feat: update feishu intake

skills/ack/scripts/feishu_bug_intake.py

@@ -26,6 +26,9 @@ from typing import Any
 from yaml_subset import DuplicateKeyError, YamlSubsetError, load_json_unique, load_yaml_subset, make_unique_pyyaml_loader
 
 REQUIRED_FIELDS = ("title", "actual", "expected", "stepsToReproduce", "acceptance", "priority", "attachments", "updatedAt")
+SOURCE_FACT_FIELDS = ("title", "actual", "expected", "updatedAt")
+COORDINATOR_FIELDS = ("steps", "acceptance", "priority")
+BUG_CONTENT_FIELDS = ("title", "actual", "expected", *COORDINATOR_FIELDS)
 MAX_PAGES = 100
 MAX_RECORDS = 10_000
 PAGE_SIZE = 100
@@ -444,6 +447,7 @@ def source_ref(config: dict[str, Any], record_id: str) -> str:
 def fetch(config: dict[str, Any], output_dir: Path | None) -> dict[str, Any]:
     profile_check(config)
     prepared: list[tuple[dict[str, Any], list[tuple[dict[str, Any], str]]]] = []
+    batch_warnings: list[dict[str, str]] = []
     total_attachments = 0
     total_attachment_bytes = 0
     for record_id, row in fetch_pages(config):
@@ -456,9 +460,15 @@ def fetch(config: dict[str, Any], output_dir: Path | None) -> dict[str, Any]:
         if total_attachment_bytes > MAX_TOTAL_ATTACHMENT_BYTES:
             raise IntakeError("batch exceeded the attachment byte limit")
         record = {"sourceRef": source_ref(config, record_id), "recordId": record_id, "updatedAt": text(cells["updatedAt"]), "title": text(cells["title"]), "actual": text(cells["actual"]), "expected": text(cells["expected"]), "steps": text(cells["stepsToReproduce"]), "acceptance": text(cells["acceptance"]), "priority": text(cells["priority"]), "attachments": [metadata for metadata, _ in attachment_data], "warnings": []}
-        for field in ("title", "actual", "expected", "steps", "acceptance", "priority", "updatedAt"):
+        if not attachment_data and not any(record[field] for field in BUG_CONTENT_FIELDS):
+            batch_warnings.append({"recordId": record_id, "code": "blank_record_skipped"})
+            continue
+        for field in SOURCE_FACT_FIELDS:
             if not record[field]:
                 raise IntakeError(f"record {field} must not be empty")
+        record["enrichmentRequired"] = [
+            field for field in COORDINATOR_FIELDS if not record[field]
+        ]
         prepared.append((record, attachment_data))
     download_root: Path | None = None
     if output_dir is not None:
@@ -483,10 +493,10 @@ def fetch(config: dict[str, Any], output_dir: Path | None) -> dict[str, Any]:
                     attachment["size"], min(60, remaining),
                 )
         records.append(record)
-    return {"provider": "feishu-base", "profile": config["profile"], "tableId": config["tableId"], "viewId": config["viewId"], "records": records}
+    return {"provider": "feishu-base", "profile": config["profile"], "tableId": config["tableId"], "viewId": config["viewId"], "records": records, "warnings": batch_warnings}
 
 
-def plan_actions(board: dict[str, Any], records: list[dict[str, Any]]) -> list[dict[str, str]]:
+def plan_actions(board: dict[str, Any], records: list[dict[str, Any]]) -> list[dict[str, Any]]:
     """Plan idempotent Coordinator actions without mutating the task board."""
     tasks = board.get("tasks")
     if not isinstance(tasks, list):
@@ -513,7 +523,7 @@ def plan_actions(board: dict[str, Any], records: list[dict[str, Any]]) -> list[d
             raise IntakeError("task board contains duplicate Feishu source references")
         existing[ref] = task
 
-    actions: list[dict[str, str]] = []
+    actions: list[dict[str, Any]] = []
     seen_records: set[str] = set()
     for record in records:
         ref = record.get("sourceRef")
@@ -530,22 +540,30 @@ def plan_actions(board: dict[str, Any], records: list[dict[str, Any]]) -> list[d
         seen_records.add(ref)
         task = existing.get(ref)
         if task is None:
-            actions.append({"sourceRef": ref, "recordId": record_id, "action": "create"})
+            planned_action: dict[str, Any] = {"sourceRef": ref, "recordId": record_id, "action": "create"}
+            enrichment_required = record.get("enrichmentRequired")
+            if enrichment_required:
+                planned_action["enrichmentRequired"] = enrichment_required
+            actions.append(planned_action)
             continue
         source = task["source"]
         if source["updatedAt"] == updated_at:
-            action = "unchanged"
+            action_name = "unchanged"
         elif task["status"] == "open":
-            action = "refresh"
+            action_name = "refresh"
         else:
-            action = "drift"
-        actions.append({
+            action_name = "drift"
+        planned_action = {
             "sourceRef": ref,
             "recordId": record_id,
             "taskId": task["id"],
             "status": task["status"],
-            "action": action,
-        })
+            "action": action_name,
+        }
+        enrichment_required = record.get("enrichmentRequired")
+        if enrichment_required and action_name == "refresh":
+            planned_action["enrichmentRequired"] = enrichment_required
+        actions.append(planned_action)
     return actions
 
