Related: #136257 ## What Problem This Solves Fixes an issue where activating a verified replacement sign-in left existing and fresh chats using the old credential, even after a restart. An operator report on September 11 also found misleading model-access feedback, a “Replace key” action that could add an account, and missing command-line activation after unattended setup. ## Why This Change Was Made The shared credential selector now resolves the activated account for normal replies, `/btw` side questions, and worker inference, preserving explicit account choices and different-model behavior. Duplicate caller logic is removed. Activation also compares normalized runtime settings consistently, so omitted optional model fields do not cause a false connection-change error after saving. The existing setup owner also serves the new `openclaw models auth activate` command; both activation prompts default to Yes after verification. Saved model access is reported separately from application by the running Gateway, and the provider-wide key action is labeled accurately. ## User Impact - Automatic chats and `/btw` side questions use the activated account; explicit account pins retain precedence. - Unattended replacement setup prints a command that tests and activates the saved sign-in. - Enter accepts a successfully verified connection. - Saved-but-unapplied settings include recovery guidance instead of a failed-save message. ## Evidence - Real Gateway and recording-provider requests: old credential before; replacement afterward in existing and fresh chats. Explicit pins and a different model retain their expected account selection. - Real Telegram `/btw`: the activated replacement handles an existing automatic chat, while an explicit old-account pin still uses the old account. The same flow first exposed a false activation error for sparse saved model settings; the corrected flow succeeds. - Independent public CLI/browser validation confirms the printed activation command, Enter-to-activate, and the key editor. - Real Telegram Test Server: “Show all” saves the choice in both cases; disabled reload reports saved/unconfirmed, while enabled reload reports visible models. - The initial fixes passed 377 focused tests across nine files. The caller correction passed 309 tests across five files, including `/btw`, normal replies, worker inference, and person-linked account pins. The configured-account regression fails on the pinned base. A further 17 activation/acknowledgement tests pass, including sparse saved settings and rejection of real concurrent changes. - All 17 sanitized operator-config shapes reach Gateway readiness. The Tailscale-dependent fixture uses the supported per-run exposure override on the Linux test host; Tailscale Serve itself is not claimed. - Synthetic provider credentials only. No database, migration, configuration-key, or protocol changes in this PR. | Before | After | | --- | --- | |  |  | Captures are cropped to the changed control and exclude account identifiers. Additional catalog check: sign-in completes through the real xAI plugin against a simulated provider, but its existing endpoint metadata blocks live OAuth catalog discovery. That plugin is unchanged here. New-model discovery, first-account onboarding, and real vendor entitlement are not claimed by this PR. Co-authored-by: Ayaan Zaidi <hi@obviy.us> |
||
|---|---|---|
| .agents | ||
| .claude | ||
| .github | ||
| .vscode | ||
| apps | ||
| config | ||
| custodian-skills | ||
| deploy | ||
| docs | ||
| examples/ai-chat | ||
| extensions | ||
| git-hooks | ||
| packages | ||
| patches | ||
| qa | ||
| scripts | ||
| security | ||
| skills | ||
| src | ||
| test | ||
| ui | ||
| .crabbox.yaml | ||
| .dockerignore | ||
| .env.example | ||
| .gitattributes | ||
| .gitignore | ||
| .npmrc | ||
| .oxfmtrc.jsonc | ||
| .oxlintrc.json | ||
| .pre-commit-config.yaml | ||
| .semgrepignore | ||
| AGENTS.md | ||
| appcast.xml | ||
| CHANGELOG.md | ||
| CLAUDE.md | ||
| CONTRIBUTING.md | ||
| docker-compose.yml | ||
| Dockerfile | ||
| fly.toml | ||
| LICENSE | ||
| node-runtime-recovery.d.mts | ||
| node-runtime-recovery.mjs | ||
| node-runtime-update.d.mts | ||
| node-runtime-update.mjs | ||
| node-sqlite.d.mts | ||
| node-sqlite.mjs | ||
| node-version.d.mts | ||
| node-version.mjs | ||
| openclaw.mjs | ||
| package.json | ||
| pnpm-lock.yaml | ||
| pnpm-workspace.yaml | ||
| README.md | ||
| render.yaml | ||
| SECURITY.md | ||
| taxonomy.yaml | ||
| THIRD_PARTY_NOTICES.md | ||
| tsconfig.core.json | ||
| tsconfig.extensions.json | ||
| tsconfig.extensions.projects.json | ||
| tsconfig.json | ||
| tsconfig.scripts.json | ||
| tsconfig.ui.json | ||
| tsdown.ai.config.ts | ||
| tsdown.config.ts | ||
| VISION.md | ||
| vitest.config.ts | ||
OpenClaw 🦞 — Your assistant, on your devices, in your chats
OpenClaw is an open-source AI assistant that runs on your own computer and meets you in the channels you already use: Discord, iMessage, Slack, Teams, Telegram, WhatsApp, and 20+ more, plus native apps for macOS, iOS, Android, Windows, and Linux. One Gateway runs it as a personal assistant on a laptop or as a shared team deployment; configuration is the only difference.
