@kairyou/agent-tools 0.17.1 → 0.18.0

package/README.md

@@ -56,7 +56,7 @@ Usage:
 
 ### at-zentao
 
-Work ZenTao (禅道) bugs/tasks end to end: fix, verify, stage; asks before committing and before writing status back.
+Work ZenTao (禅道) bugs/tasks end to end, read linked story context, or log task hours; asks before committing and before writing back.
 
 ```bash
 npx -y skills@latest add kairyou/agent-tools --skill at-zentao -g -y
@@ -67,7 +67,8 @@ Usage:
 - `/at-zentao bugs` — list bugs assigned to you (the configured account); pick one or several (several = batch mode)
 - `/at-zentao tasks` — same, for tasks
 - `/at-zentao bug <id>` — work a specific bug
-- `/at-zentao task <id>` — work a specific task
+- `/at-zentao task <id> [request]` — work a specific task or log hours with a natural-language request
+- `/at-zentao story <id>` — read requirement scope and acceptance context without writing back
 
 Config: `~/.agent-tools/config.jsonc` → `"zentao": { "url", "account", "password" }`. The password can be entered directly or referenced with `"password": { "env": "ZENTAO_PASSWORD" }`; never paste credentials or tokens into chat.
 

package/README.zh-CN.md

@@ -56,7 +56,7 @@ npx -y skills@latest add kairyou/agent-tools --skill at-simplify -g -y
 
 ### at-zentao
 
-读取禅道 bug/task 并端到端处理: 修复, 验证, 暂存; 提交和回写状态前均需确认.
+读取禅道 bug/task 并端到端处理, 补充关联 story 上下文, 或记录任务工时; 提交和回写前均需确认.
 
 ```bash
 npx -y skills@latest add kairyou/agent-tools --skill at-zentao -g -y
@@ -67,7 +67,8 @@ npx -y skills@latest add kairyou/agent-tools --skill at-zentao -g -y
 - `/at-zentao bugs` — 列出指派给你(配置的账号)的 bug, 挑一个或多个(多个 = 批量模式)
 - `/at-zentao tasks` — 同上, 任务清单
 - `/at-zentao bug <id>` — 直接处理指定 bug
-- `/at-zentao task <id>` — 直接处理指定 task
+- `/at-zentao task <id> [请求]` — 处理指定 task, 或用自然语言记录工时
+- `/at-zentao story <id>` — 只读查看研发需求范围和验收信息
 
 配置: `~/.agent-tools/config.jsonc` → `"zentao": { "url", "account", "password" }`. 密码可以直接填写, 也可以使用 `"password": { "env": "ZENTAO_PASSWORD" }` 引用环境变量; 不要在对话中粘贴凭据或 token.
 

package/docs/en/repository-structure.md

@@ -14,7 +14,7 @@ agent-tools/
 │   │   ├── at-review/   # Review local or hosted changes for bugs and regressions.
 │   │   └── at-simplify/ # Reduce complexity and duplication in changes.
 │   └── systems/       # Self-contained Skills for external systems.
-│       └── at-zentao/   # Self-contained ZenTao workflow and secure API script.
+│       └── at-zentao/   # Self-contained ZenTao development and time-entry workflow.
 ├── docs/              # Advanced guides and contributor reference.
 ├── tools/             # Maintainer-only upstream sync and repository tooling.
 └── scripts/           # Install, sync, validation, and maintenance scripts.

package/docs/zh-CN/repository-structure.md

@@ -14,7 +14,7 @@ agent-tools/
 │   │   ├── at-review/   # 审查本地或托管改动中的 bug 与回归风险.
 │   │   └── at-simplify/ # 减少改动中的冗余和复杂度.
 │   └── systems/       # 面向外部系统的自包含 Skills.
-│       └── at-zentao/   # 自包含的禅道工作流和安全 API 脚本.
+│       └── at-zentao/   # 自包含的禅道研发事项与工时工作流.
 ├── docs/              # 高级指南和贡献者参考.
 ├── tools/             # 仅供维护者使用的上游同步和仓库工具.
 └── scripts/           # 安装, 同步, 校验和仓库维护脚本.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@kairyou/agent-tools",
-  "version": "0.17.1",
+  "version": "0.18.0",
   "description": "Reusable Agent Skills, plus runtime capabilities (statusline, provider usage, vision) for Codex, Claude Code, and opencode.",
   "license": "MIT",
   "repository": {

