mirror of
https://github.com/BerriAI/litellm.git
synced 2026-11-13 08:52:02 +00:00
0021d5493c
* fix(bedrock): answer 400, not 500, for malformed native count-tokens requests The Bedrock count-tokens handler now checks the body before any AWS call and raises a 400 BedrockError for a missing or empty messages list, a message without role or content, or a missing model. The token counter marks that rejection as local, so it skips the Mantle fallback and the framing estimate, and /v1/messages/count_tokens answers invalid_request_error get_bedrock_base_model returns a bare cross-region prefix such as us or global unchanged instead of raising IndexError, so Bedrock judges the model id and its own 400 reaches the caller * fix(bedrock): answer 400 for a malformed message on Mantle token counts * fix(bedrock): limit the region-only model id fix to token counting * fix(bedrock): count a routing-prefixed region-only id and leave other providers' count errors as they were --------- Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com> |
||
|---|---|---|
| .. | ||
| __init__.py | ||
| test_answered_status.py | ||
| test_claude_code_marketplace.py | ||
| test_claude_code_skill_access.py | ||
| test_endpoints.py | ||
| test_gateway_endpoints.py | ||
| test_skill_upload_archive.py | ||
| test_skills_endpoints.py | ||
| test_streaming_model_restamp.py | ||