feat(safety): add contextual action review with guarded and observe modes

Introduce a pre-execution safety layer that reviews effectful agent actions
against compiled, frozen evidence before they run.

`--safety-mode guarded` allows non-destructive interaction after review;
`--safety-mode observe` permits passive target interaction only. `off` stays
the default, so existing runs are unchanged.

Deterministic rules decide what they can on their own: destructive commands,
code-loading environment overrides, blocked browser actions, and mutating
requests in observe mode are refused without a model call, and a small set of
read-only commands is allowed outright. Everything else compiles an evidence
packet — command, scope, script source and its local import closure, prior
tool-call evidence, and browser snapshot context — for a bounded reviewer that
may make one isolated inspection call. Incomplete evidence fails closed.

In safety modes, user-owned local directories are copied into the run
directory so the originals are never mounted writable, while `.git`,
`.agents`, and `.codex` inside the copy stay read-only.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
This commit is contained in:
oyasumi
2026-08-08 00:47:21 +00:00
co-authored by Claude Opus 5
parent f8a8801d56
commit 6e5bb2e76e
40 changed files with 3860 additions and 35 deletions
+72 -1
View File
@@ -4,13 +4,19 @@ from __future__ import annotations
import json
from types import SimpleNamespace
from typing import Any, cast
from typing import TYPE_CHECKING, Any, cast
import pytest
from agents.tool import CustomTool, FunctionTool
from strix.agents import factory
from strix.config import load_settings
from strix.config.settings import SafetySettings
from strix.safety.runtime import SafetyRuntime
if TYPE_CHECKING:
from pathlib import Path
def _capturing_exec_tool(captured: dict[str, str]) -> FunctionTool:
@@ -115,3 +121,68 @@ def test_function_tools_are_result_bounded() -> None:
by_name = {t.name: t for t in agent.tools}
assert getattr(by_name["think"], "_strix_bounded", False) is True
def _capturing_stdin_tool(captured: dict[str, str]) -> FunctionTool:
async def invoke(_ctx: Any, raw_input: str) -> str:
captured["raw_input"] = raw_input
return "typed"
return FunctionTool(
name="write_stdin",
description="test tool",
params_json_schema={"type": "object", "properties": {}},
on_invoke_tool=invoke,
)
class _InspectionRunner:
async def run(self, *, evidence_dir: str, script: str) -> str:
return f"unused: {evidence_dir} {script}"
def _guarded_runtime(tmp_path: Path) -> SafetyRuntime:
return SafetyRuntime(
scan_id="scan-1",
mode="guarded",
scope={},
user_instruction="",
settings=SafetySettings(),
run_dir=tmp_path,
sandbox_image="image",
inspection_runner=_InspectionRunner(),
)
@pytest.mark.asyncio
async def test_write_stdin_is_routed_through_the_safety_runtime(tmp_path: Path) -> None:
captured: dict[str, str] = {}
wrapped = factory._wrap_write_stdin(_capturing_stdin_tool(captured))
ctx = SimpleNamespace(
context={"safety_runtime": _guarded_runtime(tmp_path), "agent_id": "agent-1"},
tool_call_id="call-1",
)
result = await wrapped.on_invoke_tool(
cast("Any", ctx),
json.dumps({"session_id": "s", "chars": "rm -rf /workspace\\n"}),
)
payload = json.loads(result)
assert payload["status"] == "blocked"
assert "write_stdin is blocked" in payload["safety"]["reason"]
assert captured == {}
@pytest.mark.asyncio
async def test_write_stdin_runs_directly_without_a_safety_runtime() -> None:
captured: dict[str, str] = {}
wrapped = factory._wrap_write_stdin(_capturing_stdin_tool(captured))
ctx = SimpleNamespace(context={}, tool_call_id="call-1")
result = await wrapped.on_invoke_tool(
cast("Any", ctx), json.dumps({"session_id": "s", "chars": "y\\n"})
)
assert result == "typed"
assert json.loads(captured["raw_input"])["chars"] == "y\n"
+27
View File
@@ -33,6 +33,10 @@ _LLM_ENV_KEYS = [
# RuntimeSettings
"STRIX_IMAGE",
"STRIX_RUNTIME_BACKEND",
# SafetySettings
"STRIX_SAFETY_MODE",
"STRIX_SAFETY_MODEL",
"STRIX_SAFETY_TIMEOUT",
# TelemetrySettings
"STRIX_TELEMETRY",
]
@@ -177,6 +181,29 @@ def test_apply_override_and_load_settings_round_trip(tmp_path: Path) -> None:
assert loader.load_settings() is settings
def test_safety_settings_load_from_config(tmp_path: Path) -> None:
path = tmp_path / "cli-config.json"
path.write_text(
json.dumps(
{
"env": {
"STRIX_SAFETY_MODE": "guarded",
"STRIX_SAFETY_MODEL": "openai/safety-model",
"STRIX_SAFETY_TIMEOUT": "12",
}
}
),
encoding="utf-8",
)
loader.apply_config_override(path)
settings = loader.load_settings().safety
assert settings.mode == "guarded"
assert settings.model == "openai/safety-model"
assert settings.timeout == 12
def test_apply_config_override_invalidates_cache(tmp_path: Path) -> None:
first = tmp_path / "first.json"
first.write_text(json.dumps({"env": {"STRIX_LLM": "first-model"}}), encoding="utf-8")
+539
View File
@@ -0,0 +1,539 @@
"""Deterministic safety evidence compilation."""
