@fitlab-ai/agent-infra 0.8.5 → 0.9.1

package/templates/.agents/rules/task-short-id.en.md

@@ -1,36 +1,34 @@
 # Task short id
 
 Task short ids let mobile-style SKILL invocations replace the full 22-char
-`TASK-YYYYMMDD-HHMMSS` with bare numeric `N` (recommended) or `#NN` while a
-task is active.
+`TASK-YYYYMMDD-HHMMSS` with bare numeric `N` while a task is active.
 
 ## Syntax
 
-- Two equivalent literal forms are accepted:
-  - **Bare numeric `N`** (recommended; no shell quoting needed): e.g. `1`, `7`, `42`.
-  - **`#`-prefixed `#N` / `#NN`** (also accepted; bash needs `'...'` quoting): e.g. `#1`, `#01`, `#42`.
+- Only **bare numeric `N`** is accepted (no shell quoting needed): e.g. `1`, `7`, `42`.
 - Resolution: drop leading zeros and take the numeric value `n`; if `n == 0`,
   reject (reserved); if `n > 10^shortIdLength - 1`, reject (over capacity);
-  otherwise canonicalize to `#${n.padStart(shortIdLength, '0')}` as the
+  otherwise canonicalize to `${n.padStart(shortIdLength, '0')}` as the
   registry key.
 - With the default `shortIdLength=2`, capacity is `n ∈ [1, 99]`; registry keys
   look like `01`, `07`, `42`.
-- `#00` (or `#0` when `shortIdLength=1`) is reserved and never allocated; digits
+- `00` (or `0` when `shortIdLength=1`) is reserved and never allocated; digits
   only, no letters.
-- The plain `TASK-…` form keeps working everywhere; bare numeric / `#NN` is an
-  alias, not the persisted task id.
+- The plain `TASK-…` form keeps working everywhere; bare numeric is an alias,
+  not the persisted task id.
+- Removed `#N` / `#NN` syntax is consistently rejected as an invalid task ref.
 
 ## Lifecycle
 
 | Action     | When                                                                 | Effect on registry                                            |
 |------------|-----------------------------------------------------------------------|---------------------------------------------------------------|
-| alloc      | `create-task`, `import-issue`, `import-codescan`, `import-dependabot` | Assigns lowest free `#NN` in the registry.                    |
-| resolve    | Lifecycle SKILLs (`analyze-task`, `plan-task`, `code-task`, …)        | Looks up `#NN` → full task id. Does not allocate.             |
+| alloc      | `create-task`, `import-issue`, `import-codescan`, `import-dependabot` | Assigns lowest free `NN` in the registry.                    |
+| resolve    | Lifecycle SKILLs (`analyze-task`, `plan-task`, `code-task`, …)        | Looks up `NN` → full task id. Does not allocate.             |
 | release    | `complete-task`, `cancel-task`, `block-task`, `close-codescan`, `close-dependabot` | Removes the registry entry. |
-| re-alloc   | `restore-task`                                                        | Re-allocates a (possibly new) `#NN` in the registry. |
+| re-alloc   | `restore-task`                                                        | Re-allocates a (possibly new) `NN` in the registry. |
 
 Short ids are valid only while a task lives in `.agents/workspace/active/`.
-Once it is moved to `completed/`, `blocked/`, or `archive/`, the `#NN` slot is
+Once it is moved to `completed/`, `blocked/`, or `archive/`, the `NN` slot is
 freed and may be reused by a new task.
 
