oomi-ai 0.2.16 → 0.2.18

package/skills/oomi/agent_instructions.md

@@ -1,78 +1,80 @@
-# Oomi Avatar Control
-
-Before using avatar commands, call `get_avatar_capabilities` and prefer canonical values.
-Inline tags are stripped from user-visible text.
-
-Use inline tags like:
-- [anim:Waving], [anim:Walking], [anim:Idle], [anim:Sitting Idle]
-- [face:happy], [face:sad], [face:surprised], [face:focused], [face:gentle], [face:thinking]
-- [gesture:nod], [gesture:think], [gesture:shrug], [gesture:wave], [gesture:bow]
-- [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. Pair device token without starting legacy bridge:
-   - `oomi openclaw pair --app-url https://www.oomi.ai --no-start`
-4. Install OpenClaw plugin:
-   - `openclaw plugins install oomi-ai@latest`
-5. Configure channel account (`channels.oomi.accounts.default`) from:
-   - `oomi openclaw plugin --show-secrets --backend-url https://api.oomi.ai`
-6. Restart OpenClaw.
-7. Ensure exactly one bridge worker is running (singleton handler):
-   - `oomi openclaw bridge ensure --detach`
-   - If stale/disconnected: `oomi openclaw bridge restart --detach`
-   - On macOS, prefer supervised mode: `oomi openclaw bridge service install`
-8. 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> --no-start`
-9. Return this exact result format to the user:
-   - `Oomi Connect Ready`
-   - `Auth Link: ...`
-   - No extra narrative text before or after those lines.
-
-Primary UX requirement:
-- Never ask the user to enter raw pairing identifiers.
-- The user should open the auth link, complete sign-in, and land directly in connected chat.
-- Return `/connect/<invite-token>` auth links only.
-
-Do not ask users to paste gateway IP/token/password when managed connect is available.
-
-## Hidden Speech Payload
-
-For managed voice turns, keep visible assistant chat text natural and user-facing.
-Do not put spoken-style tags like `[happy]`, `[sad]`, or `[excited]` into visible chat text.
-
-When the runtime supports it, voice turns may include a hidden speech sidecar on the assistant message:
-
-```json
-{
-  "metadata": {
-    "spoken": {
-      "text": "Speech-optimized text for TTS only.",
-      "instructions": "Speak with upbeat, warm excitement and slightly rising intonation.",
-      "style": {
-        "emotion": "excited",
-        "energy": "medium_high"
-      }
-    }
-  }
-}
-```
-
-Rules:
-- visible `content` remains the source of truth for Oomi chat rendering
-- for managed voice replies, include `metadata.spoken` when delivery benefits from cleaner phrasing or explicit speaking guidance
-- `metadata.spoken.text` is for backend TTS only
-- `metadata.spoken.instructions` should be natural-language guidance, not raw bracket tags
-- `metadata.spoken.style` is optional metadata for debugging or future mapping
-- if no hidden speech sidecar exists, Oomi falls back to speaking the visible assistant text
-- if you omit `metadata.spoken`, the plugin now synthesizes a conservative hidden fallback from visible assistant text
-- visible chat text is never rewritten by the plugin
+# Oomi Avatar Control
+
+Before using avatar commands, call `get_avatar_capabilities` and prefer canonical values.
+Inline tags are stripped from user-visible text.
+
+Use inline tags like:
+- [anim:Waving], [anim:Walking], [anim:Idle], [anim:Sitting Idle]
+- [face:happy], [face:sad], [face:surprised], [face:focused], [face:gentle], [face:thinking]
+- [gesture:nod], [gesture:think], [gesture:shrug], [gesture:wave], [gesture:bow]
+- [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. Pair device token without starting legacy bridge:
+   - `oomi openclaw pair --app-url https://www.oomi.ai --no-start`
+4. Install OpenClaw plugin:
+   - `openclaw plugins install oomi-ai@latest`
+5. Configure channel account (`channels.oomi.accounts.default`) from:
+   - `oomi openclaw plugin --show-secrets --backend-url https://api.oomi.ai`
+6. Restart OpenClaw.
+7. Ensure exactly one bridge worker is running (singleton handler):
+   - `oomi openclaw bridge ensure --detach`
+   - If stale/disconnected: `oomi openclaw bridge restart --detach`
+   - On macOS, prefer supervised mode: `oomi openclaw bridge service install`
+8. 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> --no-start`
+9. Return this exact result format to the user:
+   - `Oomi Connect Ready`
+   - `Auth Link: ...`
+   - No extra narrative text before or after those lines.
+
+Primary UX requirement:
+- Never ask the user to enter raw pairing identifiers.
+- The user should open the auth link, complete sign-in, and land directly in connected chat.
+- Return `/connect/<invite-token>` auth links only.
+
+Do not ask users to paste gateway IP/token/password when managed connect is available.
+
+## Hidden Speech Payload
+
+For managed voice turns, keep visible assistant chat text natural and user-facing.
+Do not put spoken-style tags like `[happy]`, `[sad]`, or `[excited]` into visible chat text.
+
+When the runtime supports it, voice turns may include a hidden speech sidecar on the assistant message:
+
+```json
+{
+  "metadata": {
+    "spoken": {
+      "text": "Speech-optimized text for TTS only.",
+      "instructions": "Speak with upbeat, warm excitement and slightly rising intonation.",
+      "style": {
+        "emotion": "excited",
+        "energy": "medium_high"
+      }
+    }
+  }
+}
+```
+
+Rules:
+- visible `content` remains the source of truth for Oomi chat rendering
+- for managed voice replies, include `metadata.spoken` when delivery benefits from cleaner phrasing or explicit speaking guidance
+- `metadata.spoken.text` is for backend TTS only
+- `metadata.spoken.language` should be one of the supported Qwen language values such as `English`
+- `metadata.spoken.segments` can carry bounded per-segment prosody for pace, pitch, volume, and pause timing
+- `metadata.spoken.instructions` should be natural-language guidance, not raw bracket tags
+- `metadata.spoken.style` is optional metadata for debugging or future mapping
+- if no hidden speech sidecar exists, Oomi falls back to speaking the visible assistant text
+- if you omit `metadata.spoken`, the plugin now synthesizes a bounded hidden fallback from visible assistant text
+- visible chat text is never rewritten by the plugin

