mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-07-31 19:16:29 +00:00
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.
209 lines
8.9 KiB
Python
209 lines
8.9 KiB
Python
"""Unit tests for tools.computer_use.vision_routing.
|
|
|
|
Cover the small ``should_route_capture_to_aux_vision`` policy helper that
|
|
decides whether a captured screenshot from ``computer_use(action='capture')``
|
|
should be returned as a multimodal envelope (main model handles vision
|
|
natively) or pre-analysed via the ``auxiliary.vision`` pipeline so the
|
|
main model only sees text.
|
|
|
|
The companion end-to-end regression for #24015 lives in
|
|
``tests/tools/test_computer_use_capture_routing.py``; this file pins the
|
|
unit contract of the helper in isolation so behaviour does not regress
|
|
silently if the surrounding ``computer_use`` plumbing is refactored.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
from unittest.mock import patch
|
|
|
|
import pytest
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# _explicit_aux_vision_override
|
|
# ---------------------------------------------------------------------------
|
|
|
|
class TestExplicitAuxVisionOverride:
|
|
"""Mirror agent.image_routing — config detection must agree across paths."""
|
|
|
|
def test_returns_false_for_none_cfg(self):
|
|
from tools.computer_use.vision_routing import _explicit_aux_vision_override
|
|
assert _explicit_aux_vision_override(None) is False
|
|
|
|
def test_returns_false_for_non_dict_cfg(self):
|
|
from tools.computer_use.vision_routing import _explicit_aux_vision_override
|
|
assert _explicit_aux_vision_override("not-a-dict") is False
|
|
assert _explicit_aux_vision_override([]) is False
|
|
|
|
def test_returns_false_when_auxiliary_block_missing(self):
|
|
from tools.computer_use.vision_routing import _explicit_aux_vision_override
|
|
assert _explicit_aux_vision_override({}) is False
|
|
assert _explicit_aux_vision_override({"model": {"default": "x"}}) is False
|
|
|
|
def test_returns_false_when_vision_block_missing(self):
|
|
from tools.computer_use.vision_routing import _explicit_aux_vision_override
|
|
cfg = {"auxiliary": {"compression": {"provider": "openai"}}}
|
|
assert _explicit_aux_vision_override(cfg) is False
|
|
|
|
|
|
def test_returns_true_for_provider_auto_plus_explicit_model(self):
|
|
"""``provider: auto`` + an explicit model still counts as override."""
|
|
from tools.computer_use.vision_routing import _explicit_aux_vision_override
|
|
cfg = {
|
|
"auxiliary": {
|
|
"vision": {"provider": "auto", "model": "claude-3-haiku"},
|
|
}
|
|
}
|
|
assert _explicit_aux_vision_override(cfg) is True
|
|
|
|
def test_handles_non_dict_vision_block(self):
|
|
from tools.computer_use.vision_routing import _explicit_aux_vision_override
|
|
cfg = {"auxiliary": {"vision": "not-a-dict"}}
|
|
assert _explicit_aux_vision_override(cfg) is False
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# should_route_capture_to_aux_vision
|
|
# ---------------------------------------------------------------------------
|
|
|
|
class TestRouteDecision:
|
|
"""End-to-end policy: explicit override > tool-result support > vision caps."""
|
|
|
|
def test_explicit_override_routes_to_aux_even_for_vision_main(self):
|
|
"""Issue #24015 core repro: explicit aux config must win.
|
|
|
|
Even if the main model fully supports vision (Anthropic / Claude),
|
|
an explicit ``auxiliary.vision`` block means the user wants their
|
|
configured backend used. Don't silently bypass it.
|
|
"""
|
|
from tools.computer_use import vision_routing
|
|
|
|
cfg = {
|
|
"auxiliary": {
|
|
"vision": {
|
|
"provider": "openrouter",
|
|
"model": "google/gemini-2.5-flash",
|
|
}
|
|
}
|
|
}
|
|
with patch.object(vision_routing, "_lookup_supports_vision", return_value=True), \
|
|
patch.object(vision_routing,
|
|
"_provider_accepts_multimodal_tool_result",
|
|
return_value=True):
|
|
assert vision_routing.should_route_capture_to_aux_vision(
|
|
"anthropic", "claude-opus-4-5", cfg
|
|
) is True
|
|
|
|
def test_non_vision_main_model_routes_to_aux(self):
|
|
"""The reported #24015 scenario: tencent/hy3-preview has no vision."""
