community[minor]: add bedrock anthropic callback for token usage counting (#19864)

**Description:** add bedrock anthropic callback for token usage
counting, consulted openai callback.

---------

Co-authored-by: Massimiliano Pronesti <massimiliano.pronesti@gmail.com>

libs/community/tests/unit_tests/callbacks/test_callback_manager.py

@@ -7,6 +7,7 @@ from langchain_core.outputs import LLMResult
 from langchain_core.tracers.langchain import LangChainTracer, wait_for_all_tracers
 
 from langchain_community.callbacks import get_openai_callback
+from langchain_community.callbacks.manager import get_bedrock_anthropic_callback
 from langchain_community.llms.openai import BaseOpenAI
 
 
@@ -77,6 +78,37 @@ def test_callback_manager_configure_context_vars(
                     )
                     mngr.on_llm_start({}, ["prompt"])[0].on_llm_end(response)
 
+                    # The callback handler has been updated
+                    assert cb.successful_requests == 1
+                    assert cb.total_tokens == 3
+                    assert cb.prompt_tokens == 2
+                    assert cb.completion_tokens == 1
+                    assert cb.total_cost > 0
+
+                with get_bedrock_anthropic_callback() as cb:
+                    # This is a new empty callback handler
+                    assert cb.successful_requests == 0
+                    assert cb.total_tokens == 0
+
+                    # configure adds this bedrock anthropic cb,
+                    # but doesn't modify the group manager
+                    mngr = CallbackManager.configure(group_manager)
+                    assert mngr.handlers == [tracer, cb]
+                    assert group_manager.handlers == [tracer]
+
+                    response = LLMResult(
+                        generations=[],
+                        llm_output={
+                            "usage": {
+                                "prompt_tokens": 2,
+                                "completion_tokens": 1,
+                                "total_tokens": 3,
+                            },
+                            "model_id": "anthropic.claude-instant-v1",
+                        },
+                    )
+                    mngr.on_llm_start({}, ["prompt"])[0].on_llm_end(response)
+
                     # The callback handler has been updated
                     assert cb.successful_requests == 1
                     assert cb.total_tokens == 3

libs/community/tests/unit_tests/chat_models/test_bedrock.py

@@ -58,3 +58,32 @@ def test_different_models_bedrock(model_id: str) -> None:
 
     # should not throw an error
     model.invoke("hello there")
+
+
+def test_bedrock_combine_llm_output() -> None:
+    model_id = "anthropic.claude-3-haiku-20240307-v1:0"
+    client = MagicMock()
+    llm_outputs = [
+        {
+            "model_id": "anthropic.claude-3-haiku-20240307-v1:0",
+            "usage": {
+                "completion_tokens": 1,
+                "prompt_tokens": 2,
+                "total_tokens": 3,
+            },
+        },
+        {
+            "model_id": "anthropic.claude-3-haiku-20240307-v1:0",
+            "usage": {
+                "completion_tokens": 1,
+                "prompt_tokens": 2,
+                "total_tokens": 3,
+            },
+        },
+    ]
+    model = BedrockChat(model_id=model_id, client=client)
+    final_output = model._combine_llm_outputs(llm_outputs)
+    assert final_output["model_id"] == model_id
+    assert final_output["usage"]["completion_tokens"] == 2
+    assert final_output["usage"]["prompt_tokens"] == 4
+    assert final_output["usage"]["total_tokens"] == 6