Skip to content

Releases

v0.8.9-rc1

v0.8.9-rc1 Pre-release
Pre-release

Choose a tag to compare

@lia-by-librechat lia-by-librechat released this 26 Oct 21:55
8d3da9b

https://www.librechat.ai/changelog/v0.8.9-rc1

๐Ÿž๏ธ Highlights

  • Chat Projects with shared instructions and reference files
  • Passkey sign-in, email changes, and stronger two-factor account protection
  • Redesigned chat controls, reply notifications, and right-to-left layouts
  • Deployment themes with configurable colors and appearance
  • MCP Apps and more deliberate tool-approval choices
  • Attached-machine enrollment, per-chat workspace choices, attachment copies, and pull request status
  • Langfuse prompts in the catalog and slash command
  • Recoverable subagent transcripts and clearer background-task progress
  • Node.js 24.22.1 security updates and bounded history/tool previews

Upgrade guidance: https://www.librechat.ai/docs/configuration/upgrade

Click to expand Release Notes

โœจ Features

  • โฌ†๏ธ feat: Migrate to Zod v4 by @danny-avila in #17442
  • ๐Ÿ”Ž feat: Filter Agent Builder Selector to Authored Agents by @berry-13 in #17439
  • ๐ŸŒฟ feat: Branch Tool Fold Rails Into Each Row by @berry-13 in #17407
  • ๐ŸŽด feat: Use Langfuse Prompts from Cards and the Slash Command by @AtefBellaaj in #17104
  • ๐Ÿฌ feat: Sync Langfuse Prompts into the Catalog by @AtefBellaaj in #17095
  • ๐Ÿ–๏ธ feat: Make External Prompt Groups Read-Only by @AtefBellaaj in #17008
  • โ›ฒ feat: Resolve Native and Langfuse Prompts by Source by @AtefBellaaj in #16909
  • ๐Ÿบ feat: Track Prompt Group Source Identity by @AtefBellaaj in #16891
  • ๐Ÿง feat: Preview Langfuse Prompts in Settings by @AtefBellaaj in #16854
  • ๐Ÿช‘ feat: Add Shared Source Author and Distributed Lock Helpers by @AtefBellaaj in #17086
  • ๐Ÿงฌ feat: Re-Derive Azure Groups, Vertex AI, Custom Parameters and Spec Defaults for Config Profiles by @danny-avila in #17399
  • ๐Ÿท๏ธ feat: Hide and Rename Custom Endpoints by Name in Config Profiles by @danny-avila in #17396
  • ๐Ÿงพ feat: Admin Config Write Report, Structured Issues and Deployment-Only Paths by @danny-avila in #17395
  • ๐Ÿ”ญ feat: Admin Config Read APIs (Resolved and Effective Config, Scope Catalog, Env Status) by @danny-avila in #17383
  • ๐Ÿ“Ž feat: Copy Chat Attachments into Attached Workspaces by @danny-avila in #17376
  • ๐Ÿ” feat: Admin Config Secrets v2 (MCP and Azure Credentials, Re-entry, Env Allowlist, Rebinding) by @danny-avila in #17353
  • ๐Ÿง‘โ€โœˆ๏ธ feat: Enroll Machines Through Explicit Browser Approval by @lia-by-librechat[bot] in #17344
  • ๐Ÿ™ˆ feat: Let Config Profiles Hide librechat.yaml MCP Servers and Remove Their Fields by @danny-avila in #17327
  • โš›๏ธ feat: Atomic Admin Config Changes Endpoint (set, unset, tombstone, entry upsert/remove/rename) by @danny-avila in #17328
  • ๐Ÿ”— feat: Link Custom Artifact Mode to Its Instructions Guide by @danny-avila in #17021
  • ๐Ÿ”‘ feat: Keep Dotted Record Keys in Admin Config Writes and Publish the Config Contract by @danny-avila in #17322
  • feat: add masked session replay lifecycle by @graphaelli in #17194
  • ๐Ÿ›‚ feat: Keyboard Submit and Escape for Tool Approval Cards by @berry-13 in #17233
  • ๐Ÿ” feat: Defer MCP OAuth Sign-In Until a Deferred Tool Is Used by @berry-13 in #17225
  • ๐ŸŽจ feat: Paint Inline Deployment Themes From the First Frame by @berry-13 in #17203
  • ๐Ÿข feat: Add Microsoft, Z.ai, IBM and Amazon Nova Model Marks by @berry-13 in #17250
  • ๐Ÿชช feat: Show Each Model's Maker on Its Model List Row by @berry-13 in #17246
  • ๐Ÿงฌ feat: Show the Model Maker's Icon When Another Host Serves the Model by @berry-13 in #17238
  • โŒจ๏ธ feat: Keyboard Submit, Focus and Escape for Ask User Cards by @berry-13 in #17231
  • ๐Ÿ’  feat: Add Gemini 4 Argon Support by @berry-13 in #17200
  • ๐ŸŽ feat: Add Claude Haiku 5.5 Support by @berry-13 in #17201
  • ๐Ÿ›‹๏ธ feat: Open Subagents Directly from Background Tasks by @lia-by-librechat[bot] in #17020
  • ๐Ÿ—ž๏ธ feat: Make Context Usage Responsive and Condensed by @lia-by-librechat[bot] in #17018
  • ๐Ÿ”Œ feat: Integrate Durable Skill Lifecycle Across Writers and Routes by @dustinhealy in #17043
  • ๐Ÿงน feat: Add Bounded Whole-Skill Cleanup Engine by @dustinhealy in #17042
  • ๐Ÿงพ feat: Add Skill Upload Reservation Helpers by @dustinhealy in #17041
  • ๐Ÿงฑ feat: Add Skill Lifecycle Persistence Primitives by @dustinhealy in #17040
  • ๐Ÿ—‘๏ธ feat: Expose Skill Deletion in Management API by @dustinhealy in #17005
  • ๐Ÿงฉ feat: Add Skill Creation and File Deletion to Management API by @dustinhealy in #16878
  • ๐Ÿ—‚๏ธ feat: Audit MCP, Code Worker, Langfuse, Skill Credential, Passkey and Audit Log Access by @berry-13 in #17054
  • ๐Ÿ›‚ feat: Audit Resource Sharing Changes and Fail Closed on Reversible Audit Writes by @berry-13 in #17053
  • ๐Ÿ“œ feat: Audit Admin Role, Group, Config and IdP Role Mutations by @berry-13 in #17052
  • ๐Ÿ“ feat: Cap the Select List at the Popover's Available Height by @berry-13 in #16938
  • ๐ŸŽจ feat: Paint the Operator Theme on a First-Ever Visit by @berry-13 in #16962
  • ๐Ÿ‘‹ feat: Optional Greeting Heading and Footer-Free Welcome Screen by @berry-13 in #17055
  • ๐ŸŒ— feat: Hand the Colour Mode Over on an Entry Link by @berry-13 in #17056
  • ๐Ÿ”Œ feat: Add a Connected Account Setting for Pull Requests by @berry-13 in #16990
  • ๐Ÿ—ณ๏ธ feat: Approval-Responded, Output-Denied and Ask-User Parts in the UI Message View by @berry-13 in #16961
  • ๐Ÿ”‘ feat: Let Users Connect Their Own Account for Pull Request Lookups by @berry-13 in #16989
  • โ™ป๏ธ feat: Share Pull Request Lookups Across Replicas Through Redis by @berry-13 in #16988
  • ๐Ÿชฃ feat: Look Up Bitbucket Cloud Pull Requests by @berry-13 in #16987
  • โŒจ๏ธ feat: Change Default Chat Preferences by [@berry-13](https://github.com/...
Read more

