refactor: 统一自建 Tool Search — 移除 tool_reference/defer_loading 依赖，全 provider 通用

- 重命名 ExecuteTool → ExecuteExtraTool，作为一等工具始终可用
- ToolSearchTool 输出改为纯文本（区分 core/deferred），移除 tool_reference blocks
- 移除 modelSupportsToolReference() 及相关 GrowthBook 配置
- 移除 API 侧 defer_loading 字段和 tool search beta header 注入
- 简化 system prompt（工具使用指南从 ~120 行压缩到 ~10 行）
- extractDiscoveredToolNames 支持文本格式解析（向后兼容旧 session 的 tool_reference）
- 更新 promptEngineeringAudit 测试以匹配简化后的 prompt 结构

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

src/utils/attachments.ts

@@ -168,7 +168,6 @@ import {
   isDeferredToolsDeltaEnabled,
   isToolSearchEnabledOptimistic,
   isToolSearchToolAvailable,
-  modelSupportsToolReference,
   type DeferredToolsDeltaScanContext,
 } from './toolSearch.js'
 import {
@@ -1522,7 +1521,6 @@ export function getDeferredToolsDeltaAttachment(
   // is filtered out, but that's a narrow case and the tools announced
   // are directly callable anyway.
   if (!isToolSearchEnabledOptimistic()) return []
-  if (!modelSupportsToolReference(model)) return []
   if (!isToolSearchToolAvailable(tools)) return []
   const delta = getDeferredToolsDelta(tools, messages ?? [], scanContext)
   if (!delta) return []
@@ -1624,11 +1622,7 @@ export function getMcpInstructionsDeltaAttachment(
   // actual server `instructions` are unconditional. Decide the chrome part
   // here, pass it into the pure diff as a synthesized entry.
   const clientSide: ClientSideInstruction[] = []
-  if (
-    isToolSearchEnabledOptimistic() &&
-    modelSupportsToolReference(model) &&
-    isToolSearchToolAvailable(tools)
-  ) {
+  if (isToolSearchEnabledOptimistic() && isToolSearchToolAvailable(tools)) {
     clientSide.push({
       serverName: CLAUDE_IN_CHROME_MCP_SERVER_NAME,
       block: CHROME_TOOL_SEARCH_INSTRUCTIONS,