Rows Free of a Synthesized Failure

* 🧪 test: Cover the Compaction Flag in the Redis Job Round Trip

* 📴 fix: Keep a Stopped Compaction Honest and Its Anchor Untouched
2026-10-05 21:38:04 +02:00
Atef Bellaaj
3c90cde7d8
🔗 feat: use LibreChat prompt groups as agent instructions (#16686)
* 🔗 feat(agents): use LibreChat prompt groups as agent instructions

Agents can link a prompt group revision or Production as their instructions. The link resolves at the start of each turn through a cached resolver. The cache clears on promote and delete. Editors without VIEW on the group see a restricted placeholder.

* fix: remove duplicate logger import from agent initialization tests

* fix: honor prompt management capabilities for linked agent instructions

* test: seed prompt manager capabilities in authorization fixtures

* fix: clear acknowledged linked prompt edits before version restore

* test: adapt merged chain coverage to prompt-aware payload helper

---------

Co-authored-by: Lia <lia@librechat.ai>
2026-10-04 21:27:26 -04:00
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]
38a9dab3f5
🦫 feat: Enforce Scheduled MCP Read-Only Authority (#16681)
* feat: enforce scheduled MCP read-only authority

* fix: preserve startup admission and enforce consent deadline

* fix: fail closed on malformed scheduled consent

* fix: preserve scheduled MCP authority failure receipts

* fix: preserve scheduled MCP handoffs and manual runs

* fix: persist mandatory scheduled tool policy denials

* fix: fence late scheduled consent and retain denial recovery

* fix: retain scheduled transport denials and prevent replay

* fix: merge retained scheduled denials during settlement

* fix: prevent enrolled schedule completion wakeup escapes

* fix: close scheduled consent admission and receipt races

* fix: retain scheduled completion authority across approval

* fix: retain safe scheduled authorization dependency denials

* fix: sanitize scheduled authorization preparation failures

* fix: bind schedule completion authority to task origin

---------

Co-authored-by: Lia <lia@librechat.ai>
2026-10-03 20:39:43 -04:00
Marco Beretta
7957d0b587
🧾 fix: Commit Resume Provenance With the Approval Claim (#16430)
* fix: persist approval provenance in the resume claim and publish the pre-claim paths from any unapplied abort

The claim CAS now records the provenance it replaces. An abort that lands
before the resumed provider crosses its start CAS publishes those paths, so
schedule deletion, account deletion and user stops no longer label
model-authored chunks as user-submitted.

* test: add approval provenance scenario on the shared approval e2e helpers

* test: seed an earlier started segment before the unapplied abort case

* fix: label abort provenance by the published content and persist the same selection

A path the approval claim added is user-authored only once its tool call
carries output in the abort content, so an abort between the provider
start CAS and the resumed tool keeps the pre-claim labels, and an ask
answer stamped by the abort route keeps its own. AbortResult.jobData
carries the selection so the persisted row matches the final event.

* fix: keep claimed non-tool provenance paths on an abort

Only tool-call paths wait for their resumed call to complete; a steer the
claim already found in the seed content needs no decision to apply.

* fix: count a completed tool call with an empty output as applied in abort provenance

* fix: check abort provenance on the unfiltered content and remap it onto the published parts

* test: type the abort provenance overrides with the job store field names

* test: assert the preserved paths when an unanswered ask aborts
2026-10-03 13:31:20 +02:00
Marco Beretta
fb1dd57a9b
🔓 feat: Remember Tool Approvals Per Conversation (#16557)
* feat: Remember Tool Approvals Per Conversation

Adds an opt-in "Always allow" choice to the tool approval card. When
endpoints.agents.toolApproval.allowAlways is true, the server marks eligible
paused calls with allow_always; approving with scope "session" stores that
exact tool name on the conversation, and later runs in the same conversation
fold the stored names into the policy as exact-name allow entries.

The server enforces every step: the resume route rejects a session scope the
pause did not offer, eligibility is rechecked against the live policy before
storing, the list is written only through an owner-scoped bounded method, and
generic saves and imports cannot set or clear it. Admin deny and ask rules and
programmatic hooks still win, stored names are ignored under dontAsk or when
the flag is off, and native code tools stay under the code approval picker.
The flag defaults to false, so existing deployments keep prompting.

* fix: Share the Effective Approval Policy and Persist Allows After Resume Fences

Offering, resume re-check, scheduled admission and createRun now read one
policy from buildEffectiveToolApprovalPolicy: endpoint rules healed against
MCP alias spellings, then the conversation's remembered tools. A call held by
a healed ask rule is no longer offered "Always allow", and a scheduled fire
whose known tools are all remembered is no longer rejected as pause capable.

The remembered-tools cap and name length cap move to
toolApproval.allowAlwaysMaxTools and allowAlwaysMaxToolNameLength (defaults
64 and 256). The card stops offering the choice for new tools once the cap is
reached instead of silently approving once.

The resume route stores remembered tools only after the schedule and project
context fences pass; a storage failure still approves the call once.

* fix: Offer Always Allow Only When It Will Hold

Offer allow_always only when storing the name would auto-approve the next
identical call on the run's own path: every MCP spelling of the tool passes
the healed static policy and no programmatic or plugin approval hook can
apply to it (the pause payload does not record which hook asked).

Remembered names now expand to every alias spelling of the same tool, and a
deny or ask on any spelling keeps the tool ineligible. A table-driven spec
walks the invariant through the real hook wiring.

* fix: Recheck Approval Hooks Before Remembering a Resumed Approval

The resume-time eligibility recheck now applies the same programmatic and
plugin PreToolUse hook check as marking, with a hook context built from the
resume request and the live plugin hook source. A hook registered after the
pause turns the choice into a one-time approval: nothing is stored and the
resume continues.

Document that toolApproval.allowAlways should be enabled only once every
replica supports it, since older replicas ignore the choice.

* fix: Judge Always Allow Offers Against the Run's Live Aliases and Active Cap

* fix: Charge Only New Tool Names Against the Remembered Approval Cap

* fix: Recheck Remembered Approvals Against the Paused Run's Aliases

* chore: Sort Imports in Agent Run After Rebase
2026-10-03 11:47:32 +02:00
Danny Avila
2529b22a66
🔕 fix: Log Lost Generation Predecessor Fences as Warnings (#16689)
A conditional generation create that loses its predecessor fence is an expected admission outcome: the store rejects before replacing anything, an automatic continuation defers without consuming an attempt, and a client restores its queued turn. Sibling background-tool wake-ups for one conversation race this fence by design, which logged every lost race as an initialization error with a stack.

Route the controller's initialization-failure log through a typed packages/api helper that logs a predecessor mismatch as a concise warning with the stream, conversation, continuation flag, and whether the current generation is active, and keeps every other failure at error level as redacted text.
2026-10-02 20:12:22 -04:00