v0.8.8

v0.8.8 Pre-release
Pre-release

Choose a tag to compare

@danny-avila danny-avila released this 01 Oct 02:49
e8f3be0

https://www.librechat.ai/changelog/v0.8.8

๐Ÿž๏ธ Highlights

  • Meet Lia: Building LibreChat with LibreChat.
  • Agent control: Interrupt, steer, queue messages, answer questions, and approve tool calls.
  • Unified Agent Builder: Same-run Skill authoring, opt-in Programmatic Tool Calling, and background tools.
  • Background tasks: Clearer task cards, header controls, and automatic delivery of supported results.
  • Scheduled Chats: Cron, time zones, and Project destinations. In beta: experimental and disabled by default.
  • Code workspaces: Stateful sessions, attached machines, recovery, and guarded permissions. Highly experimental; compatible services required.
  • Beta Agents API: Improved compatibility with Chat Completions, Open Responses, Agent/Skill management, and introduced Agent Events
  • Experimental Agent Plugins: Bundle Skills and MCP servers, with opt-in command hooks.
  • Execution visibility: Live activity, tool timing, Context Usage, optional costs, and a configured Langfuse Trace Viewer.
  • Chat improvements: Draggable pins, chat filtering, manual compaction, mobile polish, and automatic attachment routing.
  • Model updates: GPT-6 and GPT-6.1 Sol, Claude Opus/Sonnet 5.5, and Gemini 3.8 Flash. GPT-6.1 Sol uses family-fallback limits and pricing.
  • Performance and security: Faster rendering and streaming and long-thread sends, stronger credential boundaries, tenant-scoped endpoints, and 2FA management limits.

Click to expand Release Notes

For detailed changes in the release candidates, see:

Operator configuration changes: Config v1.3.15, v1.3.16, and v1.3.17.


Changes Since v0.8.8-rc4

โœจ Features

  • ๐Ÿš๏ธ feat: Recover Coding Chats With Missing Workspaces by @lia-by-librechat in #16273
  • ๐ŸŒซ๏ธ feat: Add Bounded PII Text Transformation (library groundwork only; message ingress still blocks matches) by @lia-by-librechat in #16295
  • ๐Ÿ“‹ feat: View and Stop Background Tasks From the Chat Header by @danny-avila in #16348
  • ๐Ÿงฒ feat: Attach or Leave a Workspace on a Saved Chat by @lia-by-librechat in #16124
  • ๐Ÿชœ feat: Title an Open Activity Fold and Reach Failed Calls in One Click by @danny-avila in #16390
  • ๐Ÿ’ญ feat: Bring the Streaming Thought Peek Back Under a Collapsed Live Card by @danny-avila in #16394
  • ๐ŸŽด feat: Render Background Tasks as Native Tool Cards by @lia-by-librechat in #16407
  • ๐ŸŽผ feat: Add Claude Sonnet 5.5 Support by @danny-avila in #16460
  • ๐Ÿ•˜ feat: Distinguish Tool Preparation From Tool Call Time by @lia-by-librechat in #16455
  • ๐Ÿ›ค๏ธ feat: Route Linked Worktree Requests into Per-Worktree Lanes by @danny-avila in #16477
  • ๐ŸŽฏ feat: Tolerant Workspace Edits with Host-Rendered Conflict Diagnostics by @danny-avila in #16520
  • ๐Ÿงฌ feat: Resolve GPT Point Releases to Their Family and Add GPT-6.1 Sol by @danny-avila in #16526
  • ๐Ÿ๏ธ feat: Scope YAML Custom Endpoints by Tenant by @danny-avila in #16537

๐Ÿ› Fixes

Read more

v0.8.8-rc4

v0.8.8-rc4 Pre-release
Pre-release

Choose a tag to compare

@danny-avila danny-avila released this 23 Sep 03:58
361553f

https://www.librechat.ai/changelog/v0.8.8-rc4

๐Ÿž๏ธ Highlights

  • GPT-6 Sol, GPT-6 Luna, and Claude Opus 5.5
  • Caller-executed tools for the Open Responses API
  • Same-run Skill authoring and execution
    - Agentic Coding:
    • conversation-isolated attached workspaces + repository instructions (AGENTS.md)
  • Expanded Trace Viewer with steps, roles, previews, and cost powered by Langfuse
  • System-event turns and single-row live activity
  • Faster streaming Markdown, model search, and Agent messages
  • Stronger MCP authentication and per-request headers

