2002f03e42
Change-detectors, tautologies, source-reading tests, redundant duplicates, mock-echo tests and dead/unrunnable tests. Per-test rationale in the lane ledger (category + reason for every removal).
158 lines
5.0 KiB
Python
158 lines
5.0 KiB
Python
"""Regressions for the context-engine host contract.
|
|
|
|
These tests pin the five generic host-side guarantees that external context
|
|
engine plugins (e.g. hermes-lcm) rely on:
|
|
|
|
1. ``_transition_context_engine_session`` drives the full lifecycle
|
|
(on_session_end → on_session_reset → on_session_start → optional
|
|
carry_over_new_session_context) and ``reset_session_state`` delegates
|
|
to it when callers pass session metadata.
|
|
|
|
2. ``on_session_start`` receives ``conversation_id`` derived from
|
|
``_gateway_session_key`` at agent init time.
|
|
|
|
3. ``conversation_loop`` forwards canonical cache buckets
|
|
(``cache_read_tokens``, ``cache_write_tokens``, ``input_tokens``,
|
|
``output_tokens``, ``reasoning_tokens``) to the engine's
|
|
``update_from_response``, on top of the legacy aggregate keys.
|
|
|
|
4. ``_discover_context_engines`` includes plugin-registered engines (not
|
|
just repo-shipped engines under ``plugins/context_engine/``).
|
|
|
|
5. The repo-shipped ``_EngineCollector`` honors ``ctx.register_command``
|
|
from a plugin engine's ``register(ctx)`` entry point and routes it
|
|
to the global plugin command registry.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
|
|
from agent.context_compressor import ContextCompressor
|
|
from hermes_state import SessionDB
|
|
from run_agent import AIAgent
|
|
|
|
|
|
def _bare_agent() -> AIAgent:
|
|
agent = object.__new__(AIAgent)
|
|
agent.session_id = "test-session"
|
|
agent.model = "fake-model"
|
|
agent.platform = "telegram"
|
|
agent._gateway_session_key = "agent:main:telegram:dm:42"
|
|
return agent
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def test_transition_skips_optional_hooks_when_engine_lacks_them():
|
|
"""Engines that don't implement on_session_end/carry_over still work."""
|
|
class MinimalEngine:
|
|
def __init__(self):
|
|
self.context_length = 100_000
|
|
self.reset_called = False
|
|
self.start_called_with = None
|
|
|
|
def on_session_reset(self):
|
|
self.reset_called = True
|
|
|
|
def on_session_start(self, sid, **kw):
|
|
self.start_called_with = (sid, kw)
|
|
|
|
engine = MinimalEngine()
|
|
agent = _bare_agent()
|
|
agent.context_compressor = engine
|
|
|
|
# Should not raise even though on_session_end / carry_over are missing.
|
|
agent._transition_context_engine_session(
|
|
old_session_id="old",
|
|
new_session_id="new",
|
|
previous_messages=[{"role": "user", "content": "hi"}],
|
|
carry_over_context=True,
|
|
)
|
|
|
|
assert engine.reset_called is True
|
|
assert engine.start_called_with is not None
|
|
new_sid, kw = engine.start_called_with
|
|
assert new_sid == "new"
|
|
assert kw.get("old_session_id") == "old"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def test_reset_session_state_rebinds_builtin_compressor_after_session_switch(tmp_path, monkeypatch):
|
|
"""Reset-only session switches must rebind durable cooldown state to the new session."""
|
|
db = SessionDB(db_path=tmp_path / "state.db")
|
|
db.create_session("old-sid", source="cli")
|
|
db.create_session("new-sid", source="cli")
|
|
db.record_compression_failure_cooldown("old-sid", 4_000_000_000.0, "old-timeout")
|
|
db.set_compression_fallback_streak("old-sid", 2)
|
|
|
|
monkeypatch.setattr(
|
|
"agent.context_compressor.get_model_context_length",
|
|
lambda *_a, **_k: 100_000,
|
|
)
|
|
compressor = ContextCompressor(
|
|
model="fake-model",
|
|
threshold_percent=0.85,
|
|
protect_first_n=2,
|
|
protect_last_n=2,
|
|
quiet_mode=True,
|
|
)
|
|
compressor.bind_session_state(db, "old-sid")
|
|
|
|
agent = _bare_agent()
|
|
agent._session_db = db
|
|
agent.context_compressor = compressor
|
|
agent.session_id = "new-sid"
|
|
|
|
agent.reset_session_state()
|
|
|
|
assert compressor._session_id == "new-sid"
|
|
assert compressor.get_active_compression_failure_cooldown() is None
|
|
assert compressor._fallback_compression_streak == 0
|
|
assert db.get_compression_failure_cooldown("old-sid") is not None
|
|
assert db.get_compression_fallback_streak("old-sid") == 2
|
|
|
|
compressor._record_compression_failure_cooldown(30.0, "new-timeout")
|
|
|
|
assert db.get_compression_failure_cooldown("new-sid") is not None
|
|
assert db.get_compression_failure_cooldown("old-sid")["error"] == "old-timeout"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def test_engine_collector_forwards_register_command_to_plugin_manager():
|
|
"""A plugin context engine can register a slash command via ``ctx.register_command``."""
|
|
from plugins.context_engine import _EngineCollector
|
|
from hermes_cli.plugins import get_plugin_manager
|
|
|
|
handler = lambda raw_args: f"echo: {raw_args}"
|
|
|
|
collector = _EngineCollector(engine_name="my-lcm")
|
|
collector.register_command(
|
|
"my-lcm-test-cmd",
|
|
handler,
|
|
description="test command from a context engine",
|
|
args_hint="<msg>",
|
|
)
|
|
|
|
manager = get_plugin_manager()
|
|
try:
|
|
assert "my-lcm-test-cmd" in manager._plugin_commands
|
|
entry = manager._plugin_commands["my-lcm-test-cmd"]
|
|
assert entry["handler"] is handler
|
|
assert entry["args_hint"] == "<msg>"
|
|
assert entry["plugin"] == "context-engine:my-lcm"
|
|
finally:
|
|
# Clean up so we don't leak the registration across tests.
|
|
manager._plugin_commands.pop("my-lcm-test-cmd", None)
|
|
|
|
|