1a59519244
A `/model <m> --global` switch (typed or picker) used to persist twice: the profile config.yaml AND a per-session `model_override` in the session store. The session copy has higher precedence on rehydration, so after a later global change (CLI `hermes model`, another chat's `--global`) and a gateway restart the stale override silently won — #100314 saw an explicit `gpt-5.6-sol-900k` resume as the base 272K `gpt-5.6-sol`. Now `_record_model_switch` writes config.yaml FIRST and, on success, drops the redundant session override from memory and the store. If the config write fails the switch stays a truthful session override and the confirmation says "config.yaml not updated (...)" plus the session-only hint instead of claiming "Saved to config.yaml"; a riding `--reasoning` pin follows the same effective scope. `--session` and `--once` semantics are unchanged. Tests: two invariants in tests/gateway/test_model_picker_persist.py (typed+picker clear the durable override and a fresh SessionStore rehydrates nothing; failed config write keeps the override and an honest reply), red on base. test_model_command_request_overrides now points get_hermes_home at its own config so the --provider switch resolves session-scoped as intended instead of the sandbox's fresh-install first-pick rule. Fixes #100314 Supersedes #99825 (slim redo; the original wrapped the commit boundary through a sys.modules-swapped mixin). Co-authored-by: Andrex Ibiza, MBA <andrexibiza@gmail.com>
54 lines
2.2 KiB
Python
54 lines
2.2 KiB
Python
"""Gateway ``/model <m> --reasoning <level>``: the effort rides with the pick through the same
|
|
applier ``/reasoning`` uses (session override by default, ``agent.reasoning_effort`` on --global)."""
|
|
|
|
from types import SimpleNamespace
|
|
from unittest.mock import AsyncMock
|
|
|
|
import pytest
|
|
|
|
from gateway.config import Platform
|
|
from gateway.slash_commands_model import _ModelSwitchContext
|
|
|
|
|
|
def _runner():
|
|
from gateway.run import GatewayRunner
|
|
|
|
runner = object.__new__(GatewayRunner)
|
|
calls = {}
|
|
runner._switch_cached_agent_model = lambda *_a, **_k: None
|
|
runner._record_model_switch = AsyncMock(return_value=None) # None = config write succeeded
|
|
runner._model_switch_confirmation = AsyncMock(return_value="switched")
|
|
runner._apply_reasoning_selection = (
|
|
lambda session_key, platform_key, value, persist_global=False:
|
|
calls.setdefault("applied", (session_key, platform_key, value, persist_global)) and "effort set")
|
|
return runner, calls
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_reasoning_flag_applies_after_the_switch_with_the_pick_scope():
|
|
runner, calls = _runner()
|
|
ctx = _ModelSwitchContext(session_key="telegram:c1", source=None, config_path=None,
|
|
persist_global=True, reasoning_effort="high")
|
|
result = SimpleNamespace(new_model="m", target_provider="nous")
|
|
source = SimpleNamespace(platform=Platform.TELEGRAM)
|
|
|
|
reply = await runner._commit_model_switch(result, ctx, source=source)
|
|
|
|
assert calls["applied"] == ("telegram:c1", "telegram", "high", True)
|
|
assert reply == "switched\neffort set"
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_no_flag_and_once_leave_reasoning_untouched():
|
|
runner, calls = _runner()
|
|
source = SimpleNamespace(platform=Platform.TELEGRAM)
|
|
result = SimpleNamespace(new_model="m", target_provider="nous")
|
|
await runner._commit_model_switch(
|
|
result, _ModelSwitchContext(session_key="k", source=None, config_path=None, persist_global=False),
|
|
source=source)
|
|
await runner._commit_model_switch(
|
|
result, _ModelSwitchContext(session_key="k", source=None, config_path=None, persist_global=False,
|
|
one_turn=True, reasoning_effort="high"),
|
|
source=source)
|
|
assert "applied" not in calls
|