File size: 62,258 Bytes
a1e98ae 9855610 a1e98ae 9855610 a1e98ae 9855610 a1e98ae 9855610 a1e98ae 9855610 a1e98ae 9855610 a1e98ae 9855610 a1e98ae 9855610 a1e98ae 9855610 a1e98ae 9855610 a1e98ae 9855610 a1e98ae 9855610 a1e98ae 9855610 a1e98ae 9855610 a1e98ae 9855610 a1e98ae 9855610 a1e98ae 9855610 a1e98ae 9855610 a1e98ae 9855610 a1e98ae 9855610 a1e98ae 9855610 a1e98ae 9855610 a1e98ae 9855610 a1e98ae 9855610 a1e98ae 9855610 a1e98ae 9855610 a1e98ae 9855610 a1e98ae 9855610 a1e98ae 9855610 a1e98ae 9855610 a1e98ae 9855610 a1e98ae 9855610 a1e98ae 9855610 a1e98ae 9855610 a1e98ae 9855610 a1e98ae 9855610 a1e98ae 9855610 a1e98ae 9855610 a1e98ae 9855610 a1e98ae 9855610 a1e98ae 9855610 a1e98ae 9855610 a1e98ae 9855610 a1e98ae 9855610 a1e98ae 9855610 a1e98ae 9855610 a1e98ae 9855610 a1e98ae 9855610 a1e98ae 9855610 a1e98ae 9855610 a1e98ae 9855610 a1e98ae 9855610 a1e98ae 9855610 a1e98ae 9855610 a1e98ae 9855610 a1e98ae 9855610 a1e98ae 9855610 a1e98ae 9855610 a1e98ae 9855610 a1e98ae 9855610 a1e98ae 9855610 a1e98ae 9855610 a1e98ae 9855610 a1e98ae 9855610 a1e98ae 9855610 a1e98ae 9855610 a1e98ae 9855610 a1e98ae | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 | from fastapi import (
APIRouter,
Depends,
HTTPException,
Request,
Query,
WebSocket,
WebSocketDisconnect,
)
from fastapi.responses import HTMLResponse, StreamingResponse, RedirectResponse
from typing import Optional
from pydantic import BaseModel
from app.core.auth import verify_api_key, verify_app_key, get_admin_api_key
from app.core.config import config, get_config
from app.core.batch_tasks import create_task, get_task, expire_task
from app.core.storage import get_storage, LocalStorage, RedisStorage, SQLStorage
from app.core.exceptions import AppException
from app.services.token.manager import get_token_manager
from app.services.grok.utils.batch import run_in_batches
import os
import time
import uuid
from pathlib import Path
import aiofiles
import asyncio
import orjson
from app.core.logger import logger
from app.api.v1.image import resolve_aspect_ratio
from app.services.grok.services.voice import VoiceService
from app.services.grok.services.image import image_service
from app.services.grok.models.model import ModelService
from app.services.grok.processors.image_ws_processors import ImageWSCollectProcessor
from app.services.token import EffortType
TEMPLATE_DIR = Path(__file__).parent.parent.parent / "static"
router = APIRouter()
IMAGINE_SESSION_TTL = 600
_IMAGINE_SESSIONS: dict[str, dict] = {}
_IMAGINE_SESSIONS_LOCK = asyncio.Lock()
async def _cleanup_imagine_sessions(now: float) -> None:
expired = [
key
for key, info in _IMAGINE_SESSIONS.items()
if now - float(info.get("created_at") or 0) > IMAGINE_SESSION_TTL
]
for key in expired:
_IMAGINE_SESSIONS.pop(key, None)
async def _create_imagine_session(prompt: str, aspect_ratio: str) -> str:
task_id = uuid.uuid4().hex
now = time.time()
async with _IMAGINE_SESSIONS_LOCK:
await _cleanup_imagine_sessions(now)
_IMAGINE_SESSIONS[task_id] = {
"prompt": prompt,
"aspect_ratio": aspect_ratio,
"created_at": now,
}
return task_id
async def _get_imagine_session(task_id: str) -> Optional[dict]:
if not task_id:
return None
now = time.time()
async with _IMAGINE_SESSIONS_LOCK:
await _cleanup_imagine_sessions(now)
info = _IMAGINE_SESSIONS.get(task_id)
if not info:
return None
created_at = float(info.get("created_at") or 0)
if now - created_at > IMAGINE_SESSION_TTL:
_IMAGINE_SESSIONS.pop(task_id, None)
return None
return dict(info)
async def _delete_imagine_session(task_id: str) -> None:
if not task_id:
return
async with _IMAGINE_SESSIONS_LOCK:
_IMAGINE_SESSIONS.pop(task_id, None)
async def _delete_imagine_sessions(task_ids: list[str]) -> int:
if not task_ids:
return 0
removed = 0
async with _IMAGINE_SESSIONS_LOCK:
for task_id in task_ids:
if task_id and task_id in _IMAGINE_SESSIONS:
_IMAGINE_SESSIONS.pop(task_id, None)
removed += 1
return removed
def _collect_tokens(data: dict) -> list[str]:
"""从请求数据中收集 token 列表"""
tokens = []
if isinstance(data.get("token"), str) and data["token"].strip():
tokens.append(data["token"].strip())
if isinstance(data.get("tokens"), list):
tokens.extend([str(t).strip() for t in data["tokens"] if str(t).strip()])
return tokens
def _truncate_tokens(
tokens: list[str], max_tokens: int, operation: str = "operation"
) -> tuple[list[str], bool, int]:
"""去重并截断 token 列表，返回 (unique_tokens, truncated, original_count)"""
unique_tokens = list(dict.fromkeys(tokens))
original_count = len(unique_tokens)
truncated = False
if len(unique_tokens) > max_tokens:
unique_tokens = unique_tokens[:max_tokens]
truncated = True
logger.warning(
f"{operation}: truncated from {original_count} to {max_tokens} tokens"
)
return unique_tokens, truncated, original_count
def _mask_token(token: str) -> str:
"""掩码 token 显示"""
return f"{token[:8]}...{token[-8:]}" if len(token) > 20 else token
async def render_template(filename: str):
"""渲染指定模板"""
template_path = TEMPLATE_DIR / filename
if not template_path.exists():
return HTMLResponse(f"Template {filename} not found.", status_code=404)
async with aiofiles.open(template_path, "r", encoding="utf-8") as f:
content = await f.read()
return HTMLResponse(content)
def _sse_event(payload: dict) -> str:
return f"data: {orjson.dumps(payload).decode()}\n\n"
def _verify_stream_api_key(request: Request) -> None:
api_key = get_admin_api_key()
if not api_key:
return
key = request.query_params.get("api_key")
if key != api_key:
