mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-07-31 19:16:29 +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.
99 lines
4.4 KiB
Python
99 lines
4.4 KiB
Python
"""Tests for None guard on browser_tool LLM response content.
|
|
|
|
browser_tool.py has two call sites that access response.choices[0].message.content
|
|
without checking for None — _extract_relevant_content (line 996) and
|
|
browser_vision (line 1626). When reasoning-only models (DeepSeek-R1, QwQ)
|
|
return content=None, these produce null snapshots or null analysis.
|
|
|
|
These tests verify both sites are guarded.
|
|
"""
|
|
|
|
import types
|
|
from unittest.mock import patch
|
|
|
|
|
|
# ── helpers ────────────────────────────────────────────────────────────────
|
|
|
|
def _make_response(content):
|
|
"""Build a minimal OpenAI-compatible ChatCompletion response stub."""
|
|
message = types.SimpleNamespace(content=content)
|
|
choice = types.SimpleNamespace(message=message)
|
|
return types.SimpleNamespace(choices=[choice])
|
|
|
|
|
|
# ── _extract_relevant_content (line 996) ──────────────────────────────────
|
|
|
|
class TestExtractRelevantContentNoneGuard:
|
|
"""tools/browser_tool.py — _extract_relevant_content()"""
|
|
|
|
def test_none_content_falls_back_to_truncated(self):
|
|
"""When LLM returns None content, should fall back to truncated snapshot."""
|
|
with patch("tools.browser_tool.call_llm", return_value=_make_response(None)), \
|
|
patch("tools.browser_tool._get_extraction_model", return_value="test-model"):
|
|
from tools.browser_tool import _extract_relevant_content
|
|
result = _extract_relevant_content("This is a long snapshot text", "find the button")
|
|
|
|
assert result is not None
|
|
assert isinstance(result, str)
|
|
assert len(result) > 0
|
|
|
|
|
|
def test_empty_string_content_falls_back(self):
|
|
"""Empty string content should also fall back to truncated."""
|
|
with patch("tools.browser_tool.call_llm", return_value=_make_response(" ")), \
|
|
patch("tools.browser_tool._get_extraction_model", return_value="test-model"):
|
|
from tools.browser_tool import _extract_relevant_content
|
|
result = _extract_relevant_content("This is a long snapshot text", "task")
|
|
|
|
assert result is not None
|
|
assert len(result) > 0
|
|
|
|
|
|
# ── browser_vision (line 1626) ────────────────────────────────────────────
|
|
|
|
class TestBrowserVisionNoneGuard:
|
|
"""tools/browser_tool.py — browser_vision() analysis extraction"""
|
|
|
|
def test_none_content_produces_fallback_message(self):
|
|
"""When LLM returns None content, analysis should have a fallback message."""
|
|
response = _make_response(None)
|
|
analysis = (response.choices[0].message.content or "").strip()
|
|
fallback = analysis or "Vision analysis returned no content."
|
|
|
|
assert fallback == "Vision analysis returned no content."
|
|
|
|
def test_normal_content_passes_through(self):
|
|
"""Normal analysis content should pass through unchanged."""
|
|
response = _make_response(" The page shows a login form. ")
|
|
analysis = (response.choices[0].message.content or "").strip()
|
|
fallback = analysis or "Vision analysis returned no content."
|
|
|
|
assert fallback == "The page shows a login form."
|
|
|
|
|
|
# ── source line verification ──────────────────────────────────────────────
|
|
|
|
class TestBrowserSourceLinesAreGuarded:
|
|
"""Verify the actual source file has the fix applied."""
|
|
|
|
@staticmethod
|
|
def _read_file() -> str:
|
|
import os
|
|
base = os.path.dirname(os.path.dirname(os.path.dirname(__file__)))
|
|
with open(os.path.join(base, "tools", "browser_tool.py")) as f:
|
|
return f.read()
|
|
|
|
def test_extract_relevant_content_guarded(self):
|
|
src = self._read_file()
|
|
# The old unguarded pattern should NOT exist
|
|
assert "return response.choices[0].message.content\n" not in src, (
|
|
"browser_tool.py _extract_relevant_content still has unguarded "
|
|
".content return — apply None guard"
|
|
)
|
|
|
|
def test_browser_vision_guarded(self):
|
|
src = self._read_file()
|
|
assert "analysis = response.choices[0].message.content\n" not in src, (
|
|
"browser_tool.py browser_vision still has unguarded "
|
|
".content assignment — apply None guard"
|
|
)
|