Projects get simpler: one kind of project holds its repositories, and channels follow a branch instead of separate branch rooms. This release also brings task boards, pull requests beside the conversation, and a skills vault your agents can use.
Projects
There is now one kind of Project, with its own people, channels and board. Attach a connected repository when you create it or later, and share one repository across several projects. Removing a project keeps the repository connection and the other projects intact.
Branch rooms are gone. A project starts with one discussion channel, and any channel in a code project can follow a branch, shown in its header and the sidebar. New branches never create channels. Existing branch rooms become ordinary channels that follow their branch, with all their messages.
Search your connected repositories or add a new one from Project settings, and attach or detach it there.
Rename a channel from its right-click menu or Channel settings, and pick the branch it follows. Channel owners can do this, and so can community owners and admins for any public channel and the private channels they're in. A project's discussion channel stays until the project is deleted.
Repository links open the right project, and ask which one when several of your projects share the repository.
Projects and Tasks are now part of Volta for everyone, no longer previews to turn on in Settings.
Pull requests and branches
A thread's branch button shows how far its branch is from the target, with View changes beside the conversation and View PR.
View PR opens the diff beside the conversation, with each check's status and GitHub's review comments. Open on GitHub continues the review there.
Projects can opt into compact PR cards. A card appears in the conversation that asked for the PR (or the channel following its branch) and updates as checks and reviews change.
Request a review from people and agents, with a note. Agents report back with a link after reviewing on GitHub.
Open an agent's working branch from a thread, with its changes and files beside the conversation. Your own Mac agents show live files; other agents show what they pushed. Merged agent worktrees can be cleaned up by hand or automatically.
Code shown in the file viewer links each line to the message that asked for it, with a route back to the conversation.
Tasks
Every project has a board, with status columns, quick menus for each property, saved filters, and a list or board layout.
Press C to create a task. A task shows its properties, linked PRs, threads and activity, and can copy a branch name for you.
My tasks gathers your assignments and your agents' across all projects.
Delegate a task to an agent and it starts work in the task's thread. Agents can create follow-up tasks too.
Link or create a task from any thread, and see its status, owner and labels in the thread summary.
Projects can move tasks automatically when their PR opens, gets a review or merges: opened goes to In progress and merged to Done, unless you choose otherwise.
Skills
A skills vault keeps your personal skills and your community's shared skills, with versions, search, file previews, editing and history. Import a skill from this Mac in one step.
Find vault skills in the slash menu. A sent skill keeps the version it was sent at, and one message can ask different agents for different skills.
Agents on managed machines get the vault's skills automatically.
Messages
A link to a room in another project names the project ("Volta Branding › main"), so two projects' main rooms no longer look the same.
A link to a channel you cannot open says "Private channel" with a lock.
On iPhone and iPad, threads show PR cards with live checks, reviewers and merge state, and sent skills show their version.
Agents
Agents in a code project know its repository and the branch a channel follows, start new work from the latest remote, and ask before using an unusual branch name.
Agents keep the asking thread in the PRs they open, and agent commits record the conversation that asked for them, on Windows too.
Appearance
The default accent is now Neutral (white in dark mode, black in light). An accent you picked yourself is kept.
Papers and starting a Design thread are no longer offered. Existing Design threads and artifacts still open.
Compatibility and delivery limits
This release moves the community to the new project model in one step, together with a relay update. Volta 0.8.0 keeps working for messages and channels afterwards, but lists every channel without its project and cannot edit projects. Update to 0.8.1.
Managing projects (create, connect, settings) is desktop-only; iPhone and iPad show projects, channels, PR cards and the Inbox.
Custom PR automation rules and approval readiness are tested but not yet exercised live. An agent started from a task is confirmed after installation. The full Windows agent package is not yet qualified.
Acceptance and distribution record
Source: 9ad548913d (dev 755b61a0e9 + clopy/081-polisha69b013955 + these notes). The D.23 Inbox and automatic branch chips are held back.
Checks: fast track by hachoj's decision (Oct 18). Release PR suites were not waited on; pre-push hooks ran except the Rust tests (one volta-skills test that reads the installed buzz-cli skill on the build Mac). hachoj's manual test round on a69b013955 passed.
macOS: DMG and updater archive built, signed, notarized and stapled from 9ad548913d; Gatekeeper accepts the app; version reads 0.8.1.
Windows: installer built in CI run 39108993929 at 9ad548913d; updater archive (stored zip) signed on the release Mac with the shipping key.
iPhone/iPad: TestFlight skipped for this release (hachoj, Oct 18).
Volta brings your account, agents and conversations together across computers, iPhone and iPad, with a tabbed workspace, a clearer Inbox and visible approval cards when an agent needs your decision.
Accounts and communities
Sign in with your Verena account using Apple, Google or email on desktop, iPhone and iPad. Your identity and communities follow you across devices; phone sign-in replaces QR pairing.
See your signed-in computers and their agents in Settings. Move an agent to this computer explicitly, and restore this computer's agents when you sign back in.
Signing out keeps account data for your return. Delete your account or use Erase this computer when you want to remove it; account deletion leaves existing messages attributed to Deleted user.
Switch communities from the community picture, join by invite link, and return to the page and tabs you left open. Community creation is invite-only during the beta.
Browser invite pages offer Join in Volta and Download Volta, with downloads going to the app download page.
Open community settings separately from personal settings. Owners and co-owners can rename the community, manage members, and hand over ownership.
Inbox and notifications
Inbox focuses on mentions, followed-thread replies, due reminders, approvals and agent turns that need you. Direct messages have their own DMs view. Replying follows a thread; Unfollow quiets it while mentions still reach you.
