Compare commits
11
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
2349db5a1c | ||
|
|
9568b9c787 | ||
|
|
106922d530 | ||
|
|
a3ef205489 | ||
|
|
97c56212df | ||
|
|
c0ce4c5c3c | ||
|
|
1d86359767 | ||
|
|
56aa3e832f | ||
|
|
9136894837 | ||
|
|
096a85e638 | ||
|
|
2a6097528a |
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"name": "jsc-hooks",
|
||||
"version": "0.3.8",
|
||||
"version": "0.4.2",
|
||||
"description": "跨 CLI hooks:STE100 語言強制、工時計時、技能用量記錄、SDLC 模型鎖、版本前置檢查、註解範圍守門、繁中編碼守門、部署後強制重啟、寫入與提交閘門",
|
||||
"skills": "./skills",
|
||||
"author": {
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
{
|
||||
"hooks": "./hooks/codex-hooks.json",
|
||||
"name": "jsc-hooks",
|
||||
"version": "0.3.8",
|
||||
"version": "0.4.2",
|
||||
"description": "跨 CLI hooks:STE100 語言強制、工時計時、技能用量記錄、SDLC 模型鎖、版本前置檢查、註解範圍守門、繁中編碼守門、部署後強制重啟、寫入與提交閘門",
|
||||
"skills": "./skills",
|
||||
"jsc": {
|
||||
|
||||
@@ -169,8 +169,9 @@ Claude 由 `hooks/hooks.json` 自動接線九支 hook;其他 CLI 用 `hooks-in
|
||||
| --- | --- |
|
||||
| `tools/jsc-wrap.sh` | 沒有完整 hook 系統的 CLI 的包裝啟動器:匯出 `JSC_CLI`、`JSC_SESSION_ID`,前後接 `session-timer.sh`,結束時自動跑 `scan-logs.sh` 回填,再依序跑一次 `comment-scope.sh sweep` 與 `lang-guard.sh sweep` 掃整個 git 工作區的註解範圍與繁中編碼(copilot 與 antigravity 沒有任何逐輪事件,整個工作階段只有這裡掃得到)。兩次收尾掃描一律不影響結束碼:包裝器原樣回傳 CLI 自己的結束碼,`sweep` 命中只把警告印到 stderr。`JSC_CLI` 存 CLI 代號,實際執行的是對應的執行檔(antigravity 是 agy、kiro 是 kiro-cli) |
|
||||
| `tools/scan-logs.sh` | 離線回填:解析 copilot、antigravity、codex 的原生日誌,把技能用量與階段界線補進 `$JSC_HOME`,重掃不重複 |
|
||||
| `tools/report-error.sh` | 失敗回報流程:把一筆 hook 或工具異常寫成 wiki 的 `ERROR_{HASH}`,並在 `ERROR_CONTENTS` 附上一列索引。目錄頁一律先讀回舊頁再附加新列、整頁寫回,不整頁覆蓋:只有 `wiki-get` 回 4(頁面真的不存在)才用範本建新頁,回 7(金鑰失效)或 8(其他 API 失敗)代表舊內容未知,放棄目錄頁寫入並以 exit 4 回報,免得拿範本蓋掉所有既有列。目錄頁指向異常頁的連結用 `gitea.sh wiki-url` 的絕對網址,跨存取庫的 `[[頁名]]` 解不開。網址在異常頁寫成功之後才取:頁名的 hash 帶時間戳,每次回報都是全新的頁,寫進去之前查一定是 404,先查就只拿得到空字串。取不到網址時只印頁名,原因走 stderr,結束碼照舊回 0。wiki 位置分兩次解析:異常頁走 `jsc-gitea` 的 `gitea.sh wiki-repo ERROR`,目錄頁走 `gitea.sh wiki-repo CONTENTS`,兩者是兩個不同的存取庫。異常頁的存取庫解不出來就整支安靜降級;只有目錄頁的存取庫解不出來,就只寫異常頁、跳過目錄頁更新,仍回 exit 0。由操作者手動執行,或由 `hooks-install` 在 `wire-cli.sh` 回報 `status=failed` 時執行;**不接在失敗的 hook 上自動觸發**(hook 一律安靜 exit 0,自我回報會疊出迴圈) |
|
||||
| `tools/report-error.sh` | 失敗回報流程:把一筆 hook 或工具異常寫成 wiki 的 `ERROR_{HASH}`,並在 `ERROR_CONTENTS` 附上一列索引。目錄頁一律先讀回舊頁再附加新列、整頁寫回,不整頁覆蓋:只有 `wiki-get` 回 4(頁面真的不存在)才用範本建新頁,回 7(金鑰失效)或 8(其他 API 失敗)代表舊內容未知,放棄目錄頁寫入並以 exit 4 回報,免得拿範本蓋掉所有既有列。目錄頁那一列指向異常頁,連結一律寫成 `[{文字}]({連結})`,網址取 `jsc-gitea` 的 `gitea.sh wiki-url` 印出的那一個,不自己組路徑。寫進那一格之前,先把那個網址交給 `jsc-gitea` 的 `tools/link-check.sh` 驗一次,結束碼 0 才寫連結;`link-check.sh` 的路徑由已經解出來的 `gitea.sh` 推得,兩支同一個 tools 目錄。驗不過(含找不到 `link-check.sh`、`GITEA_HOST` 未設定回 3、金鑰失效回 7)就只在那一格留純文字頁名,那一列照寫、異常頁照寫、結束碼照舊,原因走 stderr——回報失敗不該再變成一次失敗。網址在異常頁寫成功之後才取:頁名的 hash 帶時間戳,每次回報都是全新的頁,寫進去之前查一定是 404,先查就只拿得到空字串。取不到網址時只印頁名,原因走 stderr,結束碼照舊回 0。wiki 位置分兩次解析:異常頁走 `jsc-gitea` 的 `gitea.sh wiki-repo ERROR`,目錄頁走 `gitea.sh wiki-repo CONTENTS`,兩者是兩個不同的存取庫。異常頁的存取庫解不出來就整支安靜降級;只有目錄頁的存取庫解不出來,就只寫異常頁、跳過目錄頁更新,仍回 exit 0。由操作者手動執行,或由 `hooks-install` 在 `wire-cli.sh` 回報 `status=failed` 時執行;**不接在失敗的 hook 上自動觸發**(hook 一律安靜 exit 0,自我回報會疊出迴圈) |
|
||||
| `tools/wire-cli.sh` | 單一 CLI 的 hook 生命週期,共四個用法。`{cli}` 是接線:先建立或更新 `$JSC_HOME/current/jsc-hooks` 指向目前這版 plugin,接著把對應的設定編輯、包裝別名安裝、hook 檔建立成穩定路徑,皆以 `<!-- jsc-hooks -->`(或 `# jsc-hooks`)標記整段重寫,重跑等同先移除再重裝;寫完每個檔案會重讀驗證位置正確才回報成功(codex 的 `notify` 必須是根層鍵、`.codex-plugin/plugin.json` 的 matcher 必須是 `Bash`、copilot 必須是小寫 `skill` 且沒有第二種大小寫的事件名、antigravity 的 matcher 必須帶錨點 `^view_file$` 且有 `PreInvocation`、kiro 的 agent JSON 必須成對且 `hooks`、`resources`、`tools` 在最上層並含兩層 `skill://` glob),也會確認寫入路徑能解到既有腳本。matcher 本身要單獨驗:鍵在、matcher 卻錯的形態最難查,回報會說接好了,實際一次都不會被叫用。檔案系統不能建立 symlink 時,會明確回報並退回目前根目錄,不會靜默寫出壞路徑。`status=wired\|degraded\|skipped\|failed` 回報接線結果。`purge {cli}` 是移除:把該 CLI 的**所有** hook 清掉,含非 jsc 的第三方項目,動到的檔案先原樣備份到 `$JSC_HOME/backup/hooks/{cli}/{yyyyMMdd_HHmmss}/`,備份失敗就不移除;移除標記段落時會先去掉標記行前後空白,所以縮排或尾端補空白的 jsc 區塊一樣會移除;移除後重讀驗證,驗不過自動還原備份,以 `status=purged\|skipped\|failed` 回報。`smoke {cli}` 是執行期冒煙測試:九支 hook 的每個接線模式各跑一次,非零退出即為錯誤,另外把五支 CLI 的真實負載各餵進 `skill-name.sh` 一次驗技能名解析、四種阻擋形態各驗一次 `deny.sh`,再把那些負載直接餵進 `restart-gate.sh` 驗「解析→判定→輸出形態」整條串得起來(含 fail-open、豁免放行與 kiro 的注入路徑)——前兩組分開看都會顯示正常,中間接不上照樣是全程放行,那正是先前三支 CLI 失效的樣子;另外用一份暫時的 `$JSC_HOME` 狀態檔把模型來源與階段鎖、工作包歸屬、部署後重啟閘門與寫入提交閘門的每條判定路徑各跑一次並比對結束碼(模型來源的每個案例各自指定 CLI 代號,不跟著這一輪接線的 CLI 走——偵測鏈已依 CLI 分流;「不知道能力就擋下」的三種情形連訊息裡的逃生門一起驗,只比結束碼的話訊息漏掉逃生門也是綠燈),再用一份暫時的 `HOME`(假的 `installed_plugins.json` 與各 plugin 的 manifest)把 `version-guard.sh` 相依版本檢查的每條路徑跑一次——相依落後的擋人與訊息內容、相等與超前的放行、豁免技能在相依落後時照樣放行、四種 fail-open、逃生門,另加一條回歸:多行縮排的 manifest,`jsc.requires` 的最後一個鍵也要解得到。驗的是判定結果本身,不只是腳本跑得完(例外有四個:`sdlc-gate.sh check` 的 exit 2 是階段鎖的設計行為,`comment-scope.sh`、`lang-guard.sh` 掃描模式與 `write-guard.sh` 三種模式的 exit 2 是命中違規的設計行為——`sweep` 在髒工作區本來就會回 2,`write-guard.sh` 在機器剛好鎖在 `plan` 階段時也會回 2,都不算 hook 壞掉),以 `status=ok\|failed` 回報。