hosting
POST /v1/sites/{siteId}/ide-chat
One turn of the web editor's AI chat.
אימות
נקודת קצה זו היא ציבורית. היא אינה דורשת שורת פרטי זיהוי ואינה דורשת ארגון – זהו המידע שאתרי השיווק ומנועי התשובות מבוססי ה-AI שלנו קוראים.
נקודת קצה זו אינה דורשת מזהה ארגון. המפתח שלך כבר מזהה את הארגון שאליו הוא שייך, והתגובה מוגבלת אליו בלבד.
נסה זאת
החלף כל דבר בסוגריים זוויתיים בערכים משלך, ואת מציין מיקום המפתח במפתח מלוח הבקרה שלך.
curl -X POST https://api.zinndigital.com/v1/sites/{siteId}/ide-chat \
-H "Content-Type: application/json" \
-d '{ "messages": <IdeChatMessage[]> }'מחובר? קונסולת ה-API בלוח הבקרה שלך מזינה את מזהה הארגון האמיתי שלך ואת המפתח שלך, ומריצה את הבקשה מול ה-API הפיזי כך שתוכל לראות את התגובה בפועל. פתח נקודת קצה זו במסוף ה-API
פרטים
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.
פרמטרים
| שם | סוג | נדרש | מה זה |
|---|---|---|---|
siteId (path) | Uuid | כן | Site ID (UUIDv7). |
גוף הבקשה
| שם | סוג | נדרש | מה זה |
|---|---|---|---|
messages | IdeChatMessage[] | כן | The conversation so far. The engine is stateless, so the whole transcript arrives on every call and the caller bounds it. |
tools | IdeChatToolOffer[] | לא | 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 | לא | The file the customer is looking at, if any. |
context | string | לא | That file's contents, truncated to the assistant's context cap. |
model | string | לא | A model from `/ide-assist/models`. Omit for the automatic choice, which is the cheapest priced model the organisation can run. |
תשובה
| שם | סוג | נדרש | מה זה |
|---|---|---|---|
answer | string | כן | 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[] | כן | — |
model | string | כן | — |
funding | string | כן | 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 | כן | 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. |
שגיאות שנקודה קצה זו עשויה להחזיר
404 · 422 · 429