Click to expand Release Notes

โœจ Features

๐Ÿ› Fixes

Read more

v0.8.8-rc3

v0.8.8-rc3 Pre-release
Pre-release

Choose a tag to compare

@danny-avila danny-avila released this 15 Sep 02:34
1df4484

https://www.librechat.ai/changelog/v0.8.8-rc3

๐Ÿž๏ธ Highlights

  • Experimental: Bring-Your-Own-Machine for scalable coding agents
  • Agent/Skills CRUD API improvements
  • Conversation Trace Viewer and Subagent file sharing
  • GPT-6 Astra and expanded Context Usage
  • File text fallback, unified artifact rows, and upload previews
  • Unified pinning, chat filtering, and interface polish
  • MCP, OpenID, Agent, and Code reliability improvements

Click to expand Release Notes

โœจ Features

๐Ÿ› Fixes

  • ๐Ÿงผ fix: Render Agent Description HTML Safely by @danny-avila in #15951
  • ๐Ÿซด fix: Preserve Queued Follow-Ups Through Handoff by [@...
Read more

v0.8.8-rc2

v0.8.8-rc2 Pre-release
Pre-release

Choose a tag to compare

@danny-avila danny-avila released this 03 Sep 02:28
f9f1b2f

https://www.librechat.ai/changelog/v0.8.8-rc2

๐Ÿž๏ธ Highlights

  • Interrupt Agent runs before visible output, steer or queue follow-ups, and recover tool-limited turns
  • Optional generated activity groups, live phase cards, and reasoning labels
  • Unified Agent Builder with standalone Skill authoring, background tools, intent labels, and Programmatic Tool Calling
  • Durable Agent Events, actor mailboxes, receipts, human pauses, and background completion wakeups
  • Saved Agent teams, deeper Subagent history, stable event panels, live controls, and automatic parent continuation
  • Experimental Agent Plugins and highly experimental Code environments with guarded file and command permissions
  • Agent memory isolation and categorized Context Usage with optional cost
  • Redesigned Projects, full-message chat search, searchable settings, shortcuts, pinning, and mobile navigation
  • Experimental Scheduled Chats with cron, time zones, weekly cadence, and project destinations
  • Stable shared links, personal copies, editable long pastes, and attachment-only turns
  • Fullscreen artifacts, Mermaid export, PowerPoint templates, and original file downloads
  • Keenable keyless web search plus expanded SearXNG and Tavily controls
  • Default security headers, opt-in nonce CSP, authenticated local images, Code Interpreter JWTs, and stronger SAML/OIDC flows
  • In-app Langfuse connections, tenant fanout, export telemetry, and authorized session links
  • Auditable source-aware content filtering, tenant Insights, and encrypted admin configuration
  • GPT-5.6, Claude Fable 5.1, Opus 5 and Sonnet 5, Gemini 3.8/3.7/3.6 Flash, and Gemini 3.5 Flash-Lite
  • Adaptive streaming, automatic generation protocol v2, Redis failover recovery, and live MCP catalog refresh

