From aadc2646a3b034d825dbc5d18b4e281e3ed1add7 Mon Sep 17 00:00:00 2001 From: Codex Date: Thu, 28 May 2026 18:06:51 +0000 Subject: [PATCH] chore: add low-risk disk anti-bloat policy --- AGENTS.md | 2 +- docker-compose.yml | 36 +++- docs/reference/cli.md | 2 +- docs/reference/observability.md | 6 +- scripts/src/docker.ts | 4 +- scripts/src/gc.ts | 193 +++++++++++++++++- scripts/src/help.ts | 8 +- .../microservices/oa-event-flow/src/index.ts | 15 +- 8 files changed, 237 insertions(+), 29 deletions(-) diff --git a/AGENTS.md b/AGENTS.md index 2687ea46..a2df3f96 100644 --- a/AGENTS.md +++ b/AGENTS.md @@ -145,7 +145,7 @@ UniDesk 是一个以主 server 为统一入口的分布式工作平台；本文 - `bun scripts/cli.ts server swap status|ensure [--path /swapfile] [--size 2GiB] [--dry-run]`：以 JSON 查看或幂等创建主 server swapfile，`ensure` 输出 before/after、动作、持久化状态和 degraded/failed 详情，规则见 `docs/reference/deployment.md`。 - `bun scripts/cli.ts server logs [--tail-bytes N]`：分页返回文件日志与 Docker 日志尾部并带截断元数据，日志规则见 `docs/reference/observability.md`。 - `bun scripts/cli.ts server cleanup plan [--min-age-hours N] [--limit N]`：只读/干跑生成主 server Docker 镜像清理计划，默认只列出至少 24 小时前创建的非保护镜像，输出 active/protected images、stale candidates、预计释放空间、风险等级和必须人工确认的 `docker image rm` 命令；禁止默认删除、禁止 prune、禁止触碰 database volume、registry storage 或 Baidu Netdisk 状态。 -- `bun scripts/cli.ts gc plan|run|db-trace --confirm`：主 server 磁盘高水位一次性缓解入口，覆盖日志、journald、Docker BuildKit cache、allowlisted `/tmp` 诊断目录和显式 trace 遥测留存；默认 `gc run` 不碰数据库，`gc db-trace` 需要单独确认和 `--vacuum-full`，规则见 `docs/reference/cli.md`。 +- `bun scripts/cli.ts gc plan|run|db-trace|policy`：主 server 磁盘高水位一次性缓解和低风险防膨胀入口，覆盖日志、journald、Docker BuildKit cache、allowlisted `/tmp` 诊断目录、显式 trace 遥测留存和 systemd 定时策略；`gc run` 和 `gc db-trace run` 需要显式确认，规则见 `docs/reference/cli.md`。 - `bun scripts/cli.ts server rebuild `：以 build-first、Compose lock、no-deps force-recreate 和 post-up validation 的异步 job 重建主 server Compose 内单个服务；对 database、File Browser、Code Queue 执行面、k3sctl-adapter 或未知对象返回结构化 `unsupported-server-rebuild`，规则见 `docs/reference/deployment.md` 与 `docs/reference/cicd-standardization.md`。 - `bun scripts/cli.ts provider attach [--master-server URL] [--up] [--force]` / `bun scripts/cli.ts provider triage [--observed-error text] [--observed-scope scope] [--microservice id ...] [--full|--raw]`：前者在新增计算节点上生成两项配置的 provider-gateway 挂载包；后者是只读多信号健康裁决入口，默认低噪声输出 `decision`、`healthyScopes`、`failedScopes`、`retryable` 和异常信号摘要，用来把单路径 `provider is not online`、SSH 超时、registry 失败或 proxy 失败归类为 `retryable-transient`、`service-degraded` 或 `global-offline`，完整 evidence 需显式 `--full|--raw`，规则见 `docs/reference/provider-gateway.md` 和 `docs/reference/code-queue-supervision.md`。 - `bun scripts/cli.ts ssh [operation args...]` / `tran [operation args...]`：通过 provider-gateway 的 Host SSH / WSL SSH 维护桥进入 provider、host workspace、Windows cmd route、k3s 控制面或 pod workspace，并提供带 SHA-256 校验的 `upload`/`download` 文件传输；主 server 人工/Codex 分布式操作必须用本机 `tran` wrapper，CLI 参考和可移植脚本可保留完整命令，细则见 `docs/reference/cli.md`、`docs/reference/windows-passthrough.md` 和 `docs/reference/provider-gateway.md`。 diff --git a/docker-compose.yml b/docker-compose.yml index b0de9a32..cb651ad9 100644 --- a/docker-compose.yml +++ b/docker-compose.yml @@ -1,3 +1,9 @@ +x-unidesk-log-rotation: &unidesk-log-rotation + driver: json-file + options: + max-size: "${UNIDESK_DOCKER_LOG_MAX_SIZE:-20m}" + max-file: "${UNIDESK_DOCKER_LOG_MAX_FILE:-3}" + services: database: image: postgres:16-alpine @@ -38,6 +44,7 @@ services: interval: 5s timeout: 3s retries: 20 + logging: *unidesk-log-rotation backend-core: image: unidesk-backend-core @@ -73,7 +80,7 @@ services: UNIDESK_DEPLOY_COMMIT: "${UNIDESK_DEPLOY_COMMIT:-}" UNIDESK_DEPLOY_REQUESTED_COMMIT: "${UNIDESK_DEPLOY_REQUESTED_COMMIT:-}" LOG_FILE: "/var/log/unidesk/${UNIDESK_LOG_DAY}/${UNIDESK_LOG_PREFIX}_backend-core.jsonl" - UNIDESK_LOG_RETENTION_BYTES: "${UNIDESK_LOG_RETENTION_BYTES:-1GiB}" + UNIDESK_LOG_RETENTION_BYTES: "${UNIDESK_LOG_RETENTION_BYTES:-512MiB}" volumes: - ${UNIDESK_LOG_DIR}:/var/log/unidesk - ./.state/baidu-netdisk/staging:/data/baidu-netdisk-staging @@ -84,6 +91,7 @@ services: interval: 5s timeout: 3s retries: 20 + logging: *unidesk-log-rotation code-queue-mgr: image: code-queue-mgr @@ -107,7 +115,7 @@ services: CODE_QUEUE_WORKDIR: "/workspace" CODE_QUEUE_REMOTE_WORKDIR: "${UNIDESK_CODE_QUEUE_REMOTE_WORKDIR:-/home/ubuntu}" LOG_FILE: "/var/log/unidesk/${UNIDESK_LOG_DAY}/${UNIDESK_LOG_PREFIX}_code-queue-mgr.jsonl" - UNIDESK_LOG_RETENTION_BYTES: "${UNIDESK_LOG_RETENTION_BYTES:-1GiB}" + UNIDESK_LOG_RETENTION_BYTES: "${UNIDESK_LOG_RETENTION_BYTES:-512MiB}" UNIDESK_CODE_QUEUE_MGR_DEPLOY_REF: "${UNIDESK_CODE_QUEUE_MGR_DEPLOY_REF:-deploy.json#environments.prod.services.code-queue-mgr}" UNIDESK_CODE_QUEUE_MGR_DEPLOY_SERVICE_ID: "${UNIDESK_CODE_QUEUE_MGR_DEPLOY_SERVICE_ID:-code-queue-mgr}" UNIDESK_CODE_QUEUE_MGR_DEPLOY_REPO: "${UNIDESK_CODE_QUEUE_MGR_DEPLOY_REPO:-}" @@ -120,6 +128,7 @@ services: interval: 5s timeout: 3s retries: 20 + logging: *unidesk-log-rotation code-agent-sandbox: image: code-agent-sandbox @@ -155,7 +164,7 @@ services: UNIDESK_DEPLOY_COMMIT: "${UNIDESK_CODE_AGENT_SANDBOX_DEPLOY_COMMIT:-}" UNIDESK_DEPLOY_REQUESTED_COMMIT: "${UNIDESK_CODE_AGENT_SANDBOX_DEPLOY_REQUESTED_COMMIT:-}" LOG_FILE: "/var/log/unidesk/${UNIDESK_LOG_DAY}/${UNIDESK_LOG_PREFIX}_code-agent-sandbox.jsonl" - UNIDESK_LOG_RETENTION_BYTES: "${UNIDESK_LOG_RETENTION_BYTES:-1GiB}" + UNIDESK_LOG_RETENTION_BYTES: "${UNIDESK_LOG_RETENTION_BYTES:-512MiB}" volumes: - ${UNIDESK_LOG_DIR}:/var/log/unidesk - ./.state/code-agent-sandbox:/var/lib/unidesk/code-agent-sandbox @@ -164,6 +173,7 @@ services: interval: 5s timeout: 3s retries: 20 + logging: *unidesk-log-rotation auth-broker: image: auth-broker @@ -189,7 +199,7 @@ services: UNIDESK_DEPLOY_COMMIT: "${UNIDESK_AUTH_BROKER_DEPLOY_COMMIT:-}" UNIDESK_DEPLOY_REQUESTED_COMMIT: "${UNIDESK_AUTH_BROKER_DEPLOY_REQUESTED_COMMIT:-}" LOG_FILE: "/var/log/unidesk/${UNIDESK_LOG_DAY}/${UNIDESK_LOG_PREFIX}_auth-broker.jsonl" - UNIDESK_LOG_RETENTION_BYTES: "${UNIDESK_LOG_RETENTION_BYTES:-1GiB}" + UNIDESK_LOG_RETENTION_BYTES: "${UNIDESK_LOG_RETENTION_BYTES:-512MiB}" volumes: - ${UNIDESK_LOG_DIR}:/var/log/unidesk healthcheck: @@ -197,6 +207,7 @@ services: interval: 30s timeout: 3s retries: 1 + logging: *unidesk-log-rotation todo-note: image: todo-note @@ -245,6 +256,7 @@ services: interval: 5s timeout: 3s retries: 20 + logging: *unidesk-log-rotation oa-event-flow: image: oa-event-flow @@ -269,7 +281,7 @@ services: PIPELINE_OA_BRIDGE_INTERVAL_MS: "${UNIDESK_PIPELINE_OA_BRIDGE_INTERVAL_MS:-15000}" PIPELINE_OA_BRIDGE_RUN_LIMIT: "${UNIDESK_PIPELINE_OA_BRIDGE_RUN_LIMIT:-50}" LOG_FILE: "/var/log/unidesk/${UNIDESK_LOG_DAY}/${UNIDESK_LOG_PREFIX}_oa-event-flow.jsonl" - UNIDESK_LOG_RETENTION_BYTES: "${UNIDESK_LOG_RETENTION_BYTES:-1GiB}" + UNIDESK_LOG_RETENTION_BYTES: "${UNIDESK_LOG_RETENTION_BYTES:-512MiB}" UNIDESK_DEPLOY_REF: "${UNIDESK_OA_EVENT_FLOW_DEPLOY_REF:-deploy.json#environments.prod.services.oa-event-flow}" UNIDESK_DEPLOY_SERVICE_ID: "${UNIDESK_OA_EVENT_FLOW_DEPLOY_SERVICE_ID:-oa-event-flow}" UNIDESK_DEPLOY_REPO: "${UNIDESK_OA_EVENT_FLOW_DEPLOY_REPO:-}" @@ -282,6 +294,7 @@ services: interval: 5s timeout: 3s retries: 20 + logging: *unidesk-log-rotation project-manager: image: project-manager @@ -300,7 +313,7 @@ services: DATABASE_URL: "postgres://${UNIDESK_DATABASE_USER}:${UNIDESK_DATABASE_PASSWORD}@database:5432/${UNIDESK_DATABASE_NAME}" DATABASE_POOL_MAX: "${UNIDESK_PROJECT_MANAGER_DATABASE_POOL_MAX:-1}" LOG_FILE: "/var/log/unidesk/${UNIDESK_LOG_DAY}/${UNIDESK_LOG_PREFIX}_project-manager.jsonl" - UNIDESK_LOG_RETENTION_BYTES: "${UNIDESK_LOG_RETENTION_BYTES:-1GiB}" + UNIDESK_LOG_RETENTION_BYTES: "${UNIDESK_LOG_RETENTION_BYTES:-512MiB}" UNIDESK_DEPLOY_REF: "${UNIDESK_PROJECT_MANAGER_DEPLOY_REF:-deploy.json#environments.prod.services.project-manager}" UNIDESK_DEPLOY_SERVICE_ID: "${UNIDESK_PROJECT_MANAGER_DEPLOY_SERVICE_ID:-project-manager}" UNIDESK_DEPLOY_REPO: "${UNIDESK_PROJECT_MANAGER_DEPLOY_REPO:-}" @@ -313,6 +326,7 @@ services: interval: 5s timeout: 3s retries: 20 + logging: *unidesk-log-rotation baidu-netdisk: image: baidu-netdisk @@ -336,7 +350,7 @@ services: BAIDU_NETDISK_APP_ROOT: "${UNIDESK_BAIDU_NETDISK_APP_ROOT:-/}" BAIDU_NETDISK_STAGING_DIR: "/data/staging" LOG_FILE: "/var/log/unidesk/${UNIDESK_LOG_DAY}/${UNIDESK_LOG_PREFIX}_baidu-netdisk.jsonl" - UNIDESK_LOG_RETENTION_BYTES: "${UNIDESK_LOG_RETENTION_BYTES:-1GiB}" + UNIDESK_LOG_RETENTION_BYTES: "${UNIDESK_LOG_RETENTION_BYTES:-512MiB}" UNIDESK_DEPLOY_REF: "${UNIDESK_BAIDU_NETDISK_DEPLOY_REF:-deploy.json#environments.prod.services.baidu-netdisk}" UNIDESK_DEPLOY_SERVICE_ID: "${UNIDESK_BAIDU_NETDISK_DEPLOY_SERVICE_ID:-baidu-netdisk}" UNIDESK_DEPLOY_REPO: "${UNIDESK_BAIDU_NETDISK_DEPLOY_REPO:-}" @@ -350,6 +364,7 @@ services: interval: 5s timeout: 3s retries: 20 + logging: *unidesk-log-rotation frontend: build: @@ -377,7 +392,7 @@ services: UNIDESK_DEPLOY_COMMIT: "${UNIDESK_FRONTEND_DEPLOY_COMMIT:-}" UNIDESK_DEPLOY_REQUESTED_COMMIT: "${UNIDESK_FRONTEND_DEPLOY_REQUESTED_COMMIT:-}" LOG_FILE: "/var/log/unidesk/${UNIDESK_LOG_DAY}/${UNIDESK_LOG_PREFIX}_frontend.jsonl" - UNIDESK_LOG_RETENTION_BYTES: "${UNIDESK_LOG_RETENTION_BYTES:-1GiB}" + UNIDESK_LOG_RETENTION_BYTES: "${UNIDESK_LOG_RETENTION_BYTES:-512MiB}" volumes: - ${UNIDESK_LOG_DIR}:/var/log/unidesk healthcheck: @@ -385,6 +400,7 @@ services: interval: 5s timeout: 3s retries: 20 + logging: *unidesk-log-rotation