@qqbrowser/openclaw-qbot 0.10.19 → 0.10.20

package/skills/qqbrowser-skill/SKILL.md

@@ -23,10 +23,10 @@ permissions:
 
 This skill requires the following permissions to function properly:
 
-| Permission                   | Scope                      | Purpose                                                            |
-| ---------------------------- | -------------------------- | ------------------------------------------------------------------ |
-| **Network Access**           | Outbound HTTP/HTTPS        | Required for browser navigation, page loading, and web interaction |
-| **File System (Read/Write)** | Temporary directories only | Required for saving screenshots (`.webp`) and downloaded files     |
+| Permission | Scope | Purpose |
+|------------|-------|--------|
+| **Network Access** | Outbound HTTP/HTTPS | Required for browser navigation, page loading, and web interaction |
+| **File System (Read/Write)** | Temporary directories only | Required for saving screenshots (`.webp`) and downloaded files |
 
 ### File Storage
 
@@ -41,14 +41,27 @@ Please call the standalone qqbrowser-skill browser_snapshot command only when ne
 
 ## Core Workflow
 
+> **MANDATORY for AI tasks:** every automation **MUST** be wrapped in
+> `browser_start_session` / `browser_end_session` (see
+> [Session Lifecycle](#session-lifecycle-mandatory-for-ai-tasks)). Running any
+> other `browser_*` command without an active session is **not allowed** for AI
+> agents — it will pollute the user's normal browsing tabs and bypass task
+> isolation. Always start the session first, then run the workflow below
+> inside it, then end the session.
+
 Every browser automation follows this pattern:
 
-1. **Navigate**: `qqbrowser-skill browser_go_to_url --url <url>`
-2. **Snapshot**: `qqbrowser-skill browser_snapshot` (get indexed element refs)
-3. **Interact**: Use element index to click, fill, select
-4. **Re-snapshot**: After navigation or DOM changes, get fresh refs
+1. **Start session**: `qqbrowser-skill browser_start_session --sessionId <unique-id>` (REQUIRED)
+2. **Navigate**: `qqbrowser-skill browser_go_to_url --url <url>`
+3. **Snapshot**: `qqbrowser-skill browser_snapshot` (get indexed element refs)
+4. **Interact**: Use element index to click, fill, select
+5. **Re-snapshot**: After navigation or DOM changes, get fresh refs
+6. **End session**: `qqbrowser-skill browser_end_session --sessionId <unique-id>` (REQUIRED)
 
 ```bash
+# REQUIRED: open an isolated session before any other browser command.
+qqbrowser-skill browser_start_session --sessionId task-abc123
+
 qqbrowser-skill browser_go_to_url --url https://example.com/form
 qqbrowser-skill browser_snapshot
 # Output includes element indices: [1] input "email", [2] input "password", [3] button "Submit"
@@ -58,6 +71,9 @@ qqbrowser-skill browser_input_text --index 2 --text "password123"
 qqbrowser-skill browser_click_element --index 3
 qqbrowser-skill browser_wait --seconds 2
 qqbrowser-skill browser_snapshot  # Check result
+
+# REQUIRED: end the session when the task finishes.
+qqbrowser-skill browser_end_session --sessionId task-abc123
 ```
 
