@fitlab-ai/agent-infra 0.11.15 → 0.12.1

package/templates/.agents/skills/archive-tasks/SKILL.zh-CN.md

@@ -7,16 +7,16 @@ description: >
 
 # 归档已完成任务
 
-将 `.agents/workspace/completed/` 中的已完成任务归档到 `.agents/workspace/archive/YYYY/MM/DD/TASK-xxx/local/`，并重建三级归档索引。TASK 本地材料位于 `local/`，含按路径排序的 `contents.sha256`；TASK 根目录不存放普通文件。
-- 根 manifest：`.agents/workspace/archive/manifest.md`
-- 年 manifest：`.agents/workspace/archive/YYYY/manifest.md`
-- 月 manifest：`.agents/workspace/archive/YYYY/MM/manifest.md`
+将 `<task-workspace>/completed/` 中的已完成任务归档到 `<task-workspace>/archive/YYYY/MM/DD/TASK-xxx/local/`，并重建三级归档索引。TASK 本地材料位于 `local/`，含按路径排序的 `contents.sha256`；TASK 根目录不存放普通文件。
+- 根 manifest：`<task-workspace>/archive/manifest.md`
+- 年 manifest：`<task-workspace>/archive/YYYY/manifest.md`
+- 月 manifest：`<task-workspace>/archive/YYYY/MM/manifest.md`
 
 ## 执行流程
 
 ### 1. 验证环境
 
-确认 `.agents/workspace/completed/` 存在，并根据用户输入选择以下四种调用方式之一：
+确认 `<task-workspace>/completed/` 存在，并根据用户输入选择以下四种调用方式之一：
 - 无参数：归档全部已完成任务
 - `--days N`：保留最近 `N` 天，仅归档更早的任务
 - `--before YYYY-MM-DD`：仅归档指定日期之前的任务

package/templates/.agents/skills/archive-tasks/scripts/archive-tasks.sh

@@ -4,7 +4,15 @@ set -e
 
 SCRIPT_DIR=$(CDPATH= cd "$(dirname "$0")" && pwd)
 REPO_ROOT=$(CDPATH= cd "$SCRIPT_DIR/../../../.." && pwd)
-WORKSPACE_ROOT="$REPO_ROOT/.agents/workspace"
+if [ -f "$REPO_ROOT/bin/internal-cli.sh" ]; then
+  WORKSPACE_RESULT=$(CDPATH= cd "$REPO_ROOT" && sh "$REPO_ROOT/bin/internal-cli.sh" task-workspace resolve --boundary host)
+elif command -v agent-infra-internal >/dev/null 2>&1; then
+  WORKSPACE_RESULT=$(CDPATH= cd "$REPO_ROOT" && agent-infra-internal task-workspace resolve --boundary host)
+else
+  printf 'archive-tasks: agent-infra-internal task-workspace resolver is unavailable\n' >&2
+  exit 1
+fi
+WORKSPACE_ROOT=$(printf '%s' "$WORKSPACE_RESULT" | node -e 'let input="";process.stdin.setEncoding("utf8");process.stdin.on("data",chunk=>input+=chunk);process.stdin.on("end",()=>{const result=JSON.parse(input);if(result.status!=="resolved"||typeof result.root!=="string")process.exit(1);process.stdout.write(result.root);});')
 COMPLETED_DIR="$WORKSPACE_ROOT/completed"
 ARCHIVE_DIR="$WORKSPACE_ROOT/archive"
 MANIFEST_PATH="$ARCHIVE_DIR/manifest.md"
@@ -586,4 +594,4 @@ echo
 echo "Summary:"
 printf -- '- Archived: %s\n' "$archived_count"
 printf -- '- Skipped: %s\n' "$skipped_count"
-printf -- '- Manifest: %s\n' ".agents/workspace/archive/manifest.md"
+printf -- '- Manifest: %s\n' "$ARCHIVE_DIR/manifest.md"

package/templates/.agents/skills/block-task/SKILL.en.md

@@ -38,7 +38,7 @@ After prerequisites pass, Step 3 declares one lifecycle intent that atomically w
 
 ### 1. Verify Task Exists
 
-Check that the task exists in `.agents/workspace/active/{task-id}/`.
+Check that the task exists in `<task-workspace>/active/{task-id}/`.
 
 Note: `{task-id}` format is `TASK-{yyyyMMdd-HHmmss}`, e.g. `TASK-20260306-143022`
 
@@ -68,7 +68,7 @@ Confirm `targetState=blocked`, the target path, and the committed short-id effec
 ### 5. Preserve Recovery Identity
 
 ```bash
-ls .agents/workspace/blocked/{task-id}/task.md
+ls <task-workspace>/blocked/{task-id}/task.md
 ```
 
 ### 6. Sync to Issue (Optional)
@@ -111,7 +111,7 @@ Task {task-id} marked as blocked.
 
 Blocking reason: {summary}
 Required to unblock: {what's needed}
-Archived to: .agents/workspace/blocked/{task-id}/
+Archived to: <task-workspace>/blocked/{task-id}/
 
