first to addDB service

Reviewed-on: #3

.env.example

@@ -2,9 +2,23 @@
 LOG_LEVEL=INFO
 
 # Matrix Configuration
-HOMESERVER_URL = "https://matrix.org"
+MATRIX_HOMESERVER_URL="https://matrix.org"
-USER_ID = "@botbot_user:matrix.org"
+MATRIX_USER_ID="@botbot_user:matrix.org"
-PASSWORD = "botbot_password"
+MATRIX_PASSWORD="botbot_password"
+MATRIX_LOGIN_TRIES=5 # Number of login attempts before giving up, default is 5
+MATRIX_LOGIN_DELAY_INCREMENT=5 # Delay increment,in seconds, between login attempts, default is 5
+AI_HANDLER_URL="http://ai_service:8000"
 
 # OpenAI API Key
 OPENAI_API_KEY=your_openai_api_key_here
+AI_HANDLER_TOKEN=common_token_here
+
+# db_service
+LOG_TOKEN=your_log_token_here
+
+
+# PostgreSQL Configuration
+POSTGRES_USER=database_user
+POSTGRES_PASSWORD=database_password
+POSTGRES_DB=database_name
+POSTGRES_HOST=postgres

README.md

@@ -1,3 +1,131 @@
-# botbot
+# Botbot
 
-Botbot, your not so friendly Bot
+*Botbot, your not so friendly Bot*
+
+**Botbot** aimsto be a multi‑service chat assistant for [Matrix](https://matrix.org) that captures room conversations, stores them, and uses Large‑Language‑Models to provide concise summaries, answer follow‑up questions, and surface action points.
+
+### Roadmap / Aspirational goals
+
+* Persistent conversation store (PostgreSQL) for long‑range context.
+* Pluggable LLM back‑ends (local models, Ollama, etc.).
+* Structured meeting summaries with action‑items and deadlines.
+* Additional chat front‑ends (Telegram, WhatsApp, …).
+
+---
+
+## Architecture
+
+```mermaid
+flowchart LR
+  MS["matrix_service<br/>(Python & nio)"]
+  AI["ai_service<br/>(FastAPI)"]
+  Redis["Redis<br/>Deduplicates replies / guarantees idempotency"]
+
+  MS -- "HTTP (Bearer token)" --> AI
+  AI -- "Matrix Events" --> MS
+
+  MS -.-> Redis
+  AI -.-> Redis
+```
+
+| Component           | Image / Entry‑Point                   | Purpose                                                                               |
+| ------------------- | ------------------------------------- | ------------------------------------------------------------------------------------- |
+| **matrix\_service** | `python matrix_service/main.py`       | Listens to Matrix rooms, forwards each message to `ai_service`, posts the reply back. |
+| **ai\_service**     | `python ai_service/main.py` (FastAPI) | Builds a prompt, calls the configured LLM (OpenAI today), caches the reply in Redis.  |
+| **redis**           | `redis:7`                             | Reply cache & simple key/value store.                                                 |
+
+The services talk to each other over the internal Docker network.  Authentication between them is a static bearer token (`AI_HANDLER_TOKEN`).
+
+---
+
+## Current Features
+
+* **Auto‑Join on Invite** – secure E2EE join including device verification.
+* **Stateless AI handler** – FastAPI endpoint `/api/v1/message` receiving a JSON payload.
+* **Idempotent replies** – duplicate Matrix events reuse the cached answer.
+
+
+---
+
+## Quick Start (development)
+
+```bash
+# clone & cd
+$ git clone https://gitea.alluna.pt/jfig/botbot.git
+$ cd botbot
+
+# copy environment template
+$ cp .env.example .env
+# edit .env with your homeserver, credentials and OpenAI key
+
+# start everything (hot‑reload volumes mounted)
+$ docker compose up --build
+```
+
+The default compose file launches three containers:
+
+* `matrix_service` – watches your rooms
+* `ai_service` – handles AI prompts
+* `redis` – reply cache
+
+Stop with <kbd>Ctrl‑C</kbd> or `docker compose down`.
+
+### Production (single image per service)
+
+Build once, then deploy with your orchestrator of choice:
+
+```bash
+$ docker compose -f docker-compose.yml --profile prod build
+$ docker compose -f docker-compose.yml --profile prod up -d
+```
+
+---
+
+## Configuration
+
+All settings are environment variables.  The table below reflects the current codebase (commit `ae27a2c`).
+
+| Variable                       | Service         | Default                  | Description                              |
+| ------------------------------ | --------------- | ------------------------ | ---------------------------------------- |
+| `LOG_LEVEL`                    | both            | `INFO`                   | Python logging level.                    |
+| `MATRIX_HOMESERVER_URL`        | matrix\_service | –                        |  Matrix homeserver base URL.             |
+| `MATRIX_USER_ID`               | matrix\_service | –                        |    Full user id of the bot.              |
+| `MATRIX_PASSWORD`              | matrix\_service | –                        |    Password for the bot account.         |
+| `MATRIX_LOGIN_TRIES`           | matrix\_service |  `5`                     |    Number of login attempts before exit. |
+| `MATRIX_LOGIN_DELAY_INCREMENT` | matrix\_service |  `5`                     | Seconds added per retry.                 |
+| `AI_HANDLER_URL`               | matrix\_service | `http://ai_service:8000` | Where to POST messages.                  |
+| `AI_HANDLER_TOKEN`             | both            | –                        | Shared bearer token (keep secret).       |
+| `OPENAI_API_KEY`               | ai\_service     | –                        | Key for `openai` Python SDK.             |
+| `REDIS_URL`                    | ai\_service     | `redis://redis:6379`     | Connection string used by `redis-py`.    |
+
+---
+
+## API (ai\_service)
+
+```http
+POST /api/v1/message
+Authorization: Bearer <AI_HANDLER_TOKEN>
+Content-Type: application/json
+
+{
+  "roomId": "!foo:matrix.org",
+  "userId": "@alice:matrix.org",
+  "eventId": "$abc123",
+  "serverTimestamp": 1714821630123,
+  "content": "Hello there"
+}
+```
+
+Returns `{"reply": "Hello Alice!"}` or HTTP 401/500 on error.
+
+---
+
+## Contributing
+
+Pull requests are welcome!  Please open an issue first to discuss what you want to change.  All source code is formatted with **ruff** / **black** – run `pre-commit run --all-files` before pushing.
+
+---
+
+## License
+
+[MIT](LICENSE)