Click to expand Release Notes

โœจ Features

  • ๐Ÿ•’ feat: Track terms acceptance timestamp by @berry-13 in #10810
  • ๐Ÿ”„ feat: Continue Shared Conversations as Personal Copies by @berry-13 in #13714
  • ๐Ÿช feat: HITL Tool Approval Scaffolding (Slice A) by @danny-avila in #12938
  • ๐Ÿง  feat: Add Memory as an Agent Capability with Inline Tools and Ephemeral Badge by @danny-avila in #13869
  • ๐Ÿ“‡ feat: Agent Contact Visibility with Owner Fallback by @peeeteeer in #13663
  • ๐ŸชŸ feat: Faithful Over-Window Context Estimate via Prune Mirror and Overhead Reserve by @danny-avila in #13959
  • ๐Ÿชญ feat: Add opt-in Langfuse fanout gateway + collector by @upman in #13872
  • ๐Ÿช feat: Human-in-the-Loop Runtime - Tool Approval + Ask-User-Question (Slice B) by @danny-avila in #13942
  • ๐Ÿช— feat: Dock-Style Fisheye Nav Rail With Instant Hover Preview by @danny-avila in #14021
  • ๐Ÿค– feat: Add Claude Sonnet 5 Support by @danny-avila in #14042
  • ๐Ÿฅท feat: Add showInMenu Option to Model Specs by @alexkorep in #14034
  • ๐Ÿซท feat: Exclude File Authoring Tools From Eager Execution by @danny-avila in #14051
  • ๐Ÿช feat: Configurable Tool-Approval Policy via Programmatic Hooks by @danny-avila in #14025
  • ๐Ÿงน feat: Eager HITL Checkpoint Cleanup (Expiry + Deletion) & Full-Wiring E2E by @danny-avila in #14123
  • ๐Ÿงฐ feat: Redesign Agent Builder with Unified Tools Marketplace, Skills & Orchestration by @berry-13 in #13952
  • ๐Ÿ“ก feat: add rum browser page-load diagnostics by @upman in #14106
  • ๐ŸŽš๏ธ feat: Explicit "Use All Skills" Toggle in the Skills Section by @berry-13 in #14125
  • ๐Ÿ™‹ feat: ask_user_question - agent-initiated questions with durable pause/resume by @danny-avila in #14139
  • ๐Ÿ—‚๏ธ feat: Per-Agent Memory Partitions by @danny-avila in #14084
  • ๐Ÿค– feat: Add GPT-5.6 (Sol/Terra/Luna) OpenAI Models by @danny-avila in #14206
  • ๐Ÿชญ feat: support per-run central export suppression by @upman in #14207
  • โœจ feat: stateful_code_sessions capability for warm Code API sandbox sessions (experimental) by @danny-avila in #14150
  • ๐Ÿง  feat: Add GPT-5.6 reasoning.mode + reasoning.context (Responses API) by @danny-avila in #14233
  • ๐Ÿงต feat: Background Tool Calls for Agents & Model Specs by @danny-avila in #14197
  • ๐Ÿ—๏ธ feat: Encrypted Langfuse Fanout Config by @dustinhealy in #14107
  • ๐Ÿงญ feat: Mid-Run Steering and Queued Messages for Agent Runs by @danny-avila in #14220
  • โ™จ๏ธ feat: Prewarm Stateful Code Sandboxes with Cold-Boot UX Feedback by @danny-avila in #14239
  • ๐Ÿ“› feat: Add Client Name Header to Tavily Search Requests by @manisrinivasan2k1 in #14082
  • ๐Ÿ’ฌ feat: Explain Steering & Queuing at Every User-Facing Surface by @danny-avila in #14260
  • ๐Ÿ–ผ๏ธ feat: Return Sandbox Images From read_file as Viewable Artifacts by @danny-avila in #14277
  • feat: add low-noise Redis observability by @upman in #14309
  • โœ‹ feat: Add Reclaim-Gated Controls to In-Flight Steers by @danny-avila in #14321
  • ๐Ÿซง feat: Float In-Flight Steers Over the Thread with Collapsible Content by @danny-avila in #14365
  • โšก feat: Add Gemini 3.6 Flash and Gemini 3.5 Flash-Lite Support by @danny-avila in #14369
  • ๐Ÿงต feat: Native Background Execution for Code Interpreter Tools by @danny-avila in #14386
  • โœณ๏ธ feat: Claude Opus 5 Support by @danny-avila in #14422
  • โฑ๏ธ feat: Configurable HTTP Server Timeouts by @danny-avila in #14481
  • ๐Ÿ•ถ feat: Generalize Admin Config Secret Redaction by @dustinhealy in #14509
  • ๐Ÿท๏ธ feat: Activity Groups With Fast-Model Headers by @danny-avila in #14391
  • ๐Ÿ—๏ธ feat: Custom Endpoint API Key Encryption via Array Secret Registry by @danny-avila in #14510
  • ๐ŸŽฏ feat: Tool Intent Label Capability (tool_intents) by @danny-avila in #14499
  • ๐Ÿชข feat: Langfuse Fanout Connection Setting by @danny-avila in #14108
  • ๐Ÿ›‘ feat: Preemptive Steer - Backend Interrupt & Steer by @danny-avila in #14518
  • ๐ŸŽฏ feat: Per-Tool Intent Labels for Model Specs by @danny-avila in #14526
  • โšก feat: Interrupt & Steer, Client by @danny-avila in #14528
  • ๐Ÿงต feat: Background-Native Code Execution Tools by @danny-avila in #14532
  • ๐ŸŽฏ feat: Render Tool Intent as the Live Tool-Call Label by @danny-avila in #14536
  • ๐ŸŽฏ feat: Per-Tool Intent Label Toggles in the Agent Builder by @danny-avila in #14550
  • โšก feat: Reliable Interrupt & Steer Escalation and Recovery by @danny-avila in #14558
  • ๐Ÿ’ฌ feat: Interim Progress Card for Streaming Q&A Calls by @danny-avila in #14576
  • ๐Ÿšฆ feat: Configurable Circuit Breakers for Runaway Streamed Tool Args by @danny-avila in #14613
  • โšก feat: Coalesce Redis Streaming Delta Publications into Windowed Batches by @danny-avila in #14614
  • ๐Ÿ”’ feat: Add allowedAddresses Exemption to Speech (STT/TTS) and OCR Config Schemas by @dustinhealy in #14559
  • ๐ŸŒŠ feat: Wire Adaptive Stream Smoothing Across Google, Bedrock, and Zero-Disable Semantics by @danny-avila in #14660
  • ๐Ÿ”— feat: Admin Panel Link in Settings for Admins by @dustinhealy in #14662
  • ๐Ÿ‘‹ feat: Day-Aware Landing Greeting Schedule by @berry-13 in #14633
  • ๐Ÿ”‘ feat: Refresh-Capable Google Admin OAuth Sessions by @dustinhealy in #13832
  • ๐Ÿ›ก๏ธ feat: Add Batched MCP Authority Proofs by @danny-avila in #14688
  • ๐Ÿช feat: Add Claude Hook Compatibility Layer by @danny-avila in #14412
  • โ›ถ feat: add fullscreen artifact ...
Read more

v0.8.8-rc1

v0.8.8-rc1 Pre-release
Pre-release

Choose a tag to compare

@danny-avila danny-avila released this 14 Aug 07:33
eaef87f

https://www.librechat.ai/changelog/v0.8.8-rc1

๐Ÿž๏ธ Highlights

  • Interrupt or steer Agent runs in progress, or queue the next message
  • Agents can ask up to four related questions in one form, pause for input or approval, then resume
  • Redesigned Agent Builder with a unified Tools marketplace and background tools
  • Experimental Agent Plugins with deployment Skills, MCP servers, and opt-in command hooks
  • Activity groups, parent phase summaries, and live tool intent labels
  • Experimental stateful Code Interpreter sessions with reusable conversation workspaces
  • Agent-managed memory with optional per-agent isolation
  • Stable shared-link updates, active-link badges, and personal copies
  • Fullscreen artifact previews and Mermaid SVG/PNG export
  • In-app Langfuse connections, tenant fanout, and admin session links
  • Unified message layouts, multi-part response editing, and full-message copy
  • Smooth text fade-in, adaptive streaming, and live MCP tool-catalog refresh
  • Stronger SSRF guards for speech, OCR, and web tools
  • Provider updates: GPT-5.6, Claude Opus 5 and Sonnet 5, Gemini 3.7 and 3.6 Flash, and Gemini 3.5 Flash-Lite

