Improve skill tab reuse guidance

Author: iFurySt

apps/chrome-extension/manifest.json

@@ -2,7 +2,7 @@
   "manifest_version": 3,
   "name": "Open Browser Use",
   "description": "Open Browser Use Chrome automation extension.",
-  "version": "0.1.39",
+  "version": "0.1.40",
   "icons": {
     "16": "icons/icon-16.png",
     "32": "icons/icon-32.png",

cmd/open-browser-use/main.go

@@ -27,7 +27,7 @@ import (
 	"github.com/spf13/cobra"
 )
 
-const version = "0.1.39"
+const version = "0.1.40"
 const defaultChromeExtensionID = "bgjoihaepiejlfjinojjfgokghnodnhd"
 const defaultCLISessionID = "obu-cli"
 const defaultMCPSessionID = "obu-mcp"

docs/histories/2026-05/20260522-1559-reuse-deliverable-tabs.md

@@ -0,0 +1,34 @@
+## [2026-05-22 15:59] | Task: Reuse deliverable tabs
+
+### 🤖 Execution Context
+
+- **Agent ID**: `Codex`
+- **Base Model**: `GPT-5`
+- **Runtime**: `Codex CLI`
+
+### 📥 User Query
+
+> 调整 Open Browser Use skill 说明：连续相关任务不应每次新开重复 tab，而应能从已完成分组里找回已有 tab 继续使用。
+
+### 🛠 Changes Overview
+
+**Scope:** `skills/open-browser-use`
+
+**Key Actions:**
+
+- **[Skill guidance]**: Added a core workflow step requiring agents to inspect existing user tabs before opening a new tab.
+- **[Tab lifecycle]**: Documented that related follow-up tasks should claim matching tabs from `✅ Open Browser Use` or handoff groups and finalize them back as deliverables when appropriate.
+- **[Release]**: Bumped runtime/package versions to `0.1.40` and added the user-facing release note.
+
+### 🧠 Design Intent (Why)
+
+连续相关任务经常指向同一个页面。明确要求先查找并 claim 已有 deliverable / handoff tab，可以避免完成分组里持续堆积重复页面，同时仍保留无明确匹配时新开 tab 的安全边界。
+
+### 📁 Files Modified
+
+- `skills/open-browser-use/SKILL.md`
+- `docs/releases/feature-release-notes.md`
+- `cmd/open-browser-use/main.go`
+- `apps/chrome-extension/manifest.json`
+- `packages/*/package.json`
+- `packages/open-browser-use-python/pyproject.toml`

docs/releases/feature-release-notes.md

@@ -4,6 +4,7 @@
 
 | 日期 | 功能域 | 用户价值 | 变更摘要 |
 | --- | --- | --- | --- |
+| 2026-05-22 | Skill Tab Reuse | Agent 处理连续相关任务时会优先复用已交付或 handoff 的匹配标签页，不再把同一个页面反复堆进完成分组。 | 发布 `0.1.40` patch 版本，强化 `skills/open-browser-use` 的 Core Workflow、Operating Rules 和 Tab Lifecycle：新开 tab 前先检查 `user-tabs`，从 `✅ Open Browser Use` 或旧 handoff group 中 claim 明确匹配的 tab，并在有歧义时避免误 claim。 |
 | 2026-05-17 | macOS Native Host Socket | macOS 用户在较长 `TMPDIR` 环境下也能稳定连接 native host，不再因为 Unix socket 路径过长导致 popup 只显示 `Native host has exited`。 | 发布 `0.1.39` patch 版本，Unix 默认 socket 根目录恢复为固定短路径 `/tmp/open-browser-use`，Windows 继续使用系统临时目录；bind 失败错误补充 socket 路径长度，并新增默认路径、实际 bind、长路径诊断的回归测试。 |
 | 2026-05-16 | Chrome Extension Popup | 用户打开 popup 时能直接看到当前 extension 版本，并根据自己的系统看到合适的 CLI 安装命令；macOS 保留 npm 和 Homebrew 两条路径，Windows/Linux 只显示 npm。 | 发布 `0.1.38` patch 版本，popup 新增版本 pill 和 OS-aware CLI install 面板，补充 OBU render harness 验证，并同步 README skill 安装命令去掉不再需要的 `--copy`。 |
 | 2026-05-16 | Windows CLI Install | Windows 用户可以通过 `npm i -g open-browser-use && open-browser-use setup` 完成 native host 注册和 Chrome Web Store 扩展连接，也可以从 GitHub Release 下载 Windows zip 直接运行 CLI。 | 发布 `0.1.37` patch 版本，补齐 Windows registry setup、stable exe copy、`--parent-window` native host 启动识别、Windows socket/profile 路径、release Windows zip 制品，并用真实 Windows Chrome 跑通 `info`、`user-tabs`、`open-tab`、`page-info` 和 `finalize-tabs`。 |