**結果行數由腳本自己數、自己斷言**:`status=` 之後緊接一行 `lines<TAB>{數量}`,那是其後 `[jsc]` 結果行的實際條數,與腳本內逐類宣告的預期條數比對,不符就回非零。判定路徑增減時只改腳本裡的預期值,散文一律引用這一行,不另外抄一份數字。`status {cli}` 是唯讀盤點:只讀設定檔判斷段落與 matcher 對不對,不寫檔也不執行 hook,claude、codex、copilot、antigravity 回 `wired`,kiro 回 `degraded` 並在 `reason` 講明那是 CLI 限制;每個接線點印一行 `item<TAB>{項目}<TAB>{路徑}<TAB>{present\|missing\|unverified}`,也會把帶版號快取路徑、開發存取庫路徑與不存在的腳本列為缺項。狀態有三格不是兩格:`unverified` 是「這一項驗不了」,只有 `missing` 才算缺項——`kiro-cli agent validate` 在沒登入時印的是環境問題,不是這個檔案的問題,報 `present` 會讓沒驗到的東西看起來像通過,報 `missing` 會把沒登入算成接線缺漏;`status claude` 讀 Claude Code 實際載入的 `installed_plugins.json`,不再檢查目前腳本旁邊那份 `hooks.json`。體檢類技能(`/jsc-cli:doctor`)只能用這個子命令,另外三個都會動到環境;那道限制另有程式層把關,`JSC_READONLY=1` 之下只准 `status` 與 `smoke`,`purge` 與接線一律以 exit 6 拒絕並回報 `status=readonly`,環境不會被動到 |
|
||||
| `tools/report-status.sh` | 技能與 hook 的執行狀態事件流,寫進 `$JSC_HOME/usage/events.jsonl`,一次一行。`skill-start`、`skill-end`、`hook-end` 三個記錄子命令;`drain` 印出上次排空之後的新事件(位移存在 `usage/scan-state/events.offset`,檔案比位移小就當作輪替過、從頭讀,不比對 inode——五支 CLI 與容器裡的行程看到的 inode 不保證一致);`rotate` 超過 5 MiB 就改名成 `.1` 並把位移歸零,只留一份舊的。`status` 是 `ok`、`blocked`、`failed`、`degraded`、`aborted` 五選一。**三個記錄子命令一律回 0,寫檔失敗也是 0**:回報機制自己壞掉,不可以讓被回報的東西跟著壞——hook 的結束碼是閘門的判準,被記錄動到就等於閘門行為被記錄改寫。參數檢查是例外,那是呼叫端的程式錯誤,寫進去只會汙染事件流,所以以 2 擋在記錄之前。本檔不讀 stdin:技能由 Bash 呼叫它,stdin 可能是還沒關閉的管線,讀下去會卡住宿主,所有資訊一律走參數。輪替不放在每次寫入,那等於每次提示多一次系統呼叫;改由巡檢排空之後呼叫。為什麼不直接寫 wiki:hook 每次提示都跑,網路寫入會拖垮宿主 CLI,而且失敗的 hook 自我回報會疊出迴圈,`report-error.sh` 因此刻意不接在失敗的 hook 上,這裡沿用同一條線 |
|
||||
| `tools/scan-hook-errors.sh` | 掃 CLI 原生紀錄找 hook 的執行期錯誤(接線寫對、跑起來出錯)。只有 claude 有 hook 結果紀錄,掃 `~/.claude/projects/**/*.jsonl` 的 `hook_non_blocking_error` 與非空 `hookErrors`;codex、copilot、antigravity、kiro 沒有等價紀錄,一律回報 `unavailable` 並指向 `wire-cli.sh smoke {cli}`。每筆錯誤附加一行 JSON 到 `$JSC_HOME/errors/hooks.jsonl`,`jsc` 欄位標明是不是 jsc 自己的 hook(第三方 hook 的錯誤只回報,不由 jsc 修正);去重與 `scan-logs.sh` 同法,重掃只讀新增段落,以 `status=clean\|errors\|unavailable` 回報 |
|
||||
|
||||
## 失敗回報範本
|
||||
@@ -181,7 +182,7 @@ Claude 由 `hooks/hooks.json` 自動接線九支 hook;其他 CLI 用 `hooks-in
|
||||
| 範本 | 用途 |
|
||||
| --- | --- |
|
||||
| `templates/error-page.md` | 單筆 hook 異常頁 `ERROR_{HASH}`,記錄當次失敗的觸發條件、錯誤摘要與處理結果。 |
|
||||
| `templates/error-contents.md` | 異常目錄 `ERROR_CONTENTS`,彙整所有異常頁,方便先看最新問題再往下追。落在目錄專用存取庫,一律 upsert 附加,連結用絕對網址。 |
|
||||
| `templates/error-contents.md` | 異常目錄 `ERROR_CONTENTS`,彙整所有異常頁,方便先看最新問題再往下追。落在目錄專用存取庫,一律 upsert 附加,連結一律寫成 `[{文字}]({連結})` 且先過 `link-check.sh` 驗過才寫。 |
|
||||
|
||||
## Skills 目錄
|
||||
|
||||
|
||||
@@ -120,6 +120,7 @@ if [ "${JSC_ASSISTANT_GATE:-}" = "off" ]; then
|
||||
fi
|
||||
|
||||
HERE=$(dirname "$0"); . "$HERE/lib.sh"
|
||||
hook_trace "assistant-gate ${1:-}"
|
||||
|
||||
read_stdin
|
||||
|
||||
@@ -200,5 +201,8 @@ esac
|
||||
printf '%s\n' "$second"
|
||||
printf '仍可使用:/jsc-assist:*、/jsc-hooks:repair、/jsc-hooks:hooks-install、/jsc-cli:doctor、/jsc-cli:setup、/jsc-cli:deploy、/jsc-cli:models、/jsc-gitea:wiki、/jsc-ask:ask、/jsc-git:commit、/jsc-git:pr(啟動助理與修環境這兩條路徑要永遠走得通,包括它們轉呼叫的下一層)\n'
|
||||
printf '確定要略過閘門:JSC_ASSISTANT_GATE=off\n'
|
||||
# 這條路徑是「已經擋下」,但輸出形態依 CLI 而定:antigravity 走 stdout 的 deny JSON、
|
||||
# kiro 只印警告,兩者的結束碼都是 0。不覆寫狀態的話,事件流會把擋下記成放行。
|
||||
JSC_EVENT_STATUS=blocked
|
||||
} | sh "$HERE/deny.sh" "$(cli_name)"
|
||||
exit $?
|
||||
|
||||
@@ -25,6 +25,7 @@
|
||||
set -u
|
||||
|
||||
. "$(CDPATH= cd -- "$(dirname -- "$0")" && pwd)/lib.sh" 2>/dev/null || true
|
||||
command -v hook_trace >/dev/null 2>&1 && hook_trace "comment-scope ${1:-}"
|
||||
|
||||
[ "${JSC_COMMENT_SCOPE:-on}" = "off" ] && exit 0
|
||||
|
||||
|
||||
@@ -75,6 +75,7 @@
|
||||
# 2。這一點的後果與 restart-gate.sh 不同:那支接在 PreToolUse 上,回 2 等於無聲擋下每一次
|
||||
# 技能呼叫;這支沒接任何 hook,回 2 只會讓呼叫端收到「心跳判不出來」,擋不到任何人。
|
||||
HERE=$(dirname "$0"); . "$HERE/lib.sh"
|
||||
hook_trace "heartbeat ${1:-}"
|
||||
|
||||
# 這支永遠不讀標準輸入,但 session_id() 會去看 STDIN_JSON。先設成空字串,讓它直接走環境
|
||||
# 變數那條路,不會因為變數沒定義而拿到不確定的值。
|
||||
|
||||
@@ -32,6 +32,7 @@
|
||||
set -u
|
||||
|
||||
. "$(CDPATH= cd -- "$(dirname -- "$0")" && pwd)/lib.sh" 2>/dev/null || true
|
||||
command -v hook_trace >/dev/null 2>&1 && hook_trace "lang-guard ${1:-}"
|
||||
|
||||
[ "${JSC_LANG_GUARD:-on}" = "off" ] && exit 0
|
||||
|
||||
|
||||
@@ -263,3 +263,59 @@ cli_bin() { # $1=CLI 代號
|
||||
|
||||
now_epoch() { date +%s; }
|
||||
now_iso() { date -u +%Y-%m-%dT%H:%M:%SZ; }
|
||||
|
||||
# --- 執行狀態事件流 ---
|
||||
#
|
||||
# 每支 hook 與每支技能的執行結果都寫進 $JSC_HOME/usage/events.jsonl,助理巡檢時排空。
|
||||
# 為什麼不直接寫 wiki:hook 每次提示都跑,網路寫入會拖垮宿主 CLI;而且失敗的 hook
|
||||
# 自我回報會疊出迴圈,report-error.sh 因此刻意不接在失敗的 hook 上,這裡沿用同一條線。
|
||||
#
|
||||
# 兩條硬規則,違反哪一條這套機制都會反過來害到被它記錄的東西:
|
||||
# 一、一行一次 printf,且長度壓在 4096 位元組內。五支 CLI 併發時,單次 O_APPEND
|
||||
# 寫入才不會互相插隊;拆成多次 printf 就會交錯成無法解析的行。detail 因此要截斷。
|
||||
# 二、寫入失敗一律吞掉,不得改變呼叫端的結束碼。回報機制自己壞掉,不可以讓被回報的
|
||||
# 東西跟著壞——hook 的結束碼是閘門的判準,被記錄動到就等於閘門行為被記錄改寫。
|
||||
|
||||
# JSON 字串值跳脫:只處理反斜線、雙引號與會拆行的字元。這三類不處理就會寫出解析不了的行。
|