ai_service/Dockerfile

@@ -0,0 +1,12 @@
+FROM python:3.11-slim
+
+WORKDIR /app
+
+COPY requirements.txt ./
+
+RUN pip install --no-cache-dir -r requirements.txt
+
+COPY main.py ./
+
+CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "8000"]
+

ai_service/main.py

@@ -0,0 +1,66 @@
+import os
+from dotenv import load_dotenv
+from fastapi import FastAPI, Header, HTTPException
+from pydantic import BaseModel
+from openai import OpenAI
+import logging
+import redis
+
+LOG_LEVEL = os.getenv("LOG_LEVEL", "INFO").upper()
+AI_TOKEN = os.environ["AI_HANDLER_TOKEN"]
+
+AIclient = OpenAI(
+    api_key=os.environ["OPENAI_API_KEY"],
+)
+
+r = redis.Redis.from_url(os.environ.get("REDIS_URL", "redis://redis:6379"))
+
+# --- Logging Setup ---
+numeric_level = getattr(logging, LOG_LEVEL, logging.INFO)
+logging.basicConfig(
+    level=numeric_level,
+    format="%(asctime)s %(levelname)s %(name)s: %(message)s"
+)
+logger = logging.getLogger(__name__)
+
+class MessagePayload(BaseModel):
+    roomId:          str
+    userId:          str
+    eventId:         str
+    serverTimestamp: int
+    content:         str
+
+app = FastAPI()
+
+@app.post("/api/v1/message")
+async def message(
+    payload: MessagePayload,
+    authorization: str = Header(None)
+):
+    if authorization != f"Bearer {AI_TOKEN}":
+        raise HTTPException(status_code=401, detail="Unauthorized")
+
+    # Idempotency: ignore duplicates
+    if r.get(payload.eventId):
+        return {"reply": r.get(payload.eventId).decode()}
+
+    # Build prompt (very simple example)
+    prompt = f"User {payload.userId} said: {payload.content}\nBot:"
+    chat_response = AIclient.chat.completions.create(
+        model="gpt-3.5-turbo",
+        messages=[
+            {"role": "system", "content": "You are a helpful assistant."},
+            {"role": "user", "content": prompt}
+        ],
+        max_tokens=150,
+        n=1,
+        stop=None,
+        temperature=0.7,
+    )
+
+    reply = chat_response.choices[0].message.content.strip()
+
+    # Cache reply for idempotency
+    r.set(payload.eventId, reply, ex=3600)
+
+    return {"reply": reply}

ai_service/requirements.txt

@@ -0,0 +1,6 @@
+python-dotenv>=1.0.0
+openai>=1.0.0
+fastapi>=0.95
+uvicorn>=0.22
+redis>=4.5
+pydantic>=1.10

db_service/Dockerfile

@@ -0,0 +1,20 @@
+FROM python:3.11-slim
+
+# Prevent Python from buffering stdout/stderr so logs appear immediately
+ENV PYTHONUNBUFFERED=1
+
+# Install system dependencies (none needed for asyncpg on slim)
+
+WORKDIR /app
+
+# Install Python dependencies first to leverage Docker layer caching
+COPY requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Copy service source code only after dependencies
+COPY . /app
+
+EXPOSE 8000
+
+# Use Uvicorn as the ASGI server
+CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "8000"]

