nanobot/nanobot/agent/autocompact.py
chengyongru d1a94dae8a
refactor(dream): replace two-phase Dream class with simple cron + process_direct (#3990)
* refactor(dream): replace two-phase Dream class with simple cron + process_direct

- Remove the heavyweight Dream class (AgentRunner-based two-phase system)
  from nanobot/agent/memory.py
- Delete dream_phase1.md and dream_phase2.md templates
- New dream.md template serves as the consolidation prompt
- Cron callback uses agent.process_direct(prompt, session_key=\"dream\")
  instead of agent.dream.run()
- Always performs git auto_commit after execution
- /dream command updated to use process_direct + git commit
- DreamConfig kept for backward compatibility; deprecated fields
  (model_override, max_batch_size, max_iterations, annotate_line_ages)
  are ignored but accepted in config
- interval_h remains configurable via agents.defaults.dream.interval_h
- Update tests and webui settings to match new architecture

* feat(loop): add ephemeral mode to process_direct, skip history writes for Dream

When ephemeral=True, _state_save skips enforce_file_cap (which calls
raw_archive -> append_history) and consolidator.maybe_consolidate_by_tokens.
This prevents Dream sessions from creating a positive feedback loop where
they process their own output. The session IS still saved to disk.

* fix(loop): skip extra hooks for ephemeral sessions (Dream)

* feat(dream): per-run timestamped sessions with rotation for WebUI

* test(config): restore DreamConfig schedule and alias tests

* fix(dream): include LLM response summary in git auto-commit message

The old two-phase Dream class included the Phase 1 analysis in the git
commit message body. The new single-phase version lost this. Restore it
by extracting resp.content from the process_direct return value and
appending it to the commit message in both the cron handler and the
/dream command.

* fix(test): accept ephemeral kwarg in test_openai_api fake_process

* refactor(dream): merge dream_session.py into MemoryStore

The standalone dream_session.py module only contained three small helpers
that all revolve around MemoryStore concerns (session keys, commit messages,
file pruning). Fold them into MemoryStore as @staticmethod to reduce
indirection and avoid a 35-line module with no independent reason to exist.

* fix(test): address code review — patch correct instance, use actual function

- Fix test_ephemeral_skips_raw_archive to patch loop.context.memory
  instead of the fixture's separate MemoryStore instance
- Fix TestDreamCommitMessage to call MemoryStore.build_dream_commit_message
  instead of reimplementing the logic inline
- Move Dream helpers in memory.py above the Consolidator section comment
  to avoid misleading visual boundary

* fix(dream): gate cursor advancement and restrict tools

maintainer edit: Dream now processes backlog from the oldest unprocessed entries, only advances the cursor after a completed ephemeral run, and uses a restricted file-only tool registry for background consolidation.

* fix(dream): skip idle compact for dream sessions

Dream runs use internal dream:* sessions that are pruned by Dream retention. Exclude them from AutoCompact scheduling, archive execution, and summary injection so idle-session compaction cannot truncate Dream transcripts.

* fix(dream): keep batched history isolated

* feat(dream): tag archived memory for single-phase Dream

---------

Co-authored-by: Xubin Ren <52506698+Re-bin@users.noreply.github.com>
2026-06-02 22:46:47 +08:00

97 lines
3.9 KiB
Python

"""Auto compact: proactive compression of idle sessions to reduce token cost and latency."""
from __future__ import annotations
from collections.abc import Collection
from datetime import datetime
from typing import TYPE_CHECKING, Callable, Coroutine
from loguru import logger
from nanobot.session.manager import Session, SessionManager
if TYPE_CHECKING:
from nanobot.agent.memory import Consolidator
class AutoCompact:
_RECENT_SUFFIX_MESSAGES = 8
_INTERNAL_SESSION_PREFIXES = ("dream:",)
def __init__(self, sessions: SessionManager, consolidator: Consolidator,
session_ttl_minutes: int = 0):
self.sessions = sessions
self.consolidator = consolidator
self._ttl = session_ttl_minutes
self._archiving: set[str] = set()
self._summaries: dict[str, tuple[str, datetime]] = {}
def _is_expired(self, ts: datetime | str | None,
now: datetime | None = None) -> bool:
if self._ttl <= 0 or not ts:
return False
if isinstance(ts, str):
ts = datetime.fromisoformat(ts)
return ((now or datetime.now()) - ts).total_seconds() >= self._ttl * 60
@staticmethod
def _format_summary(text: str, last_active: datetime) -> str:
return f"Previous conversation summary (last active {last_active.isoformat()}):\n{text}"
@classmethod
def _is_internal_session(cls, key: str) -> bool:
return key.startswith(cls._INTERNAL_SESSION_PREFIXES)
def check_expired(self, schedule_background: Callable[[Coroutine], None],
active_session_keys: Collection[str] = ()) -> None:
"""Schedule archival for idle sessions, skipping those with in-flight agent tasks."""
now = datetime.now()
for info in self.sessions.list_sessions():
key = info.get("key", "")
if not key or self._is_internal_session(key) or key in self._archiving:
continue
if key in active_session_keys:
continue
if self._is_expired(info.get("updated_at"), now):
self._archiving.add(key)
schedule_background(self._archive(key))
async def _archive(self, key: str) -> None:
if self._is_internal_session(key):
self._archiving.discard(key)
return
try:
summary = await self.consolidator.compact_idle_session(
key, self._RECENT_SUFFIX_MESSAGES,
)
if summary and summary != "(nothing)":
session = self.sessions.get_or_create(key)
meta = session.metadata.get("_last_summary")
if isinstance(meta, dict):
self._summaries[key] = (
meta["text"],
datetime.fromisoformat(meta["last_active"]),
)
except Exception:
logger.exception("Auto-compact: failed for {}", key)
finally:
self._archiving.discard(key)
def prepare_session(self, session: Session, key: str) -> tuple[Session, str | None]:
if self._is_internal_session(key):
self._archiving.discard(key)
self._summaries.pop(key, None)
return session, None
if key in self._archiving or self._is_expired(session.updated_at):
logger.info("Auto-compact: reloading session {} (archiving={})", key, key in self._archiving)
session = self.sessions.get_or_create(key)
# Hot path: summary from in-memory dict (process hasn't restarted).
entry = self._summaries.pop(key, None)
if entry:
return session, self._format_summary(entry[0], entry[1])
# Cold path: summary persisted in session metadata (process restarted).
meta = session.metadata.get("_last_summary")
if isinstance(meta, dict):
return session, self._format_summary(meta["text"], datetime.fromisoformat(meta["last_active"]))
return session, None