packages/browser-client-rewrite/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@open-browser-use/browser-client-rewrite",
-  "version": "0.1.39",
+  "version": "0.1.40",
   "private": true,
   "type": "module",
   "scripts": {

packages/browser-use-protocol/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@open-browser-use/browser-use-protocol",
-  "version": "0.1.39",
+  "version": "0.1.40",
   "private": true,
   "description": "Browser Use native pipe framing and JSON-RPC helpers.",
   "type": "module",

packages/open-browser-use-cli/package.json

@@ -1,6 +1,6 @@
 {
   "name": "open-browser-use",
-  "version": "0.1.39",
+  "version": "0.1.40",
   "description": "Open Browser Use native host and CLI binary.",
   "license": "MIT",
   "type": "module",

packages/open-browser-use-js/package.json

@@ -1,6 +1,6 @@
 {
   "name": "open-browser-use-sdk",
-  "version": "0.1.39",
+  "version": "0.1.40",
   "description": "JavaScript/TypeScript SDK for Open Browser Use.",
   "license": "MIT",
   "type": "module",

packages/open-browser-use-python/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "open-browser-use-sdk"
-version = "0.1.39"
+version = "0.1.40"
 description = "Python SDK for Open Browser Use."
 readme = "README.md"
 requires-python = ">=3.10"

skills/open-browser-use/SKILL.md

@@ -14,13 +14,14 @@ Open Browser Use connects an MV3 Chrome extension, a local native messaging host
 1. Check setup with `open-browser-use ping` or `obu ping`. If it fails because setup is missing, read [references/installation.md](references/installation.md).
 2. Pick the right browser/profile if multiple are installed. See "Browser and profile handling" below before issuing browser commands.
 3. Choose a unique browser session id for the current agent task before opening or claiming tabs. Prefer the surrounding runtime's conversation/session id when available; otherwise create a short unique id such as `obu-<task-slug>-<timestamp>`. Reuse that same id for every Open Browser Use command in this task.
-3. Name the current browser task group before opening or claiming tabs. Use a short task label followed by ` - OBU`; if no better task label is available, use `Task - OBU`.
-4. Use the CLI for simple inspection or one-shot actions: `info`, `tabs`, `user-tabs`, `history`, `open-tab`, `navigate`, `cdp`, and `call`.
-5. Use `open-browser-use run` / `obu run` for CLI-level multi-step orchestration when a small line-oriented action plan is enough and writing SDK code would be unnecessary.
-6. If the surrounding agent runtime supports local MCP servers, configure `obu mcp` and call the exposed browser tools directly. Use the `run_action_plan` MCP tool for the same line-oriented orchestration from MCP. Read [references/sdk-and-protocol.md](references/sdk-and-protocol.md).
-7. Use the JavaScript, Python, or Go SDK for larger multi-step workflows, event subscriptions, richer control flow, or when the surrounding agent runtime already runs code. Read [references/sdk-and-protocol.md](references/sdk-and-protocol.md).
-8. Before ending browser work, release or keep session tabs with `open-browser-use finalize-tabs --session-id "$OBU_SESSION_ID" --keep '<json-array>'`, the MCP `finalize_tabs` tool, or the SDK `finalizeTabs` / `finalize_tabs` / `FinalizeTabs` method.
-9. If communication fails after setup, read [references/troubleshooting.md](references/troubleshooting.md).
+4. Name the current browser task group before opening or claiming tabs. Use a short task label followed by ` - OBU`; if no better task label is available, use `Task - OBU`.
+5. Before opening a new tab, run `user-tabs` / `user_tabs` and check whether the task continues from an existing tab, including tabs in `✅ Open Browser Use` or an earlier `handoff` task group. If the URL/title/group clearly matches the current task, claim that tab and continue from it instead of opening a duplicate.
+6. Use the CLI for simple inspection or one-shot actions: `info`, `tabs`, `user-tabs`, `history`, `open-tab`, `navigate`, `cdp`, and `call`.
+7. Use `open-browser-use run` / `obu run` for CLI-level multi-step orchestration when a small line-oriented action plan is enough and writing SDK code would be unnecessary.
+8. If the surrounding agent runtime supports local MCP servers, configure `obu mcp` and call the exposed browser tools directly. Use the `run_action_plan` MCP tool for the same line-oriented orchestration from MCP. Read [references/sdk-and-protocol.md](references/sdk-and-protocol.md).
+9. Use the JavaScript, Python, or Go SDK for larger multi-step workflows, event subscriptions, richer control flow, or when the surrounding agent runtime already runs code. Read [references/sdk-and-protocol.md](references/sdk-and-protocol.md).
+10. Before ending browser work, release or keep session tabs with `open-browser-use finalize-tabs --session-id "$OBU_SESSION_ID" --keep '<json-array>'`, the MCP `finalize_tabs` tool, or the SDK `finalizeTabs` / `finalize_tabs` / `FinalizeTabs` method.
+11. If communication fails after setup, read [references/troubleshooting.md](references/troubleshooting.md).
 
