Mason Daugherty 61fd90a2f3 fix(core): extract usage metadata from serialized tracer message outputs (#35526) ...

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.

2026-03-02 17:43:33 -05:00

..

__init__.py

style(core): lint (#34862)

2026-01-23 23:07:48 -05:00

chat_generation.py

fix(core): fix setting ChatGeneration.text (#35191)

2026-02-12 15:43:53 -05:00

chat_result.py

fix(core): extract usage metadata from serialized tracer message outputs (#35526)

2026-03-02 17:43:33 -05:00

generation.py

style(core): lint (#34862)

2026-01-23 23:07:48 -05:00

llm_result.py

fix(core): extract usage metadata from serialized tracer message outputs (#35526)

2026-03-02 17:43:33 -05:00

run_info.py

style(core): lint (#34862)

2026-01-23 23:07:48 -05:00