Mason Daugherty e91da86efe feat(openrouter): add streaming token usage support (#35559) ...

Streaming token usage was silently dropped for `ChatOpenRouter`. Both
`_stream` and `_astream` skipped any SSE chunk without a `choices` array
— which is exactly the shape OpenRouter uses for the final
usage-reporting chunk. This meant `usage_metadata` was never populated
on streamed responses, causing downstream consumers (like the Deep
Agents CLI) to show "unknown" model with 0 tokens.

## Changes
- Add `stream_usage: bool = True` field to `ChatOpenRouter`, which
passes `stream_options: {"include_usage": True}` to the OpenRouter API
when streaming — matching the pattern already established in
`langchain-openai`'s `BaseChatOpenAI`
- Handle usage-only chunks (no `choices`, just `usage`) in both
`_stream` and `_astream` by emitting a `ChatGenerationChunk` with
`usage_metadata` via `_create_usage_metadata`, instead of silently
`continue`-ing past them

2026-03-04 15:35:30 -05:00

..

integration_tests

feat(openrouter): add langchain-openrouter provider package (#35211)

2026-02-15 02:09:13 -05:00

unit_tests

feat(openrouter): add streaming token usage support (#35559)

2026-03-04 15:35:30 -05:00

__init__.py

feat(openrouter): add langchain-openrouter provider package (#35211)

2026-02-15 02:09:13 -05:00

conftest.py

feat(openrouter): add langchain-openrouter provider package (#35211)

2026-02-15 02:09:13 -05:00