fix(ci): restore parallel TileLib ST and watchdog labels

[mouliangyu]

背景

PR #1028 已经将 TileLib ST 改为按 case 使用 pytest-xdist 并行调度，但后续 CI workflow 修改重新使用了串行 run_tilelib_st.py 入口。当前 154 个 case 因此共享一个 simulator 会话串行执行；最近一次串行门禁中的 Run TileLib ST CI 用时约 59 分钟。

同一次门禁超过 watchdog 的 90 分钟软预算后，watchdog 虽然正确识别了慢运行，却在给 PR 添加 ci-slow label 时因为 GITHUB_TOKEN 只有 pull-request read 权限而收到 403。该 job 的 continue-on-error 又让 Watchdog workflow 最终显示为 success，没有留下 label 或评论。

修改

• 恢复 TileLib ST 的 pytest 入口，使用 16 路 pytest-xdist --dist=worksteal 调度独立 case。
• 保留当前 TILELIB_ST_WORKSPACE、PTODSL Python、PTOAS 和日志路径配置。
• 将 TileLib artifact 从整个 case simulator 工作目录收敛为聚合日志、每 case 日志、退出码、复现脚本和 msprof stdout，避免并行输出产生百万级临时文件上传。
• 为慢 CI 告警 job 同时授予 issues: write 和 pull-requests: write，使 GITHUB_TOKEN 可以更新 PR 的 ci-slow label 和 Conversation 评论。
• 移除 watchdog job 的 continue-on-error，使 watchdog 自身的权限或脚本错误在独立 workflow 中可见；该 workflow 不是 ci-sim required check，不会改变原门禁结果。

验证

• .github/workflows/ci_sim.yml 和 .github/workflows/watchdog.yml 通过 PyYAML 解析。
• TileLib ST Python 文件通过 py_compile。
• 使用 CI 同款 PTODSL Python、pytest 9.1.1 和 pytest-xdist 3.8.0：154 个 case 收集成功。
• pytest --collect-only -n 16 --dist=worksteal test/tilelib-st/test_tilelib_st.py 通过。
• PR CI 中 154 个 TileLib ST case 全部通过，并行运行时间为 9 分 18 秒。
• 根据该次 CI 实际输出验证 artifact 收敛：上传文件从 1,101,864 个降至 616 个，约 2.6 MB。
• git diff --check 通过。

后续 CI 出现的 exit 143 已确认来自宿主机 OOM：PR #1105 的 TileLib simulator 与 PR #1104 的 PTOAS 编译等任务同时运行，runner 所在 tmux scope 使用 OOMPolicy=stop，action 子进程成为 OOM victim 后连带关闭了整个 runner。该宿主机部署问题不通过降低本 PR 的 TileLib 并行度处理。

说明：workflow_run 会从默认分支加载 watchdog，因此新的 PR 写权限需要在本 PR 合入后，由下一次 PR ci-sim 完成事件做端到端验证。

Follow-up to #1028 and #1031.

[reedhecre]

A5 板测成功

• 触发方式：merged
• 源码提交：dbfbec2dcf5e
• 结果汇总：OK 21 / FAIL 0 / SKIP 0
• 日志：/root/ptoas-board-monitor-a5/logs/20260803_185605_merged_pr1105.log
• 结果 TSV：/root/ptoas-board-monitor-a5/logs/20260803_185605_merged_pr1105.tsv

[reedhecre]

A3 板测失败

• 触发方式：merged
• 源码提交：dbfbec2dcf5e
• 结果汇总：OK 218 / FAIL 2 / SKIP 3
• 日志：/home/zhongxuan/ptoas-board-monitor/runtime/logs/20260803_035525_merged_pr1105.log
• 失败阶段：board-validation / exit=1

失败用例

• comm_p2p_binding_variants (run, exit=1)
• comm_p2p (run, exit=1)

[reedhecre]

