@fitlab-ai/agent-infra 0.9.2 → 0.9.4

package/templates/.agents/rules/no-mid-flow-questions.zh-CN.md

@@ -39,6 +39,23 @@
 
 - `analyze-task`：任务描述/需求信息不足以支撑可靠分析时，可在入口处逐个提问收敛需求
 
+### 例外 4：当前快照的远端发布授权
+
+仅允许在当前会话已完成准备、已展示待发布的最新快照或精确内容后，询问一次是否执行对应远端发布。确认不跨会话、不跨快照复用；否定、调整、疑问、歧义或中断均 fail closed，不得写入远端。
+
+当前归入本例外的 SKILL：
+
+- `release`：展示最新 release snapshot 后确认是否 publish
+- `create-release-note`：展示 stage 后的精确 notes 与摘要后确认是否 publish
+
+### 例外 5：生命周期启动缺少完整模型策略
+
+仅当 `run-task` 在创建任何 run、baseline、receipt 或 child 之前收到核心错误 `ORCHESTRATION_MODEL_POLICY_REQUIRED` 时，可展示带完整性标签的模型选择上下文，并一次询问 executor/reviewer 的完整 model + reasoning effort。部分显式策略、缺少 client、active delegation 或其他暂停原因不适用；用户未回答时不得创建 run。
+
+当前归入本例外的 SKILL：
+
+- `run-task`：仅补齐核心明确要求的原子模型策略
+
 ## 禁言条款（默认行为）
 
 不属于上述任一例外的所有 SKILL 执行场景，遵循以下默认行为：

package/templates/.agents/rules/pr-checks-commands.en.md

@@ -1,6 +1,6 @@
-# Required-checks Platform Intents
+# PR Readiness Platform Intents
 
-Typed intents own required-only selection, polling deadlines, run/job resolution, and log retrieval. The skill/model owns failure classification, root-cause analysis, minimum fixes, tests, and authorized commit/push actions.
+Typed intents own full check-set retrieval, PR mergeability, polling deadlines, run/job resolution, and logs. Every inspect/poll aggregates facts from one PR head snapshot; facts are never mixed across heads.
 
 ```bash
 agent-infra-internal platform-checks inspect {task-id}
@@ -15,4 +15,4 @@ agent-infra-internal platform-checks logs {task-id} \
   --run {run-id} [--job {job-id}]
 ```
 
-`checks.state` is `passed|failed|pending|timed-out|cancelled|no-required`. Green/no-required exits 0; definite failure/cancellation exits 1; pending, timeout, or network blocking exits 2. Each platform adapter validates its own dependencies before operations and preserves dependency or deterministic platform errors without compatibility degradation. Run resolution prefers a validated details URL and otherwise requires one exact PR-head/check-name match. Platform intents never edit business code or push.
+`readiness.state` is `ready|conflicting|checks-failed|pending|timed-out|cancelled` and carries `headSha`. Only `ready` exits 0; conflicting/check failures exit 1; all other readiness or network blocking exits 2. `checks.state` remains available as check-only diagnostics. Adapter dependency and deterministic platform errors are preserved without degradation. Platform intents never edit business code or push.

package/templates/.agents/rules/pr-checks-commands.github.en.md

@@ -1,4 +1,4 @@
-# Required-checks Platform Intents
+# GitHub PR Readiness Intents
 
 The GitHub adapter requires `gh >= 2.16.0`. Platform context checks this dependency before any GitHub API, PR, or checks operation. Projects that do not select GitHub neither probe nor depend on `gh`.
 
@@ -15,4 +15,4 @@ agent-infra-internal platform-checks logs {task-id} \
   --run {run-id} [--job {job-id}]
 ```
 
-The core owns required-only selection, deadlines, exact run/job resolution, and faithful logs. Green/no-required exits 0; definite failure exits 1; pending, timeout, or network blocking exits 2. Missing dependencies, unsupported versions, and deterministic platform failures preserve their structured errors without compatibility degradation. The skill/model still owns diagnosis, fixes, tests, and authorized commit/push actions.
+The adapter normalizes REST `mergeable=false` to `conflicting`, null/missing to `unknown`, and true to `mergeable`; `mergeable=true` plus diagnostic `dirty` is contradictory and becomes `unknown`. Other diagnostics such as `blocked` do not override REST true. Core combines that fact with all checks for one `headSha`: only `ready` exits 0, `conflicting|checks-failed` exit 1, and pending/timeout/cancel/network blocking exit 2. Dependency and deterministic platform errors are preserved without degradation.

package/templates/.agents/rules/pr-checks-commands.github.zh-CN.md

@@ -1,6 +1,6 @@
-# PR required checks 平台意图
+# GitHub PR readiness 平台意图
 
-required checks 的筛选、轮询 deadline、失败 run/job 定位和日志获取统一由 typed internal intent 执行。SKILL/模型只负责失败分类、根因分析、最小修复和授权后的提交推送。
+PR 全部 checks 的获取、轮询 deadline、失败 run/job 定位和日志获取统一由 typed internal intent 执行。SKILL/模型只负责失败分类、根因分析、最小修复和授权后的提交推送。
 
 GitHub adapter 要求 `gh >= 2.16.0`。平台上下文会在任何 GitHub API、PR 或 checks 操作前检查该依赖；未选择 GitHub 平台时不探测也不依赖 `gh`。
 
@@ -13,7 +13,7 @@ agent-infra-internal platform-checks watch {task-id} \
   --interval-seconds 30 --deadline-seconds 1800
 ```
 
-结构化 `checks.state` 为 `passed|failed|pending|timed-out|cancelled|no-required`。`passed|no-required` 退出 0；确定失败/取消退出 1；pending、timeout 或网络阻塞退出 2。依赖缺失、版本过低和确定性平台错误直接返回其原始结构化错误，不执行兼容降级。
+adapter 把 REST `mergeable=false` 规范化为 `conflicting`，null/缺失为 `unknown`，true 为 `mergeable`；true 与诊断 `dirty` 矛盾时降为 `unknown`。`blocked` 等其他诊断不覆盖 REST true。core 在同一 `headSha` 上与全部 checks 聚合：仅 `ready` 退出 0，`conflicting|checks-failed` 退出 1，pending/timeout/cancel/网络阻塞退出 2。依赖与确定性平台错误不降级。
 
