homeai/homeai-agent/openclaw-http-bridge.py

#!/usr/bin/env python3
"""
OpenClaw HTTP Bridge

A simple HTTP server that translates HTTP POST requests to OpenClaw CLI calls.
This allows Home Assistant (running in Docker on a different machine) to
communicate with OpenClaw via HTTP.

Usage:
    python3 openclaw-http-bridge.py [--port 8081]

Endpoints:
    POST /api/agent/message
    {
        "message": "Your message here",
        "agent": "main"
    }

    Returns:
    {
        "response": "OpenClaw response text"
    }
"""

import argparse
import json
import os
import subprocess
import sys
import asyncio
import urllib.request
import threading
from http.server import HTTPServer, BaseHTTPRequestHandler
from socketserver import ThreadingMixIn
from urllib.parse import urlparse
from pathlib import Path
import wave
import io
import re
from wyoming.client import AsyncTcpClient
from wyoming.tts import Synthesize, SynthesizeVoice
from wyoming.asr import Transcribe, Transcript
from wyoming.audio import AudioStart, AudioChunk, AudioStop
from wyoming.info import Info

# Timeout settings (seconds)
TIMEOUT_WARM = 120   # Model already loaded in VRAM
TIMEOUT_COLD = 180   # Model needs loading first (~10-20s load + inference)
OLLAMA_PS_URL = "http://localhost:11434/api/ps"
VTUBE_BRIDGE_URL = "http://localhost:8002"


def _vtube_fire_and_forget(path: str, data: dict):
    """Send a non-blocking POST to the VTube Studio bridge. Failures are silent."""
    def _post():
        try:
            body = json.dumps(data).encode()
            req = urllib.request.Request(
                f"{VTUBE_BRIDGE_URL}{path}",
                data=body,
                headers={"Content-Type": "application/json"},
                method="POST",
            )
            urllib.request.urlopen(req, timeout=2)
        except Exception:
            pass  # bridge may not be running — that's fine
    threading.Thread(target=_post, daemon=True).start()


def is_model_warm() -> bool:
    """Check if the default Ollama model is already loaded in VRAM."""
    try:
        req = urllib.request.Request(OLLAMA_PS_URL)
        with urllib.request.urlopen(req, timeout=2) as resp:
            data = json.loads(resp.read())
            return len(data.get("models", [])) > 0
    except Exception:
        # If we can't reach Ollama, assume cold (safer longer timeout)
        return False


CHARACTERS_DIR = Path("/Users/aodhan/homeai-data/characters")
SATELLITE_MAP_PATH = Path("/Users/aodhan/homeai-data/satellite-map.json")
MEMORIES_DIR = Path("/Users/aodhan/homeai-data/memories")
ACTIVE_TTS_VOICE_PATH = Path("/Users/aodhan/homeai-data/active-tts-voice.json")


def clean_text_for_tts(text: str) -> str:
    """Strip content that shouldn't be spoken: tags, asterisks, emojis, markdown."""
    # Remove HTML/XML tags and their content for common non-spoken tags
    text = re.sub(r'<[^>]+>', '', text)
    # Remove content between asterisks (actions/emphasis markup like *sighs*)
    text = re.sub(r'\*[^*]+\*', '', text)
    # Remove markdown bold/italic markers that might remain
    text = re.sub(r'[*_]{1,3}', '', text)
    # Remove markdown headers
    text = re.sub(r'^#{1,6}\s+', '', text, flags=re.MULTILINE)
    # Remove markdown links [text](url) → keep text
    text = re.sub(r'\[([^\]]+)\]\([^)]+\)', r'\1', text)
    # Remove bare URLs
    text = re.sub(r'https?://\S+', '', text)
    # Remove code blocks and inline code
    text = re.sub(r'```[\s\S]*?```', '', text)
    text = re.sub(r'`[^`]+`', '', text)
    # Remove emojis
    text = re.sub(
        r'[\U0001F600-\U0001F64F\U0001F300-\U0001F5FF\U0001F680-\U0001F6FF'
        r'\U0001F1E0-\U0001F1FF\U0001F900-\U0001F9FF\U0001FA00-\U0001FAFF'
        r'\U00002702-\U000027B0\U0000FE00-\U0000FE0F\U0000200D'
        r'\U00002600-\U000026FF\U00002300-\U000023FF]+', '', text
    )
    # Collapse multiple spaces/newlines
    text = re.sub(r'\n{2,}', '\n', text)
    text = re.sub(r'[ \t]{2,}', ' ', text)
    return text.strip()


