From bdff8573b686773fc5d82ab71eb047e8cb7a48c8 Mon Sep 17 00:00:00 2001 From: Chinesezjc Date: Fri, 24 Jul 2026 12:44:00 +0800 Subject: [PATCH 01/36] ci: run coverage on in-house vm-backup pool Coverage does not gate merges, so move it off the metered dsh-enterprise-ubuntu-24-04-32core-test pool onto the in-house self-hosted pool (vm-backup label, 64-core). Also switch the pnpm store cache path to ~ so it resolves under both /home/runner (hosted) and self-hosted home directories. Verified on the self-hosted pool: the full coverage job (including prepare-ci-bubblewrap and the exhaustive suite) completed green in ~5 min. --- .github/workflows/ci.yml | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml index 2eceefa114..a2e70cab6f 100644 --- a/.github/workflows/ci.yml +++ b/.github/workflows/ci.yml @@ -77,7 +77,9 @@ jobs: node-24-coverage: if: github.event_name == 'pull_request' - runs-on: dsh-enterprise-ubuntu-24-04-32core-test + # Coverage does not gate merges, so it runs on the in-house pool + # (self-hosted, 64-core) instead of the metered enterprise pool. + runs-on: [self-hosted, linux, x64, vm-backup] name: node 24 / coverage env: DSH_COVERAGE_MAX_WORKERS: '24' @@ -89,7 +91,8 @@ jobs: - uses: actions/cache/restore@v4 with: - path: /home/runner/.local/share/pnpm/store/v11 + # ~ resolves on both hosted (/home/runner) and self-hosted homes + path: ~/.local/share/pnpm/store/v11 key: ${{ runner.os }}-node-${{ env.PRIMARY_NODE_VERSION }}-pnpm-${{ hashFiles('pnpm-lock.yaml') }} restore-keys: | ${{ runner.os }}-node-${{ env.PRIMARY_NODE_VERSION }}-pnpm- From 81890d7a994ab791c7db8bc93667caf21fc38f45 Mon Sep 17 00:00:00 2001 From: Chinesezjc Date: Fri, 24 Jul 2026 16:37:59 +0800 Subject: [PATCH 02/36] =?UTF-8?q?ci:=20address=20review=20=E2=80=94=20same?= =?UTF-8?q?-repo=20guard,=20keep=20cache=20path=20identical?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit - Restrict node-24-coverage to same-repo PRs so fork-originated code can never reach the self-hosted runner (defense in depth; the repo is private with forking disabled today). - Revert the pnpm cache path to the literal /home/runner/... save-side path: actions/cache hashes the path into the cache version, so the ~ variant could never match the cache saved by the master lane. On self-hosted the persistent local pnpm store covers warm installs. - Drop the incorrect 'does not gate merges' claim: node-24-coverage is needed by all-checks-passed. Pool capacity notes moved into comments. --- .github/workflows/ci.yml | 19 ++++++++++++++----- 1 file changed, 14 insertions(+), 5 deletions(-) diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml index a2e70cab6f..dd60593a85 100644 --- a/.github/workflows/ci.yml +++ b/.github/workflows/ci.yml @@ -76,9 +76,14 @@ jobs: compression-level: 0 node-24-coverage: - if: github.event_name == 'pull_request' - # Coverage does not gate merges, so it runs on the in-house pool - # (self-hosted, 64-core) instead of the metered enterprise pool. + # Same-repo PRs only: this lane runs on an in-house self-hosted runner, + # so fork-originated code must never land here. The repo is currently + # private with forking disabled; this guard keeps that invariant explicit + # if either setting ever changes. + if: github.event_name == 'pull_request' && github.event.pull_request.head.repo.full_name == github.repository + # Runs on the in-house pool (self-hosted, 64-core) instead of the metered + # enterprise pool. The pool holds 4 always-on instances plus 4 registered + # spares; the runner service is systemd-managed and self-healing. runs-on: [self-hosted, linux, x64, vm-backup] name: node 24 / coverage env: @@ -91,8 +96,12 @@ jobs: - uses: actions/cache/restore@v4 with: - # ~ resolves on both hosted (/home/runner) and self-hosted homes - path: ~/.local/share/pnpm/store/v11 + # Path must stay byte-identical to the save-side path in the master + # lane: actions/cache hashes the literal path into the cache version, + # so any variation (e.g. ~) would never match the saved cache. On + # self-hosted this restore simply misses and the persistent local + # pnpm store covers warm installs instead. + path: /home/runner/.local/share/pnpm/store/v11 key: ${{ runner.os }}-node-${{ env.PRIMARY_NODE_VERSION }}-pnpm-${{ hashFiles('pnpm-lock.yaml') }} restore-keys: | ${{ runner.os }}-node-${{ env.PRIMARY_NODE_VERSION }}-pnpm- From 5818fd62242f8799484fbf166c11f1fc8434bf48 Mon Sep 17 00:00:00 2001 From: Chinesezjc Date: Fri, 24 Jul 2026 23:00:56 +0800 Subject: [PATCH 03/36] =?UTF-8?q?ci:=20address=20second=20review=20round?= =?UTF-8?q?=20=E2=80=94=20dependabot=20lane,=20drop=20dead=20restore,=20up?= =?UTF-8?q?date=20topology=20note?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit - Route untrusted PRs (forks + Dependabot, same author test as e2e.yml) back to the hosted enterprise pool via a runs-on expression: Dependabot PRs are same-repo, so the previous head.repo guard admitted dependency-supplied code onto the persistent self-hosted VM. A single job with pool selection keeps all-checks-passed free of skips. - Drop the pnpm-store cache restore from this lane: on self-hosted the hosted-path cache actually HIT (Linux key) and spent ~52 s pulling 181 MB into a path pnpm never reads; the persistent local store already serves warm installs in seconds. - Update the larger-hosted-runners Agent Note (en/zh + i18n pairing record) so the decision record describes the shipped topology: coverage on the in-house vm-backup pool for trusted PRs, hosted Ubuntu 24.04 32-core retained for untrusted PRs. --- ...ence-based-larger-hosted-runners.i18n.yaml | 4 +- ...22-evidence-based-larger-hosted-runners.md | 2 +- ...evidence-based-larger-hosted-runners.zh.md | 2 +- .github/workflows/ci.yml | 39 +++++++++---------- 4 files changed, 23 insertions(+), 24 deletions(-) diff --git a/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.i18n.yaml b/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.i18n.yaml index 9d87cb9ad3..360395102e 100644 --- a/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.i18n.yaml +++ b/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.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 -2026-07-22-evidence-based-larger-hosted-runners.md: aaeab4ed9ae9687598f9f1d4a862120405697672 -2026-07-22-evidence-based-larger-hosted-runners.zh.md: 72b69c85908990a9f35b60f4c0a2ce213f9c8134 +2026-07-22-evidence-based-larger-hosted-runners.md: c3e6344ae61669da4810090e558589875ca7536e +2026-07-22-evidence-based-larger-hosted-runners.zh.md: e5b322673b7a1eb004eb15b3784d21f500e83719 diff --git a/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.md b/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.md index aaeab4ed9a..c3e6344ae6 100644 --- a/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.md +++ b/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.md @@ -12,7 +12,7 @@ Larger runners make it possible to pay setup once and parallelize inside the rep ## Decision -The enterprise keeps repo-restricted x64 larger-runner pools for Ubuntu and Windows. Ordinary pull requests name three 32-core pools directly: Ubuntu 24.04 for exhaustive coverage, Ubuntu latest for the remaining primary Node 24 inventory, and Windows 2025 for blocking Windows contracts. Public IPs are disabled, and workflow concurrency remains bounded because an autoscaling ceiling neither allocates idle machines nor makes repository work scale without limit. +The enterprise keeps repo-restricted x64 larger-runner pools for Ubuntu and Windows. Ordinary pull requests name two 32-core hosted pools directly: Ubuntu latest for the remaining primary Node 24 inventory and Windows 2025 for blocking Windows contracts. Exhaustive coverage moved off the metered Ubuntu 24.04 32-core pool onto the in-house self-hosted pool (`vm-backup` label: a 64-core VM running four always-on systemd-managed runner instances plus four registered spares) for trusted same-repo PRs; untrusted PRs — forks and Dependabot — keep coverage on the hosted Ubuntu 24.04 32-core pool so dependency-supplied code never reaches the persistent VM. Public IPs are disabled, and workflow concurrency remains bounded because an autoscaling ceiling neither allocates idle machines nor makes repository work scale without limit. The required primary path depends on those enterprise pools. Standard GitHub-hosted jobs retain the Node 22.19, Node 26, and Python SDK compatibility contracts, while the [portable recovery boundary](2026-07-23-portable-required-pull-request-ci.md) and [serial reference](2026-07-21-serial-cross-platform-ci-reference.md) keep complete standard-runner evidence available on `master`. `suite=larger-runner-benchmark` compares isolated critical lanes across provisioned sizes, and `suite=consolidated-runner-benchmark` compares whole aggregates. Each benchmark reports its observed processor and memory capacity before running repository work. diff --git a/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.zh.md b/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.zh.md index 72b69c8590..e5b322673b 100644 --- a/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.zh.md +++ b/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.zh.md @@ -12,7 +12,7 @@ Status: implemented ## 决策 -企业保留仅限本仓库使用的 Ubuntu 和 Windows x64 大型运行器池。普通拉取请求直接指定 3 个 32 核运行器池：Ubuntu 24.04 用于完整覆盖率，Ubuntu latest 用于其余主 Node 24 清单，Windows 2025 用于阻塞性 Windows 契约。公网 IP 已禁用；工作流并发仍设有边界，因为自动扩缩容上限既不会分配闲置机器，也不意味着仓库工作可以无限扩展。 +企业保留仅限本仓库使用的 Ubuntu 和 Windows x64 大型运行器池。普通拉取请求直接指定 2 个 32 核托管运行器池：Ubuntu latest 用于其余主 Node 24 清单，Windows 2025 用于阻塞性 Windows 契约。完整覆盖率已从计费的 Ubuntu 24.04 32 核池迁移至公司自有的自托管池（`vm-backup` 标签：一台 64 核虚拟机，运行 4 个常驻的 systemd 管理运行器实例，另有 4 个已注册备用位），仅面向可信的同仓库拉取请求；不可信的拉取请求——fork 与 Dependabot——的覆盖率仍在托管的 Ubuntu 24.04 32 核池上运行，确保依赖方提供的代码永远不会进入持久化虚拟机。公网 IP 已禁用；工作流并发仍设有边界，因为自动扩缩容上限既不会分配闲置机器，也不意味着仓库工作可以无限扩展。 必需主路径依赖这些企业级运行器池。GitHub 标准托管作业保留 Node 22.19、Node 26 和 Python SDK 兼容性契约，而[可移植恢复边界](2026-07-23-portable-required-pull-request-ci.md)与[串行参考流程](2026-07-21-serial-cross-platform-ci-reference.md)则在 `master` 上持续提供完整的标准运行器证据。`suite=larger-runner-benchmark` 比较已预配规格上相互独立的关键通道，`suite=consolidated-runner-benchmark` 则比较完整聚合流程。每项基准测试都会先报告实测的处理器和内存容量，再运行仓库工作。 diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml index dd60593a85..dc45bc9a7a 100644 --- a/.github/workflows/ci.yml +++ b/.github/workflows/ci.yml @@ -76,15 +76,19 @@ jobs: compression-level: 0 node-24-coverage: - # Same-repo PRs only: this lane runs on an in-house self-hosted runner, - # so fork-originated code must never land here. The repo is currently - # private with forking disabled; this guard keeps that invariant explicit - # if either setting ever changes. - if: github.event_name == 'pull_request' && github.event.pull_request.head.repo.full_name == github.repository - # Runs on the in-house pool (self-hosted, 64-core) instead of the metered - # enterprise pool. The pool holds 4 always-on instances plus 4 registered - # spares; the runner service is systemd-managed and self-healing. - runs-on: [self-hosted, linux, x64, vm-backup] + if: github.event_name == 'pull_request' + # Trusted same-repo PRs run on the in-house pool (self-hosted, 64-core; + # 4 always-on systemd-managed instances plus 4 registered spares) instead + # of the metered enterprise pool. Untrusted PRs — forks and Dependabot + # (same-repo but dependency-supplied code; same author test as e2e.yml) — + # stay on the hosted enterprise pool so no untrusted code reaches the + # persistent self-hosted VM. Selecting the pool via runs-on keeps this a + # single job, so the all-checks-passed aggregate never sees a skip. + runs-on: >- + ${{ (github.event.pull_request.head.repo.full_name != github.repository + || github.event.pull_request.user.login == 'dependabot[bot]') + && 'dsh-enterprise-ubuntu-24-04-32core-test' + || fromJSON('["self-hosted", "linux", "x64", "vm-backup"]') }} name: node 24 / coverage env: DSH_COVERAGE_MAX_WORKERS: '24' @@ -94,17 +98,12 @@ jobs: with: persist-credentials: false - - uses: actions/cache/restore@v4 - with: - # Path must stay byte-identical to the save-side path in the master - # lane: actions/cache hashes the literal path into the cache version, - # so any variation (e.g. ~) would never match the saved cache. On - # self-hosted this restore simply misses and the persistent local - # pnpm store covers warm installs instead. - path: /home/runner/.local/share/pnpm/store/v11 - key: ${{ runner.os }}-node-${{ env.PRIMARY_NODE_VERSION }}-pnpm-${{ hashFiles('pnpm-lock.yaml') }} - restore-keys: | - ${{ runner.os }}-node-${{ env.PRIMARY_NODE_VERSION }}-pnpm- + # No pnpm-store cache restore in this lane: on the self-hosted pool + # pnpm's persistent store lives outside /home/runner, so restoring the + # hosted cache here downloads ~180 MB into a path pnpm never reads + # (measured: 52 s restore, then a 2.8 s install straight from the + # persistent store). The rare hosted (untrusted-PR) run just does a + # cold install. - uses: actions/setup-node@v6 with: From e532c9ccc245a2360df74bb6d4795ea1f3c13162 Mon Sep 17 00:00:00 2001 From: Chinesezjc Date: Fri, 24 Jul 2026 23:12:20 +0800 Subject: [PATCH 04/36] ci: restore pnpm cache on the hosted leg only Keep the cache restore for the ephemeral hosted (untrusted-PR) leg where it is a genuine speedup, gated by the same expression as the runs-on pool selector; the self-hosted leg skips it and installs from the persistent local store. --- .github/workflows/ci.yml | 21 +++++++++++++++------ 1 file changed, 15 insertions(+), 6 deletions(-) diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml index dc45bc9a7a..d0d51fde9b 100644 --- a/.github/workflows/ci.yml +++ b/.github/workflows/ci.yml @@ -98,12 +98,21 @@ jobs: with: persist-credentials: false - # No pnpm-store cache restore in this lane: on the self-hosted pool - # pnpm's persistent store lives outside /home/runner, so restoring the - # hosted cache here downloads ~180 MB into a path pnpm never reads - # (measured: 52 s restore, then a 2.8 s install straight from the - # persistent store). The rare hosted (untrusted-PR) run just does a - # cold install. + # Restore the pnpm-store cache only on the hosted (untrusted-PR) leg, + # where the VM is ephemeral and the same-region download is fast. On + # the self-hosted leg pnpm's persistent store lives outside + # /home/runner, so this restore would spend ~52 s pulling ~180 MB into + # a path pnpm never reads (measured; install then took 2.8 s straight + # from the persistent store). Condition mirrors the runs-on selector. + - uses: actions/cache/restore@v4 + if: >- + github.event.pull_request.head.repo.full_name != github.repository + || github.event.pull_request.user.login == 'dependabot[bot]' + with: + path: /home/runner/.local/share/pnpm/store/v11 + key: ${{ runner.os }}-node-${{ env.PRIMARY_NODE_VERSION }}-pnpm-${{ hashFiles('pnpm-lock.yaml') }} + restore-keys: | + ${{ runner.os }}-node-${{ env.PRIMARY_NODE_VERSION }}-pnpm- - uses: actions/setup-node@v6 with: From 8d53d44b6055ce37aecdd22be1eb9d1429a96cae Mon Sep 17 00:00:00 2001 From: Chinesezjc Date: Fri, 24 Jul 2026 23:49:58 +0800 Subject: [PATCH 05/36] docs(ci): reconcile every present-tense topology description with the coverage lane move MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Sweep all remaining sources that still described coverage as an enterprise 32-core job: the ci.yml jobs preamble, the three-job paragraph of the larger-hosted-runners note, and the required-pool sentence of the portable-recovery note — English and Chinese sides of both notes, with their i18n pairing records re-recorded. --- ...026-07-22-evidence-based-larger-hosted-runners.i18n.yaml | 4 ++-- .../2026-07-22-evidence-based-larger-hosted-runners.md | 2 +- .../2026-07-22-evidence-based-larger-hosted-runners.zh.md | 2 +- .../2026-07-23-portable-required-pull-request-ci.i18n.yaml | 4 ++-- .../process/2026-07-23-portable-required-pull-request-ci.md | 2 +- .../2026-07-23-portable-required-pull-request-ci.zh.md | 2 +- .github/workflows/ci.yml | 6 ++++-- 7 files changed, 12 insertions(+), 10 deletions(-) diff --git a/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.i18n.yaml b/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.i18n.yaml index 360395102e..4d781caa54 100644 --- a/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.i18n.yaml +++ b/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.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 -2026-07-22-evidence-based-larger-hosted-runners.md: c3e6344ae61669da4810090e558589875ca7536e -2026-07-22-evidence-based-larger-hosted-runners.zh.md: e5b322673b7a1eb004eb15b3784d21f500e83719 +2026-07-22-evidence-based-larger-hosted-runners.md: 88b9e6d83777172d8afb6a391512e5f293b81171 +2026-07-22-evidence-based-larger-hosted-runners.zh.md: b1105f00cd08b1af633d258ea4ff28a835ce6074 diff --git a/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.md b/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.md index c3e6344ae6..88b9e6d837 100644 --- a/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.md +++ b/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.md @@ -18,7 +18,7 @@ The required primary path depends on those enterprise pools. Standard GitHub-hos The former gate-level and coarse primary shard jobs are absent from the workflow. Their static, lint, coverage, snapshot, and scenario shard selectors are also absent from the repository, so an unused diagnostic path cannot preserve a second CI architecture. -Linux primary work uses three independent 32-core jobs. Coverage runs alone with its own worker bound, and the static scheduler runs alone so its result has no post-build consumer tail. After static gates finish, that job publishes its emitted `apps/*/lib`, `packages/*/*/lib`, and `vendor/*/lib` tree as a run-scoped artifact. The third job restores that exact tree, then starts lint, Node 24 runtime compatibility, build-backed snapshots, and all artifact consumers without repeating the build. Generated NodeNext consumer directories are excluded from ESLint discovery because the artifact check removes them while these processes overlap. The pnpm store and ESLint cache are restored without putting cache uploads on the pull-request critical path. Performance reports use each job's `startedAt` to `completedAt` interval; runner queue delay is capacity evidence, not repository execution time. +Linux primary work uses three independent jobs: static gates and the consumer tail on hosted 32-core pools, and coverage on the in-house self-hosted 64-core pool for trusted PRs (hosted 32-core for untrusted ones). Coverage runs alone with its own worker bound, and the static scheduler runs alone so its result has no post-build consumer tail. After static gates finish, that job publishes its emitted `apps/*/lib`, `packages/*/*/lib`, and `vendor/*/lib` tree as a run-scoped artifact. The third job restores that exact tree, then starts lint, Node 24 runtime compatibility, build-backed snapshots, and all artifact consumers without repeating the build. Generated NodeNext consumer directories are excluded from ESLint discovery because the artifact check removes them while these processes overlap. The pnpm store and ESLint cache are restored without putting cache uploads on the pull-request critical path. Performance reports use each job's `startedAt` to `completedAt` interval; runner queue delay is capacity evidence, not repository execution time. Windows shares one 32-core setup across the blocking build and production site plus observational built-artifact contracts. Linux owns the duplicate lint, coverage, and snapshot inventories because running those observational copies on Windows extends the paid critical path without adding a blocking platform claim. diff --git a/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.zh.md b/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.zh.md index e5b322673b..b1105f00cd 100644 --- a/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.zh.md +++ b/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.zh.md @@ -18,7 +18,7 @@ Status: implemented 原有的门禁级和粗粒度主流程分片作业已从工作流中移除。相应的静态、lint、覆盖率、快照和场景分片选择器也已从仓库中移除，因此未使用的诊断路径无法继续维系第二套 CI 架构。 -Linux 主流程使用 3 个相互独立的 32 核作业。覆盖率单独运行，并设有自己的工作线程上限；静态调度器也单独运行，因此构建后的消费方不会拖延其结果。静态门禁完成后，该作业将其生成的 `apps/*/lib`、`packages/*/*/lib` 和 `vendor/*/lib` 目录树作为仅供本次运行使用的产物发布。第三个作业恢复完全相同的目录树，再让 lint、Node 24 运行时兼容性、依赖构建产物的快照和所有产物消费方基于构建完成后的工作树启动，而不重复构建。生成的 NodeNext 消费方目录不会纳入 ESLint 的文件发现范围，因为这些进程重叠执行时，产物检查会删除这些目录。pnpm store 和 ESLint 缓存会得到恢复，但缓存上传不会进入拉取请求关键路径。性能报告采用每个作业从 `startedAt` 到 `completedAt` 的区间；运行器排队延迟是容量证据，而非仓库执行时间。 +Linux 主流程使用 3 个相互独立的作业：静态门禁与消费方尾部作业运行在托管 32 核池上，覆盖率对可信拉取请求运行在公司自有的自托管 64 核池上（不可信请求仍用托管 32 核池）。覆盖率单独运行，并设有自己的工作线程上限；静态调度器也单独运行，因此构建后的消费方不会拖延其结果。静态门禁完成后，该作业将其生成的 `apps/*/lib`、`packages/*/*/lib` 和 `vendor/*/lib` 目录树作为仅供本次运行使用的产物发布。第三个作业恢复完全相同的目录树，再让 lint、Node 24 运行时兼容性、依赖构建产物的快照和所有产物消费方基于构建完成后的工作树启动，而不重复构建。生成的 NodeNext 消费方目录不会纳入 ESLint 的文件发现范围，因为这些进程重叠执行时，产物检查会删除这些目录。pnpm store 和 ESLint 缓存会得到恢复，但缓存上传不会进入拉取请求关键路径。性能报告采用每个作业从 `startedAt` 到 `completedAt` 的区间；运行器排队延迟是容量证据，而非仓库执行时间。 Windows 以一次 32 核环境设置同时承载阻塞性构建、生产网站和观测性的构建产物契约。重复的 lint、覆盖率和快照清单由 Linux 承担，因为在 Windows 上运行这些观测性副本会延长付费关键路径，却不会新增任何阻塞性平台契约。 diff --git a/.agents/notes/implemented/process/2026-07-23-portable-required-pull-request-ci.i18n.yaml b/.agents/notes/implemented/process/2026-07-23-portable-required-pull-request-ci.i18n.yaml index f8b54b0ec5..ed97fe08a7 100644 --- a/.agents/notes/implemented/process/2026-07-23-portable-required-pull-request-ci.i18n.yaml +++ b/.agents/notes/implemented/process/2026-07-23-portable-required-pull-request-ci.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 -2026-07-23-portable-required-pull-request-ci.md: 9cf8d97016300c5258c075879176aa6abd64e59e -2026-07-23-portable-required-pull-request-ci.zh.md: c6839a133d0c3fe7a699362f6168e17d827a5b61 +2026-07-23-portable-required-pull-request-ci.md: 29b2cfa3f431a4a8be4aaa685b16cffdb4bf2593 +2026-07-23-portable-required-pull-request-ci.zh.md: 8b6d067637ce83c09529977f463f16dfa4af5a8b diff --git a/.agents/notes/implemented/process/2026-07-23-portable-required-pull-request-ci.md b/.agents/notes/implemented/process/2026-07-23-portable-required-pull-request-ci.md index 9cf8d97016..29b2cfa3f4 100644 --- a/.agents/notes/implemented/process/2026-07-23-portable-required-pull-request-ci.md +++ b/.agents/notes/implemented/process/2026-07-23-portable-required-pull-request-ci.md @@ -12,7 +12,7 @@ Billing health, a runner definition's `Ready` state, and a large autoscaling cei ## Decision -[CI](../../../../.github/workflows/ci.yml) runs the required primary Node 24 and Windows jobs on repo-restricted enterprise 32-core pools. Standard `ubuntu-latest` jobs retain Node 22.19, Node 26, and Python SDK compatibility, and `master` runs complete serial Linux, macOS, and Windows references. Those standard-hosted jobs keep the portable execution boundary observable without duplicating the primary inventory on every pull request. +[CI](../../../../.github/workflows/ci.yml) runs the required primary Node 24 and Windows jobs on repo-restricted enterprise 32-core pools, except exhaustive coverage, which runs on the in-house self-hosted 64-core pool for trusted same-repo pull requests (hosted 32-core for forks and Dependabot). Standard `ubuntu-latest` jobs retain Node 22.19, Node 26, and Python SDK compatibility, and `master` runs complete serial Linux, macOS, and Windows references. Those standard-hosted jobs keep the portable execution boundary observable without duplicating the primary inventory on every pull request. The two Linux primary jobs, Node compatibility, Python SDK, and `windows node 24 / complete` remain dependencies of `all checks passed`; branch protection continues to require `e2e` and `all checks passed`. There is no automatic fallback when an enterprise label cannot allocate: the standard jobs continue to report their own contracts, but they cannot manufacture the missing required result. diff --git a/.agents/notes/implemented/process/2026-07-23-portable-required-pull-request-ci.zh.md b/.agents/notes/implemented/process/2026-07-23-portable-required-pull-request-ci.zh.md index c6839a133d..8b6d067637 100644 --- a/.agents/notes/implemented/process/2026-07-23-portable-required-pull-request-ci.zh.md +++ b/.agents/notes/implemented/process/2026-07-23-portable-required-pull-request-ci.zh.md @@ -12,7 +12,7 @@ Status: implemented ## 决策 -[CI](../../../../.github/workflows/ci.yml) 在仅限本仓库使用的企业级 32 核运行器池上运行必需的主 Node 24 作业和 Windows 作业。标准 `ubuntu-latest` 作业保留 Node 22.19、Node 26 和 Python SDK 兼容性，`master` 则运行完整的 Linux、macOS 和 Windows 串行参考流程。这些标准托管作业让可移植执行边界保持可观测，而不必在每个拉取请求中重复主清单。 +[CI](../../../../.github/workflows/ci.yml) 在仅限本仓库使用的企业级 32 核运行器池上运行必需的主 Node 24 作业和 Windows 作业；唯一例外是完整覆盖率——可信的同仓库拉取请求在公司自有的自托管 64 核池上运行（fork 与 Dependabot 仍用托管 32 核池）。标准 `ubuntu-latest` 作业保留 Node 22.19、Node 26 和 Python SDK 兼容性，`master` 则运行完整的 Linux、macOS 和 Windows 串行参考流程。这些标准托管作业让可移植执行边界保持可观测，而不必在每个拉取请求中重复主清单。 两项 Linux 主作业、Node 兼容性、Python SDK 和 `windows node 24 / complete` 继续作为 `all checks passed` 的依赖项；分支保护继续要求 `e2e` 和 `all checks passed`。企业级运行器标签无法分配运行器时没有自动后备机制：标准作业会继续报告各自的契约，但无法产出缺失的必需结果。 diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml index d0d51fde9b..a21086754b 100644 --- a/.github/workflows/ci.yml +++ b/.github/workflows/ci.yml @@ -27,8 +27,10 @@ env: jobs: - # Three enterprise jobs isolate coverage, static analysis, and the - # build-backed consumer tail. The static job publishes its exact build so + # Three independent Linux jobs isolate coverage, static analysis, and the + # build-backed consumer tail: static and consumers on hosted enterprise + # 32-core pools; coverage on the in-house self-hosted pool for trusted PRs + # (hosted for forks/Dependabot). The static job publishes its exact build so # consumers do not repeat the longest part of their critical path. node-24: if: github.event_name == 'pull_request' From 1a5d892ec53beb5f1b7212decfc2a10bd9ea2741 Mon Sep 17 00:00:00 2001 From: Chinesezjc Date: Sat, 25 Jul 2026 00:45:31 +0800 Subject: [PATCH 06/36] ci: halve coverage workers on the shared self-hosted leg MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The hosted 32-core runner is exclusive to one job, but the vm-backup pool shares one 64-core VM across four runner instances; concurrent PRs could stack 4×24 = 96 Vitest workers and re-trigger the documented aggregate-contention failures in the timing-sensitive process suites. Bound the self-hosted leg at 12 workers per job (48 host-wide fully loaded) and keep 24 on the hosted leg, selected by the same expression as the pool. --- .github/workflows/ci.yml | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml index a21086754b..dc5ad98ec4 100644 --- a/.github/workflows/ci.yml +++ b/.github/workflows/ci.yml @@ -93,7 +93,16 @@ jobs: || fromJSON('["self-hosted", "linux", "x64", "vm-backup"]') }} name: node 24 / coverage env: - DSH_COVERAGE_MAX_WORKERS: '24' + # Worker bound is per-leg: the hosted 32-core runner is exclusive to + # one job, but the self-hosted pool shares one 64-core VM across four + # runner instances, so concurrent PRs would otherwise stack up to + # 4×24 = 96 workers and re-trigger the aggregate-contention failures + # documented for the timing-sensitive process suites. 12 per job caps + # the shared host at 48 workers even fully loaded. + DSH_COVERAGE_MAX_WORKERS: >- + ${{ (github.event.pull_request.head.repo.full_name != github.repository + || github.event.pull_request.user.login == 'dependabot[bot]') + && '24' || '12' }} DSH_GATE_CONCURRENCY: '8' steps: - uses: actions/checkout@v6 From f09539581d33a5110c97d81cfe2778c74337690e Mon Sep 17 00:00:00 2001 From: Chinesezjc Date: Sat, 25 Jul 2026 00:54:35 +0800 Subject: [PATCH 07/36] docs(ci): record disabled forking as an explicit precondition of the self-hosted lane MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The pool selector is defense-in-depth only — pull_request executes the PR's own workflow definition, so YAML cannot enforce runner trust. Make the actual enforcement boundary explicit in the decision record: org-side disabled forking (the public release is an isolated read-only mirror under a separate org), with migration to a repo-restricted org-level runner group with base-branch workflow pinning as a hard gate before forking could ever be enabled. --- .../2026-07-22-evidence-based-larger-hosted-runners.i18n.yaml | 4 ++-- .../2026-07-22-evidence-based-larger-hosted-runners.md | 2 +- .../2026-07-22-evidence-based-larger-hosted-runners.zh.md | 2 +- 3 files changed, 4 insertions(+), 4 deletions(-) diff --git a/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.i18n.yaml b/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.i18n.yaml index 4d781caa54..ea3a57e072 100644 --- a/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.i18n.yaml +++ b/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.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 -2026-07-22-evidence-based-larger-hosted-runners.md: 88b9e6d83777172d8afb6a391512e5f293b81171 -2026-07-22-evidence-based-larger-hosted-runners.zh.md: b1105f00cd08b1af633d258ea4ff28a835ce6074 +2026-07-22-evidence-based-larger-hosted-runners.md: 497c6f297d79245fb40cd30457e4b1d1e36db651 +2026-07-22-evidence-based-larger-hosted-runners.zh.md: bcb0c6e9f11081b2cff696a9b6b425a40ee4aeb4 diff --git a/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.md b/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.md index 88b9e6d837..497c6f297d 100644 --- a/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.md +++ b/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.md @@ -12,7 +12,7 @@ Larger runners make it possible to pay setup once and parallelize inside the rep ## Decision -The enterprise keeps repo-restricted x64 larger-runner pools for Ubuntu and Windows. Ordinary pull requests name two 32-core hosted pools directly: Ubuntu latest for the remaining primary Node 24 inventory and Windows 2025 for blocking Windows contracts. Exhaustive coverage moved off the metered Ubuntu 24.04 32-core pool onto the in-house self-hosted pool (`vm-backup` label: a 64-core VM running four always-on systemd-managed runner instances plus four registered spares) for trusted same-repo PRs; untrusted PRs — forks and Dependabot — keep coverage on the hosted Ubuntu 24.04 32-core pool so dependency-supplied code never reaches the persistent VM. Public IPs are disabled, and workflow concurrency remains bounded because an autoscaling ceiling neither allocates idle machines nor makes repository work scale without limit. +The enterprise keeps repo-restricted x64 larger-runner pools for Ubuntu and Windows. Ordinary pull requests name two 32-core hosted pools directly: Ubuntu latest for the remaining primary Node 24 inventory and Windows 2025 for blocking Windows contracts. Exhaustive coverage moved off the metered Ubuntu 24.04 32-core pool onto the in-house self-hosted pool (`vm-backup` label: a 64-core VM running four always-on systemd-managed runner instances plus four registered spares) for trusted same-repo PRs; untrusted PRs — forks and Dependabot — keep coverage on the hosted Ubuntu 24.04 32-core pool so dependency-supplied code never reaches the persistent VM. **Precondition: repository forking stays disabled.** The workflow's pool selector is defense-in-depth only — `pull_request` executes the PR's own workflow definition, so YAML cannot enforce runner trust against a fork that edits it. Disabled forking (org-side, not PR-editable) is the enforcement boundary; the planned public release is an isolated read-only mirror under a separate org, preserving this. Before forking is ever enabled, the runners must first move into an org-level runner group restricted to this repository with base-branch workflow pinning — that migration is the gate, not a follow-up. Public IPs are disabled, and workflow concurrency remains bounded because an autoscaling ceiling neither allocates idle machines nor makes repository work scale without limit. The required primary path depends on those enterprise pools. Standard GitHub-hosted jobs retain the Node 22.19, Node 26, and Python SDK compatibility contracts, while the [portable recovery boundary](2026-07-23-portable-required-pull-request-ci.md) and [serial reference](2026-07-21-serial-cross-platform-ci-reference.md) keep complete standard-runner evidence available on `master`. `suite=larger-runner-benchmark` compares isolated critical lanes across provisioned sizes, and `suite=consolidated-runner-benchmark` compares whole aggregates. Each benchmark reports its observed processor and memory capacity before running repository work. diff --git a/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.zh.md b/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.zh.md index b1105f00cd..bcb0c6e9f1 100644 --- a/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.zh.md +++ b/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.zh.md @@ -12,7 +12,7 @@ Status: implemented ## 决策 -企业保留仅限本仓库使用的 Ubuntu 和 Windows x64 大型运行器池。普通拉取请求直接指定 2 个 32 核托管运行器池：Ubuntu latest 用于其余主 Node 24 清单，Windows 2025 用于阻塞性 Windows 契约。完整覆盖率已从计费的 Ubuntu 24.04 32 核池迁移至公司自有的自托管池（`vm-backup` 标签：一台 64 核虚拟机，运行 4 个常驻的 systemd 管理运行器实例，另有 4 个已注册备用位），仅面向可信的同仓库拉取请求；不可信的拉取请求——fork 与 Dependabot——的覆盖率仍在托管的 Ubuntu 24.04 32 核池上运行，确保依赖方提供的代码永远不会进入持久化虚拟机。公网 IP 已禁用；工作流并发仍设有边界，因为自动扩缩容上限既不会分配闲置机器，也不意味着仓库工作可以无限扩展。 +企业保留仅限本仓库使用的 Ubuntu 和 Windows x64 大型运行器池。普通拉取请求直接指定 2 个 32 核托管运行器池：Ubuntu latest 用于其余主 Node 24 清单，Windows 2025 用于阻塞性 Windows 契约。完整覆盖率已从计费的 Ubuntu 24.04 32 核池迁移至公司自有的自托管池（`vm-backup` 标签：一台 64 核虚拟机，运行 4 个常驻的 systemd 管理运行器实例，另有 4 个已注册备用位），仅面向可信的同仓库拉取请求；不可信的拉取请求——fork 与 Dependabot——的覆盖率仍在托管的 Ubuntu 24.04 32 核池上运行，确保依赖方提供的代码永远不会进入持久化虚拟机。**前置条件：仓库必须保持禁用 fork。**工作流中的运行器池选择表达式仅是纵深防御——`pull_request` 执行的是拉取请求自带的工作流定义，因此 YAML 无法对能修改它的 fork 实施运行器信任约束。真正的强制边界是组织侧（拉取请求无法修改）的 fork 禁用设置；规划中的开源发布采用独立组织下的只读镜像仓库，正是为了保持这一边界。将来若要启用 fork，必须先把运行器迁入组织级 runner group（限定本仓库并绑定基线分支工作流）——该迁移是启用 fork 的先决门槛，而非事后跟进项。公网 IP 已禁用；工作流并发仍设有边界，因为自动扩缩容上限既不会分配闲置机器，也不意味着仓库工作可以无限扩展。 必需主路径依赖这些企业级运行器池。GitHub 标准托管作业保留 Node 22.19、Node 26 和 Python SDK 兼容性契约，而[可移植恢复边界](2026-07-23-portable-required-pull-request-ci.md)与[串行参考流程](2026-07-21-serial-cross-platform-ci-reference.md)则在 `master` 上持续提供完整的标准运行器证据。`suite=larger-runner-benchmark` 比较已预配规格上相互独立的关键通道，`suite=consolidated-runner-benchmark` 则比较完整聚合流程。每项基准测试都会先报告实测的处理器和内存容量，再运行仓库工作。 From 310a387b144526354bec79ab8f913cd419fcf570 Mon Sep 17 00:00:00 2001 From: Chinesezjc Date: Sun, 26 Jul 2026 00:08:26 +0800 Subject: [PATCH 08/36] =?UTF-8?q?ci:=20pivot=20=E2=80=94=20keep=20coverage?= =?UTF-8?q?=20hosted,=20add=20self-hosted=20serial=20standby=20lane?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Direction change after review discussion. Moving a REQUIRED check onto a single in-house VM traded merge-path availability for modest savings and accumulated trust/contention caveats (six review rounds' worth). Revert every coverage-lane change: coverage stays on the enterprise Ubuntu 24.04 32-core pool exactly as on master. Instead, add serial-linux-selfhosted: on every master push the in-house pool (vm-backup) runs the complete unsharded primary aggregate as a hot-standby drill. It blocks nothing, yet continuously proves the environment end to end, so any hosted-pool outage can be answered with a one-line runs-on retarget onto continuously verified capacity. Push-triggered lanes execute the base branch's own workflow definition, so no PR-editable path selects these runners — the entire fork-trust discussion is structurally moot for this lane. Topology notes (en/zh + pairing records) describe the standby lane and the switch play. --- ...ence-based-larger-hosted-runners.i18n.yaml | 4 +- ...22-evidence-based-larger-hosted-runners.md | 6 +- ...evidence-based-larger-hosted-runners.zh.md | 6 +- ...ortable-required-pull-request-ci.i18n.yaml | 4 +- ...07-23-portable-required-pull-request-ci.md | 2 +- ...23-portable-required-pull-request-ci.zh.md | 2 +- .github/workflows/ci.yml | 78 ++++++++++--------- 7 files changed, 57 insertions(+), 45 deletions(-) diff --git a/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.i18n.yaml b/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.i18n.yaml index ea3a57e072..1b14f5b689 100644 --- a/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.i18n.yaml +++ b/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.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 -2026-07-22-evidence-based-larger-hosted-runners.md: 497c6f297d79245fb40cd30457e4b1d1e36db651 -2026-07-22-evidence-based-larger-hosted-runners.zh.md: bcb0c6e9f11081b2cff696a9b6b425a40ee4aeb4 +2026-07-22-evidence-based-larger-hosted-runners.md: 6654f5eb3e21b48c6d33fd9d74ebd23cf3065d54 +2026-07-22-evidence-based-larger-hosted-runners.zh.md: 3fe5715b20d3b881f8fb439b61900bdb84e5a588 diff --git a/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.md b/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.md index 497c6f297d..6654f5eb3e 100644 --- a/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.md +++ b/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.md @@ -12,13 +12,13 @@ Larger runners make it possible to pay setup once and parallelize inside the rep ## Decision -The enterprise keeps repo-restricted x64 larger-runner pools for Ubuntu and Windows. Ordinary pull requests name two 32-core hosted pools directly: Ubuntu latest for the remaining primary Node 24 inventory and Windows 2025 for blocking Windows contracts. Exhaustive coverage moved off the metered Ubuntu 24.04 32-core pool onto the in-house self-hosted pool (`vm-backup` label: a 64-core VM running four always-on systemd-managed runner instances plus four registered spares) for trusted same-repo PRs; untrusted PRs — forks and Dependabot — keep coverage on the hosted Ubuntu 24.04 32-core pool so dependency-supplied code never reaches the persistent VM. **Precondition: repository forking stays disabled.** The workflow's pool selector is defense-in-depth only — `pull_request` executes the PR's own workflow definition, so YAML cannot enforce runner trust against a fork that edits it. Disabled forking (org-side, not PR-editable) is the enforcement boundary; the planned public release is an isolated read-only mirror under a separate org, preserving this. Before forking is ever enabled, the runners must first move into an org-level runner group restricted to this repository with base-branch workflow pinning — that migration is the gate, not a follow-up. Public IPs are disabled, and workflow concurrency remains bounded because an autoscaling ceiling neither allocates idle machines nor makes repository work scale without limit. +The enterprise keeps repo-restricted x64 larger-runner pools for Ubuntu and Windows. Ordinary pull requests name three 32-core pools directly: Ubuntu 24.04 for exhaustive coverage, Ubuntu latest for the remaining primary Node 24 inventory, and Windows 2025 for blocking Windows contracts. Public IPs are disabled, and workflow concurrency remains bounded because an autoscaling ceiling neither allocates idle machines nor makes repository work scale without limit. The required primary path depends on those enterprise pools. Standard GitHub-hosted jobs retain the Node 22.19, Node 26, and Python SDK compatibility contracts, while the [portable recovery boundary](2026-07-23-portable-required-pull-request-ci.md) and [serial reference](2026-07-21-serial-cross-platform-ci-reference.md) keep complete standard-runner evidence available on `master`. `suite=larger-runner-benchmark` compares isolated critical lanes across provisioned sizes, and `suite=consolidated-runner-benchmark` compares whole aggregates. Each benchmark reports its observed processor and memory capacity before running repository work. The former gate-level and coarse primary shard jobs are absent from the workflow. Their static, lint, coverage, snapshot, and scenario shard selectors are also absent from the repository, so an unused diagnostic path cannot preserve a second CI architecture. -Linux primary work uses three independent jobs: static gates and the consumer tail on hosted 32-core pools, and coverage on the in-house self-hosted 64-core pool for trusted PRs (hosted 32-core for untrusted ones). Coverage runs alone with its own worker bound, and the static scheduler runs alone so its result has no post-build consumer tail. After static gates finish, that job publishes its emitted `apps/*/lib`, `packages/*/*/lib`, and `vendor/*/lib` tree as a run-scoped artifact. The third job restores that exact tree, then starts lint, Node 24 runtime compatibility, build-backed snapshots, and all artifact consumers without repeating the build. Generated NodeNext consumer directories are excluded from ESLint discovery because the artifact check removes them while these processes overlap. The pnpm store and ESLint cache are restored without putting cache uploads on the pull-request critical path. Performance reports use each job's `startedAt` to `completedAt` interval; runner queue delay is capacity evidence, not repository execution time. +Linux primary work uses three independent 32-core jobs. Coverage runs alone with its own worker bound, and the static scheduler runs alone so its result has no post-build consumer tail. After static gates finish, that job publishes its emitted `apps/*/lib`, `packages/*/*/lib`, and `vendor/*/lib` tree as a run-scoped artifact. The third job restores that exact tree, then starts lint, Node 24 runtime compatibility, build-backed snapshots, and all artifact consumers without repeating the build. Generated NodeNext consumer directories are excluded from ESLint discovery because the artifact check removes them while these processes overlap. The pnpm store and ESLint cache are restored without putting cache uploads on the pull-request critical path. Performance reports use each job's `startedAt` to `completedAt` interval; runner queue delay is capacity evidence, not repository execution time. Windows shares one 32-core setup across the blocking build and production site plus observational built-artifact contracts. Linux owns the duplicate lint, coverage, and snapshot inventories because running those observational copies on Windows extends the paid critical path without adding a blocking platform claim. @@ -48,6 +48,8 @@ The process-bound coverage project contains exactly five suite files. Thirty-two Complete serial Linux, macOS, and Windows references run only when `master` moves. Pull requests use the enterprise required path plus standard-hosted compatibility jobs, while other larger-runner sizes run only by manual dispatch. +An additional serial Linux reference runs on the in-house self-hosted pool (`vm-backup` label: a 64-core VM with four always-on systemd-managed runner instances plus four registered spares) on every `master` push. It is a hot-standby drill, not a required check: each run re-proves that the persistent VM can execute the complete unsharded aggregate, so if the enterprise pools degrade, a required lane can be retargeted with a one-line `runs-on` change onto an environment with continuously verified evidence. Because the lane is push-triggered, it always executes the base branch's workflow definition — no pull-request-editable path can route code to these runners, and the repository additionally keeps forking disabled. + ## Alternatives considered **Keep the three coarse primary Linux lanes.** The core, CPU, and production-site jobs met the latency targets, but they paid three setup waves and left primary Node work sharded after larger runners were available. The all-size trace showed that one unnecessary dependency, not a lack of host capacity, kept the single-box aggregate above one minute. diff --git a/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.zh.md b/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.zh.md index bcb0c6e9f1..3fe5715b20 100644 --- a/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.zh.md +++ b/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.zh.md @@ -12,13 +12,13 @@ Status: implemented ## 决策 -企业保留仅限本仓库使用的 Ubuntu 和 Windows x64 大型运行器池。普通拉取请求直接指定 2 个 32 核托管运行器池：Ubuntu latest 用于其余主 Node 24 清单，Windows 2025 用于阻塞性 Windows 契约。完整覆盖率已从计费的 Ubuntu 24.04 32 核池迁移至公司自有的自托管池（`vm-backup` 标签：一台 64 核虚拟机，运行 4 个常驻的 systemd 管理运行器实例，另有 4 个已注册备用位），仅面向可信的同仓库拉取请求；不可信的拉取请求——fork 与 Dependabot——的覆盖率仍在托管的 Ubuntu 24.04 32 核池上运行，确保依赖方提供的代码永远不会进入持久化虚拟机。**前置条件：仓库必须保持禁用 fork。**工作流中的运行器池选择表达式仅是纵深防御——`pull_request` 执行的是拉取请求自带的工作流定义，因此 YAML 无法对能修改它的 fork 实施运行器信任约束。真正的强制边界是组织侧（拉取请求无法修改）的 fork 禁用设置；规划中的开源发布采用独立组织下的只读镜像仓库，正是为了保持这一边界。将来若要启用 fork，必须先把运行器迁入组织级 runner group（限定本仓库并绑定基线分支工作流）——该迁移是启用 fork 的先决门槛，而非事后跟进项。公网 IP 已禁用；工作流并发仍设有边界，因为自动扩缩容上限既不会分配闲置机器，也不意味着仓库工作可以无限扩展。 +企业保留仅限本仓库使用的 Ubuntu 和 Windows x64 大型运行器池。普通拉取请求直接指定 3 个 32 核运行器池：Ubuntu 24.04 用于完整覆盖率，Ubuntu latest 用于其余主 Node 24 清单，Windows 2025 用于阻塞性 Windows 契约。公网 IP 已禁用；工作流并发仍设有边界，因为自动扩缩容上限既不会分配闲置机器，也不意味着仓库工作可以无限扩展。 必需主路径依赖这些企业级运行器池。GitHub 标准托管作业保留 Node 22.19、Node 26 和 Python SDK 兼容性契约，而[可移植恢复边界](2026-07-23-portable-required-pull-request-ci.md)与[串行参考流程](2026-07-21-serial-cross-platform-ci-reference.md)则在 `master` 上持续提供完整的标准运行器证据。`suite=larger-runner-benchmark` 比较已预配规格上相互独立的关键通道，`suite=consolidated-runner-benchmark` 则比较完整聚合流程。每项基准测试都会先报告实测的处理器和内存容量，再运行仓库工作。 原有的门禁级和粗粒度主流程分片作业已从工作流中移除。相应的静态、lint、覆盖率、快照和场景分片选择器也已从仓库中移除，因此未使用的诊断路径无法继续维系第二套 CI 架构。 -Linux 主流程使用 3 个相互独立的作业：静态门禁与消费方尾部作业运行在托管 32 核池上，覆盖率对可信拉取请求运行在公司自有的自托管 64 核池上（不可信请求仍用托管 32 核池）。覆盖率单独运行，并设有自己的工作线程上限；静态调度器也单独运行，因此构建后的消费方不会拖延其结果。静态门禁完成后，该作业将其生成的 `apps/*/lib`、`packages/*/*/lib` 和 `vendor/*/lib` 目录树作为仅供本次运行使用的产物发布。第三个作业恢复完全相同的目录树，再让 lint、Node 24 运行时兼容性、依赖构建产物的快照和所有产物消费方基于构建完成后的工作树启动，而不重复构建。生成的 NodeNext 消费方目录不会纳入 ESLint 的文件发现范围，因为这些进程重叠执行时，产物检查会删除这些目录。pnpm store 和 ESLint 缓存会得到恢复，但缓存上传不会进入拉取请求关键路径。性能报告采用每个作业从 `startedAt` 到 `completedAt` 的区间；运行器排队延迟是容量证据，而非仓库执行时间。 +Linux 主流程使用 3 个相互独立的 32 核作业。覆盖率单独运行，并设有自己的工作线程上限；静态调度器也单独运行，因此构建后的消费方不会拖延其结果。静态门禁完成后，该作业将其生成的 `apps/*/lib`、`packages/*/*/lib` 和 `vendor/*/lib` 目录树作为仅供本次运行使用的产物发布。第三个作业恢复完全相同的目录树，再让 lint、Node 24 运行时兼容性、依赖构建产物的快照和所有产物消费方基于构建完成后的工作树启动，而不重复构建。生成的 NodeNext 消费方目录不会纳入 ESLint 的文件发现范围，因为这些进程重叠执行时，产物检查会删除这些目录。pnpm store 和 ESLint 缓存会得到恢复，但缓存上传不会进入拉取请求关键路径。性能报告采用每个作业从 `startedAt` 到 `completedAt` 的区间；运行器排队延迟是容量证据，而非仓库执行时间。 Windows 以一次 32 核环境设置同时承载阻塞性构建、生产网站和观测性的构建产物契约。重复的 lint、覆盖率和快照清单由 Linux 承担，因为在 Windows 上运行这些观测性副本会延长付费关键路径，却不会新增任何阻塞性平台契约。 @@ -48,6 +48,8 @@ Windows 仓库工作在超过 16 核后收益很小，但 32 核池可以让完 只有在 `master` 移动时，才运行完整的 Linux、macOS 和 Windows 串行参考。拉取请求使用企业级运行器必需路径和标准托管兼容性作业，其他大型运行器规格仅通过手动触发运行。 +另有一条串行 Linux 参考在每次 `master` 推送时运行于公司自有的自托管池（`vm-backup` 标签：一台 64 核虚拟机，运行 4 个常驻的 systemd 管理运行器实例，另有 4 个已注册备用位）。它是热备演练而非必需检查：每次运行都重新证明这台持久化虚拟机能够执行完整的未分片聚合流程，因此当企业池发生故障时，只需一行 `runs-on` 修改即可把必需通道切换到一个具有持续验证证据的环境上。该通道由 push 触发，执行的始终是基线分支自身的工作流定义——不存在任何可由拉取请求编辑的路径能把代码路由到这些运行器上；此外仓库继续保持禁用 fork。 + ## 曾考虑的替代方案 **保留 3 个粗粒度 Linux 主流程通道。** 核心、CPU 和生产网站作业均达到延迟目标，但它们需要 3 轮设置，而且在大型运行器已经可用后仍对主 Node 工作进行分片。全规格运行轨迹表明，让单机聚合流程超过 1 分钟的是一项不必要的依赖，而非主机容量不足。 diff --git a/.agents/notes/implemented/process/2026-07-23-portable-required-pull-request-ci.i18n.yaml b/.agents/notes/implemented/process/2026-07-23-portable-required-pull-request-ci.i18n.yaml index ed97fe08a7..f8b54b0ec5 100644 --- a/.agents/notes/implemented/process/2026-07-23-portable-required-pull-request-ci.i18n.yaml +++ b/.agents/notes/implemented/process/2026-07-23-portable-required-pull-request-ci.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 -2026-07-23-portable-required-pull-request-ci.md: 29b2cfa3f431a4a8be4aaa685b16cffdb4bf2593 -2026-07-23-portable-required-pull-request-ci.zh.md: 8b6d067637ce83c09529977f463f16dfa4af5a8b +2026-07-23-portable-required-pull-request-ci.md: 9cf8d97016300c5258c075879176aa6abd64e59e +2026-07-23-portable-required-pull-request-ci.zh.md: c6839a133d0c3fe7a699362f6168e17d827a5b61 diff --git a/.agents/notes/implemented/process/2026-07-23-portable-required-pull-request-ci.md b/.agents/notes/implemented/process/2026-07-23-portable-required-pull-request-ci.md index 29b2cfa3f4..9cf8d97016 100644 --- a/.agents/notes/implemented/process/2026-07-23-portable-required-pull-request-ci.md +++ b/.agents/notes/implemented/process/2026-07-23-portable-required-pull-request-ci.md @@ -12,7 +12,7 @@ Billing health, a runner definition's `Ready` state, and a large autoscaling cei ## Decision -[CI](../../../../.github/workflows/ci.yml) runs the required primary Node 24 and Windows jobs on repo-restricted enterprise 32-core pools, except exhaustive coverage, which runs on the in-house self-hosted 64-core pool for trusted same-repo pull requests (hosted 32-core for forks and Dependabot). Standard `ubuntu-latest` jobs retain Node 22.19, Node 26, and Python SDK compatibility, and `master` runs complete serial Linux, macOS, and Windows references. Those standard-hosted jobs keep the portable execution boundary observable without duplicating the primary inventory on every pull request. +[CI](../../../../.github/workflows/ci.yml) runs the required primary Node 24 and Windows jobs on repo-restricted enterprise 32-core pools. Standard `ubuntu-latest` jobs retain Node 22.19, Node 26, and Python SDK compatibility, and `master` runs complete serial Linux, macOS, and Windows references. Those standard-hosted jobs keep the portable execution boundary observable without duplicating the primary inventory on every pull request. The two Linux primary jobs, Node compatibility, Python SDK, and `windows node 24 / complete` remain dependencies of `all checks passed`; branch protection continues to require `e2e` and `all checks passed`. There is no automatic fallback when an enterprise label cannot allocate: the standard jobs continue to report their own contracts, but they cannot manufacture the missing required result. diff --git a/.agents/notes/implemented/process/2026-07-23-portable-required-pull-request-ci.zh.md b/.agents/notes/implemented/process/2026-07-23-portable-required-pull-request-ci.zh.md index 8b6d067637..c6839a133d 100644 --- a/.agents/notes/implemented/process/2026-07-23-portable-required-pull-request-ci.zh.md +++ b/.agents/notes/implemented/process/2026-07-23-portable-required-pull-request-ci.zh.md @@ -12,7 +12,7 @@ Status: implemented ## 决策 -[CI](../../../../.github/workflows/ci.yml) 在仅限本仓库使用的企业级 32 核运行器池上运行必需的主 Node 24 作业和 Windows 作业；唯一例外是完整覆盖率——可信的同仓库拉取请求在公司自有的自托管 64 核池上运行（fork 与 Dependabot 仍用托管 32 核池）。标准 `ubuntu-latest` 作业保留 Node 22.19、Node 26 和 Python SDK 兼容性，`master` 则运行完整的 Linux、macOS 和 Windows 串行参考流程。这些标准托管作业让可移植执行边界保持可观测，而不必在每个拉取请求中重复主清单。 +[CI](../../../../.github/workflows/ci.yml) 在仅限本仓库使用的企业级 32 核运行器池上运行必需的主 Node 24 作业和 Windows 作业。标准 `ubuntu-latest` 作业保留 Node 22.19、Node 26 和 Python SDK 兼容性，`master` 则运行完整的 Linux、macOS 和 Windows 串行参考流程。这些标准托管作业让可移植执行边界保持可观测，而不必在每个拉取请求中重复主清单。 两项 Linux 主作业、Node 兼容性、Python SDK 和 `windows node 24 / complete` 继续作为 `all checks passed` 的依赖项；分支保护继续要求 `e2e` 和 `all checks passed`。企业级运行器标签无法分配运行器时没有自动后备机制：标准作业会继续报告各自的契约，但无法产出缺失的必需结果。 diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml index dc5ad98ec4..2666c93b8c 100644 --- a/.github/workflows/ci.yml +++ b/.github/workflows/ci.yml @@ -27,10 +27,8 @@ env: jobs: - # Three independent Linux jobs isolate coverage, static analysis, and the - # build-backed consumer tail: static and consumers on hosted enterprise - # 32-core pools; coverage on the in-house self-hosted pool for trusted PRs - # (hosted for forks/Dependabot). The static job publishes its exact build so + # Three enterprise jobs isolate coverage, static analysis, and the + # build-backed consumer tail. The static job publishes its exact build so # consumers do not repeat the longest part of their critical path. node-24: if: github.event_name == 'pull_request' @@ -79,46 +77,17 @@ jobs: node-24-coverage: if: github.event_name == 'pull_request' - # Trusted same-repo PRs run on the in-house pool (self-hosted, 64-core; - # 4 always-on systemd-managed instances plus 4 registered spares) instead - # of the metered enterprise pool. Untrusted PRs — forks and Dependabot - # (same-repo but dependency-supplied code; same author test as e2e.yml) — - # stay on the hosted enterprise pool so no untrusted code reaches the - # persistent self-hosted VM. Selecting the pool via runs-on keeps this a - # single job, so the all-checks-passed aggregate never sees a skip. - runs-on: >- - ${{ (github.event.pull_request.head.repo.full_name != github.repository - || github.event.pull_request.user.login == 'dependabot[bot]') - && 'dsh-enterprise-ubuntu-24-04-32core-test' - || fromJSON('["self-hosted", "linux", "x64", "vm-backup"]') }} + runs-on: dsh-enterprise-ubuntu-24-04-32core-test name: node 24 / coverage env: - # Worker bound is per-leg: the hosted 32-core runner is exclusive to - # one job, but the self-hosted pool shares one 64-core VM across four - # runner instances, so concurrent PRs would otherwise stack up to - # 4×24 = 96 workers and re-trigger the aggregate-contention failures - # documented for the timing-sensitive process suites. 12 per job caps - # the shared host at 48 workers even fully loaded. - DSH_COVERAGE_MAX_WORKERS: >- - ${{ (github.event.pull_request.head.repo.full_name != github.repository - || github.event.pull_request.user.login == 'dependabot[bot]') - && '24' || '12' }} + DSH_COVERAGE_MAX_WORKERS: '24' DSH_GATE_CONCURRENCY: '8' steps: - uses: actions/checkout@v6 with: persist-credentials: false - # Restore the pnpm-store cache only on the hosted (untrusted-PR) leg, - # where the VM is ephemeral and the same-region download is fast. On - # the self-hosted leg pnpm's persistent store lives outside - # /home/runner, so this restore would spend ~52 s pulling ~180 MB into - # a path pnpm never reads (measured; install then took 2.8 s straight - # from the persistent store). Condition mirrors the runs-on selector. - uses: actions/cache/restore@v4 - if: >- - github.event.pull_request.head.repo.full_name != github.repository - || github.event.pull_request.user.login == 'dependabot[bot]' with: path: /home/runner/.local/share/pnpm/store/v11 key: ${{ runner.os }}-node-${{ env.PRIMARY_NODE_VERSION }}-pnpm-${{ hashFiles('pnpm-lock.yaml') }} @@ -396,6 +365,45 @@ jobs: DSH_SNAPSHOT_MAX_CONCURRENCY: '1' run: pnpm run check:ci + # Hot-standby drill for the in-house self-hosted pool: every master move + # re-runs the complete unsharded aggregate on the persistent 64-core VM, + # continuously proving that environment can take over a required lane if + # the hosted pools degrade (the switch is then a one-line runs-on change). + # Push-triggered, so it always executes the base branch's own workflow + # definition — no PR-editable path selects these runners. Non-blocking for + # pull requests; no cache steps because the VM's persistent pnpm store and + # tool caches make them redundant (and saving here would poison the hosted + # cache namespace with self-hosted paths). + serial-linux-selfhosted: + if: github.event_name == 'push' && github.ref == 'refs/heads/master' + name: serial / linux (self-hosted standby) + runs-on: [self-hosted, linux, x64, vm-backup] + steps: + - uses: actions/checkout@v6 + + - uses: actions/setup-node@v6 + with: + node-version: ${{ env.PRIMARY_NODE_VERSION }} + + - name: Enable corepack (pnpm) + run: corepack enable + + - name: Install (immutable) + run: pnpm install --frozen-lockfile + + - name: Prepare bubblewrap (unrestrict userns) + run: bash scripts/prepare-ci-bubblewrap.sh + + - name: Run complete unsharded primary Node CI serially + env: + DSH_COVERAGE_MAX_WORKERS: '1' + DSH_E2E_MAX_WORKERS: '1' + DSH_ESLINT_CACHE: '1' + DSH_GATE_CONCURRENCY: '1' + DSH_PUBLINT_CONCURRENCY: '1' + DSH_SNAPSHOT_MAX_CONCURRENCY: '1' + run: pnpm run check:ci + serial-macos: if: github.event_name == 'push' && github.ref == 'refs/heads/master' name: serial / macos From 0fd6dc8924a087db5c3a8190a2f1783766660e8b Mon Sep 17 00:00:00 2001 From: Chinesezjc Date: Sun, 26 Jul 2026 00:34:53 +0800 Subject: [PATCH 09/36] ci: pre-wire admin-only failover from hosted pools to the in-house pool MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The three required Linux jobs now resolve their pool through the DSH_CI_FAILOVER repository variable. Unset, everything runs exactly as today on the hosted enterprise pools. Setting it to 'selfhosted' (repo-admin-only, not PR-editable, no merge required — a merge would be deadlocked behind the failing checks themselves) retargets all three onto the vm-backup pool, halves the coverage worker bound and snapshot concurrency for the shared VM, and skips the hosted-path cache restores. Adds a bilingual failover runbook (switch, capacity via the four registered spare instances, switch-back, trust boundary) and links it from the topology note. The push-triggered standby lane remains the continuous proof that the failover target works. --- ...ence-based-larger-hosted-runners.i18n.yaml | 4 +- ...22-evidence-based-larger-hosted-runners.md | 2 +- ...evidence-based-larger-hosted-runners.zh.md | 2 +- .../process/ci-failover-runbook.i18n.yaml | 6 +++ .../process/ci-failover-runbook.md | 33 +++++++++++++++ .../process/ci-failover-runbook.zh.md | 33 +++++++++++++++ .github/workflows/ci.yml | 40 ++++++++++++++++--- 7 files changed, 111 insertions(+), 9 deletions(-) create mode 100644 .agents/notes/implemented/process/ci-failover-runbook.i18n.yaml create mode 100644 .agents/notes/implemented/process/ci-failover-runbook.md create mode 100644 .agents/notes/implemented/process/ci-failover-runbook.zh.md diff --git a/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.i18n.yaml b/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.i18n.yaml index 1b14f5b689..cd3ae7a181 100644 --- a/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.i18n.yaml +++ b/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.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 -2026-07-22-evidence-based-larger-hosted-runners.md: 6654f5eb3e21b48c6d33fd9d74ebd23cf3065d54 -2026-07-22-evidence-based-larger-hosted-runners.zh.md: 3fe5715b20d3b881f8fb439b61900bdb84e5a588 +2026-07-22-evidence-based-larger-hosted-runners.md: dd07280092565257f4b5324f997d5efd4c9c51cc +2026-07-22-evidence-based-larger-hosted-runners.zh.md: a9c034b643da0cb9148d08c0300f3e142eec31e6 diff --git a/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.md b/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.md index 6654f5eb3e..dd07280092 100644 --- a/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.md +++ b/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.md @@ -48,7 +48,7 @@ The process-bound coverage project contains exactly five suite files. Thirty-two Complete serial Linux, macOS, and Windows references run only when `master` moves. Pull requests use the enterprise required path plus standard-hosted compatibility jobs, while other larger-runner sizes run only by manual dispatch. -An additional serial Linux reference runs on the in-house self-hosted pool (`vm-backup` label: a 64-core VM with four always-on systemd-managed runner instances plus four registered spares) on every `master` push. It is a hot-standby drill, not a required check: each run re-proves that the persistent VM can execute the complete unsharded aggregate, so if the enterprise pools degrade, a required lane can be retargeted with a one-line `runs-on` change onto an environment with continuously verified evidence. Because the lane is push-triggered, it always executes the base branch's workflow definition — no pull-request-editable path can route code to these runners, and the repository additionally keeps forking disabled. +An additional serial Linux reference runs on the in-house self-hosted pool (`vm-backup` label: a 64-core VM with four always-on systemd-managed runner instances plus four registered spares) on every `master` push. It is a hot-standby drill, not a required check: each run re-proves that the persistent VM can execute the complete unsharded aggregate. The actual switch is pre-wired: the three required Linux jobs resolve their pool through the admin-only `DSH_CI_FAILOVER` repository variable, so an outage response is setting one variable and re-running — no merge, which would be deadlocked behind the failing checks themselves ([runbook](ci-failover-runbook.md)). Because the standby lane is push-triggered, it always executes the base branch's workflow definition — no pull-request-editable path can route code to these runners, and the repository additionally keeps forking disabled. ## Alternatives considered diff --git a/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.zh.md b/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.zh.md index 3fe5715b20..a9c034b643 100644 --- a/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.zh.md +++ b/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.zh.md @@ -48,7 +48,7 @@ Windows 仓库工作在超过 16 核后收益很小，但 32 核池可以让完 只有在 `master` 移动时，才运行完整的 Linux、macOS 和 Windows 串行参考。拉取请求使用企业级运行器必需路径和标准托管兼容性作业，其他大型运行器规格仅通过手动触发运行。 -另有一条串行 Linux 参考在每次 `master` 推送时运行于公司自有的自托管池（`vm-backup` 标签：一台 64 核虚拟机，运行 4 个常驻的 systemd 管理运行器实例，另有 4 个已注册备用位）。它是热备演练而非必需检查：每次运行都重新证明这台持久化虚拟机能够执行完整的未分片聚合流程，因此当企业池发生故障时，只需一行 `runs-on` 修改即可把必需通道切换到一个具有持续验证证据的环境上。该通道由 push 触发，执行的始终是基线分支自身的工作流定义——不存在任何可由拉取请求编辑的路径能把代码路由到这些运行器上；此外仓库继续保持禁用 fork。 +另有一条串行 Linux 参考在每次 `master` 推送时运行于公司自有的自托管池（`vm-backup` 标签：一台 64 核虚拟机，运行 4 个常驻的 systemd 管理运行器实例，另有 4 个已注册备用位）。它是热备演练而非必需检查：每次运行都重新证明这台持久化虚拟机能够执行完整的未分片聚合流程。实际切换机制已预先布线：三个必需 Linux 作业通过仅限管理员的仓库变量 `DSH_CI_FAILOVER` 解析运行器池，因此故障响应就是设置一个变量并重跑——无需合并（合并本身会被正在失败的检查死锁）（[切换手册](ci-failover-runbook.zh.md)）。该热备通道由 push 触发，执行的始终是基线分支自身的工作流定义——不存在任何可由拉取请求编辑的路径能把代码路由到这些运行器上；此外仓库继续保持禁用 fork。 ## 曾考虑的替代方案 diff --git a/.agents/notes/implemented/process/ci-failover-runbook.i18n.yaml b/.agents/notes/implemented/process/ci-failover-runbook.i18n.yaml new file mode 100644 index 0000000000..294ed38ddf --- /dev/null +++ b/.agents/notes/implemented/process/ci-failover-runbook.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# 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 +ci-failover-runbook.md: d22c93fbedd3216e71bc24101dfa06dc606521c2 +ci-failover-runbook.zh.md: d7d26287191165cd3cb2666de4b1c7d6217ba71d diff --git a/.agents/notes/implemented/process/ci-failover-runbook.md b/.agents/notes/implemented/process/ci-failover-runbook.md new file mode 100644 index 0000000000..d22c93fbed --- /dev/null +++ b/.agents/notes/implemented/process/ci-failover-runbook.md @@ -0,0 +1,33 @@ +# Agent Note: CI failover runbook — hosted pools → in-house pool + +Status: implemented + +English | [中文](ci-failover-runbook.zh.md) + +## What this is + +The three required Linux jobs in [CI](../../../../.github/workflows/ci.yml) (`node 24 / static`, `node 24 / coverage`, `node 24 / snapshots and artifacts`) resolve their runner pool through the `DSH_CI_FAILOVER` repository variable. Normally the variable is unset and they run on the hosted enterprise 32-core pools. When the hosted pools are degraded (jobs queue indefinitely, the enterprise labels vanish, or GitHub-side capacity fails), a repository admin can retarget all three onto the in-house self-hosted pool without merging anything — merging would itself be blocked by the very checks that are failing. + +The in-house pool (`vm-backup`: one 64-core VM, four always-on systemd-managed runner instances, four registered spares) is continuously re-proven by the `serial / linux (self-hosted standby)` lane, which runs the complete unsharded aggregate on every master push. Check its latest run before switching: green standby = verified-yesterday capacity. + +## Switch (repo admin, ~1 minute, no merge) + +1. Repository **Settings → Secrets and variables → Actions → Variables → New repository variable**: name `DSH_CI_FAILOVER`, value `selfhosted`. +2. Re-run the failed/queued required jobs (Re-run failed jobs on affected PRs, or let new pushes pick it up). +3. That is the entire switch. Under failover the workflow also, automatically: halves `DSH_COVERAGE_MAX_WORKERS` to 12 and `DSH_SNAPSHOT_MAX_CONCURRENCY` to 16 (shared-VM contention bounds), and skips the hosted-path pnpm cache restores (the VM's persistent store serves warm installs). + +## Capacity during failover + +Four always-on instances absorb normal PR traffic. If queues build, bring the four registered spares online on the VM (no token needed — they are already registered): + +```bash +for i in 7 8 9 10; do cd /data_local/actions-runner-$i && sudo ./svc.sh install ubuntu && sudo ./svc.sh start; done +``` + +## Switch back + +Delete the `DSH_CI_FAILOVER` variable (or set it to anything other than `selfhosted`). New runs resolve back to the hosted enterprise pools. Stop the spare instances if they were started. + +## Trust boundary + +The variable is repository-admin-only state: a pull request can neither set it nor read a different value into effect, and the expressions live in the base branch's workflow definition. This failover path therefore adds no PR-editable route to the self-hosted pool. (Runner-side enforcement — an org-level runner group restricting these runners to the master-ref workflow — is tracked separately and composes with this mechanism.) diff --git a/.agents/notes/implemented/process/ci-failover-runbook.zh.md b/.agents/notes/implemented/process/ci-failover-runbook.zh.md new file mode 100644 index 0000000000..d7d2628719 --- /dev/null +++ b/.agents/notes/implemented/process/ci-failover-runbook.zh.md @@ -0,0 +1,33 @@ +# Agent Note: CI 故障切换手册 — 托管池 → 自有池 + +Status: implemented + +[English](ci-failover-runbook.md) | 中文 + +## 这是什么 + +[CI](../../../../.github/workflows/ci.yml) 中三个必需的 Linux 作业（`node 24 / static`、`node 24 / coverage`、`node 24 / snapshots and artifacts`）通过仓库变量 `DSH_CI_FAILOVER` 解析运行器池。正常情况下该变量不存在，作业运行在托管的企业级 32 核池上。当托管池发生故障（作业无限排队、企业标签消失或 GitHub 侧容量故障）时，仓库管理员无需合并任何代码即可把三个作业整体切换到公司自有的自托管池——此时合并本身正被这些失败的检查阻塞，任何"先合 PR 再切换"的方案都是死锁。 + +自有池（`vm-backup`：一台 64 核虚拟机，4 个常驻 systemd 管理的运行器实例，另有 4 个已注册备用位）由 `serial / linux (self-hosted standby)` 通道持续验证——每次 master 推送都在其上运行完整的未分片聚合流程。切换前先看该通道最近一次运行：绿色 = 这套环境昨天刚被全量验证过。 + +## 切换步骤（仓库管理员，约 1 分钟，无需合并） + +1. 仓库 **Settings → Secrets and variables → Actions → Variables → New repository variable**：名称 `DSH_CI_FAILOVER`，值 `selfhosted`。 +2. 对受影响 PR 的失败/排队作业点 Re-run failed jobs（或等新推送自然触发）。 +3. 切换到此完成。故障切换状态下工作流还会自动：把 `DSH_COVERAGE_MAX_WORKERS` 降为 12、`DSH_SNAPSHOT_MAX_CONCURRENCY` 降为 16（共享虚拟机的争抢上限），并跳过托管路径的 pnpm 缓存恢复（虚拟机的持久 store 直接提供热安装）。 + +## 切换期间的容量 + +4 个常驻实例可承接正常 PR 流量。若出现排队，在虚拟机上把 4 个已注册的备用位拉起（无需 token——它们已注册）： + +```bash +for i in 7 8 9 10; do cd /data_local/actions-runner-$i && sudo ./svc.sh install ubuntu && sudo ./svc.sh start; done +``` + +## 切回 + +删除 `DSH_CI_FAILOVER` 变量（或改为 `selfhosted` 以外的任何值），新的运行即解析回托管企业池。若启动过备用实例，将其停止。 + +## 信任边界 + +该变量是仅限仓库管理员的状态：拉取请求既不能设置它，也不能让不同的值生效，且表达式存在于基线分支的工作流定义中。因此这条故障切换路径没有增加任何可由 PR 编辑的自托管池访问途径。（运行器侧的强制约束——通过组织级 runner group 把这批运行器限定到 master 引用的工作流——另行跟踪，与本机制互补。） diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml index 2666c93b8c..88722804f9 100644 --- a/.github/workflows/ci.yml +++ b/.github/workflows/ci.yml @@ -30,9 +30,22 @@ jobs: # Three enterprise jobs isolate coverage, static analysis, and the # build-backed consumer tail. The static job publishes its exact build so # consumers do not repeat the longest part of their critical path. + # + # FAILOVER: each Linux enterprise job resolves its pool through the + # DSH_CI_FAILOVER repository variable. Unset (normal), the expressions + # pick the hosted enterprise pools below. Setting the variable to + # 'selfhosted' (repo Settings → Actions → Variables; admin-only, not + # PR-editable, no merge required) retargets all three onto the in-house + # vm-backup pool and re-running the failed jobs is the entire switch — + # see .agents/notes/implemented/process/ci-failover-runbook.md. The + # in-house pool's readiness is re-proven on every master push by the + # serial-linux-selfhosted standby lane below. node-24: if: github.event_name == 'pull_request' - runs-on: dsh-enterprise-ubuntu-latest-32core-test + runs-on: >- + ${{ vars.DSH_CI_FAILOVER == 'selfhosted' + && fromJSON('["self-hosted", "linux", "x64", "vm-backup"]') + || 'dsh-enterprise-ubuntu-latest-32core-test' }} name: node 24 / static env: DSH_GATE_CONCURRENCY: '8' @@ -77,17 +90,28 @@ jobs: node-24-coverage: if: github.event_name == 'pull_request' - runs-on: dsh-enterprise-ubuntu-24-04-32core-test + runs-on: >- + ${{ vars.DSH_CI_FAILOVER == 'selfhosted' + && fromJSON('["self-hosted", "linux", "x64", "vm-backup"]') + || 'dsh-enterprise-ubuntu-24-04-32core-test' }} name: node 24 / coverage env: - DSH_COVERAGE_MAX_WORKERS: '24' + # Failover halves the worker bound: the hosted 32-core runner is + # exclusive to one job, but the failover pool shares one 64-core VM + # across four runner instances, and the timing-sensitive process + # suites have documented aggregate-contention failures. + DSH_COVERAGE_MAX_WORKERS: ${{ vars.DSH_CI_FAILOVER == 'selfhosted' && '12' || '24' }} DSH_GATE_CONCURRENCY: '8' steps: - uses: actions/checkout@v6 with: persist-credentials: false + # Skipped under failover: the self-hosted VM's persistent pnpm store + # serves warm installs directly, and this hosted-path restore would + # spend ~52 s pulling ~180 MB into a path pnpm never reads there. - uses: actions/cache/restore@v4 + if: vars.DSH_CI_FAILOVER != 'selfhosted' with: path: /home/runner/.local/share/pnpm/store/v11 key: ${{ runner.os }}-node-${{ env.PRIMARY_NODE_VERSION }}-pnpm-${{ hashFiles('pnpm-lock.yaml') }} @@ -118,7 +142,10 @@ jobs: node-24-consumers: needs: node-24 if: github.event_name == 'pull_request' - runs-on: dsh-enterprise-ubuntu-latest-32core-test + runs-on: >- + ${{ vars.DSH_CI_FAILOVER == 'selfhosted' + && fromJSON('["self-hosted", "linux", "x64", "vm-backup"]') + || 'dsh-enterprise-ubuntu-latest-32core-test' }} name: node 24 / snapshots and artifacts env: DSH_ESLINT_CACHE: '1' @@ -126,7 +153,8 @@ jobs: DSH_GATE_CONCURRENCY: '8' DSH_NODE_COMPAT_SKIP_TYPECHECK: '1' DSH_PUBLINT_CONCURRENCY: '8' - DSH_SNAPSHOT_MAX_CONCURRENCY: '32' + # Failover halves snapshot concurrency for the shared 64-core VM. + DSH_SNAPSHOT_MAX_CONCURRENCY: ${{ vars.DSH_CI_FAILOVER == 'selfhosted' && '16' || '32' }} steps: - uses: actions/checkout@v6 with: @@ -140,7 +168,9 @@ jobs: - name: Restore built tree run: tar -xzf "$RUNNER_TEMP/node-24-built-tree.tar.gz" + # Skipped under failover — see the coverage lane's identical rationale. - uses: actions/cache/restore@v4 + if: vars.DSH_CI_FAILOVER != 'selfhosted' with: path: /home/runner/.local/share/pnpm/store/v11 key: ${{ runner.os }}-node-${{ env.PRIMARY_NODE_VERSION }}-pnpm-${{ hashFiles('pnpm-lock.yaml') }} From 68e280ce4ff86629ea0443a012d7c7080289ce4d Mon Sep 17 00:00:00 2001 From: Chinesezjc Date: Sun, 26 Jul 2026 05:22:28 +0800 Subject: [PATCH 10/36] docs(ci): make the failover runbook a conforming dated Agent Note The failover runbook landed as .agents/notes/implemented/process/ci-failover-runbook.md, which fails three doc-sync gates: the classification/format gates require a yyyy-mm-dd-topic.md filename and the implemented Agent Note skeleton (Problem/Decision/Alternatives/Consequences), and the bilingual pairing gate requires cross-note link targets to match between the two language sides. Rename to 2026-07-26-ci-failover-runbook.md/.zh.md, reshape both sides into the implemented skeleton (the runbook steps live in bespoke sections under Decision), point the sibling topology note and the ci.yml comment at the dated filename, and make both sides link the canonical .md per the bilingual convention. Re-recorded the i18n pairing records. --- ...ence-based-larger-hosted-runners.i18n.yaml | 4 +- ...22-evidence-based-larger-hosted-runners.md | 2 +- ...evidence-based-larger-hosted-runners.zh.md | 2 +- ... 2026-07-26-ci-failover-runbook.i18n.yaml} | 4 +- .../process/2026-07-26-ci-failover-runbook.md | 49 +++++++++++++++++++ .../2026-07-26-ci-failover-runbook.zh.md | 49 +++++++++++++++++++ .../process/ci-failover-runbook.md | 33 ------------- .../process/ci-failover-runbook.zh.md | 33 ------------- .github/workflows/ci.yml | 2 +- 9 files changed, 105 insertions(+), 73 deletions(-) rename .agents/notes/implemented/process/{ci-failover-runbook.i18n.yaml => 2026-07-26-ci-failover-runbook.i18n.yaml} (65%) create mode 100644 .agents/notes/implemented/process/2026-07-26-ci-failover-runbook.md create mode 100644 .agents/notes/implemented/process/2026-07-26-ci-failover-runbook.zh.md delete mode 100644 .agents/notes/implemented/process/ci-failover-runbook.md delete mode 100644 .agents/notes/implemented/process/ci-failover-runbook.zh.md diff --git a/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.i18n.yaml b/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.i18n.yaml index b2d20fb999..84a10e5ab9 100644 --- a/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.i18n.yaml +++ b/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.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 -2026-07-22-evidence-based-larger-hosted-runners.md: 6e989a908b1faa363d04746e4efaa1a77358be9d -2026-07-22-evidence-based-larger-hosted-runners.zh.md: 02c2ab405ec10dd381b051581d72662ec342e21e +2026-07-22-evidence-based-larger-hosted-runners.md: 21e602b2b5850176df981dcf448f4f827b756719 +2026-07-22-evidence-based-larger-hosted-runners.zh.md: ba49ff18ac304f4078d4c8ebfd00bb1a85ada0b3 diff --git a/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.md b/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.md index 6e989a908b..21e602b2b5 100644 --- a/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.md +++ b/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.md @@ -52,7 +52,7 @@ The process-bound coverage project contains exactly five suite files. Thirty-two Complete serial Linux, macOS, and Windows references run only when `master` moves. Pull requests use the enterprise required path plus standard-hosted compatibility jobs, while other larger-runner sizes run only by manual dispatch. -An additional serial Linux reference runs on the in-house self-hosted pool (`vm-backup` label: a 64-core VM with four always-on systemd-managed runner instances plus four registered spares) on every `master` push. It is a hot-standby drill, not a required check: each run re-proves that the persistent VM can execute the complete unsharded aggregate. The actual switch is pre-wired: the three required Linux jobs resolve their pool through the admin-only `DSH_CI_FAILOVER` repository variable, so an outage response is setting one variable and re-running — no merge, which would be deadlocked behind the failing checks themselves ([runbook](ci-failover-runbook.md)). Because the standby lane is push-triggered, it always executes the base branch's workflow definition — no pull-request-editable path can route code to these runners, and the repository additionally keeps forking disabled. +An additional serial Linux reference runs on the in-house self-hosted pool (`vm-backup` label: a 64-core VM with four always-on systemd-managed runner instances plus four registered spares) on every `master` push. It is a hot-standby drill, not a required check: each run re-proves that the persistent VM can execute the complete unsharded aggregate. The actual switch is pre-wired: the three required Linux jobs resolve their pool through the admin-only `DSH_CI_FAILOVER` repository variable, so an outage response is setting one variable and re-running — no merge, which would be deadlocked behind the failing checks themselves ([runbook](2026-07-26-ci-failover-runbook.md)). Because the standby lane is push-triggered, it always executes the base branch's workflow definition — no pull-request-editable path can route code to these runners, and the repository additionally keeps forking disabled. ## Alternatives considered diff --git a/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.zh.md b/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.zh.md index 02c2ab405e..ba49ff18ac 100644 --- a/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.zh.md +++ b/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.zh.md @@ -52,7 +52,7 @@ Windows 仓库工作在超过 16 核后收益很小，但 32 核池可以让完 只有在 `master` 移动时，才运行完整的 Linux、macOS 和 Windows 串行参考。拉取请求使用企业级运行器必需路径和标准托管兼容性作业，其他大型运行器规格仅通过手动触发运行。 -另有一条串行 Linux 参考在每次 `master` 推送时运行于公司自有的自托管池（`vm-backup` 标签：一台 64 核虚拟机，运行 4 个常驻的 systemd 管理运行器实例，另有 4 个已注册备用位）。它是热备演练而非必需检查：每次运行都重新证明这台持久化虚拟机能够执行完整的未分片聚合流程。实际切换机制已预先布线：三个必需 Linux 作业通过仅限管理员的仓库变量 `DSH_CI_FAILOVER` 解析运行器池，因此故障响应就是设置一个变量并重跑——无需合并（合并本身会被正在失败的检查死锁）（[切换手册](ci-failover-runbook.zh.md)）。该热备通道由 push 触发，执行的始终是基线分支自身的工作流定义——不存在任何可由拉取请求编辑的路径能把代码路由到这些运行器上；此外仓库继续保持禁用 fork。 +另有一条串行 Linux 参考在每次 `master` 推送时运行于公司自有的自托管池（`vm-backup` 标签：一台 64 核虚拟机，运行 4 个常驻的 systemd 管理运行器实例，另有 4 个已注册备用位）。它是热备演练而非必需检查：每次运行都重新证明这台持久化虚拟机能够执行完整的未分片聚合流程。实际切换机制已预先布线：三个必需 Linux 作业通过仅限管理员的仓库变量 `DSH_CI_FAILOVER` 解析运行器池，因此故障响应就是设置一个变量并重跑——无需合并（合并本身会被正在失败的检查死锁）（[切换手册](2026-07-26-ci-failover-runbook.md)）。该热备通道由 push 触发，执行的始终是基线分支自身的工作流定义——不存在任何可由拉取请求编辑的路径能把代码路由到这些运行器上；此外仓库继续保持禁用 fork。 ## 曾考虑的替代方案 diff --git a/.agents/notes/implemented/process/ci-failover-runbook.i18n.yaml b/.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.i18n.yaml similarity index 65% rename from .agents/notes/implemented/process/ci-failover-runbook.i18n.yaml rename to .agents/notes/implemented/process/2026-07-26-ci-failover-runbook.i18n.yaml index 294ed38ddf..7a65ff5479 100644 --- a/.agents/notes/implemented/process/ci-failover-runbook.i18n.yaml +++ b/.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.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 -ci-failover-runbook.md: d22c93fbedd3216e71bc24101dfa06dc606521c2 -ci-failover-runbook.zh.md: d7d26287191165cd3cb2666de4b1c7d6217ba71d +2026-07-26-ci-failover-runbook.md: 9100cf226467d06835478b13c41904bc50270b78 +2026-07-26-ci-failover-runbook.zh.md: 4ec80ae36411335a378f7979b9bca704c17732d0 diff --git a/.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.md b/.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.md new file mode 100644 index 0000000000..9100cf2264 --- /dev/null +++ b/.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.md @@ -0,0 +1,49 @@ +# Agent Note: CI failover runbook — hosted pools → in-house pool + +Status: implemented + +English | [中文](2026-07-26-ci-failover-runbook.zh.md) + +## Problem + +The three required Linux jobs in [CI](../../../../.github/workflows/ci.yml) (`node 24 / static`, `node 24 / coverage`, `node 24 / snapshots and artifacts`) run on the hosted enterprise 32-core pools. When those pools degrade — jobs queue indefinitely, the enterprise labels vanish, or GitHub-side capacity fails — every open pull request becomes unmergeable, and the ordinary recovery of merging a fix is itself deadlocked behind the very required checks that cannot run. An outage therefore needs a switch a repository admin can throw without merging anything. + +## Decision + +Each of the three required Linux jobs resolves its runner pool through the `DSH_CI_FAILOVER` repository variable. Unset (normal), they run on the hosted enterprise pools. Set to `selfhosted` by a repository admin, all three retarget onto the in-house self-hosted `vm-backup` pool, coverage and snapshot concurrency drop to shared-VM bounds, and the hosted-path pnpm cache restores are skipped. The switch is admin-only repository state, not a merge, so it works while every check is red. The in-house pool's readiness is continuously re-proven by the `serial / linux (self-hosted standby)` lane, which runs the complete unsharded aggregate on every master push. + +### What the in-house pool is + +`vm-backup`: one 64-core VM, four always-on systemd-managed runner instances, four registered spares. Check the latest `serial / linux (self-hosted standby)` run before switching: a green standby is verified-yesterday capacity. + +### Switch (repo admin, ~1 minute, no merge) + +1. Repository **Settings → Secrets and variables → Actions → Variables → New repository variable**: name `DSH_CI_FAILOVER`, value `selfhosted`. +2. Re-run the failed/queued required jobs (Re-run failed jobs on affected PRs, or let new pushes pick it up). +3. That is the entire switch. Under failover the workflow also, automatically: halves `DSH_COVERAGE_MAX_WORKERS` to 12 and `DSH_SNAPSHOT_MAX_CONCURRENCY` to 16 (shared-VM contention bounds), and skips the hosted-path pnpm cache restores (the VM's persistent store serves warm installs). + +### Capacity during failover + +Four always-on instances absorb normal PR traffic. If queues build, bring the four registered spares online on the VM (no token needed — they are already registered): + +```bash +for i in 7 8 9 10; do cd /data_local/actions-runner-$i && sudo ./svc.sh install ubuntu && sudo ./svc.sh start; done +``` + +### Switch back + +Delete the `DSH_CI_FAILOVER` variable (or set it to anything other than `selfhosted`). New runs resolve back to the hosted enterprise pools. Stop the spare instances if they were started. + +### Trust boundary + +The variable is repository-admin-only state: a pull request can neither set it nor read a different value into effect, and the expressions live in the base branch's workflow definition. This failover path therefore adds no PR-editable route to the self-hosted pool. Runner-side enforcement — an org-level runner group restricting these runners to the master-ref workflow — is tracked separately and composes with this mechanism. + +## Alternatives considered + +**Merge a workflow change to switch pools.