 ## 定位失败 run/job
 

package/templates/.agents/rules/pr-checks-commands.zh-CN.md

@@ -1,6 +1,6 @@
-# PR required checks 平台意图
+# PR readiness 平台意图
 
-required checks 的筛选、轮询 deadline、失败 run/job 定位和日志获取统一由 typed internal intent 执行。SKILL/模型只负责失败分类、根因分析、最小修复和授权后的提交推送。
+PR 全部 checks、PR mergeability、轮询 deadline、失败 run/job 定位和日志获取统一由 typed internal intent 执行。每次 inspect/poll 都在同一 PR head 快照上聚合，不跨 head 拼接事实。
 
 ## 快照与监控
 
@@ -11,7 +11,7 @@ agent-infra-internal platform-checks watch {task-id} \
   --interval-seconds 30 --deadline-seconds 1800
 ```
 
-结构化 `checks.state` 为 `passed|failed|pending|timed-out|cancelled|no-required`。`passed|no-required` 退出 0；确定失败/取消退出 1；pending、timeout 或网络阻塞退出 2。平台 adapter 必须在操作前验证自身依赖；依赖或确定性平台错误直接透传，不执行兼容降级。
+结构化 `readiness.state` 为 `ready|conflicting|checks-failed|pending|timed-out|cancelled`，并携带 `headSha`。仅 `ready` 退出 0；`conflicting|checks-failed` 退出 1；其余或网络阻塞退出 2。`checks.state` 仍保留 check-only 诊断；平台 adapter 的依赖和确定性错误不降级。
 
 ## 定位失败 run/job
 

package/templates/.agents/rules/pr-sync.en.md

@@ -1,5 +1,7 @@
 # PR Summary Synchronization
 
+> `--agent` values follow the "Collaborator Token Specification" in `.agents/rules/task-management.md`: standard AI short tokens (`claude`/`codex`/`antigravity`/`opencode`/`cursor`), long-name normalization (`claude-code`->`claude`, `antigravity-cli`->`antigravity`), or the `human` manual exception.
+
 The model writes the semantic reviewer summary. Typed core owns canonical artifact selection, the marker, current HEAD, paginated comment lookup, and create/update/no-op reconciliation.
 
 ## Inputs
@@ -16,7 +18,7 @@ Write only the summary body to a file, without marker or SHA:
 
 ```bash
 agent-infra-internal platform-pr summary-sync {task-id} \
-  --agent {agent} --body-file {summary-body-file}
+  --agent {standard-agent-token} --body-file {summary-body-file}
 ```
 
 The core wraps `<!-- sync-pr:{task-id}:summary -->` and current `<!-- last-commit: ... -->`, then creates, updates in place, or returns no-op. Duplicate markers fail deterministically. Callers never assemble shell/heredoc comment commands.

package/templates/.agents/rules/pr-sync.github.en.md

@@ -1,12 +1,22 @@
 # PR Summary Synchronization
 
+> `--agent` values follow the "Collaborator Token Specification" in `.agents/rules/task-management.md`: standard AI short tokens (`claude`/`codex`/`antigravity`/`opencode`/`cursor`), long-name normalization (`claude-code`->`claude`, `antigravity-cli`->`antigravity`), or the `human` manual exception.
+
 The model writes the semantic reviewer summary. Typed core owns canonical artifact selection, marker/HEAD wrapping, paginated comment lookup, and reconciliation.
 
+## Three-Layer Isolation
+
+- `sync-pr:{task-id}:summary` (`platform-pr summary-sync`) is an updatable reviewer summary; it is neither a process copy nor a formal Review.
+- The full `pr-review*` process copy lives in the Issue artifact comment (`platform-comment sync --kind artifact`) and is restored by `restore-task` under its Issue-only contract.
+- A formal PR Review (`platform-pr-review publish`) is the only formal conclusion carrier published to the PR, bound to the reviewed head SHA, and includes conclusion, findings, receipt, and the Issue artifact link.
+
+The three never cross: a regular PR comment does not carry the full process copy; an Issue artifact comment is not treated as a formal Review; a summary is not presented as a formal Review.
+
 ```bash
 agent-infra-internal platform-pr summary-context {task-id}
 
 agent-infra-internal platform-pr summary-sync {task-id} \
-  --agent {agent} --body-file {summary-body-file}
+  --agent {standard-agent-token} --body-file {summary-body-file}
 ```
 
 Use only canonical inputs returned by the context command. Write the plain body without marker or SHA. The core owns `<!-- sync-pr:{task-id}:summary -->`, current `<!-- last-commit: ... -->`, create/update/no-op behavior, and duplicate-marker conflicts. Summary failure never rolls back a PR or commit.

package/templates/.agents/rules/pr-sync.github.zh-CN.md

@@ -1,7 +1,17 @@
 # PR 摘要同步
 
+> `--agent` 取值见 `.agents/rules/task-management.md`「合作者 token 规范」：标准 AI 短名（`claude`/`codex`/`antigravity`/`opencode`/`cursor`）、长名归一化（`claude-code`→`claude`、`antigravity-cli`→`antigravity`）或人工例外 `human`。
+
 PR 摘要的语义聚合由模型完成；canonical 产物选择、marker、当前 HEAD、分页评论查找和 create/update/no-op 由 typed core 负责。
 
+## 三层隔离
+
+- `sync-pr:{task-id}:summary`（`platform-pr summary-sync`）是可更新的 reviewer 摘要，不是过程原文，也不是正式 Review。
+- `pr-review*` 完整过程原文在 Issue artifact 评论（`platform-comment sync --kind artifact`），由 `restore-task` 按 Issue-only 契约恢复。
+- 正式 PR Review（`platform-pr-review publish`）是唯一发布到 PR 的正式结论载体，绑定被审 head SHA，含结论、finding、receipt 与 Issue artifact 链接。
+
+三者不串用：PR 普通评论不承载完整过程原文；Issue artifact 评论不当作正式 Review；摘要不冒充正式 Review。
+
 ## 聚合输入
 
