DOC-API-MODEL-schema-ph6avse89k#overview
ConversationSettings
Conversation-level settings controlling behavior across sends
maxLoops caps the total number of generations in a run — not the number of tool round trips. Default is 2, which is what one round trip costs: a first generation to emit the tool call, a second to synthesize its result.
On the final generation the model is sent no tools at all (the request omits the tools array), so it cannot emit a call there. maxLoops: 1 therefore means a single tool-free reply — a valid way to ask for one, but not a way to get one tool round trip.
Meaning and usage
Section ID: DOC-API-MODEL-schema-ph6avse89k#meaning
See the definition above.
Usage profiles
Section ID: DOC-API-MODEL-schema-ph6avse89k#fields
| Usage | Fields and validation |
|---|---|
| In requests | View fields |
| In responses | View fields |
In requests
Section ID: DOC-API-MODEL-schema-ph6avse89k#request
API JSON uses JSON field names (camelCase).
| Field | Type | Presence | Meaning |
|---|---|---|---|
Section ID: DOC-API-MODEL-schema-ph6avse89k#request-field-interruptpolicyinterruptPolicy | string (INTERRUPT_POLICY_REJECT_NEW, INTERRUPT_POLICY_CANCEL_ONGOING, INTERRUPT_POLICY_QUEUE, INTERRUPT_POLICY_IGNORE) or integer (int32) | Optional; explicit presence | Policy for an incoming message while another generation run is active. |
Section ID: DOC-API-MODEL-schema-ph6avse89k#request-field-maxloopsmaxLoops | string (int64) | Optional | Default limit on agentic generation loops for the conversation. Pattern: ^-?\d+$. |
Section ID: DOC-API-MODEL-schema-ph6avse89k#request-field-maxparalleltoolsmaxParallelTools | string (int64) | Optional | Maximum number of tool executions allowed concurrently by this configuration. Pattern: ^-?\d+$. |
Section ID: DOC-API-MODEL-schema-ph6avse89k#request-field-mcpserversmcpServers | Array of MCPServerReference | Optional | MCP servers available to this conversation; used for tool discovery/filtering |
Section ID: DOC-API-MODEL-schema-ph6avse89k#request-field-toolpolicytoolPolicy | ToolExecutionPolicy | Optional | Optional per-conversation tool execution policy applied to AgentConfig |
Section ID: DOC-API-MODEL-schema-ph6avse89k#request-field-promptvariablespromptVariables | Map from string to JSON value | Optional | Typed values used when rendering profile prompt templates. Numbers, arrays, Boolean values and strings retain their respective JSON types. The values are shared by profiles in the conversation and can be refreshed with UpdatePromptVariables. Switching profiles renders the new template with the same values. |
Values of interruptPolicy
Section ID: DOC-API-MODEL-schema-ph6avse89k#request-values-interruptpolicy
How a conversation handles a new send while another generation run is active.
| Value | No. | Form | Meaning |
|---|---|---|---|
INTERRUPT_POLICY_REJECT_NEW | 0 | Canonical | See meaning below. |
INTERRUPT_POLICY_CANCEL_ONGOING | 1 | Canonical | See meaning below. |
INTERRUPT_POLICY_QUEUE | 2 | Canonical | See meaning below. |
INTERRUPT_POLICY_IGNORE | 3 | Canonical | Accept the send without persisting its message or starting a new run; let the ongoing run continue. |
INTERRUPT_POLICY_REJECT_NEW
Reject the new send with an error while a run is active; do not append its user message.
Reject the new Send with an error if a run is active
INTERRUPT_POLICY_CANCEL_ONGOING
Cancel the ongoing run and start a new run for the incoming message.
Cancel the ongoing run and immediately start a new one with the new message
INTERRUPT_POLICY_QUEUE
Queue the incoming message to run after the current run completes.
