CERBERUS/LibreChat
1
0
Fork 0
mirror of https://github.com/danny-avila/LibreChat.git synced 2026-10-21 17:44:11 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 6
Enhanced ChatGPT Clone: Features Agents, MCP, DeepSeek, Anthropic, AWS, OpenAI, Responses API, Azure, Groq, o1, GPT-5, Mistral, OpenRouter, Vertex AI, Gemini, Artifacts, AI model switching, message search, Code Interpreter, langchain, DALL-E-3, OpenAPI Actions, Functions, Secure Multi-User Auth, Presets, open-source for self-hosting. Active. https://librechat.ai/
5353 commits 356 branches 113 tags 1 GiB
Find a file
Danny Avila 0219513115
🛑 fix: Forward Run Abort Signal to Foreground Tool Calls (#15517) 
* 🛑 fix: Forward Run Abort Signal to Foreground Tool Calls

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

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

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

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

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

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

Addresses both findings from the Codex review of 48fded564a.

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

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

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

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

Addresses both findings from the Codex review of b3c67082cd.

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

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

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

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

Addresses the Codex review of d53ff170ab.

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

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

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

* 🪪 fix: Keep an Action OAuth Abort an Abort

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

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

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

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

Addresses the Codex review of 9bcf1aa57e.

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

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

* 🧹 chore: Restore Import Order in the Agents Tool Handler
2026-09-02 13:32:33 -04:00
.claude/skills 🪝 feat: Execute Agent Plugin Command Hooks (#14755) 2026-08-12 13:21:15 -04:00
.devcontainer 🐳 chore: Upgrade Docker Builds To Node 24 (#13448) 2026-06-01 10:03:18 -04:00
.github 🫂 ci: Unify Docker Image Publishing Workflows (#15447) 2026-08-31 23:29:57 -04:00
.husky 🪥 chore: Run CI's Static Checks on Each Commit's Diff (#15303) 2026-08-28 10:08:37 -04:00
.vscode
api 🛑 fix: Forward Run Abort Signal to Foreground Tool Calls (#15517) 2026-09-02 13:32:33 -04:00
client 🕹️ feat: Configure BYOM Tool Permissions (#15504) 2026-09-02 10:38:00 -04:00
config 🛞 feat: Manage Personal Code Environment Lifecycles (#15369) 2026-09-01 21:10:05 -04:00