 Optional: clean up this task's sandbox
 (The task is blocked and moved to blocked/; task-bound sandboxes are protected from automatic `ai sandbox rm --unbound` cleanup. If cleanup is necessary, manually verify the container, control manifest, and worktree identity first.)
@@ -129,7 +129,7 @@ Next step - check task status after unblocking:
 
 - [ ] Analyzed and documented the blocking reason
 - [ ] Updated task.md with blocked status and blocking information
-- [ ] Moved task directory to `.agents/workspace/blocked/`
+- [ ] Moved task directory to `<task-workspace>/blocked/`
 - [ ] Verified move succeeded
 - [ ] Informed user how to unblock
 

package/templates/.agents/skills/block-task/SKILL.zh-CN.md

@@ -37,7 +37,7 @@ description: >
 ## 执行步骤
 ### 1. 验证任务存在
 
-检查任务是否存在于 `.agents/workspace/active/{task-id}/`。
+检查任务是否存在于 `<task-workspace>/active/{task-id}/`。
 
 注意：`{task-id}` 格式为 `TASK-{yyyyMMdd-HHmmss}`，例如 `TASK-20260306-143022`
 
@@ -62,10 +62,10 @@ agent-infra-internal task-lifecycle {task-id} block --agent {standard-agent-toke
 
 ### 4. 验证本地终态
 
-确认结构化结果的 `targetState=blocked`、目标路径为 `.agents/workspace/blocked/{task-id}`、短号效果已提交，并检查：
+确认结构化结果的 `targetState=blocked`、目标路径为 `<task-workspace>/blocked/{task-id}`、短号效果已提交，并检查：
 
 ```bash
-ls .agents/workspace/blocked/{task-id}/task.md
+ls <task-workspace>/blocked/{task-id}/task.md
 ```
 
 ### 5. 保留恢复身份
@@ -110,7 +110,7 @@ agent-infra-internal task-verify {task-id} block-task.completed --format text
 
 阻塞原因：{摘要}
 解除阻塞所需：{需要什么}
-归档路径：.agents/workspace/blocked/{task-id}/
+归档路径：<task-workspace>/blocked/{task-id}/
 
 可选：清理本任务的沙箱
 （任务已阻塞并移到 blocked/，task-bound 沙箱受保护，不会被 `ai sandbox rm --unbound` 自动删除；如确需清理，请先人工核对容器、控制清单和工作树身份。）
@@ -128,7 +128,7 @@ agent-infra-internal task-verify {task-id} block-task.completed --format text
 
 - [ ] 分析并记录了阻塞原因
 - [ ] 更新了 task.md 的阻塞状态和阻塞信息
-- [ ] 将任务目录移动到 `.agents/workspace/blocked/`
+- [ ] 将任务目录移动到 `<task-workspace>/blocked/`
 - [ ] 验证了移动成功
 - [ ] 告知了用户如何解除阻塞
 

package/templates/.agents/skills/block-task/config/verify.json

@@ -18,7 +18,6 @@
       "require_blocked_at": true
     },
     "activity-log": {
-      "expected_action_pattern": "(Block Task|Blocked)"
     },
     "platform-sync": {
       "when": "platform_issue_identity_exists"

package/templates/.agents/skills/cancel-task/SKILL.en.md

@@ -33,9 +33,9 @@ After prerequisites pass, Step 3 declares one lifecycle intent that atomically c
 ### 1. Verify Task Exists
 
 Check these directories in order:
-- `.agents/workspace/active/{task-id}/`
-- `.agents/workspace/blocked/{task-id}/`
-- `.agents/workspace/completed/{task-id}/`
+- `<task-workspace>/active/{task-id}/`
+- `<task-workspace>/blocked/{task-id}/`
+- `<task-workspace>/completed/{task-id}/`
 
 Handling rules:
 - If found in `active/` or `blocked/`: continue
@@ -69,7 +69,7 @@ Confirm `targetState=completed`, terminal fields, and the short-id effect from t
 ### 5. Verify the Move
 
 ```bash
-ls .agents/workspace/completed/{task-id}/task.md
+ls <task-workspace>/completed/{task-id}/task.md
 ```
 
 Confirm the task directory was moved successfully.
@@ -83,7 +83,7 @@ If a valid `platform_issue_identity` exists, require `applied` / `no-op` without
 - Write the cancellation body to a temporary file and run `agent-infra-internal platform-comment sync {task-id} --kind cancel --body-file {path} --agent {standard-agent-token}`
 - Run `agent-infra-internal platform-comment sync {task-id} --kind task --agent {standard-agent-token}`
 
-The cancellation comment must include at least:
+The cancellation comment JSON fields are `taskId`, `title`, `outcome:"cancelled"`, `reason`, `cancelledAt`, and `lastCompletedArtifact`, sourced from task identity, task.md, the recorded cancellation reason/time, and the current artifact registry (`null` when no completed artifact exists). It must include at least:
 - the cancellation reason
 - the selected `status:` label
 
@@ -120,7 +120,7 @@ Task {task-id} cancelled; task directory moved to completed/.
 