from __future__ import annotations
import io
from types import SimpleNamespace
from typing import TYPE_CHECKING, Any
import pytest
from strix.config.settings import SafetySettings
from strix.safety.evidence import compile_evidence, parse_command
if TYPE_CHECKING:
from pathlib import Path
# Marks a path that exists but cannot be read, which must not look like an absent module.
_UNREADABLE = "<unreadable>"
class _Sandbox:
def __init__(self, files: dict[str, str]) -> None:
self.files = files
async def read(self, path: Path) -> io.BytesIO:
key = path.as_posix()
if key not in self.files:
raise FileNotFoundError(key)
if self.files[key] == _UNREADABLE:
raise PermissionError(key)
return io.BytesIO(self.files[key].encode())
def _ctx(files: dict[str, str], *, turn_input: list[Any] | None = None) -> Any:
return SimpleNamespace(
context={"agent_id": "agent-1", "sandbox_session": _Sandbox(files)},
tool_call_id="call-1",
turn_input=turn_input or [],
)
async def _compile(
command: str,
files: dict[str, str] | None = None,
*,
turn_input: list[Any] | None = None,
workdir: str | None = None,
mode: str = "guarded",
) -> Any:
arguments: dict[str, Any] = {"cmd": command}
if workdir is not None:
arguments["workdir"] = workdir
return await compile_evidence(
case_id="case",
ctx=_ctx(files or {}, turn_input=turn_input),
arguments=arguments,
mode=mode,
scope={},
user_instruction="",
settings=SafetySettings(),
)
def test_parse_command_identifies_direct_browser_action() -> None:
plan = parse_command("agent-browser click @e3")
assert plan.browser is True
assert plan.browser_action == "click"
assert plan.compound is False
def test_parse_command_marks_browser_chaining_compound() -> None:
plan = parse_command("agent-browser click @e3 && agent-browser snapshot -i")
assert plan.browser is True
assert plan.compound is True
@pytest.mark.asyncio
async def test_python_script_collects_local_dependency_source() -> None:
bundle = await compile_evidence(
case_id="case-1",
ctx=_ctx(
{
"/workspace/check.py": "from helper import target\nprint(target)\n",
"/workspace/helper.py": 'target = "https://example.test/health"\n',
}
),
arguments={"cmd": "python /workspace/check.py"},
mode="guarded",
scope={"authorized_targets": [{"value": "https://example.test"}]},
user_instruction="Inspect the test target.",
settings=SafetySettings(),
)
try:
paths = {item["path"] for item in bundle.packet["artifacts"]}
assert paths == {"/workspace/check.py", "/workspace/helper.py"}
assert bundle.complete is True
assert bundle.deterministic_block is None
finally:
bundle.cleanup()
@pytest.mark.asyncio
async def test_browser_automation_inside_script_is_blocked() -> None:
bundle = await compile_evidence(
case_id="case-2",
ctx=_ctx(
{
"/workspace/browser.py": (
'import subprocess\nsubprocess.run(["agent-browser", "click", "@e3"])\n'
)
}
),
arguments={"cmd": "python /workspace/browser.py"},
mode="guarded",
scope={},
user_instruction="",
settings=SafetySettings(),
)
try:
assert bundle.deterministic_block is not None
assert "direct agent-browser commands" in bundle.deterministic_block
finally:
bundle.cleanup()
@pytest.mark.asyncio
async def test_browser_library_import_inside_script_is_blocked() -> None:
bundle = await compile_evidence(
case_id="case-browser-import",
ctx=_ctx({"/workspace/browser.py": "from playwright.async_api import Browser\n"}),
arguments={"cmd": "python /workspace/browser.py"},
mode="guarded",
scope={},
user_instruction="",
settings=SafetySettings(),
)
try:
assert bundle.deterministic_block is not None
assert "direct agent-browser commands" in bundle.deterministic_block
