feat(eval): Locomo bot eval add check

[yeshion23333]

Description

本 PR 聚焦 Vikingbot LoCoMo 评测前置校验与 account 一致性，避免“导入成功但评测查不到上下文”的问题。

• 新增 preflight_eval_config.py：校验/修复 ov.conf 与 ovcli.conf 的 root key、account 相关配置；root key 首次配置后要求重启服务并退出。
• 新增 preflight_eval_runtime.py：统一解析 ACCOUNT/OPENVIKING_URL，并在导入前校验 OpenViking 可用性与 account 存在（可交互自动创建）。
• run_full_eval.sh 与 import_and_eval_one.sh 统一接入 preflight，消除重复逻辑，并通过 OPENVIKING_CONFIG_FILE 保证同一配置路径贯穿全流程。
• import_to_ov.py 增加 --account 并透传到 SDK client。
• 更新 benchmark/locomo/README.md（配置关系与排查指引）。

This PR improves Vikingbot LoCoMo evaluation reliability by enforcing preflight checks and account consistency.

• Added preflight_eval_config.py to validate/fix root-key and account-related settings in ov.conf/ovcli.conf; if root key is newly initialized, it exits and asks for server restart.
• Added preflight_eval_runtime.py to centralize ACCOUNT/OPENVIKING_URL resolution and perform pre-import OpenViking/account readiness checks (with optional interactive account auto-creation).
• Updated both run_full_eval.sh and import_and_eval_one.sh to use shared preflight runtime logic and OPENVIKING_CONFIG_FILE for a single consistent config path.
• Added --account support in import_to_ov.py and passed it into the SDK client.
• Updated benchmark/locomo/README.md with config mapping and troubleshooting guidance.

Related Issue

Type of Change

• Bug fix (non-breaking change that fixes an issue)
• New feature (non-breaking change that adds functionality)
• Breaking change (fix or feature that would cause existing functionality to not work as expected)
• Documentation update
• Refactoring (no functional changes)
• Performance improvement
• Test update

Changes Made

Testing

• I have added tests that prove my fix is effective or that my feature works
• New and existing unit tests pass locally with my changes
• I have tested this on the following platforms:
  • Linux
  • macOS
  • Windows

Checklist

• My code follows the project's coding style
• I have performed a self-review of my code
• I have commented my code, particularly in hard-to-understand areas
• I have made corresponding changes to the documentation
• My changes generate no new warnings
• Any dependent changes have been merged and published

Screenshots (if applicable)

Additional Notes

[github-actions]

PR Code Suggestions ✨

No code suggestions found for the PR.