** Rejected because the outage that motivates the switch is exactly the state in which no PR can merge: the required checks are the ones failing. A repository variable is admin-controlled state that takes effect on re-run without a merge. + +**Keep the self-hosted pool always in the required path.** Rejected because it trades hosted-pool availability for the in-house VM's, moving a single point of failure rather than adding a fallback. The variable keeps the hosted pools primary and the self-hosted pool a proven, one-action standby. + +## Consequences + +Recovering from a hosted-pool outage is a single admin variable plus a re-run, with no merge on the critical path. The cost is a second runner topology to keep working: the standby lane exercises it on every master push so the failover target never goes stale, and the concurrency and cache-restore branches in `ci.yml` carry a `selfhosted` leg that must stay in step with the hosted leg. diff --git a/.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.zh.md b/.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.zh.md new file mode 100644 index 0000000000..4ec80ae364 --- /dev/null +++ b/.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.zh.md @@ -0,0 +1,49 @@ +# Agent Note: CI 故障切换手册 — 托管池 → 自有池 + +Status: implemented + +[English](2026-07-26-ci-failover-runbook.md) | 中文 + +## 问题 + +[CI](../../../../.github/workflows/ci.yml) 中三个必需的 Linux 作业（`node 24 / static`、`node 24 / coverage`、`node 24 / snapshots and artifacts`）运行在托管的企业级 32 核池上。当这些托管池发生故障——作业无限排队、企业标签消失或 GitHub 侧容量故障——所有开启的拉取请求都无法合并，而"合并一个修复"这一常规恢复手段本身正被那些无法运行的必需检查死锁。因此故障需要一个仓库管理员无需合并任何代码即可触发的开关。 + +## 决策 + +三个必需的 Linux 作业各自通过仓库变量 `DSH_CI_FAILOVER` 解析运行器池。变量不存在（正常）时它们运行在托管企业池上；由仓库管理员设为 `selfhosted` 时，三者全部切换到公司自有的自托管 `vm-backup` 池，coverage 与 snapshot 的并发降到共享虚拟机上限，并跳过托管路径的 pnpm 缓存恢复。这个开关是仅限管理员的仓库状态而非一次合并，因此在所有检查都是红色时仍然有效。自有池的就绪状态由 `serial / linux (self-hosted standby)` 通道持续验证——每次 master 推送都在其上运行完整的未分片聚合流程。 + +### 自有池是什么 + +`vm-backup`：一台 64 核虚拟机，4 个常驻 systemd 管理的运行器实例，另有 4 个已注册备用位。切换前先看 `serial / linux (self-hosted standby)` 最近一次运行：绿色 = 这套环境昨天刚被全量验证过。 + +### 切换步骤（仓库管理员，约 1 分钟，无需合并） + +1. 仓库 **Settings → Secrets and variables → Actions → Variables → New repository variable**：名称 `DSH_CI_FAILOVER`，值 `selfhosted`。 +2. 对受影响 PR 的失败/排队作业点 Re-run failed jobs（或等新推送自然触发）。 +3. 切换到此完成。故障切换状态下工作流还会自动：把 `DSH_COVERAGE_MAX_WORKERS` 降为 12、`DSH_SNAPSHOT_MAX_CONCURRENCY` 降为 16（共享虚拟机的争抢上限），并跳过托管路径的 pnpm 缓存恢复（虚拟机的持久 store 直接提供热安装）。 + +### 切换期间的容量 + +4 个常驻实例可承接正常 PR 流量。若出现排队，在虚拟机上把 4 个已注册的备用位拉起（无需 token——它们已注册）： + +```bash +for i in 7 8 9 10; do cd /data_local/actions-runner-$i && sudo ./svc.sh install ubuntu && sudo ./svc.sh start; done +``` + +### 切回 + +删除 `DSH_CI_FAILOVER` 变量（或改为 `selfhosted` 以外的任何值），新的运行即解析回托管企业池。若启动过备用实例，将其停止。 + +### 信任边界 + +该变量是仅限仓库管理员的状态：拉取请求既不能设置它，也不能让不同的值生效，且表达式存在于基线分支的工作流定义中。因此这条故障切换路径没有增加任何可由 PR 编辑的自托管池访问途径。运行器侧的强制约束——通过组织级 runner group 把这批运行器限定到 master 引用的工作流——另行跟踪，与本机制互补。 + +## 曾考虑的替代方案 + +**通过合并一次工作流改动来切换池。** 否决，因为触发切换的故障状态恰恰是任何 PR 都无法合并的状态：必需检查正是失败的那些。仓库变量是管理员控制的状态，重跑即生效，无需合并。 + +**让自托管池长期处于必需路径中。** 否决，因为这是拿托管池的可用性去换自有虚拟机的可用性，只是搬移了单点故障而非增加回退。该变量让托管池保持主路径，自托管池作为一个经过验证、一步即可启用的热备。 + +## 后果 + +从托管池故障中恢复只需一个管理员变量加一次重跑，关键路径上没有合并。代价是要维护第二套运行器拓扑：热备通道在每次 master 推送时都运行它，使故障切换目标永不失效；而 `ci.yml` 中的并发与缓存恢复分支带有一条 `selfhosted` 支路，必须与托管支路保持同步。 diff --git a/.agents/notes/implemented/process/ci-failover-runbook.md b/.agents/notes/implemented/process/ci-failover-runbook.md deleted file mode 100644 index d22c93fbed..0000000000 --- a/.agents/notes/implemented/process/ci-failover-runbook.md +++ /dev/null @@ -1,33 +0,0 @@ -# Agent Note: CI failover runbook — hosted pools → in-house pool - -Status: implemented - -English | [中文](ci-failover-runbook.zh.md) - -## What this is - -The three required Linux jobs in [CI](../../../../.github/workflows/ci.yml) (`node 24 / static`, `node 24 / coverage`, `node 24 / snapshots and artifacts`) resolve their runner pool through the `DSH_CI_FAILOVER` repository variable. Normally the variable is unset and they run on the hosted enterprise 32-core pools. When the hosted pools are degraded (jobs queue indefinitely, the enterprise labels vanish, or GitHub-side capacity fails), a repository admin can retarget all three onto the in-house self-hosted pool without merging anything — merging would itself be blocked by the very checks that are failing. - -The in-house pool (`vm-backup`: one 64-core VM, four always-on systemd-managed runner instances, four registered spares) is continuously re-proven by the `serial / linux (self-hosted standby)` lane, which runs the complete unsharded aggregate on every master push. Check its latest run before switching: green standby = verified-yesterday capacity. - -## Switch (repo admin, ~1 minute, no merge) - -1. Repository **Settings → Secrets and variables → Actions → Variables → New repository variable**: name `DSH_CI_FAILOVER`, value `selfhosted`. -2. Re-run the failed/queued required jobs (Re-run failed jobs on affected PRs, or let new pushes pick it up). -3. That is the entire switch. Under failover the workflow also, automatically: halves `DSH_COVERAGE_MAX_WORKERS` to 12 and `DSH_SNAPSHOT_MAX_CONCURRENCY` to 16 (shared-VM contention bounds), and skips the hosted-path pnpm cache restores (the VM's persistent store serves warm installs). - -## Capacity during failover - -Four always-on instances absorb normal PR traffic. If queues build, bring the four registered spares online on the VM (no token needed — they are already registered): - -```bash -for i in 7 8 9 10; do cd /data_local/actions-runner-$i && sudo ./svc.sh install ubuntu && sudo ./svc.sh start; done -``` - -## Switch back - -Delete the `DSH_CI_FAILOVER` variable (or set it to anything other than `selfhosted`). New runs resolve back to the hosted enterprise pools. Stop the spare instances if they were started. - -## Trust boundary - -The variable is repository-admin-only state: a pull request can neither set it nor read a different value into effect, and the expressions live in the base branch's workflow definition. This failover path therefore adds no PR-editable route to the self-hosted pool. (Runner-side enforcement — an org-level runner group restricting these runners to the master-ref workflow — is tracked separately and composes with this mechanism.) diff --git a/.agents/notes/implemented/process/ci-failover-runbook.zh.md b/.agents/notes/implemented/process/ci-failover-runbook.zh.md deleted file mode 100644 index d7d2628719..0000000000 --- a/.agents/notes/implemented/process/ci-failover-runbook.zh.md +++ /dev/null @@ -1,33 +0,0 @@ -# Agent Note: CI 故障切换手册 — 托管池 → 自有池 - -Status: implemented - -[English](ci-failover-runbook.md) | 中文 - -## 这是什么 - -[CI](../../../../.github/workflows/ci.yml) 中三个必需的 Linux 作业（`node 24 / static`、`node 24 / coverage`、`node 24 / snapshots and artifacts`）通过仓库变量 `DSH_CI_FAILOVER` 解析运行器池。正常情况下该变量不存在，作业运行在托管的企业级 32 核池上。当托管池发生故障（作业无限排队、企业标签消失或 GitHub 侧容量故障）时，仓库管理员无需合并任何代码即可把三个作业整体切换到公司自有的自托管池——此时合并本身正被这些失败的检查阻塞，任何"先合 PR 再切换"的方案都是死锁。 - -自有池（`vm-backup`：一台 64 核虚拟机，4 个常驻 systemd 管理的运行器实例，另有 4 个已注册备用位）由 `serial / linux (self-hosted standby)` 通道持续验证——每次 master 推送都在其上运行完整的未分片聚合流程。切换前先看该通道最近一次运行：绿色 = 这套环境昨天刚被全量验证过。 - -## 切换步骤（仓库管理员，约 1 分钟，无需合并） - -1. 仓库 **Settings → Secrets and variables → Actions → Variables → New repository variable**：名称 `DSH_CI_FAILOVER`，值 `selfhosted`。 -2. 对受影响 PR 的失败/排队作业点 Re-run failed jobs（或等新推送自然触发）。 -3. 切换到此完成。故障切换状态下工作流还会自动：把 `DSH_COVERAGE_MAX_WORKERS` 降为 12、`DSH_SNAPSHOT_MAX_CONCURRENCY` 降为 16（共享虚拟机的争抢上限），并跳过托管路径的 pnpm 缓存恢复（虚拟机的持久 store 直接提供热安装）。 - -## 切换期间的容量 - -4 个常驻实例可承接正常 PR 流量。若出现排队，在虚拟机上把 4 个已注册的备用位拉起（无需 token——它们已注册）： - -```bash -for i in 7 8 9 10; do cd /data_local/actions-runner-$i && sudo ./svc.sh install ubuntu && sudo ./svc.sh start; done -``` - -## 切回 - -删除 `DSH_CI_FAILOVER` 变量（或改为 `selfhosted` 以外的任何值），新的运行即解析回托管企业池。若启动过备用实例，将其停止。 - -## 信任边界 - -该变量是仅限仓库管理员的状态：拉取请求既不能设置它，也不能让不同的值生效，且表达式存在于基线分支的工作流定义中。因此这条故障切换路径没有增加任何可由 PR 编辑的自托管池访问途径。（运行器侧的强制约束——通过组织级 runner group 把这批运行器限定到 master 引用的工作流——另行跟踪，与本机制互补。） diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml index 88722804f9..0be7655193 100644 --- a/.github/workflows/ci.yml +++ b/.github/workflows/ci.yml @@ -37,7 +37,7 @@ jobs: # 'selfhosted' (repo Settings → Actions → Variables; admin-only, not # PR-editable, no merge required) retargets all three onto the in-house # vm-backup pool and re-running the failed jobs is the entire switch — - # see .agents/notes/implemented/process/ci-failover-runbook.md. The + # see .agents/notes/implemented/process/2026-07-26-ci-failover-runbook.md. The # in-house pool's readiness is re-proven on every master push by the # serial-linux-selfhosted standby lane below. node-24: From 498df1d8de66d3f17ed52ec93d7ffa863604cde8 Mon Sep 17 00:00:00 2001 From: Chinesezjc Date: Sun, 26 Jul 2026 05:44:35 +0800 Subject: [PATCH 11/36] ci: gate static lane's cache restore under failover; fix runbook recovery steps Review round on the pivoted design: - node-24 (static) kept an unconditional hosted pnpm cache restore while the coverage and consumers lanes skip it under failover. On the self-hosted VM that restore downloads ~180 MB into /home/runner, a path pnpm never reads there, adding latency and contention during an outage. Gate it with the same `vars.DSH_CI_FAILOVER != 'selfhosted'` condition so all three lanes match. - Runbook switch step 2 said "Re-run failed jobs", but the documented indefinite-queue outage leaves jobs queued (not failed), which cannot be re-run in place and do not retarget on variable change. Correct both language sides to cancel the run and re-run all jobs, or push a new commit. - The standby-lane comment still described the switch as a one-line runs-on change; it is now setting the admin-only DSH_CI_FAILOVER variable. --- .../process/2026-07-26-ci-failover-runbook.i18n.yaml | 4 ++-- .../implemented/process/2026-07-26-ci-failover-runbook.md | 2 +- .../process/2026-07-26-ci-failover-runbook.zh.md | 2 +- .github/workflows/ci.yml | 7 +++++-- 4 files changed, 9 insertions(+), 6 deletions(-) diff --git a/.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.i18n.yaml b/.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.i18n.yaml index 7a65ff5479..a2725da1b2 100644 --- a/.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.i18n.yaml +++ b/.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.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 -2026-07-26-ci-failover-runbook.md: 9100cf226467d06835478b13c41904bc50270b78 -2026-07-26-ci-failover-runbook.zh.md: 4ec80ae36411335a378f7979b9bca704c17732d0 +2026-07-26-ci-failover-runbook.md: db8e0676ecc6eeaea16438e7868ccf9ac43887cc +2026-07-26-ci-failover-runbook.zh.md: b3b4149f460784e88ce03458fc556f402c38fa2f diff --git a/.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.md b/.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.md index 9100cf2264..db8e0676ec 100644 --- a/.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.md +++ b/.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.md @@ -19,7 +19,7 @@ Each of the three required Linux jobs resolves its runner pool through the `DSH_ ### Switch (repo admin, ~1 minute, no merge) 1. Repository **Settings → Secrets and variables → Actions → Variables → New repository variable**: name `DSH_CI_FAILOVER`, value `selfhosted`. -2. Re-run the failed/queued required jobs (Re-run failed jobs on affected PRs, or let new pushes pick it up). +2. Retrigger the required jobs so they re-resolve their pool. Jobs already **queued** for the hosted labels do not retarget and cannot be re-run in place, so for the documented indefinite-queue outage, cancel the stuck run and re-run all jobs, or push a new commit; "Re-run failed jobs" only helps once a job has actually failed rather than queued. 3. That is the entire switch. Under failover the workflow also, automatically: halves `DSH_COVERAGE_MAX_WORKERS` to 12 and `DSH_SNAPSHOT_MAX_CONCURRENCY` to 16 (shared-VM contention bounds), and skips the hosted-path pnpm cache restores (the VM's persistent store serves warm installs). ### Capacity during failover diff --git a/.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.zh.md b/.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.zh.md index 4ec80ae364..b3b4149f46 100644 --- a/.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.zh.md +++ b/.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.zh.md @@ -19,7 +19,7 @@ Status: implemented ### 切换步骤（仓库管理员，约 1 分钟，无需合并） 1. 仓库 **Settings → Secrets and variables → Actions → Variables → New repository variable**：名称 `DSH_CI_FAILOVER`，值 `selfhosted`。 -2. 对受影响 PR 的失败/排队作业点 Re-run failed jobs（或等新推送自然触发）。 +2. 重新触发必需作业，使其重新解析运行器池。已经为托管标签**排队**的作业不会重定向，也无法原地 re-run，因此对于本手册所述的无限排队故障，应取消卡住的运行并 re-run all jobs，或推送一个新提交；“Re-run failed jobs”只有在作业真正失败（而非仍在排队）时才有用。 3. 切换到此完成。故障切换状态下工作流还会自动：把 `DSH_COVERAGE_MAX_WORKERS` 降为 12、`DSH_SNAPSHOT_MAX_CONCURRENCY` 降为 16（共享虚拟机的争抢上限），并跳过托管路径的 pnpm 缓存恢复（虚拟机的持久 store 直接提供热安装）。 ### 切换期间的容量 diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml index 0be7655193..95b54b44f9 100644 --- a/.github/workflows/ci.yml +++ b/.github/workflows/ci.yml @@ -55,8 +55,10 @@ jobs: persist-credentials: false # Pull requests consume the default-branch cache but do not put cache - # compression and upload on the paid latency-critical path. + # compression and upload on the paid latency-critical path. Skipped + # under failover — see the coverage lane's identical rationale. - uses: actions/cache/restore@v4 + if: vars.DSH_CI_FAILOVER != 'selfhosted' with: path: /home/runner/.local/share/pnpm/store/v11 key: ${{ runner.os }}-node-${{ env.PRIMARY_NODE_VERSION }}-pnpm-${{ hashFiles('pnpm-lock.yaml') }} @@ -398,7 +400,8 @@ jobs: # Hot-standby drill for the in-house self-hosted pool: every master move # re-runs the complete unsharded aggregate on the persistent 64-core VM, # continuously proving that environment can take over a required lane if - # the hosted pools degrade (the switch is then a one-line runs-on change). + # the hosted pools degrade (the switch is then setting the admin-only + # DSH_CI_FAILOVER variable — see the failover runbook, no merge required). # Push-triggered, so it always executes the base branch's own workflow # definition — no PR-editable path selects these runners. Non-blocking for # pull requests; no cache steps because the VM's persistent pnpm store and From 45a5175e441ad073d82a8a0db688aa3572b90057 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Mon, 27 Jul 2026 00:22:13 +0800 Subject: [PATCH 12/36] feat(tool-web): replace the regex HTML-to-markdown converter with turndown MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Implements the turndown Agent Note from the NIH dependency audit (full variant, not the minimal entities-only fallback): dsh-tool-web's fetch rendering now converts HTML through turndown + @joplin/turndown-plugin-gfm (atx headings, fenced code, dash bullets, GFM tables/strikethrough) over the real domino DOM, with script/style/noscript removed wholesale. The hand-rolled ~86-line regex converter html.ts and its entity tables are deleted; renderBody wraps the conversion in try/catch falling back to the raw HTML body, because turndown's recursive DOM walk overflows with a RangeError on pathological nesting (measured: 4k levels on the main thread, 8k in a worker) where the regex version could never throw. Closure weight, measured: tool-web IS in the single-exe runtime closure, and the exe asset globs would pack ~7.9 MB of the three new packages — but ~6 MB of that is domino's test corpus, with runtime lib/ at ~550 KB against a ~174 MB artifact (<0.5% either way), so the swap wins. Per testing policy the previously-missing keyless web_fetch snapshot ships in the same change: the acp-agent `web-fetch` scenario boots a new web.cordis.yml overlay (web seam + real dsh-web-fetch-local provider + tool-web fetch-only + a loopback HTTP fixture server on a fixed port serving deterministic HTML with entities, a GFM table, and nesting), so recording and keyless replay both drive the real HTTP fetch and real conversion end to end; the scenario pins the new `web` header class. The Agent Note moves proposed -> implemented and is rewritten per the lifecycle contract (Decision/Consequences/Testing, closure verdict and alternatives recorded); tool-web and acp-agent READMEs updated in both languages and pairs re-recorded. --- ...ndown-for-tool-web-html-markdown.i18n.yaml | 4 +- ...-26-turndown-for-tool-web-html-markdown.md | 37 ++ ...-turndown-for-tool-web-html-markdown.zh.md | 37 ++ ...-26-turndown-for-tool-web-html-markdown.md | 32 -- ...-turndown-for-tool-web-html-markdown.zh.md | 32 -- docs/config-catalog.md | 2 +- examples/acp-agent/README.i18n.yaml | 4 +- examples/acp-agent/README.md | 2 +- examples/acp-agent/README.zh.md | 2 +- examples/acp-agent/tests/acp.snapshot.ts | 7 + .../tests/snapshots/web-fetch/input.json | 7 + .../tests/snapshots/web-fetch/session.jsonl | 127 +++++ .../snapshots/web-fetch/stdout.expected.jsonl | 4 + .../web-fetch/system-prompt.expected.md | 27 + .../web-fetch/tool-schemas.expected.json | 489 ++++++++++++++++++ .../acp-agent/web-fetch-fixture-server.mjs | 52 ++ examples/acp-agent/web.cordis.snapshot.yml | 31 ++ examples/acp-agent/web.cordis.yml | 21 + examples/package.json | 1 + packages/web/tool-web/README.i18n.yaml | 4 +- packages/web/tool-web/README.md | 4 +- packages/web/tool-web/README.zh.md | 4 +- packages/web/tool-web/package.json | 5 +- packages/web/tool-web/src/fetch.ts | 34 +- packages/web/tool-web/src/html.ts | 86 --- packages/web/tool-web/src/index.ts | 1 - .../web/tool-web/src/turndown-plugin-gfm.d.ts | 12 + packages/web/tool-web/tests/tool-web.spec.ts | 69 +-- pnpm-lock.yaml | 35 ++ 29 files changed, 962 insertions(+), 210 deletions(-) rename .agents/notes/{proposed => implemented}/simplification/2026-07-26-turndown-for-tool-web-html-markdown.i18n.yaml (60%) create mode 100644 .agents/notes/implemented/simplification/2026-07-26-turndown-for-tool-web-html-markdown.md create mode 100644 .agents/notes/implemented/simplification/2026-07-26-turndown-for-tool-web-html-markdown.zh.md delete mode 100644 .agents/notes/proposed/simplification/2026-07-26-turndown-for-tool-web-html-markdown.md delete mode 100644 .agents/notes/proposed/simplification/2026-07-26-turndown-for-tool-web-html-markdown.zh.md create mode 100644 examples/acp-agent/tests/snapshots/web-fetch/input.json create mode 100644 examples/acp-agent/tests/snapshots/web-fetch/session.jsonl create mode 100644 examples/acp-agent/tests/snapshots/web-fetch/stdout.expected.jsonl create mode 100644 examples/acp-agent/tests/snapshots/web-fetch/system-prompt.expected.md create mode 100644 examples/acp-agent/tests/snapshots/web-fetch/tool-schemas.expected.json create mode 100644 examples/acp-agent/web-fetch-fixture-server.mjs create mode 100644 examples/acp-agent/web.cordis.snapshot.yml create mode 100644 examples/acp-agent/web.cordis.yml delete mode 100644 packages/web/tool-web/src/html.ts create mode 100644 packages/web/tool-web/src/turndown-plugin-gfm.d.ts diff --git a/.agents/notes/proposed/simplification/2026-07-26-turndown-for-tool-web-html-markdown.i18n.yaml b/.agents/notes/implemented/simplification/2026-07-26-turndown-for-tool-web-html-markdown.i18n.yaml similarity index 60% rename from .agents/notes/proposed/simplification/2026-07-26-turndown-for-tool-web-html-markdown.i18n.yaml rename to .agents/notes/implemented/simplification/2026-07-26-turndown-for-tool-web-html-markdown.i18n.yaml index ced514a423..60a5d9aca7 100644 --- a/.agents/notes/proposed/simplification/2026-07-26-turndown-for-tool-web-html-markdown.i18n.yaml +++ b/.agents/notes/implemented/simplification/2026-07-26-turndown-for-tool-web-html-markdown.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 -2026-07-26-turndown-for-tool-web-html-markdown.md: 7f25e51bf6e6fc9313a880abee737bca80a472af -2026-07-26-turndown-for-tool-web-html-markdown.zh.md: 3a59b08e13fd392e4f34ac543f32f5b4648f3c1c +2026-07-26-turndown-for-tool-web-html-markdown.md: c72decc336055f3b78dafdf98f2be3771b833cdb +2026-07-26-turndown-for-tool-web-html-markdown.zh.md: 30667b62538ec50608cae461b5cdf651b48e2731 diff --git a/.agents/notes/implemented/simplification/2026-07-26-turndown-for-tool-web-html-markdown.md b/.agents/notes/implemented/simplification/2026-07-26-turndown-for-tool-web-html-markdown.md new file mode 100644 index 0000000000..c72decc336 --- /dev/null +++ b/.agents/notes/implemented/simplification/2026-07-26-turndown-for-tool-web-html-markdown.md @@ -0,0 +1,37 @@ +# Agent Note: Replace tool-web's regex HTML-to-markdown converter with turndown + +Status: implemented + +English | [中文](2026-07-26-turndown-for-tool-web-html-markdown.zh.md) + +## Problem + +`dsh-tool-web`'s `src/html.ts` (~86 lines, ~40 lines of dedicated tests; deleted by this change) converted fetched HTML to markdown with regexes: strip script/style/noscript/comments, convert ``/``/`
  • `, decode numeric entities plus a 12-entry named-entity table, collapse whitespace. The module's own JSDoc said "A richer converter can replace it without changing the seam or tool schema", and the README's Known Limitations documented it as "a minimal regex converter, not an HTML parser — tables, images, and nested formatting are lost." The [web capability seam note](../architecture/2026-06-24-web-capability-seam.md) assigns HTML→markdown to this package as presentation, so the swap point was exactly here. The converter's output is model-visible on every fetched HTML page; no keyless snapshot exercised `web_fetch`, so no expected outputs pinned it. + +## Decision + +`packages/web/tool-web/src/fetch.ts` owns a module-level [`turndown`](https://github.com/mixmark-io/turndown) instance (`headingStyle: 'atx'`, `codeBlockStyle: 'fenced'`, `bulletListMarker: '-'` — fixed model-facing presentation, not deployment tunables) with `@joplin/turndown-plugin-gfm`'s composite `gfm` plugin for tables/strikethrough and `remove(['script', 'style', 'noscript'])` replacing the old wholesale drops. `renderBody`'s `html` arm calls it in a try/catch falling back to the raw HTML body: the regex version could never throw, while turndown/domino's recursive DOM walk overflows with a `RangeError` at a few thousand nesting levels (measured: 4k throws on the main thread, 8k in a worker thread), and a degraded page beats an error for a body the provider already decoded. `html.ts` and its conversion tests are deleted; the fallback and the status-header/truncation-footer formatting are tested in `tests/tool-web.spec.ts`, and the README's Known Limitations trades the regex-converter caveat for the pathological-nesting fallback. The gfm plugin ships no types; `src/turndown-plugin-gfm.d.ts` declares the one imported export over `@types/turndown` (a devDependency). + +The dependency-weight question the proposal flagged resolves in favor of the swap: `@deepseek-ai/dsh-tool-web` is in the single-file-executable closure ([single-exe note](../architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.md)), and the exe's asset globs would pack ~7.9 MB of the three packages as published — but ~6 MB of that is `@mixmark-io/domino`'s test corpus (`test/**`), with runtime `lib/` at ~550 KB against a ~174 MB artifact, under 0.5% either way. + +## Snapshot coverage + +The previously-missing keyless `web_fetch` snapshot ships with the change as the acp-agent scenario `web-fetch`: `examples/acp-agent/web.cordis.yml` composes the web seam, the real `dsh-web-fetch-local` provider, `tool-web` with `search: false`, and `web-fetch-fixture-server.mjs` — a loopback HTTP fixture on a fixed port (the fetched URL is part of the recorded transcript) serving deterministic HTML with named entities, a GFM table, and nested formatting. Recording and keyless replay both drive the real HTTP fetch and conversion; the pinned tool result is the turndown output, and the scenario pins the `web` header class (the `web_fetch` schema and guidance). + +## Alternatives considered + +- **`@mozilla/readability` + a DOM.** Solves a different problem (content extraction, not conversion) and drags a heavier DOM dependency; the seam only asks for markdown rendering of whatever the fetch returned. +- **Keep the regex converter.** It was an explicit v1 placeholder per its own JSDoc; keeping it meant model-visible quality (tables, images, nested formatting) stayed lost for the cost of maintaining bespoke entity tables. +- **The minimal `entities`-only variant.** The proposal's fallback position: replace only the entity-decoding third of `html.ts` with the zero-dependency `entities` package, deleting less but avoiding the dependency-weight question. Not taken because the closure math above made the weight immaterial while the full swap deletes the whole hand-rolled converter and its documented quality gaps. +- **`turndown-plugin-gfm` (the original) instead of `@joplin/turndown-plugin-gfm`.** The original is unmaintained (last publish 2018); the Joplin fork is current against turndown 7 and actively released. + +## Consequences + +- **Bought**: full-fidelity model-visible markdown — tables, images, strikethrough, nested emphasis, fenced code blocks, and the complete named-entity set — plus the deletion of the bespoke converter and its entity tables, with the README's regex-converter caveat narrowed to one degenerate case. +- **Paid**: two runtime dependencies (`turndown` → `@mixmark-io/domino`) enter tool-web and therefore the exe closure (~550 KB of runtime code as measured above), and a new failure mode — pathological nesting — is handled by falling back to raw HTML rather than converting. +- Model-visible output changed on every fetched HTML page; nothing pinned the old output, and the new snapshot pins the new one. + +## Testing + +- `packages/web/tool-web/tests/tool-web.spec.ts` covers the turndown conversion surface (entities, links, tables, nesting, script/style/noscript removal) through `renderBody`, and the raw-HTML fallback with a measured reliably-overflowing 20k-level nesting input; per-file coverage on the package src is 100%. +- The `web-fetch` acp-agent snapshot pins the assembled behavior keylessly end to end (real Loader composition, real HTTP fetch, real conversion). diff --git a/.agents/notes/implemented/simplification/2026-07-26-turndown-for-tool-web-html-markdown.zh.md b/.agents/notes/implemented/simplification/2026-07-26-turndown-for-tool-web-html-markdown.zh.md new file mode 100644 index 0000000000..30667b6253 --- /dev/null +++ b/.agents/notes/implemented/simplification/2026-07-26-turndown-for-tool-web-html-markdown.zh.md @@ -0,0 +1,37 @@ +# Agent Note: 用 turndown 替换 tool-web 的正则 HTML 转 markdown 转换器 + +Status: implemented + +[English](2026-07-26-turndown-for-tool-web-html-markdown.md) | 中文 + +## 问题 + +`dsh-tool-web` 的 `src/html.ts`（约 86 行，另有约 40 行专属测试；已由本变更删除）曾用正则表达式把抓取到的 HTML 转成 markdown：剥离 script、style、noscript 标签与注释，转换 ``/``/`
  • `，解码数字实体外加一张 12 项的命名实体表，并折叠空白。该模块自身的 JSDoc 写明「A richer converter can replace it without changing the seam or tool schema」，README 的 Known Limitations 章节也把它记载为「a minimal regex converter, not an HTML parser — tables, images, and nested formatting are lost」。[web 能力 seam 决策记录](../architecture/2026-06-24-web-capability-seam.md)把 HTML 转 markdown 作为呈现职责划归本包（package），因此替换点恰好就在这里。每个抓取到的 HTML 页面上，该转换器的输出都对模型可见；此前没有任何无密钥快照执行到 `web_fetch`，因此没有预期输出固定它的行为。 + +## 决策 + +`packages/web/tool-web/src/fetch.ts` 持有一个模块级 [`turndown`](https://github.com/mixmark-io/turndown) 实例（`headingStyle: 'atx'`、`codeBlockStyle: 'fenced'`、`bulletListMarker: '-'`——固定的面向模型呈现方式，不是部署可调项），配合 `@joplin/turndown-plugin-gfm` 的组合 `gfm` 插件提供表格／删除线支持，并用 `remove(['script', 'style', 'noscript'])` 替代旧实现的整体剥离。`renderBody` 的 `html` 分支把调用包在 try/catch 中，失败时回退为原始 HTML 主体：正则版本从不可能抛异常，而 turndown/domino 的递归 DOM 遍历在数千层嵌套（实测：主线程 4k 层抛出，worker 线程 8k 层抛出）会以 `RangeError` 栈溢出，对提供方已经解码的主体来说，降级页面好过报错。`html.ts` 及其转换测试已删除；回退路径与状态头、截断页脚的格式化在 `tests/tool-web.spec.ts` 中有测试覆盖，README 的 Known Limitations 用病态嵌套回退条目替换了正则转换器的警示说明。gfm 插件不带类型声明；`src/turndown-plugin-gfm.d.ts` 基于 `@types/turndown`（devDependency）声明了唯一被导入的导出。 + +提案标记的依赖体积问题的裁决结果支持替换：`@deepseek-ai/dsh-tool-web` 在单文件可执行文件闭包内（[single-exe 决策记录](../architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.md)），可执行文件的资产 glob 会把这三个包按发布原样打入约 7.9 MB——但其中约 6 MB 是 `@mixmark-io/domino` 的测试语料（`test/**`），运行时 `lib/` 仅约 550 KB，相对约 174 MB 的产物，两种口径都不到 0.5%。 + +## 快照覆盖 + +此前缺失的无密钥 `web_fetch` 快照随本变更以 acp-agent 场景 `web-fetch` 落地：`examples/acp-agent/web.cordis.yml` 组合了 web seam、真实的 `dsh-web-fetch-local` 提供方、`search: false` 的 `tool-web`，以及 `web-fetch-fixture-server.mjs`——一个固定端口（抓取的 URL 是录制 transcript（文本记录）的一部分）上的回环 HTTP fixture，提供包含命名实体、GFM 表格与嵌套格式的确定性 HTML。录制与无密钥回放都驱动真实的 HTTP 抓取与转换；固定住的工具结果就是 turndown 的输出，该场景同时固定 `web` header 类（`web_fetch` 的 schema 与指引）。 + +## 曾考虑的替代方案 + +- **`@mozilla/readability` 加一个 DOM。** 它解决的是另一个问题（内容提取，而非格式转换），还会拖入更重的 DOM 依赖；这个 seam 只要求把抓取返回的内容渲染成 markdown。 +- **保留正则转换器。** 按其自身 JSDoc 的说法，它本来就是明确的 v1 占位实现；保留它意味着模型可见的质量（表格、图片、嵌套格式）继续缺失，代价还是维护一套自制实体表。 +- **仅引入 `entities` 的最小变体。** 提案中的退守方案：只用零依赖的 `entities` 包替换 `html.ts` 中的实体解码部分，删得更少但完全避开依赖体积问题。未采纳：上述闭包测算表明体积无关紧要，而完整替换能删掉整个手写转换器及其记录在案的质量缺口。 +- **用原版 `turndown-plugin-gfm` 而非 `@joplin/turndown-plugin-gfm`。** 原版已无人维护（最后发布于 2018 年）；Joplin 分叉与 turndown 7 保持同步并持续发布。 + +## 后果 + +- **收益**：模型可见的完整保真 markdown——表格、图片、删除线、嵌套强调、围栏代码块以及完整的命名实体集——并删除了自制转换器及其实体表，README 中的正则转换器警示收窄为一个退化用例。 +- **代价**：两个运行时依赖（`turndown` → `@mixmark-io/domino`）进入 tool-web 进而进入可执行文件闭包（如上实测约 550 KB 运行时代码），并新增一种失败模式——病态嵌套改为回退原始 HTML 而非转换。 +- 每个抓取到的 HTML 页面上模型可见的输出都已变化；旧输出本无任何固定，新快照固定了新输出。 + +## 测试 + +- `packages/web/tool-web/tests/tool-web.spec.ts` 通过 `renderBody` 覆盖 turndown 转换面（实体、链接、表格、嵌套、script/style/noscript 移除），并用实测可稳定溢出的 2 万层嵌套输入覆盖原始 HTML 回退；该包 src 的逐文件覆盖率为 100%。 +- acp-agent 的 `web-fetch` 快照无密钥地端到端固定组装后的行为（真实 Loader 组合、真实 HTTP 抓取、真实转换）。 diff --git a/.agents/notes/proposed/simplification/2026-07-26-turndown-for-tool-web-html-markdown.md b/.agents/notes/proposed/simplification/2026-07-26-turndown-for-tool-web-html-markdown.md deleted file mode 100644 index 7f25e51bf6..0000000000 --- a/.agents/notes/proposed/simplification/2026-07-26-turndown-for-tool-web-html-markdown.md +++ /dev/null @@ -1,32 +0,0 @@ -# Agent Note: Replace tool-web's regex HTML-to-markdown converter with turndown - -Status: proposed - -English | [中文](2026-07-26-turndown-for-tool-web-html-markdown.zh.md) - -## Problem - -`packages/web/tool-web/src/html.ts` (~86 lines, ~40 lines of dedicated tests) converts fetched HTML to markdown with regexes: strip script/style/noscript/comments, convert ``/``/`
  • `, decode numeric entities plus a 12-entry named-entity table, collapse whitespace. The module's own JSDoc says "A richer converter can replace it without changing the seam or tool schema", and the README's Known Limitations documents it as "a minimal regex converter, not an HTML parser — tables, images, and nested formatting are lost." The [web capability seam note](../../implemented/architecture/2026-06-24-web-capability-seam.md) assigns HTML→markdown to this package as presentation, so the swap point is exactly here. The converter's output is model-visible on every fetched HTML page; no keyless snapshot currently exercises `web_fetch`, so no expected outputs pin it. - -## Proposal - -Replace `htmlToMarkdown` with `turndown` (`new TurndownService().turndown(html)`), optionally with `turndown-plugin-gfm` for tables. The consumer switch in `fetch.ts` and the status-header/truncation-footer formatting stay. Wrap the call in try/catch falling back to the raw text path: the regex version could never throw; turndown on pathological HTML could. Delete `html.ts` and its conversion tests; keep tests for the fallback and the surrounding formatting. Update the README's Known Limitations to drop the regex-converter caveat. - -If the "deliberately minimal fallback" stance is preferred instead, a minimal variant still deletes the worst part: replace the entity-decoding third of the file (~30 lines: `decodeEntities`, `NAMED_ENTITIES`, `safeFromCodePoint`) with the zero-dependency `entities` package (already in the lockfile transitively), erasing the documented "about a dozen entities" limitation at near-zero risk. - -## Alternatives considered - -- **`@mozilla/readability` + a DOM.** Solves a different problem (content extraction, not conversion) and drags a heavier DOM dependency; the seam only asks for markdown rendering of whatever the fetch returned. -- **Keep the regex converter.** It was an explicit v1 placeholder per its own JSDoc; keeping it means model-visible quality (tables, images, nested formatting) stays lost for the cost of maintaining bespoke entity tables. -- **The minimal `entities`-only variant.** Kept in the proposal as the fallback position; it deletes less but avoids the dependency-weight question entirely. - -## Acceptance criteria - -- `web_fetch` renders tables/nested formatting via turndown (or, minimal variant: decodes all named entities), with the README limitation updated. -- Unit tests cover the fallback path; `pnpm run test` passes for the package. -- A keyless snapshot exercising `web_fetch` markdown rendering is added per testing policy (the missing snapshot coverage is part of the change, and it pins the new output). - -## Risks - -- Model-visible output changes on every fetched HTML page — transcript drift is acceptable pre-release, and nothing currently pins the old output. -- Dependency weight: turndown's one dependency (`@mixmark-io/domino`) is a ~200 KB DOM that would enter the single-file-executable closure if tool-web ships in it ([single-exe note](../../implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.md)); the minimal `entities` variant avoids this if closure size is the deciding factor. diff --git a/.agents/notes/proposed/simplification/2026-07-26-turndown-for-tool-web-html-markdown.zh.md b/.agents/notes/proposed/simplification/2026-07-26-turndown-for-tool-web-html-markdown.zh.md deleted file mode 100644 index 3a59b08e13..0000000000 --- a/.agents/notes/proposed/simplification/2026-07-26-turndown-for-tool-web-html-markdown.zh.md +++ /dev/null @@ -1,32 +0,0 @@ -# Agent Note: 用 turndown 替换 tool-web 的正则 HTML 转 markdown 转换器 - -Status: proposed - -[English](2026-07-26-turndown-for-tool-web-html-markdown.md) | 中文 - -## 问题 - -`packages/web/tool-web/src/html.ts`（约 86 行，另有约 40 行专属测试）用正则表达式把抓取到的 HTML 转成 markdown：剥离 script、style、noscript 标签与注释，转换 ``/``/`
  • `，解码数字实体外加一张 12 项的命名实体表，并折叠空白。该模块自身的 JSDoc 写明「A richer converter can replace it without changing the seam or tool schema」，README 的 Known Limitations 章节也把它记载为「a minimal regex converter, not an HTML parser — tables, images, and nested formatting are lost」。[web 能力 seam 决策记录](../../implemented/architecture/2026-06-24-web-capability-seam.md)把 HTML 转 markdown 作为呈现职责划归本包（package），因此替换点恰好就在这里。每个抓取到的 HTML 页面上，该转换器的输出都对模型可见；当前没有任何无密钥快照执行到 `web_fetch`，因此没有预期输出固定它的行为。 - -## 提案 - -用 `turndown` 替换 `htmlToMarkdown`（`new TurndownService().turndown(html)`），可选择配合 `turndown-plugin-gfm` 支持表格。`fetch.ts` 中的消费方分支与状态头、截断页脚的格式化保持不变。把调用包在 try/catch 中，失败时回退到原始文本路径：正则版本从不可能抛异常，而 turndown 处理病态 HTML 时可能抛出。删除 `html.ts` 及其转换测试；保留回退路径与外围格式化的测试。更新 README 的 Known Limitations 章节，移除正则转换器的警示说明。 - -如果更倾向于「刻意保持最小回退实现」的立场，最小变体仍能删掉最糟的部分：用零依赖的 `entities` 包（已通过传递依赖存在于 lockfile 中）替换文件中占三分之一的实体解码部分（约 30 行：`decodeEntities`、`NAMED_ENTITIES`、`safeFromCodePoint`），以近乎为零的风险抹掉文档记载的「about a dozen entities」限制。 - -## 曾考虑的替代方案 - -- **`@mozilla/readability` 加一个 DOM。** 它解决的是另一个问题（内容提取，而非格式转换），还会拖入更重的 DOM 依赖；这个 seam 只要求把抓取返回的内容渲染成 markdown。 -- **保留正则转换器。** 按其自身 JSDoc 的说法，它本来就是明确的 v1 占位实现；保留它意味着模型可见的质量（表格、图片、嵌套格式）继续缺失，代价还是维护一套自制实体表。 -- **仅引入 `entities` 的最小变体。** 已作为退守方案保留在提案中；它删得更少，但完全避开了依赖体积问题。 - -## 验收标准 - -- `web_fetch` 经由 turndown 渲染表格与嵌套格式（或在最小变体下：解码全部命名实体），README 中的限制说明同步更新。 -- 单元测试覆盖回退路径；该包的 `pnpm run test` 通过。 -- 按测试政策补充一个执行 `web_fetch` markdown 渲染的无密钥快照（缺失的快照覆盖是本变更的一部分，它同时固定新输出）。 - -## 风险 - -- 模型可见的输出在每个抓取到的 HTML 页面上都会变化：预发布阶段的 transcript（文本记录）漂移可以接受，且当前没有任何东西固定旧输出。 -- 依赖体积：turndown 的唯一依赖（`@mixmark-io/domino`）是一个约 200 KB 的 DOM 实现，若 tool-web 进入单文件可执行文件，它会一并进入闭包（[single-exe 决策记录](../../implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.md)）；若闭包体积是决定因素，最小的 `entities` 变体可以避开这一点。 diff --git a/docs/config-catalog.md b/docs/config-catalog.md index 9880761894..30499c7df6 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -1672,7 +1672,7 @@ export interface Config { } ``` -Source: [`packages/web/tool-web/src/index.ts:29`](../packages/web/tool-web/src/index.ts) +Source: [`packages/web/tool-web/src/index.ts:28`](../packages/web/tool-web/src/index.ts) ## `@deepseek-ai/dsh-tool-workflow` diff --git a/examples/acp-agent/README.i18n.yaml b/examples/acp-agent/README.i18n.yaml index 22842fcd04..391967d91c 100644 --- a/examples/acp-agent/README.i18n.yaml +++ b/examples/acp-agent/README.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 -README.md: 4b3d86b00613cc7c37a8898ef3b39d40a167e66b -README.zh.md: 5bcd85f2b4ae34a11b980bf196d3401f764004d8 +README.md: 0d63ec1f2d9165b9faf0817bd94fbe15b97fa961 +README.zh.md: 0c5f8866ea640843513fd9a4c15a17ed4db59d3b diff --git a/examples/acp-agent/README.md b/examples/acp-agent/README.md index 4b3d86b006..0d63ec1f2d 100644 --- a/examples/acp-agent/README.md +++ b/examples/acp-agent/README.md @@ -9,7 +9,7 @@ pnpm run demo:acp # needs DEEPSEEK_API_KEY (repo-root .env or env) pnpm run demo:code-mode acp # same protocol with the Code Mode tool transport ``` -The leaf loads the ACP app, DeepSeek adapter, sandboxed bash and filesystem stacks, one-shot approval policy, compaction, subagents, workflows, hooks, a derived session-query index, and repeat guard. The app creates one fresh agent per `session/new`, persists sessions to JSONL, and keeps stdout protocol-pure. [`session-query.cordis.yml`](session-query.cordis.yml) explicitly opts into the workspace-authorized query tools and generic timeout/spill policies for their dedicated snapshot; [`fs.cordis.yml`](fs.cordis.yml) adds spill storage for filesystem scenarios, while [`code-mode.cordis.yml`](code-mode.cordis.yml) adds `run_code` and its generated TypeScript SDK. +The leaf loads the ACP app, DeepSeek adapter, sandboxed bash and filesystem stacks, one-shot approval policy, compaction, subagents, workflows, hooks, a derived session-query index, and repeat guard. The app creates one fresh agent per `session/new`, persists sessions to JSONL, and keeps stdout protocol-pure. [`session-query.cordis.yml`](session-query.cordis.yml) explicitly opts into the workspace-authorized query tools and generic timeout/spill policies for their dedicated snapshot; [`fs.cordis.yml`](fs.cordis.yml) adds spill storage for filesystem scenarios, [`code-mode.cordis.yml`](code-mode.cordis.yml) adds `run_code` and its generated TypeScript SDK, and [`web.cordis.yml`](web.cordis.yml) adds the web seam, the local fetch provider, `web_fetch`, and a loopback HTML fixture server for the web-fetch snapshot. ## Protocol channel diff --git a/examples/acp-agent/README.zh.md b/examples/acp-agent/README.zh.md index 5bcd85f2b4..0c5f8866ea 100644 --- a/examples/acp-agent/README.zh.md +++ b/examples/acp-agent/README.zh.md @@ -9,7 +9,7 @@ pnpm run demo:acp # needs DEEPSEEK_API_KEY (repo-root .env or env) pnpm run demo:code-mode acp # same protocol with the Code Mode tool transport ``` -该叶节点加载 ACP 应用、DeepSeek 适配器、受沙箱限制的 bash 与文件系统栈、一次性批准策略、压缩（compaction）、subagent、工作流、钩子、派生会话查询索引和重复守卫。应用为每次 `session/new` 创建一个新 agent，将会话持久化到 JSONL，并保持 stdout 只含协议内容。[`session-query.cordis.yml`](session-query.cordis.yml) 为其专用快照显式选用 workspace 授权的查询工具和通用超时／溢出策略；[`fs.cordis.yml`](fs.cordis.yml) 为文件系统场景添加溢出存储，[`code-mode.cordis.yml`](code-mode.cordis.yml) 则添加 `run_code` 及其生成的 TypeScript SDK。 +该叶节点加载 ACP 应用、DeepSeek 适配器、受沙箱限制的 bash 与文件系统栈、一次性批准策略、压缩（compaction）、subagent、工作流、钩子、派生会话查询索引和重复守卫。应用为每次 `session/new` 创建一个新 agent，将会话持久化到 JSONL，并保持 stdout 只含协议内容。[`session-query.cordis.yml`](session-query.cordis.yml) 为其专用快照显式选用 workspace 授权的查询工具和通用超时／溢出策略；[`fs.cordis.yml`](fs.cordis.yml) 为文件系统场景添加溢出存储，[`code-mode.cordis.yml`](code-mode.cordis.yml) 添加 `run_code` 及其生成的 TypeScript SDK，[`web.cordis.yml`](web.cordis.yml) 则为 web-fetch 快照添加 web seam、本地抓取提供方、`web_fetch` 与一个回环 HTML fixture 服务器。 ## 协议通道 diff --git a/examples/acp-agent/tests/acp.snapshot.ts b/examples/acp-agent/tests/acp.snapshot.ts index 8e74711a57..ed4a7d6a58 100644 --- a/examples/acp-agent/tests/acp.snapshot.ts +++ b/examples/acp-agent/tests/acp.snapshot.ts @@ -41,6 +41,7 @@ const PACKED_CHUNKS_CONFIG = fileURLToPath(new URL('../packed-chunks.cordis.yml' const SESSION_SANDBOX_ROOT_CONFIG = fileURLToPath(new URL('../session-sandbox-root.cordis.yml', import.meta.url)) const RETRY_CONFIG = fileURLToPath(new URL('../retry.cordis.yml', import.meta.url)) const LSP_CONFIG = fileURLToPath(new URL('./lsp.cordis.yml', import.meta.url)) +const WEB_CONFIG = fileURLToPath(new URL('../web.cordis.yml', import.meta.url)) const SNAPSHOTS_DIR = join(dirname(fileURLToPath(import.meta.url)), 'snapshots') const PACKED_CHUNKS_SOURCE = 'hook-cc-pretool-deny' @@ -110,6 +111,12 @@ const SCENARIOS: Scenario[] = [ { name: 'todo-write', hasModelTurn: true, recorded: true }, { name: 'skill-load', hasModelTurn: true, recorded: false, pinsHeader: true, headerClass: 'skill' }, { name: 'lsp-definition', hasModelTurn: true, recorded: false, pinsHeader: true, headerClass: 'lsp', configPath: LSP_CONFIG }, + // web_fetch markdown rendering end to end: the overlay's loopback fixture + // server supplies deterministic HTML (entities, a GFM table, nesting), the + // REAL local fetch provider retrieves it, and the tool result pins the + // turndown conversion. The fetched URL (fixed port) is part of the recorded + // transcript; replay re-executes the real fetch against the same fixture. + { name: 'web-fetch', hasModelTurn: true, recorded: true, pinsHeader: true, headerClass: 'web', configPath: WEB_CONFIG }, { name: 'workspace-edit', hasModelTurn: true, diff --git a/examples/acp-agent/tests/snapshots/web-fetch/input.json b/examples/acp-agent/tests/snapshots/web-fetch/input.json new file mode 100644 index 0000000000..dc1993235d --- /dev/null +++ b/examples/acp-agent/tests/snapshots/web-fetch/input.json @@ -0,0 +1,7 @@ +{ + "steps": [ + { "op": "initialize" }, + { "op": "newSession" }, + { "op": "prompt", "text": "Use the web_fetch tool exactly once to fetch http://127.0.0.1:43117/menu.html, then reply with exactly DONE. Do not describe the content." } + ] +} diff --git a/examples/acp-agent/tests/snapshots/web-fetch/session.jsonl b/examples/acp-agent/tests/snapshots/web-fetch/session.jsonl new file mode 100644 index 0000000000..c6c34bc8e3 --- /dev/null +++ b/examples/acp-agent/tests/snapshots/web-fetch/session.jsonl @@ -0,0 +1,127 @@ +{"type":"session","version":0,"id":"c12fa9af-1042-4a92-9ba4-4a968ff23495","createdAt":1785078727712,"cwd":"/tmp/acp-snap-cwd-hqkZWE","delegationDepth":0} +{"type":"turn/start","seq":0,"time":1785078727718,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} +{"type":"user/message","seq":1,"time":1785078727719,"data":{"content":[{"type":"text","text":"Use the web_fetch tool exactly once to fetch http://127.0.0.1:43117/menu.html, then reply with exactly DONE. Do not describe the content."}],"source":{"kind":"user"}},"surfaceOp":"append"} +{"type":"session/title","seq":2,"time":1785078727721,"data":{"title":"Use the web_fetch tool exactly","messageSeqs":[1],"source":{"kind":"fallback"}}} +{"type":"step/start","seq":3,"time":1785078727730,"data":{"turn":1,"step":1}} +{"type":"request/header","seq":4,"time":1785078727731,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-pro"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"assistant/chunk","seq":5,"time":1785078728804,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} +{"type":"assistant/chunk","seq":6,"time":1785078728805,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} +{"type":"assistant/chunk","seq":7,"time":1785078728943,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} +{"type":"assistant/chunk","seq":8,"time":1785078728989,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" wants"}}} +{"type":"assistant/chunk","seq":9,"time":1785078728989,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" me"}}} +{"type":"assistant/chunk","seq":10,"time":1785078728989,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} +{"type":"assistant/chunk","seq":11,"time":1785078728990,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" use"}}} +{"type":"assistant/chunk","seq":12,"time":1785078728990,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} +{"type":"assistant/chunk","seq":13,"time":1785078728990,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" web"}}} +{"type":"assistant/chunk","seq":14,"time":1785078729038,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"_f"}}} +{"type":"assistant/chunk","seq":15,"time":1785078729038,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"etch"}}} +{"type":"assistant/chunk","seq":16,"time":1785078729039,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" tool"}}} +{"type":"assistant/chunk","seq":17,"time":1785078729039,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" exactly"}}} +{"type":"assistant/chunk","seq":18,"time":1785078729085,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" once"}}} +{"type":"assistant/chunk","seq":19,"time":1785078729086,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} +{"type":"assistant/chunk","seq":20,"time":1785078729086,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" fetch"}}} +{"type":"assistant/chunk","seq":21,"time":1785078729086,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" http"}}} +{"type":"assistant/chunk","seq":22,"time":1785078729086,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"://"}}} +{"type":"assistant/chunk","seq":23,"time":1785078729086,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"127"}}} +{"type":"assistant/chunk","seq":24,"time":1785078729132,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} +{"type":"assistant/chunk","seq":25,"time":1785078729133,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"0"}}} +{"type":"assistant/chunk","seq":26,"time":1785078729133,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} +{"type":"assistant/chunk","seq":27,"time":1785078729133,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"0"}}} +{"type":"assistant/chunk","seq":28,"time":1785078729133,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} +{"type":"assistant/chunk","seq":29,"time":1785078729133,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"1"}}} +{"type":"assistant/chunk","seq":30,"time":1785078729182,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":":"}}} +{"type":"assistant/chunk","seq":31,"time":1785078729182,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"431"}}} +{"type":"assistant/chunk","seq":32,"time":1785078729183,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"17"}}} +{"type":"assistant/chunk","seq":33,"time":1785078729183,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"/m"}}} +{"type":"assistant/chunk","seq":34,"time":1785078729183,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"enu"}}} +{"type":"assistant/chunk","seq":35,"time":1785078729183,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":".html"}}} +{"type":"assistant/chunk","seq":36,"time":1785078729230,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":","}}} +{"type":"assistant/chunk","seq":37,"time":1785078729230,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" then"}}} +{"type":"assistant/chunk","seq":38,"time":1785078729230,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" reply"}}} +{"type":"assistant/chunk","seq":39,"time":1785078729230,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" with"}}} +{"type":"assistant/chunk","seq":40,"time":1785078729230,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" exactly"}}} +{"type":"assistant/chunk","seq":41,"time":1785078729231,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" \""}}} +{"type":"assistant/chunk","seq":42,"time":1785078729276,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"D"}}} +{"type":"assistant/chunk","seq":43,"time":1785078729277,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"ONE"}}} +{"type":"assistant/chunk","seq":44,"time":1785078729277,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"\"."}}} +{"type":"assistant/chunk","seq":45,"time":1785078729277,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" Let"}}} +{"type":"assistant/chunk","seq":46,"time":1785078729322,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" me"}}} +{"type":"assistant/chunk","seq":47,"time":1785078729323,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" do"}}} +{"type":"assistant/chunk","seq":48,"time":1785078729323,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" that"}}} +{"type":"assistant/chunk","seq":49,"time":1785078729323,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} +{"type":"assistant/chunk","seq":50,"time":1785078729463,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"tool-call"}}} +{"type":"assistant/chunk","seq":51,"time":1785078729464,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_sxjOyfDYN07koiE7jiIa5326","name":"web_fetch","argumentsDelta":""}}} +{"type":"assistant/chunk","seq":52,"time":1785078729511,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_sxjOyfDYN07koiE7jiIa5326","name":"web_fetch","argumentsDelta":"{"}}} +{"type":"assistant/chunk","seq":53,"time":1785078729511,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_sxjOyfDYN07koiE7jiIa5326","name":"web_fetch","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":54,"time":1785078729511,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_sxjOyfDYN07koiE7jiIa5326","name":"web_fetch","argumentsDelta":"url"}}} +{"type":"assistant/chunk","seq":55,"time":1785078729511,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_sxjOyfDYN07koiE7jiIa5326","name":"web_fetch","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":56,"time":1785078729511,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_sxjOyfDYN07koiE7jiIa5326","name":"web_fetch","argumentsDelta":": "}}} +{"type":"assistant/chunk","seq":57,"time":1785078729557,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_sxjOyfDYN07koiE7jiIa5326","name":"web_fetch","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":58,"time":1785078729557,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_sxjOyfDYN07koiE7jiIa5326","name":"web_fetch","argumentsDelta":"http"}}} +{"type":"assistant/chunk","seq":59,"time":1785078729557,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_sxjOyfDYN07koiE7jiIa5326","name":"web_fetch","argumentsDelta":"://"}}} +{"type":"assistant/chunk","seq":60,"time":1785078729558,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_sxjOyfDYN07koiE7jiIa5326","name":"web_fetch","argumentsDelta":"127"}}} +{"type":"assistant/chunk","seq":61,"time":1785078729604,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_sxjOyfDYN07koiE7jiIa5326","name":"web_fetch","argumentsDelta":"."}}} +{"type":"assistant/chunk","seq":62,"time":1785078729604,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_sxjOyfDYN07koiE7jiIa5326","name":"web_fetch","argumentsDelta":"0"}}} +{"type":"assistant/chunk","seq":63,"time":1785078729604,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_sxjOyfDYN07koiE7jiIa5326","name":"web_fetch","argumentsDelta":"."}}} +{"type":"assistant/chunk","seq":64,"time":1785078729604,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_sxjOyfDYN07koiE7jiIa5326","name":"web_fetch","argumentsDelta":"0"}}} +{"type":"assistant/chunk","seq":65,"time":1785078729604,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_sxjOyfDYN07koiE7jiIa5326","name":"web_fetch","argumentsDelta":"."}}} +{"type":"assistant/chunk","seq":66,"time":1785078729605,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_sxjOyfDYN07koiE7jiIa5326","name":"web_fetch","argumentsDelta":"1"}}} +{"type":"assistant/chunk","seq":67,"time":1785078729651,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_sxjOyfDYN07koiE7jiIa5326","name":"web_fetch","argumentsDelta":":"}}} +{"type":"assistant/chunk","seq":68,"time":1785078729652,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_sxjOyfDYN07koiE7jiIa5326","name":"web_fetch","argumentsDelta":"431"}}} +{"type":"assistant/chunk","seq":69,"time":1785078729652,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_sxjOyfDYN07koiE7jiIa5326","name":"web_fetch","argumentsDelta":"17"}}} +{"type":"assistant/chunk","seq":70,"time":1785078729652,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_sxjOyfDYN07koiE7jiIa5326","name":"web_fetch","argumentsDelta":"/m"}}} +{"type":"assistant/chunk","seq":71,"time":1785078729652,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_sxjOyfDYN07koiE7jiIa5326","name":"web_fetch","argumentsDelta":"enu"}}} +{"type":"assistant/chunk","seq":72,"time":1785078729652,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_sxjOyfDYN07koiE7jiIa5326","name":"web_fetch","argumentsDelta":".html"}}} +{"type":"assistant/chunk","seq":73,"time":1785078729697,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_sxjOyfDYN07koiE7jiIa5326","name":"web_fetch","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":74,"time":1785078729698,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_sxjOyfDYN07koiE7jiIa5326","name":"web_fetch","argumentsDelta":"}"}}} +{"type":"assistant/chunk","seq":75,"time":1785078729803,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user wants me to use the web_fetch tool exactly once to fetch http://127.0.0.1:43117/menu.html, then reply with exactly \"DONE\". Let me do that."}}}} +{"type":"assistant/chunk","seq":76,"time":1785078729803,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_sxjOyfDYN07koiE7jiIa5326","name":"web_fetch","arguments":"{\"url\": \"http://127.0.0.1:43117/menu.html\"}"}}}} +{"type":"assistant/chunk","seq":77,"time":1785078729803,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":5405,"outputTokens":103,"cacheReadTokens":0,"reasoningTokens":44}}}} +{"type":"assistant/chunk","seq":78,"time":1785078729804,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} +{"type":"assistant/message","seq":79,"time":1785078729807,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to use the web_fetch tool exactly once to fetch http://127.0.0.1:43117/menu.html, then reply with exactly \"DONE\". Let me do that."},{"type":"tool-call","id":"call_00_sxjOyfDYN07koiE7jiIa5326","name":"web_fetch","arguments":"{\"url\": \"http://127.0.0.1:43117/menu.html\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-pro"},"usage":{"inputTokens":5405,"outputTokens":103,"cacheReadTokens":0,"reasoningTokens":44}},"sourceEventSeqs":[5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78],"surfaceOp":"append"} +{"type":"tool/call","seq":80,"time":1785078729809,"data":{"turn":1,"step":1,"callId":"call_00_sxjOyfDYN07koiE7jiIa5326","name":"web_fetch","arguments":"{\"url\": \"http://127.0.0.1:43117/menu.html\"}"}} +{"type":"tool/result","seq":81,"time":1785078729843,"data":{"turn":1,"step":1,"callId":"call_00_sxjOyfDYN07koiE7jiIa5326","content":[{"type":"text","text":"Fetched http://127.0.0.1:43117/menu.html (HTTP 200)\n\nMenu\n\n# Café menu\n\nPrices include **service & _tax_** — updated daily.\n\n- Espresso\n- Flat white\n\n| Drink | Price |\n| --- | --- |\n| Espresso | €2 |\n| Flat white | €3 |\n\nSee [today’s specials](https://fixture.invalid/specials)."}],"isError":false},"sourceEventSeqs":[80],"surfaceOp":"append"} +{"type":"step/end","seq":82,"time":1785078729847,"data":{"turn":1,"step":1}} +{"type":"step/start","seq":83,"time":1785078729848,"data":{"turn":1,"step":2}} +{"type":"assistant/chunk","seq":84,"time":1785078730611,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} +{"type":"assistant/chunk","seq":85,"time":1785078730612,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} +{"type":"assistant/chunk","seq":86,"time":1785078730770,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} +{"type":"assistant/chunk","seq":87,"time":1785078730824,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" asked"}}} +{"type":"assistant/chunk","seq":88,"time":1785078730825,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" me"}}} +{"type":"assistant/chunk","seq":89,"time":1785078730825,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} +{"type":"assistant/chunk","seq":90,"time":1785078730825,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" fetch"}}} +{"type":"assistant/chunk","seq":91,"time":1785078730861,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} +{"type":"assistant/chunk","seq":92,"time":1785078730862,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" URL"}}} +{"type":"assistant/chunk","seq":93,"time":1785078730909,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":","}}} +{"type":"assistant/chunk","seq":94,"time":1785078730956,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" then"}}} +{"type":"assistant/chunk","seq":95,"time":1785078731002,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" reply"}}} +{"type":"assistant/chunk","seq":96,"time":1785078731003,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" with"}}} +{"type":"assistant/chunk","seq":97,"time":1785078731003,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" exactly"}}} +{"type":"assistant/chunk","seq":98,"time":1785078731003,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" \""}}} +{"type":"assistant/chunk","seq":99,"time":1785078731050,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"D"}}} +{"type":"assistant/chunk","seq":100,"time":1785078731050,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"ONE"}}} +{"type":"assistant/chunk","seq":101,"time":1785078731050,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"\"."}}} +{"type":"assistant/chunk","seq":102,"time":1785078731050,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" I"}}} +{"type":"assistant/chunk","seq":103,"time":1785078731050,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"'ve"}}} +{"type":"assistant/chunk","seq":104,"time":1785078731051,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" fetched"}}} +{"type":"assistant/chunk","seq":105,"time":1785078731097,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" it"}}} +{"type":"assistant/chunk","seq":106,"time":1785078731140,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} +{"type":"assistant/chunk","seq":107,"time":1785078731141,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" Now"}}} +{"type":"assistant/chunk","seq":108,"time":1785078731141,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" I"}}} +{"type":"assistant/chunk","seq":109,"time":1785078731141,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" just"}}} +{"type":"assistant/chunk","seq":110,"time":1785078731189,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" reply"}}} +{"type":"assistant/chunk","seq":111,"time":1785078731189,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" with"}}} +{"type":"assistant/chunk","seq":112,"time":1785078731235,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" \""}}} +{"type":"assistant/chunk","seq":113,"time":1785078731235,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"D"}}} +{"type":"assistant/chunk","seq":114,"time":1785078731235,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"ONE"}}} +{"type":"assistant/chunk","seq":115,"time":1785078731235,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"\"."}}} +{"type":"assistant/chunk","seq":116,"time":1785078731235,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":1,"blockType":"text"}}} +{"type":"assistant/chunk","seq":117,"time":1785078731236,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"D"}}} +{"type":"assistant/chunk","seq":118,"time":1785078731282,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"ONE"}}} +{"type":"assistant/chunk","seq":119,"time":1785078731282,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user asked me to fetch the URL, then reply with exactly \"DONE\". I've fetched it. Now I just reply with \"DONE\"."}}}} +{"type":"assistant/chunk","seq":120,"time":1785078731282,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"DONE"}}}} +{"type":"assistant/chunk","seq":121,"time":1785078731282,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":239,"outputTokens":34,"cacheReadTokens":5376,"reasoningTokens":31}}}} +{"type":"assistant/chunk","seq":122,"time":1785078731282,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} +{"type":"assistant/message","seq":123,"time":1785078731283,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The user asked me to fetch the URL, then reply with exactly \"DONE\". I've fetched it. Now I just reply with \"DONE\"."},{"type":"text","text":"DONE"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-pro"},"usage":{"inputTokens":239,"outputTokens":34,"cacheReadTokens":5376,"reasoningTokens":31}},"sourceEventSeqs":[84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122],"surfaceOp":"append"} +{"type":"step/end","seq":124,"time":1785078731286,"data":{"turn":1,"step":2}} +{"type":"turn/end","seq":125,"time":1785078731286,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/web-fetch/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/web-fetch/stdout.expected.jsonl new file mode 100644 index 0000000000..82ae8907ca --- /dev/null +++ b/examples/acp-agent/tests/snapshots/web-fetch/stdout.expected.jsonl @@ -0,0 +1,4 @@ +{"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}"}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"DONE"}}}} +{"jsonrpc":"2.0","id":3,"result":{"stopReason":"end_turn"}} diff --git a/examples/acp-agent/tests/snapshots/web-fetch/system-prompt.expected.md b/examples/acp-agent/tests/snapshots/web-fetch/system-prompt.expected.md new file mode 100644 index 0000000000..45705db0a5 --- /dev/null +++ b/examples/acp-agent/tests/snapshots/web-fetch/system-prompt.expected.md @@ -0,0 +1,27 @@ +You are an AI agent powered by the DeepSeek Harness SDK. + +You are a coding assistant powered by the deepseek-v4-pro model. Your working directory is {{cwd}}. Your bash tool runs under a file sandbox — a `[sandbox: file access denied …]` result is policy, not a command bug. + +Verify your work by running the code or tests. Keep answers brief and factual. + + +Use the read tool — not shell commands like cat — to inspect text files. Results include line numbers. Use offset and limit to continue reading large files. + +Use the write tool to create files or completely replace file contents. Existing files are overwritten, so read an existing file first (the default fs-policy requires it) and prefer edit for targeted changes. + +Use the edit tool for targeted changes to existing UTF-8 text files. It replaces literal old_string with new_string; by default old_string must appear exactly once. If old_string appears multiple times, provide a more specific old_string or set replace_all to true. Read the file first (the default fs-policy requires it), unless you just created or edited it in this session. + +Check the [exit code: N] marker on every bash result; investigate failures before moving on. + +Track every background task id you start. You are notified in-session when a task finishes — do not busy-poll or sleep on one; keep working on independent steps and do not duplicate a running task's work. Before giving a final answer, collect every still-relevant task with task_output (set wait: true only when you are genuinely blocked on it), and task_kill tasks that stopped mattering. + +Use the web_fetch tool to retrieve the content of a specific HTTP(S) URL (for example a result from web_search). It returns the page content decoded to text. Cite the URL as a markdown link when you use its content. + +Use goal tools for one long-running completion objective in the current session. create_goal may infer goal intent from a direct human request in any language; do not create a goal for routine single-turn work. Call get_goal before update_goal and copy its exact goal_id and revision. After session resume or fork, an active goal is disarmed: when a human asks to continue or resume in any wording or language, use update_goal action resume to rearm it. Mark complete only when the objective is actually achieved. Mark blocked only after the same blocking condition persists for at least 3 consecutive goal rounds, and report that concrete condition in blocked_reason; difficulty, uncertainty, or useful remaining work is not blocked. + +Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`). + + +Use the workflow tool ONLY when the user explicitly asks for a workflow or for large multi-agent orchestration: you write a JavaScript script (the tool description documents the exact format) that fans work out across many subagents with phases and structured results. For one or two delegations, prefer plain subagent calls. + +Use the ralph tool ONLY when the direct human explicitly asks for a Ralph loop or fresh-agent iterative execution. Each Ralph round starts a fresh child with no conversation seed and uses the shared workspace as durable memory. Completion and blockers are worker reports, not independent evaluation. Use same-session goal tools for ordinary long-running objectives, and plain subagents or workflows for bounded delegation and fan-out. diff --git a/examples/acp-agent/tests/snapshots/web-fetch/tool-schemas.expected.json b/examples/acp-agent/tests/snapshots/web-fetch/tool-schemas.expected.json new file mode 100644 index 0000000000..1ee86b38ba --- /dev/null +++ b/examples/acp-agent/tests/snapshots/web-fetch/tool-schemas.expected.json @@ -0,0 +1,489 @@ +{ + "initial": [ + { + "name": "bash", + "description": "Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Current harness environment facts are exposed through managed `$DSH_*` variables; inspect them when needed. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; read its output with `task_output` and stop it with `task_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.", + "parameters": { + "type": "object", + "properties": { + "command": { + "type": "string", + "description": "The bash command to execute." + }, + "description": { + "type": "string", + "description": "Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"." + }, + "timeoutMs": { + "type": "number", + "description": "Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry." + }, + "workdir": { + "type": "string", + "description": "Working directory for this command. Defaults to the session workspace; a relative path is resolved against it." + }, + "run_in_background": { + "type": "boolean", + "description": "Run in the background and return a task id immediately (collect with task_output, stop with task_kill). No timeout applies." + }, + "sandbox_permissions": { + "type": "string", + "description": "The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.", + "enum": [ + "workspace-write", + "danger-full-access" + ] + }, + "justification": { + "type": "string", + "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access." + } + }, + "required": [ + "command", + "description" + ] + } + }, + { + "name": "create_goal", + "description": "Create one persisted same-session completion goal when the current direct human request is a long-running objective that should continue across autonomous goal rounds. You may infer that intent without requiring the user to say \"create a goal\". Do not use this for trivial single-turn work. Execution rejects non-human and subagent authority.", + "parameters": { + "type": "object", + "properties": { + "objective": { + "type": "string", + "description": "The concrete completion objective inferred from the direct human request." + }, + "max_goal_rounds": { + "type": "number", + "description": "Optional positive safe-integer limit on automatic continuation rounds." + } + }, + "required": [ + "objective" + ] + } + }, + { + "name": "edit", + "description": "Edit an existing UTF-8 text file by replacing literal text.", + "parameters": { + "type": "object", + "properties": { + "file_path": { + "type": "string", + "description": "Path to edit, resolved by the filesystem backend." + }, + "old_string": { + "type": "string", + "description": "Literal text to replace. Must match exactly." + }, + "new_string": { + "type": "string", + "description": "Literal replacement text. Use an empty string to delete the match." + }, + "replace_all": { + "type": "boolean", + "description": "Replace all matches. Defaults to false; when false, old_string must appear exactly once." + }, + "sandbox_permissions": { + "type": "string", + "description": "The wider sandbox mode this file operation needs. Only valid as a one-shot retry of an operation the sandbox just denied; requires justification and user approval.", + "enum": [ + "workspace-write", + "danger-full-access" + ] + }, + "justification": { + "type": "string", + "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access." + } + }, + "required": [ + "file_path", + "old_string", + "new_string" + ] + } + }, + { + "name": "get_goal", + "description": "Read the current same-session goal, including its exact id/revision, objective, phase, completed continuation rounds, round limit, blocker reason when present, and whether another continuation is armed. Call this before updating a goal.", + "parameters": { + "type": "object", + "properties": {} + } + }, + { + "name": "ralph", + "description": "Run a foreground fresh-agent Ralph loop toward one immutable objective. Use only when the direct human explicitly asks for Ralph or fresh-agent iteration. Each round opens a new child with no parent conversation or prior child session; the shared workspace is long-term memory, and only a bounded structured report crosses rounds. The call returns when a worker reports completion or a concrete blocker, or at the round limit. Ordinary long-running same-session work belongs to goal tools.", + "parameters": { + "type": "object", + "properties": { + "objective": { + "type": "string", + "description": "The immutable completion objective for every fresh Ralph round." + }, + "maxRounds": { + "type": "number", + "description": "Optional positive safe-integer round cap, bounded by the deployment ceiling." + } + }, + "required": [ + "objective" + ] + } + }, + { + "name": "read", + "description": "Read a UTF-8 text file and return line-numbered content.", + "parameters": { + "type": "object", + "properties": { + "file_path": { + "type": "string", + "description": "Path to read, resolved by the filesystem backend." + }, + "offset": { + "type": "number", + "description": "1-based first line to return. Defaults to 1." + }, + "limit": { + "type": "number", + "description": "Maximum number of lines to return. Defaults to 2000." + } + }, + "required": [ + "file_path" + ] + } + }, + { + "name": "skill", + "description": "Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.", + "parameters": { + "type": "object", + "properties": { + "name": { + "type": "string", + "description": "The exact skill name from the available skills list." + } + }, + "required": [ + "name" + ] + } + }, + { + "name": "subagent", + "description": "Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation. Set `run_in_background: true` to return a task id; collect with `task_output` and stop with `task_kill`.", + "parameters": { + "type": "object", + "properties": { + "description": { + "type": "string", + "description": "A short (3-5 word) description of the delegated task, for display." + }, + "prompt": { + "type": "string", + "description": "The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs." + }, + "run_in_background": { + "type": "boolean", + "description": "Run as a background task and return its id; collect with task_output or stop with task_kill." + } + }, + "required": [ + "description", + "prompt" + ] + } + }, + { + "name": "subagent_fork", + "description": "Delegate a task to a subagent that inherits this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps. Set `run_in_background: true` to return a task id; collect with `task_output` and stop with `task_kill`.", + "parameters": { + "type": "object", + "properties": { + "description": { + "type": "string", + "description": "A short (3-5 word) description of the delegated task, for display." + }, + "prompt": { + "type": "string", + "description": "The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new." + }, + "run_in_background": { + "type": "boolean", + "description": "Run as a background task and return its id; collect with task_output or stop with task_kill." + } + }, + "required": [ + "description", + "prompt" + ] + } + }, + { + "name": "task_kill", + "description": "Request cancellation of a running background task by task id. Returns immediately; the task settles as killed once its work actually stops.", + "parameters": { + "type": "object", + "properties": { + "task_id": { + "type": "string", + "description": "Task id returned by the tool that started the background work." + }, + "reason": { + "type": "string", + "description": "Optional short reason, recorded in the log and forwarded to the task." + } + }, + "required": [ + "task_id" + ] + } + }, + { + "name": "task_list", + "description": "List your background tasks (running and finished) with their ids, kinds, and statuses.", + "parameters": { + "type": "object", + "properties": {} + } + }, + { + "name": "task_output", + "description": "Read a background task. Stream tasks return only output since the previous read; final-output tasks return their result after settlement. Every response ends with `[status: ...]`. Reads are non-blocking unless `wait: true`, which waits up to the configured cap.", + "parameters": { + "type": "object", + "properties": { + "task_id": { + "type": "string", + "description": "Task id returned by the tool that started the background work." + }, + "wait": { + "type": "boolean", + "description": "Block until the task reaches a terminal status or the timeout expires. A timed-out wait returns [status: running] and leaves the task alive." + }, + "timeout_ms": { + "type": "number", + "description": "Max wait in milliseconds (only meaningful with wait: true). Defaults to the configured wait timeout; capped by the configured maximum." + } + }, + "required": [ + "task_id" + ] + } + }, + { + "name": "todo_write", + "description": "Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).", + "parameters": { + "type": "object", + "properties": { + "todos": { + "type": "array", + "description": "The COMPLETE task list, replacing any previous list.", + "items": { + "type": "object", + "additionalProperties": true, + "properties": { + "content": { + "type": "string", + "description": "What the task is — a short imperative line." + }, + "status": { + "type": "string", + "description": "pending (not started) | in_progress (now) | completed (done).", + "enum": [ + "pending", + "in_progress", + "completed" + ] + } + }, + "required": [ + "content", + "status" + ] + } + } + }, + "required": [ + "todos" + ] + } + }, + { + "name": "update_goal", + "description": "Update the exact current goal revision. edit, pause, and resume require a direct top-level human request. During an automatic continuation of the current goal, complete and blocked are also allowed. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds and must explain it in blocked_reason.", + "parameters": { + "type": "object", + "properties": { + "goal_id": { + "type": "string", + "description": "Exact id returned by get_goal." + }, + "revision": { + "type": "number", + "description": "Exact positive revision returned by get_goal." + }, + "action": { + "type": "string", + "description": "edit | pause | resume | complete | blocked", + "enum": [ + "edit", + "pause", + "resume", + "complete", + "blocked" + ] + }, + "objective": { + "type": "string", + "description": "Replacement objective; valid only with action edit." + }, + "max_goal_rounds": { + "type": "number", + "description": "Replacement cap; valid only with action edit." + }, + "blocked_reason": { + "type": "string", + "description": "Concrete blocking condition; required only with action blocked." + } + }, + "required": [ + "goal_id", + "revision", + "action" + ] + } + }, + { + "name": "web_fetch", + "description": "Fetch the content of a specific HTTP(S) URL and return it decoded to text.", + "parameters": { + "type": "object", + "properties": { + "url": { + "type": "string", + "description": "The HTTP(S) URL to fetch." + } + }, + "required": [ + "url" + ] + } + }, + { + "name": "workflow", + "description": "Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const/oneOf — no pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), and independent `provider`/`model` LLM target overrides (either may be provided alone). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.", + "parameters": { + "type": "object", + "properties": { + "script": { + "type": "string", + "description": "The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)." + }, + "meta": { + "type": "object", + "description": "The workflow identity block (plain JSON — never code).", + "additionalProperties": true, + "properties": { + "name": { + "type": "string", + "description": "Short kebab-case workflow name." + }, + "description": { + "type": "string", + "description": "One-line description of what the workflow does." + }, + "whenToUse": { + "type": "string", + "description": "Optional guidance on when this workflow applies." + }, + "phases": { + "type": "array", + "description": "Optional phase declarations matched by phase() calls.", + "items": { + "type": "object", + "additionalProperties": true, + "properties": { + "title": { + "type": "string", + "description": "The phase title phase() calls match by exact string." + }, + "detail": { + "type": "string", + "description": "Optional one-line description of the phase." + }, + "provider": { + "type": "string", + "description": "Optional provider override this phase is expected to use." + }, + "model": { + "type": "string", + "description": "Optional model override this phase is expected to use." + } + }, + "required": [ + "title" + ] + } + } + }, + "required": [ + "name", + "description" + ] + }, + "args": { + "type": "object", + "description": "Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]}).", + "additionalProperties": true + } + }, + "required": [ + "script", + "meta" + ] + } + }, + { + "name": "write", + "description": "Create or fully replace a UTF-8 text file.", + "parameters": { + "type": "object", + "properties": { + "file_path": { + "type": "string", + "description": "Path to write, resolved by the filesystem backend." + }, + "content": { + "type": "string", + "description": "Full UTF-8 text content to write." + }, + "sandbox_permissions": { + "type": "string", + "description": "The wider sandbox mode this file operation needs. Only valid as a one-shot retry of an operation the sandbox just denied; requires justification and user approval.", + "enum": [ + "workspace-write", + "danger-full-access" + ] + }, + "justification": { + "type": "string", + "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access." + } + }, + "required": [ + "file_path", + "content" + ] + } + } + ], + "changes": [] +} diff --git a/examples/acp-agent/web-fetch-fixture-server.mjs b/examples/acp-agent/web-fetch-fixture-server.mjs new file mode 100644 index 0000000000..34a45fdd15 --- /dev/null +++ b/examples/acp-agent/web-fetch-fixture-server.mjs @@ -0,0 +1,52 @@ +/** + * Deterministic loopback HTTP fixture for the web-fetch snapshot scenario: a + * small HTML page (headings, named entities, a GFM table, nested formatting) + * on a fixed port, so recording and keyless replay drive the REAL + * `dsh-web-fetch-local` transport and `dsh-tool-web` markdown rendering + * without external network. The port is fixed because the fetched URL is part + * of the recorded model transcript. + */ +import { createServer } from 'node:http' + +/** Fixed loopback port the scenario prompt points `web_fetch` at. */ +const PORT = 43117 + +const PAGE = ` +Menu + +

