List progress
Returns how far along one run is: the share of its goal that is done, whether it is running, blocked or finished, and a line saying what it is doing right…
GET /v1/agents/sessions/{id}/progress
| Address | https://api.hanzo.ai/v1/agents/sessions/{id}/progress |
| Method | GET |
| Operation | get_agents_sessions_by_id_progress |
| Auth | Authorization: Bearer $HANZO_API_KEY |
Returns how far along one run is: the share of its goal that is done, whether it is running, blocked or finished, and a line saying what it is doing right now.
It is a MODEL ESTIMATE read off the run's own transcript, not a measurement —
estimated says so on every answer, and a run whose progress cannot be told
reports phase "unknown" with no percentage rather than a zero it does not
mean. A session that has already finished answers from its own status instead,
and is marked not estimated.
The list and detail reads carry the same value; this address is the one that WAITS. Where the stored estimate has gone stale it is remade before answering, so a human deciding whether to step into a run gets a current reading rather than the last poll's — which costs one small completion, charged to the same wallet the session already names, at most once every thirty seconds per run.
Request
1 field.
| Field | In | Type | Required | Description |
|---|---|---|---|---|
id | path | string | yes | ID is the session to act on, from the path. |
Response
| Status | Body | Meaning |
|---|---|---|
200 | sessionProgress | ok |
200 body — 5 fields.
| Field | In | Type | Always | Description |
|---|---|---|---|---|
activity | body | string | — | Activity is the one line saying what the run is doing right now ("running the reaper's tests"), up to 120 characters, in the model's words. |
at | body | string | — | At is when this was determined, RFC 3339 in UTC to the second. |
estimated | body | boolean | — | Estimated says a MODEL produced this, from the run's transcript, and it may be wrong. |
pct | body | integer | — | Pct is how much of the run is done, 0 to 100. |
phase | body | string | — | Phase is what shape the run is in: running, blocked, done, error, or unknown when nothing has estimated it yet. |
Failure carries the platform error shape — see Errors.
Examples
hanzo agents sessions progress <id>import { Configuration, AgentsApi } from 'hanzoai';
const api = new AgentsApi(new Configuration({ accessToken: process.env.HANZO_API_KEY }));
const { data } = await api.getAgentsSessionsByIdProgress({ id: 'id' });from hanzoai.cloud import ApiClient, Configuration
from hanzoai.cloud.api import AgentsApi
client = ApiClient(Configuration(access_token=os.environ["HANZO_API_KEY"]))
result = AgentsApi(client).get_agents_sessions_by_id_progress(id='id')cfg := cloud.NewConfiguration()
cfg.AddDefaultHeader("Authorization", "Bearer "+os.Getenv("HANZO_API_KEY"))
client := cloud.NewAPIClient(cfg)
resp, _, err := client.AgentsAPI.GetAgentsSessionsByIdProgress(context.Background()).Execute()
if err != nil {
return err
}use hanzo_cloud::apis::{configuration::Configuration, agents_api};
let mut cfg = Configuration::new();
cfg.bearer_access_token = std::env::var("HANZO_API_KEY").ok();
let result = agents_api::get_agents_sessions_by_id_progress(&cfg, Default::default()).await?;import ai.hanzo.cloud.ApiClient;
import ai.hanzo.cloud.api.AgentsApi;
ApiClient client = new ApiClient();
client.setRequestInterceptor(b -> b.header("Authorization", "Bearer " + System.getenv("HANZO_API_KEY")));
var result = new AgentsApi(client).getAgentsSessionsByIdProgress();curl https://api.hanzo.ai/v1/agents/sessions/<id>/progress \
-H "Authorization: Bearer $HANZO_API_KEY"MCP reaches agents through the agents tool, which names its 36 operations with its own verbs — this one among them, under a name only MCP declares. describe explains any of them:
curl -X POST https://api.hanzo.ai/v1/mcp \
-H "Content-Type: application/json" \
-d '{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "describe",
"arguments": {
"op": "list_agent_conversations"
}
}
}'How is this guide?