aiagent/backend/app/agent_runtime/schemas.py

"""
Agent Runtime 配置与数据结构 Schema
"""
from __future__ import annotations

import logging
logger = logging.getLogger(__name__)
logger.warning("SCHEMAS_MODULE_LOADED_V3_FIELD_VALIDATOR")

from typing import Any, Dict, List, Optional
from pydantic import BaseModel, Field, field_validator
from app.agent_runtime.permissions import DEFAULT_REQUIRE_APPROVAL_TOOLS


class AgentToolConfig(BaseModel):
    """Agent 可用工具配置"""
    # 若为空列表则使用全部已注册工具
    include_tools: List[str] = Field(default_factory=list, description="允许的工具名称白名单")
    exclude_tools: List[str] = Field(default_factory=list, description="排除的工具名称黑名单")
    require_approval: List[str] = Field(default_factory=lambda: list(DEFAULT_REQUIRE_APPROVAL_TOOLS), description="需要人工审批的工具名列表（默认包含 destructive 工具）")

    @field_validator("include_tools", "exclude_tools", "require_approval", "cache_tool_whitelist", "auto_approve_rules", "deny_tools", mode="before")
    @classmethod
    def coerce_none_to_empty(cls, v: Any) -> Any:
        return v if v is not None else []
    approval_timeout_ms: int = Field(default=60000, description="审批超时（毫秒），超时使用默认策略")
    approval_default: str = Field(default="deny", description="超时默认策略: approve | deny | skip")
    # 结果缓存
    cache_enabled: bool = Field(default=True, description="是否启用工具结果缓存（确定性工具默认开启）")
    cache_tool_whitelist: List[str] = Field(default_factory=list, description="启用缓存的工具名（空=确定性工具默认）")
    cache_ttl_ms: int = Field(default=3600000, description="缓存 TTL（毫秒），默认 1 小时")

    # 工具安全分级 (P3 — 参考 Claude Code PermissionMode)
    permission_level: str = Field(
        default="default",
        description="权限级别: bypass | acceptEdits | default | plan"
    )
    auto_approve_rules: List[Dict[str, Any]] = Field(
        default_factory=list,
        description="自动批准规则: [{tool_pattern, param_conditions, description}]"
    )
    deny_tools: List[str] = Field(default_factory=list, description="禁用的工具名列表")


class AgentMemoryConfig(BaseModel):
    """Agent 记忆配置"""
    enabled: bool = True
    max_history_messages: int = 20  # 注入 LLM 的上文最大消息数
    session_key: Optional[str] = None  # 会话标识，默认自动生成
    persist_to_db: bool = True       # 是否写入 MySQL 长期记忆
    vector_memory_enabled: bool = True  # 是否启用向量记忆（语义检索）
    vector_memory_top_k: int = 5       # 向量检索 Top-K
    vector_memory_rerank: bool = False  # 是否启用 LLM Rerank（向量 top-20 → LLM 精选 top-K）
    memory_type_filter: Optional[List[str]] = None  # 记忆类型过滤，如 ["user","project"]，None=全部
    team_id: Optional[str] = None     # 团队共享 ID，非空时记忆在团队间共享
    team_share_enabled: bool = False  # 是否将新记忆自动发布到团队池
    learning_enabled: bool = True     # 是否启用自主学习（工具模式学习）
    # 文件式记忆 (MEMORY.md — 参考 Claude Code memdir)
    memory_dir_enabled: bool = False   # 是否启用文件式自动记忆
    memory_dir_path: str = ""          # 记忆目录路径（空=自动使用项目 .claude/memory）
    parent_agent_id: Optional[str] = None  # 父 Agent ID（继承经验）
    # 对话自动压缩 (参考 Claude Code src/services/compact/)
    compaction: Optional[Any] = None   # CompactionConfig — 惰性导入避免循环依赖


class AgentLLMConfig(BaseModel):
    """Agent 模型配置"""
    provider: str = "openai"        # openai / deepseek
    model: str = "gpt-4o-mini"
    temperature: float = 0.7
    max_tokens: Optional[int] = None
    api_key: Optional[str] = None
    base_url: Optional[str] = None
    max_iterations: int = 10        # ReAct 循环最大步数
    request_timeout: float = 120.0
    extra_body: Optional[Dict[str, Any]] = None
    self_review_threshold: float = 0.6  # self-review 通过阈值（0-1）
    cache_enabled: bool = False          # LLM 响应缓存（默认关闭，语义缓存有风险）
    cache_ttl_ms: int = 300000           # LLM 缓存 TTL，默认 5 分钟
    fallback_llm: Optional[Dict[str, Any]] = None  # 降级模型配置 {provider, model, api_key, base_url}
    # 计划模式 (P2 — 参考 Claude Code EnterPlanModeTool)
    plan_mode_enabled: bool = False       # 是否启用计划模式
    plan_approval_required: bool = True   # 是否需要用户审批计划
    plan_model: Optional[str] = None      # 计划生成使用的模型（默认复用主模型）
    # 上下文窗口 (用于 Compaction 触发计算)
    context_window: int = 128000          # 模型上下文窗口大小（token 数）