 ```bash
@@ -35,7 +45,7 @@ core 最终包装出的 canonical 评论结构为：
 
 ```bash
 agent-infra-internal platform-pr summary-sync {task-id} \
-  --agent {agent} --body-file {summary-body-file}
+  --agent {standard-agent-token} --body-file {summary-body-file}
 ```
 
 core 会包装唯一 `<!-- sync-pr:{task-id}:summary -->` 和当前 `<!-- last-commit: ... -->`，分页查找 PR 普通评论：不存在则创建、正文变化则原地更新、无差异则 no-op、重复 marker 则稳定失败。正文通过文件输入，调用方不得拼 shell/heredoc。

package/templates/.agents/rules/pr-sync.zh-CN.md

@@ -1,5 +1,7 @@
 # PR 摘要同步
 
+> `--agent` 取值见 `.agents/rules/task-management.md`「合作者 token 规范」：标准 AI 短名（`claude`/`codex`/`antigravity`/`opencode`/`cursor`）、长名归一化（`claude-code`→`claude`、`antigravity-cli`→`antigravity`）或人工例外 `human`。
+
 PR 摘要的语义聚合由模型完成；canonical 产物选择、marker、当前 HEAD、分页评论查找和 create/update/no-op 由 typed core 负责。
 
 ## 聚合输入
@@ -23,7 +25,7 @@ agent-infra-internal platform-pr summary-context {task-id}
 
 ```bash
 agent-infra-internal platform-pr summary-sync {task-id} \
-  --agent {agent} --body-file {summary-body-file}
+  --agent {standard-agent-token} --body-file {summary-body-file}
 ```
 
 core 会包装唯一 `<!-- sync-pr:{task-id}:summary -->` 和当前 `<!-- last-commit: ... -->`，分页查找 PR 普通评论：不存在则创建、正文变化则原地更新、无差异则 no-op、重复 marker 则稳定失败。正文通过文件输入，调用方不得拼 shell/heredoc。

package/templates/.agents/rules/release-commands.en.md

@@ -2,4 +2,4 @@
 
 This code platform does not provide a release-note adapter.
 
-Use `agent-infra-internal platform-release-notes context` to receive a structured `PLATFORM_RELEASE_NOTES_UNSUPPORTED` no-op. Do not probe another platform client. Publishing remains a no-op until an adapter is provided.
+Local `agent-infra-internal platform-release-notes stage --notes-file "{notes-file}"` still normalizes an external file and returns its digest. Use `context` to receive a structured `PLATFORM_RELEASE_NOTES_UNSUPPORTED` no-op and do not probe another platform client. Publish with `--expected-sha256` remains a no-op until an adapter is provided.

package/templates/.agents/rules/release-commands.github.en.md

@@ -14,6 +14,15 @@ agent-infra-internal platform-release-notes context \
 
 The result contains `history`, `pullRequests`, `closingIssues`, and commit `authors` with normalized `login` / `resolution` values. `status: no-op` with error code `PLATFORM_RELEASE_NOTES_UNSUPPORTED` means the current platform does not support remote release-note operations.
 
+## Stage Release Notes
+
+```bash
+agent-infra-internal platform-release-notes stage \
+  --notes-file "{notes-file}"
+```
+
+The command accepts only an external regular file, normalizes it atomically, and returns SHA-256 for its exact bytes.
+
 ## Publish Release Notes
 
 Call this only after user confirmation:
@@ -22,7 +31,8 @@ Call this only after user confirmation:
 agent-infra-internal platform-release-notes publish \
   --tag "v{version}" \
   --title "v{version}" \
-  --notes-file "{notes-file}"
+  --notes-file "{notes-file}" \
+  --expected-sha256 "{preview-sha256}"
 ```
 
-The command updates an existing Release or creates it when missing; `--dry-run` returns only the planned operation. Exit code `0` means success, `1` means a stable failure, and `2` means a network or platform block.
+The command recomputes the digest before platform access and performs no platform write on mismatch. On a match it updates an existing Release or creates it when missing; `--dry-run` returns only the planned operation. Exit code `0` means success, `1` means a stable failure, and `2` means a network or platform block.

package/templates/.agents/rules/release-commands.github.zh-CN.md

@@ -14,6 +14,15 @@ agent-infra-internal platform-release-notes context \
 
 结果包含 `history`、`pullRequests`、`closingIssues` 和带规范化 `login` / `resolution` 的 commit `authors`。`status: no-op` 且错误码为 `PLATFORM_RELEASE_NOTES_UNSUPPORTED` 表示当前平台不支持远端发布说明能力。
 
+## Stage Release notes
+
+```bash
+agent-infra-internal platform-release-notes stage \
+  --notes-file "{notes-file}"
+```
+
+命令只接受工作树外普通文件，原子规范化并返回精确 bytes 的 SHA-256。
+
 ## 发布 Release notes
 
 用户确认后调用：
@@ -22,7 +31,8 @@ agent-infra-internal platform-release-notes context \
 agent-infra-internal platform-release-notes publish \
   --tag "v{version}" \
   --title "v{version}" \
-  --notes-file "{notes-file}"
+  --notes-file "{notes-file}" \
+  --expected-sha256 "{preview-sha256}"
 ```
 
