feat: 工具层及 mcp 大重构 (#252)

* feat: 第一版大重构

* fix: 修复类型问题

* chore: 更新版本到 1.3.2

* Add brave as alternative WebSearchTool

* fix: 修正顺序

* fix: 修复对穷鬼模式的 auto dream 和 session memory 越过

* feat: 穷鬼模式去除 session-summary

* feat: 创建 builtin-tools 包,搬运所有工具实现

将 src/tools/ 下的全部 60 个工具目录迁移至 packages/builtin-tools/src/tools/,
内部导入路径已更新为 src/ alias 模式。

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* refactor: 更新 src/ 中所有工具引用至 builtin-tools 包,删除 src/tools/

- src/tools.ts 及 178 个 src/ 文件的 import 路径从 ./tools/ 改为 builtin-tools/tools/
- 删除 src/tools/ 整个目录(已迁移至 packages/builtin-tools/)

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* chore: 添加 builtin-tools 路径别名至 tsconfig,更新 bun.lock

- tsconfig.json 新增 builtin-tools/* 和 builtin-tools 路径映射
- 新增 packages/builtin-tools/src 至 include

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* refactor: 为 builtin-tools、mcp-client、agent-tools 添加 @claude-code-best 作用域前缀

所有包名及 import 路径统一添加 @claude-code-best/ 前缀:
- builtin-tools → @claude-code-best/builtin-tools
- mcp-client → @claude-code-best/mcp-client
- agent-tools → @claude-code-best/agent-tools

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* fix: 修复 node 环境没有 bun 的问题

---------

Co-authored-by: Eric-Guo <eric.guocz@gmail.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
claude-code-best
2026-04-13 09:52:05 +08:00
committed by GitHub
parent bbb8b613a9
commit 2fb1c9dcd8
559 changed files with 9346 additions and 1837 deletions

View File

@@ -0,0 +1,127 @@
import React from 'react'
import { MessageResponse } from 'src/components/MessageResponse.js'
import { TOOL_SUMMARY_MAX_LENGTH } from 'src/constants/toolLimits.js'
import { Box, Text } from '@anthropic/ink'
import type { ProgressMessage } from 'src/types/message.js'
import { truncate } from 'src/utils/format.js'
import type {
Output,
SearchResult,
WebSearchProgress,
} from './WebSearchTool.js'
function getSearchSummary(
results: (SearchResult | string | null | undefined)[],
): {
searchCount: number
totalResultCount: number
} {
let searchCount = 0
let totalResultCount = 0
for (const result of results) {
if (result != null && typeof result !== 'string') {
searchCount++
totalResultCount += result.content?.length ?? 0
}
}
return { searchCount, totalResultCount }
}
export function renderToolUseMessage(
{
query,
allowed_domains,
blocked_domains,
}: Partial<{
query: string
allowed_domains?: string[]
blocked_domains?: string[]
}>,
{ verbose }: { verbose: boolean },
): React.ReactNode {
if (!query) {
return null
}
let message = ''
if (query) {
message += `"${query}"`
}
if (verbose) {
if (allowed_domains && allowed_domains.length > 0) {
message += `, only allowing domains: ${allowed_domains.join(', ')}`
}
if (blocked_domains && blocked_domains.length > 0) {
message += `, blocking domains: ${blocked_domains.join(', ')}`
}
}
return message
}
export function renderToolUseProgressMessage(
progressMessages: ProgressMessage<WebSearchProgress>[],
): React.ReactNode {
if (progressMessages.length === 0) {
return null
}
const lastProgress = progressMessages[progressMessages.length - 1]
if (!lastProgress?.data) {
return null
}
const data = lastProgress.data
switch (data.type) {
case 'query_update':
return (
<MessageResponse>
<Text dimColor>Searching: {data.query}</Text>
</MessageResponse>
)
case 'search_results_received':
return (
<MessageResponse>
<Text dimColor>
Found {data.resultCount} results for &quot;{data.query}&quot;
</Text>
</MessageResponse>
)
default:
return null
}
}
export function renderToolResultMessage(output: Output): React.ReactNode {
const { searchCount } = getSearchSummary(output.results ?? [])
const timeDisplay =
output.durationSeconds >= 1
? `${Math.round(output.durationSeconds)}s`
: `${Math.round(output.durationSeconds * 1000)}ms`
return (
<Box justifyContent="space-between" width="100%">
<MessageResponse height={1}>
<Text>
Did {searchCount} search
{searchCount !== 1 ? 'es' : ''} in {timeDisplay}
</Text>
</MessageResponse>
</Box>
)
}
export function getToolUseSummary(
input: Partial<{ query: string }> | undefined,
): string | null {
if (!input?.query) {
return null
}
return truncate(input.query, TOOL_SUMMARY_MAX_LENGTH)
}

View File

@@ -0,0 +1,221 @@
import type { PermissionResult } from 'src/utils/permissions/PermissionResult.js'
import { z } from 'zod/v4'
import { buildTool, type ToolDef } from 'src/Tool.js'
import { lazySchema } from 'src/utils/lazySchema.js'
import { jsonStringify } from 'src/utils/slowOperations.js'
import { createAdapter } from './adapters/index.js'
import { getWebSearchPrompt, WEB_SEARCH_TOOL_NAME } from './prompt.js'
import {
getToolUseSummary,
renderToolResultMessage,
renderToolUseMessage,
renderToolUseProgressMessage,
} from './UI.js'
const inputSchema = lazySchema(() =>
z.strictObject({
query: z.string().min(2).describe('The search query to use'),
allowed_domains: z
.array(z.string())
.optional()
.describe('Only include search results from these domains'),
blocked_domains: z
.array(z.string())
.optional()
.describe('Never include search results from these domains'),
}),
)
type InputSchema = ReturnType<typeof inputSchema>
const searchResultSchema = lazySchema(() => {
const searchHitSchema = z.object({
title: z.string().describe('The title of the search result'),
url: z.string().describe('The URL of the search result'),
snippet: z.string().optional().describe('A short description of the search result'),
})
return z.object({
tool_use_id: z.string().describe('ID of the tool use'),
content: z.array(searchHitSchema).describe('Array of search hits'),
})
})
export type SearchResult = z.infer<ReturnType<typeof searchResultSchema>>
const outputSchema = lazySchema(() =>
z.object({
query: z.string().describe('The search query that was executed'),
results: z
.array(z.union([searchResultSchema(), z.string()]))
.describe('Search results and/or text commentary from the model'),
durationSeconds: z
.number()
.describe('Time taken to complete the search operation'),
}),
)
type OutputSchema = ReturnType<typeof outputSchema>
export type Output = z.infer<OutputSchema>
// Re-export WebSearchProgress from centralized types to break import cycles
export type { WebSearchProgress } from 'src/types/tools.js'
import type { WebSearchProgress } from 'src/types/tools.js'
export const WebSearchTool = buildTool({
name: WEB_SEARCH_TOOL_NAME,
searchHint: 'search the web for current information',
maxResultSizeChars: 100_000,
shouldDefer: true,
async description(input) {
return `Claude wants to search the web for: ${input.query}`
},
userFacingName() {
return 'Web Search'
},
getToolUseSummary,
getActivityDescription(input) {
const summary = getToolUseSummary(input)
return summary ? `Searching for ${summary}` : 'Searching the web'
},
isEnabled() {
// Always enabled — the adapter factory selects the appropriate backend
// (API server-side search or Bing fallback) based on provider capabilities.
return true
},
get inputSchema(): InputSchema {
return inputSchema()
},
get outputSchema(): OutputSchema {
return outputSchema()
},
isConcurrencySafe() {
return true
},
isReadOnly() {
return true
},
toAutoClassifierInput(input) {
return input.query
},
async checkPermissions(_input): Promise<PermissionResult> {
return {
behavior: 'passthrough',
message: 'WebSearchTool requires permission.',
suggestions: [
{
type: 'addRules',
rules: [{ toolName: WEB_SEARCH_TOOL_NAME }],
behavior: 'allow',
destination: 'localSettings',
},
],
}
},
async prompt() {
return getWebSearchPrompt()
},
renderToolUseMessage,
renderToolUseProgressMessage,
renderToolResultMessage,
extractSearchText() {
return ''
},
async validateInput(input) {
const { query, allowed_domains, blocked_domains } = input
if (!query.length) {
return {
result: false,
message: 'Error: Missing query',
errorCode: 1,
}
}
if (allowed_domains?.length && blocked_domains?.length) {
return {
result: false,
message:
'Error: Cannot specify both allowed_domains and blocked_domains in the same request',
errorCode: 2,
}
}
return { result: true }
},
async call(input, context, _canUseTool, _parentMessage, onProgress) {
const startTime = performance.now()
const { query } = input
const adapter = createAdapter()
const adapterResults = await adapter.search(query, {
allowedDomains: input.allowed_domains,
blockedDomains: input.blocked_domains,
signal: context.abortController.signal,
onProgress(progress) {
if (onProgress) {
const progressCounter = Date.now()
onProgress({
toolUseID: `search-progress-${progressCounter}`,
data: progress,
})
}
},
})
const endTime = performance.now()
const durationSeconds = (endTime - startTime) / 1000
// Convert adapter SearchResult[] to legacy Output format
const results: (SearchResult | string)[] = []
if (adapterResults.length > 0) {
results.push({
tool_use_id: 'adapter-search-1',
content: adapterResults.map(r => ({ title: r.title, url: r.url, snippet: r.snippet })),
})
} else {
results.push('No search results found.')
}
const data: Output = {
query,
results,
durationSeconds,
}
return { data }
},
mapToolResultToToolResultBlockParam(output, toolUseID) {
const { query, results } = output
let formattedOutput = `Web search results for query: "${query}"\n\n`
;(results ?? []).forEach(result => {
if (result == null) {
return
}
if (typeof result === 'string') {
formattedOutput += result + '\n\n'
} else {
if (result.content?.length > 0) {
formattedOutput += 'Links:\n'
for (const link of result.content) {
formattedOutput += ` - [${link.title}](${link.url})`
if (link.snippet) {
formattedOutput += `: ${link.snippet}`
}
formattedOutput += '\n'
}
formattedOutput += '\n'
} else {
formattedOutput += 'No links found.\n\n'
}
}
})
formattedOutput +=
'\nREMINDER: You MUST include the sources above in your response to the user using markdown hyperlinks.'
return {
tool_use_id: toolUseID,
type: 'tool_result',
content: formattedOutput.trim(),
}
},
} satisfies ToolDef<InputSchema, Output, WebSearchProgress>)

