fix: provider-aware model routing with fallback visibility

- Extract createClientFromConfig() to dispatch on provider field instead
  of hardcoding all tiers as AnthropicClient
- Add fallback/fallbackReason metadata to ChatResponse and ChatStreamEvent
  so callers know when a fallback model was used
- Enhance doctor check to report full model stack and warn on missing
  API keys for cloud providers
- Log fallback warnings in NativeAgent and display them in TUI
- Support tier names and local_providers entries in fallback_chain
- Add 8 tests for createClientFromConfig covering all provider types

src/backends/native/agent.ts

@@ -79,6 +79,10 @@ export class NativeAgent {
 
     const response = await this.chatWithRouter(request);
 
+    if (response.fallback) {
+      console.warn(`[Flynn] ${response.fallbackReason}`);
+    }
+
     const assistantMsg: Message = { role: 'assistant', content: response.content };
     this.addToHistory(assistantMsg);
 
@@ -106,6 +110,10 @@ export class NativeAgent {
 
       const response = await this.chatWithRouter(request);
 
+      if (response.fallback) {
+        console.warn(`[Flynn] ${response.fallbackReason}`);
+      }
+
       // If the model didn't request tool use, we're done
       if (response.stopReason !== 'tool_use' || !response.toolCalls?.length) {
         const assistantMsg: Message = { role: 'assistant', content: response.content };