finally:
bundle.cleanup()
@pytest.mark.asyncio
async def test_dynamic_exec_makes_script_evidence_incomplete() -> None:
bundle = await compile_evidence(
case_id="case-3",
ctx=_ctx({"/workspace/dynamic.py": "exec(input())\n"}),
arguments={"cmd": "python /workspace/dynamic.py"},
mode="guarded",
scope={},
user_instruction="",
settings=SafetySettings(),
)
try:
assert bundle.complete is False
assert any("exec" in reason for reason in bundle.incomplete_reasons)
finally:
bundle.cleanup()
@pytest.mark.asyncio
async def test_dynamic_network_destination_is_incomplete() -> None:
bundle = await compile_evidence(
case_id="case-dynamic-network",
ctx=_ctx(
{"/workspace/network.py": ("import requests\nimport sys\nrequests.get(sys.argv[1])\n")}
),
arguments={"cmd": "python /workspace/network.py https://example.test"},
mode="guarded",
scope={},
user_instruction="",
settings=SafetySettings(),
)
try:
assert bundle.complete is False
assert any("dynamic network destination" in item for item in bundle.incomplete_reasons)
finally:
bundle.cleanup()
@pytest.mark.asyncio
async def test_creation_and_execution_chain_must_be_split() -> None:
bundle = await compile_evidence(
case_id="case-chain",
ctx=_ctx({}),
arguments={"cmd": "curl https://example.test/x.py -o x.py && python x.py"},
mode="guarded",
scope={},
user_instruction="",
settings=SafetySettings(),
)
try:
assert bundle.deterministic_block is not None
assert "split" in bundle.deterministic_block
finally:
bundle.cleanup()
@pytest.mark.asyncio
async def test_browser_ref_requires_prior_snapshot() -> None:
bundle = await compile_evidence(
case_id="case-4",
ctx=_ctx({}),
arguments={"cmd": "agent-browser click @e3"},
mode="guarded",
scope={},
user_instruction="",
settings=SafetySettings(),
)
try:
assert bundle.complete is False
assert "prior snapshot" in bundle.incomplete_reasons[0]
finally:
bundle.cleanup()
@pytest.mark.asyncio
async def test_browser_ref_uses_prior_snapshot_output() -> None:
history = [
{
"type": "function_call",
"name": "exec_command",
"call_id": "snapshot-1",
"arguments": '{"cmd":"agent-browser snapshot -i"}',
},
{
"type": "function_call_output",
"call_id": "snapshot-1",
"output": '@e3 [button type="submit"] "Search"',
},
]
bundle = await compile_evidence(
case_id="case-5",
ctx=_ctx({}, turn_input=history),
arguments={"cmd": "agent-browser click @e3"},
mode="guarded",
scope={},
user_instruction="",
settings=SafetySettings(),
)
try:
assert bundle.complete is True
assert bundle.packet["browser"]["latest_snapshot"]["call_id"] == "snapshot-1"
finally:
bundle.cleanup()
@pytest.mark.parametrize(
"command",
[
"ls -la\nrm -rf /workspace/app",
"ls & rm -rf /workspace/app",
"ls -la; rm -rf /workspace/app",
],
)
def test_separators_beyond_double_operators_are_compound(command: str) -> None:
plan = parse_command(command)
assert plan.compound is True
assert plan.read_only is False
@pytest.mark.asyncio
@pytest.mark.parametrize(
"command",
["ls -la\nrm -rf /workspace/app", "ls & rm -rf /workspace/app"],
)
async def test_destructive_command_chained_to_a_read_command_is_blocked(command: str) -> None:
bundle = await _compile(command)
try:
assert bundle.deterministic_allow is None
assert bundle.deterministic_block is not None
assert "destructive" in bundle.deterministic_block
finally:
bundle.cleanup()
def test_quoted_separator_is_not_compound() -> None:
assert parse_command("curl 'https://example.test/?a=1&b=2'").compound is False
assert parse_command('agent-browser open "https://example.test/?a=1&b=2"').compound is False
def test_read_only_fast_path_inspects_options() -> None:
assert parse_command("rg -n --json needle /workspace").read_only is True
assert parse_command("ls -la /workspace").read_only is True
# `--pre` hands ripgrep an arbitrary program to run on every matched file.
assert parse_command("rg --pre /workspace/payload.sh -e . /workspace").read_only is False
assert parse_command("rg --search-zip needle /workspace").read_only is False
assert parse_command("file -C -m /workspace/magic /workspace/x").read_only is False
@pytest.mark.asyncio
async def test_inline_python_source_collects_local_dependencies() -> None:
bundle = await _compile(
'python -c "import wipe; wipe.go()"',
{"/workspace/wipe.py": "import shutil\n\n\ndef go():\n shutil.rmtree('/workspace')\n"},
workdir="/workspace",
)
try:
artifacts = bundle.packet["artifacts"]
assert [item["path"] for item in artifacts] == ["<inline>", "/workspace/wipe.py"]
dependency = bundle.root / artifacts[1]["evidence_path"]
assert "shutil.rmtree" in dependency.read_text(encoding="utf-8")
finally:
bundle.cleanup()
@pytest.mark.asyncio
async def test_inline_python_dynamic_feature_is_incomplete() -> None:
bundle = await _compile('python -c "exec(input())"', workdir="/workspace")
try:
assert bundle.complete is False
assert any("exec" in reason for reason in bundle.incomplete_reasons)
finally:
bundle.cleanup()
@pytest.mark.asyncio
async def test_relative_imports_are_collected() -> None:
bundle = await _compile(
"python /workspace/main.py",
{
"/workspace/main.py": "import pkg.mod\n",
"/workspace/pkg/__init__.py": "",
"/workspace/pkg/mod.py": "from . import payload\nfrom ..sibling import helper\n",
"/workspace/pkg/payload.py": "import shutil\nshutil.rmtree('/workspace/app')\n",
"/workspace/sibling.py": "helper = 1\n",
},
)
try:
paths = {item["path"] for item in bundle.packet["artifacts"]}
assert "/workspace/pkg/payload.py" in paths
assert "/workspace/sibling.py" in paths
finally:
bundle.cleanup()
@pytest.mark.asyncio
async def test_import_path_mutation_makes_evidence_incomplete() -> None:
bundle = await _compile(
"python /workspace/run.py",
{
"/workspace/run.py": (
"import sys\nsys.path.insert(0, '/workspace/lib')\nimport payload\npayload.main()\n"
)
},
)
try:
assert bundle.complete is False
assert any("search path" in reason for reason in bundle.incomplete_reasons)
finally:
bundle.cleanup()
@pytest.mark.asyncio
async def test_unreadable_local_module_is_reported() -> None:
bundle = await _compile(
"python /workspace/run.py",
{"/workspace/run.py": "import payload\n", "/workspace/payload.py": _UNREADABLE},
)
try:
assert bundle.complete is False
assert any("cannot read local module" in reason for reason in bundle.incomplete_reasons)
finally:
bundle.cleanup()
@pytest.mark.asyncio
async def test_interpreter_environment_override_is_blocked() -> None:
bundle = await _compile("PYTHONPATH=/workspace/lib python /workspace/run.py")
try:
assert bundle.deterministic_block is not None
assert "PYTHONPATH" in bundle.deterministic_block
finally:
bundle.cleanup()
@pytest.mark.asyncio
async def test_parent_traversal_leaves_the_workspace() -> None:
bundle = await _compile("python ../../opt/staged/run.py", workdir="/workspace")
try:
assert bundle.complete is False
assert "outside the inspectable workspace" in bundle.incomplete_reasons[0]
finally:
bundle.cleanup()
def test_env_wrapper_resolves_the_real_executable() -> None:
plan = parse_command("/usr/bin/env agent-browser click @e5")
assert plan.browser is True
assert plan.browser_action == "click"
def test_opaque_wrapper_fails_closed() -> None:
assert parse_command("timeout 5 rm -rf /workspace").parse_error is not None
@pytest.mark.asyncio
async def test_browser_session_env_override_is_blocked() -> None:
bundle = await _compile("AGENT_BROWSER_SESSION=shared agent-browser click @e3")
try:
assert bundle.deterministic_block is not None
assert "AGENT_BROWSER_SESSION" in bundle.deterministic_block
finally:
bundle.cleanup()
@pytest.mark.asyncio
async def test_unknown_browser_option_cannot_mask_the_action() -> None:
bundle = await _compile("agent-browser --timeout 5000 eval \"fetch('/x')\"")
try:
assert bundle.packet["pending_action"]["browser_action"] == "eval"
assert bundle.deterministic_block is not None
assert "eval" in bundle.deterministic_block
finally:
bundle.cleanup()
@pytest.mark.asyncio
async def test_unparseable_browser_option_fails_closed() -> None:
bundle = await _compile("agent-browser --unknown-flag value click @e3")
try:
assert bundle.complete is False
assert any("unrecognized" in reason for reason in bundle.incomplete_reasons)
finally:
bundle.cleanup()
@pytest.mark.asyncio
async def test_attached_browser_session_override_is_blocked() -> None:
bundle = await _compile("agent-browser --session=evil click @e3")
try:
assert bundle.deterministic_block is not None
assert "overrides are blocked" in bundle.deterministic_block
finally:
bundle.cleanup()
@pytest.mark.asyncio
async def test_snapshot_taken_before_a_navigation_is_stale() -> None:
history = [
{
"type": "function_call",
"name": "exec_command",
"call_id": "snapshot-1",
