Teknium
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.
98 lines
3.0 KiB
Python
98 lines
3.0 KiB
Python
"""Regression tests for max_tokens propagation from config.yaml to AIAgent.
|
|
|
|
Covers #20741: `model.max_tokens` was silently dropped before reaching the
|
|
gateway-spawned agent, so providers without a hardcoded default (OpenRouter
|
|
free models, Ollama Cloud, custom OpenAI-compatible endpoints) truncated long
|
|
generations with `finish_reason="length"`.
|
|
|
|
Precedence verified here:
|
|
HERMES_MAX_TOKENS env > model.max_tokens > per-provider
|
|
max_output_tokens > None
|
|
"""
|
|
|
|
import importlib
|
|
import os
|
|
import sys
|
|
import textwrap
|
|
|
|
import pytest
|
|
|
|
|
|
@pytest.fixture
|
|
def isolated_home(tmp_path, monkeypatch):
|
|
"""Isolated HERMES_HOME with a writable config.yaml and a clean module cache.
|
|
|
|
These tests deliberately re-import ``hermes_cli`` / ``gateway`` so each
|
|
config write is read fresh. To avoid leaking that purge into sibling test
|
|
files in the same worker (which breaks their import-time mocks), we snapshot
|
|
the affected modules and restore them on teardown.
|
|
"""
|
|
hermes_home = tmp_path / ".hermes"
|
|
hermes_home.mkdir()
|
|
monkeypatch.setenv("HERMES_HOME", str(hermes_home))
|
|
monkeypatch.delenv("HERMES_MAX_TOKENS", raising=False)
|
|
|
|
_saved = {
|
|
k: v
|
|
for k, v in sys.modules.items()
|
|
if k.startswith(("hermes_cli", "gateway"))
|
|
}
|
|
|
|
def write_cfg(body: str) -> None:
|
|
(hermes_home / "config.yaml").write_text(textwrap.dedent(body))
|
|
|
|
def fresh_gateway():
|
|
for mod in list(sys.modules.keys()):
|
|
if mod.startswith(("hermes_cli", "gateway")):
|
|
del sys.modules[mod]
|
|
return importlib.import_module("gateway.run")
|
|
|
|
try:
|
|
yield write_cfg, fresh_gateway
|
|
finally:
|
|
# Drop anything we (re)imported, then restore the pre-test snapshot so
|
|
# the next test file sees the module objects it was loaded with.
|
|
for k in list(sys.modules.keys()):
|
|
if k.startswith(("hermes_cli", "gateway")):
|
|
del sys.modules[k]
|
|
sys.modules.update(_saved)
|
|
|
|
|
|
def test_top_level_max_tokens_propagates(isolated_home):
|
|
"""model.max_tokens is read into the gateway runtime kwargs (#20741)."""
|
|
write_cfg, fresh_gateway = isolated_home
|
|
write_cfg(
|
|
"""
|
|
model:
|
|
default: glm-5.1
|
|
provider: openrouter
|
|
max_tokens: 16384
|
|
"""
|
|
)
|
|
grun = fresh_gateway()
|
|
kw = grun._resolve_runtime_agent_kwargs()
|
|
assert kw["max_tokens"] == 16384
|
|
|
|
|
|
def test_per_provider_max_output_tokens_fallback(isolated_home):
|
|
"""A custom provider's max_output_tokens fills in when no global is set."""
|
|
write_cfg, fresh_gateway = isolated_home
|
|
write_cfg(
|
|
"""
|
|
model:
|
|
default: glm-5.1
|
|
provider: mylocal
|
|
providers:
|
|
mylocal:
|
|
api: http://localhost:11434/v1
|
|
api_key: sk-test
|
|
default_model: glm-5.1
|
|
max_output_tokens: 12000
|
|
"""
|
|
)
|
|
grun = fresh_gateway()
|
|
kw = grun._resolve_runtime_agent_kwargs()
|
|
assert kw["max_tokens"] == 12000
|
|
|
|
|