View File

@@ -0,0 +1,59 @@
import { afterEach, describe, expect, mock, test } from 'bun:test'
let isFirstPartyBaseUrl = true
// Only mock the external dependency that controls adapter selection
mock.module('src/utils/model/providers.js', () => ({
isFirstPartyAnthropicBaseUrl: () => isFirstPartyBaseUrl,
}))
const { createAdapter } = await import('../adapters/index')
const originalWebSearchAdapter = process.env.WEB_SEARCH_ADAPTER
afterEach(() => {
isFirstPartyBaseUrl = true
if (originalWebSearchAdapter === undefined) {
delete process.env.WEB_SEARCH_ADAPTER
} else {
process.env.WEB_SEARCH_ADAPTER = originalWebSearchAdapter
}
})
describe('createAdapter', () => {
test('reuses the same instance when the selected backend does not change', () => {
process.env.WEB_SEARCH_ADAPTER = 'brave'
const firstAdapter = createAdapter()
const secondAdapter = createAdapter()
expect(firstAdapter).toBe(secondAdapter)
expect(firstAdapter.constructor.name).toBe('BraveSearchAdapter')
})
test('rebuilds the adapter when WEB_SEARCH_ADAPTER changes', () => {
process.env.WEB_SEARCH_ADAPTER = 'brave'
const braveAdapter = createAdapter()
process.env.WEB_SEARCH_ADAPTER = 'bing'
const bingAdapter = createAdapter()
expect(bingAdapter).not.toBe(braveAdapter)
expect(bingAdapter.constructor.name).toBe('BingSearchAdapter')
})
test('selects the API adapter for first-party Anthropic URLs', () => {
delete process.env.WEB_SEARCH_ADAPTER
isFirstPartyBaseUrl = true
expect(createAdapter().constructor.name).toBe('ApiSearchAdapter')
})
test('selects the Bing adapter for third-party Anthropic base URLs', () => {
delete process.env.WEB_SEARCH_ADAPTER
isFirstPartyBaseUrl = false
expect(createAdapter().constructor.name).toBe('BingSearchAdapter')
})
})

View File

@@ -0,0 +1,82 @@
/**
* Integration test for BingSearchAdapter — hits the real Bing search.
*
* Usage:
* bun run src/tools/WebSearchTool/__tests__/bingAdapter.integration.ts
*
* Optional env vars:
* BING_QUERY — search query (default: "Claude AI Anthropic")
*/
// Provide MACRO globals needed by the codebase when running outside dev mode
if (!globalThis.MACRO) {
globalThis.MACRO = { VERSION: '0.0.0-test', BUILD_TIME: '0' } as any
}
import { BingSearchAdapter, extractBingResults } from '../adapters/bingAdapter'
const query = process.env.BING_QUERY || 'Claude AI Anthropic'
async function main() {
console.log(`\n🔍 Searching Bing for: "${query}"\n`)
const adapter = new BingSearchAdapter()
const startTime = Date.now()
const results = await adapter.search(query, {
onProgress: (p) => {
if (p.type === 'query_update') {
console.log(` → Query sent: ${p.query}`)
}
if (p.type === 'search_results_received') {
console.log(` → Received ${p.resultCount} results`)
}
},
})
const elapsed = Date.now() - startTime
console.log(`\n✅ Done in ${elapsed}ms — ${results.length} result(s)\n`)
if (results.length === 0) {
console.log('⚠️ No results returned. Possible causes:')
console.log(' - Bing returned a CAPTCHA or rate-limited the request')
console.log(' - Network/firewall issue')
console.log(' - Bing HTML structure changed')
console.log(' - Anti-bot detection triggered\n')
process.exit(1)
}
for (const [i, r] of results.entries()) {
console.log(` ${i + 1}. ${r.title}`)
console.log(` ${r.url}`)
if (r.snippet) {
const snippet = r.snippet.replace(/\n/g, ' ')
console.log(` ${snippet.slice(0, 150)}${snippet.length > 150 ? '…' : ''}`)
}
console.log()
}
// Validate result structure
let passed = true
for (const [i, r] of results.entries()) {
if (!r.title || typeof r.title !== 'string') {
console.error(`❌ Result ${i + 1}: missing or non-string title`, r)
passed = false
}
if (!r.url || !r.url.startsWith('http')) {
console.error(`❌ Result ${i + 1}: missing or non-http url`, r)
passed = false
}
}
if (passed) {
console.log('✅ All results have valid structure.\n')
} else {
process.exit(1)
}
}
main().catch((e) => {
console.error('❌ Fatal error:', e)
process.exit(1)
})

