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.
101 lines
3.2 KiB
Python
101 lines
3.2 KiB
Python
"""Tests for reply-to pointer injection in _prepare_inbound_message_text.
|
|
|
|
The `[Replying to: "..."]` prefix is a *disambiguation pointer*, not
|
|
deduplication. It must always be injected when the user explicitly replies
|
|
to a prior message — even when the quoted text already exists somewhere
|
|
in the conversation history. History can contain the same or similar text
|
|
multiple times, and without an explicit pointer the agent has to guess
|
|
which prior message the user is referencing.
|
|
"""
|
|
import pytest
|
|
|
|
from gateway.config import GatewayConfig, Platform, PlatformConfig
|
|
from gateway.platforms.base import MessageEvent
|
|
from gateway.run import GatewayRunner
|
|
from gateway.session import SessionSource
|
|
|
|
|
|
def _make_runner() -> GatewayRunner:
|
|
runner = object.__new__(GatewayRunner)
|
|
runner.config = GatewayConfig(
|
|
platforms={Platform.TELEGRAM: PlatformConfig(enabled=True, token="fake")},
|
|
)
|
|
runner.adapters = {}
|
|
runner._model = "openai/gpt-4.1-mini"
|
|
runner._base_url = None
|
|
return runner
|
|
|
|
|
|
def _source() -> SessionSource:
|
|
return SessionSource(
|
|
platform=Platform.TELEGRAM,
|
|
chat_id="123",
|
|
chat_name="DM",
|
|
chat_type="private",
|
|
user_name="Alice",
|
|
)
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_reply_prefix_injected_when_text_absent_from_history():
|
|
runner = _make_runner()
|
|
source = _source()
|
|
event = MessageEvent(
|
|
text="What's the best time to go?",
|
|
source=source,
|
|
reply_to_message_id="42",
|
|
reply_to_text="Japan is great for culture, food, and efficiency.",
|
|
)
|
|
|
|
result = await runner._prepare_inbound_message_text(
|
|
event=event,
|
|
source=source,
|
|
history=[{"role": "user", "content": "unrelated"}],
|
|
)
|
|
|
|
assert result is not None
|
|
assert result.startswith(
|
|
'[Replying to: "Japan is great for culture, food, and efficiency."]'
|
|
)
|
|
assert result.endswith("What's the best time to go?")
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_reply_prefix_still_injected_when_text_in_history():
|
|
"""Regression test: the pointer must survive even when the quoted text
|
|
already appears in history. Previously a `found_in_history` guard
|
|
silently dropped the prefix, leaving the agent to guess which prior
|
|
message the user was referencing."""
|
|
runner = _make_runner()
|
|
source = _source()
|
|
quoted = "Japan is great for culture, food, and efficiency."
|
|
event = MessageEvent(
|
|
text="What's the best time to go?",
|
|
source=source,
|
|
reply_to_message_id="42",
|
|
reply_to_text=quoted,
|
|
)
|
|
|
|
history = [
|
|
{"role": "user", "content": "I'm thinking of going to Japan or Italy."},
|
|
{
|
|
"role": "assistant",
|
|
"content": (
|
|
f"{quoted} Italy is better if you prefer a relaxed pace."
|
|
),
|
|
},
|
|
{"role": "user", "content": "How long should I stay?"},
|
|
{"role": "assistant", "content": "For Japan, 10-14 days is ideal."},
|
|
]
|
|
|
|
result = await runner._prepare_inbound_message_text(
|
|
event=event,
|
|
source=source,
|
|
history=history,
|
|
)
|
|
|
|
assert result is not None
|
|
assert result.startswith(f'[Replying to: "{quoted}"]')
|
|
assert result.endswith("What's the best time to go?")
|
|
|
|
|