-命令会更新已存在的 Release，缺失时创建；`--dry-run` 只返回 planned operation。退出码为 `0` 时成功，`1` 表示稳定失败，`2` 表示网络或平台阻塞。
+命令在平台访问前复算摘要，不匹配时零写入；匹配时更新已有 Release，缺失时创建。`--dry-run` 只返回 planned operation。退出码为 `0` 时成功，`1` 表示稳定失败，`2` 表示网络或平台阻塞。

package/templates/.agents/rules/release-commands.zh-CN.md

@@ -2,4 +2,4 @@
 
 当前代码平台未提供发布说明 adapter。
 
-调用 `agent-infra-internal platform-release-notes context` 会返回结构化的 `PLATFORM_RELEASE_NOTES_UNSUPPORTED` no-op，不得探测其他平台 client。在提供 adapter 前，发布操作同样保持 no-op。
+本地 `agent-infra-internal platform-release-notes stage --notes-file "{notes-file}"` 仍可规范化工作树外文件并返回摘要。调用 `context` 会返回结构化的 `PLATFORM_RELEASE_NOTES_UNSUPPORTED` no-op，不得探测其他平台 client；提供 adapter 前，带 `--expected-sha256` 的 publish 同样保持 no-op。

package/templates/.agents/rules/review-handshake.zh-CN.md

@@ -93,7 +93,7 @@
 - 成功提交后令 `B=last_reviewed_commit=<new_head>`；`B` 只表示已经落到 Git commit 的审查锚点。
 - `complete-task` 的 `post-review-commit` gate 只使用 B；B 缺失、畸形或对象不存在时报告 `reviewed snapshot was not anchored`，不得回退 R。
 - 若 B 之后代码 / 规则路径出现新提交，gate 会拦截，要求重新 `review-code`。自动例外仅限两类：(1) 绑定的平台变更请求（PR/MR）已合并，且平台适配器提供权威快照与远端 Git 证据引用；gate 在隔离的临时仓库中抓取受审查 head 与目标分支，证明 B 是原变更请求 head、merge commit 位于权威目标分支历史中、受审查变更与单父 squash commit 的规范化补丁完全一致，并且 merge 后受保护路径没有新提交；(2) 无有效变更请求，B 后恰有一个受保护路径提交，该提交是本地 HEAD 历史中的单父重写，且它与 B 的完整 tree 相同或受保护内容相同，重写后也没有受保护路径提交。适配器不支持该能力，缺少所需平台 / Git 证据，或当前 Git 凭据不能读取这些远端 refs 时 fail closed。
-- required checks 由合并前的分支保护 / ruleset 与 `review-code` / `watch-pr` 路由负责。post-review-commit 仍独立执行适用的严格 / PR squash / 本地重写等价判定。
+- 全部 PR checks 由合并前的 `review-code` / `watch-pr` 路由负责，其中 required checks 仍受分支保护 / ruleset 强制。post-review-commit 仍独立执行适用的严格 / PR squash / 本地重写等价判定。
 - **豁免**：在账本追加一行 `| PRC-1 | post-review-commit | - | - | human-decided | <裁定说明> |`，记录人工明确允许该批提交免复审。
 
 ## gate 行为速查

package/templates/.agents/rules/task-management.en.md

@@ -19,6 +19,17 @@ Map user intent to the corresponding workflow command:
 - Before updating `agent_infra_version`, read `.agents/rules/version-stamp.md`
 - Activity Log entries are append-only and must never overwrite history
 
+## Collaborator Token Specification
+
+`--agent` values must converge on the standard AI collaborator tokens; OS usernames (e.g. `devuser`) and git usernames (e.g. a human name) are forbidden. The standard set (short tokens are the single source of truth for the activity log):
+
+- AI short tokens: `claude` / `codex` / `antigravity` / `opencode` / `cursor`
+- Long-name mapping (normalized to the short token before writing): `claude-code` -> `claude`, `antigravity-cli` -> `antigravity`
+- Historical `gemini` / `gemini-cli` remain read-only for `ai task log` rendering and are not writable
+- Manual-step exception: no matter which agent is used, a human-made decision is always declared as `human`
+
+The six internal commands (`task-event` / `task-lifecycle` / `platform-issue` / `platform-comment` / `platform-pr` / `task-orchestration`) hard-validate `--agent` against a whitelist: they accept a short token, a long name, or `human`, and reject non-standard values with the matching `*_PAYLOAD_INVALID` error; long names are normalized to the short token before being persisted or forwarded. The `ai task log` renderer keeps unknown tokens grouped as `human` but appends a visible `(unknown)` marker.
+
 ## State Snapshot and Completion Verification Entrypoints
 
 - Runtime skills that record git, task-directory, and task.md tail evidence must call `agent-infra-internal task-snapshot {task-id} --format text`; they must not resolve short ids, scan workspaces, or reconstruct the three observations themselves.
@@ -72,4 +83,6 @@ Map user intent to the corresponding workflow command:
 - **Deferred form (the skill creates task.md, so there is no file to write to at the start)** — capture `started_at` in memory before running, then when writing the Activity Log at the end, **append both lines at once** (started line uses `started_at`, done line uses the completion time):
   `create-task`, `import-issue`, `import-codescan`, `import-dependabot`.
 
+- **After host resolution** — `review-pr` writes started through `task-activity pr-review-start` only after resolving the unique task host, canonical round, and reviewed head. Success closes through `pr-review-complete`; a controlled pre-publication failure or head drift closes through `pr-review-terminate` with an `aborted` / `superseded` terminal. Replaying the same task/round/head/terminal payload is a no-op; one-shot review never writes a task Activity Log.
+
 **Exceptions**: read-only inspection skills that do not represent real progress (e.g. `check-task`) do not write started. A bare operation with no task.md context (e.g. a `commit` not tied to a task) likewise skips it.

package/templates/.agents/rules/task-management.zh-CN.md

@@ -19,6 +19,17 @@
 - 更新 `agent_infra_version` 前，先读取 `.agents/rules/version-stamp.md`
 - Activity Log 只能追加，不能覆盖历史记录
 