 Cancellation reason: {reason}
 Status label: {status-label or skipped}
-Target path: .agents/workspace/completed/{task-id}/
+Target path: <task-workspace>/completed/{task-id}/
 
 Optional: clean up this task's sandbox
 (The task is completed and archived; the sandbox container and per-branch config directory are not reclaimed automatically. Run this if you no longer need them:)
@@ -136,7 +136,7 @@ Next step - inspect the moved task:
 ## Completion Checklist
 
 - [ ] Recorded the cancellation reason and updated task.md
-- [ ] Moved the task directory into `.agents/workspace/completed/`
+- [ ] Moved the task directory into `<task-workspace>/completed/`
 - [ ] Completed Issue sync when an Issue exists
 - [ ] Ran and passed the verification gate
 - [ ] Showed the full next-step command set to the user

package/templates/.agents/skills/cancel-task/SKILL.zh-CN.md

@@ -32,9 +32,9 @@ description: >
 ### 1. 验证任务存在
 
 依次检查以下目录：
-- `.agents/workspace/active/{task-id}/`
-- `.agents/workspace/blocked/{task-id}/`
-- `.agents/workspace/completed/{task-id}/`
+- `<task-workspace>/active/{task-id}/`
+- `<task-workspace>/blocked/{task-id}/`
+- `<task-workspace>/completed/{task-id}/`
 
 处理规则：
 - 如果在 `active/` 或 `blocked/` 中找到：继续
@@ -68,7 +68,7 @@ agent-infra-internal task-lifecycle {task-id} cancel --agent {standard-agent-tok
 ### 5. 验证转移
 
 ```bash
-ls .agents/workspace/completed/{task-id}/task.md
+ls <task-workspace>/completed/{task-id}/task.md
 ```
 
 确认任务目录已成功移动。
@@ -82,7 +82,7 @@ ls .agents/workspace/completed/{task-id}/task.md
 - 将取消正文写入临时文件，调用 `agent-infra-internal platform-comment sync {task-id} --kind cancel --body-file {path} --agent {standard-agent-token}`
 - 调用 `agent-infra-internal platform-comment sync {task-id} --kind task --agent {standard-agent-token}`
 
-取消评论至少包含：
+取消评论 JSON 字段为 `taskId`、`title`、`outcome:"cancelled"`、`reason`、`cancelledAt`、`lastCompletedArtifact`，值来自任务身份、task.md、已记录取消原因与时间和当前 artifact registry；无已完成产物时用 `null`。取消评论至少包含：
 - 取消原因
 - 选定的 `status:` label
 
@@ -117,7 +117,7 @@ agent-infra-internal task-verify {task-id} cancel-task.completed --format text
 
 取消原因：{reason}
 状态标签：{status-label 或 skipped}
-目标路径：.agents/workspace/completed/{task-id}/
+目标路径：<task-workspace>/completed/{task-id}/
 
 可选：清理本任务的沙箱
 （任务已完成并归档，沙箱容器和 per-branch 配置目录不会自动回收。如果不再需要可执行：）
@@ -133,7 +133,7 @@ ai sandbox rm {task-id}
 ## 完成检查清单
 
 - [ ] 已记录取消原因并更新 task.md
-- [ ] 已将任务目录移动到 `.agents/workspace/completed/`
+- [ ] 已将任务目录移动到 `<task-workspace>/completed/`
 - [ ] 已在存在 Issue 时完成 Issue 同步
 - [ ] 已运行 gate 校验并通过
 - [ ] 已通过统一 helper 渲染已选场景的下一步命令

package/templates/.agents/skills/cancel-task/config/verify.json

@@ -19,7 +19,6 @@
       "require_cancelled_at": true
     },
     "activity-log": {
-      "expected_action_pattern": "(Cancel Task|Cancelled)"
     },
     "platform-sync": {
       "when": "platform_issue_identity_exists"

package/templates/.agents/skills/code-task/SKILL.en.md

@@ -126,7 +126,7 @@ agent-infra-internal task-artifact {task-id} init --family code --artifact {code
 
 The skeleton contains identity metadata, stable section markers, and required headings only; real implementation and verification content is required before the completion gate can pass. On a preflight or finalization structural error, follow `.agents/rules/local-artifact-repair.md` to correct the formal artifact directly and rerun the same entry point; current structure, qualification, and summary facts are the only gate.
 
-Create `.agents/workspace/active/{task-id}/{code-artifact}`.
+Create `<task-workspace>/active/{task-id}/{code-artifact}`.
 