raise HTTPException(status_code=401, detail="Invalid authentication token")
@router.get("/api/v1/admin/batch/{task_id}/stream")
async def stream_batch(task_id: str, request: Request):
_verify_stream_api_key(request)
task = get_task(task_id)
if not task:
raise HTTPException(status_code=404, detail="Task not found")
async def event_stream():
queue = task.attach()
try:
yield _sse_event({"type": "snapshot", **task.snapshot()})
final = task.final_event()
if final:
yield _sse_event(final)
return
while True:
try:
event = await asyncio.wait_for(queue.get(), timeout=15)
except asyncio.TimeoutError:
yield ": ping\n\n"
final = task.final_event()
if final:
yield _sse_event(final)
return
continue
yield _sse_event(event)
if event.get("type") in ("done", "error", "cancelled"):
return
finally:
task.detach(queue)
return StreamingResponse(event_stream(), media_type="text/event-stream")
@router.post(
"/api/v1/admin/batch/{task_id}/cancel", dependencies=[Depends(verify_api_key)]
)
async def cancel_batch(task_id: str):
task = get_task(task_id)
if not task:
raise HTTPException(status_code=404, detail="Task not found")
task.cancel()
return {"status": "success"}
@router.get("/admin", response_class=HTMLResponse, include_in_schema=False)
async def admin_login_page():
"""管理后台登录页"""
return await render_template("login/login.html")
@router.get("/", include_in_schema=False)
async def root_redirect():
return RedirectResponse(url="/admin")
@router.get("/admin/config", response_class=HTMLResponse, include_in_schema=False)
async def admin_config_page():
"""配置管理页"""
return await render_template("config/config.html")
@router.get("/admin/token", response_class=HTMLResponse, include_in_schema=False)
async def admin_token_page():
"""Token 管理页"""
return await render_template("token/token.html")
@router.get("/admin/voice", response_class=HTMLResponse, include_in_schema=False)
async def admin_voice_page():
"""Voice Live 调试页"""
return await render_template("voice/voice.html")
@router.get("/admin/imagine", response_class=HTMLResponse, include_in_schema=False)
async def admin_imagine_page():
"""Imagine 图片瀑布流"""
return await render_template("imagine/imagine.html")
class VoiceTokenResponse(BaseModel):
token: str
url: str
participant_name: str = ""
room_name: str = ""
@router.get(
"/api/v1/admin/voice/token",
dependencies=[Depends(verify_api_key)],
response_model=VoiceTokenResponse,
)
async def admin_voice_token(
voice: str = "ara",
personality: str = "assistant",
speed: float = 1.0,
):
"""获取 Grok Voice Mode (LiveKit) Token"""
token_mgr = await get_token_manager()
sso_token = None
for pool_name in ("ssoBasic", "ssoSuper"):
sso_token = token_mgr.get_token(pool_name)
if sso_token:
break
if not sso_token:
raise AppException(
"No available tokens for voice mode",
code="no_token",
status_code=503,
)
service = VoiceService()
try:
data = await service.get_token(
token=sso_token,
voice=voice,
personality=personality,
speed=speed,
)
token = data.get("token")
if not token:
raise AppException(
"Upstream returned no voice token",
code="upstream_error",
status_code=502,
)
return VoiceTokenResponse(
token=token,
url="wss://livekit.grok.com",
participant_name="",
room_name="",
)
except Exception as e:
if isinstance(e, AppException):
raise
raise AppException(
f"Voice token error: {str(e)}",
code="voice_error",
status_code=500,
)
async def _verify_imagine_ws_auth(websocket: WebSocket) -> tuple[bool, Optional[str]]:
task_id = websocket.query_params.get("task_id")
if task_id:
info = await _get_imagine_session(task_id)
if info:
return True, task_id
api_key = get_admin_api_key()
if not api_key:
return True, None
key = websocket.query_params.get("api_key")
return key == api_key, None
@router.websocket("/api/v1/admin/imagine/ws")
async def admin_imagine_ws(websocket: WebSocket):
ok, session_id = await _verify_imagine_ws_auth(websocket)
if not ok:
await websocket.close(code=1008)
return
await websocket.accept()
stop_event = asyncio.Event()
run_task: Optional[asyncio.Task] = None
async def _send(payload: dict) -> bool:
try:
await websocket.send_text(orjson.dumps(payload).decode())
return True
except Exception:
return False
async def _stop_run():
nonlocal run_task
stop_event.set()
if run_task and not run_task.done():
run_task.cancel()
try:
await run_task
except Exception:
pass
run_task = None
stop_event.clear()
async def _run(prompt: str, aspect_ratio: str):
model_id = "grok-imagine-1.0"
model_info = ModelService.get(model_id)
if not model_info or not model_info.is_image:
await _send(
{
"type": "error",
"message": "Image model is not available.",
"code": "model_not_supported",
}
)
return
token_mgr = await get_token_manager()
enable_nsfw = bool(get_config("image.image_ws_nsfw", True))
sequence = 0
run_id = uuid.uuid4().hex
await _send(
{
"type": "status",
"status": "running",
"prompt": prompt,
"aspect_ratio": aspect_ratio,
"run_id": run_id,
}
)
while not stop_event.is_set():
try:
await token_mgr.reload_if_stale()
token = None
for pool_name in ModelService.pool_candidates_for_model(
model_info.model_id
):
token = token_mgr.get_token(pool_name)
if token:
break
if not token:
await _send(
{
"type": "error",
"message": "No available tokens. Please try again later.",
"code": "rate_limit_exceeded",
}
)
await asyncio.sleep(2)
continue
upstream = image_service.stream(
token=token,
prompt=prompt,
aspect_ratio=aspect_ratio,
n=6,
enable_nsfw=enable_nsfw,
)
processor = ImageWSCollectProcessor(
model_info.model_id,
token,
n=6,
