[阶段2] FAM-Edge 重构为整视频分析+同步接口+人物服务 - 移除切片/抽帧/队列，新增 oracle_db/person_service/qa/watch_processor/video_processor，api_gateway 提供 /api/oracle/sync 与 /api/oracle/people/correct

fam-edge/src/fam_edge/video_processor.py

@@ -0,0 +1,132 @@
+"""
+VideoProcessor - 整视频分析编排
+
+流程（不再切片/抽帧）:
+1. 从 OracleDB 取当前 known_members_context（已命名/合并的人物）
+2. 按 vision_order 依次调适配器的 analyze_video（Gemini 整视频 -> NVIDIA 整视频）
+3. 首个成功结果 -> 归一化 -> 写 OracleDB（videos + events 表）
+4. 把本视频 people_mentioned 更新进 people 表（供 person_service 后续合并）
+
+降级: 全部视觉模型失败 -> 标记视频 failed（不再本地融合）
+"""
+import os
+import re
+from datetime import datetime, timedelta, timezone
+from typing import Dict, List, Optional
+
+from .logger import setup_logger
+from .config_loader import load_config
+from .model_adapters.adapter_factory import build_adapters
+from .model_adapters.base_adapter import BaseModelAdapter
+from . import oracle_db
+
+logger = setup_logger('fam-edge.video_processor')
+
+
+def _parse_event_start_from_filename(filename: str) -> str:
+    """从监控文件名解析开始时间（北京时间）。示例: 2026-08-21_081500.mp4"""
+    m = re.search(r'(\d{4})[-_](\d{2})[-_](\d{2})[_-]?(\d{2})(\d{2})(\d{2})', filename)
+    if m:
+        y, mo, d, hh, mm, ss = m.groups()
+        try:
+            dt = datetime(int(y), int(mo), int(d), int(hh), int(mm), int(ss))
+            return dt.strftime('%Y-%m-%d %H:%M:%S')
+        except ValueError:
+            pass
+    # 退而求其次: 2026-08-21 08-15-00 等
+    m2 = re.search(r'(\d{4}-\d{2}-\d{2})[ _T-]+(\d{2})[-:](\d{2})[-:](\d{2})', filename)
+    if m2:
+        return f"{m2.group(1)} {m2.group(2)}:{m2.group(3)}:{m2.group(4)}"
+    return ''
+
+
+class VideoProcessor:
+    def __init__(self, db: oracle_db.OracleDB):
+        self.config = load_config()
+        self.db = db
+        self.vision_order = self.config.get('video_processing', {}).get(
+            'vision_order', ['gemini', 'nvidia'])
+        self.vision_timeout = self.config.get('video_processing', {}).get('timeout', 900)
+        self.parse_start = self.config.get('gdrive_sync', {}).get(
+            'parse_start_from_filename', True)
+        adapters = build_adapters(self.config.get('models', []))
+        self.vision_adapters: Dict[str, BaseModelAdapter] = {
+            a.provider_name: a for a in adapters if a.get_role() == 'vision'}
+
+    def _ordered_vision_adapters(self) -> List[BaseModelAdapter]:
+        ordered = []
+        for name in self.vision_order:
+            if name in self.vision_adapters:
+                ordered.append(self.vision_adapters[name])
+        # 追加未在顺序里但启用的视觉适配器
+        for name, a in self.vision_adapters.items():
+            if name not in self.vision_order:
+                ordered.append(a)
+        return ordered
+
+    def process_video(self, video_id: int, filename: str, local_path: str) -> bool:
+        """处理一个视频记录，返回是否成功。"""
+        if not os.path.isfile(local_path):
+            logger.error(f"[video_id={video_id}] 文件不存在，跳过: {local_path}")
+            self.db.mark_video_failed(video_id, "file_missing")
+            return False
+
+        camera_name = self.db.get_video_by_filename(filename)['camera_name'] or ''
+        event_start = ''
+        if self.parse_start:
+            event_start = _parse_event_start_from_filename(filename)
+            # 回写解析到的开始时间
+            if event_start:
+                self.db._conn.execute(
+                    "UPDATE videos SET event_start_time=? WHERE id=?",
+                    (event_start, video_id))
+                self.db._conn.commit()
+
+        known = self.db.get_known_members_context()
+        logger.info(f"[video_id={video_id}] 开始整视频分析: {filename} "
+                    f"(event_start={event_start}, known_members={'有' if known else '无'})")
+
+        last_err = "no_vision_adapter"
+        for adapter in self._ordered_vision_adapters():
+            try:
+                logger.info(f"[video_id={video_id}] 尝试 {adapter.provider_name} 整视频分析")
+                result = adapter.analyze_video(local_path, known, event_start)
+            except Exception as e:
+                logger.error(f"[video_id={video_id}] {adapter.provider_name} 异常: {e}")
+                last_err = str(e)
+                continue
+            if result:
+                self._store_result(video_id, result)
+                return True
+            else:
+                last_err = f"{adapter.provider_name}_failed"
+                logger.warning(f"[video_id={video_id}] {adapter.provider_name} 未返回结果，降级下一模型")
+
+        logger.error(f"[video_id={video_id}] 所有视觉模型失败，标记 failed: {last_err}")
+        self.db.mark_video_failed(video_id, last_err)
+        return False
+
+    def _store_result(self, video_id: int, result: Dict):
+        events = result.get('events', [])
+        people = result.get('people_mentioned', [])
+        summary = result.get('global_summary', '')
+        provider = result.get('compute_provider', 'unknown')
+
+        # 归一化 events 时间戳（若模型给的是相对偏移，这里不强制；以模型输出为准）
+        norm_events = []
+        for ev in events:
+            norm_events.append({
+                "timestamp": str(ev.get('timestamp', '')),
+                "description": str(ev.get('description', '')),
+                "people": [str(p) for p in ev.get('people', []) if p],
+                "is_attention_event": bool(ev.get('is_attention_event', False)),
+            })
+
+        self.db.mark_video_processed(video_id, summary, norm_events, people, provider)
+
+        # 更新 people 表（标签级，待 person_service 合并）
+        for p in people:
+            if p and p not in ('无人', '无'):
+                self.db.upsert_person(p, source='llm')
+        logger.info(f"[video_id={video_id}] 已落库: summary={len(summary)}字, "
+                    f"events={len(norm_events)}, people={people}")