fix(core): extract usage metadata from serialized tracer message outputs

[Mason Daugherty (mdrxy)]

Fixes missing run.metadata.usage_metadata population in LangChainTracer for real LLM/chat traces following #34414

• Fix extraction to read usage from serialized tracer message shape: outputs.generations[*][*].message.kwargs.usage_metadata
• Remove non-serialized direct message shape handling (message.usage_metadata) from extractor to match real tracer output path
• Clarify tracer docstrings around chat callback naming (on_chat_model_start + shared on_llm_end) to reduce ambiguity

Why

#34414 introduced usage duplication into run.metadata.usage_metadata, but the extractor read message.usage_metadata.

In real tracer flow, messages are serialized with dumpd(...) during run completion, so usage metadata lives under message.kwargs.usage_metadata. Because of this mismatch, duplication did not trigger in real traces.

[codspeed-hq]

Merging this PR will not alter performance

⚠️ Unknown Walltime execution environment detected

Using the Walltime instrument on standard Hosted Runners will lead to inconsistent data.

For the most accurate results, we recommend using CodSpeed Macro Runners: bare-metal machines fine-tuned for performance measurement consistency.

✅ 13 untouched benchmarks
⏩ 23 skipped benchmarks¹

---

_{Comparing mdrxy/fix-usage (f9ac259) with master (cdf140e)²}

Footnotes

1. 23 benchmarks were skipped, so the baseline results were used instead. If they were deleted from the codebase, click here and archive them to remove them from the performance reports. ↩

2. No successful run was found on master (d2c86df) during the generation of this report, so cdf140e was used instead as the comparison base. There might be some changes unrelated to this pull request in this report. ↩