Skip to content
Console

Business A2A reference

Setting Value
Agent card GET https://api.inside.chat/.well-known/agent-card.json, no authentication
Endpoint POST https://api.inside.chat/a2a
Protocol A2A 1.0, JSON-RPC binding
Headers Authorization: Bearer ..., Content-Type: application/json, A2A-Version: 1.0
Tokens An installation token, or an OAuth token requested with resource=https://api.inside.chat/a2a
Resource metadata GET /.well-known/oauth-protected-resource/a2a
Method Use
SendMessage Start a task. The message has exactly one data part with skill and arguments.
GetTask Read a task by id
ListTasks List this credential’s unexpired tasks
CancelTask Stop a task’s result from being published

Streaming and push notification methods aren’t supported.

{
"data": { "skill": "support_insights", "arguments": { "website_id": "web_4927_123", "range": "last-7-days" } },
"mediaType": "application/json"
}
Skill Arguments Required scopes
support_insights website_id, range (today, last-7-days, last-month or date), and start, end, timezone for date reports_read, conversation_read
conversation_evidence conversation_id, optional limit (1 to 100, default 50) and cursor conversation_read, message_content_read, contact_read_pii, plus message_content and pii
configuration_inspection website_id, path (/ai/features or /ai/features/{feature_id}), optional limit and cursor config_read
contact_inspection contact_id contact_read; personal fields need contact_read_pii and pii
offline_language_detection feature_id, expected_version, context: {"type":"text","text":"...","default_language":"en"} ai_features_read, ai_execute
State Meaning
TASK_STATE_SUBMITTED Accepted, not started
TASK_STATE_WORKING Running
TASK_STATE_COMPLETED Finished with one JSON artifact of at most 128 KiB
TASK_STATE_FAILED Finished without a result
TASK_STATE_CANCELED Cancelled before its result was published
Limit Value
Task lifetime 15 minutes, or until the credential expires
Unexpired tasks per installation 100
Running tasks per installation 5
Artifact size 128 KiB
Quota One unit per A2A request, plus one for each new task’s underlying read

Resending the same messageId, skill and arguments returns the existing task without running it again.