db_service/main.py

@@ -0,0 +1,182 @@
+from __future__ import annotations
+
+import logging
+import os
+from typing import AsyncGenerator
+
+from dotenv import load_dotenv
+from fastapi import Depends, FastAPI, Header, HTTPException, status
+from pydantic import BaseModel, Field
+from sqlalchemy import BigInteger, Column, MetaData, Table, Text, text
+from sqlalchemy.exc import OperationalError
+from sqlalchemy.ext.asyncio import (
+    AsyncEngine,
+    AsyncSession,
+    async_sessionmaker,
+    create_async_engine,
+)
+
+# ---------------------------------------------------------------------------
+# Environment & logging setup
+# ---------------------------------------------------------------------------
+
+load_dotenv()
+LOG_LEVEL = os.getenv("LOG_LEVEL", "INFO").upper()
+logging.basicConfig(level=LOG_LEVEL, format="%(levelname)s | %(name)s | %(message)s")
+log = logging.getLogger("db_service")
+
+LOG_TOKEN = os.getenv("LOG_TOKEN", "changeme")
+POSTGRES_USER = os.getenv("POSTGRES_USER", "postgres")
+POSTGRES_PASSWORD = os.getenv("POSTGRES_PASSWORD", "postgres")
+POSTGRES_DB = os.getenv("POSTGRES_DB", "botbot")
+POSTGRES_HOST = os.getenv("POSTGRES_HOST", "postgres")
+POSTGRES_PORT = os.getenv("POSTGRES_PORT", "5432")
+
+DATABASE_URL = (
+    f"postgresql+asyncpg://{POSTGRES_USER}:{POSTGRES_PASSWORD}" f"@{POSTGRES_HOST}:{POSTGRES_PORT}/{POSTGRES_DB}"
+)
+ADMIN_URL = (
+    f"postgresql+asyncpg://{POSTGRES_USER}:{POSTGRES_PASSWORD}" f"@{POSTGRES_HOST}:{POSTGRES_PORT}/postgres"
+)
+
+# ---------------------------------------------------------------------------
+# SQLAlchemy table definition (metadata)
+# ---------------------------------------------------------------------------
+
+metadata = MetaData()
+
+messages = Table(
+    "messages",
+    metadata,
+    Column("event_id", Text, primary_key=True),
+    Column("room_id", Text, nullable=False),
+    Column("user_id", Text, nullable=False),
+    Column("ts_ms", BigInteger, nullable=False),
+    Column("body", Text, nullable=False),
+)
+
+# ---------------------------------------------------------------------------
+# FastAPI app
+# ---------------------------------------------------------------------------
+
+app = FastAPI(title="Botbot Logging Service", version="1.1.0")
+
+
+class MessageIn(BaseModel):
+    """Payload received from matrix_service."""
+
+    event_id: str = Field(..., example="$14327358242610PhrSn:matrix.org")
+    room_id: str = Field(..., example="!someroomid:matrix.org")
+    user_id: str = Field(..., example="@alice:matrix.org")
+    ts_ms: int = Field(..., example=1713866689000, description="Matrix server_timestamp in ms since epoch")
+    body: str = Field(..., example="Hello, world!")
+
+
+# ---------------------------------------------------------------------------
+# Database engine/session factories (populated on startup)
+# ---------------------------------------------------------------------------
+
+engine: AsyncEngine | None = None
+SessionLocal: async_sessionmaker[AsyncSession] | None = None
+
+
+async def ensure_database_exists() -> None:
+    """Connect to the admin DB and create `POSTGRES_DB` if it is missing."""
+
+    log.info("Checking whether database %s exists", POSTGRES_DB)
+
+    admin_engine = create_async_engine(ADMIN_URL, pool_pre_ping=True)