 

skills/ack/scripts/select_tasks.py

@@ -0,0 +1,261 @@
+#!/usr/bin/env python3
+"""为 ACK Coordinator 输出有预算的任务板上下文。
+
+脚本会解析并校验完整 tasks.yaml，但只输出项目配置、摘要、可工作任务或显式任务，
+以及这些任务引用的 worker receipt 和 delivery run。它不会修改任务板，也不会静默
+截断超过预算的任务集合。
+"""
+
+from __future__ import annotations
+
+import argparse
+import json
+import sys
+from pathlib import Path
+from typing import Any
+
+from validate_tasks import STATUS_ENUM, load_document, validate_builtin  # type: ignore
+
+
+ACTIONABLE_STATUSES = (
+    "open",
+    "dispatched",
+    "fixed_by_dev",
+    "retesting",
+    "failed_retest",
+)
+DEFAULT_LIMIT = 20
+MAX_LIMIT = 100
+MAX_OUTPUT_BYTES = 512 * 1024
+BOARD_METADATA_FIELDS = (
+    "version",
+    "updatedAt",
+    "source",
+    "ackVersion",
+    "kitVersion",
+    "testRecord",
+    "statusReference",
+)
+
+
+class SelectionError(ValueError):
+    pass
+
+
+def _unique(values: list[str]) -> list[str]:
+    return list(dict.fromkeys(values))
+
+
+def select_tasks(
+    data: dict[str, Any],
+    *,
+    task_ids: list[str] | None = None,
+    statuses: list[str] | None = None,
+    limit: int = DEFAULT_LIMIT,
+) -> tuple[str, list[str], list[dict[str, Any]]]:
+    if isinstance(limit, bool) or not isinstance(limit, int) or not 1 <= limit <= MAX_LIMIT:
+        raise SelectionError(f"limit 必须在 1..{MAX_LIMIT} 之间")
+    tasks = data.get("tasks")
+    if not isinstance(tasks, list):
+        raise SelectionError("tasks 必须是列表")
+
+    requested_ids = _unique(task_ids or [])
+    requested_statuses = _unique(statuses or [])
+    if requested_ids and requested_statuses:
+        raise SelectionError("--task-id 与 --status 不能同时使用")
+
+    if requested_ids:
+        by_id = {
+            task.get("id"): task
+            for task in tasks
+            if isinstance(task, dict) and isinstance(task.get("id"), str)
+        }
+        missing = [task_id for task_id in requested_ids if task_id not in by_id]
+        if missing:
+            raise SelectionError("找不到任务: " + ", ".join(missing))
+        selected = [by_id[task_id] for task_id in requested_ids]
+        mode = "task_ids"
+        criteria = requested_ids
+    else:
+        effective_statuses = requested_statuses or list(ACTIONABLE_STATUSES)
+        unknown = [status for status in effective_statuses if status not in STATUS_ENUM]
+        if unknown:
+            raise SelectionError("未知状态: " + ", ".join(unknown))
+        wanted = set(effective_statuses)
+        selected = [
+            task
+            for task in tasks
+            if isinstance(task, dict) and task.get("status") in wanted
+        ]
+        mode = "statuses"
+        criteria = effective_statuses
+
+    if len(selected) > limit:
+        raise SelectionError(
+            f"命中 {len(selected)} 条任务，超过 --limit={limit}；"
+            "请用 --task-id/--status 缩小范围或显式提高 limit"
+        )
+    return mode, criteria, selected
+
+
+def select_referenced_receipts(
+    data: dict[str, Any], selected: list[dict[str, Any]]
+) -> list[dict[str, Any]]:
+    receipt_ids: list[str] = []
+    for task in selected:
+        dispatch = task.get("dispatch")
+        if not isinstance(dispatch, dict):
+            continue
+        for role in ("developer", "test"):
+            role_dispatch = dispatch.get(role)
+            if not isinstance(role_dispatch, dict):
+                continue
+            receipt_id = role_dispatch.get("receiptId")
+            if isinstance(receipt_id, str) and receipt_id not in receipt_ids:
+                receipt_ids.append(receipt_id)
+    if not receipt_ids:
+        return []
+
+    receipts = data.get("workerReceipts")
+    if not isinstance(receipts, list):
+        raise SelectionError("选中任务引用了 receipt，但 workerReceipts 不是列表")
+    by_id = {
+        receipt.get("id"): receipt
+        for receipt in receipts
+        if isinstance(receipt, dict) and isinstance(receipt.get("id"), str)
+    }
+    missing = [receipt_id for receipt_id in receipt_ids if receipt_id not in by_id]
+    if missing:
+        raise SelectionError("选中任务引用了未知 receipt: " + ", ".join(missing))
+    return [by_id[receipt_id] for receipt_id in receipt_ids]
+
+
+def select_delivery_runs(
+    data: dict[str, Any], selected: list[dict[str, Any]]
+) -> list[dict[str, Any]]:
+    selected_ids = {
+        task.get("id")
+        for task in selected
+        if isinstance(task.get("id"), str)
+    }
+    runs = data.get("deliveryRuns")
+    if not selected_ids or not isinstance(runs, list):
+        return []
+    return [
+        run
+        for run in runs
+        if isinstance(run, dict)
+        and isinstance(run.get("taskIds"), list)
+        and any(task_id in selected_ids for task_id in run["taskIds"])
+    ]
+
+
+def build_payload(
+    data: dict[str, Any],
+    *,
+    mode: str,
+    criteria: list[str],
+    selected: list[dict[str, Any]],
+) -> dict[str, Any]:
+    receipts = select_referenced_receipts(data, selected)
+    delivery_runs = select_delivery_runs(data, selected)
+    tasks = data.get("tasks")
+    metadata = {
+        field: data[field]
+        for field in BOARD_METADATA_FIELDS
+        if field in data
+    }
+    selected_ids = [
+        task["id"]
+        for task in selected
+        if isinstance(task.get("id"), str)
+    ]
+    payload: dict[str, Any] = {
+        "board": metadata,
+        "project": data.get("project"),
+        "summary": data.get("summary"),
+        "selection": {
+            "mode": mode,
+            "criteria": criteria,
+            "count": len(selected),
+            "totalTasks": len(tasks) if isinstance(tasks, list) else 0,
+            "selectedTaskIds": selected_ids,
+            "referencedReceiptIds": [receipt.get("id") for receipt in receipts],
+            "deliveryRunIds": [run.get("id") for run in delivery_runs],
+        },
+        "tasks": selected,
+        "workerReceipts": receipts,
+        "deliveryRuns": delivery_runs,
+    }
+    return payload
+
+
+def _parser() -> argparse.ArgumentParser:
+    parser = argparse.ArgumentParser(
+        description="选择 ACK 任务板的有预算 Coordinator 上下文"
+    )
+    parser.add_argument(
+        "tasks",
+        nargs="?",
+        default="docs/ack/tasks.yaml",
+        help="任务板路径",
+    )
+    parser.add_argument("--task-id", action="append", default=[])
+    parser.add_argument(
+        "--status",
+        action="append",
+        default=[],
+        choices=sorted(STATUS_ENUM),
+    )
+    parser.add_argument("--limit", type=int, default=DEFAULT_LIMIT)
+    parser.add_argument("--compact", action="store_true", help="输出紧凑 JSON")
+    return parser
+
+
+def main(argv: list[str] | None = None) -> int:
+    args = _parser().parse_args(argv)
+    tasks_path = Path(args.tasks)
+    if not tasks_path.is_file():
+        sys.stderr.write(f"找不到任务板文件: {tasks_path}\n")
+        return 2
+
+    data = load_document(tasks_path)
+    errors = validate_builtin(data)
+    if errors:
+        sys.stderr.write(f"任务板无效，拒绝选择，共 {len(errors)} 项：\n")
+        for error in errors:
+            sys.stderr.write(f"  - {error}\n")
+        return 1
+
+    try:
+        mode, criteria, selected = select_tasks(
+            data,
+            task_ids=args.task_id,
+            statuses=args.status,
+            limit=args.limit,
+        )
+        payload = build_payload(
+            data,
+            mode=mode,
+            criteria=criteria,
+            selected=selected,
+        )
+    except SelectionError as exc:
+        sys.stderr.write(f"任务选择失败: {exc}\n")
+        return 1
+
+    if args.compact:
+        output = json.dumps(payload, ensure_ascii=False, separators=(",", ":"))
+    else:
+        output = json.dumps(payload, ensure_ascii=False, indent=2)
+    if len(output.encode("utf-8")) > MAX_OUTPUT_BYTES:
+        sys.stderr.write(
+            f"任务选择输出超过 {MAX_OUTPUT_BYTES} bytes；请进一步缩小任务范围\n"
+        )
+        return 1
+    sys.stdout.write(output + "\n")
+    return 0
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())