feat(observability): implement global database error logging, Prometheus error metrics, and max 3-panel Grafana dashboard

core/error_logger.py

@@ -0,0 +1,38 @@
+import json
+import logging
+import traceback
+from typing import Optional, Dict, Any
+from db.database import get_db_pool
+from core.metrics import ERRORS_TOTAL
+
+logger = logging.getLogger("copykar.errors")
+
+async def log_exception(service_name: str, error: Exception, context: Optional[Dict[str, Any]] = None):
+    """Log an exception to Database, Prometheus metrics, and Python logs."""
+    error_type = type(error).__name__
+    error_msg = str(error)
+    tb_str = traceback.format_exc()
+    ctx_json = json.dumps(context or {}, default=str)
+
+    # 1. Prometheus Metric
+    try:
+        ERRORS_TOTAL.labels(service=service_name, error_type=error_type).inc()
+    except Exception as e:
+        logger.debug(f"Failed to increment error metric: {e}")
+
+    # 2. Python standard logger
+    logger.error(f"[{service_name}] {error_type}: {error_msg}\nContext: {ctx_json}\n{tb_str}")
+
+    # 3. PostgreSQL Database
+    try:
+        pool = await get_db_pool()
+        async with pool.acquire() as conn:
+            await conn.execute(
+                """
+                INSERT INTO error_logs (service_name, error_type, error_message, traceback, context)
+                VALUES ($1, $2, $3, $4, $5::jsonb);
+                """,
+                service_name, error_type, error_msg, tb_str, ctx_json
+            )
+    except Exception as db_err:
+        logger.critical(f"Failed to write error to database: {db_err}")

core/metrics.py

@@ -46,6 +46,12 @@ POSTS_PUBLISHED_TOTAL = Counter(
     ["target_channel_id"]
 )
 
+ERRORS_TOTAL = Counter(
+    "copykar_errors_total",
+    "Total exceptions and errors caught across services",
+    ["service", "error_type"]
+)
+
 # Histograms
 AI_LATENCY_SECONDS = Histogram(
     "copykar_ai_latency_seconds",