Click to expand Release Notes

โœจ Features

  • ๐Ÿ•’ feat: Track terms acceptance timestamp by @berry-13 in #10810
  • ๐Ÿ”„ feat: Continue Shared Conversations as Personal Copies by @berry-13 in #13714
  • ๐Ÿช feat: HITL Tool Approval Scaffolding (Slice A) by @danny-avila in #12938
  • ๐Ÿง  feat: Add Memory as an Agent Capability with Inline Tools and Ephemeral Badge by @danny-avila in #13869
  • ๐Ÿ“‡ feat: Agent Contact Visibility with Owner Fallback by @peeeteeer in #13663
  • ๐ŸชŸ feat: Faithful Over-Window Context Estimate via Prune Mirror and Overhead Reserve by @danny-avila in #13959
  • ๐Ÿชญ feat: Add opt-in Langfuse fanout gateway + collector by @upman in #13872
  • ๐Ÿช feat: Human-in-the-Loop Runtime - Tool Approval + Ask-User-Question (Slice B) by @danny-avila in #13942
  • ๐Ÿช— feat: Dock-Style Fisheye Nav Rail With Instant Hover Preview by @danny-avila in #14021
  • ๐Ÿค– feat: Add Claude Sonnet 5 Support by @danny-avila in #14042
  • ๐Ÿฅท feat: Add showInMenu Option to Model Specs by @alexkorep in #14034
  • ๐Ÿซท feat: Exclude File Authoring Tools From Eager Execution by @danny-avila in #14051
  • ๐Ÿช feat: Configurable Tool-Approval Policy via Programmatic Hooks by @danny-avila in #14025
  • ๐Ÿงน feat: Eager HITL Checkpoint Cleanup (Expiry + Deletion) & Full-Wiring E2E by @danny-avila in #14123
  • ๐Ÿงฐ feat: Redesign Agent Builder with Unified Tools Marketplace, Skills & Orchestration by @berry-13 in #13952
  • ๐Ÿ“ก feat: add rum browser page-load diagnostics by @upman in #14106
  • ๐ŸŽš๏ธ feat: Explicit "Use All Skills" Toggle in the Skills Section by @berry-13 in #14125
  • ๐Ÿ™‹ feat: ask_user_question - agent-initiated questions with durable pause/resume by @danny-avila in #14139
  • ๐Ÿ—‚๏ธ feat: Per-Agent Memory Partitions by @danny-avila in #14084
  • ๐Ÿค– feat: Add GPT-5.6 (Sol/Terra/Luna) OpenAI Models by @danny-avila in #14206
  • ๐Ÿชญ feat: support per-run central export suppression by @upman in #14207
  • โœจ feat: stateful_code_sessions capability for warm Code API sandbox sessions (experimental) by @danny-avila in #14150
  • ๐Ÿง  feat: Add GPT-5.6 reasoning.mode + reasoning.context (Responses API) by @danny-avila in #14233
  • ๐Ÿงต feat: Background Tool Calls for Agents & Model Specs by @danny-avila in #14197
  • ๐Ÿ—๏ธ feat: Encrypted Langfuse Fanout Config by @dustinhealy in #14107
  • ๐Ÿงญ feat: Mid-Run Steering and Queued Messages for Agent Runs by @danny-avila in #14220
  • โ™จ๏ธ feat: Prewarm Stateful Code Sandboxes with Cold-Boot UX Feedback by @danny-avila in #14239
  • ๐Ÿ“› feat: Add Client Name Header to Tavily Search Requests by @manisrinivasan2k1 in #14082
  • ๐Ÿ’ฌ feat: Explain Steering & Queuing at Every User-Facing Surface by @danny-avila in #14260
  • ๐Ÿ–ผ๏ธ feat: Return Sandbox Images From read_file as Viewable Artifacts by @danny-avila in #14277
  • feat: add low-noise Redis observability by @upman in #14309
  • โœ‹ feat: Add Reclaim-Gated Controls to In-Flight Steers by @danny-avila in #14321
  • ๐Ÿซง feat: Float In-Flight Steers Over the Thread with Collapsible Content by @danny-avila in #14365
  • โšก feat: Add Gemini 3.6 Flash and Gemini 3.5 Flash-Lite Support by @danny-avila in #14369
  • ๐Ÿงต feat: Native Background Execution for Code Interpreter Tools by @danny-avila in #14386
  • โœณ๏ธ feat: Claude Opus 5 Support by @danny-avila in #14422
  • โฑ๏ธ feat: Configurable HTTP Server Timeouts by @danny-avila in #14481
  • ๐Ÿ•ถ feat: Generalize Admin Config Secret Redaction by @dustinhealy in #14509
  • ๐Ÿท๏ธ feat: Activity Groups With Fast-Model Headers by @danny-avila in #14391
  • ๐Ÿ—๏ธ feat: Custom Endpoint API Key Encryption via Array Secret Registry by @danny-avila in #14510
  • ๐ŸŽฏ feat: Tool Intent Label Capability (tool_intents) by @danny-avila in #14499
  • ๐Ÿชข feat: Langfuse Fanout Connection Setting by @danny-avila in #14108
  • ๐Ÿ›‘ feat: Preemptive Steer - Backend Interrupt & Steer by @danny-avila in #14518
  • ๐ŸŽฏ feat: Per-Tool Intent Labels for Model Specs by @danny-avila in #14526
  • โšก feat: Interrupt & Steer, Client by @danny-avila in #14528
  • ๐Ÿงต feat: Background-Native Code Execution Tools by @danny-avila in #14532
  • ๐ŸŽฏ feat: Render Tool Intent as the Live Tool-Call Label by @danny-avila in #14536
  • ๐ŸŽฏ feat: Per-Tool Intent Label Toggles in the Agent Builder by @danny-avila in #14550
  • โšก feat: Reliable Interrupt & Steer Escalation and Recovery by @danny-avila in #14558
  • ๐Ÿ’ฌ feat: Interim Progress Card for Streaming Q&A Calls by @danny-avila in #14576
  • ๐Ÿšฆ feat: Configurable Circuit Breakers for Runaway Streamed Tool Args by [@danny-avila](https://github.com/danny...
Read more

v0.8.7

v0.8.7 Pre-release
Pre-release

Choose a tag to compare

@danny-avila danny-avila released this 24 Jun 19:41
9e74cc0

https://www.librechat.ai/changelog/v0.8.7

๐Ÿž๏ธ Highlights

  • Chat projects for organizing chats into folders
  • Context Usage gauge showing current window usage, tokens used, and cost (optional)
  • Agents with skills enabled can author new skills on the fly
  • GitHub sync for skills, and local bundled skills
  • Settings redesign, keyboard shortcuts, default pinned tools, and pinned conversations.
  • Provider updates:
    • Claude Fable 5, Anthropic custom endpoints, prompt cache TTL, Google URL Context with YouTube handling, and custom endpoint option for reasoning replay.
  • Shared links, OpenID, and MCP now have stronger access controls and safer auth flows.
  • Bundled Admin Panel to default compose files
  • Released Code Interpreter for secure code execution and file generation

Click to expand Release Notes

For detailed changes in the release candidate, see:


