@ai-setting/roy-task-plugin 0.7.13 → 0.7.14

package/dist/cli.js

@@ -449,120 +449,159 @@ class NdjsonAssembler {
   }
 }
 
-// ../agent/src/roy-prompt-core.ts
-import {
-  TASK_DISCIPLINE_COMPLETE,
-  TASK_DISCIPLINE_GOALS,
-  TASK_DISCIPLINE_LIFECYCLE,
-  TASK_DISCIPLINE_OPERATION
-} from "@ai-setting/roy-agent-core/env/task/prompt";
-
-// ../agent/src/trim-permission.ts
-var ROLE_SCOPE_QUALIFIER = /验收方|收尾分两种角色/;
-var TRIM_RULES = Object.freeze([
-  {
-    name: "complete-禁止调用",
-    match: (line) => /(不要|禁止|别|无需|不需要|不能|无权|不得|仍无|不持有|不具备|未获得)/.test(line) && /task_complete/.test(line)
-  },
-  {
-    name: "角色权限断言",
-    match: (line) => /(执行方|验收方)/.test(line) && /(权限|资格|无权|不能|没有)/.test(line) && /task_complete/.test(line) && !/你的收尾动作是/.test(line)
-  },
-  {
-    name: "track-禁止置终态",
-    match: (line) => /终态由验收方落/.test(line) || /不要/.test(line) && /置为/.test(line) && /completed/.test(line)
-  },
-  {
-    name: "lifecycle-角色二分标题",
-    match: (line) => /收尾分两种角色/.test(line),
-    replace: () => "6. COMPLETE — 收尾：用 `task_complete` after item-by-item verification" + " (see Complete Discipline below)"
-  },
-  {
-    name: "lifecycle-执行方条目",
-    match: (line) => /执行方/.test(line) && /(roy )?sub-agent/.test(line)
-  },
-  {
-    name: "lifecycle-执行方收尾指令",
-    match: (line, ctx) => (/结束并返回结果|结束并返回/.test(line) || /最后一条/.test(line) && /task_operation_create/.test(line)) && (/执行方/.test(line) || /执行方/.test(ctx.prevLine ?? ""))
-  },
-  {
-    name: "lifecycle-验收方条目",
-    match: (line) => /验收方/.test(line) && /(default agent|接待员)/.test(line)
-  },
-  {
-    name: "complete-标题角色限定",
-    match: (line) => /^#{1,6}\s/.test(line) && /验收方/.test(line),
-    replace: (line) => line.replace(/\s*[（(][^）)]*验收方[^）)]*[）)]/g, "")
-  },
-  {
-    name: "complete-角色作用域引用块",
-    match: (line) => /角色作用域/.test(line) || /若你是/.test(line) && /执行方/.test(line) && /权限/.test(line) || /你的收尾动作是/.test(line) && /验收由主智能体负责/.test(line)
-  }
+// ../../../packages/cli/src/daemon/discipline.ts
+var PLUGIN_TASK_DISCIPLINE_PROMPT = `### Task Lifecycle — the plugin's contract
+
+> **Task is the first-class citizen.** No task, no work.
+
+You are the worker agent: you act through the tools, and your output is
+what the user sees. The user reads task titles and milestones, not a
+process log.
+
+#### 0. Orient before you create
+
+- If a \`[当前 Task #N]\` marker is in your context → \`task_get #N\`
+  directly, skip searching.
+- Otherwise \`task_list\` / \`task_search\` for related work first.
+- \`task_tree(depth=1)\` before creating: decide whether the work belongs
+  under an existing root instead of piling up new roots. Keep the root
+  tasks ≤ 10 — a wide forest is a sign the work was not oriented.
+
+#### 1. Create or reuse
+
+\`task_create\` with a **title**, a **description**, and
+\`goals_and_expected_deliverables\` written as **numbered sub-items**
+(编号子项) — each one separately verifiable:
+
+1. 实现 X（含文件路径）
+2. 测试 Y 覆盖 Z 场景（pass/fail 计数）
+3. 文档 W 落盘到 <path>
+
+Each sub-item must be checkable by one of the four atomic forms:
+**文件断言** (file exists / size / content grep), **进程断言**
+(command exit code / stdout), **测试断言** (pass/fail counts, no NEW
+fail), **状态断言** (version / HTTP 200 / status field). A vague
+one-line goal gives the reviewer nothing to check against.
+
+Reuse before you create: if a matching task exists, \`task_update\` it
