feat: 公开用户排行榜页面 + 修复 checkpointer 连接与前端依赖
- 新增公开排行榜页面与后端 public_leaderboard 路由 - 完善 skills/agents 路由 - checkpointer Postgres 改用连接池(自愈), 解决连接关闭后定时任务连环失败 - 修复前端 mermaid 依赖未声明导致 Vite 解析失败 (新增 pnpm-lock) Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
吉鑫升andClaude Opus 4.8 committed
1 parent
8113b822c5
commit
80d2db6315
26 files changed
+1877
-967
No files matched your search
@@ -2,12 +2,12 @@ import asyncio
|
||||
import logging
|
||||
import os
|
||||
import queue
|
||||
import sys
|
||||
import threading
|
||||
from collections.abc import AsyncGenerator
|
||||
from contextlib import asynccontextmanager
|
||||
from datetime import datetime
|
||||
from time import perf_counter
|
||||
import sys
|
||||
import threading
|
||||
from collections.abc import AsyncGenerator
|
||||
from contextlib import asynccontextmanager
|
||||
from datetime import datetime
|
||||
from time import perf_counter
|
||||
|
||||
from dotenv import load_dotenv
|
||||
from fastapi import FastAPI
|
||||
@@ -29,13 +29,13 @@ from app.gateway.routers import (
|
||||
ai_writing,
|
||||
admin_users,
|
||||
agents,
|
||||
artifacts,
|
||||
assistants_compat,
|
||||
auth,
|
||||
browser_context,
|
||||
channels,
|
||||
checkpoint_migration,
|
||||
feedback,
|
||||
artifacts,
|
||||
assistants_compat,
|
||||
auth,
|
||||
browser_context,
|
||||
channels,
|
||||
checkpoint_migration,
|
||||
feedback,
|
||||
html_page_favorites,
|
||||
intent,
|
||||
llm_metrics,
|
||||
@@ -45,6 +45,7 @@ from app.gateway.routers import (
|
||||
multi_agent,
|
||||
notifications,
|
||||
public_embed,
|
||||
public_leaderboard,
|
||||
public_scheduled_tasks,
|
||||
recommend,
|
||||
recommended_questions,
|
||||
@@ -381,7 +382,7 @@ def _release_singleton_lock(handle) -> None:
|
||||
pass
|
||||
|
||||
|
||||
async def _curator_scheduler_loop() -> None:
|
||||
async def _curator_scheduler_loop() -> None:
|
||||
"""常驻后台任务:每隔 _CURATOR_CHECK_INTERVAL_SECONDS 检查一次需不需要进化。
|
||||
|
||||
多 worker 部署下用文件锁做 leader 选举 —— 只有抢到锁的那个 worker 进程真正
|
||||
@@ -407,344 +408,344 @@ async def _curator_scheduler_loop() -> None:
|
||||
except Exception:
|
||||
logger.exception("Curator scheduler tick failed (non-fatal)")
|
||||
await asyncio.sleep(_CURATOR_CHECK_INTERVAL_SECONDS)
|
||||
finally:
|
||||
_release_singleton_lock(lock_handle)
|
||||
|
||||
|
||||
def _env_bool(name: str, default: bool) -> bool:
|
||||
raw = os.getenv(name)
|
||||
if raw is None:
|
||||
return default
|
||||
return raw.strip().lower() not in {"0", "false", "no", "off"}
|
||||
|
||||
|
||||
def _env_int(name: str, default: int, *, alias: str | None = None, minimum: int = 1) -> int:
|
||||
raw = os.getenv(name)
|
||||
if raw is None and alias:
|
||||
raw = os.getenv(alias)
|
||||
if raw is None:
|
||||
raw = str(default)
|
||||
try:
|
||||
value = int(raw)
|
||||
except ValueError:
|
||||
return default
|
||||
return max(minimum, value)
|
||||
|
||||
|
||||
def _env_float(name: str, default: float, *, alias: str | None = None, minimum: float = 0.0) -> float:
|
||||
raw = os.getenv(name)
|
||||
if raw is None and alias:
|
||||
raw = os.getenv(alias)
|
||||
if raw is None:
|
||||
raw = str(default)
|
||||
try:
|
||||
value = float(raw)
|
||||
except ValueError:
|
||||
return default
|
||||
return max(minimum, value)
|
||||
|
||||
|
||||
_LEADERBOARD_SNAPSHOT_BACKGROUND_ENABLED = _env_bool("ADMIN_LEADERBOARD_BACKGROUND_ENABLED", True)
|
||||
_LEADERBOARD_SNAPSHOT_PREWARM_DAYS = _env_int(
|
||||
"ADMIN_LEADERBOARD_BACKGROUND_PREWARM_DAYS",
|
||||
30,
|
||||
)
|
||||
_LEADERBOARD_SNAPSHOT_BATCH_SIZE = _env_int(
|
||||
"ADMIN_LEADERBOARD_BACKGROUND_BATCH_SIZE",
|
||||
1,
|
||||
)
|
||||
_LEADERBOARD_SNAPSHOT_INTERVAL_SECONDS = _env_float(
|
||||
"ADMIN_LEADERBOARD_BACKGROUND_INTERVAL_SECONDS",
|
||||
300.0,
|
||||
)
|
||||
_LEADERBOARD_SNAPSHOT_SLEEP_SECONDS = _env_float(
|
||||
"ADMIN_LEADERBOARD_BACKGROUND_SLEEP_SECONDS",
|
||||
2.0,
|
||||
)
|
||||
_LEADERBOARD_SNAPSHOT_RUNNING_TTL_SECONDS = _env_int(
|
||||
"ADMIN_LEADERBOARD_BACKGROUND_RUNNING_TTL_SECONDS",
|
||||
1800,
|
||||
)
|
||||
_LEADERBOARD_SNAPSHOT_STARTUP_DELAY_SECONDS = _env_float(
|
||||
"ADMIN_LEADERBOARD_BACKGROUND_STARTUP_DELAY_SECONDS",
|
||||
60.0,
|
||||
)
|
||||
|
||||
|
||||
def _leaderboard_scheduler_sql_for_log(stmt) -> str:
|
||||
try:
|
||||
