feat(matrix-bridge-dagi): add matrix client wrapper and synapse setup (PR-M1.1)

- adds MatrixClient with send_text/sync_poll/join_room/whoami (idempotent via txn_id)
- LRU dedupe for incoming event_ids (2048 capacity)
- exponential backoff retry (max 3 attempts) for 429/5xx/network errors
- extract_room_messages: filters own messages, non-text, duplicates
- health endpoint now probes matrix_reachable + gateway_reachable at startup
- adds docker-compose.synapse-node1.yml (Synapse + Postgres for NODA1)
- adds ops/runbook-matrix-setup.md (10-step setup: DNS, config, bot, room, .env)
- 19 tests passing, no real Synapse required

Made-with: Cursor

services/matrix-bridge-dagi/app/main.py

@@ -8,11 +8,18 @@ import logging
 import os
 import time
 from contextlib import asynccontextmanager
-from typing import Any, Dict
+from typing import Any, Dict, Optional
 
 from fastapi import FastAPI, Response
 from fastapi.middleware.cors import CORSMiddleware
 
+try:
+    import httpx as _httpx
+    _HTTPX_OK = True
+except ImportError:  # pragma: no cover
+    _httpx = None  # type: ignore
+    _HTTPX_OK = False
+
 try:
     from prometheus_client import (
         Counter, Histogram, Gauge,
@@ -60,13 +67,27 @@ if _PROM_OK:
 
 # ── Startup state ─────────────────────────────────────────────────────────────
 _START_TIME = time.monotonic()
-_cfg: BridgeConfig | None = None
-_config_error: str | None = None
+_cfg: Optional[BridgeConfig] = None
+_config_error: Optional[str] = None
+_matrix_reachable: Optional[bool] = None    # probed at startup
+_gateway_reachable: Optional[bool] = None   # probed at startup
+
+
+async def _probe_url(url: str, timeout: float = 5.0) -> bool:
+    """Quick GET probe — returns True if HTTP 2xx."""
+    if not _HTTPX_OK or not url:
+        return False
+    try:
+        async with _httpx.AsyncClient(timeout=timeout) as client:
+            r = await client.get(url)
+            return r.status_code < 400
+    except Exception:
+        return False
 
 # ── Lifespan ──────────────────────────────────────────────────────────────────
 @asynccontextmanager
 async def lifespan(app_: Any):
-    global _cfg, _config_error
+    global _cfg, _config_error, _matrix_reachable, _gateway_reachable
     try:
         _cfg = load_config()
         logger.info(
@@ -74,6 +95,21 @@ async def lifespan(app_: Any):
             _cfg.node_id, _cfg.build_sha, _cfg.matrix_homeserver_url,
             _cfg.sofiia_room_id, list(_cfg.bridge_allowed_agents),
         )
+        # Connectivity smoke probes (non-blocking failures)
+        _matrix_reachable = await _probe_url(
+            f"{_cfg.matrix_homeserver_url}/_matrix/client/versions"
+        )
+        _gateway_reachable = await _probe_url(
+            f"{_cfg.dagi_gateway_url}/health"
+        )
+        if _matrix_reachable:
+            logger.info("✅ Matrix homeserver reachable: %s", _cfg.matrix_homeserver_url)
+        else:
+            logger.warning("⚠️  Matrix homeserver NOT reachable: %s", _cfg.matrix_homeserver_url)
+        if _gateway_reachable:
+            logger.info("✅ DAGI Gateway reachable: %s", _cfg.dagi_gateway_url)
+        else:
+            logger.warning("⚠️  DAGI Gateway NOT reachable: %s", _cfg.dagi_gateway_url)
         if _PROM_OK:
             _bridge_up.set(1)
     except RuntimeError as exc:
@@ -111,8 +147,11 @@ async def health() -> Dict[str, Any]:
             "uptime_s": uptime,
             "error": _config_error or "service not initialised",
         }
+    matrix_ok = _matrix_reachable is True
+    gateway_ok = _gateway_reachable is True
+    overall_ok = matrix_ok and gateway_ok
     return {
-        "ok": True,
+        "ok": overall_ok,
         "service": "matrix-bridge-dagi",
         "version": "0.1.0",
         "build": _cfg.build_sha,
@@ -121,10 +160,12 @@ async def health() -> Dict[str, Any]:
         "uptime_s": uptime,
         "node_id": _cfg.node_id,
         "homeserver": _cfg.matrix_homeserver_url,
+        "matrix_reachable": _matrix_reachable,
         "bridge_user": _cfg.matrix_user_id,
         "sofiia_room_id": _cfg.sofiia_room_id,
         "allowed_agents": list(_cfg.bridge_allowed_agents),
         "gateway": _cfg.dagi_gateway_url,
+        "gateway_reachable": _gateway_reachable,
         "config_ok": True,
     }