hermes-agent/tests/hermes_cli/test_codex_models.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

181 lines
6.2 KiB
Python

import json
from unittest.mock import patch
from hermes_cli.codex_models import DEFAULT_CODEX_MODELS, get_codex_model_ids
def test_setup_wizard_codex_import_resolves():
"""Regression test for #712: setup.py must import the correct function name."""
# This mirrors the exact import used in hermes_cli/setup.py line 873.
# A prior bug had 'get_codex_models' (wrong) instead of 'get_codex_model_ids'.
from hermes_cli.codex_models import get_codex_model_ids as setup_import
assert callable(setup_import)
def test_fetch_from_api_keeps_supported_in_api_false_models(monkeypatch):
"""Regression: gpt-5.3-codex-spark is returned by the live Codex backend
with ``supported_in_api: false`` because it isn't in the public OpenAI
API. The Codex CLI / OAuth route still serves it for ChatGPT Pro
accounts, so we must not drop it on that flag. visibility=hidden is
the separate signal that *should* still filter entries out.
"""
import sys
from hermes_cli import codex_models
class _FakeResp:
status_code = 200
def json(self):
return {
"models": [
{"slug": "gpt-5.5", "priority": 0, "supported_in_api": True},
{"slug": "gpt-5.3-codex-spark", "priority": 7, "supported_in_api": False},
{"slug": "gpt-5-internal", "priority": 99, "visibility": "hidden"},
]
}
class _FakeHttpx:
@staticmethod
def get(url, headers=None, timeout=None):
return _FakeResp()
monkeypatch.setitem(sys.modules, "httpx", _FakeHttpx)
models = codex_models._fetch_models_from_api(access_token="tok")
assert "gpt-5.5" in models
assert "gpt-5.3-codex-spark" in models
assert "gpt-5-internal" not in models
def test_model_command_prompts_to_reuse_or_reauthenticate_codex_session(monkeypatch, capsys):
from hermes_cli.main import _model_flow_openai_codex
captured = {"login_calls": 0}
choices = iter(["2"])
monkeypatch.setattr("builtins.input", lambda prompt="": next(choices))
monkeypatch.setattr(
"hermes_cli.auth.get_codex_auth_status",
lambda: {"logged_in": True, "source": "hermes-auth-store"},
)
monkeypatch.setattr(
"hermes_cli.auth.resolve_codex_runtime_credentials",
lambda *args, **kwargs: {"api_key": "fresh-codex-token"},
)
def _fake_login(*args, force_new_login=False, **kwargs):
captured["login_calls"] += 1
captured["force_new_login"] = force_new_login
monkeypatch.setattr("hermes_cli.auth._login_openai_codex", _fake_login)
monkeypatch.setattr(
"hermes_cli.codex_models.get_codex_model_ids",
lambda access_token=None: ["gpt-5.4", "gpt-5.3-codex"],
)
monkeypatch.setattr(
"hermes_cli.auth._prompt_model_selection",
lambda model_ids, current_model="", **_kwargs: None,
)
_model_flow_openai_codex({}, current_model="gpt-5.4")
out = capsys.readouterr().out
assert "Use existing credentials" in out
assert "Reauthenticate (new OAuth login)" in out
assert captured["login_calls"] == 1
assert captured["force_new_login"] is True
# ── Tests for _normalize_model_for_provider ──────────────────────────
def _make_cli(model="anthropic/claude-opus-4.6", **kwargs):
"""Create a HermesCLI with minimal mocking."""
import cli as _cli_mod
from cli import HermesCLI
_clean_config = {
"model": {
"default": "anthropic/claude-opus-4.6",
"base_url": "https://openrouter.ai/api/v1",
"provider": "auto",
},
"display": {"compact": False, "tool_progress": "all", "resume_display": "full"},
"agent": {},
"terminal": {"env_type": "local"},
}
clean_env = {"LLM_MODEL": "", "HERMES_MAX_ITERATIONS": ""}
with (
patch("cli.get_tool_definitions", return_value=[]),
patch.dict("os.environ", clean_env, clear=False),
patch.dict(_cli_mod.__dict__, {"CLI_CONFIG": _clean_config}),
):
cli = HermesCLI(model=model, **kwargs)
return cli
class TestNormalizeModelForProvider:
"""_normalize_model_for_provider() trusts user-selected models.
Only two things happen:
1. Provider prefixes are stripped (API needs bare slugs)
2. The *untouched default* model is swapped for a Codex model
Everything else passes through — the API is the judge.
"""
def test_non_codex_provider_is_noop(self):
cli = _make_cli(model="gpt-5.4")
changed = cli._normalize_model_for_provider("openrouter")
assert changed is False
assert cli.model == "gpt-5.4"
def test_opencode_zen_claude_sets_messages_mode(self):
cli = _make_cli(model="opencode-zen/claude-sonnet-4-6")
cli.api_mode = "chat_completions"
changed = cli._normalize_model_for_provider("opencode-zen")
assert changed is True
assert cli.model == "claude-sonnet-4-6"
assert cli.api_mode == "anthropic_messages"
def test_default_model_replaced(self):
"""No model configured (empty default) gets swapped for codex."""
import cli as _cli_mod
_clean_config = {
"model": {
"default": "",
"base_url": "",
"provider": "auto",
},
"display": {"compact": False, "tool_progress": "all", "resume_display": "full"},
"agent": {},
"terminal": {"env_type": "local"},
}
# Don't pass model= so _model_is_default is True
with (
patch("cli.get_tool_definitions", return_value=[]),
patch.dict("os.environ", {"LLM_MODEL": "", "HERMES_MAX_ITERATIONS": ""}, clear=False),
patch.dict(_cli_mod.__dict__, {"CLI_CONFIG": _clean_config}),
):
from cli import HermesCLI
cli = HermesCLI()
assert cli._model_is_default is True
with patch(
"hermes_cli.codex_models.get_codex_model_ids",
return_value=["gpt-5.3-codex", "gpt-5.4"],
):
changed = cli._normalize_model_for_provider("openai-codex")
assert changed is True
# Uses first from available list
assert cli.model == "gpt-5.3-codex"