+(append to description / goals) instead of creating a near-duplicate.
+
+#### 2. Execute, and record as you go
+
+- Work in stages; each stage is one \`task_operation_create\` call.
+- **边干边记** — record the moment a stage lands, never batch at the
+  end. Milestones recorded in a batch at the end read as filler.
+
+**Operation records carry two dimensions** — keep them apart:
+
+| dimension | field | what it answers |
+|---|---|---|
+| state | \`milestone_type\` + \`milestone_title\` + \`milestone_description\` | **what** was reached |
+| process | \`process_description\` (100–500 characters) | **how** it was reached |
+
+Record **as you work**, **not after the fact**. The chain is the evidence
+the acceptance side reads, so it has to be complete and honest.
+
+\`milestone_title\` is a **短语** (≤ 20 字, verb-first) naming what was
+locked down — e.g. \`泄漏源锁定\`, \`测试全绿\`. Not a label like
+"progress" and not a sentence.
+\`milestone_description\` is a dense technical narrative — file paths,
+symbols, commands, numbers (pass/fail counts, exit codes, sizes).
+\`process_description\` is the route (strategy + tool steps) and must
+**not** repeat the description.
+
+#### 3. Track
+
+- \`task_update(progress=…, current_status=…)\` as you advance.
+- Status vocabulary: \`todo\` → \`active\` → \`to_validate\` → \`completed\`.
+  **Do not** set \`completed\` yourself before the acceptance step below.
+
+#### 4. Submit for acceptance — \`task_pre_complete\`
+
+When the work is done and the deliverables exist, **submit**:
+
+\`\`\`
+task_pre_complete(
+  task_id=<id>,
+  deliverable_storage_path="<path(s)>",
+  current_status="<one-line progress summary>"
+)
+\`\`\`
+
+- It sets \`status = "to_validate"\` (待验证) — **not** a terminal state.
+- The deliverable path lands in \`task.context.deliverable_storage_path\`
+  and in the operation trail, so the acceptance side can check it.
+- \`deliverable_storage_path\` may name **several paths**, space-separated
+  (\`/tmp/report.md /tmp/diff.patch\`); \`,\` \`;\` \`、\` and \` + \` also
+  split. A local path may carry the \`file://\` scheme. Declare **every**
+  artefact you produced — a path left out reads as "not produced".
+- \`cycle\` tasks are periodic by design: they cannot be submitted or
+  completed. Use \`task_update\` to reset their progress instead.
+
+**Self-check on submission.** Submitting runs the goal check (the
+"goal vs. deliverables" judge) **once**, at submission time. If the
+result carries a \`[TASK_COMPLETION_HINT]\`, you MUST verify it
+(核实义务) — never ignore it:
+
+1. Re-read the task with \`task_get(task_id=<id>)\`.
+2. Then do exactly one of:
+   - **not met** → fix the gap, then submit again (\`task_pre_complete\`
+     is idempotent — a later submission replaces the earlier one's
+     status / deliverable, and each one leaves its own operation);
+   - **met after all** → record a \`decision\` operation
+     (\`task_operation_create(milestone_type="decision")\`) stating why the
+     sub-items are actually satisfied.
+
+#### 5. Accept — \`task_complete\`
+
+The acceptance step is a **separate, explicit** call. Before it:
+
+1. Read the task's goal and delivery fields (\`task_get\`).
+2. Validate **item-by-item** (按子项逐条验收) against the operation
+   chain and the deliverable evidence in
+   \`context.deliverable_storage_path\`.
+3. Honour a \`[TASK_COMPLETION_HINT]\` if one is present — same verify
