fix(security): 路径穿越防护+导出行数上限+并发同步锁(3 critical/important)

- media.py: GET /api/media/{hash} 现强制 file 必须位于 Settings.media_dir
  沙箱内(resolve + relative_to),杜绝 local_path 越权读取任意文件。
- export.py: /api/export/chat-html 加 EXPORT_MAX_ROWS=5000 硬上限(.limit()),
  超出时仅渲染前 5000 条并插入 .export-warning 横幅,防止 OOM。
- scheduler.py: _safe_run 增加 SyncRun advisory lock(60min TTL),发现同
  entity 存在 status='running' 且在 TTL 内的记录即返回 skipped SyncResult;
  同时为本轮 stake 一行 wrapping SyncRun,让并发 CLI/scheduler/手动触发
  能相互避让。崩溃场景由 TTL 自动恢复。
- tests: 新增 path-traversal 拒绝/export 截断警告/advisory lock skip+TTL
  恢复 5 个测试;test_api_media 的 fixture 改为 MEDIA_DIR=tmp_path 以适配
  新沙箱语义。

Co-Authored-By: Claude <noreply@anthropic.com>

yunke-server/app/api/routers/export.py

@@ -21,6 +21,13 @@ router = APIRouter(prefix="/api/export", tags=["export"])
 
 SessionDep = Annotated[AsyncSession, Depends(get_session)]
 
+# Hard cap on rows an HTML export will load + render. An account-wide export
+# with no date range can match millions of messages; rendering all of them in
+# memory risks OOM. The cap is a safety valve, not a tight budget — at 5k rows
+# the HTML is already unwieldy in any browser. When hit, the response carries
+# a visible warning banner so the operator knows to narrow the date range.
+EXPORT_MAX_ROWS = 5000
+
 
 def _ts_text(ts: int | None) -> str:
     if not ts:
@@ -73,7 +80,14 @@ def _render_media(m) -> str:
     return ""
 
 
-def _render_chat_html(rows: list[Message], channel: str, owner: str, peer: str) -> str:
+def _render_chat_html(
+    rows: list[Message],
+    channel: str,
+    owner: str,
+    peer: str,
+    *,
+    warning: str = "",
+) -> str:
     bubbles = []
     for m in rows:
         side = "right" if m.is_send else "left"
@@ -90,6 +104,7 @@ def _render_chat_html(rows: list[Message], channel: str, owner: str, peer: str)
 <title>{title}</title><style>
 body{{font-family:-apple-system,Segoe UI,sans-serif;background:#f5f5f5;margin:0;padding:16px}}
 h1{{font-size:16px;margin:0 0 12px}}
+.export-warning{{background:#fff3cd;border:1px solid #ffeeba;color:#856404;padding:8px 12px;border-radius:4px;margin:0 0 12px;font-size:13px}}
 .bubble{{max-width:70%;margin:6px 0;padding:8px 12px;border-radius:8px;clear:both}}
 .bubble.right{{float:right;background:#95ec69;text-align:right}}
 .bubble.left{{float:left;background:#fff}}
@@ -98,7 +113,7 @@ h1{{font-size:16px;margin:0 0 12px}}
 .bubble .media{{margin-top:4px;font-size:13px}}
 .bubble .media audio,.bubble .media video,.bubble .media img{{display:block;max-width:100%}}
 .bubble .media .dur{{font-size:12px;color:#666;margin-left:4px}}
-</style></head><body><h1>{title}</h1>
+</style></head><body>{warning}<h1>{title}</h1>
 {''.join(bubbles) or '<p>暂无消息</p>'}
 </body></html>"""
 
@@ -132,9 +147,21 @@ async def export_chat_html(
         q = q.where(Message.timestamp >= start)
     if end is not None:
         q = q.where(Message.timestamp <= end)
-    q = q.order_by(sa.nullslast(Message.timestamp.asc()), Message.msg_id.asc())
+    q = q.order_by(sa.nullslast(Message.timestamp.asc()), Message.msg_id.asc()).limit(
+        EXPORT_MAX_ROWS
+    )
     rows = (await session.execute(q)).scalars().all()
-    html = _render_chat_html(list(rows), channel, owner_account_id, peer)
+    # If we filled the cap there may be more rows beyond it — surface a visible
+    # warning so the operator knows the export was truncated and can re-run
+    # with a tighter date range.
+    capped = len(rows) >= EXPORT_MAX_ROWS
+    warning = (
+        f'<div class="export-warning">⚠️ 结果超过 {EXPORT_MAX_ROWS} 条，'
+        f'仅导出前 {EXPORT_MAX_ROWS} 条。请缩小日期范围。</div>'
+        if capped
+        else ""
+    )
+    html = _render_chat_html(list(rows), channel, owner_account_id, peer, warning=warning)
     safe = peer or "all"
     filename = f"chat-{channel}-{owner_account_id}-{safe}.html".replace("@", "_").replace("/", "_")
     return Response(

yunke-server/app/api/routers/media.py

@@ -22,6 +22,7 @@ from fastapi.responses import FileResponse
 from sqlalchemy.ext.asyncio import AsyncSession
 
 from app.api.deps import get_session
+from app.config import get_settings
 from app.db.models import Media
 from app.scraper.media import guess_mime_type
 
@@ -41,7 +42,19 @@ async def get_media(media_hash: str, session: SessionDep) -> FileResponse:
     if row is None or not row.local_path:
         raise HTTPException(status_code=404, detail="media not found")
 