dev-frontend-proxy: build: @@ -401,6 +417,7 @@ services: interval: 10s timeout: 5s retries: 12 + logging: *unidesk-log-rotation provider-gateway: image: unidesk_provider-gateway @@ -431,7 +448,7 @@ services: PROVIDER_UPGRADE_SERVICE: "${UNIDESK_PROVIDER_UPGRADE_SERVICE}" PROVIDER_UPGRADE_RUNNER_IMAGE: "${UNIDESK_PROVIDER_UPGRADE_RUNNER_IMAGE}" LOG_FILE: "/var/log/unidesk/${UNIDESK_LOG_DAY}/${UNIDESK_LOG_PREFIX}_provider-gateway.jsonl" - UNIDESK_LOG_RETENTION_BYTES: "${UNIDESK_LOG_RETENTION_BYTES:-1GiB}" + UNIDESK_LOG_RETENTION_BYTES: "${UNIDESK_LOG_RETENTION_BYTES:-512MiB}" HOST_SSH_HOST: "${UNIDESK_HOST_SSH_HOST}" HOST_SSH_PORT: "${UNIDESK_HOST_SSH_PORT}" HOST_SSH_USER: "${UNIDESK_HOST_SSH_USER}" @@ -445,6 +462,7 @@ services: - ${UNIDESK_LOG_DIR}:/var/log/unidesk extra_hosts: - "host.docker.internal:host-gateway" + logging: *unidesk-log-rotation volumes: unidesk_pgdata_10gb: diff --git a/docs/reference/cli.md b/docs/reference/cli.md index 652adbb3..d1ffec4f 100644 --- a/docs/reference/cli.md +++ b/docs/reference/cli.md @@ -25,7 +25,7 @@ CI/CD、GitOps、rollout、artifact 发布、PR 合并后的 DEV/PROD 滚动、P - `server swap status|ensure [--path /swapfile] [--size 2GiB] [--dry-run]` 是主 server swap 管理入口。`status` 仅读 `/proc/meminfo`、`/proc/swaps` 和 `/etc/fstab` 并返回 JSON；`ensure` 在已有任何 active swap 时只报告 no-op，在无 active swap 时创建固定 swapfile、`chmod 600`、`mkswap`、`swapon` 并尽量写入 `/etc/fstab`。输出必须包含 `before`、`after`、total memory、active swap、持久化状态、关键动作和错误详情；若 swap 已启用但 fstab 写入失败，状态为 `degraded`，调用者需按返回的 detail 修复持久化。 - `server logs` 返回 `logs/` 文件日志和 Docker 容器日志的尾部，默认限制输出大小，避免日志爆炸。实现必须只读取文件末尾字节，不得为了 tail 先把巨大日志完整读入 CLI 内存。 - `server cleanup plan [--min-age-hours N] [--limit N]` 只生成主 server Docker 镜像清理 dry-run 计划，不执行删除；默认 `--min-age-hours 24`，避免把刚发布或刚验证的镜像列为 stale。输出必须包含 `dryRun=true`、`mutation=false`、`policy.deletionExecuted=false`、active containers/images、受保护镜像、candidate stale images、估算释放空间、风险等级、`commandsToReview` 和人工审批清单。计划必须保守白名单：保留 running containers 使用的 image ID，保留 stopped containers 引用的 image ID 直到人工先复核容器，保留 `deploy.json`/`CI.json` 当前 commit-pinned artifact、Compose stable image、上游 digest pin 和 provider-gateway runner image；`protectedStorage` 必须显式列出 PostgreSQL named volume、Baidu Netdisk `.state`、D601 registry storage 和 Docker volumes/host data policy。该入口禁止生成或执行 `docker system prune`、`docker image prune`、`docker builder prune`、`docker volume rm`、`docker compose down -v`、数据库清理或 host data `rm` 命令；未来若增加真实删除，必须另设显式审批参数并先复核 dry-run 输出。 -- `gc plan|run --confirm` 是主 server 磁盘高水位的一次性短期缓解入口，覆盖 UniDesk 文件日志、Docker `json-file` 容器日志、systemd journal、Docker BuildKit cache 和 allowlisted `/tmp` 诊断目录。`gc plan` 默认只读并返回候选、风险、估算释放空间、受保护对象和数据库只读摘要；候选列表默认按释放空间排序限制为 50 条，`--limit N` 调整页大小，`--full|--raw` 才展开全部候选。输出中的 `estimatedReclaim` 表示全量候选估算，`returnedEstimatedReclaim` 表示当前输出页估算。`gc run` 必须显式 `--confirm`，只执行当前输出候选中的短期清理动作，因此默认不会执行被分页隐藏的候选。`gc` 不删除 Docker image/container/volume，不触碰 PostgreSQL PGDATA，不删除 Baidu Netdisk staging/backups 或 D601 registry storage；默认路径中数据库只做诊断摘要。`gc db-trace plan|run --confirm --before-date YYYY-MM-DD --vacuum-full` 是显式数据库 trace 遥测留存入口，只删除 `oa_events` 中默认 trace 高频事件类型在指定日期前的数据，并在 `--vacuum-full` 下重写 `public.oa_events` 让 `df` 真正回收磁盘；执行前必须确认近期 PostgreSQL basebackup，且应视为维护窗口操作。常用参数包括 `--logs-keep-days N`、`--file-log-max-bytes SIZE`、`--file-log-tail-bytes SIZE`、`--docker-log-max-bytes SIZE`、`--journal-target-size SIZE`、`--build-cache-until 24h`、显式清空全部 BuildKit cache 的 `--build-cache-all`、`--tmp-min-age-hours N` 和显式 `--include-browser-cache`。 +- `gc plan|run --confirm` 是主 server 磁盘高水位的一次性短期缓解入口，覆盖 UniDesk 文件日志、Docker `json-file` 容器日志、systemd journal、Docker BuildKit cache 和 allowlisted `/tmp` 诊断目录。`gc plan` 默认只读并返回候选、风险、估算释放空间、受保护对象和数据库只读摘要；候选列表默认按释放空间排序限制为 50 条，`--limit N` 调整页大小，`--full|--raw` 才展开全部候选。输出中的 `estimatedReclaim` 表示全量候选估算，`returnedEstimatedReclaim` 表示当前输出页估算；`gc run` 默认只返回前 50 条结果，`--result-limit N` 调整结果页大小，避免 GC 自身输出膨胀。`gc run` 必须显式 `--confirm`，只执行当前输出候选中的短期清理动作，因此默认不会执行被分页隐藏的候选。`gc` 不删除 Docker image/container/volume，不触碰 PostgreSQL PGDATA，不删除 Baidu Netdisk staging/backups 或 D601 registry storage；默认路径中数据库只做诊断摘要。`gc policy plan|install` 渲染或安装低风险长期策略：journald 512MiB 上限和每日 `unidesk-gc.timer`，该 timer 只运行文件日志与 allowlisted `/tmp` 低风险 GC，不主动 vacuum journal，不触碰数据库、Docker image/volume 或 Baidu staging，输出写入 `.state/gc/`。`gc db-trace plan|run --confirm --before-date YYYY-MM-DD --vacuum-full` 是显式数据库 trace 遥测留存入口，只删除 `oa_events` 中默认 trace 高频事件类型在指定日期前的数据，并在 `--vacuum-full` 下重写 `public.oa_events` 让 `df` 真正回收磁盘；执行前必须确认近期 PostgreSQL basebackup，且应视为维护窗口操作。常用参数包括 `--logs-keep-days N`、`--file-log-max-bytes SIZE`、`--file-log-tail-bytes SIZE`、`--docker-log-max-bytes SIZE`、`--journal-target-size SIZE`、`--build-cache-until 24h`、显式清空全部 BuildKit cache 的 `--build-cache-all`、`--tmp-min-age-hours N` 和显式 `--include-browser-cache`。 - `server rebuild ` 创建异步 job，先构建目标服务镜像，随后在 `.state/locks/server-compose.lock` 串行保护下用 `--no-deps --force-recreate` 替换目标 service 并等待容器 `healthy/running`；该命令用于替代手工删除容器的兜底流程，其中 `dev-frontend-proxy` 只更新主 server dev 入口薄代理，`todo-note`、`code-queue-mgr`、`project-manager`、`baidu-netdisk` 和 `oa-event-flow` 只重建主 server 承载的对应后端，不会重建或删除 database 命名卷。D601 Code Queue 执行面不由 `server rebuild` 管理，Rust backend-core 迭代不得用 `server rebuild backend-core` 在 master server 编译，规则见 `docs/reference/dev-environment.md`。 - `provider attach [--master-server URL] [--up] [--force]` 在新计算节点生成两项配置的 provider-gateway 挂载包：`.state/provider-.env` 默认只包含 `UNIDESK_MASTER_SERVER` 与 `PROVIDER_ID`，`provider-.yml` 固定 Docker socket、`pid: "host"`、`restart: always`、只读 `/workspace` 和 SSH 维护私钥挂载；`--up` 会立即执行生成的 `docker compose up -d --build`。`provider triage [--observed-error text] [--observed-scope scope] [--microservice id ...] [--full|--raw]` 是只读多信号健康裁决入口，会把单路径 `provider is not online`、SSH 超时、registry 失败和 service proxy 失败归类成 `runner-local-observation-gap`、`service-degraded`、`provider-degraded` 或 `global-blocker`。默认输出只返回裁决、scope、失败/降级/未知信号和有界 evidence 摘要，完整 evidence 必须显式加 `--full` 或 `--raw`；推荐交叉验证命令仍包含 `debug health`、`debug dispatch host.ssh --wait-ms 15000`、`ssh argv true`、`artifact-registry health --provider-id `、`microservice health k3sctl-adapter`、`microservice health code-queue` 和 `codex tasks --view supervisor --limit 20`。 - `ssh [operation args...]` / `tran [operation args...]` 通过 backend-core 内网 WebSocket broker 和 provider-gateway 的 Host SSH / WSL SSH 维护桥连接目标节点；`route` 基础形态是 provider id，例如 `D601` 或 `G14`，也可以扩展为纯定位路径 `provider:plane[:namespace:resource[:container]]`，例如 `D601:win`、`D601:win/c/test`、`G14:k3s`、`D601:k3s` 或 `G14:k3s::`。WSL provider 的 Windows cmd 入口固定写 `tran D601:win cmd `，需要 Windows cwd 时用 `tran D601:win/c/test cmd cd`，由 CLI 自动设置 `chcp 65001`、`PYTHONUTF8=1` 和 `PYTHONIOENCODING=utf-8`；命名只允许 `win`，不得使用 `win32`。非交互远端命令优先使用 `ssh argv ...`；需要 shell 脚本、管道、变量或循环时优先使用 quoted heredoc 单步传输，例如 `tran G14 script <<'SCRIPT'`、`tran G14:k3s script <<'SCRIPT'` 或 `tran G14:k3s:: script <<'SCRIPT'`，把脚本走 stdin。`script -- '<单个字符串>'` 是无需 stdin 的远端 shell one-liner，例如 `tran G14:/root/hwlab script -- 'cd /root/hwlab && git status --short --branch'`；`script -- <多个 argv>` 才是 direct argv，适合 `tran D601:/path script -- sed -n '1,20p' file` 这类带短横线的单进程命令。顶层 remote option parser 必须保留命令已经开始后的 `--`，不得把它吞成全局选项结束符。需要远端改文本文件时默认优先使用 ` apply-patch < patch.diff`；需要可靠传输非文本或整文件时使用 ` upload ` 和 ` download `，CLI 会按字节数与 SHA-256 自动校验并在 provider-gateway stdin/argv 限制下切换客户端分块策略；需要旧 helper 时显式使用 `:k3s:: apply-patch-v1` 或 ` apply-patch-v1`。ssh-like 命令遇到 timeout/kex/255 类失败时，CLI 会在 stderr 追加一行 `UNIDESK_SSH_HINT` JSON，提示 stdin script/argv 重试和 provider triage 交叉验证。 diff --git a/docs/reference/observability.md b/docs/reference/observability.md index b65dc73a..ed439723 100644 --- a/docs/reference/observability.md +++ b/docs/reference/observability.md @@ -10,7 +10,11 @@ UniDesk 的可观测性优先级高于静默成功。CLI、服务日志、Docker 服务日志位于 `logs/{YYYYMMDD}/`，每次 `server start` 都生成新的本地时间戳前缀。新写入的 UniDesk JSONL 日志必须按小时切片：`logs/{YYYYMMDD}/{startStamp}_{YYYYMMDD}_{HH}_{service}.jsonl`，一天一个目录，禁止长期追加到单个巨大 JSONL。所有 UniDesk Bun 服务（frontend、provider-gateway、Code Queue、project-manager、baidu-netdisk 以及后续新增 Bun 服务）必须复用 `src/components/shared/src/rotating-jsonl.ts` 中的 `createHourlyJsonlWriter`；Rust backend-core 必须提供等价的 hourly rotation and retention behavior in `src/components/backend-core/src/logger.rs`。`LOG_FILE` 只作为推导 `logs` 根目录、启动前缀和 service 后缀的 base path，不得长期追加到单个文件。database 通过 PostgreSQL logging collector 写入同一日期目录。 -日志保留默认按日志族限制为 `1GiB`：服务写入或 Code Queue 导出日志时必须扫描同一 service 后缀的历史文件，超过上限后自动删除最旧切片；当前活跃切片不能被保留清理删除。全局上限由 `UNIDESK_LOG_RETENTION_BYTES` 控制，服务级上限使用 `UNIDESK__LOG_MAX_BYTES`（如 `UNIDESK_FRONTEND_LOG_MAX_BYTES`、`UNIDESK_PROVIDER_GATEWAY_LOG_MAX_BYTES`），历史兼容变量只允许作为过渡入口。Codex app-server 的 `logs_*.sqlite` 仅作为 Codex 上游运行时的短暂缓冲，Code Queue 必须周期性导出为同样按小时切片的 `codex-app-server` JSONL，并删除/压缩已导出的 SQLite 行，避免 `logs_2.sqlite` 成为长期大文件。 +日志保留默认按日志族限制为 `512MiB`：服务写入或 Code Queue 导出日志时必须扫描同一 service 后缀的历史文件，超过上限后自动删除最旧切片；当前活跃切片不能被保留清理删除。全局上限由 `UNIDESK_LOG_RETENTION_BYTES` 控制，服务级上限使用 `UNIDESK__LOG_MAX_BYTES`（如 `UNIDESK_FRONTEND_LOG_MAX_BYTES`、`UNIDESK_PROVIDER_GATEWAY_LOG_MAX_BYTES`），历史兼容变量只允许作为过渡入口。主 server Compose 服务必须启用 Docker `json-file` 轮转，默认 `UNIDESK_DOCKER_LOG_MAX_SIZE=20m`、`UNIDESK_DOCKER_LOG_MAX_FILE=3`；该配置在服务重建或重建容器后生效。Codex app-server 的 `logs_*.sqlite` 仅作为 Codex 上游运行时的短暂缓冲，Code Queue 必须周期性导出为同样按小时切片的 `codex-app-server` JSONL，并删除/压缩已导出的 SQLite 行，避免 `logs_2.sqlite` 成为长期大文件。 + +主 server 应安装 `bun scripts/cli.ts gc policy install` 渲染的低风险防膨胀策略：systemd journal 上限 `512MiB`，并启用每日 `unidesk-gc.timer` 执行文件日志与 allowlisted `/tmp` 低风险 GC。