Implement batched server parity and observability

scripts/endpoint_reasoning.py

@@ -0,0 +1,53 @@
+#!/usr/bin/env python3
+import json
+import sys
+import urllib.request
+
+
+base_url = sys.argv[1] if len(sys.argv) > 1 else "http://127.0.0.1:9000"
+prompt = "Think briefly, then reply with only the number: 17 * 19."
+cases = [
+    (
+        "chat",
+        "/v1/chat/completions",
+        {
+            "model": "deepseek-v4-flash",
+            "messages": [{"role": "user", "content": prompt}],
+            "reasoning_effort": "low",
+            "temperature": 0,
+            "max_tokens": 96,
+        },
+    ),
+    (
+        "anthropic",
+        "/v1/messages",
+        {
+            "model": "deepseek-v4-flash",
+            "messages": [{"role": "user", "content": prompt}],
+            "thinking": {"type": "enabled", "budget_tokens": 64},
+            "output_config": {"effort": "low"},
+            "temperature": 0,
+            "max_tokens": 96,
+        },
+    ),
+    (
+        "responses",
+        "/v1/responses",
+        {
+            "model": "deepseek-v4-flash",
+            "input": prompt,
+            "reasoning": {"effort": "low", "summary": "auto"},
+            "temperature": 0,
+            "max_output_tokens": 96,
+        },
+    ),
+]
+
+for name, path, payload in cases:
+    request = urllib.request.Request(
+        base_url + path,
+        data=json.dumps(payload).encode(),
+        headers={"Content-Type": "application/json"},
+    )
+    with urllib.request.urlopen(request, timeout=120) as response:
+        print(name, json.dumps(json.load(response), separators=(",", ":")))