Fix on_llm_new_token(chunk=) for some chat models (#12784)

It was passing in message instead of generation

<!-- Thank you for contributing to LangChain!

Replace this entire comment with:
  - **Description:** a description of the change, 
  - **Issue:** the issue # it fixes (if applicable),
  - **Dependencies:** any dependencies required for this change,
- **Tag maintainer:** for a quicker response, tag the relevant
maintainer (see below),
- **Twitter handle:** we announce bigger features on Twitter. If your PR
gets announced, and you'd like a mention, we'll gladly shout you out!

Please make sure your PR is passing linting and testing before
submitting. Run `make format`, `make lint` and `make test` to check this
locally.

See contribution guidelines for more information on how to write/run
tests, lint, etc:

https://github.com/langchain-ai/langchain/blob/master/.github/CONTRIBUTING.md

If you're adding a new integration, please include:
1. a test for the integration, preferably unit tests that do not rely on
network access,
2. an example notebook showing its use. It lives in `docs/extras`
directory.

If no one reviews your PR within a few days, please @-mention one of
@baskaryan, @eyurtsev, @hwchase17.
 -->

libs/langchain/langchain/chat_models/fireworks.py

@@ -210,9 +210,10 @@ class ChatFireworks(BaseChatModel):
                 dict(finish_reason=finish_reason) if finish_reason is not None else None
             )
             default_chunk_class = chunk.__class__
-            yield ChatGenerationChunk(message=chunk, generation_info=generation_info)
+            chunk = ChatGenerationChunk(message=chunk, generation_info=generation_info)
+            yield chunk
             if run_manager:
-                run_manager.on_llm_new_token(chunk.content, chunk=chunk)
+                run_manager.on_llm_new_token(chunk.text, chunk=chunk)
 
     async def _astream(
         self,
@@ -239,9 +240,10 @@ class ChatFireworks(BaseChatModel):
                 dict(finish_reason=finish_reason) if finish_reason is not None else None
             )
             default_chunk_class = chunk.__class__
-            yield ChatGenerationChunk(message=chunk, generation_info=generation_info)
+            chunk = ChatGenerationChunk(message=chunk, generation_info=generation_info)
+            yield chunk
             if run_manager:
-                await run_manager.on_llm_new_token(token=chunk.content, chunk=chunk)
+                await run_manager.on_llm_new_token(token=chunk.text, chunk=chunk)
 
 
 def conditional_decorator(

libs/langchain/langchain/chat_models/konko.py

@@ -212,9 +212,10 @@ class ChatKonko(ChatOpenAI):
                 dict(finish_reason=finish_reason) if finish_reason is not None else None
             )
             default_chunk_class = chunk.__class__
-            yield ChatGenerationChunk(message=chunk, generation_info=generation_info)
+            chunk = ChatGenerationChunk(message=chunk, generation_info=generation_info)
+            yield chunk
             if run_manager:
-                run_manager.on_llm_new_token(chunk.content, chunk=chunk)
+                run_manager.on_llm_new_token(chunk.text, chunk=chunk)
 
     def _generate(
         self,

libs/langchain/langchain/chat_models/openai.py

@@ -341,9 +341,10 @@ class ChatOpenAI(BaseChatModel):
                 dict(finish_reason=finish_reason) if finish_reason is not None else None
             )
             default_chunk_class = chunk.__class__
-            yield ChatGenerationChunk(message=chunk, generation_info=generation_info)
+            chunk = ChatGenerationChunk(message=chunk, generation_info=generation_info)
+            yield chunk
             if run_manager:
-                run_manager.on_llm_new_token(chunk.content, chunk=chunk)
+                run_manager.on_llm_new_token(chunk.text, chunk=chunk)
 
     def _generate(
         self,
@@ -415,9 +416,10 @@ class ChatOpenAI(BaseChatModel):
                 dict(finish_reason=finish_reason) if finish_reason is not None else None
             )
             default_chunk_class = chunk.__class__
-            yield ChatGenerationChunk(message=chunk, generation_info=generation_info)
+            chunk = ChatGenerationChunk(message=chunk, generation_info=generation_info)
+            yield chunk
             if run_manager:
-                await run_manager.on_llm_new_token(token=chunk.content, chunk=chunk)
+                await run_manager.on_llm_new_token(token=chunk.text, chunk=chunk)
 
     async def _agenerate(
         self,

libs/langchain/langchain/chat_models/tongyi.py

@@ -360,9 +360,10 @@ class ChatTongyi(BaseChatModel):
                 dict(finish_reason=finish_reason) if finish_reason is not None else None
             )
             default_chunk_class = chunk.__class__
-            yield ChatGenerationChunk(message=chunk, generation_info=generation_info)
+            chunk = ChatGenerationChunk(message=chunk, generation_info=generation_info)
+            yield chunk
             if run_manager:
-                run_manager.on_llm_new_token(chunk.content, chunk=chunk)
+                run_manager.on_llm_new_token(chunk.text, chunk=chunk)
             length = len(choice["message"]["content"])
 
     def _create_message_dicts(