diff --git a/.gitea/workflows/deploy-staging.yml b/.gitea/workflows/deploy-staging.yml index d5378f57..db6f873e 100644 --- a/.gitea/workflows/deploy-staging.yml +++ b/.gitea/workflows/deploy-staging.yml @@ -96,7 +96,19 @@ jobs: git init . git remote remove origin 2>/dev/null || true git remote add origin https://git.copse.top/root/Jyotisha.git - git fetch --no-tags origin main "$DEPLOY_SHA" + fetch_succeeded=false + for attempt in 1 2 3; do + if timeout 120 git fetch --no-tags origin main "$DEPLOY_SHA"; then + fetch_succeeded=true + break + fi + if [ "$attempt" -eq 3 ]; then + echo "trusted main fetch failed after $attempt bounded attempts" >&2 + exit 1 + fi + sleep $((attempt * 10)) + done + [[ "$fetch_succeeded" == true ]] git checkout --detach --force origin/main git merge-base --is-ancestor "$DEPLOY_SHA" HEAD || { echo "staging revision is not in trusted main history" >&2; exit 1; } diff --git a/.gitea/workflows/migrate-staging-database.yml b/.gitea/workflows/migrate-staging-database.yml index 0b4e750d..67f2f1c1 100644 --- a/.gitea/workflows/migrate-staging-database.yml +++ b/.gitea/workflows/migrate-staging-database.yml @@ -68,7 +68,19 @@ jobs: git init . git remote remove origin 2>/dev/null || true git remote add origin https://git.copse.top/root/Jyotisha.git - git fetch --no-tags origin main "$DEPLOY_SHA" + fetch_succeeded=false + for attempt in 1 2 3; do + if timeout 120 git fetch --no-tags origin main "$DEPLOY_SHA"; then + fetch_succeeded=true + break + fi + if [ "$attempt" -eq 3 ]; then + echo "trusted main fetch failed after $attempt bounded attempts" >&2 + exit 1 + fi + sleep $((attempt * 10)) + done + [[ "$fetch_succeeded" == true ]] git checkout --detach --force origin/main git merge-base --is-ancestor "$DEPLOY_SHA" HEAD || { echo "staging revision is not in trusted main history" >&2; exit 1; } diff --git a/docs/BUG_HISTORY.md b/docs/BUG_HISTORY.md index 5c7fa924..967278be 100644 --- a/docs/BUG_HISTORY.md +++ b/docs/BUG_HISTORY.md @@ -2223,4 +2223,20 @@ - 防复发:禁止 staging workflow 直接注入多行私钥或打印 decoded secret 变量;env owner 必须由部署树身份决定,root 受控脚本不得用 root 临时文件改变持久 env owner。任何凭据日志暴露先轮换/撤销/清理,再修代码和重跑。 - 相关记录:BUG-124、BUG-127、ERR-092、ERR-093、ERR-094 - 复发自:无 -- 修复版本:待安全修复 PR 与 staging 验收 +- 修复版本:`f7a615a5bf11ed95b3a6c7e6d28dfe8150a825ef`;staging migration/deploy 与安全验收完成 + +## BUG-129 | staging trusted-main checkout 无界 fetch 导致自动部署长期占用 mutation queue + +- 状态:investigating +- 首次发现:2026-08-06 +- 最近更新:2026-08-06 +- 影响面:Gitea staging deploy/migration 控制器的 trusted-main checkout;production 与 staging 应用数据面未受影响。 +- 用户现象:exact-SHA quality gate run `1473` 成功后,自动 deploy run `1474` 超过通常部署时长仍停在 `git fetch --no-tags origin main "$DEPLOY_SHA"`;日志在远端对象压缩阶段停止推进,staging 公网与 `.state/deployed-revision` 均保持上一健康 SHA,SSH/远端 mutation 尚未开始。 +- 触发条件:Gitea runner 在空仓库中抓取 reviewed `main` 和目标 SHA 时,Git HTTP 传输停滞;checkout step 没有命令级 timeout/retry,只依赖 30 分钟 job 总超时。 +- 根因:发布控制器对镜像拉取有 bounded retry,却对 trusted-main Git fetch 采用无界单次调用;短暂远端/runner 传输停滞会长期占用 `staging-mutation` queue,并推迟后续受控重试。 +- 修复:Gitea deploy 与 migration 的 trusted-main fetch 改为最多 3 次、每次 120 秒的 bounded retry,重试间隔递增;耗尽后明确 fail closed。仍只 checkout `origin/main`,仍要求目标 SHA 是 reviewed main ancestor,不改变 exact-SHA artifact、forward-only 或 manual rollback 边界。 +- 验证:待本地 workflow contract、Gitea PR quality gate、原 run `1474` 终止以及修复后 exact-SHA staging deploy 完成;未完成前不得标记 resolved。 +- 防复发:所有 release-controller 网络调用必须同时具备命令级上限和失败闭合;不得仅依赖 job 总 timeout。回归测试必须同时覆盖 deploy 和 migration 的 attempt 数、单次 timeout、最终错误和 ancestry check。 +- 相关记录:BUG-128、ERR-094、ERR-095 +- 复发自:无 +- 修复版本:待控制面修复 PR 与 staging 验收 diff --git a/docs/research/pre_work_error_ledger.md b/docs/research/pre_work_error_ledger.md index 92620164..e67b52cc 100644 --- a/docs/research/pre_work_error_ledger.md +++ b/docs/research/pre_work_error_ledger.md @@ -145,6 +145,12 @@ A failed exact-SHA staging deploy displayed the multiline staging SSH private ke Prevention: store `STAGING_SSH_PRIVATE_KEY` only as one unwrapped base64 line; workflows decode it into a mode-`0600` temporary key, validate it with `ssh-keygen`, and delete the temporary directory on every exit. Contract tests must reject direct multiline `SSH_PRIVATE_KEY` injection or `printf` of a decoded secret variable. A leaked staging key must be rotated and revoked before any rerun; production keys remain a separate boundary and were not involved in this incident. +## ERR-095 | Gitea trusted-main fetch can stall until the whole deploy job times out | investigating 2026-08-06 + +After exact-SHA staging gate `1473` succeeded, automatic deploy `1474` stopped making progress in the empty-repository `git fetch --no-tags origin main "$DEPLOY_SHA"` step before any SSH or staging mutation. Public and state SHAs remained on the previous healthy release. The checkout had no command-level bound, so the 30-minute job timeout was the only escape and the shared mutation queue remained occupied. + +Prevention: wrap the Gitea deploy and migration trusted-main fetch in three 120-second bounded attempts with incremental delay and explicit fail-closed exhaustion. Preserve the reviewed-main ancestry check, exact-SHA gate artifact, forward-only deploy policy, and shared mutation queue. Never treat an in-progress or timed-out fetch as a deployment result. + ## Fragment Sweep Command Set ## ERR-086 | Steve Jobs jyotishganit artifacts used non-San-Francisco coordinates | mitigated 2026-07-21 diff --git a/frontend/tests/staging-backend-workflows.test.ts b/frontend/tests/staging-backend-workflows.test.ts index cc6e9845..c34a9500 100644 --- a/frontend/tests/staging-backend-workflows.test.ts +++ b/frontend/tests/staging-backend-workflows.test.ts @@ -488,7 +488,10 @@ test("Gitea deploy and migration consume the exact successful gate artifact", () assert.match(workflow, /actions\/artifacts\/\$artifact_id\/zip/); assert.match(workflow, /node frontend\/scripts\/staging-image-manifest\.mjs/); assert.match(workflow, /name: Checkout trusted main controller/); - assert.match(workflow, /git fetch --no-tags origin main "\$DEPLOY_SHA"/); + assert.match(workflow, /for attempt in 1 2 3/); + assert.match(workflow, /timeout 120 git fetch --no-tags origin main "\$DEPLOY_SHA"/); + assert.match(workflow, /trusted main fetch failed after \$attempt bounded attempts/); + assert.match(workflow, /\[\[ "\$fetch_succeeded" == true \]\]/); assert.match(workflow, /git checkout --detach --force origin\/main/); assert.match(workflow, /git merge-base --is-ancestor "\$DEPLOY_SHA" HEAD/); assert.doesNotMatch(workflow, /docker manifest inspect/);