"arguments": '{"cmd":"agent-browser snapshot -i"}',
},
{
"type": "function_call_output",
"call_id": "snapshot-1",
"output": '@e3 [button] "Search"',
},
{
"type": "function_call",
"name": "exec_command",
"call_id": "navigate-1",
"arguments": '{"cmd":"agent-browser navigate https://example.test/admin"}',
},
{"type": "function_call_output", "call_id": "navigate-1", "output": "ok"},
]
bundle = await _compile("agent-browser click @e3", turn_input=history)
try:
assert bundle.complete is False
assert any("predates" in reason for reason in bundle.incomplete_reasons)
finally:
bundle.cleanup()
@pytest.mark.asyncio
async def test_reading_the_page_does_not_stale_a_snapshot() -> None:
history = [
{
"type": "function_call",
"name": "exec_command",
"call_id": "snapshot-1",
"arguments": '{"cmd":"agent-browser snapshot -i"}',
},
{
"type": "function_call_output",
"call_id": "snapshot-1",
"output": '@e3 [button] "Search"',
},
{
"type": "function_call",
"name": "exec_command",
"call_id": "get-1",
"arguments": '{"cmd":"agent-browser get text @e3"}',
},
{"type": "function_call_output", "call_id": "get-1", "output": "Search"},
]
bundle = await _compile("agent-browser click @e3", turn_input=history)
try:
assert bundle.complete is True
assert bundle.packet["browser"]["latest_snapshot"]["stale"] is False
finally:
bundle.cleanup()
@pytest.mark.asyncio
async def test_dependency_closure_may_exceed_one_file_limit() -> None:
settings = SafetySettings()
filler = "#" * (settings.max_artifact_bytes - 64)
bundle = await _compile(
"python /workspace/run.py",
{
"/workspace/run.py": f"import first\nimport second\n{filler}",
"/workspace/first.py": filler,
"/workspace/second.py": filler,
},
)
try:
assert bundle.complete is True
assert len(bundle.packet["artifacts"]) == 3
finally:
bundle.cleanup()
@pytest.mark.parametrize(
("command", "expected"),
[
("curl -X DELETE https://example.test/users/1", "DELETE"),
("curl --request PUT https://example.test/users/1", "PUT"),
("curl -d payload https://example.test/users", "-d"),
("wget --post-data=x https://example.test/users", "--post-data"),
],
)
def test_mutating_http_requests_are_recognized(command: str, expected: str) -> None:
assert expected in (parse_command(command).mutating_request or "")
def test_passive_http_requests_are_not_flagged() -> None:
assert parse_command("curl https://example.test/users").mutating_request is None
assert parse_command("curl -X GET https://example.test/users").mutating_request is None
+184
View File
@@ -0,0 +1,184 @@
"""The safety model may decide immediately or use one inspection call."""
from __future__ import annotations
import json
from pathlib import Path
from types import SimpleNamespace
from typing import TYPE_CHECKING, Any
import pytest
from agents.tool_context import ToolContext
import strix.safety.reviewer as reviewer_module
from strix.config.settings import SafetySettings
from strix.safety.evidence import EvidenceBundle
from strix.safety.reviewer import SafetyReviewer, run_inspection
from strix.safety.types import InspectionContext, SafetyVerdict
if TYPE_CHECKING:
from pytest import MonkeyPatch
class _InspectionRunner:
def __init__(self) -> None:
self.calls = 0
async def run(self, *, evidence_dir: str, script: str) -> str:
self.calls += 1
return f"inspected {Path(evidence_dir).name}: {script}"
class _Result:
def __init__(self, verdict: SafetyVerdict) -> None:
self._verdict = verdict
self.context_wrapper = SimpleNamespace(usage=SimpleNamespace())
def final_output_as(self, _cls: type[Any], *, raise_if_incorrect_type: bool) -> SafetyVerdict:
assert raise_if_incorrect_type is True
return self._verdict
def _settings() -> Any:
return SimpleNamespace(
safety=SafetySettings(model="test-model"),
llm=SimpleNamespace(
model="main-model",
extra_headers=None,
),
)
@pytest.mark.asyncio
async def test_reviewer_is_capped_at_two_turns_and_zero_retries(
tmp_path: Path,
monkeypatch: MonkeyPatch,
) -> None:
captured: dict[str, Any] = {}
async def fake_run(agent: Any, *, input: str, context: Any, max_turns: int) -> _Result: # noqa: A002
captured.update(agent=agent, input=input, context=context, max_turns=max_turns)
return _Result(
SafetyVerdict(
decision="allow",
risk="low",
categories=[],
reason="read only",
confidence=0.99,
)
)
monkeypatch.setattr(reviewer_module, "load_settings", _settings)
monkeypatch.setattr(reviewer_module, "configure_sdk_model_defaults", lambda _settings: None)
monkeypatch.setattr(
reviewer_module.StrixProvider, "get_model", lambda _self, _name: "test-model"
)
monkeypatch.setattr(reviewer_module.Runner, "run", fake_run)
monkeypatch.setattr(reviewer_module, "get_global_report_state", lambda: None)
bundle = EvidenceBundle(
case_id="case-1",
root=tmp_path,
packet={"completeness": {"status": "complete"}},
complete=True,
incomplete_reasons=[],
)
decision = await SafetyReviewer(inspection_runner=_InspectionRunner()).review(bundle)
assert decision.allowed is True
assert captured["max_turns"] == 2
assert [tool.name for tool in captured["agent"].tools] == ["run_inspection"]