+    try:
+        async with admin_engine.begin() as conn:
+            db_exists = await conn.scalar(
+                text("SELECT 1 FROM pg_database WHERE datname = :db"),
+                {"db": POSTGRES_DB},
+            )
+            if not db_exists:
+                log.warning("Database %s not found – creating it", POSTGRES_DB)
+                await conn.execute(text(f'CREATE DATABASE "{POSTGRES_DB}"'))
+                log.info("Database %s created", POSTGRES_DB)
+    finally:
+        await admin_engine.dispose()
+
+
+async def create_engine_and_tables() -> None:
+    """Initialise SQLAlchemy engine and create the `messages` table if needed."""
+
+    global engine, SessionLocal  # noqa: PLW0603
+
+    engine = create_async_engine(DATABASE_URL, pool_pre_ping=True)
+
+    async with engine.begin() as conn:
+        await conn.run_sync(metadata.create_all)
+
+    SessionLocal = async_sessionmaker(engine, expire_on_commit=False)
+    log.info("Database initialised and tables ensured.")
+
+
+async def get_session() -> AsyncGenerator[AsyncSession, None]:
+    async with SessionLocal() as session:  # type: ignore[arg-type]
+        yield session
+
+
+# ---------------------------------------------------------------------------
+# Lifespan events
+# ---------------------------------------------------------------------------
+
+@app.on_event("startup")
+async def on_startup() -> None:  # noqa: D401 (imperative mood)
+    """Ensure the database *and* table exist before serving traffic."""
+    log.info("Starting up")
+
+    try:
+        await create_engine_and_tables()
+    except OperationalError as err:
+        # Common case: database itself does not yet exist.
+        if "does not exist" in str(err):
+            log.warning("Primary database missing – attempting to create it")
+            await ensure_database_exists()
+            # Retry now that DB exists
+            await create_engine_and_tables()
+        else:
+            log.error("Database connection failed: %s", err)
+            raise
+
+
+@app.on_event("shutdown")
+async def on_shutdown() -> None:  # noqa: D401
+    if engine:
+        await engine.dispose()
+
+
+# ---------------------------------------------------------------------------
+# API endpoints
+# ---------------------------------------------------------------------------
+
+
+@app.get("/healthz", tags=["health"])
+async def healthz() -> dict[str, str]:
+    return {"status": "ok"}
+
+
+@app.post("/api/v1/log", status_code=status.HTTP_202_ACCEPTED, tags=["log"])
+async def log_message(
+    payload: MessageIn,
+    x_log_token: str = Header(alias="X-Log-Token"),
+    session: AsyncSession = Depends(get_session),
+) -> dict[str, str]:
+    """Persist one Matrix message to Postgres.
+
+    Requires header `X-Log-Token` matching the `LOG_TOKEN` env‑var.
+    """
+
+    if x_log_token != LOG_TOKEN:
+        raise HTTPException(status_code=status.HTTP_401_UNAUTHORIZED, detail="invalid token")
+
+    stmt = (
+        messages.insert()
+        .values(**payload.model_dump())
+        .on_conflict_do_nothing(index_elements=[messages.c.event_id])
+    )
+    await session.execute(stmt)
+    await session.commit()
+    return {"status": "accepted"}