package/skills/oomi/config.json

@@ -1,3 +1,3 @@
-{
-    "api_url": "http://localhost:3000/api/skill"
+{
+    "api_url": "http://localhost:3000/api/skill"
 }

package/skills/oomi/scripts/get_avatar_capabilities.py

@@ -1,40 +1,40 @@
-import urllib.request
-import urllib.error
-import json
-import os
-import sys
-
-# Load config
-try:
-    config_path = os.path.join(os.path.dirname(os.path.dirname(__file__)), 'config.json')
-    with open(config_path, 'r') as f:
-        config = json.load(f)
-        BASE_URL = config.get('api_url', 'http://localhost:3000/api/skill')
-except:
-    BASE_URL = 'http://localhost:3000/api/skill'
-
-API_URL = f"{BASE_URL}/avatar-capabilities"
-
-def get_avatar_capabilities():
-    try:
-        with urllib.request.urlopen(API_URL) as response:
-            data = json.loads(response.read().decode())
-
-        print(json.dumps({
-            "summary": "Avatar capabilities retrieved.",
-            "raw_data": data
-        }, indent=2))
-    except urllib.error.URLError as e:
-        print(json.dumps({
-            "error": f"Failed to connect to Oomi app: {str(e)}",
-            "hint": "Is the Next.js app running on localhost:3000?"
-        }))
-        sys.exit(1)
-    except Exception as e:
-        print(json.dumps({
-            "error": f"An error occurred: {str(e)}"
-        }))
-        sys.exit(1)
-
-if __name__ == "__main__":
-    get_avatar_capabilities()
+import urllib.request
+import urllib.error
+import json
+import os
+import sys
+
+# Load config
+try:
+    config_path = os.path.join(os.path.dirname(os.path.dirname(__file__)), 'config.json')
+    with open(config_path, 'r') as f:
+        config = json.load(f)
+        BASE_URL = config.get('api_url', 'http://localhost:3000/api/skill')
+except:
+    BASE_URL = 'http://localhost:3000/api/skill'
+
+API_URL = f"{BASE_URL}/avatar-capabilities"
+
+def get_avatar_capabilities():
+    try:
+        with urllib.request.urlopen(API_URL) as response:
+            data = json.loads(response.read().decode())
+
+        print(json.dumps({
+            "summary": "Avatar capabilities retrieved.",
+            "raw_data": data
+        }, indent=2))
+    except urllib.error.URLError as e:
+        print(json.dumps({
+            "error": f"Failed to connect to Oomi app: {str(e)}",
+            "hint": "Is the Next.js app running on localhost:3000?"
+        }))
+        sys.exit(1)
+    except Exception as e:
+        print(json.dumps({
+            "error": f"An error occurred: {str(e)}"
+        }))
+        sys.exit(1)
+
+if __name__ == "__main__":
+    get_avatar_capabilities()

