(1) After MCPActivate, the continuation prompt now enumerates the
activated server's callable tool names so the next turn calls them
directly instead of burning a turn on tool-discovery guesses.
(2) Resume no longer deletes the session file from disk; previously
every click on a past chat permanently removed it from history.
(3) WS replay skips agent:closed events; replaying them on a fresh
client destructively deleted the session being opened.
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.
claude_code preset auto-attaches the user's claude.ai-connected partner
MCPs (mcp__claude_ai_*). They bypass MCPActivate, don't share OAuth
state with OpenSwarm's Gmail/Drive/Calendar connectors, and confuse
the model into picking the partner shim instead of our vetted server.
Hard-block via disallowed_tools + add a system-prompt rule.
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)
reasoning text" note instead of vanishing); friendlier MCP tool names (Gmail/Slack/etc with verb-derived actions); auto-collapse Anthropic
thinking pill on turn end so the answer comes first; header timer matches per-turn pill (sums in ms, rounds once); thinking pill rolls 251s
to 4m 11s; parallel tool count chips do not jitter as N grows; drop Gemini 2.5 from picker (Gemini 3 family only); aux-LLM calls route
per-model so cheap-tier auxiliary calls do not 401 on cc/ subscription routes
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
state.models.byProvider, disambiguates same-named models by · Provider), toolbar now honors the stored default_model instead of snapping to
stale Redux initial 'sonnet' and re-syncs on every reopen so last-used picks don't leak, smart fallback per priority Anthropic > OpenAI >
Gemini > OpenSwarm Pro > OpenSwarm with Snackbar warning when the user's default becomes unreachable, new Default thinking mode setting
(Auto/Off/Low/Medium/High) added to AppSettings and threaded into AgentSession on launch, onboarding flow for user intuitive-ness slight tweaks
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
- Add BUILTIN_MODELS for OpenAI (GPT-5.4/Mini/5.3-Codex), Google (Gemini 3 Pro/Flash, 2.5 Pro/Flash), and GitHub Copilot
- Add resolve_model_id_for_sdk() and resolve_aux_model() to route prefixed model IDs (cx/, gc/, gh/) through 9Router translator
- Add GET /agents/models endpoint returning available models based on live 9Router connection state
- Enable ENABLE_TOOL_SEARCH=auto for all providers so non-Claude models get full tool access (23 built-in + all MCPs)
- Add thinking block streaming support (ThinkingBlock in stream handler + AssistantMessage) for reasoning models
- Fix Gemini 3 thought-signature errors: use skip_thought_signature_validator per Google docs
- Fix WebSearch blocked_domains/allowed_domains empty-list rejection on Anthropic API
- Fix browser_agent text_parts UnboundLocalError on non-Claude models
- Fix auxiliary LLM calls (title gen, group meta, dashboard naming, view builder, browser agent) via resolve_aux_model
- Add Codex OAuth callback listener on port 1455 for ChatGPT Plus subscription connect
- Route Gemini OAuth through system browser since Google blocks embedded webviews
- Override Electron popup user-agent for OAuth
- Fix duplicate OAuth callback with idempotent completed_oauth tracking
- Fix Settings modal tab routing and stale warning banner
- Add API key inputs for OpenAI, Google, and OpenRouter
- Add MCP warning banner when selecting non-Claude model with many tools
- Force session fork on cross-provider model switch to prevent transcript corruption
- Disable GitHub Copilot subscription card (9Router poll issue, marked preview)
- Delete dead CopilotProvider import and unused CopilotAuthButton component
ciregenz