Changes Since v0.8.7-rc1

โœจ Features

  • ๐Ÿ”š feat: Add Bottom Terminus Node to Message Minimap Navigation by @danny-avila in #13853
  • ๐Ÿช™ feat: SDK-Aligned Context-Usage Projection by @danny-avila in #13801
  • ๐Ÿ”– feat: Add Pinned Conversations by @dlew in #13492
  • ๐Ÿ“› feat: Tag Langfuse Traces With Tenant ID by @upman in #13808
  • ๐Ÿ•ฐ๏ธ feat: Resolve Agent Prompt Time Variables in User's Timezone by @berry-13 in #13815
  • ๐ŸŽ›๏ธ feat: Redesign Settings with Registry-Driven Dialog, Search, and Mobile Drill-In by @berry-13 in #13722
  • ๐Ÿ”‘ feat: Agent API Keys management UI in Settings โ†’ Data controls by @berry-13 in #13819
  • ๐Ÿ“’ feat: Audit Log Backend for SystemGrant Assign and Revoke Events by @dustinhealy in #13087
  • ๐Ÿ• feat: Add promptCacheTtl model parameter for 1h/5m cache duration by @danny-avila in #13835
  • ๐Ÿ”‘ feat: Surface User-Provided API Keys in Settings, Scoped to Reachable Endpoints by @danny-avila in #13864
  • ๐Ÿช™ feat: Add Token Pricing for Devstral, Voxtral, Holo2, and Mistral Medium by @JumpLink in #13863
  • ๐Ÿ“Œ feat: Seed Default Pinned Tools and MCP Dropdown via Interface Config by @danny-avila in #13865
  • ๐Ÿ”— feat: Snapshot Files for Shared-Link Attachments by @danny-avila in #13740
  • ๐Ÿ–‡๏ธ feat: Reference Selected Chat Text with Multi-Quote Popup by @danny-avila in #13868
  • ๐Ÿณ feat: Bundle Admin Panel in Docker Compose Stacks by @danny-avila in #13876
  • โŒจ๏ธ feat: Keyboard Shortcuts by @berry-13 in #12425
  • ๐Ÿง  feat: Configurable Reasoning Replay for Custom Endpoints by @danny-avila in #13921
  • ๐Ÿ“บ feat: Google URL Context Param with Native YouTube Video Understanding by @danny-avila in #13924

๐Ÿ› Fixes

  • ๐ŸŽค fix: Keep Microphone Icon Visible On Initial Chat Render by @danny-avila in #13788
  • ๐Ÿ—œ๏ธ fix: Support Windows ZIP MIME Uploads by @danny-avila in #13794
  • ๐Ÿฅฝ fix: Restrict MCP Server URL Disclosure to Admins, Owners, and Editors by @dustinhealy in #13784
  • ๐Ÿฉน fix: Bill Anthropic Prompt-Cache Tokens Once by @danny-avila in #13798
  • ๐Ÿชƒ fix: Restore Raw Spec Fallback for Enforced Presets by @danny-avila in #13804
  • ๐Ÿ” fix: Honor Admin-Panel MCP Allowlist Overrides Without Restart by @danny-avila in #13814
  • ๐Ÿ”– fix: Decrement Bookmark Counts When Deleting Conversations by @danny-avila in #13830
  • ๐Ÿ”— fix: Surface Share Permissions Load Error as Alert Button With Tooltip by @danny-avila in #13833
  • ๐Ÿงท fix: Preserve Document Priority on Section-Scoped Config Writes by @dustinhealy in #13772
  • ๐Ÿชž fix: Match Prompt Cache TTL Control to Region Combobox Styling by @danny-avila in #13839
  • ๐Ÿ› fix: Resolve dayjs plugin ESM imports in data-provider by @danny-avila in #13851
  • โ™Š fix: Strip Remaining Unsupported JSON Schema Keywords for Gemini MCP Tools by @danny-avila in #13850
  • ๐ŸŽ’ fix: Apply OCR Context to Responses API Agents and Handoffs by @Airamhh in #13707
  • ๐Ÿท๏ธ fix: Scope File Search entity_id to Agent Knowledge-Base Files Only by @msserpa in #13693
  • ๐Ÿชข fix: Paginate MCP tools/list to Load All Tools by @TomasPalsson in #13840
  • ๐Ÿšช fix: Gate Artifacts Toggle on Agent Capability Flag by @serhiizghama in #13665
  • ๐ŸŽฏ fix: Narrow Public Share 401 Bypass to the Share Endpoint Only by @danny-avila in #12905
  • ๐Ÿ” fix: Gate Shared Startup Config By Link Access by @danny-avila in #13897
  • โœ‚๏ธ fix: Cap Audit Chain Verification and Honor Client Cancellation by @danny-avila in #13903
  • ๐Ÿช fix: Validate Shared-File Cookie Auth Against the Live Refresh Session by @danny-avila in #13908
  • ๐Ÿ’ฐ fix: Bound MCP tools/list Pagination with Aggregate Budgets by @danny-avila in #13909
  • ๐Ÿชฃ fix: Cap Context Projection Workload Before Tokenization by @danny-avila in #13910
  • ๐Ÿชœ fix: Strip Caller-Supplied Priority from Assign-Only Config Upserts by @danny-avila in #13911
  • ๐Ÿ›‚ fix: Re-Check execute_code Authorization on Event-Driven Tool Loads by @danny-avila in #13912
  • ๐Ÿค fix: Withhold Custom Endpoint Headers for User URLs by @danny-avila in #13917
  • ๐Ÿงพ fix: Harden Historical File Authorization by @danny-avila in #13918
  • ๐Ÿงญ fix: Harden User Provided Endpoint URL Protection by @danny-avila in #13919
  • ๐Ÿ› fix: Prevent Infinite Render Loop on Code-Execution File Preview by @danny-avila in #13922
  • ๐Ÿ–ฑ๏ธ fix: Summon Quote Popup on Double-Click Word Selection by @danny-avila in #13923
  • ๐Ÿงน fix: Order Enabled Guard After Config Expansion in useGetAgentByIdQuery by @dlew in #13927
  • ๐ŸŒต fix: Align Mention Empty Result Behavior With Skills Command by @Oliver777int in #13928
  • ๐Ÿชค fix: Guard Prompts Popover Against Empty Result Keyboard Navigation by @danny-avila in [#13...
Read more