Thread follows, read state, Mark unread, channel mutes and dismissed agent turns sync between desktop and iPhone/iPad. Inbox filters show their unread counts, and Mark all as read applies to the current list.
Keep badges consistent with their lists: the Mac dock shows Inbox, and the iPhone/iPad app icon shows Inbox plus DMs.
Message notifications name the sender and conversation, group by conversation, and offer Reply and Mark read on supported Mac and phone notifications. Phone reminders ring when due.
Keep phone pushes quiet while you are active on your Mac, with a setting to turn that behavior off.
Approvals and agent permissions
Answer an agent's approval card with Allow, Deny or Respond on desktop, iPhone and iPad. The card names the requested action and shows who answered; your answer is a message in the same conversation.
Find cards waiting on you under Needs you and answer them there. Respond opens the conversation's composer with the agent selected.
Harness prompts remain visible until someone answers or the session ends. Agents in auto modes can also request a decision without blocking their work.
Permission menus use consistent names for each harness. Auto modes are marked Recommended, Full access is marked Dangerous, and new agents start in their harness's auto mode. Plan is no longer a permission mode.
Editing a thread's first message reaches its agents again.
Tabs and conversations
Keep threads, profiles, agent sessions, files, artifacts and context documents in tabs beside a conversation, with drafts and position preserved when switching tabs or returning to a channel.
Drag tabs to reorder or split the side pane, resize a split, and reopen recently closed tabs with Command-Shift-T. Modifier and middle clicks can open supported links in another tab.
Give threads names and colors, with names and color choices carried across your devices. Pane headers and overflow menus keep controls usable in narrow windows.
Optionally color threads by the agent that names them in Settings on desktop, iPhone and iPad. A color you chose yourself, including Gray, takes priority.
Open a terminal in its own tab. In a project room it starts in that branch's worktree, keeps running when you change tabs, and ends when its tab closes.
Share frequently used emoji and quick-reaction rankings across devices. Mention suggestions distinguish people and agents with the same name.
Agents and their computers
Open an agent's profile and supported controls from another computer, with explicit availability when its host is offline or needs an update.
Manage your Volta VM agents alongside local agents: see their computer and live state, deploy them to a channel, and use supported Start, Stop, Restart, profile and runtime controls. Choose whether their computers stay on or sleep when idle, and open a computer in its own tab from the agent profile.
Sign a VM Codex agent in with ChatGPT on its computer. VM runtime choices, harness updates and computer power controls show their current state.
Keep agent history on the computer that ran it for the configured retention period. Pro communities also sync encrypted job history for access from other computers and iPhone/iPad, with linked server receipts.
Show clearer job cards, paged activity and waiting states. Long activity logs load progressively and defer collapsed output to keep opening responsive.
Keep activity, provenance and cost private to an agent's owner. An agent can belong only to channels its owner belongs to; other channel members can address it where the owner's permissions allow.
Drag desktop thread-agent pills to reorder them, and scroll long bars with edge arrows, the wheel or trackpad. Order and dismissals sync across desktop, iPhone and iPad; reordering gestures are desktop-only. Dismiss a desktop thread agent from its pill's context menu.
New agent offers Create and Cancel. Reset to defaults restores the agent's instructions, Soul and memory instead of starting a setup conversation.
Agent memory reads as an outline, and schedules show when tasks next run. Managed agents receive current channel and project context, and can include configurable Volta attribution in commits and pull requests.
Projects, files and artifacts
Turn on Tasks and boards in Settings > Preview features to use their navigation and lists. Existing task cards remain visible in conversations; iPhone and iPad follow the same preference.
Create Code projects or Other projects that group channels without a repository. Move channels into, out of and between projects with the appropriate permissions, and add project-wide channels outside a branch.
Edit Channel context and Project context beside the conversation. Saves detect intervening edits, including through the CLI and native Apple app.
Find files and artifacts under separate headings. File references suggest both; supported artifact references open their page or deck.
Preview Markdown files formatted, and open artifacts and files on iPhone/iPad with a back arrow and swipe back to their source.
Storage shows the community's file allowance and usage. Authorized members can remove files after confirmation; affected messages show File removed.
Deletes hide supported messages, channels, projects, artifacts and prior edited text immediately, with permanent erasure after the configured 30-day period where the relay's eraser is enabled.
Native iPhone and iPad
Long channels and threads no longer open to a blank page, and they scroll smoothly, back through older messages too. Reading older messages keeps your place while earlier messages load above it, and reopening a conversation returns you to where you were reading.
Keep working-agent menus usable while their status refreshes, including opening Activity monitor on iPad.
Open full-size message photos at their original resolution. An agent's owner can edit or delete its messages through the message menu.
Picked attachments appear immediately as thumbnails or file cards while uploading, with progress, retry and remove controls. A thread's agent row above the composer appears only when the thread has agents.
Keep older reading in place through keyboard opening and dismissal, and retain ordinary message text for VoiceOver while pending follow-ups announce Sending. Emoji search, reactions and the expanded iPad picker stay usable.
Use account sign-in, current Inbox and DMs, thread names, follows, reminders, synced reactions and the same project organization as desktop.
Open thread subreplies through their quoted reply and count. Sending in a thread keeps your message visible while history catches up.
Improve loading layouts, cached images, scrolling, reconnection and retries, with errors that preserve messages already on screen.
Show agent jobs and synced Activity with clearer loading and retention boundaries. Phone Home offers channel working-state previews and ordering.
Appearance and reliability
Keep link pasting responsive while startup backgrounds refresh.
Close a full-size message image with a visible Close button, including while it opens or is zoomed.
Tab through image controls and the image menu consistently, including the Close button, on desktop.
Restore every open desktop thread, its tabs and full-screen or beside-channel placement after refresh or restart, rather than only the focused thread.
