feat(research): hydrate web-search results with cleaned page content

Fetch and clean each search result's page body (bounded by size,
concurrency, and a configurable MaxPageContentRunes), store it on the
new ResearchResult.Content field, and surface those excerpts in agent
memory so the model reasons over real page text rather than snippets
alone. Promotes golang.org/x/net to a direct dependency for HTML
parsing.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

server/internal/svc/service_context.go

@@ -256,8 +256,9 @@ func newResearcher(c config.Config) design.Researcher {
 	switch opts.Driver {
 	case "", "duckduckgo":
 		return websearch.NewDuckDuckGoResearcher(websearch.DuckDuckGoOptions{
-			TimeoutSeconds: opts.TimeoutSeconds,
-			MaxResults:     opts.MaxResults,
+			TimeoutSeconds:      opts.TimeoutSeconds,
+			MaxResults:          opts.MaxResults,
+			MaxPageContentRunes: opts.MaxPageContentRunes,
 		})
 	case "none", "disabled":
 		return nil