Fix mutation bugs in callback manager configure (#11603)

<!-- 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/callbacks/manager.py

@@ -1891,13 +1891,13 @@ def _configure(
             )
         else:
             callback_manager = callback_manager_cls(
-                handlers=inheritable_callbacks.handlers,
-                inheritable_handlers=inheritable_callbacks.inheritable_handlers,
+                handlers=inheritable_callbacks.handlers.copy(),
+                inheritable_handlers=inheritable_callbacks.inheritable_handlers.copy(),
                 parent_run_id=inheritable_callbacks.parent_run_id,
-                tags=inheritable_callbacks.tags,
-                inheritable_tags=inheritable_callbacks.inheritable_tags,
-                metadata=inheritable_callbacks.metadata,
-                inheritable_metadata=inheritable_callbacks.inheritable_metadata,
+                tags=inheritable_callbacks.tags.copy(),
+                inheritable_tags=inheritable_callbacks.inheritable_tags.copy(),
+                metadata=inheritable_callbacks.metadata.copy(),
+                inheritable_metadata=inheritable_callbacks.inheritable_metadata.copy(),
             )
         local_handlers_ = (
             local_callbacks
@@ -1991,7 +1991,7 @@ def _configure(
                         e,
                     )
         if open_ai is not None and not any(
-            isinstance(handler, OpenAICallbackHandler)
+            handler is open_ai  # direct pointer comparison
             for handler in callback_manager.handlers
         ):
             callback_manager.add_handler(open_ai, True)

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

@@ -4,8 +4,15 @@ from typing import List, Tuple
 import pytest
 
 from langchain.callbacks.base import BaseCallbackHandler
-from langchain.callbacks.manager import AsyncCallbackManager, CallbackManager
+from langchain.callbacks.manager import (
+    AsyncCallbackManager,
+    CallbackManager,
+    get_openai_callback,
+    trace_as_chain_group,
+)
 from langchain.callbacks.stdout import StdOutCallbackHandler
+from langchain.callbacks.tracers.langchain import LangChainTracer
+from langchain.llms.openai import BaseOpenAI
 from langchain.schema import AgentAction, AgentFinish, LLMResult
 from tests.unit_tests.callbacks.fake_callback_handler import (
     BaseFakeCallbackHandler,
@@ -291,3 +298,75 @@ def test_callback_manager_configure(monkeypatch: pytest.MonkeyPatch) -> None:
         handler4,
     ]
     assert isinstance(async_configured_manager, AsyncCallbackManager)
+
+
+def test_callback_manager_configure_context_vars(
+    monkeypatch: pytest.MonkeyPatch,
+) -> None:
+    monkeypatch.setenv("LANGCHAIN_TRACING_V2", "false")
+    monkeypatch.setenv("LANGCHAIN_TRACING", "false")
+
+    with trace_as_chain_group("test") as group_manager:
+        assert len(group_manager.handlers) == 1
+        tracer = group_manager.handlers[0]
+        assert isinstance(tracer, LangChainTracer)
+
+        with get_openai_callback() as cb:
+            # This is a new empty callback handler
+            assert cb.successful_requests == 0
+            assert cb.total_tokens == 0
+
+            # configure adds this openai 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={
+                    "token_usage": {
+                        "prompt_tokens": 2,
+                        "completion_tokens": 1,
+                        "total_tokens": 3,
+                    },
+                    "model_name": BaseOpenAI.__fields__["model_name"].default,
+                },
+            )
+            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_openai_callback() as cb:
+            # This is a new empty callback handler
+            assert cb.successful_requests == 0
+            assert cb.total_tokens == 0
+
+            # configure adds this openai 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={
+                    "token_usage": {
+                        "prompt_tokens": 2,
+                        "completion_tokens": 1,
+                        "total_tokens": 3,
+                    },
+                    "model_name": BaseOpenAI.__fields__["model_name"].default,
+                },
+            )
+            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