Merge PR #1361: fix(feishu): parse post wrapper payload for rich text messages

nanobot/channels/feishu.py

@@ -181,57 +181,59 @@ def _extract_element_content(element: dict) -> list[str]:
 
 
 def _extract_post_content(content_json: dict) -> tuple[str, list[str]]:
-    """Extract text and image keys from Feishu post (rich text) message content.
+    """Extract text and image keys from Feishu post (rich text) message.
 
-    Supports two formats:
-    1. Direct format: {"title": "...", "content": [...]}
-    2. Localized format: {"zh_cn": {"title": "...", "content": [...]}}
-
-    Returns:
-        (text, image_keys) - extracted text and list of image keys
+    Handles three payload shapes:
+    - Direct:    {"title": "...", "content": [[...]]}
+    - Localized: {"zh_cn": {"title": "...", "content": [...]}}
+    - Wrapped:   {"post": {"zh_cn": {"title": "...", "content": [...]}}}
     """
-    def extract_from_lang(lang_content: dict) -> tuple[str | None, list[str]]:
-        if not isinstance(lang_content, dict):
+
+    def _parse_block(block: dict) -> tuple[str | None, list[str]]:
+        if not isinstance(block, dict) or not isinstance(block.get("content"), list):
             return None, []
-        title = lang_content.get("title", "")
-        content_blocks = lang_content.get("content", [])
-        if not isinstance(content_blocks, list):
-            return None, []
-        text_parts = []
-        image_keys = []
-        if title:
-            text_parts.append(title)
-        for block in content_blocks:
-            if not isinstance(block, list):
+        texts, images = [], []
+        if title := block.get("title"):
+            texts.append(title)
+        for row in block["content"]:
+            if not isinstance(row, list):
                 continue
-            for element in block:
-                if isinstance(element, dict):
-                    tag = element.get("tag")
-                    if tag == "text":
-                        text_parts.append(element.get("text", ""))
-                    elif tag == "a":
-                        text_parts.append(element.get("text", ""))
-                    elif tag == "at":
-                        text_parts.append(f"@{element.get('user_name', 'user')}")
-                    elif tag == "img":
-                        img_key = element.get("image_key")
-                        if img_key:
-                            image_keys.append(img_key)
-        text = " ".join(text_parts).strip() if text_parts else None
-        return text, image_keys
+            for el in row:
+                if not isinstance(el, dict):
+                    continue
+                tag = el.get("tag")
+                if tag in ("text", "a"):
+                    texts.append(el.get("text", ""))
+                elif tag == "at":
+                    texts.append(f"@{el.get('user_name', 'user')}")
+                elif tag == "img" and (key := el.get("image_key")):
+                    images.append(key)
+        return (" ".join(texts).strip() or None), images
 
-    # Try direct format first
-    if "content" in content_json:
-        text, images = extract_from_lang(content_json)
-        if text or images:
-            return text or "", images
+    # Unwrap optional {"post": ...} envelope
+    root = content_json
+    if isinstance(root, dict) and isinstance(root.get("post"), dict):
+        root = root["post"]
+    if not isinstance(root, dict):
+        return "", []
 
-    # Try localized format
-    for lang_key in ("zh_cn", "en_us", "ja_jp"):
-        lang_content = content_json.get(lang_key)
-        text, images = extract_from_lang(lang_content)
-        if text or images:
-            return text or "", images
+    # Direct format
+    if "content" in root:
+        text, imgs = _parse_block(root)
+        if text or imgs:
+            return text or "", imgs
+
+    # Localized: prefer known locales, then fall back to any dict child
+    for key in ("zh_cn", "en_us", "ja_jp"):
+        if key in root:
+            text, imgs = _parse_block(root[key])
+            if text or imgs:
+                return text or "", imgs
+    for val in root.values():
+        if isinstance(val, dict):
+            text, imgs = _parse_block(val)
+            if text or imgs:
+                return text or "", imgs
 
     return "", []
 

tests/test_feishu_post_content.py

@@ -0,0 +1,40 @@
+from nanobot.channels.feishu import _extract_post_content
+
+
+def test_extract_post_content_supports_post_wrapper_shape() -> None:
+    payload = {
+        "post": {
+            "zh_cn": {
+                "title": "日报",
+                "content": [
+                    [
+                        {"tag": "text", "text": "完成"},
+                        {"tag": "img", "image_key": "img_1"},
+                    ]
+                ],
+            }
+        }
+    }
+
+    text, image_keys = _extract_post_content(payload)
+
+    assert text == "日报 完成"
+    assert image_keys == ["img_1"]
+
+
+def test_extract_post_content_keeps_direct_shape_behavior() -> None:
+    payload = {
+        "title": "Daily",
+        "content": [
+            [
+                {"tag": "text", "text": "report"},
+                {"tag": "img", "image_key": "img_a"},
+                {"tag": "img", "image_key": "img_b"},
+            ]
+        ],
+    }
+
+    text, image_keys = _extract_post_content(payload)
+
+    assert text == "Daily report"
+    assert image_keys == ["img_a", "img_b"]