 ## Operating Rules
 
@@ -29,6 +30,8 @@ Open Browser Use connects an MV3 Chrome extension, a local native messaging host
 - Do not assume Codex.app helpers, Node REPL globals, or a bundled plugin UI are available. Use the installed `open-browser-use` / `obu` CLI or the published SDKs.
 - Do not guess tab ids. List tabs first, then use ids returned by `tabs`, `user-tabs`, `open-tab`, or SDK calls.
 - Prefer `claim-tab` / `claimUserTab` for existing user tabs. Claiming should be based on the current `user-tabs` result and visible evidence such as URL, title, recency, or group.
+- For follow-up tasks, inspect `user-tabs` before opening a tab and reuse a matching tab from `✅ Open Browser Use` or a previous handoff group. A deliverable tab can be claimed back into the new task session, worked on, and finalized as `deliverable` again when it remains the user-facing result. This keeps repeated work on the same page converged to one live tab.
+- Do not claim unrelated deliverable tabs just because they are in `✅ Open Browser Use`. If several tabs plausibly match, prefer the most recent exact URL/title match; ask the user when the match is ambiguous.
 - Use `--socket` only when the user or runtime provides an explicit socket. Otherwise let the CLI and SDKs discover the active socket registry.
 - Do not rely on the CLI fallback session `obu-cli` for agent tasks. Always pass a task-unique `--session-id` to CLI and MCP commands, or set `sessionId` / `session_id` / `SessionID` in SDK clients. The fallback exists for quick manual use and can reuse stale task groups across unrelated agent sessions.
 - Direct CLI subcommands and `open-browser-use run` can share the same browser session only when they use the same explicit `--session-id`. Finalize that same session before ending browser work.
@@ -155,6 +158,7 @@ each individual browser operation.
 - Session tabs are tabs Open Browser Use has created or claimed for the current agent workflow.
 - Use one unique session id per agent task or conversation. Do not share the fallback `obu-cli` session across unrelated tasks.
 - Task session groups should be named from the task, using the pattern `<short task> - OBU`. Use `Task - OBU` as the fallback name.
+- At the start of a related follow-up task, list all user tabs and check `tabGroup`, `title`, and `url` before creating anything new. Claim an existing matching deliverable or handoff tab into the current session; only open a new tab when no suitable tab exists.
 - Keep no tabs by default: `open-browser-use finalize-tabs --session-id "$OBU_SESSION_ID" --keep '[]'`.
 - Keep a tab only when the user needs that live page after the turn. Omit research, source, search, intermediate, duplicate, blank, error, and login/navigation tabs after extracting what you need.
 - Keep a tab with `status: "deliverable"` when the tab itself is the user-facing output or requested open page, such as a created or edited document, dashboard, checkout/cart, submitted form result, or a page the user explicitly asked to inspect directly.