    Café menu

    +

    Prices include service & tax — updated daily.

    +
    • Espresso
    • Flat white
    +
    DrinkPrice
    Espresso€2
    Flat white€3
    +

    See today’s specials.

    + +` + +/** Cordis plugin name. */ +export const name = 'web-fetch-fixture-server' + +/** + * Start the fixture server on 127.0.0.1 and register its shutdown. + * @param ctx - Cordis context; the effect disposes the server with the fiber. + */ +export async function apply(ctx) { + const server = createServer((req, res) => { + if (req.url === '/menu.html') { + res.writeHead(200, { 'content-type': 'text/html; charset=utf-8' }) + res.end(PAGE) + return + } + res.writeHead(404, { 'content-type': 'text/plain; charset=utf-8' }) + res.end('not found') + }) + await new Promise((resolve, reject) => { + server.once('error', reject) + server.listen(PORT, '127.0.0.1', () => resolve(undefined)) + }) + // The fixture must never hold the process open past protocol shutdown. + server.unref() + ctx.effect(() => () => { + server.close() + server.closeAllConnections() + }, 'web-fetch-fixture-server') +} diff --git a/examples/acp-agent/web.cordis.snapshot.yml b/examples/acp-agent/web.cordis.snapshot.yml new file mode 100644 index 0000000000..015e67e221 --- /dev/null +++ b/examples/acp-agent/web.cordis.snapshot.yml @@ -0,0 +1,31 @@ +# Keyless replay counterpart to web.cordis.yml: the web stack and loopback +# fixture server stay real (the tool call re-executes the actual HTTP fetch and +# markdown rendering); only the model adapter is replaced by replay. +- id: base + name: '@cordisjs/plugin-include' + config: + path: ./cordis.yml + patches: + - id: llm-deepseek + name: '@deepseek-ai/dsh-llm-deepseek' + disabled: true + - insert: + - id: web + name: '@deepseek-ai/dsh-web' + - id: web-fetch-local + name: '@deepseek-ai/dsh-web-fetch-local' + - id: web-fetch-fixture + name: './web-fetch-fixture-server.mjs' + - id: tool-web + name: '@deepseek-ai/dsh-tool-web' + config: + search: false + - id: llm-replay + name: '@deepseek-ai/dsh-llm-replay' + config: + providers: + - id: deepseek + name: DeepSeek + models: + - id: deepseek-v4-flash + - id: deepseek-v4-pro diff --git a/examples/acp-agent/web.cordis.yml b/examples/acp-agent/web.cordis.yml new file mode 100644 index 0000000000..1ed0b3efba --- /dev/null +++ b/examples/acp-agent/web.cordis.yml @@ -0,0 +1,21 @@ +# Web-fetch composition for the web-fetch snapshot scenario: the web seam, the +# real local HTTP fetch provider, the model-facing web tools (fetch only, so +# the pinned header carries exactly the surface under test), and the loopback +# fixture server the scenario prompt fetches — deterministic content, no +# external network, in recording and replay alike. +- id: base + name: '@cordisjs/plugin-include' + config: + path: ./cordis.yml + patches: + - insert: + - id: web + name: '@deepseek-ai/dsh-web' + - id: web-fetch-local + name: '@deepseek-ai/dsh-web-fetch-local' + - id: web-fetch-fixture + name: './web-fetch-fixture-server.mjs' + - id: tool-web + name: '@deepseek-ai/dsh-tool-web' + config: + search: false diff --git a/examples/package.json b/examples/package.json index 395c135a2d..3d0cc13718 100644 --- a/examples/package.json +++ b/examples/package.json @@ -63,6 +63,7 @@ "@deepseek-ai/dsh-tool-session-query": "workspace:*", "@deepseek-ai/dsh-tool-subagent": "workspace:*", "@deepseek-ai/dsh-tool-todo": "workspace:*", + "@deepseek-ai/dsh-tool-web": "workspace:*", "@deepseek-ai/dsh-tool-workflow": "workspace:*", "@deepseek-ai/dsh-tools": "workspace:*", "@deepseek-ai/dsh-user-approval": "workspace:*", diff --git a/packages/web/tool-web/README.i18n.yaml b/packages/web/tool-web/README.i18n.yaml index eb3fa4731d..1e746ed566 100644 --- a/packages/web/tool-web/README.i18n.yaml +++ b/packages/web/tool-web/README.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 -README.md: 5e567115c386d14b7e412ed2502e7290826a5e5e -README.zh.md: b17fe4107908381806d4029481bbf03696c4f313 +README.md: 5fe48ced81a2cd02197cf8cc10a7d6567b17ffca +README.zh.md: 34ad08e290166ee6db2cd7b836746541d18aad52 diff --git a/packages/web/tool-web/README.md b/packages/web/tool-web/README.md index 5e567115c3..5fe48ced81 100644 --- a/packages/web/tool-web/README.md +++ b/packages/web/tool-web/README.md @@ -11,7 +11,7 @@ Each tool is registered independently; a product that wants only one disables th | Tool | Args | Behavior | |---|---|---| | `web_search` | `query` (string) | Discovery. Returns an optional answer plus source URLs. `max_results` is **not** model-facing — the tool sets the bound (the `searchMaxResults` config, default 8) and passes it to the seam. | -| `web_fetch` | `url` (string) | Retrieves a specific URL. HTML bodies are rendered to markdown-ish text; text bodies pass through. A non-2xx status is reported, not an error. The tool-call timeout is deployment policy (`dsh-timeout-policy`), not a model argument. | +| `web_fetch` | `url` (string) | Retrieves a specific URL. HTML bodies are rendered to markdown (turndown with GFM tables/strikethrough); text bodies pass through. A non-2xx status is reported, not an error. The tool-call timeout is deployment policy (`dsh-timeout-policy`), not a model argument. | Both tools opt into concurrent scheduling because provider reads return content without mutating parent-agent state. @@ -126,6 +126,6 @@ Append-only; newly visible content follows the reusable request prefix and does ## Known Limitations and Deferred Work -- **`htmlToMarkdown` is a minimal regex converter, not an HTML parser** — it strips script/style/noscript, keeps headings/bullets/links, and decodes about a dozen named entities; tables, images, and nested formatting are lost. +- **HTML→markdown conversion falls back to raw HTML on pathological input** — [turndown](https://github.com/mixmark-io/turndown) (with GFM tables/strikethrough) converts fetched HTML through a real DOM, but its recursive walk overflows on absurdly deep nesting (thousands of levels); such a body passes through unconverted rather than erroring ([Agent Note](../../../.agents/notes/implemented/simplification/2026-07-26-turndown-for-tool-web-html-markdown.md)). - **The model-facing surface is minimal by design, with promotions deferred** — `max_results` stays a config bound (not a model argument), and `web_fetch` takes only `url` (no `format`/`prompt`/LLM-summarization mode); both are named later steps in [the seam Agent Note](../../../.agents/notes/implemented/architecture/2026-06-24-web-capability-seam.md). - **No web-specific permission policy** — both tools execute without requesting `ctx.approval`; a deployment that needs confirmation must add a `tools/pre-execute` policy, and the package does not define persistent URL/domain grants. diff --git a/packages/web/tool-web/README.zh.md b/packages/web/tool-web/README.zh.md index b17fe41079..34ad08e290 100644 --- a/packages/web/tool-web/README.zh.md +++ b/packages/web/tool-web/README.zh.md @@ -11,7 +11,7 @@ | 工具 | 参数 | 行为 | |---|---|---| | `web_search` | `query`（string） | 发现。返回可选答案与源 URL。`max_results` **不** 面向模型：工具设置上限（`searchMaxResults` 配置，默认 8）并传给 seam。 | -| `web_fetch` | `url`（string） | 获取特定 URL。HTML 主体渲染为近似 markdown 的文本；文本主体原样通过。非 2xx 状态会报告，而非报错。工具调用超时是部署策略（`dsh-timeout-policy`），不是模型参数。 | +| `web_fetch` | `url`（string） | 获取特定 URL。HTML 主体渲染为 markdown（turndown，带 GFM 表格／删除线）；文本主体原样通过。非 2xx 状态会报告，而非报错。工具调用超时是部署策略（`dsh-timeout-policy`），不是模型参数。 | 两个工具都选择并发调度，因为提供方读取会返回内容，不会修改父 agent 状态。 @@ -126,6 +126,6 @@ Use the web_fetch tool to retrieve the content of a specific HTTP(S) URL (for ex ## 已知限制与暂缓事项 -- **`htmlToMarkdown` 是最小正则转换器，不是 HTML parser**：它会移除 script/style/noscript，保留标题／项目符号／链接，并解码约十余个命名 entity；表格、图片与嵌套格式会丢失。 +- **HTML→markdown 转换在病态输入上回退为原始 HTML**：[turndown](https://github.com/mixmark-io/turndown)（带 GFM 表格／删除线）通过真实 DOM 转换抓取到的 HTML，但其递归遍历在极深嵌套（数千层）上会栈溢出；此类主体不经转换原样通过，而非报错（[决策记录](../../../.agents/notes/implemented/simplification/2026-07-26-turndown-for-tool-web-html-markdown.md)）。 - **面向模型的表层有意保持最小，提升项暂缓**：`max_results` 保持为配置上限（不是模型参数），`web_fetch` 只接受 `url`（没有 `format`／`prompt`／LLM 摘要模式）；两项都列为 [seam Agent Note](../../../.agents/notes/implemented/architecture/2026-06-24-web-capability-seam.md) 中的后续步骤。 - **没有 web 专用权限策略**：两个工具都不会请求 `ctx.approval` 就直接执行；需要确认的部署必须添加 `tools/pre-execute` 策略，该包不定义持久 URL／domain 授权。 diff --git a/packages/web/tool-web/package.json b/packages/web/tool-web/package.json index ec1d33f4d4..9e1a54b6cd 100644 --- a/packages/web/tool-web/package.json +++ b/packages/web/tool-web/package.json @@ -35,10 +35,13 @@ "cordis": "^4.0.0-rc.7" }, "dependencies": { - "schemastery": "^3.18.0" + "@joplin/turndown-plugin-gfm": "^1.0.67", + "schemastery": "^3.18.0", + "turndown": "^7.2.4" }, "devDependencies": { "@deepseek-ai/dsh-agent": "workspace:^", + "@types/turndown": "^5.0.6", "@deepseek-ai/dsh-invariants": "workspace:^", "@deepseek-ai/dsh-llm": "workspace:^", "@deepseek-ai/dsh-session": "workspace:^", diff --git a/packages/web/tool-web/src/fetch.ts b/packages/web/tool-web/src/fetch.ts index cc2ae52970..60c0f33507 100644 --- a/packages/web/tool-web/src/fetch.ts +++ b/packages/web/tool-web/src/fetch.ts @@ -6,12 +6,29 @@ */ import type { Context } from 'cordis' +import TurndownService from 'turndown' +import { gfm } from '@joplin/turndown-plugin-gfm' import { defineTool } from '@deepseek-ai/dsh-tools' import type { GenericCallView } from '@deepseek-ai/dsh-tools' import type { WebFetchBody, WebFetchResult } from '@deepseek-ai/dsh-web' import { assertNever } from '@deepseek-ai/dsh-llm' import type {} from '@deepseek-ai/dsh-system-prompt' -import { htmlToMarkdown } from './html.ts' + +/** + * The shared HTML→markdown converter: turndown over its bundled domino DOM, + * with GitHub-flavored tables/strikethrough (`@joplin/turndown-plugin-gfm`). + * The style options are fixed model-facing presentation (matching the repo's + * markdown conventions), not deployment tunables. `remove` drops non-content + * elements wholesale — turndown's default keeps their text. The instance is + * stateless across `turndown()` calls and safe to share. + */ +const turndown = new TurndownService({ + headingStyle: 'atx', + codeBlockStyle: 'fenced', + bulletListMarker: '-', +}) +turndown.use(gfm) +turndown.remove(['script', 'style', 'noscript']) /** * Validate value constraints the schema DSL can't express: a non-blank `url`. @@ -30,14 +47,23 @@ export function parseFetchArgs(args: { url: string }): { url: string } { /** * Render a fetched body to model-facing markdown text. * - * @param body - the decoded body; `html` is converted via - * {@link htmlToMarkdown}, `text` passes through verbatim. + * @param body - the decoded body; `html` is converted via turndown, `text` + * passes through verbatim. When turndown throws (deeply pathological HTML + * overflows its recursive DOM walk), the raw HTML passes through instead — + * a degraded page beats an error for a body the provider already decoded. * @returns the text for the tool's output block. */ export function renderBody(body: WebFetchBody): string { switch (body.kind) { case 'html': - return htmlToMarkdown(body.content) + try { + return turndown.turndown(body.content) + } catch { + // turndown's DOM walk recurses per element; pathological nesting (a + // few thousand levels) throws RangeError. Provider errors stay + // structured WebErrors upstream; conversion failure downgrades to raw HTML. + return body.content + } case 'text': return body.content /* v8 ignore next 2 -- WebFetchBody is a closed union; this arm is unreachable and only makes adding a kind a compile error. */ diff --git a/packages/web/tool-web/src/html.ts b/packages/web/tool-web/src/html.ts deleted file mode 100644 index 1d6ffdb9a3..0000000000 --- a/packages/web/tool-web/src/html.ts +++ /dev/null @@ -1,86 +0,0 @@ -/** - * Minimal dependency-free HTML-to-readable-text conversion for `web_fetch`, not a full parser. It - * removes non-content elements and tags, decodes common entities, collapses whitespace, and keeps - * basic headings, lists, and links. A richer converter can replace it without changing the seam or - * tool schema. - * @module @deepseek-ai/dsh-tool-web/html - */ - -/** Decode the handful of HTML entities common in textual content. */ -function decodeEntities(text: string): string { - return text - .replace(/&(#[xX][0-9a-fA-F]+|#[0-9]+|[a-zA-Z]+);/g, (match, entity: string) => { - if (entity.startsWith('#x') || entity.startsWith('#X')) { - const code = Number.parseInt(entity.slice(2), 16) - return safeFromCodePoint(code, match) - } - if (entity.startsWith('#')) { - const code = Number.parseInt(entity.slice(1), 10) - return safeFromCodePoint(code, match) - } - return NAMED_ENTITIES[entity] ?? match - }) -} - -const NAMED_ENTITIES: Record = { - amp: '&', lt: '<', gt: '>', quot: '"', apos: "'", nbsp: ' ', - copy: '©', reg: '®', trade: '™', hellip: '…', mdash: '—', ndash: '–', -} - -function safeFromCodePoint(code: number, fallback: string): string { - try { - return String.fromCodePoint(code) - } catch { - // An out-of-range code point (RangeError) is the only failure here; keep the - // original entity text rather than throwing out of pure presentation. - return fallback - } -} - -/** - * Convert an HTML document to a readable markdown-ish text approximation. - * Best-effort and lossy by design — fidelity is the job of a future heavier - * converter, not this fallback. - * - * @param html - the raw HTML source. - * @returns plain text with markdown headings, list bullets, and links; - * whitespace collapsed to at most one blank line and trimmed. - */ -export function htmlToMarkdown(html: string): string { - let text = html - // Drop non-content elements entirely (including their contents). - .replace(/]*>[\s\S]*?<\/script>/gi, '') - .replace(/]*>[\s\S]*?<\/style>/gi, '') - .replace(/]*>[\s\S]*?<\/noscript>/gi, '') - .replace(//g, '') - - // Convert links to markdown before stripping tags. - text = text.replace(/]*\bhref\s*=\s*["']([^"']*)["'][^>]*>([\s\S]*?)<\/a>/gi, (_match, href: string, label: string) => { - const cleanLabel = label.replace(/<[^>]+>/g, '').trim() - return cleanLabel.length > 0 ? `[${cleanLabel}](${href})` : href - }) - - // Headings → markdown hashes. - text = text.replace(/]*>([\s\S]*?)<\/h\1>/gi, (_match, level: string, body: string) => { - const hashes = '#'.repeat(Number(level)) - return `\n\n${hashes} ${body.replace(/<[^>]+>/g, '').trim()}\n\n` - }) - - // List items → bullets. - text = text.replace(/]*>([\s\S]*?)<\/li>/gi, (_match, body: string) => `\n- ${body.replace(/<[^>]+>/g, '').trim()}`) - - // Block-level breaks become paragraph breaks. - text = text - .replace(/<\/(p|div|section|article|header|footer|tr|table|ul|ol|blockquote)>/gi, '\n\n') - .replace(//gi, '\n') - - // Drop all remaining tags, decode entities, collapse whitespace. - text = text.replace(/<[^>]+>/g, '') - text = decodeEntities(text) - text = text - .replace(/[ \t\f\v]+/g, ' ') - .replace(/ *\n */g, '\n') - .replace(/\n{3,}/g, '\n\n') - .trim() - return text -} diff --git a/packages/web/tool-web/src/index.ts b/packages/web/tool-web/src/index.ts index 7096371ed1..e7ac4b2453 100644 --- a/packages/web/tool-web/src/index.ts +++ b/packages/web/tool-web/src/index.ts @@ -14,7 +14,6 @@ import { applyWebFetchTool } from './fetch.ts' export { WEB_SEARCH_MAX_RESULTS, applyWebSearchTool, formatSearchOutput, parseSearchArgs, presentSearchCall } from './search.ts' export { applyWebFetchTool, formatFetchOutput, parseFetchArgs, presentFetchCall, renderBody } from './fetch.ts' -export { htmlToMarkdown } from './html.ts' /** Cordis plugin name used by loader diagnostics. */ export const name = 'tool-web' diff --git a/packages/web/tool-web/src/turndown-plugin-gfm.d.ts b/packages/web/tool-web/src/turndown-plugin-gfm.d.ts new file mode 100644 index 0000000000..66c9d929e4 --- /dev/null +++ b/packages/web/tool-web/src/turndown-plugin-gfm.d.ts @@ -0,0 +1,12 @@ +/** + * Ambient module declaration for `@joplin/turndown-plugin-gfm`, which ships no + * types and has no DefinitelyTyped package. Only the composite `gfm` plugin is + * declared; the package's individual plugins (`tables`, `strikethrough`, …) + * stay undeclared until something imports them. + */ +declare module '@joplin/turndown-plugin-gfm' { + import type TurndownService from 'turndown' + + /** The composite GitHub-flavored-markdown plugin (tables, strikethrough, task lists, highlighted code blocks). */ + export const gfm: TurndownService.Plugin +} diff --git a/packages/web/tool-web/tests/tool-web.spec.ts b/packages/web/tool-web/tests/tool-web.spec.ts index 093184c4a7..f9ffb1b5c5 100644 --- a/packages/web/tool-web/tests/tool-web.spec.ts +++ b/packages/web/tool-web/tests/tool-web.spec.ts @@ -14,7 +14,6 @@ import { presentSearchCall, presentFetchCall, renderBody, - htmlToMarkdown, WEB_SEARCH_MAX_RESULTS, } from '@deepseek-ai/dsh-tool-web' @@ -82,6 +81,11 @@ describe('search formatting', () => { expect(parseSearchArgs({ query: 'hi' })).toEqual({ query: 'hi' }) }) + it('falls back to the raw URL as a source label when the URL is unparseable', () => { + const out = formatSearchOutput({ truncated: false, sources: [{ url: 'not a url' }] }) + expect(out).toContain('[not a url](not a url)') + }) + it('presents a search call as a search-kind card titled by the query', () => { expect(presentSearchCall({ query: 'find me' })).toEqual({ card: 'generic', title: 'find me', kind: 'search', rawInput: 'find me' }) }) @@ -112,6 +116,29 @@ describe('fetch formatting', () => { expect(renderBody({ kind: 'html', content: '

    y

    ' })).toBe('y') }) + it('converts html via turndown: entities, links, tables, nesting; drops script/style/noscript', () => { + expect(renderBody({ + kind: 'html', + content: '

    Tom & Jerry © Résumé

    link', + })).toBe('Tom & Jerry © Résumé\n\n[link](https://a.test)') + expect(renderBody({ kind: 'html', content: '

    Heading

    • one
    • two
    ' })) + .toBe('## Heading\n\n- one\n- two') + expect(renderBody({ kind: 'html', content: '
    AB
    12
    ' })) + .toBe('| A | B |\n| --- | --- |\n| 1 | 2 |') + expect(renderBody({ kind: 'html', content: '

    bold italic

    quoted

    ' })) + .toBe('**bold _italic_**\n\n> quoted') + }) + + it('falls back to the raw html body when turndown throws on pathological nesting', { timeout: 60_000 }, () => { + // Nesting past V8's default stack overflows turndown/domino's recursive + // walk with a RangeError (measured: 4k levels throw on the main thread, + // 8k in a worker); 20k adds margin over either stack size. The raw body + // must pass through instead of throwing. + const depth = 20_000 + const pathological = '
    '.repeat(depth) + 'x' + '
    '.repeat(depth) + expect(renderBody({ kind: 'html', content: pathological })).toBe(pathological) + }) + it('validates url (non-empty), no timeout parameter', () => { expect(() => parseFetchArgs({ url: ' ' })).toThrow('non-empty') expect(parseFetchArgs({ url: 'https://a.test' })).toEqual({ url: 'https://a.test' }) @@ -122,46 +149,6 @@ describe('fetch formatting', () => { }) }) -describe('htmlToMarkdown', () => { - it('drops scripts/styles, keeps text, decodes entities, converts links', () => { - const md = htmlToMarkdown('

    Tom & Jerry

    link') - expect(md).not.toContain('bad()') - expect(md).not.toContain('.x{}') - expect(md).toContain('Tom & Jerry') - expect(md).toContain('[link](https://a.test)') - }) - - it('decodes numeric entities and collapses whitespace', () => { - expect(htmlToMarkdown('

    a'b

    ')).toBe("a'b") - expect(htmlToMarkdown('
    x
    \n\n\n
    y
    ')).toBe('x\n\ny') - }) - - it('decodes hex entities and named entities, and leaves unknown/out-of-range ones intact', () => { - expect(htmlToMarkdown('

    AB

    ')).toBe('AB') - expect(htmlToMarkdown('

    © —

    ')).toBe('© —') - expect(htmlToMarkdown('

    ¬areal;

    ')).toBe('¬areal;') - // An out-of-range code point keeps the original entity text (fromCodePoint fallback). - expect(htmlToMarkdown('

    �

    ')).toBe('�') - expect(htmlToMarkdown('

    �

    ')).toBe('�') - }) - - it('renders a link with an empty label as its bare href', () => { - expect(htmlToMarkdown('')).toBe('https://a.test') - }) - - it('converts headings and list items to markdown', () => { - expect(htmlToMarkdown('