+   duty as above: either **reopen** the task (\`task_update(status="todo")\`)
+   and finish the missing work, or **state why** the sub-items are already
+   met (a \`decision\` operation).
+4. If the goal and the deliverables disagree, either extend the task
+   (\`task_update\`) or record the discrepancy as a \`decision\` operation.
+
+\`task_complete(task_id=<id>)\` then sets \`status = "completed"\` and
+\`progress = 100\`. It takes **no** deliverable parameter — the
+deliverables were already submitted through \`task_pre_complete\`.
+
+⚠️ If \`task_pre_complete\` is not in your tool surface (an older
+core), submit with \`task_complete(deliverable_storage_path=...)\`
+instead — the legacy one-call contract.
+
+#### Where tasks live
+
+All tasks and operations are persisted by the plugin in the **single**
+project store — locally SQLite at \`~/.roy-task-plugin/tasks.db\` (or the
+remote service when the plugin runs with \`persistence: "remote"\`). Do
+not create side databases, do not keep your own to-do list in files, and
+do not track work in chat only: if it is not in the task store, it is
+not tracked.
+
+#### Style
+
+- Be direct and concrete.
+- Report the task id and its state whenever you finish a step.
+- If a task is blocked, mark it (\`task_update(status="paused")\`) and
+  record a \`problem\` milestone explaining the blocker instead of going
+  silent.`;
+var RUNTIMES_WITH_AGENT_SYSTEM_PROMPT = Object.freeze([
+  "opencode",
+  "claude"
 ]);
-function isListItemHead(line) {
-  return /^\s*([-*+]\s|\d+\.\s)/.test(line);
-}
-function isContinuationOf(line, head) {
-  if (isListItemHead(line))
-    return false;
-  if (/^\s*(#{1,6}\s|>)/.test(line))
-    return false;
-  if (/^\s*```/.test(line))
-    return false;
-  if (line.trim() === "")
+function needsDispatchInjection(runtime) {
+  if (!runtime)
     return false;
-  const indent = (s) => s.match(/^\s*/)?.[0].length ?? 0;
-  return indent(line) > indent(head);
-}
-function trimTaskCompletePermissionText(text) {
-  if (!text)
-    return text;
-  const lines = text.split(`
-`);
-  const out = [];
-  for (let i = 0;i < lines.length; i++) {
-    const line = lines[i];
-    const rule = TRIM_RULES.find((r) => r.match(line, { prevLine: lines[i - 1] }));
-    if (!rule) {
-      out.push(line);
-      continue;
-    }
-    if (rule.replace) {
-      const replaced = rule.replace(line);
-      if (ROLE_SCOPE_QUALIFIER.test(replaced)) {
-        throw new Error(`trim-permission: rule "${rule.name}" matched the line but its replace() ` + `left the role qualifier in place — core's wording drifted and this ` + `trim rule must be updated.
-  line: ${line}`);
-      }
-      out.push(replaced);
-    }
-    if (!rule.replace && isListItemHead(line)) {
-      while (i + 1 < lines.length && isContinuationOf(lines[i + 1], line)) {
-        i++;
-      }
-    }
-  }
-  const collapsed = [];
-  let inFence = false;
-  for (const line of out) {
-    if (/^\s*```/.test(line)) {
-      inFence = !inFence;
-      collapsed.push(line);
-      continue;
-    }
-    if (!inFence && line.trim() === "" && collapsed.length > 0 && collapsed[collapsed.length - 1].trim() === "") {
-      continue;
-    }
-    collapsed.push(line);
-  }
-  return collapsed.join(`
-`);
+  return !RUNTIMES_WITH_AGENT_SYSTEM_PROMPT.includes(runtime);
 }
 
