feat: initial release of q38max gateway

xtest.sh

@@ -0,0 +1,67 @@
+#!/usr/bin/env bash
+set -e
+
+PORT=${1:-18080}
+BASE_URL="http://localhost:${PORT}"
+
+echo "=== 1. Testing Models Endpoint ==="
+curl -s "${BASE_URL}/v1/models" | jq .
+
+echo ""
+echo "=== 2. Testing Non-Streaming Chat Completion ==="
+curl -s -X POST "${BASE_URL}/v1/chat/completions" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "model": "qwen-3.8-max",
+    "messages": [
+      {"role": "user", "content": "What is the capital of Italy? Answer in 1 word."}
+    ],
+    "reasoning_effort": "none",
+    "max_tokens": 50
+  }' | jq .
+
+echo ""
+echo "=== 3. Testing Streaming SSE Completion (with reasoning) ==="
+curl -N -s -X POST "${BASE_URL}/v1/chat/completions" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "model": "qwen-3.8-max",
+    "messages": [
+      {"role": "user", "content": "Calculate 25 * 25 and explain briefly in one sentence."}
+    ],
+    "stream": true,
+    "reasoning_effort": "medium",
+    "max_tokens": 150
+  }'
+
+echo ""
+echo "=== 4. Testing Function/Tool Calling ==="
+curl -s -X POST "${BASE_URL}/v1/chat/completions" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "model": "qwen-3.8-max",
+    "messages": [
+      {"role": "user", "content": "What is the weather in Berlin?"}
+    ],
+    "tools": [
+      {
+        "type": "function",
+        "function": {
+          "name": "get_weather",
+          "description": "Get current weather for location",
+          "parameters": {
+            "type": "object",
+            "properties": {
+              "location": {"type": "string"}
+            },
+            "required": ["location"]
+          }
+        }
+      }
+    ],
+    "reasoning_effort": "none",
+    "max_tokens": 200
+  }' | jq .
+
+echo ""
+echo "=== All integration tests finished successfully! ==="