Files
hermes/tests/run_agent/test_memory_nudge_counter_hydration.py
teknium1 0530252384 refactor(run_agent): extract run_conversation to agent/conversation_loop.py
The 3,877-line run_conversation body — the agent loop itself — moves out
of run_agent.py into a dedicated module.  AIAgent.run_conversation is
now a thin forwarder that delegates to agent.conversation_loop.run_conversation
with the AIAgent instance as the first argument.

This is the largest single extraction in the run_agent.py refactor.
The body keeps all 163 self.X references intact (rewritten as agent.X),
all nested closures, all retry/backoff/compression machinery.  Symbols
that tests or callers patch on run_agent (_set_interrupt,
handle_function_call, AIAgent class attrs) are resolved through _ra()
inside the extracted module so the patch surface is preserved.

Five tests doing inspect.getsource(AIAgent.run_conversation) updated to
scan agent.conversation_loop.run_conversation. Two source-introspection
tests (TestMemoryNudgeCounterPersistence, TestMemoryProviderTurnStart)
updated to accept either self.X (legacy) or agent.X (extracted
form) in the matched assertions.

Live E2E verified on three model paths:
  * openai/gpt-5.4 (OpenAI chat completions via OpenRouter)
  * anthropic/claude-sonnet-4.6 (Anthropic Messages via OpenRouter)
  * moonshotai/kimi-k2-thinking (reasoning model, reasoning_content path)
Plus read_file tool execution, terminal tool, web_search.

tests/run_agent/ + tests/agent/: 4313 passed, 1 pre-existing failure
(test_auxiliary_client::test_custom_endpoint... — same as on main).

run_agent.py: 9800 -> 5944 lines (-3856).
Total reduction since baseline: 16083 -> 5944 (-10139, 63%).
2026-05-16 19:26:52 -07:00

140 lines
5.7 KiB
Python

"""Regression test for issue #22357 — gateway memory-nudge counter hydration.
The gateway creates a fresh AIAgent for each inbound message in several
common scenarios (cache miss, 1h idle eviction at gateway/run.py
_AGENT_CACHE_IDLE_TTL_SECS, config-signature mismatch, process restart).
A freshly built AIAgent has _turns_since_memory=0 and _user_turn_count=0.
Without hydration from conversation_history, the memory.nudge_interval
trigger (`_turns_since_memory >= _memory_nudge_interval`) can never be
reached: every turn looks like turn 1 to the counter, so a user can chat
for hours without ever seeing a "💾 Self-improvement review:" message.
This test pins the hydration behavior added at the top of run_conversation().
"""
from __future__ import annotations
def _make_minimal_agent():
"""Build the smallest object that can run the hydration block.
The hydration code only touches attributes — no I/O, no API calls.
We can just set up a SimpleNamespace-like object with the right fields
and call run_conversation's prelude logic via a thin wrapper.
The hydration block itself is straightforward enough that we test it
by replicating it inline against the same inputs — that's the only
way to test ~10 lines deep inside a 500+ line method without rewriting
the whole agent loop.
"""
def _run_hydration(conversation_history, memory_nudge_interval=10,
prior_turn_count=0, prior_turns_since_memory=0):
"""Replicate the hydration block from run_agent.py:11128-11150.
Keeping this in sync with the production code is a one-line job; the
block has no dependencies on anything except primitives + history.
"""
user_turn_count = prior_turn_count
turns_since_memory = prior_turns_since_memory
if conversation_history and user_turn_count == 0:
prior_user_turns = sum(
1 for m in conversation_history if m.get("role") == "user"
)
if prior_user_turns > 0:
user_turn_count = prior_user_turns
if memory_nudge_interval > 0 and turns_since_memory == 0:
turns_since_memory = prior_user_turns % memory_nudge_interval
return user_turn_count, turns_since_memory
def test_no_history_leaves_counters_at_zero():
user_turn, since_mem = _run_hydration([], memory_nudge_interval=10)
assert user_turn == 0
assert since_mem == 0
def test_seven_user_turns_history_hydrates_to_seven():
"""Mid-cycle history: 7 prior user turns, interval 10 → counter at 7."""
history = []
for i in range(7):
history.append({"role": "user", "content": f"q{i}"})
history.append({"role": "assistant", "content": f"a{i}"})
user_turn, since_mem = _run_hydration(history, memory_nudge_interval=10)
assert user_turn == 7
assert since_mem == 7 # 7 % 10 = 7, next 3 turns will trigger review
def test_thirteen_turns_history_wraps_via_modulo():
"""13 prior user turns, interval 10 → counter at 3 (post-wrap), preserving cadence."""
history = [{"role": "user", "content": f"q{i}"} for i in range(13)]
user_turn, since_mem = _run_hydration(history, memory_nudge_interval=10)
assert user_turn == 13
assert since_mem == 3 # 13 % 10 = 3, next 7 turns to trigger
def test_idempotent_when_counters_already_set():
"""A cached agent with existing counters must NOT have them clobbered.
Without the `_user_turn_count == 0` guard, cached agents would lose
their accumulated state every time they re-entered the function.
"""
history = [{"role": "user", "content": "q1"}, {"role": "assistant", "content": "a1"}]
user_turn, since_mem = _run_hydration(
history, memory_nudge_interval=10,
prior_turn_count=15, prior_turns_since_memory=5,
)
# Existing counters preserved (cache hit case)
assert user_turn == 15
assert since_mem == 5
def test_zero_nudge_interval_disables_hydration_of_review_counter():
"""When memory.nudge_interval=0 (review disabled), don't touch the counter."""
history = [{"role": "user", "content": "q1"}]
user_turn, since_mem = _run_hydration(history, memory_nudge_interval=0)
assert user_turn == 1
assert since_mem == 0 # untouched when interval is 0
def test_assistant_only_history_does_not_advance_user_turn_count():
"""Defensive: only role==user messages contribute. Other roles are noise."""
history = [
{"role": "system", "content": "sys"},
{"role": "assistant", "content": "a"},
{"role": "tool", "content": "t"},
]
user_turn, since_mem = _run_hydration(history, memory_nudge_interval=10)
assert user_turn == 0
assert since_mem == 0
def test_production_code_contains_hydration_block():
"""Smoke test: confirm the hydration code is actually wired into
run_conversation(). If someone deletes it, tests above still pass
against the inline replica — this fails them awake.
The body now lives in agent/conversation_loop.py after the
run_agent.py refactor; check both files for safety.
"""
from pathlib import Path
repo = Path(__file__).resolve().parents[2]
src_ra = (repo / "run_agent.py").read_text(encoding="utf-8")
src_cl = (repo / "agent" / "conversation_loop.py").read_text(encoding="utf-8")
content = src_ra + src_cl
# Anchor on the unique comment + the modulo line.
assert "Hydrate per-session nudge counters from persisted history" in content
# The line uses ``self.`` in run_agent.py form and ``agent.`` in the
# extracted module, accept either.
assert (
"self._turns_since_memory = prior_user_turns % self._memory_nudge_interval" in content
or "agent._turns_since_memory = prior_user_turns % agent._memory_nudge_interval" in content
)