fix: embedding 改 cuda + OCR 超时 300s + 重试退避 20s 起 + jitter 防雷群

- config/default.yaml: embed.device cpu → cuda
- adapters/ocr.py: _TIMEOUT_S 15 → 300（5 分钟）
- adapters/llm.py: 指数退避加 ±50% jitter 避免 24 路同时重试
- .env: LLM_RETRY_BASE_DELAY 2→20s, LLM_RETRY_MAX_DELAY 30→120s

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

adapters/llm.py

@@ -449,12 +449,15 @@ class GovernedLLMClient:
                         },
                     )
                     if attempt < self._max_retries - 1:
-                        delay = min(
+                        import random
+
+                        base = min(
                             self._retry_base_delay_s * (2**attempt),
                             self._retry_max_delay_s,
                         )
-                        if delay > 0:
-                            await asyncio.sleep(delay)
+                        jitter = base * random.uniform(0.5, 1.5)
+                        if jitter > 0:
+                            await asyncio.sleep(jitter)
                     continue
 
                 # 非瞬时、非致命 → 记遥测后直接抛出

adapters/ocr.py

@@ -14,7 +14,7 @@ from pathlib import Path  # noqa: TC003 — 运行时需要（方法签名 + ope
 import requests
 from loguru import logger
 
-_TIMEOUT_S = 15
+_TIMEOUT_S = 300
 
 
 class MonkeyOCRClient:

config/default.yaml

@@ -20,7 +20,7 @@ embed:
   backend: "local"
   model_name: "BAAI/bge-base-zh-v1.5"
   embed_dim: 768
-  device: "cpu"
+  device: "cuda"
 
 # ── Harness 自进化循环 ──
 harness: