PicoBot/src/tools/registry.rs
oudecheng bf8c227634 refactor: 迁移 parking_lot 锁并优化阻塞 IO 与内存管理
## 锁迁移:std::sync → parking_lot
消除锁中毒(poison)导致的级联崩溃风险。parking_lot 锁不会中毒,
且性能更优。迁移覆盖全部生产代码:
- experts/mod.rs: 4 RwLock + 13 expect
- skills/mod.rs: 1 RwLock + 11 expect
- tools/registry.rs: 1 RwLock + 2 expect
- gateway/model_selection.rs: 1 RwLock + 2 expect
- tools/task/repository.rs: 1 RwLock + 4 unwrap
- tools/task/runtime.rs: 2 RwLock + 17 expect
- gateway/session.rs + task/runtime.rs: stream_message_id Mutex
- gateway/processor.rs: description_generation_in_flight Mutex
- command/handler.rs + help.rs: metadata Mutex(公开 API)
- mcp/client.rs: stderr_lines Mutex

测试代码中的 std::sync::Mutex(串行化锁 + TestObserver)有意保留,
已通过 unwrap_or_else(|err| err.into_inner()) 做中毒恢复。

## P1: 阻塞 IO 迁移到 spawn_blocking
将 3 处阻塞 async worker 的操作迁移到 blocking 线程池:
- file_read.rs: read_to_string + 行处理 + base64 编码整体包入 spawn_blocking
- agent_loop.rs: 新增 preencode_images_for_request 两阶段预编码
  (顺序分配预算 → 并行 spawn_blocking 编码),build_llm_request 改为 async
- wechat.rs: media_to_send_content 改为 async,std::fs::read 用 spawn_blocking 包裹

## P2: session_history topic_histories 内存上限
新增 MAX_CACHED_TOPICS=32 上限和 evict_inactive_if_needed 方法。
超限时驱逐非活跃 topic(不在 chat_topic_ids、不在 compression_in_flight、
serial_lock 未被持有)。活跃 topic 永不误驱逐。
remove_history 同步清理 topic_serial_locks,防止无限增长。

## P3: 减少 panic 面
agent_loop.rs retry 循环的 response.expect(...) 改为 ok_or_else(...)?
返回 AgentError::Other,逻辑 bug 不再导致整个 agent 崩溃。

## 对抗性审查修复
- preencode_images_for_request: 用 seen HashSet 去重,防止同 path 重复
  编码导致 HashMap entry 覆盖(NoBudget 覆盖 Encoded 等)
- evict_inactive_if_needed: 检查 topic_serial_lock.try_lock(),防止驱逐
  正在 agent 处理中的 topic(original_topic_id 不在 chat_topic_ids 但
  agent 仍持锁)
- remove_history: 清理 topic_serial_locks

## 验证
- cargo check: 通过(仅既有 lifetime 警告)
- cargo test: 559 passed / 3 failed(均为环境/sandbox 权限问题,与本次改动无关)
2026-08-06 08:18:04 +08:00

