跳转到主要内容

Documentation Index

Fetch the complete documentation index at: https://simplellmfunc.cn/llms.txt

Use this file to discover all available pages before exploring further.

​
上下文类型 API 参考

​
ContextState

from SimpleLLMFunc.base.types import ContextState
对话状态的运行时表示。 
@dataclass
class ContextState:
    messages: NormalizedMessageList
    data_from_selfref: Optional[DataFromSelfRef] = None
    pending_mutations: List[ContextMutation] = field(default_factory=list)
字段类型描述
messagesNormalizedMessageList当前对话记录
data_from_selfrefDataFromSelfRef | None持久化的自引用（SelfReference）状态
pending_mutationsList[ContextMutation]等待下一个编译边界的变更

​
CompileSource

from SimpleLLMFunc.base.types import CompileSource
编译的输入边界。 
@dataclass(frozen=True)
class CompileSource:
    data_from_agent_config: DataFromAgentConfig
    data_from_selfref: Optional[DataFromSelfRef]
    input_messages: NormalizedMessageList

​
DataFromAgentConfig

from SimpleLLMFunc.base.types import DataFromAgentConfig
来自装饰器的静态配置。 
@dataclass(frozen=True)
class DataFromAgentConfig:
    base_system_prompt: str
    template_params: Optional[Dict[str, Any]] = None
    tool_prompt_specs: List[Dict[str, Any]] = field(default_factory=list)
    include_must_principles: bool = False
字段描述
base_system_prompt文档字符串内容（可能包含 {占位符}）
template_params用于占位符替换的值
tool_prompt_specs用于系统提示词注入的工具最佳实践规格
include_must_principles是否追加结构化调用规则

​
DataFromSelfRef

from SimpleLLMFunc.base.types import DataFromSelfRef
来自 SelfReference 后端的持久化状态。 
@dataclass(frozen=True)
class DataFromSelfRef:
    base_system_prompt: str
    experiences: List[Dict[str, str]] = field(default_factory=list)
    summary: Optional[Dict[str, Any]] = None
    summary_message: Optional[Dict[str, Any]] = None
    working_messages: NormalizedMessageList = field(default_factory=list)
字段描述
base_system_prompt带有自引用标记的系统提示词
experiences[{id: str, text: str}, ...] — 持久化的记忆事实
summary压缩元数据
summary_message可展示的摘要消息
working_messages压缩后的工作对话记录

​
ContextMutation (Union)

from SimpleLLMFunc.base.types import ContextMutation

ContextMutation = Union[
    AssistantMessageMutation,
    ToolResultMutation,
    MultimodalToolResultMutation,
    UserMessageMutation,
    ContextReplaceMutation,
    ContextSummaryMutation,
    ExperienceRememberMutation,
    ExperienceForgetMutation,
    AssistantTruncatedMutation,
    ToolCancelledMutation,
]

​
AssistantMessageMutation

@dataclass
class AssistantMessageMutation:
    role: Literal["assistant"] = "assistant"
    content: Optional[str] = None
    tool_calls: List[Dict[str, Any]] = field(default_factory=list)
    reasoning_details: List[Dict[str, Any]] = field(default_factory=list)

​
ToolResultMutation

@dataclass
class ToolResultMutation:
    tool_call_id: str
    content: str
    role: Literal["tool"] = "tool"

​
MultimodalToolResultMutation

@dataclass
class MultimodalToolResultMutation:
    tool_call_id: str
    tool_name: str
    arguments: str
    user_messages: List[Dict[str, Any]]

​
UserMessageMutation

@dataclass
class UserMessageMutation:
    message: Dict[str, Any]

​
ContextReplaceMutation

@dataclass
class ContextReplaceMutation:
    messages: List[Dict[str, Any]]

​
ContextSummaryMutation

@dataclass
class ContextSummaryMutation:
    summary_message: Dict[str, Any]
    remember: List[Dict[str, str]] = field(default_factory=list)

​
ExperienceRememberMutation

@dataclass
class ExperienceRememberMutation:
    text: str

​
ExperienceForgetMutation

@dataclass
class ExperienceForgetMutation:
    experience_id: str

​
AssistantTruncatedMutation

@dataclass
class AssistantTruncatedMutation:
    partial_content: str
    abort_reason: str = ""

​
ToolCancelledMutation

@dataclass
class ToolCancelledMutation:
    tool_call_id: str
    tool_name: str
    abort_reason: str = ""

​
编译输出

​
ReducedTurnContext

from SimpleLLMFunc.base.types import ReducedTurnContext
阶段 1（变更应用）的输出： 
@dataclass
class ReducedTurnContext:
    transcript: NormalizedMessageList
    selfref_snapshot: Optional[DataFromSelfRef] = None

​
CompiledTurnContext

from SimpleLLMFunc.base.types import CompiledTurnContext
完整流水线的输出（已准备好发送给 LLM）： 
@dataclass
class CompiledTurnContext:
    transcript: NormalizedMessageList
    system_prompt: Optional[str]
    llm_messages: NormalizedMessageList
    selfref_snapshot: Optional[DataFromSelfRef] = None
字段描述
transcript系统提示词解析后的消息列表
system_prompt已解析的系统提示词文本
llm_messages发送给提供商的最终消息（已注入工具规格）
selfref_snapshot向前传递的自引用状态

​
CompiledContext

from SimpleLLMFunc.base.types import CompiledContext
中间编译状态（在 LLM 渲染之前）： 
@dataclass
class CompiledContext:
    messages: NormalizedMessageList
    data_from_selfref: Optional[DataFromSelfRef] = None

​
流水线函数

​
compile_invocation_turn

from SimpleLLMFunc.base.compile_pipeline import compile_invocation_turn

def compile_invocation_turn(
    spec: InvocationSpec,
    transcript: NormalizedMessageList,
    pending_mutations: Optional[List[ContextMutation]] = None,
    selfref_snapshot: Optional[DataFromSelfRef] = None,
) -> CompiledTurnContext:
完整编译流水线的单一入口点。

​
reduce_turn_context

from SimpleLLMFunc.base.compile_pipeline import reduce_turn_context

def reduce_turn_context(
    transcript: NormalizedMessageList,
    pending_mutations: List[ContextMutation],
    selfref_snapshot: Optional[DataFromSelfRef] = None,
) -> ReducedTurnContext:
仅阶段 1：应用变更，刷新自引用快照。

​
convert_to_llm_request

from SimpleLLMFunc.base.compile_pipeline import convert_to_llm_request

def convert_to_llm_request(
    reduced: ReducedTurnContext,
    prompt_contract: PromptContract,
) -> CompiledTurnContext:
阶段 2：解析系统提示词，渲染最终消息。