 > Read `reference/report-template.md` before writing the report.
 

package/templates/.agents/skills/code-task/SKILL.zh-CN.md

@@ -75,7 +75,7 @@ agent-infra-internal task-snapshot {task-id} --format text
 ### 1. 验证前置条件
 
 先检查：
-- `.agents/workspace/active/{task-id}/task.md`
+- `<task-workspace>/active/{task-id}/task.md`
 
 如果缺少任务文件，立即停止。生命周期输入由步骤 4 的核心查询按已选路径验证；技能不得预先固定要求方案产物。
 
@@ -165,7 +165,7 @@ agent-infra-internal task-artifact {task-id} init --family code --artifact {code
 
 骨架只包含身份元数据、稳定 section marker 和必需标题；必须填入真实实现与验证内容后才能通过完成门禁。preflight 或 finalizer 返回结构错误时，按 `.agents/rules/local-artifact-repair.md` 直接修正正式产物并重跑原入口；当前结构、资格和摘要事实是唯一门禁。
 
-创建 `.agents/workspace/active/{task-id}/{code-artifact}`。
+创建 `<task-workspace>/active/{task-id}/{code-artifact}`。
 
 > 报告结构、必填章节和完整模板见 `reference/report-template.md`。写报告前先读取 `reference/report-template.md`。
 
@@ -207,7 +207,7 @@ echo "$finalizer"
 
 ### 11. 更新任务状态
 
-更新 `.agents/workspace/active/{task-id}/task.md`：
+更新 `<task-workspace>/active/{task-id}/task.md`：
 - 审查 `## 需求` 段落，仅把本轮已由代码实现且有测试通过支撑的条目从 `- [ ]` 勾为 `- [x]`
 - 产物链接、阶段与完成日志由 completed 事件统一登记
 - 完成业务内容更新后声明完成事件：

package/templates/.agents/skills/code-task/config/verify.en.json

@@ -21,7 +21,6 @@
     },
     "implementation-input": {},
     "activity-log": {
-      "expected_action_pattern": "(Code Task|Code) \\(Round \\d+(?:(?:, fix for review-code(?:-r\\d+)?\\.md)|(?:, decision II-[1-9]\\d*))?\\)"
     },
     "review-ledger": {
       "stage_scope": [

package/templates/.agents/skills/code-task/config/verify.zh-CN.json

@@ -21,7 +21,6 @@
     },
     "implementation-input": {},
     "activity-log": {
-      "expected_action_pattern": "(Code Task|Code) \\(Round \\d+(?:(?:, fix for review-code(?:-r\\d+)?\\.md)|(?:, decision II-[1-9]\\d*))?\\)"
     },
     "review-ledger": {
       "stage_scope": [

package/templates/.agents/skills/code-task/reference/output-template.en.md

@@ -13,7 +13,7 @@ Summary:
 - All tests passed: {yes/no}
 
 Output files:
-- Code report: .agents/workspace/active/{task-id}/{code-artifact}
+- Code report: <task-workspace>/active/{task-id}/{code-artifact}
 
 Next step - code review:
 {next-step-commands}

package/templates/.agents/skills/code-task/reference/output-template.zh-CN.md

@@ -13,7 +13,7 @@
 - 所有测试通过：{是/否}
 
 产出文件：
-- 实现报告：.agents/workspace/active/{task-id}/{code-artifact}
+- 实现报告：<task-workspace>/active/{task-id}/{code-artifact}
 
 下一步 - 代码审查：
 {next-step-commands}

package/templates/.agents/skills/commit/SKILL.en.md

@@ -71,7 +71,7 @@ Example:
 }
 ```
 
-Taskless direct mode omits `taskRef`; direct task-bound commits use push delivery. The core owns repository/worktree mutation locking, task locking when bound, path and sensitive-file checks, staged scope, HEAD/tree, branch/ref, commit, push, protected-branch policy, warnings, and idempotency.
+Taskless direct mode omits `taskRef`; direct task-bound commits use push delivery. Both modes execute serially at the caller boundary; the core still owns path and sensitive-file checks, staged scope, HEAD/tree, branch/ref, commit, push, protected-branch policy, warnings, and idempotency.
 
 - Create at most one local commit for explicit changes.
 - If there are no changes but HEAD is ahead and delivery is requested, perform push-only and do not create an empty commit.

package/templates/.agents/skills/commit/SKILL.zh-CN.md

@@ -71,7 +71,7 @@ agent-infra-internal git-workflow commit --input {commit-operation.json}
 }
 ```
 
-taskless direct 省略 `taskRef`；direct task-bound commit 使用 push delivery。core 统一负责 repository/worktree mutation lock、task lock（仅 task-bound）、路径和敏感文件、staged scope、HEAD/tree、branch/ref、commit、push、保护分支、warning 和幂等校验。
+taskless direct 省略 `taskRef`；direct task-bound commit 使用 push delivery。两种模式都按调用方串行执行；core 仍负责路径和敏感文件、staged scope、HEAD/tree、branch/ref、commit、push、保护分支、warning 和幂等校验。
 
 - 有明确修改时最多创建一个本地 commit。
 - 无修改但需要交付本地领先的 HEAD 时只执行 push-only，不创建空 commit。

package/templates/.agents/skills/commit/config/verify.json

@@ -15,7 +15,6 @@
       ]
     },
     "activity-log": {
-      "expected_action_pattern": "Commit"
     },
     "platform-sync": {
       "when": "pr_fact_bound"

package/templates/.agents/skills/commit/reference/commit-orchestration.en.md

@@ -4,12 +4,12 @@ Commit, push, result mapping, and task finalization use one `commit-operation.ex
 