该 timer 不主动 vacuum journal，不触碰数据库、Docker image/volume 或 Baidu staging；输出固定写入 `.state/gc/last-run.json` 和 `.state/gc/last-run.stderr`，不得把全量候选 JSON 打进 systemd journal；数据库 trace 留存仍必须由 `gc db-trace` 显式维护，不得加入默认 timer。 + +OA Event Flow 的高频 trace 统计不得把每个 `trace-stats-updated` 投影事件长期写入 `oa_events`；持久化真相是 `oa_trace_stats` 与 `oa_trace_steps`，SSE/API 发布时可以返回短暂投影通知用于实时 UI 刷新。需要历史回收时只通过 `gc db-trace plan|run` 做显式维护窗口操作，禁止把数据库 VACUUM FULL 或 trace 表大规模删除接入默认 timer。 新增或迁移服务的长期规范：Dockerfile 必须把 `src/components/shared` 复制到与仓库相同的相对路径，TypeScript 配置必须能解析 shared 引用，Compose 必须传入 `LOG_FILE` 和 `UNIDESK_LOG_RETENTION_BYTES`；如果服务需要在内存中暴露 `/logs`，可以继续维护有限 `recentLogs`，但落盘只能通过统一 hourly writer。业务归档日志（例如 Code Queue task output archive）可以保留 append-only 文件，但不得复用 UniDesk service JSONL 命名族，也不得替代 `/logs` 的结构化服务日志。 diff --git a/scripts/src/docker.ts b/scripts/src/docker.ts index b6ce21ba..57b775ef 100644 --- a/scripts/src/docker.ts +++ b/scripts/src/docker.ts @@ -222,7 +222,9 @@ export function writeComposeEnv(config: UniDeskConfig, freshLogPrefix: boolean): UNIDESK_LOG_DIR: logRoot, UNIDESK_LOG_DAY: logDay, UNIDESK_LOG_PREFIX: logPrefix, - UNIDESK_LOG_RETENTION_BYTES: runtimeSecret("UNIDESK_LOG_RETENTION_BYTES") || "1GiB", + UNIDESK_LOG_RETENTION_BYTES: runtimeSecretWithDefault("UNIDESK_LOG_RETENTION_BYTES", "512MiB", "1GiB"), + UNIDESK_DOCKER_LOG_MAX_SIZE: runtimeSecret("UNIDESK_DOCKER_LOG_MAX_SIZE") || "20m", + UNIDESK_DOCKER_LOG_MAX_FILE: runtimeSecret("UNIDESK_DOCKER_LOG_MAX_FILE") || "3", UNIDESK_HOST_ROOT_SSH_DIR: process.env.UNIDESK_HOST_ROOT_SSH_DIR || "/root/.ssh", UNIDESK_HOST_SSH_KEY_DIR: config.sshForwarding.keyDir, UNIDESK_HOST_SSH_HOST: config.sshForwarding.host, diff --git a/scripts/src/gc.ts b/scripts/src/gc.ts index 7b0cb7a9..a1c727cc 100644 --- a/scripts/src/gc.ts +++ b/scripts/src/gc.ts @@ -1,5 +1,5 @@ import { spawnSync } from "node:child_process"; -import { closeSync, existsSync, ftruncateSync, lstatSync, openSync, readdirSync, readSync, rmSync, statSync, unlinkSync, writeSync } from "node:fs"; +import { closeSync, existsSync, ftruncateSync, lstatSync, mkdirSync, openSync, readdirSync, readSync, rmSync, statSync, unlinkSync, writeFileSync, writeSync } from "node:fs"; import { basename, join, resolve } from "node:path"; import { type UniDeskConfig, repoRoot, rootPath } from "./config"; @@ -31,6 +31,7 @@ interface GcOptions { browserCache: boolean; dbSummary: boolean; limit: number; + resultLimit: number; full: boolean; } @@ -41,6 +42,11 @@ interface DbTraceGcOptions { confirm: boolean; } +interface GcPolicyOptions { + dryRun: boolean; + enableNow: boolean; +} + interface DiskSnapshot { filesystem: string; sizeBytes: number; @@ -114,6 +120,9 @@ interface GcRunResult { failedCount: number; estimatedReclaimBytes: number; actualDiskReclaimBytes: number | null; + resultCount: number; + returnedResultCount: number; + omittedResultCount: number; }; results: Array; protected: ProtectedGcItem[]; @@ -136,6 +145,7 @@ const DEFAULT_OPTIONS: GcOptions = { browserCache: false, dbSummary: true, limit: 50, + resultLimit: 50, full: false, }; @@ -173,6 +183,18 @@ const TMP_EXACT_PROTECT = new Set([ export async function runGcCommand(config: UniDeskConfig, args: string[]): Promise { const [action = "plan", ...rest] = args; + if (action === "policy") { + const [subaction = "plan", ...policyArgs] = rest; + const options = parseGcPolicyOptions(policyArgs); + if (subaction === "plan" || subaction === "render" || subaction === "dry-run") return gcPolicyPlan(options); + if (subaction === "install") return gcPolicyInstall(options); + return { + ok: false, + error: "unsupported-gc-policy-action", + action: subaction, + supportedActions: ["plan", "render", "dry-run", "install"], + }; + } if (action === "db-trace" || action === "db-trace-retention") { const [subaction = "plan", ...dbArgs] = rest; const options = parseDbTraceGcOptions(dbArgs); @@ -221,7 +243,7 @@ export async function runGcCommand(config: UniDeskConfig, args: string[]): Promi ok: false, error: "unsupported-gc-action", action, - supportedActions: ["plan", "run"], + supportedActions: ["plan", "run", "db-trace", "policy"], }; } @@ -324,6 +346,7 @@ export function gcRun(config: UniDeskConfig, options: GcOptions = DEFAULT_OPTION const failedCount = results.filter((item) => item.status === "failed").length; const estimatedReclaimBytes = plan.summary.returnedEstimatedReclaimBytes; const actualDiskReclaimBytes = diskBefore !== null && diskAfter !