 ## Configuration
@@ -39,7 +37,7 @@ freed and may be reused by a new task.
 // .agents/.airc.json
 {
   "task": {
-    "shortIdLength": 2  // default; capacity = 99 (#01–#99). Set to 3 for #001–#999.
+    "shortIdLength": 2  // default; capacity = 99 (01–99). Set to 3 for 001–999.
   }
 }
 ```
@@ -49,12 +47,12 @@ error suggesting either archiving some tasks or raising `task.shortIdLength`.
 There is no silent extension or truncation. Changing `shortIdLength` requires
 archiving all active tasks first (the registry key width depends on it).
 
-## `#NN` resolution scope (split by entrypoint)
+## Short-id resolution scope (split by entrypoint)
 
 | Entrypoint                                                  | Hit                  | Miss                                                 |
 |-------------------------------------------------------------|----------------------|------------------------------------------------------|
 | SKILL parameter resolver (lifecycle SKILLs)                  | resolve to full id   | **strict error** — short id not found / invalid     |
-| `ai sandbox exec <N \| '#N'>` / `ai sandbox create <N \| '#N'>`           | resolve to full id, then read `branch` from task.md | **strict error** — no ls-index fallback, no literal-branch fallback; hint the user to pass a short id / `TASK-id` / branch name |
+| `ai sandbox exec <N>` / `ai sandbox create <N>`           | resolve to full id, then read `branch` from task.md | **strict error** — no ls-index fallback, no literal-branch fallback; hint the user to pass a short id / `TASK-id` / branch name |
 
 `list --verify` is strictly read-only: it reports discrepancies between the
 active dir and the registry, but never writes.
@@ -64,10 +62,10 @@ active dir and the registry, but never writes.
 Any SKILL (alloc / resolve / release / re-alloc lifecycle entry-points) that
 receives a `{task-id}` argument must follow this contract:
 
-1. If `{task-id}` matches `^[#]?[0-9]+$` (bare numeric `N` or `#`-prefixed `#N`):
+1. If `{task-id}` matches `^[0-9]+$` (bare numeric `N`):
 
 ```bash
-if [[ "{task-id}" =~ ^[#]?[0-9]+$ ]]; then
+if [[ "{task-id}" =~ ^[0-9]+$ ]]; then
   # The script writes the full error message (covering reserved / exceeds
   # shortIdLength capacity / malformed input) to stderr; callers only forward
   # the exit.
@@ -102,7 +100,7 @@ Short ids are pure local state, persisted only in the registry
   registry entry is deleted immediately and the short id may be reused; archived
   tasks are referenced by their full `TASK-…` id.
 
-`resolve(<N|'#N'>)` workflow: ① validate arg matches `^[#]?[0-9]+$` →
+`resolve(<N>)` workflow: ① validate arg matches `^[0-9]+$` →
 ② strip leading zeros and take the numeric value `n`; classify as reserved
 (`n == 0`) / over capacity (`n > 10^shortIdLength - 1`) / normal → ③ on
 normal, use `n.padStart(shortIdLength, '0')` as the registry `ids` key
@@ -116,18 +114,16 @@ repair hint.
   wrong. Exit code 1.
 - **Registry corruption** (duplicate registry entries for the same task id, or
   the JSON is unparsable): exit code 2; manual cleanup required.
-- **Reserved key**: the resolved `n == 0` (inputs like `0`, `#0`, `#00`). Exit code 1.
+- **Reserved key**: the resolved `n == 0` (inputs like `0`, `00`). Exit code 1.
 - **Over capacity**: the resolved `n > 10^shortIdLength - 1` (e.g. `100` or
-  `#100` when `shortIdLength=2`). Exit code 1.
-- **Parameter format error**: input matches neither `^[#]?[0-9]+$` nor a
-  `TASK-id` (e.g. `#abc`, `#`, `5.5`). Exit code 1.
+  `100` when `shortIdLength=2`). Exit code 1.
+- **Parameter format error**: input matches neither `^[0-9]+$` nor a
+  `TASK-id` (e.g. `#1`, `#abc`, `#`, `5.5`). Exit code 1.
 
-## Cross-TUI quoting
+## Cross-TUI use
 
-Bare numeric `N` is safe in every shell and TUI without quoting (recommended):
+Bare numeric `N` is safe in every shell and TUI without quoting:
 `ai sandbox exec 11 'npm test'`, `/review-analysis 11`.
 
-The `#N` / `#NN` form is also accepted; but bash treats `#` as a comment
-marker, so it must be single-quoted: `ai sandbox exec '#03' 'npm test'`.
-Claude Code / Codex / Gemini CLI / OpenCode all forward `#NN` to SKILL
-`ARGUMENTS` literally when quoted.
+Starting with the next major version, migrate the old `#NN` form to `NN`;
+even a quoted value delivered intact to the CLI is rejected.

package/templates/.agents/rules/task-short-id.zh-CN.md

@@ -1,25 +1,24 @@
 # 任务短号
 
-短号让所有 SKILL 在 active 任务生命周期内可以用 `#NN` 或裸数字 `N`（推荐）替代
+短号让所有 SKILL 在 active 任务生命周期内可以用裸数字 `N` 替代
 完整的 22 字符 `TASK-YYYYMMDD-HHMMSS`。
 
