hermes-agent/tests/gateway/test_stt_config.py
Teknium 39975613b1
test: prune wave 2 + speed fixes — 28,106 → 19,757 test functions, suite wall 315s → 294s
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.
2026-07-29 13:39:40 -07:00

97 lines
3.5 KiB
Python

"""Gateway STT config tests — honor stt.enabled: false from config.yaml."""
from pathlib import Path
from unittest.mock import AsyncMock, patch
import pytest
import yaml
from gateway.config import GatewayConfig, Platform, load_gateway_config
from gateway.platforms.base import MessageEvent, MessageType
from gateway.session import SessionSource
def test_gateway_config_stt_disabled_from_dict_nested():
config = GatewayConfig.from_dict({"stt": {"enabled": False}})
assert config.stt_enabled is False
def test_load_gateway_config_bridges_stt_enabled_from_config_yaml(tmp_path, monkeypatch):
hermes_home = tmp_path / ".hermes"
hermes_home.mkdir()
(hermes_home / "config.yaml").write_text(
yaml.dump({"stt": {"enabled": False}}),
encoding="utf-8",
)
monkeypatch.setenv("HERMES_HOME", str(hermes_home))
monkeypatch.setattr(Path, "home", lambda: tmp_path)
config = load_gateway_config()
assert config.stt_enabled is False
@pytest.mark.asyncio
async def test_enrich_message_with_transcription_returns_tuple_for_empty_content_placeholder():
"""A successful transcription whose caption is the empty-content placeholder
must still return the ``(text, transcripts)`` tuple.
The Discord adapter delivers a captionless voice note as the literal
``"(The user sent a message with no text content)"`` placeholder. When STT
succeeds we strip that redundant placeholder and return just the transcript
prefix — but the method's contract (and every caller, which unpacks the
result as ``text, transcripts = ...``) requires a 2-tuple. Returning a bare
string here raised ``ValueError: too many values to unpack`` and dropped the
whole voice message on the floor.
"""
from gateway.run import GatewayRunner
runner = GatewayRunner.__new__(GatewayRunner)
runner.config = GatewayConfig(stt_enabled=True)
runner._has_setup_skill = lambda: False
with patch(
"tools.transcription_tools.transcribe_audio",
return_value={
"success": True,
"transcript": "hello from a captionless voice note",
"provider": "local_command",
},
):
result, transcripts = await runner._enrich_message_with_transcription(
"(The user sent a message with no text content)",
["/tmp/voice.ogg"],
)
# The redundant placeholder is stripped, leaving only the transcript prefix.
assert "hello from a captionless voice note" in result
assert "(The user sent a message with no text content)" not in result
# Crucially, the transcripts are still surfaced so callers can echo them.
assert transcripts == ["hello from a captionless voice note"]
@pytest.mark.asyncio
async def test_enrich_message_with_transcription_guards_empty_transcript():
"""success=True with an empty/whitespace transcript must not emit empty
quotes — it gets a sentinel note and is excluded from transcripts (#41603)."""
from gateway.run import GatewayRunner
runner = GatewayRunner.__new__(GatewayRunner)
runner.config = GatewayConfig(stt_enabled=True)
runner._has_setup_skill = lambda: False
with patch(
"tools.transcription_tools.transcribe_audio",
return_value={"success": True, "transcript": " \n\t", "provider": "local_command"},
):
result, transcripts = await runner._enrich_message_with_transcription(
"caption",
["/tmp/voice.ogg"],
)
assert "empty or inaudible" in result
assert '""' not in result
assert transcripts == []