@dai_ming/plugin-deliverables 1.0.18 → 1.0.19

package/agents-rules/deliverables.md

@@ -55,21 +55,23 @@ Tool name note:
 2. If you need to use the `write` tool, the target path MUST be inside `output/`. Never write deliverable files to the workspace root.
 3. If you already wrote the file to the wrong place, move/copy it into `output/` before finalizing the task and before describing the saved path to the user.
 4. If format is HTML, prefer `type=article` and file name ends with `.html`.
-5. If format is markdown/text, use `type=article` and `.md`/`.txt`.
-6. For multi-file deliverables (game/site), you MUST prefer `type=game` with `files[]`, keep files as a folder structure, and do NOT zip before upload unless the user explicitly asks for a zip package.
-7. Static multi-file game/site deliverables SHOULD include a root `index.html` so the preview link can open the homepage directly.
-8. If a generated project requires starting a separate backend service, custom port, database, or long-running process to work, do NOT pretend the deliverables preview can run it. Tell the user that deliverables preview only supports static output, and that runtime projects need deployment/ingress instead.
-9. After successful upload, the final assistant message MUST start with 1-2 short sentences in your own words, briefly describing what you generated for the user.
-10. The intro must be based on the actual deliverable content/request, not a fixed sentence like `交付物已上传成功，可直接在线预览或下载。`
-11. If tool result contains `reply_markdown`, append that field verbatim after your intro on the following lines.
-12. Otherwise final reply MUST include Markdown links (short label + full URL target):
+5. Every single-file deliverable MUST use a file name with an explicit extension.
+6. If format is markdown/text, use `type=article` and `.md`/`.txt`.
+7. If the user did not specify a document/text format, default to Markdown and use a `.md` file name.
+8. For multi-file deliverables (game/site), you MUST prefer `type=game` with `files[]`, keep files as a folder structure, and do NOT zip before upload unless the user explicitly asks for a zip package.
+9. Static multi-file game/site deliverables SHOULD include a root `index.html` so the preview link can open the homepage directly.
+10. If a generated project requires starting a separate backend service, custom port, database, or long-running process to work, do NOT pretend the deliverables preview can run it. Tell the user that deliverables preview only supports static output, and that runtime projects need deployment/ingress instead.
+11. After successful upload, the final assistant message MUST start with 1-2 short sentences in your own words, briefly describing what you generated for the user.
+12. The intro must be based on the actual deliverable content/request, not a fixed sentence like `交付物已上传成功，可直接在线预览或下载。`
+13. If tool result contains `reply_markdown`, append that field verbatim after your intro on the following lines.
+14. Otherwise final reply MUST include Markdown links (short label + full URL target):
    `预览链接：[点击预览](<full_url>)`
    `下载链接：[点击下载](<full_url>)`
-13. For multi-file/game deliverables, if the tool gives directory-style output, the second line may be:
+15. For multi-file/game deliverables, if the tool gives directory-style output, the second line may be:
    `文件列表：[查看目录](<full_url>)`
    Keep that format instead of forcing a zip link.
-14. Do NOT only say "已保存到工作空间".
-15. Do NOT append workspace path or a raw URL block after the Markdown links.
+16. Do NOT only say "已保存到工作空间".
+17. Do NOT append workspace path or a raw URL block after the Markdown links.
 
 ### Exception
 

package/index.js

@@ -10,6 +10,7 @@ const RUNTIME_DELIVERABLES_GUIDANCE = [
   "",
   "- These rules apply to the main agent and all subagents.",
   "- When the user asks for a document, article, report, HTML page, Markdown file, PPT, image, archive, game, or any other file deliverable, you MUST create it under the current workspace `output/` directory and upload it with `deliverables__upload_deliverable`.",
+  "- Every single-file deliverable must use a file name with an explicit extension. If the user did not specify a document/text format, default to Markdown and use a `.md` file name.",
   "- Do not use direct message attachments to deliver generated files. This includes the message tool attachment fields such as `media`, `path`, `filePath`, `buffer`, `attachment`, or similar file-carrying fields.",
   "- Do not emit `MEDIA:` file references for user-facing deliverables. Deliverable links must come from the deliverables upload tool instead.",
   "- After a successful upload, reply with a substantive content summary before the links. For documents/articles/reports, prefer 1 short intro plus 3-6 concise bullets covering key sections, highlights, or findings, then preserve the Markdown links returned by the deliverables tool.",
@@ -505,6 +506,7 @@ function shouldSplitPalzPayload(body) {
     return {
       summary: cachedSummary,
       links: split.links,
+      primaryLinkUrl: split.primaryLinkUrl,
     };
   }
   return split;

package/mcp-servers/deliverables.js

@@ -22,6 +22,68 @@ var GATEWAY_PUBLIC = (process.env.CLAW_GATEWAY_PUBLIC_URL || GATEWAY_URL).replac
 // breaking deliverable uploads during rolling migration.
 var API_KEY        = process.env.CLAW_GATEWAY_API_KEY || process.env.OPENCLAW_GATEWAY_API_KEY || "api-key-1";
 
