fix(webui): keep idle compaction out of session recency

This commit is contained in:
chengyongru 2026-06-30 18:00:41 +08:00 committed by Xubin Ren
parent bfbae5a7b3
commit 3403b87641
7 changed files with 145 additions and 25 deletions

View File

@ -8,6 +8,7 @@ from typing import TYPE_CHECKING, Callable, Coroutine
from loguru import logger
from nanobot.agent.memory import LAST_COMPACTED_AT_META
from nanobot.session.manager import Session, SessionManager
if TYPE_CHECKING:
@ -26,13 +27,36 @@ class AutoCompact:
self._archiving: set[str] = set()
self._summaries: dict[str, tuple[str, datetime]] = {}
@staticmethod
def _timestamp(ts: datetime | str | None) -> float | None:
if not ts:
return None
if isinstance(ts, str):
try:
ts = datetime.fromisoformat(ts)
except ValueError:
return None
return ts.timestamp()
def _is_expired(self, ts: datetime | str | None,
now: datetime | None = None) -> bool:
if self._ttl <= 0 or not ts:
ts_epoch = self._timestamp(ts)
if self._ttl <= 0 or ts_epoch is None:
return False
if isinstance(ts, str):
ts = datetime.fromisoformat(ts)
return ((now or datetime.now()) - ts).total_seconds() >= self._ttl * 60
now_epoch = self._timestamp(now or datetime.now())
return now_epoch is not None and now_epoch - ts_epoch >= self._ttl * 60
def _compacted_after_activity(self, key: str, last_active: datetime | str | None) -> bool:
metadata_row = self.sessions.read_session_metadata(key)
metadata = metadata_row.get("metadata") if isinstance(metadata_row, dict) else None
if not isinstance(metadata, dict):
return False
compacted_at = metadata.get(LAST_COMPACTED_AT_META)
if not isinstance(compacted_at, str):
return False
compacted_epoch = self._timestamp(compacted_at)
active_epoch = self._timestamp(last_active)
return compacted_epoch is not None and active_epoch is not None and compacted_epoch >= active_epoch
@staticmethod
def _format_summary(text: str, last_active: datetime) -> str:
@ -52,7 +76,8 @@ class AutoCompact:
continue
if key in active_session_keys:
continue
if self._is_expired(info.get("updated_at"), now):
updated_at = info.get("updated_at")
if self._is_expired(updated_at, now) and not self._compacted_after_activity(key, updated_at):
self._archiving.add(key)
schedule_background(self._archive(key))

View File

@ -33,6 +33,8 @@ if TYPE_CHECKING:
from nanobot.providers.base import LLMProvider
from nanobot.session.manager import SessionManager
LAST_COMPACTED_AT_META = "_last_compacted_at"
# ---------------------------------------------------------------------------
# MemoryStore — pure file I/O layer
@ -1003,10 +1005,11 @@ class Consolidator:
async with lock:
self.sessions.invalidate(session_key)
session = self.sessions.get_or_create(session_key)
compacted_at = datetime.now().isoformat()
messages_to_summarize = list(session.messages[session.last_consolidated:])
if not messages_to_summarize:
session.updated_at = datetime.now()
session.metadata[LAST_COMPACTED_AT_META] = compacted_at
self.sessions.save(session)
return ""
@ -1023,7 +1026,7 @@ class Consolidator:
messages_to_remove = result.dropped[result.already_consolidated_count:]
if not messages_to_remove and not messages_to_keep:
session.updated_at = datetime.now()
session.metadata[LAST_COMPACTED_AT_META] = compacted_at
self.sessions.save(session)
return ""
@ -1046,7 +1049,7 @@ class Consolidator:
session.messages = messages_to_keep
session.last_consolidated = 0
session.updated_at = datetime.now()
session.metadata[LAST_COMPACTED_AT_META] = compacted_at
self.sessions.save(session)
if messages_to_remove:

View File

@ -26,10 +26,11 @@ from nanobot.session.manager import (
_metadata_title,
)
_INDEX_VERSION = 1
_INDEX_VERSION = 2
_INDEX_FILENAME = ".webui_session_index.json"
_WEBUI_ACTIVITY_MTIME_NS = "webui_activity_mtime_ns"
_WEBUI_ACTIVITY_SIZE = "webui_activity_size"
_MESSAGE_ACTIVITY_ROLES = {"user", "assistant"}
def list_webui_sessions(session_manager: SessionManager) -> list[dict[str, Any]]:
@ -214,14 +215,40 @@ def _latest_updated_at(stored: str | None, activity: str | None) -> str | None:
return stored
def _message_activity_updated_at(messages: list[dict[str, Any]]) -> str | None:
latest: str | None = None
for item in messages:
if item.get(CRON_HISTORY_META) is True:
continue
if item.get("role") not in _MESSAGE_ACTIVITY_ROLES:
continue
timestamp = item.get("timestamp")
if isinstance(timestamp, str):
latest = _latest_updated_at(latest, timestamp)
return latest
def _session_activity_updated_at(
stored: str | None,
message_activity: str | None,
webui_activity: str | None,
) -> str | None:
return _latest_updated_at(message_activity, webui_activity) or stored
def _indexed_row_for_session(session: Session, path: Path) -> dict[str, Any]:
signature = _file_signature(path)
activity_signature = _webui_activity_signature(session.key)
activity_updated_at = _webui_activity_updated_at(activity_signature)
message_updated_at = _message_activity_updated_at(session.messages)
return {
"key": session.key,
"created_at": session.created_at.isoformat(),
"updated_at": _latest_updated_at(session.updated_at.isoformat(), activity_updated_at),
"updated_at": _session_activity_updated_at(
session.updated_at.isoformat(),
message_updated_at,
activity_updated_at,
),
"title": _metadata_title(session.metadata),
"preview": _preview_from_messages(session.messages),
"file": path.name,
@ -244,6 +271,7 @@ def _scan_session_row(session_manager: SessionManager, path: Path) -> dict[str,
return None
preview = ""
fallback_preview = ""
message_updated_at = None
scanned_records = 0
scanned_chars = 0
for line in f:
@ -251,13 +279,17 @@ def _scan_session_row(session_manager: SessionManager, path: Path) -> dict[str,
continue
scanned_records += 1
scanned_chars += len(line)
item = json.loads(line)
if item.get("_type") == "metadata":
continue
if item.get(CRON_HISTORY_META) is not True and item.get("role") in _MESSAGE_ACTIVITY_ROLES:
timestamp = item.get("timestamp")
if isinstance(timestamp, str):
message_updated_at = _latest_updated_at(message_updated_at, timestamp)
if (
scanned_records > _SESSION_LIST_PREVIEW_MAX_RECORDS
or scanned_chars > _SESSION_LIST_PREVIEW_MAX_CHARS
):
break
item = json.loads(line)
if item.get("_type") == "metadata":
continue
if item.get(CRON_HISTORY_META) is True:
continue
@ -282,7 +314,11 @@ def _scan_session_row(session_manager: SessionManager, path: Path) -> dict[str,
return {
"key": key,
"created_at": created_at_s,
"updated_at": _latest_updated_at(updated_at_s, activity_updated_at),
"updated_at": _session_activity_updated_at(
updated_at_s,
message_updated_at,
activity_updated_at,
),
"title": _metadata_title(data.get("metadata", {})),
"preview": preview or fallback_preview,
"file": path.name,