assert captured["agent"].model_settings.retry.max_retries == 0
# The cap also covers reasoning tokens; a verdict-sized budget would truncate the
# structured output on a reasoning model and fail every review closed.
assert captured["agent"].model_settings.max_tokens == SafetySettings().max_output_tokens
@pytest.mark.asyncio
async def test_review_budget_covers_both_turns_and_the_inspection(
tmp_path: Path,
monkeypatch: MonkeyPatch,
) -> None:
captured: dict[str, Any] = {}
async def fake_wait_for(awaitable: Any, *, timeout: float) -> Any:
captured["timeout"] = timeout
return await awaitable
async def fake_run(_agent: Any, **_kwargs: Any) -> _Result:
return _Result(
SafetyVerdict(
decision="allow",
risk="low",
categories=[],
reason="read only",
confidence=0.99,
)
)
monkeypatch.setattr(reviewer_module, "load_settings", _settings)
monkeypatch.setattr(reviewer_module, "configure_sdk_model_defaults", lambda _settings: None)
monkeypatch.setattr(
reviewer_module.StrixProvider, "get_model", lambda _self, _name: "test-model"
)
monkeypatch.setattr(reviewer_module.Runner, "run", fake_run)
monkeypatch.setattr(reviewer_module, "get_global_report_state", lambda: None)
monkeypatch.setattr(reviewer_module.asyncio, "wait_for", fake_wait_for)
bundle = EvidenceBundle(
case_id="case-budget",
root=tmp_path,
packet={"completeness": {"status": "complete"}},
complete=True,
incomplete_reasons=[],
)
await SafetyReviewer(inspection_runner=_InspectionRunner()).review(bundle)
safety = SafetySettings()
assert captured["timeout"] == 2 * safety.timeout + safety.inspection_timeout
@pytest.mark.asyncio
async def test_inspection_tool_can_only_run_once(tmp_path: Path) -> None:
runner = _InspectionRunner()
state = InspectionContext(evidence_dir=str(tmp_path), runner=runner)
ctx = ToolContext(
context=state,
tool_name="run_inspection",
tool_call_id="inspect-1",
tool_arguments="{}",
)
raw = json.dumps({"reason": "correlate files", "script": "print('ok')"})
first = await run_inspection.on_invoke_tool(ctx, raw)
second = await run_inspection.on_invoke_tool(ctx, raw)
assert "inspected" in first
assert "already used" in second
assert runner.calls == 1
@pytest.mark.asyncio
async def test_reviewer_failure_blocks(tmp_path: Path, monkeypatch: MonkeyPatch) -> None:
async def fail(*_args: Any, **_kwargs: Any) -> Any:
raise RuntimeError("provider down")
monkeypatch.setattr(reviewer_module, "load_settings", _settings)
monkeypatch.setattr(reviewer_module, "configure_sdk_model_defaults", lambda _settings: None)
monkeypatch.setattr(
reviewer_module.StrixProvider, "get_model", lambda _self, _name: "test-model"
)
monkeypatch.setattr(reviewer_module.Runner, "run", fail)
bundle = EvidenceBundle(
case_id="case-2",
root=tmp_path,
packet={"completeness": {"status": "complete"}},
complete=True,
incomplete_reasons=[],
)
decision = await SafetyReviewer(inspection_runner=_InspectionRunner()).review(bundle)
assert decision.allowed is False
assert decision.source == "review_error"
+303
View File
@@ -0,0 +1,303 @@
"""Run-scoped safety enforcement."""
