Skip to main content
A session is one conversation on an instance. An instance holds many sessions, one per thread, and each session keeps its own full history, so you only ever send the new input. These endpoints are served by the gateway running inside the instance. The gateway keeps no session index of its own. The agent harness owns both the transcript and the list (Hermes’ session store, OpenClaw’s history), and the gateway projects them on read. So a session’s fields are the harness’s own, and a list or read always reflects the live state of that harness. Everything on this page lives on the instance URL, not the hosting API: the base is https://{instanceId}.agent37.app, with the same sk_live_ key sent as the X-Agent37-Key header. The platform edge authenticates the key and checks the instance belongs to your workspace, then the gateway answers. See Instance and preview URLs.

Endpoints

You never create a session directly. The first POST /v1/responses without a session_id mints one and returns its id; reuse that id to continue the thread.

Choosing the harness

Every read on this page takes an optional ?agent= query, hermes or openclaw, that selects which harness on the instance answers. Omit it (or send it empty) and the instance’s configured default harness answers; the response echoes which agent it was. An unknown value is 400 validation_error, and targeting a harness the instance was not provisioned with is 503 agent_unavailable. Your agent37-hermes Cloud instances serve Hermes, so you can leave ?agent= off.

The session object

There is no gateway-defined session shape. GET /v1/sessions passes each entry through from the harness’s own store, native fields untouched, so the exact fields depend on the harness and can evolve with it.
string
The only field the gateway guarantees across harnesses. It is the session id you pass back to GET, PATCH, and DELETE /v1/sessions/{id}, and the session_id every response in the conversation carries. 32 hex characters, no prefix.
A Hermes session object also carries Hermes’ own fields: title, model, message_count, started_at, last_active, and preview (see the example below). OpenClaw returns its own native fields. These come straight from the harness; the gateway does not normalize them, so field names, types, and timestamp units track the harness rather than this API (unlike a history message’s created_at, which the gateway does normalize to epoch milliseconds). Read what you need by name; don’t assume a field exists on every harness.

List sessions

GET /v1/sessions returns the harness’s sessions, newest first (Hermes orders by most recent activity), wrapped in { "agent": "...", "data": [...] }. The agent names which harness the list is for. Pass ?agent=hermes or ?agent=openclaw to pick a harness; omit it for the instance default. The list carries session metadata only, never history, so it stays cheap to poll for a sidebar. A harness without a list API returns data: [].

Retrieve a session with history

GET /v1/sessions/{id} returns { "id", "agent", "active_response_id", "history" }: history is the full transcript, in order, projected from the harness. You read it for display or audit; you never resend it, because the session already holds it. An unknown id returns an empty history rather than a 404, because the harness owns whether a session exists. Pass ?agent= to pick the harness.
string | null
The id of the response currently running on the session, or null when it is idle. The harness writes a turn’s messages at turn end, so while this is set the running turn is normally not in history yet. Follow it live with GET /v1/responses/{id}/stream. This is how a client that lost its state (page reload, new device) rediscovers a running turn and reattaches. Two timing edges: right at turn end, one read can briefly show the finished turn in history and its id still here; reattaching is still correct, the replay just ends immediately. And once it reads null the transcript is complete, with one exception: a cancelled OpenClaw turn is persisted by OpenClaw on its own schedule and can surface in history shortly after.
Each entry in history is a message:
string
The message id. Treat it as opaque; it uses a different format from session and response ids.
string
The session the message belongs to.
string
user, assistant, or system.
string
The message text.
string
The assistant’s reasoning for that turn, when the agent recorded any. Absent otherwise.
number
When the message was created, in epoch milliseconds.

Rename a session

PATCH /v1/sessions/{id} sets a session’s title, writing it straight into the harness’s own store, and returns { "id", "agent", "renamed" }. renamed is false when no session matched the id. Send the new title in the body:
string
required
The new title. Cannot be empty. Hermes enforces a unique, length-capped title: a title already used by another session returns 409 title_conflict, and an over-long one returns 400 validation_error.
Rename is only available on harnesses that natively store an editable title. Hermes supports it; a harness that does not returns 405 rename_unsupported. Pass ?agent= to pick the harness.

Delete a session

DELETE /v1/sessions/{id} is a best-effort removal from the harness’s store and returns { "id": "...", "deleted": true|false }. deleted is true when a transcript was removed and false when nothing matched the id, so the call is idempotent: repeating it simply returns deleted: false rather than erroring. A harness with no delete route (OpenClaw) always returns deleted: false and keeps its copy. Pass ?agent= to pick the harness.
Deleting a session removes the conversation and its history from the harness, but leaves the instance (its files, memory, and connected accounts) untouched. The per-turn response receipts are in-memory and short-lived; they expire on their own.

One turn at a time

A session runs one response at a time. Posting new input while a turn is in flight returns 409 session_busy, normally with the running response’s id in error.response_id. Reattach to it with GET /v1/responses/{id}/stream, cancel it with POST /v1/responses/{id}/cancel, or start the new input on another session. Two sessions on the same instance run independently. To see which models a harness can run, and to set the model per turn, see Models. For the readiness probe an app polls after create or start, see Health & version.