View File

@ -8,6 +8,7 @@ from unittest.mock import AsyncMock, MagicMock
import pytest
from nanobot.agent.loop import AgentLoop
from nanobot.agent.memory import LAST_COMPACTED_AT_META
from nanobot.bus.events import InboundMessage
from nanobot.bus.queue import MessageBus
from nanobot.command import CommandContext
@ -88,10 +89,11 @@ def _make_fake_compact(
async def _fake_compact(key: str, max_suffix: int = 8) -> str:
state["count"] += 1
session = loop.sessions.get_or_create(key)
compacted_at = datetime.now().isoformat()
tail = list(session.messages[session.last_consolidated:])
if not tail:
session.updated_at = datetime.now()
session.metadata[LAST_COMPACTED_AT_META] = compacted_at
loop.sessions.save(session)
return ""
@ -111,7 +113,7 @@ def _make_fake_compact(
archive_msgs = result.dropped[result.already_consolidated_count:]
if not archive_msgs and not kept:
session.updated_at = datetime.now()
session.metadata[LAST_COMPACTED_AT_META] = compacted_at
loop.sessions.save(session)
return ""
@ -132,7 +134,7 @@ def _make_fake_compact(
session.messages = kept
session.last_consolidated = 0
session.updated_at = datetime.now()
session.metadata[LAST_COMPACTED_AT_META] = compacted_at
loop.sessions.save(session)
return s
@ -1021,14 +1023,14 @@ class TestProactiveAutoCompact:
await self._run_check_expired(loop)
assert _fake_compact.state["count"] == 1
# Second tick: should NOT re-schedule (updated_at is fresh after clear)
# Second tick: should NOT re-schedule (maintenance timestamp is fresh)
await self._run_check_expired(loop)
assert _fake_compact.state["count"] == 1 # Still 1, not re-scheduled
await loop.close_mcp()
@pytest.mark.asyncio
async def test_empty_skip_refreshes_updated_at_prevents_reschedule(self, tmp_path):
"""Empty session skip refreshes updated_at, preventing immediate re-scheduling."""
async def test_empty_skip_records_compaction_prevents_reschedule(self, tmp_path):
"""Empty session skip records maintenance, preventing immediate re-scheduling."""
loop = _make_loop(tmp_path, session_ttl_minutes=15)
session = loop.sessions.get_or_create("cli:test")
session.updated_at = datetime.now() - timedelta(minutes=20)
@ -1036,11 +1038,11 @@ class TestProactiveAutoCompact:
loop.consolidator.compact_idle_session = _make_fake_compact(loop)
# First tick: skips (no messages), refreshes updated_at
# First tick: skips (no messages), records compaction metadata
await self._run_check_expired(loop)
assert "cli:test" not in loop.auto_compact._summaries
# Second tick: should NOT re-schedule because updated_at is fresh
# Second tick: should NOT re-schedule because maintenance metadata is fresh
await self._run_check_expired(loop)
assert "cli:test" not in loop.auto_compact._summaries
await loop.close_mcp()

View File

@ -6,6 +6,7 @@ from unittest.mock import AsyncMock, MagicMock
import pytest
from nanobot.agent.autocompact import AutoCompact
from nanobot.agent.memory import LAST_COMPACTED_AT_META
from nanobot.session.manager import Session, SessionManager
@ -273,6 +274,24 @@ class TestCheckExpired:
scheduler.assert_not_called()
assert "dream:20260602-155256" not in ac._archiving
def test_already_compacted_session_skips(self):
"""Expired session already maintained after last activity should not be re-scheduled."""
ac = _make_autocompact(ttl=15)
mock_sm = MagicMock(spec=SessionManager)
last_active = datetime(2026, 1, 1, 10, 0, 0)
mock_sm.list_sessions.return_value = [
{"key": "cli:done", "updated_at": last_active.isoformat()},
]
mock_sm.read_session_metadata.return_value = {
"metadata": {LAST_COMPACTED_AT_META: datetime(2026, 1, 1, 10, 30, 0).isoformat()},
}
ac.sessions = mock_sm
scheduler = MagicMock()
ac.check_expired(scheduler)
scheduler.assert_not_called()
# ---------------------------------------------------------------------------
# _archive

