mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-07-30 19:09:28 +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.
105 lines
3.4 KiB
Python
105 lines
3.4 KiB
Python
"""Structured stream-event protocol + dispatcher behavior.
|
|
|
|
Covers the agent→gateway delivery contract introduced to decouple *what
|
|
happened* (typed events) from *how it's delivered* (adapter decides). The
|
|
default BasePlatformAdapter rendering must reproduce today's behavior exactly;
|
|
an adapter may override format_tool_event to eat tool chrome on platforms that
|
|
can't render it.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
from unittest.mock import MagicMock
|
|
|
|
from gateway.stream_dispatch import GatewayEventDispatcher
|
|
from gateway.stream_events import (
|
|
Commentary,
|
|
GatewayNotice,
|
|
LongToolHint,
|
|
MessageChunk,
|
|
MessageStop,
|
|
ToolCallChunk,
|
|
ToolCallFinished,
|
|
)
|
|
|
|
|
|
def _base_adapter():
|
|
"""A real BasePlatformAdapter instance (abstractmethods cleared) so we
|
|
exercise the genuine default render hooks, not a mock."""
|
|
from gateway.platforms.base import BasePlatformAdapter
|
|
|
|
Concrete = type("Concrete", (BasePlatformAdapter,), {})
|
|
Concrete.__abstractmethods__ = frozenset()
|
|
return Concrete.__new__(Concrete)
|
|
|
|
|
|
class _FakeSink:
|
|
def __init__(self):
|
|
self.deltas = []
|
|
self.commentary = []
|
|
self.segment_breaks = 0
|
|
|
|
def on_delta(self, text):
|
|
self.deltas.append(text)
|
|
|
|
def on_commentary(self, text):
|
|
self.commentary.append(text)
|
|
|
|
def on_segment_break(self):
|
|
self.segment_breaks += 1
|
|
|
|
|
|
# ── Message events → sink ────────────────────────────────────────────────────
|
|
|
|
def test_message_chunk_flows_to_sink_on_delta():
|
|
sink = _FakeSink()
|
|
d = GatewayEventDispatcher(_base_adapter(), sink)
|
|
d.dispatch(MessageChunk("hello "))
|
|
d.dispatch(MessageChunk("world"))
|
|
assert sink.deltas == ["hello ", "world"]
|
|
|
|
|
|
def test_intermediate_message_stop_breaks_segment_but_final_does_not():
|
|
sink = _FakeSink()
|
|
d = GatewayEventDispatcher(_base_adapter(), sink)
|
|
d.dispatch(MessageStop(final=False))
|
|
d.dispatch(MessageStop(final=True))
|
|
assert sink.segment_breaks == 1 # only the non-final stop breaks
|
|
|
|
|
|
def test_commentary_flows_to_sink():
|
|
sink = _FakeSink()
|
|
d = GatewayEventDispatcher(_base_adapter(), sink)
|
|
d.dispatch(Commentary("I'll inspect the repo first."))
|
|
assert sink.commentary == ["I'll inspect the repo first."]
|
|
|
|
|
|
# ── Tool events → progress queue, formatted by adapter ───────────────────────
|
|
|
|
def test_tool_call_chunk_renders_default_chrome():
|
|
lines = []
|
|
d = GatewayEventDispatcher(
|
|
_base_adapter(), _FakeSink(),
|
|
enqueue_tool_line=lines.append, tool_mode="all",
|
|
)
|
|
d.dispatch(ToolCallChunk(tool_name="terminal", preview="ls -la"))
|
|
assert len(lines) == 1
|
|
assert "terminal" in lines[0]
|
|
assert "ls -la" in lines[0]
|
|
|
|
|
|
def test_new_mode_dedups_same_tool():
|
|
lines = []
|
|
d = GatewayEventDispatcher(
|
|
_base_adapter(), _FakeSink(),
|
|
enqueue_tool_line=lines.append, tool_mode="new",
|
|
)
|
|
d.dispatch(ToolCallChunk(tool_name="terminal", preview="a"))
|
|
d.dispatch(ToolCallChunk(tool_name="terminal", preview="b")) # deduped
|
|
d.dispatch(ToolCallChunk(tool_name="read_file", preview="c"))
|
|
assert len(lines) == 2 # terminal once, read_file once
|
|
|
|
|
|
# ── Control events → gateway-owned hooks ─────────────────────────────────────
|
|
|
|
|