hosting

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

One turn of the web editor's AI chat.

Svi hosting krajnji točke

Autentifikacija

Ova je krajnja točka javna. Ne zahtijeva nikakve vjerodajnice ni organizaciju – to je ono što čitaju naše vlastite marketinške stranice i AI strojevi za odgovore.

Ova krajnja točka ne prihvaća ID organizacije. Vaš ključ već identificira organizaciju kojoj pripada, a odgovor je ograničen na nju.

Isprobajte

Zamijenite sve unutar šiljastih zagrada svojim vlastitim vrijednostima, a rezervirano mjesto za ključ s ključem iz vaše nadzorne ploče.

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

Prijavljeni ste? API konzola na vašoj nadzornoj ploči automatski unosi stvarni ID vaše organizacije i vaš vlastiti ključ te šalje zahtjev prema aktivnom API-ju kako biste mogli vidjeti stvarni odgovor. Otvori ovu krajnju točku u API konzoli

Pojedinosti

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.

Parametri

NazivVrstaObaveznoŠto je to
siteId (path)UuidDaSite ID (UUIDv7).

Tijelo zahtjeva

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

Odgovor

NazivVrstaObaveznoŠto je to
answerstringDaEmpty 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[]Da
modelstringDa
fundingstringDaWhich 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.
turnsintegerDaHow 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.

Pogreške koje ova krajnja točka može vratiti

404 · 422 · 429