def load_satellite_map() -> dict:
    """Load the satellite-to-character mapping."""
    try:
        with open(SATELLITE_MAP_PATH) as f:
            return json.load(f)
    except Exception:
        return {"default": "aria_default", "satellites": {}}


def set_active_tts_voice(character_id: str, tts_config: dict):
    """Write the active TTS config to a state file for the Wyoming TTS server to read."""
    try:
        ACTIVE_TTS_VOICE_PATH.parent.mkdir(parents=True, exist_ok=True)
        state = {
            "character_id": character_id,
            "engine": tts_config.get("engine", "kokoro"),
            "kokoro_voice": tts_config.get("kokoro_voice", ""),
            "elevenlabs_voice_id": tts_config.get("elevenlabs_voice_id", ""),
            "elevenlabs_model": tts_config.get("elevenlabs_model", "eleven_multilingual_v2"),
            "speed": tts_config.get("speed", 1),
        }
        with open(ACTIVE_TTS_VOICE_PATH, "w") as f:
            json.dump(state, f)
    except Exception as e:
        print(f"[OpenClaw Bridge] Warning: could not write active TTS config: {e}")


def resolve_character_id(satellite_id: str = None) -> str:
    """Resolve a satellite ID to a character profile ID."""
    sat_map = load_satellite_map()
    if satellite_id and satellite_id in sat_map.get("satellites", {}):
        return sat_map["satellites"][satellite_id]
    return sat_map.get("default", "aria_default")


def load_character(character_id: str = None) -> dict:
    """Load a character profile by ID. Returns the full character data dict."""
    if not character_id:
        character_id = resolve_character_id()
    safe_id = character_id.replace("/", "_")
    character_path = CHARACTERS_DIR / f"{safe_id}.json"
    if not character_path.exists():
        return {}
    try:
        with open(character_path) as f:
            profile = json.load(f)
            return profile.get("data", {})
    except Exception:
        return {}


def load_character_prompt(satellite_id: str = None, character_id: str = None) -> str:
    """Load the full system prompt for a character, resolved by satellite or explicit ID.
    Builds a rich prompt from system_prompt + profile fields (background, dialogue_style, etc.)."""
    if not character_id:
        character_id = resolve_character_id(satellite_id)
    char = load_character(character_id)
    if not char:
        return ""

    sections = []

    # Core system prompt
    prompt = char.get("system_prompt", "")
    if prompt:
        sections.append(prompt)

    # Character profile fields
    profile_parts = []
    if char.get("background"):
        profile_parts.append(f"## Background\n{char['background']}")
    if char.get("appearance"):
        profile_parts.append(f"## Appearance\n{char['appearance']}")
    if char.get("dialogue_style"):
        profile_parts.append(f"## Dialogue Style\n{char['dialogue_style']}")
    if char.get("skills"):
        skills = char["skills"]
        if isinstance(skills, list):
            skills_text = ", ".join(skills[:15])
        else:
            skills_text = str(skills)
        profile_parts.append(f"## Skills & Interests\n{skills_text}")
    if profile_parts:
        sections.append("[Character Profile]\n" + "\n\n".join(profile_parts))

    # Character metadata
    meta_lines = []
    if char.get("display_name"):
        meta_lines.append(f"Your name is: {char['display_name']}")
    # Support both v1 (gaze_preset string) and v2 (gaze_presets array)
    gaze_presets = char.get("gaze_presets", [])
    if gaze_presets and isinstance(gaze_presets, list):
        for gp in gaze_presets:
            preset = gp.get("preset", "")
            trigger = gp.get("trigger", "self-portrait")
            if preset:
                meta_lines.append(f"GAZE preset '{preset}' — use for: {trigger}")
    elif char.get("gaze_preset"):
        meta_lines.append(f"Your gaze_preset for self-portraits is: {char['gaze_preset']}")
    if meta_lines:
        sections.append("[Character Metadata]\n" + "\n".join(meta_lines))