A3 板测失败详情：PR #1105

comm_p2p_binding_variants

stage=run info=exit=1

[ERROR] aclrtSynchronizeStream(stream) failed: 507035 (/home/zhongxuan/ptoas-board-monitor/runtime/runs/20260803_035525_merged_pr1105/npu_validation/CommSync/comm_p2p_binding_variants/main.cpp:122)
[ERROR] RecentErrMsg: EZ9999: Inner Error!
EZ9999[PID: 474747] 2026-08-03-04:29:42.876.605 (EZ9999):  The error from device(chipId:1, dieId:1), serial number is 617, there is an exception of aivec error, core id is 46, error code = 0x10, dump info: pc start: 0x124600000000, current: 0x124600000164, vec error info: 0xf7029bb145, mte error info: 0x7503000008, ifu error info: 0x212d052480440, ccu error info: 0x40a414030000004f, cube error info: 0, biu error info: 0, aic error mask: 0x6500020bd00028c, para base: 0x12c100000000.[FUNC:PrintCoreInfo][FILE:device_error_core_proc.cc][LINE:645]
        TraceBack (most recent call last):
       The extend info: errcode:(0x10, 0, 0) errorStr: Illegal instruction, which is usually caused by unaligned UUB addresses. fixp_error0 info: 0x3000008, fixp_error1 info: 0x75, fsmId:0, tslot:3, thread:0, ctxid:0, blk:0, sublk:0, subErrType:4.[FUNC:PrintCoreInfo][FILE:device_error_core_proc.cc][LINE:658]
       Kernel task happen error, retCode=0x31, [vector core exception].[FUNC:PreCheckTaskErr][FILE:davinci_kernel_task.cc][LINE:1729]
       AIV Kernel happen error, retCode=0x31.[FUNC:GetError][FILE:stream.cc][LINE:1475]
       [AIC_INFO] after execute:args print end[FUNC:GetError][FILE:stream.cc][LINE:1475]
       [DFX_INFO]Aicore kernel execute failed, device_id=3, stream_id=46, report_stream_id=46, task_id=0, flip_num=0, fault kernel_name=comm_p2p_binding_variants_kernel, fault kernel info ext=comm_p2p_binding_variants_kernel, program id=0, hash=16541545288638093324.[FUNC:GetError][FILE:stream.cc][LINE:1475]
       rtStreamSynchronize execution failed, reason=vector core exception[FUNC:FuncErrorReason][FILE:error_message_manage.cc][LINE:65]
       synchronize stream failed, runtime result = 507035[FUNC:ReportCallError][FILE:log_inner.cpp][LINE:148]
[2026-08-03 04:29:44] ERROR: testcase failed (exit 1): comm_p2p_binding_variants

comm_p2p

stage=run info=exit=1

[ERROR] aclrtSynchronizeStream(stream) failed: 507035 (/home/zhongxuan/ptoas-board-monitor/runtime/runs/20260803_035525_merged_pr1105/npu_validation/CommSync/comm_p2p/main.cpp:122)
[ERROR] RecentErrMsg: EZ9999: Inner Error!
EZ9999[PID: 487219] 2026-08-03-04:30:03.343.379 (EZ9999):  The error from device(chipId:1, dieId:1), serial number is 618, there is an exception of aivec error, core id is 1, error code = 0x10, dump info: pc start: 0x124600000000, current: 0x124600000168, vec error info: 0xc9000000bd, mte error info: 0x7503000008, ifu error info: 0x212cf84100200, ccu error info: 0x40a414030000004f, cube error info: 0, biu error info: 0, aic error mask: 0x6500020bd00028c, para base: 0x12c100000000.[FUNC:PrintCoreInfo][FILE:device_error_core_proc.cc][LINE:645]
        TraceBack (most recent call last):
       The extend info: errcode:(0x10, 0, 0) errorStr: Illegal instruction, which is usually caused by unaligned UUB addresses. fixp_error0 info: 0x3000008, fixp_error1 info: 0x75, fsmId:1, tslot:3, thread:0, ctxid:0, blk:0, sublk:0, subErrType:4.[FUNC:PrintCoreInfo][FILE:device_error_core_proc.cc][LINE:658]
       Kernel task happen error, retCode=0x31, [vector core exception].[FUNC:PreCheckTaskErr][FILE:davinci_kernel_task.cc][LINE:1729]
       AIV Kernel happen error, retCode=0x31.[FUNC:GetError][FILE:stream.cc][LINE:1475]
       [AIC_INFO] after execute:args print end[FUNC:GetError][FILE:stream.cc][LINE:1475]
       [DFX_INFO]Aicore kernel execute failed, device_id=3, stream_id=46, report_stream_id=46, task_id=0, flip_num=0, fault kernel_name=comm_p2p_kernel, fault kernel info ext=comm_p2p_kernel, program id=0, hash=6260346515940177617.[FUNC:GetError][FILE:stream.cc][LINE:1475]
       rtStreamSynchronize execution failed, reason=vector core exception[FUNC:FuncErrorReason][FILE:error_message_manage.cc][LINE:65]
       synchronize stream failed, runtime result = 507035[FUNC:ReportCallError][FILE:log_inner.cpp][LINE:148]
[2026-08-03 04:30:05] ERROR: testcase failed (exit 1): comm_p2p