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>

backend/scripts/fix_agent_permission.py

@@ -0,0 +1,90 @@
+#!/usr/bin/env python3
+"""
+修复 Agent 权限级别: 将目标 Agent 的 permission_level 改为 acceptEdits
+避免每次文件写入都需要弹窗确认
+"""
+import sys
+import os
+sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+
+from app.core.database import SessionLocal
+from app.models.agent import Agent
+import json
+
+
+def fix_agent_permission(agent_name: str = None):
+    """将指定 Agent 的 permission_level 设为 acceptEdits"""
+    db = SessionLocal()
+
+    try:
+        agents = db.query(Agent).all()
+
+        if not agents:
+            print("[ERROR] No agents found")
+            return
+
+        print(f"[INFO] Found {len(agents)} agents:\n")
+        for a in agents:
+            wc = a.workflow_config or {}
+            nodes = wc.get("nodes", [])
+            perm = "default"
+            for n in nodes:
+                if n.get("type") in ("agent", "llm", "template"):
+                    perm = n.get("data", {}).get("permission_level", "default")
+                    break
+            print(f"  [{a.status}] {a.name} (id={a.id}) -- permission_level={perm}")
+
+        if agent_name:
+            target = db.query(Agent).filter(Agent.name == agent_name).first()
+            if not target:
+                target = db.query(Agent).filter(Agent.name.like(f"%{agent_name}%")).first()
+            if not target:
+                print(f"\n[ERROR] No agent matching '{agent_name}' found")
+                return
+            agents_to_fix = [target]
+        else:
+            agents_to_fix = agents
+
+        print(f"\n[INFO] Fixing permission_level...")
+        fixed = 0
+        for agent in agents_to_fix:
+            wc = agent.workflow_config or {}
+            nodes = wc.get("nodes", [])
+
+            updated = False
+            for node in nodes:
+                if node.get("type") in ("agent", "llm", "template"):
+                    data = node.get("data") or {}
+                    old_perm = data.get("permission_level", "default")
+                    if old_perm != "acceptEdits":
+                        data["permission_level"] = "acceptEdits"
+                        node["data"] = data
+                        updated = True
+                        print(f"  [FIXED] [{agent.name}] permission_level: {old_perm} -> acceptEdits")
+
+            if updated:
+                agent.workflow_config = wc
+                fixed += 1
+
+        if fixed > 0:
+            db.commit()
+            print(f"\n[DONE] Fixed {fixed} agent(s), permission_level set to acceptEdits")
+            print(f"       File write/edit operations will no longer require confirmation")
+        else:
+            print(f"\n[INFO] No agents need fixing (already acceptEdits)")
+
+    except Exception as e:
+        db.rollback()
+        print(f"[ERROR] Fix failed: {e}")
+        import traceback
+        traceback.print_exc()
+    finally:
+        db.close()
+
+
+if __name__ == "__main__":
+    import argparse
+    parser = argparse.ArgumentParser(description="Fix Agent permission level")
+    parser.add_argument("-n", "--name", type=str, help="Agent name (fuzzy match)")
+    args = parser.parse_args()
+    fix_agent_permission(agent_name=args.name)