on_llm_end, invoke will provide the usage and stop_reason information

…on_chunk

Also allowed additional response_body information to be passed into the generation_info (such as token counts and stop reasons)

The on_llm_end call will include all GenerationChunks as well as info on usage and stop_reason (in the llm_output)

Added a provider stop code mapping

…sages api and outputs

…from the correct dict

…s api

Need the `message_delta` to return in order to get the stop reason and output token count

https://docs.anthropic.com/claude/reference/messages-streaming

…ncluding the stop_reason rather than just usage_info

Removing the on_llm_end that was added and moving to _call to match with the pattern used for the ChatModel (as this was causing on_llm_end to be called twice)

…d use

…nfo rather than the full chunks to make it compatible with some calls needed from ChatBedrock

Updating the usage info to use prompt_tokens and completion_tokens to match those returned from the non streaming route

…being cleared from the llm_output

This was returning llm_outputs with no usage information

…reaming and non-streaming generation and passing into the ChatResult

These appear to be holdovers from the langchain repo's structure and default branch

…ptured on_llm_end.

…hese integer values to prevent errors when merge_dicts is called from langchain_core.utils.

…PTlME/langchain-aws into bedrock-token-count-callbacks

… lists to the message_start message type.

…ion to reduce the code duplication.

…nfo` test would occasionally fail (returned "Hello! How are you doing?" one time)