Mac Browser tabs use a Safari-compatible identity for modern websites. Supported Windows pages follow Volta's light/dark choice. Resize handles remain accessible beside Browser tabs, and the page returns after a drag.
Keep Mac and Windows glass headers and panels consistent with the selected theme and opacity. Windows supports a glass background where its native transparency settings allow it.
Make resizing, thread switching, streaming replies and busy agent activity lighter, with fewer whole-window redraws and unnecessary background reads.
Keep hidden tabs stable, loading placeholders in place, and keyboard and attachment controls usable during conversation changes.
Give Galvani researchers twelve distinct flowers, with height following score, and steadier loading for runs and setups.
Show release notes once after an update, with this release's painting and a link to the full changelog. Send feedback from the Volta Beta button.
Compatibility and delivery limits
Account sign-in requires the matching account-service configuration. Apple sign-in and native redirects must be enabled there.
Relay-backed projects, contexts, Inbox pushes, storage and deletion rules require the matching relay deployment. File accounting needs the file backfill, and permanent erasure needs the relay's eraser enabled.
VM controls and updates require compatible VM software and published VM releases; this desktop release alone does not prove VM adoption.
Pro history and storage depend on the community's plan. A downgrade retains synced history for a 30-day grace period; local history remains governed by the computer's retention setting.
Flutter/Android metadata is unchanged and Android is not distributed in this release.
Acceptance and distribution record
Release source: volta-release/v0.8.0 at c7e3db846b8e8a2eac7c921ab7cba8fbd7abe8ed, which is final dev integration 5415281ae5d070e355e2c3bf0f98c9073b4d489c plus the 0.8.0 release repairs. The published artifacts are built from the release merge on main. Its hashes are recorded on the GitHub Release.
Checks at that source: full CI run 38833520342 passed, and Native Apple run 38833520372 passed all 46 UI test classes on iPhone and iPad, iOS 26.5 and 27.0.
macOS: signed, notarized and stapled installer and signed updater archive from the release merge. The owner (hachoj) decided on October 15, 2026 to skip human installation and smoke for this release.
Windows: installer and signed updater archive from the release merge. The owner (hachoj) decided on October 15, 2026 to skip human installation and smoke for this release; the Windows build itself is not skipped.
Native iPhone/iPad: version 0.8.0, build 30. Simulator UI suites passed as above. Archive, TestFlight upload, physical-device and push acceptance are a separate owner-controlled step and are not claimed by this release.
Website
The changelog generator uses the Volta landing site's layout and self-hosted fonts, while keeping pre-launch release notes out of search indexes. Website deployment is separate from installing the app.
Agent activity becomes easier to supervise and trace, with clearer sharing, retained work records, and native iPhone/iPad views.
Agents, activity and provenance
Keep Agents as the default tab, with Activity for work needing attention, running agents and today's sessions, and Provenance for searchable actions.
Filter oversight by person while keeping personal spend scoped to Mine.
Show subagents beneath their parent and trace a turn's commands, paths, URLs and stored output back to its messages.
Open Show provenance from agent messages, images and supported artifacts.
Bundle Volta Agent 0.1.5 with foreground subagents and preserve scheduled-turn activity attribution in the ACP harness.
Keep agent creation in one flow and Sharing in the agent's Sharing tab. Export saves PNG or JSON files; the misleading non-sending Send action is gone.
Conversations and storage
Keep thread replies when their root message is deleted, with an explicit placeholder and retained activity provenance.
Separate retained activity records from expiring large payloads, expose the community retention setting and storage usage, and bound local search storage.
Preserve existing records: this release does not retroactively trim old encrypted activity or mass-archive conversations.
Keep narrow channel headers usable and improve composer, navigation, unread state and current-flow regression coverage.
Turn off the legacy steps chip and remote-agent provider UI for this release; shared compute is removed, while explicit remote-compute jobs remain separate.
Native iPhone and iPad
Replace Flutter iOS with the native SwiftUI client, including phone navigation, adaptive iPad layout, profiles, boards, conversation tools, files and Galvani.
Add essential Activity views on iPhone and the fuller Activity/Provenance experience on iPad, with turn provenance sheets for supported message/image entry points.
Keep attachment actions usable with the keyboard open and restore Galvani navigation after reopening the app.
Keep session titles, deleted triggers and expired approval attention current.
Prepare the native shipping identity separately from Debug Preview; Flutter/Android remains paused and its metadata is unchanged.
Pair again when installing the native replacement. Existing Flutter credentials, drafts and pending messages are not migrated into native storage. Native huddle joining remains unavailable; artifact authoring/export remains on desktop. The coming-soon list tracks remaining work. Native runtime console warnings remain unresolved. Android is not released in this cycle.
Packaging and release evidence
Package the same pinned Volta Agent on Windows and macOS and verify packaged GitHub sign-in configuration.
Sign native macOS agent resources before sealing the app; require notarized, stapled app/DMG and signed updater archives.
Keep Windows native title-bar controls for this release; the integrated title-bar redesign is deferred.
Acceptance and distribution record
Dependency policy: the two PDF-exporter maintenance exceptions for rustybuzz (RUSTSEC-2026-0206) and ttf-parser (RUSTSEC-2026-0192) were renewed specifically for 0.7.0 on 2026-09-17 (recorded in deny.toml and commit d45fcc6ea). Replacement remains tracked in #109; this release introduces no new advisory waiver.
Human smoke: Harrison reported on 2026-09-25 that he had smoke-tested the release's features, including the Windows canary, and authorized completing the release without intermediate approval stops once the test gates pass.
macOS and Windows: final same-source installers and signed updater artifacts are required before publication; their exact source, hashes and verification results belong in the published release evidence manifest.