View File

@@ -0,0 +1,499 @@
import { describe, expect, mock, test } from 'bun:test'
import { extractBingResults, decodeHtmlEntities } from '../adapters/bingAdapter'
// ---------------------------------------------------------------------------
// decodeHtmlEntities
// ---------------------------------------------------------------------------
describe('decodeHtmlEntities', () => {
test('decodes common named entities', () => {
expect(decodeHtmlEntities('&amp; &lt; &gt;')).toBe('& < >')
})
test('decodes quote entities', () => {
expect(decodeHtmlEntities('&quot;hello&quot;')).toBe('"hello"')
})
test('decodes numeric and hex apostrophe entities', () => {
expect(decodeHtmlEntities('&#39;it&#x27;s')).toBe("'it's")
})
test('decodes &nbsp; to non-breaking space (\\u00A0)', () => {
expect(decodeHtmlEntities('a&nbsp;b')).toBe('a\u00A0b')
})
test('returns plain text unchanged', () => {
expect(decodeHtmlEntities('hello world')).toBe('hello world')
})
test('handles empty string', () => {
expect(decodeHtmlEntities('')).toBe('')
})
test('decodes multiple occurrences of the same entity', () => {
expect(decodeHtmlEntities('a&amp;b&amp;c')).toBe('a&b&c')
})
test('handles mixed entities in one string', () => {
expect(decodeHtmlEntities('&lt;a&nbsp;href=&quot;x&quot;&gt;')).toBe('<a\u00A0href="x">')
})
})
// ---------------------------------------------------------------------------
// extractBingResults
// ---------------------------------------------------------------------------
describe('extractBingResults', () => {
test('extracts results from standard Bing HTML', () => {
const html = `
<ol id="b_results">
<li class="b_algo">
<h2><a href="https://example.com/page1" h="ID=SERP,1">Example Title 1</a></h2>
<div class="b_caption">
<p class="b_lineclamp">First result description</p>
</div>
</li>
<li class="b_algo">
<h2><a href="https://example.com/page2" h="ID=SERP,2">Example Title 2</a></h2>
<div class="b_caption">
<p class="b_lineclamp">Second result description</p>
</div>
</li>
</ol>
`
const results = extractBingResults(html)
expect(results).toHaveLength(2)
expect(results[0]).toEqual({
title: 'Example Title 1',
url: 'https://example.com/page1',
snippet: 'First result description',
})
expect(results[1]).toEqual({
title: 'Example Title 2',
url: 'https://example.com/page2',
snippet: 'Second result description',
})
})
test('returns empty array when no b_algo blocks exist', () => {
const html = `
<ol id="b_results">
<li class="b_ad">Ad result</li>
<li class="b_ans">Answer card</li>
</ol>
`
expect(extractBingResults(html)).toEqual([])
})
test('returns empty array for empty HTML', () => {
expect(extractBingResults('')).toEqual([])
})
test('returns empty array for unrelated HTML', () => {
expect(extractBingResults('<html><body>Hello</body></html>')).toEqual([])
})
test('skips Bing-internal links', () => {
const html = `
<li class="b_algo">
<h2><a href="/search?q=more">More results</a></h2>
</li>
<li class="b_algo">
<h2><a href="https://www.bing.com/videos">Bing Videos</a></h2>
</li>
<li class="b_algo">
<h2><a href="#anchor">Jump link</a></h2>
</li>
`
expect(extractBingResults(html)).toEqual([])
})
test('strips HTML tags from titles', () => {
const html = `
<li class="b_algo">
<h2><a href="https://example.com">Result with <strong>bold</strong> and <em>italic</em></a></h2>
</li>
`
const results = extractBingResults(html)
expect(results).toHaveLength(1)
expect(results[0].title).toBe('Result with bold and italic')
})
test('decodes HTML entities in titles', () => {
const html = `
<li class="b_algo">
<h2><a href="https://example.com">Tom &amp; Jerry &lt;cartoon&gt;</a></h2>
</li>
`
const results = extractBingResults(html)
expect(results[0].title).toBe('Tom & Jerry <cartoon>')
})
test('extracts snippet from b_lineclamp class', () => {
const html = `
<li class="b_algo">
<h2><a href="https://example.com">Title</a></h2>
<p class="b_lineclamp3 b_algo_slug">Lineclamp snippet text here</p>
</li>
`
const results = extractBingResults(html)
expect(results[0].snippet).toBe('Lineclamp snippet text here')
})
test('extracts snippet from b_caption paragraph fallback', () => {
const html = `
<li class="b_algo">
<h2><a href="https://example.com">Title</a></h2>
<div class="b_caption">
<p>Caption paragraph text</p>
</div>
</li>
`
const results = extractBingResults(html)
expect(results[0].snippet).toBe('Caption paragraph text')
})
test('extracts snippet from b_caption div fallback', () => {
const html = `
<li class="b_algo">
<h2><a href="https://example.com">Title</a></h2>
<div class="b_caption">Direct caption text without p tag</div>
</li>
`
const results = extractBingResults(html)
expect(results[0].snippet).toBe('Direct caption text without p tag')
})
test('returns undefined snippet when no caption exists', () => {
const html = `
<li class="b_algo">
<h2><a href="https://example.com">Title Only</a></h2>
</li>
`
const results = extractBingResults(html)
expect(results[0].snippet).toBeUndefined()
})
test('handles mixed result types and only extracts b_algo', () => {
const html = `
<ol id="b_results">
<li class="b_ad"><h2><a href="https://ad.com">Ad Title</a></h2></li>
<li class="b_algo">
<h2><a href="https://real-result.com">Real Result</a></h2>
<p class="b_lineclamp">A real snippet</p>
</li>
<li class="b_ans"><div>People also ask</div></li>
<li class="b_algo">
<h2><a href="https://another.com">Another Result</a></h2>
</li>
</ol>
`
const results = extractBingResults(html)
expect(results).toHaveLength(2)
expect(results[0].title).toBe('Real Result')
expect(results[1].title).toBe('Another Result')
})
test('skips b_algo blocks without h2 > a structure', () => {
const html = `
<li class="b_algo">
<div>No link here</div>
</li>
<li class="b_algo">
<h2><a href="https://example.com">Valid Result</a></h2>
</li>
`
const results = extractBingResults(html)
expect(results).toHaveLength(1)
expect(results[0].title).toBe('Valid Result')
})
test('handles extra whitespace in h2 > a structure', () => {
const html = `
<li class="b_algo">
<h2>
<a href="https://example.com" h="ID=SERP,1" >
Whitespace Title
</a>
</h2>
</li>
`
const results = extractBingResults(html)
expect(results).toHaveLength(1)
expect(results[0].title).toBe('Whitespace Title')
})
test('handles snippet with HTML entities', () => {
const html = `
<li class="b_algo">
<h2><a href="https://example.com">Title</a></h2>
<p class="b_lineclamp">5 &lt; 10 &amp; 10 &gt; 5</p>
</li>
`
const results = extractBingResults(html)
expect(results[0].snippet).toBe('5 < 10 & 10 > 5')
})
test('handles real-world Bing HTML structure', () => {
const html = `
<ol id="b_results" role="main">
<li class="b_algo" data-id="">
<div class="b_title">
<h2>
<a href="https://docs.python.org/3/tutorial/index.html" target="_blank" h="ID=SERP,5125.1">
Python Tutorial
</a>
</h2>
</div>
<div class="b_caption">
<div class="b_attribution" u="0|5125|4976674477245">
<cite>https://docs.python.org</cite>
</div>
<p class="b_lineclamp3">
Welcome to the Python Tutorial. This tutorial introduces you to the basic concepts and features...
</p>
</div>
</li>
<li class="b_algo">
<h2>
<a href="https://realpython.com/python-guide/" h="ID=SERP,5125.2">
Real Python Guide
</a>
</h2>
<div class="b_caption">
<div class="b_attribution">
<cite>https://realpython.com</cite>
</div>
<p>
The ultimate Python guide for beginners and experts alike.
</p>
</div>
</li>
</ol>
`
const results = extractBingResults(html)
expect(results).toHaveLength(2)
expect(results[0].title).toBe('Python Tutorial')
expect(results[0].url).toBe('https://docs.python.org/3/tutorial/index.html')
expect(results[0].snippet).toContain('Welcome to the Python Tutorial')
expect(results[1].title).toBe('Real Python Guide')
expect(results[1].snippet).toContain('ultimate Python guide')
})
})
// ---------------------------------------------------------------------------
// BingSearchAdapter.search (integration with mocked axios)
// ---------------------------------------------------------------------------
describe('BingSearchAdapter.search', () => {
// Dynamic import so mock.module() takes effect
const createAdapter = async () => {
const { BingSearchAdapter } = await import('../adapters/bingAdapter')
return new BingSearchAdapter()
}
const SAMPLE_HTML = `
<ol id="b_results">
<li class="b_algo">
<h2><a href="https://example.com/result1">Result One</a></h2>
<p class="b_lineclamp">Snippet one</p>
</li>
<li class="b_algo">
<h2><a href="https://example.com/result2">Result Two</a></h2>
<p class="b_lineclamp">Snippet two</p>
</li>
</ol>
`
test('returns parsed results from fetched HTML', async () => {
mock.module('axios', () => ({
default: {
get: mock(() => Promise.resolve({ data: SAMPLE_HTML })),
isCancel: () => false,
},
}))
mock.module('src/utils/http', () => ({
getWebFetchUserAgent: () => 'TestAgent/1.0',
}))
const adapter = await createAdapter()
const results = await adapter.search('test query', {})
expect(results).toHaveLength(2)
expect(results[0].title).toBe('Result One')
expect(results[1].title).toBe('Result Two')
})
test('calls onProgress with query_update and search_results_received', async () => {
mock.module('axios', () => ({
default: {
get: mock(() => Promise.resolve({ data: SAMPLE_HTML })),
isCancel: () => false,
},
}))
mock.module('src/utils/http', () => ({
getWebFetchUserAgent: () => 'TestAgent/1.0',
}))
const progressCalls: any[] = []
const onProgress = (p: any) => progressCalls.push(p)
const adapter = await createAdapter()
await adapter.search('test', { onProgress })
expect(progressCalls).toHaveLength(2)
expect(progressCalls[0].type).toBe('query_update')
expect(progressCalls[0].query).toBe('test')
expect(progressCalls[1].type).toBe('search_results_received')
expect(progressCalls[1].resultCount).toBe(2)
})
test('filters results by allowedDomains', async () => {
const mixedHtml = `
<ol id="b_results">
<li class="b_algo">
<h2><a href="https://allowed.com/a">Allowed Result</a></h2>
</li>
<li class="b_algo">
<h2><a href="https://blocked.com/b">Blocked Result</a></h2>
</li>
</ol>
`
mock.module('axios', () => ({
default: {
get: mock(() => Promise.resolve({ data: mixedHtml })),
isCancel: () => false,
},
}))
mock.module('src/utils/http', () => ({
getWebFetchUserAgent: () => 'TestAgent/1.0',
}))
const adapter = await createAdapter()
const results = await adapter.search('test', {
allowedDomains: ['allowed.com'],
})
expect(results).toHaveLength(1)
expect(results[0].url).toBe('https://allowed.com/a')
})
test('filters results by blockedDomains', async () => {
const mixedHtml = `
<ol id="b_results">
<li class="b_algo">
<h2><a href="https://good.com/a">Good Result</a></h2>
</li>
<li class="b_algo">
<h2><a href="https://spam.com/b">Spam Result</a></h2>
</li>
</ol>
`
mock.module('axios', () => ({
default: {
get: mock(() => Promise.resolve({ data: mixedHtml })),
isCancel: () => false,
},
}))
mock.module('src/utils/http', () => ({
getWebFetchUserAgent: () => 'TestAgent/1.0',
}))
const adapter = await createAdapter()
const results = await adapter.search('test', {
blockedDomains: ['spam.com'],
})
expect(results).toHaveLength(1)
expect(results[0].url).toBe('https://good.com/a')
})
test('filters subdomains with allowedDomains', async () => {
const html = `
<ol id="b_results">
<li class="b_algo">
<h2><a href="https://docs.example.com/page">Subdomain Result</a></h2>
</li>
<li class="b_algo">
<h2><a href="https://other.com/page">Other Result</a></h2>
</li>
</ol>
`
mock.module('axios', () => ({
default: {
get: mock(() => Promise.resolve({ data: html })),
isCancel: () => false,
},
}))
mock.module('src/utils/http', () => ({
getWebFetchUserAgent: () => 'TestAgent/1.0',
}))
const adapter = await createAdapter()
const results = await adapter.search('test', {
allowedDomains: ['example.com'],
})
expect(results).toHaveLength(1)
expect(results[0].url).toBe('https://docs.example.com/page')
})
test('throws AbortError when signal is already aborted', async () => {
mock.module('axios', () => ({
default: {
get: mock((_url: string, config: any) => {
if (config?.signal?.aborted) {
const err = new Error('canceled')
;(err as any).__CANCEL__ = true
return Promise.reject(err)
}
return Promise.resolve({ data: SAMPLE_HTML })
}),
isCancel: (e: any) => e?.__CANCEL__ === true,
},
}))
mock.module('src/utils/http', () => ({
getWebFetchUserAgent: () => 'TestAgent/1.0',
}))
const adapter = await createAdapter()
const controller = new AbortController()
controller.abort()
const { AbortError } = await import('src/utils/errors')
await expect(
adapter.search('test', { signal: controller.signal }),
).rejects.toThrow(AbortError)
})
test('re-throws non-abort axios errors', async () => {
const networkError = new Error('Network error')
mock.module('axios', () => ({
default: {
get: mock(() => Promise.reject(networkError)),
isCancel: () => false,
},
}))
mock.module('src/utils/http', () => ({
getWebFetchUserAgent: () => 'TestAgent/1.0',
}))
const adapter = await createAdapter()
await expect(adapter.search('test', {})).rejects.toThrow('Network error')
})
test('encodes query parameter in URL', async () => {
const axiosGet = mock(() => Promise.resolve({ data: SAMPLE_HTML }))
mock.module('axios', () => ({
default: {
get: axiosGet,
isCancel: () => false,
},
}))
mock.module('src/utils/http', () => ({
getWebFetchUserAgent: () => 'TestAgent/1.0',
}))
const adapter = await createAdapter()
await adapter.search('hello world & special=chars', {})
const calledUrl = (axiosGet.mock.calls as string[][])[0][0]
expect(calledUrl).toContain('q=hello%20world%20%26%20special%3Dchars')
})
})

