Implement batched server parity and observability

scripts/endpoint_parity.py

@@ -0,0 +1,101 @@
+#!/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"
+streaming = "--stream" in sys.argv
+parameters = {
+    "type": "object",
+    "properties": {"text": {"type": "string"}},
+    "required": ["text"],
+}
+cases = [
+    (
+        "chat",
+        "/v1/chat/completions",
+        {
+            "model": "deepseek-v4-flash",
+            "messages": [
+                {
+                    "role": "user",
+                    "content": "Call echo with text hi. Do not answer normally.",
+                }
+            ],
+            "tools": [
+                {
+                    "type": "function",
+                    "function": {
+                        "name": "echo",
+                        "description": "Echo text",
+                        "parameters": parameters,
+                    },
+                }
+            ],
+            "reasoning_effort": "none",
+            "temperature": 0,
+            "max_tokens": 128,
+        },
+    ),
+    (
+        "anthropic",
+        "/v1/messages",
+        {
+            "model": "deepseek-v4-flash",
+            "messages": [
+                {
+                    "role": "user",
+                    "content": "Call echo with text hi. Do not answer normally.",
+                }
+            ],
+            "tools": [
+                {
+                    "name": "echo",
+                    "description": "Echo text",
+                    "input_schema": parameters,
+                }
+            ],
+            "thinking": {"type": "disabled"},
+            "temperature": 0,
+            "max_tokens": 128,
+        },
+    ),
+    (
+        "responses",
+        "/v1/responses",
+        {
+            "model": "deepseek-v4-flash",
+            "input": "Call echo with text hi. Do not answer normally.",
+            "tools": [
+                {
+                    "type": "function",
+                    "name": "echo",
+                    "description": "Echo text",
+                    "parameters": parameters,
+                }
+            ],
+            "reasoning": {"effort": "none"},
+            "temperature": 0,
+            "max_output_tokens": 128,
+        },
+    ),
+]
+
+for name, path, payload in cases:
+    if streaming:
+        payload["stream"] = True
+        if name == "chat":
+            payload["stream_options"] = {"include_usage": True}
+    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:
+        if streaming:
+            for line in response:
+                if line.strip():
+                    print(name, line.decode().rstrip())
+        else:
+            print(name, json.dumps(json.load(response), separators=(",", ":")))