Where an error is caught and logged under a span that would otherwise stay clean, also record_exception and set ERROR on that span: the CONSUMER span when a stream message fails, fraud.score_transaction when the sanctions call times out or fails, and the SERVER span of every /readyz check (a 503 already made it ERROR, but without the exception). Left alone where instrumentation already records it: ledger's app-wide exception handler (FastAPI SERVER span), caught httpx errors (CLIENT span), and the stream publish failure (PRODUCER span). The consumers' failed reads run outside any span, so they stay log-only. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
108 lines
4.0 KiB
Python
108 lines
4.0 KiB
Python
import httpx
|
|
from fastapi import FastAPI, Request
|
|
from fastapi.responses import JSONResponse
|
|
from pydantic import BaseModel
|
|
from opentelemetry import 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"],
|
|
)
|
|
|
|
|
|
class ScoreRequest(BaseModel):
|
|
account_id: str
|
|
holder_name: str
|
|
category_id: int | None = None
|
|
amount_minor: int
|
|
request_id: str = "unknown"
|
|
|
|
|
|
@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("received chatty-health healthz probe from gateway")
|
|
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(f"readyz check failed: {exc}")
|
|
return JSONResponse(status_code=503, content={"status": "unavailable"})
|
|
return {"status": "ok"}
|
|
|
|
|
|
@app.post("/internal/score")
|
|
async def score_transaction(body: ScoreRequest):
|
|
logger.info(f"scoring account {body.account_id} request_id={body.request_id}")
|
|
await redis_client.incr("fraud:calls_total")
|
|
|
|
if await chaos.blocking_event_loop_enabled():
|
|
logger.info(f"blocking_event_loop chaos engaged for request_id={body.request_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(body.request_id) as client:
|
|
try:
|
|
resp = await client.post(
|
|
f"{settings.sanctions_url}/internal/lookup",
|
|
json={"holder_name": body.holder_name, "request_id": body.request_id},
|
|
)
|
|
except httpx.TimeoutException as exc:
|
|
span.record_exception(exc)
|
|
span.set_status(StatusCode.ERROR, "sanctions lookup timed out")
|
|
logger.exception(f"sanctions lookup timed out for request_id={body.request_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(f"sanctions lookup failed for request_id={body.request_id}: {exc}")
|
|
return JSONResponse(status_code=502, content={"error": "sanctions lookup failed"})
|
|
|
|
if resp.status_code >= 300:
|
|
logger.info(f"sanctions returned {resp.status_code} for request_id={body.request_id}")
|
|
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)
|
|
return {"risk_score": risk_score, "matched": matched}
|