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.
120 lines
3.6 KiB
Python
120 lines
3.6 KiB
Python
"""Tests for hermes_cli.azure_detect — transport & model auto-detection."""
|
|
|
|
from __future__ import annotations
|
|
|
|
import json
|
|
from unittest.mock import MagicMock, patch
|
|
|
|
import pytest
|
|
|
|
from hermes_cli import azure_detect
|
|
|
|
|
|
# ----------------------------------------------------------------------
|
|
# Helpers
|
|
# ----------------------------------------------------------------------
|
|
|
|
class _FakeHTTPResponse:
|
|
"""Minimal stand-in for urllib.request.urlopen's context manager."""
|
|
|
|
def __init__(self, status: int, body: bytes):
|
|
self.status = status
|
|
self._body = body
|
|
|
|
def __enter__(self):
|
|
return self
|
|
|
|
def __exit__(self, exc_type, exc, tb):
|
|
return False
|
|
|
|
def read(self) -> bytes:
|
|
return self._body
|
|
|
|
|
|
def _openai_models_body(*ids: str) -> bytes:
|
|
return json.dumps({
|
|
"object": "list",
|
|
"data": [{"id": i, "object": "model"} for i in ids],
|
|
}).encode()
|
|
|
|
|
|
def _anthropic_error_body(msg: str = "model not found") -> bytes:
|
|
return json.dumps({
|
|
"type": "error",
|
|
"error": {"type": "invalid_request_error", "message": msg},
|
|
}).encode()
|
|
|
|
|
|
# ----------------------------------------------------------------------
|
|
# _looks_like_anthropic_path
|
|
# ----------------------------------------------------------------------
|
|
|
|
|
|
|
|
# ----------------------------------------------------------------------
|
|
# _extract_model_ids
|
|
# ----------------------------------------------------------------------
|
|
|
|
|
|
|
|
|
|
|
|
# ----------------------------------------------------------------------
|
|
# detect() integration
|
|
# ----------------------------------------------------------------------
|
|
|
|
|
|
|
|
def test_detect_openai_models_probe_success():
|
|
"""/models probe returning a model list → chat_completions."""
|
|
def _fake_get(url, api_key, timeout=6.0, **kwargs):
|
|
assert "key-abc" == api_key
|
|
return 200, json.loads(_openai_models_body("gpt-5.4", "claude-opus-4-6"))
|
|
|
|
with patch.object(azure_detect, "_http_get_json", side_effect=_fake_get):
|
|
result = azure_detect.detect(
|
|
"https://my.openai.azure.com/openai/v1", "key-abc",
|
|
)
|
|
assert result.api_mode == "chat_completions"
|
|
assert result.models_probe_ok is True
|
|
assert result.models == ["gpt-5.4", "claude-opus-4-6"]
|
|
assert "/models" in result.reason
|
|
|
|
|
|
# ----------------------------------------------------------------------
|
|
# _probe_openai_models URL list (Azure vs v1 api-version)
|
|
# ----------------------------------------------------------------------
|
|
|
|
def test_probe_openai_models_tries_multiple_api_versions():
|
|
"""First call (no api-version) fails, api-version fallback succeeds."""
|
|
calls = []
|
|
|
|
def _fake_get(url, api_key, timeout=6.0, **kwargs):
|
|
calls.append(url)
|
|
if "api-version" not in url:
|
|
return 404, None
|
|
return 200, json.loads(_openai_models_body("gpt-4.1"))
|
|
|
|
with patch.object(azure_detect, "_http_get_json", side_effect=_fake_get):
|
|
ok, models = azure_detect._probe_openai_models(
|
|
"https://my.openai.azure.com/openai/v1", "k",
|
|
)
|
|
assert ok is True
|
|
assert models == ["gpt-4.1"]
|
|
# Should have tried without api-version first, then with at least one
|
|
assert any("api-version" not in u for u in calls)
|
|
assert any("api-version" in u for u in calls)
|
|
|
|
|
|
# ----------------------------------------------------------------------
|
|
# _http_get_json error handling
|
|
# ----------------------------------------------------------------------
|
|
|
|
|
|
|
|
# ----------------------------------------------------------------------
|
|
# lookup_context_length
|
|
# ----------------------------------------------------------------------
|
|
|
|
|
|
|