hermes-agent/tests/run_agent/test_invalid_context_length_warning.py
kshitijk4poor c1647dadba fix(tests): resolve 53 CI test failures across 8 root causes
1. Telegram xdist mock pollution (37 tests): Add tests/gateway/conftest.py
   with a shared _ensure_telegram_mock() that runs at collection time.
   Under pytest-xdist, test_telegram_caption_merge.py (bare top-level
   import, no mock) would trigger the ImportError fallback in
   gateway/platforms/telegram.py, caching ChatType=None and Update=Any
   for the entire worker — cascading into 37 downstream failures.

2. VIRTUAL_ENV env var leak (4 tests): TestDetectVenvDir tests monkeypatched
   sys.prefix but didn't clear VIRTUAL_ENV. After commit 50c35dca added a
   VIRTUAL_ENV check to _detect_venv_dir(), CI's real venv leaked through.

3. Copilot base_url missing (1 test): _resolve_runtime_from_pool_entry()
   set api_mode for copilot but didn't add the base_url fallback — unlike
   openrouter, anthropic, and codex which all have one. Production bug.

4. Stale vision model assertion (1 test): _PROVIDER_VISION_MODELS added
   zai -> glm-5v-turbo but the test still expected the main model glm-5.1.

5. Reasoning item id intentionally stripped (1 test): Production code at
   run_agent.py:3738 deliberately excludes 'id' from reasoning items
   (store=False causes API 404). Test was asserting the old behavior.

6. context_length warning not reaching custom_providers (1 test): The test
   didn't pass base_url to AIAgent, so self.base_url was empty and the
   custom_providers URL comparison at line 1302 never matched.

7. Matrix room ID URL-encoding (1 test): Production code now URL-encodes
   room IDs (!room:example.com -> %21room%3Aexample.com) but the test
   assertion wasn't updated.

8. Google Workspace calendar tests (2 tests): Tests assert on +agenda CLI
   args that don't exist in the production calendar_list() function. They
   only 'passed' before because _gws_binary() returned None, the Python
   SDK fallback ran, googleapiclient import failed, SystemExit was raised,
   and post-exit assertions were never reached. Skip when gws not installed.

Remaining 4 failures (test_run_progress_topics.py) are pre-existing flaky
tests that fail inconsistently under xdist — confirmed on clean main.
2026-04-16 07:24:16 +05:30

114 lines
4.3 KiB
Python

"""Tests that invalid context_length values in config produce visible warnings."""
from unittest.mock import patch, MagicMock, call
def _build_agent(model_cfg, custom_providers=None, model="anthropic/claude-opus-4.6"):
"""Build an AIAgent with the given model config."""
cfg = {"model": model_cfg}
if custom_providers is not None:
cfg["custom_providers"] = custom_providers
base_url = model_cfg.get("base_url", "")
with (
patch("hermes_cli.config.load_config", return_value=cfg),
patch("agent.model_metadata.get_model_context_length", return_value=128_000),
patch("run_agent.get_tool_definitions", return_value=[]),
patch("run_agent.check_toolset_requirements", return_value={}),
patch("run_agent.OpenAI"),
):
from run_agent import AIAgent
agent = AIAgent(
model=model,
api_key="test-key-1234567890",
base_url=base_url,
quiet_mode=True,
skip_context_files=True,
skip_memory=True,
)
return agent
def test_valid_integer_context_length_no_warning():
"""Plain integer context_length should work silently."""
with patch("run_agent.logger") as mock_logger:
agent = _build_agent({"default": "gpt5.4", "provider": "custom",
"base_url": "http://localhost:4000/v1",
"context_length": 256000})
assert agent._config_context_length == 256000
# No warning about invalid context_length
for c in mock_logger.warning.call_args_list:
assert "Invalid" not in str(c)
def test_string_k_suffix_context_length_warns():
"""context_length: '256K' should warn the user clearly."""
with patch("run_agent.logger") as mock_logger:
agent = _build_agent({"default": "gpt5.4", "provider": "custom",
"base_url": "http://localhost:4000/v1",
"context_length": "256K"})
assert agent._config_context_length is None
# Should have warned
warning_calls = [c for c in mock_logger.warning.call_args_list
if "Invalid" in str(c) and "256K" in str(c)]
assert len(warning_calls) == 1
assert "plain integer" in str(warning_calls[0])
def test_string_numeric_context_length_works():
"""context_length: '256000' (string) should parse fine via int()."""
with patch("run_agent.logger") as mock_logger:
agent = _build_agent({"default": "gpt5.4", "provider": "custom",
"base_url": "http://localhost:4000/v1",
"context_length": "256000"})
assert agent._config_context_length == 256000
for c in mock_logger.warning.call_args_list:
assert "Invalid" not in str(c)
def test_custom_providers_invalid_context_length_warns():
"""Invalid context_length in custom_providers should warn."""
custom_providers = [
{
"name": "LiteLLM",
"base_url": "http://localhost:4000/v1",
"models": {
"gpt5.4": {"context_length": "256K"}
},
}
]
with patch("run_agent.logger") as mock_logger:
agent = _build_agent(
{"default": "gpt5.4", "provider": "custom",
"base_url": "http://localhost:4000/v1"},
custom_providers=custom_providers,
model="gpt5.4",
)
warning_calls = [c for c in mock_logger.warning.call_args_list
if "Invalid" in str(c) and "256K" in str(c)]
assert len(warning_calls) == 1
assert "custom_providers" in str(warning_calls[0])
def test_custom_providers_valid_context_length():
"""Valid integer in custom_providers should work silently."""
custom_providers = [
{
"name": "LiteLLM",
"base_url": "http://localhost:4000/v1",
"models": {
"gpt5.4": {"context_length": 256000}
},
}
]
with patch("run_agent.logger") as mock_logger:
agent = _build_agent(
{"default": "gpt5.4", "provider": "custom",
"base_url": "http://localhost:4000/v1"},
custom_providers=custom_providers,
model="gpt5.4",
)
for c in mock_logger.warning.call_args_list:
assert "Invalid" not in str(c)