response_format="b64_json",
)
start_at = time.time()
images = await processor.process(upstream)
elapsed_ms = int((time.time() - start_at) * 1000)
if images and all(img and img != "error" for img in images):
# 一次发送所有 6 张图片
for img_b64 in images:
sequence += 1
await _send(
{
"type": "image",
"b64_json": img_b64,
"sequence": sequence,
"created_at": int(time.time() * 1000),
"elapsed_ms": elapsed_ms,
"aspect_ratio": aspect_ratio,
"run_id": run_id,
}
)
# 消耗 token（6 张图片按高成本计算）
try:
effort = (
EffortType.HIGH
if (model_info and model_info.cost.value == "high")
else EffortType.LOW
)
await token_mgr.consume(token, effort)
except Exception as e:
logger.warning(f"Failed to consume token: {e}")
else:
await _send(
{
"type": "error",
"message": "Image generation returned empty data.",
"code": "empty_image",
}
)
except asyncio.CancelledError:
break
except Exception as e:
logger.warning(f"Imagine stream error: {e}")
await _send(
{
"type": "error",
"message": str(e),
"code": "internal_error",
}
)
await asyncio.sleep(1.5)
await _send({"type": "status", "status": "stopped", "run_id": run_id})
try:
while True:
try:
raw = await websocket.receive_text()
except (RuntimeError, WebSocketDisconnect):
# WebSocket already closed or disconnected
break
try:
payload = orjson.loads(raw)
except Exception:
await _send(
{
"type": "error",
"message": "Invalid message format.",
"code": "invalid_payload",
}
)
continue
msg_type = payload.get("type")
if msg_type == "start":
prompt = str(payload.get("prompt") or "").strip()
if not prompt:
await _send(
{
"type": "error",
"message": "Prompt cannot be empty.",
"code": "empty_prompt",
}
)
continue
ratio = str(payload.get("aspect_ratio") or "2:3").strip()
if not ratio:
ratio = "2:3"
ratio = resolve_aspect_ratio(ratio)
await _stop_run()
stop_event.clear()
run_task = asyncio.create_task(_run(prompt, ratio))
elif msg_type == "stop":
await _stop_run()
elif msg_type == "ping":
await _send({"type": "pong"})
else:
await _send(
{
"type": "error",
"message": "Unknown command.",
"code": "unknown_command",
}
)
except WebSocketDisconnect:
logger.debug("WebSocket disconnected by client")
except Exception as e:
logger.warning(f"WebSocket error: {e}")
finally:
await _stop_run()
try:
from starlette.websockets import WebSocketState
if websocket.client_state == WebSocketState.CONNECTED:
await websocket.close(code=1000, reason="Server closing connection")
except Exception as e:
logger.debug(f"WebSocket close ignored: {e}")
if session_id:
await _delete_imagine_session(session_id)
class ImagineStartRequest(BaseModel):
prompt: str
aspect_ratio: Optional[str] = "2:3"
@router.post("/api/v1/admin/imagine/start", dependencies=[Depends(verify_api_key)])
async def admin_imagine_start(data: ImagineStartRequest):
prompt = (data.prompt or "").strip()
if not prompt:
raise HTTPException(status_code=400, detail="Prompt cannot be empty")
ratio = resolve_aspect_ratio(str(data.aspect_ratio or "2:3").strip() or "2:3")
task_id = await _create_imagine_session(prompt, ratio)
return {"task_id": task_id, "aspect_ratio": ratio}
class ImagineStopRequest(BaseModel):
task_ids: list[str]
@router.post("/api/v1/admin/imagine/stop", dependencies=[Depends(verify_api_key)])
async def admin_imagine_stop(data: ImagineStopRequest):
removed = await _delete_imagine_sessions(data.task_ids or [])
return {"status": "success", "removed": removed}
@router.get("/api/v1/admin/imagine/sse")
async def admin_imagine_sse(
request: Request,
task_id: str = Query(""),
prompt: str = Query(""),
aspect_ratio: str = Query("2:3"),
):
"""Imagine 图片瀑布流（SSE 兜底）"""
session = None
if task_id:
session = await _get_imagine_session(task_id)
if not session:
raise HTTPException(status_code=404, detail="Task not found")
else:
_verify_stream_api_key(request)
if session:
prompt = str(session.get("prompt") or "").strip()
ratio = str(session.get("aspect_ratio") or "2:3").strip() or "2:3"
else:
prompt = (prompt or "").strip()
if not prompt:
raise HTTPException(status_code=400, detail="Prompt cannot be empty")
ratio = str(aspect_ratio or "2:3").strip() or "2:3"
ratio = resolve_aspect_ratio(ratio)
async def event_stream():
try:
model_id = "grok-imagine-1.0"
model_info = ModelService.get(model_id)
if not model_info or not model_info.is_image:
yield _sse_event(
{
"type": "error",
"message": "Image model is not available.",
"code": "model_not_supported",
}
)
return
token_mgr = await get_token_manager()
enable_nsfw = bool(get_config("image.image_ws_nsfw", True))
sequence = 0
run_id = uuid.uuid4().hex
yield _sse_event(
{
"type": "status",
"status": "running",
"prompt": prompt,
"aspect_ratio": ratio,
"run_id": run_id,
}
)
while True:
if await request.is_disconnected():
break
if task_id:
session_alive = await _get_imagine_session(task_id)
if not session_alive:
break
try:
await token_mgr.reload_if_stale()
token = None
for pool_name in ModelService.pool_candidates_for_model(
model_info.model_id
):
token = token_mgr.get_token(pool_name)
if token:
break
if not token:
yield _sse_event(
{
"type": "error",
"message": "No available tokens. Please try again later.",
"code": "rate_limit_exceeded",
}
)
await asyncio.sleep(2)
continue
upstream = image_service.stream(
token=token,
prompt=prompt,
aspect_ratio=ratio,
n=6,
enable_nsfw=enable_nsfw,
)
processor = ImageWSCollectProcessor(
model_info.model_id,
token,
n=6,
response_format="b64_json",
)
start_at = time.time()
images = await processor.process(upstream)
elapsed_ms = int((time.time() - start_at) * 1000)
