fix: use responses API (backport #83)

[mergify]

Use the OpenAI Responses API for model calls and upgrade langchain-openai, avoiding model-specific handling for reasoning models with tools. Extract output through AIMessage.text so structured reasoning metadata never appears in chat responses.

---

This is an automatic backport of pull request #83 done by Mergify.

[greptile-apps]

Confidence Score: 5/5

The PR appears safe to merge.

No blocking failure remains; the previously reported conflict markers have been removed from the current field-agent test module.

Sequence Diagram

sequenceDiagram
  participant Client
  participant AskALYF
  participant ChatOpenAI
  participant ResponsesAPI as OpenAI Responses API
  Client->>AskALYF: Send chat message
  AskALYF->>ChatOpenAI: Invoke agent with message history
  ChatOpenAI->>ResponsesAPI: POST /v1/responses
  ResponsesAPI-->>ChatOpenAI: AIMessage with response blocks
  ChatOpenAI-->>AskALYF: Agent result messages
  AskALYF->>AskALYF: Extract AIMessage.text
  AskALYF-->>Client: Final answer text

Loading

_{Reviews (3): Last reviewed commit: "style: remove blank line" | Re-trigger Greptile}