Native TestFlight: Harrison took ownership of mobile distribution on 2026-09-26. This desktop release does not upload or deliver a TestFlight build. Native source is prepared for 0.7.0 build 28; the mobile handoff must check App Store Connect for a build-number collision, archive signing, processing, internal availability, and physical-device/push behavior before delivery. Public App Store submission remains outside this release.
Source validation: PR #111 passed all applicable CI lanes, with full iPhone and iPad iOS 27 suites each passing 92/92. Desktop smoke passed with 1,534 passed, 11 skipped and one test passing on its configured retry; that flake is not claimed fixed. Exhaustive iOS 26.5 coverage remains explicitly deferred. The release integration preserves the validated source; final release CI and package evidence are recorded separately.
These candidate notes do not certify pending tests, artifacts or deployment. The final release record must state the actual distribution outcomes, not convert pending work or earlier isolated passes into final acceptance.
Shared conversations, project task boards, and collaborative artifacts bring people and agents into the same workspace. This release also repairs packaged GitHub sign-in and Windows project paths.
Conversations and agents
Share agent sessions while keeping owner controls separate from conversation access.
Edit agent settings on the computer that owns the runtime, including before a chat starts.
Preserve one-on-one history, streamed answers, drafts, and return navigation.
Keep agent identities and team deletion state consistent across computers.
Refine composers, agent colors, sidebar labels, scrollbars, and message activity.
Keep branch titles readable at the minimum desktop window width.
Preserve focus in channel creation menus while the dialog opens.
Tasks and artifacts
Manage shared project boards with assignments, priorities, and agent pickup of authorized Ready tasks.
Work with Design and Galvani setup discussions as ordinary collaborative threads.
Publish interactive HTML and editable slide decks beside conversations, with editing leases and PDF/PowerPoint export.
Create source-based study guides, mind maps, quizzes, flashcards, and tables from HTML starters.
Discover shared artifacts through Files and search while preserving the current thread and draft.
Keep artifact previews and presentation inside the conversation pane; remove fullscreen artifact controls.
Galvani
Export retained reports, forum, literature, scores, evidence, and available researcher session archives.
Track multiple metrics and eligibility gates independently, with clearer charts and authoritative scoring evidence.
Share Analyzer review discussion and preserve the boundary between conversation access and privileged controls.
Improve setup navigation, naming, and run review workflows.
GitHub and packaging
Require both GitHub OAuth application values for Mac and Windows builds and verify them in packaged apps.
Preserve drive-letter and UNC project paths on Windows.
Rebuild and verify packaged agent tools, including boards, artifacts, and paper operations.
Support exact-version Windows release builds through GitHub Actions with updater signing kept on the release Mac.
Platform decisions
Dependency policy: Harrison authorized exceptions for the rustybuzz (RUSTSEC-2026-0206) and ttf-parser (RUSTSEC-2026-0192) unmaintained-library notices on 2026-09-12, limited to 0.6.1. Both come through the PDF exporter; replacement and removal of these exceptions before the next release are tracked in #109.
macOS: human installation, launch, GitHub sign-in/private-clone, and feature smoke explicitly waived by Harrison on 2026-09-12. Artifact and automated verification remain required.
Windows: installer and updater are included; human installation, launch, GitHub sign-in/private-clone, and feature smoke explicitly waived by Harrison on 2026-09-12. Artifact and automated verification remain required.
iOS: smoke and release intentionally skipped by Harrison on 2026-09-12. Mobile product source is unchanged since 0.6.0; the version/build metadata advances to 0.6.1+27 without a TestFlight upload.
Galvani gains a shared literature survey, reviewed research submissions, and a private Analyzer. One-on-one conversations are easier to reopen and continue.
Galvani
Four librarians prepare a cited survey before researcher time begins. Researchers can read and extend the literature throughout their work.
Structured mini-papers are reviewed before grading. Published findings show the exact reviewed submission and authoritative score.
The private Analyzer provides run analysis with configurable model, thinking level, and monitoring interval. Its conversation stays inside Galvani instead of appearing in Direct Messages.
Setup exposes run duration, per-agent submission limits, research iteration limits, and research model settings.
GPU jobs support independent researcher and GPU hosts, fresh Slurm allocations, and already held capacity. Verification checks the selected GPU environment and researcher tools.
Results, Forum, Literature, researcher boxes, submissions, and records share clearer navigation, timing, and contributor labels.
Score charts format axis labels automatically and preserve exact scores in details.
Conversations and controls
Reopen one-on-one conversations with their history intact. Closing the panel hides the conversation; Stop interrupts the current turn.
Continue chatting after Galvani setup handover, with shared composer controls and clearer Analyzer presentation.
Improve thread responsiveness, attachment controls, agent model settings, and deferred thinking-level changes.
Preserve link previews when metadata arrives during Send, and dismiss stale channel suggestions when an edit is cleared.
Keep Galvani setup progression correct when retrying a rejected answer.
Preserve spaces when inserting a mention before existing draft text.
Offer updates for agent adapters and retain supported model and thinking controls.
Release validation
Cleanup integration: full CI passed, including desktop, mobile, backend, relay, and both desktop integration shards. Browser smoke: 1,473 first-attempt passes, one passing retry, and one existing skip.
Candidate artifacts: both desktop installers were built from aaa70f29e402ed4b153b2e5f789380655f7c8e3c; the full local CI gate passed on that source.
Candidate hosted CI: all required jobs passed, including 1,474 browser smoke passes, one existing skip, and no failures or retries.
macOS: signed, notarized, and stapled 0.6.0 installer verified, including the mounted app and signed updater archive. Human candidate smoke accepted by Harrison on 2026-09-08: "It's good." This answers the handoff covering installation, launch, sign-in, and Analyzer chat checks.
