github Significant-Gravitas/AutoGPT autogpt-platform-beta-v0.8.4

5 hours ago

🚀 Release autogpt-platform-beta-v0.8.4

Date: October 2026


🔥 What's New?

New Features

  • #15089 - Run Copilot chat on a turn runtime that resumes at its cursor on one connection (by @Pwuts)
  • #15199 - Expert integrations connect through MCP first (by @0ubbe)
  • #15248 - Add “Give feedback” to the account menu (hotfix) (by @kcze)
  • #15216 - Keep Otto and expert replies short (by @0ubbe)
  • #15217 - Make the expert hire card short and Typeform-like (by @0ubbe)
  • #15249 - Send onboarding role to MailerLite and PostHog; exclude Iran and Russia from MailerLite (by @ntindle)
  • #15204 - Redesign wallet with chat usage and credits (by @Torantulino)
  • #15196 - Move onboarding paywall after personalization (by @Torantulino)
  • #15061 - Approval cards label/word tool arguments from the tool schema (by @Pwuts)
  • #15358 - Canceling a trial keeps access until the trial ends (by @itsababseh)
  • #15361 - Sub-session waits for a slot when the user’s slots are full (by @Pwuts)
  • #15043 - Approved call chain row expands to show what ran (by @Pwuts)
  • #15349 - Add “Chats” to the collapsed sidebar (by @itsababseh)
  • #15441 - Show “Thinking…” instead of backend status lines in Copilot (by @0ubbe)
  • #15442 - Restyle chat markdown tables (by @0ubbe)
  • #15462 - Give Copilot turns and graph node runs their own Sentry traces (by @ntindle)
  • #15460 - Tag Sentry events with deployed commit and allow environment overrides (by @ntindle)
  • #15213 - Route browser PostHog traffic through our own domain (by @kcze)
  • #15480 - Add Meta Muse Wonder support (by @ntindle)
  • #15466 - Send MailerLite segmentation fields to PostHog too (by @ntindle)
  • #15496 - Add Google Gemini 4 Argon support (by @ntindle)
  • #15498 - Attribute AutoPilot generations in PostHog and send reply feedback there (by @kcze)

Enhancements

  • #15461 - Add shared Sentry perf-compare recipe for performance agents (by @ntindle)

UI/UX Improvements

  • #15343 - Allow scrolling anywhere in the sidebar (by @Torantulino)
  • #15407 - Show a single paywall toast with an upgrade link when a Copilot send is refused (by @ntindle)
  • #15439 - Indicate no model is connected in builder chat; hide spend without billing (by @ntindle)
  • #15448 - Prevent mobile expert pill overlap (by @0ubbe)
  • #15455 - Line up mobile expert pill with the floating controls (by @0ubbe)