if images and all(img and img != "error" for img in images):
for img_b64 in images:
sequence += 1
yield _sse_event(
{
"type": "image",
"b64_json": img_b64,
"sequence": sequence,
"created_at": int(time.time() * 1000),
"elapsed_ms": elapsed_ms,
"aspect_ratio": ratio,
"run_id": run_id,
}
)
try:
effort = (
EffortType.HIGH
if (model_info and model_info.cost.value == "high")
else EffortType.LOW
)
await token_mgr.consume(token, effort)
except Exception as e:
logger.warning(f"Failed to consume token: {e}")
else:
yield _sse_event(
{
"type": "error",
"message": "Image generation returned empty data.",
"code": "empty_image",
}
)
except asyncio.CancelledError:
break
except Exception as e:
logger.warning(f"Imagine SSE error: {e}")
yield _sse_event(
{"type": "error", "message": str(e), "code": "internal_error"}
)
await asyncio.sleep(1.5)
yield _sse_event({"type": "status", "status": "stopped", "run_id": run_id})
finally:
if task_id:
await _delete_imagine_session(task_id)
return StreamingResponse(
event_stream(),
media_type="text/event-stream",
headers={"Cache-Control": "no-cache", "Connection": "keep-alive"},
)
@router.post("/api/v1/admin/login", dependencies=[Depends(verify_app_key)])
async def admin_login_api():
"""管理后台登录验证（使用 app_key）"""
return {"status": "success", "api_key": get_admin_api_key()}
@router.get("/api/v1/admin/config", dependencies=[Depends(verify_api_key)])
async def get_config_api():
"""获取当前配置"""
# 暴露原始配置字典
return config._config
@router.post("/api/v1/admin/config", dependencies=[Depends(verify_api_key)])
async def update_config_api(data: dict):
"""更新配置"""
try:
await config.update(data)
return {"status": "success", "message": "配置已更新"}
except Exception as e:
raise HTTPException(status_code=500, detail=str(e))
@router.get("/api/v1/admin/storage", dependencies=[Depends(verify_api_key)])
async def get_storage_info():
"""获取当前存储模式"""
storage_type = os.getenv("SERVER_STORAGE_TYPE", "").lower()
if not storage_type:
storage_type = str(get_config("storage.type")).lower()
if not storage_type:
storage = get_storage()
if isinstance(storage, LocalStorage):
storage_type = "local"
elif isinstance(storage, RedisStorage):
storage_type = "redis"
elif isinstance(storage, SQLStorage):
storage_type = {
"mysql": "mysql",
"mariadb": "mysql",
"postgres": "pgsql",
"postgresql": "pgsql",
"pgsql": "pgsql",
}.get(storage.dialect, storage.dialect)
return {"type": storage_type or "local"}
@router.get("/api/v1/admin/tokens", dependencies=[Depends(verify_api_key)])
async def get_tokens_api():
"""获取所有 Token"""
storage = get_storage()
tokens = await storage.load_tokens()
return tokens or {}
@router.post("/api/v1/admin/tokens", dependencies=[Depends(verify_api_key)])
async def update_tokens_api(data: dict):
"""更新 Token 信息"""
storage = get_storage()
try:
from app.services.token.manager import get_token_manager
from app.services.token.models import TokenInfo
async with storage.acquire_lock("tokens_save", timeout=10):
existing = await storage.load_tokens() or {}
normalized = {}
allowed_fields = set(TokenInfo.model_fields.keys())
existing_map = {}
for pool_name, tokens in existing.items():
if not isinstance(tokens, list):
continue
pool_map = {}
for item in tokens:
if isinstance(item, str):
token_data = {"token": item}
elif isinstance(item, dict):
token_data = dict(item)
else:
continue
raw_token = token_data.get("token")
if isinstance(raw_token, str) and raw_token.startswith("sso="):
token_data["token"] = raw_token[4:]
token_key = token_data.get("token")
if isinstance(token_key, str):
pool_map[token_key] = token_data
existing_map[pool_name] = pool_map
for pool_name, tokens in (data or {}).items():
if not isinstance(tokens, list):
continue
pool_list = []
for item in tokens:
if isinstance(item, str):
token_data = {"token": item}
elif isinstance(item, dict):
token_data = dict(item)
else:
continue
raw_token = token_data.get("token")
if isinstance(raw_token, str) and raw_token.startswith("sso="):
token_data["token"] = raw_token[4:]
base = existing_map.get(pool_name, {}).get(
token_data.get("token"), {}
)
merged = dict(base)
merged.update(token_data)
if merged.get("tags") is None:
merged["tags"] = []
filtered = {k: v for k, v in merged.items() if k in allowed_fields}
try:
info = TokenInfo(**filtered)
pool_list.append(info.model_dump())
except Exception as e:
logger.warning(f"Skip invalid token in pool '{pool_name}': {e}")
continue
normalized[pool_name] = pool_list
await storage.save_tokens(normalized)
mgr = await get_token_manager()
await mgr.reload()
return {"status": "success", "message": "Token 已更新"}
except Exception as e:
raise HTTPException(status_code=500, detail=str(e))
@router.post("/api/v1/admin/tokens/refresh", dependencies=[Depends(verify_api_key)])
async def refresh_tokens_api(data: dict):
"""刷新 Token 状态"""
try:
mgr = await get_token_manager()
tokens = _collect_tokens(data)
if not tokens:
raise HTTPException(status_code=400, detail="No tokens provided")
# 去重并截断
max_tokens = int(get_config("performance.usage_max_tokens"))
unique_tokens, truncated, original_count = _truncate_tokens(
tokens, max_tokens, "Usage refresh"
)
# 批量执行配置
max_concurrent = get_config("performance.usage_max_concurrent")
batch_size = get_config("performance.usage_batch_size")
async def _refresh_one(t):
return await mgr.sync_usage(
t, "grok-3", consume_on_fail=False, is_usage=False
)
raw_results = await run_in_batches(
unique_tokens,
_refresh_one,
max_concurrent=max_concurrent,
