feat(video): DashScope video specialist with correct i2v request bodies

- Add video_generation_client: async video-synthesis, t2v vs i2v (Wan 2.7 input.media first_frame vs legacy img_url).

- Coerce *-t2v* to *-i2v* when first frame present; AIA_VIDEO_I2V_INPUT_STYLE / I2V_MODEL overrides.

- Gateway/direct_loop early return for video specialist; workspace video + factory allowlist.

- Normalize WS and admin chat attachments (image_ref parity); mp4 attachment store roundtrip tests.

Co-authored-by: Cursor <cursoragent@cursor.com>

interfaces/admin/chat_api.py

@@ -2,7 +2,6 @@
 
 from __future__ import annotations
 
-import base64
 import json
 import queue
 import threading
@@ -28,8 +27,8 @@ from oclaw.platform.files.file_attachments import (
     DEFAULT_MAX_EXCEL_SHEETS,
     DEFAULT_TABULAR_ROWS_READ,
     clear_attachment_limits_cache,
-    process_file_data,
 )
+from oclaw.interfaces.ws.common import normalize_ws_attachments
 from oclaw.platform.files.session_export import export_session_json, export_session_markdown
 from oclaw.platform.persistence.sqlite_store import SqliteStore
 from oclaw.runtime.gateway import OclawGateway
@@ -270,45 +269,9 @@ def _clear_stop(session_id: str) -> None:
         _CHAT_STOP_EVENTS.pop(str(session_id), None)
 
 
-def _decode_base64_payload(s: str) -> bytes | None:
-    """Decode base64 from browser (may lack padding; URL-safe variants)."""
-    raw = (s or "").strip()
-    if not raw:
-        return None
-    if raw.startswith("data:") and "," in raw:
-        raw = raw.split(",", 1)[1].strip()
-    raw = raw.replace("-", "+").replace("_", "/")
-    pad = (-len(raw)) % 4
-    if pad:
-        raw += "=" * pad
-    try:
-        return base64.b64decode(raw, validate=False)
-    except Exception:
-        try:
-            return base64.standard_b64decode(raw)
-        except Exception:
-            return None
-
-
 def _parse_attachments_payload(raw: Any) -> list[dict[str, Any]] | None:
-    if not raw:
-        return None
-    if not isinstance(raw, list):
-        return None
-    out: list[dict[str, Any]] = []
-    for item in raw:
-        if not isinstance(item, dict):
-            continue
-        name = str(item.get("name") or "file").strip() or "file"
-        b64 = item.get("data_base64") if "data_base64" in item else item.get("data")
-        if not isinstance(b64, str) or not b64.strip():
-            continue
-        data = _decode_base64_payload(b64)
-        if not data:
-            continue
-        got = process_file_data(name, data)
-        if got:
-            out.extend(got)
+    """Match WebSocket :func:`normalize_ws_attachments`: base64 uploads plus pass-through typed refs."""
+    out = normalize_ws_attachments(raw)
     return out if out else None
 
 

interfaces/admin/static/chat.js

@@ -168,6 +168,7 @@ const I18N = {
     "chat.specialistGeneralistShort": "通用",
     "chat.specialistOpsShort": "运维",
     "chat.specialistImageShort": "图像",
+    "chat.specialistVideoShort": "视频",
     "chat.specialistMemoryShort": "记忆",
     "chat.specialistManagerSelfShort": "全能者",
     "chat.attachment.download": "下载",
@@ -344,6 +345,7 @@ const I18N = {
     "chat.specialistGeneralistShort": "Generalist",
     "chat.specialistOpsShort": "Ops",
     "chat.specialistImageShort": "Image",
+    "chat.specialistVideoShort": "Video",
     "chat.specialistMemoryShort": "Memory",
     "chat.specialistManagerSelfShort": "Manager",
     "chat.attachment.download": "Download",
@@ -649,6 +651,7 @@ function specialistLabel(specialist) {
   if (s === "manager_self") return t("chat.specialistManagerSelfShort");
   if (s === "ops") return t("chat.specialistOpsShort");
   if (s === "image") return t("chat.specialistImageShort");
+  if (s === "video") return t("chat.specialistVideoShort");
   if (s === "memory") return t("chat.specialistMemoryShort");
   return t("chat.specialistGeneralistShort");
 }
@@ -2190,6 +2193,39 @@ async function renderAttachmentsEl(raw) {
             text: t("chat.attachment.download"),
           }),
         );
+        if (String(typ || "") === "video_ref" && mime.toLowerCase().startsWith("video/")) {
+          card.appendChild(
+            el("video", {
+              class: "chat-att-video",
+              controls: true,
+              preload: "metadata",
+              style: "max-width:100%;max-height:420px;margin-top:8px;border-radius:8px;",
+              src: url,
+            }),
+          );
+        }
+      }
+    } else {
+      const remote = String(att.url || "").trim();
+      if (remote && String(typ || "") === "video_ref" && mime.toLowerCase().startsWith("video/")) {
+        card.appendChild(
+          el("video", {
+            class: "chat-att-video",
+            controls: true,
+            preload: "metadata",
+            style: "max-width:100%;max-height:420px;margin-top:8px;border-radius:8px;",
+            src: remote,
+          }),
+        );
+        card.appendChild(
+          el("a", {
+            class: "chat-att-ref__link",
+            href: remote,
+            target: "_blank",
+            rel: "noopener noreferrer",
+            text: t("chat.attachment.download"),
+          }),
+        );
       }
     }
     const canPreviewText = !!aid && (String(typ || "") === "text_ref" || isTextLikeMime(mime));