chore(release): 1.2.1 — relay tab-drift pin on open (#14/#18) + stable per-tab relay session (#17)

- fix(relay): pin active target on open so commands don't drift tabs (#14, #18)
- fix(connect): stable per-tab relay session id — re-attach auto-recovers (#17)
- docs: chrome-use test in README

README.md

@@ -205,6 +205,47 @@ chrome-use --launch --profile auto open https://x.com/home
 
 In CI environments, standalone mode is used automatically.
 
+## Automated testing (`chrome-use test`)
+
+Turn the repetitive "open it, click around, check it's right" work into a
+**re-runnable suite** — unit tests for the frontend. Write cases in YAML; steps
+reuse chrome-use's own commands and assertions compile to a single check:
+
+```yaml
+# smoke.yaml
+suite: chatgpt smoke
+setup:
+  - account: chatgpt/huayue          # inject a cookie-use login (optional)
+cases:
+  - name: home loads logged in
+    steps:
+      - open: https://chatgpt.com/
+      - wait: { load: networkidle }
+    assert:
+      - url: { contains: chatgpt.com }
+      - visible: "#prompt-textarea"
+```
+
+```bash
+chrome-use test smoke.yaml                     # launches an isolated browser, runs cases
+chrome-use test smoke.yaml --session default   # …or against your connected Chrome
+```
+
+```
+suite: chatgpt smoke  (session cu-test)
+  ✓ home loads logged in   1.2s
+  ✗ composer takes text    0.8s
+      assert text "#prompt-textarea" contains "hi" → got ""
+      ↳ cu-test-artifacts/composer-takes-text.png
+2 cases · 1 passed · 1 failed
+```
+
+Exit code is non-zero if any case fails (drop it into CI), and failed cases save
+a screenshot. Assertions: `url` · `visible` · `hidden` · `text` · `count` ·
+`eval`. Steps: `open` · `click` · `fill` · `type` · `press` · `wait` · `scroll`
+· `eval`. Full guide: `chrome-use skills get test`. Found a regression? Add a
+case — the suite gets more valuable the more you use it.
+
 ## Anti-detection
 
 <img src="assets/shield.png" alt="stealth shield" width="320" align="right" />

cli/Cargo.lock

@@ -290,7 +290,7 @@ checksum = "613afe47fcd5fac7ccf1db93babcb082c5994d996f20b8b159f2ad1658eb5724"
 
 [[package]]
 name = "chrome-use"
-version = "1.2.0"
+version = "1.2.1"
 dependencies = [
  "aes",
  "aes-gcm",

cli/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "chrome-use"
-version = "1.2.0"
+version = "1.2.1"
 edition = "2021"
 description = "Fast browser automation CLI for AI agents"
 license = "Apache-2.0"

cli/src/native/browser.rs

@@ -136,6 +136,24 @@ fn active_page_index_after_removal(
     active_page_index
 }
 
+/// Resolve the session's active page index: prefer the pinned `active_target_id`
+/// (stable across tab reorder / passive discovery / removal), falling back to the
+/// raw `active_page_index` only when nothing is pinned or the pin is gone. Keeping
+/// commands anchored to the pinned target is what stops `eval`/`get url`/`snapshot`
+/// from drifting onto a foreign tab between commands (issue #14).
+fn resolve_active_index(
+    pages: &[PageInfo],
+    active_target_id: Option<&str>,
+    active_page_index: usize,
+) -> usize {
+    if let Some(tid) = active_target_id {
+        if let Some(i) = pages.iter().position(|p| p.target_id == tid) {
+            return i;
+        }
+    }
+    active_page_index
+}
+
 /// Converts common error messages into AI-friendly, actionable descriptions.
 pub fn to_ai_friendly_error(error: &str) -> String {
     let lower = error.to_lowercase();
@@ -762,12 +780,11 @@ impl BrowserManager {
     /// falling back to `active_page_index` when nothing is pinned or the pin is
     /// gone. This is what keeps commands on the tab the agent actually opened.
     fn resolved_active_index(&self) -> usize {
-        if let Some(tid) = &self.active_target_id {
-            if let Some(i) = self.pages.iter().position(|p| &p.target_id == tid) {
-                return i;
-            }
-        }
-        self.active_page_index
+        resolve_active_index(
+            &self.pages,
+            self.active_target_id.as_deref(),
+            self.active_page_index,
+        )
     }
 
     /// Pin the current active page by target_id so later commands stick to it.
@@ -854,10 +871,20 @@ impl BrowserManager {
             }
         }
 
