ВМ1: реализован сбор логов

VM1_app/codebase/backend/sms-service/app/worker.py

@@ -10,6 +10,7 @@ from datetime import UTC, datetime, timedelta
 import httpx
 import structlog
 from opentelemetry import trace
+from opentelemetry.propagate import extract
 from prometheus_client import start_http_server
 from sqlalchemy import and_, func, or_, select, update
 
@@ -26,14 +27,27 @@ from app.metrics import (
 from app.provider import IdgtlClient, IdgtlConfig
 from app.service import RuntimeSettings, load_runtime_settings
 from app.settings import Settings, get_settings
-from app.telemetry import add_trace_context, init_telemetry
+from app.telemetry import TelemetryRuntime, add_trace_context, init_telemetry
 
 log = structlog.get_logger()
 MAX_CONNECT_ATTEMPTS = 3
 
 
-def configure_logging(level: str) -> None:
+def origin_links(traceparent: str | None) -> list[trace.Link]:
+    if not traceparent:
+        return []
+    context = extract({"traceparent": traceparent})
+    span_context = trace.get_current_span(context).get_span_context()
+    return [trace.Link(span_context)] if span_context.is_valid else []
+
+
+def configure_logging(level: str, telemetry: TelemetryRuntime | None = None) -> None:
     logging.basicConfig(level=level, format="%(message)s")
+    if telemetry and telemetry.logging_handler not in logging.getLogger().handlers:
+        telemetry.logging_handler.addFilter(
+            lambda record: not record.name.startswith("opentelemetry")
+        )
+        logging.getLogger().addHandler(telemetry.logging_handler)
     structlog.configure(
         processors=[
             structlog.contextvars.merge_contextvars,
@@ -42,7 +56,10 @@ def configure_logging(level: str) -> None:
             structlog.processors.TimeStamper(fmt="iso", utc=True, key="timestamp"),
             structlog.stdlib.add_log_level,
             structlog.processors.JSONRenderer(),
-        ]
+        ],
+        logger_factory=structlog.stdlib.LoggerFactory(),
+        wrapper_class=structlog.stdlib.BoundLogger,
+        cache_logger_on_first_use=True,
     )
 
 
@@ -177,7 +194,7 @@ async def update_queue_metrics(db: Database) -> None:
 async def worker_loop(stop: asyncio.Event) -> None:
     settings = get_settings()
     telemetry = init_telemetry("sms-worker")
-    configure_logging(settings.log_level)
+    configure_logging(settings.log_level, telemetry)
     structlog.contextvars.bind_contextvars(**{"service.name": "sms-worker"})
     metrics_server, metrics_thread = start_http_server(
         settings.metrics_port,
@@ -200,8 +217,17 @@ async def worker_loop(stop: asyncio.Event) -> None:
                         await update_queue_metrics(db)
                         await asyncio.wait_for(stop.wait(), timeout=runtime.poll_interval_ms / 1000)
                         continue
-                    process_span = tracer.start_span("sms.process", start_time=claim_started_ns)
-                    with trace.use_span(process_span, end_on_exit=True):
+                    process_span = tracer.start_span(
+                        "sms.process",
+                        start_time=claim_started_ns,
+                        links=origin_links(message.traceparent),
+                    )
+                    with (
+                        trace.use_span(process_span, end_on_exit=True),
+                        structlog.contextvars.bound_contextvars(
+                            sms_message_id=str(message.id)
+                        ),
+                    ):
                         claim_span = tracer.start_span("sms.claim", start_time=claim_started_ns)
                         claim_span.set_attribute("sms.claimed", True)
                         claim_span.end(end_time=claim_finished_ns)