Add project_archives table and MCP tools (CF-264)

- Created migration 009: project_archives table with semantic search
- Implemented archives.ts: archiveAdd, archiveSearch, archiveList, archiveGet
- Registered archive tools in index.ts and tools/index.ts
- Archive types: session, research, audit, investigation, completed, migration
- Uses project_key (TEXT) FK to projects table
- Tested: archive_add and archive_list working correctly

Replaces filesystem archives with database-backed storage.
Eliminates context pollution from Glob/Grep operations.

Task: CF-264
Session: session_20260119111342_66de546b

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

src/tools/index.ts

@@ -974,4 +974,62 @@ export const toolDefinitions = [
       },
     },
   },
+
+  // Archive Tools
+  {
+    name: 'archive_add',
+    description: 'Archive content to database with semantic embedding. Replaces filesystem archives.',
+    inputSchema: {
+      type: 'object',
+      properties: {
+        project: { type: 'string', description: 'Project key (e.g., CF, VPN)' },
+        archive_type: { type: 'string', enum: ['session', 'research', 'audit', 'investigation', 'completed', 'migration'], description: 'Archive type' },
+        title: { type: 'string', description: 'Archive title' },
+        content: { type: 'string', description: 'Archive content (markdown)' },
+        original_path: { type: 'string', description: 'Original file path (optional)' },
+        file_size: { type: 'number', description: 'File size in bytes (optional)' },
+        archived_by_session: { type: 'string', description: 'Session ID that archived it (optional)' },
+        metadata: { type: 'object', description: 'Additional metadata (optional)' },
+      },
+      required: ['project', 'archive_type', 'title', 'content'],
+    },
+  },
+  {
+    name: 'archive_search',
+    description: 'Search archives using semantic similarity',
+    inputSchema: {
+      type: 'object',
+      properties: {
+        query: { type: 'string', description: 'Search query' },
+        project: { type: 'string', description: 'Filter by project (optional)' },
+        archive_type: { type: 'string', enum: ['session', 'research', 'audit', 'investigation', 'completed', 'migration'], description: 'Filter by archive type (optional)' },
+        limit: { type: 'number', description: 'Max results (default: 5)' },
+      },
+      required: ['query'],
+    },
+  },
+  {
+    name: 'archive_list',
+    description: 'List archives with optional filters',
+    inputSchema: {
+      type: 'object',
+      properties: {
+        project: { type: 'string', description: 'Filter by project (optional)' },
+        archive_type: { type: 'string', enum: ['session', 'research', 'audit', 'investigation', 'completed', 'migration'], description: 'Filter by archive type (optional)' },
+        since: { type: 'string', description: 'Show archives since date (ISO format, optional)' },
+        limit: { type: 'number', description: 'Max results (default: 20)' },
+      },
+    },
+  },
+  {
+    name: 'archive_get',
+    description: 'Get full content of specific archive by ID',
+    inputSchema: {
+      type: 'object',
+      properties: {
+        id: { type: 'number', description: 'Archive ID' },
+      },
+      required: ['id'],
+    },
+  },
 ];