return str(stmt.compile(compile_kwargs={"literal_binds": True}))
|
||||
except Exception:
|
||||
return str(stmt)
|
||||
|
||||
|
||||
async def _execute_leaderboard_scheduler_query(session, step: str, stmt, **context):
|
||||
sql = _leaderboard_scheduler_sql_for_log(stmt)
|
||||
logger.info(
|
||||
"Leaderboard snapshot DB query start: step=%s stat_date=%s job=%s settings_hash=%s started_at=%s sql=%s",
|
||||
step,
|
||||
context.get("stat_date") or context.get("stat_dates") or "",
|
||||
context.get("job_key") or "",
|
||||
context.get("settings_hash") or "",
|
||||
datetime.now().isoformat(),
|
||||
sql,
|
||||
)
|
||||
start = perf_counter()
|
||||
try:
|
||||
result = await session.execute(stmt)
|
||||
except Exception:
|
||||
logger.exception(
|
||||
"Leaderboard snapshot DB query failed: step=%s stat_date=%s job=%s settings_hash=%s elapsed_ms=%.2f",
|
||||
step,
|
||||
context.get("stat_date") or context.get("stat_dates") or "",
|
||||
context.get("job_key") or "",
|
||||
context.get("settings_hash") or "",
|
||||
(perf_counter() - start) * 1000,
|
||||
)
|
||||
raise
|
||||
logger.info(
|
||||
"Leaderboard snapshot DB query done: step=%s stat_date=%s job=%s settings_hash=%s finished_at=%s elapsed_ms=%.2f",
|
||||
step,
|
||||
context.get("stat_date") or context.get("stat_dates") or "",
|
||||
context.get("job_key") or "",
|
||||
context.get("settings_hash") or "",
|
||||
datetime.now().isoformat(),
|
||||
(perf_counter() - start) * 1000,
|
||||
)
|
||||
return result
|
||||
|
||||
|
||||
async def _time_leaderboard_scheduler_db_operation(step: str, operation, *, sql: str = "", **context):
|
||||
logger.info(
|
||||
"Leaderboard snapshot DB query start: step=%s stat_date=%s job=%s settings_hash=%s started_at=%s sql=%s",
|
||||
step,
|
||||
context.get("stat_date") or context.get("stat_dates") or "",
|
||||
context.get("job_key") or "",
|
||||
context.get("settings_hash") or "",
|
||||
datetime.now().isoformat(),
|
||||
sql,
|
||||
)
|
||||
start = perf_counter()
|
||||
try:
|
||||
result = await operation()
|
||||
except Exception:
|
||||
logger.exception(
|
||||
"Leaderboard snapshot DB query failed: step=%s stat_date=%s job=%s settings_hash=%s elapsed_ms=%.2f",
|
||||
step,
|
||||
context.get("stat_date") or context.get("stat_dates") or "",
|
||||
context.get("job_key") or "",
|
||||
context.get("settings_hash") or "",
|
||||
(perf_counter() - start) * 1000,
|
||||
)
|
||||
raise
|
||||
logger.info(
|
||||
"Leaderboard snapshot DB query done: step=%s stat_date=%s job=%s settings_hash=%s finished_at=%s elapsed_ms=%.2f",
|
||||
step,
|
||||
context.get("stat_date") or context.get("stat_dates") or "",
|
||||
context.get("job_key") or "",
|
||||
context.get("settings_hash") or "",
|
||||
datetime.now().isoformat(),
|
||||
(perf_counter() - start) * 1000,
|
||||
)
|
||||
return result
|
||||
|
||||
|
||||
def _recent_leaderboard_stat_dates(days: int) -> list[str]:
|
||||
from datetime import datetime, timedelta
|
||||
|
||||
from deerflow.persistence.types import BEIJING_TZ
|
||||
|
||||
today = datetime.now(BEIJING_TZ).date()
|
||||
start = today - timedelta(days=max(1, days) - 1)
|
||||
return [(start + timedelta(days=i)).isoformat() for i in range((today - start).days + 1)]
|
||||
|
||||
|
||||
async def _leaderboard_snapshot_due_dates(
|
||||
session_factory,
|
||||
*,
|
||||
settings_hash: str,
|
||||
limit: int,
|
||||
running_ttl_seconds: int,
|
||||
) -> list[str]:
|
||||
from datetime import UTC, datetime, timedelta
|
||||
|
||||
from sqlalchemy import and_, or_, select
|
||||
|
||||
from deerflow.persistence.admin_stats.model import AdminLeaderboardDailyStatRow
|
||||
|
||||
cutoff = datetime.now(UTC) - timedelta(seconds=running_ttl_seconds)
|
||||
async with session_factory() as session:
|
||||
stmt = (
|
||||
select(AdminLeaderboardDailyStatRow.stat_date)
|
||||
.where(
|
||||
AdminLeaderboardDailyStatRow.settings_hash == settings_hash,
|
||||
or_(
|
||||
AdminLeaderboardDailyStatRow.status.in_(["queued", "error"]),
|
||||
and_(
|
||||
AdminLeaderboardDailyStatRow.status == "running",
|
||||
AdminLeaderboardDailyStatRow.updated_at < cutoff,
|
||||
),
|
||||
),
|
||||
)
|
||||
.order_by(AdminLeaderboardDailyStatRow.stat_date.desc())
|
||||
.limit(limit)
|
||||
)
|
||||
rows = (
|
||||
await _execute_leaderboard_scheduler_query(
