Yijia-Xiao 3cddf1e331 fix(llm): use the OpenAI Responses API only for native endpoints ...

The Responses API exists only on native OpenAI. When the openai provider is
pointed at a custom base_url (a proxy, gateway, or local server that speaks only
Chat Completions), keep the Responses API off so the call does not fail.

2026-06-14 07:23:19 +00:00

..

__init__.py

feat: add multi-provider LLM support with factory pattern

2026-02-03 22:27:20 +00:00

anthropic_client.py

feat(config): expose sampling temperature and document reproducibility

2026-05-31 03:51:50 +00:00

api_key_env.py

feat(llm): add Amazon Bedrock as a first-class provider

2026-06-14 04:24:54 +00:00

azure_client.py

feat(config): expose sampling temperature and document reproducibility

2026-05-31 03:51:50 +00:00

base_client.py

Merge pull request #464 from CadeYu/sync-validator-models

2026-03-29 11:07:51 -07:00

bedrock_client.py

feat(llm): add Amazon Bedrock as a first-class provider

2026-06-14 04:24:54 +00:00

capabilities.py

fix(llm): gate MiniMax reasoning_split by model capability (#826)

2026-05-17 07:49:42 +00:00

factory.py

feat(llm): add Amazon Bedrock as a first-class provider

2026-06-14 04:24:54 +00:00

google_client.py

feat(config): expose sampling temperature and document reproducibility

2026-05-31 03:51:50 +00:00

model_catalog.py

feat(llm): add Amazon Bedrock as a first-class provider

2026-06-14 04:24:54 +00:00

openai_client.py

fix(llm): use the OpenAI Responses API only for native endpoints

2026-06-14 07:23:19 +00:00

validators.py

feat(llm): add Amazon Bedrock as a first-class provider

2026-06-14 04:24:54 +00:00