hermes-agent/tests/gateway/test_session_model_override_persistence.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

135 lines
4.2 KiB
Python

"""Per-session /model overrides must survive gateway restarts (#3659 salvage).
``GatewayRunner._session_model_overrides`` is in-memory, so before persistence
a gateway restart silently reverted every session to the global default model.
The non-secret parts (model/provider/base_url) are now written through to the
session store (``SessionEntry.model_override`` in sessions.json) and lazily
rehydrated on first use after a restart, with credentials re-resolved through
the normal runtime provider resolution.
Covers:
- the override survives a simulated restart (a second SessionStore instance
reading the same sessions dir, and a fresh runner rehydrating from it)
- /new (SessionStore.reset_session) clears the persisted override so a
restart cannot resurrect it
- api_key is NEVER serialized to sessions.json
"""
import json
from unittest.mock import patch
import pytest
from gateway.config import GatewayConfig, Platform
from gateway.session import (
SessionEntry,
SessionSource,
SessionStore,
sanitize_model_override,
)
OVERRIDE = {
"model": "gpt-5o",
"provider": "openai",
"api_key": "sk-SUPER-SECRET-do-not-persist",
"base_url": "https://api.openai.example/v1",
"api_mode": "responses",
}
def _make_source() -> SessionSource:
return SessionSource(
platform=Platform.TELEGRAM,
user_id="u1",
chat_id="c1",
user_name="tester",
chat_type="dm",
)
@pytest.fixture
def store_factory(tmp_path, monkeypatch):
"""Build SessionStores over a shared sessions dir, without SQLite."""
def _raise():
raise RuntimeError("SQLite disabled in test")
import hermes_state
monkeypatch.setattr(hermes_state, "SessionDB", _raise)
def _make() -> SessionStore:
store = SessionStore(sessions_dir=tmp_path, config=GatewayConfig())
assert store._db is None
return store
return _make
def _sessions_json(tmp_path) -> str:
return (tmp_path / "sessions.json").read_text(encoding="utf-8")
def test_override_persists_and_survives_restart(store_factory, tmp_path):
store = store_factory()
entry = store.get_or_create_session(_make_source())
session_key = entry.session_key
store.set_model_override(session_key, OVERRIDE)
# Simulated restart: a brand-new store instance reads the same dir.
store2 = store_factory()
persisted = store2.get_model_override(session_key)
assert persisted == {
"model": "gpt-5o",
"provider": "openai",
"base_url": "https://api.openai.example/v1",
}
def _make_runner(store):
from gateway.run import GatewayRunner
runner = object.__new__(GatewayRunner)
runner._session_model_overrides = {}
runner.session_store = store
return runner
def test_runner_rehydrates_override_after_restart(store_factory):
store = store_factory()
entry = store.get_or_create_session(_make_source())
session_key = entry.session_key
store.set_model_override(session_key, OVERRIDE)
# Simulated restart: fresh store + fresh runner with an empty in-memory
# override map, credentials re-resolved via runtime provider resolution.
runner = _make_runner(store_factory())
with patch(
"gateway.run._resolve_runtime_agent_kwargs_for_provider",
return_value={
"api_key": "sk-fresh-from-keychain",
"api_mode": "responses",
"base_url": "https://api.openai.example/v1",
"provider": "openai",
},
):
runner._rehydrate_session_model_override(session_key)
override = runner._session_model_overrides[session_key]
assert override["model"] == "gpt-5o"
assert override["provider"] == "openai"
assert override["base_url"] == "https://api.openai.example/v1"
# Credentials come from live resolution, never from disk.
assert override["api_key"] == "sk-fresh-from-keychain"
assert override["api_mode"] == "responses"
def test_sanitize_model_override():
assert sanitize_model_override(None) is None
assert sanitize_model_override({}) is None
assert sanitize_model_override({"api_key": "sk-x", "api_mode": "chat"}) is None
assert sanitize_model_override(OVERRIDE) == {
"model": "gpt-5o",
"provider": "openai",
"base_url": "https://api.openai.example/v1",
}