View File

@ -6,6 +6,7 @@ import pytest
from nanobot.agent.memory import (
_ARCHIVE_SUMMARY_MAX_CHARS,
LAST_COMPACTED_AT_META,
Consolidator,
MemoryStore,
)
@ -430,9 +431,11 @@ class TestCompactIdleSession:
)
sessions = real_consolidator.sessions
session = sessions.get_or_create("cli:test")
old_ts = session.updated_at
for i in range(20):
session.add_message("user", f"user msg {i}")
session.add_message("assistant", f"assistant msg {i}")
session.updated_at = old_ts
sessions.save(session)
result = await real_consolidator.compact_idle_session("cli:test", max_suffix=8)
@ -445,6 +448,8 @@ class TestCompactIdleSession:
assert meta is not None
assert meta["text"] == "Summary of old conversation."
assert "last_active" in meta
assert LAST_COMPACTED_AT_META in reloaded.metadata
assert reloaded.updated_at == old_ts
@pytest.mark.asyncio
async def test_summarizes_retained_suffix_not_just_dropped_prefix(
@ -518,8 +523,10 @@ class TestCompactIdleSession:
assert entries[0]["session_key"] == "cli:test"
@pytest.mark.asyncio
async def test_empty_session_refreshes_timestamp(self, real_consolidator):
"""Empty session with old updated_at → refreshed after call, returns ''."""
async def test_empty_session_records_compaction_without_refreshing_timestamp(
self, real_consolidator
):
"""Empty session with old updated_at records maintenance separately."""
from datetime import datetime, timedelta
sessions = real_consolidator.sessions
@ -532,7 +539,8 @@ class TestCompactIdleSession:
assert result == ""
reloaded = sessions.get_or_create("cli:empty")
assert reloaded.updated_at > old_ts
assert reloaded.updated_at == old_ts
assert LAST_COMPACTED_AT_META in reloaded.metadata
@pytest.mark.asyncio
async def test_nothing_summary_not_stored(self, real_consolidator, mock_provider):

View File

@ -101,6 +101,7 @@ def test_webui_session_list_uses_webui_transcript_activity_for_sort(
old_session.created_at = datetime(2026, 6, 15, 10, 0, 0)
old_session.updated_at = datetime(2026, 6, 15, 10, 0, 0)
old_session.add_message("user", "old metadata")
old_session.messages[-1]["timestamp"] = "2026-06-15T10:00:00"
old_session.updated_at = datetime(2026, 6, 15, 10, 0, 0)
manager.save(old_session)
@ -108,6 +109,7 @@ def test_webui_session_list_uses_webui_transcript_activity_for_sort(
newer_metadata.created_at = datetime(2026, 6, 15, 11, 0, 0)
newer_metadata.updated_at = datetime(2026, 6, 15, 11, 0, 0)
newer_metadata.add_message("user", "newer metadata")
newer_metadata.messages[-1]["timestamp"] = "2026-06-15T11:00:00"
newer_metadata.updated_at = datetime(2026, 6, 15, 11, 0, 0)
manager.save(newer_metadata)
@ -141,6 +143,7 @@ def test_webui_session_list_rescans_when_transcript_changes(
session.created_at = datetime(2026, 6, 15, 10, 0, 0)
session.updated_at = datetime(2026, 6, 15, 10, 0, 0)
session.add_message("user", "preview")
session.messages[-1]["timestamp"] = "2026-06-15T10:00:00"
session.updated_at = datetime(2026, 6, 15, 10, 0, 0)
manager.save(session)
@ -169,6 +172,30 @@ def test_webui_session_list_rescans_when_transcript_changes(
assert rows[0]["updated_at"].startswith("2026-06-15T12:30:00")
def test_webui_session_list_sorts_by_message_activity_not_maintenance_timestamp(
tmp_path: Path,
) -> None:
manager = SessionManager(tmp_path)
old = manager.get_or_create("websocket:old")
old.created_at = datetime(2026, 6, 5, 10, 0, 0)
old.add_message("user", "old real activity")
old.messages[-1]["timestamp"] = "2026-06-05T10:00:00"
old.updated_at = datetime(2026, 6, 30, 17, 40, 0)
manager.save(old)
newer = manager.get_or_create("websocket:newer")
newer.created_at = datetime(2026, 6, 24, 10, 0, 0)
newer.add_message("user", "newer real activity")
newer.messages[-1]["timestamp"] = "2026-06-24T10:00:00"
newer.updated_at = datetime(2026, 6, 24, 10, 0, 0)
manager.save(newer)
rows = list_webui_sessions(manager)
assert [row["key"] for row in rows] == ["websocket:newer", "websocket:old"]
assert rows[1]["updated_at"] == "2026-06-05T10:00:00"
def list_webui_sessions(manager: SessionManager) -> list[dict]:
return session_list_index.list_webui_sessions(manager)