== null ? diskAfter.availableBytes - diskBefore.availableBytes : null; + const returnedResults = returnedRunResults(results, options); return { ok: failedCount === 0, @@ -341,8 +364,11 @@ export function gcRun(config: UniDeskConfig, options: GcOptions = DEFAULT_OPTION failedCount, estimatedReclaimBytes, actualDiskReclaimBytes, + resultCount: results.length, + returnedResultCount: returnedResults.length, + omittedResultCount: Math.max(0, results.length - returnedResults.length), }, - results, + results: returnedResults, protected: plan.protected, }; } @@ -389,6 +415,10 @@ function parseGcOptions(args: string[]): GcOptions { const value = parseNonNegativeNumber(arg, args[++index]); if (!Number.isInteger(value) || value <= 0) throw new Error("--limit must be a positive integer"); options.limit = Math.min(value, 5000); + } else if (arg === "--result-limit") { + const value = parseNonNegativeNumber(arg, args[++index]); + if (!Number.isInteger(value) || value <= 0) throw new Error("--result-limit must be a positive integer"); + options.resultLimit = Math.min(value, 5000); } else if (arg === "--full" || arg === "--raw") { options.full = true; } else if (arg === "--confirm" || arg === "--dry-run") { @@ -437,6 +467,18 @@ function parseDbTraceGcOptions(args: string[]): DbTraceGcOptions { return options; } +function parseGcPolicyOptions(args: string[]): GcPolicyOptions { + const options: GcPolicyOptions = { + dryRun: args.includes("--dry-run"), + enableNow: !args.includes("--no-enable-now"), + }; + for (const arg of args) { + if (arg === "--dry-run" || arg === "--no-enable-now") continue; + throw new Error(`unknown gc policy option: ${arg}`); + } + return options; +} + function parseNonNegativeNumber(name: string, raw: string | undefined): number { const value = Number(raw); if (!Number.isFinite(value) || value < 0) throw new Error(`${name} must be a non-negative number`); @@ -481,6 +523,7 @@ function publicOptions(options: GcOptions): Record { browserCache: options.browserCache, dbSummary: options.dbSummary, limit: options.limit, + resultLimit: options.resultLimit, full: options.full, }; } @@ -799,6 +842,143 @@ function gcDbTraceRun(options: DbTraceGcOptions): unknown { }; } +function gcPolicyPlan(options: GcPolicyOptions): unknown { + const files = gcPolicyFiles(); + return { + ok: true, + action: "gc policy plan", + dryRun: true, + mutation: false, + observedAt: new Date().toISOString(), + options, + files, + commands: { + install: [ + ["mkdir", "-p", "/etc/systemd/journald.conf.d", "/etc/systemd/system"], + ["systemctl", "daemon-reload"], + ["systemctl", "enable", "--now", "unidesk-gc.timer"], + ], + journalRestart: ["systemctl", "restart", "systemd-journald"], + }, + policy: { + safeScope: [ + "systemd journal is capped at 512MiB", + "daily timer runs file-log and allowlisted /tmp low-risk gc only", + "timer does not touch PostgreSQL PGDATA, Docker images, Docker volumes or Baidu Netdisk staging", + "timer output is redirected under .state/gc and capped by gc --result-limit", + ], + manualDbRetention: "gc db-trace remains explicit maintenance and is not scheduled automatically.", + }, + }; +} + +function gcPolicyInstall(options: GcPolicyOptions): unknown { + const plan = gcPolicyPlan(options); + if (options.dryRun) return plan; + const files = gcPolicyFiles(); + mkdirSync("/etc/systemd/journald.conf.d", { recursive: true }); + mkdirSync("/etc/systemd/system", { recursive: true }); + mkdirSync(rootPath(".state", "gc"), { recursive: true }); + writeFileSync(files.journald.path, files.journald.content, "utf8"); + writeFileSync(files.service.path, files.service.content, "utf8"); + writeFileSync(files.timer.path, files.timer.content, "utf8"); + const daemonReload = command(["systemctl", "daemon-reload"], 15000); + const enableTimer = options.enableNow ? command(["systemctl", "enable", "--now", "unidesk-gc.timer"], 15000) : null; + const restartJournald = command(["systemctl", "restart", "systemd-journald"], 15000); + const timerStatus = command(["systemctl", "is-enabled", "unidesk-gc.timer"], 5000); + const activeStatus = command(["systemctl", "is-active", "unidesk-gc.timer"], 5000); + const results = { + daemonReload: boundedCommandOutput(daemonReload), + enableTimer: enableTimer === null ? { skipped: true } : boundedCommandOutput(enableTimer), + restartJournald: boundedCommandOutput(restartJournald), + timerStatus: { + enabled: timerStatus.stdout.trim(), + active: activeStatus.stdout.trim(), + }, + }; + const failed = daemonReload.exitCode !== 0 + || restartJournald.exitCode !== 0 + || (enableTimer !== null && enableTimer.exitCode !