List activity
Serves the org-wide recent-activity feed. Events are REAL: each recorded run is an invoked (ok) or failed (error) event; each agent's own create/update…
GET /v1/agent/activity
| Address | https://api.hanzo.ai/v1/agent/activity |
| Method | GET |
| Operation | get_agent_activity |
| Auth | Authorization: Bearer $HANZO_API_KEY |
Serves the org-wide recent-activity feed. Events are REAL: each recorded run is an invoked (ok) or failed (error) event; each agent's own create/update timestamps are created/updated events. Merged, newest first, capped. Nothing is invented — an org with no agents and no runs gets [].
Request
GET /v1/agent/activity takes no parameters and no body — the credential is the whole request.
Response
| Status | Body | Meaning |
|---|---|---|
200 | agent.activityFeed | ok |
default | problem-details | refused |
200 body — 6 fields.
| Field | In | Type | Always | Description |
|---|---|---|---|---|
activity | body | agent.activityView[] | — | Activity is the merged run/create/update events, newest first, capped at 50. |
activity[].agent | body | string | — | agent name |
activity[].at | body | string | — | RFC3339 UTC |
activity[].id | body | string | — | ID identifies the event, and its shape says which kind it is: a run event carries the run's own id, while an agent event is the agent id suffixed ":created" or… |
activity[].kind | body | string | — | invoked|failed|created|updated (from real events) |
activity[].message | body | string | — | Message is the line to render, already bounded: "Invoked <model>" for a run that worked, the run's own error truncated to 200 characters for one that did not… |
Failure carries the platform error shape — see Errors.
Examples
hanzo agent activityimport { Configuration, AgentApi } from 'hanzoai';
const api = new AgentApi(new Configuration({ accessToken: process.env.HANZO_API_KEY }));
const { data } = await api.getAgentActivity();from hanzoai.cloud import ApiClient, Configuration
from hanzoai.cloud.api import AgentApi
client = ApiClient(Configuration(access_token=os.environ["HANZO_API_KEY"]))
result = AgentApi(client).get_agent_activity()cfg := hanzoai.NewConfiguration()
cfg.AddDefaultHeader("Authorization", "Bearer "+os.Getenv("HANZO_API_KEY"))
client := hanzoai.NewAPIClient(cfg)
resp, _, err := client.AgentAPI.GetAgentActivity(context.Background()).Execute()
if err != nil {
return err
}use hanzo_client::apis::{configuration::Configuration, agent_api};
let mut cfg = Configuration::new();
cfg.bearer_access_token = std::env::var("HANZO_API_KEY").ok();
let result = agent_api::get_agent_activity(&cfg, Default::default()).await?;import ai.hanzo.cloud.ApiClient;
import ai.hanzo.cloud.api.AgentApi;
ApiClient client = new ApiClient();
client.setBearerToken(System.getenv("HANZO_API_KEY"));
var result = new AgentApi(client).getAgentActivity();The method above is the one at the current release of the document. [email protected] (npm) was generated from an earlier release, where this operation carried a different id, so it spells the method differently — regenerating the clients is what makes the two agree. SDKs →
curl https://api.hanzo.ai/v1/agent/activity \
-H "Authorization: Bearer $HANZO_API_KEY"Tool agents, op get_agent_activity — POST the JSON-RPC envelope to https://api.hanzo.ai/v1/mcp.
curl -X POST https://api.hanzo.ai/v1/mcp \
-H "Authorization: Bearer $HANZO_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "agents",
"arguments": {
"op": "get_agent_activity",
"input": {}
}
}
}'How is this guide?