feat(pi-web-search): 统一 web_search/web_fetch 并由主模型路由搜索厂商

7 个按厂商命名的搜索工具收敛为 2 个统一工具，schema 与提示词不再暴露
provider 概念：web_search 由当前主模型按内置规则在 Tavily/Exa/Keenable
间路由（会话内 LRU 缓存，失败按可用性降级），web_fetch 固定走 Exa 并
静默降级。三家均改为纯 fetch 直连——Exa 直接对 mcp.exa.ai 发 JSON-RPC
并缓存会话，彻底移除 pi-mcp-adapter、@tavily/pi-extension 与
@keenable/pi-search 依赖。

Generated with [Devin](https://devin.ai)

Co-Authored-By: Devin <158243242+devin-ai-integration[bot]@users.noreply.github.com>

pi-web-search/package.json

@@ -0,0 +1,42 @@
+{
+	"name": "pi-web-search",
+	"version": "0.1.0",
+	"description": "Unified web search and fetch tools with main-model provider routing (Tavily, Exa, Keenable).",
+	"private": true,
+	"type": "module",
+	"license": "MIT",
+	"main": "./index.ts",
+	"exports": {
+		".": "./index.ts"
+	},
+	"files": [
+		"index.ts",
+		"router.ts",
+		"clients",
+		"README.md",
+		"LICENSE"
+	],
+	"pi": {
+		"extensions": [
+			"./index.ts"
+		]
+	},
+	"scripts": {
+		"test": "node --test test/*.test.ts"
+	},
+	"peerDependencies": {
+		"@earendil-works/pi-coding-agent": "*",
+		"typebox": "*"
+	},
+	"peerDependenciesMeta": {
+		"@earendil-works/pi-coding-agent": {
+			"optional": true
+		},
+		"typebox": {
+			"optional": true
+		}
+	},
+	"engines": {
+		"node": ">=22.19.0"
+	}
+}