Fix OpenAI tool history replay

app.py

@@ -36,7 +36,11 @@ from transformers import (
     StoppingCriteria,
     StoppingCriteriaList,
 )
-from tool_calls import extract_tool_call, has_complete_tool_call
+from tool_calls import (
+    extract_tool_call,
+    has_complete_tool_call,
+    normalize_openai_tool_arguments,
+)
 
 
 # Qwen3-Coder-30B-A3B is the strongest coding-specialized Qwen checkpoint that
@@ -266,7 +270,9 @@ def _normalized_tool_calls(raw_calls: object) -> list[dict[str, Any]]:
             "type": "function",
             "function": {
                 "name": name,
-                "arguments": function.get("arguments", "{}"),
+                "arguments": normalize_openai_tool_arguments(
+                    function.get("arguments", {})
+                ),
             },
         }
         if isinstance(raw_call.get("id"), str) and raw_call["id"]:

test_tool_calls.py

@@ -5,7 +5,11 @@ from __future__ import annotations
 import json
 import unittest
 
-from tool_calls import extract_tool_call, has_complete_tool_call
+from tool_calls import (
+    extract_tool_call,
+    has_complete_tool_call,
+    normalize_openai_tool_arguments,
+)
 
 
 ALLOWED = {"Bash", "Read"}
@@ -88,6 +92,17 @@ class ToolCallTests(unittest.TestCase):
         self.assertIsNone(call)
         self.assertIn("Delete", visible)
 
+    def test_openai_history_arguments_are_mappings_for_qwen_template(self) -> None:
+        self.assertEqual(
+            normalize_openai_tool_arguments('{"command":"pwd"}'),
+            {"command": "pwd"},
+        )
+        self.assertEqual(
+            normalize_openai_tool_arguments({"file_path": "/tmp/a.txt"}),
+            {"file_path": "/tmp/a.txt"},
+        )
+        self.assertEqual(normalize_openai_tool_arguments("not-json"), {})
+
 
 if __name__ == "__main__":
     unittest.main()

tool_calls.py

@@ -147,6 +147,18 @@ def _arguments(value: Any) -> dict[str, Any] | None:
     return dict(parsed) if isinstance(parsed, Mapping) else None
 
 
+def normalize_openai_tool_arguments(value: Any) -> dict[str, Any]:
+    """Return the mapping required by Qwen3's chat-template ``items`` filter.
+
+    OpenAI serializes function arguments as a JSON string, while Qwen3's
+    official template iterates them as a mapping when replaying tool history.
+    Accept both representations so a completed tool call can be followed by a
+    tool result without raising a template ``TypeError``.
+    """
+    parsed = _arguments(value)
+    return parsed if parsed is not None else {}
+
+
 def _openai_call(
     name: Any,
     arguments: Any,