mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-07-30 19:09:28 +00:00
39975613b1
Second, deeper pass over tools/gateway/hermes_cli plus first pass over the trees wave 1 missed (acp, acp_adapter, skills, computer_use, docker, dashboard, conformance, monitoring, secret_sources, hermes_state, providers). Same rubric as wave 1 (AGENTS.md test policy); security, alternation/caching invariants, issue-number regressions, and E2E kept. Real test-quality fixes found and rooted out along the way: - tests/tools/test_command_guards.py made real auxiliary-LLM HTTPS calls (DEFAULT_CONFIG smart-approval leaked in) — pinned approval mode=manual via autouse fixture: 17.4s → 0.4s. - test_model_switch_custom_providers.py / test_user_providers_model_switch.py silently probed live provider catalogs (~2s/test) — stubbed cached_provider_model_ids/provider_model_ids/fetch_api_models. - test_telegram_noise_filter.py: 15-platform copy-paste matrix over shared gateway.run logic → 3 representative platforms (55s → 3.9s). - test_gateway_shutdown.py: stop()'s 5s interrupt-deadline loop spun on MagicMock agents — interrupt.side_effect now clears _running_agents (22s → 1.0s). - test_gateway_inactivity_timeout.py poll-harness timings shrunk 3-5x (24s → 1.1s); test_mcp_stability.py backoff/SIGTERM-grace sleeps patched (15.4s → 2.5s); test_async_delegation.py negative-drain wait 5s → 0.5s. - test_telegram_init_deadline.py: loop-block margin restored to 1.0s with rationale comment — the watchdog-dump assertion needs the loop blocked well past deadline+grace under parallel load (flaked once in the 40-worker verification run at a 0.2s margin). Verification: full hermetic suite via scripts/run_tests.sh — 2,438 files, 21,718 tests passed, 0 failed, 293.9s wall. Suite totals vs original baseline: 46,820 → 19,757 test functions (−57.8%), wall 583.5s → 293.9s (−50%), subprocess CPU 13,564s → 11,623s.
124 lines
3.3 KiB
Python
124 lines
3.3 KiB
Python
"""Tests for ACP pre-edit approval gating."""
|
|
|
|
from __future__ import annotations
|
|
|
|
import json
|
|
import tempfile
|
|
from pathlib import Path
|
|
|
|
from acp_adapter.edit_approval import (
|
|
EditProposal,
|
|
build_acp_edit_tool_call,
|
|
clear_edit_approval_requester,
|
|
set_edit_approval_requester,
|
|
should_auto_approve_edit,
|
|
)
|
|
from model_tools import handle_function_call
|
|
|
|
|
|
def teardown_function() -> None:
|
|
clear_edit_approval_requester()
|
|
|
|
|
|
def test_acp_permission_tool_call_uses_edit_kind_and_diff_content():
|
|
proposal = EditProposal(
|
|
tool_name="write_file",
|
|
path="demo.txt",
|
|
old_text="old\n",
|
|
new_text="new\n",
|
|
arguments={"path": "demo.txt", "content": "new\n"},
|
|
)
|
|
|
|
tool_call = build_acp_edit_tool_call(proposal)
|
|
|
|
assert tool_call.kind == "edit"
|
|
assert tool_call.status == "pending"
|
|
assert tool_call.rawInput == {"tool": "write_file", "arguments": proposal.arguments}
|
|
assert len(tool_call.content) == 1
|
|
diff = tool_call.content[0]
|
|
assert diff.path == "demo.txt"
|
|
assert diff.oldText == "old\n"
|
|
assert diff.newText == "new\n"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def test_requester_exception_denies_and_does_not_mutate(tmp_path):
|
|
target = tmp_path / "sample.txt"
|
|
target.write_text("before\n", encoding="utf-8")
|
|
|
|
def boom(_proposal):
|
|
raise RuntimeError("zed disconnected")
|
|
|
|
set_edit_approval_requester(boom)
|
|
|
|
result = json.loads(
|
|
handle_function_call(
|
|
"write_file",
|
|
{"path": str(target), "content": "after\n"},
|
|
task_id="acp-edit-exception",
|
|
)
|
|
)
|
|
|
|
assert "error" in result
|
|
assert "Edit approval denied" in result["error"]
|
|
assert target.read_text(encoding="utf-8") == "before\n"
|
|
|
|
|
|
def test_patch_replace_rejection_does_not_mutate(tmp_path):
|
|
target = tmp_path / "sample.txt"
|
|
target.write_text("alpha\nbeta\n", encoding="utf-8")
|
|
|
|
set_edit_approval_requester(lambda _proposal: False)
|
|
|
|
result = json.loads(
|
|
handle_function_call(
|
|
"patch",
|
|
{
|
|
"mode": "replace",
|
|
"path": str(target),
|
|
"old_string": "beta\n",
|
|
"new_string": "gamma\n",
|
|
},
|
|
task_id="acp-patch-reject",
|
|
)
|
|
)
|
|
|
|
assert "error" in result
|
|
assert "Edit approval denied" in result["error"]
|
|
assert target.read_text(encoding="utf-8") == "alpha\nbeta\n"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def test_workspace_auto_approval_allows_workspace_and_tmp_but_not_sensitive(tmp_path):
|
|
workspace_file = tmp_path / "src.py"
|
|
# Use tempfile.gettempdir() so this test exercises the same code path on
|
|
# Linux (`/tmp`), macOS (`/private/var/folders/...`) and Windows
|
|
# (`%LOCALAPPDATA%\Temp`). Before the fix this branch only worked on Linux.
|
|
tmp_file = Path(tempfile.gettempdir()) / "hermes-acp-auto-approve-test.txt"
|
|
env_file = tmp_path / ".env"
|
|
|
|
assert should_auto_approve_edit(
|
|
EditProposal("write_file", str(workspace_file), None, "x", {}),
|
|
"workspace_session",
|
|
str(tmp_path),
|
|
)
|
|
assert should_auto_approve_edit(
|
|
EditProposal("write_file", str(tmp_file), None, "x", {}),
|
|
"workspace_session",
|
|
str(tmp_path),
|
|
)
|
|
assert not should_auto_approve_edit(
|
|
EditProposal("write_file", str(env_file), None, "SECRET=x", {}),
|
|
"session",
|
|
str(tmp_path),
|
|
)
|