|
|
from tools.computer_use import vision_routing
|
|
|
|
cfg = {"model": {"default": "tencent/hy3-preview", "provider": "openrouter"}}
|
|
with patch.object(vision_routing, "_lookup_supports_vision", return_value=False), \
|
|
patch.object(vision_routing,
|
|
"_provider_accepts_multimodal_tool_result",
|
|
return_value=True):
|
|
assert vision_routing.should_route_capture_to_aux_vision(
|
|
"openrouter", "tencent/hy3-preview", cfg
|
|
) is True
|
|
|
|
def test_vision_main_model_no_override_keeps_multimodal(self):
|
|
"""Default path: vision-capable main model + no aux override → native."""
|
|
from tools.computer_use import vision_routing
|
|
|
|
with patch.object(vision_routing, "_lookup_supports_vision", return_value=True), \
|
|
patch.object(vision_routing,
|
|
"_provider_accepts_multimodal_tool_result",
|
|
return_value=True):
|
|
assert vision_routing.should_route_capture_to_aux_vision(
|
|
"anthropic", "claude-opus-4-5", None
|
|
) is False
|
|
|
|
|
|
def test_user_declared_vision_support_keeps_custom_provider_native(self):
|
|
"""Local/custom VLMs use config as their tool-result image escape hatch."""
|
|
from tools.computer_use import vision_routing
|
|
|
|
cfg = {
|
|
"model": {
|
|
"default": "Qwen3.6-35B-A3B-local-vlm",
|
|
"provider": "omlx",
|
|
"supports_vision": True,
|
|
}
|
|
}
|
|
with patch.object(vision_routing,
|
|
"_provider_accepts_multimodal_tool_result",
|
|
return_value=False):
|
|
assert vision_routing.should_route_capture_to_aux_vision(
|
|
"custom", "Qwen3.6-35B-A3B-local-vlm", cfg
|
|
) is False
|
|
|
|
|
|
def test_unknown_provider_capabilities_fail_closed(self):
|
|
"""When tool-result lookup returns None, route to aux (safe default)."""
|
|
from tools.computer_use import vision_routing
|
|
|
|
with patch.object(vision_routing, "_lookup_supports_vision", return_value=True), \
|
|
patch.object(vision_routing,
|
|
"_provider_accepts_multimodal_tool_result",
|
|
return_value=None):
|
|
assert vision_routing.should_route_capture_to_aux_vision(
|
|
"exotic-provider", "exotic-model", {}
|
|
) is True
|
|
|
|
|
|
def test_explicit_override_wins_over_unknown_caps(self):
|
|
"""Explicit aux config wins regardless of unknown caps elsewhere."""
|
|
from tools.computer_use import vision_routing
|
|
|
|
cfg = {"auxiliary": {"vision": {"provider": "openrouter"}}}
|
|
with patch.object(vision_routing, "_lookup_supports_vision", return_value=None), \
|
|
patch.object(vision_routing,
|
|
"_provider_accepts_multimodal_tool_result",
|
|
return_value=None):
|
|
assert vision_routing.should_route_capture_to_aux_vision(
|
|
"openrouter", "tencent/hy3-preview", cfg
|
|
) is True
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Internal lookups — defensive paths
|
|
# ---------------------------------------------------------------------------
|
|
|
|
class TestLookupHelpers:
|
|
def test_lookup_supports_vision_returns_none_for_blank_provider(self):
|
|
from tools.computer_use.vision_routing import _lookup_supports_vision
|
|
assert _lookup_supports_vision("", "claude") is None
|
|
|
|
|
|
def test_provider_accepts_multimodal_tool_result_returns_none_for_blank_provider(self):
|
|
from tools.computer_use.vision_routing import (
|
|
_provider_accepts_multimodal_tool_result,
|
|
)
|
|
assert _provider_accepts_multimodal_tool_result("", "claude") is None
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Module surface
|
|
# ---------------------------------------------------------------------------
|
|
|
|
class TestModuleSurface:
|
|
"""Pin the public surface so dependents stay in lockstep."""
|
|
|
|
def test_should_route_capture_to_aux_vision_is_exported(self):
|
|
from tools.computer_use import vision_routing
|
|
|
|
assert "should_route_capture_to_aux_vision" in vision_routing.__all__
|
|
assert callable(vision_routing.should_route_capture_to_aux_vision)
|
|
|
|
@pytest.mark.parametrize("name", [
|
|
"_explicit_aux_vision_override",
|
|
"_lookup_supports_vision",
|
|
"_provider_accepts_multimodal_tool_result",
|
|
])
|
|
def test_internal_helpers_are_addressable(self, name):
|
|
"""Internal helpers stay importable so tests can monkeypatch them."""
|
|
from tools.computer_use import vision_routing
|
|
|
|
assert hasattr(vision_routing, name)
|
|
assert callable(getattr(vision_routing, name))
|