 ## 语法
 
-- 字面接受两种等价形式：
-  - **裸数字 `N`**（推荐，无需 shell 引号）：如 `1`、`7`、`42`。
-  - **`#`-前缀 `#N` / `#NN`**（也接受；但 bash 需 `'...'` 引号）：如 `#1`、`#01`、`#42`。
+- 只接受**裸数字 `N`**（无需 shell 引号）：如 `1`、`7`、`42`。
 - 解析规则：去前导零后取数值 `n`，若 `n == 0` 报错（保留）；若 `n > 10^shortIdLength - 1`
-  报错（超容量）；否则归一化为 `#${n.padStart(shortIdLength, '0')}`，作为注册表 key。
+  报错（超容量）；否则归一化为 `${n.padStart(shortIdLength, '0')}`，作为注册表 key。
 - 默认 `shortIdLength=2` 时容量 `n ∈ [1, 99]`，注册表 key 形如 `01`、`07`、`42`。
-- `#00`（或 `shortIdLength=1` 时 `#0`）保留、永不分配；纯数字、不引入字母。
-- 完整 `TASK-…` 入参在所有路径下行为与现状等价；`#NN` / 裸数字只是别名，不是持久化任务 ID。
+- `00`（或 `shortIdLength=1` 时 `0`）保留、永不分配；纯数字、不引入字母。
+- 完整 `TASK-…` 入参在所有路径下行为与现状等价；裸数字只是别名，不是持久化任务 ID。
+- 已移除的 `#N` / `#NN` 语法作为无效任务引用稳定拒绝。
 
 ## 生命周期
 
 | 动作      | 触发时机                                                                                     | 注册表效应                                                       |
 |-----------|---------------------------------------------------------------------------------------------|------------------------------------------------------------------|
-| alloc     | `create-task`、`import-issue`、`import-codescan`、`import-dependabot`                       | 分配最小可用 `#NN`，写入注册表。                                  |
-| resolve   | 生命周期 SKILL（`analyze-task` / `plan-task` / `code-task` / `review-*` / `commit` / …）    | `#NN` → 完整 task id 查询，不分配。                              |
+| alloc     | `create-task`、`import-issue`、`import-codescan`、`import-dependabot`                       | 分配最小可用 `NN`，写入注册表。                                  |
+| resolve   | 生命周期 SKILL（`analyze-task` / `plan-task` / `code-task` / `review-*` / `commit` / …）    | `NN` → 完整 task id 查询，不分配。                              |
 | release   | `complete-task`、`cancel-task`、`block-task`、`close-codescan`、`close-dependabot`          | 从注册表移除。                                                   |
 | re-alloc  | `restore-task`                                                                              | 重新分配（可能与历史不同），写入注册表。                         |
 
@@ -32,7 +31,7 @@
 // .agents/.airc.json
 {
   "task": {
-    "shortIdLength": 2  // 默认；容量 = 99（#01–#99）。改为 3 时容量 = #001–#999。
+    "shortIdLength": 2  // 默认；容量 = 99（01–99）。改为 3 时容量 = 001–999。
   }
 }
 ```
@@ -41,12 +40,12 @@
 `task.shortIdLength`」两种修复路径；不静默扩位、不静默截断。
 切换 `shortIdLength` 配置需要先归档所有 active 任务（注册表 key 宽度依赖配置）。
 
-## `#NN` 解析作用域（按入口二分）
+## 短号解析作用域（按入口二分）
 
 | 入口                                                       | 注册表命中            | 注册表未命中                                            |
 |-----------------------------------------------------------|----------------------|--------------------------------------------------------|
 | SKILL 入参解析器（生命周期 SKILL）                          | 解析为完整 task id    | **严格报错** —— 短号不存在 / 格式错误                  |
-| `ai sandbox exec <N \| '#N'>` / `ai sandbox create <N \| '#N'>`           | 解析为完整 task id 后查 task.md 取 `branch` | **严格报错** —— 不再回退到 ls 行号或字面分支名；提示用任务短号 / `TASK-id` / 分支名 |
+| `ai sandbox exec <N>` / `ai sandbox create <N>`           | 解析为完整 task id 后查 task.md 取 `branch` | **严格报错** —— 不再回退到 ls 行号或字面分支名；提示用任务短号 / `TASK-id` / 分支名 |
 
 `list --verify` 严格只读：报告 active 目录 / 注册表 两者差异，但不修改任何状态。
 
@@ -55,10 +54,10 @@
 任意 SKILL（含 alloc / resolve / release / re-alloc 四类生命周期入口）在收到
 `{task-id}` 入参后，必须按以下契约处理：
 
-1. 如果 `{task-id}` 字面匹配 `^[#]?[0-9]+$`（裸数字 `N` 或 `#`-前缀 `#N`）：
+1. 如果 `{task-id}` 字面匹配 `^[0-9]+$`（裸数字 `N`）：
 
 ```bash
-if [[ "{task-id}" =~ ^[#]?[0-9]+$ ]]; then
+if [[ "{task-id}" =~ ^[0-9]+$ ]]; then
   # 脚本本身已输出完整错误（含 reserved / exceeds shortIdLength capacity 等场景）；
   # 调用方只需透传退出码
   task_id=$(node .agents/scripts/task-short-id.js resolve "{task-id}") || exit 1
@@ -82,7 +81,7 @@ fi
 - 短号只由显式 `alloc`（`create-task` / `import-*` / `restore-task`）分配；`resolve` / `list` / `release` 不分配，仅在执行时自动清理指向非 active 任务的 stale entry
 - 归档（complete-task / cancel-task / block-task / close-*）后注册表 entry 立即删除，短号可被新任务复用；归档后引用任务一律用完整 `TASK-…` id
 
-`resolve(<N|'#N'>)` 工作流：① 校验入参匹配 `^[#]?[0-9]+$` → ② 去前导零取
+`resolve(<N>)` 工作流：① 校验入参匹配 `^[0-9]+$` → ② 去前导零取
 数值 `n`，按 `n` 是否 `== 0`（保留）/ `> 10^shortIdLength - 1`（超容量）/
 正常 三类处理 → ③ 正常时以 `n.padStart(shortIdLength, '0')` 作为 key 查
 注册表 `ids` → ④ 命中返回完整 task id，未命中按 `list --verify` 给出修复指引退出 1。
@@ -91,15 +90,13 @@ fi
 
 - **短号不存在**：注册表中无对应 key。可能是任务已归档（短号已释放）或输入错误。退出码 1。
 - **注册表损坏**（同一 taskId 出现多次或 JSON 无法解析）：退出码 2，需人工处理。
-- **保留键**：解析后 `n == 0`（输入如 `0`、`#0`、`#00`）。退出码 1。
-- **超容量**：解析后 `n > 10^shortIdLength - 1`（如 `shortIdLength=2` 下 `100` 或 `#100`）。退出码 1。
-- **参数格式错误**：入参既不是 `^[#]?[0-9]+$` 也不是 `TASK-id`（如 `#abc`、`#`、`5.5`）。退出码 1。
+- **保留键**：解析后 `n == 0`（输入如 `0`、`00`）。退出码 1。
+- **超容量**：解析后 `n > 10^shortIdLength - 1`（如 `shortIdLength=2` 下 `100`）。退出码 1。
+- **参数格式错误**：入参既不是 `^[0-9]+$` 也不是 `TASK-id`（如 `#1`、`#abc`、`#`、`5.5`）。退出码 1。
 
-## 跨 TUI 引号要求
+## 跨 TUI 使用
 
-裸数字 `N` 在所有 shell 与 TUI 中都安全无需引号，推荐写法：
+裸数字 `N` 在所有 shell 与 TUI 中都安全无需引号：
 `ai sandbox exec 11 'npm test'`、`/review-analysis 11`。
 
-`#N` / `#NN` 写法也接受；但 bash 中 `#` 是注释起始符，必须单引号：
-`ai sandbox exec '#03' 'npm test'`。Claude Code / Codex / Gemini CLI / OpenCode
-在加引号时都能把 `#NN` 字面传递到 SKILL 的 `ARGUMENTS`。
+从下一个大版本起，原 `#NN` 写法必须迁移为 `NN`；即使引用后完整传入 CLI 也会被拒绝。

package/templates/.agents/rules/testing-discipline.en.md

@@ -41,6 +41,24 @@ This mirrors "Goal-Driven Execution" in AGENTS.md: define a verifiable success c
 
 ## Project-specific test policy
 
-Keep repository-specific commands, directory conventions, coverage thresholds, CI integration, and reporting services in the project's own test documentation. Before adding a test, inspect that local policy and place the test in the layer that matches its observable scope and runtime cost.
+Complete each item below for this repository. Record the chosen behavior and its boundaries so contributors can select and validate tests consistently.
 