batch_size=batch_size,
)
results = {}
for token, res in raw_results.items():
if res.get("ok"):
results[token] = res.get("data", False)
else:
results[token] = False
response = {"status": "success", "results": results}
if truncated:
response["warning"] = (
f"数量超出限制，仅处理前 {max_tokens} 个（共 {original_count} 个）"
)
return response
except Exception as e:
raise HTTPException(status_code=500, detail=str(e))
@router.post(
"/api/v1/admin/tokens/refresh/async", dependencies=[Depends(verify_api_key)]
)
async def refresh_tokens_api_async(data: dict):
"""刷新 Token 状态（异步批量 + SSE 进度）"""
mgr = await get_token_manager()
tokens = _collect_tokens(data)
if not tokens:
raise HTTPException(status_code=400, detail="No tokens provided")
# 去重并截断
max_tokens = int(get_config("performance.usage_max_tokens"))
unique_tokens, truncated, original_count = _truncate_tokens(
tokens, max_tokens, "Usage refresh"
)
max_concurrent = get_config("performance.usage_max_concurrent")
batch_size = get_config("performance.usage_batch_size")
task = create_task(len(unique_tokens))
async def _run():
try:
async def _refresh_one(t: str):
return await mgr.sync_usage(
t, "grok-3", consume_on_fail=False, is_usage=False
)
async def _on_item(item: str, res: dict):
task.record(bool(res.get("ok")))
raw_results = await run_in_batches(
unique_tokens,
_refresh_one,
max_concurrent=max_concurrent,
batch_size=batch_size,
on_item=_on_item,
should_cancel=lambda: task.cancelled,
)
if task.cancelled:
task.finish_cancelled()
return
results: dict[str, bool] = {}
ok_count = 0
fail_count = 0
for token, res in raw_results.items():
if res.get("ok") and res.get("data") is True:
ok_count += 1
results[token] = True
else:
fail_count += 1
results[token] = False
await mgr._save()
result = {
"status": "success",
"summary": {
"total": len(unique_tokens),
"ok": ok_count,
"fail": fail_count,
},
"results": results,
}
warning = None
if truncated:
warning = (
f"数量超出限制，仅处理前 {max_tokens} 个（共 {original_count} 个）"
)
task.finish(result, warning=warning)
except Exception as e:
task.fail_task(str(e))
finally:
asyncio.create_task(expire_task(task.id, 300))
asyncio.create_task(_run())
return {
"status": "success",
"task_id": task.id,
"total": len(unique_tokens),
}
@router.post("/api/v1/admin/tokens/nsfw/enable", dependencies=[Depends(verify_api_key)])
async def enable_nsfw_api(data: dict):
"""批量开启 NSFW (Unhinged) 模式"""
from app.services.grok.services.nsfw import NSFWService
try:
mgr = await get_token_manager()
nsfw_service = NSFWService()
# 收集 token 列表
tokens = _collect_tokens(data)
# 若未指定，则使用所有 pool 中的 token
if not tokens:
for pool_name, pool in mgr.pools.items():
for info in pool.list():
raw = (
info.token[4:] if info.token.startswith("sso=") else info.token
)
tokens.append(raw)
if not tokens:
raise HTTPException(status_code=400, detail="No tokens available")
# 去重并截断
max_tokens = int(get_config("performance.nsfw_max_tokens"))
unique_tokens, truncated, original_count = _truncate_tokens(
tokens, max_tokens, "NSFW enable"
)
# 批量执行配置
max_concurrent = get_config("performance.nsfw_max_concurrent")
batch_size = get_config("performance.nsfw_batch_size")
# 定义 worker
async def _enable(token: str):
result = await nsfw_service.enable(token)
# 成功后添加 nsfw tag
if result.success:
await mgr.add_tag(token, "nsfw")
return {
"success": result.success,
"http_status": result.http_status,
"grpc_status": result.grpc_status,
"grpc_message": result.grpc_message,
"error": result.error,
}
# 执行批量操作
raw_results = await run_in_batches(
unique_tokens, _enable, max_concurrent=max_concurrent, batch_size=batch_size
)
# 构造返回结果（mask token）
results = {}
ok_count = 0
fail_count = 0
for token, res in raw_results.items():
masked = _mask_token(token)
if res.get("ok") and res.get("data", {}).get("success"):
ok_count += 1
results[masked] = res.get("data", {})
else:
fail_count += 1
results[masked] = res.get("data") or {"error": res.get("error")}
response = {
"status": "success",
"summary": {
"total": len(unique_tokens),
"ok": ok_count,
"fail": fail_count,
},
"results": results,
}
# 添加截断提示
if truncated:
response["warning"] = (
f"数量超出限制，仅处理前 {max_tokens} 个（共 {original_count} 个）"
)
return response
except HTTPException:
raise
except Exception as e:
logger.error(f"Enable NSFW failed: {e}")
raise HTTPException(status_code=500, detail=str(e))
@router.post(
"/api/v1/admin/tokens/nsfw/enable/async", dependencies=[Depends(verify_api_key)]
)
async def enable_nsfw_api_async(data: dict):
"""批量开启 NSFW (Unhinged) 模式（异步批量 + SSE 进度）"""
from app.services.grok.services.nsfw import NSFWService
mgr = await get_token_manager()
nsfw_service = NSFWService()
tokens = _collect_tokens(data)
if not tokens:
for pool_name, pool in mgr.pools.items():
for info in pool.list():
raw = info.token[4:] if info.token.startswith("sso=") else info.token
tokens.append(raw)
if not tokens:
raise HTTPException(status_code=400, detail="No tokens available")
# 去重并截断
max_tokens = int(get_config("performance.nsfw_max_tokens"))
unique_tokens, truncated, original_count = _truncate_tokens(
tokens, max_tokens, "NSFW enable"
)
max_concurrent = get_config("performance.nsfw_max_concurrent")
batch_size = get_config("performance.nsfw_batch_size")
task = create_task(len(unique_tokens))
async def _run():
try:
async def _enable(token: str):
result = await nsfw_service.enable(token)
if result.success:
await mgr.add_tag(token, "nsfw")
return {
"success": result.success,
"http_status": result.http_status,
"grpc_status": result.grpc_status,