 ## Entry modes
 
-- `mode=direct`: explicit user invocation is the authorization. Task-bound direct may read task facts but does not require a delegation receipt; taskless direct is allowed only for `TASK_CONTEXT_NOT_FOUND` and skips task facts, review, task lock, checkpoint, and task.md finalization.
+- `mode=direct`: explicit user invocation is the authorization. Task-bound direct may read task facts but does not require a delegation receipt; taskless direct is allowed only for `TASK_CONTEXT_NOT_FOUND` and skips task facts, review, checkpoint, and task.md finalization.
 - `mode=orchestrated` is removed: standalone commit is no longer a lifecycle delegation stage. This mode returns `ORCHESTRATED_COMMIT_REMOVED` without writing Git; the code stage closes through a local checkpoint.
 
 ## Shared order
 
-1. Acquire the repository/worktree mutation lock; task-bound execution also acquires the task lock.
+1. Direct commits execute serially at the caller boundary.
 2. Validate the repository, current branch, explicit paths, sensitive paths, staged scope, expected HEAD/tree, remote, and full heads ref.
 3. Validate direct-mode authorization.
 4. Create at most one local commit; with no changes, allow push-only and never create an empty commit.

package/templates/.agents/skills/commit/reference/commit-orchestration.zh-CN.md

@@ -4,12 +4,12 @@ commit、push、结果映射和任务收尾使用同一个 `commit-operation.exe
 
 ## 入口模式
 
-- `mode=direct`：用户显式调用授权。task-bound direct 可读取 task facts，但不要求 delegation receipt；taskless direct 只在 `TASK_CONTEXT_NOT_FOUND` 时允许，并跳过 task facts、review、task lock、checkpoint 和 task.md 收尾。
+- `mode=direct`：用户显式调用授权。task-bound direct 可读取 task facts，但不要求 delegation receipt；taskless direct 只在 `TASK_CONTEXT_NOT_FOUND` 时允许，并跳过 task facts、review、checkpoint 和 task.md 收尾。
 - `mode=orchestrated` 已移除：独立 commit 不再是生命周期 delegation stage；调用该模式返回 `ORCHESTRATED_COMMIT_REMOVED`，不写 Git。生命周期 code 阶段完成后由 local checkpoint 直接收口。
 
 ## 共享执行顺序
 
-1. 获取 repository/worktree mutation lock；task-bound 额外获取 task lock。
+1. direct commit 按调用方串行执行。
 2. 验证 repository、当前 branch、明确 paths、敏感路径、staged scope、expected HEAD/tree、remote 和 full heads ref。
 3. 完成 direct 模式授权校验。
 4. 最多创建一个本地 commit；无修改时只允许 push-only，不创建空 commit。

package/templates/.agents/skills/commit/reference/pr-summary-sync.en.md

@@ -3,7 +3,7 @@
 Run only when `{task-id}` is valid and task.md has a `bound/verified` `pr_delivery_fact`.
 
 1. Run `agent-infra-internal platform-pr summary-context {task-id}` to obtain canonical inputs and report status; rebuild a stale/missing sidecar through the `change-report` flow for the current head.
-2. Generate the plain summary body per `.agents/rules/pr-sync.md`, with exactly one `<!-- canonical-pr-change-report -->` placeholder, and write it to a temporary file.
-3. Run `agent-infra-internal platform-pr summary-sync {task-id} --agent {standard-agent-token} --body-file {summary-body-file} --change-report-file .agents/workspace/active/{task-id}/pr-change-report.json --result no_op`. The commit path only synchronizes an existing PR summary and neither creates nor reuses a PR, so `no_op` explicitly represents the unchanged PR identity.
+2. Generate the complete PR summary JSON payload per `.agents/rules/pr-sync.md` and write it to a temporary file.
+3. Run `agent-infra-internal platform-pr summary-sync {task-id} --agent {standard-agent-token} --body-file {summary-body-file} --change-report-file <task-workspace>/active/{task-id}/pr-change-report.json --result no_op`. The commit path only synchronizes an existing PR summary and neither creates nor reuses a PR, so `no_op` explicitly represents the unchanged PR identity.
 