||||
json_escape() {
|
||||
printf '%s' "$1" | sed -e 's/\\/\\\\/g' -e 's/"/\\"/g' | tr -d '\n\r\t'
|
||||
}
|
||||
|
||||
# emit_event <kind> <name> <phase> <status> <exit> [ms] [detail]
|
||||
emit_event() {
|
||||
_ek="$1"; _en="$2"; _ep="$3"; _es="$4"; _ex="$5"; _em="${6:-}"; _ed="${7:-}"
|
||||
# detail 截到 200 字元:長內容是硬規則一的主要威脅,來源不可信就先砍再寫。
|
||||
[ -n "$_ed" ] && _ed=$(printf '%s' "$_ed" | cut -c1-200)
|
||||
_ems=""
|
||||
[ -n "$_em" ] && _ems=$(printf ',"ms":%s' "$_em")
|
||||
_eds=""
|
||||
[ -n "$_ed" ] && _eds=$(printf ',"detail":"%s"' "$(json_escape "$_ed")")
|
||||
printf '{"ts":"%s","cli":"%s","session":"%s","kind":"%s","name":"%s","phase":"%s","status":"%s","exit":%s%s%s}\n' \
|
||||
"$(now_iso)" "$(cli_name)" "$(session_id)" "$_ek" "$(json_escape "$_en")" \
|
||||
"$_ep" "$_es" "$_ex" "$_ems" "$_eds" \
|
||||
>> "$JSC_HOME/usage/events.jsonl" 2>/dev/null || true
|
||||
}
|
||||
|
||||
# 結束碼推 status。各 hook 的 2 一律是「擋下」的設計行為,不是壞掉。
|
||||
hook_status_of() {
|
||||
case "$1" in
|
||||
0) printf ok ;;
|
||||
2) printf blocked ;;
|
||||
*) printf failed ;;
|
||||
esac
|
||||
}
|
||||
|
||||
# hook_trace <名稱> — 裝一個 EXIT trap,腳本不論從哪一個 exit 離開都記一筆。
|
||||
#
|
||||
# 為什麼用 trap 而不是逐點改:這幾支 hook 的 exit 點很多,sdlc-gate.sh 一支就有五十幾個。
|
||||
# 逐點換成「記錄再離開」要改動每一條判定路徑,而那些路徑正是閘門的判準;為了加一行紀錄
|
||||
# 去動閘門,風險遠大於收益。trap 只加一行,且涵蓋每一條離開路徑,含 set -e 的中途失敗。
|
||||
#
|
||||
# 狀態預設由結束碼推。推不出來的由 hook 自己在離開前設 JSC_EVENT_STATUS 覆寫——
|
||||
# version-guard.sh 就有這種情形:antigravity 走 stdout 的 deny JSON、kiro 只印警告,
|
||||
# 兩者擋下時結束碼都是 0,單看結束碼會把「已經擋下」記成「放行」。
|
||||
hook_trace() {
|
||||
JSC_EVENT_NAME="$1"
|
||||
JSC_EVENT_STATUS=""
|
||||
trap '_rc=$?; emit_event hook "$JSC_EVENT_NAME" end "${JSC_EVENT_STATUS:-$(hook_status_of "$_rc")}" "$_rc"' EXIT
|
||||
}
|
||||
|
||||
@@ -120,6 +120,7 @@
|
||||
#
|
||||
# 逃生門:JSC_RESTART_GATE=off 完全略過這道閘門。
|
||||
HERE=$(dirname "$0"); . "$HERE/lib.sh"
|
||||
hook_trace "restart-gate ${1:-}"
|
||||
|
||||
STATE_DIR="$JSC_HOME/restart-required.d"
|
||||
# 舊格式的單一狀態檔。只為過渡而讀,可移除的時機見檔頭「舊檔相容」。
|
||||
@@ -249,5 +250,8 @@ info=""
|
||||
printf '重新啟動:結束 %s 再重新開啟一次,狀態檔 %s 會在新工作階段開始時自動清除。\n' \
|
||||
"$bin" "$state"
|
||||
printf '仍可使用:/jsc-cli:deploy、/jsc-hooks:hooks-install、/jsc-hooks:repair、/jsc-gitea:wiki、/jsc-log:worklog、/jsc-log:learn、/jsc-meta:*、/jsc-ask:ask、/jsc-git:pr、/jsc-git:commit(部署後的異動報告與工作日誌要寫得完,hook 壞掉也要修得回來) | 確定要略過閘門:JSC_RESTART_GATE=off\n'
|
||||
# 這條路徑是「已經擋下」,但輸出形態依 CLI 而定:antigravity 走 stdout 的 deny JSON、
|
||||
# kiro 只印警告,兩者的結束碼都是 0。不覆寫狀態的話,事件流會把擋下記成放行。
|
||||
JSC_EVENT_STATUS=blocked
|
||||
} | sh "$HERE/deny.sh" "$(cli_name)"
|
||||
exit $?
|
||||
|
||||
@@ -123,6 +123,7 @@
|
||||
# 刻意的例外——鎖存在且不合規時 exit 2 擋下。只用提示注入的話模型可以無視,閘門形同虛設。
|
||||
# 無鎖、或資料不足無法判定時,仍照舊 exit 0 安靜降級。
|
||||
HERE=$(dirname "$0"); . "$HERE/lib.sh"
|
||||
hook_trace "sdlc-gate ${1:-}"
|
||||
# 只有需要 stdin JSON 的子命令才讀它:模型判定要 transcript_path,session 判定要 session_id。
|
||||
# wp-lock、wp-unlock、wp-claim、wp-unclaim、wp-report 兩者都不需要,而 read_stdin 在標準輸入
|
||||
# 是管線又沒人關閉時會一直等——工具腳本(jsc-sdlc 的 wp-gate.sh)轉呼叫這些子命令時就這樣整支
|
||||
|
||||
@@ -25,6 +25,7 @@
|
||||
# 清除的範圍是「跑到這一支腳本的那個 CLI 自己那一份狀態檔」,由 restart-gate.sh clear 認定,
|
||||
# 這裡不必也不能過問:這個工作階段開始的只有一支 CLI,別支沒重啟,閘門要留著。
|
||||
HERE=$(dirname "$0"); . "$HERE/lib.sh"
|
||||
hook_trace "session-timer ${1:-}"
|
||||
read_stdin
|
||||
sid=$(session_id)
|
||||
|
||||
|
||||
@@ -12,6 +12,7 @@
|
||||
# 唯一的非零來源同 session-timer.sh:本檔以 `. "$HERE/lib.sh"` 載入,沒有接 `|| true`,
|
||||
# lib.sh 讀不到時 sh 會就地結束並回 2。
|
||||
HERE=$(dirname "$0"); . "$HERE/lib.sh"
|
||||
hook_trace "skill-usage ${1:-}"
|
||||
read_stdin
|
||||
skill="${JSC_SKILL:-$(json_str skill)}"
|
||||
[ -n "$skill" ] || exit 0
|
||||
@@ -25,4 +26,10 @@ if [ -n "$last" ]; then
|
||||
"$ts" "$cli" "$sid" "$last" "$skill" >> "$JSC_HOME/usage/chains.jsonl"
|
||||
fi
|
||||
printf '%s' "$skill" > "$last_f"
|
||||
|
||||
# 技能的 start 事件在這裡發,不必改任何 SKILL.md:這支接在技能指示載入之後,那一刻
|
||||
# 就是「技能開始跑」。end 只能由技能自己在收尾步驟寫——本 hook 觸發時,技能的實際工作
|
||||
# 還在後面的模型輪次,看不到成敗。有 start 沒有配對的 end,就是那一輪中止了。
|
||||
emit_event skill "$skill" start ok 0
|
||||
|
||||
exit 0
|
||||
|
||||
@@ -101,6 +101,7 @@
|
||||
# 再呼叫一次 report,這裡刻意不混印,免得 cut 取值被表格內容打亂。
|
||||
# recommend 只讀不擋,永遠 exit 0:判定結果只看那一行的第二欄。
|
||||
HERE=$(dirname "$0"); . "$HERE/lib.sh"
|
||||
hook_trace "version-guard ${1:-}"
|
||||
|
||||
REG="$HOME/.claude/plugins/installed_plugins.json"
|
||||
MK="$HOME/.claude/plugins/known_marketplaces.json"
|
||||
@@ -354,6 +355,9 @@ deny() { # $1=訊息
|
||||
{ printf '[jsc][版本檢查][ERR]:%s\n' "$1"
|
||||
printf '更新指令:%s\n' "$(update_cmd "$domain")"
|
||||
printf '更新整組:/jsc-cli:deploy | 確定要略過檢查:JSC_VERSION_GUARD=off\n'
|
||||
# 這條路徑是「已經擋下」,但輸出形態依 CLI 而定:antigravity 走 stdout 的 deny JSON、
|
||||
# kiro 只印警告,兩者的結束碼都是 0。不覆寫狀態的話,事件流會把擋下記成放行。
|
||||
JSC_EVENT_STATUS=blocked
|
||||
} | sh "$HERE/deny.sh" "$(cli_name)"
|
||||
exit $?