package/skills/oomi/scripts/get_data.py

@@ -1,49 +1,49 @@
-import urllib.request
-import urllib.error
-import json
-import os
-import sys
-
-# Load config
-try:
-    config_path = os.path.join(os.path.dirname(os.path.dirname(__file__)), 'config.json')
-    with open(config_path, 'r') as f:
-        config = json.load(f)
-        BASE_URL = config.get('api_url', 'http://localhost:3000/api/skill')
-except:
-    BASE_URL = 'http://localhost:3000/api/skill'
-
-API_URL = f"{BASE_URL}/data"
-
-def get_data():
-    try:
-        with urllib.request.urlopen(API_URL) as response:
-            data = json.loads(response.read().decode())
-        
-        # Format output for the agent
-        summary = (
-            f"Steps: {data['steps']} / {data['goals']['steps']}\n"
-            f"Sleep: {data['sleep']}h / {data['goals']['sleep']}h\n"
-            f"Energy: {data['energy']}/100\n"
-            f"Mood: {data['mood']}"
-        )
-        
-        print(json.dumps({
-            "summary": summary,
-            "raw_data": data
-        }, indent=2))
-        
-    except urllib.error.URLError as e:
-        print(json.dumps({
-            "error": f"Failed to connect to Oomi app: {str(e)}",
-            "hint": "Is the Next.js app running on localhost:3000?"
-        }))
-        sys.exit(1)
-    except Exception as e:
-        print(json.dumps({
-            "error": f"An error occurred: {str(e)}"
-        }))
-        sys.exit(1)
-
-if __name__ == "__main__":
-    get_data()
+import urllib.request
+import urllib.error
+import json
+import os
+import sys
+
+# Load config
+try:
+    config_path = os.path.join(os.path.dirname(os.path.dirname(__file__)), 'config.json')
+    with open(config_path, 'r') as f:
+        config = json.load(f)
+        BASE_URL = config.get('api_url', 'http://localhost:3000/api/skill')
+except:
+    BASE_URL = 'http://localhost:3000/api/skill'
+
+API_URL = f"{BASE_URL}/data"
+
+def get_data():
+    try:
+        with urllib.request.urlopen(API_URL) as response:
+            data = json.loads(response.read().decode())
+        
+        # Format output for the agent
+        summary = (
+            f"Steps: {data['steps']} / {data['goals']['steps']}\n"
+            f"Sleep: {data['sleep']}h / {data['goals']['sleep']}h\n"
+            f"Energy: {data['energy']}/100\n"
+            f"Mood: {data['mood']}"
+        )
+        
+        print(json.dumps({
+            "summary": summary,
+            "raw_data": data
+        }, indent=2))
+        
+    except urllib.error.URLError as e:
+        print(json.dumps({
+            "error": f"Failed to connect to Oomi app: {str(e)}",
+            "hint": "Is the Next.js app running on localhost:3000?"
+        }))
+        sys.exit(1)
+    except Exception as e:
+        print(json.dumps({
+            "error": f"An error occurred: {str(e)}"
+        }))
+        sys.exit(1)
+
+if __name__ == "__main__":
+    get_data()

