teknium1
d10bb2ab6f
`scripts/run_tests.sh tests/<dir>/` is how a change gets its regression
coverage run, so a test filed under the wrong directory is a test nobody
runs when that code changes. Two kinds of drift had accumulated.
Parallel directories for one source package, folded into the mirror:
tests/acp -> tests/acp_adapter (its __init__/conftest move with it)
tests/cli -> tests/hermes_cli (prompt_toolkit fixture merged into
hermes_cli/conftest.py)
tests/run_agent -> tests/agent (backoff fixture becomes
agent/conftest.py)
tests/relay -> tests/gateway/relay
tests/state -> tests/hermes_state
246 loose files at tests/ root, routed by the package they import/patch:
hermes_cli, hermes_state, agent, gateway, tools, plugins, tui_gateway, cron.
Installer and desktop-update script tests go to tests/scripts/{install,
desktop_update}/. 43 tests of root-level modules (batch_runner, utils,
hermes_constants, packaging) stay at the root.
Filenames drop their issue numbers (95 files: test_89315_x.py -> test_x.py);
the number stays in the module docstring where it has context.
Collisions: test_cli_skin_integration.py existed in both tests/ and tests/cli
with different subsets — merged into one (10 tests, all kept);
run_agent/test_pre_compress_memory_context.py -> agent/..._handoff.py;
tests/test_account_usage.py -> agent/test_account_usage_fetch.py;
tests/test_web_server.py -> hermes_cli/test_web_server_ws_ping.py.
Deleted: test_minisweagent_path.py (empty since PR #2804),
test_model_picker_scroll.py (tested a private copy of the logic, imported
nothing), test_process_loop_event_loop_warning.py (asserted asyncio behaviour,
imported nothing from Hermes).
Repo-root path arithmetic (Path(__file__).parents[N], dirname chains) is
bumped for the 202 files that changed depth and verified by evaluating every
such expression against the new location. classify_changes' desktop-updater
lane prefix, tests-os.yml's ignore glob and every in-tree path comment follow
the moves. tests/test_tests_tree_layout.py keeps the tree from drifting back.
120 lines
4.1 KiB
Python
120 lines
4.1 KiB
Python
from contextlib import nullcontext
|
|
|
|
from agent.conversation_compression import (
|
|
_queue_context_engine_compression_notification,
|
|
)
|
|
from cli import HermesCLI
|
|
|
|
|
|
class DummyAgent:
|
|
def __init__(self):
|
|
self.compression_enabled = True
|
|
self._cached_system_prompt = "FULL CACHED SYSTEM PROMPT SHOULD NOT BE NESTED"
|
|
self.session_id = "new-session"
|
|
self.calls = []
|
|
self.flush_calls = []
|
|
self.flush_error = None
|
|
self.host_events = []
|
|
self.boundary_calls = []
|
|
self.context_compressor = type("ContextEngineStub", (), {})()
|
|
self.context_compressor.on_session_start = self._record_boundary
|
|
|
|
def _record_boundary(self, session_id, **kwargs):
|
|
self.host_events.append("notify")
|
|
self.boundary_calls.append((session_id, kwargs))
|
|
|
|
def _flush_messages_to_session_db(self, messages, _session_id=None):
|
|
self.host_events.append("persist")
|
|
self.flush_calls.append((list(messages), _session_id))
|
|
if self.flush_error is not None:
|
|
raise self.flush_error
|
|
|
|
def _compress_context(
|
|
self,
|
|
messages,
|
|
system_message,
|
|
*,
|
|
approx_tokens=None,
|
|
focus_topic=None,
|
|
force=False,
|
|
defer_context_engine_notification=False,
|
|
):
|
|
self.calls.append(
|
|
{
|
|
"messages": messages,
|
|
"system_message": system_message,
|
|
"approx_tokens": approx_tokens,
|
|
"focus_topic": focus_topic,
|
|
"force": force,
|
|
"defer_context_engine_notification": (
|
|
defer_context_engine_notification
|
|
),
|
|
}
|
|
)
|
|
if defer_context_engine_notification:
|
|
_queue_context_engine_compression_notification(
|
|
self,
|
|
new_session_id=self.session_id,
|
|
old_session_id="old-session",
|
|
)
|
|
return ([{"role": "user", "content": "[CONTEXT SUMMARY]: compacted"}], "new system prompt")
|
|
|
|
|
|
def test_manual_compress_does_not_pass_cached_system_prompt(monkeypatch):
|
|
"""Manual /compress should rebuild the next prompt without nesting the old one."""
|
|
cli = HermesCLI.__new__(HermesCLI)
|
|
cli.conversation_history = [
|
|
{"role": "user", "content": "one"},
|
|
{"role": "assistant", "content": "two"},
|
|
{"role": "user", "content": "three"},
|
|
{"role": "assistant", "content": "four"},
|
|
]
|
|
cli.agent = DummyAgent()
|
|
cli.session_id = "old-session"
|
|
cli._pending_title = "old title"
|
|
cli._busy_command = lambda _message, **_kwargs: nullcontext()
|
|
|
|
monkeypatch.setattr(
|
|
"agent.manual_compression_feedback.summarize_manual_compression",
|
|
lambda *args, **kwargs: {
|
|
"noop": False,
|
|
"headline": "compressed",
|
|
"token_line": "tokens reduced",
|
|
"note": "",
|
|
},
|
|
)
|
|
|
|
cli._manual_compress("/compress database schema")
|
|
|
|
assert len(cli.agent.calls) == 1
|
|
call = cli.agent.calls[0]
|
|
assert call["system_message"] is None
|
|
assert call["system_message"] != cli.agent._cached_system_prompt
|
|
assert call["focus_topic"] == "database schema"
|
|
assert cli.session_id == "new-session"
|
|
assert cli._pending_title is None
|
|
assert len(cli.agent.flush_calls) == 1
|
|
assert cli.agent.host_events == ["persist", "notify"]
|
|
assert len(cli.agent.boundary_calls) == 1
|
|
|
|
|
|
def test_manual_compress_flush_failure_discards_notification(monkeypatch):
|
|
cli = HermesCLI.__new__(HermesCLI)
|
|
cli.conversation_history = [
|
|
{"role": "user", "content": "one"},
|
|
{"role": "assistant", "content": "two"},
|
|
{"role": "user", "content": "three"},
|
|
{"role": "assistant", "content": "four"},
|
|
]
|
|
cli.agent = DummyAgent()
|
|
cli.agent.flush_error = RuntimeError("synthetic child flush failure")
|
|
cli.session_id = "old-session"
|
|
cli._pending_title = "old title"
|
|
cli._busy_command = lambda _message, **_kwargs: nullcontext()
|
|
|
|
cli._manual_compress("/compress")
|
|
|
|
assert len(cli.agent.flush_calls) == 1
|
|
assert cli.agent.host_events == ["persist"]
|
|
assert cli.agent.boundary_calls == []
|