Yours, with no catch. State, memory, and credentials live on your hardware. Models and agent harnesses (Claude, Codex, local models) are plugins you can swap without changing anything else. Your prompts go to the model provider and chat platforms you configure, plus any diagnostics export you enable yourself; by default OpenClaw itself phones home for nothing but a daily version check, anonymous feature statistics are opt-in, and update.checkOnStart: false disables both (what OpenClaw sends). OpenClaw is stewarded by the OpenClaw Foundation, an independent 501(c)(3), and has no paid tier, hosted service, or token. The architecture case — trusted gateway, untrusted execution, deterministic policy — is in Why OpenClaw.
Website · Docs · Getting started · Why OpenClaw · Showcase · FAQ · Vision · DeepWiki
Install
The installer supports macOS, Linux, and Windows. It provisions a supported Node.js runtime when needed.
# macOS / Linux / WSL2
curl -fsSL https://openclaw.ai/install.sh | bash
# Windows PowerShell
iwr -useb https://openclaw.ai/install.ps1 | iex
Already manage Node.js? Install the published package instead (Node 24.16+ or 26.1+; Node 26 recommended):
npm install -g openclaw@latest --allow-scripts=openclaw
That command is for npm 12 or npm 11.16+. On npm 11.15 and earlier, omit
--allow-scripts=openclaw. See the
installation guide for the lifecycle script
contract, Docker, Nix, and other deployment paths.
Quick start
On a fresh install, the installer scripts start onboarding automatically. Complete the wizard they open. If you installed the package directly with npm, pnpm, or Bun, run:
openclaw onboard --install-daemon
After onboarding:
openclaw gateway status
openclaw dashboard
Onboarding verifies model access, creates the workspace, and configures the Gateway. The last command opens the Control UI; send a message there to confirm the assistant is working. See the getting started guide for channel setup and troubleshooting.
How it fits together
- The Gateway is the local control plane for sessions, tools, events, and channel connections.
- The Control UI, CLI, and TUI connect to the Gateway.
- Channels bring the assistant to WhatsApp, Telegram, Slack, Discord, Google Chat, Signal, iMessage, and other messaging services.
- Companion apps and nodes add voice, Canvas, camera, screen, and device-local actions on supported platforms.
OpenClaw works with hosted and local model providers. Its tools, skills, and plugins extend what an assistant can do.
Security
Treat inbound messages as untrusted input. DM-capable channels pair unknown senders by default; approve a pairing request with openclaw pairing approve <channel> <code>.
Tools run on the host for the main session unless you configure sandboxing. Read the security guide, exposure runbook, and sandboxing guide before connecting other users or exposing the Gateway remotely.
Documentation
| Goal | Start here |
|---|---|
| Configure models and auth | Models · Model providers |
| Connect a messaging service | Channels |
| Add tools, skills, and plugins | Tools · Skills · Plugins · ClawHub |
| Run apps and device nodes | Platforms · Nodes |
| Use the CLI and chat commands | CLI reference · Slash commands |
| Configure or operate the Gateway | Configuration · Architecture · Updating · Release channels |
Development
The repository is a pnpm workspace. Plain npm install at the repository root is not supported.
git clone https://github.com/openclaw/openclaw.git
cd openclaw
pnpm install
pnpm build
pnpm ui:build
See CONTRIBUTING.md for the contribution workflow and the source setup guide for the development loop.
Governance
OpenClaw is developed in the open by the OpenClaw Foundation, an independent 501(c)(3). The Foundation employs the core team and signs releases. Donors and infrastructure sponsors support the Foundation; none of them own or direct the project. OpenAI is a donor, not an owner.
Community
See CONTRIBUTING.md for maintainers and contribution guidelines; AI-assisted PRs are welcome.
Use the issue chooser for bugs and feature requests, ask setup questions in Discord, and report vulnerabilities through SECURITY.md. New capabilities usually belong in plugins built on the plugin SDK and shared through ClawHub.
OpenClaw was built for Molty, a space lobster AI assistant, by Peter Steinberger and the community. Explore the project lore, soul.md, Peter's site, Star History, and @openclaw.
Special thanks to Mario Zechner for his support and for pi, and to Adam Doppelt for the lobster.bot domain.
Donors and sponsors
The Foundation is funded by donors including the University of Michigan, OpenAI, Amazon, Red Hat, Offline Holdings, and Lobster Computer Company, with infrastructure support from GitHub, NVIDIA, Vercel, Blacksmith, and Convex.
Contributors
Thanks to all clawtributors:
License
MIT © OpenClaw Foundation. See THIRD_PARTY_NOTICES.md for incorporated or adapted code.