|
||||
}
|
||||
|
||||
@@ -75,6 +75,7 @@ HERE=$(CDPATH= cd -- "$(dirname -- "$0")" && pwd)
|
||||
# 的 exit 2——而 PreToolUse 的 exit 2 正是「擋下」,等於每一次寫檔與提交都被無聲擋死。
|
||||
[ -r "$HERE/lib.sh" ] || exit 0
|
||||
. "$HERE/lib.sh"
|
||||
hook_trace "write-guard ${1:-}"
|
||||
# lib.sh 沒載到時這個變數就沒人設,下面兩個模式都要用它組狀態檔路徑,補一份同樣的預設值。
|
||||
JSC_HOME="${JSC_HOME:-$HOME/.jsc}"
|
||||
|
||||
|
||||
+1
-1
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"name": "jsc-hooks",
|
||||
"version": "0.3.8",
|
||||
"version": "0.4.2",
|
||||
"description": "跨 CLI hooks:STE100 語言強制、工時計時、技能用量記錄、SDLC 模型鎖、版本前置檢查、註解範圍守門、繁中編碼守門、部署後強制重啟、寫入與提交閘門",
|
||||
"skills": "./skills/",
|
||||
"jsc": {
|
||||
|
||||
@@ -7,17 +7,17 @@
|
||||
| 項目 | 內容 |
|
||||
| --- | --- |
|
||||
| 觸發時機 | 裝好或更新完 jsc 技能組之後,要把九支 hook 接線到每一支已安裝的 CLI 時用;`jsc-cli:deploy` 收尾會把偵測到的 CLI 清單交給它。不用於撰寫新的 hook,也不用於單獨修一支壞掉的 hook,那是 `jsc-hooks:repair` 的事 |
|
||||
| 關鍵步驟 | 取得 CLI 清單(呼叫端交來的優先,沒有才自己跑 `detect-clis.sh`)、第一支 CLI 單獨跑完整條管線(它負責更新共用的 `$JSC_HOME/current/jsc-hooks` 連結)、其餘 CLI 一支一個 sub agent 並行、每支 CLI 依序走 purge、接線、status、smoke、scan 五道關卡、讀每道關卡自己印的第一行判定、任一關卡出錯就寫 `ERROR_{HASH}` 並轉給 `jsc-hooks:repair`(異常頁與索引目錄頁分屬兩個存取庫,各自解析;只解不出目錄頁的存取庫時異常頁照寫、索引跳過,回報要講明那一頁沒被索引)、逐 CLI 回報五道關卡的結果 |
|
||||
| 外部呼叫 | `tools/wire-cli.sh purge`、`tools/wire-cli.sh {cli}`、`tools/wire-cli.sh status`、`tools/wire-cli.sh smoke`、`tools/scan-hook-errors.sh`、`tools/report-error.sh`、`jsc-cli/tools/detect-clis.sh`、`jsc-hooks:repair` 技能、`jsc-gitea:wiki`(寫 `ERROR_{HASH}` 時經 `report-error.sh`);接線腳本內部另呼叫 `hooks/skill-name.sh` 與 `hooks/deny.sh` 做冒煙斷言 |
|
||||
| 完成條件 | 每一支偵測到的 CLI 都有五道關卡各一行判定,沒有任何一道回結束碼 2,smoke 的 `lines` 條數與它自己的斷言相符,claude、codex、copilot、antigravity 回 `wired` 而 kiro 回 `degraded`(CLI 擋不下技能叫用),四支非 claude 的執行期錯誤掃描一律據實回 `unavailable`,各 CLI 的形狀與觸發驗證等級分開寫進回報(codex、antigravity、kiro 形狀實證,copilot 形狀未證;kiro 觸發部分實證,其餘未驗證),而且每一筆錯誤都帶一個 `ERROR_{HASH}` 結果與一條對 `develop` 的修正 PR 連結 |
|
||||
| 可驗證跡象 | 各 CLI 的設定檔多出 jsc 段落:codex 的 `config.toml` 標記段落、`hooks/codex-hooks.json`(從 `hooks/hooks.json` 推導,matcher `Skill` 換成 `Bash`)與 `.codex-plugin/plugin.json` 指過去的 `hooks` 路徑字串、copilot 的 `~/.copilot/settings.json` 頂層 `hooks` 鍵(matcher `skill`,合併不覆寫,`enabledPlugins` 與第三方條目原樣保留)與 `$COPILOT_HOME` 底下的指引檔、antigravity 的 `~/.gemini/config/hooks.json` 的 `jsc` 段落(`PreToolUse` 為 Grouped、matcher `^view_file$`,`PreInvocation` 維持 Flat)、kiro 的 `~/.kiro/agents/jsc.json`(`hooks` 為 `agentSpawn`、`userPromptSubmit`、`stop` 三個合法事件加 `timeout_ms`、兩層 `skill://` glob 的 `resources`、明列的 `tools`,並通過 `kiro-cli agent validate`)與 `~/.kiro/settings/cli.json` 的 `chat.defaultAgent=jsc`;四支非 claude 的接線命令都以 `JSC_CLI={代號}` 前綴自帶 CLI 代號,缺了它兩道閘門解不出技能名、一律安靜放行,所以 `status` 把它列成單獨一項;另有 `$JSC_HOME/current/jsc-hooks` 符號連結建立或更新、`$JSC_HOME/backup/hooks/{cli}/{時間戳}/` 留下 purge 前的備份、出錯時 wiki 多一頁 `ERROR_{HASH}`(落在 `JSC_WIKI_REPO_ERROR` 解出的存取庫)並在索引目錄頁補一列(落在 `JSC_WIKI_REPO_CONTENTS` 解出的另一個存取庫,那一列指向異常頁的連結是絕對網址)、修正路徑留下一條對 `develop` 的 PR |
|
||||
| 關鍵步驟 | 取得 CLI 清單(呼叫端交來的優先,沒有才自己跑 `detect-clis.sh`)、第一支 CLI 單獨跑完整條管線(它負責更新共用的 `$JSC_HOME/current/jsc-hooks` 連結)、其餘 CLI 一支一個 sub agent 並行、每支 CLI 依序走 purge、接線、status、smoke、scan 五道關卡、讀每道關卡自己印的第一行判定、任一關卡出錯就寫 `ERROR_{HASH}` 並轉給 `jsc-hooks:repair`(異常頁與索引目錄頁分屬兩個存取庫,各自解析;只解不出目錄頁的存取庫時異常頁照寫、索引跳過,回報要講明那一頁沒被索引)、目錄頁那一列指向異常頁的連結一律寫成 `[{文字}]({連結})`,網址取 `gitea.sh wiki-url`,寫進去之前先過 `jsc-gitea/tools/link-check.sh`,結束碼 0 才寫連結、驗不過那一格只留純文字頁名而那一列與異常頁照寫(`report-error.sh` 內部做完,結束碼不變)、逐 CLI 回報五道關卡的結果、最後由主代理呼叫一次 `tools/report-status.sh skill-end jsc-hooks:hooks-install {status} {結束碼} {detail}` 記下整輪怎麼結束。腳本在同一個存取庫,用 `tools/` 相對路徑;這一筆只由主代理寫一次,寫在並行的各 CLI sub agent 裡會變成五筆互相矛盾的結局。腳本不在就安靜跳過,回報失敗不得變成接線失敗 |
|
||||
| 外部呼叫 | `tools/wire-cli.sh purge`、`tools/wire-cli.sh {cli}`、`tools/wire-cli.sh status`、`tools/wire-cli.sh smoke`、`tools/scan-hook-errors.sh`、`tools/report-error.sh`、`jsc-cli/tools/detect-clis.sh`、`jsc-hooks:repair` 技能、`jsc-gitea:wiki`(寫 `ERROR_{HASH}` 時經 `report-error.sh`)、`jsc-gitea/tools/gitea.sh wiki-url` 與 `jsc-gitea/tools/link-check.sh`(同樣經 `report-error.sh`,取目錄頁那一列的網址並驗它連得到);接線腳本內部另呼叫 `hooks/skill-name.sh` 與 `hooks/deny.sh` 做冒煙斷言 |
|
||||
| 完成條件 | 每一支偵測到的 CLI 都有五道關卡各一行判定,沒有任何一道回結束碼 2,smoke 的 `lines` 條數與它自己的斷言相符,claude、codex、copilot、antigravity 回 `wired` 而 kiro 回 `degraded`(CLI 擋不下技能叫用),四支非 claude 的執行期錯誤掃描一律據實回 `unavailable`,各 CLI 的形狀與觸發驗證等級分開寫進回報(codex、antigravity、kiro 形狀實證,copilot 形狀未證;kiro 觸發部分實證,其餘未驗證),每一筆錯誤都帶一個 `ERROR_{HASH}` 結果與一條對 `develop` 的修正 PR 連結,而且目錄頁那一列的連結驗不過時,回報要講明那一列只有純文字頁名、沒有連結。以上收完之後還要走完最後一步:呼叫 `report-status.sh skill-end`,狀態五選一——每一支偵測到的 CLI 五道關卡全過而且一律回 `wired` 是 `ok`,實務上等於那台機器沒有 kiro;跑完整輪但有一部分沒到 `wired` 是 `degraded`,涵蓋 kiro 只能降級接線,以及某支 CLI 接線失敗、已經轉交 `jsc-hooks:repair` 而且拿到一條對 `develop` 的 PR,還有被跳過的 CLI;關卡失敗而沒人接手是 `failed`,也就是修正技能起不來或回不出 PR,壞掉的 hook 還掛在那裡;`JSC_READONLY=1` 讓 `wire-cli.sh` 回 exit 6、一支 CLI 都沒動是 `blocked`;偵測不到任何 CLI 而主動停止是 `aborted`。腳本不在磁碟上就跳過,這一步照樣算走完 |
|
||||
| 可驗證跡象 | 各 CLI 的設定檔多出 jsc 段落:codex 的 `config.toml` 標記段落、`hooks/codex-hooks.json`(從 `hooks/hooks.json` 推導,matcher `Skill` 換成 `Bash`)與 `.codex-plugin/plugin.json` 指過去的 `hooks` 路徑字串、copilot 的 `~/.copilot/settings.json` 頂層 `hooks` 鍵(matcher `skill`,合併不覆寫,`enabledPlugins` 與第三方條目原樣保留)與 `$COPILOT_HOME` 底下的指引檔、antigravity 的 `~/.gemini/config/hooks.json` 的 `jsc` 段落(`PreToolUse` 為 Grouped、matcher `^view_file$`,`PreInvocation` 維持 Flat)、kiro 的 `~/.kiro/agents/jsc.json`(`hooks` 為 `agentSpawn`、`userPromptSubmit`、`stop` 三個合法事件加 `timeout_ms`、兩層 `skill://` glob 的 `resources`、明列的 `tools`,並通過 `kiro-cli agent validate`)與 `~/.kiro/settings/cli.json` 的 `chat.defaultAgent=jsc`;四支非 claude 的接線命令都以 `JSC_CLI={代號}` 前綴自帶 CLI 代號,缺了它兩道閘門解不出技能名、一律安靜放行,所以 `status` 把它列成單獨一項;另有 `$JSC_HOME/current/jsc-hooks` 符號連結建立或更新、`$JSC_HOME/backup/hooks/{cli}/{時間戳}/` 留下 purge 前的備份、出錯時 wiki 多一頁 `ERROR_{HASH}`(落在 `JSC_WIKI_REPO_ERROR` 解出的存取庫)並在索引目錄頁補一列(落在 `JSC_WIKI_REPO_CONTENTS` 解出的另一個存取庫,那一列的第 2 格寫成 `[{頁名}]({絕對網址})`,網址取自 `gitea.sh wiki-url` 且已經過 `link-check.sh` 驗到結束碼 0;驗不過那一格只有純文字頁名,`report-error.sh` 在 stderr 留一行 `[jsc]` 講明是哪一種原因)、修正路徑留下一條對 `develop` 的 PR 。接線完成後 `$JSC_HOME/usage/events.jsonl` 會逐行長出 `{kind:hook}` 事件,每支 hook 每次執行一筆,欄位含 `status` 與實際結束碼;跑過技能之後另有 `{kind:skill,phase:start}`。這支技能自己收尾時,同一個 `$JSC_HOME/usage/events.jsonl` 尾端會多一筆 `{kind:skill,phase:end}`,`name` 是 `jsc-hooks:hooks-install`,整輪只有一筆,`status` 與那次結局相符,`exit` 是決定結局的那道關卡的結束碼;`report-status.sh` 不在那台機器上就沒有這一筆,接線結果一字不變。事件寫不進去不影響任何 hook 的結束碼,也不影響本技能的結局 |
