# List events URL: https://docs.hanzo.ai/docs/openapi/agent/get-agent-sessions-by-id-events > Reads a session's log in order, a page at a time: everything after the seq a reader last saw, so a poll resumes exactly where it stopped. `GET /v1/agent/sessions/{id}/events` > [Agent →](https://docs.hanzo.ai/docs/openapi/agent) · [All API references →](https://docs.hanzo.ai/docs/openapi) · [Get started →](https://docs.hanzo.ai/docs/guides) | | | | ------------- | ---------------------------------------------------- | | **Address** | `https://api.hanzo.ai/v1/agent/sessions/{id}/events` | | **Method** | `GET` | | **Operation** | `get_agent_sessions_by_id_events` | | **Auth** | `Authorization: Bearer $HANZO_API_KEY` | Reads a session's log in order, a page at a time: everything after the seq a reader last saw, so a poll resumes exactly where it stopped. It is how to see what a run did and why it ended — each model turn, tool call, status and log line, as the run wrote them. A run whose process went away is ended first, with its reason as the last event. ## Request 3 fields. | Field | In | Type | Required | Description | | ------- | ----- | ------- | -------- | -------------------------------------------------------------------------- | | `id` | path | string | yes | ID is the session to read, from the path. | | `after` | query | integer | — | After is the seq of the last event already read; the page starts after it. | | `limit` | query | integer | — | Limit caps the page. | ## Response | Status | Body | Meaning | | --------- | --------------- | ------- | | `200` | agent.eventList | ok | | `default` | problem-details | refused | `200` body — 9 fields. | Field | In | Type | Always | Description | | -------------------- | ---- | ------------------ | ------ | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | `events` | body | agent.eventView\[] | — | Events is the page, in seq order. | | `events[].actor` | body | string | — | Actor is who produced the turn. | | `events[].createdAt` | body | string | — | CreatedAt is when the turn was recorded, RFC 3339 in UTC to the second. | | `events[].id` | body | string | — | ID is the event's own handle, minted as "evt\_" + 32 hex characters. | | `events[].kind` | body | string | — | Kind is what the turn IS, from a closed six: message (a model turn), tool-call, spawn (a subagent started), log, status, control (a steering command the running surface consumes). | | `events[].payload` | body | any | — | Payload is the turn's body, embedded as JSON rather than as a string — whatever the writer sent, up to 64 KiB, checked for well-formedness and scanned for credentials before it was stored. | | `events[].seq` | body | integer (int64) | — | Seq is the turn's position in this session's log: monotonic from 1, assigned by the store inside the insert, and unique PER SESSION rather than globally. | | `events[].sessionId` | body | string | — | SessionID is the session this turn belongs to. | | `next` | body | integer (int64) | — | Next is the seq to pass as after for the page beyond this one; absent when this page reached the end of the log as it stands now. | Failure carries the platform error shape — see [Errors](https://docs.hanzo.ai/docs/errors). ## Examples **CLI** ```bash hanzo agent sessions events get ``` **SDK** **.ts** ```ts import { Configuration, AgentApi } from 'hanzoai'; const api = new AgentApi(new Configuration({ accessToken: process.env.HANZO_API_KEY })); const { data } = await api.getAgentSessionsByIdEvents({ id: 'id' }); ``` **.py** ```python 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_sessions_by_id_events(id='id') ``` **.go** ```go cfg := hanzoai.NewConfiguration() cfg.AddDefaultHeader("Authorization", "Bearer "+os.Getenv("HANZO_API_KEY")) client := hanzoai.NewAPIClient(cfg) resp, _, err := client.AgentAPI.GetAgentSessionsByIdEvents(context.Background()).Execute() if err != nil { return err } ``` **.rs** ```rust 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_sessions_by_id_events(&cfg, Default::default()).await?; ``` **.java** ```java 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).getAgentSessionsByIdEvents(); ``` The method above is the one at the current release of the document. `hanzoai@8.5.914` (npm) and `hanzoai@8.5.914` (PyPI) were 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 →](https://docs.hanzo.ai/docs/sdks) **HTTP** ```bash curl https://api.hanzo.ai/v1/agent/sessions//events \ -H "Authorization: Bearer $HANZO_API_KEY" ``` **MCP** MCP reaches **agent** through the `agent` tool, which names its 51 operations with its own verbs — this one among them, under a name only MCP declares. `describe` explains any of them: ```bash 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_agents" } } }' ``` --- [Agent API](https://docs.hanzo.ai/docs/openapi/agent) · [All Hanzo APIs](https://docs.hanzo.ai/docs/openapi) · [Interactive reference](https://docs.hanzo.ai/docs/openapi/reference)