mirror of
https://github.com/MODSetter/SurfSense.git
synced 2026-05-25 19:15:18 +02:00
LiteLLM normalizes every provider's cache fields onto usage.prompt_tokens_details (cached_tokens + cache_creation_tokens). The earlier fallback to usage.cache_read_input_tokens / usage.cache_creation_input_tokens was wrong: Anthropic-shaped fields only live there via a trailing setattr loop, and the canonical field name on the wrapper is cache_creation_tokens (not _input_tokens). |
||
|---|---|---|
| .. | ||
| alembic | ||
| app | ||
| scripts | ||
| tests | ||
| .dockerignore | ||
| .env.example | ||
| .gitignore | ||
| .python-version | ||
| alembic.ini | ||
| celery_worker.py | ||
| Dockerfile | ||
| main.py | ||
| pyproject.toml | ||
| uv.lock | ||