"grpc_message": result.grpc_message,
"error": result.error,
}
async def _on_item(item: str, res: dict):
ok = bool(res.get("ok") and res.get("data", {}).get("success"))
task.record(ok)
raw_results = await run_in_batches(
unique_tokens,
_enable,
max_concurrent=max_concurrent,
batch_size=batch_size,
on_item=_on_item,
should_cancel=lambda: task.cancelled,
)
if task.cancelled:
task.finish_cancelled()
return
results = {}
ok_count = 0
fail_count = 0
for token, res in raw_results.items():
masked = f"{token[:8]}...{token[-8:]}" if len(token) > 20 else token
if res.get("ok") and res.get("data", {}).get("success"):
ok_count += 1
results[masked] = res.get("data", {})
else:
fail_count += 1
results[masked] = res.get("data") or {"error": res.get("error")}
await mgr._save()
result = {
"status": "success",
"summary": {
"total": len(unique_tokens),
"ok": ok_count,
"fail": fail_count,
},
"results": results,
}
warning = None
if truncated:
warning = (
f"数量超出限制，仅处理前 {max_tokens} 个（共 {original_count} 个）"
)
task.finish(result, warning=warning)
except Exception as e:
task.fail_task(str(e))
finally:
asyncio.create_task(expire_task(task.id, 300))
asyncio.create_task(_run())
return {
"status": "success",
"task_id": task.id,
"total": len(unique_tokens),
}
@router.get("/admin/cache", response_class=HTMLResponse, include_in_schema=False)
async def admin_cache_page():
"""缓存管理页"""
return await render_template("cache/cache.html")
@router.get("/api/v1/admin/cache", dependencies=[Depends(verify_api_key)])
async def get_cache_stats_api(request: Request):
"""获取缓存统计"""
from app.services.grok.services.assets import DownloadService, ListService
from app.services.token.manager import get_token_manager
from app.services.grok.utils.batch import run_in_batches
try:
dl_service = DownloadService()
image_stats = dl_service.get_stats("image")
video_stats = dl_service.get_stats("video")
mgr = await get_token_manager()
pools = mgr.pools
accounts = []
for pool_name, pool in pools.items():
for info in pool.list():
raw_token = (
info.token[4:] if info.token.startswith("sso=") else info.token
)
masked = (
f"{raw_token[:8]}...{raw_token[-16:]}"
if len(raw_token) > 24
else raw_token
)
accounts.append(
{
"token": raw_token,
"token_masked": masked,
"pool": pool_name,
"status": info.status,
"last_asset_clear_at": info.last_asset_clear_at,
}
)
scope = request.query_params.get("scope")
selected_token = request.query_params.get("token")
tokens_param = request.query_params.get("tokens")
selected_tokens = []
if tokens_param:
selected_tokens = [t.strip() for t in tokens_param.split(",") if t.strip()]
online_stats = {
"count": 0,
"status": "unknown",
"token": None,
"last_asset_clear_at": None,
}
online_details = []
account_map = {a["token"]: a for a in accounts}
max_concurrent = max(1, int(get_config("performance.assets_max_concurrent")))
batch_size = max(1, int(get_config("performance.assets_batch_size")))
max_tokens = int(get_config("performance.assets_max_tokens"))
truncated = False
original_count = 0
async def _fetch_assets(token: str):
list_service = ListService()
try:
return await list_service.count(token)
finally:
await list_service.close()
async def _fetch_detail(token: str):
account = account_map.get(token)
try:
count = await _fetch_assets(token)
return {
"detail": {
"token": token,
"token_masked": account["token_masked"] if account else token,
"count": count,
"status": "ok",
"last_asset_clear_at": account["last_asset_clear_at"]
if account
else None,
},
"count": count,
}
except Exception as e:
return {
"detail": {
"token": token,
"token_masked": account["token_masked"] if account else token,
"count": 0,
"status": f"error: {str(e)}",
"last_asset_clear_at": account["last_asset_clear_at"]
if account
else None,
},
"count": 0,
}
if selected_tokens:
selected_tokens, truncated, original_count = _truncate_tokens(
selected_tokens, max_tokens, "Assets fetch"
)
total = 0
raw_results = await run_in_batches(
selected_tokens,
_fetch_detail,
max_concurrent=max_concurrent,
batch_size=batch_size,
)
for token, res in raw_results.items():
if res.get("ok"):
data = res.get("data", {})
detail = data.get("detail")
total += data.get("count", 0)
else:
account = account_map.get(token)
detail = {
"token": token,
"token_masked": account["token_masked"] if account else token,
"count": 0,
"status": f"error: {res.get('error')}",
"last_asset_clear_at": account["last_asset_clear_at"]
if account
else None,
}
if detail:
online_details.append(detail)
online_stats = {
"count": total,
"status": "ok" if selected_tokens else "no_token",
"token": None,
"last_asset_clear_at": None,
}
scope = "selected"
elif scope == "all":
total = 0
tokens = list(dict.fromkeys([account["token"] for account in accounts]))
original_count = len(tokens)
if len(tokens) > max_tokens:
tokens = tokens[:max_tokens]
truncated = True
raw_results = await run_in_batches(
tokens,
_fetch_detail,
max_concurrent=max_concurrent,
batch_size=batch_size,
)
for token, res in raw_results.items():
if res.get("ok"):
data = res.get("data", {})
detail = data.get("detail")
total += data.get("count", 0)
else:
account = account_map.get(token)
detail = {
"token": token,
"token_masked": account["token_masked"] if account else token,
"count": 0,
"status": f"error: {res.get('error')}",
"last_asset_clear_at": account["last_asset_clear_at"]
if account
else None,
}
if detail:
online_details.append(detail)
online_stats = {
"count": total,
"status": "ok" if accounts else "no_token",
