diff --git a/nanobot/channels/feishu.py b/nanobot/channels/feishu.py
index 9017b40..bc4a2b8 100644
--- a/nanobot/channels/feishu.py
+++ b/nanobot/channels/feishu.py
@@ -39,6 +39,53 @@ MSG_TYPE_MAP = {
 }
 
 
+def _extract_post_text(content_json: dict) -> str:
+    """Extract plain text from Feishu post (rich text) message content.
+    
+    Supports two formats:
+    1. Direct format: {"title": "...", "content": [...]}
+    2. Localized format: {"zh_cn": {"title": "...", "content": [...]}}
+    """
+    def extract_from_lang(lang_content: dict) -> str | None:
+        if not isinstance(lang_content, dict):
+            return None
+        title = lang_content.get("title", "")
+        content_blocks = lang_content.get("content", [])
+        if not isinstance(content_blocks, list):
+            return None
+        text_parts = []
+        if title:
+            text_parts.append(title)
+        for block in content_blocks:
+            if not isinstance(block, 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')}")
+        return " ".join(text_parts).strip() if text_parts else None
+    
+    # Try direct format first
+    if "content" in content_json:
+        result = extract_from_lang(content_json)
+        if result:
+            return result
+    
+    # Try localized format
+    for lang_key in ("zh_cn", "en_us", "ja_jp"):
+        lang_content = content_json.get(lang_key)
+        result = extract_from_lang(lang_content)
+        if result:
+            return result
+    
+    return ""
+
+
 class FeishuChannel(BaseChannel):
     """
     Feishu/Lark channel using WebSocket long connection.
@@ -326,6 +373,12 @@ class FeishuChannel(BaseChannel):
                     content = json.loads(message.content).get("text", "")
                 except json.JSONDecodeError:
                     content = message.content or ""
+            elif msg_type == "post":
+                try:
+                    content_json = json.loads(message.content)
+                    content = _extract_post_text(content_json)
+                except (json.JSONDecodeError, TypeError):
+                    content = message.content or ""
             else:
                 content = MSG_TYPE_MAP.get(msg_type, f"[{msg_type}]")
             
diff --git a/nanobot/providers/litellm_provider.py b/nanobot/providers/litellm_provider.py
index 7865139..a39893b 100644
--- a/nanobot/providers/litellm_provider.py
+++ b/nanobot/providers/litellm_provider.py
@@ -122,6 +122,10 @@ class LiteLLMProvider(LLMProvider):
         """
         model = self._resolve_model(model or self.default_model)
         
+        # Clamp max_tokens to at least 1 — negative or zero values cause
+        # LiteLLM to reject the request with "max_tokens must be at least 1".
+        max_tokens = max(1, max_tokens)
+        
         kwargs: dict[str, Any] = {
             "model": model,
             "messages": messages,