View File

@@ -0,0 +1,106 @@
import { describe, expect, test } from 'bun:test'
import { extractBraveResults } from '../adapters/braveAdapter'
describe('extractBraveResults', () => {
test('extracts generic grounding results', () => {
const results = extractBraveResults({
grounding: {
generic: [
{
title: 'Example Title 1',
url: 'https://example.com/page1',
snippets: ['First result description'],
},
{
title: 'Example Title 2',
url: 'https://example.com/page2',
snippets: ['Second result description'],
},
],
},
})
expect(results).toEqual([
{
title: 'Example Title 1',
url: 'https://example.com/page1',
snippet: 'First result description',
},
{
title: 'Example Title 2',
url: 'https://example.com/page2',
snippet: 'Second result description',
},
])
})
test('combines generic, poi, and map grounding results', () => {
const results = extractBraveResults({
grounding: {
generic: [{ title: 'Generic', url: 'https://example.com/generic' }],
poi: { title: 'POI', url: 'https://maps.example.com/poi' },
map: [{ title: 'Map', url: 'https://maps.example.com/map' }],
},
})
expect(results).toEqual([
{ title: 'Generic', url: 'https://example.com/generic', snippet: undefined },
{ title: 'POI', url: 'https://maps.example.com/poi', snippet: undefined },
{ title: 'Map', url: 'https://maps.example.com/map', snippet: undefined },
])
})
test('joins multiple snippets into one summary string', () => {
const results = extractBraveResults({
grounding: {
generic: [
{
title: 'Joined Snippets',
url: 'https://example.com/joined',
snippets: ['First snippet.', 'Second snippet.'],
},
],
},
})
expect(results[0].snippet).toBe('First snippet. Second snippet.')
})
test('skips entries without a title or URL', () => {
const results = extractBraveResults({
grounding: {
generic: [
{ title: 'Missing URL' },
{ url: 'https://example.com/missing-title' },
{ title: 'Valid', url: 'https://example.com/valid' },
],
},
})
expect(results).toEqual([
{ title: 'Valid', url: 'https://example.com/valid', snippet: undefined },
])
})
test('deduplicates repeated URLs across grounding buckets', () => {
const results = extractBraveResults({
grounding: {
generic: [{ title: 'First', url: 'https://example.com/dup' }],
poi: { title: 'Second', url: 'https://example.com/dup' },
map: [{ title: 'Third', url: 'https://example.com/dup' }],
},
})
expect(results).toEqual([
{ title: 'First', url: 'https://example.com/dup', snippet: undefined },
])
})
test('returns empty array when grounding is missing', () => {
expect(extractBraveResults({})).toEqual([])
})
test('returns empty array when grounding arrays are absent', () => {
expect(extractBraveResults({ grounding: {} })).toEqual([])
})
})