 ## Essential Commands
@@ -160,11 +176,72 @@ qqbrowser-skill <skill_name> --help                  # Show help for a specific
 qqbrowser-skill status                               # Check skill status
 ```
 
+## Session Lifecycle (Mandatory for AI Tasks)
+
+**AI agents MUST wrap every task with `browser_start_session` /
+`browser_end_session`.** This is not optional. The extension creates a
+dedicated **Chrome Tab Group** as the AI workspace, isolating the task from the
+user's other tabs and letting the user review the AI's work after the task
+ends (the tab group is preserved on `end_session`).
+
+Hard rules for AI agents:
+- **Always call `browser_start_session` first**, before any other `browser_*`
+  command. Calling other commands without an active session is **forbidden** —
+  it will mix AI-driven tabs with the user's personal browsing.
+- **Isolation mode is fixed to `enforce`** and is no longer configurable from the
+  client side — `browser_start_session` does not accept an `--isolation` flag.
+  Every AI task automatically runs in the enforced Tab Group isolation mode.
+- **Always call `browser_end_session`** when the task finishes (success,
+  failure, or early exit), so the in-memory mapping is released cleanly.
+- **One `sessionId` per task.** Generate a unique, stable ID per task (e.g.
+  UUID, task ID); do **not** reuse an ID across unrelated tasks.
+
+```bash
+# 1. REQUIRED: start an isolated session BEFORE any other browser command.
+#    sessionId is required and must be unique per task; pass any string you control.
+qqbrowser-skill browser_start_session --sessionId task-abc123
+
+#    Optional flags (isolation mode is fixed to enforce internally and cannot be overridden):
+#      --title    "AI: research"             (default: "AI: <first 8 chars of sessionId>")
+#      --color    blue|red|green|yellow|grey|pink|purple|cyan|orange  (default: blue)
+#      --initialUrl https://example.com      (default: about:blank)
+#      --windowId 12345                      (default: pick any normal window)
+qqbrowser-skill browser_start_session --sessionId task-abc123 \
+    --title "AI: research" --color blue \
+    --initialUrl https://www.baidu.com
+
+# 2. Run the normal browser workflow inside the session.
+qqbrowser-skill browser_snapshot
+qqbrowser-skill browser_click_element --index 1
+# ... etc
+
+# 3. REQUIRED: end the session when the task finishes (idempotent for the same sessionId).
+#    Call this even on failure / early exit so resources are released cleanly.
+qqbrowser-skill browser_end_session --sessionId task-abc123
+```
+
+Notes:
+- `browser_start_session` is **idempotent** — calling it twice with the same
+  `sessionId` reuses the existing tab group.
+- `browser_end_session` only releases the in-memory mapping; the tab group and
+  its tabs stay open for the user to review.
+- If the WebSocket disconnects, the extension auto-ends the session after a
+  ~30-minute grace period, so leaking sessions on crashes is bounded — but AI
+  agents must still explicitly call `browser_end_session`; do not rely on the
+  grace period as the normal exit path.
+
 ## Common Patterns
 
+> All examples below assume you are already **inside an active session**
+> opened with `browser_start_session` (see
+> [Session Lifecycle](#session-lifecycle-mandatory-for-ai-tasks)). For brevity
+> the `start_session` / `end_session` calls are omitted from each snippet, but
+> AI agents **must** always include them in real runs.
+
 ### Form Submission
 
 ```bash
+qqbrowser-skill browser_start_session --sessionId task-form-001
 qqbrowser-skill browser_go_to_url --url https://example.com/signup
 qqbrowser-skill browser_snapshot
 qqbrowser-skill browser_input_text --index 1 --text "Jane Doe"
@@ -174,6 +251,7 @@ qqbrowser-skill browser_check_op --index 4 --value
 qqbrowser-skill browser_click_element --index 5
 qqbrowser-skill browser_wait --seconds 2
 qqbrowser-skill browser_snapshot  # Verify result
+qqbrowser-skill browser_end_session --sessionId task-form-001
 ```
 
 ### Data Extraction
@@ -184,21 +262,25 @@ Choose the right `browser_snapshot` mode based on intent:
 - **`browser_snapshot`** (default) — required for **interacting** with the page. Returns indexed elements for use with `browser_click_element`, `browser_input_text`, etc.
 
 ```bash
+qqbrowser-skill browser_start_session --sessionId task-extract-001
 qqbrowser-skill browser_go_to_url --url https://example.com/products
 qqbrowser-skill browser_snapshot --markdown                # Read the whole page as clean markdown
 
 # Use default snapshot + get_info when you need to interact or read a specific element
 qqbrowser-skill browser_snapshot
 qqbrowser-skill browser_get_info --type text --index 5     # Get a specific element's text
+qqbrowser-skill browser_end_session --sessionId task-extract-001
 ```
 
 ### Infinite Scroll Pages
 
 ```bash
+qqbrowser-skill browser_start_session --sessionId task-feed-001
 qqbrowser-skill browser_go_to_url --url https://example.com/feed
 qqbrowser-skill browser_scroll_to_bottom     # Trigger lazy loading
 qqbrowser-skill browser_wait --seconds 2     # Wait for content
 qqbrowser-skill browser_snapshot             # Get updated content
+qqbrowser-skill browser_end_session --sessionId task-feed-001
 ```
 
 ## Element Index Lifecycle (Important)

package/node_modules/@aws-sdk/credential-provider-sso/dist-cjs/loadSso-BKDNrsal.js

@@ -1,8 +0,0 @@
-'use strict';
-
-var sso = require('@aws-sdk/nested-clients/sso');
-
-
-
-exports.GetRoleCredentialsCommand = sso.GetRoleCredentialsCommand;
-exports.SSOClient = sso.SSOClient;