身份验证
此端点是公开的。它不需要任何凭据或组织——这是我们自己的营销网站和 AI 问答引擎所读取的内容。
此端点不需要组织 ID。您的密钥已用于识别其所属的组织，且响应范围也仅限于该组织。
免费试用
将尖括号中的内容替换为您自己的值，并将键占位符替换为您仪表板中的一个键。
curl -X POST https://api.zinndigital.com/v1/sites/{siteId}/ide-chat \
-H "Content-Type: application/json" \
-d '{ "messages": <IdeChatMessage[]> }'已登录？您仪表板中的 API 控制台会自动填入您真实的组织 ID 和您自己的密钥，并针对实时 API 运行请求，以便您查看实际的响应。 在 API 控制台中打开此端点
详细信息
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.
参数
| 名称 | 类型 | 必填 | 内容简介 |
|---|---|---|---|
siteId (path) | Uuid | 是 | Site ID (UUIDv7). |
请求正文
| 名称 | 类型 | 必填 | 内容简介 |
|---|---|---|---|
messages | IdeChatMessage[] | 是 | The conversation so far. The engine is stateless, so the whole transcript arrives on every call and the caller bounds it. |
tools | IdeChatToolOffer[] | 否 | 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 | 否 | The file the customer is looking at, if any. |
context | string | 否 | That file's contents, truncated to the assistant's context cap. |
model | string | 否 | A model from `/ide-assist/models`. Omit for the automatic choice, which is the cheapest priced model the organisation can run. |
响应
| 名称 | 类型 | 必填 | 内容简介 |
|---|---|---|---|
answer | string | 是 | 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[] | 是 | — |
model | string | 是 | — |
funding | string | 是 | 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 | 是 | 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. |
此端点可能返回的错误
404 · 422 · 429