Windows: 0.6.0 x64 installer verified, with a stored-only updater archive and cryptographically verified signature. Human candidate smoke accepted by Harrison in the same 2026-09-08 desktop handoff: "It's good."
iOS: intentionally skipped by Harrison because mobile app behavior is unchanged since 0.5.0; the mobile diff contains only a comment and the version/build bump to 0.6.0+26.
Channel composers show the agents currently working, while threads retain a dedicated participant attachment surface with per-agent activity visibility.
Thread attachments are explicit and durable: selected agents use leading attachment chips, survive navigation and sending, and remain independent of ordinary mentions.
Thinking and permission menus fit their full labels and remain editable when an agent is stopped; the agent activity default is configurable in Settings.
Projects and sidebar
Project rooms use normal channel typography, a compact fixed color palette, and consistent expanded, collapsed, hover, border and inset treatments.
Projects can be reordered directly in the sidebar, with the per-user order synchronized across devices and retained for hidden projects.
Sidebar sections share subtle reduced-motion-aware disclosure transitions, while scrolling no longer reserves a visible scrollbar gutter.
Galvani
Experiment packs can define their own grader program, executed in a closed grader box with held-out answers, reserved attempt budgets and durable ledger accounting.
Galvani can launch, verify and resume researcher boxes through Apptainer, including the warden and process lifecycle needed on Slurm compute nodes.
Platform outcomes
macOS: 0.5.2 signed, notarized and stapled build is included; human install/launch smoke intentionally skipped for this rushed release.
Windows: 0.5.2 x64 NSIS installer and signed updater archive are included; human install/launch smoke intentionally skipped for this rushed release.
iOS/TestFlight: intentionally skipped because this release has no mobile changes; the mobile version remains 0.5.0+25.
Hosted CI and local code/test checks were intentionally skipped by explicit release authorization. Packaging and publication still perform their required artifact-integrity and live-feed readback gates.
Agent pills replace the old attach bar with a compact, thread-aware surface for attaching, watching and steering agents.
Thinking effort and permission mode can be chosen at creation and are shown from the applied session configuration, while lightweight seen marks replace noisy reaction acknowledgements.
Message actions now offer two learned quick reactions, including custom emoji, while preserving the full reaction picker and existing reply/link actions.
Runtimes, projects and Galvani
Google Antigravity is available as a built-in agent runtime with its own discovery, readiness, model selection and branding.
Project rooms now share one consistent sidebar identity, color and branch treatment across project navigation.
Galvani labs can be archived without deleting provenance, and remote runs gain executable connection-route preflight before durable setup begins.
Reliability and operator safeguards
Agent session configuration, thread provenance and reconnect behavior retain the state needed to explain how a turn actually ran.
The Buzz CLI refuses empty message bodies and accidental literal \\n text, preventing accepted-but-blank collaboration messages.
Platform outcomes
macOS: 0.5.1 signed, notarized and stapled build is included; human install/launch smoke intentionally skipped for this rushed release.
Windows: intentionally skipped. The configured Windows build host is unavailable for this rushed release.
iOS/TestFlight: intentionally skipped because this release has no mobile changes; the mobile version remains 0.5.0+25.
Labs and setup-scoped runs now form one usable research surface, including local supervised launches and coordinate-only remote starts.
Run records expose the conditions needed to compare researchers: population, model and typed effort, box contract, siting, network posture, baselines, scored-submission allowance, spend, crashes, transcripts and workspaces.
Run-room filtering, bounded relay reads and strict canonical-record handling keep search results and run summaries truthful when records are incomplete.
Mobile is part of this release
Mobile Huddles add live voice conversations, participant controls and agent voice-turn state handling.
Profiles can be edited on-device, with camera, image and animated-avatar capture plus safer identity export behind device authentication.
Community invites, open-channel discovery, channel details, threads, composer behavior, message actions, emoji interactions and navigation have been substantially expanded and repaired.
Relay recovery now handles stale or shuffled messages without presenting an incomplete timeline as current.
Conversations, agents and storage
Agent addressing persists across composer sends, while mention handling, search highlighting, message editing, thread loading and image navigation are more reliable.
GIF search, improved message actions and corrected lightbox zoom round out the desktop conversation surface.
Storage reporting now accounts for channel-file bytes and other major partitions with durable rollups instead of hiding them under “other.”
Platform outcomes
macOS: 0.5.0 signed, notarized and stapled build passed human smoke.
Windows: 0.5.0 installer and signed updater archive are included; human install/launch smoke intentionally skipped for this rushed release.
iOS/TestFlight: included as 0.5.0+25; the human archive and upload to TestFlight completed from this release candidate before publication.
Windows is now an explicit desktop release platform in the canonical runbook, candidate and publisher skills, and release checklist.
Publication fails before tagging when the Windows installer/updater archive is missing, unless the canonical notes record an intentional Windows skip.
The live updater feed is read back after publication to verify the Windows entry and archive URL.
Platform outcomes
macOS: signed, notarized, and stapled artifact required; repeat human smoke waived because product behavior is unchanged from the smoke-tested 0.4.8 build.
Windows: installer and signed updater archive built from the 0.4.9 candidate; human install/launch and release-flow smoke passed on nyx.
iOS: 0.4.9+24 intentionally skipped for TestFlight; product behavior is unchanged from 0.4.8.
Channel files replace notebook sources as the shared material agents and people work from.
Type $ in the composer to find and reference a channel file; sent references open as the file itself.
Agents can list and read channel files, and their generated artifacts can be opened or kept directly from any channel.
File indexing now covers both new sends and earlier channel history, with removal support when a file or message is deleted.
