hosting
POST /v1/sites/{siteId}/ide-chat
One turn of the web editor's AI chat.
Ìfàṣẹ́pọ̀
Ojú-wọ̀n yìí jẹ́ ti gbogbo ènìyàn. Kò gba àmì ìdánimọ̀ kankan tàbí àgbájọ kankan — ohun tí ojú-wọ̀n ìpolówó wa àti àwọn ẹ̀rọ ìdáhùn AI ǹkà kọ́ ni.
Ojú abánisọ̀rọ̀ yìí kò gba id ajọ kankan. Kọ́kọ́rọ́ rẹ ti mọ ajọ ti o jẹ ti e, a o si fèsì nipa rẹ̀.
Gbiyanju rẹ
Rọ́pọ̀ èyíkéyìí nínú àwọn àmì ìtọ́ka < > pẹ̀lú iye tirẹ̀, àti àmì ìdánimọ̀ bọ́tìnnì náà pẹ̀lú bọ́tìnnì kan láti inú dásibọ̀ọ̀dù rẹ.
curl -X POST https://api.zinndigital.com/v1/sites/{siteId}/ide-chat \
-H "Content-Type: application/json" \
-d '{ "messages": <IdeChatMessage[]> }'Ṣé o ti wọlé? Iwọ̀n api ní nú ìgbékalẹ̀ rẹ kún id àjọ gidi rẹ ati bọtini tirẹ, o si nṣiṣẹ ibeere na lòdì si api gidi ki o le rii esi gidi na. Ṣí ojú abáná yìí sílẹ̀ nínú kọnsólù API
Àwọn kúlẹ̀kúlẹ̀
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.
Àwọn ìpìlẹ̀
| Orúkọ | Iru | Tí a nílò | Kini o jẹ |
|---|---|---|---|
siteId (path) | Uuid | Bẹẹni | Site ID (UUIDv7). |
Akoonu ibeere naa
| Orúkọ | Iru | Tí a nílò | Kini o jẹ |
|---|---|---|---|
messages | IdeChatMessage[] | Bẹẹni | The conversation so far. The engine is stateless, so the whole transcript arrives on every call and the caller bounds it. |
tools | IdeChatToolOffer[] | Bẹẹkọ | 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 | Bẹẹkọ | The file the customer is looking at, if any. |
context | string | Bẹẹkọ | That file's contents, truncated to the assistant's context cap. |
model | string | Bẹẹkọ | A model from `/ide-assist/models`. Omit for the automatic choice, which is the cheapest priced model the organisation can run. |
Idahun
| Orúkọ | Iru | Tí a nílò | Kini o jẹ |
|---|---|---|---|
answer | string | Bẹẹni | 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[] | Bẹẹni | — |
model | string | Bẹẹni | — |
funding | string | Bẹẹni | 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 | Bẹẹni | 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. |
Awọn aṣiṣe ti ibudo ipari yii le da pada
404 · 422 · 429