 Failure records a warning but never blocks or rolls back the completed commit. `no-op` maps to `summary skipped (no diff)`.

package/templates/.agents/skills/commit/reference/pr-summary-sync.zh-CN.md

@@ -3,7 +3,7 @@
 仅当 `{task-id}` 有效且 `task.md` 存在 `bound/verified` 的 `pr_delivery_fact` 时执行；否则跳过。
 
 1. 调用 `agent-infra-internal platform-pr summary-context {task-id}` 获取 canonical 聚合输入和报告状态；sidecar stale/missing 时先按 `change-report` 流程重建当前 head 报告。
-2. 按 `.agents/rules/pr-sync.md` 生成只含一次 `<!-- canonical-pr-change-report -->` 的纯摘要正文并写入临时文件。
-3. 调用 `agent-infra-internal platform-pr summary-sync {task-id} --agent {standard-agent-token} --body-file {summary-body-file} --change-report-file .agents/workspace/active/{task-id}/pr-change-report.json --result no_op`。commit 路径只同步已有 PR 摘要，不创建或复用 PR，因此固定使用 `no_op` 表示 PR 身份未变化。
+2. 按 `.agents/rules/pr-sync.md` 生成完整 PR 摘要 JSON payload 并写入临时文件；字段和零值状态由内容合同规定。
+3. 调用 `agent-infra-internal platform-pr summary-sync {task-id} --agent {standard-agent-token} --body-file {summary-body-file} --change-report-file <task-workspace>/active/{task-id}/pr-change-report.json --result no_op`。commit 路径只同步已有 PR 摘要，不创建或复用 PR，因此固定使用 `no_op` 表示 PR 身份未变化。
 
 同步失败只记录 warning，不阻塞或回滚已经完成的 commit。`no-op` 回传 `summary skipped (no diff)`。

package/templates/.agents/skills/complete-manual-validation/SKILL.en.md

@@ -59,7 +59,7 @@ complete-manual-validation [--task <ref> | -t <ref>] [{pr-ref}] {verification-su
 ### 2. Verify Prerequisites
 
 Check:
-- `.agents/workspace/active/{task-id}/task.md`
+- `<task-workspace>/active/{task-id}/task.md`
 - a valid PR: prefer explicit `{pr-ref}`, otherwise read verified `pr_delivery_fact.identity.number` from task.md frontmatter
 
 Stop if the task is missing, the validation summary is missing, or no valid PR can be resolved.
@@ -96,7 +96,7 @@ Follow `reference/summary-update.md` to validate the PR binding, obtain canonica
 ```bash
 agent-infra-internal manual-validation transaction {task-id} \
   --artifact {manual-validation-artifact} \
-  --summary-file {summary-body-file} --change-report-file .agents/workspace/active/{task-id}/pr-change-report.json \
+  --summary-file {summary-body-file} --change-report-file <task-workspace>/active/{task-id}/pr-change-report.json \
   --agent {standard-agent-token} --result no_op
 ```
 

package/templates/.agents/skills/complete-manual-validation/SKILL.zh-CN.md

@@ -59,7 +59,7 @@ complete-manual-validation [--task <ref> | -t <ref>] [{pr-ref}] {verification-su
 ### 2. 验证前置条件
 
 检查：
-- `.agents/workspace/active/{task-id}/task.md`
+- `<task-workspace>/active/{task-id}/task.md`
 - 有效 PR：优先使用显式 `{pr-ref}`，否则读取 task.md frontmatter 的 verified `pr_delivery_fact.identity.number`
 
 如果任务不存在、验证说明缺失，或无法解析有效 PR，立即停止。
@@ -96,7 +96,7 @@ prepare 必须先幂等登记 `manual-validation.started`，再写入 prepared t
 ```bash
 agent-infra-internal manual-validation transaction {task-id} \
   --artifact {manual-validation-artifact} \
-  --summary-file {summary-body-file} --change-report-file .agents/workspace/active/{task-id}/pr-change-report.json \
+  --summary-file {summary-body-file} --change-report-file <task-workspace>/active/{task-id}/pr-change-report.json \
   --agent {standard-agent-token} --result no_op
 ```
 

package/templates/.agents/skills/complete-manual-validation/config/verify.en.json

@@ -28,7 +28,6 @@
       ]
     },
     "activity-log": {
-      "expected_action_pattern": "Complete Manual Validation"
     },
     "review-ledger": {
       "stage_scope": [

package/templates/.agents/skills/complete-manual-validation/config/verify.zh-CN.json

@@ -28,7 +28,6 @@
       ]
     },
     "activity-log": {
-      "expected_action_pattern": "Complete Manual Validation"
     },
     "review-ledger": {
       "stage_scope": [

package/templates/.agents/skills/complete-manual-validation/reference/summary-update.en.md

@@ -4,7 +4,7 @@ Run only for a valid `{task-id}` whose task.md binds a verified `pr_delivery_fac
 
 Follow `.agents/rules/pr-sync.md` for the shared summary structure and failure semantics.
 