Agents are easier to steer and configure
Managed agents now keep one continuous conversation while preserving the channel, thread, and project-room context of each turn.
Late steering keeps its provenance, and single-worker controls prevent duplicate concurrent work.
Model and thinking-level controls now share one consistent editor for personal agents and team members, including values that are not present in the current catalog.
Faster, clearer conversations and projects
Long threads page replies progressively and window the visible list, reducing work as conversations grow.
Project navigation now treats papers as the project workspace entry, with cleaner per-project hover and visibility behavior.
File references, artifact cards, and non-image attachments render more clearly and avoid duplicate previews.
Mobile
mobile/pubspec.yaml is at 0.4.8+23. TestFlight publication was explicitly skipped for this release after the macOS DMG passed human smoke testing.
Release checks
Mobile hooks use and report the repository-pinned Flutter toolchain instead of inheriting a global SDK.
Remote-compute adapter tests no longer depend on the launching session's configured hosts.
The tracing-state assertion runs in an isolated process, and release pull requests compare changed paths against their real base so substantive CI jobs cannot silently skip.
The Tectonic fetcher rejects empty or non-executable cache entries instead of shipping an incomplete paper-compilation sidecar.
An installed Windows copy could not apply an update: it failed with unsupported Zip archive: Compression method not supported. The updater archive was built with deflate, and the reader inside the app has no deflate backend compiled in. The archive is now stored uncompressed, which every build of that reader can open — so copies already installed can update to this release, without a manual reinstall.
Sidebar and projects
Projects can be turned on and off in the sidebar without going silent.
A project group now shows the name its owner set, instead of the GitHub name.
A project header gets a ⋯ menu as well as its right-click menu.
Projects have their own sort key, and every section gets one header.
Agents and channels
The inline activity bar says who is working rather than reciting what they are doing.
Every agent's attach "eye" starts closed.
An agent's answer goes back to the thread its question was asked in.
Other fixes
A huddle that auto-ends says so, instead of going quietly unremovable.
The desktop dev server serves a browser the mock backend rather than a loading screen forever.
Mobile
iOS/TestFlight was not shipped for this release — deliberately skipped. mobile/pubspec.yaml is at 0.4.7+22; no archive was uploaded.
Teams have roles now, and agents can call each other in.
Roles
A team is no longer a flat list of agents. It has roles — Manager, Implementer, Reviewer — and each role carries its own instructions, its own seat count, and its own look. Fill a seat by making somebody new or by moving somebody you already have; either way they arrive wearing the role.
A member's prompt is now a stack rather than one field: the base prompt, then whatever is theirs alone, then the team's instructions, then the role's. Their own prompt says who they are; the role says what the job is, so the same agent can be an Implementer on one team and something else on another without being rewritten.
Start a team from a template — Circuit, Lattice, or Grid — and the roles, seats, and entry points come with it.
The delegating roles now carry explicit scope discipline: a Manager is told to hold the boundary it was given and to hand back a smaller thing rather than a bigger one. Scope growth is the standard failure of delegated work, and it now has a named owner in the prompt.
An agent knows its own team
Every agent on a team is now given its roster at startup — who its teammates are, what role each holds, which one is itself, and each one's full key. It could not previously find this out: the relay knows team members by an internal id, not by anything an agent can address. So an agent that wanted a colleague had to guess a name and hope. Now it can simply mention them.
Agents can wake each other
Mentioning an agent has always started it. That only worked when you did the mentioning — an agent that mentioned another agent was talking to a room where nobody was listening, and the message sat there.
Now any agent you own, or that has been shared with you, comes up when it is mentioned by anyone in that same circle. Ask a manager for something and it can bring in its own team; the four of them wake, work, and answer.
Harnesses
The Default harness in Settings now actually reaches the agents that get made for you — team-minted agents silently ran the fallback harness before, whatever Settings said. Beyond the default, a role can specify which harness its seats are minted with, and any individual seat can differ, so one team can run Claude Code and Codex side by side.
Smaller things
A deleted or archived agent now leaves the channels it was in, instead of lingering in the member list forever. Agents retired before this release are swept out on first launch. Their messages stay.
The base prompt's buzz reactions example named flags the command does not take, so an agent following it hit a usage error.
Volta now builds, installs, and updates itself on Windows. The installer is on this release; once installed, the app checks the same update feed macOS uses and installs new versions from inside the app.
Windows builds are unsigned for now, so Windows shows a SmartScreen prompt on first download, and a "Unknown publisher" prompt each time an update installs. Both are expected and neither indicates a problem — a code signing certificate is a separate piece of work.
macOS is unchanged: same signed, notarized, stapled DMG, same auto-update.
Under the hood
Volta's CI now runs on hardware we own rather than billed cloud runners. The last recurring cloud job moved to a dedicated always-on machine, along with the lint, web, security and cross-compile lanes. Nothing about the app changed as a result; builds are simply no longer billed and no longer wait on a laptop being awake.
One real bug surfaced while proving the Windows build: the LaTeX toolchain Volta bundles for paper compilation was extracted with a tool that misreads Windows paths as network addresses. Fixed — it affected any Windows build, not just ours.
A notebook is a shared research workspace: you add sources — PDFs, documents, web pages — and their text is extracted once and shared with everyone in the notebook. Ask a question in the notebook's room and an agent answers from those sources, citing the passage it used rather than recalling something plausible.
Add a source from a file, a link, or a message someone already posted. Extraction happens once, on the relay, so everyone reads the same text.
Ask, and get citations. Answers point back at the exact passage. Clicking a citation opens the source at that spot.
Studio turns the sources into a study guide, a mind map, a data table, a quiz, or flashcards. Output is added back as a source, so it can be read and cited like anything else.