|
||||
|
||||
## repair
|
||||
|
||||
| 項目 | 內容 |
|
||||
| --- | --- |
|
||||
| 觸發時機 | `hooks-install` 或 `report-error.sh` 回報某一支 hook 失敗時用,或是重新接線之後那支 hook 還是一直失敗時用。不用於例行接線,也不用於與 hook 無關的修改 |
|
||||
| 關鍵步驟 | 從 `ERROR_{HASH}` 讀失敗情境(沒有頁就讀失敗的 `status=` 那一行,讀不到就停下來問)、跑 `detect-clis.sh`、每一支偵測到的 CLI 各開一個唯讀 sub agent 診斷並交回根因、要改的檔案與驗證指令、挑最小的修正改進 hooks 存取庫(技能名解析改 `hooks/skill-name.sh`、阻擋形態改 `hooks/deny.sh`,兩支是唯一真實來源,不在閘門裡各補一份)、跑 `wire-cli.sh smoke {cli}` 驗到 exit 0、跑 `sync-skill-manifest.sh .` 同步版本、以 `jsc-git:pr` 對 `develop` 開 PR |
|
||||
| 關鍵步驟 | 從 `ERROR_{HASH}` 讀失敗情境(沒有頁就讀失敗的 `status=` 那一行,讀不到就停下來問)、跑 `detect-clis.sh`、每一支偵測到的 CLI 各開一個唯讀 sub agent 診斷並交回根因、要改的檔案與驗證指令、挑最小的修正改進 hooks 存取庫(技能名解析改 `hooks/skill-name.sh`、阻擋形態改 `hooks/deny.sh`,兩支是唯一真實來源,不在閘門裡各補一份)、跑 `wire-cli.sh smoke {cli}` 驗到 exit 0、跑 `sync-skill-manifest.sh .` 同步版本、以 `jsc-git:pr` 對 `develop` 開 PR、收尾呼叫 `tools/report-status.sh skill-end jsc-hooks:repair {status} {結束碼} {detail}` 記下這次修正怎麼結束(腳本在同一個存取庫,用 `tools/` 相對路徑,比照 `tools/wire-cli.sh`;檔案不在就安靜跳過,回報失敗不得變成修正失敗) |
|
||||
| 外部呼叫 | `jsc-gitea:wiki`、`jsc-cli/tools/detect-clis.sh`、`tools/wire-cli.sh smoke`、`jsc-meta/tools/sync-skill-manifest.sh`、`jsc-git:pr`;診斷階段另以 sub agent 叫用各支已安裝的 AI CLI |
|
||||
| 完成條件 | 修正已經落在磁碟上、`wire-cli.sh smoke` 對受影響的 CLI 回 exit 0、`sync-skill-manifest.sh` 回 exit 0 而且三份 manifest 版本一致,最後拿到一條對 `develop` 的 PR 連結;開不出 PR 時要講明修正已套用但尚未合併、帶上分支名與失敗原因 |
|
||||
| 可驗證跡象 | hooks 存取庫多一個修正提交與一條推上去的分支、`develop` 上多一條 PR、三份 manifest 與 README 技能清單版本一致、`wire-cli.sh smoke` 由失敗轉為 exit 0 |
|
||||
| 完成條件 | 修正已經落在磁碟上、`wire-cli.sh smoke` 對受影響的 CLI 回 exit 0、`sync-skill-manifest.sh` 回 exit 0 而且三份 manifest 版本一致,最後拿到一條對 `develop` 的 PR 連結;開不出 PR 時要講明修正已套用但尚未合併、帶上分支名與失敗原因。每一條路線都要走完最後一步:呼叫 `report-status.sh skill-end`,狀態五選一——修正落地、smoke 回 exit 0、三份 manifest 版本一致而且拿到 PR 連結是 `ok`;smoke 過了但東西沒送出去是 `degraded`,也就是開不出 PR 只剩分支,或 manifest 沒對齊;修不好是 `failed`,也就是診斷繞回去以後 smoke 還是回 exit 4,或同步版本踩到環境錯誤,壞掉的接線還是壞的;沒有可修的項目是 `aborted`,也就是讀不到任何失敗情境。本技能豁免版本閘門與部署後重啟閘門,沒有別的閘門擋得住它,所以不會用 `blocked`。腳本不在磁碟上就跳過,這一步照樣算走完 |
|
||||
| 可驗證跡象 | hooks 存取庫多一個修正提交與一條推上去的分支、`develop` 上多一條 PR、三份 manifest 與 README 技能清單版本一致、`wire-cli.sh smoke` 由失敗轉為 exit 0;不論走哪一條路線,`$JSC_HOME/usage/events.jsonl` 尾端都會多一筆 `{kind:skill,phase:end}` 事件,`name` 是 `jsc-hooks:repair`,`status` 與那次結局相符,`exit` 是決定結局的那支工具的結束碼;`report-status.sh` 不在那台機器上就沒有這一筆,修正結果一字不變 |
|
||||
|
||||
@@ -75,8 +75,12 @@ The detailed flow **MUST run as a sub agent**; the main agent only reports the s
|
||||
5. `tools/scan-hook-errors.sh --cli {cli}` — only claude keeps hook results in its native records and can answer `clean` or `errors`; codex, copilot, antigravity and kiro answer `unavailable`, and their runtime evidence comes from the smoke stage alone. Exit 0 covers both `clean` and `unavailable`, exit 1 is `errors` and every entry with `jsc=true` goes to step 3, exit 2 is a bad CLI name.
|
||||
|
||||
Done when every detected CLI has exactly one verdict line per stage, no stage exited 2, the smoke stage's `lines` count matches its own assertion, the four non-claude CLIs are reported as `unavailable` rather than clean on the scan stage, and antigravity and kiro carry the note that their hook firing is unverified.
|
||||
3. For each error — a failed purge, a failed wiring, an `unwired` status, a failed smoke, or a scanned error with `jsc=true` — run `tools/report-error.sh --hook {script name} --exit {code} --summary "{reason}" --cli {cli}` with the script's `[jsc]` output on stdin, then hand the failure to `jsc-hooks:repair`, which **MUST run as a sub agent** and must finish by opening a PR against `develop`. Aborting the remaining installs here is allowed as long as the repair starts. The error page and the error directory page live in two different wiki repos, resolved separately: the page through `wiki-repo ERROR`, the directory through `wiki-repo CONTENTS`. Exit 0 with an `ERROR_{HASH}` page name and URL on stdout means the page was written; the same exit 0 with a `[jsc]` line on stderr still means the page landed, and that line says what is missing — either the directory repo would not resolve, so nothing indexes the page, or the page URL could not be read back, so the page name comes out on its own — carry that note into step 4. Exit 0 with no output at all means the run ended on one of the quiet-degradation reasons listed in the script's own header — no `gitea.sh` on the path, the error page's wiki repo unresolved, the hash not computed, or a temp file not created — so no page was written at all and that reason goes into step 4 instead; exit 2 means the call itself was malformed — `--hook` or `--summary` is missing — so fix the arguments and rerun the same call; exit 4 means the wiki record did not land, so report the failure text and still start the repair — a page that could not be written is no reason to leave a broken hook wired. Exit 4 covers two cases, and the report has to say which: a failed write, or the script refusing to write the error directory page because it could not read the old one back. That directory is appended to, never overwritten: every row on it is somebody else's error report, so the script reads the page, adds this run's row, and writes the whole page. Only a genuine 404 (`wiki-get` exit 4) means the page is not there yet and lets it build one from the template. An invalid key (exit 7) or any other API failure (exit 8) leaves the old rows unknown, so it skips the directory write and names the code instead — writing a fresh template over a directory it never read would erase every earlier report, with no merge and no backup behind it. A scanned error with `jsc=false` belongs to a third-party hook: report it and leave it alone. Skip this step when every CLI passed all five stages. Done when every error carries one `ERROR_{HASH}` result — a page name with its URL, a page name plus the reason the URL is missing, or the recorded reason no page was written — and one repair PR URL against `develop`.