    # Memories (personal + general)
    personal, general = load_memories(character_id)
    if personal:
        sections.append("[Personal Memories]\n" + "\n".join(f"- {m}" for m in personal))
    if general:
        sections.append("[General Knowledge]\n" + "\n".join(f"- {m}" for m in general))

    return "\n\n".join(sections)


def load_memories(character_id: str) -> tuple[list[str], list[str]]:
    """Load personal (per-character) and general memories.
    Returns (personal_contents, general_contents) truncated to fit context budget."""
    PERSONAL_BUDGET = 4000  # max chars for personal memories in prompt
    GENERAL_BUDGET = 3000   # max chars for general memories in prompt

    def _read_memories(path: Path, budget: int) -> list[str]:
        try:
            with open(path) as f:
                data = json.load(f)
        except Exception:
            return []
        memories = data.get("memories", [])
        # Sort newest first
        memories.sort(key=lambda m: m.get("createdAt", ""), reverse=True)
        result = []
        used = 0
        for m in memories:
            content = m.get("content", "").strip()
            if not content:
                continue
            if used + len(content) > budget:
                break
            result.append(content)
            used += len(content)
        return result

    safe_id = character_id.replace("/", "_")
    personal = _read_memories(MEMORIES_DIR / "personal" / f"{safe_id}.json", PERSONAL_BUDGET)
    general = _read_memories(MEMORIES_DIR / "general.json", GENERAL_BUDGET)
    return personal, general


class OpenClawBridgeHandler(BaseHTTPRequestHandler):
    """HTTP request handler for OpenClaw bridge."""

    def log_message(self, format, *args):
        """Log requests to stderr."""
        print(f"[OpenClaw Bridge] {self.address_string()} - {format % args}")

    def _send_json_response(self, status_code: int, data: dict):
        """Send a JSON response."""
        self.send_response(status_code)
        self.send_header("Content-Type", "application/json")
        self.end_headers()
        self.wfile.write(json.dumps(data).encode())

    def do_POST(self):
        """Handle POST requests."""
        parsed_path = urlparse(self.path)

        # Handle wake word notification
        if parsed_path.path == "/wake":
            self._handle_wake_word()
            return

        # Handle TTS preview requests
        if parsed_path.path == "/api/tts":
            self._handle_tts_request()
            return

        # Handle STT requests
        if parsed_path.path == "/api/stt":
            self._handle_stt_request()
            return

        # Only handle the agent message endpoint
        if parsed_path.path == "/api/agent/message":
            self._handle_agent_request()
            return
            
        self._send_json_response(404, {"error": "Not found"})

    def _handle_tts_request(self):
        """Handle TTS request and return audio. Routes to Kokoro or ElevenLabs based on engine."""
        content_length = int(self.headers.get("Content-Length", 0))
        if content_length == 0:
            self._send_json_response(400, {"error": "Empty body"})
            return

        try:
            body = self.rfile.read(content_length).decode()
            data = json.loads(body)
        except json.JSONDecodeError:
            self._send_json_response(400, {"error": "Invalid JSON"})
            return

        text = data.get("text", "Hello, this is a test.")
        text = clean_text_for_tts(text)
        voice = data.get("voice", "af_heart")
        engine = data.get("engine", "kokoro")

        try:
            # Signal avatar: speaking
            _vtube_fire_and_forget("/expression", {"event": "speaking"})

            if engine == "elevenlabs":
                audio_bytes, content_type = self._synthesize_elevenlabs(text, voice, data.get("model"))
            else:
                # Default: local Kokoro via Wyoming
                audio_bytes = asyncio.run(self._synthesize_audio(text, voice))
                content_type = "audio/wav"

