diff --git a/backend/python/common/mlx_utils.py b/backend/python/common/mlx_utils.py
index 6b34eb962..de624fd5b 100644
--- a/backend/python/common/mlx_utils.py
+++ b/backend/python/common/mlx_utils.py
@@ -20,7 +20,15 @@ def split_reasoning(text, think_start, think_end):
     Returns ``(reasoning_content, remaining_text)``. When ``think_start`` is
     empty or not found, returns ``("", text)`` unchanged.
     """
-    if not think_start or not text or think_start not in text:
+    if not think_start or not text:
+        return "", text
+    if think_start not in text:
+        # Models like Qwen3.5 open assistant turns already INSIDE thinking, so
+        # the generated text carries only the closing tag. Everything before it
+        # is reasoning that would otherwise leak into the content.
+        if think_end and think_end in text:
+            head, _, tail = text.partition(think_end)
+            return head.strip(), tail.strip()
         return "", text
     pattern = re.compile(
         re.escape(think_start) + r"(.*?)" + re.escape(think_end or ""),
diff --git a/backend/python/common/mlx_utils_test.py b/backend/python/common/mlx_utils_test.py
new file mode 100644
index 000000000..809354ede
--- /dev/null
+++ b/backend/python/common/mlx_utils_test.py
@@ -0,0 +1,75 @@
+"""Unit tests for the mlx/mlx-vlm shared helpers (mlx_utils.py).
+
+Run standalone (Python standard library only, no backend venv needed):
+    python3 -m unittest mlx_utils_test
+
+These mirror the server-less helper tests in backend/python/mlx/test.py
+(TestSharedHelpers), but live here so they run on any platform: the mlx
+test module imports grpc/backend_pb2 at import time and needs the MLX venv,
+whereas mlx_utils only needs the standard library.
+"""
+
+import types
+import unittest
+
+from mlx_utils import parse_tool_calls, split_reasoning
+
+
+class TestSplitReasoning(unittest.TestCase):
+    def test_both_tags(self):
+        r, c = split_reasoning(
+            "<think>step 1\nstep 2</think>The answer is 42.", "<think>", "</think>"
+        )
+        self.assertEqual(r, "step 1\nstep 2")
+        self.assertEqual(c, "The answer is 42.")
+
+    def test_implicit_opener_only_closing_tag(self):
+        # Qwen3.5 opens the assistant turn already inside thinking, so the
+        # output carries only the closing tag; everything before it is reasoning.
+        r, c = split_reasoning(
+            "The user is asking about the weather.\n</think>\n\nThe weather in Rome is sunny.",
+            "<think>",
+            "</think>",
+        )
+        self.assertEqual(r, "The user is asking about the weather.")
+        self.assertEqual(c, "The weather in Rome is sunny.")
+
+    def test_no_tags_at_all(self):
+        r, c = split_reasoning("just text", "<think>", "</think>")
+        self.assertEqual(r, "")
+        self.assertEqual(c, "just text")
+
+    def test_empty_think_end_and_no_opener_match(self):
+        # No think_end to anchor on, and the opener is absent → return unchanged.
+        r, c = split_reasoning("no opener here", "<think>", "")
+        self.assertEqual(r, "")
+        self.assertEqual(c, "no opener here")
+
+    def test_empty_text(self):
+        r, c = split_reasoning("", "<think>", "</think>")
+        self.assertEqual(r, "")
+        self.assertEqual(c, "")
+
+
+class TestParseToolCalls(unittest.TestCase):
+    def test_with_shim(self):
+        tm = types.SimpleNamespace(
+            tool_call_start="<tool_call>",
+            tool_call_end="</tool_call>",
+            parse_tool_call=lambda body, tools: {
+                "name": "get_weather",
+                "arguments": {"location": body.strip()},
+            },
+        )
+        calls, remaining = parse_tool_calls(
+            "Sure: <tool_call>Paris</tool_call>", tm, tools=None
+        )
+        self.assertEqual(len(calls), 1)
+        self.assertEqual(calls[0]["name"], "get_weather")
+        self.assertEqual(calls[0]["arguments"], '{"location": "Paris"}')
+        self.assertEqual(calls[0]["index"], 0)
+        self.assertNotIn("<tool_call>", remaining)
+
+
+if __name__ == "__main__":
+    unittest.main()
diff --git a/backend/python/common/python_utils.py b/backend/python/common/python_utils.py
index aa61ab578..c89813e2c 100644
--- a/backend/python/common/python_utils.py
+++ b/backend/python/common/python_utils.py
@@ -58,7 +58,18 @@ def messages_to_dicts(proto_messages):
             d["reasoning_content"] = msg.reasoning_content
         if msg.tool_calls:
             try:
-                d["tool_calls"] = json.loads(msg.tool_calls)
+                tool_calls = json.loads(msg.tool_calls)
+                # Chat templates (e.g. Qwen) iterate function.arguments as a
+                # mapping, but the OpenAI wire format carries it as a JSON
+                # string — decode it back so the template's .items() works.
