refactor(observability): restructure into service-owned packages

src/core/api/main.py

@@ -1,21 +1,18 @@
 from contextlib import asynccontextmanager
 
 from fastapi import FastAPI
-from fastapi.responses import JSONResponse, Response
-
-from prometheus_client import CONTENT_TYPE_LATEST
 
 from core.api.kafka_publisher import KafkaPublisher
-from core.api.publisher import Publisher
-from core.api.routes import router
-from core.config import get_settings
-from core.api.metrics import ApiMetrics
-from core.api.stats import (
+from core.api.observability.metrics import ApiMetrics
+from core.api.observability.routes import create_observability_router
+from core.api.observability.stats import (
     ApiRuntimeStats,
     HttpWorkerStatsClient,
     WorkerStatsProvider,
-    WorkerStatsUnavailable,
 )
+from core.api.publisher import Publisher
+from core.api.routes import router
+from core.config import get_settings
 
 
 def create_app(
@@ -27,6 +24,15 @@ def create_app(
     api_metrics = ApiMetrics()
     api_stats = ApiRuntimeStats()
 
+    active_worker_stats_client = (
+        worker_stats_client
+        if worker_stats_client is not None
+        else HttpWorkerStatsClient(
+            url=settings.worker_stats_url,
+            timeout_seconds=settings.worker_stats_timeout_seconds,
+        )
+    )
+
     @asynccontextmanager
     async def lifespan(app: FastAPI):
         active_publisher = publisher
@@ -36,20 +42,6 @@ def create_app(
                 settings
             )
 
-        active_worker_stats_client = (
-            worker_stats_client
-        )
-
-        if active_worker_stats_client is None:
-            active_worker_stats_client = (
-                HttpWorkerStatsClient(
-                    url=settings.worker_stats_url,
-                    timeout_seconds=(
-                        settings.worker_stats_timeout_seconds
-                    ),
-                )
-            )
-
         app.state.publisher = active_publisher
 
         app.state.worker_stats_client = (
@@ -75,73 +67,27 @@ def create_app(
     app.state.api_metrics = api_metrics
     app.state.api_stats = api_stats
 
+    observability_router = create_observability_router(
+        metrics=api_metrics,
+        stats=api_stats,
+        worker_stats_provider=active_worker_stats_client,
+    )
+
     app.include_router(
         router,
         prefix="/api/v1",
     )
 
+    app.include_router(
+        observability_router,
+    )
+
     @app.get("/health")
     async def health() -> dict[str, str]:
         return {
             "status": "ok",
         }
 
-    @app.get(
-        "/metrics",
-        include_in_schema=False,
-    )
-    async def metrics() -> Response:
-        return Response(
-            content=api_metrics.render(),
-            media_type=CONTENT_TYPE_LATEST,
-        )
-
-    @app.get("/stats")
-    async def stats():
-        try:
-            worker_stats = await (
-                app.state
-                .worker_stats_client
-                .get_stats()
-            )
-
-        except WorkerStatsUnavailable as exc:
-            return JSONResponse(
-                status_code=503,
-                content={
-                    "error": "worker_stats_unavailable",
-                    "detail": str(exc),
-                },
-            )
-
-        api_snapshot = api_stats.snapshot()
-
-        worker_pipeline = (
-            worker_stats["pipeline"]
-        )
-
-        return {
-            "pipeline": {
-                "total_received":
-                    api_snapshot["total_received"],
-
-                "total_processed":
-                    worker_pipeline["total_processed"],
-
-                "total_dlq":
-                    worker_pipeline["total_dlq"],
-
-                "in_flight_buffer":
-                    worker_pipeline["in_flight_buffer"],
-
-                "last_flush_at":
-                    worker_pipeline["last_flush_at"],
-            },
-
-            "breakdown":
-                worker_stats["breakdown"],
-        }
-
     return app