新增: Phase2 阶段收尾(Sprint 1-20)

重构:删 5 零引用 crate(df-evolve/plugin/stages/task/traceability)+ 清死模块、ai.rs 拆 11 子 module、ai.ts 拆 6 composable、i18n 拆目录
功能:知识库全栈(df-project/scan + CRUD + 时间线 + 前端)、Settings 拆分、appSettings KV 迁移、模型池、LLM 并发 Semaphore
修复:审批持久化根治、ConditionEngine 默认拒绝、NodeRegistry unimplemented 清除、promote 补偿删除、工具结果截断 50KB、路径校验防 symlink 逃逸
文档:B-03 人工审批设计、决策记录三分档、规格契约自检、经验记录、todo 看板、PROGRESS 更新

详见 PROGRESS.md。src-tauri/儿童每日打卡应用/ 与本项目无关,已排除。
This commit is contained in:
2026-06-14 14:08:20 +08:00
parent 98393b4908
commit cf017f81e2
167 changed files with 19549 additions and 6886 deletions

View File

@@ -4,12 +4,14 @@ use std::path::Path;
use std::sync::Arc;
use anyhow::Result;
use tokio::sync::Mutex;
use serde::{Deserialize, Serialize};
use tokio::sync::{Mutex, Semaphore};
use df_ai::ai_tools::{AiToolRegistry, RiskLevel};
use df_ai::ai_tools::AiToolRegistry;
use df_storage::crud::{
AiConversationRepo, AiProviderRepo, AiToolExecutionRepo, IdeaRepo, NodeExecutionRepo,
ProjectRepo, ReleaseRepo, TaskRepo, WorkflowRepo,
AiConversationRepo, AiProviderRepo, AiToolExecutionRepo, IdeaRepo, KnowledgeEventsRepo,
KnowledgeRepo, NodeExecutionRepo, ProjectRepo, ReleaseRepo, SettingsRepo, TaskRepo,
WorkflowRepo,
};
use df_storage::db::Database;
use df_workflow::eventbus::EventBus;
@@ -17,6 +19,116 @@ use df_workflow::registry::NodeRegistry;
use crate::commands::ai::AiSession;
// ============================================================
// 知识库配置(提取 + 注入)
// ============================================================
/// AI 提炼触发方式
#[derive(Debug, Clone, Serialize, Deserialize, PartialEq)]
#[serde(rename_all = "snake_case")]
pub enum ExtractTrigger {
/// 对话正常完成时(默认)
OnComplete,
/// 对话闲置 N 秒后
OnIdle,
/// 仅手动按钮触发
ManualOnly,
}
/// 知识库行为配置(存 AppState 内存,前后端通过 IPC 读写)
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct KnowledgeConfig {
/// 提炼总开关,默认 true
pub auto_extract: bool,
/// 提炼触发方式,默认 OnComplete
pub trigger_mode: ExtractTrigger,
/// 最少消息数守卫(防闲聊噪音),默认 4
pub min_messages: u32,
/// 闲置触发超时(ms),默认 30000
pub idle_timeout_ms: u64,
/// 聊天时自动注入相关知识开关,默认 true
pub auto_inject: bool,
/// 语义检索(向量)总开关,默认 false——关闭时纯 LIKE 零外部依赖
#[serde(default)]
pub vector_enabled: bool,
/// embedding 用的 provider id(仅 openai_compat 类型,Anthropic 无 embed API)
#[serde(default)]
pub embedding_provider_id: Option<String>,
/// embedding 模型名(如 embedding-3 / text-embedding-3-small)
#[serde(default)]
pub embedding_model: Option<String>,
}
impl Default for KnowledgeConfig {
fn default() -> Self {
Self {
auto_extract: true,
trigger_mode: ExtractTrigger::OnComplete,
min_messages: 4,
idle_timeout_ms: 30_000,
auto_inject: true,
vector_enabled: false,
embedding_provider_id: None,
embedding_model: None,
}
}
}
// ============================================================
// LLM 调用并发控制(双层 Semaphore
// ============================================================
/// LLM 调用并发控制 — 全局 + 单对话双层 Semaphore
///
/// 限流对象:所有真实 LLM 调用(主循环 stream_llm / 标题生成 / 知识提炼)。
/// 不限流本地工具执行tools.execute——本地操作无外部成本、不受 RPM 约束。
///
/// 运行时调整tokio Semaphore 的 permits 数构造时固定、不可增减,
/// 故用 `Arc<Mutex<Arc<Semaphore>>>` 双层包装——替换内层 Arc 即重建 Semaphore。
/// 已持有旧 permit 的任务不受影响permit 绑定旧 Semaphore软收敛
/// 新请求 lock 后克隆到最新 Arc、自动走新限制。旧 Semaphore 随最后 permit 释放而 drop。
///
/// 注意per_conv 当前是应用级单一信号量(非 per-conv map)。因 AiSession 为单例 +