-1. Run `agent-infra-internal platform-pr summary-context {task-id}` to obtain the canonical summary body; the maintainer's PR validation comment and validation summary are the human-validation authority.
+1. Run `agent-infra-internal platform-pr summary-context {task-id}` to obtain canonical summary facts. `--summary-file` uses the complete PR summary JSON payload; the maintainer's PR validation comment and validation summary are the human-validation authority.
 2. Before creating the canonical `manual-validation*` artifact, call the transaction coordinator in prepare mode to record `started` before writing the prepared transaction:
 
 ```bash
@@ -13,13 +13,13 @@ agent-infra-internal manual-validation transaction {task-id} --prepare \
   --summary-file {summary-body-file} --agent {standard-agent-token}
 ```
 
-3. After prepare succeeds, write the canonical `manual-validation*` artifact, write the pending plain body with exactly one `<!-- canonical-pr-change-report -->` placeholder to a temporary file, and run the transaction coordinator:
+3. After prepare succeeds, write the canonical `manual-validation*` artifact, set the JSON payload's `manualValidation.state` to `pending` with a non-empty explanation, and run the transaction coordinator:
 
 ```bash
 agent-infra-internal manual-validation transaction {task-id} \
   --artifact {manual-validation-artifact} \
   --summary-file {summary-body-file} \
-  --change-report-file .agents/workspace/active/{task-id}/pr-change-report.json \
+  --change-report-file <task-workspace>/active/{task-id}/pr-change-report.json \
   --agent {standard-agent-token} --result no_op
 ```
 

package/templates/.agents/skills/complete-manual-validation/reference/summary-update.zh-CN.md

@@ -4,7 +4,7 @@
 
 摘要结构与失败语义统一遵循 `.agents/rules/pr-sync.md`。
 
-1. 调用 `agent-infra-internal platform-pr summary-context {task-id}`，取得 canonical 摘要正文；维护者提供的 PR 人工验证留言和验证说明作为完成人工校验依据。
+1. 调用 `agent-infra-internal platform-pr summary-context {task-id}`，取得 canonical 摘要事实；`--summary-file` 使用完整 PR 摘要 JSON payload，维护者提供的 PR 人工验证留言和验证说明作为完成人工校验依据。
 2. 在创建 canonical `manual-validation*` artifact 前，调用 transaction coordinator 的 prepare 模式，先登记 started，再写 prepared transaction：
 
 ```bash
@@ -13,13 +13,13 @@ agent-infra-internal manual-validation transaction {task-id} --prepare \
   --summary-file {summary-body-file} --agent {standard-agent-token}
 ```
 
-3. prepare 成功后写入 canonical `manual-validation*` artifact，并把只含一次 `<!-- canonical-pr-change-report -->` 的 pending 正文写入临时文件，调用 transaction coordinator：
+3. prepare 成功后写入 canonical `manual-validation*` artifact，并将 JSON payload 中 `manualValidation` 设置为 `pending`、提供非空说明后写入临时文件，调用 transaction coordinator：
 
 ```bash
 agent-infra-internal manual-validation transaction {task-id} \
   --artifact {manual-validation-artifact} \
   --summary-file {summary-body-file} \
-  --change-report-file .agents/workspace/active/{task-id}/pr-change-report.json \
+  --change-report-file <task-workspace>/active/{task-id}/pr-change-report.json \
   --agent {standard-agent-token} --result no_op
 ```
 

package/templates/.agents/skills/complete-task/SKILL.en.md

@@ -18,8 +18,7 @@ Host finalization uses receipt v4 with an immutable `receiptId`, monotonic `revi
 
 Before generating a completion report or synchronized content, read `.agents/rules/evidence-reporting.md`. Successful checks record the command, scope, status or structured result, actual result, and uncovered parts; failures, blocking conditions, or disputes retain a reproducible entry point, exact location, and decisive excerpt.
 
-- This command updates task metadata AND physically moves the task directory
-- Do not move a task that has incomplete workflow steps unless forced
+- Host finalization updates task metadata and atomically moves the task directory
 - The entry point accepts optional `--external-pr <N>` only to select among ambiguous external-delivery candidates; it never bypasses identity or platform gates
 
 Version stamp rule: when creating or updating `task.md` frontmatter, read `.agents/rules/version-stamp.md` first and write or refresh `agent_infra_version`.
@@ -50,7 +49,7 @@ On the normal path, complete business updates, platform sync, and the pre-comple
 
 ### 1. Verify Task Exists
 
-Check that the task exists in `.agents/workspace/active/{task-id}/`.
+Check that the task exists in `<task-workspace>/active/{task-id}/`.
 
 Note: `{task-id}` format is `TASK-{yyyyMMdd-HHmmss}`, e.g. `TASK-20260306-143022`
 