View File

@@ -0,0 +1,91 @@
/**
* Integration test for BraveSearchAdapter — hits Brave's LLM context API.
*
* Usage:
* BRAVE_SEARCH_API_KEY=... bun run src/tools/WebSearchTool/__tests__/braveAdapter.integration.ts
*
* Optional env vars:
* BRAVE_QUERY — search query (default: "Claude AI Anthropic")
* BRAVE_API_KEY — fallback key env var
*/
if (!globalThis.MACRO) {
globalThis.MACRO = { VERSION: '0.0.0-test', BUILD_TIME: '0' } as any
}
import { BraveSearchAdapter } from '../adapters/braveAdapter'
const query = process.env.BRAVE_QUERY || 'Claude AI Anthropic'
async function main() {
if (!process.env.BRAVE_SEARCH_API_KEY && !process.env.BRAVE_API_KEY) {
console.error(
'❌ Missing Brave API key. Set BRAVE_SEARCH_API_KEY or BRAVE_API_KEY.',
)
process.exit(1)
}
console.log(`\n🔍 Searching Brave for: "${query}"\n`)
const adapter = new BraveSearchAdapter()
const startTime = Date.now()
const results = await adapter.search(query, {
onProgress: p => {
if (p.type === 'query_update') {
console.log(` → Query sent: ${p.query}`)
}
if (p.type === 'search_results_received') {
console.log(` → Received ${p.resultCount} results`)
}
},
})
const elapsed = Date.now() - startTime
console.log(`\n✅ Done in ${elapsed}ms — ${results.length} result(s)\n`)
if (results.length === 0) {
console.log('⚠️ No results returned. Possible causes:')
console.log(' - Brave returned no grounding data for the query')
console.log(' - Network/firewall issue')
console.log(' - Invalid or rate-limited Brave API key\n')
process.exit(1)
}
for (const [i, r] of results.entries()) {
console.log(` ${i + 1}. ${r.title}`)
console.log(` ${r.url}`)
if (r.snippet) {
const snippet = r.snippet.replace(/\n/g, ' ')
console.log(
` ${snippet.slice(0, 150)}${snippet.length > 150 ? '…' : ''}`,
)
}
console.log()
}
let passed = true
for (const [i, r] of results.entries()) {
if (!r.title || typeof r.title !== 'string') {
console.error(`❌ Result ${i + 1}: missing or non-string title`, r)
passed = false
}
if (!r.url || !r.url.startsWith('http')) {
console.error(`❌ Result ${i + 1}: missing or non-http url`, r)
passed = false
}
}
if (passed) {
console.log('✅ All results have valid structure.\n')
} else {
process.exit(1)
}
}
if (import.meta.main) {
main().catch(e => {
console.error('❌ Fatal error:', e)
process.exit(1)
})
}

View File

@@ -0,0 +1,273 @@
import { afterEach, beforeEach, describe, expect, mock, test } from 'bun:test'
const originalBraveSearchApiKey = process.env.BRAVE_SEARCH_API_KEY
const originalBraveApiKey = process.env.BRAVE_API_KEY
describe('BraveSearchAdapter.search', () => {
const createAdapter = async () => {
const { BraveSearchAdapter } = await import('../adapters/braveAdapter')
return new BraveSearchAdapter()
}
const SAMPLE_RESPONSE = {
grounding: {
generic: [
{
title: 'Result One',
url: 'https://example.com/result1',
snippets: ['Snippet one'],
},
{
title: 'Result Two',
url: 'https://example.com/result2',
snippets: ['Snippet two'],
},
],
},
}
beforeEach(() => {
process.env.BRAVE_SEARCH_API_KEY = 'test-brave-key'
delete process.env.BRAVE_API_KEY
})
afterEach(() => {
mock.restore()
if (originalBraveSearchApiKey === undefined) {
delete process.env.BRAVE_SEARCH_API_KEY
} else {
process.env.BRAVE_SEARCH_API_KEY = originalBraveSearchApiKey
}
if (originalBraveApiKey === undefined) {
delete process.env.BRAVE_API_KEY
} else {
process.env.BRAVE_API_KEY = originalBraveApiKey
}
})
test('returns parsed results from Brave LLM context payload', async () => {
mock.module('axios', () => ({
default: {
get: mock(() => Promise.resolve({ data: SAMPLE_RESPONSE })),
isCancel: () => false,
},
}))
const adapter = await createAdapter()
const results = await adapter.search('test query', {})
expect(results).toHaveLength(2)
expect(results[0]).toEqual({
title: 'Result One',
url: 'https://example.com/result1',
snippet: 'Snippet one',
})
expect(results[1].title).toBe('Result Two')
})
test('calls onProgress with query_update and search_results_received', async () => {
mock.module('axios', () => ({
default: {
get: mock(() => Promise.resolve({ data: SAMPLE_RESPONSE })),
isCancel: () => false,
},
}))
const progressCalls: any[] = []
const onProgress = (p: any) => progressCalls.push(p)
const adapter = await createAdapter()
await adapter.search('test', { onProgress })
expect(progressCalls).toHaveLength(2)
expect(progressCalls[0]).toEqual({
type: 'query_update',
query: 'test',
})
expect(progressCalls[1]).toEqual({
type: 'search_results_received',
resultCount: 2,
query: 'test',
})
})
test('filters results by allowedDomains', async () => {
const mixedResponse = {
grounding: {
generic: [
{ title: 'Allowed', url: 'https://allowed.com/a' },
{ title: 'Blocked', url: 'https://blocked.com/b' },
],
},
}
mock.module('axios', () => ({
default: {
get: mock(() => Promise.resolve({ data: mixedResponse })),
isCancel: () => false,
},
}))
const adapter = await createAdapter()
const results = await adapter.search('test', {
allowedDomains: ['allowed.com'],
})
expect(results).toHaveLength(1)
expect(results[0].url).toBe('https://allowed.com/a')
})
test('filters results by blockedDomains', async () => {
const mixedResponse = {
grounding: {
generic: [
{ title: 'Good', url: 'https://good.com/a' },
{ title: 'Spam', url: 'https://spam.com/b' },
],
},
}
mock.module('axios', () => ({
default: {
get: mock(() => Promise.resolve({ data: mixedResponse })),
isCancel: () => false,
},
}))
const adapter = await createAdapter()
const results = await adapter.search('test', {
blockedDomains: ['spam.com'],
})
expect(results).toHaveLength(1)
expect(results[0].url).toBe('https://good.com/a')
})
test('filters subdomains with allowedDomains', async () => {
const response = {
grounding: {
generic: [
{ title: 'Subdomain', url: 'https://docs.example.com/page' },
{ title: 'Other', url: 'https://other.com/page' },
],
},
}
mock.module('axios', () => ({
default: {
get: mock(() => Promise.resolve({ data: response })),
isCancel: () => false,
},
}))
const adapter = await createAdapter()
const results = await adapter.search('test', {
allowedDomains: ['example.com'],
})
expect(results).toHaveLength(1)
expect(results[0].url).toBe('https://docs.example.com/page')
})
test('throws AbortError when signal is already aborted', async () => {
mock.module('axios', () => ({
default: {
get: mock((_url: string, config: any) => {
if (config?.signal?.aborted) {
const err = new Error('canceled')
;(err as any).__CANCEL__ = true
return Promise.reject(err)
}
return Promise.resolve({ data: SAMPLE_RESPONSE })
}),
isCancel: (e: any) => e?.__CANCEL__ === true,
},
}))
const adapter = await createAdapter()
const controller = new AbortController()
controller.abort()
const { AbortError } = await import('src/utils/errors')
await expect(
adapter.search('test', { signal: controller.signal }),
).rejects.toThrow(AbortError)
})
test('re-throws non-abort axios errors', async () => {
const networkError = new Error('Network error')
mock.module('axios', () => ({
default: {
get: mock(() => Promise.reject(networkError)),
isCancel: () => false,
},
}))
const adapter = await createAdapter()
await expect(adapter.search('test', {})).rejects.toThrow('Network error')
})
test('sends the documented HTTPS endpoint with query params and auth header', async () => {
const axiosGet = mock(() => Promise.resolve({ data: SAMPLE_RESPONSE }))
mock.module('axios', () => ({
default: {
get: axiosGet,
isCancel: () => false,
},
}))
const adapter = await createAdapter()
await adapter.search('hello world & special=chars', {})
expect(axiosGet.mock.calls).toHaveLength(1)
expect((axiosGet.mock.calls as any[][])[0][0]).toBe(
'https://api.search.brave.com/res/v1/llm/context',
)
expect((axiosGet.mock.calls as any[][])[0][1]).toMatchObject({
params: { q: 'hello world & special=chars' },
headers: {
Accept: 'application/json',
'X-Subscription-Token': 'test-brave-key',
},
})
})
test('accepts BRAVE_API_KEY as a fallback env var', async () => {
delete process.env.BRAVE_SEARCH_API_KEY
process.env.BRAVE_API_KEY = 'fallback-key'
const axiosGet = mock(() => Promise.resolve({ data: SAMPLE_RESPONSE }))
mock.module('axios', () => ({
default: {
get: axiosGet,
isCancel: () => false,
},
}))
const adapter = await createAdapter()
await adapter.search('test', {})
expect((axiosGet.mock.calls as any[][])[0][1].headers).toMatchObject({
'X-Subscription-Token': 'fallback-key',
})
})
test('throws when no Brave API key is configured', async () => {
delete process.env.BRAVE_SEARCH_API_KEY
delete process.env.BRAVE_API_KEY
mock.module('axios', () => ({
default: {
get: mock(() => Promise.resolve({ data: SAMPLE_RESPONSE })),
isCancel: () => false,
},
}))
const adapter = await createAdapter()
await expect(adapter.search('test', {})).rejects.toThrow(
'BraveSearchAdapter requires BRAVE_SEARCH_API_KEY or BRAVE_API_KEY',
)
})
})