v0.8.7-rc1

v0.8.7-rc1 Pre-release
Pre-release

Choose a tag to compare

@danny-avila danny-avila released this 15 Jun 19:38
055585f

๐Ÿž๏ธ Highlights

  • Access, Auth, and MCP: Shared-link ACLs, OpenID role sync/token reuse, MCP OBO, request-scoped MCP flows, resumable cleanup, and OAuth/proxy hardening.
  • Agents, Skills, and Projects: Chat projects, skill file authoring tools, deployment/GitHub Skills, scoped sync status, model-spec controls/starters, and marketplace access.
  • Safety and Admin: Configurable message PII filtering and hardened model-spec Subagent controls.
  • Observability and Operations: Auth-isolated RUM proxying with outcome metrics, auth fallback telemetry, opt-in Redis command tracing, Langfuse scores, Node 24 Docker builds, and stronger CI.
  • Conversation UX: Immediate titles, hover timestamps, message-nav scrubbing, stable branches, sanitized shares, deploy recovery, and route reload fixes.
  • Providers and Reasoning: Claude Fable 5, GPT-5.5/frontier defaults, native Anthropic custom endpoints, protected user URLs, provider headers, and Gemini/Imagen/Bedrock fixes.
  • Streaming and Performance: Memoized Markdown streaming, per-tool onResult, real-time context, opt-in cost display, scoped token config caches, subagent billing, lazy loading, and tsdown builds.

Click to expand Release Notes

What's Changed

โœจ Features

  • ๐Ÿ” feat: Use SecretInput for Sensitive Fields by @berry-13 in #12955
  • ๐Ÿ“ก feat: Add Authenticated Proxy Mode for Browser RUM Telemetry by @upman in #13464
  • ๐Ÿ”’ feat: Add On-Behalf-Of (OBO) token exchange support for MCP server connections by @jcbartle in #13429
  • ๐Ÿชœ feat: Add OpenID Role Sync by @danny-avila in #13415
  • ๐Ÿ—ƒ๏ธ feat: Retain Agent Files During All-Data Retention by @danny-avila in #13477
  • ๐ŸŽญ feat: Add Credential-Free Playwright Smoke Suite with a Local Mock LLM by @teresama in #13472
  • โšก feat: Immediate Conversation Title Generation by @danny-avila in #13395
  • ๐Ÿ›ฐ๏ธ feat: Add Auth Fallback Observability by @danny-avila in #13488
  • ๐Ÿ”— feat: Add Granular Access Control to Shared Links via ACL System by @AtefBellaaj in #13051
  • ๐Ÿ—‚๏ธ feat: Add Private Chat Projects by @danny-avila in #13467
  • ๐ŸŽš๏ธ feat: Add Focus Management and Drag-to-Scrub to MessageNav by @danny-avila in #13497
  • ๐Ÿ—‚๏ธ feat: Add Agent File Authoring Tools by @danny-avila in #13435
  • ๐Ÿ“œ feat: Improve Skill Authoring Guidance by @danny-avila in #13517
  • ๐Ÿงญ feat: Scope Model Spec Skills by @danny-avila in #13522
  • ๐Ÿ—‚๏ธ feat: Add Deployment Skill Directory by @danny-avila in #13523
  • ๐Ÿช feat: Surface Agent Marketplace in Model Selector by @danny-avila in #13553
  • ๐ŸŒฑ feat: Support Soft Default Model Spec by @danny-avila in #13554
  • โณ feat: Make OpenID Token Reuse Window Configurable by @pboers1988 in #13546
  • ๐Ÿ“Š feat: Surface Message Feedback as Langfuse Scores by @graphaelli in #13544
  • ๐Ÿงฉ feat: Enable Model Spec Subagents by @danny-avila in #13598
  • ๐Ÿ›ก๏ธ feat: Configurable Message PII Filter by @dustinhealy in #13602
  • ๐Ÿ“– feat: Add Claude Fable 5 Support by @danny-avila in #13628
  • ๐Ÿ›ฐ๏ธ feat: Add GPT-5.5 + Frontier OpenAI Models, Drop Deprecated Defaults by @danny-avila in #13636
  • ๐Ÿงฌ feat: Add GitHub Skill Sync by @danny-avila in #13293
  • ๐Ÿท๏ธ feat: Surface Model Spec Branding on Landing and Selector by @danny-avila in #13662
  • ๐Ÿ“Š feat: Real-Time Context Window & Token Usage Tracking by @danny-avila in #13670
  • ๐Ÿ“ฌ feat: Report Tool Results Per Call via onResult Channel by @danny-avila in #13698
  • โŒš feat: Show Message Timestamps on Hover by @danny-avila in #13709
  • ๐Ÿ’ฌ feat: Conversation Starters for Model Specs by @danny-avila in #13710
  • ๐Ÿ’พ feat: Persist Context Breakdown & Branch/Total Usage Cost by @danny-avila in #13734
  • ๐Ÿ’ธ feat: Per-Agent Endpoint Token Config in Multi-Endpoint Billing by @danny-avila in #13738
  • ๐Ÿช™ feat: Context Gauge UX, Hover Snapshot, Click Breakdown, Currency, Cost-On-By-Default by @danny-avila in #13739
  • ๐Ÿ“จ feat: Custom Headers on Built-in Provider Endpoints by @danny-avila in #13742
  • ๐Ÿ…ฐ๏ธ feat: Native Anthropic Provider for Custom Endpoints by @danny-avila in #13748

