cayu.sessions.ResumeRequest

Part of cayu.sessions.base. Read the Python API overview and install the required extra.

from cayu.sessions import ResumeRequest

Continue a conversation; omitted loop controls inherit verified prior settings.

max_steps, limits, and retry_policy inherit from the latest profile-bound model completion when available. Explicit values still pass normal execution-profile admission. Legacy/fork sessions without matching evidence use application defaults. This does not reset session-scoped limits.

Bases: BaseModel.

Fields and attributes

Defaults below are source expressions; Field(...) includes schema/validation settings and default_factory creates a fresh value. Inherited declarations are included. Constructor behavior follows the model or dataclass shown in the bases/decorators.

Name	Type	Default
`session_id`	`str`	`required`
`task_worker_id`	`str \| None`	`None`
`task_handoff_id`	`str \| None`	`None`
`messages`	`list[Message]`	`required`
`target`	`ModelTarget \| None`	`None`
`failover`	`ModelFailoverPolicy \| None`	`Field(default=None, exclude_if=lambda value: value is None)`
`tool_capability_ceiling`	`ToolCapabilityCeiling \| None`	`None`
`tool_grants`	`tuple[TargetedToolGrant, ...]`	`()`
`profile_adoption`	`ExecutionProfileAdoptionIntent \| None`	`None`
`metadata`	`dict[str, Any]`	`Field(default_factory=dict)`
`max_steps`	`StrictInt`	`Field(default=DEFAULT_MAX_STEPS, ge=1, le=MAX_STEPS)`
`limits`	`RunLimits`	`Field(default_factory=RunLimits)`
`budget_limits`	`tuple[BudgetLimit, ...]`	`Field(default_factory=tuple)`
`retry_policy`	`RetryPolicy \| None`	`None`
`structured_output`	`StructuredOutputSpec \| None`	`None`
`thinking`	`ThinkingConfig \| None`	`None`
`tool_completion`	`ToolCompletionPolicy \| None`	`Field(default=None, exclude_if=lambda value: value is None, description='Complete a single-call round from a designated successful none or idempotent tool.')`
`loop_policies`	`SkipJsonSchema[tuple[LoopPolicy, ...]]`	`Field(default_factory=tuple, exclude=True)`

copy_failover (method)

ResumeRequest.copy_failover(value: object) -> ModelFailoverPolicy | None

copy_messages (method)

ResumeRequest.copy_messages(value)

validate_optional_task_worker_id (method)

ResumeRequest.validate_optional_task_worker_id(value: str | None) -> str | None

validate_task_handoff_authority (method)

ResumeRequest.validate_task_handoff_authority() -> ResumeRequest

copy_request_metadata (method)

ResumeRequest.copy_request_metadata(value: dict[str, Any]) -> dict[str, Any]

copy_structured_output (method)

ResumeRequest.copy_structured_output(value: StructuredOutputSpec | None) -> StructuredOutputSpec | None

copy_tool_capability_ceiling (method)

ResumeRequest.copy_tool_capability_ceiling(value: object) -> ToolCapabilityCeiling | None

copy_tool_grants (method)

ResumeRequest.copy_tool_grants(value: object) -> tuple[TargetedToolGrant, ...]

copy_profile_adoption (method)

ResumeRequest.copy_profile_adoption(value: object) -> ExecutionProfileAdoptionIntent | None

copy_budget_limits (method)

ResumeRequest.copy_budget_limits(value) -> tuple[BudgetLimit, ...]

copy_limits (method)

ResumeRequest.copy_limits(value: RunLimits) -> RunLimits

copy_tool_completion (method)

ResumeRequest.copy_tool_completion(value: object) -> ToolCompletionPolicy | None

copy_loop_policies (method)

ResumeRequest.copy_loop_policies(value) -> tuple[LoopPolicy, ...]

validate_optional_nonblank_strings (method)

ResumeRequest.validate_optional_nonblank_strings(value: str | None, info) -> str | None

Release source · Runtime guarantees · Capability guides