Minghao Xiao c2524473e7 fix(consolidation): set output token budget (#1967) ...

* fix(consolidation): set output token budget

* fix(consolidation): default max_completion_tokens to unset for full backwards compat

A 64k default still passes a raw value through to models LiteLLM does not
have a registry cap for (e.g. non-registered models on OpenAI/Gemini),
which is not a guaranteed no-op. Leaving it unset omits the key entirely
so every provider keeps its current implicit output budget — byte
identical to prior behaviour. Operators on providers with a low hidden
cap (notably Bedrock imported models) set the env var to fix #1939.

---------

Co-authored-by: Nicolò Boschi <boschi1997@gmail.com>

2026-06-08 15:27:04 +02:00

..

developer

fix(consolidation): set output token budget (#1967)

2026-06-08 15:27:04 +02:00

sdks

Release v0.7.2

2026-06-02 15:17:05 +02:00