e2e 🕹️ feat: Configure BYOM Tool Permissions (#15504) 2026-09-02 10:38:00 -04:00
helm 🛫 refactor: Promote Generation Protocol V2 Automatically (#15324) 2026-08-28 17:17:09 -04:00
otel/langfuse-fanout 🗿 chore: Upgrade gRPC to Prevent Receive Buffer Exhaustion (#15493) 2026-09-01 21:32:20 -04:00
packages 🛑 fix: Forward Run Abort Signal to Foreground Tool Calls (#15517) 2026-09-02 13:32:33 -04:00
redis-config
scripts 🪥 chore: Run CI's Static Checks on Each Commit's Diff (#15303) 2026-08-28 10:08:37 -04:00
search 🐋 chore: add opt-in alternative local stack experiments (#14678) 2026-08-07 10:40:58 -04:00
skill 🗂️ feat: Add Deployment Skill Directory (#13523) 2026-06-05 10:24:28 -04:00
src/tests
utils
.codex 🧴 fix: Strip LangChain URLs From Provider Errors (#15421) 2026-08-31 12:51:34 -04:00
.dockerignore
.env.example 📖 feat: Add Claude Fable 5.1 Support (#15512) 2026-09-02 10:45:54 -04:00
.gitattributes
.gitignore 🧪 test(e2e): add Bombadil property exploration (#14462) 2026-08-10 02:11:06 +02:00
.nvmrc 🐳 chore: Upgrade Docker Builds To Node 24 (#13448) 2026-06-01 10:03:18 -04:00
.prettierrc
AGENTS.md 🔌 refactor: Give the Subagent Surface a Host Seam and Its Own Jotai State (#15455) 2026-09-01 11:15:42 -04:00
bun.lock ⬆️ chore: Bump @librechat/agents to v3.6.0 (#14890) 2026-08-16 09:15:35 -04:00
CLAUDE.md 🔌 refactor: Give the Subagent Surface a Host Seam and Its Own Jotai State (#15455) 2026-09-01 11:15:42 -04:00
CONTEXT.md 🛄 fix: Reclaim Pending MCP OAuth Prompts on Resume (#15471) 2026-09-01 16:52:18 -04:00
deploy-compose.langfuse-fanout.yml 🪭 feat: support per-run central langfuse export suppression (#14207) 2026-07-12 08:03:27 -04:00
deploy-compose.yml 🫆 chore: Remove Published Credential Defaults (#14680) 2026-08-07 07:25:05 -04:00
docker-compose.langfuse-fanout.yml 🪭 feat: support per-run central langfuse export suppression (#14207) 2026-07-12 08:03:27 -04:00
docker-compose.override.yml.example
docker-compose.yml 🫆 chore: Remove Published Credential Defaults (#14680) 2026-08-07 07:25:05 -04:00
Dockerfile 🚀 chore: Prepare v0.8.8-rc1 (#14394) 2026-08-14 03:24:59 -04:00
Dockerfile.multi 🚀 chore: Prepare v0.8.8-rc1 (#14394) 2026-08-14 03:24:59 -04:00
eslint.config.mjs 🎨 feat: Refine Client Colors and Sharing Dialogs (#14734) 2026-08-10 22:43:57 -04:00
librechat.example.yaml 📖 feat: Add Claude Fable 5.1 Support (#15512) 2026-09-02 10:45:54 -04:00
LICENSE 🗒️ docs: Update LICENSE.md Year: 2025 -> 2026 (#12554) 2026-04-08 09:12:44 -04:00
package-lock.json 🧴 chore: Refresh Sanitizer and Selector Parser Dependencies (#15494) 2026-09-01 21:38:08 -04:00
package.json 📱 test: Add Mobile Chat Performance Benchmark (#15510) 2026-09-02 10:36:33 -04:00
rag.yml
README.md 🚀 chore: Prepare v0.8.8-rc1 (#14394) 2026-08-14 03:24:59 -04:00
README.zh.md ✨ v0.8.7-rc1 (#13592) 2026-06-15 13:10:30 -04:00
tool-intent-spec.md 🎯 feat: Tool Intent Label Capability (tool_intents) (#14499) 2026-07-29 15:40:52 -04:00
turbo.json 🌯 chore: Retire Rollup-Era devDependencies After tsdown Migration (#14496) 2026-07-28 22:08:52 -04:00