package/skills/systems/at-zentao/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: at-zentao
-description: "Work ZenTao bugs/tasks end to end: fetch details, confirm understanding, fix, verify, stage with git add, then ask before committing and before writing status back to ZenTao. Supports single items and sequential batches. Use when the user references ZenTao (禅道) bugs or tasks."
-argument-hint: "bug <id> | task <id> | bugs | tasks | export bug|task <id>"
+description: "Work ZenTao bugs/tasks end to end, log task hours, or read a linked story as development context: fetch details, handle the user's request, verify changes, and ask before committing or writing back to ZenTao. Supports single items and sequential batches. Use when the user references ZenTao (禅道) bugs, tasks, stories, requirements, or task hours."
+argument-hint: "bug <id> [request] | task <id> [request] | story <id> | bugs | tasks | export bug|task <id>"
 ---
 
 # ZenTao Bug/Task Workflow
@@ -70,6 +70,7 @@ node <skill-root>/scripts/zentao-cli.mjs list bugs
 node <skill-root>/scripts/zentao-cli.mjs list tasks
 node <skill-root>/scripts/zentao-cli.mjs get bug <id>
 node <skill-root>/scripts/zentao-cli.mjs get task <id>
+node <skill-root>/scripts/zentao-cli.mjs get story <id>
 node <skill-root>/scripts/zentao-cli.mjs get bug <id> --download-dir <path>
 ```
 
@@ -84,6 +85,7 @@ confirmation steps below:
 node <skill-root>/scripts/zentao-cli.mjs comment bug <id>
 node <skill-root>/scripts/zentao-cli.mjs comment task <id>
 node <skill-root>/scripts/zentao-cli.mjs resolve bug <id>
+node <skill-root>/scripts/zentao-cli.mjs log-hours task <id>
 node <skill-root>/scripts/zentao-cli.mjs finish task <id>
 ```
 
@@ -92,28 +94,43 @@ Input shapes:
 ```json
 {"comment":"Root cause and result."}
 {"resolution":"fixed","resolvedBuild":"trunk","comment":"Root cause and result, commit abc1234."}
+{"date":"2026-08-11","consumed":2,"left":14,"work":"Implemented the first part of the task."}
 {"currentConsumed":1.5,"realStarted":"2026-08-11 09:00:00","finishedDate":"2026-08-11 10:30:00"}
 ```
 
 For `duplicate`, also pass `"duplicateBug": <id>`. Send JSON through stdin,
 not as a command-line argument. The CLI handles UTF-8 form encoding and
 computes a task's total consumed hours from its current ZenTao value.
+`log-hours` defaults `date` to today, requires positive remaining hours,
+and keeps the task open. Use `finish` when the task is complete.
 
 ## Usage
 
 - `/at-zentao bug <id>` — handle a single bug.
 - `/at-zentao task <id>` — handle a single task.
+- `/at-zentao story <id>` — read requirement scope and acceptance context.
+  This mode is read-only; do not implement a Story status or comment workflow.
 - `/at-zentao bugs` — list bugs assigned to the configured account; let the
   user select one or more.
 - `/at-zentao tasks` — list assigned tasks and let the user select.
 - `/at-zentao export bug <id>` or `export task <id>` — create a read-only,
   self-contained handoff bundle.
 
+Treat text after an item id as a natural-language request. Phrases such as
+`填工时`, `记录工时`, `log hours`, and `worklog` enter task time-entry mode;
+users do not need to know the internal `log-hours` CLI command. Reuse any date,
+hours, or work description already supplied instead of asking twice.
+
 If a list response includes pager data showing more items than returned, tell
 the user the shown and total counts. Do not silently imply the list is complete.
 Do not browse through products/projects; start from assigned lists or an
 explicit item id.
 
+When a fetched Bug or Task has a positive `story` id, fetch that Story before
+planning the implementation. Use its `spec` and `verify` fields to identify
+scope, acceptance criteria, constraints, and non-goals. Keep the Bug or Task as
+the unit of work: never change, close, activate, or comment on the Story.
+
 ## Per-item workflow
 
 Follow these steps in order:
@@ -147,10 +164,16 @@ Bug resolutions are `fixed`, `notrepro`, `duplicate`, `bydesign`, `external`,
 write-back comment is one sentence containing root cause, change summary, and
 the commit hash when committed.
 