            # Signal avatar: idle
            _vtube_fire_and_forget("/expression", {"event": "idle"})

            self.send_response(200)
            self.send_header("Content-Type", content_type)
            self.send_header("Access-Control-Allow-Origin", "*")
            self.end_headers()
            self.wfile.write(audio_bytes)

        except Exception as e:
            _vtube_fire_and_forget("/expression", {"event": "error"})
            self._send_json_response(500, {"error": str(e)})

    def _synthesize_elevenlabs(self, text: str, voice_id: str, model: str = None) -> tuple[bytes, str]:
        """Call ElevenLabs TTS API and return (audio_bytes, content_type)."""
        api_key = os.environ.get("ELEVENLABS_API_KEY", "")
        if not api_key:
            raise RuntimeError("ELEVENLABS_API_KEY not set in environment")
        if not voice_id:
            raise RuntimeError("No ElevenLabs voice ID provided")

        model = model or "eleven_multilingual_v2"
        url = f"https://api.elevenlabs.io/v1/text-to-speech/{voice_id}"
        payload = json.dumps({
            "text": text,
            "model_id": model,
            "voice_settings": {"stability": 0.5, "similarity_boost": 0.75},
        }).encode()

        req = urllib.request.Request(
            url,
            data=payload,
            headers={
                "Content-Type": "application/json",
                "xi-api-key": api_key,
                "Accept": "audio/mpeg",
            },
            method="POST",
        )
        with urllib.request.urlopen(req, timeout=30) as resp:
            audio_bytes = resp.read()
        return audio_bytes, "audio/mpeg"

    def do_OPTIONS(self):
        """Handle CORS preflight requests."""
        self.send_response(204)
        self.send_header("Access-Control-Allow-Origin", "*")
        self.send_header("Access-Control-Allow-Methods", "POST, GET, OPTIONS")
        self.send_header("Access-Control-Allow-Headers", "Content-Type")
        self.end_headers()

    async def _synthesize_audio(self, text: str, voice: str) -> bytes:
        """Connect to Wyoming TTS server and get audio bytes."""
        client = AsyncTcpClient("127.0.0.1", 10301)
        await client.connect()
        
        # Read the initial Info event
        await client.read_event()
        
        # Send Synthesize event
        await client.write_event(Synthesize(text=text, voice=SynthesizeVoice(name=voice)).event())
        
        audio_data = bytearray()
        rate = 24000
        width = 2
        channels = 1
        
        while True:
            event = await client.read_event()
            if event is None:
                break
                
            if AudioStart.is_type(event.type):
                start = AudioStart.from_event(event)
                rate = start.rate
                width = start.width
                channels = start.channels
            elif AudioChunk.is_type(event.type):
                chunk = AudioChunk.from_event(event)
                audio_data.extend(chunk.audio)
            elif AudioStop.is_type(event.type):
                break
                
        await client.disconnect()
        
        # Package raw PCM into WAV
        wav_io = io.BytesIO()
        with wave.open(wav_io, 'wb') as wav_file:
            wav_file.setnchannels(channels)
            wav_file.setsampwidth(width)
            wav_file.setframerate(rate)
            wav_file.writeframes(audio_data)
            
        return wav_io.getvalue()

    def _handle_stt_request(self):
        """Handle STT request — accept WAV audio, return transcribed text."""
        content_length = int(self.headers.get("Content-Length", 0))
        if content_length == 0:
            self._send_json_response(400, {"error": "Empty body"})
            return

        try:
            audio_bytes = self.rfile.read(content_length)

            # Parse WAV to get PCM data and format
            wav_io = io.BytesIO(audio_bytes)
            with wave.open(wav_io, 'rb') as wav_file:
                rate = wav_file.getframerate()
                width = wav_file.getsampwidth()
                channels = wav_file.getnchannels()
                pcm_data = wav_file.readframes(wav_file.getnframes())