|
||||
session,
|
||||
"scheduler.due_dates",
|
||||
stmt,
|
||||
settings_hash=settings_hash,
|
||||
)
|
||||
).all()
|
||||
return [str(row[0]) for row in rows]
|
||||
|
||||
|
||||
async def _claim_leaderboard_snapshot(
|
||||
session_factory,
|
||||
*,
|
||||
stat_date: str,
|
||||
settings_hash: str,
|
||||
running_ttl_seconds: int,
|
||||
) -> bool:
|
||||
from datetime import UTC, datetime
|
||||
|
||||
from app.gateway.routers.admin_users import _snapshot_is_fresh
|
||||
from deerflow.persistence.admin_stats.model import AdminLeaderboardDailyStatRow
|
||||
from deerflow.persistence.types import BEIJING_TZ
|
||||
|
||||
async with session_factory() as session:
|
||||
row = await _time_leaderboard_scheduler_db_operation(
|
||||
"scheduler.claim.get",
|
||||
lambda: session.get(
|
||||
AdminLeaderboardDailyStatRow,
|
||||
{"stat_date": stat_date, "settings_hash": settings_hash},
|
||||
),
|
||||
sql="SELECT admin_leaderboard_daily_stats by primary key",
|
||||
stat_date=stat_date,
|
||||
settings_hash=settings_hash,
|
||||
)
|
||||
if row is None or _snapshot_is_fresh(row, stat_date):
|
||||
return False
|
||||
if row.status == "running":
|
||||
updated_at = row.updated_at
|
||||
if isinstance(updated_at, datetime):
|
||||
if updated_at.tzinfo is None:
|
||||
updated_at = updated_at.replace(tzinfo=BEIJING_TZ)
|
||||
age = (datetime.now(BEIJING_TZ) - updated_at.astimezone(BEIJING_TZ)).total_seconds()
|
||||
if age < running_ttl_seconds:
|
||||
return False
|
||||
row.status = "running"
|
||||
row.message = "排行榜后台统计任务已认领。"
|
||||
row.error = None
|
||||
row.updated_at = datetime.now(UTC)
|
||||
await _time_leaderboard_scheduler_db_operation(
|
||||
"scheduler.claim.commit",
|
||||
lambda: session.commit(),
|
||||
sql="COMMIT",
|
||||
stat_date=stat_date,
|
||||
settings_hash=settings_hash,
|
||||
)
|
||||
return True
|
||||
|
||||
|
||||
async def _run_leaderboard_snapshot_tick() -> tuple[int, int]:
|
||||
from app.gateway.routers.admin_users import (
|
||||
_daily_job_key,
|
||||
_queue_daily_leaderboard_snapshots,
|
||||
_refresh_daily_leaderboard_snapshot,
|
||||
_resolve_leaderboard_snapshot_scope,
|
||||
)
|
||||
from deerflow.config.system_settings import load_system_settings
|
||||
from deerflow.persistence.engine import get_session_factory
|
||||
|
||||
session_factory = get_session_factory()
|
||||
if session_factory is None:
|
||||
return 0, 0
|
||||
|
||||
settings = load_system_settings().leaderboard
|
||||
excluded, include_scheduled, include_admins, include_failed, settings_hash = _resolve_leaderboard_snapshot_scope(settings)
|
||||
stat_dates = _recent_leaderboard_stat_dates(_LEADERBOARD_SNAPSHOT_PREWARM_DAYS)
|
||||
queued_dates = await _queue_daily_leaderboard_snapshots(
|
||||
session_factory,
|
||||
stat_dates,
|
||||
settings_hash,
|
||||
message="排行榜后台统计任务定期预热/补算队列。",
|
||||
)
|
||||
|
||||
due_dates = await _leaderboard_snapshot_due_dates(
|
||||
session_factory,
|
||||
settings_hash=settings_hash,
|
||||
limit=_LEADERBOARD_SNAPSHOT_BATCH_SIZE,
|
||||
running_ttl_seconds=_LEADERBOARD_SNAPSHOT_RUNNING_TTL_SECONDS,
|
||||
)
|
||||
processed = 0
|
||||
for stat_date in due_dates:
|
||||
claimed = await _claim_leaderboard_snapshot(
|
||||
session_factory,
|
||||
stat_date=stat_date,
|
||||
settings_hash=settings_hash,
|
||||
running_ttl_seconds=_LEADERBOARD_SNAPSHOT_RUNNING_TTL_SECONDS,
|
||||
)
|
||||
if not claimed:
|
||||
continue
|
||||
logger.info("Leaderboard snapshot scheduler: building date=%s hash=%s", stat_date, settings_hash[:10])
|
||||
await _refresh_daily_leaderboard_snapshot(
|
||||
_daily_job_key(stat_date, settings_hash),
|
||||
session_factory=session_factory,
|
||||
settings=settings,
|
||||
stat_date=stat_date,
|
||||
settings_hash=settings_hash,
|
||||
excluded=excluded,
|
||||
include_scheduled=include_scheduled,
|
||||
include_admins=include_admins,
|
||||
include_failed=include_failed,
|
||||
)
|
||||
processed += 1
|
||||
if _LEADERBOARD_SNAPSHOT_SLEEP_SECONDS > 0 and processed < len(due_dates):
|
||||
await asyncio.sleep(_LEADERBOARD_SNAPSHOT_SLEEP_SECONDS)
|
||||
return processed, len(queued_dates)
|
||||
|
||||
|
||||
async def _leaderboard_snapshot_scheduler_loop() -> None:
|
||||
"""Background task inside the existing gateway process for daily snapshots."""