    Heading

    after

    ')).toContain('## Heading') - const list = htmlToMarkdown('
    • one
    • two
    ') - expect(list).toContain('- one') - expect(list).toContain('- two') - }) - - it('falls back to the raw URL as a source label when the URL is unparseable', () => { - const out = formatSearchOutput({ truncated: false, sources: [{ url: 'not a url' }] }) - expect(out).toContain('[not a url](not a url)') - }) -}) - describe('tool-web registration', () => { it('registers both tools by default', async () => { const { fiber, ctx } = await mountTools() diff --git a/pnpm-lock.yaml b/pnpm-lock.yaml index 1946a841bb..430cf6ea0a 100644 --- a/pnpm-lock.yaml +++ b/pnpm-lock.yaml @@ -523,6 +523,9 @@ importers: '@deepseek-ai/dsh-tool-todo': specifier: workspace:* version: link:../packages/todo/tool-todo + '@deepseek-ai/dsh-tool-web': + specifier: workspace:* + version: link:../packages/web/tool-web '@deepseek-ai/dsh-tool-workflow': specifier: workspace:* version: link:../packages/workflow/tool-workflow @@ -4259,9 +4262,15 @@ importers: packages/web/tool-web: dependencies: + '@joplin/turndown-plugin-gfm': + specifier: ^1.0.67 + version: 1.0.67 schemastery: specifier: ^3.18.0 version: 3.18.0 + turndown: + specifier: ^7.2.4 + version: 7.2.4 devDependencies: '@deepseek-ai/dsh-agent': specifier: workspace:^ @@ -4299,6 +4308,9 @@ importers: '@deepseek-ai/dsh-web-search-exa': specifier: workspace:^ version: link:../web-search-exa + '@types/turndown': + specifier: ^5.0.6 + version: 5.0.6 cordis: specifier: ^4.0.0-rc.7 version: 4.0.0-rc.7(@cordisjs/plugin-include@1.0.4)(@cordisjs/plugin-loader@1.0.0-rc.5) @@ -5971,6 +5983,9 @@ packages: resolution: {integrity: sha512-O8jcjabXaleOG9DQ0+ARXWZBTfnP4WNAqzuiJK7ll44AmxGKv/J2M4TPjxjY3znBCfvBXFzucm1twdyFybFqEA==} engines: {node: '>=12'} + '@joplin/turndown-plugin-gfm@1.0.67': + resolution: {integrity: sha512-FZfW5EZfidhzd1IaY1uxHnIZPTVOxAdleMZ4/1U6Nt5b7+Qj5JThDnaIomuJtetnUBzuRNbe9FWMuqD4B3dlWA==} + '@jridgewell/gen-mapping@0.3.13': resolution: {integrity: sha512-2kkt/7niJ6MgEPxF0bYdQ6etZaA+fQvDcLKckhy1yIQOzaoKjBBjSj63/aLVjYE3qhRt5dvM+uUyfCg6UKCBbA==} @@ -6076,6 +6091,9 @@ packages: '@opentelemetry/api': optional: true + '@mixmark-io/domino@2.2.0': + resolution: {integrity: sha512-Y28PR25bHXUg88kCV7nivXrP2Nj2RueZ3/l/jdx6J9f8J4nsEGcgX0Qe6lt7Pa+J79+kPiJU3LguR6O/6zrLOw==} + '@modelcontextprotocol/sdk@1.29.0': resolution: {integrity: sha512-zo37mZA9hJWpULgkRpowewez1y6ML5GsXJPY8FI0tBBCd77HEvza4jDqRKOXgHNn867PVGCyTdzqpz0izu5ZjQ==} engines: {node: '>=18'} @@ -7005,6 +7023,9 @@ packages: '@types/trusted-types@2.0.7': resolution: {integrity: sha512-ScaPdn1dQczgbl0QFTeTOmVHFULt394XJgOQNoyVhZ6r2vLnMLJfBPd53SB52T/3G36VI1/g2MZaX0cwDuXsfw==} + '@types/turndown@5.0.6': + resolution: {integrity: sha512-ru00MoyeeouE5BX4gRL+6m/BsDfbRayOskWqUvh7CLGW+UXxHQItqALa38kKnOiZPqJrtzJUgAC2+F0rL1S4Pg==} + '@types/unist@2.0.11': resolution: {integrity: sha512-CmBKiL6NNo/OqgmMn95Fk9Whlp2mtvIv+KNpQKN2F4SjvrEesubTRWGYSg+BnWZOnlCaSTU1sMpsBOzgbYhnsA==} @@ -9463,6 +9484,10 @@ packages: engines: {node: '>=18.0.0'} hasBin: true + turndown@7.2.4: + resolution: {integrity: sha512-I8yFsfRzmzK0WV1pNNOA4A7y4RDfFxPRxb3t+e3ui14qSGOxGtiSP6GjeX+Y6CHb7HYaFj7ECUD7VE5kQMZWGQ==} + engines: {node: '>=18', npm: '>=9'} + type-check@0.4.0: resolution: {integrity: sha512-XleUoc9uwGXqjWwXaUTZAmzMcFZ5858QA2vvx1Ur5xIcixXIP+8LnFDgRplU30us6teqdlskFfu+ae4K79Ooew==} engines: {node: '>= 0.8.0'} @@ -10860,6 +10885,8 @@ snapshots: wrap-ansi: 8.1.0 wrap-ansi-cjs: wrap-ansi@7.0.0 + '@joplin/turndown-plugin-gfm@1.0.67': {} + '@jridgewell/gen-mapping@0.3.13': dependencies: '@jridgewell/sourcemap-codec': 1.5.5 @@ -10951,6 +10978,8 @@ snapshots: - bufferutil - utf-8-validate + '@mixmark-io/domino@2.2.0': {} + '@modelcontextprotocol/sdk@1.29.0(zod@4.4.3)': dependencies: '@hono/node-server': 1.19.14(hono@4.12.29) @@ -11705,6 +11734,8 @@ snapshots: '@types/trusted-types@2.0.7': optional: true + '@types/turndown@5.0.6': {} + '@types/unist@2.0.11': {} '@types/unist@3.0.3': {} @@ -14645,6 +14676,10 @@ snapshots: optionalDependencies: fsevents: 2.3.3 + turndown@7.2.4: + dependencies: + '@mixmark-io/domino': 2.2.0 + type-check@0.4.0: dependencies: prelude-ls: 1.2.1 From 187cf6f804bfef9800f3e07e1629207af92eac0c Mon Sep 17 00:00:00 2001 From: NI0317 Date: Mon, 27 Jul 2026 12:38:11 +0800 Subject: [PATCH 13/36] feat(web): delete workspace registrations --- ...-07-25-workspace-ui-product-flow.i18n.yaml | 6 +- .../2026-07-25-workspace-ui-product-flow.md | 8 +- ...2026-07-25-workspace-ui-product-flow.zh.md | 8 +- ...-workspace-registration-deletion.i18n.yaml | 6 + ...6-07-27-workspace-registration-deletion.md | 53 +++++++++ ...7-27-workspace-registration-deletion.zh.md | 53 +++++++++ ...-domain-kv-storage-and-workspace.i18n.yaml | 6 +- ...6-07-24-domain-kv-storage-and-workspace.md | 14 ++- ...7-24-domain-kv-storage-and-workspace.zh.md | 14 ++- apps/web/tests/workspace-management.e2e.ts | 103 ++++++++++++++++-- docs/cordis-catalog/services.md | 10 ++ .../client/connection/src/client/fixture.ts | 15 +++ packages/client/connection/tests/fake-api.ts | 1 + .../client/connection/tests/fixture.spec.ts | 25 +++++ packages/client/runtime/README.i18n.yaml | 6 +- packages/client/runtime/README.md | 4 +- packages/client/runtime/README.zh.md | 4 +- .../runtime/src/client/workspaces/manager.ts | 46 +++++++- .../runtime/src/client/workspaces/service.ts | 10 ++ packages/client/runtime/tests/fake-api.ts | 4 + .../runtime/tests/workspaces-service.spec.ts | 58 ++++++++++ packages/client/ui-workspace/README.i18n.yaml | 6 +- packages/client/ui-workspace/README.md | 4 +- packages/client/ui-workspace/README.zh.md | 4 +- .../src/client/WorkspaceBrowser.module.css | 10 ++ .../src/client/WorkspaceBrowser.tsx | 74 ++++++++++++- .../ui-workspace/src/client/contract/slots.ts | 2 + .../client/ui-workspace/src/client/index.ts | 1 + .../ui-workspace/src/client/rows/Rows.tsx | 14 +-- .../client/ui-workspace/tests/rows.spec.tsx | 8 +- .../tests/workspace-browser.spec.tsx | 69 ++++++++++++ .../cordis/tool-cordis/src/api-catalog.ts | 4 + packages/host/apiproxy/README.i18n.yaml | 6 +- packages/host/apiproxy/README.md | 2 +- packages/host/apiproxy/README.zh.md | 2 +- packages/host/apiproxy/src/api-proxy.ts | 23 +++- .../host/apiproxy/src/api/events.schema.ts | 3 +- packages/host/apiproxy/src/api/events.ts | 5 +- packages/host/apiproxy/src/api/rpc-map.ts | 1 + .../host/apiproxy/src/api/workspace.schema.ts | 10 ++ packages/host/apiproxy/src/api/workspace.ts | 8 ++ packages/host/apiproxy/src/fetch/client.ts | 4 + packages/host/apiproxy/src/fetch/handler.ts | 2 + .../tests/api-proxy-workspace.spec.ts | 27 +++++ .../apiproxy/tests/client-handler.spec.ts | 5 +- .../host/apiproxy/tests/fetch-carrier.spec.ts | 3 + .../host/apiproxy/tests/rpc-schemas.spec.ts | 13 +++ packages/workspace/README.i18n.yaml | 6 +- packages/workspace/README.md | 4 +- packages/workspace/README.zh.md | 4 +- packages/workspace/workspace/README.i18n.yaml | 6 +- packages/workspace/workspace/README.md | 3 +- packages/workspace/workspace/README.zh.md | 3 +- packages/workspace/workspace/src/index.ts | 39 +++++++ packages/workspace/workspace/src/invariant.ts | 5 +- .../workspace/tests/invariant.spec.ts | 2 +- .../workspace/tests/workspace.spec.ts | 34 ++++++ 57 files changed, 786 insertions(+), 84 deletions(-) create mode 100644 .agents/notes/implemented/feature/2026-07-27-workspace-registration-deletion.i18n.yaml create mode 100644 .agents/notes/implemented/feature/2026-07-27-workspace-registration-deletion.md create mode 100644 .agents/notes/implemented/feature/2026-07-27-workspace-registration-deletion.zh.md diff --git a/.agents/notes/implemented/feature/2026-07-25-workspace-ui-product-flow.i18n.yaml b/.agents/notes/implemented/feature/2026-07-25-workspace-ui-product-flow.i18n.yaml index 3295a845f3..b8266cdd49 100644 --- a/.agents/notes/implemented/feature/2026-07-25-workspace-ui-product-flow.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-07-25-workspace-ui-product-flow.i18n.yaml @@ -1,6 +1,6 @@ # Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each # 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 -2026-07-25-workspace-ui-product-flow.md: a02087235a36f2c257de407facf2dc02ed072f3b -2026-07-25-workspace-ui-product-flow.zh.md: 8ccbf5b98401bef9c3fd40e948d35ec5f0818202 +# pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-07-25-workspace-ui-product-flow.md +2026-07-25-workspace-ui-product-flow.md: b8e1ec1efe19127cad8a12405dddeec38a4ff91e +2026-07-25-workspace-ui-product-flow.zh.md: b80b75a80671e9aa2ab59ff72c44c18a8ec5c16e diff --git a/.agents/notes/implemented/feature/2026-07-25-workspace-ui-product-flow.md b/.agents/notes/implemented/feature/2026-07-25-workspace-ui-product-flow.md index a02087235a..b8e1ec1efe 100644 --- a/.agents/notes/implemented/feature/2026-07-25-workspace-ui-product-flow.md +++ b/.agents/notes/implemented/feature/2026-07-25-workspace-ui-product-flow.md @@ -21,10 +21,11 @@ The Host provides the following GUI wiring on the Workspace entity: | `workspace.list` | Returns persistent Workspaces in order and filters out Session ids that fail header validation | | `workspace.create({ name })` | Creates a directory and Workspace at `workspaceRoot/name`; fails on a display-name conflict | | `workspace.create({ path })` | Adopts an existing directory and does not create an arbitrary path | +| `workspace.delete({ workspaceId })` | Removes the Workspace registration while retaining its directory and session logs; its Sessions become Ungrouped | | `session.create({ workspaceId, sessionId? })` | Resolves cwd from the Workspace, idempotently creates a Session with an optional preallocated id, and attaches it | | `session.create({ cwd })` | Remains available to non-Workspace callers and creates an Ungrouped Session | -`workspaceRoot` is an independent Host setting that falls back to the Host cwd when unset; it is unrelated to `storageRoot`, which stores Workspace domain data. The Host stream pushes Workspace and Session deltas, and the Client refreshes the `workspace.list` and `session.list` baselines separately after reconnecting. +`workspaceRoot` is an independent Host setting that falls back to the Host cwd when unset; it is unrelated to `storageRoot`, which stores Workspace domain data. The Host stream pushes Workspace and Session deltas, including `host/workspace-removed`, and the Client refreshes the `workspace.list` and `session.list` baselines separately after reconnecting. Registration-deletion ownership and safety are defined in the [Workspace registration deletion Agent Note](2026-07-27-workspace-registration-deletion.md). A Workspace's `sessionIds` is an ordered candidate index. A membership projection requires both that an id appear in the index and that the corresponding canonicalized `SessionHeader.cwd` equal the Workspace path; SessionHeader does not gain a `workspaceId`. A Session whose cwd matches but whose id is absent from the index remains Ungrouped, while an indexed id is filtered out if its header is missing, its cwd is invalid, or its cwd does not match. Two Workspace indexes claiming the same Session is corrupt state and fails loudly. @@ -51,7 +52,7 @@ When no Workspace exists, the page creates a frontend Workspace object named `wo Top-level New Session, the plus button on a Workspace row, and the Workspace picker all invoke the same New Session action. An explicit Workspace id becomes the target directly; when none is specified, the action uses the most recent Workspace, or the Workspace Intent if no real Workspace exists. The Workspace picker's Use an existing folder and Create a new workspace actions immediately create a real Workspace when the user confirms, then retarget the frontend Session to it; an explicitly created empty Workspace remains even if the user sends no message. -Create a new workspace temporarily uses the same input as both the directory name and display name. The UI prevents duplicate confirmation based on current Workspace titles, while the Host continues to reject same-name requests that bypass the UI or race concurrently. Rename, Delete, moving across Workspaces, drag-and-drop ordering, manual adoption from Ungrouped, and separate display-name and directory-name inputs are outside this iteration's scope. +Create a new workspace temporarily uses the same input as both the directory name and display name. The UI prevents duplicate confirmation based on current Workspace titles, while the Host continues to reject same-name requests that bypass the UI or race concurrently. Moving Sessions across Workspaces, manual adoption from Ungrouped, and separate display-name and directory-name inputs remain outside this flow. ### First send and recovery @@ -75,6 +76,8 @@ A frontend Session Intent appears as a “New session” row and temporarily cou Real Sessions that cannot be assigned to any Workspace appear under Ungrouped. Host `session-added` and `workspace-changed` events may arrive in either order; list merging does not depend on frame order. +Deleting a Workspace registration removes its group without deleting or closing any Session. Its accounted Sessions immediately join Ungrouped, including the current Session; a reload reconstructs the same result from the independent Workspace and Session baselines. + ### React and slot boundaries React components only consume `useSessions`, `useWorkspaces`, and session-scoped hooks; they do not own entity lifecycles. The Zustand store retains only layout, the current view, composer text for ordinary real Sessions, and other purely presentational state. Session and Workspace Intents, materialization phases, errors, and retained prompts reside in the React-free runtime object layer. @@ -106,6 +109,7 @@ The Sidebar and conversation empty hero receive standardized actions through slo - The initial default target is determined exactly once after both baselines are ready; Workspace groups are not reordered as a whole by hydration or Session activity, and an active Session moves only itself to the front. - A frontend Session under a real Workspace temporarily counts toward the sidebar total, while a Workspace Intent remains hidden; neither publication nor refresh leaves duplicate rows or counts. - Both the UI and Host reject duplicate Workspace names; cwd-only Sessions, Sessions with invalid historical cwd values, and unattached Sessions remain Ungrouped. +- Confirmed Workspace deletion removes only the registration, retains the current Session, directory, files, and session log, and survives reload; package tests pin unary/frame/baseline races and failure rollback. - Keyless runnable snapshots cover the zero state, explicit creation, and the first send; package-level tests cover bootstrap, membership validation, ordering, idempotency, failure recovery, and arbitrary frame order. ## Consequences diff --git a/.agents/notes/implemented/feature/2026-07-25-workspace-ui-product-flow.zh.md b/.agents/notes/implemented/feature/2026-07-25-workspace-ui-product-flow.zh.md index 8ccbf5b984..b80b75a806 100644 --- a/.agents/notes/implemented/feature/2026-07-25-workspace-ui-product-flow.zh.md +++ b/.agents/notes/implemented/feature/2026-07-25-workspace-ui-product-flow.zh.md @@ -21,10 +21,11 @@ Host 在 Workspace entity 上提供以下 GUI 接线： | `workspace.list` | 返回持久有序的 Workspace，并过滤未通过 header 校验的 Session id | | `workspace.create({ name })` | 在 `workspaceRoot/name` 创建目录和 Workspace；显示名冲突时失败 | | `workspace.create({ path })` | 收编已经存在的目录，不为任意路径创建目录 | +| `workspace.delete({ workspaceId })` | 移除 Workspace 注册记录，同时保留目录和会话日志；相关 Session 进入 Ungrouped | | `session.create({ workspaceId, sessionId? })` | 从 Workspace 解析 cwd，以可选预分配 id 幂等创建 Session 并 attach | | `session.create({ cwd })` | 保留给非 Workspace 调用方，创建 Ungrouped Session | -`workspaceRoot` 是独立 Host 配置，未配置时回退到 Host cwd；它与保存 Workspace domain 数据的 `storageRoot` 无关。Host stream 推送 Workspace 与 Session 增量，Client 重连后分别刷新 `workspace.list` 与 `session.list` 基线。 +`workspaceRoot` 是独立 Host 配置，未配置时回退到 Host cwd；它与保存 Workspace domain 数据的 `storageRoot` 无关。Host stream 推送 Workspace 与 Session 增量，包括 `host/workspace-removed`；Client 重连后分别刷新 `workspace.list` 与 `session.list` 基线。删除注册记录的所有权与安全边界由 [Workspace 注册记录删除 Agent Note](2026-07-27-workspace-registration-deletion.md)定义。 Workspace 的 `sessionIds` 是有序候选索引。成员投影同时要求 id 位于索引且对应 `SessionHeader.cwd` canonical 后等于 Workspace path；SessionHeader 不增加 `workspaceId`。cwd 匹配但未入索引的 Session 保持 Ungrouped，索引命中但 header 缺失、cwd 无效或 cwd 不匹配的 id 被过滤。同一 Session 被两个 Workspace 索引占用属于损坏状态并 fail loud。 @@ -51,7 +52,7 @@ Session 自己持有首条输入并驱动一条内部流水线：必要时以预 顶部 New Session、Workspace 行内加号和 Workspace picker 最终都调用同一 New Session 动作：显式 Workspace id 直接成为目标，未指定时使用最近 Workspace，没有真实 Workspace 时使用 Workspace Intent。Workspace picker 的 Use an existing folder 与 Create a new workspace 会在用户确认时立即创建真实 Workspace，再把前端 Session 定位到该 Workspace；即使用户不发送消息，显式创建的空 Workspace 也保留。 -Create a new workspace 暂时用同一个输入作为目录名和显示名。UI 根据当前 Workspace title 禁止重复确认，Host 继续拒绝绕过 UI 或并发产生的同名请求。Rename、Delete、跨 Workspace 移动、拖拽排序、Ungrouped 手动收编和显示名/目录名双输入不在本期范围。 +Create a new workspace 暂时用同一个输入作为目录名和显示名。UI 根据当前 Workspace title 禁止重复确认，Host 继续拒绝绕过 UI 或并发产生的同名请求。跨 Workspace 移动 Session、从 Ungrouped 手动收编以及分别输入显示名和目录名仍不在此动线范围内。 ### 首次发送与恢复 @@ -75,6 +76,8 @@ Workspace 组严格使用 Host 返回的持久顺序。Bootstrap 一次性确定 无法归入任何 Workspace 的真实 Session 进入 Ungrouped。Host `session-added` 与 `workspace-changed` 可以任意顺序到达，列表合并不依赖 frame 顺序。 +删除 Workspace 注册记录会移除其分组，但不会删除或关闭任何 Session。已记账的 Session（包括当前 Session）会立即进入 Ungrouped；刷新后，独立的 Workspace 与 Session 基线会重建出相同结果。 + ### React 与 slot 边界 React 组件只消费 `useSessions`、`useWorkspaces` 与 session-scoped hooks，不拥有实体生命周期。Zustand store 只保留布局、当前 view、普通真实 Session 的 composer 文本和其他纯呈现状态；Session/Workspace Intent、materialize phase、错误和 retained prompt 位于 React-free runtime 对象层。 @@ -106,6 +109,7 @@ Sidebar 与 conversation empty hero 通过 slot 获得标准化动作：`startSe - 初始默认目标只在两份基线 ready 后确定一次；Workspace 组不因 hydration 或 Session 活跃整体重排，单个活跃 Session 只前移自身。 - 真实 Workspace 下的前端 Session 临时计入 sidebar 数量，Workspace Intent 保持隐藏，发布与刷新都不会留下重复行或重复计数。 - UI 与 Host 两层拒绝同名 Workspace；cwd-only Session、无效历史 cwd 和未 attach Session 保持 Ungrouped。 +- 经确认的 Workspace 删除只移除注册记录，保留当前 Session、目录、文件和会话日志，并在刷新后保持该状态；包级测试固定一元响应／帧／基线竞态和失败回滚行为。 - keyless runnable snapshot 覆盖零态、显式创建和首次发送；包级测试覆盖 bootstrap、成员校验、排序、幂等、失败恢复及任意 frame 顺序。 ## Consequences diff --git a/.agents/notes/implemented/feature/2026-07-27-workspace-registration-deletion.i18n.yaml b/.agents/notes/implemented/feature/2026-07-27-workspace-registration-deletion.i18n.yaml new file mode 100644 index 0000000000..847b040457 --- /dev/null +++ b/.agents/notes/implemented/feature/2026-07-27-workspace-registration-deletion.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# 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/feature/2026-07-27-workspace-registration-deletion.md +2026-07-27-workspace-registration-deletion.md: cae01d529bc6fd97da6fb61839bd5ec8e21557e2 +2026-07-27-workspace-registration-deletion.zh.md: 76377ebc5e93101e1e3efce1d29c3c654df032c2 diff --git a/.agents/notes/implemented/feature/2026-07-27-workspace-registration-deletion.md b/.agents/notes/implemented/feature/2026-07-27-workspace-registration-deletion.md new file mode 100644 index 0000000000..cae01d529b --- /dev/null +++ b/.agents/notes/implemented/feature/2026-07-27-workspace-registration-deletion.md @@ -0,0 +1,53 @@ +# Agent Note: Workspace Registration Deletion + +Status: implemented + +English | [中文](2026-07-27-workspace-registration-deletion.zh.md) + +## Problem + +A Workspace registers an existing code directory so the GUI can name it and order its Sessions. That record has no reliable provenance proving that Harness created or owns the directory, and the Session log is an independent persistence object. Treating the row's Delete action as recursive source deletion or Session deletion would destroy data outside the record's ownership boundary. + +The existing visual-only menu row also left deletion semantics undefined across durable order, the Workspace table, Host streams, concurrent browser tabs, reconnect baselines, and a list request racing the mutation. + +## Decision + +`ctx.workspace.delete(id)` deletes only the Workspace registration: its id leaves durable `workspaceIds`, its `workspaces` table row and entity-cache entry disappear, and its ordered `sessionIds` account disappears with that row. It never calls filesystem removal or `SessionPersistence`; the directory, every user file, every live Session, and every persisted Session log remain. Because sidebar grouping is the complement of all surviving Workspace accounts, those Sessions immediately appear under Ungrouped, including the current Session. + +Unknown ids return `false` at the domain seam. `workspace.delete({ workspaceId })` maps that distinction to `workspace-not-found`; success returns `{ deleted: true }`. `workspace.list` remains the reconnect baseline. + +## Durable commit and publication + +Registry operations serialize create and delete. Deletion first writes the Workspace order without the id, then removes the entity from the cache, then deletes the table row. The table deletion is the notification commit point: the package invariant accepts it only after the cache stopped publishing the entity, and the Host emits `host/workspace-removed` only from that committed deletion. A table-write failure restores the cache and prior durable order; no removal frame is published. + +The Host stream keeps its committed-id set through the preceding global-order write and removes the id only on the table deletion. Create rollback therefore emits no false removal, while every connected tab receives exactly the id needed to delete its projection. + +## Client convergence + +`WorkspaceManager` treats both `host/workspace-changed` and `host/workspace-removed` as ordered deltas replayed over an in-flight `workspace.list` response. A successful unary delete removes the row immediately instead of waiting for its own stream echo. Removal is idempotent, and a process-local tombstone rejects late changed frames or stale baseline rows for the never-reused Workspace id. A reconnect still refreshes from `workspace.list`; Session state is never pruned by a Workspace delta. + +## Confirmation interaction + +The existing Workspace row menu opens a shared `Modal` before deletion. The text states all three consequences: the Workspace leaves the list, the folder and session logs remain, and its Sessions appear under Ungrouped. While the request is pending, the confirm and Cancel controls are disabled, duplicate confirmation is ignored, and Escape or Close cannot dismiss the operation. Failure keeps the Modal open with the error; Cancel, Escape, and Close before submission never delete. + +The menu, Modal, and buttons retain their existing structure and design tokens. Session deletion remains visual-only and outside this decision. + +## Alternatives considered + +**Cascade-delete Sessions.** Rejected because Workspace registration does not own Session persistence and the product requirement is to preserve histories under Ungrouped. Session deletion needs its own lifecycle, running checks, descendant semantics, and explicit UI. + +**Move the folder to Trash.** Rejected because the record cannot prove directory ownership. A future destructive filesystem action must be separately named, separately confirmed, and enforce explicit safety boundaries. + +**Delete the table row and repair order later.** Rejected because a crash or write failure would leave an initialized registry whose order and table disagree. The registry updates both under one serialized operation and restores the prior order on table failure. + +**Refetch both lists after success.** Rejected because the committed removal frame plus immediate unary echo is sufficient, preserves the current Session object, and avoids turning a local mutation into two list requests. Reconnect baselines remain the repair path. + +## Verification + +Workspace package tests pin successful metadata-only deletion, unknown-id idempotence, table-failure rollback, and cache/table invariant behavior. Apiproxy and carrier tests pin the schema, handler, `workspace-not-found`, retained Session/folder, and committed `host/workspace-removed` frame. Client tests pin unary direct echo, duplicate removal, late changed frames, and deletion racing an in-flight baseline. Component tests pin confirmation, pending-state duplicate suppression, success, failure, Cancel, Escape, and Close. + +The assembled keyless Web scenario registers an existing temporary project directory, accounts a persisted Session, makes that Session current, confirms deletion in Chromium, and verifies the Workspace group disappears while Ungrouped retains the current Session. It checks the user file and JSONL log before and after deletion and repeats the UI, directory, and log assertions after reload. + +## Consequences + +Deleting a Workspace is intentionally reversible by registering the same directory again, although its prior manual Session order is gone; re-registration does not automatically re-adopt existing Sessions after bootstrap. The operation gives up a one-click cleanup of Session histories or source directories in exchange for a deletion boundary that matches what the record actually owns. diff --git a/.agents/notes/implemented/feature/2026-07-27-workspace-registration-deletion.zh.md b/.agents/notes/implemented/feature/2026-07-27-workspace-registration-deletion.zh.md new file mode 100644 index 0000000000..76377ebc5e --- /dev/null +++ b/.agents/notes/implemented/feature/2026-07-27-workspace-registration-deletion.zh.md @@ -0,0 +1,53 @@ +# Agent Note（agent 决策记录）：删除 Workspace 注册记录 + +Status: implemented + +[English](2026-07-27-workspace-registration-deletion.md) | 中文 + +## Problem + +Workspace 注册已有代码目录，使 GUI 能够为目录命名，并对其会话排序。该记录没有可靠的来源信息来证明 Harness 创建或拥有该目录，会话日志也是独立的持久化对象。若将行内 Delete 操作视为递归删除源码或删除会话，就会破坏该记录所有权边界之外的数据。 + +现有菜单行仅提供视觉效果，因此持久顺序、Workspace 表、Host 流、并发浏览器标签页、重连基线，以及列表请求与变更并发时的删除语义也没有定义。 + +## Decision + +`ctx.workspace.delete(id)` 只删除 Workspace 注册记录：其 id 会从持久 `workspaceIds` 中移除，`workspaces` 表行与实体缓存条目会消失，有序 `sessionIds` 账本也随该行一并消失。它绝不调用文件系统移除操作或 `SessionPersistence`；目录、所有用户文件、所有实时会话和所有持久化会话日志都会保留。侧边栏分组是所有存续 Workspace 账本的补集，因此这些会话（包括当前会话）会立即出现在 Ungrouped 下。 + +未知 id 在 domain seam 返回 `false`。`workspace.delete({ workspaceId })` 将该结果映射为 `workspace-not-found`；成功时返回 `{ deleted: true }`。`workspace.list` 仍是重连基线。 + +## 持久提交与发布 + +注册表操作会串行执行创建与删除。删除时先写入移除该 id 后的 Workspace 顺序，再从缓存中移除实体，最后删除表行。表删除是通知提交点：只有缓存停止发布该实体后，包不变量才接受该删除；Host 也只根据这次已提交的删除发出 `host/workspace-removed`。表写入失败时，系统会恢复缓存和此前的持久顺序，且不会发布移除帧。 + +Host 流在前一笔全局顺序写入期间继续保留其已提交 id 集合，只在删除表行时移除该 id。因此，创建回滚不会发出错误的移除帧，而每个已连接标签页都能收到从自身投影中删除该记录所需的准确 id。 + +## 客户端收敛 + +`WorkspaceManager` 将 `host/workspace-changed` 与 `host/workspace-removed` 都视为有序增量，并在进行中的 `workspace.list` 响应之上回放。成功的一元删除会立即移除行，无需等待本次操作自己的流回显。移除操作具有幂等性；由于 Workspace id 永不复用，进程本地删除标记会拒绝延迟到达的 changed 帧或陈旧基线行。重连仍从 `workspace.list` 刷新；Workspace 增量绝不会剪除会话状态。 + +## 确认交互 + +现有 Workspace 行菜单会在删除前打开共享 `Modal`。文案明确说明三项后果：Workspace 会从列表中移除，文件夹和会话日志会保留，相关会话会出现在 Ungrouped 下。请求待处理期间，确认与 Cancel 控件均被禁用，重复确认会被忽略，Escape 或 Close 也无法关闭此次操作。失败时 `Modal` 保持打开并显示错误；提交前使用 Cancel、Escape 或 Close 绝不会触发删除。 + +菜单、`Modal` 和按钮保留现有结构与设计 token。会话删除仍仅提供视觉效果，不在本决策范围内。 + +## Alternatives considered + +**级联删除会话。** 不予采纳，因为 Workspace 注册记录不拥有会话持久化，且产品需求是将历史记录保留在 Ungrouped 下。会话删除需要自己的生命周期、运行状态检查、后代对象的处理语义和明确 UI。 + +**将文件夹移到废纸篓。** 不予采纳，因为该记录无法证明目录所有权。未来的破坏性文件系统操作必须使用单独名称、单独确认，并实施明确的安全边界。 + +**先删除表行，之后再修复顺序。** 不予采纳，因为崩溃或写入失败会使已初始化注册表的顺序与表不一致。注册表会在同一串行操作内更新二者，并在表操作失败时恢复此前顺序。 + +**成功后重新拉取两个列表。** 不予采纳，因为已提交的移除帧与即时一元回显已足够，既能保留当前会话对象，也避免将局部变更扩大为两次列表请求。重连基线仍是修复路径。 + +## Verification + +Workspace 包测试固定了仅删除元数据的成功路径、未知 id 的幂等行为、表操作失败回滚，以及缓存／表不变量行为。Apiproxy 与载体测试固定了 schema、处理器、`workspace-not-found`、保留会话／文件夹，以及已提交的 `host/workspace-removed` 帧。客户端测试固定了一元直接回显、重复移除、延迟到达的 changed 帧，以及删除与进行中基线并发的行为。组件测试固定了确认交互、待处理状态下抑制重复提交、成功、失败、Cancel、Escape 与 Close。 + +组装后的无密钥 Web 场景会注册一个已有临时项目目录，将持久化会话计入账本，把该会话设为当前会话，在 Chromium 中确认删除，并验证 Workspace 分组消失，而 Ungrouped 保留当前会话。该场景在删除前后检查用户文件和 JSONL 日志，并在刷新后重复验证 UI、目录与日志。 + +## Consequences + +删除 Workspace 后仍可重新注册同一目录，因此该操作有意设计为可逆；但此前的手动会话顺序会丢失，重新注册后，系统也不会在 bootstrap 结束后自动重新收编现有会话。该操作放弃一键清理会话历史或源码目录，以换取与记录实际所有权一致的删除边界。 diff --git a/.agents/notes/proposed/architecture/2026-07-24-domain-kv-storage-and-workspace.i18n.yaml b/.agents/notes/proposed/architecture/2026-07-24-domain-kv-storage-and-workspace.i18n.yaml index 5ab7a8229d..6e5f8b8391 100644 --- a/.agents/notes/proposed/architecture/2026-07-24-domain-kv-storage-and-workspace.i18n.yaml +++ b/.agents/notes/proposed/architecture/2026-07-24-domain-kv-storage-and-workspace.i18n.yaml @@ -1,6 +1,6 @@ # Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each # 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 -2026-07-24-domain-kv-storage-and-workspace.md: cd666a47a3cba4dea8846cd0f1373224e6fc456f -2026-07-24-domain-kv-storage-and-workspace.zh.md: 81adf1eb6bc32aa3ca8b9ef4c352fb94f95ace91 +# pnpm run verify-translation-pairing --write .agents/notes/proposed/architecture/2026-07-24-domain-kv-storage-and-workspace.md +2026-07-24-domain-kv-storage-and-workspace.md: 230877628428dc88dbddeecfe5f4353cf15e151d +2026-07-24-domain-kv-storage-and-workspace.zh.md: 050f72cd3327f83e2c3f3cefcab63c01e8f112ee diff --git a/.agents/notes/proposed/architecture/2026-07-24-domain-kv-storage-and-workspace.md b/.agents/notes/proposed/architecture/2026-07-24-domain-kv-storage-and-workspace.md index cd666a47a3..2308776284 100644 --- a/.agents/notes/proposed/architecture/2026-07-24-domain-kv-storage-and-workspace.md +++ b/.agents/notes/proposed/architecture/2026-07-24-domain-kv-storage-and-workspace.md @@ -11,7 +11,9 @@ The host's only persistence surface is the session event log (`packages/session- - **The workspace entity.** The GUI needs workspace as a real object: path, title, and the list of owned sessions. Ownership belongs to the workspace — "which sessions belong to this workspace" is not any single session's fact, so writing it into the session log is semantically wrong. Until now workspace was only a sidebar visual grouping derived from cwd, with no entity (that conclusion has been overturned). - **Dynamic session metadata** (the foreseeable second consumer). Cold session listings read only the first log line (an immutable creation-time snapshot); title, terminal status, and anything that evolves with the session is unavailable. The fix direction is a sidecar metadata table — exactly a KV table with high-frequency per-key updates. -Separately, workspace deletion will eventually need to delete its owned sessions, and `SessionPersistence` has no delete primitive nor does the host expose a `session.delete` endpoint — that gap's design is settled in this note, but its implementation is marked future work: this phase touches no session-side code. +Separately, Session deletion needs a `SessionPersistence` delete primitive and a `session.delete` endpoint. That gap's design is settled in this note, but its implementation remains future work. + +The later [Workspace registration deletion decision](../../implemented/feature/2026-07-27-workspace-registration-deletion.md) supersedes only that coupling: deleting a Workspace registration preserves its Sessions and their logs, while Session deletion remains separate future work. The cascade design below is therefore not the Workspace GUI delete semantic. ## Proposal @@ -234,14 +236,14 @@ export class WorkspaceRegistry extends Service { get(id: WorkspaceId): Workspace | undefined list(): Workspace[] resolveByPath(path: string): Promise // 同 realpath 口径，故 async - // delete：future work（与 session 级联删一起做，见下）；本期不提供任何删除入口 + delete(id: WorkspaceId): Promise // 只删注册记录；目录与 session 日志保留 } ``` - **Path canon**: the stored value = `fs.realpath(input)` (trailing slashes, `..`, and symlinks all resolved); uniqueness = string equality after normalization (a symlink resolving to the same directory counts as a collision). A missing directory makes create reject outright (realpath fails — a workspace must point at an existing directory; "Create new = make the directory" is upper-layer interaction: mkdir first, then create). The session cwd in attach checks follows the same canon. Single-valued cwd + unique path ⇒ one session structurally belongs to at most one workspace; double bookkeeping is impossible on the write side. - **Title**: a display name, defaults to `basename(path)`, mutable, duplicates allowed. Ownership is never derived from cwd as a fallback — cwd cannot express ordering, and ownership is a workspace-side fact; sessions started headless belong to no workspace. - Consumers see only the `Workspace` interface; `WorkspaceEntity` stays inside the package (a single implementation does not pre-split a seam). Entities are unique per id (registry cache); the record snapshot is swapped in place after each write, and the outside sees getters only. Every write funnels through the entity's internal `mutate(fn)` → `table.update`, with `updatedAt` refreshed inside mutate. Domain objects never cross RPC; next phase the wire layer projects records into zod wire schemas. -- **Workspace deletion is future work as a whole** (settled 2026-07-24): the registry ships no delete method this phase — the half-measure "delete the record, keep the sessions" is not exposed; deletion and the session cascade (`recursive` parameter, running checks, bottom-up order, crash-rerun convergence) land as one complete semantic together with the session delete primitive; the order then is delete sessions one by one → prune the ledger → delete the workspace record. +- **Session deletion remains future work.** The later [Workspace registration deletion decision](../../implemented/feature/2026-07-27-workspace-registration-deletion.md) ships `ctx.workspace.delete(id)` as a metadata-only operation that preserves Sessions and logs. Recursive Session deletion, running checks, and crash-rerun convergence belong to a separate `session.delete` capability. Consistency doctrine (the ledger = the only ownership authority; the implementation and test baseline): @@ -285,7 +287,7 @@ Snapshots: no model-visible or assembly surface this phase, none added; next pha | Not doing | Trigger | Rework point | Groundwork | | --- | --- | --- | --- | -| The full deletion suite (`SessionPersistence.delete`, the deleted event, `registry.delete` cascade, recursive delete, running checks) | future work starts (before the GUI needs delete interactions) | implement per the future-work section above: the session primitive + `registry.delete(id, { recursive? })` land as one | orchestration rules and rejection table settled in this note; no deletion entry exists this phase, so no half-semantics to stay compatible with | +| Session deletion (`SessionPersistence.delete`, the deleted event, recursive delete, running checks) | a destructive Session-delete product flow starts | implement the session primitive plus `session.delete`; keep it independent from Workspace registration deletion | orchestration rules and rejection table above remain groundwork; Workspace deletion preserves Sessions and logs | | The `log` facet and the session-backend migration | any phase after this one | sink the medium operations (the reuse audit table is the work list) | the facet structure is in place; both backends' medium code is organized in sinkable shape already | | Multi-process write protection | two host processes writing one medium | JSON backend file locks; SQLite WAL is natively multi-process | all writes already funnel through the domain's single point; locking touches backends only | | Cross-process change observation | GUI reconnect awareness | the revision pattern (copy session-persistence) | `domain/changed` already exists in-process | @@ -296,7 +298,7 @@ Snapshots: no model-visible or assembly surface this phase, none added; next pha | Cross-table atomic transactions | one business operation touching two tables of one domain atomically | `domain.transact(fn)`; JSON whole-unit rewrite is naturally atomic, SQLite wraps a transaction | — | | Secondary indexes / conditional queries | in-memory filtering stops scaling (tens of thousands of records) | SQLite JSON1 over the value column, a read-only query facet on the seam | the JSON backend does not follow | | Moving a session across workspaces | a product need appears | relax the attach check into a "detach first, then attach" orchestration | — | -| RPC/GUI/boot | next phase | `workspace.*` + `session.delete` endpoints, wire schemas, boot mounting, sidebar on real data | this phase's model and semantics are the direct source of the wire projection | +| Session-delete RPC/GUI | a destructive Session-delete product flow starts | `session.delete` endpoint, wire schema, and explicit confirmation UI | Workspace RPC/GUI is shipped separately; no cascade coupling remains | ## Alternatives considered @@ -317,7 +319,7 @@ Snapshots: no model-visible or assembly surface this phase, none added; next pha ## Acceptance criteria - This phase's four test suites all green: the shared backend contract suite on both json/sqlite, registry/mount disposer semantics, the domain layer (including the six open steps and fail-loud routing), and full workspace semantics (create/attach checks/consistency doctrine). -- `ctx.workspace` completes the create → attach → list lifecycle under a test assembly (deletion is future work). +- `ctx.workspace` completes the create → attach → list → metadata-only delete lifecycle under a test assembly. - Zero diff in the session-persistence packages (the acceptance line for not touching the session side this phase). - No new snapshots this phase (no model-visible or assembly surface); added next phase with the RPC wiring. diff --git a/.agents/notes/proposed/architecture/2026-07-24-domain-kv-storage-and-workspace.zh.md b/.agents/notes/proposed/architecture/2026-07-24-domain-kv-storage-and-workspace.zh.md index 81adf1eb6b..050f72cd33 100644 --- a/.agents/notes/proposed/architecture/2026-07-24-domain-kv-storage-and-workspace.zh.md +++ b/.agents/notes/proposed/architecture/2026-07-24-domain-kv-storage-and-workspace.zh.md @@ -11,7 +11,9 @@ host 侧唯一的持久化面是 session 事件日志（`packages/session-persis - **workspace 实体**。GUI 要把 workspace 做成真实对象：路径、标题、关联 session 清单。归属关系由 workspace 持有——"哪些 session 属于这个 workspace"不是任何单个 session 自己的事实，塞进 session log 语义不成立。此前 workspace 只是 sidebar 上按 cwd 分组的视觉概念，没有实体（该结论已被推翻）。 - **session 动态元信息**（可预见的第二个消费者）。冷会话列表只读日志首行 header（创建时的不可变快照），title、结束状态这类随会话推进变化的信息拿不到；补齐方向是 sidecar 元数据表——正是一张按 key 高频点更新的 KV 表。 -另外，workspace 删除最终需要删除其关联 session，而 `SessionPersistence` 没有删除原语，host 也没有 `session.delete` 端点——该空白的设计随本 Note 定案，但实施标记为 future work：本期不动 session 侧任何代码。 +另外，Session 删除需要 `SessionPersistence` 删除原语和 `session.delete` 端点。该空白的设计随本 Note 定案，但实现仍属未来工作。 + +后续的 [Workspace 注册记录删除决策](../../implemented/feature/2026-07-27-workspace-registration-deletion.md)取代的仅是上述耦合关系：删除 Workspace 注册记录会保留相关 Session 及其日志，Session 删除仍是独立的未来工作。因此，下文的级联设计并不是 Workspace GUI 的删除语义。 ## Proposal @@ -234,14 +236,14 @@ export class WorkspaceRegistry extends Service { get(id: WorkspaceId): Workspace | undefined list(): Workspace[] resolveByPath(path: string): Promise // 同 realpath 口径，故 async - // delete：future work（与 session 级联删一起做，见下）；本期不提供任何删除入口 + delete(id: WorkspaceId): Promise // 只删注册记录；目录与 session 日志保留 } ``` - **path 规范**：落盘值 = `fs.realpath(输入)`（尾斜杠、`..`、符号链接全解析）；唯一性 = 规范化后字符串相等（符号链接指向同一目录算撞）。目录不存在时 create 直接 reject（realpath 失败——workspace 必须指向存在目录；"Create new = 建目录"是上层交互，先 mkdir 再 create）。attach 校验的 session cwd 同口径。cwd 单值 + path 唯一 ⇒ 一个 session 结构上最多归属一个 workspace，双重记账写侧不可能。 - **title**：显示名，默认 `basename(path)`，可改，允许重复。归属不用 cwd 派生兜底——cwd 表达不了排序，归属是 workspace 侧事实；headless 直开的 session 不属于任何 workspace。 - 消费者只见 `Workspace` 接口，`WorkspaceEntity` 不出包（单实现不预拆 seam）；实体按 id 唯一（registry 缓存），记录快照写后原地换新，外部只见 getter；所有写收敛到实体内 `mutate(fn)` → `table.update`，`updatedAt` 在 mutate 内统一刷。领域对象不过 RPC，下期 wire 层把记录投影成 zod wire schema。 -- **workspace 删除整体为 future work**（2026-07-24 拍板）：本期 registry 不提供 delete 方法——半截的"只删记录留 session"语义不对外暴露，删除与 session 级联（`recursive` 参数、运行中检查、自底向上、崩溃重跑收敛）作为一个完整语义随 session 删除原语一起落地；届时顺序为逐个删 session → 摘账 → 删记录。 +- **Session 删除仍属未来工作。** 后续的 [Workspace 注册记录删除决策](../../implemented/feature/2026-07-27-workspace-registration-deletion.md)已将 `ctx.workspace.delete(id)` 作为仅删除元数据、保留 Session 与日志的操作交付。递归删除 Session、运行中检查和崩溃重跑收敛属于独立的 `session.delete` 能力。 一致性口径（账 = 归属唯一依据；实现与测试基准）： @@ -285,7 +287,7 @@ export class WorkspaceRegistry extends Service { | 不做 | 触发条件 | 返工点 | 预埋 | | --- | --- | --- | --- | -| 删除全套（`SessionPersistence.delete`、deleted 事件、`registry.delete` 级联、递归删、运行中检查） | future work 启动（GUI 需要删除交互前） | 按上文 future work 节实施：session 原语 + `registry.delete(id, { recursive? })` 一体落地 | 编排规则/拒绝清单已定案在本 Note；本期无任何删除入口，无半截语义要兼容 | +| Session 删除（`SessionPersistence.delete`、deleted 事件、递归删除、运行中检查） | 破坏性的 Session 删除产品流启动 | 实现 Session 原语及 `session.delete`；与 Workspace 注册记录删除保持独立 | 上文编排规则和拒绝清单仍是基础；Workspace 删除会保留 Session 与日志 | | `log` facet 与 session 后端迁移 | 本期后任意期启动 | 介质操作下沉（复用审计表即施工清单） | facet 结构已留位；两后端介质代码本期即按可下沉形状组织 | | 多进程并发写保护 | 两 host 进程同写一介质 | JSON 后端文件锁；SQLite WAL 天然多进程 | 写全经 domain 单点串行，加锁只动后端 | | 跨进程变更观测 | GUI 断线重连感知 | revision 模式（抄 session-persistence） | 进程内已有 `domain/changed` | @@ -296,7 +298,7 @@ export class WorkspaceRegistry extends Service { | 跨表原子事务 | 同域两表一次原子操作需求 | `domain.transact(fn)`；JSON 天然原子，SQLite 包事务 | — | | 二级索引/条件查询 | 内存过滤不动（万级记录） | SQLite JSON1 查 value 列，加只读 query 面 | JSON 后端不陪跑 | | session 跨 workspace 移动 | 产品需求出现 | attach 校验放宽为"先 detach 后 attach"编排 | — | -| RPC/GUI/boot | 下期 | `workspace.*` + `session.delete` 端点、wire schema、boot 挂载、sidebar 接真数据 | 本期模型与语义即 wire 投影的直接来源 | +| Session 删除 RPC／GUI | 破坏性的 Session 删除产品流启动 | `session.delete` 端点、wire schema 与明确的确认 UI | Workspace RPC／GUI 已独立交付，不再存在级联耦合 | ## Alternatives considered @@ -317,7 +319,7 @@ export class WorkspaceRegistry extends Service { ## Acceptance criteria - 测试矩阵本期四套件全绿：backend 契约共享套件在 json/sqlite 双端、registry/mount disposer 语义、domain 层（含 open 六步与路由 fail-loud）、workspace 全语义（create/attach 校验/一致性口径）。 -- `ctx.workspace` 可在测试组装下完成 create → attach → list 生命周期（删除为 future work）。 +- `ctx.workspace` 可在测试组装下完成 create → attach → list → 仅删除元数据的 delete 生命周期。 - session-persistence 包零 diff（本期不动 session 侧的验收线）。 - 本期无新快照（无模型可见面与组装面）；下期 RPC 接线时补。 diff --git a/apps/web/tests/workspace-management.e2e.ts b/apps/web/tests/workspace-management.e2e.ts index a19211c6bf..4dbcca36ae 100644 --- a/apps/web/tests/workspace-management.e2e.ts +++ b/apps/web/tests/workspace-management.e2e.ts @@ -5,12 +5,13 @@ // calls: workspace.create/rename are host RPCs with no model involvement, // and the one session row the flat/hover scenarios need comes from a seeded // fixture (the seeded-history seed reused verbatim — no new recording). -import { mkdir, readFile, writeFile } from 'node:fs/promises' +import { mkdir, readFile, stat, writeFile } from 'node:fs/promises' import { fileURLToPath } from 'node:url' import { join } from 'node:path' import type { Browser, Page } from 'playwright' import { chromium } from 'playwright' import { afterAll, beforeAll, describe, expect, it, onTestFailed } from 'vitest' +import { SessionId } from '@deepseek-ai/dsh-session' import { acknowledgeReloadConnectionLoss, assertFixtureInventory, launchWebScaffold, seedSession, watchConsole, webSnapshotMode, type WebScaffold, @@ -105,6 +106,86 @@ describe('web e2e: workspace management (create / rename / flat view / hover car expect(tripwire.pageErrors).toEqual([]) }, 90_000) + it('deletes only the Workspace registration and keeps its current Session, folder, and log', async () => { + onTestFailed(() => saveFailureShot(page, 'web-e2e-ws-delete')) + // Register the scaffold's existing project directory through the real UI. + await page.getByRole('button', { name: 'Create workspace' }).click() + await page.getByRole('menuitem', { name: 'Create workspace' }).hover() + await page.getByRole('menuitem', { name: 'Use an existing folder' }).click() + const useFolder = page.getByRole('dialog', { name: 'Use an existing folder' }) + await useFolder.getByLabel('Existing folder path').fill(scaffold.workspaceCwd) + await useFolder.getByRole('button', { name: 'Use folder' }).click() + await expect.poll(() => useFolder.count(), { timeout: 10_000 }).toBe(0) + + const workspace = await scaffold.ctx.workspace.resolveByPath(scaffold.workspaceCwd) + if (workspace === undefined) throw new Error('GUI did not register the existing project directory') + await workspace.attachSession(SessionId(SEED_ID)) + const header = (await scaffold.ctx.sessionPersistence.list()) + .find(candidate => candidate.id === SEED_ID) + if (header === undefined) throw new Error('seeded Session log disappeared before deletion') + const logLocation = scaffold.ctx.sessionPersistence.locate(header) + if (logLocation === undefined) throw new Error('JSONL persistence did not expose the seeded log path') + expect(await readFile(join(scaffold.workspaceCwd, 'workspace', 'a.txt'), 'utf8')).toBe('alpha\n') + await stat(logLocation.path) + + // Open the seeded (first/accounted) Session so deletion must preserve the + // current selection while it moves into Ungrouped. + const groupRow = page.locator('[role="treeitem"]').filter({ hasText: workspace.title }).first() + await groupRow.waitFor({ timeout: 10_000 }) + const groupSection = groupRow.locator('..') + if (await groupSection.locator('[role="treeitem"]').count() < 2) await groupRow.click() + await expect.poll( + () => groupSection.locator('[role="treeitem"]').count(), + { timeout: 10_000 }, + ).toBeGreaterThanOrEqual(2) + const seededRow = groupSection.locator('[role="treeitem"]').nth(1) + await seededRow.click() + await expect.poll(() => seededRow.getAttribute('aria-selected'), { timeout: 10_000 }).toBe('true') + + await groupRow.hover() + await page.getByRole('button', { name: `Workspace actions for ${workspace.title}` }).click() + await page.getByRole('menuitem', { name: 'Delete workspace' }).click() + const dialog = page.getByRole('dialog', { name: 'Delete workspace' }) + await dialog.waitFor({ timeout: 10_000 }) + const copy = await dialog.textContent() + expect(copy).toContain('workspace list') + expect(copy).toContain('folder and session logs will be kept') + expect(copy).toContain('sessions will appear under Ungrouped') + await dialog.getByRole('button', { name: 'Delete workspace' }).click() + await expect.poll(() => dialog.count(), { timeout: 10_000 }).toBe(0) + + expect(scaffold.ctx.workspace.get(workspace.id)).toBeUndefined() + await expect.poll( + () => page.getByRole('button', { name: `Workspace actions for ${workspace.title}` }).count(), + { timeout: 10_000 }, + ).toBe(0) + await expect.poll(() => page.getByText('Ungrouped', { exact: true }).count(), { timeout: 10_000 }) + .toBeGreaterThanOrEqual(1) + await expect.poll( + () => page.locator('[role="treeitem"][aria-selected="true"]').count(), + { timeout: 10_000 }, + ).toBe(1) + expect(await readFile(join(scaffold.workspaceCwd, 'workspace', 'a.txt'), 'utf8')).toBe('alpha\n') + await stat(logLocation.path) + expect((await scaffold.ctx.sessionPersistence.inspect(SessionId(SEED_ID))).events.length).toBeGreaterThan(0) + + const warningStart = tripwire.warnings.length + await page.reload({ waitUntil: 'load' }) + await page.waitForSelector('[class*="frame"]', { timeout: 30_000 }) + acknowledgeReloadConnectionLoss(tripwire, warningStart) + await expect.poll(() => page.getByText('Ungrouped', { exact: true }).count(), { timeout: 15_000 }) + .toBeGreaterThanOrEqual(1) + await expect.poll( + () => page.locator('[role="treeitem"][aria-selected="true"]').count(), + { timeout: 15_000 }, + ).toBe(1) + expect(scaffold.ctx.workspace.get(workspace.id)).toBeUndefined() + expect(await readFile(join(scaffold.workspaceCwd, 'workspace', 'a.txt'), 'utf8')).toBe('alpha\n') + await stat(logLocation.path) + expect((await scaffold.ctx.sessionPersistence.inspect(SessionId(SEED_ID))).events.length).toBeGreaterThan(0) + expect(tripwire.pageErrors).toEqual([]) + }, 90_000) + it('switches to the flat "In one list" view and persists the preference', async () => { onTestFailed(() => saveFailureShot(page, 'web-e2e-ws-flat')) // Grouped default: workspace group rows render (the seeded session sits @@ -134,12 +215,20 @@ describe('web e2e: workspace management (create / rename / flat view / hover car onTestFailed(() => saveFailureShot(page, 'web-e2e-ws-hover')) // Expand Ungrouped to reveal the seeded session row, then dwell on it // (the card opens after a 500ms hover delay, portaled to body). - await page.getByText('Ungrouped', { exact: true }).click() - // A cold summary carries no durable title, so the row falls back to a - // cwd-derived display title — anchored on the run-local workspace-root - // basename rather than a literal. - const wsBase = scaffold.workspaceCwd.split('/').pop()! - const sessionRow = page.locator('[role="treeitem"]').filter({ hasText: wsBase }).first() + const ungroupedRow = page.getByText('Ungrouped', { exact: true }).locator('..').locator('..') + const ungroupedSection = ungroupedRow.locator('..') + // Initial-current auto-expansion can race this following test's gesture; + // converge on expanded rather than assuming which update wins first. + await expect.poll(async () => { + if (await ungroupedRow.getAttribute('aria-expanded') !== 'true') { + await page.getByText('Ungrouped', { exact: true }).click() + await page.waitForTimeout(50) + } + return await ungroupedRow.getAttribute('aria-expanded') + }, { timeout: 5_000 }).toBe('true') + // The only visible child is the non-blank persisted Session; the blank + // Session created while adopting the Workspace remains hidden. + const sessionRow = ungroupedSection.locator('[role="treeitem"]').nth(1) await sessionRow.waitFor({ timeout: 10_000 }) await sessionRow.hover() // Card content: the full title plus the Idle status line (display-only diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index cc21210f3b..2c72632c2f 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -2015,6 +2015,16 @@ get(id: WorkspaceId): Workspace | undefined */ list(): Workspace[] +/** + * Delete one workspace registration while retaining its directory and every + * session log. The durable order is updated before the table deletion; a + * failed table write restores the prior order and keeps the entity + * published. Unknown ids are an idempotent no-op for domain callers. + * @param id - Workspace registration to remove. + * @returns `true` when a record was deleted, `false` when it was unknown. + */ +delete(id: WorkspaceId): Promise + /** * Resolve by canonical directory path without creating or mutating a * workspace. A missing path rejects during `realpath`; an existing unowned diff --git a/packages/client/connection/src/client/fixture.ts b/packages/client/connection/src/client/fixture.ts index eaab0a43f9..fcd04f2460 100644 --- a/packages/client/connection/src/client/fixture.ts +++ b/packages/client/connection/src/client/fixture.ts @@ -723,6 +723,20 @@ export function createFixtureApi(options: FixtureOptions = {}): ApiProxy { } return ok(request, { workspace: { ...workspace } }) }, + delete: (request) => { + const { workspaceId } = request.payload + const index = workspaces.findIndex(workspace => workspace.workspaceId === workspaceId) + if (index === -1) { + return err(request, { + code: 'workspace-not-found', + message: `no workspace ${workspaceId}`, + details: { workspaceId }, + }) + } + workspaces.splice(index, 1) + emitHost({ type: 'host/workspace-removed', workspaceId }) + return ok(request, { deleted: true as const }) + }, insertSessionBefore: (request) => { const { workspaceId, sessionId, beforeSessionId } = request.payload const workspace = workspaces.find(w => w.workspaceId === workspaceId) @@ -914,6 +928,7 @@ export class FixtureApiClient extends AbstractApiClient { case 'workspace.list': return this.api.workspace.list(request) case 'workspace.create': return this.api.workspace.create(request) case 'workspace.rename': return this.api.workspace.rename(request) + case 'workspace.delete': return this.api.workspace.delete(request) case 'workspace.insertSessionBefore': return this.api.workspace.insertSessionBefore(request) case 'command.list': return this.api.commands.list(request) // The in-memory execute never blocks, so a never-aborting signal is faithful here. diff --git a/packages/client/connection/tests/fake-api.ts b/packages/client/connection/tests/fake-api.ts index bf7295cc50..1c58e604ab 100644 --- a/packages/client/connection/tests/fake-api.ts +++ b/packages/client/connection/tests/fake-api.ts @@ -81,6 +81,7 @@ export class FakeApiClient implements IApiClient { rename: (payload: unknown) => this.record('workspace.rename', payload, Promise.resolve(ok({ workspace: { workspaceId: 'fk-ws' as never, path: '/f/ws', title: 'ws', sessionIds: [], createdAt: '0', updatedAt: '0' }, }))), + delete: (payload: unknown) => this.record('workspace.delete', payload, Promise.resolve(ok({ deleted: true as const }))), insertSessionBefore: (payload: unknown) => this.record('workspace.insertSessionBefore', payload, Promise.resolve(ok({ workspace: { workspaceId: 'fk-ws' as never, path: '/f/ws', title: 'ws', sessionIds: [], createdAt: '0', updatedAt: '0' }, }))), diff --git a/packages/client/connection/tests/fixture.spec.ts b/packages/client/connection/tests/fixture.spec.ts index 0374f92b3b..7200291229 100644 --- a/packages/client/connection/tests/fixture.spec.ts +++ b/packages/client/connection/tests/fixture.spec.ts @@ -365,6 +365,31 @@ describe('createFixtureApi', () => { expect(noop.result.value.workspace.updatedAt).toBe(before) }) + it('workspace.delete removes only the Workspace row and emits the removal frame', async () => { + const api = createFixtureApi() + const abort = new AbortController() + const seen: HostFrame[] = [] + const consuming = (async () => { + for await (const envelope of api.events.host(req({}), abort.signal)) { + seen.push(envelope.payload) + abort.abort() + } + })() + await new Promise(resolve => setTimeout(resolve, 10)) + const missing = await api.workspace.delete(req({ workspaceId: 'fx-ws-void' as WorkspaceId })) + expect(missing.result).toMatchObject({ ok: false, error: { code: 'workspace-not-found' } }) + const deleted = await api.workspace.delete(req({ workspaceId: 'fx-ws-fixture' as WorkspaceId })) + expect(deleted.result).toEqual({ ok: true, value: { deleted: true } }) + await consuming + expect(seen).toEqual([{ type: 'host/workspace-removed', workspaceId: 'fx-ws-fixture' }]) + const list = await api.workspace.list(req({})) + if (!list.result.ok) throw new Error('workspace list failed') + expect(list.result.value.items.some(workspace => workspace.workspaceId === 'fx-ws-fixture')).toBe(false) + const sessions = await api.sessions.list(req({})) + if (!sessions.result.ok) throw new Error('session list failed') + expect(sessions.result.value.items.map(session => session.sessionId)).toContain('fx-alpha') + }) + it('session.create({workspaceId}) lands on the account and unknown ids error', async () => { const api = createFixtureApi() const abort = new AbortController() diff --git a/packages/client/runtime/README.i18n.yaml b/packages/client/runtime/README.i18n.yaml index 5e73979b0b..bb4a2d4d2b 100644 --- a/packages/client/runtime/README.i18n.yaml +++ b/packages/client/runtime/README.i18n.yaml @@ -1,6 +1,6 @@ # Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each # 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 -README.md: 4724ebc75d441252245a0e811a4ae34f8b529a98 -README.zh.md: 6a0076742efccaf946910c77c77a9b74194b9dc5 +# pnpm run verify-translation-pairing --write packages/client/runtime/README.md +README.md: d2a10b3d97837ac859c52c206afab06913ea222e +README.zh.md: f23f8cb184242edbd6d19aeff5823f1efbee8eba diff --git a/packages/client/runtime/README.md b/packages/client/runtime/README.md index 4724ebc75d..d2a10b3d97 100644 --- a/packages/client/runtime/README.md +++ b/packages/client/runtime/README.md @@ -6,7 +6,9 @@ Client cordis boot and React-free object services: SlotsService wraps SlotCore a ## Workspace and Session lists -Workspace and Session lists have independent monotone `pending` → `ready` baseline phases and separate refresh activity/error state. Incremental frames arriving during a list request replay over its response. The first successful baseline establishes Host order; later refreshes update rows and membership without changing the relative order of identities already shown. Workspace recency is derived only after both baselines are ready and never changes Workspace list order. +Workspace and Session lists have independent monotone `pending` → `ready` baseline phases and separate refresh activity/error state. Incremental upsert/removal frames and unary mutation echoes arriving during a list request replay over its response. The first successful baseline establishes Host order; later refreshes update rows and membership without changing the relative order of identities already shown. Removed Workspace ids retain process-local tombstones so late changed frames cannot resurrect them; reconnect still takes `workspace.list` as the baseline. Workspace recency is derived only after both baselines are ready and never changes Workspace list order. + +`WorkspacesService.delete(workspaceId)` removes the registration from the client projection after the successful unary response; the matching `host/workspace-removed` frame is idempotent and synchronizes other tabs. Session state and the current Session selection are independent, so accounted Sessions immediately project under Ungrouped after their Workspace disappears. SlotsService gives the renderer separate bare observables for `useSessions` and `useWorkspaces`; web-react creates the hooks. Workspace business state does not enter `SessionListState` or an entry store. diff --git a/packages/client/runtime/README.zh.md b/packages/client/runtime/README.zh.md index 6a0076742e..f23f8cb184 100644 --- a/packages/client/runtime/README.zh.md +++ b/packages/client/runtime/README.zh.md @@ -6,7 +6,9 @@ ## Workspace 与 Session 列表 -Workspace 和 Session 列表各自具有单调的 `pending` → `ready` 基线阶段，也有各自的刷新活动／错误状态。列表请求期间到达的增量帧会在其响应之上回放。第一次成功的基线建立 Host 顺序；后续刷新更新行和成员关系，但不改变已经显示的标识之间的相对顺序。Workspace 新近程度只在两条基线都 ready 后派生，且绝不改变 Workspace 列表顺序。 +Workspace 和 Session 列表各自具有单调的 `pending` → `ready` 基线阶段，也有各自的刷新活动／错误状态。列表请求期间到达的增量更新／移除帧与一元变更回显会在其响应之上回放。第一次成功的基线建立 Host 顺序；后续刷新更新行和成员关系，但不改变已经显示的标识之间的相对顺序。已移除的 Workspace id 会保留进程本地删除标记，避免延迟到达的 changed 帧将其复活；重连仍以 `workspace.list` 作为基线。Workspace 新近程度只在两条基线都 ready 后派生，且绝不改变 Workspace 列表顺序。 + +`WorkspacesService.delete(workspaceId)` 在一元响应成功后从客户端投影中移除注册记录；对应的 `host/workspace-removed` 帧具有幂等性，并负责同步其他标签页。Session 状态与当前 Session selection 相互独立，因此 Workspace 消失后，其已记账的 Session 会立即投影到 Ungrouped 下。 SlotsService 分别为 renderer 提供 `useSessions` 与 `useWorkspaces` 的裸 observable；web-react 创建 hook。Workspace 业务状态不会进入 `SessionListState` 或配置项 store。 diff --git a/packages/client/runtime/src/client/workspaces/manager.ts b/packages/client/runtime/src/client/workspaces/manager.ts index e7caecfe82..83275e9a2a 100644 --- a/packages/client/runtime/src/client/workspaces/manager.ts +++ b/packages/client/runtime/src/client/workspaces/manager.ts @@ -19,6 +19,10 @@ export interface WorkspaceListSnapshot { error: RpcError | null } +type WorkspaceDelta = + | { type: 'upsert'; workspace: WorkspaceView } + | { type: 'remove'; workspaceId: WorkspaceId } + /** Workspace object cluster driven by one list baseline and changed-frame upserts. */ export class WorkspaceManager { private items: Workspace[] = [] @@ -28,7 +32,8 @@ export class WorkspaceManager { private phase: WorkspaceListPhase = 'pending' private error: RpcError | null = null private inflight: Promise | null = null - private refreshFrames: WorkspaceView[] | null = null + private refreshFrames: WorkspaceDelta[] | null = null + private readonly removedIds = new Set() private snapshotCache: WorkspaceListSnapshot private readonly notifier = new Notifier(() => { this.snapshotCache = this.buildSnapshot() @@ -51,7 +56,7 @@ export class WorkspaceManager { this.state = 'loading' this.error = null const established = this.itemViews() - const frames: WorkspaceView[] = [] + const frames: WorkspaceDelta[] = [] this.refreshFrames = frames this.notifier.markDirty() this.inflight = (async () => { @@ -61,7 +66,8 @@ export class WorkspaceManager { let items = this.phase === 'pending' ? result.value.items : mergeOrderedBaseline(established, result.value.items, workspace => workspace.workspaceId) - for (const workspace of frames) items = upsertWorkspace(items, workspace) + items = items.filter(workspace => !this.removedIds.has(workspace.workspaceId)) + for (const delta of frames) items = applyWorkspaceDelta(items, delta) this.installViews(items) this.state = 'idle' this.phase = 'ready' @@ -111,6 +117,18 @@ export class WorkspaceManager { return result } + /** + * Delete a Workspace registration and remove its local projection from the + * unary response without waiting for the Host frame. + * @param workspaceId - target workspace. + * @returns the wire result. + */ + async delete(workspaceId: WorkspaceId): Promise> { + const { result } = await this.api.workspace.delete({ workspaceId }) + if (result.ok) this.remove(workspaceId) + return result + } + /** * Move a session within its Workspace's manual order, then publish the * returned snapshot without waiting for the changed frame. @@ -139,6 +157,7 @@ export class WorkspaceManager { */ handleHostEnvelope(envelope: RpcRequest): void { if (envelope.payload.type === 'host/workspace-changed') this.upsert(envelope.payload.workspace) + else if (envelope.payload.type === 'host/workspace-removed') this.remove(envelope.payload.workspaceId) } /** Re-pull the baseline after each connection generation. */ @@ -175,7 +194,8 @@ export class WorkspaceManager { /** Upsert one Host view, optionally retaining the local object that materialized it. */ private upsert(view: WorkspaceView, identity?: Workspace): void { - this.refreshFrames?.push(view) + if (this.removedIds.has(view.workspaceId)) return + this.refreshFrames?.push({ type: 'upsert', workspace: view }) const index = this.items.findIndex(item => item.getSnapshot().view?.workspaceId === view.workspaceId) // Mutation responses and changed frames race (two carriers, no ordering): // reject a snapshot strictly older than the installed projection so a @@ -195,6 +215,17 @@ export class WorkspaceManager { this.notifier.markDirty() } + /** Remove one id idempotently and retain a tombstone against late echoes. */ + private remove(workspaceId: WorkspaceId): void { + this.refreshFrames?.push({ type: 'remove', workspaceId }) + this.removedIds.add(workspaceId) + const items = this.items.filter(item => + item.getSnapshot().view?.workspaceId !== workspaceId) + if (items.length === this.items.length) return + this.items = items + this.notifier.markDirty() + } + private installViews(views: readonly WorkspaceView[]): void { const existing = new Map( this.items.flatMap((workspace) => { @@ -234,3 +265,10 @@ function upsertWorkspace(items: readonly WorkspaceView[], workspace: WorkspaceVi ? [workspace, ...items] : items.map((item, position) => position === index ? workspace : item) } + + +function applyWorkspaceDelta(items: readonly WorkspaceView[], delta: WorkspaceDelta): WorkspaceView[] { + return delta.type === 'upsert' + ? upsertWorkspace(items, delta.workspace) + : items.filter(workspace => workspace.workspaceId !== delta.workspaceId) +} diff --git a/packages/client/runtime/src/client/workspaces/service.ts b/packages/client/runtime/src/client/workspaces/service.ts index 1e281ca792..4cb26aa220 100644 --- a/packages/client/runtime/src/client/workspaces/service.ts +++ b/packages/client/runtime/src/client/workspaces/service.ts @@ -174,6 +174,16 @@ export class WorkspacesService { return result.value.workspace } + /** + * Delete one Workspace registration. Sessions, session logs, and the + * directory remain Host-owned outside this operation. + * @param workspaceId - target workspace. + */ + async delete(workspaceId: WorkspaceId): Promise { + const result = await this.manager.delete(workspaceId) + if (!result.ok) throw new Error(`workspace delete failed: ${result.error.code}: ${result.error.message}`) + } + /** * Move a session within its Workspace's manual order (DOM-insertBefore-like). * @param workspaceId - owning workspace. diff --git a/packages/client/runtime/tests/fake-api.ts b/packages/client/runtime/tests/fake-api.ts index dcb334f6ea..9f6147cdd3 100644 --- a/packages/client/runtime/tests/fake-api.ts +++ b/packages/client/runtime/tests/fake-api.ts @@ -96,6 +96,9 @@ export class FakeApiClient implements IApiClient { onWorkspaceRename: (payload: unknown) => Promise> = () => Promise.resolve(ok({ workspace: fakeWorkspace('fk-ws') })) + onWorkspaceDelete: (payload: unknown) => Promise> = + () => Promise.resolve(ok({ deleted: true })) + onWorkspaceInsertSessionBefore: (payload: unknown) => Promise> = () => Promise.resolve(ok({ workspace: fakeWorkspace('fk-ws') })) @@ -103,6 +106,7 @@ export class FakeApiClient implements IApiClient { list: (payload: unknown) => this.record('workspace.list', payload, this.onWorkspaceList(payload)), create: (payload: unknown) => this.record('workspace.create', payload, this.onWorkspaceCreate(payload)), rename: (payload: unknown) => this.record('workspace.rename', payload, this.onWorkspaceRename(payload)), + delete: (payload: unknown) => this.record('workspace.delete', payload, this.onWorkspaceDelete(payload)), insertSessionBefore: (payload: unknown) => this.record('workspace.insertSessionBefore', payload, this.onWorkspaceInsertSessionBefore(payload)), } diff --git a/packages/client/runtime/tests/workspaces-service.spec.ts b/packages/client/runtime/tests/workspaces-service.spec.ts index d020b74fec..210c04d896 100644 --- a/packages/client/runtime/tests/workspaces-service.spec.ts +++ b/packages/client/runtime/tests/workspaces-service.spec.ts @@ -76,6 +76,48 @@ describe('WorkspaceManager', () => { ok: false, error: { code: 'internal', message: 'create transport' }, }) }) + + it('replays removal over an in-flight baseline and ignores duplicate or late updates', async () => { + const api = new FakeApiClient() + const gate = deferred>>() + api.onWorkspaceList = () => gate.promise + const manager = new WorkspaceManager(api) + const hydration = manager.refresh() + manager.handleHostEnvelope({ + rpcId: 'removed' as never, + payload: { type: 'host/workspace-removed', workspaceId: wid('gone') }, + }) + gate.resolve(ok({ items: [workspace('gone'), workspace('kept')] as never[] })) + await hydration + expect(manager.getSnapshot().items.map(item => item.workspaceId)).toEqual(['kept']) + + manager.handleHostEnvelope({ + rpcId: 'late-change' as never, + payload: { type: 'host/workspace-changed', workspace: workspace('gone') }, + }) + manager.handleHostEnvelope({ + rpcId: 'duplicate-remove' as never, + payload: { type: 'host/workspace-removed', workspaceId: wid('gone') }, + }) + expect(manager.getSnapshot().items.map(item => item.workspaceId)).toEqual(['kept']) + }) + + it('removes from the unary delete echo while a refresh is in flight', async () => { + const api = new FakeApiClient() + api.onWorkspaceList = () => Promise.resolve(ok({ items: [workspace('gone')] as never[] })) + const manager = new WorkspaceManager(api) + await manager.refresh() + const gate = deferred>>() + api.onWorkspaceList = () => gate.promise + const refresh = manager.refresh() + + await expect(manager.delete(wid('gone'))).resolves.toMatchObject({ ok: true }) + expect(api.callsOf('workspace.delete')).toEqual([{ workspaceId: 'gone' }]) + expect(manager.getSnapshot().items).toEqual([]) + gate.resolve(ok({ items: [workspace('gone')] as never[] })) + await refresh + expect(manager.getSnapshot().items).toEqual([]) + }) }) describe('WorkspacesService', () => { @@ -175,4 +217,20 @@ describe('WorkspacesService', () => { })) await expect(workspaces.create({ path: '/missing' })).rejects.toThrow(/workspace-invalid-path: missing/) }) + + it('deletes a Workspace or preserves it when the Host rejects deletion', async () => { + const ctx = new Context() + const api = new FakeApiClient() + const sessions = new SessionsService(ctx, api) + const workspaces = new WorkspacesService(ctx, api, sessions) + api.onWorkspaceList = () => Promise.resolve(ok({ items: [workspace('alpha')] as never[] })) + await workspaces.refresh() + await expect(workspaces.delete(wid('alpha'))).resolves.toBeUndefined() + expect(workspaces.list.getSnapshot().items).toEqual([]) + + api.onWorkspaceDelete = () => Promise.resolve(err({ + code: 'workspace-not-found', message: 'gone', details: { workspaceId: 'ghost' }, + })) + await expect(workspaces.delete(wid('ghost'))).rejects.toThrow(/workspace-not-found: gone/) + }) }) diff --git a/packages/client/ui-workspace/README.i18n.yaml b/packages/client/ui-workspace/README.i18n.yaml index d0f2d0a20a..88638b9e35 100644 --- a/packages/client/ui-workspace/README.i18n.yaml +++ b/packages/client/ui-workspace/README.i18n.yaml @@ -1,6 +1,6 @@ # Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each # 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 -README.md: e0247b3e26f617f86e9c0094afa1cbc920f02d33 -README.zh.md: 92ef463faab4b1ccda85d7f3cec1678a338d4010 +# pnpm run verify-translation-pairing --write packages/client/ui-workspace/README.md +README.md: b5a78c30ddae5e12612bb8cced65b5fe95f7e259 +README.zh.md: 904543a48f1609e23ba80cf240be965d0654a951 diff --git a/packages/client/ui-workspace/README.md b/packages/client/ui-workspace/README.md index e0247b3e26..b5a78c30dd 100644 --- a/packages/client/ui-workspace/README.md +++ b/packages/client/ui-workspace/README.md @@ -4,7 +4,7 @@ English | [中文](README.zh.md) Shared Workspace picker plugin. `WorkspacePicker` is registered into the sidebar's `sidebar.workspace` slot and the page-local Session Intent hero's `conversation.empty.workspace` slot, so both surfaces use the same menu and creation modals. -The picker lists real Host Workspace entities through the global `useWorkspaces` hook. Selecting a Workspace invokes the slot owner's `onPick` callback to retarget the frontend Session object; the existing-folder and create-new actions first create a real Workspace through the object layer, then select it. Create-new disables names already present in that list, while the Host remains authoritative for concurrent or non-UI callers. The runtime Session and Workspace services own materialization. +The picker lists real Host Workspace entities through the global `useWorkspaces` hook. Selecting a Workspace invokes the slot owner's `onPick` callback to retarget the frontend Session object; the existing-folder and create-new actions first create a real Workspace through the object layer, then select it. Create-new disables names already present in that list, while the Host remains authoritative for concurrent or non-UI callers. The runtime Session and Workspace services own materialization. The Workspace row's Delete action opens a confirmation that states the retention boundary, blocks duplicate submission, and keeps failures open; success removes the group while its Sessions remain under Ungrouped. Both target slots are declared by other plugins, so `apply` registers through declaration-aware deferral and re-registers after a declaring slot is restored. @@ -18,5 +18,5 @@ None; this package neither assembles nor sends a provider request. ## Known Limitations and Deferred Work -- **No Workspace rename/delete controls** — the picker supports selection and creation only. +- **No Session deletion control** — the existing Session menu row remains visual-only; Workspace registration deletion does not delete Sessions. - **Existing-folder entry is manual path input only** — Host creation failures are shown in the modal. diff --git a/packages/client/ui-workspace/README.zh.md b/packages/client/ui-workspace/README.zh.md index 92ef463faa..904543a48f 100644 --- a/packages/client/ui-workspace/README.zh.md +++ b/packages/client/ui-workspace/README.zh.md @@ -4,7 +4,7 @@ 共享 Workspace 选择器插件。`WorkspacePicker` 注册到侧边栏的 `sidebar.workspace` slot，以及页面局部 Session Intent 主视觉区的 `conversation.empty.workspace` slot，因此两个表层使用同一菜单和创建模态框。 -该选择器通过全局 `useWorkspaces` hook 列出真实的 Host Workspace 实体。选择 Workspace 会调用 slot owner 的 `onPick` 回调，重新定位前端 Session 对象；使用现有文件夹和新建操作时，系统会先通过对象层创建真实 Workspace，再将其选中。新建操作会禁用列表中已有的名称，而 Host 对并发或非 UI 调用方仍具有最终决定权。运行时 Session 与 Workspace 服务负责物化。 +该选择器通过全局 `useWorkspaces` hook 列出真实的 Host Workspace 实体。选择 Workspace 会调用 slot owner 的 `onPick` 回调，重新定位前端 Session 对象；使用现有文件夹和新建操作时，系统会先通过对象层创建真实 Workspace，再将其选中。新建操作会禁用列表中已有的名称，而 Host 对并发或非 UI 调用方仍具有最终决定权。运行时 Session 与 Workspace 服务负责物化。Workspace 行内的 Delete 操作会打开确认框，说明保留边界、阻止重复提交，并在失败时保持打开；成功后，该分组会被移除，其 Session 则留在 Ungrouped 下。 两个目标 slot 都由其他插件声明，因此 `apply` 通过声明感知的延迟机制完成注册，并在声明该 slot 的插件恢复后重新注册。 @@ -18,5 +18,5 @@ ## 已知限制与暂缓事项 -- **没有 Workspace 重命名／删除控件**：选择器仅支持选择和创建。 +- **没有 Session 删除控件**：现有 Session 菜单行仍仅提供视觉效果；删除 Workspace 注册记录不会删除 Session。 - **现有文件夹入口仅支持手动输入路径**：Host 创建失败会显示在模态框中。 diff --git a/packages/client/ui-workspace/src/client/WorkspaceBrowser.module.css b/packages/client/ui-workspace/src/client/WorkspaceBrowser.module.css index d6375cb698..c03d511c92 100644 --- a/packages/client/ui-workspace/src/client/WorkspaceBrowser.module.css +++ b/packages/client/ui-workspace/src/client/WorkspaceBrowser.module.css @@ -258,6 +258,16 @@ color: var(--dsw-alias-state-error-primary); } +.deleteAction:not(:disabled) { + color: var(--dsw-alias-state-error-primary); +} + +.deleteStatus { + font-size: 12px; + line-height: 18px; + color: var(--dsw-alias-label-secondary); +} + @media (prefers-reduced-motion: reduce) { .wide { animation: none; diff --git a/packages/client/ui-workspace/src/client/WorkspaceBrowser.tsx b/packages/client/ui-workspace/src/client/WorkspaceBrowser.tsx index 0dc6485929..0090164928 100644 --- a/packages/client/ui-workspace/src/client/WorkspaceBrowser.tsx +++ b/packages/client/ui-workspace/src/client/WorkspaceBrowser.tsx @@ -87,10 +87,15 @@ type SessionTreeProps = Pick< query: string /** Open the browser-owned rename dialog for a real Workspace group. */ onRenameRequest: (workspaceId: WorkspaceId, currentTitle: string) => void + /** Open the browser-owned delete-confirmation dialog for a real Workspace group. */ + onDeleteRequest: (workspaceId: WorkspaceId, currentTitle: string) => void } /** The scrolling session tree; unmounting at collapse settle drops the sessions subscription and expansion state. */ -function SessionTree({ useSessions, startSession, open, workspaces, query, onRenameRequest, insertSessionBefore }: SessionTreeProps) { +function SessionTree({ + useSessions, startSession, open, workspaces, query, + onRenameRequest, onDeleteRequest, insertSessionBefore, +}: SessionTreeProps) { const list = useSessions((s) => s) const current = list.current const [expandedProjects, setExpandedProjects] = useState([]) @@ -128,11 +133,17 @@ function SessionTree({ useSessions, startSession, open, workspaces, query, onRen onCreate={() => { if (group.workspaceId !== undefined) startSession(group.workspaceId) }} - onRename={group.workspaceId === undefined + actions={group.workspaceId === undefined ? undefined - : () => { - /* v8 ignore next -- narrowing guard: the closure is only created for real-workspace groups. */ - if (group.workspaceId !== undefined) onRenameRequest(group.workspaceId, group.label) + : { + rename: () => { + /* v8 ignore next -- narrowing guard: the actions object exists only for real-workspace groups. */ + if (group.workspaceId !== undefined) onRenameRequest(group.workspaceId, group.label) + }, + delete: () => { + /* v8 ignore next -- narrowing guard: the actions object exists only for real-workspace groups. */ + if (group.workspaceId !== undefined) onDeleteRequest(group.workspaceId, group.label) + }, }} /> {group.sessions.map((node, index) => { @@ -236,6 +247,7 @@ export function WorkspaceBrowser({ startSession, open, renameWorkspace, + deleteWorkspace, insertSessionBefore, createWorkspace, }: WorkspaceBrowserProps) { @@ -291,6 +303,30 @@ export function WorkspaceBrowser({ }) } + // Delete dialog is separate from the row so a successful removal can + // unmount that row without tearing down the in-flight confirmation state. + const [deleteTarget, setDeleteTarget] = useState<{ workspaceId: WorkspaceId; title: string } | null>(null) + const [deleting, setDeleting] = useState(false) + const [deleteError, setDeleteError] = useState(null) + const closeDelete = () => { + if (deleting) return + setDeleteTarget(null) + setDeleteError(null) + } + const confirmDelete = () => { + /* v8 ignore next -- the Modal is absent without a target and its button is disabled while deleting. */ + if (deleting || deleteTarget === null) return + setDeleting(true) + setDeleteError(null) + deleteWorkspace(deleteTarget.workspaceId).then(() => { + setDeleting(false) + setDeleteTarget(null) + }).catch((reason: unknown) => { + setDeleting(false) + setDeleteError(reason instanceof Error ? reason.message : String(reason)) + }) + } + return (
    @@ -382,6 +418,10 @@ export function WorkspaceBrowser({ setRenameDraft(currentTitle) setRenameError(null) }} + onDeleteRequest={(workspaceId, title) => { + setDeleteTarget({ workspaceId, title }) + setDeleteError(null) + }} /> ))}
    @@ -416,6 +456,30 @@ export function WorkspaceBrowser({ )} {renameError !== null &&
    {renameError}
    } + + + + + )} + > + {deleting &&
    Deleting workspace…
    } + {deleteError !== null &&
    {deleteError}
    } +