 // ../agent/src/roy-prompt-core.ts
-var TRIMMED_LIFECYCLE = trimTaskCompletePermissionText(TASK_DISCIPLINE_LIFECYCLE);
-var TRIMMED_GOALS = trimTaskCompletePermissionText(TASK_DISCIPLINE_GOALS);
-var TRIMMED_OPERATION = trimTaskCompletePermissionText(TASK_DISCIPLINE_OPERATION);
-var TRIMMED_COMPLETE = trimTaskCompletePermissionText(TASK_DISCIPLINE_COMPLETE);
 var ROY_PROMPT_COMMON = `# Roy — task-first-class-citizen agent
 
 You are **Roy**, an agent whose defining rule is simple:
@@ -572,44 +611,17 @@ You are **Roy**, an agent whose defining rule is simple:
 You are a worker agent: you act through the tools, and your output is what
 the user sees.
 
-${TRIMMED_LIFECYCLE}
-
-${TRIMMED_GOALS}
-
-The tool returns a **numeric task id** — that number is your handle for the
-rest of the conversation.
-
-${TRIMMED_OPERATION}
-
-${TRIMMED_COMPLETE}
-
-#### Several deliverables in one field
-\`deliverable_storage_path\` may name **multiple paths**, space-separated
-(\`/tmp/report.md /tmp/diff.patch\`) — the judge splits on whitespace as well
-as \`,\` \`;\` \`、\` and \` + \`. A local path may also be written in its
-\`file://\` form (\`file:///tmp/report.md\`) — the scheme is stripped and the
-path kept. Declare **every** artefact you produced: a path left out reads as
-"not produced" and drags the task toward a false completion hint.
-
-\`task_complete\` cannot be used on \`cycle\` tasks (they are periodic by
-design) — use \`task_update\` to reset those.
+${PLUGIN_TASK_DISCIPLINE_PROMPT}
 
 ## Other tools
 
 - \`task_get(task_id, include_operations)\` — full detail; use it before
-  resuming or completing a task.
+  resuming, submitting or accepting a task.
 - \`task_list(...)\` — flat listing with filters (status / priority / type).
 - \`task_search(keywords)\` — find by title / description / goals / tags.
   **Search before creating**, to avoid duplicates.
-
-## Where tasks live
-
-All tasks and operations are persisted by the roy-task-plugin in the
-**single** project store — locally that is SQLite at
-\`~/.roy-task-plugin/tasks.db\` (or the remote service when the plugin is
-configured with \`persistence: "remote"\`). Do not create side databases, do
-not maintain your own to-do list in files, and do not track work in chat only:
-if it is not in the task store, it is not tracked.
+- \`task_tree(depth=1)\` — the task hierarchy; use it to place new work
+  under an existing root instead of piling up roots.
 
 ## Style
 
@@ -700,7 +712,8 @@ loads. Call them directly:
 | \`task_create\` | \`mcp__roy-task__task_create\` |
 | \`task_update\` | \`mcp__roy-task__task_update\` |
 | \`task_operation_create\` | \`mcp__roy-task__task_operation_create\` |
-| \`task_complete\` | \`mcp__roy-task__task_complete\` |
+| \`task_pre_complete\` (submit for acceptance) | \`mcp__roy-task__task_pre_complete\` |
+| \`task_complete\` (accept) | \`mcp__roy-task__task_complete\` |
 | \`task_get\` | \`mcp__roy-task__task_get\` |
 | \`task_list\` | \`mcp__roy-task__task_list\` |
 | \`task_search\` | \`mcp__roy-task__task_search\` |
@@ -716,12 +729,13 @@ instead of silently skipping the lifecycle.`;
 
 // ../../../packages/cli/src/daemon/runners/claude-agents.ts
 var CLAUDE_ROY_AGENT_NAME = "roy";
-var ROY_AGENT_DESCRIPTION = "Roy — task-as-first-class-citizen agent. Uses the roy-agent task lifecycle " + "(task_tree → task_create → task_update → task_operation_create → task_complete) " + "so every piece of work is tracked in the local task store.";
+var ROY_AGENT_DESCRIPTION = "Roy — task-as-first-class-citizen agent. Uses the roy-agent task lifecycle " + "(task_tree → task_create → task_update → task_operation_create → " + "task_pre_complete → task_complete) " + "so every piece of work is tracked in the local task store.";
 var ROY_TASK_MCP_SERVER = "roy-task";
 var ROY_TASK_MCP_TOOLS = Object.freeze([
   "task_create",
   "task_update",
   "task_operation_create",
+  "task_pre_complete",
   "task_complete",
   "task_get",
   "task_list",
@@ -1260,20 +1274,6 @@ function errMsg(err) {
   return String(err);
 }
 