|
||||
if not _LEADERBOARD_SNAPSHOT_BACKGROUND_ENABLED:
|
||||
logger.info("Leaderboard snapshot scheduler disabled by ADMIN_LEADERBOARD_BACKGROUND_ENABLED")
|
||||
return
|
||||
|
||||
from deerflow.config.runtime_paths import runtime_home
|
||||
|
||||
lock_handle = _acquire_singleton_lock(runtime_home() / ".leaderboard_snapshot_scheduler.lock")
|
||||
if lock_handle is None:
|
||||
logger.info("Leaderboard snapshot scheduler: another gateway worker holds the lock; this worker skips")
|
||||
return
|
||||
|
||||
logger.info(
|
||||
"Leaderboard snapshot scheduler started: prewarm_days=%d batch_size=%d interval=%.1fs",
|
||||
_LEADERBOARD_SNAPSHOT_PREWARM_DAYS,
|
||||
_LEADERBOARD_SNAPSHOT_BATCH_SIZE,
|
||||
_LEADERBOARD_SNAPSHOT_INTERVAL_SECONDS,
|
||||
)
|
||||
try:
|
||||
if _LEADERBOARD_SNAPSHOT_STARTUP_DELAY_SECONDS > 0:
|
||||
await asyncio.sleep(_LEADERBOARD_SNAPSHOT_STARTUP_DELAY_SECONDS)
|
||||
while True:
|
||||
try:
|
||||
processed, queued = await _run_leaderboard_snapshot_tick()
|
||||
if processed or queued:
|
||||
logger.info(
|
||||
"Leaderboard snapshot scheduler tick: queued=%d processed=%d",
|
||||
queued,
|
||||
processed,
|
||||
)
|
||||
except Exception:
|
||||
logger.exception("Leaderboard snapshot scheduler tick failed (non-fatal)")
|
||||
await asyncio.sleep(_LEADERBOARD_SNAPSHOT_INTERVAL_SECONDS)
|
||||
finally:
|
||||
_release_singleton_lock(lock_handle)
|
||||
|
||||
|
||||
def _warn_if_multi_worker() -> None:
|
||||
finally:
|
||||
_release_singleton_lock(lock_handle)
|
||||
|
||||
|
||||
def _env_bool(name: str, default: bool) -> bool:
|
||||
raw = os.getenv(name)
|
||||
if raw is None:
|
||||
return default
|
||||
return raw.strip().lower() not in {"0", "false", "no", "off"}
|
||||
|
||||
|
||||
def _env_int(name: str, default: int, *, alias: str | None = None, minimum: int = 1) -> int:
|
||||
raw = os.getenv(name)
|
||||
if raw is None and alias:
|
||||
raw = os.getenv(alias)
|
||||
if raw is None:
|
||||
raw = str(default)
|
||||
try:
|
||||
value = int(raw)
|
||||
except ValueError:
|
||||
return default
|
||||
return max(minimum, value)
|
||||
|
||||
|
||||
def _env_float(name: str, default: float, *, alias: str | None = None, minimum: float = 0.0) -> float:
|
||||
raw = os.getenv(name)
|
||||
if raw is None and alias:
|
||||
raw = os.getenv(alias)
|
||||
if raw is None:
|
||||
raw = str(default)
|
||||
try:
|
||||
value = float(raw)
|
||||
except ValueError:
|
||||
return default
|
||||
return max(minimum, value)
|
||||
|
||||
|
||||
_LEADERBOARD_SNAPSHOT_BACKGROUND_ENABLED = _env_bool("ADMIN_LEADERBOARD_BACKGROUND_ENABLED", True)
|
||||
_LEADERBOARD_SNAPSHOT_PREWARM_DAYS = _env_int(
|
||||
"ADMIN_LEADERBOARD_BACKGROUND_PREWARM_DAYS",
|
||||
30,
|
||||
)
|
||||
_LEADERBOARD_SNAPSHOT_BATCH_SIZE = _env_int(
|
||||
"ADMIN_LEADERBOARD_BACKGROUND_BATCH_SIZE",
|
||||
1,
|
||||
)
|
||||
_LEADERBOARD_SNAPSHOT_INTERVAL_SECONDS = _env_float(
|
||||
"ADMIN_LEADERBOARD_BACKGROUND_INTERVAL_SECONDS",
|
||||
300.0,
|
||||
)
|
||||
_LEADERBOARD_SNAPSHOT_SLEEP_SECONDS = _env_float(
|
||||
"ADMIN_LEADERBOARD_BACKGROUND_SLEEP_SECONDS",
|
||||
2.0,
|
||||
)
|
||||
_LEADERBOARD_SNAPSHOT_RUNNING_TTL_SECONDS = _env_int(
|
||||
"ADMIN_LEADERBOARD_BACKGROUND_RUNNING_TTL_SECONDS",
|
||||
1800,
|
||||
)
|
||||
_LEADERBOARD_SNAPSHOT_STARTUP_DELAY_SECONDS = _env_float(
|
||||
"ADMIN_LEADERBOARD_BACKGROUND_STARTUP_DELAY_SECONDS",
|
||||
60.0,
|
||||
)
|
||||
|
||||
|
||||
def _leaderboard_scheduler_sql_for_log(stmt) -> str:
|
||||
try:
|
||||
return str(stmt.compile(compile_kwargs={"literal_binds": True}))
|
||||
except Exception:
|
||||
return str(stmt)
|
||||
|
||||
|
||||
async def _execute_leaderboard_scheduler_query(session, step: str, stmt, **context):
|
||||
sql = _leaderboard_scheduler_sql_for_log(stmt)
|
||||
logger.info(
|
||||
"Leaderboard snapshot DB query start: step=%s stat_date=%s job=%s settings_hash=%s started_at=%s sql=%s",
|
||||
step,
|
||||
context.get("stat_date") or context.get("stat_dates") or "",
|
||||
context.get("job_key") or "",
|
