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>
125 lines
4.4 KiB
Python
125 lines
4.4 KiB
Python
import httpx
|
|
from fastapi import FastAPI, Request
|
|
from fastapi.responses import JSONResponse
|
|
from pydantic import BaseModel
|
|
from opentelemetry import metrics, trace
|
|
from opentelemetry.trace import StatusCode
|
|
from opentelemetry.instrumentation.fastapi import FastAPIInstrumentor
|
|
|
|
from common.http import downstream_client
|
|
from common.logging_config import configure_logging
|
|
from common.redis_client import redis_client
|
|
from common.settings import settings
|
|
from common.telemetry import setup_telemetry
|
|
|
|
from . import chaos
|
|
from .scoring import score
|
|
|
|
SERVICE_NAME = "fraud"
|
|
logger = configure_logging(SERVICE_NAME)
|
|
tracer = trace.get_tracer(__name__)
|
|
setup_telemetry(service_name=SERVICE_NAME)
|
|
app = FastAPI(title=SERVICE_NAME)
|
|
|
|
FastAPIInstrumentor.instrument_app(
|
|
app,
|
|
excluded_urls="/healthz",
|
|
exclude_spans=["receive", "send"],
|
|
)
|
|
|
|
meter = metrics.get_meter(__name__)
|
|
fraud_score = meter.create_histogram(
|
|
"ledgerline.fraud.score",
|
|
description="Risk score per scoring call (0-1; gateway rejects above 0.8)",
|
|
explicit_bucket_boundaries_advisory=[0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9, 1.0],
|
|
)
|
|
|
|
|
|
class ScoreRequest(BaseModel):
|
|
account_id: str
|
|
holder_name: str
|
|
category_id: int | None = None
|
|
amount_minor: int
|
|
|
|
|
|
@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:
|
|
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"}
|
|
|
|
|
|
@app.post("/internal/score")
|
|
async def score_transaction(body: ScoreRequest):
|
|
logger.info(
|
|
"score_requested",
|
|
account_id=body.account_id,
|
|
amount_minor=body.amount_minor,
|
|
category_id=body.category_id,
|
|
)
|
|
await redis_client.incr("fraud:calls_total")
|
|
|
|
if await chaos.blocking_event_loop_enabled():
|
|
logger.info("chaos_engaged", chaos_flag="blocking_event_loop", account_id=body.account_id)
|
|
chaos.synchronous_cpu_work()
|
|
|
|
with tracer.start_as_current_span(
|
|
"fraud.score_transaction",
|
|
attributes={
|
|
"ledgerline.account.id": body.account_id,
|
|
"ledgerline.tx.amount_minor": body.amount_minor,
|
|
},
|
|
) as span:
|
|
if body.category_id is not None:
|
|
span.set_attribute("ledgerline.merchant.category_id", body.category_id)
|
|
async with downstream_client() as client:
|
|
try:
|
|
resp = await client.post(
|
|
f"{settings.sanctions_url}/internal/lookup",
|
|
json={"holder_name": body.holder_name},
|
|
)
|
|
except httpx.TimeoutException as exc:
|
|
span.record_exception(exc)
|
|
span.set_status(StatusCode.ERROR, "sanctions lookup timed out")
|
|
logger.exception("sanctions_check_timed_out", account_id=body.account_id)
|
|
return JSONResponse(status_code=504, content={"error": "sanctions lookup timed out"})
|
|
except httpx.RequestError as exc:
|
|
span.record_exception(exc)
|
|
span.set_status(StatusCode.ERROR, "sanctions lookup failed")
|
|
logger.exception("sanctions_check_failed", account_id=body.account_id)
|
|
return JSONResponse(status_code=502, content={"error": "sanctions lookup failed"})
|
|
|
|
if resp.status_code >= 300:
|
|
logger.warning(
|
|
"sanctions_check_failed", account_id=body.account_id, status_code=resp.status_code
|
|
)
|
|
return JSONResponse(status_code=502, content={"error": "sanctions lookup failed"})
|
|
|
|
matched = resp.json().get("matched", False)
|
|
risk_score = score(body.category_id, matched)
|
|
span.set_attribute("ledgerline.sanctions.matched", matched)
|
|
span.set_attribute("ledgerline.risk.score", risk_score)
|
|
fraud_score.record(risk_score)
|
|
logger.info(
|
|
"transaction_scored", account_id=body.account_id, risk_score=risk_score, matched=matched
|
|
)
|
|
return {"risk_score": risk_score, "matched": matched}
|