"token": None,
"last_asset_clear_at": None,
}
else:
token = selected_token
if token:
try:
count = await _fetch_assets(token)
match = next((a for a in accounts if a["token"] == token), None)
online_stats = {
"count": count,
"status": "ok",
"token": token,
"token_masked": match["token_masked"] if match else token,
"last_asset_clear_at": match["last_asset_clear_at"]
if match
else None,
}
except Exception as e:
match = next((a for a in accounts if a["token"] == token), None)
online_stats = {
"count": 0,
"status": f"error: {str(e)}",
"token": token,
"token_masked": match["token_masked"] if match else token,
"last_asset_clear_at": match["last_asset_clear_at"]
if match
else None,
}
else:
online_stats = {
"count": 0,
"status": "not_loaded",
"token": None,
"last_asset_clear_at": None,
}
response = {
"local_image": image_stats,
"local_video": video_stats,
"online": online_stats,
"online_accounts": accounts,
"online_scope": scope or "none",
"online_details": online_details,
}
if truncated:
response["warning"] = (
f"数量超出限制，仅处理前 {max_tokens} 个（共 {original_count} 个）"
)
return response
except Exception as e:
raise HTTPException(status_code=500, detail=str(e))
@router.post(
"/api/v1/admin/cache/online/load/async", dependencies=[Depends(verify_api_key)]
)
async def load_online_cache_api_async(data: dict):
"""在线资产统计（异步批量 + SSE 进度）"""
from app.services.grok.services.assets import DownloadService, ListService
from app.services.token.manager import get_token_manager
from app.services.grok.utils.batch import run_in_batches
mgr = await get_token_manager()
# 账号列表
accounts = []
for pool_name, pool in mgr.pools.items():
for info in pool.list():
raw_token = info.token[4:] if info.token.startswith("sso=") else info.token
masked = (
f"{raw_token[:8]}...{raw_token[-16:]}"
if len(raw_token) > 24
else raw_token
)
accounts.append(
{
"token": raw_token,
"token_masked": masked,
"pool": pool_name,
"status": info.status,
"last_asset_clear_at": info.last_asset_clear_at,
}
)
account_map = {a["token"]: a for a in accounts}
tokens = data.get("tokens")
scope = data.get("scope")
selected_tokens: list[str] = []
if isinstance(tokens, list):
selected_tokens = [str(t).strip() for t in tokens if str(t).strip()]
if not selected_tokens and scope == "all":
selected_tokens = [account["token"] for account in accounts]
scope = "all"
elif selected_tokens:
scope = "selected"
else:
raise HTTPException(status_code=400, detail="No tokens provided")
max_tokens = int(get_config("performance.assets_max_tokens"))
selected_tokens, truncated, original_count = _truncate_tokens(
selected_tokens, max_tokens, "Assets load"
)
max_concurrent = get_config("performance.assets_max_concurrent")
batch_size = get_config("performance.assets_batch_size")
task = create_task(len(selected_tokens))
async def _run():
try:
dl_service = DownloadService()
image_stats = dl_service.get_stats("image")
video_stats = dl_service.get_stats("video")
async def _fetch_detail(token: str):
account = account_map.get(token)
list_service = ListService()
try:
count = await list_service.count(token)
detail = {
"token": token,
"token_masked": account["token_masked"] if account else token,
"count": count,
"status": "ok",
"last_asset_clear_at": account["last_asset_clear_at"]
if account
else None,
}
return {"ok": True, "detail": detail, "count": count}
except Exception as e:
detail = {
"token": token,
"token_masked": account["token_masked"] if account else token,
"count": 0,
"status": f"error: {str(e)}",
"last_asset_clear_at": account["last_asset_clear_at"]
if account
else None,
}
return {"ok": False, "detail": detail, "count": 0}
finally:
await list_service.close()
async def _on_item(item: str, res: dict):
ok = bool(res.get("data", {}).get("ok"))
task.record(ok)
raw_results = await run_in_batches(
selected_tokens,
_fetch_detail,
max_concurrent=max_concurrent,
batch_size=batch_size,
on_item=_on_item,
should_cancel=lambda: task.cancelled,
)
if task.cancelled:
task.finish_cancelled()
return
online_details = []
total = 0
for token, res in raw_results.items():
data = res.get("data", {})
detail = data.get("detail")
if detail:
online_details.append(detail)
total += data.get("count", 0)
online_stats = {
"count": total,
"status": "ok" if selected_tokens else "no_token",
"token": None,
"last_asset_clear_at": None,
}
result = {
"local_image": image_stats,
"local_video": video_stats,
"online": online_stats,
"online_accounts": accounts,
"online_scope": scope or "none",
"online_details": online_details,
}
warning = None
if truncated:
warning = (
f"数量超出限制，仅处理前 {max_tokens} 个（共 {original_count} 个）"
)
task.finish(result, warning=warning)
except Exception as e:
task.fail_task(str(e))
finally:
asyncio.create_task(expire_task(task.id, 300))
asyncio.create_task(_run())
return {
"status": "success",
"task_id": task.id,
"total": len(selected_tokens),
}
@router.post("/api/v1/admin/cache/clear", dependencies=[Depends(verify_api_key)])
async def clear_local_cache_api(data: dict):
"""清理本地缓存"""
from app.services.grok.services.assets import DownloadService
cache_type = data.get("type", "image")
try:
dl_service = DownloadService()
result = dl_service.clear(cache_type)
return {"status": "success", "result": result}
except Exception as e:
raise HTTPException(status_code=500, detail=str(e))
@router.get("/api/v1/admin/cache/list", dependencies=[Depends(verify_api_key)])
async def list_local_cache_api(
cache_type: str = "image",
type_: str = Query(default=None, alias="type"),