|
||||
3. For each error — a failed purge, a failed wiring, an `unwired` status, a failed smoke, or a scanned error with `jsc=true` — run `tools/report-error.sh --hook {script name} --exit {code} --summary "{reason}" --cli {cli}` with the script's `[jsc]` output on stdin, then hand the failure to `jsc-hooks:repair`, which **MUST run as a sub agent** and must finish by opening a PR against `develop`. Aborting the remaining installs here is allowed as long as the repair starts. The error page and the error directory page live in two different wiki repos, resolved separately: the page through `wiki-repo ERROR`, the directory through `wiki-repo CONTENTS`. Exit 0 with an `ERROR_{HASH}` page name and URL on stdout means the page was written; the same exit 0 with a `[jsc]` line on stderr still means the page landed, and that line says what is missing — the directory repo would not resolve, so nothing indexes the page; the page URL could not be read back, so the page name comes out on its own; or the URL failed the reachability check, so the directory row carries the page name as plain text with no link — carry that note into step 4. Every link on that row is written as `[{text}]({url})` with the URL from `gitea.sh wiki-url`, and the script checks it with `jsc-gitea/tools/link-check.sh` before writing: exit 0 writes the link, anything else keeps the row and drops the link, and none of it changes the exit code — this is the failure-reporting path, so a failed report must never become a second failure. Exit 0 with no output at all means the run ended on one of the quiet-degradation reasons listed in the script's own header — no `gitea.sh` on the path, the error page's wiki repo unresolved, the hash not computed, or a temp file not created — so no page was written at all and that reason goes into step 4 instead; exit 2 means the call itself was malformed — `--hook` or `--summary` is missing — so fix the arguments and rerun the same call; exit 4 means the wiki record did not land, so report the failure text and still start the repair — a page that could not be written is no reason to leave a broken hook wired. Exit 4 covers two cases, and the report has to say which: a failed write, or the script refusing to write the error directory page because it could not read the old one back. That directory is appended to, never overwritten: every row on it is somebody else's error report, so the script reads the page, adds this run's row, and writes the whole page. Only a genuine 404 (`wiki-get` exit 4) means the page is not there yet and lets it build one from the template. An invalid key (exit 7) or any other API failure (exit 8) leaves the old rows unknown, so it skips the directory write and names the code instead — writing a fresh template over a directory it never read would erase every earlier report, with no merge and no backup behind it. A scanned error with `jsc=false` belongs to a third-party hook: report it and leave it alone. Skip this step when every CLI passed all five stages. Done when every error carries one `ERROR_{HASH}` result — a page name with its URL, a page name plus the reason the URL is missing, or the recorded reason no page was written — and one repair PR URL against `develop`.
|
||||
4. Report five results per CLI — purge, wiring, status, smoke, scan — each with the reason its script printed, plus the smoke `lines` count, any `ERROR_{HASH}` page name and every repair PR URL. Done when every detected CLI appears with one verdict per stage and every repair has a PR against `develop`.
|
||||
5. Record how the whole install ended. Run `tools/report-status.sh skill-end jsc-hooks:hooks-install {status} {exit} "{detail}"` — the script is in this same repo, so it takes the plain `tools/` path that every other stage above uses. **The main agent makes this one call, after every per-CLI report is in.** The per-CLI pipelines run as parallel sub agents and one skill run is one event, so a call inside those sub agents would write one line per CLI and turn the install's outcome into five contradictory ones. The gate that records a skill's start fires when the skill is loaded and can never see how it ended; without this line a finished install and an install abandoned halfway look identical afterwards, which is the whole reason the closing step exists.
|
||||
- `{status}` is one of five. `ok`: every detected CLI passed all five stages and every one of them reported `wired` — in practice that means kiro was not on the machine. `degraded`: the pipeline ran to the end and part of it did not reach `wired`. That covers kiro, which is `degraded` by design because the CLI cannot block a skill call, and it covers a CLI whose stage failed and was handed to `jsc-hooks:repair` with a PR against `develop` — the failure has an owner and a fix in flight, so the install is incomplete, not broken. A `skipped` CLI belongs here too. `failed`: a stage failed and the failure was left with nobody holding it — `jsc-hooks:repair` could not be started, or it came back with no PR — so a broken hook stays wired and nothing is going to fix it. `blocked`: `wire-cli.sh` refused with exit 6 under `JSC_READONLY=1`, so no CLI was purged or wired at all. `aborted`: step 1 detected no CLI, so there was nothing to wire and the run stopped on a precondition rather than on an error.
|
||||
- Take `{exit}` from the stage that decided the ending — the `wire-cli.sh`, `smoke` or `scan-hook-errors.sh` code — and otherwise use 0 for `ok` and 1 for every other status. `{detail}` is optional, one line, at most 200 characters: the CLI count per verdict, or the CLI and stage that failed. Never fold the five per-CLI reports into it; those go to the user in step 4.
|
||||
- Reporting never changes the install. `report-status.sh` swallows its own write failures and always exits 0, and an absent file is skipped in silence — the same rule the nine hooks follow, and for the same reason: a reporter that can fail the thing it reports on is worse than no reporter. Done when the one call was made, or the script was absent and this step was skipped without a word.
|
||||
|
||||
## Notes
|
||||
|
||||
|
||||
@@ -16,3 +16,7 @@ This skill is exempt from the version guard and the post-deploy restart gate, be
|
||||
3. Pick the smallest repair that makes the wiring pass, then apply it in the `hooks` repo. When the fix touches wiring behaviour, update `hooks/tools/wire-cli.sh`, `hooks/skills/hooks-install/SKILL.md` and `hooks/README.md` in the same change. Run `tools/wire-cli.sh smoke {cli}` for the affected CLI: exit 0 means the repair holds, exit 4 means it does not — go back to step 2 with the new output, exit 2 means a bad CLI name, so fix the name and rerun. Done when the fix is on disk and smoke exits 0.
|
||||
4. Run `jsc-meta/tools/sync-skill-manifest.sh .` from the repo root. Exit 0 means the README skill list and all three manifests carry the same new version. Exit 1 means a missing path, a missing `JSC-SKILLS` marker or an unreadable manifest — fix the named file and rerun. Exit 2 means a usage error, so pass exactly one path. Any other exit code is an environment fault, never a successful sync: stop and report it. Done when the script exits 0 and the three manifests show the same version.
|
||||
5. Commit, push and open a PR with `jsc-git:pr` against `develop`. When `jsc-git:pr` returns no PR URL, report the repair as applied but unmerged, name the branch that holds it, and hand back the failure reason — never claim a PR exists. Done when a PR URL comes back, or the branch name and the failure reason are both reported.
|
||||
6. Record how the repair ended. Run `tools/report-status.sh skill-end jsc-hooks:repair {status} {exit} "{detail}"` — the script is in this same repo, so it takes the plain `tools/` path, like `tools/wire-cli.sh` in step 3. This step runs on every route out of steps 1 to 5, the ones that stopped early included. What records a skill's start fires when the skill is loaded and cannot see how it ended, so a repair that never writes this line is indistinguishable afterwards from one that was abandoned with a hook still broken.
|
||||
- `{status}` is one of five. `ok`: the fix is on disk, `wire-cli.sh smoke` exits 0 for every affected CLI, `sync-skill-manifest.sh` exits 0 with all three manifests on the same version, and a PR URL against `develop` came back. `degraded`: the repair holds — smoke exits 0 — but the change did not get all the way out, because `jsc-git:pr` returned no PR URL and the fix is sitting on a branch, or `sync-skill-manifest.sh` left the manifests unaligned. `failed`: the hook could not be repaired. Smoke still exits 4 after the diagnosis loop of step 2 came back around, or step 4 hit an environment fault, so the broken wiring is still broken. `aborted`: there was nothing to repair — step 1 found no failure context, no `ERROR_{HASH}` page and no failed `status=` line, so the run stopped on a precondition rather than on a fault. `blocked` does not arise: this skill is exempt from the version guard and the post-deploy restart gate, which are the only two gates that could hold it, and that exemption exists precisely because it is the way back from a broken hook.
|
||||
- Take `{exit}` from whatever decided the ending — the `wire-cli.sh smoke` or `sync-skill-manifest.sh` code — and otherwise use 0 for `ok` and 1 for every other status. `{detail}` is optional, one line, at most 200 characters: the hook and CLI that were repaired, or the branch that holds an unmerged fix. Diagnosis output and diffs never go on this line.
|
||||
- Reporting never changes the repair. `report-status.sh` swallows its own write failures and always exits 0, and an absent file is skipped in silence, so a missing reporter can never be the reason a repaired hook reads as unrepaired. Done when the call was made, or the script was absent and this step was skipped without a word.
