mirror of
https://github.com/karpathy/nanochat.git
synced 2026-05-09 01:10:10 +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>
88 lines
2.4 KiB
Python
88 lines
2.4 KiB
Python
"""FastAPI entrypoint for the samosaChaat chat API service."""
|
|
from __future__ import annotations
|
|
|
|
from contextlib import asynccontextmanager
|
|
|
|
import httpx
|
|
from fastapi import FastAPI, Request, Response
|
|
from fastapi.middleware.cors import CORSMiddleware
|
|
from prometheus_fastapi_instrumentator import Instrumentator
|
|
|
|
from .config import get_settings
|
|
from .logging_setup import (
|
|
configure_logging,
|
|
get_logger,
|
|
new_trace_id,
|
|
set_trace_id,
|
|
set_user_id,
|
|
)
|
|
from .routes import conversations, messages, models
|
|
|
|
|
|
@asynccontextmanager
|
|
async def lifespan(app: FastAPI):
|
|
app.state.auth_http_client = httpx.AsyncClient(
|
|
timeout=httpx.Timeout(5.0, connect=2.0)
|
|
)
|
|
app.state.inference_http_client = httpx.AsyncClient(
|
|
timeout=httpx.Timeout(60.0, connect=5.0)
|
|
)
|
|
try:
|
|
yield
|
|
finally:
|
|
await app.state.auth_http_client.aclose()
|
|
await app.state.inference_http_client.aclose()
|
|
|
|
|
|
def create_app() -> FastAPI:
|
|
configure_logging()
|
|
settings = get_settings()
|
|
logger = get_logger(__name__)
|
|
|
|
app = FastAPI(title="samosaChaat Chat API", version="0.1.0", lifespan=lifespan)
|
|
|
|
app.add_middleware(
|
|
CORSMiddleware,
|
|
allow_origins=[settings.frontend_url],
|
|
allow_credentials=True,
|
|
allow_methods=["*"],
|
|
allow_headers=["*"],
|
|
)
|
|
|
|
@app.middleware("http")
|
|
async def request_context(request: Request, call_next) -> Response:
|
|
incoming = request.headers.get("x-trace-id") or request.headers.get("x-request-id")
|
|
trace_id = incoming or new_trace_id()
|
|
set_trace_id(trace_id)
|
|
set_user_id(None)
|
|
|
|
logger.info(
|
|
"request_start",
|
|
method=request.method,
|
|
path=request.url.path,
|
|
)
|
|
response = await call_next(request)
|
|
response.headers["x-trace-id"] = trace_id
|
|
logger.info(
|
|
"request_end",
|
|
method=request.method,
|
|
path=request.url.path,
|
|
status_code=response.status_code,
|
|
)
|
|
return response
|
|
|
|
app.include_router(conversations.router)
|
|
app.include_router(messages.router)
|
|
app.include_router(models.router)
|
|
|
|
@app.get("/api/health")
|
|
async def health():
|
|
return {"status": "ok", "ready": True, "service": "chat-api"}
|
|
|
|
Instrumentator().instrument(app).expose(app, endpoint="/metrics", include_in_schema=False)
|
|
|
|
return app
|
|
|
|
|
|
app = create_app()
|