fix next feature filtering on in progress

agent.py

@@ -6,11 +6,19 @@ Core agent interaction functions for running autonomous coding sessions.
 """
 
 import asyncio
+import io
+import sys
 from pathlib import Path
 from typing import Optional
 
 from claude_agent_sdk import ClaudeSDKClient
 
+# Fix Windows console encoding for Unicode characters (emoji, etc.)
+# Without this, print() crashes when Claude outputs emoji like ✅
+if sys.platform == "win32":
+    sys.stdout = io.TextIOWrapper(sys.stdout.buffer, encoding='utf-8', errors='replace')
+    sys.stderr = io.TextIOWrapper(sys.stderr.buffer, encoding='utf-8', errors='replace')
+
 from client import create_client
 from progress import print_session_header, print_progress_summary, has_features
 from prompts import (

mcp_server/feature_mcp.py

@@ -145,26 +145,24 @@ def feature_get_stats() -> str:
 def feature_get_next() -> str:
     """Get the highest-priority pending feature to work on.
 
-    Returns the feature with the lowest priority number that has passes=false
+    Returns the feature with the lowest priority number that has passes=false.
-    and is not currently in-progress by another session.
     Use this at the start of each coding session to determine what to implement next.
 
     Returns:
         JSON with feature details (id, priority, category, name, description, steps, passes, in_progress)
-        or error message if all features are passing or in-progress.
+        or error message if all features are passing.
     """
     session = get_session()
     try:
         feature = (
             session.query(Feature)
             .filter(Feature.passes == False)
-            .filter(Feature.in_progress == False)
             .order_by(Feature.priority.asc(), Feature.id.asc())
             .first()
         )
 
         if feature is None:
-            return json.dumps({"error": "All features are passing or in-progress! No more work to do."})
+            return json.dumps({"error": "All features are passing! No more work to do."})
 
         return json.dumps(feature.to_dict(), indent=2)
     finally: