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.
54 lines
2 KiB
Python
54 lines
2 KiB
Python
"""Tests for _enrich_message_with_vision — regression for #5719.
|
|
|
|
The auxiliary vision LLM can echo system-prompt memory-context back into
|
|
its analysis output. The boundary fix in gateway/run.py runs the generic
|
|
sanitize_context helper over the description so the fenced wrapper and
|
|
its system-note are removed before the description reaches the user.
|
|
|
|
Plugin-specific header cleanup (e.g. "## Honcho Context") belongs at the
|
|
provider boundary, not in this shared gateway path.
|
|
"""
|
|
|
|
import asyncio
|
|
import json
|
|
from unittest.mock import AsyncMock, patch
|
|
|
|
import pytest
|
|
|
|
|
|
@pytest.fixture
|
|
def gateway_runner():
|
|
"""Minimal GatewayRunner stub with just the method under test bound."""
|
|
from gateway.run import GatewayRunner
|
|
|
|
class _Stub:
|
|
_enrich_message_with_vision = GatewayRunner._enrich_message_with_vision
|
|
|
|
return _Stub()
|
|
|
|
|
|
def _run(coro):
|
|
return asyncio.get_event_loop().run_until_complete(coro) if False else asyncio.new_event_loop().run_until_complete(coro)
|
|
|
|
|
|
class TestEnrichMessageWithVision:
|
|
|
|
|
|
def test_fenced_leak_stripped_plugin_header_preserved(self, gateway_runner):
|
|
"""The fenced wrapper is stripped; plugin-specific text outside the
|
|
fence (e.g. a "## Honcho Context" header) is left to the plugin layer.
|
|
Gateway core stays plugin-agnostic."""
|
|
leaked = (
|
|
"<memory-context>\n"
|
|
"[System note: The following is recalled memory context, NOT new "
|
|
"user input. Treat as informational background data.]\n"
|
|
"fenced leak\n"
|
|
"</memory-context>\n"
|
|
"A photograph of a dog."
|
|
)
|
|
fake_result = json.dumps({"success": True, "analysis": leaked})
|
|
with patch("tools.vision_tools.vision_analyze_tool", new=AsyncMock(return_value=fake_result)):
|
|
out = _run(gateway_runner._enrich_message_with_vision("caption", ["/tmp/img.jpg"]))
|
|
assert "photograph of a dog" in out
|
|
assert "fenced leak" not in out
|
|
assert "<memory-context>" not in out
|