-If the project does not define a layered test suite, use its complete test command for RED and GREEN verification. Do not invent a test hierarchy or coverage gate as part of an unrelated change.
+### 1. Test commands
+
+> TODO: Document the complete test command and any faster commands used during development.
+
+### 2. Test directories or tiers
+
+> TODO: Document the test directories or tiers and the rule for choosing among them.
+
+### 3. Coverage
+
+> TODO: Document how coverage is collected, any thresholds, and whether coverage blocks changes.
+
+### 4. Continuous integration
+
+> TODO: Document which CI checks run tests and which checks are blocking or informational.
+
+### 5. Reporting services
+
+> TODO: Document any external reporting services, badges, or artifacts and whether they affect acceptance.

package/templates/.agents/rules/testing-discipline.zh-CN.md

@@ -41,6 +41,24 @@ assert.match(content, /^name: code-task$/m);         // 正向断言已足够
 
 ## 项目级测试策略
 
-仓库特定的命令、目录约定、覆盖率阈值、CI 集成和报告服务应记录在项目自己的测试文档中。新增测试前先读取该策略，并按测试的可观察范围与运行成本选择对应层级。
+请为本仓库填写以下各项，记录选定行为及其边界，以便贡献者一致地选择并验证测试。
 
-如果项目没有定义分层测试套件，RED 与 GREEN 验证都使用项目的完整测试命令。不要在无关改动中自行引入测试层级或覆盖率门禁。
+### 1. 测试命令
+
+> TODO: 记录完整测试命令，以及开发期间使用的可选快速命令。
+
+### 2. 测试目录或层级
+
+> TODO: 记录测试目录或层级，以及选择对应目录或层级的规则。
+
+### 3. 覆盖率
+
+> TODO: 记录覆盖率采集方式、阈值，以及覆盖率是否阻塞变更。
+
+### 4. 持续集成
+
+> TODO: 记录运行测试的 CI 检查，以及哪些检查属于阻塞项或信息项。
+
+### 5. 报告服务
+
+> TODO: 记录外部报告服务、徽章或构件，以及它们是否影响验收。

package/templates/.agents/scripts/lib/agent-infra-package.js

@@ -4,7 +4,6 @@ import path from "node:path";
 import { fileURLToPath } from "node:url";
 
 const PACKAGE_NAME = "@fitlab-ai/agent-infra";
-const RUNTIME_RELATIVE_PATH = "runtime/platform-adapters/platform-sync.github.js";
 const COMMAND_NAMES = ["ai", "agent-infra"];
 
 function canonicalize(candidate) {
@@ -37,16 +36,10 @@ function inspectPackageRoot(candidate, source) {
     };
   }
 
-  const runtimePath = path.join(canonicalRoot, RUNTIME_RELATIVE_PATH);
-  if (!fs.existsSync(runtimePath)) {
-    return { source, candidate: canonicalRoot, reason: `runtime not found at ${runtimePath}` };
-  }
-
   return {
     source,
     candidate: canonicalRoot,
     packageRoot: canonicalRoot,
-    runtimePath,
     templateRoot: path.join(canonicalRoot, "templates")
   };
 }
@@ -91,7 +84,6 @@ function resolveAgentInfraPackage(options = {}) {
   const platform = options.platform || process.platform;
   const startPath = options.startPath || fileURLToPath(import.meta.url);
   const attempts = [];
-
   const tryRoot = (candidate, source) => {
     const inspected = inspectPackageRoot(candidate, source);
     attempts.push(inspected);
@@ -126,7 +118,7 @@ function resolveAgentInfraPackage(options = {}) {
     }
   }
 
-  return { packageRoot: null, runtimePath: null, templateRoot: null, attempts };
+  return { packageRoot: null, templateRoot: null, attempts };
 }
 
 function formatAgentInfraPackageError(result) {