From 2413eab8479ee68d0c6a994e9a5b833840fb34bd Mon Sep 17 00:00:00 2001 From: Chinesezjc Date: Wed, 26 Aug 2026 23:31:33 +0800 Subject: [PATCH] ci: isolate non-Windows pnpm setup per run attempt Stacked on #3115: keep its windows-* setup-pnpm-js--- destination, and extend the same isolation to non-Windows jobs in ci.yml and ci-master.yml with setup-pnpm--. This prevents sequential self-hosted Windows jobs from tripping over a stale locked pnpm.exe/reflink native module. --- ...07-29-pnpm-setup-runner-isolation.i18n.yaml | 4 ++-- .../2026-07-29-pnpm-setup-runner-isolation.md | 2 +- ...026-07-29-pnpm-setup-runner-isolation.zh.md | 2 +- .github/workflows/ci-master.yml | 10 +++++----- .github/workflows/ci.yml | 10 +++++----- scripts/ci-workflow.spec.ts | 18 +++++++++--------- 6 files changed, 23 insertions(+), 23 deletions(-) diff --git a/.agents/notes/implemented/bug-fix/2026-07-29-pnpm-setup-runner-isolation.i18n.yaml b/.agents/notes/implemented/bug-fix/2026-07-29-pnpm-setup-runner-isolation.i18n.yaml index d87d9b8af7..01d1644420 100644 --- a/.agents/notes/implemented/bug-fix/2026-07-29-pnpm-setup-runner-isolation.i18n.yaml +++ b/.agents/notes/implemented/bug-fix/2026-07-29-pnpm-setup-runner-isolation.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/bug-fix/2026-07-29-pnpm-setup-runner-isolation.md -2026-07-29-pnpm-setup-runner-isolation.md: 40a34460171777a1cf2a8d2fb940d74012113c1c -2026-07-29-pnpm-setup-runner-isolation.zh.md: 4c307bc00e980975d35a1a0c3e776d5fe371cec9 +2026-07-29-pnpm-setup-runner-isolation.md: d5cd02cceba920368f0dfe6535e4bd03ee075417 +2026-07-29-pnpm-setup-runner-isolation.zh.md: 5266112224b940c06ea2567247532eb15ce7fce8 diff --git a/.agents/notes/implemented/bug-fix/2026-07-29-pnpm-setup-runner-isolation.md b/.agents/notes/implemented/bug-fix/2026-07-29-pnpm-setup-runner-isolation.md index 40a3446017..d5cd02cceb 100644 --- a/.agents/notes/implemented/bug-fix/2026-07-29-pnpm-setup-runner-isolation.md +++ b/.agents/notes/implemented/bug-fix/2026-07-29-pnpm-setup-runner-isolation.md @@ -10,7 +10,7 @@ English | [中文](2026-07-29-pnpm-setup-runner-isolation.zh.md) ## Decision -Every non-Windows `pnpm/action-setup` step in [the primary CI workflow](../../../../.github/workflows/ci.yml) and [the master workflow](../../../../.github/workflows/ci-master.yml) sets `dest: ${{ runner.temp }}/setup-pnpm`. Each runner service owns its temporary directory, so one setup cannot replace another runner's install directory. The Windows native jobs and the [python SDK exe build](../../../../.github/workflows/build-exe-for-python-sdk.yml) use a separate pnpm executable under `setup-pnpm-js-${{ github.run_id }}-${{ github.run_attempt }}-${{ github.job }}` (not `standalone: true`; the destination keeps that executable apart): the run/attempt/job suffix gives every job a fresh directory even when sequential jobs land on the same self-hosted runner and a previous job leaves a locked @reflink native module. Persistent store reuse remains separate through `PNPM_CONFIG_STORE_DIR`, as established by the [pnpm provisioning decision](../process/2026-07-26-pnpm-action-setup-for-symmetric-ci-caching.md). +Every non-Windows `pnpm/action-setup` step in [the primary CI workflow](../../../../.github/workflows/ci.yml) and [the master workflow](../../../../.github/workflows/ci-master.yml) sets `dest: ${{ runner.temp }}/setup-pnpm-${{ github.run_id }}-${{ github.run_attempt }}`. Each runner service owns its temporary directory, so one setup cannot replace another runner's install directory, and the run/attempt suffix also protects sequential jobs on the same runner from a stale locked `pnpm.exe`. The Windows native jobs and the [python SDK exe