+## 合作者 token 规范
+
+`--agent` 取值必须收敛到标准 AI 合作者 token，禁止填入 OS 系统用户名（如 `devuser`）或 git 用户名（如 `季聿阶`）。标准集合（短名为活动日志唯一事实来源）：
+
+- AI 短名：`claude` / `codex` / `antigravity` / `opencode` / `cursor`
+- 长名映射（写入前归一化为短名）：`claude-code` → `claude`、`antigravity-cli` → `antigravity`
+- 历史 `gemini` / `gemini-cli` 仅保留 `ai task log` 渲染兼容，不接受写入
+- 人工步骤例外：无论使用哪个 Agent，只要是人做的决定，统一声明 `human`
+
+六个内部命令（`task-event` / `task-lifecycle` / `platform-issue` / `platform-comment` / `platform-pr` / `task-orchestration`）对 `--agent` 做白名单硬校验：接受短名、长名或 `human`，非标准值返回对应 `*_PAYLOAD_INVALID` 错误；长名在落库/透传前归一化为短名。渲染端 `ai task log` 对无法识别的 token 保留 `human` 归类并附加 `(unknown)` 标记。
+
 ## 状态快照与完成验证入口
 
 - 运行时 SKILL 需要记录 git、任务目录和 task.md tail 证据时，统一调用 `agent-infra-internal task-snapshot {task-id} --format text`；不得自行解析短号、扫描 workspace 或重新拼接三段状态命令。
@@ -75,4 +86,6 @@
 - **延迟补写（本技能创建 task.md，开始时无文件可写）**——开始执行前先在内存记录 `started_at`，最后写活动日志时**一次性补两条**（started 行用 `started_at`、done 行用完成时间）：
   `create-task`、`import-issue`、`import-codescan`、`import-dependabot`。
 
+- **宿主解析后写入**——`review-pr` 只有在唯一任务宿主、canonical round 与被审 head 确定后才通过 `task-activity pr-review-start` 写 started；成功以 `pr-review-complete` 闭合，已知未发布的受控失败或 head 漂移以 `pr-review-terminate` 写 `aborted` / `superseded` 终态。同一 task/round/head/terminal payload 重放为 no-op；一次性检视不写任务日志。
+
 **例外**：`check-task` 等只读巡检类、不代表实质工作推进的技能不写 started。无 task.md 上下文的纯操作（如无关联任务的 `commit`）同样跳过。

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

@@ -7,6 +7,9 @@ description: >
 ---
 
 # Analyze Task
+> `--agent` values follow the "Collaborator Token Specification" in `.agents/rules/task-management.md`: standard AI short tokens (`claude`/`codex`/`antigravity`/`opencode`/`cursor`), long-name normalization (`claude-code`->`claude`, `antigravity-cli`->`antigravity`), or the `human` manual exception.
+
+If the entry operands contain `--orchestrated`, bind `{execution-flag}` to `--orchestrated` and forward it unchanged to the completed event; otherwise bind it to an empty value. Never infer it from `orchestration.json`, environment variables, or prior artifacts.
 
 ## Boundary / Critical Rules
 
@@ -36,7 +39,7 @@ Before the state check is complete, do not make external-state assertions such a
 
 ## Step Start: Declare the started Event
 
-After resolving the artifact context and before this round's first artifact action, run `agent-infra-internal task-event {task-id} analyze.started --agent {agent}` and verify the returned `artifactContext`.
+After resolving the artifact context and before this round's first artifact action, run `agent-infra-internal task-event {task-id} analyze.started --agent {standard-agent-token}` and verify the returned `artifactContext`.
 
 ## Steps
 
@@ -103,8 +106,8 @@ Runs after Step 0 state check and Step 3 (questioning is an external-state actio
   1. Decide this round's question (consistent with 4.2):
      - if a `pending_question` already exists (the previous question is still unanswered) → restate that `pending_question`, do **not** modify it and do **not** increment `question_count`;
      - otherwise (no pending question) → pick the single highest-value question (acceptance criteria > scope > ambiguity) and write `## Brainstorming`: `status: asking`, `pending_question: <question>`, `question_count += 1`.
-  2. If `start_date` is empty, write today (`date +%F`), then run `agent-infra-internal task-event {task-id} analyze.awaiting-input --agent {agent} --question {question_count}` so the core updates base metadata and Activity Log.
-  3. Issue sync (when `issue_number` exists, skip on any failure): run `agent-infra-internal platform-comment sync {task-id} --kind task --agent {agent}` to update only the **task comment**; keep the `status` label at `pending-design-work`; do **not** publish an analysis artifact comment.
+  2. If `start_date` is empty, write today (`date +%F`), then run `agent-infra-internal task-event {task-id} analyze.awaiting-input --agent {standard-agent-token} --question {question_count}` so the core updates base metadata and Activity Log.
+  3. Issue sync (when `issue_number` exists, skip on any failure): run `agent-infra-internal platform-comment sync {task-id} --kind task --agent {standard-agent-token}` to update only the **task comment**; keep the `status` label at `pending-design-work`; do **not** publish an analysis artifact comment.
   4. Verification (replaces the step 8 artifact gate): `agent-infra-internal task-verify {task-id} analyze.awaiting-input --format text` (the early-exit set `current_step: requirement-analysis` and wrote `start_date`, so it should pass); also keep `rg -n 'Analyze Task \(Brainstorming\)' .agents/workspace/active/{task-id}/task.md` and the task-comment sync evidence. Do **not** run the artifact gate, nor `check activity-log` / `check platform-sync` (both bind to the analysis artifact path).
   5. User output: show only the current **single question** plus how to answer/continue (re-trigger `analyze-task {task-ref}` with the answer), and append the `Completed at` line per `.agents/rules/next-step-output.md`.
   6. **STOP** and wait for the answer. The next trigger returns to this step.
@@ -198,14 +201,14 @@ Update `.agents/workspace/active/{task-id}/task.md`:
   - Overwrite the `priority` field in frontmatter with the new value
   - Append a `## Priority Re-estimate` section to this round's analysis artifact `{analysis-artifact}`, recording: `priority {old} → {new} (rationale: {short basis grounded in this analysis})`
   If the re-estimated value matches the current value, skip it: do not write the `## Priority Re-estimate` section. The Flow A sync that follows reads the possibly updated frontmatter and propagates the new value to the Issue automatically.
-After the business fields are updated, run `agent-infra-internal task-event {task-id} analyze.completed --agent {agent} --artifact {analysis-artifact}` so the core atomically records the link, stage, agent, metadata, and Activity Log.
+After the business fields are updated, run `agent-infra-internal task-event {task-id} analyze.completed --agent {standard-agent-token} --artifact {analysis-artifact} {execution-flag}` so the core atomically records the link, stage, agent, metadata, and Activity Log.
   - {YYYY-MM-DD HH:mm:ss±HH:MM} — **Analyze Task (Round {N})** by {agent} — Analysis completed → {analysis-artifact}
   ```
 
 If task.md contains a valid `issue_number`, perform these sync actions (skip and continue on any failure):
-- Run `agent-infra-internal platform-issue sync {task-id} --agent {agent} --status pending-design-work --fields`
-- Run `agent-infra-internal platform-comment sync {task-id} --kind task --agent {agent}`
-- Run `agent-infra-internal platform-comment sync {task-id} --kind artifact --artifact {analysis-artifact} --agent {agent}`
+- Run `agent-infra-internal platform-issue sync {task-id} --agent {standard-agent-token} --status pending-design-work --fields`
+- Run `agent-infra-internal platform-comment sync {task-id} --kind task --agent {standard-agent-token}`
+- Run `agent-infra-internal platform-comment sync {task-id} --kind artifact --artifact {analysis-artifact} --agent {standard-agent-token}`
 
 ### 8. Verification Gate
 

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

@@ -7,6 +7,9 @@ description: >
 ---
 
 # 分析任务
+> `--agent` 取值见 `.agents/rules/task-management.md`「合作者 token 规范」：标准 AI 短名（`claude`/`codex`/`antigravity`/`opencode`/`cursor`）、长名归一化（`claude-code`→`claude`、`antigravity-cli`→`antigravity`）或人工例外 `human`。
+
+若入口业务操作数包含 `--orchestrated`，绑定 `{execution-flag}` = `--orchestrated` 并原样转发给 completed 事件；否则绑定为空。不得从 `orchestration.json`、环境变量或历史产物推断该标记。
 
 ## 行为边界 / 关键规则
 
@@ -39,7 +42,7 @@ agent-infra-internal task-snapshot {task-id} --format text
 确认前置条件和轮次后、本轮第一个产出动作之前执行：
 