    ) } diff --git a/packages/client/ui-workspace/src/client/contract/slots.ts b/packages/client/ui-workspace/src/client/contract/slots.ts index 6008da553f..2e4c88dd6b 100644 --- a/packages/client/ui-workspace/src/client/contract/slots.ts +++ b/packages/client/ui-workspace/src/client/contract/slots.ts @@ -32,6 +32,8 @@ export type WorkspaceBrowserInjected = { open: (sessionId: SessionId) => void /** Rename a Host Workspace (rejects on name conflict; resolves on durability). */ renameWorkspace: (workspaceId: WorkspaceId, title: string) => Promise + /** Delete only a Host Workspace registration; directory and Session logs remain. */ + deleteWorkspace: (workspaceId: WorkspaceId) => Promise /** * Reorder a session inside its Workspace account (DOM-insertBefore * semantics: omitted anchor appends to the end). The view refreshes from diff --git a/packages/client/ui-workspace/src/client/index.ts b/packages/client/ui-workspace/src/client/index.ts index a444464441..98adfecce3 100644 --- a/packages/client/ui-workspace/src/client/index.ts +++ b/packages/client/ui-workspace/src/client/index.ts @@ -39,6 +39,7 @@ export function apply(ctx: ClientContext): void { startSession: (workspaceId) => { ctx.workspaces.startSession(workspaceId) }, open: (sessionId) => { ctx.sessions.open(sessionId) }, renameWorkspace: async (workspaceId, title) => { await ctx.workspaces.rename(workspaceId, title) }, + deleteWorkspace: async (workspaceId) => { await ctx.workspaces.delete(workspaceId) }, insertSessionBefore: async (workspaceId, sessionId, beforeSessionId) => { await ctx.workspaces.insertSessionBefore(workspaceId, sessionId, beforeSessionId) }, diff --git a/packages/client/ui-workspace/src/client/rows/Rows.tsx b/packages/client/ui-workspace/src/client/rows/Rows.tsx index a100da83e9..ae866f58cf 100644 --- a/packages/client/ui-workspace/src/client/rows/Rows.tsx +++ b/packages/client/ui-workspace/src/client/rows/Rows.tsx @@ -3,7 +3,7 @@ * all data and callbacks arrive via props. Hover swaps (folder->chevron, * time->ellipsis, action buttons) are CSS-only. Row ... menus are visual-only * except workspace Rename; the session hover card is suppressed while a menu - * is open. + * is open. Workspace Rename/Delete are wired; session actions remain visual-only. */ import { useState } from 'react' import clsx from 'clsx' @@ -39,12 +39,12 @@ const WORKSPACE_MENU_ITEMS = [ * @param props.onCreate - start a frontend Session inside this Workspace. * @returns the row element. */ -export function ProjectRowItem({ group, onToggle, onCreate, onRename }: { +export function ProjectRowItem({ group, onToggle, onCreate, actions }: { group: GroupNode onToggle: () => void onCreate: () => void - /** Open the rename dialog; absent for the ungrouped bucket (no menu shown). */ - onRename?: (() => void) | undefined + /** Real-Workspace actions; absent for the ungrouped bucket (no menu shown). */ + actions?: { rename: () => void; delete: () => void } | undefined }) { const row = group const active = group.expanded && group.containsCurrent @@ -68,15 +68,15 @@ export function ProjectRowItem({ group, onToggle, onCreate, onRename }: { {count} - {onRename !== undefined && ( + {actions !== undefined && ( { setMenuOpen(false) }} items={WORKSPACE_MENU_ITEMS} onSelect={(id) => { setMenuOpen(false) - if (id === 'rename') onRename() - // Delete is visual-only for now. + if (id === 'rename') actions.rename() + else actions.delete() }} portal closeOnPointerLeave diff --git a/packages/client/ui-workspace/tests/rows.spec.tsx b/packages/client/ui-workspace/tests/rows.spec.tsx index 70cfb36940..6ccd923793 100644 --- a/packages/client/ui-workspace/tests/rows.spec.tsx +++ b/packages/client/ui-workspace/tests/rows.spec.tsx @@ -98,12 +98,16 @@ describe('workspace browser rows', () => { it('workspace row menu opens on the ellipsis, renames, and shows the danger delete row', () => { const onRename = vi.fn() + const onDelete = vi.fn() const onToggle = vi.fn() const group: GroupNode = { key: 'project', workspaceId: wid('project'), cwd: '/projects/project', label: 'Project', sessionCount: 0, expanded: false, containsCurrent: false, sessions: [], } - render() + render() fireEvent.click(screen.getByRole('button', { name: 'Workspace actions for Project' })) // Opening the menu neither toggles the group nor renames yet. expect(onToggle).not.toHaveBeenCalled() @@ -111,11 +115,11 @@ describe('workspace browser rows', () => { fireEvent.click(screen.getByRole('menuitem', { name: 'Rename' })) expect(onRename).toHaveBeenCalledOnce() expect(screen.queryByRole('menu')).toBeNull() - // Delete stays visual-only: selecting it just closes the menu. fireEvent.click(screen.getByRole('button', { name: 'Workspace actions for Project' })) fireEvent.click(screen.getByRole('menuitem', { name: 'Delete workspace' })) expect(screen.queryByRole('menu')).toBeNull() expect(onRename).toHaveBeenCalledOnce() + expect(onDelete).toHaveBeenCalledOnce() // Escape closes without selecting (Menu onClose path). fireEvent.click(screen.getByRole('button', { name: 'Workspace actions for Project' })) fireEvent.keyDown(document, { key: 'Escape' }) diff --git a/packages/client/ui-workspace/tests/workspace-browser.spec.tsx b/packages/client/ui-workspace/tests/workspace-browser.spec.tsx index e9b55e7b76..1dbe895b74 100644 --- a/packages/client/ui-workspace/tests/workspace-browser.spec.tsx +++ b/packages/client/ui-workspace/tests/workspace-browser.spec.tsx @@ -54,6 +54,7 @@ function mount(overrides: Partial = {}) { startSession: vi.fn(), open: vi.fn(), renameWorkspace: vi.fn(async () => {}), + deleteWorkspace: vi.fn(async () => {}), insertSessionBefore: vi.fn(async () => {}), createWorkspace: vi.fn(async () => workspace('created', [])), ...overrides, @@ -457,6 +458,74 @@ describe('WorkspaceBrowser', () => { await waitFor(() => { expect(screen.getByRole('alert').textContent).toBe('denied') }) }) + it('confirms Workspace deletion, explains retention, and blocks duplicate submission', async () => { + let resolveDelete!: () => void + const deleteWorkspace = vi.fn(() => new Promise((resolve) => { resolveDelete = resolve })) + mount({ + useWorkspaces: hook(workspaceState([workspace('alpha', ['session'], 'Alpha')])), + deleteWorkspace, + }) + fireEvent.click(screen.getByRole('button', { name: 'Workspace actions for Alpha' })) + fireEvent.click(screen.getByRole('menuitem', { name: 'Delete workspace' })) + const dialog = screen.getByRole('dialog', { name: 'Delete workspace' }) + expect(dialog.textContent).toContain('removes “Alpha” from the workspace list') + expect(dialog.textContent).toContain('folder and session logs will be kept') + expect(dialog.textContent).toContain('sessions will appear under Ungrouped') + + const confirm = screen.getByRole('button', { name: 'Delete workspace' }) as HTMLButtonElement + fireEvent.click(confirm) + fireEvent.click(confirm) + expect(deleteWorkspace).toHaveBeenCalledOnce() + expect(deleteWorkspace).toHaveBeenCalledWith(wid('alpha')) + expect(confirm.disabled).toBe(true) + expect((screen.getByRole('button', { name: 'Cancel' }) as HTMLButtonElement).disabled).toBe(true) + expect(screen.getByRole('status').textContent).toBe('Deleting workspace…') + fireEvent.keyDown(document, { key: 'Escape' }) + fireEvent.click(screen.getByRole('button', { name: 'Close' })) + expect(screen.getByRole('dialog', { name: 'Delete workspace' })).toBeTruthy() + await act(async () => { resolveDelete() }) + expect(screen.queryByRole('dialog', { name: 'Delete workspace' })).toBeNull() + }) + + it('keeps the delete dialog open on failure and allows retry or cancellation', async () => { + const deleteWorkspace = vi.fn() + .mockRejectedValueOnce(new Error('storage unavailable')) + .mockRejectedValueOnce('denied') + mount({ + useWorkspaces: hook(workspaceState([workspace('alpha', [], 'Alpha')])), + deleteWorkspace, + }) + fireEvent.click(screen.getByRole('button', { name: 'Workspace actions for Alpha' })) + fireEvent.click(screen.getByRole('menuitem', { name: 'Delete workspace' })) + fireEvent.click(screen.getByRole('button', { name: 'Delete workspace' })) + await waitFor(() => { expect(screen.getByRole('alert').textContent).toBe('storage unavailable') }) + expect(screen.getByRole('dialog', { name: 'Delete workspace' })).toBeTruthy() + fireEvent.click(screen.getByRole('button', { name: 'Delete workspace' })) + await waitFor(() => { expect(screen.getByRole('alert').textContent).toBe('denied') }) + fireEvent.click(screen.getByRole('button', { name: 'Cancel' })) + expect(screen.queryByRole('dialog', { name: 'Delete workspace' })).toBeNull() + }) + + it('Cancel, Escape, and Close dismiss deletion without calling the action', () => { + const deleteWorkspace = vi.fn(async () => {}) + mount({ + useWorkspaces: hook(workspaceState([workspace('alpha', [], 'Alpha')])), + deleteWorkspace, + }) + const open = () => { + fireEvent.click(screen.getByRole('button', { name: 'Workspace actions for Alpha' })) + fireEvent.click(screen.getByRole('menuitem', { name: 'Delete workspace' })) + } + open() + fireEvent.click(screen.getByRole('button', { name: 'Cancel' })) + open() + fireEvent.keyDown(document, { key: 'Escape' }) + open() + fireEvent.click(screen.getByRole('button', { name: 'Close' })) + expect(deleteWorkspace).not.toHaveBeenCalled() + expect(screen.queryByRole('dialog', { name: 'Delete workspace' })).toBeNull() + }) + it('search hides drag affordances (rows are not draggable during search)', () => { const sessions = sessionState([summary('needle-a', 2, { displayTitle: 'Needle A' })]) mount({ diff --git a/packages/cordis/tool-cordis/src/api-catalog.ts b/packages/cordis/tool-cordis/src/api-catalog.ts index 224e8300ab..f33722a1fc 100644 --- a/packages/cordis/tool-cordis/src/api-catalog.ts +++ b/packages/cordis/tool-cordis/src/api-catalog.ts @@ -942,6 +942,10 @@ export const SERVICE_API: readonly ServiceApiEntry[] = [ signature: 'list(): Workspace[]', jsDoc: '/**\n * Synchronous workspace projection in durable registry order. Every\n * entity\'s `sessionIds` getter is already filtered by the startup/live\n * canonical-cwd header index; this method performs no persistence reads.\n * @returns a fresh ordered array of workspace entities.\n */', }, + { + signature: 'delete(id: WorkspaceId): Promise', + jsDoc: '/**\n * Delete one workspace registration while retaining its directory and every\n * session log. The durable order is updated before the table deletion; a\n * failed table write restores the prior order and keeps the entity\n * published. Unknown ids are an idempotent no-op for domain callers.\n * @param id - Workspace registration to remove.\n * @returns `true` when a record was deleted, `false` when it was unknown.\n */', + }, { signature: 'async resolveByPath(path: string): Promise', jsDoc: '/**\n * Resolve by canonical directory path without creating or mutating a\n * workspace. A missing path rejects during `realpath`; an existing unowned\n * directory returns `undefined`.\n * @param path - Existing directory path in any spelling.\n * @returns the workspace owning the canonical path, when one exists.\n */', diff --git a/packages/host/apiproxy/README.i18n.yaml b/packages/host/apiproxy/README.i18n.yaml index eb06e14d2d..653906ba08 100644 --- a/packages/host/apiproxy/README.i18n.yaml +++ b/packages/host/apiproxy/README.i18n.yaml @@ -1,6 +1,6 @@ # Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each # 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 -README.md: 43ad70fa8b865b0b80496bbb67013f24e9e3a33f -README.zh.md: cc95a7512fb872add816bf0456a93dfcf7b84c10 +# pnpm run verify-translation-pairing --write packages/host/apiproxy/README.md +README.md: dc29abdc10f536463358db92a7ac25c1579f2a50 +README.zh.md: a69d51de086dfbc692dccf3f5f88ce7e36c74e9c diff --git a/packages/host/apiproxy/README.md b/packages/host/apiproxy/README.md index 43ad70fa8b..dc29abdc10 100644 --- a/packages/host/apiproxy/README.md +++ b/packages/host/apiproxy/README.md @@ -12,7 +12,7 @@ The layering/protocol decisions are recorded in the [GUI layering and RPC protoc The mux stream projects the latest log-backed title as a validated `session/title` control frame after each attached-session subscription baseline and immediately after the corresponding live raw title event. This projection does not add titles to `session.list`; cold sessions remain metadata-only there until opening or resuming attaches their logs. -Workspace and Session lists are separate reconnect baselines. `workspace.create` creates a unique name or adopts an existing directory, `session.create` accepts an optional preallocated Session id, and `host/workspace-changed` plus `host/session-added` carry committed increments in either arrival order. `SessionSummary.blank` and the `host/session-added` frame carry the derived zero-events bit: clients hide blank sessions and reuse them per workspace, flip blank on the first `host/session-status(running:true)`, and treat `session.list` as the reconnect authority; cold summaries are never blank because lazy persistence keeps never-appended sessions out of `list()`. +Workspace and Session lists are separate reconnect baselines. `workspace.create` creates a unique name or adopts an existing directory, `workspace.delete` removes only the Workspace registration, `session.create` accepts an optional preallocated Session id, and `host/workspace-changed`, `host/workspace-removed`, plus `host/session-added` carry committed increments in either arrival order. Registration deletion preserves the directory and session logs; its Sessions remain in `session.list` and become Ungrouped. `SessionSummary.blank` and the `host/session-added` frame carry the derived zero-events bit: clients hide blank sessions and reuse them per workspace, flip blank on the first `host/session-status(running:true)`, and treat `session.list` as the reconnect authority; cold summaries are never blank because lazy persistence keeps never-appended sessions out of `list()`. The `command.*` and `skill.*` domains expose the host command registry and skill catalog to clients. Every method addresses one session's agent by `sessionId` (a served session always has an Agent; `command.*` resumes cold sessions through the same path as `session.*`, while `skill.list` resolves the project root from the session header without touching the Agent registry). `command.execute` runs a slash-command line host-side and returns a detached result; the carrier's request signal cancels the running handler. `host/commands-changed` is the catalog invalidation frame: clients refetch `command.list` instead of diffing. diff --git a/packages/host/apiproxy/README.zh.md b/packages/host/apiproxy/README.zh.md index cc95a7512f..a69d51de08 100644 --- a/packages/host/apiproxy/README.zh.md +++ b/packages/host/apiproxy/README.zh.md @@ -12,7 +12,7 @@ mux 流会在每个已附加会话的订阅基线之后，以及对应的实时原始标题事件之后，立即把基于日志的最新标题投影为经过校验的 `session/title` 控制帧。该投影不会把标题加入 `session.list`；冷会话在其中仍只有元数据，直到打开或恢复操作附加其日志。 -Workspace 列表与 Session 列表是相互独立的重连基线。`workspace.create` 会创建唯一名称或接纳现有目录，`session.create` 接受可选的预分配 Session id，`host/workspace-changed` 与 `host/session-added` 则以任意到达顺序携带已提交的增量。`SessionSummary.blank` 与 `host/session-added` 帧携带派生的零事件位：客户端隐藏空白会话并按 workspace 复用它们，在首个 `host/session-status(running:true)` 时翻转 blank，并以 `session.list` 作为重连权威；冷会话摘要永远不是空白——惰性持久化让从未追加过事件的会话根本不出现在 `list()` 中。 +Workspace 列表与 Session 列表是相互独立的重连基线。`workspace.create` 会创建唯一名称或接纳现有目录，`workspace.delete` 只移除 Workspace 注册记录，`session.create` 接受可选的预分配 Session id，`host/workspace-changed`、`host/workspace-removed` 与 `host/session-added` 则以任意到达顺序携带已提交的增量。删除注册记录会保留目录和会话日志；相关 Session 仍留在 `session.list` 中，并进入 Ungrouped。`SessionSummary.blank` 与 `host/session-added` 帧携带派生的零事件位：客户端隐藏空白会话并按 workspace 复用它们，在首个 `host/session-status(running:true)` 时翻转 blank，并以 `session.list` 作为重连权威；冷会话摘要永远不是空白：惰性持久化让从未追加过事件的会话根本不出现在 `list()` 中。 `command.*` 与 `skill.*` 领域向客户端暴露宿主命令注册表和技能目录。每个方法都通过 `sessionId` 寻址一个会话的 Agent（被服务的会话必有 Agent；`command.*` 经由与 `session.*` 相同的路径恢复冷会话，而 `skill.list` 从会话头解析项目根目录，不触碰 Agent 注册表）。`command.execute` 在宿主侧运行一条斜杠命令行并返回脱耦结果；载体的请求信号可取消正在运行的处理器。`host/commands-changed` 是目录失效帧：客户端重新拉取 `command.list` 而不是做差分。 diff --git a/packages/host/apiproxy/src/api-proxy.ts b/packages/host/apiproxy/src/api-proxy.ts index f81f5c9be8..34e67edef9 100644 --- a/packages/host/apiproxy/src/api-proxy.ts +++ b/packages/host/apiproxy/src/api-proxy.ts @@ -764,6 +764,15 @@ export function createApiProxy(ctx: Context, defaults: ApiProxyDefaults): ApiPro return ok(request, { workspace: workspaceView(workspace) }) }, + async delete(request) { + const { workspaceId } = request.payload + const operation = workspaceCreationChain.then(() => + ctx.workspace.delete(brandWorkspaceId(workspaceId))) + workspaceCreationChain = operation.then(() => undefined, () => undefined) + if (!await operation) return workspaceNotFound(request, workspaceId) + return ok(request, { deleted: true as const }) + }, + async insertSessionBefore(request) { const { payload } = request const workspace = ctx.workspace.get(brandWorkspaceId(payload.workspaceId)) @@ -977,8 +986,9 @@ export function createApiProxy(ctx: Context, defaults: ApiProxyDefaults): ApiPro queue.push(frame({ type: 'host/agent-error', sessionId: agent.id, message: String(error) })) }), ctx.on('domain/changed', (change) => { - if (change.domain !== 'workspace' || change.operation !== 'put') return + if (change.domain !== 'workspace') return if (change.table === '') { + if (change.operation !== 'put') return const state = workspaceDomainState.parse(change.value) for (const workspaceId of state.workspaceIds) { if (committedWorkspaceIds.has(workspaceId)) continue @@ -991,7 +1001,16 @@ export function createApiProxy(ctx: Context, defaults: ApiProxyDefaults): ApiPro } return } - if (change.table !== 'workspaces' || !committedWorkspaceIds.has(change.key)) return + if (change.table !== 'workspaces') return + if (change.operation === 'deleted') { + if (!committedWorkspaceIds.delete(change.key)) return + queue.push(frame({ + type: 'host/workspace-removed', + workspaceId: change.key as WorkspaceId, + })) + return + } + if (!committedWorkspaceIds.has(change.key)) return // Existing-entity table writes are complete attach/touch commits. // A new entity's first put waits for the global registry write above. queue.push(frame({ diff --git a/packages/host/apiproxy/src/api/events.schema.ts b/packages/host/apiproxy/src/api/events.schema.ts index e95b371c54..973db5a91e 100644 --- a/packages/host/apiproxy/src/api/events.schema.ts +++ b/packages/host/apiproxy/src/api/events.schema.ts @@ -11,7 +11,7 @@ import type { Wire } from './rpc.schema.ts' import { rpcErrorSchema, rpcIdSchema } from './rpc.schema.ts' import { approvalRequestIdSchema } from './approvals.schema.ts' import { contentBlockSchema, sessionEventSchema, sessionIdSchema, toolEventViewSchema } from './sessions.schema.ts' -import { workspaceViewSchema } from './workspace.schema.ts' +import { workspaceIdSchema, workspaceViewSchema } from './workspace.schema.ts' /** Question shape validated strictly against core dsh-user-interaction. */ export const askUserQuestionItemSchema = z.object({ @@ -47,6 +47,7 @@ export const hostFrameSchema = z.discriminatedUnion('type', [ z.object({ type: z.literal('host/session-status'), sessionId: sessionIdSchema, running: z.boolean() }), z.object({ type: z.literal('host/agent-error'), sessionId: sessionIdSchema, message: z.string() }), z.object({ type: z.literal('host/workspace-changed'), workspace: workspaceViewSchema }), + z.object({ type: z.literal('host/workspace-removed'), workspaceId: workspaceIdSchema }), z.object({ type: z.literal('host/commands-changed') }), z.object({ type: z.literal('stream/error'), error: rpcErrorSchema }), ]) as unknown as z.ZodType diff --git a/packages/host/apiproxy/src/api/events.ts b/packages/host/apiproxy/src/api/events.ts index db572215cb..bf66cbf76b 100644 --- a/packages/host/apiproxy/src/api/events.ts +++ b/packages/host/apiproxy/src/api/events.ts @@ -85,7 +85,9 @@ export type MuxFrame = * agent-error is the only outlet for live failures with no turn position; * workspace-changed pushes the full new snapshot after every durable * workspace mutation (create/attach/order change — the client upserts, while - * `workspace.list` provides the reconnect baseline). + * `workspace.list` provides the reconnect baseline); workspace-removed is the + * committed registration-deletion increment and never implies directory or + * session-log deletion. */ export type HostFrame = | { type: 'host/session-added'; sessionId: SessionId; blank: boolean; parentSessionId?: SessionId; cwd?: string } @@ -93,6 +95,7 @@ export type HostFrame = | { type: 'host/session-status'; sessionId: SessionId; running: boolean } | { type: 'host/agent-error'; sessionId: SessionId; message: string } | { type: 'host/workspace-changed'; workspace: WorkspaceView } + | { type: 'host/workspace-removed'; workspaceId: WorkspaceView['workspaceId'] } /** * The command registry changed (`commands/change` passthrough). Pure * invalidation signal, no payload: clients refetch `command.list` in the diff --git a/packages/host/apiproxy/src/api/rpc-map.ts b/packages/host/apiproxy/src/api/rpc-map.ts index abe992584c..68ccc9ec89 100644 --- a/packages/host/apiproxy/src/api/rpc-map.ts +++ b/packages/host/apiproxy/src/api/rpc-map.ts @@ -26,6 +26,7 @@ export interface RpcMethodMap { 'workspace.list': WorkspaceApi['list'] 'workspace.create': WorkspaceApi['create'] 'workspace.rename': WorkspaceApi['rename'] + 'workspace.delete': WorkspaceApi['delete'] 'workspace.insertSessionBefore': WorkspaceApi['insertSessionBefore'] 'command.list': CommandsApi['list'] 'command.execute': CommandsApi['execute'] diff --git a/packages/host/apiproxy/src/api/workspace.schema.ts b/packages/host/apiproxy/src/api/workspace.schema.ts index 47c3ae6d59..e16e5339da 100644 --- a/packages/host/apiproxy/src/api/workspace.schema.ts +++ b/packages/host/apiproxy/src/api/workspace.schema.ts @@ -59,6 +59,16 @@ export const workspaceRenameValueSchema = z.object({ workspace: workspaceViewSchema, }) satisfies z.ZodType>> +/** workspace.delete request payload. */ +export const workspaceDeleteRequestSchema = z.object({ + workspaceId: workspaceIdSchema, +}) satisfies z.ZodType>> + +/** workspace.delete response value. */ +export const workspaceDeleteValueSchema = z.object({ + deleted: z.literal(true), +}) satisfies z.ZodType>> + /** workspace.insertSessionBefore request payload (anchor omitted = append to end). */ export const workspaceInsertSessionBeforeRequestSchema = z.object({ workspaceId: workspaceIdSchema, diff --git a/packages/host/apiproxy/src/api/workspace.ts b/packages/host/apiproxy/src/api/workspace.ts index 6ec636126b..ff22d845fb 100644 --- a/packages/host/apiproxy/src/api/workspace.ts +++ b/packages/host/apiproxy/src/api/workspace.ts @@ -65,6 +65,14 @@ export interface WorkspaceApi { rename(request: RpcRequest<{ workspaceId: WorkspaceId; title: string }>): Promise> + /** + * Removes one Workspace registration. The directory, every user file, and + * every session log remain untouched; those Sessions consequently become + * ungrouped. An unknown id fails with `workspace-not-found`. + */ + delete(request: RpcRequest<{ workspaceId: WorkspaceId }>): + Promise> + /** * Moves an accounted session within its workspace's manual order, * DOM-insertBefore-like: with `beforeSessionId` the session is inserted diff --git a/packages/host/apiproxy/src/fetch/client.ts b/packages/host/apiproxy/src/fetch/client.ts index 0424ba7a4f..8762670cd7 100644 --- a/packages/host/apiproxy/src/fetch/client.ts +++ b/packages/host/apiproxy/src/fetch/client.ts @@ -23,6 +23,7 @@ import { } from '../api/sessions.schema.ts' import { workspaceCreateValueSchema, + workspaceDeleteValueSchema, workspaceInsertSessionBeforeValueSchema, workspaceListValueSchema, workspaceRenameValueSchema, @@ -60,6 +61,7 @@ export interface IApiClient { list(payload: RequestPayload<'workspace.list'>, signal?: AbortSignal): Promise>> create(payload: RequestPayload<'workspace.create'>, signal?: AbortSignal): Promise>> rename(payload: RequestPayload<'workspace.rename'>, signal?: AbortSignal): Promise>> + delete(payload: RequestPayload<'workspace.delete'>, signal?: AbortSignal): Promise>> insertSessionBefore(payload: RequestPayload<'workspace.insertSessionBefore'>, signal?: AbortSignal): Promise>> } commands: { @@ -91,6 +93,7 @@ const UNARY_VALUE_SCHEMAS: { [K in keyof RpcMethodMap]: z.ZodType this.callUnary('workspace.list', payload, signal), create: (payload, signal) => this.callUnary('workspace.create', payload, signal), rename: (payload, signal) => this.callUnary('workspace.rename', payload, signal), + delete: (payload, signal) => this.callUnary('workspace.delete', payload, signal), insertSessionBefore: (payload, signal) => this.callUnary('workspace.insertSessionBefore', payload, signal), } diff --git a/packages/host/apiproxy/src/fetch/handler.ts b/packages/host/apiproxy/src/fetch/handler.ts index b79980d63e..3bbcbffba1 100644 --- a/packages/host/apiproxy/src/fetch/handler.ts +++ b/packages/host/apiproxy/src/fetch/handler.ts @@ -24,6 +24,7 @@ import { import { hostDescribeRequestSchema } from '../api/host.schema.ts' import { workspaceCreateRequestSchema, + workspaceDeleteRequestSchema, workspaceInsertSessionBeforeRequestSchema, workspaceListRequestSchema, workspaceRenameRequestSchema, @@ -57,6 +58,7 @@ const UNARY_ROUTES: UnaryRoutes = { 'workspace.list': { schema: workspaceListRequestSchema, invoke: (api, r) => api.workspace.list(r) }, 'workspace.create': { schema: workspaceCreateRequestSchema, invoke: (api, r) => api.workspace.create(r) }, 'workspace.rename': { schema: workspaceRenameRequestSchema, invoke: (api, r) => api.workspace.rename(r) }, + 'workspace.delete': { schema: workspaceDeleteRequestSchema, invoke: (api, r) => api.workspace.delete(r) }, 'workspace.insertSessionBefore': { schema: workspaceInsertSessionBeforeRequestSchema, invoke: (api, r) => api.workspace.insertSessionBefore(r) }, 'command.list': { schema: commandListRequestSchema, invoke: (api, r) => api.commands.list(r) }, 'command.execute': { schema: commandExecuteRequestSchema, invoke: (api, r, signal) => api.commands.execute(r, signal) }, diff --git a/packages/host/apiproxy/tests/api-proxy-workspace.spec.ts b/packages/host/apiproxy/tests/api-proxy-workspace.spec.ts index 11cdf5795c..d5ba628590 100644 --- a/packages/host/apiproxy/tests/api-proxy-workspace.spec.ts +++ b/packages/host/apiproxy/tests/api-proxy-workspace.spec.ts @@ -244,4 +244,31 @@ describe('Host Workspace increments', () => { abort.abort() expect(await next).toMatchObject({ done: true }) }) + + it('deletes the registration, keeps its session and folder, and streams one removal', async () => { + const { api, ctx } = await harness() + const workspace = expectOk(await api.workspace.create(request({ name: 'delete-me' }))).workspace + const sessionId = SessionId('session-kept-after-workspace-delete') + expectOk(await api.sessions.create(request({ workspaceId: workspace.workspaceId, sessionId }))) + + const abort = new AbortController() + const stream: AsyncIterator> = + api.events.host(request({}), abort.signal)[Symbol.asyncIterator]() + const removed = nextHostFrame(stream) + expectOk(await api.workspace.delete(request({ workspaceId: workspace.workspaceId }))) + expect(await removed).toMatchObject({ + payload: { type: 'host/workspace-removed', workspaceId: workspace.workspaceId }, + }) + expect(expectOk(await api.workspace.list(request({}))).items).toEqual([]) + expect(expectOk(await api.sessions.list(request({}))).items.map(item => item.sessionId)).toContain(sessionId) + expect(ctx.agents.get(sessionId)).toBeDefined() + expect(existsSync(workspace.path)).toBe(true) + + const missing = await api.workspace.delete(request({ workspaceId: workspace.workspaceId })) + expect(missing.result).toMatchObject({ + ok: false, + error: { code: 'workspace-not-found', details: { workspaceId: workspace.workspaceId } }, + }) + abort.abort() + }) }) diff --git a/packages/host/apiproxy/tests/client-handler.spec.ts b/packages/host/apiproxy/tests/client-handler.spec.ts index a9a5eac9ba..38ad7a52c9 100644 --- a/packages/host/apiproxy/tests/client-handler.spec.ts +++ b/packages/host/apiproxy/tests/client-handler.spec.ts @@ -40,6 +40,7 @@ function scriptedApi(overrides: { list: r => ok(r, { items: [] }), create: r => ok(r, { workspace: { workspaceId: 'w1' as never, path: '/t', title: 't', sessionIds: [], createdAt: '0', updatedAt: '0' }, created: true }), rename: r => ok(r, { workspace: { workspaceId: 'w1' as never, path: '/t', title: 't', sessionIds: [], createdAt: '0', updatedAt: '0' } }), + delete: r => ok(r, { deleted: true as const }), insertSessionBefore: r => ok(r, { workspace: { workspaceId: 'w1' as never, path: '/t', title: 't', sessionIds: [], createdAt: '0', updatedAt: '0' } }), }, commands: { @@ -76,13 +77,15 @@ describe('unary round trip', () => { expect(response.result).toEqual({ ok: true, value: { items: [{ sessionId: 's1', updatedAt: 7, running: false, blank: false }] } }) }) - it('routes workspace rename and insertSessionBefore through the wire', async () => { + it('routes workspace rename, delete, and insertSessionBefore through the wire', async () => { const api = scriptedApi() const c = client(api) const renamed = await c.workspace.rename({ workspaceId: 'w1' as never, title: 'next' }) expect(renamed.result.ok).toBe(true) const blankTitle = await c.workspace.rename({ workspaceId: 'w1' as never, title: ' ' }) expect(blankTitle.result).toMatchObject({ ok: false, error: { code: 'bad-request' } }) + const deleted = await c.workspace.delete({ workspaceId: 'w1' as never }) + expect(deleted.result).toEqual({ ok: true, value: { deleted: true } }) const anchored = await c.workspace.insertSessionBefore({ workspaceId: 'w1' as never, sessionId: sid('s1'), beforeSessionId: sid('s2') }) expect(anchored.result.ok).toBe(true) const appended = await c.workspace.insertSessionBefore({ workspaceId: 'w1' as never, sessionId: sid('s1') }) diff --git a/packages/host/apiproxy/tests/fetch-carrier.spec.ts b/packages/host/apiproxy/tests/fetch-carrier.spec.ts index e8d65d2a62..0a92b9f5e5 100644 --- a/packages/host/apiproxy/tests/fetch-carrier.spec.ts +++ b/packages/host/apiproxy/tests/fetch-carrier.spec.ts @@ -58,6 +58,9 @@ function fakeApi(overrides: Partial<{ muxFrames: MuxFrame[]; hostFrames: HostFra result: { ok: true, value: { workspace: { workspaceId: 'w1' as never, path: '/w', title: 'w', sessionIds: [], createdAt: 't', updatedAt: 't' } } }, } }, + async delete(request) { + return { rpcId: request.rpcId, result: { ok: true, value: { deleted: true as const } } } + }, async insertSessionBefore(request) { return { rpcId: request.rpcId, diff --git a/packages/host/apiproxy/tests/rpc-schemas.spec.ts b/packages/host/apiproxy/tests/rpc-schemas.spec.ts index 02ca8dec22..c1af02b7b9 100644 --- a/packages/host/apiproxy/tests/rpc-schemas.spec.ts +++ b/packages/host/apiproxy/tests/rpc-schemas.spec.ts @@ -14,6 +14,7 @@ import { import { hostDescribeRequestSchema, hostDescribeValueSchema } from '../src/api/host.schema.ts' import { workspaceCreateRequestSchema, workspaceCreateValueSchema, workspaceIdSchema, + workspaceDeleteRequestSchema, workspaceDeleteValueSchema, workspaceInsertSessionBeforeRequestSchema, workspaceInsertSessionBeforeValueSchema, workspaceListRequestSchema, workspaceListValueSchema, workspaceRenameRequestSchema, workspaceRenameValueSchema, workspaceViewSchema, @@ -177,6 +178,13 @@ describe('workspace domain schemas', () => { expect(workspaceRenameValueSchema.parse({ workspace: view }).workspace.workspaceId).toBe('w1') }) + it('validates workspace deletion payload and receipt', () => { + expect(workspaceDeleteRequestSchema.parse({ workspaceId: 'w1' }).workspaceId).toBe('w1') + expect(() => workspaceDeleteRequestSchema.parse({})).toThrow() + expect(workspaceDeleteValueSchema.parse({ deleted: true })).toEqual({ deleted: true }) + expect(() => workspaceDeleteValueSchema.parse({ deleted: false })).toThrow() + }) + it('insertSessionBefore accepts an anchored and an anchorless move', () => { expect(workspaceInsertSessionBeforeRequestSchema.parse({ workspaceId: 'w1', sessionId: 's1', beforeSessionId: 's2' }).beforeSessionId).toBe('s2') expect(workspaceInsertSessionBeforeRequestSchema.parse({ workspaceId: 'w1', sessionId: 's1' }).beforeSessionId).toBeUndefined() @@ -273,6 +281,11 @@ describe('events frame schemas', () => { { type: 'host/session-removed', sessionId: 's' }, { type: 'host/session-status', sessionId: 's', running: true }, { type: 'host/agent-error', sessionId: 's', message: 'boom' }, + { type: 'host/workspace-changed', workspace: { + workspaceId: 'w', path: '/w', title: 'w', sessionIds: [], + createdAt: '0', updatedAt: '0', + } }, + { type: 'host/workspace-removed', workspaceId: 'w' }, { type: 'host/commands-changed' }, { type: 'stream/error', error: { code: 'internal', message: 'm', details: {} } }, ] diff --git a/packages/workspace/README.i18n.yaml b/packages/workspace/README.i18n.yaml index a5400bc218..6d62c08c0b 100644 --- a/packages/workspace/README.i18n.yaml +++ b/packages/workspace/README.i18n.yaml @@ -1,6 +1,6 @@ # Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each # 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 -README.md: 0d5ebabfbbb2922a369adb3a5d67ea4aafbe700f -README.zh.md: b82e8e6138f3e97c3c047cf1812cee8e558ea29b +# pnpm run verify-translation-pairing --write packages/workspace/README.md +README.md: ba92e95d3cde0a95eaaeae5a9b4384c3b8c9c4b8 +README.zh.md: 8c8146bba5fa6d81c0ce5d2ed29add77b4083270 diff --git a/packages/workspace/README.md b/packages/workspace/README.md index 0d5ebabfbb..ba92e95d3c 100644 --- a/packages/workspace/README.md +++ b/packages/workspace/README.md @@ -2,10 +2,10 @@ English | [中文](README.zh.md) -The workspace family owns the persistent workspace concept: a directory the user works in, with a title and the ordered list of sessions that belong to it. Design record: [domain KV storage Agent Note](../../.agents/notes/proposed/architecture/2026-07-24-domain-kv-storage-and-workspace.zh.md). +The workspace family owns the persistent workspace concept: a directory the user works in, with a title and the ordered list of sessions that belong to it. Design record: [domain KV storage Agent Note](../../.agents/notes/proposed/architecture/2026-07-24-domain-kv-storage-and-workspace.md). | Package | Role | ctx key | |---|---|---| | `workspace/` | `WorkspaceRegistry` service over the storage domain form: realpath-unique paths, session-ownership accounting, entity cache | `ctx.workspace` | -Ownership truth lives in the workspace record's `sessionIds` (ordered), never derived from session cwd; `attachSession` verifies the session header's cwd resolves to the workspace path, so one session structurally belongs to at most one workspace. Deletion (workspace and session cascade) is deliberately absent this phase and ships with the session-side primitives. +Ownership truth lives in the workspace record's `sessionIds` (ordered), never derived from session cwd; `attachSession` verifies the session header's cwd resolves to the workspace path, so one session structurally belongs to at most one workspace. Deleting a Workspace removes only this registry record and account: directories, user files, and session logs remain, and the Sessions become Ungrouped ([decision](../../.agents/notes/implemented/feature/2026-07-27-workspace-registration-deletion.md)). diff --git a/packages/workspace/README.zh.md b/packages/workspace/README.zh.md index b82e8e6138..8c8146bba5 100644 --- a/packages/workspace/README.zh.md +++ b/packages/workspace/README.zh.md @@ -2,10 +2,10 @@ [English](README.md) | 中文 -Workspace 系列拥有持久 workspace 概念：用户工作所在的目录，包含标题以及属于它的有序会话列表。设计记录：[领域 KV 存储 Agent Note](../../.agents/notes/proposed/architecture/2026-07-24-domain-kv-storage-and-workspace.zh.md)。 +Workspace 系列拥有持久 workspace 概念：用户工作所在的目录，包含标题以及属于它的有序会话列表。设计记录：[领域 KV 存储 Agent Note](../../.agents/notes/proposed/architecture/2026-07-24-domain-kv-storage-and-workspace.md)。 | 包 | 职责 | ctx 键 | |---|---|---| | `workspace/` | 位于存储领域形式之上的 `WorkspaceRegistry` 服务：按 realpath 唯一的路径、会话所有权计数、实体缓存 | `ctx.workspace` | -所有权真相存在 workspace 记录的 `sessionIds`（有序）中，绝不从会话 cwd 派生；`attachSession` 会验证会话头的 cwd 解析到 workspace 路径，因此一个会话在结构上最多属于一个 workspace。本阶段有意不提供删除（workspace 与会话级联）；该功能将与会话侧原语一起交付。 +所有权真相存在 workspace 记录的 `sessionIds`（有序）中，绝不从会话 cwd 派生；`attachSession` 会验证会话头的 cwd 解析到 workspace 路径，因此一个会话在结构上最多属于一个 workspace。删除 Workspace 只会移除该注册表记录及账本：目录、用户文件和会话日志都会保留，相关会话则进入 Ungrouped（参见[决策记录](../../.agents/notes/implemented/feature/2026-07-27-workspace-registration-deletion.md)）。 diff --git a/packages/workspace/workspace/README.i18n.yaml b/packages/workspace/workspace/README.i18n.yaml index b3e0df9280..0904711ad3 100644 --- a/packages/workspace/workspace/README.i18n.yaml +++ b/packages/workspace/workspace/README.i18n.yaml @@ -1,6 +1,6 @@ # Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each # 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 -README.md: 0d395ecc58fc5e3362cb5f3c565a0539bb09c4dd -README.zh.md: 017e1e4d3aae9f8708ead3565f8b5b59d9b249ca +# pnpm run verify-translation-pairing --write packages/workspace/workspace/README.md +README.md: 52d03b33b3482dcb6a2f5feddbc15ac9fefee0a8 +README.zh.md: f899abdc3dd2a551179cd710c6dda84f804a8e80 diff --git a/packages/workspace/workspace/README.md b/packages/workspace/workspace/README.md index 0d395ecc58..52d03b33b3 100644 --- a/packages/workspace/workspace/README.md +++ b/packages/workspace/workspace/README.md @@ -10,6 +10,7 @@ The entity/storage rationale lives in the [domain Agent Note](../../../.agents/n - `ctx.workspace.create(path, title?)` — canonicalizes `path` via `fs.realpath`, rejects a nonexistent or non-directory path, creates at most one record per canonical path, and prepends a new record to durable workspace order. Repeated calls for that path return the existing workspace without changing its title; a different path cannot create a duplicate title. - `ctx.workspace.get(id)` / `list()` / `resolveByPath(path)` — cache-served lookups. `list()` is synchronous and follows durable registry order; `resolveByPath` is async because it applies the same `realpath` canon and rejects a missing path rather than creating it. +- `ctx.workspace.delete(id)` — removes only the Workspace registration, its durable order entry, and its session account. Unknown ids return `false`; a removed record returns `true`. The directory, user files, live Sessions, and persisted session logs are never touched, so those Sessions become Ungrouped. A table-write failure restores the prior order and published entity. - `Workspace.attachSession(id)` — validates a live or persisted session header cwd against the workspace path and prepends a new id. Unknown sessions, absent/unresolvable/non-directory cwd values, and mismatches reject without writing. `detachSession` removes only the candidate index entry. - `ctx.workspace.touchSession(id)` — moves only that validated, accounted session to the front. Ungrouped or filtered sessions are no-ops, and workspace order never changes. - `Workspace.sessionIds` — synchronous id-plus-canonical-cwd membership projection in durable candidate order. Missing headers, invalid cwd values, and mismatches are filtered; the next workspace mutation prunes them. A medium indexing one session under two workspaces, claiming one path from two records, or diverging from durable workspace order rejects at startup. @@ -35,5 +36,5 @@ Independent of live requests: the package never touches a request prefix, so it ## Known Limitations and Deferred Work -- No delete entry point in this phase — workspace deletion ships as one complete semantic together with the session-delete primitive and cascade orchestration (future-work section of the Agent Note); a half "drop the record, keep the sessions" operation is deliberately not exposed. +- Session deletion and destructive folder removal are separate, absent capabilities; Workspace registration deletion never substitutes for either ([decision](../../../.agents/notes/implemented/feature/2026-07-27-workspace-registration-deletion.md)). - The header index refreshes at startup and when attach must resolve an uncached persisted id; deletion or cwd damage performed by another process is observed after the next refresh or restart. diff --git a/packages/workspace/workspace/README.zh.md b/packages/workspace/workspace/README.zh.md index 017e1e4d3a..f899abdc3d 100644 --- a/packages/workspace/workspace/README.zh.md +++ b/packages/workspace/workspace/README.zh.md @@ -10,6 +10,7 @@ DeepSeek Harness 的 Workspace 实体注册表（`ctx.workspace`）：通过领 - `ctx.workspace.create(path, title?)`：规范化 `path` 时使用 `fs.realpath`，拒绝不存在或非目录的路径，每个规范路径最多创建一条记录，并将新记录前置到持久 workspace 顺序。对同一路径重复调用会返回现有 workspace，且不改变其标题；不同路径不能创建重复标题。 - `ctx.workspace.get(id)`/`list()`/`resolveByPath(path)`：由缓存提供的查找。`list()` 为同步操作，并遵循持久注册表顺序；`resolveByPath` 为异步操作，因为它应用同一 `realpath` 规范，并会拒绝缺失路径，而不是创建路径。 +- `ctx.workspace.delete(id)`：只移除 Workspace 注册记录、对应的持久顺序条目及会话账本。未知 id 返回 `false`，成功移除记录则返回 `true`。目录、用户文件、实时会话和持久化会话日志绝不受影响，因此相关会话会进入 Ungrouped。表写入失败时会恢复原顺序和此前发布的实体。 - `Workspace.attachSession(id)`：对照 workspace 路径验证实时或已持久化的会话头 cwd，并将新 id 前置。未知会话、缺失／无法解析／非目录的 cwd 值和不匹配情况都会在不写入的前提下被拒绝。`detachSession` 只移除候选索引条目。 - `ctx.workspace.touchSession(id)`：仅将已验证、已记账的会话移到最前。未分组或被过滤的会话为空操作，workspace 顺序绝不改变。 - `Workspace.sessionIds`：按持久候选顺序提供同步 id 加规范 cwd 成员投影。缺失头部、无效 cwd 值和不匹配情况都被过滤；下一次 workspace 变更会剪除它们。如果同一存储介质将一个会话索引到两个 workspace 下、从两条记录声明同一路径，或偏离持久 workspace 顺序，启动会被拒绝。 @@ -35,5 +36,5 @@ DeepSeek Harness 的 Workspace 实体注册表（`ctx.workspace`）：通过领 ## 已知限制与延后工作 -- 本阶段没有删除入口：workspace 删除将与会话删除原语和级联编排一起作为完整语义交付（参见 Agent Note 的未来工作一节）；系统有意不公开「删除记录、保留会话」的半成品操作。 +- 会话删除与破坏性的文件夹移除是彼此独立且尚未提供的功能；删除 Workspace 注册记录绝不能替代二者（参见[决策记录](../../../.agents/notes/implemented/feature/2026-07-27-workspace-registration-deletion.md)）。 - 头部索引会在启动时刷新，也会在 attach 必须解析未缓存持久 id 时刷新；另一进程执行的删除或 cwd 破坏会在下次刷新或重启后被观测。 diff --git a/packages/workspace/workspace/src/index.ts b/packages/workspace/workspace/src/index.ts index 0f849e7374..2699365608 100644 --- a/packages/workspace/workspace/src/index.ts +++ b/packages/workspace/workspace/src/index.ts @@ -168,6 +168,18 @@ export class WorkspaceRegistry extends Service { }) } + /** + * Delete one workspace registration while retaining its directory and every + * session log. The durable order is updated before the table deletion; a + * failed table write restores the prior order and keeps the entity + * published. Unknown ids are an idempotent no-op for domain callers. + * @param id - Workspace registration to remove. + * @returns `true` when a record was deleted, `false` when it was unknown. + */ + delete(id: WorkspaceId): Promise { + return this.enqueueOperation(() => this.deleteKnown(id)) + } + /** * Resolve by canonical directory path without creating or mutating a * workspace. A missing path rejects during `realpath`; an existing unowned @@ -231,6 +243,33 @@ export class WorkspaceRegistry extends Service { return entity } + private async deleteKnown(id: WorkspaceId): Promise { + const entity = this.entities.get(id) + if (entity === undefined) return false + const state = this.requireState() + const nextState = { + initialized: true, + workspaceIds: state.workspaceIds.filter(workspaceId => workspaceId !== id), + } + await this.setState(nextState) + this.entities.delete(id) + try { + await this.requireTable().delete(id) + } catch (error) { + this.entities.set(id, entity) + try { + await this.setState(state) + } catch (rollbackError) { + throw new AggregateError( + [error, rollbackError], + `workspace '${id}' record deletion and registry-order rollback both failed`, + ) + } + throw error + } + return true + } + private async bootstrap(headers: readonly SessionHeader[]): Promise { const table = this.requireTable() const state = this.requireState() diff --git a/packages/workspace/workspace/src/invariant.ts b/packages/workspace/workspace/src/invariant.ts index 1764ce2fe3..808ce1dedf 100644 --- a/packages/workspace/workspace/src/invariant.ts +++ b/packages/workspace/workspace/src/invariant.ts @@ -20,8 +20,9 @@ export const inject = ['invariants'] * domain's durable table. Every `domain/changed` for the `workspaces` table * must name a record the cache already holds an entity for (the registry * caches before the durable put and mutates only through cached entities). - * A delete is valid only for create rollback, after the provisional cache - * entry has been removed; deleting a published entity proves a bypass. + * A delete is valid only after the registry has removed the entity from its + * cache, whether for create rollback or an explicit registration deletion; + * deleting while the cache still publishes the entity proves a bypass. */ const install: InvariantInstaller = Object.assign( (ctx: Context, fail: (message: string) => never) => { diff --git a/packages/workspace/workspace/tests/invariant.spec.ts b/packages/workspace/workspace/tests/invariant.spec.ts index ea1fbaa64c..0d0556a44a 100644 --- a/packages/workspace/workspace/tests/invariant.spec.ts +++ b/packages/workspace/workspace/tests/invariant.spec.ts @@ -49,7 +49,7 @@ describe('workspace cache/table invariant', () => { .toThrow(/cache still publishes/) }) - it('allows deletion only after a provisional create cache entry was removed for rollback', async () => { + it('allows deletion after the registry removed the cache entry for rollback or explicit deletion', async () => { const ctx = await setup([]) expect(() => { ctx.emit('domain/changed', deleted()) }).not.toThrow() }) diff --git a/packages/workspace/workspace/tests/workspace.spec.ts b/packages/workspace/workspace/tests/workspace.spec.ts index 8ce70cc7d5..ed08b5ba50 100644 --- a/packages/workspace/workspace/tests/workspace.spec.ts +++ b/packages/workspace/workspace/tests/workspace.spec.ts @@ -424,6 +424,40 @@ describe('WorkspaceRegistry create and lookup', () => { expect(pool.media.get('workspace')!.tables.get('workspaces')!.size).toBe(1) }) + it('deletes only the registration and leaves its directory and session headers untouched', async () => { + const dir = await makeDir('delete-registration') + const result = await harness({ sessions: [header('kept-session', dir)] }) + const workspace = await result.registry.create(dir) + await workspace.attachSession(SessionId('kept-session')) + + await expect(result.registry.delete(workspace.id)).resolves.toBe(true) + await expect(result.registry.delete(workspace.id)).resolves.toBe(false) + expect(result.registry.get(workspace.id)).toBeUndefined() + expect(result.registry.list()).toEqual([]) + expect(storedState(result.pool)).toEqual({ initialized: true, workspaceIds: [] }) + expect(result.pool.media.get('workspace')!.tables.get('workspaces')!.has(workspace.id)).toBe(false) + await expect(realpath(dir)).resolves.toBe(dir) + expect(result.list).toHaveBeenCalledTimes(1) + expect(result.load).not.toHaveBeenCalled() + expect(result.inspect).not.toHaveBeenCalled() + }) + + it('rolls registry order and cache back when record deletion fails', async () => { + const dir = await makeDir('delete-rollback') + const pool = new MemoryMediaPool() + const result = await harness({ + pool, + backend: selectiveFailureBackend(pool, { deleteAt: 1 }), + }) + const workspace = await result.registry.create(dir) + + await expect(result.registry.delete(workspace.id)).rejects.toThrow(/selected rollback delete failure/) + expect(result.registry.get(workspace.id)).toBe(workspace) + expect(result.registry.list()).toEqual([workspace]) + expect(storedState(pool).workspaceIds).toEqual([workspace.id]) + expect(storedRecord(pool, workspace.id)).toMatchObject({ path: dir }) + }) + it('rejects table access before the registry has started', async () => { const dir = await makeDir('unstarted') const registry = new WorkspaceRegistry(new Context()) From 109b469a7e52a1a62e9355833001a0257bb7740d Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Mon, 27 Jul 2026 12:41:36 +0800 Subject: [PATCH 14/36] fix(tool-web): bound conversion depth and complete fetch output Two review findings on the turndown swap, both verified empirically: - Unclosed-tag nesting makes the synchronous turndown/domino walk superlinear (measured: depth 512 ~0.15s, 2k ~2s, 20k ~5s), during which the cooperative fetchTimeoutMs timer cannot fire. renderBody now preflights nesting depth with a linear tag scan and passes bodies past 512 levels through raw; the try/catch stays for markup the scan cannot see (comment-hidden tags), simulated in tests via a converter throw. - Markdown escaping can expand converted HTML ~2x (100k underscores render as 200k chars), so provider body caps no longer bounded the model-visible result. formatFetchOutput now caps the complete output (header + body + footer) under new fetchMaxOutputChars config (default 200000 = 2x the local provider's default body cap), reusing the truncation notice. README EN+ZH, config catalog, Agent Note EN+ZH updated; the new web-fetch fixture is migrated to the packed layout master now requires; tool-web coverage stays 100% per-file. --- ...ndown-for-tool-web-html-markdown.i18n.yaml | 4 +- ...-26-turndown-for-tool-web-html-markdown.md | 4 +- ...-turndown-for-tool-web-html-markdown.zh.md | 4 +- docs/config-catalog.md | 6 +- .../tests/snapshots/web-fetch/session.jsonl | 102 +----------------- packages/web/tool-web/README.i18n.yaml | 4 +- packages/web/tool-web/README.md | 5 +- packages/web/tool-web/README.zh.md | 5 +- packages/web/tool-web/src/fetch.ts | 86 ++++++++++++--- packages/web/tool-web/src/index.ts | 19 +++- packages/web/tool-web/tests/tool-web.spec.ts | 70 ++++++++++-- 11 files changed, 172 insertions(+), 137 deletions(-) diff --git a/.agents/notes/implemented/simplification/2026-07-26-turndown-for-tool-web-html-markdown.i18n.yaml b/.agents/notes/implemented/simplification/2026-07-26-turndown-for-tool-web-html-markdown.i18n.yaml index 60a5d9aca7..a114e32885 100644 --- a/.agents/notes/implemented/simplification/2026-07-26-turndown-for-tool-web-html-markdown.i18n.yaml +++ b/.agents/notes/implemented/simplification/2026-07-26-turndown-for-tool-web-html-markdown.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 -2026-07-26-turndown-for-tool-web-html-markdown.md: c72decc336055f3b78dafdf98f2be3771b833cdb -2026-07-26-turndown-for-tool-web-html-markdown.zh.md: 30667b62538ec50608cae461b5cdf651b48e2731 +2026-07-26-turndown-for-tool-web-html-markdown.md: c7ef4bf538cc949eec8463c8a2ac750685d1a715 +2026-07-26-turndown-for-tool-web-html-markdown.zh.md: 3104dac3cd6db516396b6773f5d2185f3da22ca3 diff --git a/.agents/notes/implemented/simplification/2026-07-26-turndown-for-tool-web-html-markdown.md b/.agents/notes/implemented/simplification/2026-07-26-turndown-for-tool-web-html-markdown.md index c72decc336..c7ef4bf538 100644 --- a/.agents/notes/implemented/simplification/2026-07-26-turndown-for-tool-web-html-markdown.md +++ b/.agents/notes/implemented/simplification/2026-07-26-turndown-for-tool-web-html-markdown.md @@ -10,7 +10,7 @@ English | [中文](2026-07-26-turndown-for-tool-web-html-markdown.zh.md) ## Decision -`packages/web/tool-web/src/fetch.ts` owns a module-level [`turndown`](https://github.com/mixmark-io/turndown) instance (`headingStyle: 'atx'`, `codeBlockStyle: 'fenced'`, `bulletListMarker: '-'` — fixed model-facing presentation, not deployment tunables) with `@joplin/turndown-plugin-gfm`'s composite `gfm` plugin for tables/strikethrough and `remove(['script', 'style', 'noscript'])` replacing the old wholesale drops. `renderBody`'s `html` arm calls it in a try/catch falling back to the raw HTML body: the regex version could never throw, while turndown/domino's recursive DOM walk overflows with a `RangeError` at a few thousand nesting levels (measured: 4k throws on the main thread, 8k in a worker thread), and a degraded page beats an error for a body the provider already decoded. `html.ts` and its conversion tests are deleted; the fallback and the status-header/truncation-footer formatting are tested in `tests/tool-web.spec.ts`, and the README's Known Limitations trades the regex-converter caveat for the pathological-nesting fallback. The gfm plugin ships no types; `src/turndown-plugin-gfm.d.ts` declares the one imported export over `@types/turndown` (a devDependency). +`packages/web/tool-web/src/fetch.ts` owns a module-level [`turndown`](https://github.com/mixmark-io/turndown) instance (`headingStyle: 'atx'`, `codeBlockStyle: 'fenced'`, `bulletListMarker: '-'` — fixed model-facing presentation, not deployment tunables) with `@joplin/turndown-plugin-gfm`'s composite `gfm` plugin for tables/strikethrough and `remove(['script', 'style', 'noscript'])` replacing the old wholesale drops. `renderBody`'s `html` arm guards the conversion twice: a linear tag-scan preflight passes bodies nested past 512 levels through raw (the synchronous walk is superlinear on unclosed nesting — measured seconds at 20k levels — during which the cooperative timeout cannot fire), and a try/catch falls back to the raw HTML when turndown still throws on markup the scan cannot see; a degraded page beats an error for a body the provider already decoded. `formatFetchOutput` bounds the complete output (`fetchMaxOutputChars` config, default 200,000) because markdown escaping can expand converted HTML to ~2× a provider's body cap. `html.ts` and its conversion tests are deleted; the fallback and the status-header/truncation-footer formatting are tested in `tests/tool-web.spec.ts`, and the README's Known Limitations trades the regex-converter caveat for the pathological-nesting fallback. The gfm plugin ships no types; `src/turndown-plugin-gfm.d.ts` declares the one imported export over `@types/turndown` (a devDependency). The dependency-weight question the proposal flagged resolves in favor of the swap: `@deepseek-ai/dsh-tool-web` is in the single-file-executable closure ([single-exe note](../architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.md)), and the exe's asset globs would pack ~7.9 MB of the three packages as published — but ~6 MB of that is `@mixmark-io/domino`'s test corpus (`test/**`), with runtime `lib/` at ~550 KB against a ~174 MB artifact, under 0.5% either way. @@ -33,5 +33,5 @@ The previously-missing keyless `web_fetch` snapshot ships with the change as the ## Testing -- `packages/web/tool-web/tests/tool-web.spec.ts` covers the turndown conversion surface (entities, links, tables, nesting, script/style/noscript removal) through `renderBody`, and the raw-HTML fallback with a measured reliably-overflowing 20k-level nesting input; per-file coverage on the package src is 100%. +- `packages/web/tool-web/tests/tool-web.spec.ts` covers the turndown conversion surface (entities, links, tables, nesting, script/style/noscript removal) through `renderBody`, the fast raw-HTML passthrough for 20k-level nesting, the depth scan's void/self-closing/unbalanced cases, the residual converter-throw fallback, and the whole-output cap at expanding, exact, and tiny budgets; per-file coverage on the package src is 100%. - The `web-fetch` acp-agent snapshot pins the assembled behavior keylessly end to end (real Loader composition, real HTTP fetch, real conversion). diff --git a/.agents/notes/implemented/simplification/2026-07-26-turndown-for-tool-web-html-markdown.zh.md b/.agents/notes/implemented/simplification/2026-07-26-turndown-for-tool-web-html-markdown.zh.md index 30667b6253..3104dac3cd 100644 --- a/.agents/notes/implemented/simplification/2026-07-26-turndown-for-tool-web-html-markdown.zh.md +++ b/.agents/notes/implemented/simplification/2026-07-26-turndown-for-tool-web-html-markdown.zh.md @@ -10,7 +10,7 @@ Status: implemented ## 决策 -`packages/web/tool-web/src/fetch.ts` 持有一个模块级 [`turndown`](https://github.com/mixmark-io/turndown) 实例（`headingStyle: 'atx'`、`codeBlockStyle: 'fenced'`、`bulletListMarker: '-'`——固定的面向模型呈现方式，不是部署可调项），配合 `@joplin/turndown-plugin-gfm` 的组合 `gfm` 插件提供表格／删除线支持，并用 `remove(['script', 'style', 'noscript'])` 替代旧实现的整体剥离。`renderBody` 的 `html` 分支把调用包在 try/catch 中，失败时回退为原始 HTML 主体：正则版本从不可能抛异常，而 turndown/domino 的递归 DOM 遍历在数千层嵌套（实测：主线程 4k 层抛出，worker 线程 8k 层抛出）会以 `RangeError` 栈溢出，对提供方已经解码的主体来说，降级页面好过报错。`html.ts` 及其转换测试已删除；回退路径与状态头、截断页脚的格式化在 `tests/tool-web.spec.ts` 中有测试覆盖，README 的 Known Limitations 用病态嵌套回退条目替换了正则转换器的警示说明。gfm 插件不带类型声明；`src/turndown-plugin-gfm.d.ts` 基于 `@types/turndown`（devDependency）声明了唯一被导入的导出。 +`packages/web/tool-web/src/fetch.ts` 持有一个模块级 [`turndown`](https://github.com/mixmark-io/turndown) 实例（`headingStyle: 'atx'`、`codeBlockStyle: 'fenced'`、`bulletListMarker: '-'`——固定的面向模型呈现方式，不是部署可调项），配合 `@joplin/turndown-plugin-gfm` 的组合 `gfm` 插件提供表格／删除线支持，并用 `remove(['script', 'style', 'noscript'])` 替代旧实现的整体剥离。`renderBody` 的 `html` 分支对转换做了双重防护：一次线性标签扫描预检把嵌套超过 512 层的主体直接原样透传（同步遍历在未闭合嵌套上呈超线性——实测 2 万层需要数秒——期间协作式超时无法触发），扫描看不到的标记若仍让 turndown 抛异常，则由 try/catch 回退为原始 HTML；对提供方已经解码的主体来说，降级页面好过报错。`formatFetchOutput` 对完整输出设上限（`fetchMaxOutputChars` 配置，默认 200,000）：markdown 转义可能把转换后的 HTML 膨胀到提供方主体上限的约 2 倍。`html.ts` 及其转换测试已删除；透传、回退与整体输出上限，连同状态头、截断页脚的格式化，都在 `tests/tool-web.spec.ts` 中有测试覆盖，README 的 Known Limitations 用病态嵌套回退条目替换了正则转换器的警示说明。gfm 插件不带类型声明；`src/turndown-plugin-gfm.d.ts` 基于 `@types/turndown`（devDependency）声明了唯一被导入的导出。 提案标记的依赖体积问题的裁决结果支持替换：`@deepseek-ai/dsh-tool-web` 在单文件可执行文件闭包内（[single-exe 决策记录](../architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.md)），可执行文件的资产 glob 会把这三个包按发布原样打入约 7.9 MB——但其中约 6 MB 是 `@mixmark-io/domino` 的测试语料（`test/**`），运行时 `lib/` 仅约 550 KB，相对约 174 MB 的产物，两种口径都不到 0.5%。 @@ -33,5 +33,5 @@ Status: implemented ## 测试 -- `packages/web/tool-web/tests/tool-web.spec.ts` 通过 `renderBody` 覆盖 turndown 转换面（实体、链接、表格、嵌套、script/style/noscript 移除），并用实测可稳定溢出的 2 万层嵌套输入覆盖原始 HTML 回退；该包 src 的逐文件覆盖率为 100%。 +- `packages/web/tool-web/tests/tool-web.spec.ts` 通过 `renderBody` 覆盖 turndown 转换面（实体、链接、表格、嵌套、script/style/noscript 移除）、2 万层嵌套的快速原样透传、深度扫描的空元素／自闭合／不平衡用例、残余的转换器抛错回退，以及在膨胀、恰好、极小预算下的整体输出上限；该包 src 的逐文件覆盖率为 100%。 - acp-agent 的 `web-fetch` 快照无密钥地端到端固定组装后的行为（真实 Loader 组合、真实 HTTP 抓取、真实转换）。 diff --git a/docs/config-catalog.md b/docs/config-catalog.md index 721c432f73..742d04dd71 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -1656,7 +1656,7 @@ Source: [`packages/tasks/tool-tasks/src/index.ts:23`](../packages/tasks/tool-tas Requires: `tools` · `web` · `systemPrompt` ```ts config-catalog -/** Plugin config: which web tools to register, the source cap, and per-tool budgets. */ +/** Plugin config: which web tools to register, the source cap, per-tool budgets, and the fetch output cap. */ export interface Config { /** Register `web_search`. Defaults to true. */ search?: boolean @@ -1668,10 +1668,12 @@ export interface Config { fetchTimeoutMs?: number /** Cooperative timeout budget (ms) for `web_search`. Defaults to 30000. */ searchTimeoutMs?: number + /** Cap on one `web_fetch` output's characters (header, rendered body, and footer). Defaults to 200000. */ + fetchMaxOutputChars?: number } ``` -Source: [`packages/web/tool-web/src/index.ts:28`](../packages/web/tool-web/src/index.ts) +Source: [`packages/web/tool-web/src/index.ts:37`](../packages/web/tool-web/src/index.ts) ## `@deepseek-ai/dsh-tool-workflow` diff --git a/examples/acp-agent/tests/snapshots/web-fetch/session.jsonl b/examples/acp-agent/tests/snapshots/web-fetch/session.jsonl index c6c34bc8e3..47c97b1cba 100644 --- a/examples/acp-agent/tests/snapshots/web-fetch/session.jsonl +++ b/examples/acp-agent/tests/snapshots/web-fetch/session.jsonl @@ -5,75 +5,9 @@ {"type":"step/start","seq":3,"time":1785078727730,"data":{"turn":1,"step":1}} {"type":"request/header","seq":4,"time":1785078727731,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-pro"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"assistant/chunk","seq":5,"time":1785078728804,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} -{"type":"assistant/chunk","seq":6,"time":1785078728805,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} -{"type":"assistant/chunk","seq":7,"time":1785078728943,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} -{"type":"assistant/chunk","seq":8,"time":1785078728989,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" wants"}}} -{"type":"assistant/chunk","seq":9,"time":1785078728989,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" me"}}} -{"type":"assistant/chunk","seq":10,"time":1785078728989,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} -{"type":"assistant/chunk","seq":11,"time":1785078728990,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" use"}}} -{"type":"assistant/chunk","seq":12,"time":1785078728990,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} -{"type":"assistant/chunk","seq":13,"time":1785078728990,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" web"}}} -{"type":"assistant/chunk","seq":14,"time":1785078729038,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"_f"}}} -{"type":"assistant/chunk","seq":15,"time":1785078729038,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"etch"}}} -{"type":"assistant/chunk","seq":16,"time":1785078729039,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" tool"}}} -{"type":"assistant/chunk","seq":17,"time":1785078729039,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" exactly"}}} -{"type":"assistant/chunk","seq":18,"time":1785078729085,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" once"}}} -{"type":"assistant/chunk","seq":19,"time":1785078729086,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} -{"type":"assistant/chunk","seq":20,"time":1785078729086,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" fetch"}}} -{"type":"assistant/chunk","seq":21,"time":1785078729086,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" http"}}} -{"type":"assistant/chunk","seq":22,"time":1785078729086,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"://"}}} -{"type":"assistant/chunk","seq":23,"time":1785078729086,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"127"}}} -{"type":"assistant/chunk","seq":24,"time":1785078729132,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} -{"type":"assistant/chunk","seq":25,"time":1785078729133,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"0"}}} -{"type":"assistant/chunk","seq":26,"time":1785078729133,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} -{"type":"assistant/chunk","seq":27,"time":1785078729133,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"0"}}} -{"type":"assistant/chunk","seq":28,"time":1785078729133,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} -{"type":"assistant/chunk","seq":29,"time":1785078729133,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"1"}}} -{"type":"assistant/chunk","seq":30,"time":1785078729182,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":":"}}} -{"type":"assistant/chunk","seq":31,"time":1785078729182,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"431"}}} -{"type":"assistant/chunk","seq":32,"time":1785078729183,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"17"}}} -{"type":"assistant/chunk","seq":33,"time":1785078729183,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"/m"}}} -{"type":"assistant/chunk","seq":34,"time":1785078729183,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"enu"}}} -{"type":"assistant/chunk","seq":35,"time":1785078729183,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":".html"}}} -{"type":"assistant/chunk","seq":36,"time":1785078729230,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":","}}} -{"type":"assistant/chunk","seq":37,"time":1785078729230,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" then"}}} -{"type":"assistant/chunk","seq":38,"time":1785078729230,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" reply"}}} -{"type":"assistant/chunk","seq":39,"time":1785078729230,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" with"}}} -{"type":"assistant/chunk","seq":40,"time":1785078729230,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" exactly"}}} -{"type":"assistant/chunk","seq":41,"time":1785078729231,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" \""}}} -{"type":"assistant/chunk","seq":42,"time":1785078729276,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"D"}}} -{"type":"assistant/chunk","seq":43,"time":1785078729277,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"ONE"}}} -{"type":"assistant/chunk","seq":44,"time":1785078729277,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"\"."}}} -{"type":"assistant/chunk","seq":45,"time":1785078729277,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" Let"}}} -{"type":"assistant/chunk","seq":46,"time":1785078729322,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" me"}}} -{"type":"assistant/chunk","seq":47,"time":1785078729323,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" do"}}} -{"type":"assistant/chunk","seq":48,"time":1785078729323,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" that"}}} -{"type":"assistant/chunk","seq":49,"time":1785078729323,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} +{"type":"reasoning-chunks","seq0":6,"time0":1785078728805,"data":{"turn":1,"step":1,"index":0,"dt":[138,46,0,0,1,0,0,48,0,1,0,46,1,0,0,0,0,46,1,0,0,0,0,49,0,1,0,0,0,47,0,0,0,0,1,45,1,0,0,45,1,0,0],"texts":["The"," user"," wants"," me"," to"," use"," the"," web","_f","etch"," tool"," exactly"," once"," to"," fetch"," http","://","127",".","0",".","0",".","1",":","431","17","/m","enu",".html",","," then"," reply"," with"," exactly"," \"","D","ONE","\"."," Let"," me"," do"," that","."]}} {"type":"assistant/chunk","seq":50,"time":1785078729463,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"tool-call"}}} -{"type":"assistant/chunk","seq":51,"time":1785078729464,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_sxjOyfDYN07koiE7jiIa5326","name":"web_fetch","argumentsDelta":""}}} -{"type":"assistant/chunk","seq":52,"time":1785078729511,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_sxjOyfDYN07koiE7jiIa5326","name":"web_fetch","argumentsDelta":"{"}}} -{"type":"assistant/chunk","seq":53,"time":1785078729511,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_sxjOyfDYN07koiE7jiIa5326","name":"web_fetch","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":54,"time":1785078729511,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_sxjOyfDYN07koiE7jiIa5326","name":"web_fetch","argumentsDelta":"url"}}} -{"type":"assistant/chunk","seq":55,"time":1785078729511,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_sxjOyfDYN07koiE7jiIa5326","name":"web_fetch","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":56,"time":1785078729511,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_sxjOyfDYN07koiE7jiIa5326","name":"web_fetch","argumentsDelta":": "}}} -{"type":"assistant/chunk","seq":57,"time":1785078729557,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_sxjOyfDYN07koiE7jiIa5326","name":"web_fetch","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":58,"time":1785078729557,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_sxjOyfDYN07koiE7jiIa5326","name":"web_fetch","argumentsDelta":"http"}}} -{"type":"assistant/chunk","seq":59,"time":1785078729557,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_sxjOyfDYN07koiE7jiIa5326","name":"web_fetch","argumentsDelta":"://"}}} -{"type":"assistant/chunk","seq":60,"time":1785078729558,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_sxjOyfDYN07koiE7jiIa5326","name":"web_fetch","argumentsDelta":"127"}}} -{"type":"assistant/chunk","seq":61,"time":1785078729604,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_sxjOyfDYN07koiE7jiIa5326","name":"web_fetch","argumentsDelta":"."}}} -{"type":"assistant/chunk","seq":62,"time":1785078729604,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_sxjOyfDYN07koiE7jiIa5326","name":"web_fetch","argumentsDelta":"0"}}} -{"type":"assistant/chunk","seq":63,"time":1785078729604,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_sxjOyfDYN07koiE7jiIa5326","name":"web_fetch","argumentsDelta":"."}}} -{"type":"assistant/chunk","seq":64,"time":1785078729604,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_sxjOyfDYN07koiE7jiIa5326","name":"web_fetch","argumentsDelta":"0"}}} -{"type":"assistant/chunk","seq":65,"time":1785078729604,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_sxjOyfDYN07koiE7jiIa5326","name":"web_fetch","argumentsDelta":"."}}} -{"type":"assistant/chunk","seq":66,"time":1785078729605,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_sxjOyfDYN07koiE7jiIa5326","name":"web_fetch","argumentsDelta":"1"}}} -{"type":"assistant/chunk","seq":67,"time":1785078729651,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_sxjOyfDYN07koiE7jiIa5326","name":"web_fetch","argumentsDelta":":"}}} -{"type":"assistant/chunk","seq":68,"time":1785078729652,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_sxjOyfDYN07koiE7jiIa5326","name":"web_fetch","argumentsDelta":"431"}}} -{"type":"assistant/chunk","seq":69,"time":1785078729652,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_sxjOyfDYN07koiE7jiIa5326","name":"web_fetch","argumentsDelta":"17"}}} -{"type":"assistant/chunk","seq":70,"time":1785078729652,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_sxjOyfDYN07koiE7jiIa5326","name":"web_fetch","argumentsDelta":"/m"}}} -{"type":"assistant/chunk","seq":71,"time":1785078729652,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_sxjOyfDYN07koiE7jiIa5326","name":"web_fetch","argumentsDelta":"enu"}}} -{"type":"assistant/chunk","seq":72,"time":1785078729652,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_sxjOyfDYN07koiE7jiIa5326","name":"web_fetch","argumentsDelta":".html"}}} -{"type":"assistant/chunk","seq":73,"time":1785078729697,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_sxjOyfDYN07koiE7jiIa5326","name":"web_fetch","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":74,"time":1785078729698,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_sxjOyfDYN07koiE7jiIa5326","name":"web_fetch","argumentsDelta":"}"}}} +{"type":"tool-call-chunks","seq0":51,"time0":1785078729464,"data":{"turn":1,"step":1,"index":1,"dt":[47,0,0,0,0,46,0,0,1,46,0,0,0,0,1,46,1,0,0,0,0,45,1],"id":"call_00_sxjOyfDYN07koiE7jiIa5326","name":"web_fetch","args":["","{","\"","url","\"",": ","\"","http","://","127",".","0",".","0",".","1",":","431","17","/m","enu",".html","\"","}"]}} {"type":"assistant/chunk","seq":75,"time":1785078729803,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user wants me to use the web_fetch tool exactly once to fetch http://127.0.0.1:43117/menu.html, then reply with exactly \"DONE\". Let me do that."}}}} {"type":"assistant/chunk","seq":76,"time":1785078729803,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_sxjOyfDYN07koiE7jiIa5326","name":"web_fetch","arguments":"{\"url\": \"http://127.0.0.1:43117/menu.html\"}"}}}} {"type":"assistant/chunk","seq":77,"time":1785078729803,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":5405,"outputTokens":103,"cacheReadTokens":0,"reasoningTokens":44}}}} @@ -84,37 +18,7 @@ {"type":"step/end","seq":82,"time":1785078729847,"data":{"turn":1,"step":1}} {"type":"step/start","seq":83,"time":1785078729848,"data":{"turn":1,"step":2}} {"type":"assistant/chunk","seq":84,"time":1785078730611,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} -{"type":"assistant/chunk","seq":85,"time":1785078730612,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} -{"type":"assistant/chunk","seq":86,"time":1785078730770,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} -{"type":"assistant/chunk","seq":87,"time":1785078730824,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" asked"}}} -{"type":"assistant/chunk","seq":88,"time":1785078730825,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" me"}}} -{"type":"assistant/chunk","seq":89,"time":1785078730825,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} -{"type":"assistant/chunk","seq":90,"time":1785078730825,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" fetch"}}} -{"type":"assistant/chunk","seq":91,"time":1785078730861,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} -{"type":"assistant/chunk","seq":92,"time":1785078730862,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" URL"}}} -{"type":"assistant/chunk","seq":93,"time":1785078730909,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":","}}} -{"type":"assistant/chunk","seq":94,"time":1785078730956,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" then"}}} -{"type":"assistant/chunk","seq":95,"time":1785078731002,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" reply"}}} -{"type":"assistant/chunk","seq":96,"time":1785078731003,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" with"}}} -{"type":"assistant/chunk","seq":97,"time":1785078731003,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" exactly"}}} -{"type":"assistant/chunk","seq":98,"time":1785078731003,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" \""}}} -{"type":"assistant/chunk","seq":99,"time":1785078731050,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"D"}}} -{"type":"assistant/chunk","seq":100,"time":1785078731050,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"ONE"}}} -{"type":"assistant/chunk","seq":101,"time":1785078731050,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"\"."}}} -{"type":"assistant/chunk","seq":102,"time":1785078731050,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" I"}}} -{"type":"assistant/chunk","seq":103,"time":1785078731050,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"'ve"}}} -{"type":"assistant/chunk","seq":104,"time":1785078731051,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" fetched"}}} -{"type":"assistant/chunk","seq":105,"time":1785078731097,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" it"}}} -{"type":"assistant/chunk","seq":106,"time":1785078731140,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} -{"type":"assistant/chunk","seq":107,"time":1785078731141,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" Now"}}} -{"type":"assistant/chunk","seq":108,"time":1785078731141,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" I"}}} -{"type":"assistant/chunk","seq":109,"time":1785078731141,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" just"}}} -{"type":"assistant/chunk","seq":110,"time":1785078731189,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" reply"}}} -{"type":"assistant/chunk","seq":111,"time":1785078731189,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" with"}}} -{"type":"assistant/chunk","seq":112,"time":1785078731235,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" \""}}} -{"type":"assistant/chunk","seq":113,"time":1785078731235,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"D"}}} -{"type":"assistant/chunk","seq":114,"time":1785078731235,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"ONE"}}} -{"type":"assistant/chunk","seq":115,"time":1785078731235,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"\"."}}} +{"type":"reasoning-chunks","seq0":85,"time0":1785078730612,"data":{"turn":1,"step":2,"index":0,"dt":[158,54,1,0,0,36,1,47,47,46,1,0,0,47,0,0,0,0,1,46,43,1,0,0,48,0,46,0,0,0],"texts":["The"," user"," asked"," me"," to"," fetch"," the"," URL",","," then"," reply"," with"," exactly"," \"","D","ONE","\"."," I","'ve"," fetched"," it","."," Now"," I"," just"," reply"," with"," \"","D","ONE","\"."]}} {"type":"assistant/chunk","seq":116,"time":1785078731235,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":1,"blockType":"text"}}} {"type":"assistant/chunk","seq":117,"time":1785078731236,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"D"}}} {"type":"assistant/chunk","seq":118,"time":1785078731282,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"ONE"}}} diff --git a/packages/web/tool-web/README.i18n.yaml b/packages/web/tool-web/README.i18n.yaml index 1e746ed566..44279a66be 100644 --- a/packages/web/tool-web/README.i18n.yaml +++ b/packages/web/tool-web/README.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 -README.md: 5fe48ced81a2cd02197cf8cc10a7d6567b17ffca -README.zh.md: 34ad08e290166ee6db2cd7b836746541d18aad52 +README.md: 44cb1ba2a2f4e1fba7e192d8b6645e0447ebf221 +README.zh.md: 35b390dd5407af16d84ab391dd8351f784c60035 diff --git a/packages/web/tool-web/README.md b/packages/web/tool-web/README.md index 5fe48ced81..44cb1ba2a2 100644 --- a/packages/web/tool-web/README.md +++ b/packages/web/tool-web/README.md @@ -26,8 +26,9 @@ The normalized seam results are also the canonical tool values: `WebSearchResult | `searchMaxResults` | `8` | Upper bound on sources returned by one `web_search` call (the seam truncates a longer provider list and flags it). | | `fetchTimeoutMs` | `30000` | Cooperative tool-call timeout budget (ms) for `web_fetch`. | | `searchTimeoutMs` | `30000` | Cooperative tool-call timeout budget (ms) for `web_search`. | +| `fetchMaxOutputChars` | `200000` | Cap on one `web_fetch` output's characters — header, rendered body, and footer together; a cut body gets the truncation notice. | -`fetchTimeoutMs`/`searchTimeoutMs` declare each tool's cooperative timeout budget (attached as `ToolDefinition.timeoutMs`), enforced by [`@deepseek-ai/dsh-timeout-policy`](../../timeout/timeout-policy/README.md); the model-facing schema exposes no timeout argument. +`fetchTimeoutMs`/`searchTimeoutMs` declare each tool's cooperative timeout budget (attached as `ToolDefinition.timeoutMs`), enforced by [`@deepseek-ai/dsh-timeout-policy`](../../timeout/timeout-policy/README.md); the model-facing schema exposes no timeout argument. `fetchMaxOutputChars` bounds the complete rendered output because markdown escaping can expand converted HTML past a provider's body cap (worst case ~2×); the default is 2× the local provider's default 100,000-character body cap, so it never cuts what that bound already admits. ```yaml - id: tool-web @@ -126,6 +127,6 @@ Append-only; newly visible content follows the reusable request prefix and does ## Known Limitations and Deferred Work -- **HTML→markdown conversion falls back to raw HTML on pathological input** — [turndown](https://github.com/mixmark-io/turndown) (with GFM tables/strikethrough) converts fetched HTML through a real DOM, but its recursive walk overflows on absurdly deep nesting (thousands of levels); such a body passes through unconverted rather than erroring ([Agent Note](../../../.agents/notes/implemented/simplification/2026-07-26-turndown-for-tool-web-html-markdown.md)). +- **HTML→markdown conversion falls back to raw HTML on pathological input** — [turndown](https://github.com/mixmark-io/turndown) (with GFM tables/strikethrough) converts fetched HTML through a real DOM, but the synchronous walk is superlinear on deep unclosed nesting, so bodies nested past a fixed 512-level preflight bound pass through unconverted (as does anything that still makes turndown throw) rather than stalling the event loop or erroring ([Agent Note](../../../.agents/notes/implemented/simplification/2026-07-26-turndown-for-tool-web-html-markdown.md)). - **The model-facing surface is minimal by design, with promotions deferred** — `max_results` stays a config bound (not a model argument), and `web_fetch` takes only `url` (no `format`/`prompt`/LLM-summarization mode); both are named later steps in [the seam Agent Note](../../../.agents/notes/implemented/architecture/2026-06-24-web-capability-seam.md). - **No web-specific permission policy** — both tools execute without requesting `ctx.approval`; a deployment that needs confirmation must add a `tools/pre-execute` policy, and the package does not define persistent URL/domain grants. diff --git a/packages/web/tool-web/README.zh.md b/packages/web/tool-web/README.zh.md index 34ad08e290..35b390dd54 100644 --- a/packages/web/tool-web/README.zh.md +++ b/packages/web/tool-web/README.zh.md @@ -26,8 +26,9 @@ | `searchMaxResults` | `8` | 一次 `web_search` 调用返回的源数量上限（seam 截断更长的提供方列表并标记）。 | | `fetchTimeoutMs` | `30000` | `web_fetch` 的协作式工具调用超时预算（ms）。 | | `searchTimeoutMs` | `30000` | `web_search` 的协作式工具调用超时预算（ms）。 | +| `fetchMaxOutputChars` | `200000` | 单次 `web_fetch` 输出的字符上限——状态头、渲染后的主体与页脚合并计算；被截断的主体带截断提示。 | -`fetchTimeoutMs`／`searchTimeoutMs` 声明每个工具的协作式超时预算（附加为 `ToolDefinition.timeoutMs`），由 [`@deepseek-ai/dsh-timeout-policy`](../../timeout/timeout-policy/README.md) 强制执行；面向模型的 schema 不公开超时参数。 +`fetchTimeoutMs`／`searchTimeoutMs` 声明每个工具的协作式超时预算（附加为 `ToolDefinition.timeoutMs`），由 [`@deepseek-ai/dsh-timeout-policy`](../../timeout/timeout-policy/README.md) 强制执行；面向模型的 schema 不公开超时参数。`fetchMaxOutputChars` 对完整渲染输出设上限：markdown 转义可能让转换后的 HTML 超出提供方的主体上限（最坏约 2 倍）；默认值取本地提供方默认 100,000 字符主体上限的 2 倍，因此绝不会削减该上限本已允许的内容。 ```yaml - id: tool-web @@ -126,6 +127,6 @@ Use the web_fetch tool to retrieve the content of a specific HTTP(S) URL (for ex ## 已知限制与暂缓事项 -- **HTML→markdown 转换在病态输入上回退为原始 HTML**：[turndown](https://github.com/mixmark-io/turndown)（带 GFM 表格／删除线）通过真实 DOM 转换抓取到的 HTML，但其递归遍历在极深嵌套（数千层）上会栈溢出；此类主体不经转换原样通过，而非报错（[决策记录](../../../.agents/notes/implemented/simplification/2026-07-26-turndown-for-tool-web-html-markdown.md)）。 +- **HTML→markdown 转换在病态输入上回退为原始 HTML**：[turndown](https://github.com/mixmark-io/turndown)（带 GFM 表格／删除线）通过真实 DOM 转换抓取到的 HTML，但同步遍历在深层未闭合嵌套上呈超线性，因此嵌套超过固定 512 层预检上限的主体不经转换原样通过（仍让 turndown 抛异常的输入同样如此），而非阻塞事件循环或报错（[决策记录](../../../.agents/notes/implemented/simplification/2026-07-26-turndown-for-tool-web-html-markdown.md)）。 - **面向模型的表层有意保持最小，提升项暂缓**：`max_results` 保持为配置上限（不是模型参数），`web_fetch` 只接受 `url`（没有 `format`／`prompt`／LLM 摘要模式）；两项都列为 [seam Agent Note](../../../.agents/notes/implemented/architecture/2026-06-24-web-capability-seam.md) 中的后续步骤。 - **没有 web 专用权限策略**：两个工具都不会请求 `ctx.approval` 就直接执行；需要确认的部署必须添加 `tools/pre-execute` 策略，该包不定义持久 URL／domain 授权。 diff --git a/packages/web/tool-web/src/fetch.ts b/packages/web/tool-web/src/fetch.ts index 60c0f33507..e909ea25be 100644 --- a/packages/web/tool-web/src/fetch.ts +++ b/packages/web/tool-web/src/fetch.ts @@ -44,23 +44,69 @@ export function parseFetchArgs(args: { url: string }): { url: string } { return { url: args.url } } +/** + * Nesting-depth ceiling above which HTML skips conversion and passes through + * raw. Conversion runs synchronously on the event loop, and unclosed-tag + * nesting makes domino's tree (and turndown's walk over it) superlinear — + * measured: depth 512 ≈ 0.15s, 2,000 ≈ 2s, 20,000 ≈ 5s — during which the + * cooperative `fetchTimeoutMs` timer cannot fire. Real pages nest a few dozen + * levels; 512 is far above content and far below weaponizable. A robustness + * invariant, not a tunable. + */ +const MAX_CONVERSION_DEPTH = 512 + +/** Elements that never take a closing tag, so they must not count toward nesting depth. */ +const VOID_ELEMENTS = new Set([ + 'area', 'base', 'br', 'col', 'embed', 'hr', 'img', 'input', + 'link', 'meta', 'param', 'source', 'track', 'wbr', +]) + +/** + * Estimate the maximum element nesting depth of an HTML string with one linear + * tag scan. Overestimates when markup-like text sits inside `script`/`style` + * bodies or comments (the scan does not parse those), which can only cause a + * spurious raw-HTML fallback, never a missed bound. + * + * @param html - the decoded HTML body. + * @returns the deepest open-element count the scan reaches. + */ +export function htmlNestingDepth(html: string): number { + let depth = 0 + let max = 0 + for (const tag of html.matchAll(/<(\/?)([a-zA-Z][a-zA-Z0-9-]*)[^>]*?(\/?)>/g)) { + const [, closing, rawName = '', selfClosing] = tag + const name = rawName.toLowerCase() + if (VOID_ELEMENTS.has(name) || selfClosing === '/') continue + if (closing === '/') { + if (depth > 0) depth -= 1 + } else { + depth += 1 + if (depth > max) max = depth + } + } + return max +} + /** * Render a fetched body to model-facing markdown text. * * @param body - the decoded body; `html` is converted via turndown, `text` - * passes through verbatim. When turndown throws (deeply pathological HTML - * overflows its recursive DOM walk), the raw HTML passes through instead — - * a degraded page beats an error for a body the provider already decoded. + * passes through verbatim. HTML nested beyond {@link MAX_CONVERSION_DEPTH} + * skips conversion up front (the synchronous walk over such trees is + * superlinear and blocks the event loop past the cooperative timeout), and + * when turndown itself throws the raw HTML passes through instead — a + * degraded page beats an error for a body the provider already decoded. * @returns the text for the tool's output block. */ export function renderBody(body: WebFetchBody): string { switch (body.kind) { case 'html': + if (htmlNestingDepth(body.content) > MAX_CONVERSION_DEPTH) return body.content try { return turndown.turndown(body.content) } catch { - // turndown's DOM walk recurses per element; pathological nesting (a - // few thousand levels) throws RangeError. Provider errors stay + // turndown's DOM walk recurses per element; malformed markup the depth + // scan cannot see can still throw RangeError. Provider errors stay // structured WebErrors upstream; conversion failure downgrades to raw HTML. return body.content } @@ -72,17 +118,28 @@ export function renderBody(body: WebFetchBody): string { } } +/** The truncation notice appended when the provider or the output cap cut content. */ +const TRUNCATION_FOOTER = '\n\n(Content truncated. Fetch a more specific URL or section for the full text.)' + /** - * Format a fetch result as one model-facing text block. + * Format a fetch result as one model-facing text block, bounded as a whole. + * Markdown escaping can expand converted HTML (worst case ~2× the provider's + * body cap), so the bound applies here, where the complete output — header, + * rendered body, and footer — is known. * * @param result - the seam's fetch outcome. + * @param maxOutputChars - cap on the complete returned string; a cut body gets + * the same fetch-something-narrower notice as provider-side truncation. * @returns a `Fetched (HTTP )` header, the rendered body, and a - * fetch-something-narrower notice when the provider truncated the content. + * truncation notice when the provider or the cap cut the content. */ -export function formatFetchOutput(result: WebFetchResult): string { - const header = `Fetched ${result.url} (HTTP ${result.statusCode})` - const footer = result.truncated ? '\n\n(Content truncated. Fetch a more specific URL or section for the full text.)' : '' - return `${header}\n\n${renderBody(result.body)}${footer}` +export function formatFetchOutput(result: WebFetchResult, maxOutputChars: number): string { + const header = `Fetched ${result.url} (HTTP ${result.statusCode})\n\n` + const body = renderBody(result.body) + const full = `${header}${body}${result.truncated ? TRUNCATION_FOOTER : ''}` + if (full.length <= maxOutputChars) return full + const budget = Math.max(0, maxOutputChars - header.length - TRUNCATION_FOOTER.length) + return `${header}${body.slice(0, budget)}${TRUNCATION_FOOTER}` } /** @@ -102,8 +159,11 @@ export function presentFetchCall(args: { url: string }): GenericCallView { * registrations; both are effect-scoped and unregister on plugin dispose. * @param timeoutMs - the cooperative tool-call budget (ms) attached as the tool's * `ToolDefinition.timeoutMs` for `@deepseek-ai/dsh-timeout-policy` to enforce. + * @param maxOutputChars - cap on the complete rendered tool output (see + * {@link formatFetchOutput}); markdown escaping can outgrow the provider's + * body cap, so the model-context bound is enforced on the rendered result. */ -export function applyWebFetchTool(ctx: Context, timeoutMs: number): void { +export function applyWebFetchTool(ctx: Context, timeoutMs: number, maxOutputChars: number): void { ctx.systemPrompt.section({ name: 'tool:web_fetch', order: 111, @@ -147,7 +207,7 @@ export function applyWebFetchTool(ctx: Context, timeoutMs: number): void { truncated: { type: 'boolean', required: true }, }, }, - render: (_args, value) => [{ type: 'text', text: formatFetchOutput(value) }], + render: (_args, value) => [{ type: 'text', text: formatFetchOutput(value, maxOutputChars) }], }, timeoutMs, // Provider reads do not mutate parent-agent state. diff --git a/packages/web/tool-web/src/index.ts b/packages/web/tool-web/src/index.ts index e7ac4b2453..4a0ea5202c 100644 --- a/packages/web/tool-web/src/index.ts +++ b/packages/web/tool-web/src/index.ts @@ -13,7 +13,7 @@ import { applyWebSearchTool, WEB_SEARCH_MAX_RESULTS } from './search.ts' import { applyWebFetchTool } from './fetch.ts' export { WEB_SEARCH_MAX_RESULTS, applyWebSearchTool, formatSearchOutput, parseSearchArgs, presentSearchCall } from './search.ts' -export { applyWebFetchTool, formatFetchOutput, parseFetchArgs, presentFetchCall, renderBody } from './fetch.ts' +export { applyWebFetchTool, formatFetchOutput, htmlNestingDepth, parseFetchArgs, presentFetchCall, renderBody } from './fetch.ts' /** Cordis plugin name used by loader diagnostics. */ export const name = 'tool-web' @@ -24,7 +24,16 @@ export const inject = ['tools', 'web', 'systemPrompt'] /** Default cooperative tool-call timeout budget (ms) for the web tools. */ export const DEFAULT_WEB_TOOL_TIMEOUT_MS = 30_000 -/** Plugin config: which web tools to register, the source cap, and per-tool budgets. */ +/** + * Default cap on one `web_fetch` output's characters. Markdown escaping can + * roughly double converted HTML, so this sits at 2× the local provider's + * default 100,000-char body cap: it never cuts what that composition's + * provider bound already admits, while restoring a model-context bound for + * providers with larger or absent body caps. + */ +export const DEFAULT_FETCH_MAX_OUTPUT_CHARS = 200_000 + +/** Plugin config: which web tools to register, the source cap, per-tool budgets, and the fetch output cap. */ export interface Config { /** Register `web_search`. Defaults to true. */ search?: boolean @@ -36,6 +45,8 @@ export interface Config { fetchTimeoutMs?: number /** Cooperative timeout budget (ms) for `web_search`. Defaults to 30000. */ searchTimeoutMs?: number + /** Cap on one `web_fetch` output's characters (header, rendered body, and footer). Defaults to 200000. */ + fetchMaxOutputChars?: number } export const Config: z = z.object({ @@ -44,6 +55,7 @@ export const Config: z = z.object({ searchMaxResults: z.number().default(WEB_SEARCH_MAX_RESULTS), fetchTimeoutMs: z.number().default(DEFAULT_WEB_TOOL_TIMEOUT_MS), searchTimeoutMs: z.number().default(DEFAULT_WEB_TOOL_TIMEOUT_MS), + fetchMaxOutputChars: z.number().default(DEFAULT_FETCH_MAX_OUTPUT_CHARS), }) /** The shape after schemastery applies its defaults to every field. */ @@ -71,6 +83,7 @@ export function apply(ctx: Context, config: Config): void { assertPositiveInteger('searchMaxResults', resolved.searchMaxResults) assertPositiveInteger('fetchTimeoutMs', resolved.fetchTimeoutMs) assertPositiveInteger('searchTimeoutMs', resolved.searchTimeoutMs) + assertPositiveInteger('fetchMaxOutputChars', resolved.fetchMaxOutputChars) if (resolved.search) applyWebSearchTool(ctx, resolved.searchMaxResults, resolved.searchTimeoutMs) - if (resolved.fetch) applyWebFetchTool(ctx, resolved.fetchTimeoutMs) + if (resolved.fetch) applyWebFetchTool(ctx, resolved.fetchTimeoutMs, resolved.fetchMaxOutputChars) } diff --git a/packages/web/tool-web/tests/tool-web.spec.ts b/packages/web/tool-web/tests/tool-web.spec.ts index f9ffb1b5c5..79af9cbd2a 100644 --- a/packages/web/tool-web/tests/tool-web.spec.ts +++ b/packages/web/tool-web/tests/tool-web.spec.ts @@ -1,5 +1,6 @@ -import { describe, expect, it } from 'vitest' +import { describe, expect, it, vi } from 'vitest' import { Context } from 'cordis' +import TurndownService from 'turndown' import { CallId } from '@deepseek-ai/dsh-llm' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { type ToolExecutionResult } from '@deepseek-ai/dsh-tools' @@ -9,6 +10,7 @@ import * as ToolWeb from '@deepseek-ai/dsh-tool-web' import { formatSearchOutput, formatFetchOutput, + htmlNestingDepth, parseSearchArgs, parseFetchArgs, presentSearchCall, @@ -92,11 +94,13 @@ describe('search formatting', () => { }) describe('fetch formatting', () => { + const NO_CAP = 1_000_000 + it('renders an html body to markdown text with a status header', () => { const out = formatFetchOutput({ url: 'https://a.test', statusCode: 200, truncated: false, body: { kind: 'html', content: '