/// generating 互斥,同一时刻仅一个对话的 loop 在跑,per_conv 退化为"单对话内并发"
/// (主循环 stream_llm + 标题生成 + 知识提炼)。未来若支持多对话并发,
/// 需改为 HashMap<conv_id, Semaphore>。
#[derive(Clone)]
pub struct LlmConcurrency {
global: Arc<Mutex<Arc<Semaphore>>>,
per_conv: Arc<Mutex<Arc<Semaphore>>>,
}
impl LlmConcurrency {
pub fn new(global: usize, per_conv: usize) -> Self {
Self {
global: Arc::new(Mutex::new(Arc::new(Semaphore::new(global)))),
per_conv: Arc::new(Mutex::new(Arc::new(Semaphore::new(per_conv)))),
}
}
/// 取全局并发 permit重建后新请求自动走最新 Semaphore
pub async fn acquire_global(&self) -> tokio::sync::OwnedSemaphorePermit {
let sema = self.global.lock().await.clone();
sema.acquire_owned().await.expect("llm global semaphore closed")
}
/// 取单对话并发 permit
pub async fn acquire_per_conv(&self) -> tokio::sync::OwnedSemaphorePermit {
let sema = self.per_conv.lock().await.clone();
sema.acquire_owned().await.expect("llm per_conv semaphore closed")
}
/// 重建全局 Semaphore软收敛旧 permit 不回收,待其释放后新限制完全生效)
pub async fn set_global(&self, permits: usize) {
*self.global.lock().await = Arc::new(Semaphore::new(permits));
}
/// 重建单对话 Semaphore
pub async fn set_per_conv(&self, permits: usize) {
*self.per_conv.lock().await = Arc::new(Semaphore::new(permits));
}
}
/// 应用全局状态 — 通过 `app.manage()` 注入command 中以 `State<'_, AppState>` 取用
pub struct AppState {
/// 数据库句柄Arc 包装,便于在异步任务中重建 Repo
@@ -48,14 +160,26 @@ pub struct AppState {
pub ai_tools: Arc<AiToolRegistry>,
/// AI 会话状态
pub ai_session: Arc<Mutex<AiSession>>,
// ── 知识库 ──
/// 知识库 Repo
pub knowledge: KnowledgeRepo,
/// 知识生命线事件 Repo(产生/审核/引用/归档审计)
pub knowledge_events: KnowledgeEventsRepo,
/// 知识库行为配置(提取 + 注入)
pub knowledge_config: Arc<Mutex<KnowledgeConfig>>,
/// 通用应用设置 KV Repo(前端 localStorage 迁移目标)
pub settings: SettingsRepo,
// ── LLM 并发控制 ──
/// LLM 调用并发上限(全局 + 单对话双层 Semaphore运行时可调
pub llm_concurrency: LlmConcurrency,
}
impl AppState {
/// 初始化应用状态:打开(或创建)数据库并执行迁移,构建各 Repo 与节点注册表
pub async fn init(db_path: &Path) -> Result<Self> {
let db = Arc::new(Database::open(db_path).await?);
let ai_tools = Arc::new(build_ai_tool_registry());
Ok(Self {
let ai_tools = Arc::new(crate::commands::ai::build_ai_tool_registry(&db));
let state = Self {
ideas: IdeaRepo::new(&db),
projects: ProjectRepo::new(&db),
tasks: TaskRepo::new(&db),
@@ -66,11 +190,20 @@ impl AppState {
ai_conversations: AiConversationRepo::new(&db),
ai_tool_executions: AiToolExecutionRepo::new(&db),
ai_session: Arc::new(Mutex::new(AiSession::new())),
knowledge: KnowledgeRepo::new(&db),
knowledge_events: KnowledgeEventsRepo::new(&db),
knowledge_config: Arc::new(Mutex::new(KnowledgeConfig::default())),
settings: SettingsRepo::new(&db),
llm_concurrency: LlmConcurrency::new(3, 2),
db,
event_bus: EventBus::new(),
registry: Arc::new(build_registry()),
ai_tools,
})
};
// 启动恢复:重启前卡 pending 的工具审批(内存 pending_approvals 已丢)从审计表重建,
// 使重启后待审批不丢。前端经 ai_pending_tool_calls + switchConversation 恢复 toolCard 态。
crate::commands::ai::restore_pending_approvals(&state).await;
Ok(state)
}
}
@@ -92,191 +225,3 @@ fn build_registry() -> NodeRegistry {
registry
}
// ============================================================
// AI 工具注册
// ============================================================
use serde_json::json;
fn object_schema(fields: Vec<(&str, &str, bool)>) -> serde_json::Value {
let mut props = serde_json::Map::new();
let mut required = Vec::new();
