LZH-YS1998 b2ff565ff6 fix(llm): clamp max_tokens to the model's output limit before each call ...

A generous config default (32768) hard-fails on providers that reject an
oversized max_tokens (e.g. DeepSeek caps output at 8192). Clamp to
litellm's max_output_tokens when known, log once per model; unknown
models pass through unchanged.

2026-07-04 18:03:53 +08:00

..

__init__.py

Initial commit

2026-07-01 17:56:31 +08:00

provider.py

fix(llm): clamp max_tokens to the model's output limit before each call

2026-07-04 18:03:53 +08:00

retry.py

Initial commit

2026-07-01 17:56:31 +08:00