||||
context.get("settings_hash") or "",
|
||||
datetime.now().isoformat(),
|
||||
sql,
|
||||
)
|
||||
start = perf_counter()
|
||||
try:
|
||||
result = await session.execute(stmt)
|
||||
except Exception:
|
||||
logger.exception(
|
||||
"Leaderboard snapshot DB query failed: step=%s stat_date=%s job=%s settings_hash=%s elapsed_ms=%.2f",
|
||||
step,
|
||||
context.get("stat_date") or context.get("stat_dates") or "",
|
||||
context.get("job_key") or "",
|
||||
context.get("settings_hash") or "",
|
||||
(perf_counter() - start) * 1000,
|
||||
)
|
||||
raise
|
||||
logger.info(
|
||||
"Leaderboard snapshot DB query done: step=%s stat_date=%s job=%s settings_hash=%s finished_at=%s elapsed_ms=%.2f",
|
||||
step,
|
||||
context.get("stat_date") or context.get("stat_dates") or "",
|
||||
context.get("job_key") or "",
|
||||
context.get("settings_hash") or "",
|
||||
datetime.now().isoformat(),
|
||||
(perf_counter() - start) * 1000,
|
||||
)
|
||||
return result
|
||||
|
||||
|
||||
async def _time_leaderboard_scheduler_db_operation(step: str, operation, *, sql: str = "", **context):
|
||||
logger.info(
|
||||
"Leaderboard snapshot DB query start: step=%s stat_date=%s job=%s settings_hash=%s started_at=%s sql=%s",
|
||||
step,
|
||||
context.get("stat_date") or context.get("stat_dates") or "",
|
||||
context.get("job_key") or "",
|
||||
context.get("settings_hash") or "",
|
||||
datetime.now().isoformat(),
|
||||
sql,
|
||||
)
|
||||
start = perf_counter()
|
||||
try:
|
||||
result = await operation()
|
||||
except Exception:
|
||||
logger.exception(
|
||||
"Leaderboard snapshot DB query failed: step=%s stat_date=%s job=%s settings_hash=%s elapsed_ms=%.2f",
|
||||
step,
|
||||
context.get("stat_date") or context.get("stat_dates") or "",
|
||||
context.get("job_key") or "",
|
||||
context.get("settings_hash") or "",
|
||||
(perf_counter() - start) * 1000,
|
||||
)
|
||||
raise
|
||||
logger.info(
|
||||
"Leaderboard snapshot DB query done: step=%s stat_date=%s job=%s settings_hash=%s finished_at=%s elapsed_ms=%.2f",
|
||||
step,
|
||||
context.get("stat_date") or context.get("stat_dates") or "",
|
||||
context.get("job_key") or "",
|
||||
context.get("settings_hash") or "",
|
||||
datetime.now().isoformat(),
|
||||
(perf_counter() - start) * 1000,
|
||||
)
|
||||
return result
|
||||
|
||||
|
||||
def _recent_leaderboard_stat_dates(days: int) -> list[str]:
|
||||
from datetime import datetime, timedelta
|
||||
|
||||
from deerflow.persistence.types import BEIJING_TZ
|
||||
|
||||
today = datetime.now(BEIJING_TZ).date()
|
||||
start = today - timedelta(days=max(1, days) - 1)
|
||||
return [(start + timedelta(days=i)).isoformat() for i in range((today - start).days + 1)]
|
||||
|
||||
|
||||
async def _leaderboard_snapshot_due_dates(
|
||||
session_factory,
|
||||
*,
|
||||
settings_hash: str,
|
||||
limit: int,
|
||||
running_ttl_seconds: int,
|
||||
) -> list[str]:
|
||||
from datetime import UTC, datetime, timedelta
|
||||
|
||||
from sqlalchemy import and_, or_, select
|
||||
|
||||
from deerflow.persistence.admin_stats.model import AdminLeaderboardDailyStatRow
|
||||
|
||||
cutoff = datetime.now(UTC) - timedelta(seconds=running_ttl_seconds)
|
||||
async with session_factory() as session:
|
||||
stmt = (
|
||||
select(AdminLeaderboardDailyStatRow.stat_date)
|
||||
.where(
|
||||
AdminLeaderboardDailyStatRow.settings_hash == settings_hash,
|
||||
or_(
|
||||
AdminLeaderboardDailyStatRow.status.in_(["queued", "error"]),
|
||||
and_(
|
||||
AdminLeaderboardDailyStatRow.status == "running",
|
||||
AdminLeaderboardDailyStatRow.updated_at < cutoff,
|
||||
),
|
||||
),
|
||||
)
|
||||
.order_by(AdminLeaderboardDailyStatRow.stat_date.desc())
|
||||
.limit(limit)
|
||||
)
|
||||
rows = (
|
||||
await _execute_leaderboard_scheduler_query(
|
||||
session,
|
||||
"scheduler.due_dates",
|
||||
stmt,
|
||||
settings_hash=settings_hash,
|
||||
)
|
||||
).all()
|
||||
return [str(row[0]) for row in rows]
|
||||
|
||||
|
||||
async def _claim_leaderboard_snapshot(
|
||||
session_factory,
