@jackwener/opencli 1.5.8 → 1.6.0

package/docs/guide/getting-started.md

@@ -48,6 +48,27 @@ opencli bilibili hot -f csv     # CSV
 opencli bilibili hot -v         # Verbose: show pipeline debug
 ```
 
+### Tab Completion
+
+OpenCLI supports intelligent tab completion to speed up command input:
+
+```bash
+# Add shell completion to your startup config
+echo 'eval "$(opencli completion zsh)"' >> ~/.zshrc              # Zsh
+echo 'eval "$(opencli completion bash)"' >> ~/.bashrc            # Bash
+echo 'opencli completion fish | source' >> ~/.config/fish/config.fish  # Fish
+
+# Restart your shell, then press Tab to complete:
+opencli [Tab]          # Complete site names (bilibili, zhihu, twitter...)
+opencli bilibili [Tab] # Complete commands (hot, search, me, download...)
+```
+
+The completion includes:
+- All available sites and adapters
+- Built-in commands (list, explore, validate...)
+- Command aliases
+- Real-time updates as you add new adapters
+
 ## Next Steps
 
 - [Installation details](/guide/installation)

package/docs/superpowers/specs/2026-04-02-browse-skill-testing-design.md

@@ -0,0 +1,144 @@
+# Browse Skill Testing Design
+
+Two-layer testing framework for `opencli browse` commands and the
+Claude Code skill integration.
+
+## Goal
+
+Verify that `opencli browse` works reliably on real websites and that
+Claude Code can use the skill to complete browser tasks end-to-end.
+
+## Architecture
+
+```
+autoresearch/
+├── browse-tasks.json       ← 59 task definitions with browse command sequences
+├── eval-browse.ts          ← Layer 1: deterministic browse command testing
+├── eval-skill.ts           ← Layer 2: Claude Code skill E2E testing
+├── run-browse.sh           ← Launch Layer 1
+├── run-skill.sh            ← Launch Layer 2
+├── baseline-browse.txt     ← Layer 1 best score
+├── baseline-skill.txt      ← Layer 2 best score
+└── results/                ← Per-run results (gitignored)
+```
+
+## Layer 1: Deterministic Browse Command Testing
+
+Tests `opencli browse` commands directly on real websites. No LLM
+involved — pure command reliability testing.
+
+### How It Works
+
+Each task defines a sequence of browse commands and a judge for the
+last command's output:
+
+```json
+{
+  "name": "hn-top-stories",
+  "steps": [
+    "opencli browse open https://news.ycombinator.com",
+    "opencli browse eval \"JSON.stringify([...document.querySelectorAll('.titleline a')].slice(0,5).map(a=>({title:a.textContent,url:a.href})))\""
+  ],
+  "judge": { "type": "arrayMinLength", "minLength": 5 }
+}
+```
+
+### Execution
+
+```bash
+./autoresearch/run-browse.sh
+```
+
+- Runs all 59 tasks serially
+- Each task: execute steps → judge last step output → pass/fail
+- `opencli browse close` between tasks for clean state
+- Expected: ~2 minutes, $0 cost
+
+### Task Categories
+
+| Category | Count | Example |
+|----------|-------|---------|
+| extract | 9 | Open page, eval JS to extract data |
+| list | 10 | Open page, eval JS to extract array |
+| search | 6 | Open, type query, keys Enter, eval results |
+| nav | 7 | Open, click link, eval new page title |
+| scroll | 5 | Open, scroll, eval footer/hidden content |
+| form | 6 | Open, type into fields, eval field values |
+| complex | 6 | Multi-step: open → click → navigate → extract |
+| bench | 10 | Test set (various) |
+
+## Layer 2: Claude Code Skill E2E Testing
+
+Spawns Claude Code with the opencli-operate skill to complete tasks
+autonomously using browse commands.
+
+### How It Works
+
+```bash
+claude -p \
+  --system-prompt "$(cat skills/opencli-operate/SKILL.md)" \
+  --dangerously-skip-permissions \
+  --allowedTools "Bash(opencli:*)" \
+  --output-format json \
+  "用 opencli browse 完成任务：Extract the top 5 stories from Hacker News with title and score. Start URL: https://news.ycombinator.com"
+```
+
+### Execution
+
+```bash
+./autoresearch/run-skill.sh
+```
+
+- Runs all 59 tasks serially
+- Each task: spawn Claude Code → it uses browse commands autonomously → judge output
+- Expected: ~20 minutes, ~$5-10
+
+### Judge
+
+Both layers use the same judge types:
+
+| Type | Description |
+|------|-------------|
+| `contains` | Output contains a substring |
+| `arrayMinLength` | Output is an array with ≥ N items |
+| `arrayFieldsPresent` | Array items have required fields |
+| `nonEmpty` | Output is non-empty |
+| `matchesPattern` | Output matches a regex |
+
+## Output Format
+
+```
+🔬 Layer 1: Browse Commands — 59 tasks
+
+  [1/59] extract-title-example... ✓ (0.5s)
+  [2/59] hn-top-stories... ✓ (1.2s)
+  ...
+
+  Score: 55/59 (93%)
+  Time: 2min
+  Cost: $0
+
+🔬 Layer 2: Skill E2E — 59 tasks
+
+  [1/59] extract-title-example... ✓ (8s, $0.01)
+  [2/59] hn-top-stories... ✓ (15s, $0.08)
+  ...
+
+  Score: 52/59 (88%)
+  Time: 20min
+  Cost: $6.50
+```
+
+## Constraints
+
+- All 59 tasks run on real websites (no mocks)
+- Layer 1: zero LLM cost, ~2 min
+- Layer 2: ~$5-10 LLM cost, ~20 min
+- Results saved to `autoresearch/results/` (gitignored)
+- Baselines tracked in `baseline-browse.txt` and `baseline-skill.txt`
+
+## Success Criteria
+
+- Layer 1 ≥ 90% (browse commands work on real sites)
+- Layer 2 ≥ 85% (Claude Code can use skill effectively)
+- Both layers cover all 8 task categories

package/docs/zh/guide/getting-started.md

@@ -32,6 +32,27 @@ opencli bilibili hot -f md      # Markdown
 opencli bilibili hot -f csv     # CSV
 ```
 
