ryan
0478ee7568
Tracks end-to-end response time and request counts (by stream mode and result) via prometheus_client. Exposes GET /metrics behind a bearer token (METRICS_TOKEN env var) so Prometheus can scrape it without exposing raw data publicly. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
56 lines
1.3 KiB
Python
56 lines
1.3 KiB
Python
import time
|
|
from contextlib import contextmanager
|
|
from prometheus_client import (
|
|
CollectorRegistry,
|
|
Counter,
|
|
Histogram,
|
|
generate_latest,
|
|
)
|
|
|
|
REGISTRY = CollectorRegistry(auto_describe=True)
|
|
|
|
CHAT_RESPONSE_SECONDS = Histogram(
|
|
"raggr_chat_response_seconds",
|
|
"End-to-end chat response time in seconds.",
|
|
labelnames=("stream",),
|
|
buckets=(0.5, 1, 2, 5, 10, 30, 60, 120, 300),
|
|
registry=REGISTRY,
|
|
)
|
|
|
|
CHAT_REQUESTS_TOTAL = Counter(
|
|
"raggr_chat_requests_total",
|
|
"Total chat requests by stream mode and result.",
|
|
labelnames=("stream", "result"),
|
|
registry=REGISTRY,
|
|
)
|
|
|
|
|
|
def _s(stream: bool) -> str:
|
|
return "true" if stream else "false"
|
|
|
|
|
|
@contextmanager
|
|
def time_response(stream: bool):
|
|
t0 = time.monotonic()
|
|
result = "success"
|
|
try:
|
|
yield
|
|
except Exception:
|
|
result = "error"
|
|
raise
|
|
finally:
|
|
CHAT_RESPONSE_SECONDS.labels(stream=_s(stream)).observe(time.monotonic() - t0)
|
|
CHAT_REQUESTS_TOTAL.labels(stream=_s(stream), result=result).inc()
|
|
|
|
|
|
def observe_response(stream: bool, seconds: float) -> None:
|
|
CHAT_RESPONSE_SECONDS.labels(stream=_s(stream)).observe(seconds)
|
|
|
|
|
|
def count_result(stream: bool, result: str) -> None:
|
|
CHAT_REQUESTS_TOTAL.labels(stream=_s(stream), result=result).inc()
|
|
|
|
|
|
def render_metrics() -> bytes:
|
|
return generate_latest(REGISTRY)
|