Phase 7: Agent Selector — per-agent soul.md + ChromaDB memory filtering

- Agent dropdown UI (chip button + hidden select) in composer header
- Session.agent field persists agent selection across refresh
- soul.md loaded per-agent via ephemeral_system_prompt injection
- ChromaDB memory filtered by agent topic (lotus/, sunflower/, etc.)
- Fixed streaming.py: agent→_ai_agent variable shadowing (lines 1161, 1163)
- New API endpoints: /api/agents/topology, /api/agents/memory/search
- Agent metadata registry with emoji, name, description per Tier-2 agent

api/workspace.py

@@ -309,20 +309,39 @@ def safe_resolve_ws(root: Path, requested: str) -> Path:
     return resolved
 
 
-def list_dir(workspace: Path, rel: str='.'):
+def list_dir(workspace: Path, rel: str='.', search: str=''):
     target = safe_resolve_ws(workspace, rel)
     if not target.is_dir():
         raise FileNotFoundError(f"Not a directory: {rel}")
+    query = search.lower().strip()
     entries = []
-    for item in sorted(target.iterdir(), key=lambda p: (p.is_file(), p.name.lower())):
-        entries.append({
-            'name': item.name,
-            'path': str(item.relative_to(workspace)),
-            'type': 'dir' if item.is_dir() else 'file',
-            'size': item.stat().st_size if item.is_file() else None,
-        })
-        if len(entries) >= 200:
-            break
+    if query:
+        # Recursive search
+        try:
+            for item in target.rglob('*'):
+                if item.is_file():
+                    if query in item.name.lower():
+                        entries.append({
+                            'name': item.name,
+                            'path': str(item.relative_to(workspace)),
+                            'type': 'file',
+                            'size': item.stat().st_size,
+                        })
+                if len(entries) >= 200:
+                    break
+        except (PermissionError, OSError):
+            pass
+        entries.sort(key=lambda x: x['name'].lower())
+    else:
+        for item in sorted(target.iterdir(), key=lambda p: (p.is_file(), p.name.lower())):
+            entries.append({
+                'name': item.name,
+                'path': str(item.relative_to(workspace)),
+                'type': 'dir' if item.is_dir() else 'file',
+                'size': item.stat().st_size if item.is_file() else None,
+            })
+            if len(entries) >= 200:
+                break
     return entries