"""Pool of live Agent SDK sessions across every Claude agent (ยง3.2). One :class:`Session` is one ``ClaudeSDKClient`` (one claude subprocess). The pool owns the two decisions the adapters used to make on their own: when a session is closed for idleness (TTL by conversation kind) and which one goes when memory runs out (measured RSS of the subprocess tree against the cgroup limit, ``max_live`` where there is no limit). Eviction only ever picks ``idle && !running_turn && !pending_question`` sessions that are neither pinned (the master) nor ``dirty`` (mirror gap not yet repaired); forks and jobs go first. """ from __future__ import annotations import asyncio import contextlib import logging import os import time from dataclasses import dataclass, field from pathlib import Path from typing import TYPE_CHECKING, Any, Protocol import psutil if TYPE_CHECKING: from collections.abc import AsyncIterator, Iterator, Mapping __all__ = ["DEFAULT_TTL", "Session", "SessionClient", "SessionPool", "cgroup_limit"] _log = logging.getLogger("beaver_gateway.core.sessions") DEFAULT_TTL: Mapping[str, float | None] = { "master": None, "branch": 7200.0, "deep": 1800.0, "job": 0.0, "fork": 0.0, } """Idle seconds before a session is closed; ``None`` = never (pinned kinds).""" _EVICT_ORDER = {"fork": 0, "job": 0, "deep": 1, "branch": 2, "master": 3} _RSS_HEADROOM = 0.8 class SessionClient(Protocol): async def connect(self) -> None: ... async def query(self, prompt: str) -> None: ... def receive_response(self) -> AsyncIterator[Any]: ... async def interrupt(self) -> None: ... async def disconnect(self) -> None: ... @dataclass class Session: key: str agent: str kind: str client: SessionClient session_id: str | None resumed: bool pinned: bool = False dirty: bool = False running_turn: str | None = None pending_question: bool = False interrupt_requested: bool = False lock: asyncio.Lock = field(default_factory=asyncio.Lock) last_used: float = field(default_factory=time.monotonic) created_at: float = field(default_factory=time.monotonic) turns: int = 0 state: dict[str, Any] = field(default_factory=dict) """Scratch for policy rules (``core/policy``); dies with the process.""" @property def busy(self) -> bool: return self.lock.locked() or self.running_turn is not None @property def evictable(self) -> bool: return not (self.pinned or self.dirty or self.busy or self.pending_question) @property def pid(self) -> int | None: transport = getattr(self.client, "_transport", None) process = getattr(transport, "_process", None) pid = getattr(process, "pid", None) return pid if isinstance(pid, int) else None class SessionPool: def __init__( self, *, rss_limit: int | None = None, max_live: int = 8, ttl: Mapping[str, float | None] = DEFAULT_TTL, reap_interval: float = 60.0, ) -> None: self._sessions: dict[str, Session] = {} self._rss_limit = rss_limit if rss_limit is not None else cgroup_limit() self._max_live = max_live self._ttl = dict(ttl) self._reap_interval = reap_interval def __len__(self) -> int: return len(self._sessions) def __iter__(self) -> Iterator[Session]: return iter(list(self._sessions.values())) def __contains__(self, key: object) -> bool: return key in self._sessions @property def rss_limit(self) -> int | None: return self._rss_limit def get(self, key: str) -> Session | None: return self._sessions.get(key) def add(self, session: Session) -> Session: self._sessions[session.key] = session return session def pop(self, key: str) -> Session | None: return self._sessions.pop(key, None) def rekey(self, old: str, new: str) -> Session | None: session = self._sessions.pop(old, None) if session is None: return None stale = self._sessions.pop(new, None) session.key = new self._sessions[new] = session return stale if stale is not session else None def ttl_for(self, kind: str) -> float | None: return self._ttl.get(kind, self._ttl.get("deep")) def rss(self) -> int: try: children = psutil.Process(os.getpid()).children(recursive=True) except psutil.Error: return 0 total = 0 for child in children: with contextlib.suppress(psutil.Error): total += child.memory_info().rss return total @staticmethod def rss_of(session: Session) -> int | None: pid = session.pid if pid is None: return None try: process = psutil.Process(pid) return process.memory_info().rss + sum( c.memory_info().rss for c in process.children(recursive=True) ) except psutil.Error: return None def over_limit(self) -> bool: if self._rss_limit is not None: return self.rss() > self._rss_limit * _RSS_HEADROOM return len(self._sessions) >= self._max_live def victims(self) -> list[Session]: candidates = [s for s in self._sessions.values() if s.evictable] candidates.sort(key=lambda s: (_EVICT_ORDER.get(s.kind, 1), s.last_used)) return candidates async def make_room(self) -> int: closed = 0 while self.over_limit(): victims = self.victims() if not victims: _log.warning( "session pool over limit (%d live, rss=%d) but nothing evictable", len(self._sessions), self.rss(), ) break await self.close(victims[0].key) closed += 1 return closed async def close(self, key: str) -> None: session = self._sessions.pop(key, None) if session is None: return _log.info("closing session %s (%s, %s)", session.session_id, session.kind, key) try: await session.client.disconnect() except Exception: # noqa: BLE001 _log.exception("disconnect failed for session %s", session.session_id) async def close_all(self, *, agent: str | None = None) -> None: for session in list(self._sessions.values()): if agent is None or session.agent == agent: await self.close(session.key) async def reap_once(self) -> int: now = time.monotonic() closed = 0 for session in list(self._sessions.values()): ttl = self.ttl_for(session.kind) if ttl is None or not session.evictable: continue if now - session.last_used > ttl: await self.close(session.key) closed += 1 return closed async def reap_loop(self) -> None: while True: await asyncio.sleep(self._reap_interval) try: await self.reap_once() await self.make_room() except Exception: # noqa: BLE001 _log.exception("session reaper failed") def snapshot(self) -> list[dict[str, Any]]: now = time.monotonic() return [ { "key": s.key, "agent": s.agent, "kind": s.kind, "session_id": s.session_id, "pid": s.pid, "rss": self.rss_of(s), "idle_seconds": round(now - s.last_used, 1), "age_seconds": round(now - s.created_at, 1), "turns": s.turns, "busy": s.busy, "running_turn": s.running_turn, "pending_question": s.pending_question, "pinned": s.pinned, "dirty": s.dirty, } for s in self._sessions.values() ] def cgroup_limit() -> int | None: for path in ( "/sys/fs/cgroup/memory.max", "/sys/fs/cgroup/memory/memory.limit_in_bytes", ): try: raw = Path(path).read_text(encoding="ascii").strip() except OSError: continue if raw.isdigit() and int(raw) < 1 << 60: return int(raw) return None