+function trimString(value) {
+  return typeof value === "string" ? value.trim() : "";
+}
+
+function hasExtension(fileName) {
+  return /\.[A-Za-z0-9]+$/.test(trimString(fileName));
+}
+
+function looksLikeHTMLContent(contentText) {
+  var text = trimString(contentText).toLowerCase();
+  if (!text) {
+    return false;
+  }
+  if (text.indexOf("<!doctype html") === 0 || text.indexOf("<html") === 0) {
+    return true;
+  }
+  return text.indexOf("<head") >= 0 ||
+    text.indexOf("<body") >= 0 ||
+    text.indexOf("<main") >= 0 ||
+    text.indexOf("<section") >= 0 ||
+    text.indexOf("<article") >= 0 ||
+    text.indexOf("<style") >= 0 ||
+    text.indexOf("<script") >= 0;
+}
+
+function defaultExtensionForDeliverable(args) {
+  var deliverableType = trimString(args && args.type);
+  switch (deliverableType) {
+    case "article":
+    case "game":
+      return looksLikeHTMLContent(args && args.content_text) ? ".html" : ".md";
+    case "zip":
+      return ".zip";
+    case "ppt":
+      return ".pptx";
+    case "image":
+      return ".png";
+    case "video":
+      return ".mp4";
+    default:
+      return "";
+  }
+}
+
+function normalizeDeliverableFileName(args) {
+  var fileName = trimString(args && args.file_name);
+  if (!fileName) {
+    fileName = "file";
+  }
+  if (trimString(args && args.type) === "link") {
+    return fileName;
+  }
+  if (Array.isArray(args && args.files) && args.files.length > 0) {
+    return fileName;
+  }
+  if (hasExtension(fileName)) {
+    return fileName;
+  }
+  var ext = defaultExtensionForDeliverable(args);
+  return ext ? fileName + ext : fileName;
+}
+
 var TOOL_DEFS = [
   {
     name: "upload_deliverable",
@@ -54,7 +116,7 @@ var TOOL_DEFS = [
         },
         file_name: {
           type: "string",
-          description: "用户可见的文件名，例如 adventure-game 或 report.md。多文件交付时这里应是目录名/项目名，不要写成 .zip，除非用户明确要求压缩包。"
+          description: "用户可见的文件名，单文件必须带扩展名，例如 report.md 或 report.html。若用户未指定文档格式，默认使用 .md。多文件交付时这里应是目录名/项目名，不要写成 .zip，除非用户明确要求压缩包。"
         },
         content_text: {
           type: "string",
@@ -170,12 +232,13 @@ function buildReplyMarkdown(opts) {
 // ─── Tool implementations ─────────────────────────────────────────────────────
 
 function uploadDeliverable(args) {
+  var normalizedFileName = normalizeDeliverableFileName(args);
   var body = {
     resourceId: args.resource_id,
     groupId:    args.group_id,
     userId:     args.user_id,
     type:       args.type,
-    fileName:   args.file_name,
+    fileName:   normalizedFileName,
     release:    ""  // overwritten below after release name derivation
   };
 

package/openclaw-plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "plugin-deliverables",
-  "version": "1.0.18",
+  "version": "1.0.19",
   "npm_package": "@dai_ming/plugin-deliverables",
   "description": "Deliverables plugin: MCP server + skill + AGENTS rules for AI-generated file uploads",
   "mcp_servers": {

package/openclaw.plugin.json

@@ -2,7 +2,7 @@
   "id": "plugin-deliverables",
   "name": "Deliverables",
   "description": "Deliverables runtime guard for upload-first file delivery with Palz split-send diagnostics.",
-  "version": "1.0.18",
+  "version": "1.0.19",
   "skills": ["./skills"],
   "configSchema": {
     "type": "object",

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@dai_ming/plugin-deliverables",
-  "version": "1.0.18",
+  "version": "1.0.19",
   "description": "OpenClaw deliverables plugin — upload AI-generated files to OSS and return shareable preview/download links",
   "keywords": [
     "openclaw",

package/skills/deliverables/SKILL.md

@@ -32,7 +32,7 @@ description: 上传AI生成的文件到交付物系统，返回可分享的预
 | `group_id` | 消息元数据中的 `group_id` 或 `conversation_id` | `group_abc123` |
 | `user_id` | 消息元数据中的 `sender_id` 或 `owner_id` | `cbb0fab9...` |
 | `type` | 根据内容选择：`article`/`game`/`image`/`video`/`ppt`/`zip`/`link` | `article` |
-| `file_name` | 有意义的文件名，含扩展名 | `report-2026.html` |
+| `file_name` | 有意义的文件名，单文件必须含扩展名；若用户未指定文档格式，默认用 `.md` | `report-2026.html` |
 | `content_text` | 文件的完整文本内容（HTML/Markdown等） | `<html>...</html>` |
 
 > **直接对话（direct chat）时**：`group_id` 填 `conversation_id`，`user_id` 填 `owner_id`。