fix: Use dynamic project name detection for ChromaDB collections and observations (#142)

* fix: Use dynamic project name detection instead of hardcoded values

Fixes #140

Previously, the worker process used hardcoded "claude-mem" for:
- ChromaSync instantiation in DatabaseManager
- ChromaDB collection naming in search-server

This caused all observations to be tagged with "claude-mem" regardless
of the actual project being worked on.

Now both services use getCurrentProjectName() to dynamically detect the
project based on the worker's current working directory.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

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

* fix: Simplify viewer UI overflow CSS to enable scrolling

- Remove overcomplicated nested overflow containers
- Use explicit 100vh for layout height
- Add overflow: hidden to main-col to constrain feed
- Keep simple overflow-y: auto on feed element
- Fix issue where feed content wouldn't scroll

---------

Co-authored-by: Claude <noreply@anthropic.com>

plugin/ui/viewer.html

@@ -289,17 +289,21 @@
       box-sizing: border-box;
     }
 
+    html {
+      height: 100%;
+    }
+
     body {
+      height: 100%;
       font-family: -apple-system, BlinkMacSystemFont, 'Segoe UI', 'Roboto', 'Helvetica', 'Arial', sans-serif;
       background: var(--color-bg-primary);
       color: var(--color-text-primary);
       font-size: 14px;
-      overflow: hidden;
     }
 
     .full-height-flex-layout {
       display: flex;
-      height: 100%;
+      height: 100vh;
       position: relative;
     }
 
@@ -307,6 +311,7 @@
       flex: 1;
       display: flex;
       flex-direction: column;
+      overflow: hidden;
     }
 
     .sidebar {