List runs

Returns the org's agent runs across EVERY agent, newest first — what ran here, for whom, on which model, how long it took, and why it failed.

GET /v1/agent/runs

Agent → · All API references → · Get started →


Address	`https://api.hanzo.ai/v1/agent/runs`
Method	`GET`
Operation	`get_agent_runs`
Auth	`Authorization: Bearer $HANZO_API_KEY`

Returns the org's agent runs across EVERY agent, newest first — what ran here, for whom, on which model, how long it took, and why it failed.

It is the feed the per-agent history could not be: an operator asking "what is this tenant's agent plane doing" does not start out knowing an agent ref, and answering by listing the agents and then paging each one's history is N+1 round trips to reconstruct one ordering the database already has (RunsSince, ordered by created_at over the org index).

The org is the CALLER's, resolved from identity by tenantStore — never a parameter. There is deliberately no org field on orgRunsQuery to forge: run history is the tenant's own record, and the only tenant this can answer for is the one asking.

Request

2 fields.

Field	In	Type	Required	Description
`limit`	query	integer	—	Limit caps how many runs come back, newest first.
`status`	query	string	—	Status keeps only runs with this outcome ("ok" or "error"). Empty keeps both.

Response

Status	Body	Meaning
`200`	agent.runList	ok
`default`	problem-details	refused

200 body — 16 fields.

Field	In	Type	Always	Description
`runs`	body	agent.agentRunView[]	—	Runs is the agent's executions, newest first.
`runs[].actor`	body	string	—	Actor is the "org/sub" identity the run was executed and billed AS.
`runs[].agent`	body	string	—	What an operator needs to answer "what ran, for whom, and what did it do" — and, through traceId, to leave this record for the waterfall of the very same run…
`runs[].completionTokens`	body	integer (int64)	—	CompletionTokens is the same measurement for what the model produced, on the same final completion.
`runs[].createdAt`	body	string	—	CreatedAt is when the run finished, RFC 3339 in UTC to the second — the duration above already says how long it had been going.
`runs[].durationMs`	body	integer (int64)	—	DurationMs is wall-clock milliseconds around the completion, including a failover's retries.
`runs[].error`	body	string	—	Error is why an "ok"-less run failed, as the failing call reported it.
`runs[].id`	body	string	—	ID is the run's handle, minted as "run_" + 32 hex characters.
`runs[].input`	body	string	—	Input is the text the run was given, verbatim.
`runs[].micro_usd`	body	integer (int64)	—	MicroUSD is what the run spent, integer micro-USD.
`runs[].model`	body	string	—	Model is the model that actually SERVED this run, which is not always the one the agent is defined on — a failover records what answered.
`runs[].output`	body	string	—	Output is what the model produced. Empty on an error run, and empty is also a legitimate answer from a run that succeeded with nothing to say — Status is what…
`runs[].promptTokens`	body	integer (int64)	—	PromptTokens is what the gateway reported for the run's FINAL completion, and only that one — a tool loop's earlier rounds are the metering ledger's account,…
`runs[].status`	body	string	—	Status is the run's outcome, and there are exactly two: "ok" when the model answered, "error" when it did not.
`runs[].toolCalls`	body	integer (int64)	—	ToolCalls is how many tool dispatches the run made — a count of ACTIONS, which is a different measurement from the token counts above and from the turns a…
`runs[].traceId`	body	string	—	TraceID is the trace this run IS, so the record and its spans are one thing to move between: it opens the waterfall for THIS run rather than a search that…

Failure carries the platform error shape — see Errors.

Examples

hanzo agent runs-all

import { Configuration, AgentApi } from 'hanzoai';

const api = new AgentApi(new Configuration({ accessToken: process.env.HANZO_API_KEY }));
const { data } = await api.getAgentRuns();

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_runs()

cfg := hanzoai.NewConfiguration()
cfg.AddDefaultHeader("Authorization", "Bearer "+os.Getenv("HANZO_API_KEY"))
client := hanzoai.NewAPIClient(cfg)

resp, _, err := client.AgentAPI.GetAgentRuns(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_runs(&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).getAgentRuns();

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/runs \
  -H "Authorization: Bearer $HANZO_API_KEY"

MCP reaches agent 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"
         }
       }
     }'

Agent API · All Hanzo APIs · Interactive reference

Request

Response

Examples

On this page