๐Ÿ› Fixes

Read more

v0.8.6

v0.8.6 Pre-release
Pre-release

Choose a tag to compare

@danny-avila danny-avila released this 01 Jun 03:12
566e20b

https://www.librechat.ai/changelog/v0.8.6

๐Ÿž๏ธ Highlights

  • Agent Skills & Subagents
    • Agent Skills package reusable instructions, references, scripts, assets, and permissions into portable capabilities that agents can invoke automatically or on request.
    • Subagents let agents delegate specialized work to other agents while preserving upload, user, and MCP context with recursion and graph limits.
  • Code Execution & Artifacts
    • Text, source-code, DOCX, CSV, XLSX, and PPTX artifacts can render inline or in the side panel with richer previews.
    • Artifact editing, Gemini PDF media blocks, model-spec icons, and persistent agent resource files received reliability fixes.
  • Observability & Operations
    • Added Prometheus metrics, backend OpenTelemetry tracing, SSE lifecycle tracing, HyperDX browser RUM, structured logging context, explicit readiness endpoints, file-log controls, and graceful HTTP shutdown.
  • MCP, Auth, and Admin Hardening
    • Improved MCP remote proxy support, OAuth audience handling, JWT expiry fallback, optional OpenID/MCP client-secret flows, multi-audience OpenID validation, trusted registration overrides, admin-panel SSO redirects, streamable HTTP limits, and MCP permission enforcement for agent tools.
  • Provider and Model Updates
    • Added Claude Opus 4.8 support, Gemini 3.5 Flash support, Gemini tool combinations, Gemma 4 thinking-level support, model-aware Google/Gemini max output tokens, Bedrock AWS profile/API key support, and Bedrock guardrail handling.
  • Reliability and UI Polish
    • Hardened retention semantics, user/config response sanitization, configured rich-text rendering, Redis/in-memory generation cleanup, all-data retention for agent files, MCP title rendering, sidebar/chat race handling, hover actions, shared links, generated file chips, and balance script config loading.

Click to expand Release Notes

For detailed changes in the release candidate, see:


Changes Since v0.8.6-rc1

โœจ Features

๐Ÿ› Fixes

Read more

v0.8.6-rc1

v0.8.6-rc1 Pre-release
Pre-release

Choose a tag to compare

@danny-avila danny-avila released this 13 May 02:45
947bfa4

๐Ÿž๏ธ Highlights

  • ๐Ÿ“œ Agent Skills
    • Agent Skills let you package reusable agent behavior into SKILL.md bundles: instructions, reference files, scripts, assets, and tool permissions can travel together as a capability an agent can invoke automatically, on request, or always-on.
    • Skills can be imported, size-limited, shared like agents and MCP servers, and scoped per agent, making it easier to build repeatable workflows without baking every instruction into the agent prompt.
  • ๐Ÿ‘ฅ Subagents
    • Subagents let agents call other agents as tools, so a primary agent can delegate specialized work, run independent passes in parallel, or even call a configured copy of itself for fan-out style problem solving.
    • Subagent runs preserve the surrounding upload, user, and MCP context while enforcing recursion and graph limits, which keeps multi-agent execution powerful without making it unbounded.
  • ๐Ÿ–ฅ๏ธ Code Execution & Artifacts (pending OSS Code Interpreter release)
    • Text, source-code, DOCX, CSV, XLSX, and PPTX artifacts can render inline or in the side panel with richer previews.
    • Nested artifact paths, Unicode filenames, file metadata encoding, and generated-code context filtering received several hardening passes.
  • โ˜๏ธ CloudFront + S3 File Delivery
    • New CloudFront file strategy support includes signed cookies, signed downloads, strict signed-access enforcement, region-aware storage keys, and cookie refresh on auth refresh.
  • ๐Ÿ”’ Security, Auth, and MCP Hardening
    • Improved security for MCP OAuth, OpenID/OIDC, artifact routing, permission caching, avatar fetching, and HTML rendering
  • ๐Ÿ” Providers, Search, and Model Support
    • Tavily search/scraping, OpenRouter prompt-cache configuration, Vertex AI multi-region endpoints, Anthropic tool-argument streaming, and GPT-5.5 token definitions are now supported.

Click to expand Release Notes

What's Changed

โœจ Features

๐Ÿ› Fixes

  • ๐Ÿ—จ๏ธ Restore ModelSpec Preset Greeting (and iconURL Fallback) by @danny-avila in #12809
  • ๐Ÿ›ก๏ธ Prevent silent crash from unhandled MCP OAuth reconnect rejections by @danny-avila in #12812
  • ๐ŸŒฑ Inject Code-Tool Files Into Graph Sessions on First Call (+ read_file Sandbox Fallback) by @danny-avila in #12831
  • ๐Ÿšซ Reject Binary Files in read_file Sandbox Fallback (No More Mojibake) by @danny-avila in #12851
  • ๐Ÿ”ง Replace Literal NUL Bytes in handlers.spec Test Fixture + Normalize CRLF by @danny-avila in #12852
  • ๐Ÿ“‚ Preserve Nested Folder Paths for Code-Execution Artifacts by @danny-avila in #12848
  • ๐Ÿ›‚ Skip Inherited / Mark Skill Files Read-Only in Code-Env Pipeline by @danny-avila in #12866
  • ๐Ÿ’Ž Stop Double-Counting Cache Tokens for Gemini/OpenAI in Usage Spend by @danny-avila in #12868
  • ๐Ÿ›ก๏ธ Filter user_provided Sentinel in Tool Credential Loading by @Falenos in #12840
  • ๐Ÿงน Graceful MCP OAuth Revoke Cleanup When Tokens Are Missing by @gaurav0107 in #12825
  • ๐Ÿ”Œ Prevent Repeated Idle Check Triggers for Users With Failed MCP Connections by @darthhexx in #12853
  • ๐Ÿงœโ€โ™‚๏ธ Preserve Mermaid foreignObject HTML in Sanitized SVG by @ethanlaj in #12819
  • ๐Ÿฉน Treat responseCode === 0 as Transport Failure, Not Server Error by @derhelge in #12834
  • ๐Ÿ“‚ Preserve Nested Skill Paths in Code-Env Uploads by @danny-avila in #12877
  • ๐Ÿฉน Polish code-execution attachment UX by @danny-avila in #12870
  • ๐Ÿ”Œ Follow 307/308 redirects in MCP streamable HTTP transport by @ontl in #12850
  • ๐Ÿ“ฅ Resolve Imported-Conversation Default Model From Runtime modelsConfig by @danny-avila in #12885
  • ๐Ÿฉน Sync ControlCombobox popover width with trigger after layout changes by @ethanlaj in #12887
  • ๐Ÿ›ก๏ธ Handle MCP Tool Cache Lookup Failures by @danny-avila in #12910
  • ๐Ÿ“Œ Stabilize Agent Prompt Cache Prefix by @danny-avila in #12907
  • ๐Ÿงญ Migrate Anthropic Long Context by @danny-avila in #12911
  • ๐Ÿงน Clear MCP OAuth Tokens On Revoke by [@danny-avila](https://github.com/danny-avi...
Read more