hosting
POST /v1/sites/{siteId}/ide-chat
One turn of the web editor's AI chat.
Autenticação
Este endpoint é público. Ele não requer credenciais nem organização — é o que nosso próprio site de marketing e os mecanismos de resposta de IA leem.
Este endpoint não requer um ID de organização. Sua chave já identifica a organização à qual pertence, e a resposta é delimitada a ela.
Experimente
Substitua qualquer item entre colchetes por seus próprios valores e o espaço reservado para a chave por uma chave do seu painel.
curl -X POST https://api.zinndigital.com/v1/sites/{siteId}/ide-chat \
-H "Content-Type: application/json" \
-d '{ "messages": <IdeChatMessage[]> }'Conectado? O console da API no seu painel preenche o ID da sua organização real e a sua própria chave, e executa a requisição contra a API de produção para que você possa ver a resposta real. Abra este endpoint no console da API
Detalhes
The conversation panel inside the site's web editor. Unlike `askSiteIdeAssistant` — which answers one question about one file — this carries a transcript and a catalogue of **tools** the editor is willing to run, so the assistant can answer questions about the customer's own hosting rather than only about their code. Authenticated by the same signed, site-bound grant as the rest of the editor's endpoints, and metered to the same organisation on the same `web_ide` surface. The model is the organisation's own choice, or the cheapest priced one when they have expressed none — Claude, ChatGPT, Gemini or Grok, funded from Zinn® credit or the customer's own provider key. **The engine never runs a tool.** When the model asks for one, the response carries `tool_calls` and an empty `answer`, and the conversation is unfinished: the editor invokes them through its own MCP client — where the customer's confirmation happens for anything destructive, and where the MCP server's write gate and spend caps apply — and posts the results back on the next turn. A response with an empty `answer` and no `tool_calls` is never returned; that is a `422` carrying its own sentence, because the call was paid for either way and a blank panel is indistinguishable from a broken one. The transcript is authored inside the customer's own jail, so it is treated as data: roles are mapped from a closed set, the tool list is bounded and coerced, and a malformed tool is dropped rather than offered.
Parâmetros
| Nome | Tipo | Obrigatório | O que é |
|---|---|---|---|
siteId (path) | Uuid | Sim | Site ID (UUIDv7). |
Corpo da requisição
| Nome | Tipo | Obrigatório | O que é |
|---|---|---|---|
messages | IdeChatMessage[] | Sim | The conversation so far. The engine is stateless, so the whole transcript arrives on every call and the caller bounds it. |
tools | IdeChatToolOffer[] | Não | What the editor can run — its MCP servers' tools and any the customer's own extensions contribute. Bounded and coerced on arrival; a malformed entry is dropped rather than offer… |
path | string | Não | The file the customer is looking at, if any. |
context | string | Não | That file's contents, truncated to the assistant's context cap. |
model | string | Não | A model from `/ide-assist/models`. Omit for the automatic choice, which is the cheapest priced model the organisation can run. |
Resposta
| Nome | Tipo | Obrigatório | O que é |
|---|---|---|---|
answer | string | Sim | Empty when the assistant asked for tools instead. Never empty alongside an empty `tool_calls` — that is a `422` with its own sentence, because the call was paid for either way. |
tool_calls | IdeChatToolCall[] | Sim | — |
model | string | Sim | — |
funding | string | Sim | Which purse ran it — the same value the AI page renders, from the same decision. The editor shows "your Zinn® credit" or "your own API key" beneath the answer. |
turns | integer | Sim | How many turns of this conversation have already asked for tools, so the editor can stop a model that will not settle rather than paying for it indefinitely. |
Erros que este endpoint pode retornar
404 · 422 · 429