apunkt/plano
1
0
Fork 0
mirror of https://github.com/katanemo/plano.git synced 2026-05-08 15:22:43 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix DO pricing URL, model_providers name validation, cost_metrics demo endpoint

Browse source
This commit is contained in:
Adil Hafeez 2026-03-27 17:14:18 -07:00
parent bd7afd911e
commit bd335cd8bd
6 changed files with 74 additions and 60 deletions
Download patch file Download diff file Expand all files Collapse all files

34
demos/llm_routing/model_routing_service/metrics_server.py
View file

@ -1,10 +1,14 @@
"""
Minimal Prometheus metrics server for demo purposes.
Exposes mock P95 latency data for model routing.
Demo metrics server.
Exposes two endpoints:
GET /metrics — Prometheus text format, P95 latency per model (scraped by Prometheus)
GET /costs — JSON cost data per model, compatible with cost_metrics source
"""
import json
from http.server import HTTPServer, BaseHTTPRequestHandler
METRICS = """\
PROMETHEUS_METRICS = """\
# HELP model_latency_p95_seconds P95 request latency in seconds per model
# TYPE model_latency_p95_seconds gauge
model_latency_p95_seconds{model_name="anthropic/claude-sonnet-4-20250514"} 0.85
@ -12,13 +16,27 @@ model_latency_p95_seconds{model_name="openai/gpt-4o"} 1.20
model_latency_p95_seconds{model_name="openai/gpt-4o-mini"} 0.40
""".encode()
COST_DATA = {
"anthropic/claude-sonnet-4-20250514": {"input_per_million": 3.0, "output_per_million": 15.0},
"openai/gpt-4o": {"input_per_million": 5.0, "output_per_million": 20.0},
"openai/gpt-4o-mini": {"input_per_million": 0.15, "output_per_million": 0.6},
}
class MetricsHandler(BaseHTTPRequestHandler):
def do_GET(self):
self.send_response(200)
self.send_header("Content-Type", "text/plain; version=0.0.4; charset=utf-8")
self.end_headers()
self.wfile.write(METRICS)
if self.path == "/costs":
body = json.dumps(COST_DATA).encode()
self.send_response(200)
self.send_header("Content-Type", "application/json")
self.end_headers()
self.wfile.write(body)
else:
# /metrics and everything else → Prometheus format
self.send_response(200)
self.send_header("Content-Type", "text/plain; version=0.0.4; charset=utf-8")
self.end_headers()
self.wfile.write(PROMETHEUS_METRICS)
def log_message(self, fmt, *args):
pass # suppress access logs
@ -26,5 +44,5 @@ class MetricsHandler(BaseHTTPRequestHandler):
if __name__ == "__main__":
server = HTTPServer(("", 8080), MetricsHandler)
print("metrics server listening on :8080", flush=True)
print("metrics server listening on :8080 (/metrics, /costs)", flush=True)
server.serve_forever()