refactor(core): 完成 v0.3.2 Cargo features 拆分基础设施

- 定义 16 个 features + 4 个快捷组合，default = ["full"] 保持向后兼容
- 12 个重型依赖 optional 化（tokio/reqwest/rusqlite 等）
- 全模块 #[cfg(feature)] 门控注入（llm/tools/memory/agent/engine）
- 将 LlmProvider trait 及关联类型移出 provider 模块归属 llm（ADR-1）
- 为 session.rs bundle() 方法添加 engine feature 门控
- 更新 12 个内部文件 + 4 个示例文件的 import 路径
- 向后兼容：provider.rs 保留 pub use 重导出老路径

src/llm/provider/anthropic.rs

@@ -18,7 +18,7 @@ use serde::{Deserialize, Serialize};
 use serde_json::{Value, json};
 use tracing::{debug, error, info, warn};
 
-use super::{LlmProvider, ProviderCapabilities, ProviderFeatures};
+use crate::llm::{LlmProvider, ProviderCapabilities, ProviderFeatures};
 use crate::llm::error::LlmError;
 use crate::llm::types::message::{ContentBlock, ContentBlockType, Message};
 use crate::llm::types::request_v2::MessageRequest;

src/llm/provider/ollama.rs

@@ -11,7 +11,7 @@ use futures_core::Stream;
 use reqwest::Client;
 
 use super::openai::GenericOpenaiProvider;
-use super::{LlmProvider, ProviderCapabilities};
+use crate::llm::{LlmProvider, ProviderCapabilities};
 use crate::llm::error::LlmError;
 use crate::llm::types::request_v2::MessageRequest;
 use crate::llm::types::response_v2::{MessageResponse, StreamEvent};

src/llm/provider/openai.rs

@@ -21,7 +21,7 @@ use serde::Serialize;
 use serde_json::Value;
 use tracing::{debug, error, info};
 
-use super::{LlmProvider, ProviderCapabilities, ProviderFeatures};
+use crate::llm::{LlmProvider, ProviderCapabilities, ProviderFeatures};
 use crate::llm::convert::{from_openai, to_openai};
 use crate::llm::error::LlmError;
 use crate::llm::types::message::{ContentBlock, ContentBlockType, Message};

src/llm/provider/openai_compat.rs

@@ -15,12 +15,11 @@ use std::pin::Pin;
 use async_trait::async_trait;
 use futures_core::Stream;
 
-use super::ProviderCapabilities;
 use super::openai::GenericOpenaiProvider;
 use crate::llm::error::LlmError;
-use crate::llm::provider::LlmProvider;
 use crate::llm::types::request_v2::MessageRequest;
 use crate::llm::types::response_v2::{MessageResponse, StreamEvent};
+use crate::llm::{LlmProvider, ProviderCapabilities};
 
 // =============================================================================
 // DeepSeek

src/llm/provider/registry.rs

@@ -3,7 +3,8 @@
 use std::collections::HashMap;
 
 use crate::llm::error::LlmError;
-use crate::llm::provider::{LlmProvider, ProviderConfig, ProviderType, create_provider};
+use crate::llm::provider::{ProviderConfig, ProviderType, create_provider};
+use crate::llm::LlmProvider;
 
 /// Provider 注册表 —— 管理多个 LLM Provider 实例。
 ///