mirror of
https://github.com/BerriAI/litellm.git
synced 2026-09-10 22:41:41 +00:00
71a951691a
A deployment carrying reasoning_effort in its litellm_params on the /v1/messages passthrough mapped the effort to a legacy thinking block whose budget_tokens was forwarded as is, so any request whose max_tokens sat at or below that budget was rejected upstream with a 400. The mapped budget now runs through the same cap the adaptive-to-legacy branch and the chat path already use: it is clamped to max_tokens - 1, and dropped with a warning when even the minimum budget cannot fit. The cap helper becomes public since three call sites outside AnthropicConfig use it. |
||
|---|---|---|
| .. | ||
| chat | ||
| embedding | ||
| messages | ||
| responses | ||
| __init__.py | ||
| test_abliteration_provider.py | ||
| test_assemblyai_provider.py | ||
| test_charity_engine.py | ||
| test_cognition_provider.py | ||
| test_dynamic_config.py | ||
| test_empiriolabs_provider.py | ||
| test_json_providers.py | ||
| test_libertai_provider.py | ||
| test_meta_provider.py | ||
| test_pinstripes_provider.py | ||
| test_scx_ai_provider.py | ||
| test_tensormesh_provider.py | ||
| test_xiaomi_mimo.py | ||