refactor: make routing system extensible with provider/builder interfaces

BREAKING: LLMRouter now requires explicit LLMProvider

New Abstractions:
- LLMProvider interface: swap providers (OpenAI, Claude, local, etc)
- SpecBuilder interface: custom spec generation strategies
- ParameterBinder interface: flexible parameter resolution
- ActivityExecutor interface: pluggable activity execution
- WorkflowValidator interface: composable validation

Provider System:
- ProviderRegistry: manage multiple LLM providers
- RoutingProviderLLM: fallback across providers
- CachingLLMProvider: caching wrapper
- RetryingLLMProvider: retry wrapper

Spec Building:
- DefaultSpecBuilder: basic spec generation
- CronSpecBuilder: cron workflow specialization
- SpecBuilderFactory: builder selection
- CompositeSpecBuilder: multi-strategy fallback
- BuildMetadata: context for builders

Validators:
- StateGraphValidator: DAG structure
- ActivityAvailabilityValidator: activity existence
- TimeoutValidator: timeout format
- CompositeValidator: multiple validators
- TransitionValidator: state transitions

Refactored Components:
- LLMRouter: config-driven, provider-agnostic
- LLMClient: now implements LLMProvider
- llm_router.go: 97 fewer lines (delegated to builders)

Migration Path:
OLD: NewLLMRouter(kb)
NEW: NewLLMRouter(LLMRouterConfig{Provider: ..., KB: ...})

internal/routing/llm_client.go

@@ -36,6 +36,31 @@ func NewLLMClient() *LLMClient {
 	}
 }
 
+// Name returns the provider name
+func (c *LLMClient) Name() string {
+	return "riotpiao"
+}
+
+// IsAvailable checks if the LLM service is available
+func (c *LLMClient) IsAvailable(ctx context.Context) error {
+	req, err := http.NewRequestWithContext(ctx, "GET", c.baseURL, nil)
+	if err != nil {
+		return fmt.Errorf("failed to create request: %w", err)
+	}
+	
+	resp, err := c.httpClient.Do(req)
+	if err != nil {
+		return fmt.Errorf("LLM service unavailable: %w", err)
+	}
+	defer resp.Body.Close()
+	
+	if resp.StatusCode >= 500 {
+		return fmt.Errorf("LLM service error: %d", resp.StatusCode)
+	}
+	
+	return nil
+}
+
 // llmRequest is the request body for the OpenAI-compatible API
 type llmRequest struct {
 	Model    string       `json:"model"`