Browser sub-agents can now drive Google Drive’s share-doc flow end to end: same-process cross-origin iframes (the share dialog) are visible through a frame-tree-aware AX walk, and combobox autocomplete fields fill in one click_index call via DOM.focus + Input.insertText. When a spawned browser card’s agent finishes, the card now fades through a “Task done” pill with a Keep button for ~3s instead of snapping out, so the user sees what happened.
* [aidan] ui: sidebar reorder
* [aidan] ux: sidebar naming bug fix
* [aidan] ui: title changing improvements
* [aidan] ui/ux: aux title gen streams for cx/ route + agent writes meta.json first
- All aux LLM calls (chat title, turn label, group meta, dashboard name) now stream
instead of using messages.create; 9router's cx/ subscription response translator
drops content for GPT-5-family models on the non-streaming path but works per-event.
- aux_max_tokens_for floors GPT-5 budget at 4K so reasoning still leaves headroom for
a label; non-reasoning models get the base 100.
- App Builder skill: write meta.json FIRST (step 1 of Quick start) so the app's name
surfaces in the sidebar + ViewEditor header on the agent's first tool call instead
of waiting until end-of-turn.
- Session-end sync_output_from_meta_json takes a fallback_name (= session.name) so an
agent that never writes meta.json still leaves the app with the aux-LLM chat title
rather than "Untitled App".
- Title display: truncateForTitle caps at 4 words / 30 chars; displayChatTitle picks
the right Phase 1 placeholder by session.mode; normalizeSessionName strips legacy
Agent-XXXX names at slice intake.
- Typewriter component (char-by-char delete-then-type) drives the chat header,
dashboard card title, sidebar Apps entry, and ViewEditor TextField + description
field; honors useReducedMotion.
* [aidan] tune: reduce gpt-5 aux token floor
The backend already broadcasts the originating dashboard_id with every browser_card_added, but the frontend was throwing it away. Browser cards live in a single global Redux dict and the canvas rendered all of them unfiltered, so a browser spawned by an agent on dashboard A would appear in whatever dashboard the user was currently viewing.
Tag every card with its dashboard_id (at WS arrival and at fetchLayout hydration) and filter by it in useDashboardSelectors so render, bounds, layout save, and keyboard nav all see only the local dashboard's cards.
App Builder launched from canvas chat now seeds the React template and
registers an Output row tied to the session id, so the Apps sidebar
lights up immediately. Adds a post-session-complete sync that reads
meta.json from the workspace folder and updates the Output row's name
and description, ending the 'Untitled App' problem. Also adds a stale-
approval filter to the WS replay: resolved approvals no longer
resurrect as dead cards when the user navigates back to a chat.
in sentence case; activating an MCP mid-chat now actually works instead of the model guessing at made-up tool names. Also a bunch miscelaneous ui/ux tweaks, I cant be bothered :)
completed chats no longer replays the typewriter (per-session lastSeq survives AgentChat remount so resume protocol stays at the high-water
mark instead of last_seq=0)
drop) instead of flipping to completed. Adds heartbeat (25s ping/10s pong), reconnect with infinite jittered backoff, outbound queue gated
on resume_ack, gap_detected fallback for long offlines, on-disk persistence of terminal events for post-restart recovery, and a
reconnecting connection state decoupled from session.status. 1089 backend tests covering 500 randomized disconnect scenarios + concurrent
broadcast races. Backend/WS handler does not cancel agent task on disconnect
+ webview popup dark-screen via new-window → exitFullscreen so parent stays interactive, ErrorSlime extracted to shared component and
rendered on all chat error cards (Network / Servers maxed / Plan limit / Subscription), Network issue classifier tightened to real errno
codes + retry CTA removed since edit_message-based replay was truncating successful tool history — copy now directs user to send-new-message
once WS auto-reconnects
that dir and retry once — fixes Discord/YouTube failing with "MCP stdio process exited unexpectedly" after partial npx installs,
per-browser auto-close: spawned browser cards now disappear on their own sub-agent's completion instead of lingering until the parent agent
finishes, WebSocketManager agent:status matches by session.browser_id (spawned_by is the parent, so it never matched the finishing
sub-agent), user-created/pre-selected browsers untouched
with Stripe, auto-revert to own_key on revoke/expire, PostHog identify segments events by plan, browser agent + capacity UX: browser sub-agents inherit the parent's Anthropic
pick properly, spawned browser cards auto-close on natural completion, OpenSwarm-servers-maxed card with Discord waitlist CTA, auto-clear local subscription state on cloud
revoke/expire