# -*- coding: utf-8 -*- """Low-noise local activity capture for the operations companion.""" from __future__ import annotations from datetime import datetime, timedelta from typing import Any try: from .agenda_contracts import normalize_observed_activity, stable_id except ImportError: from agenda_contracts import normalize_observed_activity, stable_id COLLABORATION_HINTS = { "代码", "插件", "开发", "排障", "测试", "部署", "运维", "NAS", "VM", "项目", "创作", "一起", "继续" } def classify_interaction(text: str, *, message_count: int = 1) -> str: content = str(text or "").strip() if not content: return "ordinary" if any(token in content for token in COLLABORATION_HINTS) and len(content) >= 8: return "sustained" if message_count >= 2 else "candidate" if message_count >= 4 and len(content) >= 12: return "sustained" if len(content) <= 12: return "ordinary" return "short" class ActivityCapture: def __init__(self, *, window_minutes: int = 30, min_sustained_messages: int = 3): self.window_minutes = max(5, int(window_minutes)) self.min_sustained_messages = max(2, int(min_sustained_messages)) def capture_message( self, *, text: str, event_time: datetime, source_ref: str, conversation_id: str, participant: str = "user", message_count: int = 1, topic: str = "", ) -> dict[str, Any] | None: interaction = classify_interaction(text, message_count=message_count) if interaction not in {"sustained", "candidate"}: return None if interaction == "candidate" and message_count < self.min_sustained_messages and not any( token in str(text or "") for token in COLLABORATION_HINTS ): return None bucket_minutes = max(5, self.window_minutes) bucket_start = event_time.replace(second=0, microsecond=0) - timedelta(minutes=event_time.minute % bucket_minutes) start = min(bucket_start, event_time - timedelta(minutes=min(self.window_minutes, max(1, message_count - 1) * 3))) title = str(topic or text or "持续互动").strip().replace("\n", " ")[:120] return normalize_observed_activity( { "activity_id": stable_id("activity", conversation_id, topic or "conversation", bucket_start.date().isoformat(), bucket_start.hour, bucket_start.minute), "title": title, "kind": "user_collaboration" if interaction == "sustained" else "conversation_candidate", "start_at": start.isoformat(), "end_at": event_time.isoformat(), "source_kind": "real", "source": "conversation", "source_refs": [source_ref], "participants": [participant, "bot"], "evidence_level": "L2" if interaction == "sustained" else "L1", "certainty": "high" if interaction == "sustained" else "low", "status": "active" if interaction == "sustained" else "unknown", }, now=event_time, ) @staticmethod def split_for_storage(activity: dict[str, Any]) -> dict[str, Any]: try: from .bot_self_store import split_shared_activity except ImportError: from bot_self_store import split_shared_activity return split_shared_activity(activity) def capture_hard_fact( self, *, title: str, start_at: datetime, end_at: datetime | None, source: str, source_refs: list[str], participants: list[str] | None = None, kind: str = "tool_activity", ) -> dict[str, Any]: return normalize_observed_activity( { "activity_id": stable_id("activity", source, title, start_at.isoformat(), *source_refs), "title": title, "kind": kind, "start_at": start_at.isoformat(), "end_at": end_at.isoformat() if end_at else "", "source_kind": "real", "source": source, "source_refs": source_refs, "participants": participants or ["bot"], "evidence_level": "L3", "certainty": "high", "status": "completed" if end_at else "active", }, now=start_at, )