|
||||
*,
|
||||
stat_date: str,
|
||||
settings_hash: str,
|
||||
running_ttl_seconds: int,
|
||||
) -> bool:
|
||||
from datetime import UTC, datetime
|
||||
|
||||
from app.gateway.routers.admin_users import _snapshot_is_fresh
|
||||
from deerflow.persistence.admin_stats.model import AdminLeaderboardDailyStatRow
|
||||
from deerflow.persistence.types import BEIJING_TZ
|
||||
|
||||
async with session_factory() as session:
|
||||
row = await _time_leaderboard_scheduler_db_operation(
|
||||
"scheduler.claim.get",
|
||||
lambda: session.get(
|
||||
AdminLeaderboardDailyStatRow,
|
||||
{"stat_date": stat_date, "settings_hash": settings_hash},
|
||||
),
|
||||
sql="SELECT admin_leaderboard_daily_stats by primary key",
|
||||
stat_date=stat_date,
|
||||
settings_hash=settings_hash,
|
||||
)
|
||||
if row is None or _snapshot_is_fresh(row, stat_date):
|
||||
return False
|
||||
if row.status == "running":
|
||||
updated_at = row.updated_at
|
||||
if isinstance(updated_at, datetime):
|
||||
if updated_at.tzinfo is None:
|
||||
updated_at = updated_at.replace(tzinfo=BEIJING_TZ)
|
||||
age = (datetime.now(BEIJING_TZ) - updated_at.astimezone(BEIJING_TZ)).total_seconds()
|
||||
if age < running_ttl_seconds:
|
||||
return False
|
||||
row.status = "running"
|
||||
row.message = "排行榜后台统计任务已认领。"
|
||||
row.error = None
|
||||
row.updated_at = datetime.now(UTC)
|
||||
await _time_leaderboard_scheduler_db_operation(
|
||||
"scheduler.claim.commit",
|
||||
lambda: session.commit(),
|
||||
sql="COMMIT",
|
||||
stat_date=stat_date,
|
||||
settings_hash=settings_hash,
|
||||
)
|
||||
return True
|
||||
|
||||
|
||||
async def _run_leaderboard_snapshot_tick() -> tuple[int, int]:
|
||||
from app.gateway.routers.admin_users import (
|
||||
_daily_job_key,
|
||||
_queue_daily_leaderboard_snapshots,
|
||||
_refresh_daily_leaderboard_snapshot,
|
||||
_resolve_leaderboard_snapshot_scope,
|
||||
)
|
||||
from deerflow.config.system_settings import load_system_settings
|
||||
from deerflow.persistence.engine import get_session_factory
|
||||
|
||||
session_factory = get_session_factory()
|
||||
if session_factory is None:
|
||||
return 0, 0
|
||||
|
||||
settings = load_system_settings().leaderboard
|
||||
excluded, include_scheduled, include_admins, include_failed, settings_hash = _resolve_leaderboard_snapshot_scope(settings)
|
||||
stat_dates = _recent_leaderboard_stat_dates(_LEADERBOARD_SNAPSHOT_PREWARM_DAYS)
|
||||
queued_dates = await _queue_daily_leaderboard_snapshots(
|
||||
session_factory,
|
||||
stat_dates,
|
||||
settings_hash,
|
||||
message="排行榜后台统计任务定期预热/补算队列。",
|
||||
)
|
||||
|
||||
due_dates = await _leaderboard_snapshot_due_dates(
|
||||
session_factory,
|
||||
settings_hash=settings_hash,
|
||||
limit=_LEADERBOARD_SNAPSHOT_BATCH_SIZE,
|
||||
running_ttl_seconds=_LEADERBOARD_SNAPSHOT_RUNNING_TTL_SECONDS,
|
||||
)
|
||||
processed = 0
|
||||
for stat_date in due_dates:
|
||||
claimed = await _claim_leaderboard_snapshot(
|
||||
session_factory,
|
||||
stat_date=stat_date,
|
||||
settings_hash=settings_hash,
|
||||
running_ttl_seconds=_LEADERBOARD_SNAPSHOT_RUNNING_TTL_SECONDS,
|
||||
)
|
||||
if not claimed:
|
||||
continue
|
||||
logger.info("Leaderboard snapshot scheduler: building date=%s hash=%s", stat_date, settings_hash[:10])
|
||||
await _refresh_daily_leaderboard_snapshot(
|
||||
_daily_job_key(stat_date, settings_hash),
|
||||
session_factory=session_factory,
|
||||
settings=settings,
|
||||
stat_date=stat_date,
|
||||
settings_hash=settings_hash,
|
||||
excluded=excluded,
|
||||
include_scheduled=include_scheduled,
|
||||
include_admins=include_admins,
|
||||
include_failed=include_failed,
|
||||
)
|
||||
processed += 1
|
||||
if _LEADERBOARD_SNAPSHOT_SLEEP_SECONDS > 0 and processed < len(due_dates):
|
||||
await asyncio.sleep(_LEADERBOARD_SNAPSHOT_SLEEP_SECONDS)
|
||||
return processed, len(queued_dates)
|
||||
|
||||
|
||||
async def _leaderboard_snapshot_scheduler_loop() -> None:
|
||||
"""Background task inside the existing gateway process for daily snapshots."""
