跳转到主要内容

​
运行时 API 参考

​
PrimitivePack

from SimpleLLMFunc.runtime import PrimitivePack
具有共享后端的命名原语（primitive）集合。 
@dataclass
class PrimitivePack:
    namespace: str                          # e.g., "selfref", "metrics"
    backend: RuntimePrimitiveBackend        # Stateful backend instance
    primitives: List[PrimitiveHandler]      # Registered primitive functions
    guide: Optional[Dict[str, Any]] = None  # Namespace documentation

​
示例

from SimpleLLMFunc.runtime import PrimitivePack, RuntimePrimitiveBackend, primitive

class MyBackend(RuntimePrimitiveBackend):
    pass

@primitive
async def my_action(ctx: PrimitiveCallContext, arg: str) -> dict:
    """Do something.

    Args:
        arg: Input argument.

    Returns:
        Result dict.

    Best Practices:
        - Use for X.
    """
    return {"result": arg}

pack = PrimitivePack(
    namespace="myns",
    backend=MyBackend(),
    primitives=[my_action],
    guide={"namespace": "myns", "overview": "My custom primitives."},
)

​
@primitive

from SimpleLLMFunc.runtime import primitive
将函数注册为运行时原语的装饰器。

​
要求

  • 第一个参数必须是 ctx: PrimitiveCallContext
  • 文档字符串必须包含 Best Practices 部分
  • 必须是 async def
@primitive
async def my_primitive(ctx: PrimitiveCallContext, param: str) -> dict:
    """Description.

    Args:
        param: Description.

    Returns:
        Result.

    Best Practices:
        - When to use this primitive.
    """
    return {"value": param}

​
PrimitiveCallContext

from SimpleLLMFunc.runtime import PrimitiveCallContext
传递给每个原语处理器的运行时上下文。 
@dataclass
class PrimitiveCallContext:
    backend: RuntimePrimitiveBackend    # The pack's backend
    fork_context: Optional[ForkContext] # Fork info if inside a fork
    event_emitter: ToolEventEmitter     # For emitting custom events

​
ForkContext

from SimpleLLMFunc.runtime import ForkContext
关于当前分叉（fork）执行上下文的信息。 
@dataclass
class ForkContext:
    parent_pack_name: str
    backend_name: str
    child_fork_id: str | None = None
    source_memory_key: str | None = None
    metadata: dict[str, Any] | None = None

​
PrimitiveSpec

from SimpleLLMFunc.runtime import PrimitiveSpec
暴露给模型的可发现性合约。 
@dataclass
class PrimitiveSpec:
    name: str                                  # Full qualified name (e.g., "selfref.context.remember")
    description: str                           # What it does
    parameters: List[PrimitiveParameterSpec]   # Parameter descriptions
    returns: str                               # Return type description
    best_practices: List[str]                  # Usage guidance

​
PrimitiveParameterSpec

@dataclass
class PrimitiveParameterSpec:
    name: str
    type: str
    description: str
    required: bool = True
    default: Optional[Any] = None

​
PrimitiveRegistry

from SimpleLLMFunc.runtime import PrimitiveRegistry
管理已安装的原语包并路由原语调用。

​
关键方法

方法描述
install_pack(pack)注册一个 PrimitivePack
call(name, **kwargs)按限定名执行原语
list_primitives()列出所有已注册的原语名称
get_spec(name)获取某个原语的 PrimitiveSpec
list_specs()获取所有规格
list_backends()列出已安装的后端包

​
RuntimePrimitiveBackend

from SimpleLLMFunc.runtime import RuntimePrimitiveBackend
原语包后端的基类。继承此类以创建有状态后端。 
class RuntimePrimitiveBackend:
    """Base class. Override to add state."""
    pass

​
内置元原语

在 PyRepl 中始终可用，无需安装任何包：
调用返回值
runtime.list_primitives()List[str] — 所有原语名称
runtime.list_primitive_specs()List[PrimitiveSpec] — 所有规格
runtime.get_primitive_spec(name)PrimitiveSpec — 单个规格
runtime.list_backends()List[str] — 已安装的包

​
SelfRef 包注册

from SimpleLLMFunc.runtime import build_self_reference_pack, register_self_reference_primitives

# Build the pack
pack = build_self_reference_pack(selfref_backend)

# Or register directly into a PyRepl
register_self_reference_primitives(repl, selfref_backend)
SelfRef 包在 runtime.selfref.context.* 和 runtime.selfref.fork.* 命名空间下提供原语。