fix: 模型思考模式配置 + Unicode 截断 + 审计修复 (13 files)

模型模式:
- 新增 LLMConfig/Source.ThinkingEnabled 配置，通过 ExtraBody
  控制 DeepSeek thinking mode，默认关闭
- SeedDefaults/ToConfig 读写 core.llm.thinking_enabled
- deepseek.lua 移除硬编码 temperature=0

Unicode 截断:
- truncateStr 改按 rune 计数，修复中文截断乱码

审计修复 (Critical):
- graph.go: defer rows.Close 在 for 循环 → 显式 Close (连接池泄漏)
- cli/openclaw/plugin.go: bare type assertion → comma-ok (panic)
- channel.go: payload["type"].(string) → comma-ok (panic)
- webui/handler.go: .(string) → fmt.Sprint (panic)
- agent.go: 添加 nil provider 错误返回

审计修复 (High):
- events/bus.go: copy handler slice under RLock (data race)
- webui/handler.go: SSE 通过 channel 串行化写入 (data race)
- timer/plugin.go: time.Sleep → select with stopCh (Stop 阻塞)
- provider.go: stream ch <- 添加 select ctx.Done (goroutine 泄漏)
- main.go: outputCh goroutine 添加 ctx.Done 退出路径

internal/agent/io/channel.go

@@ -246,10 +246,11 @@ func (m *IOManager) InjectInterrupt(source, channel string, payload map[string]i
 	if payload == nil {
 		payload = map[string]interface{}{}
 	}
+	evtType, _ := payload["type"].(string)
 	m.interruptCh <- &InputEvent{
 		RequestID:     m.nextRequestID(),
 		Source:        source,
-		Type:          payload["type"].(string),
+		Type:          evtType,
 		Payload:       payload,
 		OutputChannel: channel,
 	}