+## 终端自动补全
+
+OpenCLI 支持智能的 Tab 自动补全，加快命令输入：
+
+```bash
+# 把自动补全加入 shell 启动配置
+echo 'eval "$(opencli completion zsh)"' >> ~/.zshrc              # Zsh
+echo 'eval "$(opencli completion bash)"' >> ~/.bashrc            # Bash
+echo 'opencli completion fish | source' >> ~/.config/fish/config.fish  # Fish
+
+# 重启 shell 后，按 Tab 键补全：
+opencli [Tab]          # 补全站点名称（bilibili、zhihu、twitter...）
+opencli bilibili [Tab] # 补全命令（hot、search、me、download...）
+```
+
+补全功能包含：
+- 所有可用的站点和适配器
+- 内置命令（list、explore、validate...）
+- 命令别名
+- 新增适配器时的实时更新
+
 ## 下一步
 
 - [安装详情](/zh/guide/installation)

package/extension/package-lock.json

@@ -1,12 +1,12 @@
 {
   "name": "opencli-extension",
-  "version": "1.5.4",
+  "version": "1.5.5",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "opencli-extension",
-      "version": "1.5.4",
+      "version": "1.5.5",
       "devDependencies": {
         "@types/chrome": "^0.0.287",
         "typescript": "^5.7.0",

package/extension/src/background.test.ts

@@ -200,7 +200,7 @@ describe('background tab isolation', () => {
     ]));
   });
 
-  it('rebinds site:notebooklm to the active notebook tab instead of a home tab', async () => {
+  it('keeps site:notebooklm inside its owned automation window instead of rebinding to a user tab', async () => {
     const { chrome, tabs } = createChromeMock();
     tabs[0].url = 'https://notebooklm.google.com/';
     tabs[0].title = 'NotebookLM Home';
@@ -213,184 +213,28 @@ describe('background tab isolation', () => {
 
     const tabId = await mod.__test__.resolveTabId(undefined, 'site:notebooklm');
 
-    expect(tabId).toBe(2);
+    expect(tabId).toBe(1);
     expect(mod.__test__.getSession('site:notebooklm')).toEqual(expect.objectContaining({
-      windowId: 2,
-      preferredTabId: 2,
-      owned: false,
+      windowId: 1,
     }));
   });
 
-  it('prefers a notebook tab over an active home tab for site:notebooklm', async () => {
+  it('idle timeout closes the automation window for site:notebooklm', async () => {
     const { chrome, tabs } = createChromeMock();
     tabs[0].url = 'https://notebooklm.google.com/';
     tabs[0].title = 'NotebookLM Home';
     tabs[0].active = true;
-    tabs[1].url = 'https://notebooklm.google.com/notebook/nb-passive';
-    tabs[1].title = 'Notebook';
-    tabs[1].active = false;
-    vi.stubGlobal('chrome', chrome);
-
-    const mod = await import('./background');
-    mod.__test__.setAutomationWindowId('site:notebooklm', 1);
-
-    const tabId = await mod.__test__.resolveTabId(undefined, 'site:notebooklm');
-
-    expect(tabId).toBe(2);
-    expect(mod.__test__.getSession('site:notebooklm')).toEqual(expect.objectContaining({
-      windowId: 2,
-      preferredTabId: 2,
-      owned: false,
-    }));
-  });
 
-  it('detaches an adopted workspace session on idle instead of closing the user window', async () => {
-    const { chrome } = createChromeMock();
-    vi.stubGlobal('chrome', chrome);
     vi.useFakeTimers();
+    vi.stubGlobal('chrome', chrome);
 
     const mod = await import('./background');
-    mod.__test__.setSession('site:notebooklm', {
-      windowId: 2,
-      preferredTabId: 2,
-      owned: false,
-    });
+    mod.__test__.setAutomationWindowId('site:notebooklm', 1);
 
     mod.__test__.resetWindowIdleTimer('site:notebooklm');
     await vi.advanceTimersByTimeAsync(30001);
 