from __future__ import annotations
import asyncio
import io
import json
from types import SimpleNamespace
from typing import TYPE_CHECKING, Any
import pytest
from strix.config.settings import SafetySettings
from strix.safety.runtime import SafetyRuntime
from strix.safety.types import SafetyDecision
if TYPE_CHECKING:
from pathlib import Path
class _InspectionRunner:
async def run(self, *, evidence_dir: str, script: str) -> str:
return f"unused: {evidence_dir} {script}"
def _runtime(tmp_path: Path, mode: str) -> SafetyRuntime:
return SafetyRuntime(
scan_id="scan-1",
mode=mode, # type: ignore[arg-type]
scope={},
user_instruction="",
settings=SafetySettings(),
run_dir=tmp_path,
sandbox_image="image",
inspection_runner=_InspectionRunner(),
)
def _ctx() -> Any:
return SimpleNamespace(
context={"agent_id": "agent-1", "sandbox_session": object()},
tool_call_id="call-1",
turn_input=[],
)
@pytest.mark.asyncio
async def test_known_read_command_executes_without_model_review(tmp_path: Path) -> None:
seen: list[dict[str, Any]] = []
async def invoke(_ctx: Any, raw_input: str) -> str:
seen.append(json.loads(raw_input))
return "ok"
result = await _runtime(tmp_path, "guarded").invoke_exec(
ctx=_ctx(),
arguments={"cmd": "ls /workspace"},
invoke_tool=invoke,
)
assert result == "ok"
assert seen == [{"cmd": "ls /workspace"}]
@pytest.mark.asyncio
async def test_direct_browser_command_gets_per_agent_session(tmp_path: Path) -> None:
seen: list[str] = []
async def invoke(_ctx: Any, raw_input: str) -> str:
seen.append(json.loads(raw_input)["cmd"])
return "snapshot"
result = await _runtime(tmp_path, "guarded").invoke_exec(
ctx=_ctx(),
arguments={"cmd": "agent-browser snapshot -i"},
invoke_tool=invoke,
)
assert result == "snapshot"
assert seen == ["AGENT_BROWSER_SESSION=strix-scan-1-agent-1 agent-browser snapshot -i"]
@pytest.mark.asyncio
async def test_observe_mode_blocks_browser_click(tmp_path: Path) -> None:
invoked = False
async def invoke(_ctx: Any, _raw_input: str) -> str:
nonlocal invoked
invoked = True
return "bad"
result = await _runtime(tmp_path, "observe").invoke_exec(
ctx=_ctx(),
arguments={"cmd": "agent-browser click @e3"},
invoke_tool=invoke,
)
payload = json.loads(result)
assert payload["status"] == "blocked"
assert invoked is False
@pytest.mark.asyncio
async def test_guarded_repeat_request_fails_closed(tmp_path: Path) -> None:
async def invoke(_ctx: Any, _raw_input: str) -> str:
return "bad"
result = await _runtime(tmp_path, "guarded").invoke_mutating_tool(
ctx=_ctx(),
tool_name="repeat_request",
raw_input="{}",
invoke_tool=invoke,
)
payload = json.loads(result)
assert payload["status"] == "blocked"
assert "effective method" in payload["safety"]["reason"]
class _Sandbox:
async def read(self, path: Path) -> io.BytesIO:
if path.as_posix() == "/workspace/app.py":
return io.BytesIO(b"print(1)\n")
raise FileNotFoundError(path)
def _script_ctx() -> Any:
return SimpleNamespace(
context={"agent_id": "agent-1", "sandbox_session": _Sandbox()},
tool_call_id="call-1",
turn_input=[],
)
class _StubReviewer:
def __init__(self, on_review: Any = None) -> None:
self.on_review = on_review
self.calls = 0
async def review(self, bundle: Any) -> SafetyDecision:
self.calls += 1
if self.on_review is not None:
await self.on_review()
return SafetyDecision(
allowed=True,
source="reviewer",
reason="allowed",
case_id=bundle.case_id,
)
@pytest.mark.asyncio
async def test_write_stdin_is_blocked_in_guarded_mode(tmp_path: Path) -> None:
invoked = False
async def invoke(_ctx: Any, _raw_input: str) -> str:
nonlocal invoked
invoked = True
return "bad"
result = await _runtime(tmp_path, "guarded").invoke_write_stdin(
ctx=_ctx(),
arguments={"session_id": "s", "chars": "rm -rf /workspace/app\n"},
invoke_tool=invoke,
)
payload = json.loads(result)
assert payload["status"] == "blocked"
assert "write_stdin is blocked" in payload["safety"]["reason"]
assert invoked is False
@pytest.mark.asyncio
async def test_write_stdin_allows_an_interrupt(tmp_path: Path) -> None:
async def invoke(_ctx: Any, _raw_input: str) -> str:
return "interrupted"
result = await _runtime(tmp_path, "guarded").invoke_write_stdin(
ctx=_ctx(),
arguments={"session_id": "s", "chars": "\x03"},
invoke_tool=invoke,
)
assert result == "interrupted"
@pytest.mark.asyncio
async def test_write_stdin_is_untouched_when_safety_is_off(tmp_path: Path) -> None:
async def invoke(_ctx: Any, _raw_input: str) -> str:
return "typed"
result = await _runtime(tmp_path, "off").invoke_write_stdin(
ctx=_ctx(),
arguments={"session_id": "s", "chars": "anything\n"},
invoke_tool=invoke,