            # Run the async Wyoming client
            text = asyncio.run(self._transcribe_audio(pcm_data, rate, width, channels))

            self.send_response(200)
            self.send_header("Content-Type", "application/json")
            self.send_header("Access-Control-Allow-Origin", "*")
            self.end_headers()
            self.wfile.write(json.dumps({"text": text}).encode())

        except wave.Error as e:
            self._send_json_response(400, {"error": f"Invalid WAV: {e}"})
        except Exception as e:
            self._send_json_response(500, {"error": str(e)})

    async def _transcribe_audio(self, pcm_data: bytes, rate: int, width: int, channels: int) -> str:
        """Connect to Wyoming STT server and transcribe audio."""
        client = AsyncTcpClient("127.0.0.1", 10300)
        await client.connect()

        # Send Transcribe request (STT server does not send an initial Info event)
        await client.write_event(Transcribe(language="en").event())

        # Send audio
        await client.write_event(AudioStart(rate=rate, width=width, channels=channels).event())

        # Send in chunks (1 second each)
        bytes_per_second = rate * width * channels
        for offset in range(0, len(pcm_data), bytes_per_second):
            chunk = pcm_data[offset:offset + bytes_per_second]
            await client.write_event(AudioChunk(rate=rate, width=width, channels=channels, audio=chunk).event())

        await client.write_event(AudioStop().event())

        # Read transcript
        while True:
            event = await client.read_event()
            if event is None:
                break
            if Transcript.is_type(event.type):
                transcript = Transcript.from_event(event)
                await client.disconnect()
                return transcript.text

        await client.disconnect()
        return ""

    def _handle_wake_word(self):
        """Handle wake word detection notification."""
        content_length = int(self.headers.get("Content-Length", 0))
        wake_word_data = {}
        if content_length > 0:
            try:
                body = self.rfile.read(content_length).decode()
                wake_word_data = json.loads(body)
            except (json.JSONDecodeError, ConnectionResetError, OSError):
                # Client may close connection early, that's ok
                pass
        
        print(f"[OpenClaw Bridge] Wake word detected: {wake_word_data.get('wake_word', 'unknown')}")
        self._send_json_response(200, {"status": "ok", "message": "Wake word received"})

    @staticmethod
    def _call_openclaw(message: str, agent: str, timeout: int) -> str:
        """Call OpenClaw CLI and return stdout."""
        result = subprocess.run(
            ["/opt/homebrew/bin/openclaw", "agent", "--message", message, "--agent", agent],
            capture_output=True,
            text=True,
            timeout=timeout,
            check=True,
        )
        return result.stdout.strip()

    @staticmethod
    def _needs_followup(response: str) -> bool:
        """Detect if the model promised to act but didn't actually do it.
        Returns True if the response looks like a 'will do' without a result."""
        if not response:
            return False
        resp_lower = response.lower()
        # If the response contains a URL or JSON-like output, it probably completed
        if "http://" in response or "https://" in response or '"status"' in response:
            return False
        # If it contains a tool result indicator (ha-ctl output, gaze-ctl output)
        if any(kw in resp_lower for kw in ["image_url", "seed", "entity_id", "state:", "turned on", "turned off"]):
            return False
        # Detect promise-like language without substance
        promise_phrases = [
            "let me", "i'll ", "i will ", "sure thing", "sure,", "right away",
            "generating", "one moment", "working on", "hang on", "just a moment",
            "on it", "let me generate", "let me create",
        ]
        has_promise = any(phrase in resp_lower for phrase in promise_phrases)
        # Short responses with promise language are likely incomplete
        if has_promise and len(response) < 200:
            return True
        return False

    def _handle_agent_request(self):
        """Handle agent message request."""
        content_length = int(self.headers.get("Content-Length", 0))
        if content_length == 0:
            self._send_json_response(400, {"error": "Empty body"})
            return
            
        try:
            body = self.rfile.read(content_length).decode()
            data = json.loads(body)
        except json.JSONDecodeError:
            self._send_json_response(400, {"error": "Invalid JSON"})
            return

        message = data.get("message")
        agent = data.get("agent", "main")
        satellite_id = data.get("satellite_id")
        explicit_character_id = data.get("character_id")

        if not message:
            self._send_json_response(400, {"error": "Message is required"})
            return

        # Resolve character: explicit ID > satellite mapping > default
        if explicit_character_id:
            character_id = explicit_character_id
        else:
            character_id = resolve_character_id(satellite_id)
        system_prompt = load_character_prompt(character_id=character_id)