for (name, typ, req) in &fields {
props.insert(name.to_string(), json!({ "type": typ }));
if *req {
required.push(name.to_string());
}
}
json!({
"type": "object",
"properties": props,
"required": required,
})
}
/// 构建 AI 工具注册表 — 注册所有 CRUD 操作为可调用工具
fn build_ai_tool_registry() -> AiToolRegistry {
let mut registry = AiToolRegistry::new();
// ── 只读工具 (Low risk) ──
registry.register(
"list_projects",
"列出所有项目返回项目列表ID、名称、状态、描述",
object_schema(vec![]),
RiskLevel::Low,
Box::new(|_args| {
Box::pin(async { Ok(json!({"note": "工具执行在 IPC 层处理"})) })
}),
);
registry.register(
"list_tasks",
"列出任务,可按 project_id 筛选",
object_schema(vec![("project_id", "string", false)]),
RiskLevel::Low,
Box::new(|_args| {
Box::pin(async { Ok(json!({"note": "工具执行在 IPC 层处理"})) })
}),
);
registry.register(
"list_ideas",
"列出所有想法",
object_schema(vec![]),
RiskLevel::Low,
Box::new(|_args| {
Box::pin(async { Ok(json!({"note": "工具执行在 IPC 层处理"})) })
}),
);
// ── 创建工具 (Medium risk) ──
registry.register(
"update_project",
"更新项目的指定字段name/status/description需要提供项目 ID、字段名和新值",
object_schema(vec![
("id", "string", true),
("field", "string", true),
("value", "string", true),
]),
RiskLevel::Medium,
Box::new(|_args| {
Box::pin(async { Ok(json!({"note": "工具执行在 IPC 层处理"})) })
}),
);
registry.register(
"create_project",
"创建新项目",
object_schema(vec![
("name", "string", true),
("description", "string", false),
]),
RiskLevel::Medium,
Box::new(|_args| {
Box::pin(async { Ok(json!({"note": "工具执行在 IPC 层处理"})) })
}),
);
registry.register(
"create_task",
"在指定项目下创建新任务",
object_schema(vec![
("project_id", "string", true),
("title", "string", true),
("description", "string", false),
("priority", "integer", false),
]),
RiskLevel::Medium,
Box::new(|_args| {
Box::pin(async { Ok(json!({"note": "工具执行在 IPC 层处理"})) })
}),
);
registry.register(
"create_idea",
"捕获一个新想法",
object_schema(vec![
("title", "string", true),
("description", "string", false),
("tags", "string", false),
("source", "string", false),
]),
RiskLevel::Medium,
Box::new(|_args| {
Box::pin(async { Ok(json!({"note": "工具执行在 IPC 层处理"})) })
}),
);
// ── 高风险工具 (High risk) ──
registry.register(
"delete_project",
"删除项目及其所有关联数据",
object_schema(vec![("id", "string", true)]),
RiskLevel::High,
Box::new(|_args| {
Box::pin(async { Ok(json!({"note": "工具执行在 IPC 层处理"})) })
}),
);
registry.register(
"run_workflow",
"运行指定的工作流 DAG",
object_schema(vec![
("name", "string", true),
("dag", "object", true),
]),
RiskLevel::High,
Box::new(|_args| {
Box::pin(async { Ok(json!({"note": "工具执行在 IPC 层处理"})) })
}),
);
// ── 文件系统工具 ──
registry.register(
"read_file",
"读取文件内容,返回文本内容。支持 offset 和 limit 参数分页读取大文件",
object_schema(vec![
("path", "string", true),
("offset", "integer", false),
("limit", "integer", false),
]),
RiskLevel::Low,
Box::new(|_args| {
Box::pin(async { Ok(json!({"note": "工具执行在 IPC 层处理"})) })
}),
);
registry.register(
"list_directory",
"列出目录内容,返回文件和子目录列表(名称、类型、大小)",
object_schema(vec![
("path", "string", true),
("recursive", "boolean", false),
]),
RiskLevel::Low,
Box::new(|_args| {
Box::pin(async { Ok(json!({"note": "工具执行在 IPC 层处理"})) })
}),
);
registry.register(
"write_file",
"写入或创建文件,自动创建不存在的父目录",
object_schema(vec![
("path", "string", true),
("content", "string", true),
]),
RiskLevel::Medium,
Box::new(|_args| {
Box::pin(async { Ok(json!({"note": "工具执行在 IPC 层处理"})) })
}),
);
registry
}