View File

@@ -0,0 +1,173 @@
/**
* API-based search adapter — delegates to Anthropic's server-side
* web_search_20250305 tool via a secondary API call.
*/
import type {
BetaContentBlock,
BetaWebSearchTool20250305,
} from '@anthropic-ai/sdk/resources/beta/messages/messages.mjs'
import { getFeatureValue_CACHED_MAY_BE_STALE } from 'src/services/analytics/growthbook.js'
import { queryModelWithStreaming } from 'src/services/api/claude.js'
import { createUserMessage } from 'src/utils/messages.js'
import { getMainLoopModel, getSmallFastModel } from 'src/utils/model/model.js'
import { jsonParse } from 'src/utils/slowOperations.js'
import { asSystemPrompt } from 'src/utils/systemPromptType.js'
import type { SearchResult, SearchOptions, WebSearchAdapter } from './types.js'
function makeToolSchema(input: { allowedDomains?: string[]; blockedDomains?: string[] }): BetaWebSearchTool20250305 {
return {
type: 'web_search_20250305',
name: 'web_search',
allowed_domains: input.allowedDomains,
blocked_domains: input.blockedDomains,
max_uses: 8,
}
}
export class ApiSearchAdapter implements WebSearchAdapter {
async search(
query: string,
options: SearchOptions,
): Promise<SearchResult[]> {
const { signal, onProgress, allowedDomains, blockedDomains } = options
const userMessage = createUserMessage({
content: 'Perform a web search for the query: ' + query,
})
const toolSchema = makeToolSchema({ allowedDomains, blockedDomains })
const useHaiku = getFeatureValue_CACHED_MAY_BE_STALE('tengu_plum_vx3', false)
const queryStream = queryModelWithStreaming({
messages: [userMessage],
systemPrompt: asSystemPrompt([
'You are an assistant for performing a web search tool use',
]),
thinkingConfig: useHaiku
? { type: 'disabled' as const }
: { type: 'enabled' as const, budgetTokens: 10000 },
tools: [],
signal: signal ?? new AbortController().signal,
options: {
getToolPermissionContext: async () => ({
mode: 'default' as const,
additionalWorkingDirectories: new Map(),
alwaysAllowRules: {},
alwaysDenyRules: {},
alwaysAskRules: {},
isBypassPermissionsModeAvailable: false,
}),
model: useHaiku ? getSmallFastModel() : getMainLoopModel(),
toolChoice: useHaiku ? { type: 'tool' as const, name: 'web_search' } : undefined,
isNonInteractiveSession: false,
hasAppendSystemPrompt: false,
extraToolSchemas: [toolSchema],
querySource: 'web_search_tool' as const,
agents: [],
mcpTools: [],
agentId: undefined,
effortValue: undefined,
},
})
const allContentBlocks: BetaContentBlock[] = []
let currentToolUseId: string | null = null
let currentToolUseJson = ''
const toolUseQueries = new Map<string, string>()
let progressCounter = 0
for await (const event of queryStream) {
if (event.type === 'assistant') {
const msg = event as { message: { content: BetaContentBlock[] } }
allContentBlocks.push(...msg.message.content)
continue
}
if (event.type === 'stream_event') {
const streamEvt = event as {
event?: {
type: string
content_block?: { type: string; id?: string; tool_use_id?: string; content?: unknown; [key: string]: unknown }
delta?: { type: string; partial_json?: string; [key: string]: unknown }
[key: string]: unknown
}
}
if (streamEvt.event?.type === 'content_block_start') {
const contentBlock = streamEvt.event.content_block
if (contentBlock && contentBlock.type === 'server_tool_use') {
currentToolUseId = contentBlock.id as string
currentToolUseJson = ''
continue
}
}
if (currentToolUseId && streamEvt.event?.type === 'content_block_delta') {
const delta = streamEvt.event.delta
if (delta?.type === 'input_json_delta' && delta.partial_json) {
currentToolUseJson += delta.partial_json
try {
const queryMatch = currentToolUseJson.match(
/"query"\s*:\s*"((?:[^"\\]|\\.)*)"/,
)
if (queryMatch && queryMatch[1]) {
const parsedQuery = jsonParse('"' + queryMatch[1] + '"')
if (
!toolUseQueries.has(currentToolUseId) ||
toolUseQueries.get(currentToolUseId) !== parsedQuery
) {
toolUseQueries.set(currentToolUseId, parsedQuery)
progressCounter++
onProgress?.({
type: 'query_update',
query: parsedQuery,
})
}
}
} catch {
// Ignore parsing errors for partial JSON
}
}
}
if (streamEvt.event?.type === 'content_block_start') {
const contentBlock = streamEvt.event.content_block
if (contentBlock && contentBlock.type === 'web_search_tool_result') {
const toolUseId = contentBlock.tool_use_id as string
const actualQuery = toolUseQueries.get(toolUseId) || query
const content = contentBlock.content
progressCounter++
onProgress?.({
type: 'search_results_received',
resultCount: Array.isArray(content) ? content.length : 0,
query: actualQuery,
})
}
}
}
}
// Extract SearchResult[] from content blocks
return extractSearchResults(allContentBlocks)
}
}
function extractSearchResults(
blocks: BetaContentBlock[],
): SearchResult[] {
const results: SearchResult[] = []
for (const block of blocks) {
if (block.type === 'web_search_tool_result' && Array.isArray(block.content)) {
for (const r of block.content as Array<{ title: string; url: string; page_age?: string; type?: string }>) {
results.push({
title: r.title,
url: r.url,
})
}
}
}
return results
}

