From 6bda36606537e1fcad561ed8100f7c5e4c3d9017 Mon Sep 17 00:00:00 2001
From: Ahmed Allam <ahmed39652003@gmail.com>
Date: Sat, 25 Jul 2026 22:50:50 +0000
Subject: [PATCH] fix(context): bound native filesystem tool output in
 Responses mode

Chat-completions mode converts filesystem CustomTools to FunctionTools
(which bounds their result), but the Responses-API path kept them native
and unbounded, so a large read_file could still exhaust the context
window. Always configure the Filesystem capability to head+tail bound
tool output in both modes.
---
 strix/agents/factory.py           | 43 ++++++++++++++++++++++++++-----
 tests/test_agent_factory_shell.py | 35 ++++++++++++++++++++++++-
 2 files changed, 71 insertions(+), 7 deletions(-)

diff --git a/strix/agents/factory.py b/strix/agents/factory.py
index ea80fb61..d6b36722 100644
--- a/strix/agents/factory.py
+++ b/strix/agents/factory.py
@@ -199,12 +199,43 @@ def _custom_tool_as_function_tool(tool: CustomTool) -> FunctionTool:
     )
 
 
-def _configure_chat_completions_filesystem_tools(toolset: Any) -> None:
+def _bound_custom_tool(tool: CustomTool) -> CustomTool:
+    """Bound a native ``CustomTool`` result in place.
+
+    Chat-completions mode converts filesystem ``CustomTool``s to ``FunctionTool``s
+    (which bounds the result), but the Responses path keeps them native, so a
+    large ``read_file``/directory listing would otherwise append unbounded text
+    to history. Wrap ``on_invoke_tool`` so the same head+tail bound applies.
+    """
+    invoke_tool = tool.on_invoke_tool
+
+    async def invoke(ctx: Any, raw_input: str) -> Any:
+        return _bound_result(await invoke_tool(ctx, raw_input))
+
+    tool.on_invoke_tool = invoke
+    return tool
+
+
+def _configure_filesystem_tools(toolset: Any, *, chat_completions: bool) -> None:
     for name, tool in vars(toolset).items():
-        if isinstance(tool, CustomTool):
-            setattr(toolset, name, _custom_tool_as_function_tool(tool))
+        if chat_completions:
+            if isinstance(tool, CustomTool):
+                setattr(toolset, name, _custom_tool_as_function_tool(tool))
+            elif isinstance(tool, FunctionTool):
+                setattr(toolset, name, _function_tool_with_error_result(tool))
+        # Responses-API path: keep tools native but still bound their output so
+        # filesystem reads can't exhaust the context window on later turns.
+        elif isinstance(tool, CustomTool):
+            setattr(toolset, name, _bound_custom_tool(tool))
         elif isinstance(tool, FunctionTool):
-            setattr(toolset, name, _function_tool_with_error_result(tool))
+            setattr(toolset, name, _with_bounded_result(tool))
+
+
+def _make_filesystem_configurator(*, chat_completions: bool) -> Any:
+    def configure(toolset: Any) -> None:
+        _configure_filesystem_tools(toolset, chat_completions=chat_completions)
+
+    return configure
 
 
 _CHARS_ESCAPE_RE = re.compile(r"\\(?:u[0-9a-fA-F]{4}|x[0-9a-fA-F]{2}|[0abtnvfr\\])")
@@ -523,8 +554,8 @@ def build_strix_agent(
         model=None,
         capabilities=[
             Filesystem(
-                configure_tools=(
-                    _configure_chat_completions_filesystem_tools if chat_completions_tools else None
+                configure_tools=_make_filesystem_configurator(
+                    chat_completions=chat_completions_tools,
                 ),
             ),
             Shell(
diff --git a/tests/test_agent_factory_shell.py b/tests/test_agent_factory_shell.py
index 7165378c..22b662c7 100644
--- a/tests/test_agent_factory_shell.py
+++ b/tests/test_agent_factory_shell.py
@@ -3,10 +3,11 @@
 from __future__ import annotations
 
 import json
+from types import SimpleNamespace
 from typing import Any, cast
 
 import pytest
-from agents.tool import FunctionTool
+from agents.tool import CustomTool, FunctionTool
 
 from strix.agents import factory
 from strix.config import load_settings
@@ -77,3 +78,35 @@ async def test_wrap_exec_command_preserves_explicit_shell(shell: str) -> None:
     )
 
     assert json.loads(captured["raw_input"])["shell"] == shell
+
+
+@pytest.mark.asyncio
+async def test_responses_filesystem_custom_tool_output_is_bounded() -> None:
+    # In Responses-API mode filesystem tools stay native CustomTools; a large
+    # read must still be head+tail bounded before it enters history.
+    async def invoke(_ctx: Any, _inp: str) -> str:
+        return "line\n" * 50_000
+
+    toolset = SimpleNamespace(
+        read_file=CustomTool(name="read_file", description="read", on_invoke_tool=invoke)
+    )
+    factory._configure_filesystem_tools(toolset, chat_completions=False)
+
+    assert isinstance(toolset.read_file, CustomTool)
+    result = await toolset.read_file.on_invoke_tool(cast("Any", None), "{}")
+
+    assert "truncated" in result
+    assert len(result) < len("line\n" * 50_000)
+
+
+@pytest.mark.asyncio
+async def test_chat_completions_filesystem_custom_tool_becomes_function_tool() -> None:
+    async def invoke(_ctx: Any, _inp: str) -> str:
+        return "ok"
+
+    toolset = SimpleNamespace(
+        read_file=CustomTool(name="read_file", description="read", on_invoke_tool=invoke)
+    )
+    factory._configure_filesystem_tools(toolset, chat_completions=True)
+
+    assert isinstance(toolset.read_file, FunctionTool)