From b6f38bc90cda8cbd264e98a1aec99116728bbc2f Mon Sep 17 00:00:00 2001
From: Alex Schapiro <bearsyankees@gmail.com>
Date: Wed, 14 Oct 2026 21:17:10 +0000
Subject: [PATCH] fix(models): treat NaN/Infinity tool-call arguments as
 malformed

---
 strix/config/tool_call_arguments.py        | 12 ++++++++++--
 tests/test_agent_factory_tool_arguments.py |  5 +++--
 tests/test_tool_call_arguments.py          | 18 ++++++++++++++++--
 3 files changed, 29 insertions(+), 6 deletions(-)

diff --git a/strix/config/tool_call_arguments.py b/strix/config/tool_call_arguments.py
index 9169dcdc..d7c2f8d9 100644
--- a/strix/config/tool_call_arguments.py
+++ b/strix/config/tool_call_arguments.py
@@ -22,6 +22,14 @@ from openai.types.responses import ResponseFunctionToolCall
 MALFORMED_ARGUMENTS_KEY = "malformed_arguments"
 
 
+def _reject_constant(name: str) -> Any:
+    raise ValueError(f"non-standard JSON constant {name}")
+
+
+def _loads_strict(text: str) -> Any:
+    return json.loads(text, parse_constant=_reject_constant)
+
+
 def describe_malformed_arguments(tool_name: str, arguments: str) -> str | None:
     """Return a model-facing recovery message if ``arguments`` is not a JSON object.
 
@@ -33,7 +41,7 @@ def describe_malformed_arguments(tool_name: str, arguments: str) -> str | None:
     if not arguments.strip():
         return None
     try:
-        parsed = json.loads(arguments)
+        parsed = _loads_strict(arguments)
     except ValueError as exc:
         detail = str(exc)
     else:
@@ -52,7 +60,7 @@ def repair_arguments(arguments: object) -> str | None:
     if not isinstance(arguments, str) or not arguments.strip():
         return "{}"
     try:
-        parsed = json.loads(arguments)
+        parsed = _loads_strict(arguments)
     except ValueError:
         parsed = None
     if isinstance(parsed, dict):
diff --git a/tests/test_agent_factory_tool_arguments.py b/tests/test_agent_factory_tool_arguments.py
index 4330ca4a..aa2efa85 100644
--- a/tests/test_agent_factory_tool_arguments.py
+++ b/tests/test_agent_factory_tool_arguments.py
@@ -150,11 +150,12 @@ async def test_unknown_and_null_arguments_are_untouched() -> None:
 
 
 @pytest.mark.asyncio
-async def test_non_object_payloads_are_reported_instead_of_invoked() -> None:
+@pytest.mark.parametrize("arguments", ["not json", '{"n": NaN}'])
+async def test_non_object_payloads_are_reported_instead_of_invoked(arguments: str) -> None:
     captured: dict[str, str] = {}
     wrapped = factory._with_coerced_arguments(_capturing_tool(captured, _ARRAY))
 
-    result = await wrapped.on_invoke_tool(cast("Any", None), "not json")
+    result = await wrapped.on_invoke_tool(cast("Any", None), arguments)
 
     assert result.startswith("probe: the tool call was not executed")
     assert "raw_input" not in captured
diff --git a/tests/test_tool_call_arguments.py b/tests/test_tool_call_arguments.py
index 55631a78..fb251c8f 100644
--- a/tests/test_tool_call_arguments.py
+++ b/tests/test_tool_call_arguments.py
@@ -25,6 +25,7 @@ from openai.types.responses import ResponseFunctionToolCall
 from strix.config.models import _NonStreamingModel, _TurnGuardModel
 from strix.config.tool_call_arguments import (
     MALFORMED_ARGUMENTS_KEY,
+    _loads_strict,
     describe_malformed_arguments,
     repair_arguments,
     repair_history_arguments,
@@ -213,11 +214,21 @@ def test_repair_arguments_rewrites_anything_but_a_json_object(
     assert repair_arguments(arguments) == expected
 
 
-@pytest.mark.parametrize("arguments", ["{}", '{"cmd": "ls -la"}', '{"nested": {"a": [1]}}'])
+@pytest.mark.parametrize(
+    "arguments", ["{}", '{"cmd": "ls -la"}', '{"nested": {"a": [1]}}', '{"n": "NaN"}']
+)
 def test_repair_arguments_leaves_json_objects_alone(arguments: str) -> None:
     assert repair_arguments(arguments) is None
 
 
+@pytest.mark.parametrize("arguments", ['{"n": NaN}', '{"n": Infinity}', '{"n": -Infinity}'])
+def test_repair_arguments_wraps_non_standard_json_constants(arguments: str) -> None:
+    repaired = repair_arguments(arguments)
+
+    assert repaired is not None
+    assert _loads_strict(repaired) == {MALFORMED_ARGUMENTS_KEY: arguments}
+
+
 def test_history_repair_rewrites_only_malformed_calls() -> None:
     items = [
         {"role": "user", "content": "go"},
@@ -237,6 +248,7 @@ def test_history_repair_rewrites_only_malformed_calls() -> None:
     assert rebuilt[3] is items[3]
     assert isinstance(rebuilt[4], ResponseFunctionToolCall)
     assert rebuilt[4].arguments == "{}"
+    assert isinstance(items[1], dict)
     assert items[1]["arguments"] == '{"cmd": "ls'
 
 
@@ -247,7 +259,9 @@ def test_repair_input_returns_same_object_when_nothing_changes() -> None:
     assert repair_input("plain prompt") == "plain prompt"
 
 
-@pytest.mark.parametrize("arguments", ['{"cmd": "ls -la', "[1, 2]", "null", "not json"])
+@pytest.mark.parametrize(
+    "arguments", ['{"cmd": "ls -la', "[1, 2]", "null", "not json", '{"n": NaN}']
+)
 def test_describe_malformed_arguments_tells_the_model_to_reissue(arguments: str) -> None:
     message = describe_malformed_arguments("exec_command", arguments)