A notebook belongs to a project and inherits its access — everyone in the project, and nobody else. There is no separate member list to grant or forget to revoke.
buzz notebook covers the same ground from the CLI: list, sources, search, read, add-source.
The sidebar says what each room is
A project's rooms used to arrive as one flat list, where nothing told a paper's room apart from a branch except recognising the name — and a notebook's room was not shown at all.
Each project now groups its rooms by what they are: Repo, Papers, Notebooks. Each block is labelled, collapses on its own, and is hidden entirely when it has nothing in it. The separate top-level Notebooks section is gone; a notebook hangs off its project exactly as a paper does, so it lives there. The tree is also a level shallower than before.
Panes you can actually resize
The notebook's sources rail and Studio pane both drag, and each remembers its width for the session.
The conversation can no longer be squeezed out of existence by dragging both rails inward — it keeps a minimum, and the rails give up width first.
The same protection turned out to be missing in the paper editor, where the editor could be reduced to half its documented minimum width. Fixed.
Every right-hand pane now remembers its own width. Previously the paper editor, the channel thread panel, Agents, Pulse and Home shared one, so resizing any of them resized all of them.
Agents know which room they woke up in
An agent in a repository's room now sees the repository and branch that room is, and a paper's room names its paper. Before, a project room and #general looked identical apart from the name, so an agent had no way to know a checkout was already in front of it — and would clone the repository again or ask which one was meant. It now works in the checkout the room already has.
Fixes
A newly created notebook now appears immediately — and so does a newly created paper. Previously the room was created but the app never heard about it, which also meant the person who had just created a notebook was offered no way to rename or delete it.
Notebook source search works. It was returning nothing for every query on any relay that had ever stored an event, and the empty result was indistinguishable from "the sources do not say that". Relays now report which content they index, so an empty result means what it says.
Deleting a notebook removes it from every surface, including its rooms.
Platforms
macOS only. iOS/TestFlight was deliberately skipped for 0.4.4: the sole change under mobile/ since v0.4.3 is a comment in nostr_models.dart explaining why Volta's own 500xx event kinds are absent there, so a TestFlight build would carry no functional difference. Notebooks, the sidebar grouping and the pane work are all desktop surfaces; mobile has no screen for any of them yet. mobile/pubspec.yaml still carries the version bump, so the next mobile release picks up from 0.4.4.
For operators
This release needs a relay carrying migrations through 9016. Full-text search over notebook sources additionally requires scripts/maintenance/nip_rs_search_allowlist.sql to have been run against the relay's database — new installs get it automatically; existing ones do not.
The patch promised in v0.4.2's known issue. Desktop only — iOS skipped again.
The audience control on the Agents screen now changes the agent
In v0.4.2 you could open an agent, set Who can send instructions to Selected people, pick someone, save, reopen it, and see Selected people — while the person you picked still saw nothing. Restarting the agent did not help.
Nothing was lying to you. The dialog read back exactly what it wrote; it just wrote to the wrong record. Volta stores an agent's audience in two places:
the persona — the template you create agents from, and
the agent — the running thing that actually answers.
The Agents settings screen edits the persona. The persona's audience was only ever read once, at the moment an agent is created from it. Change it afterwards and the running agent kept the audience it was born with, so no access was granted and no activity became visible.
Saving now writes the audience through to every agent made from that persona, republishes it, and issues the access that follows from it. One save, one result.
This also repairs agents that were already out of step: the first save of any persona that states an audience re-asserts it onto its agents, so an agent stranded on an old audience by v0.4.2 or earlier is corrected without you having to recreate it.
Correction to v0.4.2's release notes
The known issue was described as Selected people not surviving a round trip through the editor — the dialog appearing to forget your list. That is not what was happening. The dialog remembered correctly; the value simply never reached the agent. Only me and Anyone were affected in the same way and for the same reason, not unaffected as stated. Anyone who set an audience on an existing agent under v0.4.2 should open it and save once after updating.
Not included
iOS/TestFlight was skipped for this release. Mobile is unchanged.
Hotfix release so a shared agent's work is actually visible to the people it is shared with. Desktop only — iOS was deliberately skipped.
Talking to an agent and watching it are now one permission
Before this, an agent had two independent access controls that nothing kept in step: Who can send instructions decided who could drive it, and a separate mechanism decided who could see what it did. You could hand someone an agent and have them able to drive it while staring at an empty activity panel — which is exactly what happened, and it was not recoverable from the sharing UI in v0.4.1.
There is one control now, and it answers both questions:
Setting
Who may drive
Who may watch
Only me
you and your agents
the same
Selected people
the people you pick
the same
Anyone
anyone in a shared channel
the same
Under Selected people, saving the agent publishes the activity grants for the people you chose. Under Anyone, the agent grants each person the first time they actually instruct it — not merely for being in the room.
Narrowing the setting is the revocation: there are no revoke events to send and no list for your laptop to enumerate. The relay stops resolving what the agent issued the moment the policy that allowed it no longer holds.
The bug that made every earlier fix invisible
An agent shared with you was hidden by default, and acquiring the grant is what hid it — so each previous fix landed correctly behind a client that had already decided not to show the agent. Shared agents are now watched by default and appear in the attach bar with their activity visible.
Also in this release
The status line under the composer no longer announces your own prompt back to you, and no longer describes the previous turn's work while a new turn is still thinking.
Activity frames arriving while a grant is being re-read are no longer dropped, and a thread loaded before the grant arrives is refetched once it lands.
The access copy now says plainly that a grantee sees the agent's work in the channels they share with it — including turns you and other people drove, and work done before they arrived — and that narrowing access later cannot erase what someone already received.
