Skip to main content
Settings methods expose the gateway-owned runtime settings that clients can read and update over JSON-RPC. These settings are gateway-scoped, not workspace-scoped. Provider API keys, MCP secrets, skills, tasks, and artifacts remain separate workspace-owned surfaces. The gateway loads settings from its runtime settings file, overlays app config defaults, and returns the effective snapshot. Updates are persisted to the same gateway settings file. Memory updates also rebuild the memory hook runtime so active recall and background extraction reflect the new values without restarting the gateway.

Methods

MethodParamsResultPurpose
settings/getGatewaySettingsGetParamsGatewaySettingsGetResponseReturn the effective gateway settings snapshot.
settings/updateGatewaySettingsUpdateParamsGatewaySettingsUpdateResponsePersist gateway settings overrides and return the new effective snapshot.

Snapshot Shape

The response contains a settings object with general and memory sections.
SectionFields
generalkeepawake, preflight_model
memoryenabled, deterministic_recall_enabled, active_recall_enabled, tools_enabled, proactive_writes_enabled, background_extraction_enabled, proactive_writes_model, debug_trace_enabled, strict_diagnostics_enabled
Model selection objects use:
FieldMeaning
sourcethread to inherit the thread model, or custom to use an explicit provider and model.
model_providerRequired for effective custom model overrides.
modelRequired for effective custom model overrides.

Reading Settings

settings/get accepts an empty params object.
{
  "jsonrpc": "2.0",
  "id": "aaaaaaaaaaaaaaaaaaaaa",
  "method": "settings/get",
  "params": {}
}
Response:
{
  "settings": {
    "general": {
      "keepawake": false,
      "preflight_model": {
        "source": "thread"
      }
    },
    "memory": {
      "enabled": true,
      "deterministic_recall_enabled": true,
      "active_recall_enabled": true,
      "tools_enabled": true,
      "proactive_writes_enabled": true,
      "background_extraction_enabled": true,
      "proactive_writes_model": {
        "source": "thread"
      },
      "debug_trace_enabled": false,
      "strict_diagnostics_enabled": false
    }
  }
}

Updating Settings

settings/update takes an update object. general is a patch: omitted fields keep their current effective value. memory is a complete memory settings object when present.
{
  "jsonrpc": "2.0",
  "id": "bbbbbbbbbbbbbbbbbbbbb",
  "method": "settings/update",
  "params": {
    "update": {
      "general": {
        "keepawake": true,
        "preflight_model": {
          "source": "custom",
          "model_provider": "openai",
          "model": "gpt-5.1"
        }
      }
    }
  }
}
To update memory settings, send the full memory section:
{
  "jsonrpc": "2.0",
  "id": "ccccccccccccccccccccc",
  "method": "settings/update",
  "params": {
    "update": {
      "memory": {
        "enabled": true,
        "deterministic_recall_enabled": true,
        "active_recall_enabled": false,
        "tools_enabled": true,
        "proactive_writes_enabled": false,
        "background_extraction_enabled": true,
        "proactive_writes_model": {
          "source": "thread"
        },
        "debug_trace_enabled": false,
        "strict_diagnostics_enabled": false
      }
    }
  }
}
The response shape is the same as settings/get and contains the new effective snapshot.

Schemas

Generated schemas include:
  • /schemas/gateway_settings_get_params.json
  • /schemas/gateway_settings_get_response.json
  • /schemas/gateway_settings_update_params.json
  • /schemas/gateway_settings_update_response.json
  • /schemas/gateway_settings_snapshot.json
  • /schemas/gateway_general_settings.json
  • /schemas/gateway_general_settings_update.json
  • /schemas/gateway_memory_settings.json
  • /schemas/gateway_memory_model_selection.json
  • /schemas/gateway_memory_model_selection_source.json