-For tasks, default to comment only. Offer `finish` only for a simple task
-completed in one sitting, and ask the user for `currentConsumed`; never invent
-hours. For multi-day work or per-day time records, comment and direct the user
-to ZenTao's web UI.
+For tasks, ask whether to record the current work after the verified result.
+For an incomplete task, collect the actual `consumed` hours and work date. When
+the task has a numeric current `left`, suggest the new `left` by subtracting the
+current entry and make that estimate editable in the confirmation; ask only
+when no reliable suggestion is possible. Draft `work` from the verified result
+when context is available. It is optional, so mention the omission without
+blocking the write when there is nothing useful to add. For a completed task,
+collect `currentConsumed` and draft a `finish` write. Never infer consumed
+hours. Show all submitted values and require the same explicit ZenTao
+confirmation before either write.
 
 ## Export mode
 

package/skills/systems/at-zentao/scripts/zentao-cli.mjs

@@ -355,6 +355,13 @@ function itemKind(value) {
   return value;
 }
 
+function detailKind(value) {
+  if (value !== "bug" && value !== "task" && value !== "story") {
+    throw new CliError("usage_error", "detail type must be bug, task, or story");
+  }
+  return value;
+}
+
 function pick(source, keys) {
   const output = {};
   for (const key of keys) if (source?.[key] !== undefined) output[key] = source[key];
@@ -367,7 +374,7 @@ function normalizeDetail(kind, response) {
   if (!detail || typeof detail !== "object") {
     throw new CliError("response_error", `ZenTao response has no ${kind} detail`);
   }
-  return { raw: detail, safe: pick(detail, [
+  const fields = [
     "id",
     "title",
     "name",
@@ -380,15 +387,24 @@ function normalizeDetail(kind, response) {
     "product",
     "project",
     "execution",
+    "story",
     "type",
     "openedDate",
     "deadline",
-  ]) };
+  ];
+  if (kind === "task") {
+    fields.push("estimate", "consumed", "left", "realStarted", "finishedDate");
+  } else if (kind === "story") {
+    fields.push("stage", "category", "plan", "estimate", "spec", "verify", "source", "sourceNote");
+  }
+  return { raw: detail, safe: pick(detail, fields) };
 }
 
 function attachmentUrls(detail) {
   const found = new Set();
-  const html = [detail.steps, detail.desc].filter((entry) => typeof entry === "string").join("\n");
+  const html = [detail.steps, detail.desc, detail.spec, detail.verify]
+    .filter((entry) => typeof entry === "string")
+    .join("\n");
   for (const match of html.matchAll(/(?:src|href)=["']([^"']*\/file-(?:read|download)-\d+[^"']*)["']/gi)) {
     found.add(match[1].replaceAll("&", "&"));
   }
@@ -461,18 +477,64 @@ function legacyResult(response) {
   return { ok: true, result, ...(typeof message === "string" ? { message: message.slice(0, 500) } : {}) };
 }
 
+async function workhourVariant(client, id) {
+  const variants = [
+    { route: `task-recordworkhour-${id}.json`, dateField: "date[1]", legacy: false },
+    { route: `task-recordestimate-${id}.json`, dateField: "dates[1]", legacy: true },
+  ];
+  for (const variant of variants) {
+    try {
+      decodeLegacy(await client.json(variant.route));
+      return variant;
+    } catch (error) {
+      const unavailable = error instanceof CliError && (
+        (error.code === "http_error" && error.status === 404) ||
+        error.code === "response_error"
+      );
+      if (!unavailable) throw error;
+    }
+  }
+  throw new CliError(
+    "unsupported_version",
+    "ZenTao exposes neither recordWorkhour nor recordEstimate for this task"
+  );
+}
+
 function localDateTime(date = new Date()) {
   const part = (value) => String(value).padStart(2, "0");
   return `${date.getFullYear()}-${part(date.getMonth() + 1)}-${part(date.getDate())} ${part(date.getHours())}:${part(date.getMinutes())}:${part(date.getSeconds())}`;
 }
 
