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.
59 lines
2 KiB
Python
59 lines
2 KiB
Python
"""Regression tests for bounded upstream TTS response reads."""
|
|
|
|
from __future__ import annotations
|
|
|
|
from unittest.mock import patch
|
|
|
|
import pytest
|
|
|
|
from tools import tts_tool
|
|
|
|
|
|
class StreamingResponse:
|
|
def __init__(self, chunks, *, status_code=200, headers=None):
|
|
self._chunks = list(chunks)
|
|
self.status_code = status_code
|
|
self.headers = headers or {}
|
|
self.closed = False
|
|
|
|
def iter_content(self, chunk_size=65536):
|
|
del chunk_size
|
|
yield from self._chunks
|
|
|
|
def close(self):
|
|
self.closed = True
|
|
|
|
def raise_for_status(self):
|
|
if self.status_code >= 400:
|
|
raise RuntimeError(f"HTTP {self.status_code}")
|
|
|
|
|
|
@pytest.fixture(autouse=True)
|
|
def small_tts_body_cap(monkeypatch):
|
|
monkeypatch.setattr(tts_tool, "TTS_RESPONSE_BODY_LIMIT_BYTES", 8)
|
|
|
|
|
|
def test_xai_tts_rejects_oversized_audio_response(tmp_path, monkeypatch):
|
|
monkeypatch.setenv("XAI_API_KEY", "test-xai-key")
|
|
response = StreamingResponse([b"12345", b"6789"], headers={"Content-Type": "audio/mpeg"})
|
|
output_path = tmp_path / "out.mp3"
|
|
|
|
with patch("requests.post", return_value=response) as post:
|
|
with pytest.raises(RuntimeError, match="xAI TTS response exceeds 8 bytes"):
|
|
tts_tool._generate_xai_tts("hello", str(output_path), {})
|
|
|
|
assert post.call_args.kwargs["stream"] is True
|
|
assert response.closed is True
|
|
assert not output_path.exists()
|
|
|
|
|
|
def test_gemini_tts_rejects_oversized_json_response(tmp_path, monkeypatch):
|
|
monkeypatch.setenv("GEMINI_API_KEY", "test-gemini-key")
|
|
response = StreamingResponse([b'{"candidates":', b"[{}]}"], headers={"Content-Type": "application/json"})
|
|
|
|
with patch("requests.post", return_value=response) as post:
|
|
with pytest.raises(RuntimeError, match="Gemini TTS response exceeds 8 bytes"):
|
|
tts_tool._generate_gemini_tts("hello", str(tmp_path / "out.wav"), {})
|
|
|
|
assert post.call_args.kwargs["stream"] is True
|
|
assert response.closed is True
|