    Title

    Body text

    ' }, - }) + }, NO_CAP) expect(out).toContain('Fetched https://a.test (HTTP 200)') expect(out).toContain('# Title') expect(out).toContain('Body text') @@ -106,11 +110,37 @@ describe('fetch formatting', () => { const out = formatFetchOutput({ url: 'https://a.test', statusCode: 200, truncated: true, body: { kind: 'text', content: 'plain' }, - }) + }, NO_CAP) expect(out).toContain('plain') expect(out).toContain('Content truncated') }) + it('caps the complete output and notes truncation, even when markdown escaping expands the body', () => { + // 1,000 underscores render as 2,000 escaped characters — conversion can + // outgrow a provider-side body cap, so the bound applies to the output. + const out = formatFetchOutput({ + url: 'https://a.test', statusCode: 200, truncated: false, + body: { kind: 'html', content: `

    ${'_'.repeat(1000)}

    ` }, + }, 500) + expect(out.length).toBeLessThanOrEqual(500) + expect(out).toContain('Fetched https://a.test (HTTP 200)') + expect(out).toContain('\\_\\_') + expect(out).toContain('Content truncated') + // Exact and tiny caps: the complete result is bounded, header and footer included. + const exact = formatFetchOutput({ + url: 'https://a.test', statusCode: 200, truncated: false, + body: { kind: 'text', content: 'abc' }, + }, 'Fetched https://a.test (HTTP 200)\n\nabc'.length) + expect(exact).toBe('Fetched https://a.test (HTTP 200)\n\nabc') + const tiny = formatFetchOutput({ + url: 'https://a.test', statusCode: 200, truncated: true, + body: { kind: 'text', content: 'abcdef' }, + }, 10) + expect(tiny).toContain('Fetched https://a.test (HTTP 200)') + expect(tiny).toContain('Content truncated') + expect(tiny).not.toContain('abcdef') + }) + it('renderBody dispatches on kind', () => { expect(renderBody({ kind: 'text', content: 'x' })).toBe('x') expect(renderBody({ kind: 'html', content: '

    y

    ' })).toBe('y') @@ -129,14 +159,38 @@ describe('fetch formatting', () => { .toBe('**bold _italic_**\n\n> quoted') }) - it('falls back to the raw html body when turndown throws on pathological nesting', { timeout: 60_000 }, () => { - // Nesting past V8's default stack overflows turndown/domino's recursive - // walk with a RangeError (measured: 4k levels throw on the main thread, - // 8k in a worker); 20k adds margin over either stack size. The raw body - // must pass through instead of throwing. + it('passes deeply nested html through raw without attempting conversion', () => { + // Unclosed-tag nesting makes the synchronous conversion superlinear + // (seconds at 20k levels, during which the cooperative timeout cannot + // fire), so the depth preflight skips conversion entirely; this must + // return fast, not merely not-throw. const depth = 20_000 const pathological = '
    '.repeat(depth) + 'x' + '
    '.repeat(depth) + const started = Date.now() expect(renderBody({ kind: 'html', content: pathological })).toBe(pathological) + expect(Date.now() - started).toBeLessThan(2_000) + }) + + it('htmlNestingDepth counts open elements, ignoring void and self-closing tags', () => { + expect(htmlNestingDepth('

    x

    ')).toBe(2) + expect(htmlNestingDepth('

    ')).toBe(1) + expect(htmlNestingDepth('

    x

    ')).toBe(1) + expect(htmlNestingDepth('plain text, no tags')).toBe(0) + expect(htmlNestingDepth('
    '.repeat(600))).toBe(600) + }) + + it('falls back to the raw html when turndown throws despite a shallow depth scan', () => { + // Comments hide markup from the depth scan by design (it may only + // over-count, never under-count real elements); simulate the residual + // turndown failure path with a converter throw instead. + const spy = vi.spyOn(TurndownService.prototype, 'turndown').mockImplementation(() => { + throw new RangeError('Maximum call stack size exceeded') + }) + try { + expect(renderBody({ kind: 'html', content: '

    x

    ' })).toBe('