        # Set the active TTS config for the Wyoming server to pick up
        char = load_character(character_id)
        tts_config = char.get("tts", {})
        if tts_config:
            set_active_tts_voice(character_id, tts_config)
            engine = tts_config.get("engine", "kokoro")
            voice_label = tts_config.get("kokoro_voice", "") if engine == "kokoro" else tts_config.get("elevenlabs_voice_id", "")
            print(f"[OpenClaw Bridge] Active TTS: {engine} / {voice_label}")

        if satellite_id:
            print(f"[OpenClaw Bridge] Satellite: {satellite_id} → character: {character_id}")
        elif explicit_character_id:
            print(f"[OpenClaw Bridge] Character: {character_id}")
        if system_prompt:
            message = f"System Context: {system_prompt}\n\nUser Request: {message}"

        # Check if model is warm to set appropriate timeout
        warm = is_model_warm()
        timeout = TIMEOUT_WARM if warm else TIMEOUT_COLD
        print(f"[OpenClaw Bridge] Model {'warm' if warm else 'cold'}, timeout={timeout}s")

        # Signal avatar: thinking
        _vtube_fire_and_forget("/expression", {"event": "thinking"})

        # Call OpenClaw CLI (use full path for launchd compatibility)
        try:
            response_text = self._call_openclaw(message, agent, timeout)

            # Re-prompt if the model promised to act but didn't call a tool.
            # Detect "I'll do X" / "Let me X" responses that lack any result.
            if self._needs_followup(response_text):
                print(f"[OpenClaw Bridge] Response looks like a promise without action, re-prompting")
                followup = (
                    "You just said you would do something but didn't actually call the exec tool. "
                    "Do NOT explain what you will do — call the tool NOW using exec and return the result."
                )
                response_text = self._call_openclaw(followup, agent, timeout)

            # Signal avatar: idle (TTS handler will override to 'speaking' if voice is used)
            _vtube_fire_and_forget("/expression", {"event": "idle"})
            self._send_json_response(200, {"response": response_text})
        except subprocess.TimeoutExpired:
            self._send_json_response(504, {"error": f"OpenClaw command timed out after {timeout}s (model was {'warm' if warm else 'cold'})"})
        except subprocess.CalledProcessError as e:
            error_msg = e.stderr.strip() if e.stderr else "OpenClaw command failed"
            self._send_json_response(500, {"error": error_msg})
        except FileNotFoundError:
            self._send_json_response(500, {"error": "OpenClaw CLI not found"})
        except Exception as e:
            self._send_json_response(500, {"error": str(e)})

    def do_GET(self):
        """Handle GET requests (health check)."""
        parsed_path = urlparse(self.path)

        if parsed_path.path == "/status" or parsed_path.path == "/":
            self._send_json_response(200, {
                "status": "ok",
                "service": "OpenClaw HTTP Bridge",
                "version": "1.0.0"
            })
        else:
            self._send_json_response(404, {"error": "Not found"})


class ThreadingHTTPServer(ThreadingMixIn, HTTPServer):
    daemon_threads = True


def main():
    """Run the HTTP bridge server."""
    parser = argparse.ArgumentParser(description="OpenClaw HTTP Bridge")
    parser.add_argument(
        "--port",
        type=int,
        default=8081,
        help="Port to listen on (default: 8081)"
    )
    parser.add_argument(
        "--host",
        default="0.0.0.0",
        help="Host to bind to (default: 0.0.0.0)"
    )
    args = parser.parse_args()

    ThreadingHTTPServer.allow_reuse_address = True
    server = ThreadingHTTPServer((args.host, args.port), OpenClawBridgeHandler)
    print(f"OpenClaw HTTP Bridge running on http://{args.host}:{args.port}")
    print(f"Endpoint: POST http://{args.host}:{args.port}/api/agent/message")
    print("Press Ctrl+C to stop")

    try:
        server.serve_forever()
    except KeyboardInterrupt:
        print("\nShutting down...")
        server.shutdown()


if __name__ == "__main__":
    main()