fix(llmobs): fix token usage parsing error for langchain ai message

[lievan]

https://datadoghq.atlassian.net/browse/MLOB-2839

Add a check that we already do for chat / llm messages for ai message type to avoid potential attribute errors when usage is None or not a dictionary

This issue is potentially related langchain-ai/langgraph#3936

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/fix-ai-tokens-df16a9c7acd23805.yaml                  @DataDog/apm-python
ddtrace/llmobs/_integrations/langchain.py                               @DataDog/ml-observability

[github-actions]

Bootstrap import analysis

Comparison of import times between this PR and base.

Summary

The average import time from this PR is: 241 ± 4 ms.

The average import time from base is: 246 ± 4 ms.

The import time difference between this PR and base is: -4.5 ± 0.2 ms.

Import time breakdown

The following import paths have shrunk:

ddtrace.auto 2.210 ms (0.92%)

ddtrace.bootstrap.sitecustomize 1.520 ms (0.63%)

ddtrace.bootstrap.preload 1.520 ms (0.63%)

ddtrace.internal.remoteconfig.client 0.736 ms (0.31%)

ddtrace 0.690 ms (0.29%)

ddtrace.internal._unpatched 0.026 ms (0.01%)

[pr-commenter]

Benchmarks

Benchmark execution time: 2025-05-29 15:42:43

Comparing candidate commit 8092ea0 in PR branch evan.li/token-usage-fix with baseline commit 074b3be in branch main.

Found 3 performance improvements and 0 performance regressions! Performance is the same for 507 metrics, 6 unstable metrics.

scenario:iastdjangostartup-appsec

• 🟩 execution_time [-1.114s; -1.042s] or [-56.585%; -52.921%]

scenario:iastdjangostartup-iast

• 🟩 execution_time [-1047.259ms; -809.329ms] or [-43.916%; -33.939%]

scenario:iastdjangostartup-tracer

• 🟩 execution_time [-852.278ms; -745.710ms] or [-48.468%; -42.407%]