db_service/requirements.txt

@@ -0,0 +1,10 @@
+# Web framework & ASGI server
+fastapi
+uvicorn[standard]
+
+# Database access
+sqlalchemy[asyncio]>=2.0
+asyncpg>=0.29
+
+# Environment / configuration helpers
+python-dotenv>=1.0

docker-compose.yml

@@ -1,12 +1,72 @@
 services:
-  botbot:
+  # -----------------------
-    build: .
+  # Database (PostgreSQL)
-    env_file:
+  # -----------------------
-      - .env
+  postgres:
-    volumes:
+    image: postgres:16-alpine
-      - ./:/app           # Mount source for hot-reload
-      - matrix_data:/app/data  # Persist Matrix client store and tokens
     restart: unless-stopped
+    environment:
+      - POSTGRES_USER
+      - POSTGRES_PASSWORD
+      - POSTGRES_DB
+    volumes:
+      - postgres-data:/var/lib/postgresql/data
+    healthcheck:
+      test: "pg_isready -U ${POSTGRES_USER} -d ${POSTGRES_DB}"
+      interval: 10s
+      timeout: 5s
+      retries: 5
+
+  # -----------------------
+  # Conversation‑logging microservice
+  # -----------------------
+  db_service:
+    build:
+      context: ./db_service
+    restart: unless-stopped
+    environment:
+      - POSTGRES_USER
+      - POSTGRES_PASSWORD
+      - POSTGRES_DB
+      - POSTGRES_HOST
+      - LOG_TOKEN
+    depends_on:
+      postgres:
+        condition: service_healthy
+    ports:
+      - "8000:8000"  # expose externally only if needed
+
+
+  matrix_service:
+    build: ./matrix_service
+    environment:
+      - MATRIX_HOMESERVER_URL
+      - MATRIX_USER_ID
+      - MATRIX_PASSWORD
+      - AI_HANDLER_URL
+      - AI_HANDLER_TOKEN
+    volumes:
+      - ./matrix_service:/app
+      - matrix_data:/app/data
+    depends_on:
+      - ai_service
+
+  ai_service:
+    build: ./ai_service
+    environment:
+      - OPENAI_API_KEY=${OPENAI_API_KEY}
+      - AI_HANDLER_TOKEN=${AI_HANDLER_TOKEN}
+      - REDIS_URL=redis://redis:6379
+    depends_on:
+      - redis
+
+  redis:
+    image: redis:7
+    restart: unless-stopped
+    volumes:
+      - redis-data:/data    
 
 volumes:
   matrix_data:
+  redis-data:
+  postgres-data:

main.py

@@ -1,128 +0,0 @@
-import os
-import asyncio
-import logging
-from dotenv import load_dotenv
-from nio import AsyncClient, AsyncClientConfig, MatrixRoom, RoomMessageText, InviteMemberEvent
-from nio.responses import LoginResponse
-from openai import AsyncOpenAI
-
-# --- Load environment variables ---
-load_dotenv()
-HOMESERVER_URL = os.getenv("HOMESERVER_URL")
-USER_ID = os.getenv("USER_ID")
-PASSWORD = os.getenv("PASSWORD")
-LOG_LEVEL = os.getenv("LOG_LEVEL", "INFO").upper()
-OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
-
-if not OPENAI_API_KEY:
-    raise RuntimeError("OPENAI_API_KEY is not set in environment")
-
-# --- Initialize Async OpenAI client ---
-openai_client = AsyncOpenAI(api_key=OPENAI_API_KEY)
-
-# --- Logging Setup ---
-numeric_level = getattr(logging, LOG_LEVEL, logging.INFO)
-logging.basicConfig(
-    level=numeric_level,
-    format="%(asctime)s %(levelname)s %(name)s: %(message)s"
-)
-logger = logging.getLogger(__name__)
-
-async def trust_all_devices(client) -> None:
-    """
-    Programmatically verify all devices to allow sharing encryption keys.
-    """
-    for room_id in client.rooms:
-        try:
-            devices = await client.room_devices(room_id)
-            if isinstance(devices, dict):
-                for user, dev_ids in devices.items():
-                    if user == USER_ID:
-                        continue
-                    for dev_id in dev_ids:
-                        device = client.crypto.device_store.get_device(user, dev_id)
-                        if device and not client.crypto.device_store.is_device_verified(device):
-                            logger.info(f"Trusting {dev_id} for {user}")
-                            client.verify_device(device)
-        except Exception:
-            logger.exception(f"Error trusting devices in {room_id}")
-
-async def message_callback(room: MatrixRoom, event: RoomMessageText):
-    """Handle incoming text messages."""
-    if event.sender == USER_ID:
-        return
-    body = event.body.strip()
-    lower = body.lower()
-    logger.info("Received '%s' from %s in %s", body, event.sender, room.display_name)
-
-    send_kwargs = {
-        "room_id": room.room_id,
-        "message_type": "m.room.message",
-        "ignore_unverified_devices": True
-    }
-
-    # Simple ping
-    if lower == "!ping":
-        await client.room_send(**send_kwargs, content={"msgtype": "m.text", "body": "Pong!"})
-        return
-
-    # Ask OpenAI via chat completion
-    if lower.startswith("!ask "):
-        question = body[5:].strip()
-        if not question:
-            await client.room_send(**send_kwargs, content={"msgtype": "m.text", "body": "Provide a question after !ask."})
-            return
-        logger.info("Querying OpenAI: %s", question)
-        try:
-            response = await openai_client.chat.completions.create(
-                model="gpt-3.5-turbo",
-                messages=[
-                    {"role": "system", "content": "You are a helpful assistant."},
-                    {"role": "user",   "content": question}
-                ],
-                max_tokens=150
-            )
-            answer = response.choices[0].message.content.strip()
-        except Exception:
-            logger.exception("OpenAI API error")
-            answer = "Sorry, I encountered an error contacting the AI service."
-        await client.room_send(**send_kwargs, content={"msgtype": "m.text", "body": answer})
-        return
-
-    # Greeting
-    if lower == "hello botbot":
-        await client.room_send(**send_kwargs, content={"msgtype": "m.text", "body": "Hello! How can I assist you today?"})
-
-async def main() -> None:
-    """Initialize and run the Matrix bot."""
-    global client
-    config = AsyncClientConfig(store_sync_tokens=True, encryption_enabled=True)
-    client = AsyncClient(HOMESERVER_URL, USER_ID, store_path="/app/data", config=config)
-
-    login_resp = await client.login(password=PASSWORD)
-    if isinstance(login_resp, LoginResponse):
-        logger.info("Logged in as %s", USER_ID)
-    else:
-        logger.error("Login failed: %s", login_resp)
-        return
-
-    await trust_all_devices(client)
-
-    # Auto-join and trust
-    async def on_invite(room, event):
-        if isinstance(event, InviteMemberEvent):
-            await client.join(room.room_id)
-            logger.info("Joined %s", room.room_id)
-            await trust_all_devices(client)
-    client.add_event_callback(on_invite, InviteMemberEvent)
-    client.add_event_callback(message_callback, RoomMessageText)
-
-    logger.info("Starting sync loop")
-    await client.sync_forever(timeout=30000)
-
-if __name__ == "__main__":
-    try:
-        asyncio.run(main())
-    except KeyboardInterrupt:
-        logger.info("Shutting down")
-        asyncio.run(client.close())