-    path = Path(row.local_path)
+    # Path-traversal defense: resolve absolute and confirm the file lives under
+    # the configured ``media_dir`` sandbox. A row whose ``local_path`` escapes
+    # media_dir (an absolute path elsewhere, or a ``..``-laced value) is treated
+    # as not found — never served. Defense-in-depth: even if a future bug or a
+    # hostile scrape payload ever lets ``local_path`` point outside the sandbox,
+    # this check keeps the file server constrained to media_dir.
+    media_dir = get_settings().media_dir.resolve()
+    path = Path(row.local_path).resolve()
+    try:
+        path.relative_to(media_dir)
+    except ValueError:
+        raise HTTPException(status_code=404, detail="media not found")
+
     if not path.is_file():
         # Row exists but the blob was removed out-of-band — treat as not-found.
         raise HTTPException(status_code=404, detail="media file missing")

yunke-server/app/sync/scheduler.py

@@ -50,6 +50,7 @@ from sqlalchemy.ext.asyncio import AsyncSession, async_sessionmaker, create_asyn
 from app.config import get_settings
 from app.db import models  # noqa: F401  (register tables on Base.metadata)
 from app.db.base import Base
+from app.db.models import SyncRun
 from app.session.yunke_client import YunkeClient
 from app.storage.object_store import ObjectStore
 from app.sync.orchestrator import (
@@ -83,6 +84,14 @@ __all__ = ["SyncScheduler", "ENTITY_FUNCS"]
 # request, so 200 conversations × N pages each can still take a while).
 DEFAULT_MAX_CONVERSATIONS_PER_RUN = 200
 
+# Advisory-lock TTL: a ``running`` SyncRun row older than this is considered
+# stale (the process probably crashed mid-run) and a new invocation may
+# proceed despite it. 60 min is generous — any entity fits inside — but
+# short enough that a crashed run auto-recovers within an hour. Tuned to
+# protect against concurrent CLI + scheduler invocations hammering 云控
+# with the same scope twice.
+ADVISORY_LOCK_TTL_MINUTES = 60
+
 
 # ---------------------------------------------------------------------------
 # Conversation discovery (drives the incremental message sync)
@@ -561,6 +570,15 @@ class SyncScheduler:
         This is the failure-policy wrapper that protects the scheduler loop:
         a raised exception becomes a logged error and an empty result list,
         and the scheduler keeps its next appointment.
+
+        Concurrency: an advisory lock refuses to run if another ``_safe_run``
+        for the same entity is still active. The lock is implemented by
+        staking a ``running`` SyncRun row keyed on the scheduler entity name
+        (e.g. ``"all"`` / ``"messages"`` / ``"friends"``) at the start and
+        finalizing it on completion. A concurrent invocation sees the row and
+        skips. The 60-min TTL (:data:`ADVISORY_LOCK_TTL_MINUTES`) auto-recovers
+        from a crashed process: a stale ``running`` row eventually falls
+        outside the window and a new run may proceed.
         """
         started_at = dt.datetime.now(dt.UTC)
         client: YunkeClient | None = None
@@ -568,8 +586,74 @@ class SyncScheduler:
         try:
             client = await _build_client_from_env()
             async with self._session_maker() as session:
+                # --- Advisory lock check ------------------------------
+                # ``SyncRun.started_at`` is a non-tz-aware DateTime; reading
+                # a row back yields a naive datetime, so the cutoff is built
+                # naive-UTC to keep the comparison type-consistent.
+                cutoff = (
+                    dt.datetime.now(dt.UTC).replace(tzinfo=None)
+                    - dt.timedelta(minutes=ADVISORY_LOCK_TTL_MINUTES)
+                )
+                existing = (
+                    await session.execute(
+                        sa.select(SyncRun)
+                        .where(SyncRun.entity_type == entity)
+                        .where(SyncRun.status == "running")
+                        .where(SyncRun.started_at > cutoff)
+                        .limit(1)
+                    )
+                ).scalar_one_or_none()
+                if existing is not None:
+                    logger.warning(
+                        "sync %s: skipped — another run is active"
+                        " (started %s)",
+                        entity,
+                        existing.started_at.isoformat(),
+                    )
+                    skipped = SyncResult(
+                        entity=entity,
+                        status="skipped",
+                        fetched=0,
+                        upserted=0,
+                        error=f"another sync is running for {entity}",
+                    )
+                    if log:
+                        _log_run(entity, [skipped], started_at=started_at)
+                    return [skipped]
+
+                # --- Stake our own 'running' row ----------------------
+                # A wrapping SyncRun at the scheduler-entity level (distinct
+                # from any sub-entity rows the orchestrator creates internally).
+                # On a caught exception the session rolls back and this row
+                # disappears with everything else — no phantom to recover
+                # from. On the success path the row is finalized + committed
+                # below. If the process hard-crashes between flush and commit,
+                # the row stays 'running' and blocks retries for up to TTL.
+                run = SyncRun(
+                    entity_type=entity,
+                    status="running",
+                    started_at=dt.datetime.now(dt.UTC),
+                )
+                session.add(run)
+                await session.flush()
+
                 runner = ENTITY_FUNCS[entity]
                 results = await runner(session, client, ObjectStore())
+
+                # --- Finalize the wrapping SyncRun --------------------
+                run.status = (
+                    "success"
+                    if all(r.status == "success" for r in results)
+                    else "failed"
+                )
+                run.records_fetched = sum(r.fetched for r in results)
+                run.records_upserted = sum(r.upserted for r in results)
+                run.finished_at = dt.datetime.now(dt.UTC)
+                if run.status == "failed":
+                    joined = "; ".join(
+                        filter(None, (r.error for r in results))
+                    )
+                    run.error = joined or None
                 await session.commit()
         except Exception as exc:  # noqa: BLE001 — scheduler MUST NOT crash
             logger.exception("sync %s failed", entity)