|
||||
|
||||
@@ -6,10 +6,12 @@
|
||||
>
|
||||
> 寫入語意:一列代表一次 hook 異常回報。寫入前先讀回整頁,同一筆異常已經有列就更新那一列,沒有才在文末附加一列,最後整頁寫回。一律 upsert 附加,禁止整頁覆蓋,也不得改動別人的列。
|
||||
>
|
||||
> 連結寫法:指向異常頁的連結一律用 `gitea.sh wiki-url` 產出的絕對網址。跨存取庫的 `[[頁名]]` 解不開,只會留下死連結。
|
||||
> 連結寫法:一律寫成 `[{文字}]({絕對網址})`,網址取 `jsc-gitea/tools/gitea.sh wiki-url` 印出的那一個,不自己組路徑。wiki 自己那種雙中括號寫法只在同一個 wiki 裡解得開,寫錯不會報錯,畫面上看起來像正常文字或死連結。
|
||||
>
|
||||
> 寫入前驗證:這一列要放進去的連結,先交給 `jsc-gitea/tools/link-check.sh`,結束碼 0 才把連結寫進那一格。驗不過就只留純文字頁名,那一列照寫,異常紀錄不因為一條連結整份丟掉。驗證走 API,不看網頁狀態碼——私有存取庫的網頁網址對未登入請求一律回 404,拿狀態碼判會把還在的頁判成死連結。結束碼 7 是金鑰失效,不算死連結,也不改寫任何既有列。
|
||||
|
||||
## 異常清單
|
||||
|
||||
| 時間 | 頁名 | 存取庫名稱 | 觸發 hook | 退出碼 | 摘要 |
|
||||
| --- | --- | --- | --- | --- | --- |
|
||||
| {yyyy-MM-dd HH:mm:ss} | [{error title}]({error url}) | {owner}/{repo} | {hook_name} | {exit_code} | {error_summary} |
|
||||
| {yyyy-MM-dd HH:mm:ss} | [{頁名}]({wiki-url 印出的絕對網址}) | {owner}/{repo} | {hook_name} | {exit_code} | {error_summary} |
|
||||
|
||||
+41
-11
@@ -24,6 +24,13 @@
|
||||
# 一份寫得成的異常紀錄,不該因為目錄頁沒地方放就整份丟掉。
|
||||
# 寫入 wiki 失敗才以 exit 4 回報,訊息走 stderr。
|
||||
#
|
||||
# 連結:
|
||||
# 目錄頁那一列指向異常頁,一律寫成 [{文字}]({連結}),網址取 jsc-gitea 的
|
||||
# gitea.sh wiki-url,不自己組路徑。
|
||||
# 寫入前先把那個網址交給 jsc-gitea 的 link-check.sh,結束碼 0 才把連結寫進那一列。
|
||||
# 驗不過就只留純文字頁名:那一列照寫、異常頁照寫、結束碼照舊。這一段一律不改結束碼,
|
||||
# 本腳本是失敗回報路徑,回報失敗不該再變成一次失敗。
|
||||
#
|
||||
# 結束碼: 0=已寫入異常頁並印出頁名(取得網址就一併印出),或以上列四種安靜降級原因之一
|
||||
# 結束、沒有寫出任何頁也沒有任何輸出——回報失敗不該再變成一次失敗
|
||||
# 2=用法錯誤(缺 --hook 或 --summary)
|
||||
@@ -139,8 +146,9 @@ if ! sh "$gsh" wiki-put "$wrepo" "$page" "$tmp_page" >/dev/null 2>&1; then
|
||||
exit 4
|
||||
fi
|
||||
|
||||
# 目錄頁與異常頁分屬兩個存取庫,wiki 的 [[頁名]] 只在同一個存取庫內解得開,跨庫一律解成
|
||||
# 死連結。所以目錄頁指向異常頁的連結一律用絕對網址。
|
||||
# 目錄頁那一列指向異常頁,連結一律寫成 [{文字}]({連結}),網址取 gitea.sh wiki-url。
|
||||
# wiki 自己那種雙中括號寫法只在同一個 wiki 裡解得開,寫錯不會報錯,畫面上看起來像正常
|
||||
# 文字或死連結,巡不到也修不了。
|
||||
# 網址取不到不算失敗:異常頁已經寫成功了,只是這一列少一條連結。這裡把原因記下來走 stderr,
|
||||
# 結束碼照舊——安靜降級仍是 exit 0,回報失敗不該再變成一次失敗。
|
||||
url=$(sh "$gsh" wiki-url "$wrepo" "$page" 2>/dev/null)
|
||||
@@ -161,17 +169,39 @@ emit() { # 異常頁已經寫成功,頁名一定要印;網址取不到就只
|
||||
if [ -n "$url" ]; then printf '%s %s\n' "$page" "$url"; else printf '%s\n' "$page"; fi
|
||||
}
|
||||
|
||||
row=$(printf '| %s | [%s](%s) | %s | %s | %s | %s |' \
|
||||
"$ts" "$hook 異常 $ts" "$url" "$repo" "$hook" "$code" "$summary")
|
||||
# 連結先驗證連得到,才寫進目錄頁那一列。沒驗過的連結寫進去,異常頁一樣會在目錄頁長出
|
||||
# 死連結,而目錄頁是別人查問題的入口。驗不過就只留純文字頁名,那一列照寫。
|
||||
link_cell="$page"
|
||||
if [ -n "$url" ]; then
|
||||
# link-check.sh 與 gitea.sh 同一個 tools 目錄,路徑直接由已經解出來的那一支推得,
|
||||
# 不另寫一套搜尋,兩邊才不會一支解到開發版面、一支解到安裝版面。
|
||||
lcs="$(dirname "$gsh")/link-check.sh"
|
||||
if [ ! -f "$lcs" ]; then
|
||||
echo "[jsc] 找不到 $lcs,這一列的連結沒驗過,只留頁名;$page 已建立。" >&2
|
||||
else
|
||||
sh "$lcs" "$url" >/dev/null 2>&1
|
||||
lc_code=$?
|
||||
case "$lc_code" in
|
||||
0) link_cell=$(printf '[%s](%s)' "$page" "$url") ;;
|
||||
# 7 是金鑰失效,不是死連結。金鑰過期時私有存取庫的回應與「頁不存在」分不出來,
|
||||
# 把它當成死連結就會連還在的頁一起判死。
|
||||
7) echo "[jsc] 連結驗證遇上金鑰失效(link-check.sh 回 7),不判成死連結,這一列只留頁名;$page 已建立。" >&2 ;;
|
||||
3) echo "[jsc] GITEA_HOST 未設定(link-check.sh 回 3),連結沒驗過,這一列只留頁名;$page 已建立。" >&2 ;;
|
||||
*) echo "[jsc] 連結驗不過(link-check.sh 結束碼 $lc_code),這一列只留頁名;$page 已建立。" >&2 ;;
|
||||
esac
|
||||
fi
|
||||
fi
|
||||
|
||||
row=$(printf '| %s | %s | %s | %s | %s | %s |' \
|
||||
"$ts" "$link_cell" "$repo" "$hook" "$code" "$summary")
|
||||
|
||||
build_contents() { # 用範本建一份全新的目錄頁;只有確定舊頁不存在時才可以呼叫
|
||||
fill '{yyyy-MM-dd HH:mm:ss}' "$ts" < "$ROOT/templates/error-contents.md" \
|
||||
| fill '{error url}' "$url" \
|
||||
| fill '{error title}' "$hook 異常 $ts" \
|
||||
| fill '{owner}/{repo}' "$repo" \
|
||||
| fill '{hook_name}' "$hook" \
|
||||
| fill '{exit_code}' "$code" \
|
||||
| fill '{error_summary}' "$summary" > "$tmp_list"
|
||||
# 範本的示範列整列換成本次這一列,不逐格填。連結那一格已經驗過也組好了,拆成頁名與
|
||||
# 網址兩個佔位再填,會在驗不過的時候留下一個空網址的死連結。
|
||||
ROW="$row" awk '
|
||||
index($0, "| {yyyy-MM-dd HH:mm:ss} |") == 1 { print ENVIRON["ROW"]; next }
|
||||
{ print }
|
||||
' "$ROOT/templates/error-contents.md" > "$tmp_list"
|
||||
}
|
||||
|
||||
if [ -z "$crepo" ]; then
|
||||
|
||||
Executable
+130
@@ -0,0 +1,130 @@
|
||||
#!/usr/bin/env sh
|
||||
# report-status.sh — 技能與 hook 的執行狀態事件流。
|
||||
#
|
||||
# 為什麼要有這支:現行 usage/skills.jsonl 只記「被叫用」,欄位是 {ts,cli,session,skill},
|
||||
# 沒有成敗、沒有結束碼。跑完整輪的技能與開場就中止的技能,在紀錄裡長得一模一樣。
|
||||
# hook 成功時更是完全不留紀錄,只有錯誤路徑會寫 wiki,而那條路徑刻意不自動觸發。
|
||||
#
|
||||
# 為什麼不直接寫 wiki:hook 每次提示都跑,網路寫入會拖垮宿主 CLI;失敗的 hook 自我回報
|
||||
# 還會疊出迴圈。所以一律先寫本機事件流,助理巡檢時排空、彙整、寫 MONITOR 頁。
|
||||
#
|
||||
# 用法:
|
||||
# report-status.sh skill-start <名稱>
|
||||
# report-status.sh skill-end <名稱> <status> [結束碼] [detail]
|
||||
# report-status.sh hook-end <名稱> <status> <結束碼> [detail]
|
||||
# report-status.sh drain # 印出上次排空之後的新事件
|
||||
# report-status.sh rotate # 超過上限就輪替,只留一份舊的
|
||||
#
|
||||
# <名稱>: 技能寫 {domain}:{skill},hook 寫 {腳本檔名} 加子命令,例如 sdlc-gate check。
|
||||
# <status>: ok、blocked、failed、degraded、aborted 五選一。
|
||||
# ok 完成條件全部達成
|
||||
# blocked 被閘門或前置條件擋下,沒有做事
|
||||
# failed 做到一半失敗
|
||||
# degraded 做完了但有部分沒達成
|
||||
# aborted 使用者中止,或前提不成立而主動停止
|
||||
#
|
||||
# 規則:
|
||||
# - 三個記錄子命令一律回 0,寫檔失敗也是 0。回報機制自己壞掉,不可以讓被回報的東西
|
||||
# 跟著壞——hook 的結束碼是閘門的判準,被記錄動到就等於閘門行為被記錄改寫。
|
||||
# 參數檢查是例外:那是呼叫端的程式錯誤,寫進去只會汙染事件流,所以先擋下來。
|
||||
# - 本檔不讀 stdin。技能由 Bash 呼叫它,stdin 可能是還沒關閉的管線,讀下去會卡住宿主。
|
||||
# 所有資訊一律走參數。
|
||||
# - 輪替不放在每次寫入。每次提示都寫事件,順手 stat 一次檔案就是每次提示多一次系統呼叫;
|
||||
# 改由巡檢排空之後呼叫 rotate,成本落在本來就週期性執行的地方。
|
||||
#
|
||||
# 結束碼: 0=成功(記錄子命令一律 0) 2=用法錯誤 3=drain 沒有新事件
|
||||
set -eu
|
||||
|
||||
HERE=$(CDPATH= cd -- "$(dirname -- "$0")" && pwd)
|
||||
# lib.sh 在同一個存取庫,不是跨 plugin 依賴。hook 必須自足,事件寫入的函式因此留在 lib.sh,
|
||||
# 這支只是把它包成命令列介面給技能用。
|
||||
STDIN_JSON=""
|
||||
. "$HERE/../hooks/lib.sh"
|
||||
|
||||