matrix_service/Dockerfile

@@ -4,10 +4,12 @@ FROM python:3.11-slim
 WORKDIR /app
 
 # Install system dependencies
-RUN apt-get update && \
+RUN apt-get update && apt-get install -y --no-install-recommends \
-    apt-get install -y --no-install-recommends \
+      libolm-dev \
-      libolm-dev build-essential python3-dev && \
+      build-essential \
-    rm -rf /var/lib/apt/lists/*
+      python3-dev \
+      && \
+    apt-get clean && rm -rf /var/lib/apt/lists/*
 
 # Install dependencies
 COPY requirements.txt .

matrix_service/main.py

@@ -0,0 +1,174 @@
+import os
+import logging
+from dotenv import load_dotenv
+
+import asyncio
+import httpx
+
+from nio import AsyncClient, AsyncClientConfig, MatrixRoom, RoomMessageText, InviteMemberEvent
+from nio.responses import LoginResponse
+
+
+# --- Load environment variables ---
+load_dotenv()
+MATRIX_HOMESERVER_URL        = os.getenv("MATRIX_HOMESERVER_URL")
+MATRIX_USER_ID               = os.getenv("MATRIX_USER_ID")
+MATRIX_PASSWORD              = os.getenv("MATRIX_PASSWORD")
+MATRIX_LOGIN_TRIES           = int(os.getenv("MATRIX_LOGIN_TRIES", 5))
+MATRIX_LOGIN_DELAY_INCREMENT = int(os.getenv("MATRIX_LOGIN_DELAY_INCREMENT", 5))
+
+LOG_LEVEL = os.getenv("LOG_LEVEL", "INFO").upper()
+
+AI_HANDLER_URL   = os.getenv("AI_HANDLER_URL")
+AI_HANDLER_TOKEN = os.getenv("AI_HANDLER_TOKEN")
+
+
+
+# --- Logging Setup ---
+numeric_level = getattr(logging, LOG_LEVEL, logging.INFO)
+logging.basicConfig(
+    level=numeric_level,
+    format="%(asctime)s %(levelname)s %(name)s: %(message)s"
+)
+logger = logging.getLogger(__name__)
+
+
+async def main() -> None:
+
+    async def trust_all_devices(client) -> None:
+        """
+        Mark every other user's device as verified so we can receive their
+        future Megolm keys without being blocked.
+        """
+        for room_id in client.rooms:
+            try:
+                devices_in_room = client.room_devices(room_id)
+                for user_id, user_devices in devices_in_room.items():
+                    if user_id == client.user_id:
+                        continue
+                    for dev_id, device in user_devices.items():
+                        if not client.device_store.is_device_verified(device):
+                            logger.info(f"Trusting {dev_id} for {user}")
+                            client.verify_device(device)
+            except Exception:
+                logger.exception(f"Error trusting devices in {room_id}")
+
+    async def on_invite(room, event):
+        """
+        Handle an invite event by joining the room and trusting all devices.
+        """
+        if isinstance(event, InviteMemberEvent):
+            await client.join(room.room_id)
+            logger.info("Joined %s", room.room_id)
+            await trust_all_devices(client)
+
+    async def send_message(room: MatrixRoom, message: str) -> None:
+        """
+        Send a message to `room`.
+        """
+        try:
+            await trust_all_devices(client)
+
+            await client.share_group_session(
+                room.room_id,
+                ignore_unverified_devices=True
+            )
+
+            await client.room_send(
+                room_id=room.room_id,
+                message_type="m.room.message",
+                content={
+                    "msgtype": "m.text",
+                    "body": message
+                },
+                ignore_unverified_devices=True
+            )
+            logger.info("Sent message to %s: %s", room.room_id, message)
+        except Exception as e:
+            logger.error(f"Error sending message: {e}")
+
+
+    async def on_message(room: MatrixRoom, event: RoomMessageText) -> None:
+        """
+        Handle incoming messages.
+        """
+
+        # Check if the message is from the bot itself
+        if event.sender == client.user_id:            
+            return
+        
+        logger.info("Received '%s' from %s in %s", event.body.strip(), event.sender, room.display_name)
+
+        
+        if isinstance(event, RoomMessageText):
+            logger.info(f"Received message in {room.room_id}: {event.body}")
+            payload = {
+                "roomId":           event.room_id,
+                "userId":           event.sender,
+                "eventId":          event.event_id,
+                "serverTimestamp":  event.server_timestamp,
+                "content":          event.body
+            }
+            headers = {"Authorization": f"Bearer {AI_HANDLER_TOKEN}"}
+            async with httpx.AsyncClient() as http:
+                try:
+                    resp = await http.post(f"{AI_HANDLER_URL}/api/v1/message", json=payload, headers=headers)
+                    resp.raise_for_status()
+                    data = resp.json()
+                    if data.get("reply"):
+                        await trust_all_devices(client)
+                        await send_message(room, data["reply"])
+                        logger.info("Reply sent: %s", data["reply"])
+                except httpx.HTTPStatusError as e:
+                    logger.error(f"HTTP error: {e.response.status_code} - {e.response.text}")
+                except Exception:
+                    logger.exception("Error while calling AI handler")
+
+    # --- Initialize the client ---
+    # Create the data directory if it doesn't exist
+    try:
+        os.makedirs("/app/data", exist_ok=True)
+    except Exception as e:
+        logger.error(f"Error creating data directory: {e}")
+        return
+    
+    # Initialize the client
+    config = AsyncClientConfig(store_sync_tokens=True, encryption_enabled=True)
+    client = AsyncClient(MATRIX_HOMESERVER_URL, MATRIX_USER_ID, store_path="/app/data", config=config)    
+  
+    for i in range(MATRIX_LOGIN_TRIES):
+        try:
+            login_response=await client.login(password=MATRIX_PASSWORD)
+            break
+        except Exception as e:
+            logger.error("Login failed: %s", login_response)
+            logger.error(f"Login attempt {i+1} failed: {e}")
+            if i == MATRIX_LOGIN_TRIES - 1:
+                return
+            await asyncio.sleep(MATRIX_LOGIN_DELAY_INCREMENT * (i + 1))
+    logger.info("Logged in successfully")
+
+    logger.debug("Upload one time Olm keys")
+    try:
+        await client.keys_upload()
+    except Exception as e:
+        logger.error(f"Error uploading keys: {e}")
+        return
+    
+    await trust_all_devices(client)
+
+    client.add_event_callback(on_invite, InviteMemberEvent)
+    client.add_event_callback(on_message, RoomMessageText)
+
+    logger.info("Starting sync loop")
+    await client.sync_forever(timeout=30000) # timeout should be moved to Variable
+
+
+
+if __name__ == "__main__":
+    try:
+        asyncio.run(main())
+    except KeyboardInterrupt:
+        logger.info("Shutting down")
+        asyncio.run(client.close())
+

matrix_service/requirements.txt

@@ -0,0 +1,4 @@
+matrix-nio[e2e]>=0.25.2
+python-dotenv>=1.0.0
+httpx>=0.23.0
+pydantic>=1.10

requirements.txt

@@ -1,3 +0,0 @@
-matrix-nio[e2e]>=0.25.0
-python-dotenv>=1.0.0
-openai