Benchmark-Qwen-Ref：v0.21.14
全新 Sandbox 引导修复后的端到端回归冒烟测试：依次运行 1 个 SWE-bench Verified 案例和 1 个 Terminal-Bench 2.0 案例。
<!-- qwen-code-dsw-swe-verified:start -->
### SWE-bench Verified
- 状态：**成功**
- 数据集：`swe-bench/swe-bench-verified@2`；1/1 已完成
- 结果：0 个已解决，0 个未解决，1 个执行错误，0 个基础设施故障
- 得分：未公布（不可评分或隔离运行）
- 得分分母：有效评分器结果（0 + 0 = 0）
- Qwen Code：`v0.21.14` (`6e20a58923b0`)；模型 `qwen3.7-plus`
- 运行：`pool-610624947a774f78`；调度工作流：https://github.com/QwenLM/qwen-code/actions/runs/32384647090
- 案例轨迹：`swe-bench-verified-dsw-eas-tb-smoke-20260820-r1-trajectories.tar.gz`（0 个案例）
<!-- qwen-code-dsw-swe-verified:end -->
<!-- qwen-code-dsw-terminal-bench-2.0:start -->
### Terminal-Bench 2.0
- 状态：**成功**
- 数据集：`
[email protected]`；1/1 已完成
- 结果：0 个已解决，0 个未解决，1 个执行错误，0 个基础设施故障
- 得分：未公布（不可评分或隔离运行）
- 得分分母：有效评分器结果（0 + 0 = 0）
- Qwen Code：`v0.21.14` (`6e20a58923b0`)；模型 `qwen3.7-plus`
- 运行：`pool-f223fac36bf54a37`；调度工作流：https://github.com/QwenLM/qwen-code/actions/runs/32384647090
- 案例轨迹：`terminal-bench-2.0-dsw-eas-tb-smoke-20260820-r1-trajectories.tar.gz`（0 个案例）
<!-- qwen-code-dsw-terminal-bench-2.0:end -->
Benchmark-Qwen-Ref: v0.21.14
End-to-end regression smoke after fresh Sandbox bootstrap repair: 1 SWE-bench Verified case followed by 1 Terminal-Bench 2.0 case.
<!-- qwen-code-dsw-swe-verified:start -->
### SWE-bench Verified
- Status: **SUCCEEDED**
- Dataset: `swe-bench/swe-bench-verified@2`; 1/1 completed
- Results: 0 resolved, 0 unresolved, 1 execution errors, 0 infrastructure failures
- Score: not published (non-scoreable or quarantined run)
- Score denominator: valid grader results (0 + 0 = 0)
- Qwen Code: `v0.21.14` (`6e20a58923b0`); model `qwen3.7-plus`
- Run: `pool-610624947a774f78`; dispatch workflow: https://github.com/QwenLM/qwen-code/actions/runs/32384647090
- Case trajectories: `swe-bench-verified-dsw-eas-tb-smoke-20260820-r1-trajectories.tar.gz` (0 cases)
<!-- qwen-code-dsw-swe-verified:end -->
<!-- qwen-code-dsw-terminal-bench-2.0:start -->
### Terminal-Bench 2.0
- Status: **SUCCEEDED**
- Dataset: `
[email protected]`; 1/1 completed
- Results: 0 resolved, 0 unresolved, 1 execution errors, 0 infrastructure failures
- Score: not published (non-scoreable or quarantined run)
- Score denominator: valid grader results (0 + 0 = 0)
- Qwen Code: `v0.21.14` (`6e20a58923b0`); model `qwen3.7-plus`
- Run: `pool-f223fac36bf54a37`; dispatch workflow: https://github.com/QwenLM/qwen-code/actions/runs/32384647090
- Case trajectories: `terminal-bench-2.0-dsw-eas-tb-smoke-20260820-r1-trajectories.tar.gz` (0 cases)
<!-- qwen-code-dsw-terminal-bench-2.0:end -->