-    expect(chrome.windows.remove).not.toHaveBeenCalled();
+    expect(chrome.windows.remove).toHaveBeenCalledWith(1);
     expect(mod.__test__.getSession('site:notebooklm')).toBeNull();
   });
-
-  it('binds the active NotebookLM tab into the workspace explicitly', async () => {
-    const { chrome, tabs } = createChromeMock();
-    tabs[1].url = 'https://notebooklm.google.com/notebook/nb-active';
-    tabs[1].title = 'Bound Notebook';
-    tabs[1].active = true;
-    vi.stubGlobal('chrome', chrome);
-
-    const mod = await import('./background');
-    const result = await mod.__test__.handleBindCurrent(
-      {
-        id: 'bind-current',
-        action: 'bind-current',
-        workspace: 'site:notebooklm',
-        matchDomain: 'notebooklm.google.com',
-        matchPathPrefix: '/notebook/',
-      },
-      'site:notebooklm',
-    );
-
-    expect(result).toEqual({
-      id: 'bind-current',
-      ok: true,
-      data: expect.objectContaining({
-        tabId: 2,
-        windowId: 2,
-        url: 'https://notebooklm.google.com/notebook/nb-active',
-        title: 'Bound Notebook',
-        workspace: 'site:notebooklm',
-      }),
-    });
-    expect(mod.__test__.getSession('site:notebooklm')).toEqual(expect.objectContaining({
-      windowId: 2,
-      preferredTabId: 2,
-      owned: false,
-    }));
-  });
-
-  it('bind-current falls back to another matching notebook tab in the current window', async () => {
-    const { chrome, tabs } = createChromeMock();
-    tabs[0].windowId = 2;
-    tabs[0].url = 'https://notebooklm.google.com/';
-    tabs[0].title = 'NotebookLM Home';
-    tabs[0].active = true;
-    tabs[1].url = 'https://notebooklm.google.com/notebook/nb-passive';
-    tabs[1].title = 'Passive Notebook';
-    tabs[1].active = false;
-    vi.stubGlobal('chrome', chrome);
-
-    const mod = await import('./background');
-    const result = await mod.__test__.handleBindCurrent(
-      {
-        id: 'bind-fallback',
-        action: 'bind-current',
-        workspace: 'site:notebooklm',
-        matchDomain: 'notebooklm.google.com',
-        matchPathPrefix: '/notebook/',
-      },
-      'site:notebooklm',
-    );
-
-    expect(result).toEqual({
-      id: 'bind-fallback',
-      ok: true,
-      data: expect.objectContaining({
-        tabId: 2,
-        windowId: 2,
-        url: 'https://notebooklm.google.com/notebook/nb-passive',
-        title: 'Passive Notebook',
-      }),
-    });
-  });
-
-  it('bind-current falls back to a matching notebook tab in another window of the same profile', async () => {
-    const { chrome, tabs } = createChromeMock();
-    tabs[0].windowId = 3;
-    tabs[0].url = 'https://notebooklm.google.com/';
-    tabs[0].title = 'NotebookLM Home';
-    tabs[0].active = true;
-    tabs[1].windowId = 2;
-    tabs[1].url = 'https://notebooklm.google.com/notebook/nb-other-window';
-    tabs[1].title = 'Notebook In Other Window';
-    tabs[1].active = false;
-    vi.stubGlobal('chrome', chrome);
-
-    const mod = await import('./background');
-    const result = await mod.__test__.handleBindCurrent(
-      {
-        id: 'bind-cross-window',
-        action: 'bind-current',
-        workspace: 'site:notebooklm',
-        matchDomain: 'notebooklm.google.com',
-        matchPathPrefix: '/notebook/',
-      },
-      'site:notebooklm',
-    );
-
-    expect(result).toEqual({
-      id: 'bind-cross-window',
-      ok: true,
-      data: expect.objectContaining({
-        tabId: 2,
-        windowId: 2,
-        url: 'https://notebooklm.google.com/notebook/nb-other-window',
-        title: 'Notebook In Other Window',
-      }),
-    });
-  });
-
-  it('rejects bind-current when the active tab is not NotebookLM', async () => {
-    const { chrome } = createChromeMock();
-    vi.stubGlobal('chrome', chrome);
-
-    const mod = await import('./background');
-    const result = await mod.__test__.handleBindCurrent(
-      {
-        id: 'bind-miss',
-        action: 'bind-current',
-        workspace: 'site:notebooklm',
-        matchDomain: 'notebooklm.google.com',
-        matchPathPrefix: '/notebook/',
-      },
-      'site:notebooklm',
-    );
-
-    expect(result).toEqual({
-      id: 'bind-miss',
-      ok: false,
-      error: 'No visible tab matching notebooklm.google.com /notebook/',
-    });
-  });
 });