)
assert result == "typed"
@pytest.mark.asyncio
async def test_observe_mode_blocks_a_mutating_request_without_the_reviewer(
tmp_path: Path,
) -> None:
runtime = _runtime(tmp_path, "observe")
reviewer = _StubReviewer()
runtime._reviewer = reviewer
invoked = False
async def invoke(_ctx: Any, _raw_input: str) -> str:
nonlocal invoked
invoked = True
return "bad"
result = await runtime.invoke_exec(
ctx=_ctx(),
arguments={"cmd": "curl -X DELETE https://example.test/v1/users/1042"},
invoke_tool=invoke,
)
payload = json.loads(result)
assert payload["status"] == "blocked"
assert payload["safety"]["source"] == "deterministic"
assert "DELETE" in payload["safety"]["reason"]
assert reviewer.calls == 0
assert invoked is False
@pytest.mark.asyncio
async def test_review_does_not_hold_the_workspace_lock(tmp_path: Path) -> None:
runtime = _runtime(tmp_path, "guarded")
concurrent = 0
peak = 0
async def on_review() -> None:
nonlocal concurrent, peak
concurrent += 1
peak = max(peak, concurrent)
await asyncio.sleep(0.05)
concurrent -= 1
runtime._reviewer = _StubReviewer(on_review)
async def invoke(_ctx: Any, _raw_input: str) -> str:
return "ok"
await asyncio.gather(
*[
runtime.invoke_exec(
ctx=_ctx(),
arguments={"cmd": f"nmap -sV host{index}"},
invoke_tool=invoke,
)
for index in range(3)
]
)
assert peak == 3
@pytest.mark.asyncio
async def test_workspace_change_during_review_invalidates_the_decision(tmp_path: Path) -> None:
runtime = _runtime(tmp_path, "guarded")
async def on_review() -> None:
runtime._workspace_epoch += 1
runtime._reviewer = _StubReviewer(on_review)
invoked = False
async def invoke(_ctx: Any, _raw_input: str) -> str:
nonlocal invoked
invoked = True
return "bad"
result = await runtime.invoke_exec(
ctx=_script_ctx(),
arguments={"cmd": "python /workspace/app.py"},
invoke_tool=invoke,
)
payload = json.loads(result)
assert payload["status"] == "blocked"
assert payload["safety"]["categories"] == ["stale_evidence"]
assert invoked is False
@pytest.mark.asyncio
async def test_unchanged_workspace_executes_after_review(tmp_path: Path) -> None:
runtime = _runtime(tmp_path, "guarded")
runtime._reviewer = _StubReviewer()
async def invoke(_ctx: Any, _raw_input: str) -> str:
return "ran"
result = await runtime.invoke_exec(
ctx=_script_ctx(),
arguments={"cmd": "python /workspace/app.py"},
invoke_tool=invoke,
)
assert result == "ran"
+79
View File
@@ -0,0 +1,79 @@
"""Safety-mode local workspace isolation."""
from __future__ import annotations
from pathlib import Path
from strix.runtime.local_dir_staging import materialize_isolated_sources
from strix.runtime.session_manager import build_bind_mounts
def test_isolated_copy_does_not_modify_original(tmp_path: Path) -> None:
source = tmp_path / "source"
source.mkdir()
original = source / "app.py"
original.write_text("before\n", encoding="utf-8")
run_dir = tmp_path / "runs" / "scan"
[staged] = materialize_isolated_sources(
[
{
"source_path": str(source),
"workspace_subdir": "source",
"protect_metadata": True,
}
],
run_dir=run_dir,
)
staged_file = Path(staged["source_path"]) / "app.py"
staged_file.write_text("after\n", encoding="utf-8")
assert original.read_text(encoding="utf-8") == "before\n"
assert staged_file.read_text(encoding="utf-8") == "after\n"
assert staged["original_source_path"] == str(source.resolve())
assert staged["workspace_mode"] == "isolated_copy"
def test_isolated_copy_keeps_metadata_read_only(tmp_path: Path) -> None:
source = tmp_path / "source"
(source / ".git").mkdir(parents=True)
(source / ".git" / "config").write_text("[core]\n", encoding="utf-8")
(source / ".agents").mkdir()
(source / ".agents" / "rules.md").write_text("instructions\n", encoding="utf-8")
[staged] = materialize_isolated_sources(
[
{
"source_path": str(source),
"workspace_subdir": "source",
"protect_metadata": True,
}
],
run_dir=tmp_path / "runs" / "scan",
)
assert staged["protect_metadata"] is True
read_only = {mount["target"] for mount in build_bind_mounts([staged]) if mount.get("read_only")}
assert "/workspace/source/.git" in read_only
assert "/workspace/source/.agents" in read_only
def test_isolated_copy_drops_out_of_tree_symlink(tmp_path: Path) -> None:
source = tmp_path / "source"
source.mkdir()
secret = tmp_path / "secret.txt"
secret.write_text("secret", encoding="utf-8")
(source / "escape").symlink_to(secret)
[staged] = materialize_isolated_sources(
[
{
"source_path": str(source),
"workspace_subdir": "source",
"protect_metadata": True,
}
],
run_dir=tmp_path / "runs" / "scan",
)
assert not (Path(staged["source_path"]) / "escape").exists()