feat(web): expose exa/perplexity search tuning as config

The Exa and Perplexity providers hard-coded request parameters that
deployments should control while defaults are still unsettled. Exa gains
searchType, numResults, and highlightsPerResult; Perplexity gains
maxTokens (it previously sent none) and an optional searchRecency. Each
follows the deepseek provider's shape: a defaulted Config field, a
DEFAULT_* constant, and a positive-integer status() check for numeric
limits. The call-level maxResults still flows through WebSearchRequest
and wins over the configured default, keeping the seam layering intact.

Addresses tianyicui's "make everything configurable" review comment.

packages/web/web-search-perplexity/tests/perplexity.e2e.ts

@@ -1,5 +1,5 @@
 import { describe, expect, it } from 'vitest'
-import { PerplexitySearchProvider, PERPLEXITY_DEFAULT_BASE_URL, PERPLEXITY_DEFAULT_MODEL } from '@deepseek-ai/dsh-web-search-perplexity'
+import { PerplexitySearchProvider, PERPLEXITY_DEFAULT_BASE_URL, PERPLEXITY_DEFAULT_MAX_TOKENS, PERPLEXITY_DEFAULT_MODEL } from '@deepseek-ai/dsh-web-search-perplexity'
 
 /**
  * Real-API smoke for the Perplexity search provider. Self-skips without
@@ -14,6 +14,7 @@ maybe('PerplexitySearchProvider real API', () => {
       apiKey: apiKey!,
       baseURL: process.env.PERPLEXITY_BASE_URL ?? PERPLEXITY_DEFAULT_BASE_URL,
       model: process.env.PERPLEXITY_MODEL ?? PERPLEXITY_DEFAULT_MODEL,
+      maxTokens: PERPLEXITY_DEFAULT_MAX_TOKENS,
     })
     const result = await provider.search({ query: 'What is the DeepSeek coding agent?', maxResults: 5 })
     expect(result.providerId).toBe('perplexity')