Bug Fixes

  • #15252 - Prevent long “Other” role input from losing onboarding profile (by @ntindle)
  • #15250 - Use the right client for worker timezone and store checks (by @ntindle)
  • #15309 - Install poetry and prisma in their own venvs so the image builds on debian:13-slim (by @Pwuts)
  • #14148 - Index schedule reads by user and reduce jobstore queries per cache miss (by @ntindle)
  • #15342 - Stop overcharging resumed SDK turns (hotfix) (by @ntindle)
  • #15147 - Marketplace search finds experts by job title (by @Pwuts)
  • #15149 - find_capability finds roster experts to hire and the user’s team (by @Pwuts)
  • #15305 - Charge each SDK turn its own cost, not the session’s running total (by @Pwuts)
  • #15182 - Bound AutoPilot trace export retries (by @ntindle)
  • #15159 - Connect Telegram by messaging the bot first; adding to a group is optional (by @Bentlybro)
  • #15254 - bash_exec kill-tree no longer leaves children alive during mid-listing exit (by @Bentlybro)
  • #15346 - Start streaming a queued turn once backend runs it (no reload needed) (by @Pwuts)
  • #15357 - PostHog flag reads carry email; dual mode logs only real disagreements (by @Pwuts)
  • #15348 - Skip scheduled Copilot turn while owner is paywalled or over cost cap (by @Pwuts)
  • #15153 - Library e2e: wait for search to apply before clicking a card (by @Pwuts)
  • #15356 - Accept Web Push subscriptions from Edge, Safari, and pre-release Chrome (by @Pwuts)
  • #15347 - Keep one running slot reserved for the user’s own message (by @Pwuts)
  • #15353 - Queued messages and approval wakes start under their correct envelope (by @Pwuts)
  • #15121 - Sync Codex transport tool rounds to the main turn limit (by @ntindle)
  • #15370 - Load feature flags at startup in every service that reads them (by @Pwuts)
  • #15380 - Show a lost send’s finished answer instead of “Failed to fetch” (by @Pwuts)
  • #15382 - Plans bought during a canceled trial update the trial’s subscription (by @ntindle)
  • #15381 - Retry Anthropic 5xx and overload errors reported by Claude CLI (by @ntindle)
  • #15391 - Make Sentry reports readable and reduce instrumentation noise (by @ntindle)
  • #15393 - Stop library, home, and AutoPilot pages waiting on the scheduler (by @ntindle)
  • #15399 - Charge retried turns only for the attempt that succeeded (by @ntindle)
  • #15310 - Strip only trailing /api in getAGPTServerBaseUrl (by @ntindle)
  • #15311 - Route briefing footer choice via proxy; echo state on MCP OAuth errors (by @ntindle)
  • #15331 - Stop transformDates rewriting user inputs and zone-less strings (by @ntindle)
  • #15389 - Prevent per-user credentials lock from stalling Copilot for 60s (by @ntindle)
  • #15395 - Make editing a schedule work end-to-end (by @ntindle)
  • #15402 - Stale-tab message during another tab’s turn shows as queued follow-up (by @Pwuts)
  • #15408 - Keep hosted-only UI out of self-hosted installs (by @ntindle)
  • #15409 - Fix self-hosted signup grant, memory page, and no-model chat (by @ntindle)
  • #15398 - Prevent false errors/spinners/endless retries after lost Copilot connection (by @Pwuts)
  • #15410 - Stop sending a locked Advanced tier from a stored choice (by @Pwuts)
  • #15413 - Replace a user’s credential list in a single transaction (by @ntindle)
  • #15412 - Share subscription lookup cache across API workers (by @ntindle)
  • #15420 - Transient retries bill once, never repeat tool calls, and work on first turns (by @ntindle)
  • #15417 - Mask credentials in request URLs before logs and Sentry (by @ntindle)
  • #15424 - Fix dropped-Escape test flakes and an unhovered usage tooltip (by @ntindle)
  • #15425 - Log logout-closed WebSocket at debug, not failure (by @ntindle)
  • #15426 - Create a new user profile on first read instead of returning 404 (by @ntindle)
  • #15419 - Show which step failed and why when a run completes with errors (by @ntindle)
  • #15066 - Sign in to Slack’s MCP server using a configured Slack app (by @Bentlybro)
  • #15367 - HubSpot block: request service key/private app token instead of retired API key (by @Bentlybro)
  • #15435 - Fail tests that leave DB transactions open; fix the offending test (by @ntindle)
  • #15433 - Stop duplicate/noisy Sentry reports (by @ntindle)
  • #15434 - Prevent optional select inputs crashing review cards and run forms (by @ntindle)
  • #15438 - Name the missing field when a graph can’t be saved (by @ntindle)
  • #15427 - Stop slow reads from hiding pending subscription changes (by @ntindle)
  • #15366 - Sign in to HubSpot’s MCP server with configured app; refuse placeholder client where secret is required (by @Bentlybro)
  • #15359 - Safely render .pptx and other Office files on Files page (SECRT-2437) (by @Abhi1992002)
  • #15464 - Refresh Debian packages daily in image builds so security fixes ship (by @ntindle)
  • #15467 - Read a trial user’s trial once per chat message (not four times) (by @ntindle)
  • #15474 - Revert 1-hour SDK prompt cache (reverts #15470) (by @ntindle)
  • #15481 - Label dev deployment as dev (not preview) in Sentry and PostHog (by @ntindle)
  • #15369 - Provision managed Ayrshare profile when AutoPilot needs it (by @Bentlybro)
  • #15482 - Make load tests authenticate through Better Auth (by @ntindle)
  • #15484 - Keep an approved call’s result out of the user’s bubbles (by @Pwuts)
  • #15221 - Hide trial offers for users with an existing plan (by @Torantulino)
  • #15219 - Finish transactional email client compatibility (by @Torantulino)
  • #14154 - Fix AI/ML API URL (blocks/llm) (by @hugoaimlapi)
  • #14939 - Stop retransmitted chat send from queueing and running again (SECRT-2695) (by @Bentlybro)
  • #15067 - Give every sidebar, popup, and builder chat the main chat’s cards (by @Bentlybro)
  • #15128 - Run community Replicate models without a version hash (SECRT-2806) (by @Bentlybro)
  • #15493 - Approval label reflects what each answered card sent to Otto (by @Pwuts)
  • #15489 - Deleted shared runs stop serving their page and files (by @kcze)
  • #15251 - Use “workflow” (not “agent”/“graph”) in user-facing copy (SECRT-2853) (by @itsababseh)

Documentation

  • (No documentation changes in this release)

Dependencies & Maintenance

  • #15230 - Halve local test RAM and dependency image footprint (by @ntindle)
  • #15354 - Drop leftover names of retired feature flags (by @Pwuts)
  • #15360 - Keep OSS Scanner build and threat model in .oss-scanner/ (by @ntindle)
  • #15379 - Verify each chat route charges what its provider billed (by @ntindle)
  • #15404 - Test billing audit mischarge report and clarify which relaunches keep the baseline (by @ntindle)
  • #15397 - Add journeys leg to e2e for hosted-config user journeys (by @ntindle)
  • #15405 - Frontend Copilot tests: assert UI after every way the connection can end (by @Pwuts)
  • #15429 - Park compaction streams in tests instead of timing them (by @ntindle)
  • #15428 - Pin retry shutdown boundary and compaction cut-short test coverage (by @ntindle)
  • #15431 - Run AutoPilot journeys against a scripted model server (by @ntindle)
  • #15072 - Bump dev dependencies (2 updates) (by @dependabot[bot])
  • #15158 - Bump production dependencies (2 updates) (by @dependabot[bot])
  • #15465 - Bump production dependencies (2 updates) (by @dependabot[bot])
  • #15457 - Apply Dependabot security bumps to backend dev dependencies (by @kcze)
  • #15242 - Bump backend dev dependencies (7 updates) (by @dependabot[bot])

🎉 Thanks to Our Contributors!

A huge shoutout to everyone who contributed to this release. Special thanks to our new contributors:

As well as our returning contributors:


📥 How to Get This Update

To update to this version, run:

git pull origin autogpt-platform-beta-v0.8.4

Or download it directly from the
Releases page.

For a complete list of changes, see the Full Changelog.


📝 Feedback and Issues

If you encounter any issues or have suggestions, please join our Discord and let us know!

Don't miss a new AutoGPT release

NewReleases is sending notifications on new releases.