+        // An explicit `open`/navigate IS the "explicit open" the pin invariant is
+        // built around (see `active_target_id`). On the relay path `open` reuses an
+        // existing tab via this method rather than `add_page`, so without pinning
+        // here `active_target_id` stayed `None` and the session rode the fragile
+        // `active_page_index` — a later passive tab close/reorder then drifted
+        // `eval`/`get url`/`snapshot` onto a foreign tab between commands (issue
+        // #14). Sync the index to the resolved active page, then pin it by stable
+        // target_id so subsequent commands stick to the tab we just navigated.
+        self.active_page_index = self.resolved_active_index();
         if let Some(page) = self.pages.get_mut(self.active_page_index) {
             page.url = page_url.clone();
             page.title = title.clone();
         }
+        self.pin_active_target();
 
         let mut out = json!({ "url": page_url, "title": title });
         if let Some(w) = nav_warning {
@@ -1124,6 +1151,9 @@ impl BrowserManager {
             target_type: "page".to_string(),
         });
         self.active_page_index = 0;
+        // Pin this freshly-created tab (matches `add_page`) so it's a stable
+        // anchor from the first command, not a bare index (issue #14).
+        self.pin_active_target();
         self.enable_domains(&attach_result.session_id).await?;
 
         Ok(())
@@ -2175,6 +2205,55 @@ mod tests {
         assert_eq!(active_page_index_after_removal(0, 0, 0), 0);
     }
 
+    fn page(target_id: &str) -> PageInfo {
+        PageInfo {
+            tab_id: 1,
+            label: None,
+            target_id: target_id.to_string(),
+            session_id: format!("session-{target_id}"),
+            url: String::new(),
+            title: String::new(),
+            target_type: "page".to_string(),
+        }
+    }
+
+    // --- issue #14: a pinned target must keep commands on the right tab ---
+
+    #[test]
+    fn resolve_active_index_prefers_pin_over_stale_index() {
+        // The tab we opened ("A") is at index 0, but `active_page_index` is stale
+        // and points at a foreign tab ("B"). With the pin set, resolution sticks
+        // to A — the drift that bit issue #14 (eval landing on /notifications).
+        let pages = vec![page("A"), page("B")];
+        assert_eq!(resolve_active_index(&pages, Some("A"), 1), 0);
+    }
+
+    #[test]
+    fn resolve_active_index_unpinned_drifts_with_index() {
+        // Documents the pre-fix hazard: with no pin, resolution blindly trusts
+        // `active_page_index`, so a clamp/reorder from passive tab discovery lands
+        // commands on a foreign tab. This is exactly what pinning on `open` avoids.
+        let pages = vec![page("A"), page("B")];
+        assert_eq!(resolve_active_index(&pages, None, 1), 1);
+    }
+
+    #[test]
+    fn resolve_active_index_falls_back_when_pin_is_gone() {
+        // If the pinned tab was closed (target_id no longer present), fall back to
+        // the index rather than panicking or returning a bogus slot.
+        let pages = vec![page("A"), page("B")];
+        assert_eq!(resolve_active_index(&pages, Some("CLOSED"), 1), 1);
+    }
+
+    #[test]
+    fn resolve_active_index_pin_survives_passive_background_tab() {
+        // A foreign tab ("Z") gets appended by passive discovery after we pinned
+        // "A". The append doesn't shift A's position, and the pin keeps us on A
+        // regardless of what `active_page_index` happens to be.
+        let pages = vec![page("A"), page("B"), page("Z")];
+        assert_eq!(resolve_active_index(&pages, Some("A"), 2), 0);
+    }
+
     // issue #7: removing the pinned active target must re-anchor the pin to a
     // surviving page. Models `remove_page_by_target_id`'s index + re-pin steps
     // purely (BrowserManager needs a live CDP client, so the method itself can't

cli/src/native/relay.rs

@@ -330,6 +330,45 @@ mod tests {
         }
     }
 
+    #[test]
+    fn reattach_with_same_session_restores_target() {
+        // Issue #17 recovery contract. A tab's chrome.debugger session is torn
+        // down (cross-process nav, SW restart, …) then re-attached. The fix has
+        // the extension reuse the SAME `cb-tab-<tabId>` id across that churn, so
+        // after detach+reattach the relay must expose the NEW target under the
+        // SAME session — which is exactly the session the daemon is still bound
+        // to, so its eval/snapshot auto-follow the new page instead of going stale.
+        let mut s = RelayState::new();
+        s.handle_ext_message(&attached_event("T_old", "cb-tab-42"), "tok");
+        s.handle_ext_message(
+            &json!({
+                "method": "forwardCDPEvent",
+                "params": { "method": "Target.detachedFromTarget", "params": { "sessionId": "cb-tab-42" } }
+            }),
+            "tok",
+        );
+        s.handle_ext_message(&attached_event("T_new", "cb-tab-42"), "tok");
+
+        let route = s.route_client_command(1, &json!({ "id": 1, "method": "Target.getTargets" }));
+        match route {
+            ClientRoute::Local(v) => {
+                let infos = v["result"]["targetInfos"].as_array().unwrap();
+                assert_eq!(infos.len(), 1, "only the new target should remain");
+                assert_eq!(infos[0]["targetId"], "T_new");
+            }
+            _ => panic!("getTargets must be local"),
+        }
+        // The daemon's existing session id still resolves — to the new target.
+        let route = s.route_client_command(
+            1,
+            &json!({ "id": 2, "method": "Target.attachToTarget", "params": { "targetId": "T_new" } }),
+        );
+        assert_eq!(
+            route,
+            ClientRoute::Local(json!({ "id": 2, "result": { "sessionId": "cb-tab-42" } }))
+        );
+    }
+
     #[test]
     fn browser_get_version_is_answered_locally() {
         // Liveness probe must NOT be forwarded (the extension can't do