README.md

LibreChat

English · 中文

Deploy on Railway Deploy on Zeabur Deploy on Sealos

Translation Progress

🚀 What's New in v0.8.8-rc1

  • Agent run control: Interrupt or steer an Agent mid-run, queue follow-up messages, and reclaim, edit, or escalate pending steers.
  • Human-in-the-loop Agents: Agents stream question progress, ask up to four related questions in one form, pause for input or tool approval, and resume.
  • Unified Agent Builder: A redesigned Tools marketplace brings together Skills, MCP, Code Interpreter, orchestration, Programmatic Tool Calling, model-spec controls, and per-tool background and intent settings.
  • Readable Agent activity: Generated activity-group headers, parent phase summaries, and live tool intent labels make long reasoning and tool runs easier to scan.
  • Code Interpreter workflows: Code and shell tools can run in the background, sandbox images return as viewable artifacts, and highly experimental stateful sessions can reuse prewarmed conversation workspaces.
  • Agent extensibility: Experimental Agent Plugins can bundle deployment Skills, MCP servers, and opt-in command hooks, while explicit subagents initialize only when selected.
  • Memory, context, and identity: Agents can manage memory with optional per-agent isolation, expose support contacts safely, and show a more faithful Context Usage gauge.
  • Sharing and files: Shared conversations show a badge and update at a stable URL, while signed-in viewers can continue them as personal copies.
  • Artifact workflows: Open previews fullscreen, work with PowerPoint .potx templates across upload, search, and code execution, upload shell scripts across common MIME variants, export Mermaid diagrams as SVG or PNG, and download original Office files from the artifact panel.
  • Models and reasoning: Added GPT-5.6 with Responses API reasoning controls, Claude Opus 5 and Sonnet 5, Gemini 3.7 and 3.6 Flash, and Gemini 3.5 Flash-Lite.
  • Langfuse observability: Configure encrypted Langfuse connections in-app, let authorized admins open sampled sessions directly, optionally fan out traces by tenant, and suppress central export per run.
  • Administration and security: Delegate config sections, encrypt registered secrets, enforce SSRF checks for speech, OCR, and web tools, and generate unique temporary credentials when secrets are blank.
  • Messages and navigation: Right-aligned user turns, unified multi-part editing, full-message copy, a dock-style message rail, virtualized search, smooth streaming, and faster Agent startup.
  • Streaming and tool reliability: Adaptive provider smoothing, Redis delta batching, dynamic MCP tool refresh, parsed MCP response media types, runtime OAuth recovery, and Agent stream circuit breakers improve long-running workflows.
  • Deployment and reliability: Added configurable HTTP timeouts, Amazon DocumentDB 5.0+ support, low-noise Redis and browser observability, and a rolling-upgrade-safe generation protocol.

Read the full v0.8.8-rc1 changelog.

✨ Features

  • 🖥️ UI & Experience inspired by ChatGPT with enhanced design and features

  • 🤖 AI Model Selection:

    • Anthropic (Claude), AWS Bedrock, OpenAI, Azure OpenAI, Google, Vertex AI, OpenAI Responses API (incl. Azure)
    • Custom Endpoints: Use any OpenAI-compatible API with LibreChat, no proxy required
    • Compatible with Local & Remote AI Providers:
      • Ollama, groq, Cohere, Mistral AI, Apple MLX, koboldcpp, together.ai,
      • OpenRouter, Helicone, Perplexity, ShuttleAI, Deepseek, Qwen, and more

  • 🔧 Code Interpreter API:

    • Secure, Sandboxed Execution in Python, Node.js (JS/TS), Go, C/C++, Java, PHP, Rust, and Fortran
    • Seamless File Handling: Upload, process, and download files directly
    • No Privacy Concerns: Fully isolated and secure execution
    • Open-Source & Self-Hostable: powered by ClickHouse/code-interpreter

  • 🔦 Agents & Tools Integration:

    • LibreChat Agents:
      • No-Code Custom Assistants: Build specialized, AI-driven helpers
      • Agent Marketplace: Discover and deploy community-built agents
      • Collaborative Sharing: Share agents with specific users and groups
      • Flexible & Extensible: Use MCP Servers, tools, file search, code execution, and more
      • Skills: Create reusable SKILL.md instruction bundles for manual, automatic, or always-on agent workflows
      • Agent Plugins: Experimentally bundle deployment Skills and MCP servers into startup-loaded packages
      • Subagents: Delegate focused work to isolated child agent runs with their own context windows
      • Compatible with Custom Endpoints, OpenAI, Azure, Anthropic, AWS Bedrock, Google, Vertex AI, Responses API, and more
      • Model Context Protocol (MCP) Support for Tools

  • 🔍 Web Search:

    • Search the internet and retrieve relevant information to enhance your AI context
    • Combines search providers, content scrapers, and result rerankers for optimal results
    • Customizable Jina Reranking: Configure custom Jina API URLs for reranking services
    • Learn More →

  • 🪄 Generative UI with Code Artifacts:

    • Code Artifacts create React, HTML, and Mermaid content directly in chat
    • Open previews fullscreen and export Mermaid diagrams as SVG or PNG

  • 🎨 Image Generation & Editing

  • 💾 Presets & Context Management:

    • Create, Save, & Share Custom Presets
    • Switch between AI Endpoints and Presets mid-chat
    • Edit, Resubmit, and Continue Messages with Conversation branching
    • Create and share prompts with specific users and groups
    • Fork Messages & Conversations for Advanced Context control

