feat: add per-agent logging UI and fix stuck agent issues

Changes:
- Add per-agent log viewer with copy-to-clipboard functionality
  - New AgentLogEntry type for structured log entries
  - Logs stored per-agent in WebSocket state (up to 500 entries)
  - Log modal rendered via React Portal to avoid overflow issues
  - Click log icon on agent card to view full activity history

- Fix agents getting stuck in "failed" state
  - Wrap client context manager in try/except (agent.py)
  - Remove failed agents from UI on error state (useWebSocket.ts)
  - Handle permanently failed features in get_all_complete()

- Add friendlier agent state labels
  - "Hit an issue" → "Trying plan B..."
  - "Retrying..." → "Being persistent..."
  - Softer colors (yellow/orange instead of red)

- Add scheduling scores for smarter feature ordering
  - compute_scheduling_scores() in dependency_resolver.py
  - Features that unblock others get higher priority

- Update CLAUDE.md with parallel mode documentation

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

agent.py

@@ -203,8 +203,14 @@ async def run_autonomous_agent(
                 prompt = get_coding_prompt(project_dir)
 
         # Run session with async context manager
-        async with client:
-            status, response = await run_agent_session(client, prompt, project_dir)
+        # Wrap in try/except to handle MCP server startup failures gracefully
+        try:
+            async with client:
+                status, response = await run_agent_session(client, prompt, project_dir)
+        except Exception as e:
+            print(f"Client/MCP server error: {e}")
+            # Don't crash - return error status so the loop can retry
+            status, response = "error", str(e)
 
         # Handle status
         if status == "continue":