feat(feishu): extract embedded video/media from post (rich text) messages (#21786)

* feat(feishu): extract embedded video/media from post (rich text) messages

Previously, parsePostContent() only extracted embedded images (img tags)
from rich text posts, ignoring embedded video/audio (media tags). Users
sending post messages with embedded videos would not have the media
downloaded or forwarded to the agent.

Changes:
- Extend parsePostContent() to also collect media tags with file_key
- Return new mediaKeys array alongside existing imageKeys
- Update resolveFeishuMediaList() to download embedded media files
  from post messages using the messageResource API
- Add appropriate logging for embedded media discovery and download

* Feishu: keep embedded post media payloads type-safe

* Feishu: format post parser after media tag extraction

---------

Co-authored-by: laopuhuluwa <laopuhuluwa@users.noreply.github.com>
Co-authored-by: Tak Hoffman <781889+Takhoffman@users.noreply.github.com>

extensions/feishu/src/bot.test.ts

@@ -682,6 +682,60 @@ describe("handleFeishuMessage command authorization", () => {
     );
   });
 
+  it("downloads embedded media tags from post messages as files", async () => {
+    mockShouldComputeCommandAuthorized.mockReturnValue(false);
+
+    const cfg: ClawdbotConfig = {
+      channels: {
+        feishu: {
+          dmPolicy: "open",
+        },
+      },
+    } as ClawdbotConfig;
+
+    const event: FeishuMessageEvent = {
+      sender: {
+        sender_id: {
+          open_id: "ou-sender",
+        },
+      },
+      message: {
+        message_id: "msg-post-media",
+        chat_id: "oc-dm",
+        chat_type: "p2p",
+        message_type: "post",
+        content: JSON.stringify({
+          title: "Rich text",
+          content: [
+            [
+              {
+                tag: "media",
+                file_key: "file_post_media_payload",
+                file_name: "embedded.mov",
+              },
+            ],
+          ],
+        }),
+      },
+    };
+
+    await dispatchMessage({ cfg, event });
+
+    expect(mockDownloadMessageResourceFeishu).toHaveBeenCalledWith(
+      expect.objectContaining({
+        messageId: "msg-post-media",
+        fileKey: "file_post_media_payload",
+        type: "file",
+      }),
+    );
+    expect(mockSaveMediaBuffer).toHaveBeenCalledWith(
+      expect.any(Buffer),
+      "video/mp4",
+      "inbound",
+      expect.any(Number),
+    );
+  });
+
   it("includes message_id in BodyForAgent on its own line", async () => {
     mockShouldComputeCommandAuthorized.mockReturnValue(false);
 

extensions/feishu/src/bot.ts

@@ -453,14 +453,19 @@ async function resolveFeishuMediaList(params: {
   const out: FeishuMediaInfo[] = [];
   const core = getFeishuRuntime();
 
-  // Handle post (rich text) messages with embedded images
+  // Handle post (rich text) messages with embedded images/media.
   if (messageType === "post") {
-    const { imageKeys } = parsePostContent(content);
-    if (imageKeys.length === 0) {
+    const { imageKeys, mediaKeys: postMediaKeys } = parsePostContent(content);
+    if (imageKeys.length === 0 && postMediaKeys.length === 0) {
       return [];
     }
 
-    log?.(`feishu: post message contains ${imageKeys.length} embedded image(s)`);
+    if (imageKeys.length > 0) {
+      log?.(`feishu: post message contains ${imageKeys.length} embedded image(s)`);
+    }
+    if (postMediaKeys.length > 0) {
+      log?.(`feishu: post message contains ${postMediaKeys.length} embedded media file(s)`);
+    }
 
     for (const imageKey of imageKeys) {
       try {
@@ -497,6 +502,40 @@ async function resolveFeishuMediaList(params: {
       }
     }
 
+    for (const media of postMediaKeys) {
+      try {
+        const result = await downloadMessageResourceFeishu({
+          cfg,
+          messageId,
+          fileKey: media.fileKey,
+          type: "file",
+          accountId,
+        });
+
+        let contentType = result.contentType;
+        if (!contentType) {
+          contentType = await core.media.detectMime({ buffer: result.buffer });
+        }
+
+        const saved = await core.channel.media.saveMediaBuffer(
+          result.buffer,
+          contentType,
+          "inbound",
+          maxBytes,
+        );
+
+        out.push({
+          path: saved.path,
+          contentType: saved.contentType,
+          placeholder: "<media:video>",
+        });
+
+        log?.(`feishu: downloaded embedded media ${media.fileKey}, saved to ${saved.path}`);
+      } catch (err) {
+        log?.(`feishu: failed to download embedded media ${media.fileKey}: ${String(err)}`);
+      }
+    }
+
     return out;
   }
 

extensions/feishu/src/post.ts

@@ -6,6 +6,7 @@ const MARKDOWN_SPECIAL_CHARS = /([\\`*_{}\[\]()#+\-!|>~])/g;
 type PostParseResult = {
   textContent: string;
   imageKeys: string[];
+  mediaKeys: Array<{ fileKey: string; fileName?: string }>;
   mentionedOpenIds: string[];
 };
 
@@ -125,7 +126,12 @@ function renderCodeBlockElement(element: Record<string, unknown>): string {
   return `\`\`\`${language}\n${code}${trailingNewline}\`\`\``;
 }
 
-function renderElement(element: unknown, imageKeys: string[], mentionedOpenIds: string[]): string {
+function renderElement(
+  element: unknown,
+  imageKeys: string[],
+  mediaKeys: Array<{ fileKey: string; fileName?: string }>,
+  mentionedOpenIds: string[],
+): string {
   if (!isRecord(element)) {
     return escapeMarkdownText(toStringOrEmpty(element));
   }
@@ -152,6 +158,14 @@ function renderElement(element: unknown, imageKeys: string[], mentionedOpenIds:
       }
       return "![image]";
     }
+    case "media": {
+      const fileKey = normalizeFeishuExternalKey(toStringOrEmpty(element.file_key));
+      if (fileKey) {
+        const fileName = toStringOrEmpty(element.file_name) || undefined;
+        mediaKeys.push({ fileKey, fileName });
+      }
+      return "[media]";
+    }
     case "emotion":
       return renderEmotionElement(element);
     case "br":
@@ -220,10 +234,16 @@ export function parsePostContent(content: string): PostParseResult {
     const parsed = JSON.parse(content);
     const payload = resolvePostPayload(parsed);
     if (!payload) {
-      return { textContent: FALLBACK_POST_TEXT, imageKeys: [], mentionedOpenIds: [] };
+      return {
+        textContent: FALLBACK_POST_TEXT,
+        imageKeys: [],
+        mediaKeys: [],
+        mentionedOpenIds: [],
+      };
     }
 
     const imageKeys: string[] = [];
+    const mediaKeys: Array<{ fileKey: string; fileName?: string }> = [];
     const mentionedOpenIds: string[] = [];
     const paragraphs: string[] = [];
 
@@ -233,7 +253,7 @@ export function parsePostContent(content: string): PostParseResult {
       }
       let renderedParagraph = "";
       for (const element of paragraph) {
-        renderedParagraph += renderElement(element, imageKeys, mentionedOpenIds);
+        renderedParagraph += renderElement(element, imageKeys, mediaKeys, mentionedOpenIds);
       }
       paragraphs.push(renderedParagraph);
     }
@@ -245,9 +265,10 @@ export function parsePostContent(content: string): PostParseResult {
     return {
       textContent: textContent || FALLBACK_POST_TEXT,
       imageKeys,
+      mediaKeys,
       mentionedOpenIds,
     };
   } catch {
-    return { textContent: FALLBACK_POST_TEXT, imageKeys: [], mentionedOpenIds: [] };
+    return { textContent: FALLBACK_POST_TEXT, imageKeys: [], mediaKeys: [], mentionedOpenIds: [] };
   }
 }