  • 💬 Multimodal & File Interactions:

    • Upload and analyze images with Claude 3, GPT-4.5, GPT-4o, o1, Llama-Vision, and Gemini 📸
    • Chat with Files using Custom Endpoints, OpenAI, Azure, Anthropic, AWS Bedrock, & Google 🗃️

  • 🌎 Multilingual UI:

    • English, 中文 (简体), 中文 (繁體), العربية, Deutsch, Español, Français, Italiano
    • Polski, Português (PT), Português (BR), Русский, 日本語, Svenska, 한국어, Tiếng Việt
    • Türkçe, Nederlands, עברית, Català, Čeština, Dansk, Eesti, فارسی
    • Suomi, Magyar, Հայերեն, Bahasa Indonesia, ქართული, Latviešu, ไทย, ئۇيغۇرچە

  • 🧠 Reasoning UI:

    • Dynamic Reasoning UI for Chain-of-Thought/Reasoning AI models like DeepSeek-R1

  • 🎨 Customizable Interface:

    • Customizable Dropdown & Interface that adapts to both power users and newcomers

  • 🌊 Resumable Streams:

    • Never lose a response: AI responses automatically reconnect and resume if your connection drops
    • Multi-Tab & Multi-Device Sync: Open the same chat in multiple tabs or pick up on another device
    • Production-Ready: Works from single-server setups to horizontally scaled deployments with Redis

  • 🗣️ Speech & Audio:

    • Chat hands-free with Speech-to-Text and Text-to-Speech
    • Automatically send and play Audio
    • Supports OpenAI, Azure OpenAI, and Elevenlabs

  • 📥 Import & Export Conversations:

    • Import Conversations from LibreChat, ChatGPT, Chatbot UI
    • Export conversations as screenshots, markdown, text, json

  • 🔍 Search & Discovery:

    • Search all messages/conversations

  • 👥 Multi-User & Secure Access:

    • Multi-User, Secure Authentication with OAuth2, LDAP, & Email Login Support
    • Built-in Moderation, and Token spend tools

  • 🎛️ Admin Panel:

    • Browser-based UI to manage users, groups, roles, and configuration overrides
    • Edit settings and per-role/group permissions live, without redeploying
    • Bundled with the Docker Compose stacks for one-command setup

  • ⚙️ Configuration & Deployment:

    • Configure Proxy, Reverse Proxy, Docker, & many Deployment options
    • Use S3 with CloudFront for stable media links, edge delivery, signed cookies, and secured downloads
    • Use completely local or deploy on the cloud

  • 📖 Open-Source & Community:

    • Completely Open-Source & Built in Public
    • Community-driven development, support, and feedback

For a thorough review of our features, see our docs here 📚

🪶 All-In-One AI Conversations with LibreChat

LibreChat is a self-hosted AI chat platform that unifies all major AI providers in a single, privacy-focused interface.

Beyond chat, LibreChat provides AI Agents, Model Context Protocol (MCP) support, Artifacts, Code Interpreter, custom actions, conversation search, and enterprise-ready multi-user authentication.

Open source, actively developed, and built for anyone who values control over their AI infrastructure.

🌐 Resources

GitHub Repo:

Other:

📝 Changelog

Keep up with the latest updates by visiting the releases page and notes:

⚠️ Please consult the changelog for breaking changes before updating.

⭐ Star History

Star History Chart

danny-avila%2FLibreChat | Trendshift ROSS Index - Fastest Growing Open-Source Startups in Q1 2024 | Runa Capital

✨ Contributions

Contributions, suggestions, bug reports and fixes are welcome!

For new features, components, or extensions, please open an issue and discuss before sending a PR.

If you'd like to help translate LibreChat into your language, we'd love your contribution! Improving our translations not only makes LibreChat more accessible to users around the world but also enhances the overall user experience. Please check out our Translation Guide.

💖 This project exists in its current state thanks to all the people who contribute

🎉 Special Thanks

We thank Locize for their translation management tools that support multiple languages in LibreChat.

Locize Logo