Queue the new Send; it will run after the current run completes
In responses
Section ID: DOC-API-MODEL-schema-ph6avse89k#response
API JSON uses JSON field names (camelCase).
| Field | Type | Presence | Meaning |
|---|---|---|---|
Section ID: DOC-API-MODEL-schema-ph6avse89k#field-interruptpolicySection ID: DOC-API-MODEL-schema-ph6avse89k#response-field-interruptpolicyinterruptPolicy | string (INTERRUPT_POLICY_REJECT_NEW, INTERRUPT_POLICY_CANCEL_ONGOING, INTERRUPT_POLICY_QUEUE, INTERRUPT_POLICY_IGNORE) or integer (int32) | Optional; explicit presence | Policy for an incoming message while another generation run is active. |
Section ID: DOC-API-MODEL-schema-ph6avse89k#field-maxloopsSection ID: DOC-API-MODEL-schema-ph6avse89k#response-field-maxloopsmaxLoops | string (int64) | Optional | Default limit on agentic generation loops for the conversation. Pattern: ^-?\d+$. |
Section ID: DOC-API-MODEL-schema-ph6avse89k#field-maxparalleltoolsSection ID: DOC-API-MODEL-schema-ph6avse89k#response-field-maxparalleltoolsmaxParallelTools | string (int64) | Optional | Maximum number of tool executions allowed concurrently by this configuration. Pattern: ^-?\d+$. |
Section ID: DOC-API-MODEL-schema-ph6avse89k#field-mcpserversSection ID: DOC-API-MODEL-schema-ph6avse89k#response-field-mcpserversmcpServers | Array of MCPServerReference | Optional | MCP servers available to this conversation; used for tool discovery/filtering |
Section ID: DOC-API-MODEL-schema-ph6avse89k#field-toolpolicySection ID: DOC-API-MODEL-schema-ph6avse89k#response-field-toolpolicytoolPolicy | ToolExecutionPolicy | Optional | Optional per-conversation tool execution policy applied to AgentConfig |
Section ID: DOC-API-MODEL-schema-ph6avse89k#field-promptvariablesSection ID: DOC-API-MODEL-schema-ph6avse89k#response-field-promptvariablespromptVariables | Map from string to JSON value | Optional | Typed values used when rendering profile prompt templates. Numbers, arrays, Boolean values and strings retain their respective JSON types. The values are shared by profiles in the conversation and can be refreshed with UpdatePromptVariables. Switching profiles renders the new template with the same values. |
Values of interruptPolicy
Section ID: DOC-API-MODEL-schema-ph6avse89k#response-values-interruptpolicy
How a conversation handles a new send while another generation run is active.
| Value | No. | Form | Meaning |
|---|---|---|---|
INTERRUPT_POLICY_REJECT_NEW | 0 | Canonical | See meaning below. |
INTERRUPT_POLICY_CANCEL_ONGOING | 1 | Canonical | See meaning below. |
INTERRUPT_POLICY_QUEUE | 2 | Canonical | See meaning below. |
INTERRUPT_POLICY_IGNORE | 3 | Canonical | Accept the send without persisting its message or starting a new run; let the ongoing run continue. |
INTERRUPT_POLICY_REJECT_NEW
Reject the new send with an error while a run is active; do not append its user message.
Reject the new Send with an error if a run is active
INTERRUPT_POLICY_CANCEL_ONGOING
Cancel the ongoing run and start a new run for the incoming message.
Cancel the ongoing run and immediately start a new one with the new message
INTERRUPT_POLICY_QUEUE
Queue the incoming message to run after the current run completes.
Queue the new Send; it will run after the current run completes
Where used
Section ID: DOC-API-MODEL-schema-ph6avse89k#where-used
| Reference | Relationship |
|---|---|
| Get full conversation state | POST /api/v1/llm/conversation-state |
| Update prompt variables | POST /api/v1/llm/update-prompt-variables |
| Update conversation settings | POST /api/v1/llm/update-settings |
| Create a new conversation thread | POST /api/v1/llm/create-thread |
Download the public reference contract.
Document ID: DOC-API-MODEL-schema-ph6avse89k