fix: 主线 B3/B4 结构化工具调用与完成前验证

- 打通 Worker → WorkerManager → Provider 的 tools 传递链路，ProviderManager/adapter
  返回结构化 tool_calls 给 WorkerRuntime
- OpenAI-compatible/Anthropic adapter 发送工具 schema，并解析 provider 返回的
  tool_calls/tool_use；OpenAI 工具名使用 fs.write ↔ fs__write 双向映射
- 修复独立复审发现的 OpenAI 协议隐患：assistant tool_use blocks 必须转换为
  assistant.tool_calls，后续 role=tool 消息的 tool_call_id 必须匹配前一轮
  tool_calls[].id；不再把 tool_use JSON 字符串化为普通文本
- ExecutorRole 优先消费原生 tool_calls，回灌 canonical tool_result block；移除
  fs.write(...)/shell.run(...) 函数调用正则解析，只保留严格 JSON tool_call
  fallback 与 filename code block 兼容
- DONE 前执行 verification-before-completion：任务要求 build/compile/run/test/编译/
  运行/测试时必须实际 shell.run 验证，失败不 checkpoint、不返回 completed
- fs.write 覆盖已有文件也强制 read-before-write，补齐 Claude Code 文件状态纪律
- 新增 packages/workers/test/executor-role.test.ts 行为测试：原生 tool_calls 执行、
  verification 失败不得 completed

真实验收:
- TSC=0
- bun test packages/workers/test/executor-role.test.ts: 2 pass / 0 fail
- OpenAI converter 探针确认 assistant.tool_calls 与 role=tool 的 tool_call_id 匹配
- 真实 GLM Worker C++ 编译运行任务通过，worker verification 记录实际命令:
  c++ hello.cpp -o /tmp/aircoding-verify && /tmp/aircoding-verify

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

packages/runtime/src/workers/WorkerManager.ts

@@ -219,13 +219,15 @@ export class WorkerManager {
         const response = await this.provider_manager.complete_text(messages, {
           model: msg.payload.model as string,
           max_tokens: msg.payload.max_tokens as number,
-          temperature: msg.payload.temperature as number
+          temperature: msg.payload.temperature as number,
+          tools: (msg.payload.tools as unknown[]) || this.tool_registry?.list?.() || []
         })
 
         this.send_to_worker(agent_id, 'llm.response', {
           call_id,
           content: response.content,
-          usage: response.usage
+          usage: response.usage,
+          tool_calls: response.tool_calls
         })
       } catch (e: any) {
         this.send_to_worker(agent_id, 'llm.response', {