fix(security): CORS限制+SSRF防护+PATCH乐观锁+accounts安全cap(4 important bugs)

- main.py + config.py: CORS origins read from Settings.cors_origins (comma-separated).
  Empty falls back to dev origin localhost:5173; never wildcard. Methods locked
  to GET/PATCH/POST; allow_credentials=False.
- scraper/media.py: download_url now passes follow_redirects=False to httpx.
  OSS URLs return 200 directly; a 3xx is treated as a download failure (caught
  by existing except clauses) instead of opening an SSRF vector to internal hosts.
- routers/voice_clips.py: PATCH /voice-clips/{id}/match accepts an optional
  If-Match header carrying the client's last-seen updated_at. On mismatch the
  row was modified by another request and the server returns 409. Without the
  header the behaviour is unchanged (backward compatible). Response now echoes
  the post-update updated_at so the client can fold it into the next request.
- routers/organization.py: /api/accounts now UNION ALLs the wechat_account and
  whatsapp_account projections at the SQL level and pushes COUNT + pagination
  (offset/limit) down to the DB. Stable ordering on (channel, account_id).
  Removes the in-memory materialization that broke at scale.

Tests: 395 passed. Added optimistic-lock coverage (If-Match accepted / stale 409 /
absent header backward-compat). Updated existing PATCH tests for the new
updated_at response field.

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

yunke-server/app/scraper/media.py

@@ -145,9 +145,17 @@ async def download_url(client: YunkeClient, url: str) -> bytes:
     for the public OSS media URLs, useful for any same-origin authenticated
     URLs) and is the transport ``respx`` mocks in the test suite, so media
     downloads go through the same mocked transport as every other scraper
-    request. Redirects are followed (OSS / avatar URLs commonly redirect).
+    request.
+
+    Redirects are NOT followed (SSRF protection): the URL is the trusted OSS /
+    recording endpoint resolved at scrape time, and following a 3xx would allow
+    a malicious or compromised host to redirect us to internal addresses such
+    as ``http://169.254.169.254/`` (cloud metadata) or other RFC1918 hosts.
+    OSS media URLs return the blob directly with 200; a 3xx here is treated as
+    a download failure and surfaces through the caller's existing
+    ``except (httpx.HTTPError, OSError)`` clause.
     """
-    resp = await client.client.get(url, follow_redirects=True)
+    resp = await client.client.get(url, follow_redirects=False)
     resp.raise_for_status()
     return resp.content