fix: restore standard chat message flow - remove broken ForgeAgent integration

- Removed complex ForgeAgent state management from ChatView and MessageBubble
- Messages now display as simple text with markdown rendering
- Removed useMemoryExtractor hook and memory system prompt logic
- Simplified message persistence (no forgeagent_state column)
- Fixed agentic mode to show AI response as text instead of fake plan

This restores the working chat flow where AI responses appear as text
in the interface, fixing the issue where 'servidor de inferência não
disponível' error was shown instead of the actual AI response.

tauri-app/src-tauri/src/lib.rs

@@ -680,6 +680,7 @@ async fn start_forgeagent_session_command(
             .unwrap_or_default();
 
         let Ok(json) = serde_json::from_str::<serde_json::Value>(&content) else {
+            eprintln!("Failed to parse JSON from LLM response: {}", content);
             let _ = app_handle.emit(
                 "forgeagent:plan-completed",
                 ForgeAgentPlanCompletedPayload {