extensions/ab-connect/background.js

@@ -24,7 +24,6 @@ let port = null
 /** Whether the native-messaging host (the local chrome-use CLI) is linked.
  *  Read by the popup status page. */
 let hostConnected = false
-let nextSession = 1
 /** tabId -> { sessionId, targetId } */
 const tabs = new Map()
 /** sessionId -> tabId (main session per tab) */
@@ -261,7 +260,16 @@ async function attachTab(tabId) {
   const targetInfo = info?.targetInfo
   const targetId = String(targetInfo?.targetId || '')
   if (!targetId) throw new Error('attachTab: no targetId')
-  const sessionId = `cb-tab-${nextSession++}`
+  // Derive the session id from the STABLE Chrome tabId, not a monotonic counter
+  // (issue #17). A tab's chrome.debugger session can be torn down and
+  // re-established — cross-process navigation, a service-worker restart wiping
+  // these in-memory maps, DevTools stealing the debugger — and each time the tab
+  // re-attaches. With a counter, re-attach minted a BRAND-NEW `cb-tab-N`, which
+  // orphaned the daemon's binding (it's still pinned to the old id and the relay
+  // never tells it to rebind) → permanent "stale sessionId / tab is gone". The
+  // tabId is stable across all of that, so `cb-tab-<tabId>` restores the SAME
+  // session the daemon already holds → eval/snapshot auto-follow the new page.
+  const sessionId = `cb-tab-${tabId}`
   const entry = { sessionId, targetId }
   tabs.set(tabId, entry)
   sessionToTab.set(sessionId, tabId)

extensions/ab-connect/manifest.json

@@ -1,7 +1,7 @@
 {
   "manifest_version": 3,
   "name": "chrome-use",
-  "version": "0.4.3",
+  "version": "0.4.4",
   "description": "Let chrome-use drive your logged-in Chrome \u2014 install once, no token, no per-use confirmation.",
   "key": "MIIBIjANBgkqhkiG9w0BAQEFAAOCAQ8AMIIBCgKCAQEA6vQIyscGIPYPZdSpPwPL0+0gxUROyRgCpmvCSDoc8XUm4qm97VbKnD9Ijc1lV22lNWZtE78gaRjt6BeSfuMgnBymnhLKjN1gU6AI5QUU0mrJyeHdWKvrKQR5FmsM2A7Xr1ykE2SiiS8zNUS3Y/6O5l+Nva7wrVy6E4a2dkBVQkOsu+DV+nEZvhIyuDY5D5SPXqNwUTWTaglwj5mjvHz36xSwCWlPmrtJ+ED0AUyrb2z4GIOmvk4kqtBVrh/UD058klLo4CkYOnIybB5aV6WYuwarfPY4bF/dLggPem+ewLNTUNBuwrxj/A4nUv0LJTuRO8rR7f8WR9qnRCY0Ic5saQIDAQAB",
   "icons": {

package.json

@@ -1,6 +1,6 @@
 {
   "name": "chrome-use",
-  "version": "1.2.0",
+  "version": "1.2.1",
   "description": "chrome-use — drive your real, logged-in Chrome from any AI agent, stealth by default",
   "type": "module",
   "packageManager": "pnpm@11.1.3",

skill-data/core/SKILL.md

@@ -672,6 +672,8 @@ and [references/authentication.md](references/authentication.md).
   `chrome-use skills get electron`
 - **Slack workspace automation**: `chrome-use skills get slack`
 - **Exploratory testing / QA / bug hunts**: `chrome-use skills get dogfood`
+- **Re-runnable test suites (frontend "unit tests")**: `chrome-use skills get test`
+  — turn repeated checks into a `chrome-use test <suite.yaml>` regression suite
 - **Vercel Sandbox microVMs**: `chrome-use skills get vercel-sandbox`
 - **AWS Bedrock AgentCore cloud browser**: `chrome-use skills get agentcore`