View File

@@ -0,0 +1,204 @@
/**
* Bing-based search adapter — fetches Bing search pages and extracts
* search results using regex pattern matching on raw HTML.
*/
import axios from 'axios'
import he from 'he'
import { AbortError } from 'src/utils/errors.js'
import type { SearchResult, SearchOptions, WebSearchAdapter } from './types.js'
const FETCH_TIMEOUT_MS = 30_000
/**
* Browser-like headers to avoid Bing's anti-bot JS-rendered response.
* These mimic Microsoft Edge on macOS to get full HTML search results.
*/
const BROWSER_HEADERS = {
'User-Agent':
'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36 Edg/131.0.0.0',
Accept:
'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8',
'Accept-Language': 'en-US,en;q=0.9',
'Accept-Encoding': 'gzip, deflate, br',
'Cache-Control': 'no-cache',
Pragma: 'no-cache',
'Sec-Ch-Ua': '"Microsoft Edge";v="131", "Chromium";v="131", "Not_A Brand";v="24"',
'Sec-Ch-Ua-Mobile': '?0',
'Sec-Ch-Ua-Platform': '"macOS"',
'Sec-Fetch-Dest': 'document',
'Sec-Fetch-Mode': 'navigate',
'Sec-Fetch-Site': 'none',
'Sec-Fetch-User': '?1',
'Upgrade-Insecure-Requests': '1',
} as const
export class BingSearchAdapter implements WebSearchAdapter {
async search(
query: string,
options: SearchOptions,
): Promise<SearchResult[]> {
const { signal, onProgress, allowedDomains, blockedDomains } = options
if (signal?.aborted) {
throw new AbortError()
}
onProgress?.({ type: 'query_update', query })
const url = `https://www.bing.com/search?q=${encodeURIComponent(query)}&setmkt=en-US`
const abortController = new AbortController()
if (signal) {
signal.addEventListener('abort', () => abortController.abort(), { once: true })
}
let html: string
try {
const response = await axios.get(url, {
signal: abortController.signal,
timeout: FETCH_TIMEOUT_MS,
responseType: 'text',
headers: BROWSER_HEADERS,
})
html = response.data
} catch (e) {
if (axios.isCancel(e) || abortController.signal.aborted) {
throw new AbortError()
}
throw e
}
if (abortController.signal.aborted) {
throw new AbortError()
}
const rawResults = extractBingResults(html)
// Client-side domain filtering
const results = rawResults.filter((r) => {
if (!r.url) return false
try {
const hostname = new URL(r.url).hostname
if (allowedDomains?.length && !allowedDomains.some(d => hostname === d || hostname.endsWith('.' + d))) {
return false
}
if (blockedDomains?.length && blockedDomains.some(d => hostname === d || hostname.endsWith('.' + d))) {
return false
}
} catch {
return false
}
return true
})
onProgress?.({
type: 'search_results_received',
resultCount: results.length,
query,
})
return results
}
}
/**
* Extract organic search results from Bing HTML.
* Bing results live in <li class="b_algo"> blocks within <ol id="b_results">.
*/
export function extractBingResults(html: string): SearchResult[] {
const results: SearchResult[] = []
const algoBlockRegex = /<li\s+class="b_algo"[^>]*>([\s\S]*?)<\/li>/gi
let blockMatch: RegExpExecArray | null
while ((blockMatch = algoBlockRegex.exec(html)) !== null) {
const block = blockMatch[1]
// Extract the primary link from <h2><a href="...">...</a></h2>
const h2LinkRegex = /<h2[^>]*>\s*<a[^>]+href="([^"]+)"[^>]*>([\s\S]*?)<\/a>/i
const linkMatch = h2LinkRegex.exec(block)
if (!linkMatch) continue
const rawUrl = decodeHtmlEntities(linkMatch[1])
const titleHtml = linkMatch[2]
// Resolve Bing redirect URLs (bing.com/ck/a?...&u=a1aHR0cHM6Ly9...)
// or skip Bing-internal / relative links
const url = resolveBingUrl(rawUrl)
if (!url) continue
const title = decodeHtmlEntities(
titleHtml.replace(/<[^>]+>/g, '').trim(),
)
// Extract snippet: try b_lineclamp → b_caption <p> → b_caption fallback
const snippet = extractSnippet(block)
results.push({ title, url, snippet })
}
return results
}
function extractSnippet(block: string): string | undefined {
// 1. Try <p class="b_lineclamp...">
const lineclampRegex = /<p[^>]*class="b_lineclamp[^"]*"[^>]*>([\s\S]*?)<\/p>/i
let match = lineclampRegex.exec(block)
if (match) {
return decodeHtmlEntities(match[1].replace(/<[^>]+>/g, '').trim())
}
// 2. Try <p> inside b_caption
const captionPRegex = /<div[^>]*class="b_caption[^"]*"[^>]*>[\s\S]*?<p[^>]*>([\s\S]*?)<\/p>/i
match = captionPRegex.exec(block)
if (match) {
return decodeHtmlEntities(match[1].replace(/<[^>]+>/g, '').trim())
}
// 3. Fallback: any text inside b_caption <div>
const fallbackRegex = /<div[^>]*class="b_caption[^"]*"[^>]*>([\s\S]*?)<\/div>/i
const fallbackMatch = fallbackRegex.exec(block)
if (fallbackMatch) {
const text = fallbackMatch[1].replace(/<[^>]+>/g, '').trim()
if (text) return decodeHtmlEntities(text)
}
return undefined
}
export const decodeHtmlEntities = he.decode
/**
* Resolve a Bing redirect URL to the actual target URL.
* Bing uses URLs like: https://www.bing.com/ck/a?...&u=a1aHR0cHM6Ly9leGFtcGxlLmNvbQ...
* The `u` query parameter is a base64-encoded URL prefixed with a1 (https) or a0 (http).
* Returns `undefined` for Bing-internal or relative links that should be skipped.
*/
export function resolveBingUrl(rawUrl: string): string | undefined {
// Skip relative / anchor links
if (rawUrl.startsWith('/') || rawUrl.startsWith('#')) return undefined
// Try to extract the `u` parameter from Bing redirect URLs
const uMatch = rawUrl.match(/[?&]u=([a-zA-Z0-9+/_=-]+)/)
if (uMatch) {
const encoded = uMatch[1]
if (encoded.length >= 3) {
const prefix = encoded.slice(0, 2)
const b64 = encoded.slice(2)
try {
// Base64url decode (pad as needed)
const padded = b64.replace(/-/g, '+').replace(/_/g, '/')
const decoded = Buffer.from(padded, 'base64').toString('utf-8')
if (decoded.startsWith('http')) return decoded
} catch {
// Fall through — not a valid base64 redirect
}
}
}
// Direct external URL (not a Bing-internal page)
if (!rawUrl.includes('bing.com')) return rawUrl
return undefined
}