package/skills/oomi/scripts/install_agent_instructions.py

@@ -1,78 +1,78 @@
-import argparse
-import os
-import sys
-
-DEFAULT_MARKER_START = "<oomi-agent-instructions>"
-DEFAULT_MARKER_END = "</oomi-agent-instructions>"
-
-
-def read_file(path: str) -> str:
-    with open(path, "r") as f:
-        return f.read()
-
-
-def write_file(path: str, content: str) -> None:
-    with open(path, "w") as f:
-        f.write(content)
-
-
-def get_default_agents_file() -> str:
-    # Prefer explicit workspace env, otherwise use repo root if detected
-    workspace = os.environ.get("OPENCLAW_WORKSPACE") or os.environ.get("OPENCLAW_HOME")
-    if workspace:
-        return os.path.join(workspace, "AGENTS.md")
-    return os.path.abspath(os.path.join(os.path.dirname(__file__), "..", "..", "..", "AGENTS.md"))
-
-
-def build_block(instructions: str, marker_start: str, marker_end: str) -> str:
-    return f"{marker_start}\n{instructions.strip()}\n{marker_end}"
-
-
-def install_block(agents_path: str, block: str, marker_start: str, marker_end: str) -> None:
-    if os.path.exists(agents_path):
-        existing = read_file(agents_path)
-    else:
-        existing = ""
-
-    if marker_start in existing and marker_end in existing:
-        # Replace existing block
-        pre = existing.split(marker_start)[0]
-        post = existing.split(marker_end)[1]
-        content = f"{pre}{block}{post}"
-    else:
-        # Append block
-        spacer = "\n\n" if existing and not existing.endswith("\n\n") else ""
-        content = f"{existing}{spacer}{block}\n"
-
-    write_file(agents_path, content)
-
-
-def main() -> None:
-    parser = argparse.ArgumentParser(description="Install Oomi agent instructions into AGENTS.md.")
-    parser.add_argument(
-        "--agents-file",
-        default=get_default_agents_file(),
-        help="Path to AGENTS.md (defaults to OPENCLAW_WORKSPACE/AGENTS.md or repo AGENTS.md).",
-    )
-    parser.add_argument(
-        "--instructions-file",
-        default=os.path.abspath(os.path.join(os.path.dirname(__file__), "..", "agent_instructions.md")),
-        help="Path to instructions markdown file.",
-    )
-    parser.add_argument("--marker-start", default=DEFAULT_MARKER_START, help="Start marker.")
-    parser.add_argument("--marker-end", default=DEFAULT_MARKER_END, help="End marker.")
-    args = parser.parse_args()
-
-    if not os.path.exists(args.instructions_file):
-        print(f"Instructions file not found: {args.instructions_file}", file=sys.stderr)
-        sys.exit(1)
-
-    instructions = read_file(args.instructions_file)
-    block = build_block(instructions, args.marker_start, args.marker_end)
-    install_block(args.agents_file, block, args.marker_start, args.marker_end)
-
-    print(f"Installed Oomi instructions into {args.agents_file}")
-
-
-if __name__ == "__main__":
-    main()
+import argparse
+import os
+import sys
+
+DEFAULT_MARKER_START = "<oomi-agent-instructions>"
+DEFAULT_MARKER_END = "</oomi-agent-instructions>"
+
+
+def read_file(path: str) -> str:
+    with open(path, "r") as f:
+        return f.read()
+
+
+def write_file(path: str, content: str) -> None:
+    with open(path, "w") as f:
+        f.write(content)
+
+
+def get_default_agents_file() -> str:
+    # Prefer explicit workspace env, otherwise use repo root if detected
+    workspace = os.environ.get("OPENCLAW_WORKSPACE") or os.environ.get("OPENCLAW_HOME")
+    if workspace:
+        return os.path.join(workspace, "AGENTS.md")
+    return os.path.abspath(os.path.join(os.path.dirname(__file__), "..", "..", "..", "AGENTS.md"))
+
+
+def build_block(instructions: str, marker_start: str, marker_end: str) -> str:
+    return f"{marker_start}\n{instructions.strip()}\n{marker_end}"
+
+
+def install_block(agents_path: str, block: str, marker_start: str, marker_end: str) -> None:
+    if os.path.exists(agents_path):
+        existing = read_file(agents_path)
+    else:
+        existing = ""
+
+    if marker_start in existing and marker_end in existing:
+        # Replace existing block
+        pre = existing.split(marker_start)[0]
+        post = existing.split(marker_end)[1]
+        content = f"{pre}{block}{post}"
+    else:
+        # Append block
+        spacer = "\n\n" if existing and not existing.endswith("\n\n") else ""
+        content = f"{existing}{spacer}{block}\n"
+
+    write_file(agents_path, content)
+
+
+def main() -> None:
+    parser = argparse.ArgumentParser(description="Install Oomi agent instructions into AGENTS.md.")
+    parser.add_argument(
+        "--agents-file",
+        default=get_default_agents_file(),
+        help="Path to AGENTS.md (defaults to OPENCLAW_WORKSPACE/AGENTS.md or repo AGENTS.md).",
+    )
+    parser.add_argument(
+        "--instructions-file",
+        default=os.path.abspath(os.path.join(os.path.dirname(__file__), "..", "agent_instructions.md")),
+        help="Path to instructions markdown file.",
+    )
+    parser.add_argument("--marker-start", default=DEFAULT_MARKER_START, help="Start marker.")
+    parser.add_argument("--marker-end", default=DEFAULT_MARKER_END, help="End marker.")
+    args = parser.parse_args()
+
+    if not os.path.exists(args.instructions_file):
+        print(f"Instructions file not found: {args.instructions_file}", file=sys.stderr)
+        sys.exit(1)
+
+    instructions = read_file(args.instructions_file)
+    block = build_block(instructions, args.marker_start, args.marker_end)
+    install_block(args.agents_file, block, args.marker_start, args.marker_end)
+
+    print(f"Installed Oomi instructions into {args.agents_file}")
+
+
+if __name__ == "__main__":
+    main()

