schema: use BD GraphQL API for enrichment, add file tree and schema artifacts

- Replace S3 bigquery_tables metadata lookup with paginated GraphQL API call
  to fetch table and column descriptions from Base dos Dados
- Add gera_schemas.py for schema compilation and S3 inventory
- Add schemas.json and file_tree.md as generated reference artifacts
- Add websocket proxy in Caddyfile for ttyd on port 7681
- Ignore generated context/ artifacts in .gitignore
- Add openai to requirements.txt

Caddyfile

@@ -11,6 +11,17 @@
         reverse_proxy 127.0.0.1:8081
     }
 
+    @websocket {
+        header Connection *Upgrade*
+        header Upgrade websocket
+    }
+
+    handle @websocket {
+        reverse_proxy localhost:7681 {
+            flush_interval -1
+        }
+    }
+
     handle {
         forward_auth 127.0.0.1:8081 {
             uri /auth