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_compliance.json

@@ -0,0 +1,96 @@
+{
+  "/compliance/eu-ai-act": {
+    "post": {
+      "tags": [
+        "compliance"
+      ],
+      "summary": "Check Eu Ai Act Compliance",
+      "description": "Check EU AI Act compliance for a spend log entry.\n\nChecks:\n- Art. 9: Guardrails applied (any guardrail)\n- Art. 5: Content screened before LLM (pre-call guardrails)\n- Art. 12: Audit record complete (user_id, model, timestamp, guardrail_results)",
+      "operationId": "check_eu_ai_act_compliance_compliance_eu_ai_act_post",
+      "requestBody": {
+        "content": {
+          "application/json": {
+            "schema": {
+              "$ref": "#/components/schemas/ComplianceCheckRequest"
+            }
+          }
+        },
+        "required": true
+      },
+      "responses": {
+        "200": {
+          "description": "Successful Response",
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/ComplianceResponse"
+              }
+            }
+          }
+        },
+        "422": {
+          "description": "Validation Error",
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/HTTPValidationError"
+              }
+            }
+          }
+        }
+      },
+      "security": [
+        {
+          "APIKeyHeader": []
+        }
+      ]
+    }
+  },
+  "/compliance/gdpr": {
+    "post": {
+      "tags": [
+        "compliance"
+      ],
+      "summary": "Check Gdpr Compliance",
+      "description": "Check GDPR compliance for a spend log entry.\n\nChecks:\n- Art. 32: Data protection applied (pre-call guardrails)\n- Art. 5(1)(c): Sensitive data protected (masked/blocked or no issues)\n- Art. 30: Audit record complete (user_id, model, timestamp, guardrail_results)",
+      "operationId": "check_gdpr_compliance_compliance_gdpr_post",
+      "requestBody": {
+        "content": {
+          "application/json": {
+            "schema": {
+              "$ref": "#/components/schemas/ComplianceCheckRequest"
+            }
+          }
+        },
+        "required": true
+      },
+      "responses": {
+        "200": {
+          "description": "Successful Response",
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/ComplianceResponse"
+              }
+            }
+          }
+        },
+        "422": {
+          "description": "Validation Error",
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/HTTPValidationError"
+              }
+            }
+          }
+        }
+      },
+      "security": [
+        {
+          "APIKeyHeader": []
+        }
+      ]
+    }
+  }
+}