191 lines
5.2 KiB
Rust

use std::collections::HashMap;
use std::sync::Arc;
use parking_lot::RwLock;
use crate::domain::tools::{Tool, ToolFunction};
use super::traits::Tool as ToolTrait;
pub struct ToolRegistry {
tools: RwLock<HashMap<String, Arc<dyn ToolTrait>>>,
}
impl ToolRegistry {
pub fn new() -> Self {
Self {
tools: RwLock::new(HashMap::new()),
}
}
pub fn register<T: ToolTrait + 'static>(&self, tool: T) {
self.tools
.write()
.insert(tool.name().to_string(), Arc::new(tool));
}
pub fn get(&self, name: &str) -> Option<Arc<dyn ToolTrait>> {
self.tools
.read()
.get(name)
.cloned()
}
/// Get all registered tools.
/// Used for concurrent tool execution when we need to look up tools by name.
pub fn get_all(&self) -> Vec<Arc<dyn ToolTrait>> {
self.tools
.read()
.values()
.cloned()
.collect()
}
pub fn get_definitions(&self) -> Vec<Tool> {
self.tools
.read()
.values()
.map(|tool| Tool {
tool_type: "function".to_string(),
function: ToolFunction {
name: tool.name().to_string(),
description: tool.description().to_string(),
parameters: tool.parameters_schema(),
},
})
.collect()
}
pub fn has_tools(&self) -> bool {
!self
.tools
.read()
.is_empty()
}
pub fn tool_names(&self) -> Vec<String> {
self.tools
.read()
.keys()
.cloned()
.collect()
}
/// 创建一个排除指定工具的新 registry 副本
pub fn without(&self, exclude: &[&str]) -> Self {
let exclude_set: std::collections::HashSet<&str> = exclude.iter().copied().collect();
let tools = self.tools.read();
let filtered: HashMap<String, Arc<dyn ToolTrait>> = tools
.iter()
.filter(|(name, _)| !exclude_set.contains(name.as_str()))
.map(|(k, v)| (k.clone(), v.clone()))
.collect();
let new_registry = ToolRegistry::new();
*new_registry
.tools
.write() = filtered;
new_registry
}
/// 创建一个仅包含指定工具的新 registry 副本(白名单)。
/// include 中不存在于当前 registry 的名称会被静默跳过(取交集语义)。
pub fn only(&self, include: &[&str]) -> Self {
let include_set: std::collections::HashSet<&str> = include.iter().copied().collect();
let tools = self.tools.read();
let filtered: HashMap<String, Arc<dyn ToolTrait>> = tools
.iter()
.filter(|(name, _)| include_set.contains(name.as_str()))
.map(|(k, v)| (k.clone(), v.clone()))
.collect();
let new_registry = ToolRegistry::new();
*new_registry
.tools
.write() = filtered;
new_registry
}
}
impl Default for ToolRegistry {
fn default() -> Self {
Self::new()
}
}
#[cfg(test)]
mod tests {
use super::*;
use crate::tools::traits::ToolResult;
use async_trait::async_trait;
/// 仅用于测试的占位工具,按构造名注册
struct FakeTool {
tool_name: String,
}
#[async_trait]
impl ToolTrait for FakeTool {
fn name(&self) -> &str {
&self.tool_name
}
fn description(&self) -> &str {
"fake"
}
fn parameters_schema(&self) -> serde_json::Value {
serde_json::json!({})
}
async fn execute(&self, _args: serde_json::Value) -> anyhow::Result<ToolResult> {
Ok(ToolResult {
success: true,
output: String::new(),
error: None,
})
}
}
fn registry_with(names: &[&str]) -> ToolRegistry {
let reg = ToolRegistry::new();
for n in names {
reg.register(FakeTool {
tool_name: n.to_string(),
});
}
reg
}
fn sorted_names(reg: &ToolRegistry) -> Vec<String> {
let mut v = reg.tool_names();
v.sort();
v
}
#[test]
fn only_keeps_listed_tools() {
let reg = registry_with(&["read", "edit", "write", "bash"]);
let filtered = reg.only(&["read", "bash"]);
assert_eq!(sorted_names(&filtered), vec!["bash", "read"]);
}
#[test]
fn only_silently_skips_missing_names() {
let reg = registry_with(&["read", "edit"]);
let filtered = reg.only(&["read", "nonexistent", "glob"]);
assert_eq!(sorted_names(&filtered), vec!["read"]);
}
#[test]
fn only_with_empty_include_returns_empty() {
let reg = registry_with(&["read", "edit"]);
let filtered = reg.only(&[]);
assert!(filtered.tool_names().is_empty());
}
#[test]
fn only_does_not_mutate_source() {
let reg = registry_with(&["read", "edit", "write"]);
let _ = reg.only(&["read"]);
// 源 registry 不受影响
let mut v = reg.tool_names();
v.sort();
assert_eq!(v, vec!["edit", "read", "write"]);
}
}