hosting

POST /v1/sites/{siteId}/ide-chat

One turn of the web editor's AI chat.

Wszystkie punkty końcowe hosting

Uwierzytelnianie

Ten punkt końcowy jest publiczny. Nie wymaga żadnych poświadczeń ani organizacji — to z niego korzysta nasza własna strona marketingowa oraz silniki odpowiedzi AI.

Ten punkt końcowy nie wymaga identyfikatora organizacji. Twój klucz już identyfikuje organizację, do której należy, a odpowiedź jest do niej ograniczona.

Wypróbuj

Zastąp wszystko w nawiasach ostrych własnymi wartościami, a zastępczy znacznik klucza kluczem ze swojego pulpitu nawigacyjnego.

curl -X POST https://api.zinndigital.com/v1/sites/{siteId}/ide-chat \
  -H "Content-Type: application/json" \
  -d '{ "messages": <IdeChatMessage[]> }'

Zalogowany? Konsola API w Twoim panelu uzupełnia rzeczywiste identyfikator organizacji oraz Twój własny klucz i wykonuje żądanie względem aktywnego API, dzięki czemu możesz zobaczyć rzeczywistą odpowiedź. Otwórz ten punkt końcowy w konsoli API

Szczegóły

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.

Parametry

NazwaTypWymaganeCo to jest
siteId (path)UuidTakSite ID (UUIDv7).

Treść żądania

NazwaTypWymaganeCo to jest
messagesIdeChatMessage[]TakThe conversation so far. The engine is stateless, so the whole transcript arrives on every call and the caller bounds it.
toolsIdeChatToolOffer[]NieWhat 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…
pathstringNieThe file the customer is looking at, if any.
contextstringNieThat file's contents, truncated to the assistant's context cap.
modelstringNieA model from `/ide-assist/models`. Omit for the automatic choice, which is the cheapest priced model the organisation can run.

Odpowiedź

NazwaTypWymaganeCo to jest
answerstringTakEmpty 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_callsIdeChatToolCall[]Tak
modelstringTak
fundingstringTakWhich 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.
turnsintegerTakHow 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.

Błędy, które ten punkt końcowy może zwrócić

404 · 422 · 429