mirror of
https://github.com/usestrix/strix.git
synced 2026-08-17 01:29:42 +02:00
Ahmed AllamandAhmed Allam
a70a87f272
Cap the size of every tool result so a single verbose command (recursive find, noisy scanner, full page dump) can't pin the conversation near the model's context window for the rest of a scan. - New ContextSettings config group with env-tunable caps. - Default the SDK shell tools' max_output_tokens so exec_command / write_stdin truncate head+tail instead of returning unbounded output. - Bound Strix's own FunctionTool/CustomTool results (line + UTF-8 byte head+tail preview with a truncation notice) and cap error strings.
66 lines
2.0 KiB
Python
66 lines
2.0 KiB
Python
"""Tests for the shell tool adapters in the agent factory."""
|
|
|
|
from __future__ import annotations
|
|
|
|
import json
|
|
from typing import Any, cast
|
|
|
|
import pytest
|
|
from agents.tool import FunctionTool
|
|
|
|
from strix.agents import factory
|
|
from strix.config import load_settings
|
|
|
|
|
|
def _capturing_exec_tool(captured: dict[str, str]) -> FunctionTool:
|
|
async def invoke(_ctx: Any, raw_input: str) -> str:
|
|
captured["raw_input"] = raw_input
|
|
return "ok"
|
|
|
|
return FunctionTool(
|
|
name="exec_command",
|
|
description="test tool",
|
|
params_json_schema={"type": "object", "properties": {}},
|
|
on_invoke_tool=invoke,
|
|
)
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_wrap_exec_command_defaults_shell_to_bash() -> None:
|
|
captured: dict[str, str] = {}
|
|
wrapped = factory._wrap_exec_command(_capturing_exec_tool(captured))
|
|
|
|
result = await wrapped.on_invoke_tool(cast("Any", None), json.dumps({"cmd": "source /tmp/env"}))
|
|
|
|
assert result == "ok"
|
|
parsed = json.loads(captured["raw_input"])
|
|
assert parsed["cmd"] == "source /tmp/env"
|
|
assert parsed["shell"] == "bash"
|
|
expected_cap = load_settings().context.tool_output_max_tokens
|
|
assert parsed["max_output_tokens"] == expected_cap
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_wrap_exec_command_preserves_explicit_output_cap() -> None:
|
|
captured: dict[str, str] = {}
|
|
wrapped = factory._wrap_exec_command(_capturing_exec_tool(captured))
|
|
|
|
await wrapped.on_invoke_tool(
|
|
cast("Any", None), json.dumps({"cmd": "echo hi", "max_output_tokens": 42})
|
|
)
|
|
|
|
assert json.loads(captured["raw_input"])["max_output_tokens"] == 42
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
@pytest.mark.parametrize("shell", ["/bin/zsh", ""])
|
|
async def test_wrap_exec_command_preserves_explicit_shell(shell: str) -> None:
|
|
captured: dict[str, str] = {}
|
|
wrapped = factory._wrap_exec_command(_capturing_exec_tool(captured))
|
|
|
|
await wrapped.on_invoke_tool(
|
|
cast("Any", None), json.dumps({"cmd": "echo test", "shell": shell})
|
|
)
|
|
|
|
assert json.loads(captured["raw_input"])["shell"] == shell
|