Skip to main content
POST
Workspace Chat

Authorizations

Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Path Parameters

workspace_id
string
required

Body

application/json

Options for workspace-level chat (no anchor peer; see DialecticOptions).

query
string
required

Workspace chat prompt

Required string length: 1 - 10000
session_id
string | null

Optional session to scope message tools to

stream
boolean
default:false
reasoning_level
enum<string>
default:low

Level of reasoning to apply: minimal, low, medium, high, or max

Available options:
minimal,
low,
medium,
high,
max
response_format
Response Format · object | null

Optional JSON Schema (root type 'object') the response must conform to. When provided, content is a JSON string matching this schema.

scope

Optional (unprefixed) scope name(s) restricting recall to the union of the scopes' member sessions (explicit allowlist, fail-closed: an empty union recalls nothing). Mutually exclusive with session_id. Requires a workspace- or admin-level key.

include_evidence
boolean
default:false

When true, the response includes an evidence object listing the conclusions and messages the agent read while answering, plus the tool calls it made. Evidence is collated from what the agent accessed; the model is never asked to cite anything, so evidence may over-report (accessed is not the same as used).

Response

Successful Response

content
string | null
required
evidence
Evidence · object | null

What the answer was built from. Present only when include_evidence is true.