+function localDate(date = new Date()) {
+  return localDateTime(date).slice(0, 10);
+}
+
+function effortDate(value) {
+  const date = value === undefined ? localDate() : value;
+  if (typeof date !== "string" || !/^\d{4}-\d{2}-\d{2}$/.test(date)) {
+    throw new CliError("usage_error", "date must use YYYY-MM-DD");
+  }
+  const [year, month, day] = date.split("-").map(Number);
+  const parsed = new Date(year, month - 1, day);
+  if (
+    parsed.getFullYear() !== year ||
+    parsed.getMonth() !== month - 1 ||
+    parsed.getDate() !== day
+  ) {
+    throw new CliError("usage_error", "date must be a valid calendar date");
+  }
+  if (date > localDate()) throw new CliError("usage_error", "date cannot be in the future");
+  return date;
+}
+
 function help() {
   return `Usage:
   zentao-cli.mjs doctor
   zentao-cli.mjs list <bugs|tasks>
-  zentao-cli.mjs get <bug|task> <id> [--download-dir <path>]
+  zentao-cli.mjs get <bug|task|story> <id> [--download-dir <path>]
   zentao-cli.mjs resolve bug <id>          # JSON on stdin
   zentao-cli.mjs comment <bug|task> <id>   # {"comment":"..."} on stdin
+  zentao-cli.mjs log-hours task <id>       # JSON on stdin
   zentao-cli.mjs finish task <id>          # JSON on stdin`;
 }
 
@@ -497,20 +559,21 @@ export async function run(argv, { env = process.env } = {}) {
     const singular = plural.slice(0, -1);
     const data = decodeLegacy(await client.json(`my-work-${singular}.json`));
     const fields = singular === "bug"
-      ? ["id", "title", "severity", "pri", "status", "project", "product"]
-      : ["id", "name", "title", "pri", "status", "project", "execution", "module"];
+      ? ["id", "title", "severity", "pri", "status", "project", "product", "story"]
+      : ["id", "name", "title", "pri", "status", "project", "execution", "module", "story", "estimate", "consumed", "left", "realStarted", "finishedDate"];
     const items = Array.isArray(data?.[plural]) ? data[plural].map((item) => pick(item, fields)) : [];
     return { items, ...(data?.pager ? { pager: pick(data.pager, ["recTotal", "recPerPage", "pageID", "pageTotal"]) } : {}) };
   }
 
   if (command === "get") {
-    const kind = itemKind(args[0]);
+    const kind = detailKind(args[0]);
     const id = positiveId(args[1]);
     let directory;
     if (args[2] === "--download-dir" && args[3]) directory = path.resolve(args[3]);
     else if (args.length > 2) throw new CliError("usage_error", "get accepts only --download-dir <path>");
     else directory = fs.mkdtempSync(path.join(os.tmpdir(), `agent-tools-zentao-${kind}-${id}-`));
-    const detail = normalizeDetail(kind, await client.json(`api.php/v1/${kind}s/${id}`));
+    const resource = kind === "story" ? "stories" : `${kind}s`;
+    const detail = normalizeDetail(kind, await client.json(`api.php/v1/${resource}/${id}`));
     const attachments = await downloadAttachments(client, detail.raw, directory);
     return { item: detail.safe, attachments };
   }
@@ -551,6 +614,38 @@ export async function run(argv, { env = process.env } = {}) {
     return legacyResult(response);
   }
 
+  if (command === "log-hours") {
+    if (args[0] !== "task") throw new CliError("usage_error", "log-hours supports tasks only");
+    const id = positiveId(args[1]);
+    const input = await readInput();
+    const consumed = Number(input.consumed);
+    const left = Number(input.left);
+    if (!Number.isFinite(consumed) || consumed <= 0) {
+      throw new CliError("usage_error", "consumed must be positive");
+    }
+    if (!Number.isFinite(left) || left <= 0) {
+      throw new CliError("usage_error", "left must be positive; use finish to complete a task");
+    }
+    if (input.work !== undefined && typeof input.work !== "string") {
+      throw new CliError("usage_error", "work must be a string when provided");
+    }
+    const date = effortDate(input.date);
+    const variant = await workhourVariant(client, id);
+    const fields = {
+      [variant.dateField]: date,
+      "work[1]": input.work?.trim(),
+      "consumed[1]": consumed,
+      "left[1]": left,
+    };
+    if (variant.legacy) fields["id[1]"] = 1;
+    const response = await client.json(variant.route, {
+      method: "POST",
+      headers: { "content-type": "application/x-www-form-urlencoded" },
+      body: formBody(fields),
+    });
+    return legacyResult(response);
+  }
+
   if (command === "finish") {
     if (args[0] !== "task") throw new CliError("usage_error", "finish supports tasks only");
     const id = positiveId(args[1]);