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/config/config.go

@@ -161,9 +161,10 @@ type CreativePlannerConfig struct {
 }
 
 type ResearchConfig struct {
-	Driver         string `json:",default=duckduckgo"`
-	TimeoutSeconds int    `json:",default=10"`
-	MaxResults     int    `json:",default=5"`
+	Driver              string `json:",default=duckduckgo"`
+	TimeoutSeconds      int    `json:",default=10"`
+	MaxResults          int    `json:",default=5"`
+	MaxPageContentRunes int    `json:",default=1800"`
 }
 
 type ObjectStorageConfig struct {