feat: comprehensive token usage tracking for V2

Add provider-specific usage details, fix streaming usage, and return
usage from all high-level APIs (Chat.Send, Generate[T], Agent.Run).

Breaking changes:
- Chat.Send/SendMessage/SendWithImages now return (string, *Usage, error)
- Generate[T]/GenerateWith[T] now return (T, *Usage, error)
- Agent.Run/RunMessages now return (string, *Usage, error)

New features:
- Usage.Details map for provider-specific token breakdowns
  (reasoning, cached, audio, thoughts tokens)
- OpenAI streaming now captures usage via StreamOptions.IncludeUsage
- Google streaming now captures UsageMetadata from final chunk
- UsageTracker.Details() for accumulated detail totals
- ModelPricing and PricingRegistry for cost computation

Closes #2

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

v2/anthropic/anthropic.go

@@ -270,6 +270,16 @@ func (p *Provider) convertResponse(resp anth.MessagesResponse) provider.Response
 		OutputTokens: resp.Usage.OutputTokens,
 		TotalTokens:  resp.Usage.InputTokens + resp.Usage.OutputTokens,
 	}
+	details := map[string]int{}
+	if resp.Usage.CacheCreationInputTokens > 0 {
+		details[provider.UsageDetailCacheCreationTokens] = resp.Usage.CacheCreationInputTokens
+	}
+	if resp.Usage.CacheReadInputTokens > 0 {
+		details[provider.UsageDetailCachedInputTokens] = resp.Usage.CacheReadInputTokens
+	}
+	if len(details) > 0 {
+		res.Usage.Details = details
+	}
 
 	return res
 }