refactor: 重构 Tool Result 契约，移除 ui_hints 统一使用 result 字段

- ToolAgentOutput 移除 result_summary 和 ui_hints，统一使用 result 字段
- 日历/用户查找工具移除 ui_hints 输出，改为机器可读的结构化结果
- Agent History 移除 tool 消息的 ui_hints 处理逻辑
- App 版本检查改为 manifest.json 方式，支持多渠道发布
- 更新 settings 配置和测试用例适配新结构

backend/AGENTS.md

@@ -246,6 +246,17 @@ class AgentType(str, Enum):
 
 Agent loop functionality MUST follow the AG-UI protocol. **Use the `ag-ui` skill** for protocol reference and implementation guidance.
 
+## Custom Tool Result Contract
+
+Custom tool `ToolAgentOutput` MUST follow these rules:
+
+- Use field name `result` only. Do not introduce or keep `result_summary` compatibility aliases.
+- `result` is for downstream agent reasoning and tool chaining, not for end-user presentation.
+- Prefer compact structural facts over prose: include identifiers and execution-critical facts (`id`, `status`, `count`, `page`, operation outcome, missing required args).
+- For list/read tools, include multiple candidate records when needed (at least top matches) with stable identifiers.
+- For write tools, always include affected resource identifiers in `result`.
+- Keep `result` concise, deterministic, and machine-oriented; avoid decorative wording and UI-style formatting.
+
 ## Multi-Agent Orchestration (AgentScope Framework)
 
 Multi-agent orchestration MUST use the AgentScope framework. **Use the `agentscope-skill`** for framework reference and implementation guidance.
@@ -264,3 +275,12 @@ Multi-agent orchestration MUST use the AgentScope framework. **Use the `agentsco
 - **Pipelines**: Ordered orchestration flow between agents
 - **Tools**: Capabilities available to agents
 - **Flows**: Workflow orchestration and state management
+
+## Testing
+
+### Real Database Tests
+
+Tests requiring real Supabase operations MUST use environment variables:
+- Define `TestSettings` in `settings.py` with nested configuration
+- Access via `settings.test.email` / `settings.test.password`
+- NEVER hardcode credentials in code