chore(langchain): remove openai cost span metric

[Yun-Kim]

MLOB-2207

This PR removes the langchain.tokens.total_cost span metric which estimates the total cost of the llm interaction (and also by extension the wrapped chain span). This was an overly complex implementation that relied on a third party (langchain-community + tiktoken) library which is more-or-less deprecated when we can simply point users to enable LLM Observability to do the cost estimation for OpenAI spans anyway.

Note that this shouldn't break anything other than the span metric tag itself, integration metrics are already disabled with 3.0.

Checklist

• PR author has checked that all the criteria below are met
• The PR description includes an overview of the change
• The PR description articulates the motivation for the change
• The change includes tests OR the PR description describes a testing strategy
• The PR description notes risks associated with the change, if any
• Newly-added code is easy to change
• The change follows the library release note guidelines
• The change includes or references documentation updates if necessary
• Backport labels are set (if applicable)

Reviewer Checklist

• Reviewer has checked that all the criteria below are met
• Title is accurate
• All changes are related to the pull request's stated goal
• Avoids breaking API changes
• Testing strategy adequately addresses listed risks
• Newly-added code is easy to change
• Release note makes sense to a user of the library
• If necessary, author has acknowledged and discussed the performance implications of this PR as reported in the benchmarks PR comment
• Backport labels are set in a manner that is consistent with the release branch maintenance policy

[github-actions]

CODEOWNERS have been resolved as:

releasenotes/notes/deprecate-langchain-openai-cost-042f3a04cda9d23b.yaml  @DataDog/apm-python
ddtrace/contrib/internal/langchain/constants.py                         @DataDog/ml-observability
ddtrace/contrib/internal/langchain/patch.py                             @DataDog/ml-observability
tests/contrib/langchain/test_langchain.py                               @DataDog/ml-observability
tests/snapshots/tests.contrib.langchain.test_langchain.test_lcel_chain_batch.json  @DataDog/apm-python
tests/snapshots/tests.contrib.langchain.test_langchain.test_lcel_chain_complicated.json  @DataDog/apm-python
tests/snapshots/tests.contrib.langchain.test_langchain.test_lcel_chain_nested.json  @DataDog/apm-python
tests/snapshots/tests.contrib.langchain.test_langchain.test_lcel_chain_simple.json  @DataDog/apm-python
tests/snapshots/tests.contrib.langchain.test_langchain.test_lcel_chain_simple_async.json  @DataDog/apm-python
tests/snapshots/tests.contrib.langchain.test_langchain.test_lcel_with_tools_openai.json  @DataDog/apm-python
tests/snapshots/tests.contrib.langchain.test_langchain.test_openai_chat_model_async_generate.json  @DataDog/apm-python
tests/snapshots/tests.contrib.langchain.test_langchain.test_openai_chat_model_sync_call_langchain_openai.json  @DataDog/apm-python
tests/snapshots/tests.contrib.langchain.test_langchain.test_openai_chat_model_sync_generate.json  @DataDog/apm-python
tests/snapshots/tests.contrib.langchain.test_langchain.test_openai_chat_model_vision_generate.json  @DataDog/apm-python
tests/snapshots/tests.contrib.langchain.test_langchain.test_openai_llm_async.json  @DataDog/apm-python
tests/snapshots/tests.contrib.langchain.test_langchain.test_openai_llm_sync.json  @DataDog/apm-python
tests/snapshots/tests.contrib.langchain.test_langchain.test_openai_llm_sync_multiple_prompts.json  @DataDog/apm-python

[lievan]

just some comments about the release note

[pr-commenter]

Benchmarks

Benchmark execution time: 2025-02-05 23:00:57

Comparing candidate commit ec1bd48 in PR branch yunkim/fix-langchain-deprecated-cost with baseline commit 25e7e2e in branch 3.x-staging.

Found 0 performance improvements and 0 performance regressions! Performance is the same for 394 metrics, 2 unstable metrics.