mirror of
https://github.com/karpathy/nanochat.git
synced 2026-05-16 12:47:34 +00:00
aa0818aae2
Replaces the helm/observability scaffold with a real monitoring stack
wired into the samosaChaat platform.
Helm chart (helm/observability/)
- Chart.yaml declares kube-prometheus-stack (~62.0) and loki-stack
(~2.10) as subchart dependencies.
- values.yaml configures Prometheus (15d retention, 50Gi PVC,
ServiceMonitor + rule selector on app.kubernetes.io/part-of:
samosachaat), Alertmanager (10Gi PVC), Grafana (OAuth-only via
GitHub + Google, local login disabled, Prometheus + Loki datasources,
dashboards auto-provisioned from a ConfigMap, email + Slack contact
points with a critical route to Slack), Loki (50Gi, 30d retention,
tsdb schema), and Promtail (JSON pipeline that lifts level / service
/ trace_id / user_id into labels, scrape config with pod labels).
- Alert rules: HighCPU, HighMemory, DiskSpaceLow, High5xxRate,
InferenceServiceDown, HighP99Latency.
- templates/grafana-dashboards-configmap.yaml renders every file under
dashboards/ into a single grafana_dashboard=1 ConfigMap.
- dashboards/node-health.json, app-performance.json, inference.json -
fully-formed Grafana dashboards with Prometheus datasource variable,
templated app selector, thresholded gauges, and LogQL-ready labels.
Scraping (helm/samosachaat/templates/servicemonitor.yaml)
- ServiceMonitor CRs for auth / chat-api / inference that Prometheus
picks up via the part-of=samosachaat selector; scrapes /metrics
every 15s and replaces the app label so dashboards line up.
Application instrumentation
- services/{auth,chat-api,inference} each depend on
prometheus-fastapi-instrumentator and expose /metrics (request count,
latency histograms, in-progress gauges).
- services/auth/src/logging_setup.py and
services/inference/src/logging_setup.py mirror the canonical
chat-api implementation - structlog JSON with service, trace_id,
user_id context injection.
- configure_logging() is called at create_app() in auth and inference;
inference's main.py now uses structlog via get_logger() instead of
logging.getLogger.
- log_level setting added to auth + inference config (LOG_LEVEL env).
Docs
- contracts/logging-standard.md defines the required JSON fields,
Python (structlog) + Node.js (pino) implementations, LogQL examples
for cross-service queries, and the x-trace-id propagation contract.
Closes #9
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
56 lines
1.7 KiB
Python
56 lines
1.7 KiB
Python
"""FastAPI entrypoint for the samosaChaat auth service."""
|
|
from __future__ import annotations
|
|
|
|
from fastapi import FastAPI
|
|
from fastapi.middleware.cors import CORSMiddleware
|
|
from fastapi.responses import JSONResponse
|
|
from prometheus_fastapi_instrumentator import Instrumentator
|
|
from slowapi.errors import RateLimitExceeded
|
|
from slowapi.middleware import SlowAPIMiddleware
|
|
from starlette.middleware.sessions import SessionMiddleware
|
|
|
|
from .config import get_settings
|
|
from .logging_setup import configure_logging
|
|
from .rate_limit import limiter
|
|
from .routes import oauth, session, users
|
|
|
|
|
|
def _rate_limit_handler(request, exc: RateLimitExceeded):
|
|
return JSONResponse(status_code=429, content={"detail": "rate limit exceeded"})
|
|
|
|
|
|
def create_app() -> FastAPI:
|
|
configure_logging()
|
|
settings = get_settings()
|
|
app = FastAPI(title="samosaChaat Auth", version="0.1.0")
|
|
|
|
app.state.limiter = limiter
|
|
app.add_exception_handler(RateLimitExceeded, _rate_limit_handler)
|
|
app.add_middleware(SlowAPIMiddleware)
|
|
|
|
# SessionMiddleware is required by authlib for the OAuth state cookie.
|
|
app.add_middleware(SessionMiddleware, secret_key=settings.session_secret)
|
|
|
|
app.add_middleware(
|
|
CORSMiddleware,
|
|
allow_origins=[settings.frontend_url],
|
|
allow_credentials=True,
|
|
allow_methods=["*"],
|
|
allow_headers=["*"],
|
|
)
|
|
|
|
app.include_router(oauth.router)
|
|
app.include_router(session.router)
|
|
app.include_router(users.router)
|
|
|
|
@app.get("/auth/health")
|
|
async def health():
|
|
return {"status": "ok"}
|
|
|
|
Instrumentator().instrument(app).expose(app, endpoint="/metrics", include_in_schema=False)
|
|
|
|
return app
|
|
|
|
|
|
app = create_app()
|