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.
84 lines
3.2 KiB
Python
84 lines
3.2 KiB
Python
"""Tests for per-model reasoning_effort override in gateway _load_reasoning_config."""
|
|
|
|
import pytest
|
|
|
|
import gateway.run as gateway_run
|
|
|
|
|
|
class TestGatewayPerModelReasoningConfig:
|
|
"""Test GatewayRunner._load_reasoning_config respects per-model overrides."""
|
|
|
|
def test_per_model_override_takes_precedence(self, monkeypatch):
|
|
"""Per-model override wins over global reasoning_effort."""
|
|
from hermes_cli.config import DEFAULT_CONFIG
|
|
|
|
fake_cfg = {
|
|
"model": {"default": "anthropic/claude-opus-4.5"},
|
|
"agent": {
|
|
"reasoning_effort": "medium",
|
|
"reasoning_overrides": {
|
|
"anthropic/claude-opus-4.5": "xhigh",
|
|
},
|
|
},
|
|
}
|
|
monkeypatch.setattr(gateway_run, "_load_gateway_runtime_config", lambda: fake_cfg)
|
|
|
|
result = gateway_run.GatewayRunner._load_reasoning_config()
|
|
assert result is not None
|
|
assert result["enabled"] is True
|
|
assert result["effort"] == "xhigh"
|
|
|
|
|
|
def test_global_fallback_with_yaml_false(self, monkeypatch):
|
|
"""YAML boolean False must reach parse_reasoning_effort uncoerced.
|
|
|
|
Regression: str(... or "").strip() turned False into "", silently
|
|
re-enabling thinking. The raw value must pass through so
|
|
parse_reasoning_effort(False) returns {'enabled': False}.
|
|
"""
|
|
fake_cfg = {
|
|
"model": {"default": "gpt-5"},
|
|
"agent": {
|
|
"reasoning_effort": False, # YAML boolean, not string
|
|
},
|
|
}
|
|
monkeypatch.setattr(gateway_run, "_load_gateway_runtime_config", lambda: fake_cfg)
|
|
|
|
result = gateway_run.GatewayRunner._load_reasoning_config()
|
|
assert result is not None
|
|
assert result.get("enabled") is False
|
|
|
|
|
|
class TestGatewaySessionEffectiveModel:
|
|
"""The reasoning override must track the SESSION's effective model.
|
|
|
|
Regression guard: _load_reasoning_config used to always read
|
|
model.default from config.yaml, so a session-only /model switch to a
|
|
different model kept resolving the config default's override.
|
|
"""
|
|
|
|
def test_explicit_model_beats_config_default(self, monkeypatch):
|
|
"""_load_reasoning_config(model=...) resolves for that model, not model.default."""
|
|
fake_cfg = {
|
|
"model": {"default": "gpt-5"},
|
|
"agent": {
|
|
"reasoning_effort": "medium",
|
|
"reasoning_overrides": {
|
|
"gpt-5": "low",
|
|
"claude-opus-4.5": "xhigh",
|
|
},
|
|
},
|
|
}
|
|
monkeypatch.setattr(gateway_run, "_load_gateway_runtime_config", lambda: fake_cfg)
|
|
|
|
# Session switched (session-only) to claude-opus-4.5 — its override
|
|
# must win over the config default model's override.
|
|
result = gateway_run.GatewayRunner._load_reasoning_config("claude-opus-4.5")
|
|
assert result is not None
|
|
assert result["effort"] == "xhigh"
|
|
|
|
# And without a model arg, the config default's override applies.
|
|
result_default = gateway_run.GatewayRunner._load_reasoning_config()
|
|
assert result_default is not None
|
|
assert result_default["effort"] == "low"
|
|
|