import json
import urllib.request
import urllib.error

HOST = "http://127.0.0.1:11434"
MODEL = "qwen3.5:9b"

tests = [
    ("plain_text", "hello"),
    ("simple_xml", "<user_request>查上海天气</user_request>"),
    ("xml_with_tool_hint", "<tools>[{\"name\":\"get_weather\"}]</tools>\n<user_request>查上海天气</user_request>\n请只输出一个 <tool_call>...</tool_call>"),
    ("minitest1","<tools>[{\"name\":\"get_weather\"}]</tools>\n<user_request>查上海天气</user_request>\n请只输出一个工具调用块"),
]

for name, prompt in tests:
    payload = {
        "model": MODEL,
        "stream": False,
        "prompt": prompt,
    }
    req = urllib.request.Request(
        f"{HOST}/api/generate",
        data=json.dumps(payload).encode("utf-8"),
        headers={"Content-Type": "application/json"},
        method="POST",
    )
    print(f"\n=== TEST: {name} ===")
    try:
        with urllib.request.urlopen(req, timeout=120) as resp:
            body = resp.read().decode("utf-8")
            print("HTTP", resp.status)
            print(body[:1000])
    except urllib.error.HTTPError as e:
        body = e.read().decode("utf-8", errors="replace")
        print("HTTPError", e.code)
        print(body)
    except Exception as e:
        print("Exception", repr(e))

---

hello

---

HTTP 200
{"model":"qwen3.5:9b","created_at":"2026-03-20T23:46:44.373588553Z","response":"Hello! 👋 How can I help you today?", ...}

---

<user_request>查上海天气</user_request>

---

HTTP 200
{"model":"qwen3.5:9b","created_at":"2026-03-20T23:47:08.663588206Z","response":"很抱歉，作为人工智能助手，我暂时无法直接获取实时的天气数据。...", ...}

---

<tools>[{"name":"get_weather"}]</tools>
<user_request>查上海天气</user_request>
请只输出一个 <tool_call>...</tool_call>

---

HTTPError 500
{"error":"EOF"}

---

<tools>[{"name":"get_weather"}]</tools>
<user_request>查上海天气</user_request>
请只输出一个工具调用块

---

HTTP 200
{"model":"qwen3.5:9b","created_at":"2026-03-20T23:47:56.226133671Z","response":"

---

### Expected behavior

The server should not return HTTP 500 / `{"error":"EOF"}` because the prompt contains `<tool_call>`-style XML text.

Even if Ollama or the model-side parser dislikes this format, the request should fail gracefully, for example by:

- returning raw model text, or
- returning a controlled parse error with a clear message

but not an internal server error.

### Actual behavior

When the prompt explicitly asks for `<tool_call>...</tool_call>` or `<tool_call></tool_call>`, `/api/generate` can fail with:

---

### Notes

This seems to be triggered specifically by the `<tool_call>` XML pattern in the prompt.

Important detail: this reproduction does **not** use native Ollama tools. The issue appears to happen even when these tags are just plain prompt text.

### Relevant log output