orangeclk 5da395ab86 feat(volcengine): add DeepSeek V4, GLM-5.2, Doubao-Seed-2.1 models and extend reasoning_effort support (#3434) ...

- Add deepseek-v4-pro-260425, deepseek-v4-flash-260425
- Add glm-5-2-260617
- Add doubao-seed-2-1-pro-260628, doubao-seed-2-1-turbo-260628, doubao-seed-evolving-latest-version
- Deprecate deepseek-v3-1-terminus and deepseek-v3-250324 in favor of V4
- Expand reasoning_effort Literal to cover none/low/medium/high/xhigh/max
- Read reasoning_effort from model_parameters instead of only inferring minimal from disabled thinking
- Bump version 0.0.11 -> 0.0.12

2026-07-14 13:51:24 +08:00

..

test_llm_call.py

feat(volcengine): add DeepSeek V4, GLM-5.2, Doubao-Seed-2.1 models and extend reasoning_effort support (#3434)

2026-07-14 13:51:24 +08:00

test_polling_llm.py

feat(models): expose Ark video generation custom models (#3386)

2026-07-06 19:28:40 +08:00