build](../../../../.github/workflows/build-exe-for-python-sdk.yml) use a separate pnpm executable under `setup-pnpm-js-${{ github.run_id }}-${{ github.run_attempt }}-${{ github.job }}` (not `standalone: true`; the destination keeps that executable apart): the run/attempt/job suffix gives every job a fresh directory even when sequential jobs land on the same self-hosted runner and a previous job leaves a locked @reflink native module. Persistent store reuse remains separate through `PNPM_CONFIG_STORE_DIR`, as established by the [pnpm provisioning decision](../process/2026-07-26-pnpm-action-setup-for-symmetric-ci-caching.md). [The workflow regression test](../../../../scripts/ci-workflow.spec.ts) discovers every `pnpm/action-setup` step in `ci.yml`, `ci-master.yml`, and `build-exe-for-python-sdk.yml` and rejects one without the runner-private destination. This keeps newly added jobs inside the same isolation boundary. diff --git a/.agents/notes/implemented/bug-fix/2026-07-29-pnpm-setup-runner-isolation.zh.md b/.agents/notes/implemented/bug-fix/2026-07-29-pnpm-setup-runner-isolation.zh.md index 4c307bc00e..5266112224 100644 --- a/.agents/notes/implemented/bug-fix/2026-07-29-pnpm-setup-runner-isolation.zh.md +++ b/.agents/notes/implemented/bug-fix/2026-07-29-pnpm-setup-runner-isolation.zh.md @@ -10,7 +10,7 @@ Status: implemented ## 决策 -[主 CI 工作流](../../../../.github/workflows/ci.yml)与 [CI master 工作流](../../../../.github/workflows/ci-master.yml)中的每个**非 Windows** `pnpm/action-setup` 步骤都设置 `dest: ${{ runner.temp }}/setup-pnpm`。每个 runner 服务独占自己的临时目录，因此一个设置过程无法替换另一个 runner 的安装目录。Windows 原生作业与 [python SDK exe 构建](../../../../.github/workflows/build-exe-for-python-sdk.yml)在 `setup-pnpm-js-${{ github.run_id }}-${{ github.run_attempt }}-${{ github.job }}` 下使用独立的 pnpm 可执行文件（非 `standalone: true`，目录本身起分离作用）：run/attempt/job 后缀让每次作业都使用全新目录，即使顺序作业落到同一自托管 runner、且前一作业留下被锁定的 @reflink 原生模块。持久 store 的复用仍由 `PNPM_CONFIG_STORE_DIR` 独立处理，遵循 [pnpm 配置决策](../process/2026-07-26-pnpm-action-setup-for-symmetric-ci-caching.zh.md)。 +[主 CI 工作流](../../../../.github/workflows/ci.yml)与 [CI master 工作流](../../../../.github/workflows/ci-master.yml)中的每个**非 Windows** `pnpm/action-setup` 步骤都设置 `dest: ${{ runner.temp }}/setup-pnpm-${{ github.run_id }}-${{ github.run_attempt }}`。每个 runner 服务独占自己的临时目录，因此一个设置过程无法替换另一个 runner 的安装目录；run/attempt 后缀还能防止同一 runner 上顺序作业因残留的锁定 `pnpm.exe` 而失败。Windows 原生作业与 [python SDK exe 构建](../../../../.github/workflows/build-exe-for-python-sdk.yml)在 `setup-pnpm-js-${{ github.run_id }}-${{ github.run_attempt }}-${{ github.job }}` 下使用独立的 pnpm 可执行文件（非 `standalone: true`，目录本身起分离作用）：run/attempt/job 后缀让每次作业都使用全新目录，即使顺序作业落到同一自托管 runner、且前一作业留下被锁定的 @reflink 原生模块。持久 store 的复用仍由 `PNPM_CONFIG_STORE_DIR` 独立处理，遵循 [pnpm 配置决策](../process/2026-07-26-pnpm-action-setup-for-symmetric-ci-caching.zh.md)。 [工作流回归测试](../../../../scripts/ci-workflow.spec.ts)会找出 `ci.yml`、`ci-master.yml` 与 `build-exe-for-python-sdk.yml` 中的每个 `pnpm/action-setup` 步骤，并拒绝缺少 runner 专属目标目录的步骤。这可确保后续新增的作业也处于同一隔离边界内。 diff --git a/.github/workflows/ci-master.yml b/.github/workflows/ci-master.yml index f324900c9e..b86720a5d3 100644 --- a/.github/workflows/ci-master.yml +++ b/.github/workflows/ci-master.yml @@ -87,7 +87,7 @@ jobs: - uses: pnpm/action-setup@v4 with: - dest: ${{ runner.temp }}/setup-pnpm + dest: ${{ runner.temp }}/setup-pnpm-${{ github.run_id }}-${{ github.run_attempt }} - uses: actions/setup-node@v6 with: @@ -131,7 +131,7 @@ jobs: - uses: pnpm/action-setup@v4 with: - dest: ${{ runner.temp }}/setup-pnpm + dest: ${{ runner.temp }}/setup-pnpm-${{ github.run_id }}-${{ github.run_attempt }} - uses: actions/setup-node@v6 with: @@ -176,7 +176,7 @@ jobs: - uses: pnpm/action-setup@v4 with: - dest: ${{ runner.temp }}/setup-pnpm + dest: ${{ runner.temp }}/setup-pnpm-${{ github.run_id }}-${{ github.run_attempt }} - uses: actions/setup-node@v6 with: @@ -264,7 +264,7 @@ jobs: - uses: pnpm/action-setup@v4 with: - dest: ${{ runner.temp }}/setup-pnpm + dest: ${{ runner.temp }}/setup-pnpm-${{ github.run_id }}-${{ github.run_attempt }} # The benchmark's Windows lanes deliberately skip the store cache like # the independent native Windows job; an empty input disables caching. @@ -355,7 +355,7 @@ jobs: - uses: pnpm/action-setup@v4 with: - dest: ${{ runner.temp }}/setup-pnpm + dest: ${{ runner.temp }}/setup-pnpm-${{ github.run_id }}-${{ github.run_attempt }} # Unlike the larger-runner suite, both platforms cache the store here: # the consolidated topology measures cache mechanics as workload. diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml index 45d345b9a3..e7f4ea86e8 100644 --- a/.github/workflows/ci.yml +++ b/.github/workflows/ci.yml @@ -55,7 +55,7 @@ jobs: - uses: pnpm/action-setup@v4 with: - dest: ${{ runner.temp }}/setup-pnpm + dest: ${{ runner.temp }}/setup-pnpm-${{ github.run_id }}-${{ github.run_attempt }} - uses: actions/setup-node@v6 with: @@ -109,7 +109,7 @@ jobs: - uses: pnpm/action-setup@v4 with: - dest: ${{ runner.temp }}/setup-pnpm + dest: ${{ runner.temp }}/setup-pnpm-${{ github.run_id }}-${{ github.run_attempt }} - uses: actions/setup-node@v6 with: @@ -173,7 +173,7 @@ jobs: - uses: pnpm/action-setup@v4 with: - dest: ${{ runner.temp }}/setup-pnpm + dest: ${{ runner.temp }}/setup-pnpm-${{ github.run_id }}-${{ github.run_attempt }} - uses: actions/setup-node@v6 with: @@ -261,7 +261,7 @@ jobs: - uses: pnpm/action-setup@v4 with: - dest: ${{ runner.temp }}/setup-pnpm + dest: ${{ runner.temp }}/setup-pnpm-${{ github.run_id }}-${{ github.run_attempt }} - uses: actions/setup-node@v6 with: @@ -329,7 +329,7 @@ jobs: - uses: pnpm/action-setup@v4 with: - dest: ${{ runner.temp }}/setup-pnpm + dest: ${{ runner.temp }}/setup-pnpm-${{ github.run_id }}-${{ github.run_attempt }} - uses: actions/setup-node@v6 with: diff --git a/scripts/ci-workflow.spec.ts b/scripts/ci-workflow.spec.ts index 6f4fa8d90d..0a59f36ae7 100644 --- a/scripts/ci-workflow.spec.ts +++ b/scripts/ci-workflow.spec.ts @@ -4,7 +4,7 @@ import * as yaml from 'js-yaml' import { describe, expect, it } from 'vitest' const root = resolve(import.meta.dirname, '..') -const runnerPrivatePnpmDestination = '${{ runner.temp }}/setup-pnpm' +const runnerPrivatePnpmDestination = /^\$\{\{ runner\.temp \}\}\/setup-pnpm-\$\{\{ github\.run_id \}\}-\$\{\{ github\.run_attempt \}\}$/ const nativeWindowsPnpmDestination = '${{ runner.temp }}/setup-pnpm-js-${{ github.run_id }}-${{ github.run_attempt }}-${{ github.job }}' describe('CI workflow', () => { @@ -25,14 +25,14 @@ describe('CI workflow', () => { expect(setups.length).toBeGreaterThan(0) for (const { jobName, step } of setups) { - expect(step, `${jobName} must not share pnpm/action-setup's default destination`).toMatchObject({ - with: { - dest: jobName.startsWith('windows-') - ? nativeWindowsPnpmDestination - : runnerPrivatePnpmDestination, - }, - }) - if (jobName.startsWith('windows-')) expect(step).not.toMatchObject({ with: { standalone: true } }) + const stepDest = (step as { with?: { dest?: unknown } }).with?.dest + if (jobName.startsWith('windows-')) { + expect(stepDest, `${jobName} must use the native Windows pnpm destination`).toBe(nativeWindowsPnpmDestination) + expect(step).not.toMatchObject({ with: { standalone: true } }) + } else { + expect(typeof stepDest, `${jobName} must use a runner-and-run-private pnpm destination`).toBe('string') + expect(stepDest as string).toMatch(runnerPrivatePnpmDestination) + } } })