 ```bash
-agent-infra-internal task-event {task-id} analyze.started --agent {agent}
+agent-infra-internal task-event {task-id} analyze.started --agent {standard-agent-token}
 ```
 
 ## 执行步骤
@@ -106,8 +109,8 @@ agent-infra-internal task-event {task-id} analyze.started --agent {agent}
   1. 确定本轮要问的问题（与 4.2 保持一致）：
      - 若已存在 `pending_question`（上一问尚未得到答案）→ 复述该 `pending_question`，**不**修改它、**不**增加 `question_count`；
      - 否则（无待答问题）→ 选最高价值的一个问题（验收标准 > 范围 > 歧义），写入 `## Brainstorming`：`status: asking`、`pending_question: <问题>`、`question_count += 1`。
-  2. 若 `start_date` 为空，写入当日日期（`date +%F`）；随后执行 `agent-infra-internal task-event {task-id} analyze.awaiting-input --agent {agent} --question {question_count}`，由核心统一更新基础 frontmatter 和 Activity Log。
-  3. Issue 同步（存在 `issue_number` 时，任一失败跳过）：调用 `agent-infra-internal platform-comment sync {task-id} --kind task --agent {agent}` 更新 **task 评论**；`status` label 维持 `pending-design-work`；**不**发布分析产物评论。
+  2. 若 `start_date` 为空，写入当日日期（`date +%F`）；随后执行 `agent-infra-internal task-event {task-id} analyze.awaiting-input --agent {standard-agent-token} --question {question_count}`，由核心统一更新基础 frontmatter 和 Activity Log。
+  3. Issue 同步（存在 `issue_number` 时，任一失败跳过）：调用 `agent-infra-internal platform-comment sync {task-id} --kind task --agent {standard-agent-token}` 更新 **task 评论**；`status` label 维持 `pending-design-work`；**不**发布分析产物评论。
   4. 校验（替代步骤 8 的 artifact gate）：`agent-infra-internal task-verify {task-id} analyze.awaiting-input --format text`（早退已置 `current_step: requirement-analysis` 且已写入 `start_date`，预期通过）；并保留 `rg -n 'Analyze Task \(Brainstorming\)' .agents/workspace/active/{task-id}/task.md` 与 task 评论同步证据。**不**跑 artifact gate，也不跑 `check activity-log` / `check platform-sync`（二者绑定分析产物路径）。
   5. 用户输出：只展示当前**单个问题** + 如何回答/继续（再次触发 `analyze-task {task-ref}` 并附答案），并按 `.agents/rules/next-step-output.md` 在末行追加 `Completed at`。
   6. **STOP**，等待回答。下一次触发回到本步骤。
@@ -199,12 +202,12 @@ agent-infra-internal task-event {task-id} analyze.started --agent {agent}
   - 用新值覆盖 frontmatter 的 `priority` 字段
   - 在本轮分析产物 `{analysis-artifact}` 中追加 `## 优先级重估` 段，记录一条：`priority {old} → {new} (rationale: {基于本轮分析的简短依据})`
   若重估值与当前值一致，跳过：不写入 `## 优先级重估` 段。后续 Flow A 同步会读取可能更新过的 frontmatter，并自动把新值同步到 Issue。
-- 完成业务内容更新后执行 `agent-infra-internal task-event {task-id} analyze.completed --agent {agent} --artifact {analysis-artifact}`，由核心原子登记链接、阶段、代理、时间、版本和 Activity Log。
+- 完成业务内容更新后执行 `agent-infra-internal task-event {task-id} analyze.completed --agent {standard-agent-token} --artifact {analysis-artifact} {execution-flag}`，由核心原子登记链接、阶段、代理、时间、版本和 Activity Log。
 
 如果 task.md 中存在有效的 `issue_number`，执行以下同步操作（任一失败则跳过并继续）：
-- 调用 `agent-infra-internal platform-issue sync {task-id} --agent {agent} --status pending-design-work --fields`
-- 调用 `agent-infra-internal platform-comment sync {task-id} --kind task --agent {agent}`
-- 调用 `agent-infra-internal platform-comment sync {task-id} --kind artifact --artifact {analysis-artifact} --agent {agent}`
+- 调用 `agent-infra-internal platform-issue sync {task-id} --agent {standard-agent-token} --status pending-design-work --fields`
+- 调用 `agent-infra-internal platform-comment sync {task-id} --kind task --agent {standard-agent-token}`
+- 调用 `agent-infra-internal platform-comment sync {task-id} --kind artifact --artifact {analysis-artifact} --agent {standard-agent-token}`
 
 ### 8. 完成校验
 

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

@@ -7,6 +7,8 @@ description: >
 ---
 
 # Block Task
+> `--agent` values follow the "Collaborator Token Specification" in `.agents/rules/task-management.md`: standard AI short tokens (`claude`/`codex`/`antigravity`/`opencode`/`cursor`), long-name normalization (`claude-code`->`claude`, `antigravity-cli`->`antigravity`), or the `human` manual exception.
+
 
 ## Boundary / Critical Rules
 
@@ -53,7 +55,7 @@ Before blocking, thoroughly analyze:
 ### 3. Apply the Local Lifecycle Intent
 
 ```bash
-agent-infra-internal task-lifecycle {task-id} block --agent {agent} \
+agent-infra-internal task-lifecycle {task-id} block --agent {standard-agent-token} \
   --reason "{one-line reason}" --unblock-condition "{unblock condition}"
 ```
 
@@ -73,8 +75,8 @@ ls .agents/workspace/blocked/{task-id}/task.md
 
 Check whether `task.md` includes a valid `issue_number`. If not, skip this step.
 
-If a valid `issue_number` exists, run `agent-infra-internal platform-issue sync {task-id} --agent {agent} --status blocked`.
-Then run `agent-infra-internal platform-comment sync {task-id} --kind task --agent {agent}`.
+If a valid `issue_number` exists, run `agent-infra-internal platform-issue sync {task-id} --agent {standard-agent-token} --status blocked`.
+Then run `agent-infra-internal platform-comment sync {task-id} --kind task --agent {standard-agent-token}`.
 
 ### 7. Verification Gate
 
@@ -115,7 +117,7 @@ Optional: clean up this task's sandbox
 ai sandbox rm {branch}
 
 To unblock when the issue is resolved:
-  agent-infra-internal task-lifecycle {task-id} activate --agent {agent} --note "{activation note}"
+  agent-infra-internal task-lifecycle {task-id} activate --agent {standard-agent-token} --note "{activation note}"
 
 Next step - check task status after unblocking:
 {next-step-commands}
@@ -136,7 +138,7 @@ Next step - check task status after unblocking:
 When the blocking issue is resolved:
 
 ```bash
-agent-infra-internal task-lifecycle {task-id} activate --agent {agent} --note "{activation note}"
+agent-infra-internal task-lifecycle {task-id} activate --agent {standard-agent-token} --note "{activation note}"
 ```
 
 Resume from the preserved `current_step`. On failure, retry the same intent from the structured recovery fields instead of hand-editing lifecycle state.

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

@@ -7,6 +7,8 @@ description: >
 ---
 
 # 标记任务阻塞
+> `--agent` 取值见 `.agents/rules/task-management.md`「合作者 token 规范」：标准 AI 短名（`claude`/`codex`/`antigravity`/`opencode`/`cursor`）、长名归一化（`claude-code`→`claude`、`antigravity-cli`→`antigravity`）或人工例外 `human`。
+
 
 ## 行为边界 / 关键规则
 
@@ -52,7 +54,7 @@ description: >
 ### 3. 执行本地生命周期意图
 
 ```bash
-agent-infra-internal task-lifecycle {task-id} block --agent {agent} \
+agent-infra-internal task-lifecycle {task-id} block --agent {standard-agent-token} \
   --reason "{一行原因}" --unblock-condition "{解除阻塞条件}"
 ```
 
@@ -74,8 +76,8 @@ ls .agents/workspace/blocked/{task-id}/task.md
 
 检查 `task.md` 中是否存在有效的 `issue_number`。如果没有，跳过。
 
-如果存在有效的 `issue_number`，调用 `agent-infra-internal platform-issue sync {task-id} --agent {agent} --status blocked`。
-随后调用 `agent-infra-internal platform-comment sync {task-id} --kind task --agent {agent}` 更新 task 评论。
+如果存在有效的 `issue_number`，调用 `agent-infra-internal platform-issue sync {task-id} --agent {standard-agent-token} --status blocked`。
+随后调用 `agent-infra-internal platform-comment sync {task-id} --kind task --agent {standard-agent-token}` 更新 task 评论。
 
 ### 7. 完成校验
 
@@ -116,7 +118,7 @@ agent-infra-internal task-verify {task-id} block-task.completed --format text
 ai sandbox rm {branch}
 
 解除阻塞时执行：
-  agent-infra-internal task-lifecycle {task-id} activate --agent {agent} --note "{恢复说明}"
+  agent-infra-internal task-lifecycle {task-id} activate --agent {standard-agent-token} --note "{恢复说明}"
 
 下一步 - 检查任务状态（解除阻塞后）：
 {next-step-commands}
@@ -137,7 +139,7 @@ ai sandbox rm {branch}
 当阻塞问题解决后：
 