== 0); + return { + ok: !failed, + action: "gc policy install", + dryRun: false, + mutation: true, + observedAt: new Date().toISOString(), + options, + files, + results, + plan, + }; +} + +function gcPolicyFiles(): Record { + const gcStateDir = rootPath(".state", "gc"); + const bunPath = bunExecutablePath(); + const gcScript = `cd ${shellQuote(repoRoot)} && mkdir -p ${shellQuote(gcStateDir)} && ${shellQuote(bunPath)} scripts/cli.ts gc run --confirm --no-db-summary --no-build-cache --no-docker-logs --no-journal --limit 5000 --result-limit 25 > ${shellQuote(join(gcStateDir, "last-run.json"))} 2> ${shellQuote(join(gcStateDir, "last-run.stderr"))}`; + return { + journald: { + path: "/etc/systemd/journald.conf.d/unidesk-gc.conf", + content: [ + "[Journal]", + "SystemMaxUse=512M", + "RuntimeMaxUse=128M", + "MaxRetentionSec=7day", + "", + ].join("\n"), + }, + service: { + path: "/etc/systemd/system/unidesk-gc.service", + content: [ + "[Unit]", + "Description=UniDesk low-risk disk garbage collection", + "Documentation=file:///root/unidesk/docs/reference/cli.md", + "", + "[Service]", + "Type=oneshot", + `WorkingDirectory=${repoRoot}`, + `ExecStart=/bin/bash -lc "${systemdDoubleQuoted(gcScript)}"`, + "", + ].join("\n"), + }, + timer: { + path: "/etc/systemd/system/unidesk-gc.timer", + content: [ + "[Unit]", + "Description=Daily UniDesk low-risk disk garbage collection", + "", + "[Timer]", + "OnCalendar=*-*-* 03:20:00", + "RandomizedDelaySec=20m", + "Persistent=true", + "", + "[Install]", + "WantedBy=timers.target", + "", + ].join("\n"), + }, + }; +} + +function bunExecutablePath(): string { + const candidates = ["/usr/bin/bun", "/root/.bun/bin/bun", process.argv[0] ?? ""]; + for (const candidate of candidates) { + if (candidate.length > 0 && existsSync(candidate)) return resolve(candidate); + } + return "bun"; +} + +function systemdDoubleQuoted(value: string): string { + return value + .replace(/\\/gu, "\\\\") + .replace(/"/gu, "\\\"") + .replace(/%/gu, "%%"); +} + +function shellQuote(value: string): string { + return `'${value.replace(/'/gu, "'\\''")}'`; +} + function sqlLiteral(value: string): string { return `'${value.replace(/'/gu, "''")}'`; } @@ -929,6 +1109,13 @@ function summarizeCandidates(candidates: GcCandidate[], returnedCandidates: GcCa }; } +function returnedRunResults(results: GcRunResult["results"], options: GcOptions): GcRunResult["results"] { + if (options.full) return results; + const failed = results.filter((item) => item.status === "failed"); + const succeeded = results.filter((item) => item.status === "succeeded"); + return [...failed, ...succeeded].slice(0, options.resultLimit); +} + function collectFiles(root: string): Array<{ path: string; sizeBytes: number; mtimeMs: number }> { const result: Array<{ path: string; sizeBytes: number; mtimeMs: number }> = []; const visit = (dir: string): void => { diff --git a/scripts/src/help.ts b/scripts/src/help.ts index 6d5b031c..ae3b32a1 100644 --- a/scripts/src/help.ts +++ b/scripts/src/help.ts @@ -18,7 +18,7 @@ export function rootHelp(): unknown { { command: "server swap status|ensure [--path /swapfile] [--size 2GiB] [--dry-run]", description: "Inspect or idempotently create host swap for low-memory main-server operation." }, { command: "server logs [--tail-bytes N]", description: "Return bounded tails from file logs and docker logs." }, { command: "server cleanup plan [--min-age-hours N] [--limit N]", description: "Dry-run Docker image cleanup plan only: list active/protected images, stale candidates older than the default 24h threshold, risk, estimated reclaim, and manual review commands without deleting anything." }, - { command: "gc plan|run|db-trace --confirm [--logs-keep-days N] [--include-browser-cache]", description: "One-time main-server disk relief for logs, journald, Docker build cache, allowlisted /tmp artifacts and explicit trace telemetry retention; plan is read-only and run requires --confirm." }, + { command: "gc plan|run|db-trace|policy [--confirm] [--logs-keep-days N] [--include-browser-cache]", description: "One-time main-server disk relief and low-risk anti-bloat policy for logs, journald, allowlisted /tmp artifacts and explicit trace telemetry retention; plan is read-only and run requires --confirm." }, { command: "server rebuild ", description: "Maintenance-only local Compose rebuild for reviewed main-server services; frontend standard release must use CI artifact plus deploy apply dev/prod artifact consumers." }, { command: "provider attach [--master-server URL] [--up] [--force] | provider triage [--observed-error text] [--observed-scope scope] [--microservice id ...] [--full|--raw]", description: "Generate the minimal external provider-gateway env/compose bundle or run the low-noise read-only provider health triage contract." }, { command: "ssh [operation args...]", description: "Open a Host SSH / WSL SSH maintenance session through the provider-gateway bridge; route syntax such as `G14:k3s` or `D601:win/c/test` only locates distributed