mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-07-30 19:09:28 +00:00
6b81590c55
Systematic prune per AGENTS.md test policy, one pass over every major test tree (gateway, hermes_cli, tools, agent, run_agent, plugins, cli, cron, tui_gateway, honcho/openviking, root-level): - DELETE: source-reading tests (read_text/getsource on prod files), change-detector tests (exact catalog counts, model-name snapshots, config version literals), mock-echo tests (assert a mock returns what it was told), assertion-free/trivial tests, near-duplicate parametrizations (boundaries + one representative kept), async/sync twin duplicates, cosmetic within-file variations. - KEEP (mandatory): security/redaction/approval guards, message-role alternation invariants, prompt-caching/deterministic-call-id invariants, issue-number regression tests (deduped), E2E tests. - 6 test files deleted outright (script-style/no-assert or fully redundant); conftest.py, fakes/, fixtures/ untouched. - tests/acp/conftest.py added: autouse fixture stubs the live models.dev/GitHub/Copilot/Anthropic inventory fetches that ACP server tests performed on every session create — test_server.py 147s → 3.4s, and the tests are now genuinely hermetic. - Sleep-based slowness shrunk where safe (codex_ttfb_watchdog, compression_concurrent_fork, etc.); no wall-clock assertion tightened. Verification: full hermetic suite via scripts/run_tests.sh — 2439 files, 31,130 tests passed, 0 failed, 0 flaky retries, 315s wall (baseline: 583s wall, 13,564s subprocess CPU).
82 lines
3.4 KiB
Python
82 lines
3.4 KiB
Python
"""Regression tests for issue #17335.
|
|
|
|
The ``quiet_mode=True`` fast path in :func:`model_tools.get_tool_definitions`
|
|
memoizes results to avoid re-walking the registry on every Gateway call. The
|
|
cached object must NOT be aliased into callers' return values \u2014 long-lived
|
|
Gateway processes mutate the returned list (``run_agent`` appends memory and
|
|
LCM context-engine tool schemas to ``self.tools``), and a shared list would
|
|
poison subsequent agent inits with duplicate tool names. Providers that
|
|
enforce uniqueness (DeepSeek, Xiaomi MiMo, Moonshot/Kimi) then reject the
|
|
API call with HTTP 400.
|
|
|
|
These tests pin:
|
|
- the cache-hit path returns a fresh list (existing #17098 behavior)
|
|
- the first uncached call also returns a fresh list (the fix)
|
|
- every call returns a list that is not the cached one, even after mutation
|
|
"""
|
|
from __future__ import annotations
|
|
|
|
import pytest
|
|
|
|
import model_tools
|
|
|
|
|
|
@pytest.fixture(autouse=True)
|
|
def _clear_cache():
|
|
"""Each test starts with an empty quiet_mode cache."""
|
|
model_tools._tool_defs_cache.clear()
|
|
yield
|
|
model_tools._tool_defs_cache.clear()
|
|
|
|
|
|
class TestQuietModeCacheIsolation:
|
|
|
|
def test_first_uncached_call_returns_fresh_list(self):
|
|
"""The first quiet_mode call must not alias the cached object \u2014
|
|
otherwise a caller mutating the returned list mutates the cache."""
|
|
first = model_tools.get_tool_definitions(quiet_mode=True)
|
|
assert isinstance(first, list)
|
|
# Find the cached value to compare identity.
|
|
assert len(model_tools._tool_defs_cache) == 1
|
|
cached = next(iter(model_tools._tool_defs_cache.values()))
|
|
assert first is not cached, (
|
|
"issue #17335: first quiet_mode call returned the cached list "
|
|
"by reference \u2014 mutations will leak into subsequent calls."
|
|
)
|
|
|
|
def test_cache_hit_returns_fresh_list(self):
|
|
"""The cache-hit path already returned a copy pre-fix; pin it."""
|
|
first = model_tools.get_tool_definitions(quiet_mode=True)
|
|
second = model_tools.get_tool_definitions(quiet_mode=True)
|
|
assert first is not second
|
|
cached = next(iter(model_tools._tool_defs_cache.values()))
|
|
assert second is not cached
|
|
|
|
|
|
|
|
def test_cache_bounded_by_eviction(self):
|
|
"""The cache evicts the oldest entry when it reaches the cap,
|
|
keeping the cache bounded instead of growing unbounded over a
|
|
long-lived Gateway's lifetime (#19251)."""
|
|
cap = model_tools._TOOL_DEFS_CACHE_MAX
|
|
# Fill cache to the cap with distinct keys by varying enabled_toolsets.
|
|
for i in range(cap):
|
|
model_tools.get_tool_definitions(
|
|
enabled_toolsets=[f"fake_toolset_{i}"], quiet_mode=True,
|
|
)
|
|
assert len(model_tools._tool_defs_cache) == cap
|
|
|
|
# Adding one more must evict the oldest, not clear everything and
|
|
# not grow past the cap.
|
|
model_tools.get_tool_definitions(
|
|
enabled_toolsets=["fake_toolset_overflow"], quiet_mode=True,
|
|
)
|
|
assert len(model_tools._tool_defs_cache) == cap, (
|
|
"Eviction should keep the cache at the cap, not clear it or grow"
|
|
)
|
|
|
|
def test_non_quiet_mode_does_not_use_cache(self):
|
|
"""Sanity: quiet_mode=False (TUI path) skips the cache entirely \u2014
|
|
explains why the bug only hit Gateway."""
|
|
model_tools.get_tool_definitions(quiet_mode=False)
|
|
assert len(model_tools._tool_defs_cache) == 0
|