View File

@@ -0,0 +1,169 @@
/**
* Brave-based search adapter — fetches Brave's LLM context API and maps the
* grounding payload into SearchResult objects.
*/
import axios from 'axios'
import { AbortError } from 'src/utils/errors.js'
import type { SearchResult, SearchOptions, WebSearchAdapter } from './types.js'
const FETCH_TIMEOUT_MS = 30_000
const BRAVE_LLM_CONTEXT_URL = 'https://api.search.brave.com/res/v1/llm/context'
const BRAVE_API_KEY_ENV_VARS = ['BRAVE_SEARCH_API_KEY', 'BRAVE_API_KEY'] as const
interface BraveGroundingResult {
title?: string
url?: string
snippets?: string[]
}
interface BraveSearchResponse {
grounding?: {
generic?: BraveGroundingResult[]
map?: BraveGroundingResult[]
poi?: BraveGroundingResult | null
}
}
export class BraveSearchAdapter implements WebSearchAdapter {
async search(
query: string,
options: SearchOptions,
): Promise<SearchResult[]> {
const { signal, onProgress, allowedDomains, blockedDomains } = options
if (signal?.aborted) {
throw new AbortError()
}
onProgress?.({ type: 'query_update', query })
const abortController = new AbortController()
if (signal) {
signal.addEventListener('abort', () => abortController.abort(), {
once: true,
})
}
let payload: BraveSearchResponse
try {
const response = await axios.get<BraveSearchResponse>(
BRAVE_LLM_CONTEXT_URL,
{
signal: abortController.signal,
timeout: FETCH_TIMEOUT_MS,
responseType: 'json',
headers: {
Accept: 'application/json',
'X-Subscription-Token': getBraveApiKey(),
},
params: { q: query },
},
)
payload = response.data
} catch (e) {
if (axios.isCancel(e) || abortController.signal.aborted) {
throw new AbortError()
}
throw e
}
if (abortController.signal.aborted) {
throw new AbortError()
}
const rawResults = extractBraveResults(payload)
const results = rawResults.filter(r => {
try {
const hostname = new URL(r.url).hostname
if (
allowedDomains?.length &&
!allowedDomains.some(
d => hostname === d || hostname.endsWith('.' + d),
)
) {
return false
}
if (
blockedDomains?.length &&
blockedDomains.some(d => hostname === d || hostname.endsWith('.' + d))
) {
return false
}
} catch {
return false
}
return true
})
onProgress?.({
type: 'search_results_received',
resultCount: results.length,
query,
})
return results
}
}
export function extractBraveResults(
payload: BraveSearchResponse,
): SearchResult[] {
const grounding = payload.grounding
if (!grounding) {
return []
}
const entries = [
...(Array.isArray(grounding.generic) ? grounding.generic : []),
...(grounding.poi ? [grounding.poi] : []),
...(Array.isArray(grounding.map) ? grounding.map : []),
]
const seenUrls = new Set<string>()
const results: SearchResult[] = []
for (const entry of entries) {
if (!entry?.url || !entry.title || seenUrls.has(entry.url)) {
continue
}
seenUrls.add(entry.url)
results.push({
title: entry.title,
url: entry.url,
snippet: normalizeSnippet(entry.snippets),
})
}
return results
}
function normalizeSnippet(snippets: string[] | undefined): string | undefined {
if (!Array.isArray(snippets)) {
return undefined
}
const normalized = snippets
.map(snippet => snippet.trim())
.filter(snippet => snippet.length > 0)
if (normalized.length === 0) {
return undefined
}
return normalized.join(' ')
}
function getBraveApiKey(): string {
for (const envVar of BRAVE_API_KEY_ENV_VARS) {
const value = process.env[envVar]?.trim()
if (value) {
return value
}
}
throw new Error(
'BraveSearchAdapter requires BRAVE_SEARCH_API_KEY or BRAVE_API_KEY',
)
}

View File

@@ -0,0 +1,47 @@
/**
* Search adapter factory — selects the appropriate backend by checking
* whether the API base URL points to Anthropic's official endpoint.
*/
import { isFirstPartyAnthropicBaseUrl } from 'src/utils/model/providers.js'
import { ApiSearchAdapter } from './apiAdapter.js'
import { BingSearchAdapter } from './bingAdapter.js'
import { BraveSearchAdapter } from './braveAdapter.js'
import type { WebSearchAdapter } from './types.js'
export type {
SearchResult,
SearchOptions,
SearchProgress,
WebSearchAdapter,
} from './types.js'
let cachedAdapter: WebSearchAdapter | null = null
let cachedAdapterKey: 'api' | 'bing' | 'brave' | null = null
export function createAdapter(): WebSearchAdapter {
const envAdapter = process.env.WEB_SEARCH_ADAPTER
const adapterKey =
envAdapter === 'api' || envAdapter === 'bing' || envAdapter === 'brave'
? envAdapter
: isFirstPartyAnthropicBaseUrl()
? 'api'
: 'bing'
if (cachedAdapter && cachedAdapterKey === adapterKey) return cachedAdapter
if (adapterKey === 'api') {
cachedAdapter = new ApiSearchAdapter()
cachedAdapterKey = 'api'
return cachedAdapter
}
if (adapterKey === 'brave') {
cachedAdapter = new BraveSearchAdapter()
cachedAdapterKey = 'brave'
return cachedAdapter
}
cachedAdapter = new BingSearchAdapter()
cachedAdapterKey = 'bing'
return cachedAdapter
}

View File

@@ -0,0 +1,22 @@
export interface SearchResult {
title: string
url: string
snippet?: string
}
export interface SearchOptions {
allowedDomains?: string[]
blockedDomains?: string[]
signal?: AbortSignal
onProgress?: (progress: SearchProgress) => void
}
export interface SearchProgress {
type: 'query_update' | 'search_results_received'
query?: string
resultCount?: number
}
export interface WebSearchAdapter {
search(query: string, options: SearchOptions): Promise<SearchResult[]>
}

View File

@@ -0,0 +1,34 @@
import { getLocalMonthYear } from 'src/constants/common.js'
export const WEB_SEARCH_TOOL_NAME = 'WebSearch'
export function getWebSearchPrompt(): string {
const currentMonthYear = getLocalMonthYear()
return `
- Allows Claude to search the web and use the results to inform responses
- Provides up-to-date information for current events and recent data
- Returns search result information formatted as search result blocks, including links as markdown hyperlinks
- Use this tool for accessing information beyond Claude's knowledge cutoff
- Searches are performed automatically within a single API call
CRITICAL REQUIREMENT - You MUST follow this:
- After answering the user's question, you MUST include a "Sources:" section at the end of your response
- In the Sources section, list all relevant URLs from the search results as markdown hyperlinks: [Title](URL)
- This is MANDATORY - never skip including sources in your response
- Example format:
[Your answer here]
Sources:
- [Source Title 1](https://example.com/1)
- [Source Title 2](https://example.com/2)
Usage notes:
- Domain filtering is supported to include or block specific websites
- Web search is only available in the US
IMPORTANT - Use the correct year in search queries:
- The current month is ${currentMonthYear}. You MUST use this year when searching for recent information, documentation, or current events.
- Example: If the user asks for "latest React docs", search for "React documentation" with the current year, NOT last year
`
}

View File

@@ -0,0 +1,2 @@
// Auto-generated type stub — replace with real implementation
export type getLocalMonthYear = any;

View File

@@ -0,0 +1,2 @@
// Auto-generated type stub — replace with real implementation
export type getAPIProvider = any;

View File

@@ -0,0 +1,2 @@
// Auto-generated type stub — replace with real implementation
export type PermissionResult = any;