Movses AslanyanandClaude Opus 5.5
920712f32b
- ledgerline.transactions.total (counter: kind, status, currency) and ledgerline.transaction.duration (histogram, seconds: kind) in gateway, the only place that sees the final outcome, failures included. currency is client input, so values outside the seeded set are recorded as "other". - ledgerline.fraud.score (histogram, buckets in 0.1 steps to 1.0) in fraud. - ledgerline.stream.lag (observable gauge: consumer_group) in audit and notifier, read from XINFO GROUPS through a separate sync Redis client, because callbacks run on the scrape thread; the call is untraced so scrapes don't create traces. - ledgerline.db.pool.in_use (observable up-down counter: pool) in every service with a DB engine. The SQLAlchemy instrumentation's own pool metric names a pool by DSN, which merges the normal and starved engines. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
69 lines
2.0 KiB
Python
69 lines
2.0 KiB
Python
from contextlib import asynccontextmanager
|
|
|
|
import asyncio
|
|
|
|
from fastapi import FastAPI, Request
|
|
from fastapi.responses import JSONResponse
|
|
from opentelemetry import trace
|
|
from opentelemetry.instrumentation.fastapi import FastAPIInstrumentor
|
|
from opentelemetry.instrumentation.sqlalchemy import SQLAlchemyInstrumentor
|
|
from opentelemetry.trace import StatusCode
|
|
|
|
from common.db import engine
|
|
from common.logging_config import configure_logging
|
|
from common.metrics import observe_db_pools, observe_stream_lag
|
|
from common.redis_client import redis_client
|
|
from common.telemetry import setup_telemetry
|
|
|
|
from . import consumer
|
|
|
|
SERVICE_NAME = "notifier"
|
|
logger = configure_logging(SERVICE_NAME)
|
|
setup_telemetry(service_name=SERVICE_NAME)
|
|
|
|
|
|
@asynccontextmanager
|
|
async def lifespan(app: FastAPI):
|
|
task = asyncio.create_task(consumer.run())
|
|
yield
|
|
task.cancel()
|
|
|
|
|
|
app = FastAPI(title=SERVICE_NAME, lifespan=lifespan)
|
|
|
|
FastAPIInstrumentor.instrument_app(
|
|
app,
|
|
excluded_urls="/healthz",
|
|
exclude_spans=["receive", "send"],
|
|
)
|
|
SQLAlchemyInstrumentor().instrument(engines=[engine.sync_engine])
|
|
observe_db_pools({"default": engine})
|
|
observe_stream_lag(consumer.GROUP)
|
|
|
|
|
|
@app.get("/")
|
|
async def root():
|
|
return {"service": SERVICE_NAME, "version": "0.1.0"}
|
|
|
|
|
|
@app.get("/healthz")
|
|
async def healthz(request: Request):
|
|
if request.headers.get("X-Ledgerline-Probe") == "chatty-health":
|
|
logger.info("healthz_probe_received", probe="chatty-health")
|
|
return {"status": "ok", "service": SERVICE_NAME}
|
|
|
|
|
|
@app.get("/readyz")
|
|
async def readyz():
|
|
try:
|
|
async with engine.connect() as conn:
|
|
await conn.exec_driver_sql("SELECT 1")
|
|
await redis_client.ping()
|
|
except Exception as exc:
|
|
span = trace.get_current_span()
|
|
span.record_exception(exc)
|
|
span.set_status(StatusCode.ERROR, str(exc))
|
|
logger.exception("readyz_check_failed")
|
|
return JSONResponse(status_code=503, content={"status": "unavailable"})
|
|
return {"status": "ok"}
|