인증
이 엔드포인트는 공개되어 있습니다. 자격 증명이나 조직 정보가 필요하지 않으며, 당사의 마케팅 사이트와 AI 답변 엔진이 읽는 것과 동일합니다.
이 엔드포인트는 조직 ID를 받지 않습니다. 사용자의 키가 이미 속한 조직을 식별하며, 응답은 해당 조직으로 한정됩니다.
무료 체험하기
대괄호 안에 있는 모든 내용을 사용자 지정 값으로 바꾸고, 키 플레이스홀더는 대시보드의 키로 바꾸세요.
curl -X POST https://api.zinndigital.com/v1/sites/{siteId}/ide-chat \
-H "Content-Type: application/json" \
-d '{ "messages": <IdeChatMessage[]> }'로그인하셨나요? 대시보드의 API 콘솔이 실제 조직 ID와 본인의 키를 자동으로 채우고 라이브 API를 대상으로 요청을 실행하므로 실제 응답을 확인할 수 있습니다. API 콘솔에서 이 엔드포인트를 여세요
상세 정보
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.
매개변수
| 이름 | 유형 | 필수 | 설명 |
|---|---|---|---|
siteId (path) | Uuid | 예 | Site ID (UUIDv7). |
요청 본문
| 이름 | 유형 | 필수 | 설명 |
|---|---|---|---|
messages | IdeChatMessage[] | 예 | The conversation so far. The engine is stateless, so the whole transcript arrives on every call and the caller bounds it. |
tools | IdeChatToolOffer[] | 아니요 | 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 | 아니요 | The file the customer is looking at, if any. |
context | string | 아니요 | That file's contents, truncated to the assistant's context cap. |
model | string | 아니요 | A model from `/ide-assist/models`. Omit for the automatic choice, which is the cheapest priced model the organisation can run. |
응답
| 이름 | 유형 | 필수 | 설명 |
|---|---|---|---|
answer | string | 예 | 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[] | 예 | — |
model | string | 예 | — |
funding | string | 예 | 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 | 예 | 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. |
이 엔드포인트가 반환할 수 있는 오류
404 · 422 · 429