Update docs to reference Responses API instead of Chat Completions

[pamelafox]

The code now uses client.responses.create throughout, but the documentation still referenced "Chat Completions" in several places. This PR updates all stale wording:

README.md:

• Intro: "OpenAI Responses API" instead of "generate chat completions"
• Section heading: "OpenAI Responses" instead of "OpenAI Chat Completions"
• Function calling section: "Responses API" instead of "Chat Completions API"
• Minor wording updates in chat.py, chat_history.py, and rag_multiturn.py descriptions

AGENTS.md:

• Overview: "OpenAI Responses API" instead of "generate chat completions"
• "Basic responses" instead of "Basic chat completions"
• "Chat Scripts" instead of "Chat Completion Scripts"

spanish/README.md:

• Intro: "API de Responses de OpenAI" instead of "generar completados de chat"
• Section heading: "Responses de OpenAI" instead of "Completados de chat de OpenAI"
• Function calling section: "API de Responses" instead of "API de Chat Completions"

[Copilot]

Pull request overview

This PR updates repository documentation to consistently refer to the OpenAI Responses API (matching the existing client.responses.create usage in the demo scripts), replacing stale “Chat Completions” terminology in English and Spanish docs.

Changes:

• Rename README/AGENTS headings and narrative from “Chat Completions” to “Responses”.
• Update function-calling and RAG descriptions to reference the Responses API.
• Apply equivalent terminology updates in spanish/README.md.

Show a summary per file

File	Description
README.md	Updates primary repo documentation to reference the Responses API instead of Chat Completions.
AGENTS.md	Updates agent-facing repo overview and script taxonomy to align with Responses API terminology.
spanish/README.md	Updates Spanish README headings and descriptions to reference Responses API terminology.

Copilot's findings

Tip

Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

Comments suppressed due to low confidence (2)

README.md:39

• The updated Function calling section still says the model may respond with message.tool_calls, but the function-calling examples in this repo read tool calls from response.output items of type function_call (and then use .name / .arguments / .call_id). Please update this wording so the README matches the actual Responses API usage demonstrated by the scripts.

These scripts demonstrate using the Responses API "tools" (a.k.a. function calling) feature, which lets the model decide when to call developer-defined functions and return structured arguments instead of (or before) a natural language answer.

In all of these examples, a list of functions is declared in the `tools` parameter. The model may respond with `message.tool_calls` containing one or more tool calls. Each tool call includes the function `name` and a JSON string of `arguments` that match the declared schema. Your application is responsible for: (1) detecting tool calls, (2) executing the corresponding local / external logic, and (3) (optionally) sending the tool result back to the model for a final answer.

spanish/README.md:37

• This paragraph still references message.tool_calls, but the function-calling scripts in this repo using the Responses API extract tool calls from response.output items of type function_call (with .name / .arguments / .call_id). Please update the Spanish README to describe that structure instead, so readers can follow the examples correctly.

Estos scripts muestran cómo usar la característica "tools" (function calling) de la API de Responses. Permite que el modelo decida si invoca funciones definidas por el desarrollador y devolver argumentos estructurados en lugar (o antes) de una respuesta en lenguaje natural.

En todos los ejemplos se declara una lista de funciones en el parámetro `tools`. El modelo puede responder con `message.tool_calls` que contiene una o más llamadas. Cada llamada incluye el `name` de la función y una cadena JSON con `arguments` que respetan el esquema declarado. Tu aplicación debe: (1) detectar las llamadas, (2) ejecutar la lógica local/externa correspondiente y (3) (opcionalmente) enviar el resultado de la herramienta de vuelta al modelo para una respuesta final.

• Files reviewed: 3/3 changed files
• Comments generated: 3

[Copilot]

Pull request overview

This PR updates repository documentation to consistently refer to the OpenAI Responses API (matching the codebase’s client.responses.create usage) instead of the legacy “Chat Completions” terminology.

Changes:

• Reworded README intros/section headings from “Chat Completions” to “Responses”.
• Updated script descriptions to talk about generating “responses” rather than “completions”.
• Applied the same terminology updates in AGENTS.md and the Spanish README.

Show a summary per file

File	Description
README.md	Renames the primary API terminology and updates example/script descriptions accordingly.
AGENTS.md	Updates the agent guidance doc to use “Responses” wording in overview and script list.
spanish/README.md	Mirrors the README terminology updates in Spanish (Responses vs. chat completions).

Copilot's findings

Tip

Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

• Files reviewed: 3/3 changed files
• Comments generated: 2