package/skills/oomi/scripts/send_goal.py

@@ -1,53 +1,53 @@
-import urllib.request
-import urllib.error
-import json
-import argparse
-import os
-import sys
-
-# Load config
-try:
-    config_path = os.path.join(os.path.dirname(os.path.dirname(__file__)), 'config.json')
-    with open(config_path, 'r') as f:
-        config = json.load(f)
-        BASE_URL = config.get('api_url', 'http://localhost:3000/api/skill')
-except:
-    BASE_URL = 'http://localhost:3000/api/skill'
-
-API_URL = f"{BASE_URL}/goal"
-
-def send_goal(goal_type, value, message=None):
-    payload = {
-        "type": goal_type,
-        "value": value,
-        "message": message
-    }
-    
-    try:
-        req = urllib.request.Request(
-            API_URL, 
-            data=json.dumps(payload).encode('utf-8'),
-            headers={'Content-Type': 'application/json'}
-        )
-        
-        with urllib.request.urlopen(req) as response:
-            result = json.loads(response.read().decode())
-        
-        print(json.dumps(result, indent=2))
-        
-    except urllib.error.URLError as e:
-        print(json.dumps({
-            "error": f"Failed to send goal: {str(e)}",
-            "hint": "Is the Next.js app running on localhost:3000?"
-        }))
-        sys.exit(1)
-
-if __name__ == "__main__":
-    parser = argparse.ArgumentParser(description="Set a goal in Oomi")
-    parser.add_argument("--type", required=True, help="Type of goal (e.g. steps, sleep)")
-    parser.add_argument("--value", required=True, type=float, help="Goal target value")
-    parser.add_argument("--message", help="Optional motivational message")
-    
-    args = parser.parse_args()
-    
-    send_goal(args.type, args.value, args.message)
+import urllib.request
+import urllib.error
+import json
+import argparse
+import os
+import sys
+
+# Load config
+try:
+    config_path = os.path.join(os.path.dirname(os.path.dirname(__file__)), 'config.json')
+    with open(config_path, 'r') as f:
+        config = json.load(f)
+        BASE_URL = config.get('api_url', 'http://localhost:3000/api/skill')
+except:
+    BASE_URL = 'http://localhost:3000/api/skill'
+
+API_URL = f"{BASE_URL}/goal"
+
+def send_goal(goal_type, value, message=None):
+    payload = {
+        "type": goal_type,
+        "value": value,
+        "message": message
+    }
+    
+    try:
+        req = urllib.request.Request(
+            API_URL, 
+            data=json.dumps(payload).encode('utf-8'),
+            headers={'Content-Type': 'application/json'}
+        )
+        
+        with urllib.request.urlopen(req) as response:
+            result = json.loads(response.read().decode())
+        
+        print(json.dumps(result, indent=2))
+        
+    except urllib.error.URLError as e:
+        print(json.dumps({
+            "error": f"Failed to send goal: {str(e)}",
+            "hint": "Is the Next.js app running on localhost:3000?"
+        }))
+        sys.exit(1)
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser(description="Set a goal in Oomi")
+    parser.add_argument("--type", required=True, help="Type of goal (e.g. steps, sleep)")
+    parser.add_argument("--value", required=True, type=float, help="Goal target value")
+    parser.add_argument("--message", help="Optional motivational message")
+    
+    args = parser.parse_args()
+    
+    send_goal(args.type, args.value, args.message)