oomi-ai 0.1.0 → 0.2.1

package/README.md

@@ -1,25 +1,112 @@
 # oomi-ai
 
-CLI to install Oomi agent instructions into an OpenClaw workspace.
+CLI to install Oomi agent instructions and skills into OpenClaw, plus sync personas to the Oomi backend registry.
 
 ## Install
 ```
+pnpm add -g oomi-ai
+```
+
+Fallback:
+```
 npm install -g oomi-ai
 ```
 
 ## Usage
+
+Install agent instructions only:
 ```
 oomi init
 ```
 
+Install agent instructions + Oomi skill:
+```
+oomi openclaw install
+```
+
+Start managed gateway bridge (OpenClaw host -> Oomi broker):
+```
+oomi openclaw bridge \
+  --broker-http https://your-signaling-service.example.com \
+  --broker-ws wss://your-signaling-service.example.com/cable \
+  --pair-code ABCD2345
+```
+
+Bridge env config:
+- `OOMI_CHAT_BROKER_HTTP_URL`
+- `OOMI_CHAT_BROKER_DEVICE_WS_URL`
+
+Pair + bootstrap bridge automatically from Oomi web backend:
+```
+oomi openclaw pair --app-url https://your-oomi-app.vercel.app --device-id my-openclaw-mac --detach
+```
+
+`--app-url` must be reachable from the OpenClaw host. If OpenClaw runs on a different machine/network, do not use `localhost` unless tunneled.
+
+This prints:
+- `Connect code: <device-id>`
+- `Connect URL: https://.../?connect=managed://<device-id>&sessionKey=...`
+- A copy-ready block for the user:
+  - `Oomi Connect Ready`
+  - `Code: ...`
+  - `Link: ...`
+
+Agent-intent mapping (recommended):
+- If user says `Connect yourself to Oomi. Use app URL https://www.oomi.ai.`
+- Run:
+  - `curl -fsSL https://www.oomi.ai/install.sh | bash`
+  - or `pnpm add -g oomi-ai@latest` (`npm install -g oomi-ai@latest` fallback)
+  - `oomi openclaw pair --app-url https://www.oomi.ai --detach`
+- If already paired and reconnecting:
+  - `oomi openclaw bridge --detach`
+
+Important distinction:
+- `pairCode` is one-time and used internally by the pair/bootstrap flow.
+- `connect code` is the stable device id used by browser connect (`managed://<device-id>`).
+
+Sync personas from the repo into the backend registry:
+```
+oomi personas sync --backend-url http://localhost:3001
+```
+
+Create a new persona (and sync it):
+```
+oomi personas create chef --name "Oomi Chef" --summary "Cooking ideas and nutrition guidance"
+```
+
 Optional flags:
 ```
 oomi init --workspace /path/to/openclaw/workspace
 oomi init --agents-file /path/to/AGENTS.md
+oomi openclaw install --skills-dir /path/to/openclaw/skills
+oomi openclaw bridge --broker-ws wss://.../cable --device-token <token>
+oomi openclaw pair --app-url https://your-oomi-app.vercel.app --no-start
+oomi openclaw pair --app-url https://your-oomi-app.vercel.app --detach
+oomi openclaw pair --app-url https://your-oomi-app.vercel.app --json
+oomi personas sync --root /path/to/oomi
+oomi personas create creator --status active --chat-session agent:main:webchat:channel:oomi-creator
 ```
 
-By default, the CLI writes to:
-- `$OPENCLAW_WORKSPACE/AGENTS.md` (if set), otherwise
-- `~/.openclaw/workspace/AGENTS.md`
+Defaults:
+- Agent instructions are written to `$OPENCLAW_WORKSPACE/AGENTS.md` (if set), otherwise `~/.openclaw/workspace/AGENTS.md`.
+- Skills are installed to `~/.openclaw/skills` and `~/clawd/skills` if present.
+
+Restart OpenClaw after running `oomi init` or `oomi openclaw install`.
 
-Restart OpenClaw after running this command.
+## Update Notifications
+- `oomi` checks npm for a newer `oomi-ai` version on normal commands (cached, best-effort).
+- When an update is available it prints:
+  - `pnpm add -g oomi-ai@latest`
+  - fallback: `npm install -g oomi-ai@latest`
+- Optional env controls:
+  - `OOMI_SKIP_UPDATE_CHECK=1` disables checks
+  - `OOMI_UPDATE_CHECK_INTERVAL_MS=<ms>` changes check interval
+  - `OOMI_UPDATE_CHECK_TIMEOUT_MS=<ms>` changes network timeout
+
+## Package Audit + Publish (pnpm)
+```
+cd <repo-root>/packages/oomi-ai
+pnpm check
+pnpm publish --dry-run --no-git-checks --access public
+pnpm publish --access public
+```

package/agent_instructions.md

@@ -10,3 +10,25 @@ Use inline tags like:
 - [look:camera], [look:left], [look:right], [look:up], [look:down]
 
 Aliases allowed (if needed): wave -> Waving, walk -> Walking, idle -> Idle, sit/sitting -> Sitting Idle
+
+## Oomi Connect Flow
+
+If the user asks to connect OpenClaw to Oomi voice/web:
+
+1. Refresh bootstrap/update first:
+   - `curl -fsSL https://www.oomi.ai/install.sh | bash`
+2. Ensure `oomi-ai` is installed (`pnpm add -g oomi-ai@latest`).
+   - Fallback: `npm install -g oomi-ai@latest`
+3. Run:
+   - `oomi openclaw pair --app-url https://www.oomi.ai --detach`
+4. If already paired and reconnecting:
+   - `oomi openclaw bridge --detach`
+5. If user provides an app URL (for example "Connect yourself to Oomi. Use app URL <URL>."):
+   - Use that URL directly in the pair command.
+   - Example: `oomi openclaw pair --app-url <URL> --detach`
+6. Return this exact result format to the user:
+   - `Oomi Connect Ready`
+   - `Code: ...`
+   - `Link: ...`
+
+Do not ask users to paste gateway IP/token/password when managed connect is available.