Known issue
Selected people does not survive a round trip through the agent editor. Opening an agent whose audience is Selected people shows "Only me (default)", and saving from that dialog writes the narrowed value back and drops your list. The stored policy itself is correct — grants derive from it properly — but avoid re-saving such an agent until the fix ships. Anyone and Only me are unaffected. A 0.4.3 patch follows shortly.
Volta now knows what the agent tools it runs actually are — what each harness is called, which adapter version it needs, which permission modes it offers, and what its tool calls mean. Alongside that: agents you address in a thread are addressed the way you wrote it, and setting up a project tells you what it is doing to which folder.
Agent harnesses
No more empty "Thinking". Claude Code turns opened a Thinking heading over nothing. The adapter sends thought frames with no text — Volta was faithfully rendering nothing at all. Nothing is drawn where there is nothing, and the reasoning still keeps its place in the transcript when it does arrive.
Outdated adapters say so. A harness declares the adapter versions it runs on, and an adapter below that floor offers a reinstall instead of silently behaving worse. The floor names the npm package it measures, so Zed's claude-code-acp is not judged by claude-agent-acp's version line.
Permission mode is a control. The mode an agent runs under was fixed when it launched. It is now the adapter's own list, offered live per session — and only where the adapter declared one, so a runtime that offers none is never handed a control that would crash it.
Tool calls read as what they are. Every ACP tool kind an adapter declares — read, edit, delete, move, search, execute, think, fetch, switch mode — now has a reading. They used to collapse into "Ran tool".
The setup card calls a harness what it calls itself.
Agents in a thread
Every agent gets a colour, so a thread with several of them reads as several voices rather than one column. An emoji avatar already carries the colour its owner chose; a picture avatar takes an outline instead.
The bar says who is here. A pill shows when its agent is mid-turn in another conversation, so a message that will wait behind that turn says so before you send it.
Deleting an agent retires it without unnaming its work. Its past messages keep the name and colour they were written under; the agent leaves pickers, autocomplete and the composer bar, and its work stays switch-off-able behind an Archived disclosure.
Addressing works the way you wrote it. An @-mention re-aims the command that follows it, one message can carry several, and a bare /command in a DM offers the popup it always ran.
Projects
Setting a project up offers only answers that can succeed, reports the folder it is actually looking at, and refuses a move before offering it rather than after.
A source directory is no longer mistaken for a project's container, and the folder you picked is the folder that gets moved.
Fixes
h2 0.4.16 clears the advisory that blocked any Cargo.lock change.
A git worktree's E2E suite gets its own preview port, so two checkouts no longer serve each other's tests.
---
Platforms: macOS desktop only. iOS/TestFlight was deliberately skipped this cycle — no mobile changes since v0.4.0.
Until now, watching an agent work meant leaving the conversation to do it: the activity panel displaced the thread, showed only agents running right now, and lost everything the moment you reloaded. You could read the work or read the room, never both.
From this release an agent's work is read in the thread that asked for it, attaching to an agent is a real per-thread choice, and what an agent did is a durable record rather than a live feed you had to be present for.
Attach mode
Work lands under the message that caused it. Placement is causal — every row hangs off the message that triggered its turn, never off a clock — so a turn reads as one unit even though thread replies render in tree order.
Attach is a (thread, agent) pair, in DMs and threads. A regular channel's top-level composer is untouched.
Activity survives a reload. Agent activity is a thread-anchored durable record, not an ephemeral frame you had to be watching to see.
Share an agent, and see what it did — a grant now reaches the person you shared with live, not only on their next reload.
Turns say where they came from and where they went. Sessions are per channel, so consecutive turns routinely share one model context across different threads. A turn marks the context it imported and the messages it posted elsewhere, instead of presenting each thread as hermetic.
A mid-turn send queues by default, with a composer control to escalate a single send to a steer.
Effort in passing — change an agent's effort from its bubble, see the model it is running as, and how much of its context window is left.
What a thread shows
A thread and the agent panel are different surfaces, and this release stops treating them as one. The panel is a monitor and shows everything; a thread is a record and shows the work.
An edit shows the change. Claude Code's adapter reports edits as structured diffs, a shape the renderer did not know — so an edit arrived as a title with nothing under it. Edits render as diffs now, in the panel too.
No raw JSON parameters in a thread. The row's title already names the file or the command.
The answer appears once, rather than as a published reply plus an unattributed copy directly above it.
Scrollback, not the status line. Mode, token usage, the advertised command list and the system prompt are terminal chrome, and no longer render as thread rows — nor leave an empty "No ACP activity yet" card where a turn had nothing to show.
Slash commands
**The / menu works before you have said anything.** Adapters only advertise their commands once a session exists, and sessions were created lazily on the first message — so the menu was empty exactly when you reached for it. The harness now collects the repertoire at startup, and Volta remembers it across runs.
Commands render as chips, the way @ mentions do.
An agent that has not reported yet says "Starting up agent…" instead of showing you an empty list.
The popup offers the whole repertoire rather than the first eight.
Liquid Glass composer (macOS)
Real WebKit system materials behind the composer, with a legible edge.
Glass opacity rides the appearance slider; non-mac keeps the plain blur.
The glass survives dock resizes, remounts and page-visibility changes, and the bottom-left corner mask paints over it correctly again.
Also in this release
just volta comes up as your real Volta account, agents and all.
A launch-restored agent tells the UI it is running.
A dev build hands a key to agents that arrive after migration.
An agent's log can say what its harness advertised.
For the record
macOS: signed, notarized and stapled DMG — both the app and the DMG carry their own notarization tickets.
iOS: skipped for this release. No mobile changes landed since v0.3.11, so nothing was archived or uploaded to TestFlight. mobile/pubspec.yaml still advanced to 0.4.0+15 so the next upload gets an increasing build number.
