mirror of
https://github.com/BerriAI/litellm.git
synced 2026-10-11 03:38:38 +00:00
9fae5cfda7
Probed real bedrock (commercial us-east-1) with a 14713-token cached prefix over streaming /v1/messages. Its raw message_delta already carries the cache breakdown alongside the uncached input_tokens, so usage stays self-consistent, prompt_tokens resolves to 14725 and the derived text_tokens to 12. Re-driving the same call with the fix reverted logged positive spend (0.00166463, 0.00165363) and zero negative rows, so _merge_message_start_cache_into_delta_usage is a no-op on this deployment. The bug needs a deployment whose message_delta omits the breakdown (GovCloud / LIT-2411), which a live commercial call cannot produce. Mark the path unsupported for live e2e rather than a gap nobody can close, keep the mock unit test as its guard, and write the evidence down so the probe is not repeated. |
||
|---|---|---|
| .. | ||
| access_control | ||
| batches | ||
| coverage_registry | ||
| llm_translation | ||
| logging | ||
| management | ||
| quota_management | ||
| bob_the_builder.py | ||
| CLAUDE.md | ||
| conftest.py | ||
| CONTRIBUTING.md | ||
| docker-compose.yml | ||
| e2e_config.py | ||
| e2e_gateway.py | ||
| e2e_http.py | ||
| lifecycle.py | ||
| models.py | ||
| pytest.ini | ||
| test_e2e_gateway.py | ||
| test_lifecycle.py | ||
| test_transport.py | ||
| transport.py | ||