page: int = 1,
page_size: int = 1000,
):
"""列出本地缓存文件"""
from app.services.grok.services.assets import DownloadService
try:
if type_:
cache_type = type_
dl_service = DownloadService()
result = dl_service.list_files(cache_type, page, page_size)
return {"status": "success", **result}
except Exception as e:
raise HTTPException(status_code=500, detail=str(e))
@router.post("/api/v1/admin/cache/item/delete", dependencies=[Depends(verify_api_key)])
async def delete_local_cache_item_api(data: dict):
"""删除单个本地缓存文件"""
from app.services.grok.services.assets import DownloadService
cache_type = data.get("type", "image")
name = data.get("name")
if not name:
raise HTTPException(status_code=400, detail="Missing file name")
try:
dl_service = DownloadService()
result = dl_service.delete_file(cache_type, name)
return {"status": "success", "result": result}
except Exception as e:
raise HTTPException(status_code=500, detail=str(e))
@router.post("/api/v1/admin/cache/online/clear", dependencies=[Depends(verify_api_key)])
async def clear_online_cache_api(data: dict):
"""清理在线缓存"""
from app.services.grok.services.assets import DeleteService
from app.services.token.manager import get_token_manager
from app.services.grok.utils.batch import run_in_batches
delete_service = None
try:
mgr = await get_token_manager()
tokens = data.get("tokens")
delete_service = DeleteService()
if isinstance(tokens, list):
token_list = [t.strip() for t in tokens if isinstance(t, str) and t.strip()]
if not token_list:
raise HTTPException(status_code=400, detail="No tokens provided")
# 去重并保持顺序
token_list = list(dict.fromkeys(token_list))
# 最大数量限制
max_tokens = int(get_config("performance.assets_max_tokens"))
token_list, truncated, original_count = _truncate_tokens(
token_list, max_tokens, "Clear online cache"
)
results = {}
max_concurrent = max(
1, int(get_config("performance.assets_max_concurrent"))
)
batch_size = max(1, int(get_config("performance.assets_batch_size")))
async def _clear_one(t: str):
try:
result = await delete_service.delete_all(t)
await mgr.mark_asset_clear(t)
return {"status": "success", "result": result}
except Exception as e:
return {"status": "error", "error": str(e)}
raw_results = await run_in_batches(
token_list,
_clear_one,
max_concurrent=max_concurrent,
batch_size=batch_size,
)
for token, res in raw_results.items():
if res.get("ok"):
results[token] = res.get("data", {})
else:
results[token] = {"status": "error", "error": res.get("error")}
response = {"status": "success", "results": results}
if truncated:
response["warning"] = (
f"数量超出限制，仅处理前 {max_tokens} 个（共 {original_count} 个）"
)
return response
token = data.get("token") or mgr.get_token()
if not token:
raise HTTPException(
status_code=400, detail="No available token to perform cleanup"
)
result = await delete_service.delete_all(token)
await mgr.mark_asset_clear(token)
return {"status": "success", "result": result}
except Exception as e:
raise HTTPException(status_code=500, detail=str(e))
finally:
if delete_service:
await delete_service.close()
@router.post(
"/api/v1/admin/cache/online/clear/async", dependencies=[Depends(verify_api_key)]
)
async def clear_online_cache_api_async(data: dict):
"""清理在线缓存（异步批量 + SSE 进度）"""
from app.services.grok.services.assets import DeleteService
from app.services.token.manager import get_token_manager
from app.services.grok.utils.batch import run_in_batches
mgr = await get_token_manager()
tokens = data.get("tokens")
if not isinstance(tokens, list):
raise HTTPException(status_code=400, detail="No tokens provided")
token_list = [t.strip() for t in tokens if isinstance(t, str) and t.strip()]
if not token_list:
raise HTTPException(status_code=400, detail="No tokens provided")
max_tokens = int(get_config("performance.assets_max_tokens"))
token_list, truncated, original_count = _truncate_tokens(
token_list, max_tokens, "Clear online cache async"
)
max_concurrent = get_config("performance.assets_max_concurrent")
batch_size = get_config("performance.assets_batch_size")
task = create_task(len(token_list))
async def _run():
delete_service = DeleteService()
try:
async def _clear_one(t: str):
try:
result = await delete_service.delete_all(t)
await mgr.mark_asset_clear(t)
return {"ok": True, "result": result}
except Exception as e:
return {"ok": False, "error": str(e)}
async def _on_item(item: str, res: dict):
ok = bool(res.get("data", {}).get("ok"))
task.record(ok)
raw_results = await run_in_batches(
token_list,
_clear_one,
max_concurrent=max_concurrent,
batch_size=batch_size,
on_item=_on_item,
should_cancel=lambda: task.cancelled,
)
if task.cancelled:
task.finish_cancelled()
return
results = {}
ok_count = 0
fail_count = 0
for token, res in raw_results.items():
data = res.get("data", {})
if data.get("ok"):
ok_count += 1
results[token] = {"status": "success", "result": data.get("result")}
else:
fail_count += 1
results[token] = {"status": "error", "error": data.get("error")}
result = {
"status": "success",
"summary": {
"total": len(token_list),
"ok": ok_count,
"fail": fail_count,
},
"results": results,
}
warning = None
if truncated:
warning = (
f"数量超出限制，仅处理前 {max_tokens} 个（共 {original_count} 个）"
)
task.finish(result, warning=warning)
except Exception as e:
task.fail_task(str(e))
finally:
await delete_service.close()
asyncio.create_task(expire_task(task.id, 300))
asyncio.create_task(_run())
return {
"status": "success",
"task_id": task.id,
"total": len(token_list),
}
|