class AgentBudgetConfig(BaseModel):
    """Agent 执行预算配置"""
    max_llm_invocations: int = 200   # LLM 调用次数上限
    max_tool_calls: int = 500        # 工具调用次数上限


class AgentTokenBudgetConfig(BaseModel):
    """Token 预算管理配置 — 参考 Claude Code tokenBudget.ts"""
    enabled: bool = True
    context_window: int = 0             # 模型上下文窗口（0=自动检测）
    output_reserve: int = 8192           # 留给模型输出的空间
    warning_threshold_pct: float = Field(default=0.75, ge=0.1, le=1.0)
    compact_threshold_pct: float = Field(default=0.85, ge=0.1, le=1.0)
    hard_limit_pct: float = Field(default=0.95, ge=0.1, le=1.0)
    user_budget: Optional[int] = None    # 用户累计 token 目标（如 500000）
    auto_continue: bool = False          # 预算用尽自动继续
    compaction_after_warning: bool = True
    max_compaction_attempts: int = 3


class AgentPromptSectionsConfig(BaseModel):
    """系统提示词分层装配配置 — 参考 Claude Code systemPromptSections.ts"""
    # 是否启用分层装配（关闭则退回到简单的 system_prompt 字符串）
    enabled: bool = True

    # 静态段开关（段名 → 是否启用）
    static_sections: Dict[str, bool] = Field(default_factory=lambda: {
        "persona": True,
        "capabilities": True,
        "tool_instructions": True,
        "safety_rules": True,
        "output_style": True,
    })

    # 动态段开关
    dynamic_sections: Dict[str, bool] = Field(default_factory=lambda: {
        "environment": True,
        "language": True,
        "memory_context": True,
        "conversation_summary": True,
        "tool_list": False,  # 工具列表默认关闭（太长）
    })

    # 语言偏好（用于 language 段）
    language: Optional[str] = None


class AgentConfig(BaseModel):
    """Agent 完整配置"""
    name: str = "default_agent"
    system_prompt: str = "你是一个有用的AI助手。请使用可用工具来帮助用户完成任务。"
    llm: AgentLLMConfig = Field(default_factory=AgentLLMConfig)
    tools: AgentToolConfig = Field(default_factory=AgentToolConfig)
    memory: AgentMemoryConfig = Field(default_factory=AgentMemoryConfig)
    budget: AgentBudgetConfig = Field(default_factory=AgentBudgetConfig)
    user_id: Optional[str] = None
    # 持久记忆 / 向量记忆的 scope_id；不设时沿用 user_id 或 name（易与其他 Agent 串记忆）
    memory_scope_id: Optional[str] = None
    # 是否开启输出质量自检（结束前用轻量 LLM 评审，不达标则追加修正）
    self_review_enabled: bool = False
    # 系统提示词分层装配 (P2 — 参考 Claude Code prompts.ts + systemPromptSections.ts)
    prompt_sections: AgentPromptSectionsConfig = Field(default_factory=AgentPromptSectionsConfig)
    # Token 预算管理 (P2 — 参考 Claude Code tokenBudget.ts)
    token_budget: AgentTokenBudgetConfig = Field(default_factory=AgentTokenBudgetConfig)


class AgentMessage(BaseModel):
    """Agent 对话消息"""
    role: str  # user / assistant / tool
    content: str
    tool_calls: Optional[List[Dict[str, Any]]] = None
    tool_call_id: Optional[str] = None
    name: Optional[str] = None


class AgentStep(BaseModel):
    """Agent 单步执行记录（用于执行追踪）"""
    iteration: int = Field(..., description="第几步")
    type: str = Field(..., description="步骤类型: think / tool_call / tool_result / final")
    content: str = Field(default="", description="步骤内容")
    tool_name: Optional[str] = Field(default=None, description="工具名称（tool_call/tool_result 类型时）")
    tool_input: Optional[Dict[str, Any]] = Field(default=None, description="工具输入参数")
    tool_result: Optional[str] = Field(default=None, description="工具执行结果")
    reasoning: Optional[str] = Field(default=None, description="思考过程")


class TokenUsageInfo(BaseModel):
    """Token 预算信息 — 随 AgentResult 返回给前端展示用量条"""
    input_tokens: int = 0
    input_remaining: int = 0
    input_usage_pct: float = 0.0
    effective_window: int = 128_000
    context_window: int = 128_000
    cumulative_total: int = 0
    cumulative_prompt: int = 0
    cumulative_completion: int = 0
    llm_call_count: int = 0
    is_warning: bool = False
    is_critical: bool = False
    is_exhausted: bool = False
    compaction_attempts: int = 0
    user_budget: Optional[int] = None
    user_budget_used: Optional[int] = None
    user_budget_remaining: Optional[int] = None
    user_budget_pct: Optional[float] = None


class AgentResult(BaseModel):
    """Agent 执行结果"""
    success: bool = True
    content: str = ""
    truncated: bool = False
    iterations_used: int = 0
    tool_calls_made: int = 0
    error: Optional[str] = None
    steps: List[AgentStep] = Field(default_factory=list, description="执行追踪步骤详情")
    token_usage: Optional[TokenUsageInfo] = Field(default=None, description="Token 预算摘要")