Refactor cockpit to use DockerTmuxController pattern

Based on claude-code-tools TmuxCLIController, this refactor:

- Added DockerTmuxController class for robust tmux session management
- Implements send_keys() with configurable delay_enter
- Implements capture_pane() for output retrieval
- Implements wait_for_prompt() for pattern-based completion detection
- Implements wait_for_idle() for content-hash-based idle detection
- Implements wait_for_shell_prompt() for shell prompt detection

Also includes workflow improvements:
- Pre-task git snapshot before agent execution
- Post-task commit protocol in agent guidelines

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

lib/research_kg_sync.py

@@ -0,0 +1,56 @@
+#!/usr/bin/env python3
+"""
+Research KG Sync - Sync research files to Luzia's research KG
+
+Called by: luzia research-sync
+"""
+
+import sys
+sys.path.insert(0, '/home/admin/mcp-servers/hybrid-memory-mcp/tools')
+
+from research_to_kg import LuziaResearchExtractor
+
+
+def sync_research(reprocess: bool = False):
+    """Sync all research files to Luzia research KG."""
+    extractor = LuziaResearchExtractor()
+
+    if reprocess:
+        extractor.index = {"processed": {}}
+        extractor.save_index()
+        print("Index cleared. Reprocessing all files...")
+
+    results = extractor.process_directory()
+    processed = [r for r in results if r.get('status') == 'processed']
+    skipped = [r for r in results if r.get('status') == 'skipped']
+
+    print(f"\n📚 Research KG Sync Complete")
+    print(f"   New files indexed: {len(processed)}")
+    print(f"   Already indexed: {len(skipped)}")
+
+    total_findings = sum(r.get('findings_added', 0) for r in processed)
+    total_nodes = sum(r.get('nodes_added', 0) for r in processed)
+    if total_findings > 0:
+        print(f"   Findings added: {total_findings}")
+        print(f"   Nodes added: {total_nodes}")
+
+    extractor.show_stats()
+
+
+def show_stats():
+    """Show research KG statistics."""
+    extractor = LuziaResearchExtractor()
+    extractor.show_stats()
+
+
+if __name__ == "__main__":
+    import argparse
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--reprocess", action="store_true", help="Reprocess all files")
+    parser.add_argument("--stats", action="store_true", help="Show stats only")
+    args = parser.parse_args()
+
+    if args.stats:
+        show_stats()
+    else:
+        sync_research(reprocess=args.reprocess)