feat(llm): mask API keys in UI responses and prevent masked-key leakage in fetch/test/save payloads

- Add mask_api_key() and is_masked_or_placeholder() to llm_provider service
- Return masked keys in all provider CRUD endpoints
- Reject masked/placeholder keys in fetch_models and test_provider_config
- Show masked key with Change button in ProviderConfig.svelte edit form
- Exclude masked keys from fetch-models, test, and submit payloads on frontend
- Update semantics-core skill with clarified complexity tier rules
- Switch agent modes from subagent to all

docs/openapi/litellm/chunks_paths/paths__v1_moderations.json

@@ -0,0 +1,27 @@
+{
+  "/v1/moderations": {
+    "post": {
+      "tags": [
+        "moderations"
+      ],
+      "summary": "Moderations",
+      "description": "The moderations endpoint is a tool you can use to check whether content complies with an LLM Providers policies.\nQuick Start\n```\ncurl --location 'http://0.0.0.0:4000/moderations'     --header 'Content-Type: application/json'     --header 'Authorization: Bearer sk-1234'     --data '{\"input\": \"Sample text goes here\", \"model\": \"text-moderation-stable\"}'\n```",
+      "operationId": "moderations_v1_moderations_post",
+      "responses": {
+        "200": {
+          "description": "Successful Response",
+          "content": {
+            "application/json": {
+              "schema": {}
+            }
+          }
+        }
+      },
+      "security": [
+        {
+          "APIKeyHeader": []
+        }
+      ]
+    }
+  }
+}