Mason Daugherty 8d0fb2d04b fix(anthropic): correct input_token count for streaming (#32591) ...

* Create usage metadata on
[`message_delta`](https://docs.anthropic.com/en/docs/build-with-claude/streaming#event-types)
instead of at the beginning. Consequently, token counts are not included
during streaming but instead at the end. This allows for accurate
reporting of server-side tool usage (important for billing)
* Add some clarifying comments
* Fix some outstanding Pylance warnings
* Remove unnecessary `text` popping in thinking blocks
* Also now correctly reports `input_cache_read`/`input_cache_creation`
as a result

2025-08-18 17:51:47 +00:00

..

__init__.py

…

test_chat_models.py

fix(anthropic): update test model names and adjust token count assertions in integration tests (#32422)

2025-08-12 19:39:35 +00:00

test_compile.py

anthropic[patch]: ruff fixes and rules (#31899)

2025-07-07 18:32:27 -04:00

test_experimental.py

fix(anthropic): update integration test models (#32189)

2025-07-22 19:51:39 +00:00

test_llms.py

fix(anthropic): correct input_token count for streaming (#32591)

2025-08-18 17:51:47 +00:00

test_standard.py

fix(anthropic): correct input_token count for streaming (#32591)

2025-08-18 17:51:47 +00:00