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/provider/provider.go

@@ -64,8 +64,19 @@ type Usage struct {
 	InputTokens  int
 	OutputTokens int
 	TotalTokens  int
+	Details      map[string]int // provider-specific breakdown (e.g., cached, reasoning tokens)
 }
 
+// Standardized detail keys for provider-specific token breakdowns.
+const (
+	UsageDetailReasoningTokens     = "reasoning_tokens"
+	UsageDetailCachedInputTokens   = "cached_input_tokens"
+	UsageDetailCacheCreationTokens = "cache_creation_tokens"
+	UsageDetailAudioInputTokens    = "audio_input_tokens"
+	UsageDetailAudioOutputTokens   = "audio_output_tokens"
+	UsageDetailThoughtsTokens      = "thoughts_tokens"
+)
+
 // StreamEventType identifies the kind of stream event.
 type StreamEventType int