hosting

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

One turn of the web editor's AI chat.

Autenticazione

Questo endpoint è pubblico. Non richiede credenziali né alcuna organizzazione: è ciò che leggono il nostro sito di marketing e i nostri motori di risposta basati su IA.

Questo endpoint non richiede alcun ID organizzazione. La tua chiave identifica già l'organizzazione a cui appartiene e la risposta è limitata ad essa.

Provalo

Sostituisci qualsiasi elemento tra parentesi angolari con i tuoi valori e il segnaposto key con una chiave dalla tua dashboard.

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

Hai effettuato l'accesso? La console API nella tua dashboard inserisce il tuo ID organizzazione reale e la tua chiave personale, ed esegue la richiesta sull'API live in modo da poter vedere la risposta effettiva. Apri questo endpoint nella console API

Dettagli

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

Nome	Tipo	Obbligatorio	Che cos'è
`siteId (path)`	`Uuid`	Sì	Site ID (UUIDv7).

Corpo della richiesta

Nome	Tipo	Obbligatorio	Che cos'è
`messages`	`IdeChatMessage[]`	Sì	The conversation so far. The engine is stateless, so the whole transcript arrives on every call and the caller bounds it.
`tools`	`IdeChatToolOffer[]`	No	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`	No	The file the customer is looking at, if any.
`context`	`string`	No	That file's contents, truncated to the assistant's context cap.
`model`	`string`	No	A model from `/ide-assist/models`. Omit for the automatic choice, which is the cheapest priced model the organisation can run.

Risposta

Nome	Tipo	Obbligatorio	Che cos'è
`answer`	`string`	Sì	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[]`	Sì	—
`model`	`string`	Sì	—
`funding`	`string`	Sì	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`	Sì	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.

Errori che questo endpoint può restituire

404 · 422 · 429

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