    x

    ') + } finally { + spy.mockRestore() + } }) it('validates url (non-empty), no timeout parameter', () => { From 5fa74343aab77f543c3dfdac2ee7d387e769132c Mon Sep 17 00:00:00 2001 From: Chinesezjc Date: Mon, 27 Jul 2026 12:54:35 +0800 Subject: [PATCH 15/36] docs(ci): six always-on instances, no pre-registered spares The spare tier is retired. Steady-state pool load is one serial standby job per master push, so six always-on instances already are the failover capacity; pre-registered offline runners are a silently expiring guarantee (GitHub garbage-collects them after 30 days offline). Incident-time extra capacity is a one-minute org-token registration, now documented in the runbook. --- ...-07-22-evidence-based-larger-hosted-runners.i18n.yaml | 6 +++--- .../2026-07-22-evidence-based-larger-hosted-runners.md | 2 +- ...2026-07-22-evidence-based-larger-hosted-runners.zh.md | 2 +- .../process/2026-07-26-ci-failover-runbook.i18n.yaml | 6 +++--- .../process/2026-07-26-ci-failover-runbook.md | 9 +++------ .../process/2026-07-26-ci-failover-runbook.zh.md | 9 +++------ 6 files changed, 14 insertions(+), 20 deletions(-) diff --git a/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.i18n.yaml b/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.i18n.yaml index 84a10e5ab9..5ebd95248c 100644 --- a/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.i18n.yaml +++ b/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.i18n.yaml @@ -1,6 +1,6 @@ # Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each # 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 -2026-07-22-evidence-based-larger-hosted-runners.md: 21e602b2b5850176df981dcf448f4f827b756719 -2026-07-22-evidence-based-larger-hosted-runners.zh.md: ba49ff18ac304f4078d4c8ebfd00bb1a85ada0b3 +# pnpm run verify-translation-pairing --write .agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.md +2026-07-22-evidence-based-larger-hosted-runners.md: 5b399be5571ddaf1f775ba43a2233198b8e09b18 +2026-07-22-evidence-based-larger-hosted-runners.zh.md: 40970ec33c1a16af85ea47be3fc932209efdd654 diff --git a/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.md b/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.md index 21e602b2b5..5b399be557 100644 --- a/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.md +++ b/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.md @@ -52,7 +52,7 @@ The process-bound coverage project contains exactly five suite files. Thirty-two Complete serial Linux, macOS, and Windows references run only when `master` moves. Pull requests use the enterprise required path plus standard-hosted compatibility jobs, while other larger-runner sizes run only by manual dispatch. -An additional serial Linux reference runs on the in-house self-hosted pool (`vm-backup` label: a 64-core VM with four always-on systemd-managed runner instances plus four registered spares) on every `master` push. It is a hot-standby drill, not a required check: each run re-proves that the persistent VM can execute the complete unsharded aggregate. The actual switch is pre-wired: the three required Linux jobs resolve their pool through the admin-only `DSH_CI_FAILOVER` repository variable, so an outage response is setting one variable and re-running — no merge, which would be deadlocked behind the failing checks themselves ([runbook](2026-07-26-ci-failover-runbook.md)). Because the standby lane is push-triggered, it always executes the base branch's workflow definition — no pull-request-editable path can route code to these runners, and the repository additionally keeps forking disabled. +An additional serial Linux reference runs on the in-house self-hosted pool (`vm-backup` label: a 64-core VM with six always-on systemd-managed runner instances) on every `master` push. It is a hot-standby drill, not a required check: each run re-proves that the persistent VM can execute the complete unsharded aggregate. The actual switch is pre-wired: the three required Linux jobs resolve their pool through the admin-only `DSH_CI_FAILOVER` repository variable, so an outage response is setting one variable and re-running — no merge, which would be deadlocked behind the failing checks themselves ([runbook](2026-07-26-ci-failover-runbook.md)). Because the standby lane is push-triggered, it always executes the base branch's workflow definition — no pull-request-editable path can route code to these runners, and the repository additionally keeps forking disabled. ## Alternatives considered diff --git a/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.zh.md b/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.zh.md index ba49ff18ac..40970ec33c 100644 --- a/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.zh.md +++ b/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.zh.md @@ -52,7 +52,7 @@ Windows 仓库工作在超过 16 核后收益很小，但 32 核池可以让完 只有在 `master` 移动时，才运行完整的 Linux、macOS 和 Windows 串行参考。拉取请求使用企业级运行器必需路径和标准托管兼容性作业，其他大型运行器规格仅通过手动触发运行。 -另有一条串行 Linux 参考在每次 `master` 推送时运行于公司自有的自托管池（`vm-backup` 标签：一台 64 核虚拟机，运行 4 个常驻的 systemd 管理运行器实例，另有 4 个已注册备用位）。它是热备演练而非必需检查：每次运行都重新证明这台持久化虚拟机能够执行完整的未分片聚合流程。实际切换机制已预先布线：三个必需 Linux 作业通过仅限管理员的仓库变量 `DSH_CI_FAILOVER` 解析运行器池，因此故障响应就是设置一个变量并重跑——无需合并（合并本身会被正在失败的检查死锁）（[切换手册](2026-07-26-ci-failover-runbook.md)）。该热备通道由 push 触发，执行的始终是基线分支自身的工作流定义——不存在任何可由拉取请求编辑的路径能把代码路由到这些运行器上；此外仓库继续保持禁用 fork。 +另有一条串行 Linux 参考在每次 `master` 推送时运行于公司自有的自托管池（`vm-backup` 标签：一台 64 核虚拟机，运行 6 个常驻的 systemd 管理运行器实例）。它是热备演练而非必需检查：每次运行都重新证明这台持久化虚拟机能够执行完整的未分片聚合流程。实际切换机制已预先布线：三个必需 Linux 作业通过仅限管理员的仓库变量 `DSH_CI_FAILOVER` 解析运行器池，因此故障响应就是设置一个变量并重跑——无需合并（合并本身会被正在失败的检查死锁）（[切换手册](2026-07-26-ci-failover-runbook.zh.md)）。该热备通道由 push 触发，执行的始终是基线分支自身的工作流定义——不存在任何可由拉取请求编辑的路径能把代码路由到这些运行器上；此外仓库继续保持禁用 fork。 ## 曾考虑的替代方案 diff --git a/.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.i18n.yaml b/.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.i18n.yaml index a2725da1b2..efb5fdd1cc 100644 --- a/.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.i18n.yaml +++ b/.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.i18n.yaml @@ -1,6 +1,6 @@ # Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each # 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 -2026-07-26-ci-failover-runbook.md: db8e0676ecc6eeaea16438e7868ccf9ac43887cc -2026-07-26-ci-failover-runbook.zh.md: b3b4149f460784e88ce03458fc556f402c38fa2f +# pnpm run verify-translation-pairing --write .agents/notes/implemented/process/2026-07-26-ci-failover-runbook.md +2026-07-26-ci-failover-runbook.md: 0bce83e0f9c842fa3dd73ae9c0a3eefc0975cdae +2026-07-26-ci-failover-runbook.zh.md: 4bc6c67bab754ad3f0127557b0d5e04f7934c8a2 diff --git a/.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.md b/.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.md index db8e0676ec..0bce83e0f9 100644 --- a/.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.md +++ b/.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.md @@ -14,7 +14,7 @@ Each of the three required Linux jobs resolves its runner pool through the `DSH_ ### What the in-house pool is -`vm-backup`: one 64-core VM, four always-on systemd-managed runner instances, four registered spares. Check the latest `serial / linux (self-hosted standby)` run before switching: a green standby is verified-yesterday capacity. +`vm-backup`: one 64-core VM, six always-on systemd-managed runner instances. Check the latest `serial / linux (self-hosted standby)` run before switching: a green standby is verified-yesterday capacity. ### Switch (repo admin, ~1 minute, no merge) @@ -24,15 +24,12 @@ Each of the three required Linux jobs resolves its runner pool through the `DSH_ ### Capacity during failover -Four always-on instances absorb normal PR traffic. If queues build, bring the four registered spares online on the VM (no token needed — they are already registered): +Six always-on instances absorb normal PR traffic (the pool's steady-state load is one serial standby job per master push, so failover capacity is effectively the full pool). If queues still build, register additional instances with an org registration token (org Settings → Actions → Runners → New runner) — cloning an existing runner directory and running `config.sh` takes about a minute per instance. -```bash -for i in 7 8 9 10; do cd /data_local/actions-runner-$i && sudo ./svc.sh install ubuntu && sudo ./svc.sh start; done -``` ### Switch back -Delete the `DSH_CI_FAILOVER` variable (or set it to anything other than `selfhosted`). New runs resolve back to the hosted enterprise pools. Stop the spare instances if they were started. +Delete the `DSH_CI_FAILOVER` variable (or set it to anything other than `selfhosted`). New runs resolve back to the hosted enterprise pools. Remove any extra instances that were registered during the incident. ### Trust boundary diff --git a/.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.zh.md b/.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.zh.md index b3b4149f46..4bc6c67bab 100644 --- a/.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.zh.md +++ b/.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.zh.md @@ -14,7 +14,7 @@ Status: implemented ### 自有池是什么 -`vm-backup`：一台 64 核虚拟机，4 个常驻 systemd 管理的运行器实例，另有 4 个已注册备用位。切换前先看 `serial / linux (self-hosted standby)` 最近一次运行：绿色 = 这套环境昨天刚被全量验证过。 +`vm-backup`：一台 64 核虚拟机，6 个常驻 systemd 管理的运行器实例。切换前先看 `serial / linux (self-hosted standby)` 最近一次运行：绿色 = 这套环境昨天刚被全量验证过。 ### 切换步骤（仓库管理员，约 1 分钟，无需合并） @@ -24,15 +24,12 @@ Status: implemented ### 切换期间的容量 -4 个常驻实例可承接正常 PR 流量。若出现排队，在虚拟机上把 4 个已注册的备用位拉起（无需 token——它们已注册）： +6 个常驻实例可承接正常 PR 流量（该池平时唯一的稳态负载是每次 master 推送一个串行热备作业，故障切换时几乎全池可用）。若仍出现排队，用组织级注册 token（组织 Settings → Actions → Runners → New runner）追加注册实例——复制现有 runner 目录再跑 `config.sh`，每个约一分钟。 -```bash -for i in 7 8 9 10; do cd /data_local/actions-runner-$i && sudo ./svc.sh install ubuntu && sudo ./svc.sh start; done -``` ### 切回 -删除 `DSH_CI_FAILOVER` 变量（或改为 `selfhosted` 以外的任何值），新的运行即解析回托管企业池。若启动过备用实例，将其停止。 +删除 `DSH_CI_FAILOVER` 变量（或改为 `selfhosted` 以外的任何值），新的运行即解析回托管企业池。若故障期间追加注册过实例，将其移除。 ### 信任边界 From 1a8225ee6cc62438a0c7c54e19ee76ba76b61b33 Mon Sep 17 00:00:00 2001 From: Ubuntu Date: Mon, 27 Jul 2026 14:35:05 +0800 Subject: [PATCH 16/36] ci: retrigger after failover switch From 7bd96af5eb8d889b0652f1d4972a4e3e4c9649e2 Mon Sep 17 00:00:00 2001 From: NI0317 Date: Mon, 27 Jul 2026 14:37:04 +0800 Subject: [PATCH 17/36] fix(workspace): make deletion recoverable --- ...-workspace-registration-deletion.i18n.yaml | 4 +- ...6-07-27-workspace-registration-deletion.md | 8 +- ...7-27-workspace-registration-deletion.zh.md | 8 +- apps/web/tests/workspace-management.e2e.ts | 29 ++++ .../runtime/src/client/workspaces/manager.ts | 10 +- .../ui-workspace/src/client/rows/Rows.tsx | 4 + .../tests/api-proxy-workspace.spec.ts | 6 + packages/workspace/workspace/README.i18n.yaml | 4 +- packages/workspace/workspace/README.md | 2 + packages/workspace/workspace/README.zh.md | 2 + packages/workspace/workspace/src/index.ts | 75 ++++++++- packages/workspace/workspace/src/spec.ts | 11 ++ .../workspace/tests/workspace.spec.ts | 151 +++++++++++++++++- 13 files changed, 294 insertions(+), 20 deletions(-) diff --git a/.agents/notes/implemented/feature/2026-07-27-workspace-registration-deletion.i18n.yaml b/.agents/notes/implemented/feature/2026-07-27-workspace-registration-deletion.i18n.yaml index 847b040457..93c78373c6 100644 --- a/.agents/notes/implemented/feature/2026-07-27-workspace-registration-deletion.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-07-27-workspace-registration-deletion.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/feature/2026-07-27-workspace-registration-deletion.md -2026-07-27-workspace-registration-deletion.md: cae01d529bc6fd97da6fb61839bd5ec8e21557e2 -2026-07-27-workspace-registration-deletion.zh.md: 76377ebc5e93101e1e3efce1d29c3c654df032c2 +2026-07-27-workspace-registration-deletion.md: 58ae5c4bef2cf1cb0a0158eda5eb37daf2e9703d +2026-07-27-workspace-registration-deletion.zh.md: 7a79a1ccc53a0d4fd7e5ab453239ade955313c6e diff --git a/.agents/notes/implemented/feature/2026-07-27-workspace-registration-deletion.md b/.agents/notes/implemented/feature/2026-07-27-workspace-registration-deletion.md index cae01d529b..58ae5c4bef 100644 --- a/.agents/notes/implemented/feature/2026-07-27-workspace-registration-deletion.md +++ b/.agents/notes/implemented/feature/2026-07-27-workspace-registration-deletion.md @@ -22,6 +22,8 @@ Registry operations serialize create and delete. Deletion first writes the Works The Host stream keeps its committed-id set through the preceding global-order write and removes the id only on the table deletion. Create rollback therefore emits no false removal, while every connected tab receives exactly the id needed to delete its projection. +Create and delete write a durable `pendingMutation` before their record/order pair can diverge. Startup completes only the named create or delete and clears the marker; it never infers crash provenance from an orphan row alone. Unmarked order/table divergence therefore retains the registry's fail-loud corruption behavior. A deletion whose table write committed but marker cleanup failed still reports success—the requested state and removal frame are already committed—and the next startup clears that marker idempotently. + ## Client convergence `WorkspaceManager` treats both `host/workspace-changed` and `host/workspace-removed` as ordered deltas replayed over an in-flight `workspace.list` response. A successful unary delete removes the row immediately instead of waiting for its own stream echo. Removal is idempotent, and a process-local tombstone rejects late changed frames or stale baseline rows for the never-reused Workspace id. A reconnect still refreshes from `workspace.list`; Session state is never pruned by a Workspace delta. @@ -40,14 +42,16 @@ The menu, Modal, and buttons retain their existing structure and design tokens. **Delete the table row and repair order later.** Rejected because a crash or write failure would leave an initialized registry whose order and table disagree. The registry updates both under one serialized operation and restores the prior order on table failure. +**Delete every unreferenced row at startup.** Rejected because the same shape can come from unexplained order corruption; silently discarding it could lose Workspace metadata and Session accounting. Recovery requires the explicit pending marker written by the owning mutation. + **Refetch both lists after success.** Rejected because the committed removal frame plus immediate unary echo is sufficient, preserves the current Session object, and avoids turning a local mutation into two list requests. Reconnect baselines remain the repair path. ## Verification -Workspace package tests pin successful metadata-only deletion, unknown-id idempotence, table-failure rollback, and cache/table invariant behavior. Apiproxy and carrier tests pin the schema, handler, `workspace-not-found`, retained Session/folder, and committed `host/workspace-removed` frame. Client tests pin unary direct echo, duplicate removal, late changed frames, and deletion racing an in-flight baseline. Component tests pin confirmation, pending-state duplicate suppression, success, failure, Cancel, Escape, and Close. +Workspace package tests pin successful metadata-only deletion, same-path re-registration, unknown-id idempotence, table-failure rollback, explicit-marker restart recovery, unexplained-corruption rejection, and cache/table invariant behavior. Apiproxy and carrier tests pin the schema, handler, `workspace-not-found`, retained Session/folder, fresh-id re-registration, and committed `host/workspace-removed` frame. Client tests pin unary direct echo, duplicate removal, late changed frames, and deletion racing an in-flight baseline. Component tests pin confirmation, pending-state duplicate suppression, success, failure, Cancel, Escape, and Close. The assembled keyless Web scenario registers an existing temporary project directory, accounts a persisted Session, makes that Session current, confirms deletion in Chromium, and verifies the Workspace group disappears while Ungrouped retains the current Session. It checks the user file and JSONL log before and after deletion and repeats the UI, directory, and log assertions after reload. ## Consequences -Deleting a Workspace is intentionally reversible by registering the same directory again, although its prior manual Session order is gone; re-registration does not automatically re-adopt existing Sessions after bootstrap. The operation gives up a one-click cleanup of Session histories or source directories in exchange for a deletion boundary that matches what the record actually owns. +Deleting a Workspace is intentionally reversible by registering the same directory again with a fresh id, although its prior manual Session order is gone; re-registration does not automatically re-adopt existing Sessions after bootstrap. The operation gives up a one-click cleanup of Session histories or source directories in exchange for a deletion boundary that matches what the record actually owns. diff --git a/.agents/notes/implemented/feature/2026-07-27-workspace-registration-deletion.zh.md b/.agents/notes/implemented/feature/2026-07-27-workspace-registration-deletion.zh.md index 76377ebc5e..7a79a1ccc5 100644 --- a/.agents/notes/implemented/feature/2026-07-27-workspace-registration-deletion.zh.md +++ b/.agents/notes/implemented/feature/2026-07-27-workspace-registration-deletion.zh.md @@ -22,6 +22,8 @@ Workspace 注册已有代码目录，使 GUI 能够为目录命名，并对其 Host 流在前一笔全局顺序写入期间继续保留其已提交 id 集合，只在删除表行时移除该 id。因此，创建回滚不会发出错误的移除帧，而每个已连接标签页都能收到从自身投影中删除该记录所需的准确 id。 +Create 与 delete 会在记录／顺序对可能分叉之前写入持久 `pendingMutation`。启动时只补全其中明确命名的 create 或 delete，并清除该标记；系统绝不会仅凭孤立表行的形状推断崩溃来源。因此，没有标记的顺序／表分叉仍会保持注册表原有的损坏直接失败语义。如果删除的表写入已经提交、但标记清理失败，操作仍会报告成功——请求状态和移除帧都已经提交——下一次启动会以幂等方式清除该标记。 + ## 客户端收敛 `WorkspaceManager` 将 `host/workspace-changed` 与 `host/workspace-removed` 都视为有序增量，并在进行中的 `workspace.list` 响应之上回放。成功的一元删除会立即移除行，无需等待本次操作自己的流回显。移除操作具有幂等性；由于 Workspace id 永不复用，进程本地删除标记会拒绝延迟到达的 changed 帧或陈旧基线行。重连仍从 `workspace.list` 刷新；Workspace 增量绝不会剪除会话状态。 @@ -40,14 +42,16 @@ Host 流在前一笔全局顺序写入期间继续保留其已提交 id 集合 **先删除表行，之后再修复顺序。** 不予采纳，因为崩溃或写入失败会使已初始化注册表的顺序与表不一致。注册表会在同一串行操作内更新二者，并在表操作失败时恢复此前顺序。 +**启动时删除所有未引用表行。** 不予采纳，因为来源不明的顺序损坏也会呈现相同形状；静默丢弃可能损失 Workspace 元数据和 Session 账本。恢复必须依赖拥有该变更的操作预先写入的明确待处理标记。 + **成功后重新拉取两个列表。** 不予采纳，因为已提交的移除帧与即时一元回显已足够，既能保留当前会话对象，也避免将局部变更扩大为两次列表请求。重连基线仍是修复路径。 ## Verification -Workspace 包测试固定了仅删除元数据的成功路径、未知 id 的幂等行为、表操作失败回滚，以及缓存／表不变量行为。Apiproxy 与载体测试固定了 schema、处理器、`workspace-not-found`、保留会话／文件夹，以及已提交的 `host/workspace-removed` 帧。客户端测试固定了一元直接回显、重复移除、延迟到达的 changed 帧，以及删除与进行中基线并发的行为。组件测试固定了确认交互、待处理状态下抑制重复提交、成功、失败、Cancel、Escape 与 Close。 +Workspace 包测试固定了仅删除元数据的成功路径、同路径重新注册、未知 id 的幂等行为、表操作失败回滚、明确标记的重启恢复、来源不明损坏的拒绝，以及缓存／表不变量行为。Apiproxy 与载体测试固定了 schema、处理器、`workspace-not-found`、保留会话／文件夹、使用新 id 重新注册，以及已提交的 `host/workspace-removed` 帧。客户端测试固定了一元直接回显、重复移除、延迟到达的 changed 帧，以及删除与进行中基线并发的行为。组件测试固定了确认交互、待处理状态下抑制重复提交、成功、失败、Cancel、Escape 与 Close。 组装后的无密钥 Web 场景会注册一个已有临时项目目录，将持久化会话计入账本，把该会话设为当前会话，在 Chromium 中确认删除，并验证 Workspace 分组消失，而 Ungrouped 保留当前会话。该场景在删除前后检查用户文件和 JSONL 日志，并在刷新后重复验证 UI、目录与日志。 ## Consequences -删除 Workspace 后仍可重新注册同一目录，因此该操作有意设计为可逆；但此前的手动会话顺序会丢失，重新注册后，系统也不会在 bootstrap 结束后自动重新收编现有会话。该操作放弃一键清理会话历史或源码目录，以换取与记录实际所有权一致的删除边界。 +删除 Workspace 后仍可使用新 id 重新注册同一目录，因此该操作有意设计为可逆；但此前的手动会话顺序会丢失，重新注册后，系统也不会在 bootstrap 结束后自动重新收编现有会话。该操作放弃一键清理会话历史或源码目录，以换取与记录实际所有权一致的删除边界。 diff --git a/apps/web/tests/workspace-management.e2e.ts b/apps/web/tests/workspace-management.e2e.ts index 4dbcca36ae..3239dcfc12 100644 --- a/apps/web/tests/workspace-management.e2e.ts +++ b/apps/web/tests/workspace-management.e2e.ts @@ -169,6 +169,34 @@ describe('web e2e: workspace management (create / rename / flat view / hover car await stat(logLocation.path) expect((await scaffold.ctx.sessionPersistence.inspect(SessionId(SEED_ID))).events.length).toBeGreaterThan(0) + // Re-registering the exact deleted path immediately, without a reload, is + // a supported reversible flow. It creates a fresh Workspace id without + // re-adopting the retained Session. + await page.getByRole('button', { name: 'Create workspace' }).click() + await page.getByRole('menuitem', { name: 'Create workspace' }).hover() + await page.getByRole('menuitem', { name: 'Use an existing folder' }).click() + const reuseFolder = page.getByRole('dialog', { name: 'Use an existing folder' }) + await reuseFolder.getByLabel('Existing folder path').fill(scaffold.workspaceCwd) + await reuseFolder.getByRole('button', { name: 'Use folder' }).click() + await expect.poll(() => reuseFolder.count(), { timeout: 10_000 }).toBe(0) + const reregistered = await scaffold.ctx.workspace.resolveByPath(scaffold.workspaceCwd) + expect(reregistered?.id).toBeDefined() + expect(reregistered?.id).not.toBe(workspace.id) + expect(reregistered?.sessionIds).toEqual([]) + await expect.poll(() => page.getByText('Ungrouped', { exact: true }).count(), { timeout: 10_000 }) + .toBeGreaterThanOrEqual(1) + expect(await readFile(join(scaffold.workspaceCwd, 'workspace', 'a.txt'), 'utf8')).toBe('alpha\n') + await stat(logLocation.path) + + // Restore the deleted-registry state so reload still verifies deletion + // persistence independently of the successful re-registration above. + if (reregistered === undefined) throw new Error('same-path re-registration did not materialize') + await scaffold.ctx.workspace.delete(reregistered.id) + await expect.poll( + () => page.getByRole('button', { name: `Workspace actions for ${reregistered.title}` }).count(), + { timeout: 10_000 }, + ).toBe(0) + const warningStart = tripwire.warnings.length await page.reload({ waitUntil: 'load' }) await page.waitForSelector('[class*="frame"]', { timeout: 30_000 }) @@ -183,6 +211,7 @@ describe('web e2e: workspace management (create / rename / flat view / hover car expect(await readFile(join(scaffold.workspaceCwd, 'workspace', 'a.txt'), 'utf8')).toBe('alpha\n') await stat(logLocation.path) expect((await scaffold.ctx.sessionPersistence.inspect(SessionId(SEED_ID))).events.length).toBeGreaterThan(0) + expect(tripwire.pageErrors).toEqual([]) }, 90_000) diff --git a/packages/client/runtime/src/client/workspaces/manager.ts b/packages/client/runtime/src/client/workspaces/manager.ts index 83275e9a2a..7179ed9eb9 100644 --- a/packages/client/runtime/src/client/workspaces/manager.ts +++ b/packages/client/runtime/src/client/workspaces/manager.ts @@ -33,6 +33,14 @@ export class WorkspaceManager { private error: RpcError | null = null private inflight: Promise | null = null private refreshFrames: WorkspaceDelta[] | null = null + /** + * Ids this process has seen removed, kept for the connection's lifetime so + * a late changed frame or a stale baseline row cannot resurrect a deleted + * row. Correctness rests on Host ids never being reused (the registry mints + * a fresh `randomUUID` per record, including when the same directory is + * registered again) — a path-derived id scheme would turn these entries + * into permanent blindfolds and must clear them instead. + */ private readonly removedIds = new Set() private snapshotCache: WorkspaceListSnapshot private readonly notifier = new Notifier(() => { @@ -266,7 +274,7 @@ function upsertWorkspace(items: readonly WorkspaceView[], workspace: WorkspaceVi : items.map((item, position) => position === index ? workspace : item) } - +/** Replay one ordered delta over a baseline: upsert in place, or drop the removed id. */ function applyWorkspaceDelta(items: readonly WorkspaceView[], delta: WorkspaceDelta): WorkspaceView[] { return delta.type === 'upsert' ? upsertWorkspace(items, delta.workspace) diff --git a/packages/client/ui-workspace/src/client/rows/Rows.tsx b/packages/client/ui-workspace/src/client/rows/Rows.tsx index ae866f58cf..e245f8b217 100644 --- a/packages/client/ui-workspace/src/client/rows/Rows.tsx +++ b/packages/client/ui-workspace/src/client/rows/Rows.tsx @@ -75,6 +75,10 @@ export function ProjectRowItem({ group, onToggle, onCreate, actions }: { items={WORKSPACE_MENU_ITEMS} onSelect={(id) => { setMenuOpen(false) + // Unknown ids leave before the dispatch: a future menu row must + // not inherit the destructive branch as an else fallback. + /* v8 ignore next -- WORKSPACE_MENU_ITEMS carries exactly these two rows today. */ + if (id !== 'rename' && id !== 'delete') return if (id === 'rename') actions.rename() else actions.delete() }} diff --git a/packages/host/apiproxy/tests/api-proxy-workspace.spec.ts b/packages/host/apiproxy/tests/api-proxy-workspace.spec.ts index d5ba628590..bbd57cb6dc 100644 --- a/packages/host/apiproxy/tests/api-proxy-workspace.spec.ts +++ b/packages/host/apiproxy/tests/api-proxy-workspace.spec.ts @@ -269,6 +269,12 @@ describe('Host Workspace increments', () => { ok: false, error: { code: 'workspace-not-found', details: { workspaceId: workspace.workspaceId } }, }) + + const reregistered = expectOk(await api.workspace.create(request({ path: workspace.path }))).workspace + expect(reregistered.workspaceId).not.toBe(workspace.workspaceId) + expect(reregistered.path).toBe(workspace.path) + expect(reregistered.sessionIds).toEqual([]) + expect(expectOk(await api.sessions.list(request({}))).items.map(item => item.sessionId)).toContain(sessionId) abort.abort() }) }) diff --git a/packages/workspace/workspace/README.i18n.yaml b/packages/workspace/workspace/README.i18n.yaml index 0904711ad3..b5eaefa98c 100644 --- a/packages/workspace/workspace/README.i18n.yaml +++ b/packages/workspace/workspace/README.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 packages/workspace/workspace/README.md -README.md: 52d03b33b3482dcb6a2f5feddbc15ac9fefee0a8 -README.zh.md: f899abdc3dd2a551179cd710c6dda84f804a8e80 +README.md: bee3e4fcb5dded273f30942ee2e42ee93b839e62 +README.zh.md: 7960a2d13df4f881687fd88cdb07e237b3abb7c8 diff --git a/packages/workspace/workspace/README.md b/packages/workspace/workspace/README.md index 52d03b33b3..bee3e4fcb5 100644 --- a/packages/workspace/workspace/README.md +++ b/packages/workspace/workspace/README.md @@ -18,6 +18,8 @@ The entity/storage rationale lives in the [domain Agent Note](../../../.agents/n `storageDomain` and `sessionPersistence` are required startup dependencies. An unavailable peer leaves the plugin pending and cannot commit an empty initialized marker. On the first successful start, the registry calls `SessionPersistence.list()` and uses only header `id`, `cwd`, and `createdAt` to group valid historical directories and persist initial order; it never reads event bodies. The initialized marker is written last, so partial bootstrap writes are reused safely after restart. Later cwd-only sessions remain Ungrouped. +Create and delete persist an explicit pending-mutation marker before their record and order can diverge. Startup completes only the marked mutation, then clears the marker; an unmarked order/table mismatch remains unexplained corruption and fails loud. Deleting and re-registering the same path creates a fresh Workspace id and does not automatically re-adopt the retained Sessions. + ## Model Experience ### Workspace records and session accounts diff --git a/packages/workspace/workspace/README.zh.md b/packages/workspace/workspace/README.zh.md index f899abdc3d..7960a2d13d 100644 --- a/packages/workspace/workspace/README.zh.md +++ b/packages/workspace/workspace/README.zh.md @@ -18,6 +18,8 @@ DeepSeek Harness 的 Workspace 实体注册表（`ctx.workspace`）：通过领 `storageDomain` 和 `sessionPersistence` 是启动必需依赖。对等服务不可用时，插件保持待处理，且不能提交空的已初始化标记。首次成功启动时，注册表调用 `SessionPersistence.list()`，仅使用头部 `id`、`cwd` 和 `createdAt` 对有效历史目录分组并持久化初始顺序；它绝不读取事件正文。已初始化标记最后写入，因此重启后可安全复用部分启动写入。后续仅有 cwd 的会话仍属于 Ungrouped。 +Create 与 delete 会在记录和顺序可能分叉之前，先持久化明确的待处理变更标记。启动时只补全被该标记证明的变更，随后清除标记；没有标记的顺序／表不一致仍属于来源不明的损坏，并会直接失败。删除后重新注册同一路径会生成新的 Workspace id，且不会自动重新接纳保留下来的 Session。 + ## 模型体验 ### Workspace 记录与会话记账 diff --git a/packages/workspace/workspace/src/index.ts b/packages/workspace/workspace/src/index.ts index 2699365608..5172c63805 100644 --- a/packages/workspace/workspace/src/index.ts +++ b/packages/workspace/workspace/src/index.ts @@ -109,6 +109,7 @@ export class WorkspaceRegistry extends Service { this.global = domain.global this.state = domain.global.get() + await this.recoverPendingMutation() this.validateStoredState(this.state) if (!this.state.initialized) { const headers = await this.ctx.sessionPersistence.list() @@ -218,10 +219,28 @@ export class WorkspaceRegistry extends Service { } const entity = new WorkspaceEntity(this.host, id, record) this.entities.set(id, entity) + const pendingState: WorkspaceDomainState = { + ...state, + pendingMutation: { operation: 'create', workspaceId: id }, + } + try { + await this.setState(pendingState) + } catch (error) { + this.entities.delete(id) + throw error + } try { await table.put(id, record) } catch (error) { this.entities.delete(id) + try { + await this.setState(state) + } catch (rollbackError) { + throw new AggregateError( + [error, rollbackError], + `workspace '${id}' record write and pending-marker rollback both failed`, + ) + } throw error } @@ -232,10 +251,17 @@ export class WorkspaceRegistry extends Service { try { await table.delete(id) } catch (rollbackError) { - this.entities.set(id, entity) throw new AggregateError( [error, rollbackError], - `workspace '${id}' was stored but its registry order and rollback both failed`, + `workspace '${id}' order write and record rollback both failed; the pending marker remains recoverable`, + ) + } + try { + await this.setState(state) + } catch (rollbackError) { + throw new AggregateError( + [error, rollbackError], + `workspace '${id}' order write and pending-marker rollback both failed`, ) } throw error @@ -251,7 +277,10 @@ export class WorkspaceRegistry extends Service { initialized: true, workspaceIds: state.workspaceIds.filter(workspaceId => workspaceId !== id), } - await this.setState(nextState) + await this.setState({ + ...nextState, + pendingMutation: { operation: 'delete', workspaceId: id }, + }) this.entities.delete(id) try { await this.requireTable().delete(id) @@ -260,6 +289,10 @@ export class WorkspaceRegistry extends Service { try { await this.setState(state) } catch (rollbackError) { + // The durable marker still says to finish deletion, so the cache must + // agree with that recoverable direction rather than republish a row + // absent from the persisted order. + this.entities.delete(id) throw new AggregateError( [error, rollbackError], `workspace '${id}' record deletion and registry-order rollback both failed`, @@ -267,9 +300,38 @@ export class WorkspaceRegistry extends Service { } throw error } + try { + await this.setState(nextState) + } catch (error) { + // The deletion committed at the table write and was already published + // to Host streams. Keep the durable marker for startup recovery rather + // than reporting failure after the requested state became true. + this.ctx.logger.warn( + `workspace '${id}' was deleted but its pending marker could not be cleared: ${String(error)}`, + ) + } return true } + /** + * Complete the one mutation explicitly named by durable state. Unexplained + * order/table divergence still reaches {@link validateStoredState} and + * fails loud; this path never infers provenance from shape alone. + */ + private async recoverPendingMutation(): Promise { + const state = this.requireState() + const pending = state.pendingMutation + if (pending === undefined) return + if (state.workspaceIds.includes(pending.workspaceId)) { + throw new Error( + `workspace domain is inconsistent: pending ${pending.operation} workspace ` + + `'${pending.workspaceId}' is still present in registry order`, + ) + } + await this.requireTable().delete(pending.workspaceId) + await this.setState({ initialized: state.initialized, workspaceIds: state.workspaceIds }) + } + private async bootstrap(headers: readonly SessionHeader[]): Promise { const table = this.requireTable() const state = this.requireState() @@ -493,7 +555,12 @@ export class WorkspaceRegistry extends Service { } private enqueueOperation(operation: () => Promise): Promise { - const result = this.operationTail.then(operation) + const result = this.operationTail.then(async () => { + // A committed delete may leave only its marker cleanup pending. Retry + // recovery before another create/delete can overwrite that provenance. + await this.recoverPendingMutation() + return await operation() + }) this.operationTail = result.then(() => {}, () => {}) return result } diff --git a/packages/workspace/workspace/src/spec.ts b/packages/workspace/workspace/src/spec.ts index 8df908949a..7b1a6a41d0 100644 --- a/packages/workspace/workspace/src/spec.ts +++ b/packages/workspace/workspace/src/spec.ts @@ -29,6 +29,16 @@ export const workspaceRecord = z.object({ /** One stored workspace record, inferred from {@link workspaceRecord}. */ export type WorkspaceRecord = z.infer +/** + * Recoverable two-write mutation marker. The marker is persisted before the + * record/order pair can diverge, so startup can distinguish an interrupted + * registry operation from unexplained medium corruption. + */ +const workspacePendingMutation = z.discriminatedUnion('operation', [ + z.object({ operation: z.literal('create'), workspaceId }), + z.object({ operation: z.literal('delete'), workspaceId }), +]) + /** * Durable registry state. `initialized` distinguishes a valid empty registry * from one that still needs the header-only history bootstrap; @@ -37,6 +47,7 @@ export type WorkspaceRecord = z.infer export const workspaceDomainState = z.object({ initialized: z.boolean(), workspaceIds: z.array(workspaceId), + pendingMutation: workspacePendingMutation.optional(), }) /** Durable registry state inferred from {@link workspaceDomainState}. */ diff --git a/packages/workspace/workspace/tests/workspace.spec.ts b/packages/workspace/workspace/tests/workspace.spec.ts index ed08b5ba50..4576155f3b 100644 --- a/packages/workspace/workspace/tests/workspace.spec.ts +++ b/packages/workspace/workspace/tests/workspace.spec.ts @@ -89,7 +89,7 @@ async function storageContext(pool: MemoryMediaPool, backend: StorageBackend = n /** Backend wrapper that injects one selected bootstrap write failure. */ function selectiveFailureBackend( pool: MemoryMediaPool, - failure: { putAt?: number; deleteAt?: number; globalAt?: number }, + failure: { putAt?: number; deleteAt?: number; globalAt?: number | readonly number[] }, ): StorageBackend { const inner = new MemoryStorageBackend(pool) let puts = 0 @@ -113,7 +113,8 @@ function selectiveFailureBackend( }, setGlobal: async (value) => { globals += 1 - if (globals === failure.globalAt) throw new Error('selected bootstrap marker failure') + const failAt = Array.isArray(failure.globalAt) ? failure.globalAt : [failure.globalAt] + if (failAt.includes(globals)) throw new Error('selected bootstrap marker failure') await unit.setGlobal(value) }, close: () => unit.close(), @@ -394,19 +395,34 @@ describe('WorkspaceRegistry create and lookup', () => { it('rolls back the provisional cache when the record write fails', async () => { const dir = await makeDir('write-failure') - const result = await harness() - result.pool.failNextWrites = 1 - await expect(result.registry.create(dir)).rejects.toThrow(/injected/) + const pool = new MemoryMediaPool() + const result = await harness({ + pool, + backend: selectiveFailureBackend(pool, { putAt: 1 }), + }) + await expect(result.registry.create(dir)).rejects.toThrow(/selected bootstrap put failure/) expect(result.registry.list()).toEqual([]) expect(await result.registry.create(dir)).toBeDefined() }) + it('does not publish a Workspace when its pending marker cannot be written', async () => { + const dir = await makeDir('pending-marker-write-failure') + const pool = new MemoryMediaPool() + const result = await harness({ + pool, + backend: selectiveFailureBackend(pool, { globalAt: 2 }), + }) + await expect(result.registry.create(dir)).rejects.toThrow(/selected bootstrap marker failure/) + expect(result.registry.list()).toEqual([]) + expect(pool.media.get('workspace')!.tables.get('workspaces')?.size ?? 0).toBe(0) + }) + it('rolls back a record when registry-order persistence fails', async () => { const dir = await makeDir('order-write-failure') const pool = new MemoryMediaPool() const result = await harness({ pool, - backend: selectiveFailureBackend(pool, { globalAt: 2 }), + backend: selectiveFailureBackend(pool, { globalAt: 3 }), }) await expect(result.registry.create(dir)).rejects.toThrow(/marker failure/) expect(result.registry.list()).toEqual([]) @@ -418,12 +434,38 @@ describe('WorkspaceRegistry create and lookup', () => { const pool = new MemoryMediaPool() const result = await harness({ pool, - backend: selectiveFailureBackend(pool, { globalAt: 2, deleteAt: 1 }), + backend: selectiveFailureBackend(pool, { globalAt: 3, deleteAt: 1 }), }) await expect(result.registry.create(dir)).rejects.toBeInstanceOf(AggregateError) expect(pool.media.get('workspace')!.tables.get('workspaces')!.size).toBe(1) }) + it('reports a record write and pending-marker rollback failure together', async () => { + const dir = await makeDir('record-marker-rollback-failure') + const pool = new MemoryMediaPool() + const result = await harness({ + pool, + backend: selectiveFailureBackend(pool, { putAt: 1, globalAt: 3 }), + }) + await expect(result.registry.create(dir)).rejects.toBeInstanceOf(AggregateError) + expect(storedState(pool)).toMatchObject({ + pendingMutation: { operation: 'create' }, + }) + }) + + it('reports an order write and pending-marker rollback failure together', async () => { + const dir = await makeDir('order-marker-rollback-failure') + const pool = new MemoryMediaPool() + const result = await harness({ + pool, + backend: selectiveFailureBackend(pool, { globalAt: [3, 4] }), + }) + await expect(result.registry.create(dir)).rejects.toBeInstanceOf(AggregateError) + expect(storedState(pool)).toMatchObject({ + pendingMutation: { operation: 'create' }, + }) + }) + it('deletes only the registration and leaves its directory and session headers untouched', async () => { const dir = await makeDir('delete-registration') const result = await harness({ sessions: [header('kept-session', dir)] }) @@ -440,6 +482,11 @@ describe('WorkspaceRegistry create and lookup', () => { expect(result.list).toHaveBeenCalledTimes(1) expect(result.load).not.toHaveBeenCalled() expect(result.inspect).not.toHaveBeenCalled() + + const reregistered = await result.registry.create(dir) + expect(reregistered.id).not.toBe(workspace.id) + expect(reregistered.path).toBe(dir) + expect(reregistered.sessionIds).toEqual([]) }) it('rolls registry order and cache back when record deletion fails', async () => { @@ -458,11 +505,58 @@ describe('WorkspaceRegistry create and lookup', () => { expect(storedRecord(pool, workspace.id)).toMatchObject({ path: dir }) }) + it('commits deletion and leaves a recoverable marker when marker cleanup fails', async () => { + const dir = await makeDir('delete-marker-cleanup') + const pool = new MemoryMediaPool() + const first = await harness({ + pool, + backend: selectiveFailureBackend(pool, { globalAt: 5 }), + }) + const workspace = await first.registry.create(dir) + + await expect(first.registry.delete(workspace.id)).resolves.toBe(true) + expect(first.registry.list()).toEqual([]) + expect(storedState(pool)).toEqual({ + initialized: true, + workspaceIds: [], + pendingMutation: { operation: 'delete', workspaceId: workspace.id }, + }) + const reregistered = await first.registry.create(dir) + expect(reregistered.id).not.toBe(workspace.id) + expect(storedState(pool)).toEqual({ + initialized: true, + workspaceIds: [reregistered.id], + }) + await first.fiber.dispose() + + const restarted = await harness({ pool }) + expect(restarted.registry.list().map(item => item.id)).toEqual([reregistered.id]) + }) + + it('keeps the failed deletion unpublished when record and order rollback both fail', async () => { + const dir = await makeDir('delete-double-failure') + const pool = new MemoryMediaPool() + const result = await harness({ + pool, + backend: selectiveFailureBackend(pool, { deleteAt: 1, globalAt: 5 }), + }) + const workspace = await result.registry.create(dir) + + await expect(result.registry.delete(workspace.id)).rejects.toBeInstanceOf(AggregateError) + expect(result.registry.get(workspace.id)).toBeUndefined() + expect(storedState(pool)).toMatchObject({ + workspaceIds: [], + pendingMutation: { operation: 'delete', workspaceId: workspace.id }, + }) + }) + it('rejects table access before the registry has started', async () => { const dir = await makeDir('unstarted') const registry = new WorkspaceRegistry(new Context()) await expect(registry.create(dir)).rejects.toThrow(/not started/) expect(() => registry.list()).toThrow(/not started/) + const internals = registry as unknown as { requireTable(): unknown } + expect(() => internals.requireTable()).toThrow(/not started/) }) }) @@ -650,6 +744,49 @@ describe('header-validated membership projection', () => { internals.entities.delete(workspace.id) expect(() => result.registry.list()).toThrow(/references missing workspace/) }) + + it('recovers only an explicitly marked interrupted create or delete', async () => { + const createDir = await makeDir('pending-create') + const deleteDir = await makeDir('pending-delete') + const createId = WorkspaceId('00000000-0000-4000-8000-000000000004') + const deleteId = WorkspaceId('00000000-0000-4000-8000-000000000005') + + const interruptedCreate = storedPool( + [[createId, record(createDir, [])]], + { + initialized: true, + workspaceIds: [], + pendingMutation: { operation: 'create', workspaceId: createId }, + }, + ) + const createRecovery = await harness({ pool: interruptedCreate }) + expect(createRecovery.registry.list()).toEqual([]) + expect(interruptedCreate.media.get('workspace')!.tables.get('workspaces')!.has(createId)).toBe(false) + expect(storedState(interruptedCreate)).toEqual({ initialized: true, workspaceIds: [] }) + + const interruptedDelete = storedPool( + [[deleteId, record(deleteDir, [])]], + { + initialized: true, + workspaceIds: [], + pendingMutation: { operation: 'delete', workspaceId: deleteId }, + }, + ) + const deleteRecovery = await harness({ pool: interruptedDelete }) + expect(deleteRecovery.registry.list()).toEqual([]) + expect(interruptedDelete.media.get('workspace')!.tables.get('workspaces')!.has(deleteId)).toBe(false) + expect(storedState(interruptedDelete)).toEqual({ initialized: true, workspaceIds: [] }) + + const corruptPending = storedPool( + [[deleteId, record(deleteDir, [])]], + { + initialized: true, + workspaceIds: [deleteId], + pendingMutation: { operation: 'delete', workspaceId: deleteId }, + }, + ) + await expect(harness({ pool: corruptPending })).rejects.toThrow(/still present in registry order/) + }) }) describe('workspace mutation and status', () => { From be80eb04ad4876dd3c60e000d9b7e1836bed3a1f Mon Sep 17 00:00:00 2001 From: Ubuntu Date: Mon, 27 Jul 2026 14:45:54 +0800 Subject: [PATCH 18/36] ci: retrigger after runner-group policy fix From fe246e4a0a14a4ce154e05e52188bac098dea80c Mon Sep 17 00:00:00 2001 From: Chinesezjc Date: Mon, 27 Jul 2026 15:17:48 +0800 Subject: [PATCH 19/36] =?UTF-8?q?ci:=20failover=20round=20=E2=80=94=20aggr?= =?UTF-8?q?egate=20follows=20the=20selector,=20tighter=20shared-VM=20bound?= =?UTF-8?q?s?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit - all-checks-passed now resolves its pool through the same DSH_CI_FAILOVER expression as the worker jobs it aggregates. Pinned to the hosted pool it would leave the branch-protection verdict queued on the failed pool after every failover job passed — observed live during the 2026-07-27 outage as a required check looping against dead capacity. - Coverage worker bound under failover drops 12 → 8 and snapshot concurrency 16 → 12: the pool now runs six always-on instances (the spare tier was retired), so worst case is 6 × 8 = 48 coverage workers on the shared 64-core VM. --- .github/workflows/ci.yml | 22 +++++++++++++++------- 1 file changed, 15 insertions(+), 7 deletions(-) diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml index 5afa5d7f62..df3d386e39 100644 --- a/.github/workflows/ci.yml +++ b/.github/workflows/ci.yml @@ -102,11 +102,12 @@ jobs: || 'dsh-enterprise-ubuntu-24-04-32core-test' }} name: node 24 / coverage env: - # Failover halves the worker bound: the hosted 32-core runner is + # Failover shrinks the worker bound: the hosted 32-core runner is # exclusive to one job, but the failover pool shares one 64-core VM - # across four runner instances, and the timing-sensitive process - # suites have documented aggregate-contention failures. - DSH_COVERAGE_MAX_WORKERS: ${{ vars.DSH_CI_FAILOVER == 'selfhosted' && '12' || '24' }} + # across six always-on runner instances, and the timing-sensitive + # process suites have documented aggregate-contention failures. + # 8 × 6 instances = 48 workers worst case on 64 cores. + DSH_COVERAGE_MAX_WORKERS: ${{ vars.DSH_CI_FAILOVER == 'selfhosted' && '8' || '24' }} DSH_GATE_CONCURRENCY: '8' steps: - uses: actions/checkout@v6 @@ -160,7 +161,7 @@ jobs: DSH_NODE_COMPAT_SKIP_TYPECHECK: '1' DSH_PUBLINT_CONCURRENCY: '8' # Failover halves snapshot concurrency for the shared 64-core VM. - DSH_SNAPSHOT_MAX_CONCURRENCY: ${{ vars.DSH_CI_FAILOVER == 'selfhosted' && '16' || '32' }} + DSH_SNAPSHOT_MAX_CONCURRENCY: ${{ vars.DSH_CI_FAILOVER == 'selfhosted' && '12' || '32' }} steps: - uses: actions/checkout@v6 with: @@ -765,8 +766,15 @@ jobs: # 'cancelled' and 'skipped'. all-checks-passed: name: all checks passed - # The required verdict must not add a separate standard-hosted billing dependency. - runs-on: dsh-enterprise-ubuntu-latest-32core-test + # The required verdict must not add a separate standard-hosted billing + # dependency — and it must follow the failover selector like the worker + # jobs it aggregates: if it stayed pinned to the hosted pool, every + # failover-passed run would still leave the branch-protection verdict + # queued forever on the failed pool. + runs-on: >- + ${{ vars.DSH_CI_FAILOVER == 'selfhosted' + && fromJSON('["self-hosted", "linux", "x64", "vm-backup"]') + || 'dsh-enterprise-ubuntu-latest-32core-test' }} needs: [node-24, node-24-coverage, node-24-consumers, node-compat, python-sdk, windows] if: always() && github.event_name == 'pull_request' steps: From aedf7fbf349df99a89faa72ddc17ec95ea2aff53 Mon Sep 17 00:00:00 2001 From: Chinesezjc Date: Mon, 27 Jul 2026 15:27:40 +0800 Subject: [PATCH 20/36] docs(i18n): keep the runbook link target identical across the pair The pairing gate requires link target #9 to be byte-identical between the language sides; my earlier 'fix' pointed the zh side at the zh runbook and broke the contract. Reverted to the shared target and re-recorded the pairing hash. --- .../2026-07-22-evidence-based-larger-hosted-runners.i18n.yaml | 2 +- .../2026-07-22-evidence-based-larger-hosted-runners.zh.md | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.i18n.yaml b/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.i18n.yaml index 5ebd95248c..99cabc76bb 100644 --- a/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.i18n.yaml +++ b/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.i18n.yaml @@ -3,4 +3,4 @@ # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.md 2026-07-22-evidence-based-larger-hosted-runners.md: 5b399be5571ddaf1f775ba43a2233198b8e09b18 -2026-07-22-evidence-based-larger-hosted-runners.zh.md: 40970ec33c1a16af85ea47be3fc932209efdd654 +2026-07-22-evidence-based-larger-hosted-runners.zh.md: f77516e2375bfc0557679d05fd275bd9cee7d8eb diff --git a/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.zh.md b/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.zh.md index 40970ec33c..f77516e237 100644 --- a/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.zh.md +++ b/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.zh.md @@ -52,7 +52,7 @@ Windows 仓库工作在超过 16 核后收益很小，但 32 核池可以让完 只有在 `master` 移动时，才运行完整的 Linux、macOS 和 Windows 串行参考。拉取请求使用企业级运行器必需路径和标准托管兼容性作业，其他大型运行器规格仅通过手动触发运行。 -另有一条串行 Linux 参考在每次 `master` 推送时运行于公司自有的自托管池（`vm-backup` 标签：一台 64 核虚拟机，运行 6 个常驻的 systemd 管理运行器实例）。它是热备演练而非必需检查：每次运行都重新证明这台持久化虚拟机能够执行完整的未分片聚合流程。实际切换机制已预先布线：三个必需 Linux 作业通过仅限管理员的仓库变量 `DSH_CI_FAILOVER` 解析运行器池，因此故障响应就是设置一个变量并重跑——无需合并（合并本身会被正在失败的检查死锁）（[切换手册](2026-07-26-ci-failover-runbook.zh.md)）。该热备通道由 push 触发，执行的始终是基线分支自身的工作流定义——不存在任何可由拉取请求编辑的路径能把代码路由到这些运行器上；此外仓库继续保持禁用 fork。 +另有一条串行 Linux 参考在每次 `master` 推送时运行于公司自有的自托管池（`vm-backup` 标签：一台 64 核虚拟机，运行 6 个常驻的 systemd 管理运行器实例）。它是热备演练而非必需检查：每次运行都重新证明这台持久化虚拟机能够执行完整的未分片聚合流程。实际切换机制已预先布线：三个必需 Linux 作业通过仅限管理员的仓库变量 `DSH_CI_FAILOVER` 解析运行器池，因此故障响应就是设置一个变量并重跑——无需合并（合并本身会被正在失败的检查死锁）（[切换手册](2026-07-26-ci-failover-runbook.md)）。该热备通道由 push 触发，执行的始终是基线分支自身的工作流定义——不存在任何可由拉取请求编辑的路径能把代码路由到这些运行器上；此外仓库继续保持禁用 fork。 ## 曾考虑的替代方案 From caabf8f671d194194b4d8b876566b847d2f73ddf Mon Sep 17 00:00:00 2001 From: Chinesezjc Date: Mon, 27 Jul 2026 15:36:11 +0800 Subject: [PATCH 21/36] ci: dependabot stays hosted under failover; runbook matches shipped bounds MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit - All four failover selectors (three workers + the verdict job) and the paired env/cache expressions now exclude dependabot[bot]: under failover, dependency-supplied code keeps queueing for the hosted pool instead of executing on the persistent VM. A delayed Dependabot PR during an outage is an acceptable cost; dependency code on the privileged host is not. - Runbook (both languages): records the shipped failover bounds (coverage 8, snapshots 12, sized for six instances) and documents that the verdict job follows the selector too — operators previously had no explanation for a verdict queued after all workers passed. - Local static gate green: 32 passed, 0 failed (translation pairing 519 pairs consistent). --- .../2026-07-26-ci-failover-runbook.i18n.yaml | 4 ++-- .../process/2026-07-26-ci-failover-runbook.md | 6 +++--- .../process/2026-07-26-ci-failover-runbook.zh.md | 6 +++--- .github/workflows/ci.yml | 14 +++++++++----- 4 files changed, 17 insertions(+), 13 deletions(-) diff --git a/.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.i18n.yaml b/.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.i18n.yaml index efb5fdd1cc..26f7f23f85 100644 --- a/.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.i18n.yaml +++ b/.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.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/process/2026-07-26-ci-failover-runbook.md -2026-07-26-ci-failover-runbook.md: 0bce83e0f9c842fa3dd73ae9c0a3eefc0975cdae -2026-07-26-ci-failover-runbook.zh.md: 4bc6c67bab754ad3f0127557b0d5e04f7934c8a2 +2026-07-26-ci-failover-runbook.md: ab1a727caa045d2074a9c577416f96f45efcd0aa +2026-07-26-ci-failover-runbook.zh.md: 5dfaca0c1c0f443307bea28bb6544385ebb68bb7 diff --git a/.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.md b/.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.md index 0bce83e0f9..ab1a727caa 100644 --- a/.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.md +++ b/.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.md @@ -6,11 +6,11 @@ English | [中文](2026-07-26-ci-failover-runbook.zh.md) ## Problem -The three required Linux jobs in [CI](../../../../.github/workflows/ci.yml) (`node 24 / static`, `node 24 / coverage`, `node 24 / snapshots and artifacts`) run on the hosted enterprise 32-core pools. When those pools degrade — jobs queue indefinitely, the enterprise labels vanish, or GitHub-side capacity fails — every open pull request becomes unmergeable, and the ordinary recovery of merging a fix is itself deadlocked behind the very required checks that cannot run. An outage therefore needs a switch a repository admin can throw without merging anything. +The three required Linux worker jobs in [CI](../../../../.github/workflows/ci.yml) (`node 24 / static`, `node 24 / coverage`, `node 24 / snapshots and artifacts`) and the required verdict job that aggregates them (`all checks passed`) run on the hosted enterprise 32-core pools. When those pools degrade — jobs queue indefinitely, the enterprise labels vanish, or GitHub-side capacity fails — every open pull request becomes unmergeable, and the ordinary recovery of merging a fix is itself deadlocked behind the very required checks that cannot run. An outage therefore needs a switch a repository admin can throw without merging anything. ## Decision -Each of the three required Linux jobs resolves its runner pool through the `DSH_CI_FAILOVER` repository variable. Unset (normal), they run on the hosted enterprise pools. Set to `selfhosted` by a repository admin, all three retarget onto the in-house self-hosted `vm-backup` pool, coverage and snapshot concurrency drop to shared-VM bounds, and the hosted-path pnpm cache restores are skipped. The switch is admin-only repository state, not a merge, so it works while every check is red. The in-house pool's readiness is continuously re-proven by the `serial / linux (self-hosted standby)` lane, which runs the complete unsharded aggregate on every master push. +Each of the three required Linux worker jobs — and the `all checks passed` verdict job, which would otherwise stay queued on the failed pool even after every worker passed — resolves its runner pool through the `DSH_CI_FAILOVER` repository variable. Unset (normal), they run on the hosted enterprise pools. Set to `selfhosted` by a repository admin, all four retarget onto the in-house self-hosted `vm-backup` pool, coverage and snapshot concurrency drop to shared-VM bounds, and the hosted-path pnpm cache restores are skipped. The switch is admin-only repository state, not a merge, so it works while every check is red. The in-house pool's readiness is continuously re-proven by the `serial / linux (self-hosted standby)` lane, which runs the complete unsharded aggregate on every master push. ### What the in-house pool is @@ -20,7 +20,7 @@ Each of the three required Linux jobs resolves its runner pool through the `DSH_ 1. Repository **Settings → Secrets and variables → Actions → Variables → New repository variable**: name `DSH_CI_FAILOVER`, value `selfhosted`. 2. Retrigger the required jobs so they re-resolve their pool. Jobs already **queued** for the hosted labels do not retarget and cannot be re-run in place, so for the documented indefinite-queue outage, cancel the stuck run and re-run all jobs, or push a new commit; "Re-run failed jobs" only helps once a job has actually failed rather than queued. -3. That is the entire switch. Under failover the workflow also, automatically: halves `DSH_COVERAGE_MAX_WORKERS` to 12 and `DSH_SNAPSHOT_MAX_CONCURRENCY` to 16 (shared-VM contention bounds), and skips the hosted-path pnpm cache restores (the VM's persistent store serves warm installs). +3. That is the entire switch. Under failover the workflow also, automatically: drops `DSH_COVERAGE_MAX_WORKERS` to 8 and `DSH_SNAPSHOT_MAX_CONCURRENCY` to 12 (sized for six always-on instances: worst case 6 × 8 = 48 coverage workers on the 64-core VM) (shared-VM contention bounds), and skips the hosted-path pnpm cache restores (the VM's persistent store serves warm installs). ### Capacity during failover diff --git a/.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.zh.md b/.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.zh.md index 4bc6c67bab..5dfaca0c1c 100644 --- a/.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.zh.md +++ b/.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.zh.md @@ -6,11 +6,11 @@ Status: implemented ## 问题 -[CI](../../../../.github/workflows/ci.yml) 中三个必需的 Linux 作业（`node 24 / static`、`node 24 / coverage`、`node 24 / snapshots and artifacts`）运行在托管的企业级 32 核池上。当这些托管池发生故障——作业无限排队、企业标签消失或 GitHub 侧容量故障——所有开启的拉取请求都无法合并，而"合并一个修复"这一常规恢复手段本身正被那些无法运行的必需检查死锁。因此故障需要一个仓库管理员无需合并任何代码即可触发的开关。 +[CI](../../../../.github/workflows/ci.yml) 中三个必需的 Linux 工作作业（`node 24 / static`、`node 24 / coverage`、`node 24 / snapshots and artifacts`）以及聚合它们的必需判定作业（`all checks passed`）运行在托管的企业级 32 核池上。当这些托管池发生故障——作业无限排队、企业标签消失或 GitHub 侧容量故障——所有开启的拉取请求都无法合并，而"合并一个修复"这一常规恢复手段本身正被那些无法运行的必需检查死锁。因此故障需要一个仓库管理员无需合并任何代码即可触发的开关。 ## 决策 -三个必需的 Linux 作业各自通过仓库变量 `DSH_CI_FAILOVER` 解析运行器池。变量不存在（正常）时它们运行在托管企业池上；由仓库管理员设为 `selfhosted` 时，三者全部切换到公司自有的自托管 `vm-backup` 池，coverage 与 snapshot 的并发降到共享虚拟机上限，并跳过托管路径的 pnpm 缓存恢复。这个开关是仅限管理员的仓库状态而非一次合并，因此在所有检查都是红色时仍然有效。自有池的就绪状态由 `serial / linux (self-hosted standby)` 通道持续验证——每次 master 推送都在其上运行完整的未分片聚合流程。 +三个必需的 Linux 工作作业——以及 `all checks passed` 判定作业（若不随切换，即使全部工作作业通过，它仍会滞留在故障池的队列中）——各自通过仓库变量 `DSH_CI_FAILOVER` 解析运行器池。变量不存在（正常）时它们运行在托管企业池上；由仓库管理员设为 `selfhosted` 时，四者全部切换到公司自有的自托管 `vm-backup` 池，coverage 与 snapshot 的并发降到共享虚拟机上限，并跳过托管路径的 pnpm 缓存恢复。这个开关是仅限管理员的仓库状态而非一次合并，因此在所有检查都是红色时仍然有效。自有池的就绪状态由 `serial / linux (self-hosted standby)` 通道持续验证——每次 master 推送都在其上运行完整的未分片聚合流程。 ### 自有池是什么 @@ -20,7 +20,7 @@ Status: implemented 1. 仓库 **Settings → Secrets and variables → Actions → Variables → New repository variable**：名称 `DSH_CI_FAILOVER`，值 `selfhosted`。 2. 重新触发必需作业，使其重新解析运行器池。已经为托管标签**排队**的作业不会重定向，也无法原地 re-run，因此对于本手册所述的无限排队故障，应取消卡住的运行并 re-run all jobs，或推送一个新提交；“Re-run failed jobs”只有在作业真正失败（而非仍在排队）时才有用。 -3. 切换到此完成。故障切换状态下工作流还会自动：把 `DSH_COVERAGE_MAX_WORKERS` 降为 12、`DSH_SNAPSHOT_MAX_CONCURRENCY` 降为 16（共享虚拟机的争抢上限），并跳过托管路径的 pnpm 缓存恢复（虚拟机的持久 store 直接提供热安装）。 +3. 切换到此完成。故障切换状态下工作流还会自动：把 `DSH_COVERAGE_MAX_WORKERS` 降为 8、`DSH_SNAPSHOT_MAX_CONCURRENCY` 降为 12（按 6 个常驻实例定容：最坏 6 × 8 = 48 个覆盖率工作进程对 64 核）（共享虚拟机的争抢上限），并跳过托管路径的 pnpm 缓存恢复（虚拟机的持久 store 直接提供热安装）。 ### 切换期间的容量 diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml index df3d386e39..8306b7e034 100644 --- a/.github/workflows/ci.yml +++ b/.github/workflows/ci.yml @@ -44,6 +44,7 @@ jobs: if: github.event_name == 'pull_request' runs-on: >- ${{ vars.DSH_CI_FAILOVER == 'selfhosted' + && github.event.pull_request.user.login != 'dependabot[bot]' && fromJSON('["self-hosted", "linux", "x64", "vm-backup"]') || 'dsh-enterprise-ubuntu-latest-32core-test' }} name: node 24 / static @@ -60,7 +61,7 @@ jobs: # compression and upload on the paid latency-critical path. Skipped # under failover — see the coverage lane's identical rationale. - uses: actions/cache/restore@v4 - if: vars.DSH_CI_FAILOVER != 'selfhosted' + if: vars.DSH_CI_FAILOVER != 'selfhosted' || github.event.pull_request.user.login == 'dependabot[bot]' with: path: /home/runner/.local/share/pnpm/store/v11 key: ${{ runner.os }}-node-${{ env.PRIMARY_NODE_VERSION }}-pnpm-${{ hashFiles('pnpm-lock.yaml') }} @@ -98,6 +99,7 @@ jobs: if: github.event_name == 'pull_request' runs-on: >- ${{ vars.DSH_CI_FAILOVER == 'selfhosted' + && github.event.pull_request.user.login != 'dependabot[bot]' && fromJSON('["self-hosted", "linux", "x64", "vm-backup"]') || 'dsh-enterprise-ubuntu-24-04-32core-test' }} name: node 24 / coverage @@ -107,7 +109,7 @@ jobs: # across six always-on runner instances, and the timing-sensitive # process suites have documented aggregate-contention failures. # 8 × 6 instances = 48 workers worst case on 64 cores. - DSH_COVERAGE_MAX_WORKERS: ${{ vars.DSH_CI_FAILOVER == 'selfhosted' && '8' || '24' }} + DSH_COVERAGE_MAX_WORKERS: ${{ vars.DSH_CI_FAILOVER == 'selfhosted' && github.event.pull_request.user.login != 'dependabot[bot]' && '8' || '24' }} DSH_GATE_CONCURRENCY: '8' steps: - uses: actions/checkout@v6 @@ -118,7 +120,7 @@ jobs: # serves warm installs directly, and this hosted-path restore would # spend ~52 s pulling ~180 MB into a path pnpm never reads there. - uses: actions/cache/restore@v4 - if: vars.DSH_CI_FAILOVER != 'selfhosted' + if: vars.DSH_CI_FAILOVER != 'selfhosted' || github.event.pull_request.user.login == 'dependabot[bot]' with: path: /home/runner/.local/share/pnpm/store/v11 key: ${{ runner.os }}-node-${{ env.PRIMARY_NODE_VERSION }}-pnpm-${{ hashFiles('pnpm-lock.yaml') }} @@ -151,6 +153,7 @@ jobs: if: github.event_name == 'pull_request' runs-on: >- ${{ vars.DSH_CI_FAILOVER == 'selfhosted' + && github.event.pull_request.user.login != 'dependabot[bot]' && fromJSON('["self-hosted", "linux", "x64", "vm-backup"]') || 'dsh-enterprise-ubuntu-latest-32core-test' }} name: node 24 / snapshots and artifacts @@ -161,7 +164,7 @@ jobs: DSH_NODE_COMPAT_SKIP_TYPECHECK: '1' DSH_PUBLINT_CONCURRENCY: '8' # Failover halves snapshot concurrency for the shared 64-core VM. - DSH_SNAPSHOT_MAX_CONCURRENCY: ${{ vars.DSH_CI_FAILOVER == 'selfhosted' && '12' || '32' }} + DSH_SNAPSHOT_MAX_CONCURRENCY: ${{ vars.DSH_CI_FAILOVER == 'selfhosted' && github.event.pull_request.user.login != 'dependabot[bot]' && '12' || '32' }} steps: - uses: actions/checkout@v6 with: @@ -177,7 +180,7 @@ jobs: # Skipped under failover — see the coverage lane's identical rationale. - uses: actions/cache/restore@v4 - if: vars.DSH_CI_FAILOVER != 'selfhosted' + if: vars.DSH_CI_FAILOVER != 'selfhosted' || github.event.pull_request.user.login == 'dependabot[bot]' with: path: /home/runner/.local/share/pnpm/store/v11 key: ${{ runner.os }}-node-${{ env.PRIMARY_NODE_VERSION }}-pnpm-${{ hashFiles('pnpm-lock.yaml') }} @@ -773,6 +776,7 @@ jobs: # queued forever on the failed pool. runs-on: >- ${{ vars.DSH_CI_FAILOVER == 'selfhosted' + && github.event.pull_request.user.login != 'dependabot[bot]' && fromJSON('["self-hosted", "linux", "x64", "vm-backup"]') || 'dsh-enterprise-ubuntu-latest-32core-test' }} needs: [node-24, node-24-coverage, node-24-consumers, node-compat, python-sdk, windows] From d606ab6877a4516a422ab45e4160873843aa9a55 Mon Sep 17 00:00:00 2001 From: Chinesezjc Date: Mon, 27 Jul 2026 15:47:19 +0800 Subject: [PATCH 22/36] =?UTF-8?q?ci:=20standby=20archive=20base=20ref;=20r?= =?UTF-8?q?unbook=20=E2=80=94=20dependabot=20exception,=20clean=20bootstra?= =?UTF-8?q?p,=20variable=20trust=20model?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit - serial-linux-selfhosted now fetches depth 2 and passes DSH_ARCHIVE_BASE_REF=github.event.before, running the same frozen-archive comparison as serial-linux instead of diffing the new manifest against itself. - Runbook (both languages): documents the deliberate dependabot exception (queued-on-hosted during failover is expected, not a failed switch); corrects the emergency-capacity bootstrap to exclude .runner/.credentials when cloning a runner directory; and replaces the 'admin-only' variable claim with the accurate trust-model statement — repository variables are writer-manageable, which in this private fork-disabled repo with an all-workflows runner group is routing among members, not an escalation. Static gate green locally: 32 passed, 0 failed. --- .../process/2026-07-26-ci-failover-runbook.i18n.yaml | 4 ++-- .../implemented/process/2026-07-26-ci-failover-runbook.md | 8 ++++++-- .../process/2026-07-26-ci-failover-runbook.zh.md | 8 ++++++-- .github/workflows/ci.yml | 6 ++++++ 4 files changed, 20 insertions(+), 6 deletions(-) diff --git a/.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.i18n.yaml b/.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.i18n.yaml index 26f7f23f85..7b8d08befe 100644 --- a/.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.i18n.yaml +++ b/.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.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/process/2026-07-26-ci-failover-runbook.md -2026-07-26-ci-failover-runbook.md: ab1a727caa045d2074a9c577416f96f45efcd0aa -2026-07-26-ci-failover-runbook.zh.md: 5dfaca0c1c0f443307bea28bb6544385ebb68bb7 +2026-07-26-ci-failover-runbook.md: 55c1350593562d62463e751451d50a79cf45a1d6 +2026-07-26-ci-failover-runbook.zh.md: 13977b78244440a23722d089849ea7ff6b751aea diff --git a/.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.md b/.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.md index ab1a727caa..55c1350593 100644 --- a/.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.md +++ b/.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.md @@ -22,9 +22,13 @@ Each of the three required Linux worker jobs — and the `all checks passed` ver 2. Retrigger the required jobs so they re-resolve their pool. Jobs already **queued** for the hosted labels do not retarget and cannot be re-run in place, so for the documented indefinite-queue outage, cancel the stuck run and re-run all jobs, or push a new commit; "Re-run failed jobs" only helps once a job has actually failed rather than queued. 3. That is the entire switch. Under failover the workflow also, automatically: drops `DSH_COVERAGE_MAX_WORKERS` to 8 and `DSH_SNAPSHOT_MAX_CONCURRENCY` to 12 (sized for six always-on instances: worst case 6 × 8 = 48 coverage workers on the 64-core VM) (shared-VM contention bounds), and skips the hosted-path pnpm cache restores (the VM's persistent store serves warm installs). -### Capacity during failover +#**Dependabot exception.** All four selectors deliberately exclude `dependabot[bot]`: under failover, Dependabot PRs stay queued for the hosted pool rather than executing dependency-supplied code on the persistent VM. A Dependabot PR that remains queued during an outage is expected behavior, not a failed switch; it completes when the hosted pool recovers. -Six always-on instances absorb normal PR traffic (the pool's steady-state load is one serial standby job per master push, so failover capacity is effectively the full pool). If queues still build, register additional instances with an org registration token (org Settings → Actions → Runners → New runner) — cloning an existing runner directory and running `config.sh` takes about a minute per instance. +**Who can flip the variable.** GitHub's API lets any collaborator with write access manage repository variables, so the switch is writer-level, not strictly admin-only. In this repository's trust model that is not an escalation: the runner group admits all workflows of this private, fork-disabled repository (a deliberate trade to make PR-ref failover possible at all), so any writer could already reach the VM by pushing a branch workflow. The boundary against untrusted code is repository membership; the variable only routes work for members. + +## Capacity during failover + +Six always-on instances absorb normal PR traffic (the pool's steady-state load is one serial standby job per master push, so failover capacity is effectively the full pool). If queues still build, register additional instances with an org registration token (org Settings → Actions → Runners → New runner). Clone an existing runner directory **excluding its identity files** — `rsync -a --exclude '.runner' --exclude '.credentials*' --exclude '_diag' --exclude '_work' / /` — then run `config.sh`; copying `.runner`/`.credentials` verbatim makes `config.sh` refuse with "already configured". About a minute per instance. ### Switch back diff --git a/.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.zh.md b/.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.zh.md index 5dfaca0c1c..13977b7824 100644 --- a/.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.zh.md +++ b/.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.zh.md @@ -22,9 +22,13 @@ Status: implemented 2. 重新触发必需作业，使其重新解析运行器池。已经为托管标签**排队**的作业不会重定向，也无法原地 re-run，因此对于本手册所述的无限排队故障，应取消卡住的运行并 re-run all jobs，或推送一个新提交；“Re-run failed jobs”只有在作业真正失败（而非仍在排队）时才有用。 3. 切换到此完成。故障切换状态下工作流还会自动：把 `DSH_COVERAGE_MAX_WORKERS` 降为 8、`DSH_SNAPSHOT_MAX_CONCURRENCY` 降为 12（按 6 个常驻实例定容：最坏 6 × 8 = 48 个覆盖率工作进程对 64 核）（共享虚拟机的争抢上限），并跳过托管路径的 pnpm 缓存恢复（虚拟机的持久 store 直接提供热安装）。 -### 切换期间的容量 +#**Dependabot 例外。**四个选择器都刻意排除了 `dependabot[bot]`：故障切换期间，Dependabot 拉取请求继续在托管池排队，而不是把依赖方提供的代码放到持久化虚拟机上执行。故障期间 Dependabot PR 持续排队是预期行为而非切换失败；托管池恢复后它会自行完成。 -6 个常驻实例可承接正常 PR 流量（该池平时唯一的稳态负载是每次 master 推送一个串行热备作业，故障切换时几乎全池可用）。若仍出现排队，用组织级注册 token（组织 Settings → Actions → Runners → New runner）追加注册实例——复制现有 runner 目录再跑 `config.sh`，每个约一分钟。 +**谁能扳动这个变量。**GitHub 的 API 允许任何具有写权限的协作者管理仓库变量，因此该开关实际是写者级而非严格的管理员级。在本仓库的信任模型下这并不构成越权：runner group 接纳本私有、禁 fork 仓库的全部工作流（这是让 PR 引用的故障切换得以成立的刻意取舍），因此任何写者本就可以通过推送分支工作流触达这台虚拟机。抵御不可信代码的边界是仓库成员资格；变量只是为成员路由工作。 + +## 切换期间的容量 + +6 个常驻实例可承接正常 PR 流量（该池平时唯一的稳态负载是每次 master 推送一个串行热备作业，故障切换时几乎全池可用）。若仍出现排队，用组织级注册 token（组织 Settings → Actions → Runners → New runner）追加注册实例。复制现有 runner 目录时**必须排除身份文件**——`rsync -a --exclude '.runner' --exclude '.credentials*' --exclude '_diag' --exclude '_work' / /`——再跑 `config.sh`；原样拷贝 `.runner`/`.credentials` 会使 `config.sh` 以 "already configured" 拒绝。每个约一分钟。 ### 切回 diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml index 8306b7e034..8c3b854ae6 100644 --- a/.github/workflows/ci.yml +++ b/.github/workflows/ci.yml @@ -423,7 +423,12 @@ jobs: name: serial / linux (self-hosted standby) runs-on: [self-hosted, linux, x64, vm-backup] steps: + # fetch-depth 2 + DSH_ARCHIVE_BASE_REF below: same frozen-archive + # comparison as serial-linux — without the prior commit the archive + # verifier defaults to HEAD and compares the new manifest with itself. - uses: actions/checkout@v6 + with: + fetch-depth: 2 - uses: actions/setup-node@v6 with: @@ -440,6 +445,7 @@ jobs: - name: Run complete unsharded primary Node CI serially env: + DSH_ARCHIVE_BASE_REF: ${{ github.event.before }} DSH_COVERAGE_MAX_WORKERS: '1' DSH_E2E_MAX_WORKERS: '1' DSH_ESLINT_CACHE: '1' From 4701373fc2cf87e14fb53885f9fa434b54ca0e20 Mon Sep 17 00:00:00 2001 From: NI0317 Date: Mon, 27 Jul 2026 15:52:35 +0800 Subject: [PATCH 23/36] fix(workspace): remove transient duplicate warning --- ...-workspace-registration-deletion.i18n.yaml | 4 +- ...6-07-27-workspace-registration-deletion.md | 4 +- ...7-27-workspace-registration-deletion.zh.md | 4 +- apps/web/tests/workspace-management.e2e.ts | 88 +++++++++++++++++++ .../runtime/src/client/workspaces/manager.ts | 15 +++- .../src/client/WorkspaceBrowser.tsx | 15 +++- .../src/client/WorkspacePicker.tsx | 2 +- .../tests/workspace-browser.spec.tsx | 7 +- .../tests/workspace-picker.spec.tsx | 33 +++++-- 9 files changed, 155 insertions(+), 17 deletions(-) diff --git a/.agents/notes/implemented/feature/2026-07-27-workspace-registration-deletion.i18n.yaml b/.agents/notes/implemented/feature/2026-07-27-workspace-registration-deletion.i18n.yaml index 93c78373c6..d576fb10e5 100644 --- a/.agents/notes/implemented/feature/2026-07-27-workspace-registration-deletion.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-07-27-workspace-registration-deletion.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/feature/2026-07-27-workspace-registration-deletion.md -2026-07-27-workspace-registration-deletion.md: 58ae5c4bef2cf1cb0a0158eda5eb37daf2e9703d -2026-07-27-workspace-registration-deletion.zh.md: 7a79a1ccc53a0d4fd7e5ab453239ade955313c6e +2026-07-27-workspace-registration-deletion.md: 8168b0832ca39e6023f6981815ffe758b5695361 +2026-07-27-workspace-registration-deletion.zh.md: b0df6982ac81426a5b0ce2f0e2b0e744212e3f5b diff --git a/.agents/notes/implemented/feature/2026-07-27-workspace-registration-deletion.md b/.agents/notes/implemented/feature/2026-07-27-workspace-registration-deletion.md index 58ae5c4bef..8168b0832c 100644 --- a/.agents/notes/implemented/feature/2026-07-27-workspace-registration-deletion.md +++ b/.agents/notes/implemented/feature/2026-07-27-workspace-registration-deletion.md @@ -28,6 +28,8 @@ Create and delete write a durable `pendingMutation` before their record/order pa `WorkspaceManager` treats both `host/workspace-changed` and `host/workspace-removed` as ordered deltas replayed over an in-flight `workspace.list` response. A successful unary delete removes the row immediately instead of waiting for its own stream echo. Removal is idempotent, and a process-local tombstone rejects late changed frames or stale baseline rows for the never-reused Workspace id. A reconnect still refreshes from `workspace.list`; Session state is never pruned by a Workspace delta. +The delete confirmation remains pending until the React Workspace projection has committed the removed id, so the next create gesture cannot observe one stale list frame. During create, duplicate-name validation is suppressed while the request is pending because the committed `host/workspace-changed` frame may publish the newly created Workspace before its unary response; after failure returns the form to editing, validation uses the latest list again. + ## Confirmation interaction The existing Workspace row menu opens a shared `Modal` before deletion. The text states all three consequences: the Workspace leaves the list, the folder and session logs remain, and its Sessions appear under Ungrouped. While the request is pending, the confirm and Cancel controls are disabled, duplicate confirmation is ignored, and Escape or Close cannot dismiss the operation. Failure keeps the Modal open with the error; Cancel, Escape, and Close before submission never delete. @@ -48,7 +50,7 @@ The menu, Modal, and buttons retain their existing structure and design tokens. ## Verification -Workspace package tests pin successful metadata-only deletion, same-path re-registration, unknown-id idempotence, table-failure rollback, explicit-marker restart recovery, unexplained-corruption rejection, and cache/table invariant behavior. Apiproxy and carrier tests pin the schema, handler, `workspace-not-found`, retained Session/folder, fresh-id re-registration, and committed `host/workspace-removed` frame. Client tests pin unary direct echo, duplicate removal, late changed frames, and deletion racing an in-flight baseline. Component tests pin confirmation, pending-state duplicate suppression, success, failure, Cancel, Escape, and Close. +Workspace package tests pin successful metadata-only deletion, same-path re-registration, unknown-id idempotence, table-failure rollback, explicit-marker restart recovery, unexplained-corruption rejection, and cache/table invariant behavior. Apiproxy and carrier tests pin the schema, handler, `workspace-not-found`, retained Session/folder, fresh-id re-registration, and committed `host/workspace-removed` frame. Client tests pin unary direct echo, duplicate removal, late changed frames, and deletion racing an in-flight baseline. Component tests pin confirmation, projection-settled closing, pending-state duplicate suppression, success-frame-before-unary ordering, failure, Cancel, Escape, and Close. The browser scenario observes every transient alert, slot error, console error, and page error while reusing a deleted title for a different directory. The assembled keyless Web scenario registers an existing temporary project directory, accounts a persisted Session, makes that Session current, confirms deletion in Chromium, and verifies the Workspace group disappears while Ungrouped retains the current Session. It checks the user file and JSONL log before and after deletion and repeats the UI, directory, and log assertions after reload. diff --git a/.agents/notes/implemented/feature/2026-07-27-workspace-registration-deletion.zh.md b/.agents/notes/implemented/feature/2026-07-27-workspace-registration-deletion.zh.md index 7a79a1ccc5..b0df6982ac 100644 --- a/.agents/notes/implemented/feature/2026-07-27-workspace-registration-deletion.zh.md +++ b/.agents/notes/implemented/feature/2026-07-27-workspace-registration-deletion.zh.md @@ -28,6 +28,8 @@ Create 与 delete 会在记录／顺序对可能分叉之前写入持久 `pendin `WorkspaceManager` 将 `host/workspace-changed` 与 `host/workspace-removed` 都视为有序增量，并在进行中的 `workspace.list` 响应之上回放。成功的一元删除会立即移除行，无需等待本次操作自己的流回显。移除操作具有幂等性；由于 Workspace id 永不复用，进程本地删除标记会拒绝延迟到达的 changed 帧或陈旧基线行。重连仍从 `workspace.list` 刷新；Workspace 增量绝不会剪除会话状态。 +删除确认框会保持待处理，直到 React Workspace 投影已经提交目标 id 的移除，因此下一次创建操作不会读到一帧陈旧列表。创建请求进行中会暂停重复名称校验，因为已提交的 `host/workspace-changed` 帧可能先于一元响应发布刚创建的 Workspace；如果请求失败并让表单回到可编辑状态，系统会重新使用最新列表执行校验。 + ## 确认交互 现有 Workspace 行菜单会在删除前打开共享 `Modal`。文案明确说明三项后果：Workspace 会从列表中移除，文件夹和会话日志会保留，相关会话会出现在 Ungrouped 下。请求待处理期间，确认与 Cancel 控件均被禁用，重复确认会被忽略，Escape 或 Close 也无法关闭此次操作。失败时 `Modal` 保持打开并显示错误；提交前使用 Cancel、Escape 或 Close 绝不会触发删除。 @@ -48,7 +50,7 @@ Create 与 delete 会在记录／顺序对可能分叉之前写入持久 `pendin ## Verification -Workspace 包测试固定了仅删除元数据的成功路径、同路径重新注册、未知 id 的幂等行为、表操作失败回滚、明确标记的重启恢复、来源不明损坏的拒绝，以及缓存／表不变量行为。Apiproxy 与载体测试固定了 schema、处理器、`workspace-not-found`、保留会话／文件夹、使用新 id 重新注册，以及已提交的 `host/workspace-removed` 帧。客户端测试固定了一元直接回显、重复移除、延迟到达的 changed 帧，以及删除与进行中基线并发的行为。组件测试固定了确认交互、待处理状态下抑制重复提交、成功、失败、Cancel、Escape 与 Close。 +Workspace 包测试固定了仅删除元数据的成功路径、同路径重新注册、未知 id 的幂等行为、表操作失败回滚、明确标记的重启恢复、来源不明损坏的拒绝，以及缓存／表不变量行为。Apiproxy 与载体测试固定了 schema、处理器、`workspace-not-found`、保留会话／文件夹、使用新 id 重新注册，以及已提交的 `host/workspace-removed` 帧。客户端测试固定了一元直接回显、重复移除、延迟到达的 changed 帧，以及删除与进行中基线并发的行为。组件测试固定了确认交互、投影稳定后关闭、待处理状态下抑制重复提交、成功帧先于一元响应、失败、Cancel、Escape 与 Close。浏览器场景会在为不同目录复用已删除名称时，观测每一次瞬时 alert、slot error、console error 与 page error。 组装后的无密钥 Web 场景会注册一个已有临时项目目录，将持久化会话计入账本，把该会话设为当前会话，在 Chromium 中确认删除，并验证 Workspace 分组消失，而 Ungrouped 保留当前会话。该场景在删除前后检查用户文件和 JSONL 日志，并在刷新后重复验证 UI、目录与日志。 diff --git a/apps/web/tests/workspace-management.e2e.ts b/apps/web/tests/workspace-management.e2e.ts index 3239dcfc12..98a2338064 100644 --- a/apps/web/tests/workspace-management.e2e.ts +++ b/apps/web/tests/workspace-management.e2e.ts @@ -108,6 +108,31 @@ describe('web e2e: workspace management (create / rename / flat view / hover car it('deletes only the Workspace registration and keeps its current Session, folder, and log', async () => { onTestFailed(() => saveFailureShot(page, 'web-e2e-ws-delete')) + const slotConsoleErrors: string[] = [] + const transientSlotErrors: string[] = [] + page.on('console', (message) => { + if (message.type() === 'error' && /slot entry crashed/i.test(message.text())) { + slotConsoleErrors.push(message.text()) + } + }) + await page.exposeFunction('recordDshSlotError', (key: string) => { + if (!transientSlotErrors.includes(key)) transientSlotErrors.push(key) + }) + await page.evaluate(() => { + const target = window as unknown as { recordDshSlotError(key: string): Promise } + const seen = new Set() + const collect = (): void => { + for (const node of document.querySelectorAll('[data-slot-error]')) { + const key = node.dataset.slotError ?? '' + if (!seen.has(key)) { + seen.add(key) + void target.recordDshSlotError(key) + } + } + } + new MutationObserver(collect).observe(document.documentElement, { childList: true, subtree: true }) + collect() + }) // Register the scaffold's existing project directory through the real UI. await page.getByRole('button', { name: 'Create workspace' }).click() await page.getByRole('menuitem', { name: 'Create workspace' }).hover() @@ -212,6 +237,69 @@ describe('web e2e: workspace management (create / rename / flat view / hover car await stat(logLocation.path) expect((await scaffold.ctx.sessionPersistence.inspect(SessionId(SEED_ID))).events.length).toBeGreaterThan(0) + expect(transientSlotErrors).toEqual([]) + expect(slotConsoleErrors).toEqual([]) + expect(tripwire.pageErrors).toEqual([]) + }, 90_000) + + it('reuses a deleted title for a different new directory without any transient error surface', async () => { + onTestFailed(() => saveFailureShot(page, 'web-e2e-ws-reuse-title')) + const title = 'same-name' + const oldPath = join(scaffold.workspaceCwd, 'adopted', title) + await mkdir(oldPath, { recursive: true }) + const transientErrors: string[] = [] + const consoleErrors: string[] = [] + page.on('console', (message) => { + if (message.type() === 'error') consoleErrors.push(message.text()) + }) + await page.exposeFunction('recordDshTransientWorkspaceError', (message: string) => { + if (!transientErrors.includes(message)) transientErrors.push(message) + }) + await page.evaluate(() => { + const target = window as unknown as { + recordDshTransientWorkspaceError(message: string): Promise + } + const collect = (): void => { + for (const node of document.querySelectorAll('[data-slot-error], [role="alert"]')) { + const message = node.dataset.slotError ?? node.textContent?.trim() ?? '' + if (message !== '') void target.recordDshTransientWorkspaceError(message) + } + } + new MutationObserver(collect).observe(document.documentElement, { childList: true, subtree: true }) + collect() + }) + + await page.getByRole('button', { name: 'Create workspace' }).click() + await page.getByRole('menuitem', { name: 'Create workspace' }).hover() + await page.getByRole('menuitem', { name: 'Use an existing folder' }).click() + const adopt = page.getByRole('dialog', { name: 'Use an existing folder' }) + await adopt.getByLabel('Existing folder path').fill(oldPath) + await adopt.getByRole('button', { name: 'Use folder' }).click() + await expect.poll(() => adopt.count(), { timeout: 10_000 }).toBe(0) + const oldWorkspace = await scaffold.ctx.workspace.resolveByPath(oldPath) + if (oldWorkspace === undefined) throw new Error('old same-name Workspace was not registered') + + const oldRow = page.locator('[role="treeitem"]').filter({ hasText: title }).first() + await oldRow.hover() + await page.getByRole('button', { name: `Workspace actions for ${title}` }).click() + await page.getByRole('menuitem', { name: 'Delete workspace' }).click() + await page.getByRole('dialog', { name: 'Delete workspace' }) + .getByRole('button', { name: 'Delete workspace' }).click() + await expect.poll(() => scaffold.ctx.workspace.get(oldWorkspace.id), { timeout: 10_000 }).toBeUndefined() + + await page.getByRole('button', { name: 'Create workspace' }).click() + await page.getByRole('menuitem', { name: 'Create workspace' }).hover() + await page.getByRole('menuitem', { name: 'Create a new workspace' }).click() + const create = page.getByRole('dialog', { name: 'Create a new workspace' }) + await create.getByLabel('New workspace name').fill(title) + await create.getByRole('button', { name: 'Create workspace' }).click() + await expect.poll(() => create.count(), { timeout: 10_000 }).toBe(0) + const fresh = scaffold.ctx.workspace.list().find(workspace => workspace.title === title) + expect(fresh?.id).toBeDefined() + expect(fresh?.id).not.toBe(oldWorkspace.id) + expect(fresh?.path).toBe(join(scaffold.workspaceCwd, title)) + expect(transientErrors).toEqual([]) + expect(consoleErrors).toEqual([]) expect(tripwire.pageErrors).toEqual([]) }, 90_000) diff --git a/packages/client/runtime/src/client/workspaces/manager.ts b/packages/client/runtime/src/client/workspaces/manager.ts index 7179ed9eb9..ce4198cd01 100644 --- a/packages/client/runtime/src/client/workspaces/manager.ts +++ b/packages/client/runtime/src/client/workspaces/manager.ts @@ -133,7 +133,7 @@ export class WorkspaceManager { */ async delete(workspaceId: WorkspaceId): Promise> { const { result } = await this.api.workspace.delete({ workspaceId }) - if (result.ok) this.remove(workspaceId) + if (result.ok) this.remove(workspaceId, true) return result } @@ -224,14 +224,21 @@ export class WorkspaceManager { } /** Remove one id idempotently and retain a tombstone against late echoes. */ - private remove(workspaceId: WorkspaceId): void { + private remove(workspaceId: WorkspaceId, direct = false): void { this.refreshFrames?.push({ type: 'remove', workspaceId }) this.removedIds.add(workspaceId) const items = this.items.filter(item => item.getSnapshot().view?.workspaceId !== workspaceId) - if (items.length === this.items.length) return + if (items.length === this.items.length) { + // The Host frame may have removed the row first but left its batched + // notification pending. A successful unary echo still flushes that + // committed state before the user action resolves. + if (direct) this.notifier.notifyNow() + return + } this.items = items - this.notifier.markDirty() + if (direct) this.notifier.notifyNow() + else this.notifier.markDirty() } private installViews(views: readonly WorkspaceView[]): void { diff --git a/packages/client/ui-workspace/src/client/WorkspaceBrowser.tsx b/packages/client/ui-workspace/src/client/WorkspaceBrowser.tsx index 0090164928..c56de93c56 100644 --- a/packages/client/ui-workspace/src/client/WorkspaceBrowser.tsx +++ b/packages/client/ui-workspace/src/client/WorkspaceBrowser.tsx @@ -307,7 +307,15 @@ export function WorkspaceBrowser({ // unmount that row without tearing down the in-flight confirmation state. const [deleteTarget, setDeleteTarget] = useState<{ workspaceId: WorkspaceId; title: string } | null>(null) const [deleting, setDeleting] = useState(false) + const [deleteCommittedId, setDeleteCommittedId] = useState(null) const [deleteError, setDeleteError] = useState(null) + useEffect(() => { + if (deleteCommittedId === null + || workspaces.some(workspace => workspace.workspaceId === deleteCommittedId)) return + setDeleting(false) + setDeleteCommittedId(null) + setDeleteTarget(null) + }, [deleteCommittedId, workspaces]) const closeDelete = () => { if (deleting) return setDeleteTarget(null) @@ -317,10 +325,13 @@ export function WorkspaceBrowser({ /* v8 ignore next -- the Modal is absent without a target and its button is disabled while deleting. */ if (deleting || deleteTarget === null) return setDeleting(true) + setDeleteCommittedId(null) setDeleteError(null) deleteWorkspace(deleteTarget.workspaceId).then(() => { - setDeleting(false) - setDeleteTarget(null) + // Keep the confirmation pending until this component has rendered the + // committed list projection without the deleted id. Closing earlier + // exposes one stale React frame to the next Create Workspace gesture. + setDeleteCommittedId(deleteTarget.workspaceId) }).catch((reason: unknown) => { setDeleting(false) setDeleteError(reason instanceof Error ? reason.message : String(reason)) diff --git a/packages/client/ui-workspace/src/client/WorkspacePicker.tsx b/packages/client/ui-workspace/src/client/WorkspacePicker.tsx index 2be39875bc..99ed2831a6 100644 --- a/packages/client/ui-workspace/src/client/WorkspacePicker.tsx +++ b/packages/client/ui-workspace/src/client/WorkspacePicker.tsx @@ -60,7 +60,7 @@ export function WorkspaceCreateFlow({ const [creating, setCreating] = useState(false) const [modalError, setModalError] = useState(null) const normalizedWorkspaceName = workspaceName.trim() - const duplicateWorkspaceName = normalizedWorkspaceName !== '' + const duplicateWorkspaceName = !creating && normalizedWorkspaceName !== '' && workspaces.some(workspace => workspace.title === normalizedWorkspaceName) const items: MenuEntry[] = [ diff --git a/packages/client/ui-workspace/tests/workspace-browser.spec.tsx b/packages/client/ui-workspace/tests/workspace-browser.spec.tsx index 1dbe895b74..33abdc1231 100644 --- a/packages/client/ui-workspace/tests/workspace-browser.spec.tsx +++ b/packages/client/ui-workspace/tests/workspace-browser.spec.tsx @@ -461,7 +461,7 @@ describe('WorkspaceBrowser', () => { it('confirms Workspace deletion, explains retention, and blocks duplicate submission', async () => { let resolveDelete!: () => void const deleteWorkspace = vi.fn(() => new Promise((resolve) => { resolveDelete = resolve })) - mount({ + const browser = mount({ useWorkspaces: hook(workspaceState([workspace('alpha', ['session'], 'Alpha')])), deleteWorkspace, }) @@ -484,6 +484,11 @@ describe('WorkspaceBrowser', () => { fireEvent.click(screen.getByRole('button', { name: 'Close' })) expect(screen.getByRole('dialog', { name: 'Delete workspace' })).toBeTruthy() await act(async () => { resolveDelete() }) + // RPC success alone does not close: the component waits until its + // useWorkspaces projection has committed the removal, preventing a stale + // duplicate-name frame from leaking into the next create gesture. + expect(screen.getByRole('dialog', { name: 'Delete workspace' })).toBeTruthy() + rerender(browser, { useWorkspaces: hook(workspaceState([])) }) expect(screen.queryByRole('dialog', { name: 'Delete workspace' })).toBeNull() }) diff --git a/packages/client/ui-workspace/tests/workspace-picker.spec.tsx b/packages/client/ui-workspace/tests/workspace-picker.spec.tsx index d487fae5f8..a5510178e7 100644 --- a/packages/client/ui-workspace/tests/workspace-picker.spec.tsx +++ b/packages/client/ui-workspace/tests/workspace-picker.spec.tsx @@ -35,18 +35,25 @@ function anchor(): { current: HTMLElement } { function mount(items: readonly WorkspaceView[] = [workspace('alpha', 'Alpha')], createWorkspace = vi.fn()) { const onPick = vi.fn() const onClose = vi.fn() - const view = render( + const anchorRef = anchor() + const renderPicker = (nextItems: readonly WorkspaceView[]) => ( , + /> ) - return { view, onPick, onClose, createWorkspace } + const view = render( + renderPicker(items), + ) + return { + view, onPick, onClose, createWorkspace, + rerenderItems: (nextItems: readonly WorkspaceView[]) => { view.rerender(renderPicker(nextItems)) }, + } } function chooseCreateItem(name: 'Use an existing folder' | 'Create a new workspace'): void { @@ -106,6 +113,22 @@ describe('WorkspacePicker', () => { expect(b.createWorkspace).not.toHaveBeenCalled() }) + it('does not flash a duplicate alert when the successful create frame arrives before its unary response', async () => { + let resolve!: (workspace: WorkspaceView) => void + const pending = new Promise((settle) => { resolve = settle }) + const created = workspace('fresh', 'same-name') + const b = mount([], vi.fn(() => pending)) + chooseCreateItem('Create a new workspace') + fireEvent.change(screen.getByLabelText('New workspace name'), { target: { value: 'same-name' } }) + fireEvent.click(screen.getByRole('button', { name: 'Create workspace' })) + + b.rerenderItems([created]) + expect(screen.getByRole('status').textContent).toBe('Creating workspace…') + expect(screen.queryByRole('alert')).toBeNull() + await act(async () => { resolve(created); await pending }) + expect(b.onPick).toHaveBeenCalledWith(created.workspaceId) + }) + it('exposes creation phase and error text while retaining the modal for retry', async () => { let reject!: (reason: unknown) => void const pending = new Promise((_resolve, rejectPromise) => { reject = rejectPromise }) From e2eca69e9c0ba88f591afe84727b4634d596c3b3 Mon Sep 17 00:00:00 2001 From: Chinesezjc Date: Mon, 27 Jul 2026 15:54:59 +0800 Subject: [PATCH 24/36] docs(ci): writer-level trust boundary stated everywhere; serial note counts four references MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit - Sweep every remaining 'admin-only' claim (workflow comments, runbook lines 13/40, topology note, all zh pairs): the variable is writer-manageable, and the boundary against untrusted code is repository membership (private, forking disabled, Dependabot excluded) — stated identically at every site instead of only in the 'who can flip' paragraph. - Serial cross-platform reference note (both languages): master now runs four references — the three hosted OS legs plus the self-hosted standby drill, linked to the failover runbook. Static gate green locally: 32 passed, 0 failed. --- ...2026-07-21-serial-cross-platform-ci-reference.i18n.yaml | 6 +++--- .../2026-07-21-serial-cross-platform-ci-reference.md | 6 +++--- .../2026-07-21-serial-cross-platform-ci-reference.zh.md | 6 +++--- ...26-07-22-evidence-based-larger-hosted-runners.i18n.yaml | 4 ++-- .../2026-07-22-evidence-based-larger-hosted-runners.md | 2 +- .../2026-07-22-evidence-based-larger-hosted-runners.zh.md | 2 +- .../process/2026-07-26-ci-failover-runbook.i18n.yaml | 4 ++-- .../implemented/process/2026-07-26-ci-failover-runbook.md | 4 ++-- .../process/2026-07-26-ci-failover-runbook.zh.md | 4 ++-- .github/workflows/ci.yml | 7 ++++--- 10 files changed, 23 insertions(+), 22 deletions(-) diff --git a/.agents/notes/implemented/process/2026-07-21-serial-cross-platform-ci-reference.i18n.yaml b/.agents/notes/implemented/process/2026-07-21-serial-cross-platform-ci-reference.i18n.yaml index 17edb300cc..50ac9c830b 100644 --- a/.agents/notes/implemented/process/2026-07-21-serial-cross-platform-ci-reference.i18n.yaml +++ b/.agents/notes/implemented/process/2026-07-21-serial-cross-platform-ci-reference.i18n.yaml @@ -1,6 +1,6 @@ # Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each # 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 -2026-07-21-serial-cross-platform-ci-reference.md: 5433d2c51831ce61d06a16ee0b0ed982911f9218 -2026-07-21-serial-cross-platform-ci-reference.zh.md: 041d53d13e14354c995e4b65defce94a97646b0a +# pnpm run verify-translation-pairing --write .agents/notes/implemented/process/2026-07-21-serial-cross-platform-ci-reference.md +2026-07-21-serial-cross-platform-ci-reference.md: 3e3d3ed06a16baf81b940b50c3d3deb75b7d8894 +2026-07-21-serial-cross-platform-ci-reference.zh.md: e05f92c05ab66d5a444f29186c605b4609d36110 diff --git a/.agents/notes/implemented/process/2026-07-21-serial-cross-platform-ci-reference.md b/.agents/notes/implemented/process/2026-07-21-serial-cross-platform-ci-reference.md index 5433d2c518..3e3d3ed06a 100644 --- a/.agents/notes/implemented/process/2026-07-21-serial-cross-platform-ci-reference.md +++ b/.agents/notes/implemented/process/2026-07-21-serial-cross-platform-ci-reference.md @@ -14,15 +14,15 @@ Reviewers also need a direct answer to a simpler question: what happens when the ## Decision -[CI](../../../../.github/workflows/ci.yml) gives pull-request and master-push events complementary responsibilities. Pull requests run consolidated Linux and Windows jobs plus the Node compatibility and Python contracts on standard GitHub-hosted capacity. A push to `master` skips those jobs and runs three explicit references named `serial / linux`, `serial / macos`, and `serial / windows`. They intentionally duplicate their short checkout, runtime setup, and immutable install sequences instead of hiding the operating systems behind a matrix or reusable workflow. `workflow_dispatch` is reserved for runner benchmarks. +[CI](../../../../.github/workflows/ci.yml) gives pull-request and master-push events complementary responsibilities. Pull requests run consolidated Linux and Windows jobs plus the Node compatibility and Python contracts on standard GitHub-hosted capacity. A push to `master` skips those jobs and runs four explicit references: `serial / linux`, `serial / macos`, and `serial / windows` on standard hosted runners, plus `serial / linux (self-hosted standby)` on the in-house `vm-backup` pool — the hot-standby drill that continuously re-proves the failover target described in the [failover runbook](2026-07-26-ci-failover-runbook.md). They intentionally duplicate their short checkout, runtime setup, and immutable install sequences instead of hiding the operating systems behind a matrix or reusable workflow. `workflow_dispatch` is reserved for runner benchmarks. -Each reference job runs `pnpm run check:ci` without any shard selector. `DSH_GATE_CONCURRENCY=1` makes the top-level aggregate execute one ready gate at a time; coverage, snapshot replay, built-bin smoke, and publication validation also receive worker counts of one. The three operating-system jobs may run beside one another, but each host's repository gates are serial and complete. Linux installs bubblewrap before replaying snapshots, and Windows enables Developer Mode before installing the symlinked workspace. +Each reference job runs `pnpm run check:ci` without any shard selector. `DSH_GATE_CONCURRENCY=1` makes the top-level aggregate execute one ready gate at a time; coverage, snapshot replay, built-bin smoke, and publication validation also receive worker counts of one. The reference jobs may run beside one another, but each host's repository gates are serial and complete. Linux installs bubblewrap before replaying snapshots, and Windows enables Developer Mode before installing the symlinked workspace. Platform ownership remains explicit inside that complete aggregate. `pty-local` supports Linux and macOS and therefore owns its unit and per-file coverage contract on POSIX rather than loading a backend that rejects `win32`; the Windows run still executes every portable package. Portable fixtures derive native paths through `node:path`, compare canonical identities with the same native realpath implementation as production, and use filenames legal on every host. ACP snapshot runs also pass both JavaScript and native realpath spellings of their generated cwd to the normalizer, which replaces aliases longest-first so Windows short and long paths cannot churn shared fixtures. The macOS reference runs the ordinary Vitest project in forked processes. Node 24 on macOS arm64 has aborted in its CJS lexer from a worker thread; the process boundary contains that external runtime failure without removing any test from the aggregate, while Linux and Windows retain the lower-overhead thread pool. Repository-owned races are fixed at their observation boundaries: dev bundle polling stages each candidate table, graph, and watch-baseline map before publishing a rescan, and a missing bundle remains dirty until a successful content hash. PTY readiness retains a prompt candidate while polling checks foreground ownership; the ordinary silence bound covers inherited markers from interactive children. Real PTY fixtures assemble synchronization tokens at runtime so the interactive shell's input echo cannot satisfy a child-readiness wait. The live-link package-manager e2e preserves the workflow-prepared Corepack home and pnpm metadata/store caches while isolating the other managers' mutable caches, so it does not discard reusable package-manager state before the install. -Master reference jobs are diagnostic and do not participate in the pull request's required `all checks passed` result. A pull request runs only its required jobs; a master push runs only the three serial references. Performance is evaluated from completed hosted-job timestamps and reported as a measurement; it is not encoded as a `timeout-minutes` value. +Master reference jobs are diagnostic and do not participate in the pull request's required `all checks passed` result. A pull request runs only its required jobs; a master push runs only the serial references. Performance is evaluated from completed hosted-job timestamps and reported as a measurement; it is not encoded as a `timeout-minutes` value. The portable reference uses GitHub's standard `ubuntu-latest`, `macos-latest`, and `windows-2025` labels. Required pull-request jobs use the same portable Linux and Windows capacity under the [required-CI decision](2026-07-23-portable-required-pull-request-ci.md). Higher-core hosted runners remain manual benchmarks because a correctness path must remain runnable without repository-external runner configuration. diff --git a/.agents/notes/implemented/process/2026-07-21-serial-cross-platform-ci-reference.zh.md b/.agents/notes/implemented/process/2026-07-21-serial-cross-platform-ci-reference.zh.md index 041d53d13e..e05f92c05a 100644 --- a/.agents/notes/implemented/process/2026-07-21-serial-cross-platform-ci-reference.zh.md +++ b/.agents/notes/implemented/process/2026-07-21-serial-cross-platform-ci-reference.zh.md @@ -14,15 +14,15 @@ Status: implemented ## 决策 -[CI](../../../../.github/workflows/ci.yml) 为拉取请求事件与 master 推送事件赋予互补的职责。