Skip to main content
POST
/
v1
/
chats
Error
A valid request URL is required to generate request examples
{
  "chat_id": "chat_d8aad64dib2c7m3ae7j0",
  "message_id": "message_d8aad64dib2c7m3ae7jg",
  "created_at": "2026-05-23T10:15:30Z"
}

Documentation Index

Fetch the complete documentation index at: https://dev.chief.bot/llms.txt

Use this file to discover all available pages before exploring further.

Authorizations

​
X-API-Key
string
header
required

Personal Access Token, sent verbatim as pat_<32 chars>. PATs are minted from the Chief settings UI.

Headers

​
X-Project-Id
string
required

Project identifier scoping the request. Required on every project-scoped public endpoint. Missing or malformed values respond with HTTP 400 and code publicapi.tenancy.project.missing.

Pattern: ^project_[a-z0-9]{20}$

Body

application/json
​
prompt
string
required

The user's message to start the chat.

​
intelligence
enum<string>

Mode preset that controls model class and tool selection. auto lets the backend classify the prompt and route. Defaults to auto when omitted.

Available options:
auto,
fast,
expert,
research
​
provider
enum<string>

Biases model selection within the chosen intelligence mode toward a specific vendor. automatic (or omitted) leaves the router's default ordering. The mode preset still controls thinking depth and tool selection — provider only re-ranks candidate models. Mirrors the UI's AI Provider picker.

Available options:
automatic,
anthropic,
openai,
google
​
skills
string[]

Skill names to pre-load before the LLM runs. The Bluesky UI's "Expert Voice" picker sends one entry; the API accepts many. Each name must reference a skill the caller can access.

​
public_data
boolean

When false, disables the public-web-search tool for this turn. Omitting or sending true leaves the mode default in place.

​
scope
object

Optional. Narrows the knowledge the assistant may consult on this turn. Each id list is independently validated for shape; access is enforced server-side.

Response

Chat accepted; workflow running.

​
chat_id
string
required
Pattern: ^chat_[a-z0-9]{20}$
​
message_id
string
required

The new turn's id. Poll GET /v1/chats/{chat_id}/messages/{message_id} to follow its lifecycle.

Pattern: ^message_[a-z0-9]{20}$
​
created_at
string<date-time>
required