+                for tc in tool_calls:
+                    fn = tc.get("function") if isinstance(tc, dict) else None
+                    if isinstance(fn, dict) and isinstance(fn.get("arguments"), str):
+                        try:
+                            fn["arguments"] = json.loads(fn["arguments"])
+                        except json.JSONDecodeError:
+                            pass
+                d["tool_calls"] = tool_calls
             except json.JSONDecodeError:
                 pass
         result.append(d)
diff --git a/backend/python/common/python_utils_test.py b/backend/python/common/python_utils_test.py
new file mode 100644
index 000000000..c395ce92d
--- /dev/null
+++ b/backend/python/common/python_utils_test.py
@@ -0,0 +1,122 @@
+"""Unit tests for the shared python backend helpers (python_utils.py).
+
+Run standalone (Python standard library only, no backend venv needed):
+    python3 -m unittest python_utils_test
+
+These mirror the server-less helper tests in backend/python/mlx/test.py
+(TestSharedHelpers), but live here so they run on any platform: the mlx
+test module imports grpc/backend_pb2 at import time and needs the MLX venv,
+whereas python_utils has no third-party dependency. Proto Message objects
+are faked with types.SimpleNamespace (real proto fields default to "").
+"""
+
+import json
+import types
+import unittest
+
+from python_utils import messages_to_dicts, parse_options
+
+
+def _msg(**fields):
+    """Fake a proto Message: every unset field is the empty string, as protobuf."""
+    defaults = {
+        "role": "",
+        "content": "",
+        "name": "",
+        "tool_call_id": "",
+        "reasoning_content": "",
+        "tool_calls": "",
+    }
+    defaults.update(fields)
+    return types.SimpleNamespace(**defaults)
+
+
+class TestParseOptions(unittest.TestCase):
+    def test_type_inference(self):
+        opts = parse_options(
+            ["temperature:0.7", "max_tokens:128", "trust:true", "name:hello", "no_colon_skipped"]
+        )
+        self.assertEqual(opts["temperature"], 0.7)
+        self.assertEqual(opts["max_tokens"], 128)
+        self.assertIs(opts["trust"], True)
+        self.assertEqual(opts["name"], "hello")
+        self.assertNotIn("no_colon_skipped", opts)
+
+
+class TestMessagesToDicts(unittest.TestCase):
+    def test_basic_fields(self):
+        out = messages_to_dicts(
+            [
+                _msg(role="user", content="hi"),
+                _msg(role="tool", content="42", tool_call_id="call_1", name="f"),
+            ]
+        )
+        self.assertEqual(out[0], {"role": "user", "content": "hi"})
+        self.assertEqual(out[1]["tool_call_id"], "call_1")
+        self.assertEqual(out[1]["name"], "f")
+
+    def test_tool_call_arguments_string_decoded_to_mapping(self):
+        # OpenAI wire format ships function.arguments as a JSON *string*; chat
+        # templates iterate it as a mapping, so it must come back as a dict.
+        out = messages_to_dicts(
+            [
+                _msg(
+                    role="assistant",
+                    tool_calls=json.dumps(
+                        [
+                            {
+                                "id": "call_1",
+                                "type": "function",
+                                "function": {
+                                    "name": "get_weather",
+                                    "arguments": '{"location": "Rome"}',
+                                },
+                            }
+                        ]
+                    ),
+                )
+            ]
+        )
+        args = out[0]["tool_calls"][0]["function"]["arguments"]
+        self.assertEqual(args, {"location": "Rome"})
+        self.assertEqual(dict(args.items()), {"location": "Rome"})
+
+    def test_tool_call_arguments_already_mapping_is_idempotent(self):
+        out = messages_to_dicts(
+            [
+                _msg(
+                    role="assistant",
+                    tool_calls=json.dumps(
+                        [{"function": {"name": "f", "arguments": {"a": 1}}}]
+                    ),
+                )
+            ]
+        )
+        self.assertEqual(out[0]["tool_calls"][0]["function"]["arguments"], {"a": 1})
+
+    def test_tool_call_arguments_invalid_json_left_as_string(self):
+        out = messages_to_dicts(
+            [
+                _msg(
+                    role="assistant",
+                    tool_calls=json.dumps(
+                        [{"function": {"name": "f", "arguments": "not-json"}}]
+                    ),
+                )
+            ]
+        )
+        self.assertEqual(out[0]["tool_calls"][0]["function"]["arguments"], "not-json")
+
+    def test_tool_call_without_function_key(self):
+        out = messages_to_dicts(
+            [_msg(role="assistant", tool_calls=json.dumps([{"id": "call_1"}]))]
+        )
+        self.assertEqual(out[0]["tool_calls"], [{"id": "call_1"}])
+
+    def test_tool_calls_invalid_json_dropped(self):
+        out = messages_to_dicts([_msg(role="assistant", tool_calls="{not json")])
+        self.assertNotIn("tool_calls", out[0])
+
+
+if __name__ == "__main__":
+    unittest.main()