-// ../../../packages/cli/src/daemon/discipline.ts
-import { TASK_DISCIPLINE_PROMPT } from "@ai-setting/roy-agent-core/env/task/prompt";
-var CORE_TASK_DISCIPLINE_PROMPT_RAW = TASK_DISCIPLINE_PROMPT;
-var PLUGIN_TASK_DISCIPLINE_PROMPT = trimTaskCompletePermissionText(CORE_TASK_DISCIPLINE_PROMPT_RAW);
-var RUNTIMES_WITH_AGENT_SYSTEM_PROMPT = Object.freeze([
-  "opencode",
-  "claude"
-]);
-function needsDispatchInjection(runtime) {
-  if (!runtime)
-    return false;
-  return !RUNTIMES_WITH_AGENT_SYSTEM_PROMPT.includes(runtime);
-}
-
 // ../../../packages/cli/src/daemon/runners/codex.ts
 var DEFAULT_CODEX_TIMEOUT_MS = 10 * 60 * 1000;
 var CODEX_STDIO = Object.freeze([
@@ -1872,7 +1872,7 @@ function buildDispatchPrompt(input) {
     ""
   ];
   if (needsDispatchInjection(input.runtime)) {
-    parts.push("## 任务纪律（Task #4889 — 来自 roy-agent core 单一真相源）", "", PLUGIN_TASK_DISCIPLINE_PROMPT, "");
+    parts.push("## 任务纪律（Task #5078 — 插件自维护的契约）", "", PLUGIN_TASK_DISCIPLINE_PROMPT, "");
   }
   parts.push("## 硬性规则", "", "1. **不要**自己调用 `lark-cli` 发送回复。守护进程会在你结束后，把你的", "   **最终回答文本**用 `lark-cli im +messages-reply` 一次性发回飞书。", "   你自己发会造成重复消息。", "2. 把**最终回答**写成给发件人看的**普通散文 / Markdown**。", "   不要输出 JSON 包裹、不要输出“我调用了某某工具”的过程流水账。", "   这段文本会**原样**成为飞书里的回复正文。", "3. 需要落任务就用 `task_*` 工具（task_create / task_update / …），", "   这是你的主要职责；不要只在回答里“描述”你打算做什么。", "", "## 什么时候该建任务（Task #4433）", "", "任务由**你**决定建不建，守护进程不会替你建。判断标准：", "", "- **该建**：需要多步操作、要动文件/跑命令、要调研并产出结论、", "  耗时预计超过一两分钟、或用户明确要求「跟踪 / 建个任务 / 后续跟进」。", "  → 用 `task_create` 建任务，**然后**再开始干活（先立任务，再动手）。", "- **不必建**：寒暄、谢谢、纯问答（「今天几号」「这个参数叫啥」）、", "  一两句话就能答完且不需要任何工具的问题。", "  → 直接回答，不要为了「显得勤快」而建一个空任务。", "- **建完要更新**：动手过程中用 `task_update` 推进度 / 改 current_status，", "  干完用 `task_complete` 收尾。建了任务却从不更新，比不建更糟——", "  看板上会留下一个卡住的任务。", "", "⚠️ **卡片与任务一一对应**：只有你建了任务，用户才会收到一张进展卡片；", "没建任务就只有文字回复。所以**不要**为了「想要一张卡片」而去建任务，", "也不要建了任务又不用它——卡片上显示的就是你建的那个任务的真 id 和标题。", "", "## 环境事实（必须使用下面这些值，不要自己猜）", "", `- lark-cli profile：\`${profile}\`（飞书 openId 是 per-app 隔离的，换 profile 会失败）`, `- chat_id：\`${chatId}\``, `- message_id：\`${messageId}\``, `- event_id：\`${eventId}\``, "", "## 原始事件（完整 JSON）", "", "```json", JSON.stringify(input.rawEvent, null, 2), "```");
   if (input.recommendedAction) {
@@ -3611,7 +3611,7 @@ function formatStatus(report) {
 }
 
 // ../../../packages/cli/src/main.ts
-var VERSION = "0.7.13";
+var VERSION = "0.7.14";
 async function main(argv) {
   const parsed = parseArgs(argv);
   switch (parsed.command) {