Save a static JPEG for each Browser tool call in the chat history folder and render that immutable image in transcript screenshot previews. Keep live Browser surface attachment available through stored browser/context metadata, and ignore generated Playwright CLI artifacts.
Delete the Browser plugin's injected bottom-action button so it no longer appears under the chat input while preserving the rest of the Browser surface entry points.
Update the browser regression coverage to assert the chat action stays absent.
Introduce the shared surfaces frontend service and stylesheet so Browser and Desktop can register docked or floating live UI without special cases in modals.js. Update Browser and right-canvas integration to preserve active viewers across canvas/modal switches and avoid creating blank tabs unless explicitly requested.
Keep Browser modal activation passive when switching from Desktop by reusing existing Browser sessions instead of creating a blank tab on viewer subscribe.
Add a Focus mode control to the Browser modal header matching Desktop's fullscreen/restore behavior.
Cover the passive subscribe path and Browser modal focus button in regression tests.
Render Browser tool Screenshot KVPs as clickable live thumbnails that open the Browser canvas while preserving the existing lower-row Browser action.\n\nAdd a lightweight websocket snapshot endpoint for existing browser runtimes and keep preview frame memory bounded with revocable object URLs.
- Auto-register tabs opened by site (window.open, target=_blank,
ctrl-click) via context.on("page",...) with registry lock and
closing-state guard.
- Modifier-key click via Playwright trusted input: keyboard.down/up
around mouse.click for coord-based path; locator.click(modifiers=...)
selector fallback for off-screen / hidden elements. Chrome focus
rule: ctrl/meta-click keeps focus on origin tab; override via
focus_popup arg.
- key_chord action: presses keys in order, releases in reverse;
guarantees release on exception. Supports Ctrl+A/C/V style chords.
- mouse modifiers click-only (raises ValueError for non-click events).
- list(include_content=true) bulk read across all tabs in parallel
via asyncio.gather (was sequential).
- multi action: batched sub-calls. Different browser_id groups run
concurrently; same browser_id sequentially. Returns array of
{ok, result|error} matching input order. Lets the agent fan out
reads or coordinated mutations across tabs in one tool call.
- Cross-tab work no longer steals viewer focus.
last_interacted_browser_id promotes only on open / set_active /
same-tab work / Chrome popup rule. WebUI auto-open allowlist
tightened to open|navigate|set_active so background actions don't
drag the viewer.
- New set_active action for explicit focus switch.
- JS helper bumps VERSION to force re-injection on cached pages;
exports boundingBoxFor returning {x,y,w,h,selector} for the
trusted-input modifier-click paths.
Backwards-compatible: every new arg is optional with safe defaults.
No removed actions; existing call shapes preserved.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Keep browser sessions context-qualified so tabs from different chats can coexist without closing on context switches.
Create a real chat context when Browser launches from dashboard/no selected context, preserving agent handoff for that session.
Move chat context detail out of visible tab labels and into hover tooltips using only real chat names, with regression coverage for the updated lifecycle.
Restart the canvas screencast after page-changing commands and remount viewport metrics when starting or resizing streams so canvas scrolling stays smooth across first mount, new tabs, and navigation.
Move Browser JS off Alpine global store lookups and onto direct store imports, tighten modal/canvas handoff state, and keep annotations aligned with accepted viewport frames.
Improve Browser tab close ergonomics, allow Chromium native error pages to render without blocking the UI, include right-canvas tab polish, and expand regression coverage for these paths.
Add Browser settings for the default starting page and tool-result autofocus, and wire them through config, APIs, runtime opens, and the settings UI.
Resolve Chrome extension __MSG_* manifest labels from locale metadata so installed extensions show readable names. Stabilize Browser viewport negotiation across canvas and modal surfaces by clearing stale frames, waiting for stable surface dimensions, and forcing sync after dock transitions. Move Browser loading/error state into a thin bottom status bar so it no longer overlays the page viewport.
- Auto-open Office and Browser canvas surfaces from fresh tool results, including history/result messages.
- Preserve Browser target IDs when focusing a canvas session from tool output.
- Convert substantial response-style artifacts into Office documents at runtime, without relying only on prompt compliance.
- Attach Office artifact metadata to the completed response log so the canvas opens without leaving a dangling Processing group.
- Polish Office UX by removing the inactive version-history action, showing only the healthy dot, and improving Collabora blank-load recovery with browser state cleanup.
- Deduplicate auto-open events and ignore stale results.
Extend Browser into a reusable panel that can run in either the Universal Canvas or the floating modal. Add canvas registration, dock/undock behavior, and keep the existing modal path working as a fallback.
Stabilize tab switching with viewer tokens and stale-frame rejection, prevent command snapshots from crossing active tabs, and keep tab changes responsive.
Improve canvas navigation and scrolling by making screencast polling non-blocking and removing page-settle waits from wheel input, so the visible frame updates promptly without stretch/catch-up artifacts.
Polish Browser busy feedback with a spinner-only status affordance to avoid misleading “updating browser” copy.
Introduce the new built-in Browser plugin for Agent Zero, replacing the legacy
browser-use-based browser agent with a direct Playwright-powered browser tool,
live WebUI viewer, browser session controls, status APIs, configuration, and
extension-management support.
Add browser-specific modal behavior so the browser can run as a floating,
resizable, no-backdrop window, including modal focus, toggle, and idempotent
open helpers for richer WebUI surfaces.
Remove the old `_browser_agent` core plugin and the `browser-use` dependency,
then clean up stale browser-model wiring and references across agent code,
model configuration docs, setup guides, troubleshooting docs, skills, and
Agent Zero knowledge.
Update regression and WebUI extension-surface coverage for the new browser
architecture and modal behavior.
The legacy browser-use implementation has been extracted from core so it can
continue separately as a community plugin published through the A0 Plugin Index for any user or professional that were relying on it for workflow.