拉取请求在 GitHub 标准托管容量上运行合并后的 Linux 和 Windows 作业，以及 Node 兼容性与 Python 契约。向 `master` 推送时会跳过这些作业，改为运行三个显式参考作业，名称分别为 `serial / linux`、`serial / macos` 和 `serial / windows`。这些作业有意分别重复简短的代码检出、运行时设置和依赖锁定的安装步骤，不用矩阵或可复用工作流把操作系统差异隐藏起来。`workflow_dispatch` 仅用于运行器基准测试。 +[CI](../../../../.github/workflows/ci.yml) 为拉取请求事件与 master 推送事件赋予互补的职责。拉取请求在 GitHub 标准托管容量上运行合并后的 Linux 和 Windows 作业，以及 Node 兼容性与 Python 契约。向 `master` 推送时会跳过这些作业，改为运行四个显式参考作业：在标准托管运行器上的 `serial / linux`、`serial / macos` 和 `serial / windows`，以及在公司自有 `vm-backup` 池上的 `serial / linux (self-hosted standby)`——后者是热备演练，持续验证[故障切换手册](2026-07-26-ci-failover-runbook.md)所描述的切换目标。这些作业有意分别重复简短的代码检出、运行时设置和依赖锁定的安装步骤，不用矩阵或可复用工作流把操作系统差异隐藏起来。`workflow_dispatch` 仅用于运行器基准测试。 -每个参考作业均在不设置任何分片选择器的情况下运行 `pnpm run check:ci`。`DSH_GATE_CONCURRENCY=1` 使顶层聚合每次只执行一个已经就绪的门禁；覆盖率、快照回放、built-bin 冒烟测试和发布验证的并发数也设为 1。三种操作系统的作业可以彼此并行，但每台主机上的仓库门禁都串行运行且完整执行。Linux 在回放快照前安装 bubblewrap，Windows 则在安装采用符号链接的工作区前启用开发人员模式。 +每个参考作业均在不设置任何分片选择器的情况下运行 `pnpm run check:ci`。`DSH_GATE_CONCURRENCY=1` 使顶层聚合每次只执行一个已经就绪的门禁；覆盖率、快照回放、built-bin 冒烟测试和发布验证的并发数也设为 1。各参考作业可以彼此并行，但每台主机上的仓库门禁都串行运行且完整执行。Linux 在回放快照前安装 bubblewrap，Windows 则在安装采用符号链接的工作区前启用开发人员模式。 该完整聚合流程仍明确划分平台归属。`pty-local` 支持 Linux 与 macOS，因此其单元测试和逐文件覆盖率契约由 POSIX 平台负责，而不会在 Windows 上加载一个明确拒绝 `win32` 的后端；Windows 仍会执行所有可移植包（package）。可移植 fixture（测试前置数据）通过 `node:path` 派生原生路径，使用与生产代码相同的原生 realpath 实现比较规范化后的路径标识，并采用所有宿主机均允许的文件名。ACP（Agent Client Protocol）快照运行还会把生成的 cwd 分别通过 realpath 的 JavaScript 实现与原生实现得到的两种表示一并传给规范化器；规范化器按长度从长到短替换这些别名，避免 Windows 的短路径与长路径表示差异导致共享 fixture 反复变化。 macOS 参考流程使用 fork 进程运行常规 Vitest 项目。macOS arm64 上的 Node 24 曾在工作线程中执行 CJS 词法分析器时异常终止；进程边界能够隔离这一外部运行时故障，且无需从聚合流程中删除任何测试，而 Linux 与 Windows 仍使用开销更低的线程池。仓库自身引入的竞态均在相应的观测边界修复：开发构建产物的轮询逻辑每次发布重新扫描结果前，都会先暂存候选表、候选图和候选监视基线映射；构建产物缺失后会一直保持脏状态，直到成功计算内容哈希。PTY 就绪检测会在轮询检查前台进程组归属期间保留提示符候选项；常规静默时限也适用于交互式子进程继承提示符标记的情况。真实 PTY fixture 会在运行时拼接同步标记，使就绪等待逻辑不会把交互式 shell 的输入回显误判为子进程已就绪。实时链接场景下的包管理器 e2e 会保留由工作流预先准备的 Corepack 主目录、pnpm 元数据缓存和 store 缓存，同时隔离其他包管理器的可变缓存，因此不会在安装前丢弃可复用的包管理器状态。 -master 分支的参考作业仅用于诊断，不参与拉取请求所要求的 `all checks passed` 结果。拉取请求只运行其必需作业；向 master 推送时只运行三个串行参考作业。系统根据已完成托管作业的时间戳评估性能，并将其报告为测量结果，而不是写成 `timeout-minutes` 值。 +master 分支的参考作业仅用于诊断，不参与拉取请求所要求的 `all checks passed` 结果。拉取请求只运行其必需作业；向 master 推送时只运行串行参考作业。系统根据已完成托管作业的时间戳评估性能，并将其报告为测量结果，而不是写成 `timeout-minutes` 值。 可移植的参考流程使用 GitHub 标准的 `ubuntu-latest`、`macos-latest` 和 `windows-2025` 标签。依据[必需 CI 决策](2026-07-23-portable-required-pull-request-ci.md)，拉取请求必需作业使用相同的可移植 Linux 和 Windows 容量。更高核心数的托管运行器仍仅用于手动基准测试，因为正确性路径必须无需仓库外部的运行器配置即可运行。 diff --git a/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.i18n.yaml b/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.i18n.yaml index 99cabc76bb..f65ebb1ba4 100644 --- a/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.i18n.yaml +++ b/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.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/process/2026-07-22-evidence-based-larger-hosted-runners.md -2026-07-22-evidence-based-larger-hosted-runners.md: 5b399be5571ddaf1f775ba43a2233198b8e09b18 -2026-07-22-evidence-based-larger-hosted-runners.zh.md: f77516e2375bfc0557679d05fd275bd9cee7d8eb +2026-07-22-evidence-based-larger-hosted-runners.md: 180cc03ad091b2e9e96a86311515250f92065c6b +2026-07-22-evidence-based-larger-hosted-runners.zh.md: b81f67805fd543e81ede02ceeac2dda1831f4cef diff --git a/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.md b/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.md index 5b399be557..180cc03ad0 100644 --- a/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.md +++ b/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.md @@ -52,7 +52,7 @@ The process-bound coverage project contains exactly five suite files. Thirty-two Complete serial Linux, macOS, and Windows references run only when `master` moves. Pull requests use the enterprise required path plus standard-hosted compatibility jobs, while other larger-runner sizes run only by manual dispatch. -An additional serial Linux reference runs on the in-house self-hosted pool (`vm-backup` label: a 64-core VM with six always-on systemd-managed runner instances) on every `master` push. It is a hot-standby drill, not a required check: each run re-proves that the persistent VM can execute the complete unsharded aggregate. The actual switch is pre-wired: the three required Linux jobs resolve their pool through the admin-only `DSH_CI_FAILOVER` repository variable, so an outage response is setting one variable and re-running — no merge, which would be deadlocked behind the failing checks themselves ([runbook](2026-07-26-ci-failover-runbook.md)). Because the standby lane is push-triggered, it always executes the base branch's workflow definition — no pull-request-editable path can route code to these runners, and the repository additionally keeps forking disabled. +An additional serial Linux reference runs on the in-house self-hosted pool (`vm-backup` label: a 64-core VM with six always-on systemd-managed runner instances) on every `master` push. It is a hot-standby drill, not a required check: each run re-proves that the persistent VM can execute the complete unsharded aggregate. The actual switch is pre-wired: the three required Linux jobs resolve their pool through the writer-manageable `DSH_CI_FAILOVER` repository variable, so an outage response is setting one variable and re-running — no merge, which would be deadlocked behind the failing checks themselves ([runbook](2026-07-26-ci-failover-runbook.md)). Because the standby lane is push-triggered, it always executes the base branch's workflow definition — no pull-request-editable path can route code to these runners, and the repository additionally keeps forking disabled. ## Alternatives considered diff --git a/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.zh.md b/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.zh.md index f77516e237..b81f67805f 100644 --- a/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.zh.md +++ b/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.zh.md @@ -52,7 +52,7 @@ Windows 仓库工作在超过 16 核后收益很小，但 32 核池可以让完 只有在 `master` 移动时，才运行完整的 Linux、macOS 和 Windows 串行参考。拉取请求使用企业级运行器必需路径和标准托管兼容性作业，其他大型运行器规格仅通过手动触发运行。 -另有一条串行 Linux 参考在每次 `master` 推送时运行于公司自有的自托管池（`vm-backup` 标签：一台 64 核虚拟机，运行 6 个常驻的 systemd 管理运行器实例）。它是热备演练而非必需检查：每次运行都重新证明这台持久化虚拟机能够执行完整的未分片聚合流程。实际切换机制已预先布线：三个必需 Linux 作业通过仅限管理员的仓库变量 `DSH_CI_FAILOVER` 解析运行器池，因此故障响应就是设置一个变量并重跑——无需合并（合并本身会被正在失败的检查死锁）（[切换手册](2026-07-26-ci-failover-runbook.md)）。该热备通道由 push 触发，执行的始终是基线分支自身的工作流定义——不存在任何可由拉取请求编辑的路径能把代码路由到这些运行器上；此外仓库继续保持禁用 fork。 +另有一条串行 Linux 参考在每次 `master` 推送时运行于公司自有的自托管池（`vm-backup` 标签：一台 64 核虚拟机，运行 6 个常驻的 systemd 管理运行器实例）。它是热备演练而非必需检查：每次运行都重新证明这台持久化虚拟机能够执行完整的未分片聚合流程。实际切换机制已预先布线：三个必需 Linux 作业通过写者可管理的仓库变量 `DSH_CI_FAILOVER` 解析运行器池，因此故障响应就是设置一个变量并重跑——无需合并（合并本身会被正在失败的检查死锁）（[切换手册](2026-07-26-ci-failover-runbook.md)）。该热备通道由 push 触发，执行的始终是基线分支自身的工作流定义——不存在任何可由拉取请求编辑的路径能把代码路由到这些运行器上；此外仓库继续保持禁用 fork。 ## 曾考虑的替代方案 diff --git a/.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.i18n.yaml b/.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.i18n.yaml index 7b8d08befe..de9ba10469 100644 --- a/.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.i18n.yaml +++ b/.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.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/process/2026-07-26-ci-failover-runbook.md -2026-07-26-ci-failover-runbook.md: 55c1350593562d62463e751451d50a79cf45a1d6 -2026-07-26-ci-failover-runbook.zh.md: 13977b78244440a23722d089849ea7ff6b751aea +2026-07-26-ci-failover-runbook.md: 05014454fa3e38045b89a857c346db0f897ab5a6 +2026-07-26-ci-failover-runbook.zh.md: e106a0de40799ca1c218217ea66c24068697dc53 diff --git a/.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.md b/.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.md index 55c1350593..05014454fa 100644 --- a/.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.md +++ b/.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.md @@ -10,7 +10,7 @@ The three required Linux worker jobs in [CI](../../../../.github/workflows/ci.ym ## Decision -Each of the three required Linux worker jobs — and the `all checks passed` verdict job, which would otherwise stay queued on the failed pool even after every worker passed — resolves its runner pool through the `DSH_CI_FAILOVER` repository variable. Unset (normal), they run on the hosted enterprise pools. Set to `selfhosted` by a repository admin, all four retarget onto the in-house self-hosted `vm-backup` pool, coverage and snapshot concurrency drop to shared-VM bounds, and the hosted-path pnpm cache restores are skipped. The switch is admin-only repository state, not a merge, so it works while every check is red. The in-house pool's readiness is continuously re-proven by the `serial / linux (self-hosted standby)` lane, which runs the complete unsharded aggregate on every master push. +Each of the three required Linux worker jobs — and the `all checks passed` verdict job, which would otherwise stay queued on the failed pool even after every worker passed — resolves its runner pool through the `DSH_CI_FAILOVER` repository variable. Unset (normal), they run on the hosted enterprise pools. Set to `selfhosted` by any repository writer, all four retarget onto the in-house self-hosted `vm-backup` pool, coverage and snapshot concurrency drop to shared-VM bounds, and the hosted-path pnpm cache restores are skipped. The switch is writer-manageable repository state, not a merge, so it works while every check is red. The in-house pool's readiness is continuously re-proven by the `serial / linux (self-hosted standby)` lane, which runs the complete unsharded aggregate on every master push. ### What the in-house pool is @@ -37,7 +37,7 @@ Delete the `DSH_CI_FAILOVER` variable (or set it to anything other than `selfhos ### Trust boundary -The variable is repository-admin-only state: a pull request can neither set it nor read a different value into effect, and the expressions live in the base branch's workflow definition. This failover path therefore adds no PR-editable route to the self-hosted pool. Runner-side enforcement — an org-level runner group restricting these runners to the master-ref workflow — is tracked separately and composes with this mechanism. +The variable is writer-manageable repository state; a pull request event itself can neither set it nor read a different value into effect, and the selector expressions live in workflow definitions. Note that under failover, `pull_request` runs execute the PR merge ref's own workflow definition — the boundary against untrusted code is repository membership (private, forking disabled, Dependabot excluded by the selectors), not the variable. Runner-side enforcement — an org-level runner group restricting these runners to the master-ref workflow — is tracked separately and composes with this mechanism. ## Alternatives considered diff --git a/.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.zh.md b/.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.zh.md index 13977b7824..e106a0de40 100644 --- a/.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.zh.md +++ b/.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.zh.md @@ -10,7 +10,7 @@ Status: implemented ## 决策 -三个必需的 Linux 工作作业——以及 `all checks passed` 判定作业（若不随切换，即使全部工作作业通过，它仍会滞留在故障池的队列中）——各自通过仓库变量 `DSH_CI_FAILOVER` 解析运行器池。变量不存在（正常）时它们运行在托管企业池上；由仓库管理员设为 `selfhosted` 时，四者全部切换到公司自有的自托管 `vm-backup` 池，coverage 与 snapshot 的并发降到共享虚拟机上限，并跳过托管路径的 pnpm 缓存恢复。这个开关是仅限管理员的仓库状态而非一次合并，因此在所有检查都是红色时仍然有效。自有池的就绪状态由 `serial / linux (self-hosted standby)` 通道持续验证——每次 master 推送都在其上运行完整的未分片聚合流程。 +三个必需的 Linux 工作作业——以及 `all checks passed` 判定作业（若不随切换，即使全部工作作业通过，它仍会滞留在故障池的队列中）——各自通过仓库变量 `DSH_CI_FAILOVER` 解析运行器池。变量不存在（正常）时它们运行在托管企业池上；由任何具备写权限的协作者设为 `selfhosted` 时，四者全部切换到公司自有的自托管 `vm-backup` 池，coverage 与 snapshot 的并发降到共享虚拟机上限，并跳过托管路径的 pnpm 缓存恢复。这个开关是写者可管理的仓库状态而非一次合并，因此在所有检查都是红色时仍然有效。自有池的就绪状态由 `serial / linux (self-hosted standby)` 通道持续验证——每次 master 推送都在其上运行完整的未分片聚合流程。 ### 自有池是什么 @@ -37,7 +37,7 @@ Status: implemented ### 信任边界 -该变量是仅限仓库管理员的状态：拉取请求既不能设置它，也不能让不同的值生效，且表达式存在于基线分支的工作流定义中。因此这条故障切换路径没有增加任何可由 PR 编辑的自托管池访问途径。运行器侧的强制约束——通过组织级 runner group 把这批运行器限定到 master 引用的工作流——另行跟踪，与本机制互补。 +该变量是写者可管理的仓库状态；`pull_request` 事件本身既不能设置它，也不能让不同的值生效，选择器表达式存在于工作流定义中。需要注意：故障切换期间，`pull_request` 运行执行的是 PR merge 引用自带的工作流定义——抵御不可信代码的边界是仓库成员资格（私有、禁 fork、选择器排除 Dependabot），而非该变量。（运行器侧的组织级 runner group 约束另行跟踪，与本机制互补。） ## 曾考虑的替代方案 diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml index 8c3b854ae6..9fe393b93c 100644 --- a/.github/workflows/ci.yml +++ b/.github/workflows/ci.yml @@ -34,8 +34,9 @@ jobs: # FAILOVER: each Linux enterprise job resolves its pool through the # DSH_CI_FAILOVER repository variable. Unset (normal), the expressions # pick the hosted enterprise pools below. Setting the variable to - # 'selfhosted' (repo Settings → Actions → Variables; admin-only, not - # PR-editable, no merge required) retargets all three onto the in-house + # 'selfhosted' (repo Settings → Actions → Variables; writer-manageable + # repository state — not PR-editable, no merge required) retargets all + # three onto the in-house # vm-backup pool and re-running the failed jobs is the entire switch — # see .agents/notes/implemented/process/2026-07-26-ci-failover-runbook.md. The # in-house pool's readiness is re-proven on every master push by the @@ -411,7 +412,7 @@ jobs: # Hot-standby drill for the in-house self-hosted pool: every master move # re-runs the complete unsharded aggregate on the persistent 64-core VM, # continuously proving that environment can take over a required lane if - # the hosted pools degrade (the switch is then setting the admin-only + # the hosted pools degrade (the switch is then setting the writer-manageable # DSH_CI_FAILOVER variable — see the failover runbook, no merge required). # Push-triggered, so it always executes the base branch's own workflow # definition — no PR-editable path selects these runners. Non-blocking for From 62e2551edd69f3277dd07ce92fb0f59840a3e257 Mon Sep 17 00:00:00 2001 From: 07akioni <07akioni2@gmail.com> Date: Mon, 27 Jul 2026 16:01:01 +0800 Subject: [PATCH 25/36] =?UTF-8?q?fix:=20darkmode=20=E6=BB=9A=E5=8A=A8?= =?UTF-8?q?=E6=9D=A1=E9=A2=9C=E8=89=B2?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- packages/client/ui-layout/README.md | 2 +- packages/client/ui-layout/README.zh.md | 2 +- .../ui-layout/src/client/theme-presenter.ts | 27 +++++++++++-------- packages/client/ui-layout/tests/apply.spec.ts | 6 ++++- .../ui-layout/tests/theme-presenter.spec.ts | 17 +++++++----- packages/client/ui-theme/README.md | 2 +- packages/client/ui-theme/README.zh.md | 2 +- 7 files changed, 36 insertions(+), 22 deletions(-) diff --git a/packages/client/ui-layout/README.md b/packages/client/ui-layout/README.md index 6aeda0e04b..26e909b964 100644 --- a/packages/client/ui-layout/README.md +++ b/packages/client/ui-layout/README.md @@ -2,7 +2,7 @@ English | [中文](README.zh.md) -Shell plugin: three-column AppFrame (drag handles and concession chain) plus the `ctx.layout` panel-geometry service; it registers into the runtime-owned `root` slot and declares `sidebar`, `conversation`, `details`, and `conversation.empty`. The sidebar is fixed-width (only details shrinks, then auto-closes); a closed sidebar retains a 56px control rail while details closes to zero width. The package also seats the theme presenter: it consumes resolved `ctx.theme` snapshots and projects them onto `document.body` (`data-ds-dark-theme` from the active color scheme plus the theme's alias tokens as inline variables). +Shell plugin: three-column AppFrame (drag handles and concession chain) plus the `ctx.layout` panel-geometry service; it registers into the runtime-owned `root` slot and declares `sidebar`, `conversation`, `details`, and `conversation.empty`. The sidebar is fixed-width (only details shrinks, then auto-closes); a closed sidebar retains a 56px control rail while details closes to zero width. The package also seats the theme presenter: it consumes resolved `ctx.theme` snapshots and projects them onto the document (`html { color-scheme }` for native UA chrome, `body[data-ds-dark-theme]` from the active color scheme, plus the theme's alias tokens as inline variables on body). AppFrame reads the runtime Session projection: `baselinesReady` selects loading, a page-local `SessionListState.intent` selects the empty composer, and a connected Session renders through `SessionProvider`. The conversation and empty-state owner shares are empty; each registrant obtains business data from standard hooks and actions from its own inject face. The sidebar owner share contains only `collapsed` and `width`; navigation actions belong to sidebar's own injected service face. diff --git a/packages/client/ui-layout/README.zh.md b/packages/client/ui-layout/README.zh.md index 9fbc2ed839..2e5799fd32 100644 --- a/packages/client/ui-layout/README.zh.md +++ b/packages/client/ui-layout/README.zh.md @@ -2,7 +2,7 @@ [English](README.md) | 中文 -外壳插件：三栏 AppFrame（拖动手柄与让步链）加 `ctx.layout` 面板几何服务；它注册到运行时拥有的 `root` slot，并声明 `sidebar`、`conversation`、`details` 和 `conversation.empty`。侧边栏宽度固定（只会收缩详情栏，然后将其自动关闭）；关闭的侧边栏仍保留 56px 控制轨道，详情栏则关闭到零宽度。该包还提供主题呈现器：它消费解析后的 `ctx.theme` 快照，并将其投影到 `document.body`（依据当前配色方案设置 `data-ds-dark-theme`，并将主题的别名 token 设为内联变量）。 +外壳插件：三栏 AppFrame（拖动手柄与让步链）加 `ctx.layout` 面板几何服务；它注册到运行时拥有的 `root` slot，并声明 `sidebar`、`conversation`、`details` 和 `conversation.empty`。侧边栏宽度固定（只会收缩详情栏，然后将其自动关闭）；关闭的侧边栏仍保留 56px 控制轨道，详情栏则关闭到零宽度。该包还提供主题呈现器：它消费解析后的 `ctx.theme` 快照，并将其投影到 document（用 `html { color-scheme }` 驱动原生 UA 控件，依据当前配色方案设置 `body[data-ds-dark-theme]`，并将主题的别名 token 设为 body 上的内联变量）。 AppFrame 读取运行时 Session 投影：`baselinesReady` 选择加载状态，页面局部的 `SessionListState.intent` 选择空白编辑器，已连接 Session 则通过 `SessionProvider` 渲染。会话及空状态的 owner share 为空；每个注册方通过标准 hook 获取业务数据，并从自身的 inject 表层获取操作。侧边栏 owner share 只包含 `collapsed` 和 `width`；导航操作属于侧边栏自身注入的服务表层。 diff --git a/packages/client/ui-layout/src/client/theme-presenter.ts b/packages/client/ui-layout/src/client/theme-presenter.ts index 958f2fd93e..07dc663c54 100644 --- a/packages/client/ui-layout/src/client/theme-presenter.ts +++ b/packages/client/ui-layout/src/client/theme-presenter.ts @@ -1,29 +1,33 @@ /** - * Global theme DOM applier: projects the resolved ThemeSnapshot onto - * document.body — the `data-ds-dark-theme` palette switch plus the active - * theme's alias-token overrides as inline CSS variables. Pure DOM writes, no - * React involvement; the presenter only ever retracts what it wrote itself, - * so foreign body attributes and inline styles survive apply/dispose. + * Global theme DOM applier: projects the resolved ThemeSnapshot onto the + * document — `html { color-scheme }` for native UA chrome (scrollbars, form + * controls), `body[data-ds-dark-theme]` for the token palette, and the active + * theme's alias-token overrides as inline CSS variables on body. Pure DOM + * writes, no React involvement; the presenter only ever retracts what it wrote + * itself, so foreign attributes and inline styles survive apply/dispose. */ import type { ThemeSnapshot } from '@deepseek-ai/dsh-client-ui-theme/client' /** Body attribute selecting the dark base palette in the token stylesheets. */ export const DARK_ATTRIBUTE = 'data-ds-dark-theme' -/** Applies theme snapshots to document.body; one instance per plugin fiber. */ +/** Applies theme snapshots to the document; one instance per plugin fiber. */ export class ThemePresenter { /** Token names this presenter wrote in the last apply (its retraction set). */ private appliedTokens: string[] = [] /** - * Project a snapshot onto the body: switch the palette attribute from - * `active.colorScheme` (never the id — `system` is resolved upstream) and - * replace the previously applied token variables with `active.tokens`. + * Project a snapshot onto the document: set root `color-scheme` and the body + * palette attribute from `active.colorScheme` (never the id — `system` is + * resolved upstream), then replace the previously applied token variables + * with `active.tokens`. * @param snapshot - resolved theme snapshot from ctx.theme. */ apply(snapshot: ThemeSnapshot): void { + const scheme = snapshot.active.colorScheme + document.documentElement.style.colorScheme = scheme const body = document.body - if (snapshot.active.colorScheme === 'dark') body.setAttribute(DARK_ATTRIBUTE, '') + if (scheme === 'dark') body.setAttribute(DARK_ATTRIBUTE, '') else body.removeAttribute(DARK_ATTRIBUTE) for (const name of this.appliedTokens) body.style.removeProperty(name) this.appliedTokens = [] @@ -33,8 +37,9 @@ export class ThemePresenter { } } - /** Retract everything this presenter wrote: the palette attribute and all applied token variables. */ + /** Retract everything this presenter wrote: root color-scheme, the palette attribute, and all applied token variables. */ dispose(): void { + document.documentElement.style.removeProperty('color-scheme') const body = document.body body.removeAttribute(DARK_ATTRIBUTE) for (const name of this.appliedTokens) body.style.removeProperty(name) diff --git a/packages/client/ui-layout/tests/apply.spec.ts b/packages/client/ui-layout/tests/apply.spec.ts index 1382f5160d..903591163c 100644 --- a/packages/client/ui-layout/tests/apply.spec.ts +++ b/packages/client/ui-layout/tests/apply.spec.ts @@ -63,15 +63,19 @@ describe('ui-layout client apply', () => { const fiber = ctx.plugin({ inject: [...inject], apply }) await fiber.await() // Initial getter application: jsdom has no matchMedia, system resolves light. + expect(document.documentElement.style.colorScheme).toBe('light') expect(document.body.hasAttribute('data-ds-dark-theme')).toBe(false) const theme = ctx.get('theme') as ThemeService theme.setTheme('dark') + expect(document.documentElement.style.colorScheme).toBe('dark') expect(document.body.hasAttribute('data-ds-dark-theme')).toBe(true) await fiber.dispose() + expect(document.documentElement.style.colorScheme).toBe('') expect(document.body.hasAttribute('data-ds-dark-theme')).toBe(false) - // Listener is off: further theme changes no longer reach the body. + // Listener is off: further theme changes no longer reach the document. theme.setTheme('light') theme.setTheme('dark') + expect(document.documentElement.style.colorScheme).toBe('') expect(document.body.hasAttribute('data-ds-dark-theme')).toBe(false) }) diff --git a/packages/client/ui-layout/tests/theme-presenter.spec.ts b/packages/client/ui-layout/tests/theme-presenter.spec.ts index ced83a379e..a14d781e5f 100644 --- a/packages/client/ui-layout/tests/theme-presenter.spec.ts +++ b/packages/client/ui-layout/tests/theme-presenter.spec.ts @@ -1,7 +1,7 @@ // @vitest-environment jsdom -// ThemePresenter behavior account: the palette attribute follows -// active.colorScheme only, token variables replace the previous apply's set, -// and dispose retracts everything the presenter wrote. +// ThemePresenter behavior account: root color-scheme and the palette attribute +// follow active.colorScheme only, token variables replace the previous apply's +// set, and dispose retracts everything the presenter wrote. import { beforeEach, describe, expect, it } from 'vitest' import type { ThemeSnapshot } from '@deepseek-ai/dsh-client-ui-theme/client' @@ -14,22 +14,26 @@ function snapshot(colorScheme: 'light' | 'dark', tokens: Record } beforeEach(() => { + document.documentElement.style.removeProperty('color-scheme') document.body.removeAttribute(DARK_ATTRIBUTE) document.body.removeAttribute('style') }) describe('ThemePresenter', () => { - it('light scheme leaves the dark attribute absent', () => { + it('light scheme sets root color-scheme and leaves the dark attribute absent', () => { const presenter = new ThemePresenter() presenter.apply(snapshot('light')) + expect(document.documentElement.style.colorScheme).toBe('light') expect(document.body.hasAttribute(DARK_ATTRIBUTE)).toBe(false) }) - it('dark scheme sets the attribute; switching back to light removes it', () => { + it('dark scheme sets root color-scheme and the attribute; switching to light clears both', () => { const presenter = new ThemePresenter() presenter.apply(snapshot('dark')) + expect(document.documentElement.style.colorScheme).toBe('dark') expect(document.body.hasAttribute(DARK_ATTRIBUTE)).toBe(true) presenter.apply(snapshot('light')) + expect(document.documentElement.style.colorScheme).toBe('light') expect(document.body.hasAttribute(DARK_ATTRIBUTE)).toBe(false) }) @@ -44,11 +48,12 @@ describe('ThemePresenter', () => { expect(document.body.style.getPropertyValue('--dsw-alias-fg')).toBe('') }) - it('dispose removes the attribute and every applied variable, sparing foreign inline styles', () => { + it('dispose removes color-scheme, the attribute, and every applied variable, sparing foreign inline styles', () => { document.body.style.setProperty('--foreign', 'kept') const presenter = new ThemePresenter() presenter.apply(snapshot('dark', { '--dsw-alias-bg': '#111' })) presenter.dispose() + expect(document.documentElement.style.colorScheme).toBe('') expect(document.body.hasAttribute(DARK_ATTRIBUTE)).toBe(false) expect(document.body.style.getPropertyValue('--dsw-alias-bg')).toBe('') expect(document.body.style.getPropertyValue('--foreign')).toBe('kept') diff --git a/packages/client/ui-theme/README.md b/packages/client/ui-theme/README.md index 5c9794d4f5..1227df357c 100644 --- a/packages/client/ui-theme/README.md +++ b/packages/client/ui-theme/README.md @@ -2,7 +2,7 @@ English | [中文](README.zh.md) -Theme plugin: ThemeService over the --dsw-* token base stylesheets (static scale + alias semantic layers). The service owns the theme preference (`light`/`dark`/`system`, persisted under `dsh.theme`), resolves `system` through `prefers-color-scheme`, and publishes immutable `ThemeSnapshot`s on the `theme/change` event; it never touches the DOM — ui-layout's presenter applies the resolved snapshot (`body[data-ds-dark-theme]` + inline alias tokens). Contract: api-contracts v3 §8. +Theme plugin: ThemeService over the --dsw-* token base stylesheets (static scale + alias semantic layers). The service owns the theme preference (`light`/`dark`/`system`, persisted under `dsh.theme`), resolves `system` through `prefers-color-scheme`, and publishes immutable `ThemeSnapshot`s on the `theme/change` event; it never touches the DOM — ui-layout's presenter applies the resolved snapshot (`html { color-scheme }`, `body[data-ds-dark-theme]`, and inline alias tokens). Contract: api-contracts v3 §8. ## Model Experience diff --git a/packages/client/ui-theme/README.zh.md b/packages/client/ui-theme/README.zh.md index 2e0f76133e..cd87ede726 100644 --- a/packages/client/ui-theme/README.zh.md +++ b/packages/client/ui-theme/README.zh.md @@ -2,7 +2,7 @@ [English](README.md) | 中文 -主题插件：基于 --dsw-* token 基础样式表（静态尺度 + 别名语义层）的 ThemeService。该服务拥有主题偏好（`light`／`dark`／`system`，以 `dsh.theme` 为键持久化），将 `system` 通过 `prefers-color-scheme` 解析为实际主题，并发布不可变的 `ThemeSnapshot`，通过 `theme/change` 事件通知变化；它绝不接触 DOM：ui-layout 的呈现器会应用解析后的快照（依据当前配色方案设置 `body[data-ds-dark-theme]`，并将主题的别名 token 设为内联变量）。契约：api-contracts v3 §8。 +主题插件：基于 --dsw-* token 基础样式表（静态尺度 + 别名语义层）的 ThemeService。该服务拥有主题偏好（`light`／`dark`／`system`，以 `dsh.theme` 为键持久化），将 `system` 通过 `prefers-color-scheme` 解析为实际主题，并发布不可变的 `ThemeSnapshot`，通过 `theme/change` 事件通知变化；它绝不接触 DOM：ui-layout 的呈现器会应用解析后的快照（`html { color-scheme }`、`body[data-ds-dark-theme]`，以及主题的别名 token 内联变量）。契约：api-contracts v3 §8。 ## 模型体验 From 24d7211f09d28055c0795eac4c91f924d3593e3c Mon Sep 17 00:00:00 2001 From: Chinesezjc Date: Mon, 27 Jul 2026 16:02:19 +0800 Subject: [PATCH 26/36] docs(ci): stop claiming no PR-editable path reaches the standby pool MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The standby lane itself is push-only, but under failover pull_request jobs do reach these runners with the PR merge ref's workflow. The workflow comment and the larger-runner note (both languages) now state that plainly and name the actual boundary — repository membership (private, forking disabled, Dependabot excluded) — matching the runbook. Static gate green locally: 32 passed, 0 failed. --- ...26-07-22-evidence-based-larger-hosted-runners.i18n.yaml | 4 ++-- .../2026-07-22-evidence-based-larger-hosted-runners.md | 2 +- .../2026-07-22-evidence-based-larger-hosted-runners.zh.md | 2 +- .github/workflows/ci.yml | 7 +++++-- 4 files changed, 9 insertions(+), 6 deletions(-) diff --git a/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.i18n.yaml b/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.i18n.yaml index f65ebb1ba4..68b4098d4f 100644 --- a/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.i18n.yaml +++ b/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.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/process/2026-07-22-evidence-based-larger-hosted-runners.md -2026-07-22-evidence-based-larger-hosted-runners.md: 180cc03ad091b2e9e96a86311515250f92065c6b -2026-07-22-evidence-based-larger-hosted-runners.zh.md: b81f67805fd543e81ede02ceeac2dda1831f4cef +2026-07-22-evidence-based-larger-hosted-runners.md: 67fc7ded5cffc6a219665f135a4c9e1cc4752691 +2026-07-22-evidence-based-larger-hosted-runners.zh.md: 71c5c067361b57fab5aae9e9ffa3850a30609db3 diff --git a/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.md b/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.md index 180cc03ad0..67fc7ded5c 100644 --- a/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.md +++ b/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.md @@ -52,7 +52,7 @@ The process-bound coverage project contains exactly five suite files. Thirty-two Complete serial Linux, macOS, and Windows references run only when `master` moves. Pull requests use the enterprise required path plus standard-hosted compatibility jobs, while other larger-runner sizes run only by manual dispatch. -An additional serial Linux reference runs on the in-house self-hosted pool (`vm-backup` label: a 64-core VM with six always-on systemd-managed runner instances) on every `master` push. It is a hot-standby drill, not a required check: each run re-proves that the persistent VM can execute the complete unsharded aggregate. The actual switch is pre-wired: the three required Linux jobs resolve their pool through the writer-manageable `DSH_CI_FAILOVER` repository variable, so an outage response is setting one variable and re-running — no merge, which would be deadlocked behind the failing checks themselves ([runbook](2026-07-26-ci-failover-runbook.md)). Because the standby lane is push-triggered, it always executes the base branch's workflow definition — no pull-request-editable path can route code to these runners, and the repository additionally keeps forking disabled. +An additional serial Linux reference runs on the in-house self-hosted pool (`vm-backup` label: a 64-core VM with six always-on systemd-managed runner instances) on every `master` push. It is a hot-standby drill, not a required check: each run re-proves that the persistent VM can execute the complete unsharded aggregate. The actual switch is pre-wired: the three required Linux jobs resolve their pool through the writer-manageable `DSH_CI_FAILOVER` repository variable, so an outage response is setting one variable and re-running — no merge, which would be deadlocked behind the failing checks themselves ([runbook](2026-07-26-ci-failover-runbook.md)). The standby lane is push-triggered, so it always executes the base branch's workflow definition. Under failover, however, `pull_request` jobs do reach these runners with the PR merge ref's own workflow definition — the trust boundary is repository membership (the repository is private with forking disabled, and the selectors exclude Dependabot), as the [failover runbook](2026-07-26-ci-failover-runbook.md) records. ## Alternatives considered diff --git a/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.zh.md b/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.zh.md index b81f67805f..71c5c06736 100644 --- a/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.zh.md +++ b/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.zh.md @@ -52,7 +52,7 @@ Windows 仓库工作在超过 16 核后收益很小，但 32 核池可以让完 只有在 `master` 移动时，才运行完整的 Linux、macOS 和 Windows 串行参考。拉取请求使用企业级运行器必需路径和标准托管兼容性作业，其他大型运行器规格仅通过手动触发运行。 -另有一条串行 Linux 参考在每次 `master` 推送时运行于公司自有的自托管池（`vm-backup` 标签：一台 64 核虚拟机，运行 6 个常驻的 systemd 管理运行器实例）。它是热备演练而非必需检查：每次运行都重新证明这台持久化虚拟机能够执行完整的未分片聚合流程。实际切换机制已预先布线：三个必需 Linux 作业通过写者可管理的仓库变量 `DSH_CI_FAILOVER` 解析运行器池，因此故障响应就是设置一个变量并重跑——无需合并（合并本身会被正在失败的检查死锁）（[切换手册](2026-07-26-ci-failover-runbook.md)）。该热备通道由 push 触发，执行的始终是基线分支自身的工作流定义——不存在任何可由拉取请求编辑的路径能把代码路由到这些运行器上；此外仓库继续保持禁用 fork。 +另有一条串行 Linux 参考在每次 `master` 推送时运行于公司自有的自托管池（`vm-backup` 标签：一台 64 核虚拟机，运行 6 个常驻的 systemd 管理运行器实例）。它是热备演练而非必需检查：每次运行都重新证明这台持久化虚拟机能够执行完整的未分片聚合流程。实际切换机制已预先布线：三个必需 Linux 作业通过写者可管理的仓库变量 `DSH_CI_FAILOVER` 解析运行器池，因此故障响应就是设置一个变量并重跑——无需合并（合并本身会被正在失败的检查死锁）（[切换手册](2026-07-26-ci-failover-runbook.md)）。该热备通道由 push 触发，执行的始终是基线分支自身的工作流定义。但需要注意：故障切换期间，`pull_request` 作业确实会带着 PR merge 引用自带的工作流定义到达这些运行器——信任边界是仓库成员资格（仓库为私有且禁用 fork，选择器排除 Dependabot），详见[故障切换手册](2026-07-26-ci-failover-runbook.md)的记录。 ## 曾考虑的替代方案 diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml index 9fe393b93c..140ae00446 100644 --- a/.github/workflows/ci.yml +++ b/.github/workflows/ci.yml @@ -414,8 +414,11 @@ jobs: # continuously proving that environment can take over a required lane if # the hosted pools degrade (the switch is then setting the writer-manageable # DSH_CI_FAILOVER variable — see the failover runbook, no merge required). - # Push-triggered, so it always executes the base branch's own workflow - # definition — no PR-editable path selects these runners. Non-blocking for + # Push-triggered, so this lane always executes the base branch's own + # workflow definition. (Under failover, pull_request jobs do reach these + # runners with the PR merge ref's workflow — the boundary there is + # repository membership: private, forking disabled, Dependabot excluded.) + # Non-blocking for # pull requests; no cache steps because the VM's persistent pnpm store and # tool caches make them redundant (and saving here would poison the hosted # cache namespace with self-hosted paths). From ce3b13bb0816d3a23b68b916087b3beef29fcc83 Mon Sep 17 00:00:00 2001 From: Chinesezjc Date: Mon, 27 Jul 2026 16:13:30 +0800 Subject: [PATCH 27/36] =?UTF-8?q?ci:=20standby=20fetches=20full=20history;?= =?UTF-8?q?=20runbook=20=E2=80=94=20writer=20wording=20throughout,=20maste?= =?UTF-8?q?r-ref=20pinning=20incompatibility?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit - serial-linux-selfhosted checks out fetch-depth 0: depth 2 misses github.event.before on multi-commit or force pushes, failing the archive verifier on a valid tree. Full fetch is cheap against the VM's local mirror. - Runbook (both languages): every remaining admin phrasing (problem statement, switch heading, alternatives, consequences) now says writer; and the 'composes with this mechanism' claim about a master-ref-pinned runner group is replaced with the truth observed live on 2026-07-27 — master-ref pinning blocks PR failover, and the shipped posture is repository-scoped all-workflow group access. Static gate green locally: 32 passed, 0 failed. --- .../process/2026-07-26-ci-failover-runbook.i18n.yaml | 4 ++-- .../process/2026-07-26-ci-failover-runbook.md | 10 +++++----- .../process/2026-07-26-ci-failover-runbook.zh.md | 10 +++++----- .github/workflows/ci.yml | 9 +++++---- 4 files changed, 17 insertions(+), 16 deletions(-) diff --git a/.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.i18n.yaml b/.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.i18n.yaml index de9ba10469..658a85ce34 100644 --- a/.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.i18n.yaml +++ b/.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.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/process/2026-07-26-ci-failover-runbook.md -2026-07-26-ci-failover-runbook.md: 05014454fa3e38045b89a857c346db0f897ab5a6 -2026-07-26-ci-failover-runbook.zh.md: e106a0de40799ca1c218217ea66c24068697dc53 +2026-07-26-ci-failover-runbook.md: ca4349661d03ff4e28d7c3c2b6e910106ff4aa30 +2026-07-26-ci-failover-runbook.zh.md: 1d59bd537879f531c9075e833c9e1dbfbd4bb0a2 diff --git a/.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.md b/.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.md index 05014454fa..ca4349661d 100644 --- a/.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.md +++ b/.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.md @@ -6,7 +6,7 @@ English | [中文](2026-07-26-ci-failover-runbook.zh.md) ## Problem -The three required Linux worker jobs in [CI](../../../../.github/workflows/ci.yml) (`node 24 / static`, `node 24 / coverage`, `node 24 / snapshots and artifacts`) and the required verdict job that aggregates them (`all checks passed`) run on the hosted enterprise 32-core pools. When those pools degrade — jobs queue indefinitely, the enterprise labels vanish, or GitHub-side capacity fails — every open pull request becomes unmergeable, and the ordinary recovery of merging a fix is itself deadlocked behind the very required checks that cannot run. An outage therefore needs a switch a repository admin can throw without merging anything. +The three required Linux worker jobs in [CI](../../../../.github/workflows/ci.yml) (`node 24 / static`, `node 24 / coverage`, `node 24 / snapshots and artifacts`) and the required verdict job that aggregates them (`all checks passed`) run on the hosted enterprise 32-core pools. When those pools degrade — jobs queue indefinitely, the enterprise labels vanish, or GitHub-side capacity fails — every open pull request becomes unmergeable, and the ordinary recovery of merging a fix is itself deadlocked behind the very required checks that cannot run. An outage therefore needs a switch any responder with repository write access can throw without merging anything. ## Decision @@ -16,7 +16,7 @@ Each of the three required Linux worker jobs — and the `all checks passed` ver `vm-backup`: one 64-core VM, six always-on systemd-managed runner instances. Check the latest `serial / linux (self-hosted standby)` run before switching: a green standby is verified-yesterday capacity. -### Switch (repo admin, ~1 minute, no merge) +### Switch (any repository writer, ~1 minute, no merge) 1. Repository **Settings → Secrets and variables → Actions → Variables → New repository variable**: name `DSH_CI_FAILOVER`, value `selfhosted`. 2. Retrigger the required jobs so they re-resolve their pool. Jobs already **queued** for the hosted labels do not retarget and cannot be re-run in place, so for the documented indefinite-queue outage, cancel the stuck run and re-run all jobs, or push a new commit; "Re-run failed jobs" only helps once a job has actually failed rather than queued. @@ -37,14 +37,14 @@ Delete the `DSH_CI_FAILOVER` variable (or set it to anything other than `selfhos ### Trust boundary -The variable is writer-manageable repository state; a pull request event itself can neither set it nor read a different value into effect, and the selector expressions live in workflow definitions. Note that under failover, `pull_request` runs execute the PR merge ref's own workflow definition — the boundary against untrusted code is repository membership (private, forking disabled, Dependabot excluded by the selectors), not the variable. Runner-side enforcement — an org-level runner group restricting these runners to the master-ref workflow — is tracked separately and composes with this mechanism. +The variable is writer-manageable repository state; a pull request event itself can neither set it nor read a different value into effect, and the selector expressions live in workflow definitions. Note that under failover, `pull_request` runs execute the PR merge ref's own workflow definition — the boundary against untrusted code is repository membership (private, forking disabled, Dependabot excluded by the selectors), not the variable. Note on runner-group policy: pinning the runner group to the master-ref workflow is **incompatible** with this failover — the four failover jobs are `pull_request` runs evaluated from PR merge refs, and a master-pinned group leaves them queued (observed live on 2026-07-27; the group was widened to all workflows of this repository to unblock the switch). A stricter runner-side policy therefore costs PR failover; the shipped posture accepts repository-scoped, all-workflow group access. ## Alternatives considered -**Merge a workflow change to switch pools.** Rejected because the outage that motivates the switch is exactly the state in which no PR can merge: the required checks are the ones failing. A repository variable is admin-controlled state that takes effect on re-run without a merge. +**Merge a workflow change to switch pools.** Rejected because the outage that motivates the switch is exactly the state in which no PR can merge: the required checks are the ones failing. A repository variable is writer-manageable state that takes effect on re-run without a merge. **Keep the self-hosted pool always in the required path.** Rejected because it trades hosted-pool availability for the in-house VM's, moving a single point of failure rather than adding a fallback. The variable keeps the hosted pools primary and the self-hosted pool a proven, one-action standby. ## Consequences -Recovering from a hosted-pool outage is a single admin variable plus a re-run, with no merge on the critical path. The cost is a second runner topology to keep working: the standby lane exercises it on every master push so the failover target never goes stale, and the concurrency and cache-restore branches in `ci.yml` carry a `selfhosted` leg that must stay in step with the hosted leg. +Recovering from a hosted-pool outage is a single variable (any writer) plus a re-run, with no merge on the critical path. The cost is a second runner topology to keep working: the standby lane exercises it on every master push so the failover target never goes stale, and the concurrency and cache-restore branches in `ci.yml` carry a `selfhosted` leg that must stay in step with the hosted leg. diff --git a/.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.zh.md b/.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.zh.md index e106a0de40..1d59bd5378 100644 --- a/.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.zh.md +++ b/.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.zh.md @@ -6,7 +6,7 @@ Status: implemented ## 问题 -[CI](../../../../.github/workflows/ci.yml) 中三个必需的 Linux 工作作业（`node 24 / static`、`node 24 / coverage`、`node 24 / snapshots and artifacts`）以及聚合它们的必需判定作业（`all checks passed`）运行在托管的企业级 32 核池上。当这些托管池发生故障——作业无限排队、企业标签消失或 GitHub 侧容量故障——所有开启的拉取请求都无法合并，而"合并一个修复"这一常规恢复手段本身正被那些无法运行的必需检查死锁。因此故障需要一个仓库管理员无需合并任何代码即可触发的开关。 +[CI](../../../../.github/workflows/ci.yml) 中三个必需的 Linux 工作作业（`node 24 / static`、`node 24 / coverage`、`node 24 / snapshots and artifacts`）以及聚合它们的必需判定作业（`all checks passed`）运行在托管的企业级 32 核池上。当这些托管池发生故障——作业无限排队、企业标签消失或 GitHub 侧容量故障——所有开启的拉取请求都无法合并，而"合并一个修复"这一常规恢复手段本身正被那些无法运行的必需检查死锁。因此故障需要一个任何具备仓库写权限的响应者都能在不合并任何代码的情况下触发的开关。 ## 决策 @@ -16,7 +16,7 @@ Status: implemented `vm-backup`：一台 64 核虚拟机，6 个常驻 systemd 管理的运行器实例。切换前先看 `serial / linux (self-hosted standby)` 最近一次运行：绿色 = 这套环境昨天刚被全量验证过。 -### 切换步骤（仓库管理员，约 1 分钟，无需合并） +### 切换步骤（任何具备写权限的协作者，约 1 分钟，无需合并） 1. 仓库 **Settings → Secrets and variables → Actions → Variables → New repository variable**：名称 `DSH_CI_FAILOVER`，值 `selfhosted`。 2. 重新触发必需作业，使其重新解析运行器池。已经为托管标签**排队**的作业不会重定向，也无法原地 re-run，因此对于本手册所述的无限排队故障，应取消卡住的运行并 re-run all jobs，或推送一个新提交；“Re-run failed jobs”只有在作业真正失败（而非仍在排队）时才有用。 @@ -37,14 +37,14 @@ Status: implemented ### 信任边界 -该变量是写者可管理的仓库状态；`pull_request` 事件本身既不能设置它，也不能让不同的值生效，选择器表达式存在于工作流定义中。需要注意：故障切换期间，`pull_request` 运行执行的是 PR merge 引用自带的工作流定义——抵御不可信代码的边界是仓库成员资格（私有、禁 fork、选择器排除 Dependabot），而非该变量。（运行器侧的组织级 runner group 约束另行跟踪，与本机制互补。） +该变量是写者可管理的仓库状态；`pull_request` 事件本身既不能设置它，也不能让不同的值生效，选择器表达式存在于工作流定义中。需要注意：故障切换期间，`pull_request` 运行执行的是 PR merge 引用自带的工作流定义——抵御不可信代码的边界是仓库成员资格（私有、禁 fork、选择器排除 Dependabot），而非该变量。关于 runner group 策略的说明：把 runner group 绑定到 master 引用的工作流与本故障切换机制**不兼容**——四个故障切换作业是从 PR merge 引用求值的 `pull_request` 运行，master 绑定的组会让它们持续排队（2026-07-27 实际故障中亲历；当时将组放宽为本仓库全部工作流才疏通了切换）。更严格的运行器侧策略以牺牲 PR 故障切换为代价；当前采用的形态是仓库范围、全工作流的组访问。 ## 曾考虑的替代方案 -**通过合并一次工作流改动来切换池。** 否决，因为触发切换的故障状态恰恰是任何 PR 都无法合并的状态：必需检查正是失败的那些。仓库变量是管理员控制的状态，重跑即生效，无需合并。 +**通过合并一次工作流改动来切换池。** 否决，因为触发切换的故障状态恰恰是任何 PR 都无法合并的状态：必需检查正是失败的那些。仓库变量是写者可管理的状态，重跑即生效，无需合并。 **让自托管池长期处于必需路径中。** 否决，因为这是拿托管池的可用性去换自有虚拟机的可用性，只是搬移了单点故障而非增加回退。该变量让托管池保持主路径，自托管池作为一个经过验证、一步即可启用的热备。 ## 后果 -从托管池故障中恢复只需一个管理员变量加一次重跑，关键路径上没有合并。代价是要维护第二套运行器拓扑：热备通道在每次 master 推送时都运行它，使故障切换目标永不失效；而 `ci.yml` 中的并发与缓存恢复分支带有一条 `selfhosted` 支路，必须与托管支路保持同步。 +从托管池故障中恢复只需一个变量（任何写者可设）加一次重跑，关键路径上没有合并。代价是要维护第二套运行器拓扑：热备通道在每次 master 推送时都运行它，使故障切换目标永不失效；而 `ci.yml` 中的并发与缓存恢复分支带有一条 `selfhosted` 支路，必须与托管支路保持同步。 diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml index 140ae00446..3c952a7bb3 100644 --- a/.github/workflows/ci.yml +++ b/.github/workflows/ci.yml @@ -427,12 +427,13 @@ jobs: name: serial / linux (self-hosted standby) runs-on: [self-hosted, linux, x64, vm-backup] steps: - # fetch-depth 2 + DSH_ARCHIVE_BASE_REF below: same frozen-archive - # comparison as serial-linux — without the prior commit the archive - # verifier defaults to HEAD and compares the new manifest with itself. + # Full history + DSH_ARCHIVE_BASE_REF below: same frozen-archive + # comparison as serial-linux. Depth 2 would miss github.event.before + # on multi-commit or force pushes; full fetch is cheap here because + # checkout resolves against the VM's local mirror. - uses: actions/checkout@v6 with: - fetch-depth: 2 + fetch-depth: 0 - uses: actions/setup-node@v6 with: From 3cf2853b3f04fdceb3ff99109dea8f764d28fbc3 Mon Sep 17 00:00:00 2001 From: Chinesezjc Date: Mon, 27 Jul 2026 16:22:30 +0800 Subject: [PATCH 28/36] docs(ci): bootstrap procedure starts the listener service config.sh only registers; the runner stays offline until svc.sh install/start. Both language sides updated so emergency capacity actually comes online. --- .../process/2026-07-26-ci-failover-runbook.i18n.yaml | 4 ++-- .../implemented/process/2026-07-26-ci-failover-runbook.md | 2 +- .../implemented/process/2026-07-26-ci-failover-runbook.zh.md | 2 +- 3 files changed, 4 insertions(+), 4 deletions(-) diff --git a/.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.i18n.yaml b/.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.i18n.yaml index 658a85ce34..0e3b0820c0 100644 --- a/.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.i18n.yaml +++ b/.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.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/process/2026-07-26-ci-failover-runbook.md -2026-07-26-ci-failover-runbook.md: ca4349661d03ff4e28d7c3c2b6e910106ff4aa30 -2026-07-26-ci-failover-runbook.zh.md: 1d59bd537879f531c9075e833c9e1dbfbd4bb0a2 +2026-07-26-ci-failover-runbook.md: 80dd7c4291e3de11c2f13b3247af56762396c720 +2026-07-26-ci-failover-runbook.zh.md: 7933a857f1559c540fccc2cd89352c4fe351dd7e diff --git a/.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.md b/.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.md index ca4349661d..80dd7c4291 100644 --- a/.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.md +++ b/.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.md @@ -28,7 +28,7 @@ Each of the three required Linux worker jobs — and the `all checks passed` ver ## Capacity during failover -Six always-on instances absorb normal PR traffic (the pool's steady-state load is one serial standby job per master push, so failover capacity is effectively the full pool). If queues still build, register additional instances with an org registration token (org Settings → Actions → Runners → New runner). Clone an existing runner directory **excluding its identity files** — `rsync -a --exclude '.runner' --exclude '.credentials*' --exclude '_diag' --exclude '_work' / /` — then run `config.sh`; copying `.runner`/`.credentials` verbatim makes `config.sh` refuse with "already configured". About a minute per instance. +Six always-on instances absorb normal PR traffic (the pool's steady-state load is one serial standby job per master push, so failover capacity is effectively the full pool). If queues still build, register additional instances with an org registration token (org Settings → Actions → Runners → New runner). Clone an existing runner directory **excluding its identity files** — `rsync -a --exclude '.runner' --exclude '.credentials*' --exclude '_diag' --exclude '_work' / /` — then run `config.sh` (copying `.runner`/`.credentials` verbatim makes it refuse with "already configured"), and **start the listener**: `sudo ./svc.sh install ubuntu && sudo ./svc.sh start`. Registration alone leaves the runner offline; only a started service adds capacity. About a minute per instance. ### Switch back diff --git a/.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.zh.md b/.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.zh.md index 1d59bd5378..7933a857f1 100644 --- a/.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.zh.md +++ b/.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.zh.md @@ -28,7 +28,7 @@ Status: implemented ## 切换期间的容量 -6 个常驻实例可承接正常 PR 流量（该池平时唯一的稳态负载是每次 master 推送一个串行热备作业，故障切换时几乎全池可用）。若仍出现排队，用组织级注册 token（组织 Settings → Actions → Runners → New runner）追加注册实例。复制现有 runner 目录时**必须排除身份文件**——`rsync -a --exclude '.runner' --exclude '.credentials*' --exclude '_diag' --exclude '_work' / /`——再跑 `config.sh`；原样拷贝 `.runner`/`.credentials` 会使 `config.sh` 以 "already configured" 拒绝。每个约一分钟。 +6 个常驻实例可承接正常 PR 流量（该池平时唯一的稳态负载是每次 master 推送一个串行热备作业，故障切换时几乎全池可用）。若仍出现排队，用组织级注册 token（组织 Settings → Actions → Runners → New runner）追加注册实例。复制现有 runner 目录时**必须排除身份文件**——`rsync -a --exclude '.runner' --exclude '.credentials*' --exclude '_diag' --exclude '_work' / /`——再跑 `config.sh`（原样拷贝 `.runner`/`.credentials` 会使其以 "already configured" 拒绝），然后**启动监听器**：`sudo ./svc.sh install ubuntu && sudo ./svc.sh start`。仅注册不会上线；只有启动了服务的 runner 才会增加容量。每个约一分钟。 ### 切回 From 900e45b365ffaaa03b4bef0cf1ace5717a5e0bc5 Mon Sep 17 00:00:00 2001 From: 07akioni <07akioni2@gmail.com> Date: Mon, 27 Jul 2026 16:24:30 +0800 Subject: [PATCH 29/36] feat: optimize todo tool ui --- .../2026-07-23-web-todo-display.i18n.yaml | 4 +- .../feature/2026-07-23-web-todo-display.md | 2 +- .../feature/2026-07-23-web-todo-display.zh.md | 2 +- apps/web/tests/todo-display.snapshot.ts | 12 +- .../client/ui-conversation/README.i18n.yaml | 4 +- packages/client/ui-conversation/README.md | 2 +- packages/client/ui-conversation/README.zh.md | 2 +- .../src/client/skeleton/InputBar.module.css | 5 +- .../src/client/skeleton/TodoPanel.module.css | 102 ++++++++-------- .../src/client/skeleton/TodoPanel.tsx | 109 +++++++++++++----- .../ui-conversation/tests/todo-panel.spec.tsx | 26 +++-- 11 files changed, 162 insertions(+), 108 deletions(-) diff --git a/.agents/notes/implemented/feature/2026-07-23-web-todo-display.i18n.yaml b/.agents/notes/implemented/feature/2026-07-23-web-todo-display.i18n.yaml index 4bccfa396e..5c8530da70 100644 --- a/.agents/notes/implemented/feature/2026-07-23-web-todo-display.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-07-23-web-todo-display.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/feature/2026-07-23-web-todo-display.md -2026-07-23-web-todo-display.md: 830f55c86c893c4942a1a9d3b8529395d5f5e38b -2026-07-23-web-todo-display.zh.md: e68928d7eddaaa92ac831722a738ee2002342b38 +2026-07-23-web-todo-display.md: 5fe08cc40c1d23ff3a9b8c6d766fea6d3694c30d +2026-07-23-web-todo-display.zh.md: c121ffc27e3d0a93707c2c22b2f180023ebae5be diff --git a/.agents/notes/implemented/feature/2026-07-23-web-todo-display.md b/.agents/notes/implemented/feature/2026-07-23-web-todo-display.md index 830f55c86c..5fe08cc40c 100644 --- a/.agents/notes/implemented/feature/2026-07-23-web-todo-display.md +++ b/.agents/notes/implemented/feature/2026-07-23-web-todo-display.md @@ -18,7 +18,7 @@ Consume `todo/write` as a Session side effect, not a surface node, and render it ### TodoPanel: the durable list as a persistent strip -The panel mounts through the `conversation.input.dock` slot (a plain registrant plugin, `todoDockEntry`, the QueueDock posture: `inject: ['slots', 'conversation']` as the load-order seam, `order: -1` above the queue rows), hidden while empty, collapsible with the in-progress item as the collapsed one-line hint; ✓/●/○ glyphs mirror the TUI plan panel. It reads `snapshot.todos` via the standard-kit `useSession` hook the dock entry receives — no store, no service, no ctx. The inner component stays props-complete and framework-free; the dock adapter is a one-line wrapper. +The panel mounts through the `conversation.input.dock` slot (a plain registrant plugin, `todoDockEntry`, the QueueDock posture: `inject: ['slots', 'conversation']` as the load-order seam, `order: -1` above the queue rows), hidden while empty, collapsible to a header of title + `"/ tasks · in progress"` (no in-progress content hint when collapsed). Status glyphs are the figma todo set (green check ring / blue fading ring / dashed pending ring) on a tip-surface card (`--dsw-specific-tip`, 14px radius, `width: calc(100% - 88px)` / `max-width: 776px` centered; InputBar top pad 6px is the gap to the composer card). It reads `snapshot.todos` via the standard-kit `useSession` hook the dock entry receives — no store, no service, no ctx. The inner component stays props-complete and framework-free; the dock adapter is a one-line wrapper. ### TodoRow: the per-call row through the keyed toolview slot diff --git a/.agents/notes/implemented/feature/2026-07-23-web-todo-display.zh.md b/.agents/notes/implemented/feature/2026-07-23-web-todo-display.zh.md index e68928d7ed..c121ffc27e 100644 --- a/.agents/notes/implemented/feature/2026-07-23-web-todo-display.zh.md +++ b/.agents/notes/implemented/feature/2026-07-23-web-todo-display.zh.md @@ -18,7 +18,7 @@ Status: implemented ### TodoPanel：长驻列表作为一条常驻横条 -面板经 `conversation.input.dock` slot 挂载（普通注册者插件 `todoDockEntry`，QueueDock 同款姿势：`inject: ['slots', 'conversation']` 载序 seam，`order: -1` 排在队列条上方），空列表时隐藏，可折叠——折叠态以进行中项作为单行提示；✓/●/○ 字形与 TUI plan 面板一致。它经 dock entry 收到的标准件 `useSession` hook 读取 `snapshot.todos`——无 store、无 service、无 ctx。内部组件保持 props 完备且框架无关；dock 适配件只是一行包装。 +面板经 `conversation.input.dock` slot 挂载（普通注册者插件 `todoDockEntry`，QueueDock 同款姿势：`inject: ['slots', 'conversation']` 载序 seam，`order: -1` 排在队列条上方），空列表时隐藏，可折叠为标题加 `"<已完成>/<总数> tasks · in progress"` 的表头（折叠态不再附带进行中条目正文）。状态图标为 figma todo 套件（绿色勾选环／蓝色渐隐环／虚线未开始环），卡片使用 tip 表面（`--dsw-specific-tip`、14px 圆角、`width: calc(100% - 88px)`／`max-width: 776px` 居中；InputBar 顶部 6px 内边距是到输入卡的间距）。它经 dock entry 收到的标准件 `useSession` hook 读取 `snapshot.todos`——无 store、无 service、无 ctx。内部组件保持 props 完备且框架无关；dock 适配件只是一行包装。 ### TodoRow：经 keyed toolview slot 的逐调用行 diff --git a/apps/web/tests/todo-display.snapshot.ts b/apps/web/tests/todo-display.snapshot.ts index 3116bf4242..f916b64b5b 100644 --- a/apps/web/tests/todo-display.snapshot.ts +++ b/apps/web/tests/todo-display.snapshot.ts @@ -143,19 +143,19 @@ it('renders the todo_write turn: dedicated tool row + the dock plan strip', asyn })), }).toMatchInlineSnapshot(` { - "panelHeader": "Plan1/3", + "panelHeader": "To-dos1/3 tasks · 1 in progress", "panelItems": [ { "status": "completed", - "text": "✓梳理需求", + "text": "梳理需求", }, { "status": "in_progress", - "text": "●实现 fixture 样本", + "text": "实现 fixture 样本", }, { "status": "pending", - "text": "○浏览器验收", + "text": "浏览器验收", }, ], "row": "☰更新任务清单1/3 已完成 · 实现 fixture 样本", @@ -164,7 +164,7 @@ it('renders the todo_write turn: dedicated tool row + the dock plan strip', asyn `) }) -it('collapses the plan strip to the in-progress hint and restores it', async () => { +it('collapses the plan strip to the count summary and restores it', async () => { boot() await openFixtureSession() @@ -179,7 +179,7 @@ it('collapses the plan strip to the in-progress hint and restores it', async () listGone: panel.querySelector('ul') === null, }).toMatchInlineSnapshot(` { - "collapsedHeader": "Plan1/3实现 fixture 样本", + "collapsedHeader": "To-dos1/3 tasks · 1 in progress", "listGone": true, } `) diff --git a/packages/client/ui-conversation/README.i18n.yaml b/packages/client/ui-conversation/README.i18n.yaml index 2ffa02d313..2f67e9eac3 100644 --- a/packages/client/ui-conversation/README.i18n.yaml +++ b/packages/client/ui-conversation/README.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 packages/client/ui-conversation/README.md -README.md: b242812411d513931ecd2767622f9e23fb0aaa34 -README.zh.md: 77f68e02d8d9161c413ae7d224121bc53547ba12 +README.md: f6b7326916122545fc87d289cb422e644c7bae6c +README.zh.md: 55d4a743709695ba04814b4529aebac235a202d9 diff --git a/packages/client/ui-conversation/README.md b/packages/client/ui-conversation/README.md index b242812411..f6b7326916 100644 --- a/packages/client/ui-conversation/README.md +++ b/packages/client/ui-conversation/README.md @@ -12,7 +12,7 @@ Generic tool rows classify the built-in bash, read, search, write, edit, and run Tool rows are slots too — the standalone tool ring (`ToolViewRegistry`/`ctx.toolviews`/outlet) is retired. The chat entry declares the keyed `'conversation.chat.toolview'` hole (session scope; the key space is runtime-open); its render site dispatches per row via `entryKey: toolName` with `GenericToolCard` as the call-site `fallback`. The owner payload is the uniform `ToolRowOwnerProps` (`callId`/`toolName`/`block`/`openDetails`) and `ToolRowProps` pre-composes it with the session standard kit. A registrant is a plain plugin: `ctx.slots.register({ name: 'conversation.chat.toolview', key: '', inject? }, Row)` with `inject: ['slots', 'conversation']` as the load-order seam (apply mounts ConversationService after the chat registration, so the service being present guarantees the slot is declared); session differentiation happens inside the component (`useSessions` reading `parentId` — the bash sample is the third-party-posture exemplar). Trajectory/waterfall toolview slots share this shape and land with their own render sites (RendersCheck rejects a declaration nobody renders). -The todo surfaces are two registrations over that shape, both plain registrant plugins with `inject: ['slots', 'conversation']`. `TodoRow` takes the `'conversation.chat.toolview'` key `todo_write` and summarizes what the call attempted (`/ 已完成 · ` parsed from its args, falling back to the generic summary on malformed or wrongly-shaped model JSON, and keeping the generic dot for non-ok execution states so a cancelled call never reads as a completed update). `TodoDock` takes the `'conversation.input.dock'` list slot at `order: -1` — above the queue rows — and is the durable plan strip: it selects `todos` off the session snapshot and renders `TodoPanel`, which takes the plain list, hides itself while the list is empty, and collapses to a one-line header carrying the in-progress item. The dock adapter owns the selection so the panel stays a pure function of its props; the persistent list lives here rather than in the row so the row stays one line. Anything the input-zone composer chain hides (a `conversation.composer` takeover such as ui-question's) hides the whole dock, this strip included. +The todo surfaces are two registrations over that shape, both plain registrant plugins with `inject: ['slots', 'conversation']`. `TodoRow` takes the `'conversation.chat.toolview'` key `todo_write` and summarizes what the call attempted (`/ 已完成 · ` parsed from its args, falling back to the generic summary on malformed or wrongly-shaped model JSON, and keeping the generic dot for non-ok execution states so a cancelled call never reads as a completed update). `TodoDock` takes the `'conversation.input.dock'` list slot at `order: -1` — above the queue rows — and is the durable plan strip: it selects `todos` off the session snapshot and renders `TodoPanel`, which takes the plain list, hides itself while the list is empty, and collapses to a header of title plus `"/ tasks · in progress"` (status glyphs are the figma check / progress / dashed-pending set). The dock adapter owns the selection so the panel stays a pure function of its props; the persistent list lives here rather than in the row so the row stays one line. Anything the input-zone composer chain hides (a `conversation.composer` takeover such as ui-question's) hides the whole dock, this strip included. Per-session UI state (selection, ordinary composer draft, active view) lives in the declared chat store (`stores.ts` `createChatStore`): apply constructs one handle and passes it to the conversation, chat-view, and details registrations, so the session slots share one instance per session (selection written by the chat view, read by details) and the framework owns instance lifecycle and draft persistence. The frontend Session Intent comes from the Session list projection; after publication, any retained prompt comes from that Session's conversation snapshot. Components are pure — the framework standard kit (`useSession`/`sessionId` when session-scoped, plus global `useSessions`/`useWorkspaces`) and the store faces (`useStore`/`actions`) arrive automatically from the registration declaration; inject factories contribute plain data and callbacks for runtime Session actions, send/stop, tabs, details, and paging. diff --git a/packages/client/ui-conversation/README.zh.md b/packages/client/ui-conversation/README.zh.md index 77f68e02d8..55d4a74370 100644 --- a/packages/client/ui-conversation/README.zh.md +++ b/packages/client/ui-conversation/README.zh.md @@ -12,7 +12,7 @@ 工具行同样是 slot：独立工具环（`ToolViewRegistry`／`ctx.toolviews`／outlet）已经退役。聊天配置项声明键控的 `'conversation.chat.toolview'` 空位（Session scope；key 空间在运行时开放）；其渲染点逐行通过 `entryKey: toolName` 分发，并以 `GenericToolCard` 作为调用点 `fallback`。owner 载荷是统一的 `ToolRowOwnerProps`（`callId`／`toolName`／`block`／`openDetails`），`ToolRowProps` 则预先将其与 Session 标准工具包组合。注册方只是普通插件：`ctx.slots.register({ name: 'conversation.chat.toolview', key: '', inject? }, Row)`，以 `inject: ['slots', 'conversation']` 作为加载顺序 seam（apply 在聊天注册后挂载 ConversationService，因此服务存在即可保证 slot 已声明）；Session 区分在组件内部完成（`useSessions` 读取 `parentId`，bash 示例是第三方姿态的范例）。Trajectory/waterfall 工具视图 slot 共享此形状，并随各自的渲染点落地（RendersCheck 会拒绝没有任何渲染方的声明）。 -todo 两个面就是在该形状上的两个注册项，都是普通注册方插件，`inject: ['slots', 'conversation']`。`TodoRow` 占用 `'conversation.chat.toolview'` 的 `todo_write` key，摘要该次调用「试图写入」的内容（从其 args 解析出 `<已完成>/<总数> 已完成 · <进行中条目>`；模型 JSON 残缺或形状不对时回落到通用摘要；非 ok 执行状态保留通用状态点，使被取消的调用绝不读成一次已完成的更新）。`TodoDock` 以 `order: -1` 占用 `'conversation.input.dock'` 列表 slot（位于队列行之上），是常驻的计划条：它从会话快照中选取 `todos` 并渲染 `TodoPanel`，后者接收纯列表，在列表为空时自我隐藏，折叠时收成携带进行中条目的单行表头。选取由 dock 适配器负责，因此面板保持为其 props 的纯函数；常驻列表放在此处而非行内，行才能保持单行。输入区 composer 链隐藏的一切（例如 ui-question 对 `conversation.composer` 的接管）也会隐藏整个 dock，包括这条计划条。 +todo 两个面就是在该形状上的两个注册项，都是普通注册方插件，`inject: ['slots', 'conversation']`。`TodoRow` 占用 `'conversation.chat.toolview'` 的 `todo_write` key，摘要该次调用「试图写入」的内容（从其 args 解析出 `<已完成>/<总数> 已完成 · <进行中条目>`；模型 JSON 残缺或形状不对时回落到通用摘要；非 ok 执行状态保留通用状态点，使被取消的调用绝不读成一次已完成的更新）。`TodoDock` 以 `order: -1` 占用 `'conversation.input.dock'` 列表 slot（位于队列行之上），是常驻的计划条：它从会话快照中选取 `todos` 并渲染 `TodoPanel`，后者接收纯列表，在列表为空时自我隐藏，折叠时收成标题加 `"<已完成>/<总数> tasks · in progress"` 的表头（状态图标为 figma 的勾选／进行中／虚线未开始一组）。选取由 dock 适配器负责，因此面板保持为其 props 的纯函数；常驻列表放在此处而非行内，行才能保持单行。输入区 composer 链隐藏的一切（例如 ui-question 对 `conversation.composer` 的接管）也会隐藏整个 dock，包括这条计划条。 逐 Session UI 状态（选择、普通编辑器草稿、活跃视图）位于已声明的聊天 store（`stores.ts` `createChatStore`）中：apply 构造一个 handle，并将其传给会话、聊天视图和详情注册，因此 Session slot 每个 Session 共享一个实例（选择由聊天视图写入、详情读取），框架拥有实例生命周期与草稿持久化。前端 Session Intent 来自 Session 列表投影；发布后，任何保留的提示词都来自该 Session 的会话快照。组件保持纯粹：框架标准工具包（Session scope 下的 `useSession`／`sessionId`，以及全局 `useSessions`／`useWorkspaces`）和 store 表层（`useStore`／`actions`）会从注册声明自动到达；inject factory 为运行时 Session 操作、发送／停止、标签页、详情和分页贡献普通数据与回调。 diff --git a/packages/client/ui-conversation/src/client/skeleton/InputBar.module.css b/packages/client/ui-conversation/src/client/skeleton/InputBar.module.css index b17027a153..63614e3c13 100644 --- a/packages/client/ui-conversation/src/client/skeleton/InputBar.module.css +++ b/packages/client/ui-conversation/src/client/skeleton/InputBar.module.css @@ -21,8 +21,9 @@ flex-direction: column; align-items: center; /* figma Input_Bottom: pad L32/R32/B12; the bottom gradient mask is owned by - the chat scroller. Top 8 hosts the error strip's breathing room. */ - padding: 8px 32px 12px; + the chat scroller. Top 6 is the gap under the dock todo strip (12px todo + margin + 6px here); error/status strips still carry their own margin. */ + padding: 6px 32px 12px; } .hero { diff --git a/packages/client/ui-conversation/src/client/skeleton/TodoPanel.module.css b/packages/client/ui-conversation/src/client/skeleton/TodoPanel.module.css index 17c9c890a7..5ac38c1c67 100644 --- a/packages/client/ui-conversation/src/client/skeleton/TodoPanel.module.css +++ b/packages/client/ui-conversation/src/client/skeleton/TodoPanel.module.css @@ -1,55 +1,53 @@ -/* Plan strip pinned above the composer: bordered card on the composer card's - axis (776px column inside 32px side padding). Colors resolve through - --dsw-alias-* tokens only; the active row rides the business blue, done - rows fade to tertiary. */ +/* Todo strip above the composer (figma 772:51905 / 772:52972 / 772:53419): + tip surface, 14px radius, status icons + secondary item labels. Column is + calc(100% - 88px) / max 776, centered; InputBar top pad supplies the gap. */ .root { flex: none; overflow: hidden; - margin: 8px auto 0; - width: calc(100% - 64px); + margin: 0 auto; + width: calc(100% - 88px); max-width: 776px; - border: 1px solid var(--dsw-alias-border-l2); - border-radius: 12px; - background: var(--dsw-alias-bg-base); + border: 1px solid var(--dsw-alias-border-l1); + border-radius: 14px; + background: var(--dsw-specific-tip); +} + +.body { + display: flex; + flex-direction: column; + gap: 10px; + padding: 10px 16px; } .header { display: flex; align-items: center; - gap: 8px; + gap: 10px; width: 100%; - padding: 8px 12px; + padding: 0; border: none; background: transparent; text-align: left; cursor: pointer; } -.header:hover { - background: var(--dsw-alias-interactive-bg-hover); -} - .title { - font-size: 13px; - line-height: 16px; - font-weight: 510; + flex: none; + font-size: 14px; + line-height: 24px; + font-weight: 500; color: var(--dsw-alias-label-primary); } .progress { - font-size: 12px; - line-height: 16px; - color: var(--dsw-alias-label-tertiary); -} - -.activeHint { - flex: 1; + flex: 1 1 auto; min-width: 0; overflow: hidden; - font-size: 12px; - line-height: 16px; - color: var(--dsw-alias-label-secondary); + font-size: 13px; + line-height: 20px; + font-weight: 400; + color: var(--dsw-alias-label-tertiary); text-overflow: ellipsis; white-space: nowrap; } @@ -58,13 +56,15 @@ display: grid; flex: none; place-items: center; - margin-left: auto; - color: var(--dsw-alias-label-secondary); + color: var(--dsw-alias-label-tertiary); } .list { + display: flex; + flex-direction: column; + gap: 8px; margin: 0; - padding: 0 12px 8px; + padding: 0; list-style: none; max-height: 180px; overflow-y: auto; @@ -72,40 +72,44 @@ .item { display: flex; - align-items: baseline; - gap: 8px; - padding: 2px 0; + align-items: center; + gap: 10px; + min-width: 0; font-size: 13px; line-height: 20px; color: var(--dsw-alias-label-secondary); } .glyph { + display: grid; flex: none; - width: 14px; - text-align: center; - color: var(--dsw-alias-label-tertiary); + place-items: center; + width: 16px; + height: 16px; } -.item[data-status='completed'] .content { - color: var(--dsw-alias-label-tertiary); - text-decoration: line-through; -} - -.item[data-status='completed'] .glyph { +.glyphCompleted { color: var(--dsw-alias-state-success-primary); } -.item[data-status='in_progress'] .content { - font-weight: 510; - color: var(--dsw-alias-label-primary); +.glyphProgress { + color: var(--dsw-alias-state-business-primary); + animation: todo-progress-spin 1s linear infinite; } -.item[data-status='in_progress'] .glyph { - color: var(--dsw-alias-state-business-primary); +.glyphPending { + color: var(--dsw-alias-label-caption); +} + +@keyframes todo-progress-spin { + to { + transform: rotate(360deg); + } } .content { min-width: 0; - overflow-wrap: anywhere; + overflow: hidden; + text-overflow: ellipsis; + white-space: nowrap; } diff --git a/packages/client/ui-conversation/src/client/skeleton/TodoPanel.tsx b/packages/client/ui-conversation/src/client/skeleton/TodoPanel.tsx index 283eeb3e5e..24764088ab 100644 --- a/packages/client/ui-conversation/src/client/skeleton/TodoPanel.tsx +++ b/packages/client/ui-conversation/src/client/skeleton/TodoPanel.tsx @@ -3,8 +3,9 @@ // no data of its own, hidden while the list is empty. Mounted through the // 'conversation.input.dock' slot (QueueDock posture): the dock adapter does // the selecting, so the panel takes the plain list and stays framework-free. +// Visual: figma 772:51905 (states) / 772:52972 (collapsed) / 772:53419 (expanded). -import { useState } from 'react' +import { useId, useState } from 'react' import type { Context } from 'cordis' import type { PropsRuntime } from '@deepseek-ai/dsh-client-ui-slots' import type { TodoItem } from '@deepseek-ai/dsh-client-runtime/client' @@ -16,45 +17,89 @@ export interface TodoPanelProps { todos: readonly TodoItem[] } -/** Status glyphs mirror the TUI plan panel (✓ done / ● active / ○ pending). */ -const STATUS_GLYPHS: Record = { - completed: '✓', in_progress: '●', pending: '○', +/** Completed: green check ring (figma ic_ds_check_16). */ +function CompletedGlyph() { + return ( + + ) +} + +/** In-progress: business-blue ring fading out; CSS spins the svg. */ +function ProgressGlyph() { + const gradientId = useId() + return ( + + ) +} + +/** Pending: dashed unstarted ring (figma 14px, dash 2.4 2.4). */ +function PendingGlyph() { + return ( + + ) +} + +function StatusGlyph({ status }: { status: TodoItem['status'] }) { + switch (status) { + case 'completed': return + case 'in_progress': return + case 'pending': return + } +} + +/** Header summary: "/ tasks · in progress". */ +function progressLabel(todos: readonly TodoItem[]): string { + const done = todos.filter(t => t.status === 'completed').length + const active = todos.filter(t => t.status === 'in_progress').length + return `${done}/${todos.length} tasks · ${active} in progress` } export function TodoPanel({ todos }: TodoPanelProps) { const [collapsed, setCollapsed] = useState(false) if (todos.length === 0) return null - const done = todos.filter(t => t.status === 'completed').length - const active = todos.find(t => t.status === 'in_progress') - return ( -
    - + {!collapsed && ( +
      + {todos.map(item => ( +
    • + + {item.content} +
      • + ))} +
    )} - - {collapsed ? : } - - - {!collapsed && ( -
      - {todos.map(item => ( -
    • - {STATUS_GLYPHS[item.status]} - {item.content} -
      • - ))} -
    - )} +
    ) } diff --git a/packages/client/ui-conversation/tests/todo-panel.spec.tsx b/packages/client/ui-conversation/tests/todo-panel.spec.tsx index 5bc3aa5c3d..8888fd5659 100644 --- a/packages/client/ui-conversation/tests/todo-panel.spec.tsx +++ b/packages/client/ui-conversation/tests/todo-panel.spec.tsx @@ -1,9 +1,9 @@ // @vitest-environment jsdom /** * Todo display acceptance: the TodoPanel plan strip (empty-hidden, status - * rows, collapse with active hint), its TodoDock adapter (selects the plan off - * the session snapshot and follows changes), and the todo_write toolview row - * (progress summary from args, generic fallback on malformed JSON, error badge, + * rows, collapse), its TodoDock adapter (selects the plan off the session + * snapshot and follows changes), and the todo_write toolview row (progress + * summary from args, generic fallback on malformed JSON, error badge, * keyboard activation). */ import { act, cleanup, fireEvent, render, screen } from '@testing-library/react' @@ -31,32 +31,36 @@ describe('TodoPanel', () => { expect(container.innerHTML).toBe('') }) - it('shows progress, one row per item with its status, and strikes done items', () => { + it('shows progress, one row per item with its status glyph', () => { render() expect(screen.getByTestId('todo-panel')).toBeTruthy() - expect(screen.getByText('1/3')).toBeTruthy() + expect(screen.getByText('To-dos')).toBeTruthy() + expect(screen.getByText('1/3 tasks · 1 in progress')).toBeTruthy() const items = screen.getAllByRole('listitem') expect(items.map(li => li.getAttribute('data-status'))).toEqual(['completed', 'in_progress', 'pending']) expect(screen.getByText('搭骨架')).toBeTruthy() expect(screen.getByText('写组件')).toBeTruthy() + // Each status row carries an SVG glyph (not a text bullet). + expect(items.every(li => li.querySelector('svg') !== null)).toBe(true) }) - it('collapse hides the list and surfaces the active item in the header; expand restores', () => { + it('collapse hides the list; expand restores; header keeps the count summary', () => { render() const header = screen.getByRole('button', { expanded: true }) fireEvent.click(header) expect(screen.queryByRole('list')).toBeNull() - // Collapsed header carries the in-progress content as the one-line hint. - expect(screen.getByText('写组件')).toBeTruthy() + // Collapsed header is title + progress only (no in-progress content hint). + expect(screen.getByText('1/3 tasks · 1 in progress')).toBeTruthy() + expect(screen.queryByText('写组件')).toBeNull() fireEvent.click(screen.getByRole('button', { expanded: false })) expect(screen.getAllByRole('listitem')).toHaveLength(3) }) - it('collapsed header omits the hint when nothing is in progress', () => { + it('collapsed header still shows zero in-progress when nothing is active', () => { render() fireEvent.click(screen.getByRole('button', { expanded: true })) expect(screen.queryByText('都完了')).toBeNull() - expect(screen.getByText('1/1')).toBeTruthy() + expect(screen.getByText('1/1 tasks · 0 in progress')).toBeTruthy() }) }) @@ -71,7 +75,7 @@ describe('TodoDock', () => { render() expect(screen.queryByTestId('todo-panel')).toBeNull() act(() => { store.set({ todos: LIST }) }) - expect(screen.getByText('1/3')).toBeTruthy() + expect(screen.getByText('1/3 tasks · 1 in progress')).toBeTruthy() // A rollback to the empty list retires the strip (the panel owns no data). act(() => { store.set({ todos: [] }) }) expect(screen.queryByTestId('todo-panel')).toBeNull() From ebb5bf4c1941cb5bddf7395a3ba6a7e718f9f9eb Mon Sep 17 00:00:00 2001 From: Chinesezjc Date: Mon, 27 Jul 2026 16:25:45 +0800 Subject: [PATCH 30/36] docs(ci): starting a new failover runner needs svc.sh, not just config.sh config.sh registers the instance without starting a listener, so the procedure as written left the new runner offline and added no capacity. --- .../process/2026-07-26-ci-failover-runbook.i18n.yaml | 4 ++-- .../implemented/process/2026-07-26-ci-failover-runbook.md | 2 +- .../implemented/process/2026-07-26-ci-failover-runbook.zh.md | 2 +- 3 files changed, 4 insertions(+), 4 deletions(-) diff --git a/.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.i18n.yaml b/.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.i18n.yaml index de9ba10469..db702da620 100644 --- a/.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.i18n.yaml +++ b/.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.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/process/2026-07-26-ci-failover-runbook.md -2026-07-26-ci-failover-runbook.md: 05014454fa3e38045b89a857c346db0f897ab5a6 -2026-07-26-ci-failover-runbook.zh.md: e106a0de40799ca1c218217ea66c24068697dc53 +2026-07-26-ci-failover-runbook.md: b93c86d73f319f40706a4f9b31f448804e7b5ba8 +2026-07-26-ci-failover-runbook.zh.md: 25b83981e70070800c5a4037807d26811e55124d diff --git a/.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.md b/.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.md index 05014454fa..b93c86d73f 100644 --- a/.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.md +++ b/.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.md @@ -28,7 +28,7 @@ Each of the three required Linux worker jobs — and the `all checks passed` ver ## Capacity during failover -Six always-on instances absorb normal PR traffic (the pool's steady-state load is one serial standby job per master push, so failover capacity is effectively the full pool). If queues still build, register additional instances with an org registration token (org Settings → Actions → Runners → New runner). Clone an existing runner directory **excluding its identity files** — `rsync -a --exclude '.runner' --exclude '.credentials*' --exclude '_diag' --exclude '_work' / /` — then run `config.sh`; copying `.runner`/`.credentials` verbatim makes `config.sh` refuse with "already configured". About a minute per instance. +Six always-on instances absorb normal PR traffic (the pool's steady-state load is one serial standby job per master push, so failover capacity is effectively the full pool). If queues still build, register additional instances with an org registration token (org Settings → Actions → Runners → New runner). Clone an existing runner directory **excluding its identity files** — `rsync -a --exclude '.runner' --exclude '.credentials*' --exclude '_diag' --exclude '_work' / /` — then run `config.sh`; copying `.runner`/`.credentials` verbatim makes `config.sh` refuse with "already configured". `config.sh` only registers the instance — it starts no listener, so a runner that stops there is registered and offline, adding no capacity. Install and start its service too: `sudo ./svc.sh install && sudo ./svc.sh start` (this pool is systemd-managed; a foreground `./run.sh` also works but dies with the shell). Confirm the instance reports Idle in org Settings → Actions → Runners before counting it. About a minute per instance. ### Switch back diff --git a/.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.zh.md b/.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.zh.md index e106a0de40..25b83981e7 100644 --- a/.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.zh.md +++ b/.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.zh.md @@ -28,7 +28,7 @@ Status: implemented ## 切换期间的容量 -6 个常驻实例可承接正常 PR 流量（该池平时唯一的稳态负载是每次 master 推送一个串行热备作业，故障切换时几乎全池可用）。若仍出现排队，用组织级注册 token（组织 Settings → Actions → Runners → New runner）追加注册实例。复制现有 runner 目录时**必须排除身份文件**——`rsync -a --exclude '.runner' --exclude '.credentials*' --exclude '_diag' --exclude '_work' / /`——再跑 `config.sh`；原样拷贝 `.runner`/`.credentials` 会使 `config.sh` 以 "already configured" 拒绝。每个约一分钟。 +6 个常驻实例可承接正常 PR 流量（该池平时唯一的稳态负载是每次 master 推送一个串行热备作业，故障切换时几乎全池可用）。若仍出现排队，用组织级注册 token（组织 Settings → Actions → Runners → New runner）追加注册实例。复制现有 runner 目录时**必须排除身份文件**——`rsync -a --exclude '.runner' --exclude '.credentials*' --exclude '_diag' --exclude '_work' / /`——再跑 `config.sh`；原样拷贝 `.runner`/`.credentials` 会使 `config.sh` 以 "already configured" 拒绝。`config.sh` 只完成注册，不启动监听进程，因此停在这一步的 runner 处于已注册但离线状态，不增加任何容量。还须安装并启动其服务：`sudo ./svc.sh install && sudo ./svc.sh start`（本池由 systemd 管理；前台运行 `./run.sh` 亦可，但会随 shell 退出而终止）。确认该实例在组织 Settings → Actions → Runners 中显示 Idle 后再计入容量。每个约一分钟。 ### 切回 From 31073cc60f50fa08e098170061e3949d2c2e7eba Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Mon, 27 Jul 2026 16:36:08 +0800 Subject: [PATCH 31/36] test(acp): refresh web-fetch tool schema snapshot --- .../tests/snapshots/web-fetch/tool-schemas.expected.json | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/examples/acp-agent/tests/snapshots/web-fetch/tool-schemas.expected.json b/examples/acp-agent/tests/snapshots/web-fetch/tool-schemas.expected.json index 1ee86b38ba..70940f8907 100644 --- a/examples/acp-agent/tests/snapshots/web-fetch/tool-schemas.expected.json +++ b/examples/acp-agent/tests/snapshots/web-fetch/tool-schemas.expected.json @@ -288,7 +288,7 @@ "description": "The COMPLETE task list, replacing any previous list.", "items": { "type": "object", - "additionalProperties": true, + "additionalProperties": false, "properties": { "content": { "type": "string", From 16598f7159c3279d607e4f6f5dc76d29f8c8c316 Mon Sep 17 00:00:00 2001 From: 07akioni <07akioni2@gmail.com> Date: Mon, 27 Jul 2026 16:36:36 +0800 Subject: [PATCH 32/36] fix: cr --- apps/web/tests/todo-display.snapshot.ts | 2 ++ .../client/ui-conversation/README.i18n.yaml | 4 ++-- packages/client/ui-conversation/README.md | 1 + packages/client/ui-conversation/README.zh.md | 1 + .../src/client/skeleton/TodoPanel.module.css | 1 + .../src/client/skeleton/TodoPanel.tsx | 20 +++++++++++++------ 6 files changed, 21 insertions(+), 8 deletions(-) diff --git a/apps/web/tests/todo-display.snapshot.ts b/apps/web/tests/todo-display.snapshot.ts index f916b64b5b..ef710129d8 100644 --- a/apps/web/tests/todo-display.snapshot.ts +++ b/apps/web/tests/todo-display.snapshot.ts @@ -133,6 +133,8 @@ it('renders the todo_write turn: dedicated tool row + the dock plan strip', asyn const panel = document.querySelector('[data-testid="todo-panel"]') if (panel === null) throw new Error('todo panel missing from the input dock') + // Header spans are adjacent inline nodes; textContent joins "To-dos" + + // "1/3…" with no space (visual gap is CSS gap: 10px, not a text node). expect({ row: visibleText(row), rowState: row.getAttribute('data-state'), diff --git a/packages/client/ui-conversation/README.i18n.yaml b/packages/client/ui-conversation/README.i18n.yaml index 2f67e9eac3..56923eff77 100644 --- a/packages/client/ui-conversation/README.i18n.yaml +++ b/packages/client/ui-conversation/README.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 packages/client/ui-conversation/README.md -README.md: f6b7326916122545fc87d289cb422e644c7bae6c -README.zh.md: 55d4a743709695ba04814b4529aebac235a202d9 +README.md: 453922dafd1eb7a617cb2d1c93ac1daa2e7273c6 +README.zh.md: 88992176165ab11050a30c7df381479796908ba2 diff --git a/packages/client/ui-conversation/README.md b/packages/client/ui-conversation/README.md index f6b7326916..453922dafd 100644 --- a/packages/client/ui-conversation/README.md +++ b/packages/client/ui-conversation/README.md @@ -33,3 +33,4 @@ None; this package neither assembles nor sends a provider request. - **Assistant footer extensions (IconActions row, per-message paging) are reserved slots** — drawn in the design, not implemented. - **The sparkle icon for the others tool row is a hand-drawn approximation** — the design glyph's vector geometry is not exportable locally; promotion into ui-primitives waits on an exact export. - **Approval cards are display-only placeholders** — question requests answer through the composer chain (ui-question), while web-side approval answering is the P-II approvals project. +- **TodoPanel truncates long item text to one ellipsized line** — the figma strip has no wrap or expand affordance; full text is not readable inline. diff --git a/packages/client/ui-conversation/README.zh.md b/packages/client/ui-conversation/README.zh.md index 55d4a74370..8899217616 100644 --- a/packages/client/ui-conversation/README.zh.md +++ b/packages/client/ui-conversation/README.zh.md @@ -33,3 +33,4 @@ todo 两个面就是在该形状上的两个注册项，都是普通注册方插 - **assistant footer 扩展（IconActions 行、逐消息分页）是预留 slot**：设计中已有图稿，尚未实现。 - **others 工具行的闪光图标是手绘近似版本**：无法在本地导出设计字形的矢量几何；等到存在精确导出后再将其提升到 ui-primitives。 - **审批卡片只是只读占位符**：问题请求通过编辑器链回答（ui-question），Web 侧审批回答属于 P-II 审批项目。 +- **TodoPanel 将过长条目截成单行省略号**：figma 条没有换行或展开入口，完整文本无法在行内读完。 diff --git a/packages/client/ui-conversation/src/client/skeleton/TodoPanel.module.css b/packages/client/ui-conversation/src/client/skeleton/TodoPanel.module.css index 5ac38c1c67..8086cbfea7 100644 --- a/packages/client/ui-conversation/src/client/skeleton/TodoPanel.module.css +++ b/packages/client/ui-conversation/src/client/skeleton/TodoPanel.module.css @@ -107,6 +107,7 @@ } } +/* Figma strip is single-line; long items ellipsize with no inline expand. */ .content { min-width: 0; overflow: hidden; diff --git a/packages/client/ui-conversation/src/client/skeleton/TodoPanel.tsx b/packages/client/ui-conversation/src/client/skeleton/TodoPanel.tsx index 24764088ab..16edc423c0 100644 --- a/packages/client/ui-conversation/src/client/skeleton/TodoPanel.tsx +++ b/packages/client/ui-conversation/src/client/skeleton/TodoPanel.tsx @@ -17,10 +17,16 @@ export interface TodoPanelProps { todos: readonly TodoItem[] } -/** Completed: green check ring (figma ic_ds_check_16). */ +/** Local exhaustiveness helper — client packages do not depend on `dsh-llm`. */ +/* v8 ignore next 3 -- closed-union backstop; only reached if status is forged */ +function assertNever(value: never): never { + throw new Error(`unreachable todo status: ${String(value)}`) +} + +/** Status glyphs share the figma 14×14 artboard; the 16×16 `.glyph` cell centers them. */ function CompletedGlyph() { return ( -
    ').replace(/\n/g, '
    ').replace(/\|+/g, '\\|').padEnd(3, ' ') + return `${prefix}${escaped} |` +} + +/** Whether a row is the table's Markdown heading row. */ +function isTableHeadingRow(row: HTMLTableRowElement): boolean { + const cells = Array.from(row.cells) + const section = row.parentElement as HTMLTableSectionElement + const table = section.parentElement as HTMLTableElement + return (section.nodeName === 'THEAD' || table.rows[0] === row) + && cells.every(cell => cell.nodeName === 'TH') +} + +/** Map an HTML table-cell alignment to the GFM separator marker. */ +function tableBorder(cell: HTMLTableCellElement): string { + const alignment = (cell.getAttribute('align') || cell.style.textAlign || '').toLowerCase() + if (alignment === 'left') return ':---' + if (alignment === 'right') return '---:' + if (alignment === 'center') return ':---:' + return '---' +} + +turndown.addRule('tableCellWithoutSpanExpansion', { + filter: ['th', 'td'], + replacement(content, node) { + const cell = node as HTMLTableCellElement + const row = cell.parentNode as HTMLTableRowElement + // GFM cannot represent spanning cells. Ignoring colspan keeps conversion + // work and output proportional to the source instead of the numeric attribute. + return renderTableCell(content, Array.prototype.indexOf.call(row.childNodes, cell)) + }, +}) +turndown.addRule('tableRowWithoutSpanExpansion', { + filter: 'tr', + replacement(content, node) { + const row = node as HTMLTableRowElement + const border = isTableHeadingRow(row) + ? Array.from(row.cells, (cell, index) => renderTableCell(tableBorder(cell), index)).join('') + : '' + return `\n${content}${border.length > 0 ? `\n${border}` : ''}` + }, +}) + /** * Validate value constraints the schema DSL can't express: a non-blank `url`. * Throws a plain `Error` otherwise. No timeout parameter — the tool-call budget @@ -55,63 +101,142 @@ export function parseFetchArgs(args: { url: string }): { url: string } { */ const MAX_CONVERSION_DEPTH = 512 -/** Elements that never take a closing tag, so they must not count toward nesting depth. */ +/** Elements that never take a closing tag, so they do not grow the lexical stack. */ const VOID_ELEMENTS = new Set([ 'area', 'base', 'br', 'col', 'embed', 'hr', 'img', 'input', 'link', 'meta', 'param', 'source', 'track', 'wbr', ]) +/** Elements whose contents HTML parses as text until their matching end tag. */ +const RAW_TEXT_ELEMENTS = new Set(['script', 'style', 'noscript']) + +/** Whether a character can occur after a raw-text end-tag name. */ +function isTagBoundary(char: string | undefined): boolean { + return char === undefined || char === '>' || char === '/' || /\s/.test(char) +} + +/** Find the matching raw-text end tag without interpreting markup-like body text. */ +function findRawTextEnd(lowerHtml: string, name: string, from: number): number { + const prefix = `` characters, and only accepts a closing + * tag for the current element; malformed input therefore over-counts rather + * than hiding nesting. * * @param html - the decoded HTML body. - * @returns the deepest open-element count the scan reaches. + * @returns whether the body crosses {@link MAX_CONVERSION_DEPTH}. */ -export function htmlNestingDepth(html: string): number { - let depth = 0 - let max = 0 - for (const tag of html.matchAll(/<(\/?)([a-zA-Z][a-zA-Z0-9-]*)[^>]*?(\/?)>/g)) { - const [, closing, rawName = '', selfClosing] = tag - const name = rawName.toLowerCase() - if (VOID_ELEMENTS.has(name) || selfClosing === '/') continue - if (closing === '/') { - if (depth > 0) depth -= 1 - } else { - depth += 1 - if (depth > max) max = depth +function exceedsConversionDepth(html: string): boolean { + const lowerHtml = html.toLowerCase() + const openElements: string[] = [] + let offset = 0 + let inComment = false + + while (offset < html.length) { + const start = html.indexOf('<', offset) + if (inComment) { + const end = html.indexOf('-->', offset) + if (end !== -1 && (start === -1 || end < start)) { + inComment = false + offset = end + 3 + continue + } } + if (start === -1) break + if (!inComment && html.startsWith(''.repeat(600) + 'x' + expect(formatFetchOutput({ + url: 'https://a.test', statusCode: 200, truncated: false, + body: { kind: 'html', content: pathological }, + }, NO_CAP)).toBe(`${HEADER}${pathological}`) + const abruptlyClosedComments = '
    '.repeat(600) + 'x' + expect(formatFetchOutput({ + url: 'https://a.test', statusCode: 200, truncated: false, + body: { kind: 'html', content: abruptlyClosedComments }, + }, NO_CAP)).toBe(`${HEADER}${abruptlyClosedComments}`) + }) + + it('the preflight accepts ordinary closed, void, self-closing, quoted, and raw-text markup', () => { + const paragraphs = '

    \'>x

    '.repeat(600) + const script = `` + expect(renderHtml(`<1bad>${paragraphs}${script}`)) + .not.toContain('x