@@ -102,7 +101,7 @@ Run /create-pr --task {task-ref} first, then complete; --skip-pr is not accepted
 ```
 
 Before lifecycle, verify only the hard gates:
-- [ ] Task identity, active state, concurrency locks, and local atomic lifecycle operations are available
+- [ ] Task identity, active-state validation, and local atomic lifecycle operations are available
 - [ ] Required-PR delivery is satisfied when `prFlow=required`
 - [ ] Other business evidence (workflow, review, commit, tests, disagreement ledger, manual validation, and platform sync) is recorded or can be checked after lifecycle; manual validation requires a committed transaction, receipt, current artifact digest, and an identity-bearing completion log
 
@@ -142,7 +141,7 @@ Check whether task.md has a valid `platform_issue_identity`. If it does not, ski
 When a valid `platform_issue_identity` exists, execute in this exact order:
 
 1. Run `agent-infra-internal platform-issue sync {task-id} --agent {standard-agent-token} --requirements --fields`.
-2. Write the business summary to a temporary file and run `agent-infra-internal platform-comment stage-summary {task-id} --body-file {path}`. This stores the body and SHA-256 in the task's durable staging record; it must not publish the summary comment directly.
+2. Write the completion summary as JSON fields `taskId`, `title`, `summary`, `artifacts`, and `verification:{state,detail}`, then run `agent-infra-internal platform-comment stage-summary {task-id} --body-file {path}`. Use the current artifact registry (`[]` when empty). If final verification has not run, use `state:"not-run"` with a non-empty explanation. The command persists the normalized payload; do not publish the summary comment in this step.
 
 The summary body records only delivery results, the associated PR and actual merge facts, verification commands with their scope/results/uncovered areas, and known todo items supported by current task evidence. Include the related commit when it helps explain verification scope. Do not infer unsupported facts; list unfinished work as a todo. This is an Issue closeout summary, not a PR comment.
 
@@ -174,11 +173,11 @@ agent-infra-internal task-verify {task-id} complete-task.preflight --format text
 
 Present the verification summary per `.agents/rules/validation-output.md`, retaining necessary failure, blocked, and soft-warning diagnostics.
 
-This event runs only the required-PR delivery hard preflight; host finalization still enforces identity, concurrency, and local atomicity before lifecycle. Peripheral review/manual/platform checks run through `complete-task.completed` after lifecycle and are projected as warning/pending steps. On a hard-gate non-zero exit (fail/blocked), keep the task active, record the stable code/target, and stop.
+This event runs only the required-PR delivery hard preflight; host finalization still enforces identity validation and local atomicity before lifecycle. Peripheral review/manual/platform checks run through `complete-task.completed` after lifecycle and are projected as warning/pending steps. On a hard-gate non-zero exit (fail/blocked), keep the task active, record the stable code/target, and stop.
 
 If a summary must mirror a human-decided `post-review-commit` exemption, make a best-effort sync in Step 4 with the original failure code/message, PRC id/evidence, and ruling details. A sync failure records `SUMMARY_SYNC_FAILED` and still allows lifecycle; terminal verification decides the final state.
 
-`--force` cannot lift identity, concurrency, local atomicity, or required-PR hard gates; failures there must stop. Other review, manual-validation, and platform evidence is recorded by terminal verification as warning/pending and can be repaired by retrying.
+`--force` cannot lift identity validation, local atomicity, or required-PR hard gates; failures there must stop. Other review, manual-validation, and platform evidence is recorded by terminal verification as warning/pending and can be repaired by retrying.
 
 ### 6. Run the Host Finalization Entry Point
 
@@ -209,7 +208,7 @@ Task {task-id} completed; task directory moved to completed/.
 Task info:
 - Title: {title}
 - Completed at: {timestamp}
-- Target path: .agents/workspace/completed/{task-id}/
+- Target path: <task-workspace>/completed/{task-id}/
 
 Deliverables:
 - {List of key outputs: files modified, tests added, etc.}
@@ -225,32 +224,18 @@ ai sandbox rm {task-id}  # or use the task's retained short id
 
 ## Completion Checklist
 
-- [ ] Verified all workflow steps are complete
-- [ ] Updated task.md with completed status and timestamp
-- [ ] Moved task directory to `.agents/workspace/completed/`
-- [ ] Verified move succeeded
-- [ ] Informed user of completion
+- [ ] Hard prerequisites are satisfied and the pre-completion gate passes
+- [ ] Host finalization returns `result=completed` or `result=completed_with_warnings`
+- [ ] Completion verification passes
+- [ ] The structured completion result and applicable warnings are reported to the user
 
 ## Notes
 
-1. **Premature completion**: Do not move a task that has incomplete steps. Examples of incomplete situations:
-   - Code is written but not committed
-   - Code is committed but not reviewed
-   - Review found blockers that haven't been fixed
-   - PR is created but not merged
-   - Manual validation items are incomplete
-
-2. **Rollback**: If a task was incorrectly moved:
-   ```bash
-   mv .agents/workspace/completed/{task-id} .agents/workspace/active/{task-id}
-   ```
-   Then update task.md status back to `active`.
-
-3. **Multiple contributors**: If multiple AI agents worked on the task, ensure all contributions are committed before completing.
+- When multiple AI agents contributed, ensure all contributions are included in the local checkpoint.
 
 ## Error Handling
 
 - Task not found: Prompt "Task {task-id} not found in active directory"
-- Already completed: Prompt "Task {task-id} is already in completed directory"
-- Task is blocked: Prompt "Task {task-id} is blocked. Unblock it first by moving to active/"
-- Move failed: Prompt error and suggest manual move
+- Already completed: Enter `finalization-retry` only when a matching Complete Task Activity Log exists; otherwise report incomplete terminal identity and stop
+- Task is blocked: Satisfy the recorded unblock condition, then reactivate it through `task-lifecycle activate` before retrying
+- Finalization failed or blocked: Preserve source data and the receipt, then recover through the same finalization entry point using its structured error; do not manually rewrite terminal state or move the task directory