EVENTS="$JSC_HOME/usage/events.jsonl"
|
||||
OFFSET="$JSC_HOME/usage/scan-state/events.offset"
|
||||
MAX_BYTES=5242880
|
||||
|
||||
usage() {
|
||||
cat >&2 <<'EOF'
|
||||
用法:
|
||||
report-status.sh skill-start <名稱>
|
||||
report-status.sh skill-end <名稱> <status> [結束碼] [detail]
|
||||
report-status.sh hook-end <名稱> <status> <結束碼> [detail]
|
||||
report-status.sh drain
|
||||
report-status.sh rotate
|
||||
|
||||
status: ok、blocked、failed、degraded、aborted
|
||||
結束碼: 0=成功 2=用法錯誤 3=drain 沒有新事件
|
||||
EOF
|
||||
exit 2
|
||||
}
|
||||
|
||||
valid_status() {
|
||||
case "$1" in
|
||||
ok|blocked|failed|degraded|aborted) ;;
|
||||
*) echo "[jsc][狀態回報][ERR]:status 須為 ok、blocked、failed、degraded、aborted 五選一,收到「$1」。" >&2; exit 2 ;;
|
||||
esac
|
||||
}
|
||||
|
||||
valid_exit() {
|
||||
case "$1" in
|
||||
''|*[!0-9]*) echo "[jsc][狀態回報][ERR]:結束碼須為非負整數,收到「$1」。" >&2; exit 2 ;;
|
||||
esac
|
||||
}
|
||||
|
||||
cmd="${1:-}"; [ -n "$cmd" ] || usage
|
||||
shift || true
|
||||
|
||||
case "$cmd" in
|
||||
skill-start)
|
||||
name="${1:-}"; [ -n "$name" ] || usage
|
||||
# start 沒有成敗可言,狀態欄固定 ok、結束碼固定 0。判讀靠的是「有沒有配對的 end」:
|
||||
# 有 start 沒 end 就是中止,那正是現行紀錄分不出來的那一種。
|
||||
emit_event skill "$name" start ok 0
|
||||
;;
|
||||
skill-end)
|
||||
name="${1:-}"; status="${2:-}"
|
||||
[ -n "$name" ] && [ -n "$status" ] || usage
|
||||
valid_status "$status"
|
||||
code="${3:-0}"; valid_exit "$code"
|
||||
emit_event skill "$name" end "$status" "$code" "" "${4:-}"
|
||||
;;
|
||||
hook-end)
|
||||
name="${1:-}"; status="${2:-}"; code="${3:-}"
|
||||
[ -n "$name" ] && [ -n "$status" ] && [ -n "$code" ] || usage
|
||||
valid_status "$status"; valid_exit "$code"
|
||||
emit_event hook "$name" end "$status" "$code" "" "${4:-}"
|
||||
;;
|
||||
drain)
|
||||
[ -f "$EVENTS" ] || exit 3
|
||||
size=$(wc -c < "$EVENTS" 2>/dev/null || echo 0)
|
||||
old=0
|
||||
[ -f "$OFFSET" ] && old=$(cat "$OFFSET" 2>/dev/null || echo 0)
|
||||
case "$old" in ''|*[!0-9]*) old=0 ;; esac
|
||||
# 檔案比已存位移還小就是輪替過,從頭讀。不比對 inode:五支 CLI 與容器裡的行程
|
||||
# 看到的 inode 不保證一致,用大小判斷才在每個環境都成立。
|
||||
[ "$size" -lt "$old" ] && old=0
|
||||
[ "$size" -eq "$old" ] && exit 3
|
||||
mkdir -p "$(dirname "$OFFSET")" 2>/dev/null || true
|
||||
# tail -c +N 從第 N 個位元組起(1 起算),所以位移要加一。
|
||||
# 不用 dd bs=1 skip=:那是一個位元組一次系統呼叫,位移到了幾 MB 就是幾百萬次,
|
||||
# 每輪巡檢都排空一次的話會慢到不能用。
|
||||
tail -c "+$((old + 1))" "$EVENTS" 2>/dev/null || true
|
||||
printf '%s' "$size" > "$OFFSET" 2>/dev/null || true
|
||||
;;
|
||||
rotate)
|
||||
[ -f "$EVENTS" ] || exit 0
|
||||
size=$(wc -c < "$EVENTS" 2>/dev/null || echo 0)
|
||||
if [ "$size" -gt "$MAX_BYTES" ]; then
|
||||
mv "$EVENTS" "$EVENTS.1" 2>/dev/null || true
|
||||
: > "$EVENTS" 2>/dev/null || true
|
||||
# 位移歸零:新檔從頭算起,不歸零的話下一次 drain 會跳過開頭那一段。
|
||||
printf '0' > "$OFFSET" 2>/dev/null || true
|
||||
printf '已輪替:%s -> %s.1(原大小 %s 位元組)\n' "$EVENTS" "$EVENTS" "$size"
|
||||
fi
|
||||
;;
|
||||
*) usage ;;
|
||||
esac
|
||||
|
||||
exit 0
|
||||
+24
-16
@@ -2302,22 +2302,30 @@ if [ "$action" = status ]; then
|
||||
if [ -n "$claude_root" ] && [ -f "$claude_hooks" ]; then st_item hooks.json "$claude_hooks" present
|
||||
else st_item hooks.json "${claude_hooks:-$HOME/.claude/plugins/installed_plugins.json}" missing; fi
|
||||
# 九支 hook 全靠這一個檔宣告,只看檔案在不在會漏掉「檔在、某支沒接進去」。
|
||||
# 後來才加進來的 comment-scope.sh、lang-guard.sh、restart-gate.sh 與 write-guard.sh
|
||||
# 是最可能漏的四支,所以各列一項。
|
||||
if [ -f "$claude_hooks" ] && grep -qF 'comment-scope.sh' "$claude_hooks" 2>/dev/null
|
||||
then st_item comment-scope "$claude_hooks" present
|
||||
else st_item comment-scope "$claude_hooks" missing; fi
|
||||
if [ -f "$claude_hooks" ] && grep -qF 'lang-guard.sh' "$claude_hooks" 2>/dev/null
|
||||
then st_item lang-guard "$claude_hooks" present
|
||||
else st_item lang-guard "$claude_hooks" missing; fi
|
||||
if [ -f "$claude_hooks" ] && grep -qF 'restart-gate.sh' "$claude_hooks" 2>/dev/null
|
||||
then st_item restart-gate "$claude_hooks" present
|
||||
else st_item restart-gate "$claude_hooks" missing; fi
|
||||
# write-guard.sh 接在兩個 matcher 上,三種模式各自是一件事,只驗腳本名會漏掉少接的那一個
|
||||
for _m in stage review commit; do
|
||||
if [ -f "$claude_hooks" ] && grep -qF "write-guard.sh\\\" $_m" "$claude_hooks" 2>/dev/null
|
||||
then st_item "write-guard-$_m" "$claude_hooks" present
|
||||
else st_item "write-guard-$_m" "$claude_hooks" missing; fi
|
||||
# 每一支都列一項,一支都不省。reason 那行講的是「全部九支」,列舉卻只挑幾支的話,
|
||||
# 拿這份輸出驗收接線的人會把沒列到的當成沒接——模型能力鎖就是這樣被誤判成沒接線的。
|
||||
for _h in comment-scope lang-guard restart-gate skill-usage version-guard; do
|
||||
if [ -f "$claude_hooks" ] && grep -qF "$_h.sh" "$claude_hooks" 2>/dev/null
|
||||
then st_item "$_h" "$claude_hooks" present
|
||||
else st_item "$_h" "$claude_hooks" missing; fi
|
||||
done
|
||||
# 一支腳本接在多個接線點時,每個點各自是一件事,只驗腳本名會漏掉少接的那一個。
|
||||
# 三支這種腳本的接線點對照(左邊是項目名,右邊是 hooks.json 裡的子命令):
|
||||
# write-guard stage、review、commit
|
||||
# sdlc-gate check(階段模型鎖)、wp-check prompt、wp-check skill(工作包歸屬)
|
||||
# session-timer start、mark
|
||||
for _p in "write-guard-stage write-guard.sh\\\" stage" \
|
||||
"write-guard-review write-guard.sh\\\" review" \
|
||||
"write-guard-commit write-guard.sh\\\" commit" \
|
||||
"sdlc-gate-check sdlc-gate.sh\\\" check" \
|
||||
"sdlc-gate-wp-prompt sdlc-gate.sh\\\" wp-check prompt" \
|
||||
"sdlc-gate-wp-skill sdlc-gate.sh\\\" wp-check skill" \
|
||||
"session-timer-start session-timer.sh\\\" start" \
|
||||
"session-timer-mark session-timer.sh\\\" mark"; do
|
||||
_name=${_p%% *}; _pat=${_p#* }
|
||||
if [ -f "$claude_hooks" ] && grep -qF "$_pat" "$claude_hooks" 2>/dev/null
|
||||
then st_item "$_name" "$claude_hooks" present
|
||||
else st_item "$_name" "$claude_hooks" missing; fi
|
||||
done ;;
|
||||
|
||||
codex)
|
||||
|
||||
Reference in New Issue
Block a user