fix: delete agent 500 error + dynamic personality + deployment guide

- Fix delete agent 500: clean up FK records (agent_llm_logs, permissions,
  schedules, executions, team_members) and unbind goals/tasks before delete
- Remove hardcoded personality templates in Android, replace with dynamic
  system prompt generation from name + description
- Set promptSectionsEnabled=false to bypass PromptComposer for personality
- Add Tencent Cloud Linux deployment guide (Docker Compose)
- Accumulated backend service updates, frontend UI fixes, Android app changes

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

misc/create_demo_agent.json

@@ -0,0 +1,66 @@
+{
+  "name": "Upgrade Demo Agent",
+  "description": "Full upgrade showcase: plan mode + permission level + file memory + audit hooks",
+  "category": "demo",
+  "is_public": true,
+  "budget_config": {
+    "max_llm_invocations": 20,
+    "max_tool_calls": 30
+  },
+  "workflow_config": {
+    "nodes": [
+      {
+        "id": "start-1",
+        "type": "start",
+        "data": {"label": "Start"},
+        "position": {"x": 80, "y": 200}
+      },
+      {
+        "id": "agent-1",
+        "type": "agent",
+        "data": {
+          "label": "Upgrade Demo",
+          "provider": "deepseek",
+          "model": "deepseek-v4-flash",
+          "temperature": 0.7,
+          "max_iterations": 10,
+          "plan_mode_enabled": true,
+          "plan_approval_required": true,
+          "permission_level": "acceptEdits",
+          "auto_approve_rules": [
+            {"tool_pattern": "file_read", "param_conditions": {}, "description": "Always approve file reads"},
+            {"tool_pattern": "list_files", "param_conditions": {}, "description": "Always approve directory listing"},
+            {"tool_pattern": "grep*", "param_conditions": {}, "description": "Always approve code searches"}
+          ],
+          "deny_tools": [],
+          "memory_dir_enabled": true,
+          "memory_max_history": 25,
+          "memory_vector_top_k": 5,
+          "memory_learning": true,
+          "memory_persist": true,
+          "memory_vector_enabled": true,
+          "tools": [
+            "file_read", "file_write", "file_edit",
+            "list_files", "search_files", "search_content",
+            "web_search", "web_fetch",
+            "task_plan", "check_progress", "self_review",
+            "code_execute", "system_info",
+            "datetime", "text_analyze", "json_process"
+          ],
+          "system_prompt": "You are the TianGong AI Platform upgrade demo assistant, running on the enhanced Agent Runtime. Your core capabilities include: 1) Plan Mode (P2) - for complex tasks, explore first, generate execution plan for user approval, then execute step by step; 2) Tool Safety (P3) - running at acceptEdits permission level with auto-approve for read and search tools; 3) File-based Memory System - categorized memory storage (user/feedback/project/reference types) with MEMORY.md index; 4) Hook Auditing - all tool calls are audited by PreToolUse/PostToolUse hooks. Instructions: For complex tasks, proactively use plan mode. Remember user preferences from the memory system. Prioritize read-only tools to understand the situation before making changes. Reply concisely."
+        },
+        "position": {"x": 300, "y": 200}
+      },
+      {
+        "id": "end-1",
+        "type": "end",
+        "data": {"label": "End"},
+        "position": {"x": 520, "y": 200}
+      }
+    ],
+    "edges": [
+      {"id": "e-start", "source": "start-1", "target": "agent-1", "sourceHandle": "right", "targetHandle": "left"},
+      {"id": "e-end", "source": "agent-1", "target": "end-1", "sourceHandle": "right", "targetHandle": "left"}
+    ]
+  }
+}