|
||||
if not _LEADERBOARD_SNAPSHOT_BACKGROUND_ENABLED:
|
||||
logger.info("Leaderboard snapshot scheduler disabled by ADMIN_LEADERBOARD_BACKGROUND_ENABLED")
|
||||
return
|
||||
|
||||
from deerflow.config.runtime_paths import runtime_home
|
||||
|
||||
lock_handle = _acquire_singleton_lock(runtime_home() / ".leaderboard_snapshot_scheduler.lock")
|
||||
if lock_handle is None:
|
||||
logger.info("Leaderboard snapshot scheduler: another gateway worker holds the lock; this worker skips")
|
||||
return
|
||||
|
||||
logger.info(
|
||||
"Leaderboard snapshot scheduler started: prewarm_days=%d batch_size=%d interval=%.1fs",
|
||||
_LEADERBOARD_SNAPSHOT_PREWARM_DAYS,
|
||||
_LEADERBOARD_SNAPSHOT_BATCH_SIZE,
|
||||
_LEADERBOARD_SNAPSHOT_INTERVAL_SECONDS,
|
||||
)
|
||||
try:
|
||||
if _LEADERBOARD_SNAPSHOT_STARTUP_DELAY_SECONDS > 0:
|
||||
await asyncio.sleep(_LEADERBOARD_SNAPSHOT_STARTUP_DELAY_SECONDS)
|
||||
while True:
|
||||
try:
|
||||
processed, queued = await _run_leaderboard_snapshot_tick()
|
||||
if processed or queued:
|
||||
logger.info(
|
||||
"Leaderboard snapshot scheduler tick: queued=%d processed=%d",
|
||||
queued,
|
||||
processed,
|
||||
)
|
||||
except Exception:
|
||||
logger.exception("Leaderboard snapshot scheduler tick failed (non-fatal)")
|
||||
await asyncio.sleep(_LEADERBOARD_SNAPSHOT_INTERVAL_SECONDS)
|
||||
finally:
|
||||
_release_singleton_lock(lock_handle)
|
||||
|
||||
|
||||
def _warn_if_multi_worker() -> None:
|
||||
"""检测 uvicorn / gunicorn 多 worker 部署并打 ERROR 日志。
|
||||
|
||||
主 agent / canvas / AI 写作流式响应在 Gateway 进程内通过 ``StreamBridge``
|
||||
@@ -898,21 +899,21 @@ async def lifespan(app: FastAPI) -> AsyncGenerator[None, None]:
|
||||
# 默认每天凌晨 3 点扫一次,删 retention_days(默认 7 天)以前的会话,联动
|
||||
# 清理 MySQL 业务表 + SQLite checkpointer 里的 thread 状态。多 worker
|
||||
# 下用文件锁选 leader,只有抢到锁的 worker 真正跑清理。
|
||||
try:
|
||||
from app.gateway.ai_writing_cleanup import cleanup_scheduler_loop
|
||||
|
||||
app.state.ai_writing_cleanup_task = asyncio.create_task(cleanup_scheduler_loop(app))
|
||||
except Exception:
|
||||
logger.exception("AI writing cleanup scheduler failed to start (non-fatal)")
|
||||
|
||||
try:
|
||||
app.state.leaderboard_snapshot_scheduler_task = asyncio.create_task(_leaderboard_snapshot_scheduler_loop())
|
||||
except Exception:
|
||||
logger.exception("Leaderboard snapshot scheduler failed to start (non-fatal)")
|
||||
|
||||
# Start IM channel service if any channels are configured
|
||||
try:
|
||||
from app.channels.service import start_channel_service
|
||||
try:
|
||||
from app.gateway.ai_writing_cleanup import cleanup_scheduler_loop
|
||||
|
||||
app.state.ai_writing_cleanup_task = asyncio.create_task(cleanup_scheduler_loop(app))
|
||||
except Exception:
|
||||
logger.exception("AI writing cleanup scheduler failed to start (non-fatal)")
|
||||
|
||||
try:
|
||||
app.state.leaderboard_snapshot_scheduler_task = asyncio.create_task(_leaderboard_snapshot_scheduler_loop())
|
||||
except Exception:
|
||||
logger.exception("Leaderboard snapshot scheduler failed to start (non-fatal)")
|
||||
|
||||
# Start IM channel service if any channels are configured
|
||||
try:
|
||||
from app.channels.service import start_channel_service
|
||||
|
||||
channel_service = await start_channel_service(app.state.config)
|
||||
logger.info("Channel service started: %s", channel_service.get_status())
|
||||
@@ -956,17 +957,17 @@ async def lifespan(app: FastAPI) -> AsyncGenerator[None, None]:
|
||||
except asyncio.CancelledError:
|
||||
pass
|
||||
except Exception:
|
||||
logger.exception("AI writing cleanup scheduler shutdown error")
|
||||
|
||||
leaderboard_snapshot_task = getattr(app.state, "leaderboard_snapshot_scheduler_task", None)
|
||||
if leaderboard_snapshot_task is not None:
|
||||
leaderboard_snapshot_task.cancel()
|
||||
try:
|
||||
await leaderboard_snapshot_task
|
||||
except asyncio.CancelledError:
|
||||
pass
|
||||
except Exception:
|
||||
logger.exception("Leaderboard snapshot scheduler shutdown error")
|
||||
logger.exception("AI writing cleanup scheduler shutdown error")
|
||||
|
||||
leaderboard_snapshot_task = getattr(app.state, "leaderboard_snapshot_scheduler_task", None)
|
||||
if leaderboard_snapshot_task is not None:
|
||||
leaderboard_snapshot_task.cancel()
|
||||
try:
|
||||
await leaderboard_snapshot_task
|
||||
except asyncio.CancelledError:
|
||||
pass
|
||||
except Exception:
|
||||
logger.exception("Leaderboard snapshot scheduler shutdown error")
|
||||
|
||||
# 阶段 7 删冗余：AI 写作 graph 不再自管 checkpointer / in-flight task；
|
||||
# thread 状态由 LangGraph Server 主 checkpointer 接管，lifespan 出口由
|
||||
@@ -1198,14 +1199,14 @@ This gateway provides custom endpoints for models, MCP configuration, skills, an
|
||||
# Artifacts API is mounted at /api/threads/{thread_id}/artifacts
|
||||
app.include_router(artifacts.router)
|
||||
|
||||
# Uploads API is mounted at /api/threads/{thread_id}/uploads
|
||||
app.include_router(uploads.router)
|
||||
|
||||
# Optional Chrome-extension page capture API is mounted at /api/browser-context
|
||||
app.include_router(browser_context.router)
|
||||
|
||||
# Thread cleanup API is mounted at /api/threads/{thread_id}
|
||||
app.include_router(threads.router)
|
||||
# Uploads API is mounted at /api/threads/{thread_id}/uploads
|
||||
app.include_router(uploads.router)
|
||||
|
||||
# Optional Chrome-extension page capture API is mounted at /api/browser-context
|
||||
app.include_router(browser_context.router)
|
||||
|
||||
# Thread cleanup API is mounted at /api/threads/{thread_id}
|
||||
app.include_router(threads.router)
|
||||
|
||||
# Agents API is mounted at /api/agents
|
||||
app.include_router(agents.router)
|
||||
@@ -1244,6 +1245,9 @@ This gateway provides custom endpoints for models, MCP configuration, skills, an
|
||||
# surface results without a DeerFlow login.
|
||||
app.include_router(public_scheduled_tasks.router)
|
||||
|
||||
# Public read-only user leaderboard publish page (/api/public/leaderboard)
|
||||
app.include_router(public_leaderboard.router)
|
||||
|
||||
# Public embed Q&A status polling (/api/public/embed/*)
|
||||
app.include_router(public_embed.router)
|
||||
app.include_router(html_page_favorites.router)
|
||||
@@ -1254,18 +1258,18 @@ This gateway provides custom endpoints for models, MCP configuration, skills, an
|
||||
# Admin LLM metrics audit + export
|
||||
app.include_router(llm_metrics.router)
|
||||
|
||||
# Admin window into other users' threads / messages / memory
|
||||
app.include_router(admin_users.router)
|
||||
app.include_router(admin_users.self_router)
|
||||
|
||||
# Admin tool / skill call metrics audit + export
|
||||
# Admin window into other users' threads / messages / memory
|
||||
app.include_router(admin_users.router)
|
||||
app.include_router(admin_users.self_router)
|
||||
|
||||
# Admin tool / skill call metrics audit + export
|
||||
app.include_router(tool_metrics.router)
|
||||
|
||||
# Channels API is mounted at /api/channels
|
||||
app.include_router(channels.router)
|
||||
|
||||
# Admin checkpoint migration API: SQLite legacy checkpoints -> Postgres.
|
||||
app.include_router(checkpoint_migration.router)
|
||||
app.include_router(channels.router)
|
||||
|
||||
# Admin checkpoint migration API: SQLite legacy checkpoints -> Postgres.
|
||||
app.include_router(checkpoint_migration.router)
|
||||
|
||||
# Assistants compatibility API (LangGraph Platform stub)
|
||||
app.include_router(assistants_compat.router)
|
||||
|
||||
Reference in new issue
Block a user