targets." }, @@ -263,7 +263,7 @@ function providerHelp(): unknown { function gcHelp(): unknown { return { - command: "gc plan|run|db-trace", + command: "gc plan|run|db-trace|policy", output: "json", usage: [ "bun scripts/cli.ts gc plan", @@ -273,6 +273,8 @@ function gcHelp(): unknown { "bun scripts/cli.ts gc run --confirm --include-browser-cache", "bun scripts/cli.ts gc db-trace plan --before-date 2026-05-25", "bun scripts/cli.ts gc db-trace run --confirm --before-date 2026-05-25 --vacuum-full", + "bun scripts/cli.ts gc policy plan", + "bun scripts/cli.ts gc policy install", "bun scripts/cli.ts gc plan --full", ], description: "Plan or execute bounded one-time main-server disk relief for file logs, Docker json logs, systemd journal, Docker BuildKit cache, allowlisted /tmp artifacts and explicitly scoped database trace telemetry retention.", @@ -292,10 +294,12 @@ function gcHelp(): unknown { "--build-cache-all": "prune all Docker builder cache without an until filter", "--tmp-min-age-hours N": "delete allowlisted /tmp artifacts older than N hours; default 24", "--limit N": "number of candidates returned and executed by run when --full is not set; default 50", + "--result-limit N": "number of per-candidate run results returned when --full is not set; default 50", "--full|--raw": "return and run against all candidates rather than the default bounded page", "--include-browser-cache": "also remove repo-local .state/playwright-browsers cache", "db-trace --before-date YYYY-MM-DD": "plan or delete default trace telemetry event types before the date", "db-trace run --vacuum-full": "rewrite public.oa_events after deletion so df can reclaim disk; requires maintenance window", + "policy plan|install": "render or install journald caps and a daily file-log plus allowlisted /tmp low-risk gc systemd timer", "--no-file-logs|--no-docker-logs|--no-journal|--no-build-cache|--no-tmp|--no-db-summary": "disable one collector", }, reference: "docs/reference/cli.md", diff --git a/src/components/microservices/oa-event-flow/src/index.ts b/src/components/microservices/oa-event-flow/src/index.ts index 10c4dbee..9e4f1880 100644 --- a/src/components/microservices/oa-event-flow/src/index.ts +++ b/src/components/microservices/oa-event-flow/src/index.ts @@ -598,7 +598,7 @@ async function fetchTraceStats(executor: SqlExecutor, scopeId: string): Promise< return rows[0] === undefined ? null : statsRowToRecord(rows[0]); } -async function insertDerivedStatsEvent(executor: SqlExecutor, stats: TraceStatsRecord, sourceEvent: OaEventRecord): Promise { +function traceStatsEvent(stats: TraceStatsRecord, sourceEvent: OaEventRecord): OaEventRecord { const tags = ["stats", "trace", `service:${stats.serviceId}`, stats.scopeId]; if (typeof stats.taskId === "string" && stats.taskId.length > 0) addTag(tags, `task:${stats.taskId}`); if (Number(stats.attemptIndex) > 0) addTag(tags, `attempt:${Number(stats.attemptIndex)}`); @@ -611,7 +611,7 @@ async function insertDerivedStatsEvent(executor: SqlExecutor, stats: TraceStatsR attemptIndex: Number(stats.attemptIndex) > 0 ? Number(stats.attemptIndex) : null, stats, }; - const derived = normalizeEvent({ + const event = normalizeEvent({ eventId: `oa-event-flow:trace-stats-updated:${stats.scopeId}:${stats.statsRevision}`, type: "trace-stats-updated", sourceKind: "projection", @@ -623,13 +623,7 @@ async function insertDerivedStatsEvent(executor: SqlExecutor, stats: TraceStatsR tags, payload, }); - const rows = await executor` - INSERT INTO oa_events (event_id, type, source_kind, source_id, aggregate_type, aggregate_id, correlation_id, causation_id, tags, payload, created_at) - VALUES (${derived.eventId}, ${derived.type}, ${derived.sourceKind}, ${derived.sourceId}, ${derived.aggregateType}, ${derived.aggregateId}, ${derived.correlationId}, ${derived.causationId}, ${executor.json(derived.tags)}, ${executor.json(derived.payload)}, ${derived.createdAt}) - ON CONFLICT (event_id) DO NOTHING - RETURNING * - `; - return rows[0] === undefined ? null : rowToEvent(rows[0]); + return { ...event, sequence: sourceEvent.sequence, createdAt: sourceEvent.createdAt }; } async function applyTraceSnapshot(executor: SqlExecutor, event: OaEventRecord, scope: TraceScope): Promise { @@ -804,8 +798,7 @@ async function publishEvents(inputs: OaEventInput[]): Promise<{ inserted: OaEven } inserted.push(stored); for (const stats of await applyTraceProjection(tx, stored)) { - const statsEvent = await insertDerivedStatsEvent(tx, stats, stored); - if (statsEvent !== null) derived.push(statsEvent); + derived.push(traceStatsEvent(stats, stored)); } } const lastSequence = Math.max(0, ...inserted.map((event) => event.sequence), ...derived.map((event) => event.sequence));