Fix ChunkTokenLimitExceededError message formatting

- Prevent passes two separate string objects to __init__
- Maintain same error output

(cherry picked from commit 6fea68bff9)

lightrag/exceptions.py

@@ -68,10 +68,7 @@ class StorageNotInitializedError(RuntimeError):
             f"{storage_type} not initialized. Please ensure proper initialization:\n"
             f"\n"
             f"  rag = LightRAG(...)\n"
-            f"  await rag.initialize_storages()  # Required\n"
+            f"  await rag.initialize_storages()  # Required - auto-initializes pipeline_status\n"
-            f"  \n"
-            f"  from lightrag.kg.shared_storage import initialize_pipeline_status\n"
-            f"  await initialize_pipeline_status()  # Required for pipeline operations\n"
             f"\n"
             f"See: https://github.com/HKUDS/LightRAG#important-initialization-requirements"
         )
@@ -82,18 +79,21 @@ class PipelineNotInitializedError(KeyError):
 
     def __init__(self, namespace: str = ""):
         msg = (
-            f"Pipeline namespace '{namespace}' not found. "
+            f"Pipeline namespace '{namespace}' not found.\n"
-            f"This usually means pipeline status was not initialized.\n"
             f"\n"
-            f"Please call 'await initialize_pipeline_status()' after initializing storages:\n"
+            f"Pipeline status should be auto-initialized by initialize_storages().\n"
+            f"If you see this error, please ensure:\n"
             f"\n"
+            f"  1. You called await rag.initialize_storages()\n"
+            f"  2. For multi-workspace setups, each LightRAG instance was properly initialized\n"
+            f"\n"
+            f"Standard initialization:\n"
+            f"  rag = LightRAG(workspace='your_workspace')\n"
+            f"  await rag.initialize_storages()  # Auto-initializes pipeline_status\n"
+            f"\n"
+            f"If you need manual control (advanced):\n"
             f"  from lightrag.kg.shared_storage import initialize_pipeline_status\n"
-            f"  await initialize_pipeline_status()\n"
+            f"  await initialize_pipeline_status(workspace='your_workspace')"
-            f"\n"
-            f"Full initialization sequence:\n"
-            f"  rag = LightRAG(...)\n"
-            f"  await rag.initialize_storages()\n"
-            f"  await initialize_pipeline_status()"
         )
         super().__init__(msg)
 
@@ -106,6 +106,28 @@ class PipelineCancelledException(Exception):
         self.message = message
 
 
+class ChunkTokenLimitExceededError(ValueError):
+    """Raised when a chunk exceeds the configured token limit."""
+
+    def __init__(
+        self,
+        chunk_tokens: int,
+        chunk_token_limit: int,
+        chunk_preview: str | None = None,
+    ) -> None:
+        preview = chunk_preview.strip() if chunk_preview else None
+        truncated_preview = preview[:80] if preview else None
+        preview_note = f" Preview: '{truncated_preview}'" if truncated_preview else ""
+        message = (
+            f"Chunk token length {chunk_tokens} exceeds chunk_token_size {chunk_token_limit}."
+            f"{preview_note}"
+        )
+        super().__init__(message)
+        self.chunk_tokens = chunk_tokens
+        self.chunk_token_limit = chunk_token_limit
+        self.chunk_preview = truncated_preview
+
+
 class QdrantMigrationError(Exception):
     """Raised when Qdrant data migration from legacy collections fails."""