 ```bash
-agent-infra-internal task-lifecycle {task-id} activate --agent {agent} --note "{恢复说明}"
+agent-infra-internal task-lifecycle {task-id} activate --agent {standard-agent-token} --note "{恢复说明}"
 ```
 
 成功后从保留的 `current_step` 继续。失败时按结构化 recovery 字段以同一 intent 重试，不手工移动目录或编辑基础元数据。

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

@@ -7,6 +7,8 @@ description: >
 ---
 
 # Cancel Task
+> `--agent` values follow the "Collaborator Token Specification" in `.agents/rules/task-management.md`: standard AI short tokens (`claude`/`codex`/`antigravity`/`opencode`/`cursor`), long-name normalization (`claude-code`->`claude`, `antigravity-cli`->`antigravity`), or the `human` manual exception.
+
 
 ## Boundary / Critical Rules
 
@@ -53,7 +55,7 @@ When syncing to the Issue, replace any existing `status:` labels with the inferr
 ### 3. Apply the Local Lifecycle Intent
 
 ```bash
-agent-infra-internal task-lifecycle {task-id} cancel --agent {agent} --reason "{one-line cancellation reason}"
+agent-infra-internal task-lifecycle {task-id} cancel --agent {standard-agent-token} --reason "{one-line cancellation reason}"
 ```
 
 Only `status=applied|no-op` means local cancellation completed. On `status=failed`, show the structured error and recovery steps and retry the same intent; do not manually edit task.md, move the directory, or release the short id.
@@ -75,9 +77,9 @@ Confirm the task directory was moved successfully.
 Check whether `task.md` contains a valid `issue_number`. If not, skip this step.
 
 If a valid `issue_number` exists:
-- Run `agent-infra-internal platform-issue sync {task-id} --agent {agent} --status {reason} --in-labels none --assignees none --milestone none --state closed --close-reason not_planned`
-- Write the cancellation body to a temporary file and run `agent-infra-internal platform-comment sync {task-id} --kind cancel --body-file {path} --agent {agent}`
-- Run `agent-infra-internal platform-comment sync {task-id} --kind task --agent {agent}`
+- Run `agent-infra-internal platform-issue sync {task-id} --agent {standard-agent-token} --status {reason} --in-labels none --assignees none --milestone none --state closed --close-reason not_planned`
+- 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 reason

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

@@ -7,6 +7,8 @@ description: >
 ---
 
 # 取消任务
+> `--agent` 取值见 `.agents/rules/task-management.md`「合作者 token 规范」：标准 AI 短名（`claude`/`codex`/`antigravity`/`opencode`/`cursor`）、长名归一化（`claude-code`→`claude`、`antigravity-cli`→`antigravity`）或人工例外 `human`。
+
 
 ## 行为边界 / 关键规则
 
@@ -52,7 +54,7 @@ description: >
 ### 3. 执行本地生命周期意图
 
 ```bash
-agent-infra-internal task-lifecycle {task-id} cancel --agent {agent} --reason "{一行取消原因}"
+agent-infra-internal task-lifecycle {task-id} cancel --agent {standard-agent-token} --reason "{一行取消原因}"
 ```
 
 仅 `status=applied|no-op` 视为本地取消完成。`status=failed` 时展示结构化 `error` 与 recovery steps，并以同一 intent 重试；不得手工编辑 task.md、移动目录或释放短号。
@@ -74,9 +76,9 @@ ls .agents/workspace/completed/{task-id}/task.md
 检查 `task.md` 中是否存在有效的 `issue_number`。如果没有，跳过此步骤。
 
 如果存在有效的 `issue_number`：
-- 调用 `agent-infra-internal platform-issue sync {task-id} --agent {agent} --status {reason} --in-labels none --assignees none --milestone none --state closed --close-reason not_planned`
-- 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 {agent}`
-- 调用 `agent-infra-internal platform-comment sync {task-id} --kind task --agent {agent}`
+- 调用 `agent-infra-internal platform-issue sync {task-id} --agent {standard-agent-token} --status {reason} --in-labels none --assignees none --milestone none --state closed --close-reason not_planned`
+- 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：
 - 取消原因

package/templates/.agents/skills/close-codescan/SKILL.en.md

@@ -6,6 +6,8 @@ description: >
 ---
 
 # Dismiss Code Scanning Alert
+> `--agent` values follow the "Collaborator Token Specification" in `.agents/rules/task-management.md`: standard AI short tokens (`claude`/`codex`/`antigravity`/`opencode`/`cursor`), long-name normalization (`claude-code`->`claude`, `antigravity-cli`->`antigravity`), or the `human` manual exception.
+
 
 Dismiss the specified Code Scanning (CodeQL) alert and record a justified reason.
 
@@ -81,7 +83,7 @@ Dismiss the alert by following the Code Scanning dismiss command in `.agents/rul
 If a related task exists (search for `codescan_alert_number: <alert-number>`):
 
 ```bash
-agent-infra-internal task-lifecycle {task-id} close-codescan --agent {agent} \
+agent-infra-internal task-lifecycle {task-id} close-codescan --agent {standard-agent-token} \
   --alert-number {alert-number} --reason "{reason}"
 ```
 

package/templates/.agents/skills/close-codescan/SKILL.zh-CN.md

@@ -6,6 +6,8 @@ description: >
 ---
 
 # 关闭 Code Scanning 告警
+> `--agent` 取值见 `.agents/rules/task-management.md`「合作者 token 规范」：标准 AI 短名（`claude`/`codex`/`antigravity`/`opencode`/`cursor`）、长名归一化（`claude-code`→`claude`、`antigravity-cli`→`antigravity`）或人工例外 `human`。
+
 
 关闭指定的 Code Scanning（CodeQL）告警并记录合理的关闭理由。
 
@@ -81,7 +83,7 @@ Code Scanning 告警 #{alert-number}
 如果有关联任务（搜索 `codescan_alert_number: <alert-number>`）：
 
 ```bash
-agent-infra-internal task-lifecycle {task-id} close-codescan --agent {agent} \
+agent-infra-internal task-lifecycle {task-id} close-codescan --agent {standard-agent-token} \
   --alert-number {alert-number} --reason "{reason}"
 ```