feat(worker): complete Phase 3 - processing worker with normalization, micro-batching, and at-least-once offset management

This commit is contained in:
2026-09-19 13:24:26 +03:30
parent 66a50cd3ba
commit 36ff3c6a34
10 changed files with 1270 additions and 7 deletions

View File

@@ -0,0 +1,95 @@
import json
import threading
from http.server import BaseHTTPRequestHandler, ThreadingHTTPServer
from typing import Optional
from app.common.config import config
from app.common.logging import setup_logger
from app.worker.metrics import worker_metrics
logger = setup_logger("processing-worker")
class WorkerHTTPRequestHandler(BaseHTTPRequestHandler):
"""
Lightweight HTTP request handler for worker internal metrics and stats.
"""
def log_message(self, format: str, *args) -> None:
# Suppress default noisy stderr logging
pass
def do_GET(self) -> None:
if self.path == "/internal/stats":
stats = worker_metrics.get_internal_stats()
body = json.dumps(stats, indent=2).encode("utf-8")
self.send_response(200)
self.send_header("Content-Type", "application/json")
self.send_header("Content-Length", str(len(body)))
self.end_headers()
self.wfile.write(body)
return
if self.path == "/metrics":
metrics_text = worker_metrics.get_prometheus_metrics()
body = metrics_text.encode("utf-8")
self.send_response(200)
self.send_header(
"Content-Type", "text/plain; version=0.0.4; charset=utf-8"
)
self.send_header("Content-Length", str(len(body)))
self.end_headers()
self.wfile.write(body)
return
if self.path in ("/health", "/healthz", "/live"):
body = b'{"status": "ok"}'
self.send_response(200)
self.send_header("Content-Type", "application/json")
self.send_header("Content-Length", str(len(body)))
self.end_headers()
self.wfile.write(body)
return
self.send_response(404)
self.send_header("Content-Type", "application/json")
body = b'{"error": "not_found"}'
self.send_header("Content-Length", str(len(body)))
self.end_headers()
self.wfile.write(body)
class WorkerInternalServer:
"""
Background HTTP server serving /internal/stats and /metrics on worker port (8001).
"""
def __init__(self, host: Optional[str] = None, port: Optional[int] = None):
self.host = host or config.worker.stats_host
self.port = port or config.worker.stats_port
self._server: Optional[ThreadingHTTPServer] = None
self._thread: Optional[threading.Thread] = None
def start(self) -> None:
self._server = ThreadingHTTPServer(
(self.host, self.port), WorkerHTTPRequestHandler
)
self._thread = threading.Thread(
target=self._server.serve_forever, daemon=True, name="WorkerInternalHTTP"
)
self._thread.start()
logger.info(
f"Worker internal HTTP server started on http://{self.host}:{self.port}",
extra={"event": "worker_http_started"},
)
def stop(self) -> None:
if self._server:
self._server.shutdown()
self._server.server_close()
if self._thread:
self._thread.join(timeout=2.0)
logger.info(
"Worker internal HTTP server stopped cleanly",
extra={"event": "worker_http_stopped"},
)