Remove final_output tool and improve scout report handback

final_output removal:
- Remove final_output from tool definitions and dispatch
- Update system prompts to request summaries as regular text
- Remove final_output_called field from StreamingState
- Update auto_continue tests to remove final_output_called parameter
- Remove final_output test from tool_execution_test.rs
- Update planner and flock prompts to not reference final_output
- Keep backwards-compat code in feedback_extraction.rs and task_result.rs

Scout report handback:
- Change from file-based to delimiter-based report extraction
- Scout outputs report between ---SCOUT_REPORT_START/END--- markers
- Research tool extracts content between markers, strips ANSI codes
- Add comprehensive tests for extraction and ANSI stripping

657 tests pass.

crates/g3-planner/src/planner.rs

@@ -553,7 +553,6 @@ pub fn get_planner_tools() -> Vec<&'static str> {
         "shell",
         "code_search",
         "str_replace",
-        "final_output",
     ]
 }
 
@@ -673,7 +672,7 @@ pub async fn run_coach_player_loop(
         ).await?;
         
         let coach_prompt = format!(
-            "You are G3 in coach mode. Review the implementation against these requirements:\n\n{}\n\nCheck:\n1. Are requirements implemented correctly?\n2. Does the code compile?\n3. What's missing?\n\nUse the final_output tool to provide your feedback.\nIf implementation is COMPLETE, include 'IMPLEMENTATION_APPROVED' in your feedback.\nOtherwise, provide specific feedback for the player to fix.",
+            "You are G3 in coach mode. Review the implementation against these requirements:\n\n{}\n\nCheck:\n1. Are requirements implemented correctly?\n2. Does the code compile?\n3. What's missing?\n\nProvide your feedback as a summary.\nIf implementation is COMPLETE, include 'IMPLEMENTATION_APPROVED' in your feedback.\nOtherwise, provide specific feedback for the player to fix.",
             requirements_content
         );