fix: use responses API - #83
Conversation
|
@Mergifyio backport version-15 develop |
✅ Backports have been createdDetails
Cherry-pick of 05bdd55 has failed: To fix up this pull request, you can check it out locally. See documentation: https://docs.github.com/en/pull-requests/collaborating-with-pull-requests/reviewing-changes-in-pull-requests/checking-out-pull-requests-locally
|
Confidence Score: 4/5The PR does not appear safe to merge while existing OpenAI Compatible configurations can still be routed to an unsupported Responses endpoint. The model builder unconditionally enables Responses API routing for both OpenAI and OpenAI Compatible providers, so configured servers that only implement Chat Completions still fail on invocation; documenting that limitation does not preserve the existing provider contract. Files Needing Attention: ask_alyf/ask_alyf/agent.py, ask_alyf/ask_alyf/field_agent.py
|
|
@Mergifyio backport version-15 develop |
☑️ Command
|
Use the OpenAI Responses API for model calls and upgrade
langchain-openai, avoiding model-specific handling for reasoning models with tools. Extract output throughAIMessage.textso structured reasoning metadata never appears in chat responses.